feedgenerator-1.9/0000755000076500000240000000000012765362060013735 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/0000755000076500000240000000000012765362056014632 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/0000755000076500000240000000000012765362056015432 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/bin/0000755000076500000240000000000012765362056016202 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/bin/activate_this.py0000644000076500000240000000216112700725535021375 0ustar jmstaff00000000000000"""By using execfile(this_file, dict(__file__=this_file)) you will activate this virtualenv environment. This can be used when you must use an existing Python interpreter, not the virtualenv bin/python """ try: __file__ except NameError: raise AssertionError( "You must run this like execfile('path/to/activate_this.py', dict(__file__='path/to/activate_this.py'))") import sys import os old_os_path = os.environ.get('PATH', '') os.environ['PATH'] = os.path.dirname(os.path.abspath(__file__)) + os.pathsep + old_os_path base = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) if sys.platform == 'win32': site_packages = os.path.join(base, 'Lib', 'site-packages') else: site_packages = os.path.join(base, 'lib', 'python%s' % sys.version[:3], 'site-packages') prev_sys_path = list(sys.path) import site site.addsitedir(site_packages) sys.real_prefix = sys.prefix sys.prefix = base # Move the added items to the front of the path: new_sys_path = [] for item in list(sys.path): if item not in prev_sys_path: new_sys_path.append(item) sys.path.remove(item) sys.path[:0] = new_sys_path feedgenerator-1.9/.tox/py26/lib/0000755000076500000240000000000012765362056016200 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/0000755000076500000240000000000012765362056017747 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/_abcoll.py0000644000076500000240000003313112612565535021713 0ustar jmstaff00000000000000# Copyright 2007 Google, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Abstract Base Classes (ABCs) for collections, according to PEP 3119. DON'T USE THIS MODULE DIRECTLY! The classes here should be imported via collections; they are defined here only to alleviate certain bootstrapping issues. Unit tests are in test_collections. """ from abc import ABCMeta, abstractmethod import sys __all__ = ["Hashable", "Iterable", "Iterator", "Sized", "Container", "Callable", "Set", "MutableSet", "Mapping", "MutableMapping", "MappingView", "KeysView", "ItemsView", "ValuesView", "Sequence", "MutableSequence", ] ### ONE-TRICK PONIES ### def _hasattr(C, attr): try: return any(attr in B.__dict__ for B in C.__mro__) except AttributeError: # Old-style class return hasattr(C, attr) class Hashable: __metaclass__ = ABCMeta @abstractmethod def __hash__(self): return 0 @classmethod def __subclasshook__(cls, C): if cls is Hashable: try: for B in C.__mro__: if "__hash__" in B.__dict__: if B.__dict__["__hash__"]: return True break except AttributeError: # Old-style class if getattr(C, "__hash__", None): return True return NotImplemented class Iterable: __metaclass__ = ABCMeta @abstractmethod def __iter__(self): while False: yield None @classmethod def __subclasshook__(cls, C): if cls is Iterable: if _hasattr(C, "__iter__"): return True return NotImplemented Iterable.register(str) class Iterator(Iterable): @abstractmethod def next(self): raise StopIteration def __iter__(self): return self @classmethod def __subclasshook__(cls, C): if cls is Iterator: if _hasattr(C, "next"): return True return NotImplemented class Sized: __metaclass__ = ABCMeta @abstractmethod def __len__(self): return 0 @classmethod def __subclasshook__(cls, C): if cls is Sized: if _hasattr(C, "__len__"): return True return NotImplemented class Container: __metaclass__ = ABCMeta @abstractmethod def __contains__(self, x): return False @classmethod def __subclasshook__(cls, C): if cls is Container: if _hasattr(C, "__contains__"): return True return NotImplemented class Callable: __metaclass__ = ABCMeta @abstractmethod def __call__(self, *args, **kwds): return False @classmethod def __subclasshook__(cls, C): if cls is Callable: if _hasattr(C, "__call__"): return True return NotImplemented ### SETS ### class Set(Sized, Iterable, Container): """A set is a finite, iterable container. This class provides concrete generic implementations of all methods except for __contains__, __iter__ and __len__. To override the comparisons (presumably for speed, as the semantics are fixed), all you have to do is redefine __le__ and then the other operations will automatically follow suit. """ def __le__(self, other): if not isinstance(other, Set): return NotImplemented if len(self) > len(other): return False for elem in self: if elem not in other: return False return True def __lt__(self, other): if not isinstance(other, Set): return NotImplemented return len(self) < len(other) and self.__le__(other) def __gt__(self, other): if not isinstance(other, Set): return NotImplemented return other < self def __ge__(self, other): if not isinstance(other, Set): return NotImplemented return other <= self def __eq__(self, other): if not isinstance(other, Set): return NotImplemented return len(self) == len(other) and self.__le__(other) def __ne__(self, other): return not (self == other) @classmethod def _from_iterable(cls, it): '''Construct an instance of the class from any iterable input. Must override this method if the class constructor signature does not accept an iterable for an input. ''' return cls(it) def __and__(self, other): if not isinstance(other, Iterable): return NotImplemented return self._from_iterable(value for value in other if value in self) def isdisjoint(self, other): for value in other: if value in self: return False return True def __or__(self, other): if not isinstance(other, Iterable): return NotImplemented chain = (e for s in (self, other) for e in s) return self._from_iterable(chain) def __sub__(self, other): if not isinstance(other, Set): if not isinstance(other, Iterable): return NotImplemented other = self._from_iterable(other) return self._from_iterable(value for value in self if value not in other) def __xor__(self, other): if not isinstance(other, Set): if not isinstance(other, Iterable): return NotImplemented other = self._from_iterable(other) return (self - other) | (other - self) # Sets are not hashable by default, but subclasses can change this __hash__ = None def _hash(self): """Compute the hash value of a set. Note that we don't define __hash__: not all sets are hashable. But if you define a hashable set type, its __hash__ should call this function. This must be compatible __eq__. All sets ought to compare equal if they contain the same elements, regardless of how they are implemented, and regardless of the order of the elements; so there's not much freedom for __eq__ or __hash__. We match the algorithm used by the built-in frozenset type. """ MAX = sys.maxint MASK = 2 * MAX + 1 n = len(self) h = 1927868237 * (n + 1) h &= MASK for x in self: hx = hash(x) h ^= (hx ^ (hx << 16) ^ 89869747) * 3644798167 h &= MASK h = h * 69069 + 907133923 h &= MASK if h > MAX: h -= MASK + 1 if h == -1: h = 590923713 return h Set.register(frozenset) class MutableSet(Set): @abstractmethod def add(self, value): """Add an element.""" raise NotImplementedError @abstractmethod def discard(self, value): """Remove an element. Do not raise an exception if absent.""" raise NotImplementedError def remove(self, value): """Remove an element. If not a member, raise a KeyError.""" if value not in self: raise KeyError(value) self.discard(value) def pop(self): """Return the popped value. Raise KeyError if empty.""" it = iter(self) try: value = next(it) except StopIteration: raise KeyError self.discard(value) return value def clear(self): """This is slow (creates N new iterators!) but effective.""" try: while True: self.pop() except KeyError: pass def __ior__(self, it): for value in it: self.add(value) return self def __iand__(self, it): for value in (self - it): self.discard(value) return self def __ixor__(self, it): if not isinstance(it, Set): it = self._from_iterable(it) for value in it: if value in self: self.discard(value) else: self.add(value) return self def __isub__(self, it): for value in it: self.discard(value) return self MutableSet.register(set) ### MAPPINGS ### class Mapping(Sized, Iterable, Container): @abstractmethod def __getitem__(self, key): raise KeyError def get(self, key, default=None): try: return self[key] except KeyError: return default def __contains__(self, key): try: self[key] except KeyError: return False else: return True def iterkeys(self): return iter(self) def itervalues(self): for key in self: yield self[key] def iteritems(self): for key in self: yield (key, self[key]) def keys(self): return list(self) def items(self): return [(key, self[key]) for key in self] def values(self): return [self[key] for key in self] # Mappings are not hashable by default, but subclasses can change this __hash__ = None def __eq__(self, other): if not isinstance(other, Mapping): return NotImplemented return dict(self.items()) == dict(other.items()) def __ne__(self, other): return not (self == other) class MappingView(Sized): def __init__(self, mapping): self._mapping = mapping def __len__(self): return len(self._mapping) class KeysView(MappingView, Set): def __contains__(self, key): return key in self._mapping def __iter__(self): for key in self._mapping: yield key class ItemsView(MappingView, Set): def __contains__(self, item): key, value = item try: v = self._mapping[key] except KeyError: return False else: return v == value def __iter__(self): for key in self._mapping: yield (key, self._mapping[key]) class ValuesView(MappingView): def __contains__(self, value): for key in self._mapping: if value == self._mapping[key]: return True return False def __iter__(self): for key in self._mapping: yield self._mapping[key] class MutableMapping(Mapping): @abstractmethod def __setitem__(self, key, value): raise KeyError @abstractmethod def __delitem__(self, key): raise KeyError __marker = object() def pop(self, key, default=__marker): try: value = self[key] except KeyError: if default is self.__marker: raise return default else: del self[key] return value def popitem(self): try: key = next(iter(self)) except StopIteration: raise KeyError value = self[key] del self[key] return key, value def clear(self): try: while True: self.popitem() except KeyError: pass def update(self, other=(), **kwds): if isinstance(other, Mapping): for key in other: self[key] = other[key] elif hasattr(other, "keys"): for key in other.keys(): self[key] = other[key] else: for key, value in other: self[key] = value for key, value in kwds.items(): self[key] = value def setdefault(self, key, default=None): try: return self[key] except KeyError: self[key] = default return default MutableMapping.register(dict) ### SEQUENCES ### class Sequence(Sized, Iterable, Container): """All the operations on a read-only sequence. Concrete subclasses must override __new__ or __init__, __getitem__, and __len__. """ @abstractmethod def __getitem__(self, index): raise IndexError def __iter__(self): i = 0 try: while True: v = self[i] yield v i += 1 except IndexError: return def __contains__(self, value): for v in self: if v == value: return True return False def __reversed__(self): for i in reversed(range(len(self))): yield self[i] def index(self, value): for i, v in enumerate(self): if v == value: return i raise ValueError def count(self, value): return sum(1 for v in self if v == value) Sequence.register(tuple) Sequence.register(basestring) Sequence.register(buffer) Sequence.register(xrange) class MutableSequence(Sequence): @abstractmethod def __setitem__(self, index, value): raise IndexError @abstractmethod def __delitem__(self, index): raise IndexError @abstractmethod def insert(self, index, value): raise IndexError def append(self, value): self.insert(len(self), value) def reverse(self): n = len(self) for i in range(n//2): self[i], self[n-i-1] = self[n-i-1], self[i] def extend(self, values): for v in values: self.append(v) def pop(self, index=-1): v = self[index] del self[index] return v def remove(self, value): del self[self.index(value)] def __iadd__(self, values): self.extend(values) return self MutableSequence.register(list) feedgenerator-1.9/.tox/py26/lib/python2.6/abc.py0000644000076500000240000001557212612565535021056 0ustar jmstaff00000000000000# Copyright 2007 Google, Inc. All Rights Reserved. # Licensed to PSF under a Contributor Agreement. """Abstract Base Classes (ABCs) according to PEP 3119.""" # Instance of old-style class class _C: pass _InstanceType = type(_C()) def abstractmethod(funcobj): """A decorator indicating abstract methods. Requires that the metaclass is ABCMeta or derived from it. A class that has a metaclass derived from ABCMeta cannot be instantiated unless all of its abstract methods are overridden. The abstract methods can be called using any of the normal 'super' call mechanisms. Usage: class C: __metaclass__ = ABCMeta @abstractmethod def my_abstract_method(self, ...): ... """ funcobj.__isabstractmethod__ = True return funcobj class abstractproperty(property): """A decorator indicating abstract properties. Requires that the metaclass is ABCMeta or derived from it. A class that has a metaclass derived from ABCMeta cannot be instantiated unless all of its abstract properties are overridden. The abstract properties can be called using any of the normal 'super' call mechanisms. Usage: class C: __metaclass__ = ABCMeta @abstractproperty def my_abstract_property(self): ... This defines a read-only property; you can also define a read-write abstract property using the 'long' form of property declaration: class C: __metaclass__ = ABCMeta def getx(self): ... def setx(self, value): ... x = abstractproperty(getx, setx) """ __isabstractmethod__ = True class ABCMeta(type): """Metaclass for defining Abstract Base Classes (ABCs). Use this metaclass to create an ABC. An ABC can be subclassed directly, and then acts as a mix-in class. You can also register unrelated concrete classes (even built-in classes) and unrelated ABCs as 'virtual subclasses' -- these and their descendants will be considered subclasses of the registering ABC by the built-in issubclass() function, but the registering ABC won't show up in their MRO (Method Resolution Order) nor will method implementations defined by the registering ABC be callable (not even via super()). """ # A global counter that is incremented each time a class is # registered as a virtual subclass of anything. It forces the # negative cache to be cleared before its next use. _abc_invalidation_counter = 0 def __new__(mcls, name, bases, namespace): cls = super(ABCMeta, mcls).__new__(mcls, name, bases, namespace) # Compute set of abstract method names abstracts = set(name for name, value in namespace.items() if getattr(value, "__isabstractmethod__", False)) for base in bases: for name in getattr(base, "__abstractmethods__", set()): value = getattr(cls, name, None) if getattr(value, "__isabstractmethod__", False): abstracts.add(name) cls.__abstractmethods__ = frozenset(abstracts) # Set up inheritance registry cls._abc_registry = set() cls._abc_cache = set() cls._abc_negative_cache = set() cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter return cls def register(cls, subclass): """Register a virtual subclass of an ABC.""" if not isinstance(cls, type): raise TypeError("Can only register classes") if issubclass(subclass, cls): return # Already a subclass # Subtle: test for cycles *after* testing for "already a subclass"; # this means we allow X.register(X) and interpret it as a no-op. if issubclass(cls, subclass): # This would create a cycle, which is bad for the algorithm below raise RuntimeError("Refusing to create an inheritance cycle") cls._abc_registry.add(subclass) ABCMeta._abc_invalidation_counter += 1 # Invalidate negative cache def _dump_registry(cls, file=None): """Debug helper to print the ABC registry.""" print >> file, "Class: %s.%s" % (cls.__module__, cls.__name__) print >> file, "Inv.counter: %s" % ABCMeta._abc_invalidation_counter for name in sorted(cls.__dict__.keys()): if name.startswith("_abc_"): value = getattr(cls, name) print >> file, "%s: %r" % (name, value) def __instancecheck__(cls, instance): """Override for isinstance(instance, cls).""" # Inline the cache checking when it's simple. subclass = getattr(instance, '__class__', None) if subclass in cls._abc_cache: return True subtype = type(instance) # Old-style instances if subtype is _InstanceType: subtype = subclass if subtype is subclass or subclass is None: if (cls._abc_negative_cache_version == ABCMeta._abc_invalidation_counter and subtype in cls._abc_negative_cache): return False # Fall back to the subclass check. return cls.__subclasscheck__(subtype) return (cls.__subclasscheck__(subclass) or cls.__subclasscheck__(subtype)) def __subclasscheck__(cls, subclass): """Override for issubclass(subclass, cls).""" # Check cache if subclass in cls._abc_cache: return True # Check negative cache; may have to invalidate if cls._abc_negative_cache_version < ABCMeta._abc_invalidation_counter: # Invalidate the negative cache cls._abc_negative_cache = set() cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter elif subclass in cls._abc_negative_cache: return False # Check the subclass hook ok = cls.__subclasshook__(subclass) if ok is not NotImplemented: assert isinstance(ok, bool) if ok: cls._abc_cache.add(subclass) else: cls._abc_negative_cache.add(subclass) return ok # Check if it's a direct subclass if cls in getattr(subclass, '__mro__', ()): cls._abc_cache.add(subclass) return True # Check if it's a subclass of a registered class (recursive) for rcls in cls._abc_registry: if issubclass(subclass, rcls): cls._abc_cache.add(subclass) return True # Check if it's a subclass of a subclass (recursive) for scls in cls.__subclasses__(): if issubclass(subclass, scls): cls._abc_cache.add(subclass) return True # No dice; update negative cache cls._abc_negative_cache.add(subclass) return False feedgenerator-1.9/.tox/py26/lib/python2.6/codecs.py0000644000076500000240000010470212612565535021563 0ustar jmstaff00000000000000""" codecs -- Python Codec Registry, API and helpers. Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """#" import __builtin__, sys ### Registry and builtin stateless codec functions try: from _codecs import * except ImportError, why: raise SystemError('Failed to load the builtin codecs: %s' % why) __all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE", "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE", "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_LE", "BOM_UTF16_BE", "BOM_UTF32", "BOM_UTF32_LE", "BOM_UTF32_BE", "strict_errors", "ignore_errors", "replace_errors", "xmlcharrefreplace_errors", "register_error", "lookup_error"] ### Constants # # Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF) # and its possible byte string values # for UTF8/UTF16/UTF32 output and little/big endian machines # # UTF-8 BOM_UTF8 = '\xef\xbb\xbf' # UTF-16, little endian BOM_LE = BOM_UTF16_LE = '\xff\xfe' # UTF-16, big endian BOM_BE = BOM_UTF16_BE = '\xfe\xff' # UTF-32, little endian BOM_UTF32_LE = '\xff\xfe\x00\x00' # UTF-32, big endian BOM_UTF32_BE = '\x00\x00\xfe\xff' if sys.byteorder == 'little': # UTF-16, native endianness BOM = BOM_UTF16 = BOM_UTF16_LE # UTF-32, native endianness BOM_UTF32 = BOM_UTF32_LE else: # UTF-16, native endianness BOM = BOM_UTF16 = BOM_UTF16_BE # UTF-32, native endianness BOM_UTF32 = BOM_UTF32_BE # Old broken names (don't use in new code) BOM32_LE = BOM_UTF16_LE BOM32_BE = BOM_UTF16_BE BOM64_LE = BOM_UTF32_LE BOM64_BE = BOM_UTF32_BE ### Codec base classes (defining the API) class CodecInfo(tuple): def __new__(cls, encode, decode, streamreader=None, streamwriter=None, incrementalencoder=None, incrementaldecoder=None, name=None): self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter)) self.name = name self.encode = encode self.decode = decode self.incrementalencoder = incrementalencoder self.incrementaldecoder = incrementaldecoder self.streamwriter = streamwriter self.streamreader = streamreader return self def __repr__(self): return "<%s.%s object for encoding %s at 0x%x>" % (self.__class__.__module__, self.__class__.__name__, self.name, id(self)) class Codec: """ Defines the interface for stateless encoders/decoders. The .encode()/.decode() methods may use different error handling schemes by providing the errors argument. These string values are predefined: 'strict' - raise a ValueError error (or a subclass) 'ignore' - ignore the character and continue with the next 'replace' - replace with a suitable replacement character; Python will use the official U+FFFD REPLACEMENT CHARACTER for the builtin Unicode codecs on decoding and '?' on encoding. 'xmlcharrefreplace' - Replace with the appropriate XML character reference (only for encoding). 'backslashreplace' - Replace with backslashed escape sequences (only for encoding). The set of allowed values can be extended via register_error. """ def encode(self, input, errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling. The method may not store state in the Codec instance. Use StreamCodec for codecs which have to keep state in order to make encoding/decoding efficient. The encoder must be able to handle zero length input and return an empty object of the output object type in this situation. """ raise NotImplementedError def decode(self, input, errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling. The method may not store state in the Codec instance. Use StreamCodec for codecs which have to keep state in order to make encoding/decoding efficient. The decoder must be able to handle zero length input and return an empty object of the output object type in this situation. """ raise NotImplementedError class IncrementalEncoder(object): """ An IncrementalEncoder encodes an input in multiple steps. The input can be passed piece by piece to the encode() method. The IncrementalEncoder remembers the state of the Encoding process between calls to encode(). """ def __init__(self, errors='strict'): """ Creates an IncrementalEncoder instance. The IncrementalEncoder may use different error handling schemes by providing the errors keyword argument. See the module docstring for a list of possible values. """ self.errors = errors self.buffer = "" def encode(self, input, final=False): """ Encodes input and returns the resulting object. """ raise NotImplementedError def reset(self): """ Resets the encoder to the initial state. """ def getstate(self): """ Return the current state of the encoder. """ return 0 def setstate(self, state): """ Set the current state of the encoder. state must have been returned by getstate(). """ class BufferedIncrementalEncoder(IncrementalEncoder): """ This subclass of IncrementalEncoder can be used as the baseclass for an incremental encoder if the encoder must keep some of the output in a buffer between calls to encode(). """ def __init__(self, errors='strict'): IncrementalEncoder.__init__(self, errors) self.buffer = "" # unencoded input that is kept between calls to encode() def _buffer_encode(self, input, errors, final): # Overwrite this method in subclasses: It must encode input # and return an (output, length consumed) tuple raise NotImplementedError def encode(self, input, final=False): # encode input (taking the buffer into account) data = self.buffer + input (result, consumed) = self._buffer_encode(data, self.errors, final) # keep unencoded input until the next call self.buffer = data[consumed:] return result def reset(self): IncrementalEncoder.reset(self) self.buffer = "" def getstate(self): return self.buffer or 0 def setstate(self, state): self.buffer = state or "" class IncrementalDecoder(object): """ An IncrementalDecoder decodes an input in multiple steps. The input can be passed piece by piece to the decode() method. The IncrementalDecoder remembers the state of the decoding process between calls to decode(). """ def __init__(self, errors='strict'): """ Creates a IncrementalDecoder instance. The IncrementalDecoder may use different error handling schemes by providing the errors keyword argument. See the module docstring for a list of possible values. """ self.errors = errors def decode(self, input, final=False): """ Decodes input and returns the resulting object. """ raise NotImplementedError def reset(self): """ Resets the decoder to the initial state. """ def getstate(self): """ Return the current state of the decoder. This must be a (buffered_input, additional_state_info) tuple. buffered_input must be a bytes object containing bytes that were passed to decode() that have not yet been converted. additional_state_info must be a non-negative integer representing the state of the decoder WITHOUT yet having processed the contents of buffered_input. In the initial state and after reset(), getstate() must return (b"", 0). """ return (b"", 0) def setstate(self, state): """ Set the current state of the decoder. state must have been returned by getstate(). The effect of setstate((b"", 0)) must be equivalent to reset(). """ class BufferedIncrementalDecoder(IncrementalDecoder): """ This subclass of IncrementalDecoder can be used as the baseclass for an incremental decoder if the decoder must be able to handle incomplete byte sequences. """ def __init__(self, errors='strict'): IncrementalDecoder.__init__(self, errors) self.buffer = "" # undecoded input that is kept between calls to decode() def _buffer_decode(self, input, errors, final): # Overwrite this method in subclasses: It must decode input # and return an (output, length consumed) tuple raise NotImplementedError def decode(self, input, final=False): # decode input (taking the buffer into account) data = self.buffer + input (result, consumed) = self._buffer_decode(data, self.errors, final) # keep undecoded input until the next call self.buffer = data[consumed:] return result def reset(self): IncrementalDecoder.reset(self) self.buffer = "" def getstate(self): # additional state info is always 0 return (self.buffer, 0) def setstate(self, state): # ignore additional state info self.buffer = state[0] # # The StreamWriter and StreamReader class provide generic working # interfaces which can be used to implement new encoding submodules # very easily. See encodings/utf_8.py for an example on how this is # done. # class StreamWriter(Codec): def __init__(self, stream, errors='strict'): """ Creates a StreamWriter instance. stream must be a file-like object open for writing (binary) data. The StreamWriter may use different error handling schemes by providing the errors keyword argument. These parameters are predefined: 'strict' - raise a ValueError (or a subclass) 'ignore' - ignore the character and continue with the next 'replace'- replace with a suitable replacement character 'xmlcharrefreplace' - Replace with the appropriate XML character reference. 'backslashreplace' - Replace with backslashed escape sequences (only for encoding). The set of allowed parameter values can be extended via register_error. """ self.stream = stream self.errors = errors def write(self, object): """ Writes the object's contents encoded to self.stream. """ data, consumed = self.encode(object, self.errors) self.stream.write(data) def writelines(self, list): """ Writes the concatenated list of strings to the stream using .write(). """ self.write(''.join(list)) def reset(self): """ Flushes and resets the codec buffers used for keeping state. Calling this method should ensure that the data on the output is put into a clean state, that allows appending of new fresh data without having to rescan the whole stream to recover state. """ pass def seek(self, offset, whence=0): self.stream.seek(offset, whence) if whence == 0 and offset == 0: self.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamReader(Codec): def __init__(self, stream, errors='strict'): """ Creates a StreamReader instance. stream must be a file-like object open for reading (binary) data. The StreamReader may use different error handling schemes by providing the errors keyword argument. These parameters are predefined: 'strict' - raise a ValueError (or a subclass) 'ignore' - ignore the character and continue with the next 'replace'- replace with a suitable replacement character; The set of allowed parameter values can be extended via register_error. """ self.stream = stream self.errors = errors self.bytebuffer = "" # For str->str decoding this will stay a str # For str->unicode decoding the first read will promote it to unicode self.charbuffer = "" self.linebuffer = None def decode(self, input, errors='strict'): raise NotImplementedError def read(self, size=-1, chars=-1, firstline=False): """ Decodes data from the stream self.stream and returns the resulting object. chars indicates the number of characters to read from the stream. read() will never return more than chars characters, but it might return less, if there are not enough characters available. size indicates the approximate maximum number of bytes to read from the stream for decoding purposes. The decoder can modify this setting as appropriate. The default value -1 indicates to read and decode as much as possible. size is intended to prevent having to decode huge files in one step. If firstline is true, and a UnicodeDecodeError happens after the first line terminator in the input only the first line will be returned, the rest of the input will be kept until the next call to read(). The method should use a greedy read strategy meaning that it should read as much data as is allowed within the definition of the encoding and the given size, e.g. if optional encoding endings or state markers are available on the stream, these should be read too. """ # If we have lines cached, first merge them back into characters if self.linebuffer: self.charbuffer = "".join(self.linebuffer) self.linebuffer = None # read until we get the required number of characters (if available) while True: # can the request can be satisfied from the character buffer? if chars < 0: if size < 0: if self.charbuffer: break elif len(self.charbuffer) >= size: break else: if len(self.charbuffer) >= chars: break # we need more data if size < 0: newdata = self.stream.read() else: newdata = self.stream.read(size) # decode bytes (those remaining from the last call included) data = self.bytebuffer + newdata try: newchars, decodedbytes = self.decode(data, self.errors) except UnicodeDecodeError, exc: if firstline: newchars, decodedbytes = self.decode(data[:exc.start], self.errors) lines = newchars.splitlines(True) if len(lines)<=1: raise else: raise # keep undecoded bytes until the next call self.bytebuffer = data[decodedbytes:] # put new characters in the character buffer self.charbuffer += newchars # there was no data available if not newdata: break if chars < 0: # Return everything we've got result = self.charbuffer self.charbuffer = "" else: # Return the first chars characters result = self.charbuffer[:chars] self.charbuffer = self.charbuffer[chars:] return result def readline(self, size=None, keepends=True): """ Read one line from the input stream and return the decoded data. size, if given, is passed as size argument to the read() method. """ # If we have lines cached from an earlier read, return # them unconditionally if self.linebuffer: line = self.linebuffer[0] del self.linebuffer[0] if len(self.linebuffer) == 1: # revert to charbuffer mode; we might need more data # next time self.charbuffer = self.linebuffer[0] self.linebuffer = None if not keepends: line = line.splitlines(False)[0] return line readsize = size or 72 line = "" # If size is given, we call read() only once while True: data = self.read(readsize, firstline=True) if data: # If we're at a "\r" read one extra character (which might # be a "\n") to get a proper line ending. If the stream is # temporarily exhausted we return the wrong line ending. if data.endswith("\r"): data += self.read(size=1, chars=1) line += data lines = line.splitlines(True) if lines: if len(lines) > 1: # More than one line result; the first line is a full line # to return line = lines[0] del lines[0] if len(lines) > 1: # cache the remaining lines lines[-1] += self.charbuffer self.linebuffer = lines self.charbuffer = None else: # only one remaining line, put it back into charbuffer self.charbuffer = lines[0] + self.charbuffer if not keepends: line = line.splitlines(False)[0] break line0withend = lines[0] line0withoutend = lines[0].splitlines(False)[0] if line0withend != line0withoutend: # We really have a line end # Put the rest back together and keep it until the next call self.charbuffer = "".join(lines[1:]) + self.charbuffer if keepends: line = line0withend else: line = line0withoutend break # we didn't get anything or this was our only try if not data or size is not None: if line and not keepends: line = line.splitlines(False)[0] break if readsize<8000: readsize *= 2 return line def readlines(self, sizehint=None, keepends=True): """ Read all lines available on the input stream and return them as list of lines. Line breaks are implemented using the codec's decoder method and are included in the list entries. sizehint, if given, is ignored since there is no efficient way to finding the true end-of-line. """ data = self.read() return data.splitlines(keepends) def reset(self): """ Resets the codec buffers used for keeping state. Note that no stream repositioning should take place. This method is primarily intended to be able to recover from decoding errors. """ self.bytebuffer = "" self.charbuffer = u"" self.linebuffer = None def seek(self, offset, whence=0): """ Set the input stream's current position. Resets the codec buffers used for keeping state. """ self.stream.seek(offset, whence) self.reset() def next(self): """ Return the next decoded line from the input stream.""" line = self.readline() if line: return line raise StopIteration def __iter__(self): return self def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamReaderWriter: """ StreamReaderWriter instances allow wrapping streams which work in both read and write modes. The design is such that one can use the factory functions returned by the codec.lookup() function to construct the instance. """ # Optional attributes set by the file wrappers below encoding = 'unknown' def __init__(self, stream, Reader, Writer, errors='strict'): """ Creates a StreamReaderWriter instance. stream must be a Stream-like object. Reader, Writer must be factory functions or classes providing the StreamReader, StreamWriter interface resp. Error handling is done in the same way as defined for the StreamWriter/Readers. """ self.stream = stream self.reader = Reader(stream, errors) self.writer = Writer(stream, errors) self.errors = errors def read(self, size=-1): return self.reader.read(size) def readline(self, size=None): return self.reader.readline(size) def readlines(self, sizehint=None): return self.reader.readlines(sizehint) def next(self): """ Return the next decoded line from the input stream.""" return self.reader.next() def __iter__(self): return self def write(self, data): return self.writer.write(data) def writelines(self, list): return self.writer.writelines(list) def reset(self): self.reader.reset() self.writer.reset() def seek(self, offset, whence=0): self.stream.seek(offset, whence) self.reader.reset() if whence == 0 and offset == 0: self.writer.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) # these are needed to make "with codecs.open(...)" work properly def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### class StreamRecoder: """ StreamRecoder instances provide a frontend - backend view of encoding data. They use the complete set of APIs returned by the codecs.lookup() function to implement their task. Data written to the stream is first decoded into an intermediate format (which is dependent on the given codec combination) and then written to the stream using an instance of the provided Writer class. In the other direction, data is read from the stream using a Reader instance and then return encoded data to the caller. """ # Optional attributes set by the file wrappers below data_encoding = 'unknown' file_encoding = 'unknown' def __init__(self, stream, encode, decode, Reader, Writer, errors='strict'): """ Creates a StreamRecoder instance which implements a two-way conversion: encode and decode work on the frontend (the input to .read() and output of .write()) while Reader and Writer work on the backend (reading and writing to the stream). You can use these objects to do transparent direct recodings from e.g. latin-1 to utf-8 and back. stream must be a file-like object. encode, decode must adhere to the Codec interface, Reader, Writer must be factory functions or classes providing the StreamReader, StreamWriter interface resp. encode and decode are needed for the frontend translation, Reader and Writer for the backend translation. Unicode is used as intermediate encoding. Error handling is done in the same way as defined for the StreamWriter/Readers. """ self.stream = stream self.encode = encode self.decode = decode self.reader = Reader(stream, errors) self.writer = Writer(stream, errors) self.errors = errors def read(self, size=-1): data = self.reader.read(size) data, bytesencoded = self.encode(data, self.errors) return data def readline(self, size=None): if size is None: data = self.reader.readline() else: data = self.reader.readline(size) data, bytesencoded = self.encode(data, self.errors) return data def readlines(self, sizehint=None): data = self.reader.read() data, bytesencoded = self.encode(data, self.errors) return data.splitlines(1) def next(self): """ Return the next decoded line from the input stream.""" data = self.reader.next() data, bytesencoded = self.encode(data, self.errors) return data def __iter__(self): return self def write(self, data): data, bytesdecoded = self.decode(data, self.errors) return self.writer.write(data) def writelines(self, list): data = ''.join(list) data, bytesdecoded = self.decode(data, self.errors) return self.writer.write(data) def reset(self): self.reader.reset() self.writer.reset() def __getattr__(self, name, getattr=getattr): """ Inherit all other methods from the underlying stream. """ return getattr(self.stream, name) def __enter__(self): return self def __exit__(self, type, value, tb): self.stream.close() ### Shortcuts def open(filename, mode='rb', encoding=None, errors='strict', buffering=1): """ Open an encoded file using the given mode and return a wrapped version providing transparent encoding/decoding. Note: The wrapped version will only accept the object format defined by the codecs, i.e. Unicode objects for most builtin codecs. Output is also codec dependent and will usually be Unicode as well. Files are always opened in binary mode, even if no binary mode was specified. This is done to avoid data loss due to encodings using 8-bit values. The default file mode is 'rb' meaning to open the file in binary read mode. encoding specifies the encoding which is to be used for the file. errors may be given to define the error handling. It defaults to 'strict' which causes ValueErrors to be raised in case an encoding error occurs. buffering has the same meaning as for the builtin open() API. It defaults to line buffered. The returned wrapped file object provides an extra attribute .encoding which allows querying the used encoding. This attribute is only available if an encoding was specified as parameter. """ if encoding is not None: if 'U' in mode: # No automatic conversion of '\n' is done on reading and writing mode = mode.strip().replace('U', '') if mode[:1] not in set('rwa'): mode = 'r' + mode if 'b' not in mode: # Force opening of the file in binary mode mode = mode + 'b' file = __builtin__.open(filename, mode, buffering) if encoding is None: return file info = lookup(encoding) srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors) # Add attributes to simplify introspection srw.encoding = encoding return srw def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'): """ Return a wrapped version of file which provides transparent encoding translation. Strings written to the wrapped file are interpreted according to the given data_encoding and then written to the original file as string using file_encoding. The intermediate encoding will usually be Unicode but depends on the specified codecs. Strings are read from the file using file_encoding and then passed back to the caller as string using data_encoding. If file_encoding is not given, it defaults to data_encoding. errors may be given to define the error handling. It defaults to 'strict' which causes ValueErrors to be raised in case an encoding error occurs. The returned wrapped file object provides two extra attributes .data_encoding and .file_encoding which reflect the given parameters of the same name. The attributes can be used for introspection by Python programs. """ if file_encoding is None: file_encoding = data_encoding data_info = lookup(data_encoding) file_info = lookup(file_encoding) sr = StreamRecoder(file, data_info.encode, data_info.decode, file_info.streamreader, file_info.streamwriter, errors) # Add attributes to simplify introspection sr.data_encoding = data_encoding sr.file_encoding = file_encoding return sr ### Helpers for codec lookup def getencoder(encoding): """ Lookup up the codec for the given encoding and return its encoder function. Raises a LookupError in case the encoding cannot be found. """ return lookup(encoding).encode def getdecoder(encoding): """ Lookup up the codec for the given encoding and return its decoder function. Raises a LookupError in case the encoding cannot be found. """ return lookup(encoding).decode def getincrementalencoder(encoding): """ Lookup up the codec for the given encoding and return its IncrementalEncoder class or factory function. Raises a LookupError in case the encoding cannot be found or the codecs doesn't provide an incremental encoder. """ encoder = lookup(encoding).incrementalencoder if encoder is None: raise LookupError(encoding) return encoder def getincrementaldecoder(encoding): """ Lookup up the codec for the given encoding and return its IncrementalDecoder class or factory function. Raises a LookupError in case the encoding cannot be found or the codecs doesn't provide an incremental decoder. """ decoder = lookup(encoding).incrementaldecoder if decoder is None: raise LookupError(encoding) return decoder def getreader(encoding): """ Lookup up the codec for the given encoding and return its StreamReader class or factory function. Raises a LookupError in case the encoding cannot be found. """ return lookup(encoding).streamreader def getwriter(encoding): """ Lookup up the codec for the given encoding and return its StreamWriter class or factory function. Raises a LookupError in case the encoding cannot be found. """ return lookup(encoding).streamwriter def iterencode(iterator, encoding, errors='strict', **kwargs): """ Encoding iterator. Encodes the input strings from the iterator using a IncrementalEncoder. errors and kwargs are passed through to the IncrementalEncoder constructor. """ encoder = getincrementalencoder(encoding)(errors, **kwargs) for input in iterator: output = encoder.encode(input) if output: yield output output = encoder.encode("", True) if output: yield output def iterdecode(iterator, encoding, errors='strict', **kwargs): """ Decoding iterator. Decodes the input strings from the iterator using a IncrementalDecoder. errors and kwargs are passed through to the IncrementalDecoder constructor. """ decoder = getincrementaldecoder(encoding)(errors, **kwargs) for input in iterator: output = decoder.decode(input) if output: yield output output = decoder.decode("", True) if output: yield output ### Helpers for charmap-based codecs def make_identity_dict(rng): """ make_identity_dict(rng) -> dict Return a dictionary where elements of the rng sequence are mapped to themselves. """ res = {} for i in rng: res[i]=i return res def make_encoding_map(decoding_map): """ Creates an encoding map from a decoding map. If a target mapping in the decoding map occurs multiple times, then that target is mapped to None (undefined mapping), causing an exception when encountered by the charmap codec during translation. One example where this happens is cp875.py which decodes multiple character to \u001a. """ m = {} for k,v in decoding_map.items(): if not v in m: m[v] = k else: m[v] = None return m ### error handlers try: strict_errors = lookup_error("strict") ignore_errors = lookup_error("ignore") replace_errors = lookup_error("replace") xmlcharrefreplace_errors = lookup_error("xmlcharrefreplace") backslashreplace_errors = lookup_error("backslashreplace") except LookupError: # In --disable-unicode builds, these error handler are missing strict_errors = None ignore_errors = None replace_errors = None xmlcharrefreplace_errors = None backslashreplace_errors = None # Tell modulefinder that using codecs probably needs the encodings # package _false = 0 if _false: import encodings ### Tests if __name__ == '__main__': # Make stdout translate Latin-1 output into UTF-8 output sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8') # Have stdin translate Latin-1 input into UTF-8 input sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1') feedgenerator-1.9/.tox/py26/lib/python2.6/copy_reg.py0000644000076500000240000001522012612565535022126 0ustar jmstaff00000000000000"""Helper to provide extensibility for pickle/cPickle. This is only useful to add pickle support for extension types defined in C, not for instances of user-defined classes. """ from types import ClassType as _ClassType __all__ = ["pickle", "constructor", "add_extension", "remove_extension", "clear_extension_cache"] dispatch_table = {} def pickle(ob_type, pickle_function, constructor_ob=None): if type(ob_type) is _ClassType: raise TypeError("copy_reg is not intended for use with classes") if not hasattr(pickle_function, '__call__'): raise TypeError("reduction functions must be callable") dispatch_table[ob_type] = pickle_function # The constructor_ob function is a vestige of safe for unpickling. # There is no reason for the caller to pass it anymore. if constructor_ob is not None: constructor(constructor_ob) def constructor(object): if not hasattr(object, '__call__'): raise TypeError("constructors must be callable") # Example: provide pickling support for complex numbers. try: complex except NameError: pass else: def pickle_complex(c): return complex, (c.real, c.imag) pickle(complex, pickle_complex, complex) # Support for pickling new-style objects def _reconstructor(cls, base, state): if base is object: obj = object.__new__(cls) else: obj = base.__new__(cls, state) if base.__init__ != object.__init__: base.__init__(obj, state) return obj _HEAPTYPE = 1<<9 # Python code for object.__reduce_ex__ for protocols 0 and 1 def _reduce_ex(self, proto): assert proto < 2 for base in self.__class__.__mro__: if hasattr(base, '__flags__') and not base.__flags__ & _HEAPTYPE: break else: base = object # not really reachable if base is object: state = None else: if base is self.__class__: raise TypeError, "can't pickle %s objects" % base.__name__ state = base(self) args = (self.__class__, base, state) try: getstate = self.__getstate__ except AttributeError: if getattr(self, "__slots__", None): raise TypeError("a class that defines __slots__ without " "defining __getstate__ cannot be pickled") try: dict = self.__dict__ except AttributeError: dict = None else: dict = getstate() if dict: return _reconstructor, args, dict else: return _reconstructor, args # Helper for __reduce_ex__ protocol 2 def __newobj__(cls, *args): return cls.__new__(cls, *args) def _slotnames(cls): """Return a list of slot names for a given class. This needs to find slots defined by the class and its bases, so we can't simply return the __slots__ attribute. We must walk down the Method Resolution Order and concatenate the __slots__ of each class found there. (This assumes classes don't modify their __slots__ attribute to misrepresent their slots after the class is defined.) """ # Get the value from a cache in the class if possible names = cls.__dict__.get("__slotnames__") if names is not None: return names # Not cached -- calculate the value names = [] if not hasattr(cls, "__slots__"): # This class has no slots pass else: # Slots found -- gather slot names from all base classes for c in cls.__mro__: if "__slots__" in c.__dict__: slots = c.__dict__['__slots__'] # if class has a single slot, it can be given as a string if isinstance(slots, basestring): slots = (slots,) for name in slots: # special descriptors if name in ("__dict__", "__weakref__"): continue # mangled names elif name.startswith('__') and not name.endswith('__'): names.append('_%s%s' % (c.__name__, name)) else: names.append(name) # Cache the outcome in the class if at all possible try: cls.__slotnames__ = names except: pass # But don't die if we can't return names # A registry of extension codes. This is an ad-hoc compression # mechanism. Whenever a global reference to , is about # to be pickled, the (, ) tuple is looked up here to see # if it is a registered extension code for it. Extension codes are # universal, so that the meaning of a pickle does not depend on # context. (There are also some codes reserved for local use that # don't have this restriction.) Codes are positive ints; 0 is # reserved. _extension_registry = {} # key -> code _inverted_registry = {} # code -> key _extension_cache = {} # code -> object # Don't ever rebind those names: cPickle grabs a reference to them when # it's initialized, and won't see a rebinding. def add_extension(module, name, code): """Register an extension code.""" code = int(code) if not 1 <= code <= 0x7fffffff: raise ValueError, "code out of range" key = (module, name) if (_extension_registry.get(key) == code and _inverted_registry.get(code) == key): return # Redundant registrations are benign if key in _extension_registry: raise ValueError("key %s is already registered with code %s" % (key, _extension_registry[key])) if code in _inverted_registry: raise ValueError("code %s is already in use for key %s" % (code, _inverted_registry[code])) _extension_registry[key] = code _inverted_registry[code] = key def remove_extension(module, name, code): """Unregister an extension code. For testing only.""" key = (module, name) if (_extension_registry.get(key) != code or _inverted_registry.get(code) != key): raise ValueError("key %s is not registered with code %s" % (key, code)) del _extension_registry[key] del _inverted_registry[code] if code in _extension_cache: del _extension_cache[code] def clear_extension_cache(): _extension_cache.clear() # Standard extension code assignments # Reserved ranges # First Last Count Purpose # 1 127 127 Reserved for Python standard library # 128 191 64 Reserved for Zope # 192 239 48 Reserved for 3rd parties # 240 255 16 Reserved for private use (will never be assigned) # 256 Inf Inf Reserved for future assignment # Extension codes are assigned by the Python Software Foundation. feedgenerator-1.9/.tox/py26/lib/python2.6/distutils/0000755000076500000240000000000012765362056021773 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/distutils/__init__.py0000644000076500000240000000761712700725532024106 0ustar jmstaff00000000000000import os import sys import warnings import imp import opcode # opcode is not a virtualenv module, so we can use it to find the stdlib # Important! To work on pypy, this must be a module that resides in the # lib-python/modified-x.y.z directory dirname = os.path.dirname distutils_path = os.path.join(os.path.dirname(opcode.__file__), 'distutils') if os.path.normpath(distutils_path) == os.path.dirname(os.path.normpath(__file__)): warnings.warn( "The virtualenv distutils package at %s appears to be in the same location as the system distutils?") else: __path__.insert(0, distutils_path) real_distutils = imp.load_module("_virtualenv_distutils", None, distutils_path, ('', '', imp.PKG_DIRECTORY)) # Copy the relevant attributes try: __revision__ = real_distutils.__revision__ except AttributeError: pass __version__ = real_distutils.__version__ from distutils import dist, sysconfig try: basestring except NameError: basestring = str ## patch build_ext (distutils doesn't know how to get the libs directory ## path on windows - it hardcodes the paths around the patched sys.prefix) if sys.platform == 'win32': from distutils.command.build_ext import build_ext as old_build_ext class build_ext(old_build_ext): def finalize_options (self): if self.library_dirs is None: self.library_dirs = [] elif isinstance(self.library_dirs, basestring): self.library_dirs = self.library_dirs.split(os.pathsep) self.library_dirs.insert(0, os.path.join(sys.real_prefix, "Libs")) old_build_ext.finalize_options(self) from distutils.command import build_ext as build_ext_module build_ext_module.build_ext = build_ext ## distutils.dist patches: old_find_config_files = dist.Distribution.find_config_files def find_config_files(self): found = old_find_config_files(self) system_distutils = os.path.join(distutils_path, 'distutils.cfg') #if os.path.exists(system_distutils): # found.insert(0, system_distutils) # What to call the per-user config file if os.name == 'posix': user_filename = ".pydistutils.cfg" else: user_filename = "pydistutils.cfg" user_filename = os.path.join(sys.prefix, user_filename) if os.path.isfile(user_filename): for item in list(found): if item.endswith('pydistutils.cfg'): found.remove(item) found.append(user_filename) return found dist.Distribution.find_config_files = find_config_files ## distutils.sysconfig patches: old_get_python_inc = sysconfig.get_python_inc def sysconfig_get_python_inc(plat_specific=0, prefix=None): if prefix is None: prefix = sys.real_prefix return old_get_python_inc(plat_specific, prefix) sysconfig_get_python_inc.__doc__ = old_get_python_inc.__doc__ sysconfig.get_python_inc = sysconfig_get_python_inc old_get_python_lib = sysconfig.get_python_lib def sysconfig_get_python_lib(plat_specific=0, standard_lib=0, prefix=None): if standard_lib and prefix is None: prefix = sys.real_prefix return old_get_python_lib(plat_specific, standard_lib, prefix) sysconfig_get_python_lib.__doc__ = old_get_python_lib.__doc__ sysconfig.get_python_lib = sysconfig_get_python_lib old_get_config_vars = sysconfig.get_config_vars def sysconfig_get_config_vars(*args): real_vars = old_get_config_vars(*args) if sys.platform == 'win32': lib_dir = os.path.join(sys.real_prefix, "libs") if isinstance(real_vars, dict) and 'LIBDIR' not in real_vars: real_vars['LIBDIR'] = lib_dir # asked for all elif isinstance(real_vars, list) and 'LIBDIR' in args: real_vars = real_vars + [lib_dir] # asked for list return real_vars sysconfig_get_config_vars.__doc__ = old_get_config_vars.__doc__ sysconfig.get_config_vars = sysconfig_get_config_vars feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/0000755000076500000240000000000012765362057021721 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/__init__.py0000644000076500000240000001300612612565546024031 0ustar jmstaff00000000000000""" Standard "encodings" Package Standard Python encoding modules are stored in this package directory. Codec modules must have names corresponding to normalized encoding names as defined in the normalize_encoding() function below, e.g. 'utf-8' must be implemented by the module 'utf_8.py'. Each codec module must export the following interface: * getregentry() -> codecs.CodecInfo object The getregentry() API must a CodecInfo object with encoder, decoder, incrementalencoder, incrementaldecoder, streamwriter and streamreader atttributes which adhere to the Python Codec Interface Standard. In addition, a module may optionally also define the following APIs which are then used by the package's codec search function: * getaliases() -> sequence of encoding name strings to use as aliases Alias names returned by getaliases() must be normalized encoding names as defined by normalize_encoding(). Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """#" import codecs from encodings import aliases import __builtin__ _cache = {} _unknown = '--unknown--' _import_tail = ['*'] _norm_encoding_map = (' . ' '0123456789 ABCDEFGHIJKLMNOPQRSTUVWXYZ ' ' abcdefghijklmnopqrstuvwxyz ' ' ' ' ' ' ') _aliases = aliases.aliases class CodecRegistryError(LookupError, SystemError): pass def normalize_encoding(encoding): """ Normalize an encoding name. Normalization works as follows: all non-alphanumeric characters except the dot used for Python package names are collapsed and replaced with a single underscore, e.g. ' -;#' becomes '_'. Leading and trailing underscores are removed. Note that encoding names should be ASCII only; if they do use non-ASCII characters, these must be Latin-1 compatible. """ # Make sure we have an 8-bit string, because .translate() works # differently for Unicode strings. if hasattr(__builtin__, "unicode") and isinstance(encoding, unicode): # Note that .encode('latin-1') does *not* use the codec # registry, so this call doesn't recurse. (See unicodeobject.c # PyUnicode_AsEncodedString() for details) encoding = encoding.encode('latin-1') return '_'.join(encoding.translate(_norm_encoding_map).split()) def search_function(encoding): # Cache lookup entry = _cache.get(encoding, _unknown) if entry is not _unknown: return entry # Import the module: # # First try to find an alias for the normalized encoding # name and lookup the module using the aliased name, then try to # lookup the module using the standard import scheme, i.e. first # try in the encodings package, then at top-level. # norm_encoding = normalize_encoding(encoding) aliased_encoding = _aliases.get(norm_encoding) or \ _aliases.get(norm_encoding.replace('.', '_')) if aliased_encoding is not None: modnames = [aliased_encoding, norm_encoding] else: modnames = [norm_encoding] for modname in modnames: if not modname or '.' in modname: continue try: # Import is absolute to prevent the possibly malicious import of a # module with side-effects that is not in the 'encodings' package. mod = __import__('encodings.' + modname, fromlist=_import_tail, level=0) except ImportError: pass else: break else: mod = None try: getregentry = mod.getregentry except AttributeError: # Not a codec module mod = None if mod is None: # Cache misses _cache[encoding] = None return None # Now ask the module for the registry entry entry = getregentry() if not isinstance(entry, codecs.CodecInfo): if not 4 <= len(entry) <= 7: raise CodecRegistryError,\ 'module "%s" (%s) failed to register' % \ (mod.__name__, mod.__file__) if not callable(entry[0]) or \ not callable(entry[1]) or \ (entry[2] is not None and not callable(entry[2])) or \ (entry[3] is not None and not callable(entry[3])) or \ (len(entry) > 4 and entry[4] is not None and not callable(entry[4])) or \ (len(entry) > 5 and entry[5] is not None and not callable(entry[5])): raise CodecRegistryError,\ 'incompatible codecs in module "%s" (%s)' % \ (mod.__name__, mod.__file__) if len(entry)<7 or entry[6] is None: entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],) entry = codecs.CodecInfo(*entry) # Cache the codec registry entry _cache[encoding] = entry # Register its aliases (without overwriting previously registered # aliases) try: codecaliases = mod.getaliases() except AttributeError: pass else: for alias in codecaliases: if not _aliases.has_key(alias): _aliases[alias] = modname # Return the registry entry return entry # Register the search_function in the Python codec registry codecs.register(search_function) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/aliases.py0000644000076500000240000003460112612565546023717 0ustar jmstaff00000000000000""" Encoding Aliases Support This module is used by the encodings package search function to map encodings names to module names. Note that the search function normalizes the encoding names before doing the lookup, so the mapping will have to map normalized encoding names to module names. Contents: The following aliases dictionary contains mappings of all IANA character set names for which the Python core library provides codecs. In addition to these, a few Python specific codec aliases have also been added. """ aliases = { # Please keep this list sorted alphabetically by value ! # ascii codec '646' : 'ascii', 'ansi_x3.4_1968' : 'ascii', 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name 'ansi_x3.4_1986' : 'ascii', 'cp367' : 'ascii', 'csascii' : 'ascii', 'ibm367' : 'ascii', 'iso646_us' : 'ascii', 'iso_646.irv_1991' : 'ascii', 'iso_ir_6' : 'ascii', 'us' : 'ascii', 'us_ascii' : 'ascii', # base64_codec codec 'base64' : 'base64_codec', 'base_64' : 'base64_codec', # big5 codec 'big5_tw' : 'big5', 'csbig5' : 'big5', # big5hkscs codec 'big5_hkscs' : 'big5hkscs', 'hkscs' : 'big5hkscs', # bz2_codec codec 'bz2' : 'bz2_codec', # cp037 codec '037' : 'cp037', 'csibm037' : 'cp037', 'ebcdic_cp_ca' : 'cp037', 'ebcdic_cp_nl' : 'cp037', 'ebcdic_cp_us' : 'cp037', 'ebcdic_cp_wt' : 'cp037', 'ibm037' : 'cp037', 'ibm039' : 'cp037', # cp1026 codec '1026' : 'cp1026', 'csibm1026' : 'cp1026', 'ibm1026' : 'cp1026', # cp1140 codec '1140' : 'cp1140', 'ibm1140' : 'cp1140', # cp1250 codec '1250' : 'cp1250', 'windows_1250' : 'cp1250', # cp1251 codec '1251' : 'cp1251', 'windows_1251' : 'cp1251', # cp1252 codec '1252' : 'cp1252', 'windows_1252' : 'cp1252', # cp1253 codec '1253' : 'cp1253', 'windows_1253' : 'cp1253', # cp1254 codec '1254' : 'cp1254', 'windows_1254' : 'cp1254', # cp1255 codec '1255' : 'cp1255', 'windows_1255' : 'cp1255', # cp1256 codec '1256' : 'cp1256', 'windows_1256' : 'cp1256', # cp1257 codec '1257' : 'cp1257', 'windows_1257' : 'cp1257', # cp1258 codec '1258' : 'cp1258', 'windows_1258' : 'cp1258', # cp424 codec '424' : 'cp424', 'csibm424' : 'cp424', 'ebcdic_cp_he' : 'cp424', 'ibm424' : 'cp424', # cp437 codec '437' : 'cp437', 'cspc8codepage437' : 'cp437', 'ibm437' : 'cp437', # cp500 codec '500' : 'cp500', 'csibm500' : 'cp500', 'ebcdic_cp_be' : 'cp500', 'ebcdic_cp_ch' : 'cp500', 'ibm500' : 'cp500', # cp775 codec '775' : 'cp775', 'cspc775baltic' : 'cp775', 'ibm775' : 'cp775', # cp850 codec '850' : 'cp850', 'cspc850multilingual' : 'cp850', 'ibm850' : 'cp850', # cp852 codec '852' : 'cp852', 'cspcp852' : 'cp852', 'ibm852' : 'cp852', # cp855 codec '855' : 'cp855', 'csibm855' : 'cp855', 'ibm855' : 'cp855', # cp857 codec '857' : 'cp857', 'csibm857' : 'cp857', 'ibm857' : 'cp857', # cp860 codec '860' : 'cp860', 'csibm860' : 'cp860', 'ibm860' : 'cp860', # cp861 codec '861' : 'cp861', 'cp_is' : 'cp861', 'csibm861' : 'cp861', 'ibm861' : 'cp861', # cp862 codec '862' : 'cp862', 'cspc862latinhebrew' : 'cp862', 'ibm862' : 'cp862', # cp863 codec '863' : 'cp863', 'csibm863' : 'cp863', 'ibm863' : 'cp863', # cp864 codec '864' : 'cp864', 'csibm864' : 'cp864', 'ibm864' : 'cp864', # cp865 codec '865' : 'cp865', 'csibm865' : 'cp865', 'ibm865' : 'cp865', # cp866 codec '866' : 'cp866', 'csibm866' : 'cp866', 'ibm866' : 'cp866', # cp869 codec '869' : 'cp869', 'cp_gr' : 'cp869', 'csibm869' : 'cp869', 'ibm869' : 'cp869', # cp932 codec '932' : 'cp932', 'ms932' : 'cp932', 'mskanji' : 'cp932', 'ms_kanji' : 'cp932', # cp949 codec '949' : 'cp949', 'ms949' : 'cp949', 'uhc' : 'cp949', # cp950 codec '950' : 'cp950', 'ms950' : 'cp950', # euc_jis_2004 codec 'jisx0213' : 'euc_jis_2004', 'eucjis2004' : 'euc_jis_2004', 'euc_jis2004' : 'euc_jis_2004', # euc_jisx0213 codec 'eucjisx0213' : 'euc_jisx0213', # euc_jp codec 'eucjp' : 'euc_jp', 'ujis' : 'euc_jp', 'u_jis' : 'euc_jp', # euc_kr codec 'euckr' : 'euc_kr', 'korean' : 'euc_kr', 'ksc5601' : 'euc_kr', 'ks_c_5601' : 'euc_kr', 'ks_c_5601_1987' : 'euc_kr', 'ksx1001' : 'euc_kr', 'ks_x_1001' : 'euc_kr', # gb18030 codec 'gb18030_2000' : 'gb18030', # gb2312 codec 'chinese' : 'gb2312', 'csiso58gb231280' : 'gb2312', 'euc_cn' : 'gb2312', 'euccn' : 'gb2312', 'eucgb2312_cn' : 'gb2312', 'gb2312_1980' : 'gb2312', 'gb2312_80' : 'gb2312', 'iso_ir_58' : 'gb2312', # gbk codec '936' : 'gbk', 'cp936' : 'gbk', 'ms936' : 'gbk', # hex_codec codec 'hex' : 'hex_codec', # hp_roman8 codec 'roman8' : 'hp_roman8', 'r8' : 'hp_roman8', 'csHPRoman8' : 'hp_roman8', # hz codec 'hzgb' : 'hz', 'hz_gb' : 'hz', 'hz_gb_2312' : 'hz', # iso2022_jp codec 'csiso2022jp' : 'iso2022_jp', 'iso2022jp' : 'iso2022_jp', 'iso_2022_jp' : 'iso2022_jp', # iso2022_jp_1 codec 'iso2022jp_1' : 'iso2022_jp_1', 'iso_2022_jp_1' : 'iso2022_jp_1', # iso2022_jp_2 codec 'iso2022jp_2' : 'iso2022_jp_2', 'iso_2022_jp_2' : 'iso2022_jp_2', # iso2022_jp_2004 codec 'iso_2022_jp_2004' : 'iso2022_jp_2004', 'iso2022jp_2004' : 'iso2022_jp_2004', # iso2022_jp_3 codec 'iso2022jp_3' : 'iso2022_jp_3', 'iso_2022_jp_3' : 'iso2022_jp_3', # iso2022_jp_ext codec 'iso2022jp_ext' : 'iso2022_jp_ext', 'iso_2022_jp_ext' : 'iso2022_jp_ext', # iso2022_kr codec 'csiso2022kr' : 'iso2022_kr', 'iso2022kr' : 'iso2022_kr', 'iso_2022_kr' : 'iso2022_kr', # iso8859_10 codec 'csisolatin6' : 'iso8859_10', 'iso_8859_10' : 'iso8859_10', 'iso_8859_10_1992' : 'iso8859_10', 'iso_ir_157' : 'iso8859_10', 'l6' : 'iso8859_10', 'latin6' : 'iso8859_10', # iso8859_11 codec 'thai' : 'iso8859_11', 'iso_8859_11' : 'iso8859_11', 'iso_8859_11_2001' : 'iso8859_11', # iso8859_13 codec 'iso_8859_13' : 'iso8859_13', 'l7' : 'iso8859_13', 'latin7' : 'iso8859_13', # iso8859_14 codec 'iso_8859_14' : 'iso8859_14', 'iso_8859_14_1998' : 'iso8859_14', 'iso_celtic' : 'iso8859_14', 'iso_ir_199' : 'iso8859_14', 'l8' : 'iso8859_14', 'latin8' : 'iso8859_14', # iso8859_15 codec 'iso_8859_15' : 'iso8859_15', 'l9' : 'iso8859_15', 'latin9' : 'iso8859_15', # iso8859_16 codec 'iso_8859_16' : 'iso8859_16', 'iso_8859_16_2001' : 'iso8859_16', 'iso_ir_226' : 'iso8859_16', 'l10' : 'iso8859_16', 'latin10' : 'iso8859_16', # iso8859_2 codec 'csisolatin2' : 'iso8859_2', 'iso_8859_2' : 'iso8859_2', 'iso_8859_2_1987' : 'iso8859_2', 'iso_ir_101' : 'iso8859_2', 'l2' : 'iso8859_2', 'latin2' : 'iso8859_2', # iso8859_3 codec 'csisolatin3' : 'iso8859_3', 'iso_8859_3' : 'iso8859_3', 'iso_8859_3_1988' : 'iso8859_3', 'iso_ir_109' : 'iso8859_3', 'l3' : 'iso8859_3', 'latin3' : 'iso8859_3', # iso8859_4 codec 'csisolatin4' : 'iso8859_4', 'iso_8859_4' : 'iso8859_4', 'iso_8859_4_1988' : 'iso8859_4', 'iso_ir_110' : 'iso8859_4', 'l4' : 'iso8859_4', 'latin4' : 'iso8859_4', # iso8859_5 codec 'csisolatincyrillic' : 'iso8859_5', 'cyrillic' : 'iso8859_5', 'iso_8859_5' : 'iso8859_5', 'iso_8859_5_1988' : 'iso8859_5', 'iso_ir_144' : 'iso8859_5', # iso8859_6 codec 'arabic' : 'iso8859_6', 'asmo_708' : 'iso8859_6', 'csisolatinarabic' : 'iso8859_6', 'ecma_114' : 'iso8859_6', 'iso_8859_6' : 'iso8859_6', 'iso_8859_6_1987' : 'iso8859_6', 'iso_ir_127' : 'iso8859_6', # iso8859_7 codec 'csisolatingreek' : 'iso8859_7', 'ecma_118' : 'iso8859_7', 'elot_928' : 'iso8859_7', 'greek' : 'iso8859_7', 'greek8' : 'iso8859_7', 'iso_8859_7' : 'iso8859_7', 'iso_8859_7_1987' : 'iso8859_7', 'iso_ir_126' : 'iso8859_7', # iso8859_8 codec 'csisolatinhebrew' : 'iso8859_8', 'hebrew' : 'iso8859_8', 'iso_8859_8' : 'iso8859_8', 'iso_8859_8_1988' : 'iso8859_8', 'iso_ir_138' : 'iso8859_8', # iso8859_9 codec 'csisolatin5' : 'iso8859_9', 'iso_8859_9' : 'iso8859_9', 'iso_8859_9_1989' : 'iso8859_9', 'iso_ir_148' : 'iso8859_9', 'l5' : 'iso8859_9', 'latin5' : 'iso8859_9', # johab codec 'cp1361' : 'johab', 'ms1361' : 'johab', # koi8_r codec 'cskoi8r' : 'koi8_r', # latin_1 codec # # Note that the latin_1 codec is implemented internally in C and a # lot faster than the charmap codec iso8859_1 which uses the same # encoding. This is why we discourage the use of the iso8859_1 # codec and alias it to latin_1 instead. # '8859' : 'latin_1', 'cp819' : 'latin_1', 'csisolatin1' : 'latin_1', 'ibm819' : 'latin_1', 'iso8859' : 'latin_1', 'iso8859_1' : 'latin_1', 'iso_8859_1' : 'latin_1', 'iso_8859_1_1987' : 'latin_1', 'iso_ir_100' : 'latin_1', 'l1' : 'latin_1', 'latin' : 'latin_1', 'latin1' : 'latin_1', # mac_cyrillic codec 'maccyrillic' : 'mac_cyrillic', # mac_greek codec 'macgreek' : 'mac_greek', # mac_iceland codec 'maciceland' : 'mac_iceland', # mac_latin2 codec 'maccentraleurope' : 'mac_latin2', 'maclatin2' : 'mac_latin2', # mac_roman codec 'macroman' : 'mac_roman', # mac_turkish codec 'macturkish' : 'mac_turkish', # mbcs codec 'dbcs' : 'mbcs', # ptcp154 codec 'csptcp154' : 'ptcp154', 'pt154' : 'ptcp154', 'cp154' : 'ptcp154', 'cyrillic-asian' : 'ptcp154', # quopri_codec codec 'quopri' : 'quopri_codec', 'quoted_printable' : 'quopri_codec', 'quotedprintable' : 'quopri_codec', # rot_13 codec 'rot13' : 'rot_13', # shift_jis codec 'csshiftjis' : 'shift_jis', 'shiftjis' : 'shift_jis', 'sjis' : 'shift_jis', 's_jis' : 'shift_jis', # shift_jis_2004 codec 'shiftjis2004' : 'shift_jis_2004', 'sjis_2004' : 'shift_jis_2004', 's_jis_2004' : 'shift_jis_2004', # shift_jisx0213 codec 'shiftjisx0213' : 'shift_jisx0213', 'sjisx0213' : 'shift_jisx0213', 's_jisx0213' : 'shift_jisx0213', # tactis codec 'tis260' : 'tactis', # tis_620 codec 'tis620' : 'tis_620', 'tis_620_0' : 'tis_620', 'tis_620_2529_0' : 'tis_620', 'tis_620_2529_1' : 'tis_620', 'iso_ir_166' : 'tis_620', # utf_16 codec 'u16' : 'utf_16', 'utf16' : 'utf_16', # utf_16_be codec 'unicodebigunmarked' : 'utf_16_be', 'utf_16be' : 'utf_16_be', # utf_16_le codec 'unicodelittleunmarked' : 'utf_16_le', 'utf_16le' : 'utf_16_le', # utf_32 codec 'u32' : 'utf_32', 'utf32' : 'utf_32', # utf_32_be codec 'utf_32be' : 'utf_32_be', # utf_32_le codec 'utf_32le' : 'utf_32_le', # utf_7 codec 'u7' : 'utf_7', 'utf7' : 'utf_7', 'unicode_1_1_utf_7' : 'utf_7', # utf_8 codec 'u8' : 'utf_8', 'utf' : 'utf_8', 'utf8' : 'utf_8', 'utf8_ucs2' : 'utf_8', 'utf8_ucs4' : 'utf_8', # uu_codec codec 'uu' : 'uu_codec', # zlib_codec codec 'zip' : 'zlib_codec', 'zlib' : 'zlib_codec', } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/ascii.py0000644000076500000240000000234012612565546023361 0ustar jmstaff00000000000000""" Python 'ascii' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.ascii_encode decode = codecs.ascii_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.ascii_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.ascii_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass class StreamConverter(StreamWriter,StreamReader): encode = codecs.ascii_decode decode = codecs.ascii_encode ### encodings module API def getregentry(): return codecs.CodecInfo( name='ascii', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/base64_codec.py0000644000076500000240000000444212612565546024517 0ustar jmstaff00000000000000""" Python 'base64_codec' Codec - base64 content transfer encoding Unlike most of the other codecs which target Unicode, this codec will return Python string objects for both encode and decode. Written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs, base64 ### Codec APIs def base64_encode(input,errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = base64.encodestring(input) return (output, len(input)) def base64_decode(input,errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = base64.decodestring(input) return (output, len(input)) class Codec(codecs.Codec): def encode(self, input,errors='strict'): return base64_encode(input,errors) def decode(self, input,errors='strict'): return base64_decode(input,errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): assert self.errors == 'strict' return base64.encodestring(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): assert self.errors == 'strict' return base64.decodestring(input) class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='base64', encode=base64_encode, decode=base64_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/big5.py0000644000076500000240000000177312612565546023130 0ustar jmstaff00000000000000# # big5.py: Python Unicode Codec for BIG5 # # Written by Hye-Shik Chang # import _codecs_tw, codecs import _multibytecodec as mbc codec = _codecs_tw.getcodec('big5') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='big5', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/big5hkscs.py0000644000076500000240000000201712612565546024154 0ustar jmstaff00000000000000# # big5hkscs.py: Python Unicode Codec for BIG5HKSCS # # Written by Hye-Shik Chang # import _codecs_hk, codecs import _multibytecodec as mbc codec = _codecs_hk.getcodec('big5hkscs') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='big5hkscs', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/bz2_codec.py0000644000076500000240000000566112612565546024134 0ustar jmstaff00000000000000""" Python 'bz2_codec' Codec - bz2 compression encoding Unlike most of the other codecs which target Unicode, this codec will return Python string objects for both encode and decode. Adapted by Raymond Hettinger from zlib_codec.py which was written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs import bz2 # this codec needs the optional bz2 module ! ### Codec APIs def bz2_encode(input,errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = bz2.compress(input) return (output, len(input)) def bz2_decode(input,errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = bz2.decompress(input) return (output, len(input)) class Codec(codecs.Codec): def encode(self, input, errors='strict'): return bz2_encode(input, errors) def decode(self, input, errors='strict'): return bz2_decode(input, errors) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): assert errors == 'strict' self.errors = errors self.compressobj = bz2.BZ2Compressor() def encode(self, input, final=False): if final: c = self.compressobj.compress(input) return c + self.compressobj.flush() else: return self.compressobj.compress(input) def reset(self): self.compressobj = bz2.BZ2Compressor() class IncrementalDecoder(codecs.IncrementalDecoder): def __init__(self, errors='strict'): assert errors == 'strict' self.errors = errors self.decompressobj = bz2.BZ2Decompressor() def decode(self, input, final=False): try: return self.decompressobj.decompress(input) except EOFError: return '' def reset(self): self.decompressobj = bz2.BZ2Decompressor() class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name="bz2", encode=bz2_encode, decode=bz2_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/charmap.py0000644000076500000240000000404412612565546023707 0ustar jmstaff00000000000000""" Generic Python Character Mapping Codec. Use this codec directly rather than through the automatic conversion mechanisms supplied by unicode() and .encode(). Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """#" import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.charmap_encode decode = codecs.charmap_decode class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict', mapping=None): codecs.IncrementalEncoder.__init__(self, errors) self.mapping = mapping def encode(self, input, final=False): return codecs.charmap_encode(input, self.errors, self.mapping)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def __init__(self, errors='strict', mapping=None): codecs.IncrementalDecoder.__init__(self, errors) self.mapping = mapping def decode(self, input, final=False): return codecs.charmap_decode(input, self.errors, self.mapping)[0] class StreamWriter(Codec,codecs.StreamWriter): def __init__(self,stream,errors='strict',mapping=None): codecs.StreamWriter.__init__(self,stream,errors) self.mapping = mapping def encode(self,input,errors='strict'): return Codec.encode(input,errors,self.mapping) class StreamReader(Codec,codecs.StreamReader): def __init__(self,stream,errors='strict',mapping=None): codecs.StreamReader.__init__(self,stream,errors) self.mapping = mapping def decode(self,input,errors='strict'): return Codec.decode(input,errors,self.mapping) ### encodings module API def getregentry(): return codecs.CodecInfo( name='charmap', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp037.py0000644000076500000240000003210112612565546023123 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp037', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> CONTROL u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> CONTROL u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL u'\x8e' # 0x0A -> CONTROL u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> CONTROL u'\x85' # 0x15 -> CONTROL u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> CONTROL u'\x8f' # 0x1B -> CONTROL u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL u'\x83' # 0x23 -> CONTROL u'\x84' # 0x24 -> CONTROL u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL u'\x8a' # 0x2A -> CONTROL u'\x8b' # 0x2B -> CONTROL u'\x8c' # 0x2C -> CONTROL u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> CONTROL u'\x94' # 0x34 -> CONTROL u'\x95' # 0x35 -> CONTROL u'\x96' # 0x36 -> CONTROL u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL u'\x9a' # 0x3A -> CONTROL u'\x9b' # 0x3B -> CONTROL u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> CONTROL u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE u'\xa2' # 0x4A -> CENT SIGN u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) u'!' # 0x5A -> EXCLAMATION MARK u'$' # 0x5B -> DOLLAR SIGN u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE u'\xa6' # 0x6A -> BROKEN BAR u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT u':' # 0x7A -> COLON u'#' # 0x7B -> NUMBER SIGN u'@' # 0x7C -> COMMERCIAL AT u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE u'\xb8' # 0x9D -> CEDILLA u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE u'\xa4' # 0x9F -> CURRENCY SIGN u'\xb5' # 0xA0 -> MICRO SIGN u'~' # 0xA1 -> TILDE u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK u'\xbf' # 0xAB -> INVERTED QUESTION MARK u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) u'\xae' # 0xAF -> REGISTERED SIGN u'^' # 0xB0 -> CIRCUMFLEX ACCENT u'\xa3' # 0xB1 -> POUND SIGN u'\xa5' # 0xB2 -> YEN SIGN u'\xb7' # 0xB3 -> MIDDLE DOT u'\xa9' # 0xB4 -> COPYRIGHT SIGN u'\xa7' # 0xB5 -> SECTION SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS u'[' # 0xBA -> LEFT SQUARE BRACKET u']' # 0xBB -> RIGHT SQUARE BRACKET u'\xaf' # 0xBC -> MACRON u'\xa8' # 0xBD -> DIAERESIS u'\xb4' # 0xBE -> ACUTE ACCENT u'\xd7' # 0xBF -> MULTIPLICATION SIGN u'{' # 0xC0 -> LEFT CURLY BRACKET u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE u'}' # 0xD0 -> RIGHT CURLY BRACKET u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb9' # 0xDA -> SUPERSCRIPT ONE u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS u'\\' # 0xE0 -> REVERSE SOLIDUS u'\xf7' # 0xE1 -> DIVISION SIGN u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE u'\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1006.py0000644000076500000240000003300012612565546023177 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1006', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO u'\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE u'\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO u'\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE u'\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR u'\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE u'\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX u'\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN u'\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT u'\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE u'\u060c' # 0xAB -> ARABIC COMMA u'\u061b' # 0xAC -> ARABIC SEMICOLON u'\xad' # 0xAD -> SOFT HYPHEN u'\u061f' # 0xAE -> ARABIC QUESTION MARK u'\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM u'\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM u'\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM u'\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM u'\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM u'\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM u'\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM u'\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM u'\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM u'\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM u'\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM u'\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM u'\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM u'\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM u'\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM u'\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM u'\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM u'\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM u'\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM u'\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM u'\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM u'\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM u'\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM u'\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM u'\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN u'\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM u'\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM u'\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM u'\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM u'\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM u'\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM u'\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM u'\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM u'\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM u'\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM u'\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM u'\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM u'\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM u'\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM u'\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM u'\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM u'\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM u'\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM u'\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM u'\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM u'\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM u'\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM u'\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM u'\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM u'\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM u'\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM u'\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM u'\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM u'\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM u'\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM u'\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM u'\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM u'\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM u'\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM u'\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM u'\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM u'\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM u'\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM u'\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM u'\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM u'\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM u'\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM u'\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM u'\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM u'\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM u'\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM u'\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM u'\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM u'\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM u'\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM u'\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM u'\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM u'\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM u'\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM u'\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM u'\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1026.py0000644000076500000240000003207112612565546023210 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1026', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> CONTROL u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> CONTROL u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL u'\x8e' # 0x0A -> CONTROL u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> CONTROL u'\x85' # 0x15 -> CONTROL u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> CONTROL u'\x8f' # 0x1B -> CONTROL u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL u'\x83' # 0x23 -> CONTROL u'\x84' # 0x24 -> CONTROL u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL u'\x8a' # 0x2A -> CONTROL u'\x8b' # 0x2B -> CONTROL u'\x8c' # 0x2C -> CONTROL u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> CONTROL u'\x94' # 0x34 -> CONTROL u'\x95' # 0x35 -> CONTROL u'\x96' # 0x36 -> CONTROL u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL u'\x9a' # 0x3A -> CONTROL u'\x9b' # 0x3B -> CONTROL u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> CONTROL u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'{' # 0x48 -> LEFT CURLY BRACKET u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE u'\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) u'\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE u'\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'[' # 0x68 -> LEFT SQUARE BRACKET u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE u'\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I u':' # 0x7A -> COLON u'\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'}' # 0x8C -> RIGHT CURLY BRACKET u'`' # 0x8D -> GRAVE ACCENT u'\xa6' # 0x8E -> BROKEN BAR u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE u'\xb8' # 0x9D -> CEDILLA u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE u'\xa4' # 0x9F -> CURRENCY SIGN u'\xb5' # 0xA0 -> MICRO SIGN u'\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK u'\xbf' # 0xAB -> INVERTED QUESTION MARK u']' # 0xAC -> RIGHT SQUARE BRACKET u'$' # 0xAD -> DOLLAR SIGN u'@' # 0xAE -> COMMERCIAL AT u'\xae' # 0xAF -> REGISTERED SIGN u'\xa2' # 0xB0 -> CENT SIGN u'\xa3' # 0xB1 -> POUND SIGN u'\xa5' # 0xB2 -> YEN SIGN u'\xb7' # 0xB3 -> MIDDLE DOT u'\xa9' # 0xB4 -> COPYRIGHT SIGN u'\xa7' # 0xB5 -> SECTION SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS u'\xac' # 0xBA -> NOT SIGN u'|' # 0xBB -> VERTICAL LINE u'\xaf' # 0xBC -> MACRON u'\xa8' # 0xBD -> DIAERESIS u'\xb4' # 0xBE -> ACUTE ACCENT u'\xd7' # 0xBF -> MULTIPLICATION SIGN u'\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'~' # 0xCC -> TILDE u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE u'\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb9' # 0xDA -> SUPERSCRIPT ONE u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\\' # 0xDC -> REVERSE SOLIDUS u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS u'\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xf7' # 0xE1 -> DIVISION SIGN u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'#' # 0xEC -> NUMBER SIGN u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'"' # 0xFC -> QUOTATION MARK u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE u'\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1140.py0000644000076500000240000003206112612565546023204 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1140', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> CONTROL u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> CONTROL u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL u'\x8e' # 0x0A -> CONTROL u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> CONTROL u'\x85' # 0x15 -> CONTROL u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> CONTROL u'\x8f' # 0x1B -> CONTROL u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL u'\x83' # 0x23 -> CONTROL u'\x84' # 0x24 -> CONTROL u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL u'\x8a' # 0x2A -> CONTROL u'\x8b' # 0x2B -> CONTROL u'\x8c' # 0x2C -> CONTROL u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> CONTROL u'\x94' # 0x34 -> CONTROL u'\x95' # 0x35 -> CONTROL u'\x96' # 0x36 -> CONTROL u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL u'\x9a' # 0x3A -> CONTROL u'\x9b' # 0x3B -> CONTROL u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> CONTROL u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE u'\xa2' # 0x4A -> CENT SIGN u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) u'!' # 0x5A -> EXCLAMATION MARK u'$' # 0x5B -> DOLLAR SIGN u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE u'\xa6' # 0x6A -> BROKEN BAR u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT u':' # 0x7A -> COLON u'#' # 0x7B -> NUMBER SIGN u'@' # 0x7C -> COMMERCIAL AT u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE u'\xb8' # 0x9D -> CEDILLA u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE u'\u20ac' # 0x9F -> EURO SIGN u'\xb5' # 0xA0 -> MICRO SIGN u'~' # 0xA1 -> TILDE u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK u'\xbf' # 0xAB -> INVERTED QUESTION MARK u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) u'\xae' # 0xAF -> REGISTERED SIGN u'^' # 0xB0 -> CIRCUMFLEX ACCENT u'\xa3' # 0xB1 -> POUND SIGN u'\xa5' # 0xB2 -> YEN SIGN u'\xb7' # 0xB3 -> MIDDLE DOT u'\xa9' # 0xB4 -> COPYRIGHT SIGN u'\xa7' # 0xB5 -> SECTION SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS u'[' # 0xBA -> LEFT SQUARE BRACKET u']' # 0xBB -> RIGHT SQUARE BRACKET u'\xaf' # 0xBC -> MACRON u'\xa8' # 0xBD -> DIAERESIS u'\xb4' # 0xBE -> ACUTE ACCENT u'\xd7' # 0xBF -> MULTIPLICATION SIGN u'{' # 0xC0 -> LEFT CURLY BRACKET u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE u'}' # 0xD0 -> RIGHT CURLY BRACKET u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb9' # 0xDA -> SUPERSCRIPT ONE u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS u'\\' # 0xE0 -> REVERSE SOLIDUS u'\xf7' # 0xE1 -> DIVISION SIGN u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE u'\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1250.py0000644000076500000240000003316612612565546023215 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1250', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\ufffe' # 0x83 -> UNDEFINED u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE u'\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE u'\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON u'\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u02c7' # 0xA1 -> CARON u'\u02d8' # 0xA2 -> BREVE u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE u'\xa4' # 0xA4 -> CURRENCY SIGN u'\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u02db' # 0xB2 -> OGONEK u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT u'\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1251.py0000644000076500000240000003246112612565546023213 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1251', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE u'\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u20ac' # 0x88 -> EURO SIGN u'\u2030' # 0x89 -> PER MILLE SIGN u'\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE u'\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE u'\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE u'\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE u'\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN u'\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE u'\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE u'\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE u'\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U u'\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U u'\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE u'\xa4' # 0xA4 -> CURRENCY SIGN u'\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO u'\u2116' # 0xB9 -> NUMERO SIGN u'\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE u'\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE u'\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE u'\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI u'\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE u'\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE u'\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE u'\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE u'\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE u'\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE u'\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE u'\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U u'\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF u'\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA u'\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE u'\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE u'\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA u'\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA u'\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN u'\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU u'\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E u'\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU u'\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU u'\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1252.py0000644000076500000240000003270712612565546023217 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1252', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE u'\ufffe' # 0x8D -> UNDEFINED u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE u'\ufffe' # 0x9D -> UNDEFINED u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1253.py0000644000076500000240000003204612612565546023214 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1253', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN u'\ufffe' # 0x8A -> UNDEFINED u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x8C -> UNDEFINED u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN u'\ufffe' # 0x9A -> UNDEFINED u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x9C -> UNDEFINED u'\ufffe' # 0x9D -> UNDEFINED u'\ufffe' # 0x9E -> UNDEFINED u'\ufffe' # 0x9F -> UNDEFINED u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS u'\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\ufffe' # 0xAA -> UNDEFINED u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\u2015' # 0xAF -> HORIZONTAL BAR u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\u0384' # 0xB4 -> GREEK TONOS u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO u'\ufffe' # 0xD2 -> UNDEFINED u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU u'\u03bd' # 0xED -> GREEK SMALL LETTER NU u'\u03be' # 0xEE -> GREEK SMALL LETTER XI u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1254.py0000644000076500000240000003267612612565546023226 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1254', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE u'\ufffe' # 0x9D -> UNDEFINED u'\ufffe' # 0x9E -> UNDEFINED u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1255.py0000644000076500000240000003066212612565546023220 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1255', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN u'\ufffe' # 0x8A -> UNDEFINED u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x8C -> UNDEFINED u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN u'\ufffe' # 0x9A -> UNDEFINED u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x9C -> UNDEFINED u'\ufffe' # 0x9D -> UNDEFINED u'\ufffe' # 0x9E -> UNDEFINED u'\ufffe' # 0x9F -> UNDEFINED u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\u20aa' # 0xA4 -> NEW SHEQEL SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xd7' # 0xAA -> MULTIPLICATION SIGN u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xf7' # 0xBA -> DIVISION SIGN u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\u05b0' # 0xC0 -> HEBREW POINT SHEVA u'\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL u'\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH u'\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS u'\u05b4' # 0xC4 -> HEBREW POINT HIRIQ u'\u05b5' # 0xC5 -> HEBREW POINT TSERE u'\u05b6' # 0xC6 -> HEBREW POINT SEGOL u'\u05b7' # 0xC7 -> HEBREW POINT PATAH u'\u05b8' # 0xC8 -> HEBREW POINT QAMATS u'\u05b9' # 0xC9 -> HEBREW POINT HOLAM u'\ufffe' # 0xCA -> UNDEFINED u'\u05bb' # 0xCB -> HEBREW POINT QUBUTS u'\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ u'\u05bd' # 0xCD -> HEBREW POINT METEG u'\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF u'\u05bf' # 0xCF -> HEBREW POINT RAFE u'\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ u'\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT u'\u05c2' # 0xD2 -> HEBREW POINT SIN DOT u'\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ u'\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV u'\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD u'\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD u'\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH u'\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM u'\ufffe' # 0xD9 -> UNDEFINED u'\ufffe' # 0xDA -> UNDEFINED u'\ufffe' # 0xDB -> UNDEFINED u'\ufffe' # 0xDC -> UNDEFINED u'\ufffe' # 0xDD -> UNDEFINED u'\ufffe' # 0xDE -> UNDEFINED u'\ufffe' # 0xDF -> UNDEFINED u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF u'\u05d1' # 0xE1 -> HEBREW LETTER BET u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL u'\u05d3' # 0xE3 -> HEBREW LETTER DALET u'\u05d4' # 0xE4 -> HEBREW LETTER HE u'\u05d5' # 0xE5 -> HEBREW LETTER VAV u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN u'\u05d7' # 0xE7 -> HEBREW LETTER HET u'\u05d8' # 0xE8 -> HEBREW LETTER TET u'\u05d9' # 0xE9 -> HEBREW LETTER YOD u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF u'\u05db' # 0xEB -> HEBREW LETTER KAF u'\u05dc' # 0xEC -> HEBREW LETTER LAMED u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM u'\u05de' # 0xEE -> HEBREW LETTER MEM u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN u'\u05e0' # 0xF0 -> HEBREW LETTER NUN u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE u'\u05e4' # 0xF4 -> HEBREW LETTER PE u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI u'\u05e7' # 0xF7 -> HEBREW LETTER QOF u'\u05e8' # 0xF8 -> HEBREW LETTER RESH u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN u'\u05ea' # 0xFA -> HEBREW LETTER TAV u'\ufffe' # 0xFB -> UNDEFINED u'\ufffe' # 0xFC -> UNDEFINED u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1256.py0000644000076500000240000003141612612565546023217 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1256', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\u067e' # 0x81 -> ARABIC LETTER PEH u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN u'\u0679' # 0x8A -> ARABIC LETTER TTEH u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE u'\u0686' # 0x8D -> ARABIC LETTER TCHEH u'\u0698' # 0x8E -> ARABIC LETTER JEH u'\u0688' # 0x8F -> ARABIC LETTER DDAL u'\u06af' # 0x90 -> ARABIC LETTER GAF u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\u06a9' # 0x98 -> ARABIC LETTER KEHEH u'\u2122' # 0x99 -> TRADE MARK SIGN u'\u0691' # 0x9A -> ARABIC LETTER RREH u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE u'\u200c' # 0x9D -> ZERO WIDTH NON-JOINER u'\u200d' # 0x9E -> ZERO WIDTH JOINER u'\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u060c' # 0xA1 -> ARABIC COMMA u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\u061b' # 0xBA -> ARABIC SEMICOLON u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\u061f' # 0xBF -> ARABIC QUESTION MARK u'\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE u'\u0627' # 0xC7 -> ARABIC LETTER ALEF u'\u0628' # 0xC8 -> ARABIC LETTER BEH u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA u'\u062a' # 0xCA -> ARABIC LETTER TEH u'\u062b' # 0xCB -> ARABIC LETTER THEH u'\u062c' # 0xCC -> ARABIC LETTER JEEM u'\u062d' # 0xCD -> ARABIC LETTER HAH u'\u062e' # 0xCE -> ARABIC LETTER KHAH u'\u062f' # 0xCF -> ARABIC LETTER DAL u'\u0630' # 0xD0 -> ARABIC LETTER THAL u'\u0631' # 0xD1 -> ARABIC LETTER REH u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN u'\u0633' # 0xD3 -> ARABIC LETTER SEEN u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN u'\u0635' # 0xD5 -> ARABIC LETTER SAD u'\u0636' # 0xD6 -> ARABIC LETTER DAD u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u0637' # 0xD8 -> ARABIC LETTER TAH u'\u0638' # 0xD9 -> ARABIC LETTER ZAH u'\u0639' # 0xDA -> ARABIC LETTER AIN u'\u063a' # 0xDB -> ARABIC LETTER GHAIN u'\u0640' # 0xDC -> ARABIC TATWEEL u'\u0641' # 0xDD -> ARABIC LETTER FEH u'\u0642' # 0xDE -> ARABIC LETTER QAF u'\u0643' # 0xDF -> ARABIC LETTER KAF u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\u0644' # 0xE1 -> ARABIC LETTER LAM u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\u0645' # 0xE3 -> ARABIC LETTER MEEM u'\u0646' # 0xE4 -> ARABIC LETTER NOON u'\u0647' # 0xE5 -> ARABIC LETTER HEH u'\u0648' # 0xE6 -> ARABIC LETTER WAW u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA u'\u064a' # 0xED -> ARABIC LETTER YEH u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u064b' # 0xF0 -> ARABIC FATHATAN u'\u064c' # 0xF1 -> ARABIC DAMMATAN u'\u064d' # 0xF2 -> ARABIC KASRATAN u'\u064e' # 0xF3 -> ARABIC FATHA u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u064f' # 0xF5 -> ARABIC DAMMA u'\u0650' # 0xF6 -> ARABIC KASRA u'\xf7' # 0xF7 -> DIVISION SIGN u'\u0651' # 0xF8 -> ARABIC SHADDA u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\u0652' # 0xFA -> ARABIC SUKUN u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1257.py0000644000076500000240000003247612612565546023227 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1257', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\ufffe' # 0x83 -> UNDEFINED u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\ufffe' # 0x88 -> UNDEFINED u'\u2030' # 0x89 -> PER MILLE SIGN u'\ufffe' # 0x8A -> UNDEFINED u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x8C -> UNDEFINED u'\xa8' # 0x8D -> DIAERESIS u'\u02c7' # 0x8E -> CARON u'\xb8' # 0x8F -> CEDILLA u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\u2122' # 0x99 -> TRADE MARK SIGN u'\ufffe' # 0x9A -> UNDEFINED u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\ufffe' # 0x9C -> UNDEFINED u'\xaf' # 0x9D -> MACRON u'\u02db' # 0x9E -> OGONEK u'\ufffe' # 0x9F -> UNDEFINED u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\ufffe' # 0xA1 -> UNDEFINED u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\ufffe' # 0xA5 -> UNDEFINED u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xe6' # 0xBF -> LATIN SMALL LETTER AE u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp1258.py0000644000076500000240000003246412612565546023225 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp1258', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\u2020' # 0x86 -> DAGGER u'\u2021' # 0x87 -> DOUBLE DAGGER u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u2030' # 0x89 -> PER MILLE SIGN u'\ufffe' # 0x8A -> UNDEFINED u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\u02dc' # 0x98 -> SMALL TILDE u'\u2122' # 0x99 -> TRADE MARK SIGN u'\ufffe' # 0x9A -> UNDEFINED u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE u'\ufffe' # 0x9D -> UNDEFINED u'\ufffe' # 0x9E -> UNDEFINED u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u0300' # 0xCC -> COMBINING GRAVE ACCENT u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\u0309' # 0xD2 -> COMBINING HOOK ABOVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN u'\u0303' # 0xDE -> COMBINING TILDE u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u0301' # 0xEC -> COMBINING ACUTE ACCENT u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\u0323' # 0xF2 -> COMBINING DOT BELOW u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN u'\u20ab' # 0xFE -> DONG SIGN u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp424.py0000644000076500000240000003002712612565546023130 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp424', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> SELECT u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> REQUIRED NEW LINE u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> GRAPHIC ESCAPE u'\x8d' # 0x09 -> SUPERSCRIPT u'\x8e' # 0x0A -> REPEAT u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION u'\x85' # 0x15 -> NEW LINE u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> UNIT BACK SPACE u'\x8f' # 0x1B -> CUSTOMER USE ONE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> DIGIT SELECT u'\x81' # 0x21 -> START OF SIGNIFICANCE u'\x82' # 0x22 -> FIELD SEPARATOR u'\x83' # 0x23 -> WORD UNDERSCORE u'\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> SET ATTRIBUTE u'\x89' # 0x29 -> START FIELD EXTENDED u'\x8a' # 0x2A -> SET MODE OR SWITCH u'\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX u'\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> u'\x91' # 0x31 -> u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> INDEX RETURN u'\x94' # 0x34 -> PRESENTATION POSITION u'\x95' # 0x35 -> TRANSPARENT u'\x96' # 0x36 -> NUMERIC BACKSPACE u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> SUBSCRIPT u'\x99' # 0x39 -> INDENT TABULATION u'\x9a' # 0x3A -> REVERSE FORM FEED u'\x9b' # 0x3B -> CUSTOMER USE THREE u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\u05d0' # 0x41 -> HEBREW LETTER ALEF u'\u05d1' # 0x42 -> HEBREW LETTER BET u'\u05d2' # 0x43 -> HEBREW LETTER GIMEL u'\u05d3' # 0x44 -> HEBREW LETTER DALET u'\u05d4' # 0x45 -> HEBREW LETTER HE u'\u05d5' # 0x46 -> HEBREW LETTER VAV u'\u05d6' # 0x47 -> HEBREW LETTER ZAYIN u'\u05d7' # 0x48 -> HEBREW LETTER HET u'\u05d8' # 0x49 -> HEBREW LETTER TET u'\xa2' # 0x4A -> CENT SIGN u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'|' # 0x4F -> VERTICAL LINE u'&' # 0x50 -> AMPERSAND u'\u05d9' # 0x51 -> HEBREW LETTER YOD u'\u05da' # 0x52 -> HEBREW LETTER FINAL KAF u'\u05db' # 0x53 -> HEBREW LETTER KAF u'\u05dc' # 0x54 -> HEBREW LETTER LAMED u'\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM u'\u05de' # 0x56 -> HEBREW LETTER MEM u'\u05df' # 0x57 -> HEBREW LETTER FINAL NUN u'\u05e0' # 0x58 -> HEBREW LETTER NUN u'\u05e1' # 0x59 -> HEBREW LETTER SAMEKH u'!' # 0x5A -> EXCLAMATION MARK u'$' # 0x5B -> DOLLAR SIGN u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'\xac' # 0x5F -> NOT SIGN u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\u05e2' # 0x62 -> HEBREW LETTER AYIN u'\u05e3' # 0x63 -> HEBREW LETTER FINAL PE u'\u05e4' # 0x64 -> HEBREW LETTER PE u'\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI u'\u05e6' # 0x66 -> HEBREW LETTER TSADI u'\u05e7' # 0x67 -> HEBREW LETTER QOF u'\u05e8' # 0x68 -> HEBREW LETTER RESH u'\u05e9' # 0x69 -> HEBREW LETTER SHIN u'\xa6' # 0x6A -> BROKEN BAR u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\ufffe' # 0x70 -> UNDEFINED u'\u05ea' # 0x71 -> HEBREW LETTER TAV u'\ufffe' # 0x72 -> UNDEFINED u'\ufffe' # 0x73 -> UNDEFINED u'\xa0' # 0x74 -> NO-BREAK SPACE u'\ufffe' # 0x75 -> UNDEFINED u'\ufffe' # 0x76 -> UNDEFINED u'\ufffe' # 0x77 -> UNDEFINED u'\u2017' # 0x78 -> DOUBLE LOW LINE u'`' # 0x79 -> GRAVE ACCENT u':' # 0x7A -> COLON u'#' # 0x7B -> NUMBER SIGN u'@' # 0x7C -> COMMERCIAL AT u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'"' # 0x7F -> QUOTATION MARK u'\ufffe' # 0x80 -> UNDEFINED u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\ufffe' # 0x8C -> UNDEFINED u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\ufffe' # 0x9A -> UNDEFINED u'\ufffe' # 0x9B -> UNDEFINED u'\ufffe' # 0x9C -> UNDEFINED u'\xb8' # 0x9D -> CEDILLA u'\ufffe' # 0x9E -> UNDEFINED u'\xa4' # 0x9F -> CURRENCY SIGN u'\xb5' # 0xA0 -> MICRO SIGN u'~' # 0xA1 -> TILDE u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\ufffe' # 0xAA -> UNDEFINED u'\ufffe' # 0xAB -> UNDEFINED u'\ufffe' # 0xAC -> UNDEFINED u'\ufffe' # 0xAD -> UNDEFINED u'\ufffe' # 0xAE -> UNDEFINED u'\xae' # 0xAF -> REGISTERED SIGN u'^' # 0xB0 -> CIRCUMFLEX ACCENT u'\xa3' # 0xB1 -> POUND SIGN u'\xa5' # 0xB2 -> YEN SIGN u'\xb7' # 0xB3 -> MIDDLE DOT u'\xa9' # 0xB4 -> COPYRIGHT SIGN u'\xa7' # 0xB5 -> SECTION SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS u'[' # 0xBA -> LEFT SQUARE BRACKET u']' # 0xBB -> RIGHT SQUARE BRACKET u'\xaf' # 0xBC -> MACRON u'\xa8' # 0xBD -> DIAERESIS u'\xb4' # 0xBE -> ACUTE ACCENT u'\xd7' # 0xBF -> MULTIPLICATION SIGN u'{' # 0xC0 -> LEFT CURLY BRACKET u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\ufffe' # 0xCB -> UNDEFINED u'\ufffe' # 0xCC -> UNDEFINED u'\ufffe' # 0xCD -> UNDEFINED u'\ufffe' # 0xCE -> UNDEFINED u'\ufffe' # 0xCF -> UNDEFINED u'}' # 0xD0 -> RIGHT CURLY BRACKET u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb9' # 0xDA -> SUPERSCRIPT ONE u'\ufffe' # 0xDB -> UNDEFINED u'\ufffe' # 0xDC -> UNDEFINED u'\ufffe' # 0xDD -> UNDEFINED u'\ufffe' # 0xDE -> UNDEFINED u'\ufffe' # 0xDF -> UNDEFINED u'\\' # 0xE0 -> REVERSE SOLIDUS u'\xf7' # 0xE1 -> DIVISION SIGN u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\ufffe' # 0xEB -> UNDEFINED u'\ufffe' # 0xEC -> UNDEFINED u'\ufffe' # 0xED -> UNDEFINED u'\ufffe' # 0xEE -> UNDEFINED u'\ufffe' # 0xEF -> UNDEFINED u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\ufffe' # 0xFB -> UNDEFINED u'\ufffe' # 0xFC -> UNDEFINED u'\ufffe' # 0xFD -> UNDEFINED u'\ufffe' # 0xFE -> UNDEFINED u'\x9f' # 0xFF -> EIGHT ONES ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp437.py0000644000076500000240000010400412612565546023131 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp437 generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp437', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00a2, # CENT SIGN 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00a5, # YEN SIGN 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xa2' # 0x009b -> CENT SIGN u'\xa3' # 0x009c -> POUND SIGN u'\xa5' # 0x009d -> YEN SIGN u'\u20a7' # 0x009e -> PESETA SIGN u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\u2310' # 0x00a9 -> REVERSED NOT SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x009b, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a5: 0x009d, # YEN SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp500.py0000644000076500000240000003210112612565546023116 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp500', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> CONTROL u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> CONTROL u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL u'\x8e' # 0x0A -> CONTROL u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> CONTROL u'\x85' # 0x15 -> CONTROL u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> CONTROL u'\x8f' # 0x1B -> CONTROL u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL u'\x83' # 0x23 -> CONTROL u'\x84' # 0x24 -> CONTROL u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL u'\x8a' # 0x2A -> CONTROL u'\x8b' # 0x2B -> CONTROL u'\x8c' # 0x2C -> CONTROL u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> CONTROL u'\x94' # 0x34 -> CONTROL u'\x95' # 0x35 -> CONTROL u'\x96' # 0x36 -> CONTROL u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL u'\x9a' # 0x3A -> CONTROL u'\x9b' # 0x3B -> CONTROL u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> CONTROL u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\xa0' # 0x41 -> NO-BREAK SPACE u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE u'[' # 0x4A -> LEFT SQUARE BRACKET u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) u']' # 0x5A -> RIGHT SQUARE BRACKET u'$' # 0x5B -> DOLLAR SIGN u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE u'\xa6' # 0x6A -> BROKEN BAR u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE u'`' # 0x79 -> GRAVE ACCENT u':' # 0x7A -> COLON u'#' # 0x7B -> NUMBER SIGN u'@' # 0x7C -> COMMERCIAL AT u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'"' # 0x7F -> QUOTATION MARK u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) u'\xb1' # 0x8F -> PLUS-MINUS SIGN u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE u'\xb8' # 0x9D -> CEDILLA u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE u'\xa4' # 0x9F -> CURRENCY SIGN u'\xb5' # 0xA0 -> MICRO SIGN u'~' # 0xA1 -> TILDE u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK u'\xbf' # 0xAB -> INVERTED QUESTION MARK u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) u'\xae' # 0xAF -> REGISTERED SIGN u'\xa2' # 0xB0 -> CENT SIGN u'\xa3' # 0xB1 -> POUND SIGN u'\xa5' # 0xB2 -> YEN SIGN u'\xb7' # 0xB3 -> MIDDLE DOT u'\xa9' # 0xB4 -> COPYRIGHT SIGN u'\xa7' # 0xB5 -> SECTION SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS u'\xac' # 0xBA -> NOT SIGN u'|' # 0xBB -> VERTICAL LINE u'\xaf' # 0xBC -> MACRON u'\xa8' # 0xBD -> DIAERESIS u'\xb4' # 0xBE -> ACUTE ACCENT u'\xd7' # 0xBF -> MULTIPLICATION SIGN u'{' # 0xC0 -> LEFT CURLY BRACKET u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE u'}' # 0xD0 -> RIGHT CURLY BRACKET u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb9' # 0xDA -> SUPERSCRIPT ONE u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS u'\\' # 0xE0 -> REVERSE SOLIDUS u'\xf7' # 0xE1 -> DIVISION SIGN u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE u'\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp737.py0000644000076500000240000010417112612565546023141 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp737 generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp737', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x0391, # GREEK CAPITAL LETTER ALPHA 0x0081: 0x0392, # GREEK CAPITAL LETTER BETA 0x0082: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x0083: 0x0394, # GREEK CAPITAL LETTER DELTA 0x0084: 0x0395, # GREEK CAPITAL LETTER EPSILON 0x0085: 0x0396, # GREEK CAPITAL LETTER ZETA 0x0086: 0x0397, # GREEK CAPITAL LETTER ETA 0x0087: 0x0398, # GREEK CAPITAL LETTER THETA 0x0088: 0x0399, # GREEK CAPITAL LETTER IOTA 0x0089: 0x039a, # GREEK CAPITAL LETTER KAPPA 0x008a: 0x039b, # GREEK CAPITAL LETTER LAMDA 0x008b: 0x039c, # GREEK CAPITAL LETTER MU 0x008c: 0x039d, # GREEK CAPITAL LETTER NU 0x008d: 0x039e, # GREEK CAPITAL LETTER XI 0x008e: 0x039f, # GREEK CAPITAL LETTER OMICRON 0x008f: 0x03a0, # GREEK CAPITAL LETTER PI 0x0090: 0x03a1, # GREEK CAPITAL LETTER RHO 0x0091: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x0092: 0x03a4, # GREEK CAPITAL LETTER TAU 0x0093: 0x03a5, # GREEK CAPITAL LETTER UPSILON 0x0094: 0x03a6, # GREEK CAPITAL LETTER PHI 0x0095: 0x03a7, # GREEK CAPITAL LETTER CHI 0x0096: 0x03a8, # GREEK CAPITAL LETTER PSI 0x0097: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x0098: 0x03b1, # GREEK SMALL LETTER ALPHA 0x0099: 0x03b2, # GREEK SMALL LETTER BETA 0x009a: 0x03b3, # GREEK SMALL LETTER GAMMA 0x009b: 0x03b4, # GREEK SMALL LETTER DELTA 0x009c: 0x03b5, # GREEK SMALL LETTER EPSILON 0x009d: 0x03b6, # GREEK SMALL LETTER ZETA 0x009e: 0x03b7, # GREEK SMALL LETTER ETA 0x009f: 0x03b8, # GREEK SMALL LETTER THETA 0x00a0: 0x03b9, # GREEK SMALL LETTER IOTA 0x00a1: 0x03ba, # GREEK SMALL LETTER KAPPA 0x00a2: 0x03bb, # GREEK SMALL LETTER LAMDA 0x00a3: 0x03bc, # GREEK SMALL LETTER MU 0x00a4: 0x03bd, # GREEK SMALL LETTER NU 0x00a5: 0x03be, # GREEK SMALL LETTER XI 0x00a6: 0x03bf, # GREEK SMALL LETTER OMICRON 0x00a7: 0x03c0, # GREEK SMALL LETTER PI 0x00a8: 0x03c1, # GREEK SMALL LETTER RHO 0x00a9: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00aa: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA 0x00ab: 0x03c4, # GREEK SMALL LETTER TAU 0x00ac: 0x03c5, # GREEK SMALL LETTER UPSILON 0x00ad: 0x03c6, # GREEK SMALL LETTER PHI 0x00ae: 0x03c7, # GREEK SMALL LETTER CHI 0x00af: 0x03c8, # GREEK SMALL LETTER PSI 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03c9, # GREEK SMALL LETTER OMEGA 0x00e1: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS 0x00e2: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS 0x00e3: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS 0x00e4: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA 0x00e5: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS 0x00e6: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS 0x00e7: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS 0x00e8: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 0x00e9: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS 0x00ea: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS 0x00eb: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS 0x00ec: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS 0x00ed: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS 0x00ee: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS 0x00ef: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS 0x00f0: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA 0x00f5: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\u0391' # 0x0080 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0x0081 -> GREEK CAPITAL LETTER BETA u'\u0393' # 0x0082 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0x0083 -> GREEK CAPITAL LETTER DELTA u'\u0395' # 0x0084 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0x0085 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0x0086 -> GREEK CAPITAL LETTER ETA u'\u0398' # 0x0087 -> GREEK CAPITAL LETTER THETA u'\u0399' # 0x0088 -> GREEK CAPITAL LETTER IOTA u'\u039a' # 0x0089 -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0x008a -> GREEK CAPITAL LETTER LAMDA u'\u039c' # 0x008b -> GREEK CAPITAL LETTER MU u'\u039d' # 0x008c -> GREEK CAPITAL LETTER NU u'\u039e' # 0x008d -> GREEK CAPITAL LETTER XI u'\u039f' # 0x008e -> GREEK CAPITAL LETTER OMICRON u'\u03a0' # 0x008f -> GREEK CAPITAL LETTER PI u'\u03a1' # 0x0090 -> GREEK CAPITAL LETTER RHO u'\u03a3' # 0x0091 -> GREEK CAPITAL LETTER SIGMA u'\u03a4' # 0x0092 -> GREEK CAPITAL LETTER TAU u'\u03a5' # 0x0093 -> GREEK CAPITAL LETTER UPSILON u'\u03a6' # 0x0094 -> GREEK CAPITAL LETTER PHI u'\u03a7' # 0x0095 -> GREEK CAPITAL LETTER CHI u'\u03a8' # 0x0096 -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0x0097 -> GREEK CAPITAL LETTER OMEGA u'\u03b1' # 0x0098 -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0x0099 -> GREEK SMALL LETTER BETA u'\u03b3' # 0x009a -> GREEK SMALL LETTER GAMMA u'\u03b4' # 0x009b -> GREEK SMALL LETTER DELTA u'\u03b5' # 0x009c -> GREEK SMALL LETTER EPSILON u'\u03b6' # 0x009d -> GREEK SMALL LETTER ZETA u'\u03b7' # 0x009e -> GREEK SMALL LETTER ETA u'\u03b8' # 0x009f -> GREEK SMALL LETTER THETA u'\u03b9' # 0x00a0 -> GREEK SMALL LETTER IOTA u'\u03ba' # 0x00a1 -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0x00a2 -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0x00a3 -> GREEK SMALL LETTER MU u'\u03bd' # 0x00a4 -> GREEK SMALL LETTER NU u'\u03be' # 0x00a5 -> GREEK SMALL LETTER XI u'\u03bf' # 0x00a6 -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0x00a7 -> GREEK SMALL LETTER PI u'\u03c1' # 0x00a8 -> GREEK SMALL LETTER RHO u'\u03c3' # 0x00a9 -> GREEK SMALL LETTER SIGMA u'\u03c2' # 0x00aa -> GREEK SMALL LETTER FINAL SIGMA u'\u03c4' # 0x00ab -> GREEK SMALL LETTER TAU u'\u03c5' # 0x00ac -> GREEK SMALL LETTER UPSILON u'\u03c6' # 0x00ad -> GREEK SMALL LETTER PHI u'\u03c7' # 0x00ae -> GREEK SMALL LETTER CHI u'\u03c8' # 0x00af -> GREEK SMALL LETTER PSI u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03c9' # 0x00e0 -> GREEK SMALL LETTER OMEGA u'\u03ac' # 0x00e1 -> GREEK SMALL LETTER ALPHA WITH TONOS u'\u03ad' # 0x00e2 -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0x00e3 -> GREEK SMALL LETTER ETA WITH TONOS u'\u03ca' # 0x00e4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u03af' # 0x00e5 -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03cc' # 0x00e6 -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u03cd' # 0x00e7 -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u03cb' # 0x00e8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u03ce' # 0x00e9 -> GREEK SMALL LETTER OMEGA WITH TONOS u'\u0386' # 0x00ea -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\u0388' # 0x00eb -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u0389' # 0x00ec -> GREEK CAPITAL LETTER ETA WITH TONOS u'\u038a' # 0x00ed -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\u038c' # 0x00ee -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\u038e' # 0x00ef -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u038f' # 0x00f0 -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u03aa' # 0x00f4 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u03ab' # 0x00f5 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b7: 0x00fa, # MIDDLE DOT 0x00f7: 0x00f6, # DIVISION SIGN 0x0386: 0x00ea, # GREEK CAPITAL LETTER ALPHA WITH TONOS 0x0388: 0x00eb, # GREEK CAPITAL LETTER EPSILON WITH TONOS 0x0389: 0x00ec, # GREEK CAPITAL LETTER ETA WITH TONOS 0x038a: 0x00ed, # GREEK CAPITAL LETTER IOTA WITH TONOS 0x038c: 0x00ee, # GREEK CAPITAL LETTER OMICRON WITH TONOS 0x038e: 0x00ef, # GREEK CAPITAL LETTER UPSILON WITH TONOS 0x038f: 0x00f0, # GREEK CAPITAL LETTER OMEGA WITH TONOS 0x0391: 0x0080, # GREEK CAPITAL LETTER ALPHA 0x0392: 0x0081, # GREEK CAPITAL LETTER BETA 0x0393: 0x0082, # GREEK CAPITAL LETTER GAMMA 0x0394: 0x0083, # GREEK CAPITAL LETTER DELTA 0x0395: 0x0084, # GREEK CAPITAL LETTER EPSILON 0x0396: 0x0085, # GREEK CAPITAL LETTER ZETA 0x0397: 0x0086, # GREEK CAPITAL LETTER ETA 0x0398: 0x0087, # GREEK CAPITAL LETTER THETA 0x0399: 0x0088, # GREEK CAPITAL LETTER IOTA 0x039a: 0x0089, # GREEK CAPITAL LETTER KAPPA 0x039b: 0x008a, # GREEK CAPITAL LETTER LAMDA 0x039c: 0x008b, # GREEK CAPITAL LETTER MU 0x039d: 0x008c, # GREEK CAPITAL LETTER NU 0x039e: 0x008d, # GREEK CAPITAL LETTER XI 0x039f: 0x008e, # GREEK CAPITAL LETTER OMICRON 0x03a0: 0x008f, # GREEK CAPITAL LETTER PI 0x03a1: 0x0090, # GREEK CAPITAL LETTER RHO 0x03a3: 0x0091, # GREEK CAPITAL LETTER SIGMA 0x03a4: 0x0092, # GREEK CAPITAL LETTER TAU 0x03a5: 0x0093, # GREEK CAPITAL LETTER UPSILON 0x03a6: 0x0094, # GREEK CAPITAL LETTER PHI 0x03a7: 0x0095, # GREEK CAPITAL LETTER CHI 0x03a8: 0x0096, # GREEK CAPITAL LETTER PSI 0x03a9: 0x0097, # GREEK CAPITAL LETTER OMEGA 0x03aa: 0x00f4, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA 0x03ab: 0x00f5, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA 0x03ac: 0x00e1, # GREEK SMALL LETTER ALPHA WITH TONOS 0x03ad: 0x00e2, # GREEK SMALL LETTER EPSILON WITH TONOS 0x03ae: 0x00e3, # GREEK SMALL LETTER ETA WITH TONOS 0x03af: 0x00e5, # GREEK SMALL LETTER IOTA WITH TONOS 0x03b1: 0x0098, # GREEK SMALL LETTER ALPHA 0x03b2: 0x0099, # GREEK SMALL LETTER BETA 0x03b3: 0x009a, # GREEK SMALL LETTER GAMMA 0x03b4: 0x009b, # GREEK SMALL LETTER DELTA 0x03b5: 0x009c, # GREEK SMALL LETTER EPSILON 0x03b6: 0x009d, # GREEK SMALL LETTER ZETA 0x03b7: 0x009e, # GREEK SMALL LETTER ETA 0x03b8: 0x009f, # GREEK SMALL LETTER THETA 0x03b9: 0x00a0, # GREEK SMALL LETTER IOTA 0x03ba: 0x00a1, # GREEK SMALL LETTER KAPPA 0x03bb: 0x00a2, # GREEK SMALL LETTER LAMDA 0x03bc: 0x00a3, # GREEK SMALL LETTER MU 0x03bd: 0x00a4, # GREEK SMALL LETTER NU 0x03be: 0x00a5, # GREEK SMALL LETTER XI 0x03bf: 0x00a6, # GREEK SMALL LETTER OMICRON 0x03c0: 0x00a7, # GREEK SMALL LETTER PI 0x03c1: 0x00a8, # GREEK SMALL LETTER RHO 0x03c2: 0x00aa, # GREEK SMALL LETTER FINAL SIGMA 0x03c3: 0x00a9, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00ab, # GREEK SMALL LETTER TAU 0x03c5: 0x00ac, # GREEK SMALL LETTER UPSILON 0x03c6: 0x00ad, # GREEK SMALL LETTER PHI 0x03c7: 0x00ae, # GREEK SMALL LETTER CHI 0x03c8: 0x00af, # GREEK SMALL LETTER PSI 0x03c9: 0x00e0, # GREEK SMALL LETTER OMEGA 0x03ca: 0x00e4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA 0x03cb: 0x00e8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 0x03cc: 0x00e6, # GREEK SMALL LETTER OMICRON WITH TONOS 0x03cd: 0x00e7, # GREEK SMALL LETTER UPSILON WITH TONOS 0x03ce: 0x00e9, # GREEK SMALL LETTER OMEGA WITH TONOS 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp775.py0000644000076500000240000010365412612565546023150 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp775', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x0101, # LATIN SMALL LETTER A WITH MACRON 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x0107, # LATIN SMALL LETTER C WITH ACUTE 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE 0x0089: 0x0113, # LATIN SMALL LETTER E WITH MACRON 0x008a: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA 0x008b: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA 0x008c: 0x012b, # LATIN SMALL LETTER I WITH MACRON 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x014d, # LATIN SMALL LETTER O WITH MACRON 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA 0x0096: 0x00a2, # CENT SIGN 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x00d7, # MULTIPLICATION SIGN 0x009f: 0x00a4, # CURRENCY SIGN 0x00a0: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON 0x00a1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x00a4: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE 0x00a5: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE 0x00a6: 0x201d, # RIGHT DOUBLE QUOTATION MARK 0x00a7: 0x00a6, # BROKEN BAR 0x00a8: 0x00a9, # COPYRIGHT SIGN 0x00a9: 0x00ae, # REGISTERED SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK 0x00b6: 0x010c, # LATIN CAPITAL LETTER C WITH CARON 0x00b7: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK 0x00b8: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK 0x00be: 0x0160, # LATIN CAPITAL LETTER S WITH CARON 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK 0x00c7: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON 0x00d0: 0x0105, # LATIN SMALL LETTER A WITH OGONEK 0x00d1: 0x010d, # LATIN SMALL LETTER C WITH CARON 0x00d2: 0x0119, # LATIN SMALL LETTER E WITH OGONEK 0x00d3: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE 0x00d4: 0x012f, # LATIN SMALL LETTER I WITH OGONEK 0x00d5: 0x0161, # LATIN SMALL LETTER S WITH CARON 0x00d6: 0x0173, # LATIN SMALL LETTER U WITH OGONEK 0x00d7: 0x016b, # LATIN SMALL LETTER U WITH MACRON 0x00d8: 0x017e, # LATIN SMALL LETTER Z WITH CARON 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e2: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x0144, # LATIN SMALL LETTER N WITH ACUTE 0x00e8: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA 0x00e9: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA 0x00ea: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA 0x00eb: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA 0x00ec: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA 0x00ed: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON 0x00ee: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA 0x00ef: 0x2019, # RIGHT SINGLE QUOTATION MARK 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x201c, # LEFT DOUBLE QUOTATION MARK 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00f4: 0x00b6, # PILCROW SIGN 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x201e, # DOUBLE LOW-9 QUOTATION MARK 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x00b9, # SUPERSCRIPT ONE 0x00fc: 0x00b3, # SUPERSCRIPT THREE 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\u0106' # 0x0080 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\u0101' # 0x0083 -> LATIN SMALL LETTER A WITH MACRON u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u0123' # 0x0085 -> LATIN SMALL LETTER G WITH CEDILLA u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\u0107' # 0x0087 -> LATIN SMALL LETTER C WITH ACUTE u'\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE u'\u0113' # 0x0089 -> LATIN SMALL LETTER E WITH MACRON u'\u0156' # 0x008a -> LATIN CAPITAL LETTER R WITH CEDILLA u'\u0157' # 0x008b -> LATIN SMALL LETTER R WITH CEDILLA u'\u012b' # 0x008c -> LATIN SMALL LETTER I WITH MACRON u'\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\u014d' # 0x0093 -> LATIN SMALL LETTER O WITH MACRON u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\u0122' # 0x0095 -> LATIN CAPITAL LETTER G WITH CEDILLA u'\xa2' # 0x0096 -> CENT SIGN u'\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE u'\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE u'\xa3' # 0x009c -> POUND SIGN u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE u'\xd7' # 0x009e -> MULTIPLICATION SIGN u'\xa4' # 0x009f -> CURRENCY SIGN u'\u0100' # 0x00a0 -> LATIN CAPITAL LETTER A WITH MACRON u'\u012a' # 0x00a1 -> LATIN CAPITAL LETTER I WITH MACRON u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\u017b' # 0x00a3 -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\u017c' # 0x00a4 -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u017a' # 0x00a5 -> LATIN SMALL LETTER Z WITH ACUTE u'\u201d' # 0x00a6 -> RIGHT DOUBLE QUOTATION MARK u'\xa6' # 0x00a7 -> BROKEN BAR u'\xa9' # 0x00a8 -> COPYRIGHT SIGN u'\xae' # 0x00a9 -> REGISTERED SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\u0141' # 0x00ad -> LATIN CAPITAL LETTER L WITH STROKE u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u0104' # 0x00b5 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u010c' # 0x00b6 -> LATIN CAPITAL LETTER C WITH CARON u'\u0118' # 0x00b7 -> LATIN CAPITAL LETTER E WITH OGONEK u'\u0116' # 0x00b8 -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u012e' # 0x00bd -> LATIN CAPITAL LETTER I WITH OGONEK u'\u0160' # 0x00be -> LATIN CAPITAL LETTER S WITH CARON u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u0172' # 0x00c6 -> LATIN CAPITAL LETTER U WITH OGONEK u'\u016a' # 0x00c7 -> LATIN CAPITAL LETTER U WITH MACRON u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u017d' # 0x00cf -> LATIN CAPITAL LETTER Z WITH CARON u'\u0105' # 0x00d0 -> LATIN SMALL LETTER A WITH OGONEK u'\u010d' # 0x00d1 -> LATIN SMALL LETTER C WITH CARON u'\u0119' # 0x00d2 -> LATIN SMALL LETTER E WITH OGONEK u'\u0117' # 0x00d3 -> LATIN SMALL LETTER E WITH DOT ABOVE u'\u012f' # 0x00d4 -> LATIN SMALL LETTER I WITH OGONEK u'\u0161' # 0x00d5 -> LATIN SMALL LETTER S WITH CARON u'\u0173' # 0x00d6 -> LATIN SMALL LETTER U WITH OGONEK u'\u016b' # 0x00d7 -> LATIN SMALL LETTER U WITH MACRON u'\u017e' # 0x00d8 -> LATIN SMALL LETTER Z WITH CARON u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN) u'\u014c' # 0x00e2 -> LATIN CAPITAL LETTER O WITH MACRON u'\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xb5' # 0x00e6 -> MICRO SIGN u'\u0144' # 0x00e7 -> LATIN SMALL LETTER N WITH ACUTE u'\u0136' # 0x00e8 -> LATIN CAPITAL LETTER K WITH CEDILLA u'\u0137' # 0x00e9 -> LATIN SMALL LETTER K WITH CEDILLA u'\u013b' # 0x00ea -> LATIN CAPITAL LETTER L WITH CEDILLA u'\u013c' # 0x00eb -> LATIN SMALL LETTER L WITH CEDILLA u'\u0146' # 0x00ec -> LATIN SMALL LETTER N WITH CEDILLA u'\u0112' # 0x00ed -> LATIN CAPITAL LETTER E WITH MACRON u'\u0145' # 0x00ee -> LATIN CAPITAL LETTER N WITH CEDILLA u'\u2019' # 0x00ef -> RIGHT SINGLE QUOTATION MARK u'\xad' # 0x00f0 -> SOFT HYPHEN u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u201c' # 0x00f2 -> LEFT DOUBLE QUOTATION MARK u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS u'\xb6' # 0x00f4 -> PILCROW SIGN u'\xa7' # 0x00f5 -> SECTION SIGN u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u201e' # 0x00f7 -> DOUBLE LOW-9 QUOTATION MARK u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\xb9' # 0x00fb -> SUPERSCRIPT ONE u'\xb3' # 0x00fc -> SUPERSCRIPT THREE u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a2: 0x0096, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x009f, # CURRENCY SIGN 0x00a6: 0x00a7, # BROKEN BAR 0x00a7: 0x00f5, # SECTION SIGN 0x00a9: 0x00a8, # COPYRIGHT SIGN 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00ae: 0x00a9, # REGISTERED SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b3: 0x00fc, # SUPERSCRIPT THREE 0x00b5: 0x00e6, # MICRO SIGN 0x00b6: 0x00f4, # PILCROW SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00b9: 0x00fb, # SUPERSCRIPT ONE 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d7: 0x009e, # MULTIPLICATION SIGN 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x0100: 0x00a0, # LATIN CAPITAL LETTER A WITH MACRON 0x0101: 0x0083, # LATIN SMALL LETTER A WITH MACRON 0x0104: 0x00b5, # LATIN CAPITAL LETTER A WITH OGONEK 0x0105: 0x00d0, # LATIN SMALL LETTER A WITH OGONEK 0x0106: 0x0080, # LATIN CAPITAL LETTER C WITH ACUTE 0x0107: 0x0087, # LATIN SMALL LETTER C WITH ACUTE 0x010c: 0x00b6, # LATIN CAPITAL LETTER C WITH CARON 0x010d: 0x00d1, # LATIN SMALL LETTER C WITH CARON 0x0112: 0x00ed, # LATIN CAPITAL LETTER E WITH MACRON 0x0113: 0x0089, # LATIN SMALL LETTER E WITH MACRON 0x0116: 0x00b8, # LATIN CAPITAL LETTER E WITH DOT ABOVE 0x0117: 0x00d3, # LATIN SMALL LETTER E WITH DOT ABOVE 0x0118: 0x00b7, # LATIN CAPITAL LETTER E WITH OGONEK 0x0119: 0x00d2, # LATIN SMALL LETTER E WITH OGONEK 0x0122: 0x0095, # LATIN CAPITAL LETTER G WITH CEDILLA 0x0123: 0x0085, # LATIN SMALL LETTER G WITH CEDILLA 0x012a: 0x00a1, # LATIN CAPITAL LETTER I WITH MACRON 0x012b: 0x008c, # LATIN SMALL LETTER I WITH MACRON 0x012e: 0x00bd, # LATIN CAPITAL LETTER I WITH OGONEK 0x012f: 0x00d4, # LATIN SMALL LETTER I WITH OGONEK 0x0136: 0x00e8, # LATIN CAPITAL LETTER K WITH CEDILLA 0x0137: 0x00e9, # LATIN SMALL LETTER K WITH CEDILLA 0x013b: 0x00ea, # LATIN CAPITAL LETTER L WITH CEDILLA 0x013c: 0x00eb, # LATIN SMALL LETTER L WITH CEDILLA 0x0141: 0x00ad, # LATIN CAPITAL LETTER L WITH STROKE 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE 0x0144: 0x00e7, # LATIN SMALL LETTER N WITH ACUTE 0x0145: 0x00ee, # LATIN CAPITAL LETTER N WITH CEDILLA 0x0146: 0x00ec, # LATIN SMALL LETTER N WITH CEDILLA 0x014c: 0x00e2, # LATIN CAPITAL LETTER O WITH MACRON 0x014d: 0x0093, # LATIN SMALL LETTER O WITH MACRON 0x0156: 0x008a, # LATIN CAPITAL LETTER R WITH CEDILLA 0x0157: 0x008b, # LATIN SMALL LETTER R WITH CEDILLA 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE 0x0160: 0x00be, # LATIN CAPITAL LETTER S WITH CARON 0x0161: 0x00d5, # LATIN SMALL LETTER S WITH CARON 0x016a: 0x00c7, # LATIN CAPITAL LETTER U WITH MACRON 0x016b: 0x00d7, # LATIN SMALL LETTER U WITH MACRON 0x0172: 0x00c6, # LATIN CAPITAL LETTER U WITH OGONEK 0x0173: 0x00d6, # LATIN SMALL LETTER U WITH OGONEK 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE 0x017a: 0x00a5, # LATIN SMALL LETTER Z WITH ACUTE 0x017b: 0x00a3, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x017c: 0x00a4, # LATIN SMALL LETTER Z WITH DOT ABOVE 0x017d: 0x00cf, # LATIN CAPITAL LETTER Z WITH CARON 0x017e: 0x00d8, # LATIN SMALL LETTER Z WITH CARON 0x2019: 0x00ef, # RIGHT SINGLE QUOTATION MARK 0x201c: 0x00f2, # LEFT DOUBLE QUOTATION MARK 0x201d: 0x00a6, # RIGHT DOUBLE QUOTATION MARK 0x201e: 0x00f7, # DOUBLE LOW-9 QUOTATION MARK 0x2219: 0x00f9, # BULLET OPERATOR 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp850.py0000644000076500000240000010307112612565546023133 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP850.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp850', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x00d7, # MULTIPLICATION SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x00ae, # REGISTERED SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x00b8: 0x00a9, # COPYRIGHT SIGN 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x00a2, # CENT SIGN 0x00be: 0x00a5, # YEN SIGN 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x00a4, # CURRENCY SIGN 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x00a6, # BROKEN BAR 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00ee: 0x00af, # MACRON 0x00ef: 0x00b4, # ACUTE ACCENT 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2017, # DOUBLE LOW LINE 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00f4: 0x00b6, # PILCROW SIGN 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x00b8, # CEDILLA 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x00a8, # DIAERESIS 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x00b9, # SUPERSCRIPT ONE 0x00fc: 0x00b3, # SUPERSCRIPT THREE 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE u'\xa3' # 0x009c -> POUND SIGN u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE u'\xd7' # 0x009e -> MULTIPLICATION SIGN u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\xae' # 0x00a9 -> REGISTERED SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xa9' # 0x00b8 -> COPYRIGHT SIGN u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\xa2' # 0x00bd -> CENT SIGN u'\xa5' # 0x00be -> YEN SIGN u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE u'\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa4' # 0x00cf -> CURRENCY SIGN u'\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH u'\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH u'\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE u'\u0131' # 0x00d5 -> LATIN SMALL LETTER DOTLESS I u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\xa6' # 0x00dd -> BROKEN BAR u'\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xb5' # 0x00e6 -> MICRO SIGN u'\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN u'\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE u'\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE u'\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xaf' # 0x00ee -> MACRON u'\xb4' # 0x00ef -> ACUTE ACCENT u'\xad' # 0x00f0 -> SOFT HYPHEN u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2017' # 0x00f2 -> DOUBLE LOW LINE u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS u'\xb6' # 0x00f4 -> PILCROW SIGN u'\xa7' # 0x00f5 -> SECTION SIGN u'\xf7' # 0x00f6 -> DIVISION SIGN u'\xb8' # 0x00f7 -> CEDILLA u'\xb0' # 0x00f8 -> DEGREE SIGN u'\xa8' # 0x00f9 -> DIAERESIS u'\xb7' # 0x00fa -> MIDDLE DOT u'\xb9' # 0x00fb -> SUPERSCRIPT ONE u'\xb3' # 0x00fc -> SUPERSCRIPT THREE u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x00bd, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x00cf, # CURRENCY SIGN 0x00a5: 0x00be, # YEN SIGN 0x00a6: 0x00dd, # BROKEN BAR 0x00a7: 0x00f5, # SECTION SIGN 0x00a8: 0x00f9, # DIAERESIS 0x00a9: 0x00b8, # COPYRIGHT SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00ae: 0x00a9, # REGISTERED SIGN 0x00af: 0x00ee, # MACRON 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b3: 0x00fc, # SUPERSCRIPT THREE 0x00b4: 0x00ef, # ACUTE ACCENT 0x00b5: 0x00e6, # MICRO SIGN 0x00b6: 0x00f4, # PILCROW SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00b8: 0x00f7, # CEDILLA 0x00b9: 0x00fb, # SUPERSCRIPT ONE 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d7: 0x009e, # MULTIPLICATION SIGN 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0131: 0x00d5, # LATIN SMALL LETTER DOTLESS I 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x2017: 0x00f2, # DOUBLE LOW LINE 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp852.py0000644000076500000240000010467212612565546023145 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP852.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp852', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE 0x0086: 0x0107, # LATIN SMALL LETTER C WITH ACUTE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE 0x008b: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE 0x0092: 0x013a, # LATIN SMALL LETTER L WITH ACUTE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x013d, # LATIN CAPITAL LETTER L WITH CARON 0x0096: 0x013e, # LATIN SMALL LETTER L WITH CARON 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x0164, # LATIN CAPITAL LETTER T WITH CARON 0x009c: 0x0165, # LATIN SMALL LETTER T WITH CARON 0x009d: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE 0x009e: 0x00d7, # MULTIPLICATION SIGN 0x009f: 0x010d, # LATIN SMALL LETTER C WITH CARON 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK 0x00a5: 0x0105, # LATIN SMALL LETTER A WITH OGONEK 0x00a6: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON 0x00a7: 0x017e, # LATIN SMALL LETTER Z WITH CARON 0x00a8: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK 0x00a9: 0x0119, # LATIN SMALL LETTER E WITH OGONEK 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE 0x00ac: 0x010c, # LATIN CAPITAL LETTER C WITH CARON 0x00ad: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00b7: 0x011a, # LATIN CAPITAL LETTER E WITH CARON 0x00b8: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x00be: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x0102, # LATIN CAPITAL LETTER A WITH BREVE 0x00c7: 0x0103, # LATIN SMALL LETTER A WITH BREVE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x00a4, # CURRENCY SIGN 0x00d0: 0x0111, # LATIN SMALL LETTER D WITH STROKE 0x00d1: 0x0110, # LATIN CAPITAL LETTER D WITH STROKE 0x00d2: 0x010e, # LATIN CAPITAL LETTER D WITH CARON 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00d4: 0x010f, # LATIN SMALL LETTER D WITH CARON 0x00d5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00d8: 0x011b, # LATIN SMALL LETTER E WITH CARON 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x0162, # LATIN CAPITAL LETTER T WITH CEDILLA 0x00de: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE 0x00e4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE 0x00e5: 0x0148, # LATIN SMALL LETTER N WITH CARON 0x00e6: 0x0160, # LATIN CAPITAL LETTER S WITH CARON 0x00e7: 0x0161, # LATIN SMALL LETTER S WITH CARON 0x00e8: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00ea: 0x0155, # LATIN SMALL LETTER R WITH ACUTE 0x00eb: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00ee: 0x0163, # LATIN SMALL LETTER T WITH CEDILLA 0x00ef: 0x00b4, # ACUTE ACCENT 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x02dd, # DOUBLE ACUTE ACCENT 0x00f2: 0x02db, # OGONEK 0x00f3: 0x02c7, # CARON 0x00f4: 0x02d8, # BREVE 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x00b8, # CEDILLA 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x00a8, # DIAERESIS 0x00fa: 0x02d9, # DOT ABOVE 0x00fb: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE 0x00fc: 0x0158, # LATIN CAPITAL LETTER R WITH CARON 0x00fd: 0x0159, # LATIN SMALL LETTER R WITH CARON 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u016f' # 0x0085 -> LATIN SMALL LETTER U WITH RING ABOVE u'\u0107' # 0x0086 -> LATIN SMALL LETTER C WITH ACUTE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\u0150' # 0x008a -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE u'\u0151' # 0x008b -> LATIN SMALL LETTER O WITH DOUBLE ACUTE u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0106' # 0x008f -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0139' # 0x0091 -> LATIN CAPITAL LETTER L WITH ACUTE u'\u013a' # 0x0092 -> LATIN SMALL LETTER L WITH ACUTE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\u013d' # 0x0095 -> LATIN CAPITAL LETTER L WITH CARON u'\u013e' # 0x0096 -> LATIN SMALL LETTER L WITH CARON u'\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE u'\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0164' # 0x009b -> LATIN CAPITAL LETTER T WITH CARON u'\u0165' # 0x009c -> LATIN SMALL LETTER T WITH CARON u'\u0141' # 0x009d -> LATIN CAPITAL LETTER L WITH STROKE u'\xd7' # 0x009e -> MULTIPLICATION SIGN u'\u010d' # 0x009f -> LATIN SMALL LETTER C WITH CARON u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\u0104' # 0x00a4 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u0105' # 0x00a5 -> LATIN SMALL LETTER A WITH OGONEK u'\u017d' # 0x00a6 -> LATIN CAPITAL LETTER Z WITH CARON u'\u017e' # 0x00a7 -> LATIN SMALL LETTER Z WITH CARON u'\u0118' # 0x00a8 -> LATIN CAPITAL LETTER E WITH OGONEK u'\u0119' # 0x00a9 -> LATIN SMALL LETTER E WITH OGONEK u'\xac' # 0x00aa -> NOT SIGN u'\u017a' # 0x00ab -> LATIN SMALL LETTER Z WITH ACUTE u'\u010c' # 0x00ac -> LATIN CAPITAL LETTER C WITH CARON u'\u015f' # 0x00ad -> LATIN SMALL LETTER S WITH CEDILLA u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u011a' # 0x00b7 -> LATIN CAPITAL LETTER E WITH CARON u'\u015e' # 0x00b8 -> LATIN CAPITAL LETTER S WITH CEDILLA u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u017b' # 0x00bd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\u017c' # 0x00be -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u0102' # 0x00c6 -> LATIN CAPITAL LETTER A WITH BREVE u'\u0103' # 0x00c7 -> LATIN SMALL LETTER A WITH BREVE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa4' # 0x00cf -> CURRENCY SIGN u'\u0111' # 0x00d0 -> LATIN SMALL LETTER D WITH STROKE u'\u0110' # 0x00d1 -> LATIN CAPITAL LETTER D WITH STROKE u'\u010e' # 0x00d2 -> LATIN CAPITAL LETTER D WITH CARON u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u010f' # 0x00d4 -> LATIN SMALL LETTER D WITH CARON u'\u0147' # 0x00d5 -> LATIN CAPITAL LETTER N WITH CARON u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\u011b' # 0x00d8 -> LATIN SMALL LETTER E WITH CARON u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u0162' # 0x00dd -> LATIN CAPITAL LETTER T WITH CEDILLA u'\u016e' # 0x00de -> LATIN CAPITAL LETTER U WITH RING ABOVE u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE u'\u0144' # 0x00e4 -> LATIN SMALL LETTER N WITH ACUTE u'\u0148' # 0x00e5 -> LATIN SMALL LETTER N WITH CARON u'\u0160' # 0x00e6 -> LATIN CAPITAL LETTER S WITH CARON u'\u0161' # 0x00e7 -> LATIN SMALL LETTER S WITH CARON u'\u0154' # 0x00e8 -> LATIN CAPITAL LETTER R WITH ACUTE u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE u'\u0155' # 0x00ea -> LATIN SMALL LETTER R WITH ACUTE u'\u0170' # 0x00eb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE u'\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE u'\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE u'\u0163' # 0x00ee -> LATIN SMALL LETTER T WITH CEDILLA u'\xb4' # 0x00ef -> ACUTE ACCENT u'\xad' # 0x00f0 -> SOFT HYPHEN u'\u02dd' # 0x00f1 -> DOUBLE ACUTE ACCENT u'\u02db' # 0x00f2 -> OGONEK u'\u02c7' # 0x00f3 -> CARON u'\u02d8' # 0x00f4 -> BREVE u'\xa7' # 0x00f5 -> SECTION SIGN u'\xf7' # 0x00f6 -> DIVISION SIGN u'\xb8' # 0x00f7 -> CEDILLA u'\xb0' # 0x00f8 -> DEGREE SIGN u'\xa8' # 0x00f9 -> DIAERESIS u'\u02d9' # 0x00fa -> DOT ABOVE u'\u0171' # 0x00fb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE u'\u0158' # 0x00fc -> LATIN CAPITAL LETTER R WITH CARON u'\u0159' # 0x00fd -> LATIN SMALL LETTER R WITH CARON u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a4: 0x00cf, # CURRENCY SIGN 0x00a7: 0x00f5, # SECTION SIGN 0x00a8: 0x00f9, # DIAERESIS 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b4: 0x00ef, # ACUTE ACCENT 0x00b8: 0x00f7, # CEDILLA 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d7: 0x009e, # MULTIPLICATION SIGN 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE 0x0102: 0x00c6, # LATIN CAPITAL LETTER A WITH BREVE 0x0103: 0x00c7, # LATIN SMALL LETTER A WITH BREVE 0x0104: 0x00a4, # LATIN CAPITAL LETTER A WITH OGONEK 0x0105: 0x00a5, # LATIN SMALL LETTER A WITH OGONEK 0x0106: 0x008f, # LATIN CAPITAL LETTER C WITH ACUTE 0x0107: 0x0086, # LATIN SMALL LETTER C WITH ACUTE 0x010c: 0x00ac, # LATIN CAPITAL LETTER C WITH CARON 0x010d: 0x009f, # LATIN SMALL LETTER C WITH CARON 0x010e: 0x00d2, # LATIN CAPITAL LETTER D WITH CARON 0x010f: 0x00d4, # LATIN SMALL LETTER D WITH CARON 0x0110: 0x00d1, # LATIN CAPITAL LETTER D WITH STROKE 0x0111: 0x00d0, # LATIN SMALL LETTER D WITH STROKE 0x0118: 0x00a8, # LATIN CAPITAL LETTER E WITH OGONEK 0x0119: 0x00a9, # LATIN SMALL LETTER E WITH OGONEK 0x011a: 0x00b7, # LATIN CAPITAL LETTER E WITH CARON 0x011b: 0x00d8, # LATIN SMALL LETTER E WITH CARON 0x0139: 0x0091, # LATIN CAPITAL LETTER L WITH ACUTE 0x013a: 0x0092, # LATIN SMALL LETTER L WITH ACUTE 0x013d: 0x0095, # LATIN CAPITAL LETTER L WITH CARON 0x013e: 0x0096, # LATIN SMALL LETTER L WITH CARON 0x0141: 0x009d, # LATIN CAPITAL LETTER L WITH STROKE 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE 0x0144: 0x00e4, # LATIN SMALL LETTER N WITH ACUTE 0x0147: 0x00d5, # LATIN CAPITAL LETTER N WITH CARON 0x0148: 0x00e5, # LATIN SMALL LETTER N WITH CARON 0x0150: 0x008a, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE 0x0151: 0x008b, # LATIN SMALL LETTER O WITH DOUBLE ACUTE 0x0154: 0x00e8, # LATIN CAPITAL LETTER R WITH ACUTE 0x0155: 0x00ea, # LATIN SMALL LETTER R WITH ACUTE 0x0158: 0x00fc, # LATIN CAPITAL LETTER R WITH CARON 0x0159: 0x00fd, # LATIN SMALL LETTER R WITH CARON 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE 0x015e: 0x00b8, # LATIN CAPITAL LETTER S WITH CEDILLA 0x015f: 0x00ad, # LATIN SMALL LETTER S WITH CEDILLA 0x0160: 0x00e6, # LATIN CAPITAL LETTER S WITH CARON 0x0161: 0x00e7, # LATIN SMALL LETTER S WITH CARON 0x0162: 0x00dd, # LATIN CAPITAL LETTER T WITH CEDILLA 0x0163: 0x00ee, # LATIN SMALL LETTER T WITH CEDILLA 0x0164: 0x009b, # LATIN CAPITAL LETTER T WITH CARON 0x0165: 0x009c, # LATIN SMALL LETTER T WITH CARON 0x016e: 0x00de, # LATIN CAPITAL LETTER U WITH RING ABOVE 0x016f: 0x0085, # LATIN SMALL LETTER U WITH RING ABOVE 0x0170: 0x00eb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE 0x0171: 0x00fb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE 0x017a: 0x00ab, # LATIN SMALL LETTER Z WITH ACUTE 0x017b: 0x00bd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x017c: 0x00be, # LATIN SMALL LETTER Z WITH DOT ABOVE 0x017d: 0x00a6, # LATIN CAPITAL LETTER Z WITH CARON 0x017e: 0x00a7, # LATIN SMALL LETTER Z WITH CARON 0x02c7: 0x00f3, # CARON 0x02d8: 0x00f4, # BREVE 0x02d9: 0x00fa, # DOT ABOVE 0x02db: 0x00f2, # OGONEK 0x02dd: 0x00f1, # DOUBLE ACUTE ACCENT 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp855.py0000644000076500000240000010247212612565546023144 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP855.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp855', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE 0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE 0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE 0x0083: 0x0403, # CYRILLIC CAPITAL LETTER GJE 0x0084: 0x0451, # CYRILLIC SMALL LETTER IO 0x0085: 0x0401, # CYRILLIC CAPITAL LETTER IO 0x0086: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE 0x0087: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE 0x0088: 0x0455, # CYRILLIC SMALL LETTER DZE 0x0089: 0x0405, # CYRILLIC CAPITAL LETTER DZE 0x008a: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 0x008b: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I 0x008c: 0x0457, # CYRILLIC SMALL LETTER YI 0x008d: 0x0407, # CYRILLIC CAPITAL LETTER YI 0x008e: 0x0458, # CYRILLIC SMALL LETTER JE 0x008f: 0x0408, # CYRILLIC CAPITAL LETTER JE 0x0090: 0x0459, # CYRILLIC SMALL LETTER LJE 0x0091: 0x0409, # CYRILLIC CAPITAL LETTER LJE 0x0092: 0x045a, # CYRILLIC SMALL LETTER NJE 0x0093: 0x040a, # CYRILLIC CAPITAL LETTER NJE 0x0094: 0x045b, # CYRILLIC SMALL LETTER TSHE 0x0095: 0x040b, # CYRILLIC CAPITAL LETTER TSHE 0x0096: 0x045c, # CYRILLIC SMALL LETTER KJE 0x0097: 0x040c, # CYRILLIC CAPITAL LETTER KJE 0x0098: 0x045e, # CYRILLIC SMALL LETTER SHORT U 0x0099: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U 0x009a: 0x045f, # CYRILLIC SMALL LETTER DZHE 0x009b: 0x040f, # CYRILLIC CAPITAL LETTER DZHE 0x009c: 0x044e, # CYRILLIC SMALL LETTER YU 0x009d: 0x042e, # CYRILLIC CAPITAL LETTER YU 0x009e: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN 0x009f: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A 0x00a1: 0x0410, # CYRILLIC CAPITAL LETTER A 0x00a2: 0x0431, # CYRILLIC SMALL LETTER BE 0x00a3: 0x0411, # CYRILLIC CAPITAL LETTER BE 0x00a4: 0x0446, # CYRILLIC SMALL LETTER TSE 0x00a5: 0x0426, # CYRILLIC CAPITAL LETTER TSE 0x00a6: 0x0434, # CYRILLIC SMALL LETTER DE 0x00a7: 0x0414, # CYRILLIC CAPITAL LETTER DE 0x00a8: 0x0435, # CYRILLIC SMALL LETTER IE 0x00a9: 0x0415, # CYRILLIC CAPITAL LETTER IE 0x00aa: 0x0444, # CYRILLIC SMALL LETTER EF 0x00ab: 0x0424, # CYRILLIC CAPITAL LETTER EF 0x00ac: 0x0433, # CYRILLIC SMALL LETTER GHE 0x00ad: 0x0413, # CYRILLIC CAPITAL LETTER GHE 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x0445, # CYRILLIC SMALL LETTER HA 0x00b6: 0x0425, # CYRILLIC CAPITAL LETTER HA 0x00b7: 0x0438, # CYRILLIC SMALL LETTER I 0x00b8: 0x0418, # CYRILLIC CAPITAL LETTER I 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x0439, # CYRILLIC SMALL LETTER SHORT I 0x00be: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x043a, # CYRILLIC SMALL LETTER KA 0x00c7: 0x041a, # CYRILLIC CAPITAL LETTER KA 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x00a4, # CURRENCY SIGN 0x00d0: 0x043b, # CYRILLIC SMALL LETTER EL 0x00d1: 0x041b, # CYRILLIC CAPITAL LETTER EL 0x00d2: 0x043c, # CYRILLIC SMALL LETTER EM 0x00d3: 0x041c, # CYRILLIC CAPITAL LETTER EM 0x00d4: 0x043d, # CYRILLIC SMALL LETTER EN 0x00d5: 0x041d, # CYRILLIC CAPITAL LETTER EN 0x00d6: 0x043e, # CYRILLIC SMALL LETTER O 0x00d7: 0x041e, # CYRILLIC CAPITAL LETTER O 0x00d8: 0x043f, # CYRILLIC SMALL LETTER PE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x041f, # CYRILLIC CAPITAL LETTER PE 0x00de: 0x044f, # CYRILLIC SMALL LETTER YA 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x042f, # CYRILLIC CAPITAL LETTER YA 0x00e1: 0x0440, # CYRILLIC SMALL LETTER ER 0x00e2: 0x0420, # CYRILLIC CAPITAL LETTER ER 0x00e3: 0x0441, # CYRILLIC SMALL LETTER ES 0x00e4: 0x0421, # CYRILLIC CAPITAL LETTER ES 0x00e5: 0x0442, # CYRILLIC SMALL LETTER TE 0x00e6: 0x0422, # CYRILLIC CAPITAL LETTER TE 0x00e7: 0x0443, # CYRILLIC SMALL LETTER U 0x00e8: 0x0423, # CYRILLIC CAPITAL LETTER U 0x00e9: 0x0436, # CYRILLIC SMALL LETTER ZHE 0x00ea: 0x0416, # CYRILLIC CAPITAL LETTER ZHE 0x00eb: 0x0432, # CYRILLIC SMALL LETTER VE 0x00ec: 0x0412, # CYRILLIC CAPITAL LETTER VE 0x00ed: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN 0x00ee: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN 0x00ef: 0x2116, # NUMERO SIGN 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x044b, # CYRILLIC SMALL LETTER YERU 0x00f2: 0x042b, # CYRILLIC CAPITAL LETTER YERU 0x00f3: 0x0437, # CYRILLIC SMALL LETTER ZE 0x00f4: 0x0417, # CYRILLIC CAPITAL LETTER ZE 0x00f5: 0x0448, # CYRILLIC SMALL LETTER SHA 0x00f6: 0x0428, # CYRILLIC CAPITAL LETTER SHA 0x00f7: 0x044d, # CYRILLIC SMALL LETTER E 0x00f8: 0x042d, # CYRILLIC CAPITAL LETTER E 0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA 0x00fa: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA 0x00fb: 0x0447, # CYRILLIC SMALL LETTER CHE 0x00fc: 0x0427, # CYRILLIC CAPITAL LETTER CHE 0x00fd: 0x00a7, # SECTION SIGN 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\u0452' # 0x0080 -> CYRILLIC SMALL LETTER DJE u'\u0402' # 0x0081 -> CYRILLIC CAPITAL LETTER DJE u'\u0453' # 0x0082 -> CYRILLIC SMALL LETTER GJE u'\u0403' # 0x0083 -> CYRILLIC CAPITAL LETTER GJE u'\u0451' # 0x0084 -> CYRILLIC SMALL LETTER IO u'\u0401' # 0x0085 -> CYRILLIC CAPITAL LETTER IO u'\u0454' # 0x0086 -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\u0404' # 0x0087 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\u0455' # 0x0088 -> CYRILLIC SMALL LETTER DZE u'\u0405' # 0x0089 -> CYRILLIC CAPITAL LETTER DZE u'\u0456' # 0x008a -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0406' # 0x008b -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0457' # 0x008c -> CYRILLIC SMALL LETTER YI u'\u0407' # 0x008d -> CYRILLIC CAPITAL LETTER YI u'\u0458' # 0x008e -> CYRILLIC SMALL LETTER JE u'\u0408' # 0x008f -> CYRILLIC CAPITAL LETTER JE u'\u0459' # 0x0090 -> CYRILLIC SMALL LETTER LJE u'\u0409' # 0x0091 -> CYRILLIC CAPITAL LETTER LJE u'\u045a' # 0x0092 -> CYRILLIC SMALL LETTER NJE u'\u040a' # 0x0093 -> CYRILLIC CAPITAL LETTER NJE u'\u045b' # 0x0094 -> CYRILLIC SMALL LETTER TSHE u'\u040b' # 0x0095 -> CYRILLIC CAPITAL LETTER TSHE u'\u045c' # 0x0096 -> CYRILLIC SMALL LETTER KJE u'\u040c' # 0x0097 -> CYRILLIC CAPITAL LETTER KJE u'\u045e' # 0x0098 -> CYRILLIC SMALL LETTER SHORT U u'\u040e' # 0x0099 -> CYRILLIC CAPITAL LETTER SHORT U u'\u045f' # 0x009a -> CYRILLIC SMALL LETTER DZHE u'\u040f' # 0x009b -> CYRILLIC CAPITAL LETTER DZHE u'\u044e' # 0x009c -> CYRILLIC SMALL LETTER YU u'\u042e' # 0x009d -> CYRILLIC CAPITAL LETTER YU u'\u044a' # 0x009e -> CYRILLIC SMALL LETTER HARD SIGN u'\u042a' # 0x009f -> CYRILLIC CAPITAL LETTER HARD SIGN u'\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A u'\u0410' # 0x00a1 -> CYRILLIC CAPITAL LETTER A u'\u0431' # 0x00a2 -> CYRILLIC SMALL LETTER BE u'\u0411' # 0x00a3 -> CYRILLIC CAPITAL LETTER BE u'\u0446' # 0x00a4 -> CYRILLIC SMALL LETTER TSE u'\u0426' # 0x00a5 -> CYRILLIC CAPITAL LETTER TSE u'\u0434' # 0x00a6 -> CYRILLIC SMALL LETTER DE u'\u0414' # 0x00a7 -> CYRILLIC CAPITAL LETTER DE u'\u0435' # 0x00a8 -> CYRILLIC SMALL LETTER IE u'\u0415' # 0x00a9 -> CYRILLIC CAPITAL LETTER IE u'\u0444' # 0x00aa -> CYRILLIC SMALL LETTER EF u'\u0424' # 0x00ab -> CYRILLIC CAPITAL LETTER EF u'\u0433' # 0x00ac -> CYRILLIC SMALL LETTER GHE u'\u0413' # 0x00ad -> CYRILLIC CAPITAL LETTER GHE u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u0445' # 0x00b5 -> CYRILLIC SMALL LETTER HA u'\u0425' # 0x00b6 -> CYRILLIC CAPITAL LETTER HA u'\u0438' # 0x00b7 -> CYRILLIC SMALL LETTER I u'\u0418' # 0x00b8 -> CYRILLIC CAPITAL LETTER I u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u0439' # 0x00bd -> CYRILLIC SMALL LETTER SHORT I u'\u0419' # 0x00be -> CYRILLIC CAPITAL LETTER SHORT I u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u043a' # 0x00c6 -> CYRILLIC SMALL LETTER KA u'\u041a' # 0x00c7 -> CYRILLIC CAPITAL LETTER KA u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa4' # 0x00cf -> CURRENCY SIGN u'\u043b' # 0x00d0 -> CYRILLIC SMALL LETTER EL u'\u041b' # 0x00d1 -> CYRILLIC CAPITAL LETTER EL u'\u043c' # 0x00d2 -> CYRILLIC SMALL LETTER EM u'\u041c' # 0x00d3 -> CYRILLIC CAPITAL LETTER EM u'\u043d' # 0x00d4 -> CYRILLIC SMALL LETTER EN u'\u041d' # 0x00d5 -> CYRILLIC CAPITAL LETTER EN u'\u043e' # 0x00d6 -> CYRILLIC SMALL LETTER O u'\u041e' # 0x00d7 -> CYRILLIC CAPITAL LETTER O u'\u043f' # 0x00d8 -> CYRILLIC SMALL LETTER PE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u041f' # 0x00dd -> CYRILLIC CAPITAL LETTER PE u'\u044f' # 0x00de -> CYRILLIC SMALL LETTER YA u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u042f' # 0x00e0 -> CYRILLIC CAPITAL LETTER YA u'\u0440' # 0x00e1 -> CYRILLIC SMALL LETTER ER u'\u0420' # 0x00e2 -> CYRILLIC CAPITAL LETTER ER u'\u0441' # 0x00e3 -> CYRILLIC SMALL LETTER ES u'\u0421' # 0x00e4 -> CYRILLIC CAPITAL LETTER ES u'\u0442' # 0x00e5 -> CYRILLIC SMALL LETTER TE u'\u0422' # 0x00e6 -> CYRILLIC CAPITAL LETTER TE u'\u0443' # 0x00e7 -> CYRILLIC SMALL LETTER U u'\u0423' # 0x00e8 -> CYRILLIC CAPITAL LETTER U u'\u0436' # 0x00e9 -> CYRILLIC SMALL LETTER ZHE u'\u0416' # 0x00ea -> CYRILLIC CAPITAL LETTER ZHE u'\u0432' # 0x00eb -> CYRILLIC SMALL LETTER VE u'\u0412' # 0x00ec -> CYRILLIC CAPITAL LETTER VE u'\u044c' # 0x00ed -> CYRILLIC SMALL LETTER SOFT SIGN u'\u042c' # 0x00ee -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u2116' # 0x00ef -> NUMERO SIGN u'\xad' # 0x00f0 -> SOFT HYPHEN u'\u044b' # 0x00f1 -> CYRILLIC SMALL LETTER YERU u'\u042b' # 0x00f2 -> CYRILLIC CAPITAL LETTER YERU u'\u0437' # 0x00f3 -> CYRILLIC SMALL LETTER ZE u'\u0417' # 0x00f4 -> CYRILLIC CAPITAL LETTER ZE u'\u0448' # 0x00f5 -> CYRILLIC SMALL LETTER SHA u'\u0428' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHA u'\u044d' # 0x00f7 -> CYRILLIC SMALL LETTER E u'\u042d' # 0x00f8 -> CYRILLIC CAPITAL LETTER E u'\u0449' # 0x00f9 -> CYRILLIC SMALL LETTER SHCHA u'\u0429' # 0x00fa -> CYRILLIC CAPITAL LETTER SHCHA u'\u0447' # 0x00fb -> CYRILLIC SMALL LETTER CHE u'\u0427' # 0x00fc -> CYRILLIC CAPITAL LETTER CHE u'\xa7' # 0x00fd -> SECTION SIGN u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a4: 0x00cf, # CURRENCY SIGN 0x00a7: 0x00fd, # SECTION SIGN 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ad: 0x00f0, # SOFT HYPHEN 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x0401: 0x0085, # CYRILLIC CAPITAL LETTER IO 0x0402: 0x0081, # CYRILLIC CAPITAL LETTER DJE 0x0403: 0x0083, # CYRILLIC CAPITAL LETTER GJE 0x0404: 0x0087, # CYRILLIC CAPITAL LETTER UKRAINIAN IE 0x0405: 0x0089, # CYRILLIC CAPITAL LETTER DZE 0x0406: 0x008b, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I 0x0407: 0x008d, # CYRILLIC CAPITAL LETTER YI 0x0408: 0x008f, # CYRILLIC CAPITAL LETTER JE 0x0409: 0x0091, # CYRILLIC CAPITAL LETTER LJE 0x040a: 0x0093, # CYRILLIC CAPITAL LETTER NJE 0x040b: 0x0095, # CYRILLIC CAPITAL LETTER TSHE 0x040c: 0x0097, # CYRILLIC CAPITAL LETTER KJE 0x040e: 0x0099, # CYRILLIC CAPITAL LETTER SHORT U 0x040f: 0x009b, # CYRILLIC CAPITAL LETTER DZHE 0x0410: 0x00a1, # CYRILLIC CAPITAL LETTER A 0x0411: 0x00a3, # CYRILLIC CAPITAL LETTER BE 0x0412: 0x00ec, # CYRILLIC CAPITAL LETTER VE 0x0413: 0x00ad, # CYRILLIC CAPITAL LETTER GHE 0x0414: 0x00a7, # CYRILLIC CAPITAL LETTER DE 0x0415: 0x00a9, # CYRILLIC CAPITAL LETTER IE 0x0416: 0x00ea, # CYRILLIC CAPITAL LETTER ZHE 0x0417: 0x00f4, # CYRILLIC CAPITAL LETTER ZE 0x0418: 0x00b8, # CYRILLIC CAPITAL LETTER I 0x0419: 0x00be, # CYRILLIC CAPITAL LETTER SHORT I 0x041a: 0x00c7, # CYRILLIC CAPITAL LETTER KA 0x041b: 0x00d1, # CYRILLIC CAPITAL LETTER EL 0x041c: 0x00d3, # CYRILLIC CAPITAL LETTER EM 0x041d: 0x00d5, # CYRILLIC CAPITAL LETTER EN 0x041e: 0x00d7, # CYRILLIC CAPITAL LETTER O 0x041f: 0x00dd, # CYRILLIC CAPITAL LETTER PE 0x0420: 0x00e2, # CYRILLIC CAPITAL LETTER ER 0x0421: 0x00e4, # CYRILLIC CAPITAL LETTER ES 0x0422: 0x00e6, # CYRILLIC CAPITAL LETTER TE 0x0423: 0x00e8, # CYRILLIC CAPITAL LETTER U 0x0424: 0x00ab, # CYRILLIC CAPITAL LETTER EF 0x0425: 0x00b6, # CYRILLIC CAPITAL LETTER HA 0x0426: 0x00a5, # CYRILLIC CAPITAL LETTER TSE 0x0427: 0x00fc, # CYRILLIC CAPITAL LETTER CHE 0x0428: 0x00f6, # CYRILLIC CAPITAL LETTER SHA 0x0429: 0x00fa, # CYRILLIC CAPITAL LETTER SHCHA 0x042a: 0x009f, # CYRILLIC CAPITAL LETTER HARD SIGN 0x042b: 0x00f2, # CYRILLIC CAPITAL LETTER YERU 0x042c: 0x00ee, # CYRILLIC CAPITAL LETTER SOFT SIGN 0x042d: 0x00f8, # CYRILLIC CAPITAL LETTER E 0x042e: 0x009d, # CYRILLIC CAPITAL LETTER YU 0x042f: 0x00e0, # CYRILLIC CAPITAL LETTER YA 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A 0x0431: 0x00a2, # CYRILLIC SMALL LETTER BE 0x0432: 0x00eb, # CYRILLIC SMALL LETTER VE 0x0433: 0x00ac, # CYRILLIC SMALL LETTER GHE 0x0434: 0x00a6, # CYRILLIC SMALL LETTER DE 0x0435: 0x00a8, # CYRILLIC SMALL LETTER IE 0x0436: 0x00e9, # CYRILLIC SMALL LETTER ZHE 0x0437: 0x00f3, # CYRILLIC SMALL LETTER ZE 0x0438: 0x00b7, # CYRILLIC SMALL LETTER I 0x0439: 0x00bd, # CYRILLIC SMALL LETTER SHORT I 0x043a: 0x00c6, # CYRILLIC SMALL LETTER KA 0x043b: 0x00d0, # CYRILLIC SMALL LETTER EL 0x043c: 0x00d2, # CYRILLIC SMALL LETTER EM 0x043d: 0x00d4, # CYRILLIC SMALL LETTER EN 0x043e: 0x00d6, # CYRILLIC SMALL LETTER O 0x043f: 0x00d8, # CYRILLIC SMALL LETTER PE 0x0440: 0x00e1, # CYRILLIC SMALL LETTER ER 0x0441: 0x00e3, # CYRILLIC SMALL LETTER ES 0x0442: 0x00e5, # CYRILLIC SMALL LETTER TE 0x0443: 0x00e7, # CYRILLIC SMALL LETTER U 0x0444: 0x00aa, # CYRILLIC SMALL LETTER EF 0x0445: 0x00b5, # CYRILLIC SMALL LETTER HA 0x0446: 0x00a4, # CYRILLIC SMALL LETTER TSE 0x0447: 0x00fb, # CYRILLIC SMALL LETTER CHE 0x0448: 0x00f5, # CYRILLIC SMALL LETTER SHA 0x0449: 0x00f9, # CYRILLIC SMALL LETTER SHCHA 0x044a: 0x009e, # CYRILLIC SMALL LETTER HARD SIGN 0x044b: 0x00f1, # CYRILLIC SMALL LETTER YERU 0x044c: 0x00ed, # CYRILLIC SMALL LETTER SOFT SIGN 0x044d: 0x00f7, # CYRILLIC SMALL LETTER E 0x044e: 0x009c, # CYRILLIC SMALL LETTER YU 0x044f: 0x00de, # CYRILLIC SMALL LETTER YA 0x0451: 0x0084, # CYRILLIC SMALL LETTER IO 0x0452: 0x0080, # CYRILLIC SMALL LETTER DJE 0x0453: 0x0082, # CYRILLIC SMALL LETTER GJE 0x0454: 0x0086, # CYRILLIC SMALL LETTER UKRAINIAN IE 0x0455: 0x0088, # CYRILLIC SMALL LETTER DZE 0x0456: 0x008a, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 0x0457: 0x008c, # CYRILLIC SMALL LETTER YI 0x0458: 0x008e, # CYRILLIC SMALL LETTER JE 0x0459: 0x0090, # CYRILLIC SMALL LETTER LJE 0x045a: 0x0092, # CYRILLIC SMALL LETTER NJE 0x045b: 0x0094, # CYRILLIC SMALL LETTER TSHE 0x045c: 0x0096, # CYRILLIC SMALL LETTER KJE 0x045e: 0x0098, # CYRILLIC SMALL LETTER SHORT U 0x045f: 0x009a, # CYRILLIC SMALL LETTER DZHE 0x2116: 0x00ef, # NUMERO SIGN 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp856.py0000644000076500000240000003060712612565546023145 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp856', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u05d0' # 0x80 -> HEBREW LETTER ALEF u'\u05d1' # 0x81 -> HEBREW LETTER BET u'\u05d2' # 0x82 -> HEBREW LETTER GIMEL u'\u05d3' # 0x83 -> HEBREW LETTER DALET u'\u05d4' # 0x84 -> HEBREW LETTER HE u'\u05d5' # 0x85 -> HEBREW LETTER VAV u'\u05d6' # 0x86 -> HEBREW LETTER ZAYIN u'\u05d7' # 0x87 -> HEBREW LETTER HET u'\u05d8' # 0x88 -> HEBREW LETTER TET u'\u05d9' # 0x89 -> HEBREW LETTER YOD u'\u05da' # 0x8A -> HEBREW LETTER FINAL KAF u'\u05db' # 0x8B -> HEBREW LETTER KAF u'\u05dc' # 0x8C -> HEBREW LETTER LAMED u'\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM u'\u05de' # 0x8E -> HEBREW LETTER MEM u'\u05df' # 0x8F -> HEBREW LETTER FINAL NUN u'\u05e0' # 0x90 -> HEBREW LETTER NUN u'\u05e1' # 0x91 -> HEBREW LETTER SAMEKH u'\u05e2' # 0x92 -> HEBREW LETTER AYIN u'\u05e3' # 0x93 -> HEBREW LETTER FINAL PE u'\u05e4' # 0x94 -> HEBREW LETTER PE u'\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI u'\u05e6' # 0x96 -> HEBREW LETTER TSADI u'\u05e7' # 0x97 -> HEBREW LETTER QOF u'\u05e8' # 0x98 -> HEBREW LETTER RESH u'\u05e9' # 0x99 -> HEBREW LETTER SHIN u'\u05ea' # 0x9A -> HEBREW LETTER TAV u'\ufffe' # 0x9B -> UNDEFINED u'\xa3' # 0x9C -> POUND SIGN u'\ufffe' # 0x9D -> UNDEFINED u'\xd7' # 0x9E -> MULTIPLICATION SIGN u'\ufffe' # 0x9F -> UNDEFINED u'\ufffe' # 0xA0 -> UNDEFINED u'\ufffe' # 0xA1 -> UNDEFINED u'\ufffe' # 0xA2 -> UNDEFINED u'\ufffe' # 0xA3 -> UNDEFINED u'\ufffe' # 0xA4 -> UNDEFINED u'\ufffe' # 0xA5 -> UNDEFINED u'\ufffe' # 0xA6 -> UNDEFINED u'\ufffe' # 0xA7 -> UNDEFINED u'\ufffe' # 0xA8 -> UNDEFINED u'\xae' # 0xA9 -> REGISTERED SIGN u'\xac' # 0xAA -> NOT SIGN u'\xbd' # 0xAB -> VULGAR FRACTION ONE HALF u'\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER u'\ufffe' # 0xAD -> UNDEFINED u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0xB0 -> LIGHT SHADE u'\u2592' # 0xB1 -> MEDIUM SHADE u'\u2593' # 0xB2 -> DARK SHADE u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\ufffe' # 0xB5 -> UNDEFINED u'\ufffe' # 0xB6 -> UNDEFINED u'\ufffe' # 0xB7 -> UNDEFINED u'\xa9' # 0xB8 -> COPYRIGHT SIGN u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT u'\xa2' # 0xBD -> CENT SIGN u'\xa5' # 0xBE -> YEN SIGN u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\ufffe' # 0xC6 -> UNDEFINED u'\ufffe' # 0xC7 -> UNDEFINED u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa4' # 0xCF -> CURRENCY SIGN u'\ufffe' # 0xD0 -> UNDEFINED u'\ufffe' # 0xD1 -> UNDEFINED u'\ufffe' # 0xD2 -> UNDEFINED u'\ufffe' # 0xD3 -> UNDEFINEDS u'\ufffe' # 0xD4 -> UNDEFINED u'\ufffe' # 0xD5 -> UNDEFINED u'\ufffe' # 0xD6 -> UNDEFINEDE u'\ufffe' # 0xD7 -> UNDEFINED u'\ufffe' # 0xD8 -> UNDEFINED u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0xDB -> FULL BLOCK u'\u2584' # 0xDC -> LOWER HALF BLOCK u'\xa6' # 0xDD -> BROKEN BAR u'\ufffe' # 0xDE -> UNDEFINED u'\u2580' # 0xDF -> UPPER HALF BLOCK u'\ufffe' # 0xE0 -> UNDEFINED u'\ufffe' # 0xE1 -> UNDEFINED u'\ufffe' # 0xE2 -> UNDEFINED u'\ufffe' # 0xE3 -> UNDEFINED u'\ufffe' # 0xE4 -> UNDEFINED u'\ufffe' # 0xE5 -> UNDEFINED u'\xb5' # 0xE6 -> MICRO SIGN u'\ufffe' # 0xE7 -> UNDEFINED u'\ufffe' # 0xE8 -> UNDEFINED u'\ufffe' # 0xE9 -> UNDEFINED u'\ufffe' # 0xEA -> UNDEFINED u'\ufffe' # 0xEB -> UNDEFINED u'\ufffe' # 0xEC -> UNDEFINED u'\ufffe' # 0xED -> UNDEFINED u'\xaf' # 0xEE -> MACRON u'\xb4' # 0xEF -> ACUTE ACCENT u'\xad' # 0xF0 -> SOFT HYPHEN u'\xb1' # 0xF1 -> PLUS-MINUS SIGN u'\u2017' # 0xF2 -> DOUBLE LOW LINE u'\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS u'\xb6' # 0xF4 -> PILCROW SIGN u'\xa7' # 0xF5 -> SECTION SIGN u'\xf7' # 0xF6 -> DIVISION SIGN u'\xb8' # 0xF7 -> CEDILLA u'\xb0' # 0xF8 -> DEGREE SIGN u'\xa8' # 0xF9 -> DIAERESIS u'\xb7' # 0xFA -> MIDDLE DOT u'\xb9' # 0xFB -> SUPERSCRIPT ONE u'\xb3' # 0xFC -> SUPERSCRIPT THREE u'\xb2' # 0xFD -> SUPERSCRIPT TWO u'\u25a0' # 0xFE -> BLACK SQUARE u'\xa0' # 0xFF -> NO-BREAK SPACE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp857.py0000644000076500000240000010256412612565546023150 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP857.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp857', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x0131, # LATIN SMALL LETTER DOTLESS I 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA 0x009f: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE 0x00a7: 0x011f, # LATIN SMALL LETTER G WITH BREVE 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x00ae, # REGISTERED SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x00b8: 0x00a9, # COPYRIGHT SIGN 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x00a2, # CENT SIGN 0x00be: 0x00a5, # YEN SIGN 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x00a4, # CURRENCY SIGN 0x00d0: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00d1: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x00d5: None, # UNDEFINED 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x00a6, # BROKEN BAR 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: None, # UNDEFINED 0x00e8: 0x00d7, # MULTIPLICATION SIGN 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x00ed: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x00ee: 0x00af, # MACRON 0x00ef: 0x00b4, # ACUTE ACCENT 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: None, # UNDEFINED 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00f4: 0x00b6, # PILCROW SIGN 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x00b8, # CEDILLA 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x00a8, # DIAERESIS 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x00b9, # SUPERSCRIPT ONE 0x00fc: 0x00b3, # SUPERSCRIPT THREE 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u0131' # 0x008d -> LATIN SMALL LETTER DOTLESS I u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\u0130' # 0x0098 -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE u'\xa3' # 0x009c -> POUND SIGN u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE u'\u015e' # 0x009e -> LATIN CAPITAL LETTER S WITH CEDILLA u'\u015f' # 0x009f -> LATIN SMALL LETTER S WITH CEDILLA u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\u011e' # 0x00a6 -> LATIN CAPITAL LETTER G WITH BREVE u'\u011f' # 0x00a7 -> LATIN SMALL LETTER G WITH BREVE u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\xae' # 0x00a9 -> REGISTERED SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xa9' # 0x00b8 -> COPYRIGHT SIGN u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\xa2' # 0x00bd -> CENT SIGN u'\xa5' # 0x00be -> YEN SIGN u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE u'\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa4' # 0x00cf -> CURRENCY SIGN u'\xba' # 0x00d0 -> MASCULINE ORDINAL INDICATOR u'\xaa' # 0x00d1 -> FEMININE ORDINAL INDICATOR u'\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE u'\ufffe' # 0x00d5 -> UNDEFINED u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\xa6' # 0x00dd -> BROKEN BAR u'\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xb5' # 0x00e6 -> MICRO SIGN u'\ufffe' # 0x00e7 -> UNDEFINED u'\xd7' # 0x00e8 -> MULTIPLICATION SIGN u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE u'\xec' # 0x00ec -> LATIN SMALL LETTER I WITH GRAVE u'\xff' # 0x00ed -> LATIN SMALL LETTER Y WITH DIAERESIS u'\xaf' # 0x00ee -> MACRON u'\xb4' # 0x00ef -> ACUTE ACCENT u'\xad' # 0x00f0 -> SOFT HYPHEN u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\ufffe' # 0x00f2 -> UNDEFINED u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS u'\xb6' # 0x00f4 -> PILCROW SIGN u'\xa7' # 0x00f5 -> SECTION SIGN u'\xf7' # 0x00f6 -> DIVISION SIGN u'\xb8' # 0x00f7 -> CEDILLA u'\xb0' # 0x00f8 -> DEGREE SIGN u'\xa8' # 0x00f9 -> DIAERESIS u'\xb7' # 0x00fa -> MIDDLE DOT u'\xb9' # 0x00fb -> SUPERSCRIPT ONE u'\xb3' # 0x00fc -> SUPERSCRIPT THREE u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x00bd, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x00cf, # CURRENCY SIGN 0x00a5: 0x00be, # YEN SIGN 0x00a6: 0x00dd, # BROKEN BAR 0x00a7: 0x00f5, # SECTION SIGN 0x00a8: 0x00f9, # DIAERESIS 0x00a9: 0x00b8, # COPYRIGHT SIGN 0x00aa: 0x00d1, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00ae: 0x00a9, # REGISTERED SIGN 0x00af: 0x00ee, # MACRON 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b3: 0x00fc, # SUPERSCRIPT THREE 0x00b4: 0x00ef, # ACUTE ACCENT 0x00b5: 0x00e6, # MICRO SIGN 0x00b6: 0x00f4, # PILCROW SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00b8: 0x00f7, # CEDILLA 0x00b9: 0x00fb, # SUPERSCRIPT ONE 0x00ba: 0x00d0, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d7: 0x00e8, # MULTIPLICATION SIGN 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ec: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00ff: 0x00ed, # LATIN SMALL LETTER Y WITH DIAERESIS 0x011e: 0x00a6, # LATIN CAPITAL LETTER G WITH BREVE 0x011f: 0x00a7, # LATIN SMALL LETTER G WITH BREVE 0x0130: 0x0098, # LATIN CAPITAL LETTER I WITH DOT ABOVE 0x0131: 0x008d, # LATIN SMALL LETTER DOTLESS I 0x015e: 0x009e, # LATIN CAPITAL LETTER S WITH CEDILLA 0x015f: 0x009f, # LATIN SMALL LETTER S WITH CEDILLA 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp860.py0000644000076500000240000010417112612565546023136 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP860.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp860', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e3, # LATIN SMALL LETTER A WITH TILDE 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x008c: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x008e: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE 0x008f: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x0092: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE 0x0099: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00a2, # CENT SIGN 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0x0084 -> LATIN SMALL LETTER A WITH TILDE u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xc1' # 0x0086 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xca' # 0x0089 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xcd' # 0x008b -> LATIN CAPITAL LETTER I WITH ACUTE u'\xd4' # 0x008c -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE u'\xc3' # 0x008e -> LATIN CAPITAL LETTER A WITH TILDE u'\xc2' # 0x008f -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xc0' # 0x0091 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc8' # 0x0092 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0x0094 -> LATIN SMALL LETTER O WITH TILDE u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE u'\xda' # 0x0096 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\xcc' # 0x0098 -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd5' # 0x0099 -> LATIN CAPITAL LETTER O WITH TILDE u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xa2' # 0x009b -> CENT SIGN u'\xa3' # 0x009c -> POUND SIGN u'\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE u'\u20a7' # 0x009e -> PESETA SIGN u'\xd3' # 0x009f -> LATIN CAPITAL LETTER O WITH ACUTE u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\xd2' # 0x00a9 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x009b, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c0: 0x0091, # LATIN CAPITAL LETTER A WITH GRAVE 0x00c1: 0x0086, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c2: 0x008f, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c3: 0x008e, # LATIN CAPITAL LETTER A WITH TILDE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c8: 0x0092, # LATIN CAPITAL LETTER E WITH GRAVE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00ca: 0x0089, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00cc: 0x0098, # LATIN CAPITAL LETTER I WITH GRAVE 0x00cd: 0x008b, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d2: 0x00a9, # LATIN CAPITAL LETTER O WITH GRAVE 0x00d3: 0x009f, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d4: 0x008c, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d5: 0x0099, # LATIN CAPITAL LETTER O WITH TILDE 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE 0x00da: 0x0096, # LATIN CAPITAL LETTER U WITH ACUTE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e3: 0x0084, # LATIN SMALL LETTER A WITH TILDE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f5: 0x0094, # LATIN SMALL LETTER O WITH TILDE 0x00f7: 0x00f6, # DIVISION SIGN 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp861.py0000644000076500000240000010411112612565546023131 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP861.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp861', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00d0, # LATIN CAPITAL LETTER ETH 0x008c: 0x00f0, # LATIN SMALL LETTER ETH 0x008d: 0x00de, # LATIN CAPITAL LETTER THORN 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00fe, # LATIN SMALL LETTER THORN 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x0098: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00a5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00a6: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00a7: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xd0' # 0x008b -> LATIN CAPITAL LETTER ETH u'\xf0' # 0x008c -> LATIN SMALL LETTER ETH u'\xde' # 0x008d -> LATIN CAPITAL LETTER THORN u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xfe' # 0x0095 -> LATIN SMALL LETTER THORN u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xdd' # 0x0097 -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xfd' # 0x0098 -> LATIN SMALL LETTER Y WITH ACUTE u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE u'\xa3' # 0x009c -> POUND SIGN u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE u'\u20a7' # 0x009e -> PESETA SIGN u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xc1' # 0x00a4 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xcd' # 0x00a5 -> LATIN CAPITAL LETTER I WITH ACUTE u'\xd3' # 0x00a6 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xda' # 0x00a7 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\u2310' # 0x00a9 -> REVERSED NOT SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a3: 0x009c, # POUND SIGN 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c1: 0x00a4, # LATIN CAPITAL LETTER A WITH ACUTE 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00cd: 0x00a5, # LATIN CAPITAL LETTER I WITH ACUTE 0x00d0: 0x008b, # LATIN CAPITAL LETTER ETH 0x00d3: 0x00a6, # LATIN CAPITAL LETTER O WITH ACUTE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00da: 0x00a7, # LATIN CAPITAL LETTER U WITH ACUTE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dd: 0x0097, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00de: 0x008d, # LATIN CAPITAL LETTER THORN 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00f0: 0x008c, # LATIN SMALL LETTER ETH 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00fd: 0x0098, # LATIN SMALL LETTER Y WITH ACUTE 0x00fe: 0x0095, # LATIN SMALL LETTER THORN 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp862.py0000644000076500000240000010153212612565546023136 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP862.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp862', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x05d0, # HEBREW LETTER ALEF 0x0081: 0x05d1, # HEBREW LETTER BET 0x0082: 0x05d2, # HEBREW LETTER GIMEL 0x0083: 0x05d3, # HEBREW LETTER DALET 0x0084: 0x05d4, # HEBREW LETTER HE 0x0085: 0x05d5, # HEBREW LETTER VAV 0x0086: 0x05d6, # HEBREW LETTER ZAYIN 0x0087: 0x05d7, # HEBREW LETTER HET 0x0088: 0x05d8, # HEBREW LETTER TET 0x0089: 0x05d9, # HEBREW LETTER YOD 0x008a: 0x05da, # HEBREW LETTER FINAL KAF 0x008b: 0x05db, # HEBREW LETTER KAF 0x008c: 0x05dc, # HEBREW LETTER LAMED 0x008d: 0x05dd, # HEBREW LETTER FINAL MEM 0x008e: 0x05de, # HEBREW LETTER MEM 0x008f: 0x05df, # HEBREW LETTER FINAL NUN 0x0090: 0x05e0, # HEBREW LETTER NUN 0x0091: 0x05e1, # HEBREW LETTER SAMEKH 0x0092: 0x05e2, # HEBREW LETTER AYIN 0x0093: 0x05e3, # HEBREW LETTER FINAL PE 0x0094: 0x05e4, # HEBREW LETTER PE 0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI 0x0096: 0x05e6, # HEBREW LETTER TSADI 0x0097: 0x05e7, # HEBREW LETTER QOF 0x0098: 0x05e8, # HEBREW LETTER RESH 0x0099: 0x05e9, # HEBREW LETTER SHIN 0x009a: 0x05ea, # HEBREW LETTER TAV 0x009b: 0x00a2, # CENT SIGN 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00a5, # YEN SIGN 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\u05d0' # 0x0080 -> HEBREW LETTER ALEF u'\u05d1' # 0x0081 -> HEBREW LETTER BET u'\u05d2' # 0x0082 -> HEBREW LETTER GIMEL u'\u05d3' # 0x0083 -> HEBREW LETTER DALET u'\u05d4' # 0x0084 -> HEBREW LETTER HE u'\u05d5' # 0x0085 -> HEBREW LETTER VAV u'\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN u'\u05d7' # 0x0087 -> HEBREW LETTER HET u'\u05d8' # 0x0088 -> HEBREW LETTER TET u'\u05d9' # 0x0089 -> HEBREW LETTER YOD u'\u05da' # 0x008a -> HEBREW LETTER FINAL KAF u'\u05db' # 0x008b -> HEBREW LETTER KAF u'\u05dc' # 0x008c -> HEBREW LETTER LAMED u'\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM u'\u05de' # 0x008e -> HEBREW LETTER MEM u'\u05df' # 0x008f -> HEBREW LETTER FINAL NUN u'\u05e0' # 0x0090 -> HEBREW LETTER NUN u'\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH u'\u05e2' # 0x0092 -> HEBREW LETTER AYIN u'\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE u'\u05e4' # 0x0094 -> HEBREW LETTER PE u'\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI u'\u05e6' # 0x0096 -> HEBREW LETTER TSADI u'\u05e7' # 0x0097 -> HEBREW LETTER QOF u'\u05e8' # 0x0098 -> HEBREW LETTER RESH u'\u05e9' # 0x0099 -> HEBREW LETTER SHIN u'\u05ea' # 0x009a -> HEBREW LETTER TAV u'\xa2' # 0x009b -> CENT SIGN u'\xa3' # 0x009c -> POUND SIGN u'\xa5' # 0x009d -> YEN SIGN u'\u20a7' # 0x009e -> PESETA SIGN u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\u2310' # 0x00a9 -> REVERSED NOT SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN) u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a2: 0x009b, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a5: 0x009d, # YEN SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN) 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f7: 0x00f6, # DIVISION SIGN 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x05d0: 0x0080, # HEBREW LETTER ALEF 0x05d1: 0x0081, # HEBREW LETTER BET 0x05d2: 0x0082, # HEBREW LETTER GIMEL 0x05d3: 0x0083, # HEBREW LETTER DALET 0x05d4: 0x0084, # HEBREW LETTER HE 0x05d5: 0x0085, # HEBREW LETTER VAV 0x05d6: 0x0086, # HEBREW LETTER ZAYIN 0x05d7: 0x0087, # HEBREW LETTER HET 0x05d8: 0x0088, # HEBREW LETTER TET 0x05d9: 0x0089, # HEBREW LETTER YOD 0x05da: 0x008a, # HEBREW LETTER FINAL KAF 0x05db: 0x008b, # HEBREW LETTER KAF 0x05dc: 0x008c, # HEBREW LETTER LAMED 0x05dd: 0x008d, # HEBREW LETTER FINAL MEM 0x05de: 0x008e, # HEBREW LETTER MEM 0x05df: 0x008f, # HEBREW LETTER FINAL NUN 0x05e0: 0x0090, # HEBREW LETTER NUN 0x05e1: 0x0091, # HEBREW LETTER SAMEKH 0x05e2: 0x0092, # HEBREW LETTER AYIN 0x05e3: 0x0093, # HEBREW LETTER FINAL PE 0x05e4: 0x0094, # HEBREW LETTER PE 0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI 0x05e6: 0x0096, # HEBREW LETTER TSADI 0x05e7: 0x0097, # HEBREW LETTER QOF 0x05e8: 0x0098, # HEBREW LETTER RESH 0x05e9: 0x0099, # HEBREW LETTER SHIN 0x05ea: 0x009a, # HEBREW LETTER TAV 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp863.py0000644000076500000240000010331412612565546023137 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP863.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp863', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00b6, # PILCROW SIGN 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x2017, # DOUBLE LOW LINE 0x008e: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x008f: 0x00a7, # SECTION SIGN 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x0092: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x0095: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00a4, # CURRENCY SIGN 0x0099: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00a2, # CENT SIGN 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x009e: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00a6, # BROKEN BAR 0x00a1: 0x00b4, # ACUTE ACCENT 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00a8, # DIAERESIS 0x00a5: 0x00b8, # CEDILLA 0x00a6: 0x00b3, # SUPERSCRIPT THREE 0x00a7: 0x00af, # MACRON 0x00a8: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xc2' # 0x0084 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xb6' # 0x0086 -> PILCROW SIGN u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u2017' # 0x008d -> DOUBLE LOW LINE u'\xc0' # 0x008e -> LATIN CAPITAL LETTER A WITH GRAVE u'\xa7' # 0x008f -> SECTION SIGN u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xc8' # 0x0091 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xca' # 0x0092 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xcb' # 0x0094 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcf' # 0x0095 -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\xa4' # 0x0098 -> CURRENCY SIGN u'\xd4' # 0x0099 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xa2' # 0x009b -> CENT SIGN u'\xa3' # 0x009c -> POUND SIGN u'\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE u'\xdb' # 0x009e -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xa6' # 0x00a0 -> BROKEN BAR u'\xb4' # 0x00a1 -> ACUTE ACCENT u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xa8' # 0x00a4 -> DIAERESIS u'\xb8' # 0x00a5 -> CEDILLA u'\xb3' # 0x00a6 -> SUPERSCRIPT THREE u'\xaf' # 0x00a7 -> MACRON u'\xce' # 0x00a8 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\u2310' # 0x00a9 -> REVERSED NOT SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xbe' # 0x00ad -> VULGAR FRACTION THREE QUARTERS u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a2: 0x009b, # CENT SIGN 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x0098, # CURRENCY SIGN 0x00a6: 0x00a0, # BROKEN BAR 0x00a7: 0x008f, # SECTION SIGN 0x00a8: 0x00a4, # DIAERESIS 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00af: 0x00a7, # MACRON 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b3: 0x00a6, # SUPERSCRIPT THREE 0x00b4: 0x00a1, # ACUTE ACCENT 0x00b5: 0x00e6, # MICRO SIGN 0x00b6: 0x0086, # PILCROW SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00b8: 0x00a5, # CEDILLA 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00be: 0x00ad, # VULGAR FRACTION THREE QUARTERS 0x00c0: 0x008e, # LATIN CAPITAL LETTER A WITH GRAVE 0x00c2: 0x0084, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c8: 0x0091, # LATIN CAPITAL LETTER E WITH GRAVE 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00ca: 0x0092, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00cb: 0x0094, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00ce: 0x00a8, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00cf: 0x0095, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00d4: 0x0099, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE 0x00db: 0x009e, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f7: 0x00f6, # DIVISION SIGN 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x2017: 0x008d, # DOUBLE LOW LINE 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp864.py0000644000076500000240000010217712612565546023146 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP864.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp864', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0025: 0x066a, # ARABIC PERCENT SIGN 0x0080: 0x00b0, # DEGREE SIGN 0x0081: 0x00b7, # MIDDLE DOT 0x0082: 0x2219, # BULLET OPERATOR 0x0083: 0x221a, # SQUARE ROOT 0x0084: 0x2592, # MEDIUM SHADE 0x0085: 0x2500, # FORMS LIGHT HORIZONTAL 0x0086: 0x2502, # FORMS LIGHT VERTICAL 0x0087: 0x253c, # FORMS LIGHT VERTICAL AND HORIZONTAL 0x0088: 0x2524, # FORMS LIGHT VERTICAL AND LEFT 0x0089: 0x252c, # FORMS LIGHT DOWN AND HORIZONTAL 0x008a: 0x251c, # FORMS LIGHT VERTICAL AND RIGHT 0x008b: 0x2534, # FORMS LIGHT UP AND HORIZONTAL 0x008c: 0x2510, # FORMS LIGHT DOWN AND LEFT 0x008d: 0x250c, # FORMS LIGHT DOWN AND RIGHT 0x008e: 0x2514, # FORMS LIGHT UP AND RIGHT 0x008f: 0x2518, # FORMS LIGHT UP AND LEFT 0x0090: 0x03b2, # GREEK SMALL BETA 0x0091: 0x221e, # INFINITY 0x0092: 0x03c6, # GREEK SMALL PHI 0x0093: 0x00b1, # PLUS-OR-MINUS SIGN 0x0094: 0x00bd, # FRACTION 1/2 0x0095: 0x00bc, # FRACTION 1/4 0x0096: 0x2248, # ALMOST EQUAL TO 0x0097: 0x00ab, # LEFT POINTING GUILLEMET 0x0098: 0x00bb, # RIGHT POINTING GUILLEMET 0x0099: 0xfef7, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM 0x009a: 0xfef8, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM 0x009b: None, # UNDEFINED 0x009c: None, # UNDEFINED 0x009d: 0xfefb, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM 0x009e: 0xfefc, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM 0x009f: None, # UNDEFINED 0x00a1: 0x00ad, # SOFT HYPHEN 0x00a2: 0xfe82, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM 0x00a5: 0xfe84, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM 0x00a6: None, # UNDEFINED 0x00a7: None, # UNDEFINED 0x00a8: 0xfe8e, # ARABIC LETTER ALEF FINAL FORM 0x00a9: 0xfe8f, # ARABIC LETTER BEH ISOLATED FORM 0x00aa: 0xfe95, # ARABIC LETTER TEH ISOLATED FORM 0x00ab: 0xfe99, # ARABIC LETTER THEH ISOLATED FORM 0x00ac: 0x060c, # ARABIC COMMA 0x00ad: 0xfe9d, # ARABIC LETTER JEEM ISOLATED FORM 0x00ae: 0xfea1, # ARABIC LETTER HAH ISOLATED FORM 0x00af: 0xfea5, # ARABIC LETTER KHAH ISOLATED FORM 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE 0x00ba: 0xfed1, # ARABIC LETTER FEH ISOLATED FORM 0x00bb: 0x061b, # ARABIC SEMICOLON 0x00bc: 0xfeb1, # ARABIC LETTER SEEN ISOLATED FORM 0x00bd: 0xfeb5, # ARABIC LETTER SHEEN ISOLATED FORM 0x00be: 0xfeb9, # ARABIC LETTER SAD ISOLATED FORM 0x00bf: 0x061f, # ARABIC QUESTION MARK 0x00c0: 0x00a2, # CENT SIGN 0x00c1: 0xfe80, # ARABIC LETTER HAMZA ISOLATED FORM 0x00c2: 0xfe81, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM 0x00c3: 0xfe83, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM 0x00c4: 0xfe85, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM 0x00c5: 0xfeca, # ARABIC LETTER AIN FINAL FORM 0x00c6: 0xfe8b, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM 0x00c7: 0xfe8d, # ARABIC LETTER ALEF ISOLATED FORM 0x00c8: 0xfe91, # ARABIC LETTER BEH INITIAL FORM 0x00c9: 0xfe93, # ARABIC LETTER TEH MARBUTA ISOLATED FORM 0x00ca: 0xfe97, # ARABIC LETTER TEH INITIAL FORM 0x00cb: 0xfe9b, # ARABIC LETTER THEH INITIAL FORM 0x00cc: 0xfe9f, # ARABIC LETTER JEEM INITIAL FORM 0x00cd: 0xfea3, # ARABIC LETTER HAH INITIAL FORM 0x00ce: 0xfea7, # ARABIC LETTER KHAH INITIAL FORM 0x00cf: 0xfea9, # ARABIC LETTER DAL ISOLATED FORM 0x00d0: 0xfeab, # ARABIC LETTER THAL ISOLATED FORM 0x00d1: 0xfead, # ARABIC LETTER REH ISOLATED FORM 0x00d2: 0xfeaf, # ARABIC LETTER ZAIN ISOLATED FORM 0x00d3: 0xfeb3, # ARABIC LETTER SEEN INITIAL FORM 0x00d4: 0xfeb7, # ARABIC LETTER SHEEN INITIAL FORM 0x00d5: 0xfebb, # ARABIC LETTER SAD INITIAL FORM 0x00d6: 0xfebf, # ARABIC LETTER DAD INITIAL FORM 0x00d7: 0xfec1, # ARABIC LETTER TAH ISOLATED FORM 0x00d8: 0xfec5, # ARABIC LETTER ZAH ISOLATED FORM 0x00d9: 0xfecb, # ARABIC LETTER AIN INITIAL FORM 0x00da: 0xfecf, # ARABIC LETTER GHAIN INITIAL FORM 0x00db: 0x00a6, # BROKEN VERTICAL BAR 0x00dc: 0x00ac, # NOT SIGN 0x00dd: 0x00f7, # DIVISION SIGN 0x00de: 0x00d7, # MULTIPLICATION SIGN 0x00df: 0xfec9, # ARABIC LETTER AIN ISOLATED FORM 0x00e0: 0x0640, # ARABIC TATWEEL 0x00e1: 0xfed3, # ARABIC LETTER FEH INITIAL FORM 0x00e2: 0xfed7, # ARABIC LETTER QAF INITIAL FORM 0x00e3: 0xfedb, # ARABIC LETTER KAF INITIAL FORM 0x00e4: 0xfedf, # ARABIC LETTER LAM INITIAL FORM 0x00e5: 0xfee3, # ARABIC LETTER MEEM INITIAL FORM 0x00e6: 0xfee7, # ARABIC LETTER NOON INITIAL FORM 0x00e7: 0xfeeb, # ARABIC LETTER HEH INITIAL FORM 0x00e8: 0xfeed, # ARABIC LETTER WAW ISOLATED FORM 0x00e9: 0xfeef, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM 0x00ea: 0xfef3, # ARABIC LETTER YEH INITIAL FORM 0x00eb: 0xfebd, # ARABIC LETTER DAD ISOLATED FORM 0x00ec: 0xfecc, # ARABIC LETTER AIN MEDIAL FORM 0x00ed: 0xfece, # ARABIC LETTER GHAIN FINAL FORM 0x00ee: 0xfecd, # ARABIC LETTER GHAIN ISOLATED FORM 0x00ef: 0xfee1, # ARABIC LETTER MEEM ISOLATED FORM 0x00f0: 0xfe7d, # ARABIC SHADDA MEDIAL FORM 0x00f1: 0x0651, # ARABIC SHADDAH 0x00f2: 0xfee5, # ARABIC LETTER NOON ISOLATED FORM 0x00f3: 0xfee9, # ARABIC LETTER HEH ISOLATED FORM 0x00f4: 0xfeec, # ARABIC LETTER HEH MEDIAL FORM 0x00f5: 0xfef0, # ARABIC LETTER ALEF MAKSURA FINAL FORM 0x00f6: 0xfef2, # ARABIC LETTER YEH FINAL FORM 0x00f7: 0xfed0, # ARABIC LETTER GHAIN MEDIAL FORM 0x00f8: 0xfed5, # ARABIC LETTER QAF ISOLATED FORM 0x00f9: 0xfef5, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM 0x00fa: 0xfef6, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM 0x00fb: 0xfedd, # ARABIC LETTER LAM ISOLATED FORM 0x00fc: 0xfed9, # ARABIC LETTER KAF ISOLATED FORM 0x00fd: 0xfef1, # ARABIC LETTER YEH ISOLATED FORM 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: None, # UNDEFINED }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'\u066a' # 0x0025 -> ARABIC PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xb0' # 0x0080 -> DEGREE SIGN u'\xb7' # 0x0081 -> MIDDLE DOT u'\u2219' # 0x0082 -> BULLET OPERATOR u'\u221a' # 0x0083 -> SQUARE ROOT u'\u2592' # 0x0084 -> MEDIUM SHADE u'\u2500' # 0x0085 -> FORMS LIGHT HORIZONTAL u'\u2502' # 0x0086 -> FORMS LIGHT VERTICAL u'\u253c' # 0x0087 -> FORMS LIGHT VERTICAL AND HORIZONTAL u'\u2524' # 0x0088 -> FORMS LIGHT VERTICAL AND LEFT u'\u252c' # 0x0089 -> FORMS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x008a -> FORMS LIGHT VERTICAL AND RIGHT u'\u2534' # 0x008b -> FORMS LIGHT UP AND HORIZONTAL u'\u2510' # 0x008c -> FORMS LIGHT DOWN AND LEFT u'\u250c' # 0x008d -> FORMS LIGHT DOWN AND RIGHT u'\u2514' # 0x008e -> FORMS LIGHT UP AND RIGHT u'\u2518' # 0x008f -> FORMS LIGHT UP AND LEFT u'\u03b2' # 0x0090 -> GREEK SMALL BETA u'\u221e' # 0x0091 -> INFINITY u'\u03c6' # 0x0092 -> GREEK SMALL PHI u'\xb1' # 0x0093 -> PLUS-OR-MINUS SIGN u'\xbd' # 0x0094 -> FRACTION 1/2 u'\xbc' # 0x0095 -> FRACTION 1/4 u'\u2248' # 0x0096 -> ALMOST EQUAL TO u'\xab' # 0x0097 -> LEFT POINTING GUILLEMET u'\xbb' # 0x0098 -> RIGHT POINTING GUILLEMET u'\ufef7' # 0x0099 -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM u'\ufef8' # 0x009a -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM u'\ufffe' # 0x009b -> UNDEFINED u'\ufffe' # 0x009c -> UNDEFINED u'\ufefb' # 0x009d -> ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM u'\ufefc' # 0x009e -> ARABIC LIGATURE LAM WITH ALEF FINAL FORM u'\ufffe' # 0x009f -> UNDEFINED u'\xa0' # 0x00a0 -> NON-BREAKING SPACE u'\xad' # 0x00a1 -> SOFT HYPHEN u'\ufe82' # 0x00a2 -> ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM u'\xa3' # 0x00a3 -> POUND SIGN u'\xa4' # 0x00a4 -> CURRENCY SIGN u'\ufe84' # 0x00a5 -> ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM u'\ufffe' # 0x00a6 -> UNDEFINED u'\ufffe' # 0x00a7 -> UNDEFINED u'\ufe8e' # 0x00a8 -> ARABIC LETTER ALEF FINAL FORM u'\ufe8f' # 0x00a9 -> ARABIC LETTER BEH ISOLATED FORM u'\ufe95' # 0x00aa -> ARABIC LETTER TEH ISOLATED FORM u'\ufe99' # 0x00ab -> ARABIC LETTER THEH ISOLATED FORM u'\u060c' # 0x00ac -> ARABIC COMMA u'\ufe9d' # 0x00ad -> ARABIC LETTER JEEM ISOLATED FORM u'\ufea1' # 0x00ae -> ARABIC LETTER HAH ISOLATED FORM u'\ufea5' # 0x00af -> ARABIC LETTER KHAH ISOLATED FORM u'\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO u'\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE u'\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO u'\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE u'\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR u'\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE u'\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX u'\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN u'\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT u'\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE u'\ufed1' # 0x00ba -> ARABIC LETTER FEH ISOLATED FORM u'\u061b' # 0x00bb -> ARABIC SEMICOLON u'\ufeb1' # 0x00bc -> ARABIC LETTER SEEN ISOLATED FORM u'\ufeb5' # 0x00bd -> ARABIC LETTER SHEEN ISOLATED FORM u'\ufeb9' # 0x00be -> ARABIC LETTER SAD ISOLATED FORM u'\u061f' # 0x00bf -> ARABIC QUESTION MARK u'\xa2' # 0x00c0 -> CENT SIGN u'\ufe80' # 0x00c1 -> ARABIC LETTER HAMZA ISOLATED FORM u'\ufe81' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM u'\ufe83' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM u'\ufe85' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM u'\ufeca' # 0x00c5 -> ARABIC LETTER AIN FINAL FORM u'\ufe8b' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM u'\ufe8d' # 0x00c7 -> ARABIC LETTER ALEF ISOLATED FORM u'\ufe91' # 0x00c8 -> ARABIC LETTER BEH INITIAL FORM u'\ufe93' # 0x00c9 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM u'\ufe97' # 0x00ca -> ARABIC LETTER TEH INITIAL FORM u'\ufe9b' # 0x00cb -> ARABIC LETTER THEH INITIAL FORM u'\ufe9f' # 0x00cc -> ARABIC LETTER JEEM INITIAL FORM u'\ufea3' # 0x00cd -> ARABIC LETTER HAH INITIAL FORM u'\ufea7' # 0x00ce -> ARABIC LETTER KHAH INITIAL FORM u'\ufea9' # 0x00cf -> ARABIC LETTER DAL ISOLATED FORM u'\ufeab' # 0x00d0 -> ARABIC LETTER THAL ISOLATED FORM u'\ufead' # 0x00d1 -> ARABIC LETTER REH ISOLATED FORM u'\ufeaf' # 0x00d2 -> ARABIC LETTER ZAIN ISOLATED FORM u'\ufeb3' # 0x00d3 -> ARABIC LETTER SEEN INITIAL FORM u'\ufeb7' # 0x00d4 -> ARABIC LETTER SHEEN INITIAL FORM u'\ufebb' # 0x00d5 -> ARABIC LETTER SAD INITIAL FORM u'\ufebf' # 0x00d6 -> ARABIC LETTER DAD INITIAL FORM u'\ufec1' # 0x00d7 -> ARABIC LETTER TAH ISOLATED FORM u'\ufec5' # 0x00d8 -> ARABIC LETTER ZAH ISOLATED FORM u'\ufecb' # 0x00d9 -> ARABIC LETTER AIN INITIAL FORM u'\ufecf' # 0x00da -> ARABIC LETTER GHAIN INITIAL FORM u'\xa6' # 0x00db -> BROKEN VERTICAL BAR u'\xac' # 0x00dc -> NOT SIGN u'\xf7' # 0x00dd -> DIVISION SIGN u'\xd7' # 0x00de -> MULTIPLICATION SIGN u'\ufec9' # 0x00df -> ARABIC LETTER AIN ISOLATED FORM u'\u0640' # 0x00e0 -> ARABIC TATWEEL u'\ufed3' # 0x00e1 -> ARABIC LETTER FEH INITIAL FORM u'\ufed7' # 0x00e2 -> ARABIC LETTER QAF INITIAL FORM u'\ufedb' # 0x00e3 -> ARABIC LETTER KAF INITIAL FORM u'\ufedf' # 0x00e4 -> ARABIC LETTER LAM INITIAL FORM u'\ufee3' # 0x00e5 -> ARABIC LETTER MEEM INITIAL FORM u'\ufee7' # 0x00e6 -> ARABIC LETTER NOON INITIAL FORM u'\ufeeb' # 0x00e7 -> ARABIC LETTER HEH INITIAL FORM u'\ufeed' # 0x00e8 -> ARABIC LETTER WAW ISOLATED FORM u'\ufeef' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA ISOLATED FORM u'\ufef3' # 0x00ea -> ARABIC LETTER YEH INITIAL FORM u'\ufebd' # 0x00eb -> ARABIC LETTER DAD ISOLATED FORM u'\ufecc' # 0x00ec -> ARABIC LETTER AIN MEDIAL FORM u'\ufece' # 0x00ed -> ARABIC LETTER GHAIN FINAL FORM u'\ufecd' # 0x00ee -> ARABIC LETTER GHAIN ISOLATED FORM u'\ufee1' # 0x00ef -> ARABIC LETTER MEEM ISOLATED FORM u'\ufe7d' # 0x00f0 -> ARABIC SHADDA MEDIAL FORM u'\u0651' # 0x00f1 -> ARABIC SHADDAH u'\ufee5' # 0x00f2 -> ARABIC LETTER NOON ISOLATED FORM u'\ufee9' # 0x00f3 -> ARABIC LETTER HEH ISOLATED FORM u'\ufeec' # 0x00f4 -> ARABIC LETTER HEH MEDIAL FORM u'\ufef0' # 0x00f5 -> ARABIC LETTER ALEF MAKSURA FINAL FORM u'\ufef2' # 0x00f6 -> ARABIC LETTER YEH FINAL FORM u'\ufed0' # 0x00f7 -> ARABIC LETTER GHAIN MEDIAL FORM u'\ufed5' # 0x00f8 -> ARABIC LETTER QAF ISOLATED FORM u'\ufef5' # 0x00f9 -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM u'\ufef6' # 0x00fa -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM u'\ufedd' # 0x00fb -> ARABIC LETTER LAM ISOLATED FORM u'\ufed9' # 0x00fc -> ARABIC LETTER KAF ISOLATED FORM u'\ufef1' # 0x00fd -> ARABIC LETTER YEH ISOLATED FORM u'\u25a0' # 0x00fe -> BLACK SQUARE u'\ufffe' # 0x00ff -> UNDEFINED ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00a0, # NON-BREAKING SPACE 0x00a2: 0x00c0, # CENT SIGN 0x00a3: 0x00a3, # POUND SIGN 0x00a4: 0x00a4, # CURRENCY SIGN 0x00a6: 0x00db, # BROKEN VERTICAL BAR 0x00ab: 0x0097, # LEFT POINTING GUILLEMET 0x00ac: 0x00dc, # NOT SIGN 0x00ad: 0x00a1, # SOFT HYPHEN 0x00b0: 0x0080, # DEGREE SIGN 0x00b1: 0x0093, # PLUS-OR-MINUS SIGN 0x00b7: 0x0081, # MIDDLE DOT 0x00bb: 0x0098, # RIGHT POINTING GUILLEMET 0x00bc: 0x0095, # FRACTION 1/4 0x00bd: 0x0094, # FRACTION 1/2 0x00d7: 0x00de, # MULTIPLICATION SIGN 0x00f7: 0x00dd, # DIVISION SIGN 0x03b2: 0x0090, # GREEK SMALL BETA 0x03c6: 0x0092, # GREEK SMALL PHI 0x060c: 0x00ac, # ARABIC COMMA 0x061b: 0x00bb, # ARABIC SEMICOLON 0x061f: 0x00bf, # ARABIC QUESTION MARK 0x0640: 0x00e0, # ARABIC TATWEEL 0x0651: 0x00f1, # ARABIC SHADDAH 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE 0x066a: 0x0025, # ARABIC PERCENT SIGN 0x2219: 0x0082, # BULLET OPERATOR 0x221a: 0x0083, # SQUARE ROOT 0x221e: 0x0091, # INFINITY 0x2248: 0x0096, # ALMOST EQUAL TO 0x2500: 0x0085, # FORMS LIGHT HORIZONTAL 0x2502: 0x0086, # FORMS LIGHT VERTICAL 0x250c: 0x008d, # FORMS LIGHT DOWN AND RIGHT 0x2510: 0x008c, # FORMS LIGHT DOWN AND LEFT 0x2514: 0x008e, # FORMS LIGHT UP AND RIGHT 0x2518: 0x008f, # FORMS LIGHT UP AND LEFT 0x251c: 0x008a, # FORMS LIGHT VERTICAL AND RIGHT 0x2524: 0x0088, # FORMS LIGHT VERTICAL AND LEFT 0x252c: 0x0089, # FORMS LIGHT DOWN AND HORIZONTAL 0x2534: 0x008b, # FORMS LIGHT UP AND HORIZONTAL 0x253c: 0x0087, # FORMS LIGHT VERTICAL AND HORIZONTAL 0x2592: 0x0084, # MEDIUM SHADE 0x25a0: 0x00fe, # BLACK SQUARE 0xfe7d: 0x00f0, # ARABIC SHADDA MEDIAL FORM 0xfe80: 0x00c1, # ARABIC LETTER HAMZA ISOLATED FORM 0xfe81: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM 0xfe82: 0x00a2, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM 0xfe83: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM 0xfe84: 0x00a5, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM 0xfe85: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM 0xfe8b: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM 0xfe8d: 0x00c7, # ARABIC LETTER ALEF ISOLATED FORM 0xfe8e: 0x00a8, # ARABIC LETTER ALEF FINAL FORM 0xfe8f: 0x00a9, # ARABIC LETTER BEH ISOLATED FORM 0xfe91: 0x00c8, # ARABIC LETTER BEH INITIAL FORM 0xfe93: 0x00c9, # ARABIC LETTER TEH MARBUTA ISOLATED FORM 0xfe95: 0x00aa, # ARABIC LETTER TEH ISOLATED FORM 0xfe97: 0x00ca, # ARABIC LETTER TEH INITIAL FORM 0xfe99: 0x00ab, # ARABIC LETTER THEH ISOLATED FORM 0xfe9b: 0x00cb, # ARABIC LETTER THEH INITIAL FORM 0xfe9d: 0x00ad, # ARABIC LETTER JEEM ISOLATED FORM 0xfe9f: 0x00cc, # ARABIC LETTER JEEM INITIAL FORM 0xfea1: 0x00ae, # ARABIC LETTER HAH ISOLATED FORM 0xfea3: 0x00cd, # ARABIC LETTER HAH INITIAL FORM 0xfea5: 0x00af, # ARABIC LETTER KHAH ISOLATED FORM 0xfea7: 0x00ce, # ARABIC LETTER KHAH INITIAL FORM 0xfea9: 0x00cf, # ARABIC LETTER DAL ISOLATED FORM 0xfeab: 0x00d0, # ARABIC LETTER THAL ISOLATED FORM 0xfead: 0x00d1, # ARABIC LETTER REH ISOLATED FORM 0xfeaf: 0x00d2, # ARABIC LETTER ZAIN ISOLATED FORM 0xfeb1: 0x00bc, # ARABIC LETTER SEEN ISOLATED FORM 0xfeb3: 0x00d3, # ARABIC LETTER SEEN INITIAL FORM 0xfeb5: 0x00bd, # ARABIC LETTER SHEEN ISOLATED FORM 0xfeb7: 0x00d4, # ARABIC LETTER SHEEN INITIAL FORM 0xfeb9: 0x00be, # ARABIC LETTER SAD ISOLATED FORM 0xfebb: 0x00d5, # ARABIC LETTER SAD INITIAL FORM 0xfebd: 0x00eb, # ARABIC LETTER DAD ISOLATED FORM 0xfebf: 0x00d6, # ARABIC LETTER DAD INITIAL FORM 0xfec1: 0x00d7, # ARABIC LETTER TAH ISOLATED FORM 0xfec5: 0x00d8, # ARABIC LETTER ZAH ISOLATED FORM 0xfec9: 0x00df, # ARABIC LETTER AIN ISOLATED FORM 0xfeca: 0x00c5, # ARABIC LETTER AIN FINAL FORM 0xfecb: 0x00d9, # ARABIC LETTER AIN INITIAL FORM 0xfecc: 0x00ec, # ARABIC LETTER AIN MEDIAL FORM 0xfecd: 0x00ee, # ARABIC LETTER GHAIN ISOLATED FORM 0xfece: 0x00ed, # ARABIC LETTER GHAIN FINAL FORM 0xfecf: 0x00da, # ARABIC LETTER GHAIN INITIAL FORM 0xfed0: 0x00f7, # ARABIC LETTER GHAIN MEDIAL FORM 0xfed1: 0x00ba, # ARABIC LETTER FEH ISOLATED FORM 0xfed3: 0x00e1, # ARABIC LETTER FEH INITIAL FORM 0xfed5: 0x00f8, # ARABIC LETTER QAF ISOLATED FORM 0xfed7: 0x00e2, # ARABIC LETTER QAF INITIAL FORM 0xfed9: 0x00fc, # ARABIC LETTER KAF ISOLATED FORM 0xfedb: 0x00e3, # ARABIC LETTER KAF INITIAL FORM 0xfedd: 0x00fb, # ARABIC LETTER LAM ISOLATED FORM 0xfedf: 0x00e4, # ARABIC LETTER LAM INITIAL FORM 0xfee1: 0x00ef, # ARABIC LETTER MEEM ISOLATED FORM 0xfee3: 0x00e5, # ARABIC LETTER MEEM INITIAL FORM 0xfee5: 0x00f2, # ARABIC LETTER NOON ISOLATED FORM 0xfee7: 0x00e6, # ARABIC LETTER NOON INITIAL FORM 0xfee9: 0x00f3, # ARABIC LETTER HEH ISOLATED FORM 0xfeeb: 0x00e7, # ARABIC LETTER HEH INITIAL FORM 0xfeec: 0x00f4, # ARABIC LETTER HEH MEDIAL FORM 0xfeed: 0x00e8, # ARABIC LETTER WAW ISOLATED FORM 0xfeef: 0x00e9, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM 0xfef0: 0x00f5, # ARABIC LETTER ALEF MAKSURA FINAL FORM 0xfef1: 0x00fd, # ARABIC LETTER YEH ISOLATED FORM 0xfef2: 0x00f6, # ARABIC LETTER YEH FINAL FORM 0xfef3: 0x00ea, # ARABIC LETTER YEH INITIAL FORM 0xfef5: 0x00f9, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM 0xfef6: 0x00fa, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM 0xfef7: 0x0099, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM 0xfef8: 0x009a, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM 0xfefb: 0x009d, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM 0xfefc: 0x009e, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp865.py0000644000076500000240000010407212612565546023143 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP865.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp865', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x009e: 0x20a7, # PESETA SIGN 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00a8: 0x00bf, # INVERTED QUESTION MARK 0x00a9: 0x2310, # REVERSED NOT SIGN 0x00aa: 0x00ac, # NOT SIGN 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00a4, # CURRENCY SIGN 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00e3: 0x03c0, # GREEK SMALL LETTER PI 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00e6: 0x00b5, # MICRO SIGN 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA 0x00ec: 0x221e, # INFINITY 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00ef: 0x2229, # INTERSECTION 0x00f0: 0x2261, # IDENTICAL TO 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO 0x00f4: 0x2320, # TOP HALF INTEGRAL 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL 0x00f6: 0x00f7, # DIVISION SIGN 0x00f7: 0x2248, # ALMOST EQUAL TO 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N 0x00fd: 0x00b2, # SUPERSCRIPT TWO 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE u'\xa3' # 0x009c -> POUND SIGN u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE u'\u20a7' # 0x009e -> PESETA SIGN u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK u'\u2310' # 0x00a9 -> REVERSED NOT SIGN u'\xac' # 0x00aa -> NOT SIGN u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xa4' # 0x00af -> CURRENCY SIGN u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA u'\xb5' # 0x00e6 -> MICRO SIGN u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA u'\u221e' # 0x00ec -> INFINITY u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON u'\u2229' # 0x00ef -> INTERSECTION u'\u2261' # 0x00f0 -> IDENTICAL TO u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL u'\xf7' # 0x00f6 -> DIVISION SIGN u'\u2248' # 0x00f7 -> ALMOST EQUAL TO u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N u'\xb2' # 0x00fd -> SUPERSCRIPT TWO u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK 0x00a3: 0x009c, # POUND SIGN 0x00a4: 0x00af, # CURRENCY SIGN 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x00aa, # NOT SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x00fd, # SUPERSCRIPT TWO 0x00b5: 0x00e6, # MICRO SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x00bf: 0x00a8, # INVERTED QUESTION MARK 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x00f6, # DIVISION SIGN 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON 0x03c0: 0x00e3, # GREEK SMALL LETTER PI 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N 0x20a7: 0x009e, # PESETA SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x221e: 0x00ec, # INFINITY 0x2229: 0x00ef, # INTERSECTION 0x2248: 0x00f7, # ALMOST EQUAL TO 0x2261: 0x00f0, # IDENTICAL TO 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO 0x2310: 0x00a9, # REVERSED NOT SIGN 0x2320: 0x00f4, # TOP HALF INTEGRAL 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp866.py0000644000076500000240000010353412612565546023146 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP866.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp866', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A 0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE 0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE 0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE 0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE 0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE 0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE 0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE 0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I 0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I 0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA 0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL 0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM 0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN 0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O 0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE 0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER 0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES 0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE 0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U 0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF 0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA 0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE 0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE 0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA 0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA 0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN 0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU 0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN 0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E 0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU 0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A 0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE 0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE 0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE 0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE 0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE 0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE 0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE 0x00a8: 0x0438, # CYRILLIC SMALL LETTER I 0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I 0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA 0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL 0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM 0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN 0x00ae: 0x043e, # CYRILLIC SMALL LETTER O 0x00af: 0x043f, # CYRILLIC SMALL LETTER PE 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x258c, # LEFT HALF BLOCK 0x00de: 0x2590, # RIGHT HALF BLOCK 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER 0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES 0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE 0x00e3: 0x0443, # CYRILLIC SMALL LETTER U 0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF 0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA 0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE 0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE 0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA 0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA 0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN 0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU 0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN 0x00ed: 0x044d, # CYRILLIC SMALL LETTER E 0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU 0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA 0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO 0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO 0x00f2: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE 0x00f3: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE 0x00f4: 0x0407, # CYRILLIC CAPITAL LETTER YI 0x00f5: 0x0457, # CYRILLIC SMALL LETTER YI 0x00f6: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U 0x00f7: 0x045e, # CYRILLIC SMALL LETTER SHORT U 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x2219, # BULLET OPERATOR 0x00fa: 0x00b7, # MIDDLE DOT 0x00fb: 0x221a, # SQUARE ROOT 0x00fc: 0x2116, # NUMERO SIGN 0x00fd: 0x00a4, # CURRENCY SIGN 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE u'\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE u'\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE u'\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE u'\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE u'\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE u'\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE u'\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U u'\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF u'\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA u'\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE u'\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE u'\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA u'\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA u'\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN u'\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU u'\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E u'\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU u'\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA u'\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A u'\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE u'\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE u'\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE u'\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE u'\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE u'\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE u'\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I u'\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA u'\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL u'\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM u'\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN u'\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O u'\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u258c' # 0x00dd -> LEFT HALF BLOCK u'\u2590' # 0x00de -> RIGHT HALF BLOCK u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U u'\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF u'\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA u'\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE u'\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE u'\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA u'\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA u'\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN u'\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU u'\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E u'\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU u'\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA u'\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO u'\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO u'\u0404' # 0x00f2 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\u0454' # 0x00f3 -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\u0407' # 0x00f4 -> CYRILLIC CAPITAL LETTER YI u'\u0457' # 0x00f5 -> CYRILLIC SMALL LETTER YI u'\u040e' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHORT U u'\u045e' # 0x00f7 -> CYRILLIC SMALL LETTER SHORT U u'\xb0' # 0x00f8 -> DEGREE SIGN u'\u2219' # 0x00f9 -> BULLET OPERATOR u'\xb7' # 0x00fa -> MIDDLE DOT u'\u221a' # 0x00fb -> SQUARE ROOT u'\u2116' # 0x00fc -> NUMERO SIGN u'\xa4' # 0x00fd -> CURRENCY SIGN u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a4: 0x00fd, # CURRENCY SIGN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b7: 0x00fa, # MIDDLE DOT 0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO 0x0404: 0x00f2, # CYRILLIC CAPITAL LETTER UKRAINIAN IE 0x0407: 0x00f4, # CYRILLIC CAPITAL LETTER YI 0x040e: 0x00f6, # CYRILLIC CAPITAL LETTER SHORT U 0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A 0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE 0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE 0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE 0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE 0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE 0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE 0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE 0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I 0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I 0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA 0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL 0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM 0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN 0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O 0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE 0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER 0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES 0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE 0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U 0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF 0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA 0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE 0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE 0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA 0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA 0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN 0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU 0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN 0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E 0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU 0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A 0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE 0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE 0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE 0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE 0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE 0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE 0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE 0x0438: 0x00a8, # CYRILLIC SMALL LETTER I 0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I 0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA 0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL 0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM 0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN 0x043e: 0x00ae, # CYRILLIC SMALL LETTER O 0x043f: 0x00af, # CYRILLIC SMALL LETTER PE 0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER 0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES 0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE 0x0443: 0x00e3, # CYRILLIC SMALL LETTER U 0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF 0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA 0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE 0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE 0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA 0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA 0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN 0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU 0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN 0x044d: 0x00ed, # CYRILLIC SMALL LETTER E 0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU 0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA 0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO 0x0454: 0x00f3, # CYRILLIC SMALL LETTER UKRAINIAN IE 0x0457: 0x00f5, # CYRILLIC SMALL LETTER YI 0x045e: 0x00f7, # CYRILLIC SMALL LETTER SHORT U 0x2116: 0x00fc, # NUMERO SIGN 0x2219: 0x00f9, # BULLET OPERATOR 0x221a: 0x00fb, # SQUARE ROOT 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x258c: 0x00dd, # LEFT HALF BLOCK 0x2590: 0x00de, # RIGHT HALF BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp869.py0000644000076500000240000010070512612565546023146 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP869.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp869', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: None, # UNDEFINED 0x0081: None, # UNDEFINED 0x0082: None, # UNDEFINED 0x0083: None, # UNDEFINED 0x0084: None, # UNDEFINED 0x0085: None, # UNDEFINED 0x0086: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS 0x0087: None, # UNDEFINED 0x0088: 0x00b7, # MIDDLE DOT 0x0089: 0x00ac, # NOT SIGN 0x008a: 0x00a6, # BROKEN BAR 0x008b: 0x2018, # LEFT SINGLE QUOTATION MARK 0x008c: 0x2019, # RIGHT SINGLE QUOTATION MARK 0x008d: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS 0x008e: 0x2015, # HORIZONTAL BAR 0x008f: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS 0x0090: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS 0x0091: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA 0x0092: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS 0x0093: None, # UNDEFINED 0x0094: None, # UNDEFINED 0x0095: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS 0x0096: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA 0x0097: 0x00a9, # COPYRIGHT SIGN 0x0098: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS 0x0099: 0x00b2, # SUPERSCRIPT TWO 0x009a: 0x00b3, # SUPERSCRIPT THREE 0x009b: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS 0x009c: 0x00a3, # POUND SIGN 0x009d: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS 0x009e: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS 0x009f: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS 0x00a0: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA 0x00a1: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS 0x00a2: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS 0x00a3: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS 0x00a4: 0x0391, # GREEK CAPITAL LETTER ALPHA 0x00a5: 0x0392, # GREEK CAPITAL LETTER BETA 0x00a6: 0x0393, # GREEK CAPITAL LETTER GAMMA 0x00a7: 0x0394, # GREEK CAPITAL LETTER DELTA 0x00a8: 0x0395, # GREEK CAPITAL LETTER EPSILON 0x00a9: 0x0396, # GREEK CAPITAL LETTER ZETA 0x00aa: 0x0397, # GREEK CAPITAL LETTER ETA 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF 0x00ac: 0x0398, # GREEK CAPITAL LETTER THETA 0x00ad: 0x0399, # GREEK CAPITAL LETTER IOTA 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00b0: 0x2591, # LIGHT SHADE 0x00b1: 0x2592, # MEDIUM SHADE 0x00b2: 0x2593, # DARK SHADE 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x00b5: 0x039a, # GREEK CAPITAL LETTER KAPPA 0x00b6: 0x039b, # GREEK CAPITAL LETTER LAMDA 0x00b7: 0x039c, # GREEK CAPITAL LETTER MU 0x00b8: 0x039d, # GREEK CAPITAL LETTER NU 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT 0x00bd: 0x039e, # GREEK CAPITAL LETTER XI 0x00be: 0x039f, # GREEK CAPITAL LETTER OMICRON 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x00c6: 0x03a0, # GREEK CAPITAL LETTER PI 0x00c7: 0x03a1, # GREEK CAPITAL LETTER RHO 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x00cf: 0x03a3, # GREEK CAPITAL LETTER SIGMA 0x00d0: 0x03a4, # GREEK CAPITAL LETTER TAU 0x00d1: 0x03a5, # GREEK CAPITAL LETTER UPSILON 0x00d2: 0x03a6, # GREEK CAPITAL LETTER PHI 0x00d3: 0x03a7, # GREEK CAPITAL LETTER CHI 0x00d4: 0x03a8, # GREEK CAPITAL LETTER PSI 0x00d5: 0x03a9, # GREEK CAPITAL LETTER OMEGA 0x00d6: 0x03b1, # GREEK SMALL LETTER ALPHA 0x00d7: 0x03b2, # GREEK SMALL LETTER BETA 0x00d8: 0x03b3, # GREEK SMALL LETTER GAMMA 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x00db: 0x2588, # FULL BLOCK 0x00dc: 0x2584, # LOWER HALF BLOCK 0x00dd: 0x03b4, # GREEK SMALL LETTER DELTA 0x00de: 0x03b5, # GREEK SMALL LETTER EPSILON 0x00df: 0x2580, # UPPER HALF BLOCK 0x00e0: 0x03b6, # GREEK SMALL LETTER ZETA 0x00e1: 0x03b7, # GREEK SMALL LETTER ETA 0x00e2: 0x03b8, # GREEK SMALL LETTER THETA 0x00e3: 0x03b9, # GREEK SMALL LETTER IOTA 0x00e4: 0x03ba, # GREEK SMALL LETTER KAPPA 0x00e5: 0x03bb, # GREEK SMALL LETTER LAMDA 0x00e6: 0x03bc, # GREEK SMALL LETTER MU 0x00e7: 0x03bd, # GREEK SMALL LETTER NU 0x00e8: 0x03be, # GREEK SMALL LETTER XI 0x00e9: 0x03bf, # GREEK SMALL LETTER OMICRON 0x00ea: 0x03c0, # GREEK SMALL LETTER PI 0x00eb: 0x03c1, # GREEK SMALL LETTER RHO 0x00ec: 0x03c3, # GREEK SMALL LETTER SIGMA 0x00ed: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA 0x00ee: 0x03c4, # GREEK SMALL LETTER TAU 0x00ef: 0x0384, # GREEK TONOS 0x00f0: 0x00ad, # SOFT HYPHEN 0x00f1: 0x00b1, # PLUS-MINUS SIGN 0x00f2: 0x03c5, # GREEK SMALL LETTER UPSILON 0x00f3: 0x03c6, # GREEK SMALL LETTER PHI 0x00f4: 0x03c7, # GREEK SMALL LETTER CHI 0x00f5: 0x00a7, # SECTION SIGN 0x00f6: 0x03c8, # GREEK SMALL LETTER PSI 0x00f7: 0x0385, # GREEK DIALYTIKA TONOS 0x00f8: 0x00b0, # DEGREE SIGN 0x00f9: 0x00a8, # DIAERESIS 0x00fa: 0x03c9, # GREEK SMALL LETTER OMEGA 0x00fb: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 0x00fc: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS 0x00fd: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS 0x00fe: 0x25a0, # BLACK SQUARE 0x00ff: 0x00a0, # NO-BREAK SPACE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> NULL u'\x01' # 0x0001 -> START OF HEADING u'\x02' # 0x0002 -> START OF TEXT u'\x03' # 0x0003 -> END OF TEXT u'\x04' # 0x0004 -> END OF TRANSMISSION u'\x05' # 0x0005 -> ENQUIRY u'\x06' # 0x0006 -> ACKNOWLEDGE u'\x07' # 0x0007 -> BELL u'\x08' # 0x0008 -> BACKSPACE u'\t' # 0x0009 -> HORIZONTAL TABULATION u'\n' # 0x000a -> LINE FEED u'\x0b' # 0x000b -> VERTICAL TABULATION u'\x0c' # 0x000c -> FORM FEED u'\r' # 0x000d -> CARRIAGE RETURN u'\x0e' # 0x000e -> SHIFT OUT u'\x0f' # 0x000f -> SHIFT IN u'\x10' # 0x0010 -> DATA LINK ESCAPE u'\x11' # 0x0011 -> DEVICE CONTROL ONE u'\x12' # 0x0012 -> DEVICE CONTROL TWO u'\x13' # 0x0013 -> DEVICE CONTROL THREE u'\x14' # 0x0014 -> DEVICE CONTROL FOUR u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x0016 -> SYNCHRONOUS IDLE u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK u'\x18' # 0x0018 -> CANCEL u'\x19' # 0x0019 -> END OF MEDIUM u'\x1a' # 0x001a -> SUBSTITUTE u'\x1b' # 0x001b -> ESCAPE u'\x1c' # 0x001c -> FILE SEPARATOR u'\x1d' # 0x001d -> GROUP SEPARATOR u'\x1e' # 0x001e -> RECORD SEPARATOR u'\x1f' # 0x001f -> UNIT SEPARATOR u' ' # 0x0020 -> SPACE u'!' # 0x0021 -> EXCLAMATION MARK u'"' # 0x0022 -> QUOTATION MARK u'#' # 0x0023 -> NUMBER SIGN u'$' # 0x0024 -> DOLLAR SIGN u'%' # 0x0025 -> PERCENT SIGN u'&' # 0x0026 -> AMPERSAND u"'" # 0x0027 -> APOSTROPHE u'(' # 0x0028 -> LEFT PARENTHESIS u')' # 0x0029 -> RIGHT PARENTHESIS u'*' # 0x002a -> ASTERISK u'+' # 0x002b -> PLUS SIGN u',' # 0x002c -> COMMA u'-' # 0x002d -> HYPHEN-MINUS u'.' # 0x002e -> FULL STOP u'/' # 0x002f -> SOLIDUS u'0' # 0x0030 -> DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE u'2' # 0x0032 -> DIGIT TWO u'3' # 0x0033 -> DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE u':' # 0x003a -> COLON u';' # 0x003b -> SEMICOLON u'<' # 0x003c -> LESS-THAN SIGN u'=' # 0x003d -> EQUALS SIGN u'>' # 0x003e -> GREATER-THAN SIGN u'?' # 0x003f -> QUESTION MARK u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET u'\\' # 0x005c -> REVERSE SOLIDUS u']' # 0x005d -> RIGHT SQUARE BRACKET u'^' # 0x005e -> CIRCUMFLEX ACCENT u'_' # 0x005f -> LOW LINE u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET u'|' # 0x007c -> VERTICAL LINE u'}' # 0x007d -> RIGHT CURLY BRACKET u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> DELETE u'\ufffe' # 0x0080 -> UNDEFINED u'\ufffe' # 0x0081 -> UNDEFINED u'\ufffe' # 0x0082 -> UNDEFINED u'\ufffe' # 0x0083 -> UNDEFINED u'\ufffe' # 0x0084 -> UNDEFINED u'\ufffe' # 0x0085 -> UNDEFINED u'\u0386' # 0x0086 -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\ufffe' # 0x0087 -> UNDEFINED u'\xb7' # 0x0088 -> MIDDLE DOT u'\xac' # 0x0089 -> NOT SIGN u'\xa6' # 0x008a -> BROKEN BAR u'\u2018' # 0x008b -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x008c -> RIGHT SINGLE QUOTATION MARK u'\u0388' # 0x008d -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u2015' # 0x008e -> HORIZONTAL BAR u'\u0389' # 0x008f -> GREEK CAPITAL LETTER ETA WITH TONOS u'\u038a' # 0x0090 -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\u03aa' # 0x0091 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u038c' # 0x0092 -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\ufffe' # 0x0093 -> UNDEFINED u'\ufffe' # 0x0094 -> UNDEFINED u'\u038e' # 0x0095 -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u03ab' # 0x0096 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'\xa9' # 0x0097 -> COPYRIGHT SIGN u'\u038f' # 0x0098 -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'\xb2' # 0x0099 -> SUPERSCRIPT TWO u'\xb3' # 0x009a -> SUPERSCRIPT THREE u'\u03ac' # 0x009b -> GREEK SMALL LETTER ALPHA WITH TONOS u'\xa3' # 0x009c -> POUND SIGN u'\u03ad' # 0x009d -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0x009e -> GREEK SMALL LETTER ETA WITH TONOS u'\u03af' # 0x009f -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03ca' # 0x00a0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u0390' # 0x00a1 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS u'\u03cc' # 0x00a2 -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u03cd' # 0x00a3 -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u0391' # 0x00a4 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0x00a5 -> GREEK CAPITAL LETTER BETA u'\u0393' # 0x00a6 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0x00a7 -> GREEK CAPITAL LETTER DELTA u'\u0395' # 0x00a8 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0x00a9 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0x00aa -> GREEK CAPITAL LETTER ETA u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF u'\u0398' # 0x00ac -> GREEK CAPITAL LETTER THETA u'\u0399' # 0x00ad -> GREEK CAPITAL LETTER IOTA u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2591' # 0x00b0 -> LIGHT SHADE u'\u2592' # 0x00b1 -> MEDIUM SHADE u'\u2593' # 0x00b2 -> DARK SHADE u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u039a' # 0x00b5 -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0x00b6 -> GREEK CAPITAL LETTER LAMDA u'\u039c' # 0x00b7 -> GREEK CAPITAL LETTER MU u'\u039d' # 0x00b8 -> GREEK CAPITAL LETTER NU u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u039e' # 0x00bd -> GREEK CAPITAL LETTER XI u'\u039f' # 0x00be -> GREEK CAPITAL LETTER OMICRON u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u03a0' # 0x00c6 -> GREEK CAPITAL LETTER PI u'\u03a1' # 0x00c7 -> GREEK CAPITAL LETTER RHO u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\u03a3' # 0x00cf -> GREEK CAPITAL LETTER SIGMA u'\u03a4' # 0x00d0 -> GREEK CAPITAL LETTER TAU u'\u03a5' # 0x00d1 -> GREEK CAPITAL LETTER UPSILON u'\u03a6' # 0x00d2 -> GREEK CAPITAL LETTER PHI u'\u03a7' # 0x00d3 -> GREEK CAPITAL LETTER CHI u'\u03a8' # 0x00d4 -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0x00d5 -> GREEK CAPITAL LETTER OMEGA u'\u03b1' # 0x00d6 -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0x00d7 -> GREEK SMALL LETTER BETA u'\u03b3' # 0x00d8 -> GREEK SMALL LETTER GAMMA u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2588' # 0x00db -> FULL BLOCK u'\u2584' # 0x00dc -> LOWER HALF BLOCK u'\u03b4' # 0x00dd -> GREEK SMALL LETTER DELTA u'\u03b5' # 0x00de -> GREEK SMALL LETTER EPSILON u'\u2580' # 0x00df -> UPPER HALF BLOCK u'\u03b6' # 0x00e0 -> GREEK SMALL LETTER ZETA u'\u03b7' # 0x00e1 -> GREEK SMALL LETTER ETA u'\u03b8' # 0x00e2 -> GREEK SMALL LETTER THETA u'\u03b9' # 0x00e3 -> GREEK SMALL LETTER IOTA u'\u03ba' # 0x00e4 -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0x00e5 -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0x00e6 -> GREEK SMALL LETTER MU u'\u03bd' # 0x00e7 -> GREEK SMALL LETTER NU u'\u03be' # 0x00e8 -> GREEK SMALL LETTER XI u'\u03bf' # 0x00e9 -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0x00ea -> GREEK SMALL LETTER PI u'\u03c1' # 0x00eb -> GREEK SMALL LETTER RHO u'\u03c3' # 0x00ec -> GREEK SMALL LETTER SIGMA u'\u03c2' # 0x00ed -> GREEK SMALL LETTER FINAL SIGMA u'\u03c4' # 0x00ee -> GREEK SMALL LETTER TAU u'\u0384' # 0x00ef -> GREEK TONOS u'\xad' # 0x00f0 -> SOFT HYPHEN u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN u'\u03c5' # 0x00f2 -> GREEK SMALL LETTER UPSILON u'\u03c6' # 0x00f3 -> GREEK SMALL LETTER PHI u'\u03c7' # 0x00f4 -> GREEK SMALL LETTER CHI u'\xa7' # 0x00f5 -> SECTION SIGN u'\u03c8' # 0x00f6 -> GREEK SMALL LETTER PSI u'\u0385' # 0x00f7 -> GREEK DIALYTIKA TONOS u'\xb0' # 0x00f8 -> DEGREE SIGN u'\xa8' # 0x00f9 -> DIAERESIS u'\u03c9' # 0x00fa -> GREEK SMALL LETTER OMEGA u'\u03cb' # 0x00fb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u03b0' # 0x00fc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS u'\u03ce' # 0x00fd -> GREEK SMALL LETTER OMEGA WITH TONOS u'\u25a0' # 0x00fe -> BLACK SQUARE u'\xa0' # 0x00ff -> NO-BREAK SPACE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # NULL 0x0001: 0x0001, # START OF HEADING 0x0002: 0x0002, # START OF TEXT 0x0003: 0x0003, # END OF TEXT 0x0004: 0x0004, # END OF TRANSMISSION 0x0005: 0x0005, # ENQUIRY 0x0006: 0x0006, # ACKNOWLEDGE 0x0007: 0x0007, # BELL 0x0008: 0x0008, # BACKSPACE 0x0009: 0x0009, # HORIZONTAL TABULATION 0x000a: 0x000a, # LINE FEED 0x000b: 0x000b, # VERTICAL TABULATION 0x000c: 0x000c, # FORM FEED 0x000d: 0x000d, # CARRIAGE RETURN 0x000e: 0x000e, # SHIFT OUT 0x000f: 0x000f, # SHIFT IN 0x0010: 0x0010, # DATA LINK ESCAPE 0x0011: 0x0011, # DEVICE CONTROL ONE 0x0012: 0x0012, # DEVICE CONTROL TWO 0x0013: 0x0013, # DEVICE CONTROL THREE 0x0014: 0x0014, # DEVICE CONTROL FOUR 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE 0x0016: 0x0016, # SYNCHRONOUS IDLE 0x0017: 0x0017, # END OF TRANSMISSION BLOCK 0x0018: 0x0018, # CANCEL 0x0019: 0x0019, # END OF MEDIUM 0x001a: 0x001a, # SUBSTITUTE 0x001b: 0x001b, # ESCAPE 0x001c: 0x001c, # FILE SEPARATOR 0x001d: 0x001d, # GROUP SEPARATOR 0x001e: 0x001e, # RECORD SEPARATOR 0x001f: 0x001f, # UNIT SEPARATOR 0x0020: 0x0020, # SPACE 0x0021: 0x0021, # EXCLAMATION MARK 0x0022: 0x0022, # QUOTATION MARK 0x0023: 0x0023, # NUMBER SIGN 0x0024: 0x0024, # DOLLAR SIGN 0x0025: 0x0025, # PERCENT SIGN 0x0026: 0x0026, # AMPERSAND 0x0027: 0x0027, # APOSTROPHE 0x0028: 0x0028, # LEFT PARENTHESIS 0x0029: 0x0029, # RIGHT PARENTHESIS 0x002a: 0x002a, # ASTERISK 0x002b: 0x002b, # PLUS SIGN 0x002c: 0x002c, # COMMA 0x002d: 0x002d, # HYPHEN-MINUS 0x002e: 0x002e, # FULL STOP 0x002f: 0x002f, # SOLIDUS 0x0030: 0x0030, # DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE 0x0032: 0x0032, # DIGIT TWO 0x0033: 0x0033, # DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE 0x003a: 0x003a, # COLON 0x003b: 0x003b, # SEMICOLON 0x003c: 0x003c, # LESS-THAN SIGN 0x003d: 0x003d, # EQUALS SIGN 0x003e: 0x003e, # GREATER-THAN SIGN 0x003f: 0x003f, # QUESTION MARK 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET 0x005c: 0x005c, # REVERSE SOLIDUS 0x005d: 0x005d, # RIGHT SQUARE BRACKET 0x005e: 0x005e, # CIRCUMFLEX ACCENT 0x005f: 0x005f, # LOW LINE 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET 0x007c: 0x007c, # VERTICAL LINE 0x007d: 0x007d, # RIGHT CURLY BRACKET 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # DELETE 0x00a0: 0x00ff, # NO-BREAK SPACE 0x00a3: 0x009c, # POUND SIGN 0x00a6: 0x008a, # BROKEN BAR 0x00a7: 0x00f5, # SECTION SIGN 0x00a8: 0x00f9, # DIAERESIS 0x00a9: 0x0097, # COPYRIGHT SIGN 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00ac: 0x0089, # NOT SIGN 0x00ad: 0x00f0, # SOFT HYPHEN 0x00b0: 0x00f8, # DEGREE SIGN 0x00b1: 0x00f1, # PLUS-MINUS SIGN 0x00b2: 0x0099, # SUPERSCRIPT TWO 0x00b3: 0x009a, # SUPERSCRIPT THREE 0x00b7: 0x0088, # MIDDLE DOT 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF 0x0384: 0x00ef, # GREEK TONOS 0x0385: 0x00f7, # GREEK DIALYTIKA TONOS 0x0386: 0x0086, # GREEK CAPITAL LETTER ALPHA WITH TONOS 0x0388: 0x008d, # GREEK CAPITAL LETTER EPSILON WITH TONOS 0x0389: 0x008f, # GREEK CAPITAL LETTER ETA WITH TONOS 0x038a: 0x0090, # GREEK CAPITAL LETTER IOTA WITH TONOS 0x038c: 0x0092, # GREEK CAPITAL LETTER OMICRON WITH TONOS 0x038e: 0x0095, # GREEK CAPITAL LETTER UPSILON WITH TONOS 0x038f: 0x0098, # GREEK CAPITAL LETTER OMEGA WITH TONOS 0x0390: 0x00a1, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS 0x0391: 0x00a4, # GREEK CAPITAL LETTER ALPHA 0x0392: 0x00a5, # GREEK CAPITAL LETTER BETA 0x0393: 0x00a6, # GREEK CAPITAL LETTER GAMMA 0x0394: 0x00a7, # GREEK CAPITAL LETTER DELTA 0x0395: 0x00a8, # GREEK CAPITAL LETTER EPSILON 0x0396: 0x00a9, # GREEK CAPITAL LETTER ZETA 0x0397: 0x00aa, # GREEK CAPITAL LETTER ETA 0x0398: 0x00ac, # GREEK CAPITAL LETTER THETA 0x0399: 0x00ad, # GREEK CAPITAL LETTER IOTA 0x039a: 0x00b5, # GREEK CAPITAL LETTER KAPPA 0x039b: 0x00b6, # GREEK CAPITAL LETTER LAMDA 0x039c: 0x00b7, # GREEK CAPITAL LETTER MU 0x039d: 0x00b8, # GREEK CAPITAL LETTER NU 0x039e: 0x00bd, # GREEK CAPITAL LETTER XI 0x039f: 0x00be, # GREEK CAPITAL LETTER OMICRON 0x03a0: 0x00c6, # GREEK CAPITAL LETTER PI 0x03a1: 0x00c7, # GREEK CAPITAL LETTER RHO 0x03a3: 0x00cf, # GREEK CAPITAL LETTER SIGMA 0x03a4: 0x00d0, # GREEK CAPITAL LETTER TAU 0x03a5: 0x00d1, # GREEK CAPITAL LETTER UPSILON 0x03a6: 0x00d2, # GREEK CAPITAL LETTER PHI 0x03a7: 0x00d3, # GREEK CAPITAL LETTER CHI 0x03a8: 0x00d4, # GREEK CAPITAL LETTER PSI 0x03a9: 0x00d5, # GREEK CAPITAL LETTER OMEGA 0x03aa: 0x0091, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA 0x03ab: 0x0096, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA 0x03ac: 0x009b, # GREEK SMALL LETTER ALPHA WITH TONOS 0x03ad: 0x009d, # GREEK SMALL LETTER EPSILON WITH TONOS 0x03ae: 0x009e, # GREEK SMALL LETTER ETA WITH TONOS 0x03af: 0x009f, # GREEK SMALL LETTER IOTA WITH TONOS 0x03b0: 0x00fc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS 0x03b1: 0x00d6, # GREEK SMALL LETTER ALPHA 0x03b2: 0x00d7, # GREEK SMALL LETTER BETA 0x03b3: 0x00d8, # GREEK SMALL LETTER GAMMA 0x03b4: 0x00dd, # GREEK SMALL LETTER DELTA 0x03b5: 0x00de, # GREEK SMALL LETTER EPSILON 0x03b6: 0x00e0, # GREEK SMALL LETTER ZETA 0x03b7: 0x00e1, # GREEK SMALL LETTER ETA 0x03b8: 0x00e2, # GREEK SMALL LETTER THETA 0x03b9: 0x00e3, # GREEK SMALL LETTER IOTA 0x03ba: 0x00e4, # GREEK SMALL LETTER KAPPA 0x03bb: 0x00e5, # GREEK SMALL LETTER LAMDA 0x03bc: 0x00e6, # GREEK SMALL LETTER MU 0x03bd: 0x00e7, # GREEK SMALL LETTER NU 0x03be: 0x00e8, # GREEK SMALL LETTER XI 0x03bf: 0x00e9, # GREEK SMALL LETTER OMICRON 0x03c0: 0x00ea, # GREEK SMALL LETTER PI 0x03c1: 0x00eb, # GREEK SMALL LETTER RHO 0x03c2: 0x00ed, # GREEK SMALL LETTER FINAL SIGMA 0x03c3: 0x00ec, # GREEK SMALL LETTER SIGMA 0x03c4: 0x00ee, # GREEK SMALL LETTER TAU 0x03c5: 0x00f2, # GREEK SMALL LETTER UPSILON 0x03c6: 0x00f3, # GREEK SMALL LETTER PHI 0x03c7: 0x00f4, # GREEK SMALL LETTER CHI 0x03c8: 0x00f6, # GREEK SMALL LETTER PSI 0x03c9: 0x00fa, # GREEK SMALL LETTER OMEGA 0x03ca: 0x00a0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA 0x03cb: 0x00fb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 0x03cc: 0x00a2, # GREEK SMALL LETTER OMICRON WITH TONOS 0x03cd: 0x00a3, # GREEK SMALL LETTER UPSILON WITH TONOS 0x03ce: 0x00fd, # GREEK SMALL LETTER OMEGA WITH TONOS 0x2015: 0x008e, # HORIZONTAL BAR 0x2018: 0x008b, # LEFT SINGLE QUOTATION MARK 0x2019: 0x008c, # RIGHT SINGLE QUOTATION MARK 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL 0x2580: 0x00df, # UPPER HALF BLOCK 0x2584: 0x00dc, # LOWER HALF BLOCK 0x2588: 0x00db, # FULL BLOCK 0x2591: 0x00b0, # LIGHT SHADE 0x2592: 0x00b1, # MEDIUM SHADE 0x2593: 0x00b2, # DARK SHADE 0x25a0: 0x00fe, # BLACK SQUARE } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp874.py0000644000076500000240000003106312612565546023142 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp874', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u20ac' # 0x80 -> EURO SIGN u'\ufffe' # 0x81 -> UNDEFINED u'\ufffe' # 0x82 -> UNDEFINED u'\ufffe' # 0x83 -> UNDEFINED u'\ufffe' # 0x84 -> UNDEFINED u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS u'\ufffe' # 0x86 -> UNDEFINED u'\ufffe' # 0x87 -> UNDEFINED u'\ufffe' # 0x88 -> UNDEFINED u'\ufffe' # 0x89 -> UNDEFINED u'\ufffe' # 0x8A -> UNDEFINED u'\ufffe' # 0x8B -> UNDEFINED u'\ufffe' # 0x8C -> UNDEFINED u'\ufffe' # 0x8D -> UNDEFINED u'\ufffe' # 0x8E -> UNDEFINED u'\ufffe' # 0x8F -> UNDEFINED u'\ufffe' # 0x90 -> UNDEFINED u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK u'\u2022' # 0x95 -> BULLET u'\u2013' # 0x96 -> EN DASH u'\u2014' # 0x97 -> EM DASH u'\ufffe' # 0x98 -> UNDEFINED u'\ufffe' # 0x99 -> UNDEFINED u'\ufffe' # 0x9A -> UNDEFINED u'\ufffe' # 0x9B -> UNDEFINED u'\ufffe' # 0x9C -> UNDEFINED u'\ufffe' # 0x9D -> UNDEFINED u'\ufffe' # 0x9E -> UNDEFINED u'\ufffe' # 0x9F -> UNDEFINED u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA u'\u0e24' # 0xC4 -> THAI CHARACTER RU u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING u'\u0e26' # 0xC6 -> THAI CHARACTER LU u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU u'\ufffe' # 0xDB -> UNDEFINED u'\ufffe' # 0xDC -> UNDEFINED u'\ufffe' # 0xDD -> UNDEFINED u'\ufffe' # 0xDE -> UNDEFINED u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN u'\u0e50' # 0xF0 -> THAI DIGIT ZERO u'\u0e51' # 0xF1 -> THAI DIGIT ONE u'\u0e52' # 0xF2 -> THAI DIGIT TWO u'\u0e53' # 0xF3 -> THAI DIGIT THREE u'\u0e54' # 0xF4 -> THAI DIGIT FOUR u'\u0e55' # 0xF5 -> THAI DIGIT FIVE u'\u0e56' # 0xF6 -> THAI DIGIT SIX u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT u'\u0e59' # 0xF9 -> THAI DIGIT NINE u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT u'\ufffe' # 0xFC -> UNDEFINED u'\ufffe' # 0xFD -> UNDEFINED u'\ufffe' # 0xFE -> UNDEFINED u'\ufffe' # 0xFF -> UNDEFINED ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp875.py0000644000076500000240000003146612612565546023152 0ustar jmstaff00000000000000""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='cp875', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x9c' # 0x04 -> CONTROL u'\t' # 0x05 -> HORIZONTAL TABULATION u'\x86' # 0x06 -> CONTROL u'\x7f' # 0x07 -> DELETE u'\x97' # 0x08 -> CONTROL u'\x8d' # 0x09 -> CONTROL u'\x8e' # 0x0A -> CONTROL u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x9d' # 0x14 -> CONTROL u'\x85' # 0x15 -> CONTROL u'\x08' # 0x16 -> BACKSPACE u'\x87' # 0x17 -> CONTROL u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x92' # 0x1A -> CONTROL u'\x8f' # 0x1B -> CONTROL u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u'\x80' # 0x20 -> CONTROL u'\x81' # 0x21 -> CONTROL u'\x82' # 0x22 -> CONTROL u'\x83' # 0x23 -> CONTROL u'\x84' # 0x24 -> CONTROL u'\n' # 0x25 -> LINE FEED u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK u'\x1b' # 0x27 -> ESCAPE u'\x88' # 0x28 -> CONTROL u'\x89' # 0x29 -> CONTROL u'\x8a' # 0x2A -> CONTROL u'\x8b' # 0x2B -> CONTROL u'\x8c' # 0x2C -> CONTROL u'\x05' # 0x2D -> ENQUIRY u'\x06' # 0x2E -> ACKNOWLEDGE u'\x07' # 0x2F -> BELL u'\x90' # 0x30 -> CONTROL u'\x91' # 0x31 -> CONTROL u'\x16' # 0x32 -> SYNCHRONOUS IDLE u'\x93' # 0x33 -> CONTROL u'\x94' # 0x34 -> CONTROL u'\x95' # 0x35 -> CONTROL u'\x96' # 0x36 -> CONTROL u'\x04' # 0x37 -> END OF TRANSMISSION u'\x98' # 0x38 -> CONTROL u'\x99' # 0x39 -> CONTROL u'\x9a' # 0x3A -> CONTROL u'\x9b' # 0x3B -> CONTROL u'\x14' # 0x3C -> DEVICE CONTROL FOUR u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE u'\x9e' # 0x3E -> CONTROL u'\x1a' # 0x3F -> SUBSTITUTE u' ' # 0x40 -> SPACE u'\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA u'\u0393' # 0x43 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0x44 -> GREEK CAPITAL LETTER DELTA u'\u0395' # 0x45 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0x46 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA u'\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA u'\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA u'[' # 0x4A -> LEFT SQUARE BRACKET u'.' # 0x4B -> FULL STOP u'<' # 0x4C -> LESS-THAN SIGN u'(' # 0x4D -> LEFT PARENTHESIS u'+' # 0x4E -> PLUS SIGN u'!' # 0x4F -> EXCLAMATION MARK u'&' # 0x50 -> AMPERSAND u'\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA u'\u039c' # 0x53 -> GREEK CAPITAL LETTER MU u'\u039d' # 0x54 -> GREEK CAPITAL LETTER NU u'\u039e' # 0x55 -> GREEK CAPITAL LETTER XI u'\u039f' # 0x56 -> GREEK CAPITAL LETTER OMICRON u'\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI u'\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO u'\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA u']' # 0x5A -> RIGHT SQUARE BRACKET u'$' # 0x5B -> DOLLAR SIGN u'*' # 0x5C -> ASTERISK u')' # 0x5D -> RIGHT PARENTHESIS u';' # 0x5E -> SEMICOLON u'^' # 0x5F -> CIRCUMFLEX ACCENT u'-' # 0x60 -> HYPHEN-MINUS u'/' # 0x61 -> SOLIDUS u'\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU u'\u03a5' # 0x63 -> GREEK CAPITAL LETTER UPSILON u'\u03a6' # 0x64 -> GREEK CAPITAL LETTER PHI u'\u03a7' # 0x65 -> GREEK CAPITAL LETTER CHI u'\u03a8' # 0x66 -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA u'\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'|' # 0x6A -> VERTICAL LINE u',' # 0x6B -> COMMA u'%' # 0x6C -> PERCENT SIGN u'_' # 0x6D -> LOW LINE u'>' # 0x6E -> GREATER-THAN SIGN u'?' # 0x6F -> QUESTION MARK u'\xa8' # 0x70 -> DIAERESIS u'\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u0389' # 0x73 -> GREEK CAPITAL LETTER ETA WITH TONOS u'\xa0' # 0x74 -> NO-BREAK SPACE u'\u038a' # 0x75 -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\u038c' # 0x76 -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'`' # 0x79 -> GRAVE ACCENT u':' # 0x7A -> COLON u'#' # 0x7B -> NUMBER SIGN u'@' # 0x7C -> COMMERCIAL AT u"'" # 0x7D -> APOSTROPHE u'=' # 0x7E -> EQUALS SIGN u'"' # 0x7F -> QUOTATION MARK u'\u0385' # 0x80 -> GREEK DIALYTIKA TONOS u'a' # 0x81 -> LATIN SMALL LETTER A u'b' # 0x82 -> LATIN SMALL LETTER B u'c' # 0x83 -> LATIN SMALL LETTER C u'd' # 0x84 -> LATIN SMALL LETTER D u'e' # 0x85 -> LATIN SMALL LETTER E u'f' # 0x86 -> LATIN SMALL LETTER F u'g' # 0x87 -> LATIN SMALL LETTER G u'h' # 0x88 -> LATIN SMALL LETTER H u'i' # 0x89 -> LATIN SMALL LETTER I u'\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0x8B -> GREEK SMALL LETTER BETA u'\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA u'\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA u'\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON u'\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA u'\xb0' # 0x90 -> DEGREE SIGN u'j' # 0x91 -> LATIN SMALL LETTER J u'k' # 0x92 -> LATIN SMALL LETTER K u'l' # 0x93 -> LATIN SMALL LETTER L u'm' # 0x94 -> LATIN SMALL LETTER M u'n' # 0x95 -> LATIN SMALL LETTER N u'o' # 0x96 -> LATIN SMALL LETTER O u'p' # 0x97 -> LATIN SMALL LETTER P u'q' # 0x98 -> LATIN SMALL LETTER Q u'r' # 0x99 -> LATIN SMALL LETTER R u'\u03b7' # 0x9A -> GREEK SMALL LETTER ETA u'\u03b8' # 0x9B -> GREEK SMALL LETTER THETA u'\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA u'\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0x9F -> GREEK SMALL LETTER MU u'\xb4' # 0xA0 -> ACUTE ACCENT u'~' # 0xA1 -> TILDE u's' # 0xA2 -> LATIN SMALL LETTER S u't' # 0xA3 -> LATIN SMALL LETTER T u'u' # 0xA4 -> LATIN SMALL LETTER U u'v' # 0xA5 -> LATIN SMALL LETTER V u'w' # 0xA6 -> LATIN SMALL LETTER W u'x' # 0xA7 -> LATIN SMALL LETTER X u'y' # 0xA8 -> LATIN SMALL LETTER Y u'z' # 0xA9 -> LATIN SMALL LETTER Z u'\u03bd' # 0xAA -> GREEK SMALL LETTER NU u'\u03be' # 0xAB -> GREEK SMALL LETTER XI u'\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0xAD -> GREEK SMALL LETTER PI u'\u03c1' # 0xAE -> GREEK SMALL LETTER RHO u'\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA u'\xa3' # 0xB0 -> POUND SIGN u'\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS u'\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS u'\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS u'\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA u'\u03c4' # 0xBB -> GREEK SMALL LETTER TAU u'\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON u'\u03c6' # 0xBD -> GREEK SMALL LETTER PHI u'\u03c7' # 0xBE -> GREEK SMALL LETTER CHI u'\u03c8' # 0xBF -> GREEK SMALL LETTER PSI u'{' # 0xC0 -> LEFT CURLY BRACKET u'A' # 0xC1 -> LATIN CAPITAL LETTER A u'B' # 0xC2 -> LATIN CAPITAL LETTER B u'C' # 0xC3 -> LATIN CAPITAL LETTER C u'D' # 0xC4 -> LATIN CAPITAL LETTER D u'E' # 0xC5 -> LATIN CAPITAL LETTER E u'F' # 0xC6 -> LATIN CAPITAL LETTER F u'G' # 0xC7 -> LATIN CAPITAL LETTER G u'H' # 0xC8 -> LATIN CAPITAL LETTER H u'I' # 0xC9 -> LATIN CAPITAL LETTER I u'\xad' # 0xCA -> SOFT HYPHEN u'\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA u'\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS u'\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS u'\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK u'\u2015' # 0xCF -> HORIZONTAL BAR u'}' # 0xD0 -> RIGHT CURLY BRACKET u'J' # 0xD1 -> LATIN CAPITAL LETTER J u'K' # 0xD2 -> LATIN CAPITAL LETTER K u'L' # 0xD3 -> LATIN CAPITAL LETTER L u'M' # 0xD4 -> LATIN CAPITAL LETTER M u'N' # 0xD5 -> LATIN CAPITAL LETTER N u'O' # 0xD6 -> LATIN CAPITAL LETTER O u'P' # 0xD7 -> LATIN CAPITAL LETTER P u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q u'R' # 0xD9 -> LATIN CAPITAL LETTER R u'\xb1' # 0xDA -> PLUS-MINUS SIGN u'\xbd' # 0xDB -> VULGAR FRACTION ONE HALF u'\x1a' # 0xDC -> SUBSTITUTE u'\u0387' # 0xDD -> GREEK ANO TELEIA u'\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK u'\xa6' # 0xDF -> BROKEN BAR u'\\' # 0xE0 -> REVERSE SOLIDUS u'\x1a' # 0xE1 -> SUBSTITUTE u'S' # 0xE2 -> LATIN CAPITAL LETTER S u'T' # 0xE3 -> LATIN CAPITAL LETTER T u'U' # 0xE4 -> LATIN CAPITAL LETTER U u'V' # 0xE5 -> LATIN CAPITAL LETTER V u'W' # 0xE6 -> LATIN CAPITAL LETTER W u'X' # 0xE7 -> LATIN CAPITAL LETTER X u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z u'\xb2' # 0xEA -> SUPERSCRIPT TWO u'\xa7' # 0xEB -> SECTION SIGN u'\x1a' # 0xEC -> SUBSTITUTE u'\x1a' # 0xED -> SUBSTITUTE u'\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xEF -> NOT SIGN u'0' # 0xF0 -> DIGIT ZERO u'1' # 0xF1 -> DIGIT ONE u'2' # 0xF2 -> DIGIT TWO u'3' # 0xF3 -> DIGIT THREE u'4' # 0xF4 -> DIGIT FOUR u'5' # 0xF5 -> DIGIT FIVE u'6' # 0xF6 -> DIGIT SIX u'7' # 0xF7 -> DIGIT SEVEN u'8' # 0xF8 -> DIGIT EIGHT u'9' # 0xF9 -> DIGIT NINE u'\xb3' # 0xFA -> SUPERSCRIPT THREE u'\xa9' # 0xFB -> COPYRIGHT SIGN u'\x1a' # 0xFC -> SUBSTITUTE u'\x1a' # 0xFD -> SUBSTITUTE u'\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\x9f' # 0xFF -> CONTROL ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp932.py0000644000076500000240000000177712612565546023146 0ustar jmstaff00000000000000# # cp932.py: Python Unicode Codec for CP932 # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('cp932') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='cp932', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp949.py0000644000076500000240000000177712612565546023156 0ustar jmstaff00000000000000# # cp949.py: Python Unicode Codec for CP949 # # Written by Hye-Shik Chang # import _codecs_kr, codecs import _multibytecodec as mbc codec = _codecs_kr.getcodec('cp949') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='cp949', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/cp950.py0000644000076500000240000000177712612565546023146 0ustar jmstaff00000000000000# # cp950.py: Python Unicode Codec for CP950 # # Written by Hye-Shik Chang # import _codecs_tw, codecs import _multibytecodec as mbc codec = _codecs_tw.getcodec('cp950') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='cp950', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/euc_jis_2004.py0000644000076500000240000000203312612565546024356 0ustar jmstaff00000000000000# # euc_jis_2004.py: Python Unicode Codec for EUC_JIS_2004 # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('euc_jis_2004') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='euc_jis_2004', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/euc_jisx0213.py0000644000076500000240000000203312612565546024407 0ustar jmstaff00000000000000# # euc_jisx0213.py: Python Unicode Codec for EUC_JISX0213 # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('euc_jisx0213') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='euc_jisx0213', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/euc_jp.py0000644000076500000240000000200312612565546023532 0ustar jmstaff00000000000000# # euc_jp.py: Python Unicode Codec for EUC_JP # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('euc_jp') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='euc_jp', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/euc_kr.py0000644000076500000240000000200312612565546023535 0ustar jmstaff00000000000000# # euc_kr.py: Python Unicode Codec for EUC_KR # # Written by Hye-Shik Chang # import _codecs_kr, codecs import _multibytecodec as mbc codec = _codecs_kr.getcodec('euc_kr') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='euc_kr', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/gb18030.py0000644000076500000240000000200712612565546023255 0ustar jmstaff00000000000000# # gb18030.py: Python Unicode Codec for GB18030 # # Written by Hye-Shik Chang # import _codecs_cn, codecs import _multibytecodec as mbc codec = _codecs_cn.getcodec('gb18030') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='gb18030', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/gb2312.py0000644000076500000240000000200312612565546023165 0ustar jmstaff00000000000000# # gb2312.py: Python Unicode Codec for GB2312 # # Written by Hye-Shik Chang # import _codecs_cn, codecs import _multibytecodec as mbc codec = _codecs_cn.getcodec('gb2312') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='gb2312', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/gbk.py0000644000076500000240000000176712612565546023050 0ustar jmstaff00000000000000# # gbk.py: Python Unicode Codec for GBK # # Written by Hye-Shik Chang # import _codecs_cn, codecs import _multibytecodec as mbc codec = _codecs_cn.getcodec('gbk') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='gbk', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/hex_codec.py0000644000076500000240000000440512612565546024216 0ustar jmstaff00000000000000""" Python 'hex_codec' Codec - 2-digit hex content transfer encoding Unlike most of the other codecs which target Unicode, this codec will return Python string objects for both encode and decode. Written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs, binascii ### Codec APIs def hex_encode(input,errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = binascii.b2a_hex(input) return (output, len(input)) def hex_decode(input,errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = binascii.a2b_hex(input) return (output, len(input)) class Codec(codecs.Codec): def encode(self, input,errors='strict'): return hex_encode(input,errors) def decode(self, input,errors='strict'): return hex_decode(input,errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): assert self.errors == 'strict' return binascii.b2a_hex(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): assert self.errors == 'strict' return binascii.a2b_hex(input) class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='hex', encode=hex_encode, decode=hex_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/hp_roman8.py0000644000076500000240000001633712612565546024177 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py. Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen) Original source: LaserJet IIP Printer User's Manual HP part no 33471-90901, Hewlet-Packard, June 1989. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_map)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='hp-roman8', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x00a1: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE 0x00a2: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX 0x00a3: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE 0x00a4: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX 0x00a5: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS 0x00a6: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 0x00a7: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS 0x00a8: 0x00b4, # ACUTE ACCENT 0x00a9: 0x02cb, # MODIFIER LETTER GRAVE ACCENT (Mandarin Chinese fourth tone) 0x00aa: 0x02c6, # MODIFIER LETTER CIRCUMFLEX ACCENT 0x00ab: 0x00a8, # DIAERESIS 0x00ac: 0x02dc, # SMALL TILDE 0x00ad: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE 0x00ae: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 0x00af: 0x20a4, # LIRA SIGN 0x00b0: 0x00af, # MACRON 0x00b1: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00b2: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x00b3: 0x00b0, # DEGREE SIGN 0x00b4: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00b5: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x00b6: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x00b7: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x00b8: 0x00a1, # INVERTED EXCLAMATION MARK 0x00b9: 0x00bf, # INVERTED QUESTION MARK 0x00ba: 0x00a4, # CURRENCY SIGN 0x00bb: 0x00a3, # POUND SIGN 0x00bc: 0x00a5, # YEN SIGN 0x00bd: 0x00a7, # SECTION SIGN 0x00be: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x00bf: 0x00a2, # CENT SIGN 0x00c0: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00c1: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00c2: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00c3: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00c4: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x00c5: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x00c6: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x00c7: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x00c8: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x00c9: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x00ca: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE 0x00cb: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x00cc: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x00cd: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ce: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x00cf: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x00d0: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE 0x00d1: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00d2: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE 0x00d3: 0x00c6, # LATIN CAPITAL LETTER AE 0x00d4: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE 0x00d5: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x00d6: 0x00f8, # LATIN SMALL LETTER O WITH STROKE 0x00d7: 0x00e6, # LATIN SMALL LETTER AE 0x00d8: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00d9: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE 0x00da: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00db: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00dc: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x00dd: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x00de: 0x00df, # LATIN SMALL LETTER SHARP S (German) 0x00df: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00e0: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00e1: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE 0x00e2: 0x00e3, # LATIN SMALL LETTER A WITH TILDE 0x00e3: 0x00d0, # LATIN CAPITAL LETTER ETH (Icelandic) 0x00e4: 0x00f0, # LATIN SMALL LETTER ETH (Icelandic) 0x00e5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00e6: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE 0x00e7: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00e8: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE 0x00e9: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00ea: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x00eb: 0x0160, # LATIN CAPITAL LETTER S WITH CARON 0x00ec: 0x0161, # LATIN SMALL LETTER S WITH CARON 0x00ed: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00ee: 0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS 0x00ef: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS 0x00f0: 0x00de, # LATIN CAPITAL LETTER THORN (Icelandic) 0x00f1: 0x00fe, # LATIN SMALL LETTER THORN (Icelandic) 0x00f2: 0x00b7, # MIDDLE DOT 0x00f3: 0x00b5, # MICRO SIGN 0x00f4: 0x00b6, # PILCROW SIGN 0x00f5: 0x00be, # VULGAR FRACTION THREE QUARTERS 0x00f6: 0x2014, # EM DASH 0x00f7: 0x00bc, # VULGAR FRACTION ONE QUARTER 0x00f8: 0x00bd, # VULGAR FRACTION ONE HALF 0x00f9: 0x00aa, # FEMININE ORDINAL INDICATOR 0x00fa: 0x00ba, # MASCULINE ORDINAL INDICATOR 0x00fb: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00fc: 0x25a0, # BLACK SQUARE 0x00fd: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00fe: 0x00b1, # PLUS-MINUS SIGN 0x00ff: None, }) ### Encoding Map encoding_map = codecs.make_encoding_map(decoding_map) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/hz.py0000644000076500000240000000176312612565546022722 0ustar jmstaff00000000000000# # hz.py: Python Unicode Codec for HZ # # Written by Hye-Shik Chang # import _codecs_cn, codecs import _multibytecodec as mbc codec = _codecs_cn.getcodec('hz') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='hz', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/idna.py0000644000076500000240000002043212612565546023206 0ustar jmstaff00000000000000# This module implements the RFCs 3490 (IDNA) and 3491 (Nameprep) import stringprep, re, codecs from unicodedata import ucd_3_2_0 as unicodedata # IDNA section 3.1 dots = re.compile(u"[\u002E\u3002\uFF0E\uFF61]") # IDNA section 5 ace_prefix = "xn--" uace_prefix = unicode(ace_prefix, "ascii") # This assumes query strings, so AllowUnassigned is true def nameprep(label): # Map newlabel = [] for c in label: if stringprep.in_table_b1(c): # Map to nothing continue newlabel.append(stringprep.map_table_b2(c)) label = u"".join(newlabel) # Normalize label = unicodedata.normalize("NFKC", label) # Prohibit for c in label: if stringprep.in_table_c12(c) or \ stringprep.in_table_c22(c) or \ stringprep.in_table_c3(c) or \ stringprep.in_table_c4(c) or \ stringprep.in_table_c5(c) or \ stringprep.in_table_c6(c) or \ stringprep.in_table_c7(c) or \ stringprep.in_table_c8(c) or \ stringprep.in_table_c9(c): raise UnicodeError("Invalid character %r" % c) # Check bidi RandAL = map(stringprep.in_table_d1, label) for c in RandAL: if c: # There is a RandAL char in the string. Must perform further # tests: # 1) The characters in section 5.8 MUST be prohibited. # This is table C.8, which was already checked # 2) If a string contains any RandALCat character, the string # MUST NOT contain any LCat character. if filter(stringprep.in_table_d2, label): raise UnicodeError("Violation of BIDI requirement 2") # 3) If a string contains any RandALCat character, a # RandALCat character MUST be the first character of the # string, and a RandALCat character MUST be the last # character of the string. if not RandAL[0] or not RandAL[-1]: raise UnicodeError("Violation of BIDI requirement 3") return label def ToASCII(label): try: # Step 1: try ASCII label = label.encode("ascii") except UnicodeError: pass else: # Skip to step 3: UseSTD3ASCIIRules is false, so # Skip to step 8. if 0 < len(label) < 64: return label raise UnicodeError("label empty or too long") # Step 2: nameprep label = nameprep(label) # Step 3: UseSTD3ASCIIRules is false # Step 4: try ASCII try: label = label.encode("ascii") except UnicodeError: pass else: # Skip to step 8. if 0 < len(label) < 64: return label raise UnicodeError("label empty or too long") # Step 5: Check ACE prefix if label.startswith(uace_prefix): raise UnicodeError("Label starts with ACE prefix") # Step 6: Encode with PUNYCODE label = label.encode("punycode") # Step 7: Prepend ACE prefix label = ace_prefix + label # Step 8: Check size if 0 < len(label) < 64: return label raise UnicodeError("label empty or too long") def ToUnicode(label): # Step 1: Check for ASCII if isinstance(label, str): pure_ascii = True else: try: label = label.encode("ascii") pure_ascii = True except UnicodeError: pure_ascii = False if not pure_ascii: # Step 2: Perform nameprep label = nameprep(label) # It doesn't say this, but apparently, it should be ASCII now try: label = label.encode("ascii") except UnicodeError: raise UnicodeError("Invalid character in IDN label") # Step 3: Check for ACE prefix if not label.startswith(ace_prefix): return unicode(label, "ascii") # Step 4: Remove ACE prefix label1 = label[len(ace_prefix):] # Step 5: Decode using PUNYCODE result = label1.decode("punycode") # Step 6: Apply ToASCII label2 = ToASCII(result) # Step 7: Compare the result of step 6 with the one of step 3 # label2 will already be in lower case. if label.lower() != label2: raise UnicodeError("IDNA does not round-trip", label, label2) # Step 8: return the result of step 5 return result ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): if errors != 'strict': # IDNA is quite clear that implementations must be strict raise UnicodeError("unsupported error handling "+errors) if not input: return "", 0 result = [] labels = dots.split(input) if labels and len(labels[-1])==0: trailing_dot = '.' del labels[-1] else: trailing_dot = '' for label in labels: result.append(ToASCII(label)) # Join with U+002E return ".".join(result)+trailing_dot, len(input) def decode(self,input,errors='strict'): if errors != 'strict': raise UnicodeError("Unsupported error handling "+errors) if not input: return u"", 0 # IDNA allows decoding to operate on Unicode strings, too. if isinstance(input, unicode): labels = dots.split(input) else: # Must be ASCII string input = str(input) unicode(input, "ascii") labels = input.split(".") if labels and len(labels[-1]) == 0: trailing_dot = u'.' del labels[-1] else: trailing_dot = u'' result = [] for label in labels: result.append(ToUnicode(label)) return u".".join(result)+trailing_dot, len(input) class IncrementalEncoder(codecs.BufferedIncrementalEncoder): def _buffer_encode(self, input, errors, final): if errors != 'strict': # IDNA is quite clear that implementations must be strict raise UnicodeError("unsupported error handling "+errors) if not input: return ("", 0) labels = dots.split(input) trailing_dot = u'' if labels: if not labels[-1]: trailing_dot = '.' del labels[-1] elif not final: # Keep potentially unfinished label until the next call del labels[-1] if labels: trailing_dot = '.' result = [] size = 0 for label in labels: result.append(ToASCII(label)) if size: size += 1 size += len(label) # Join with U+002E result = ".".join(result) + trailing_dot size += len(trailing_dot) return (result, size) class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def _buffer_decode(self, input, errors, final): if errors != 'strict': raise UnicodeError("Unsupported error handling "+errors) if not input: return (u"", 0) # IDNA allows decoding to operate on Unicode strings, too. if isinstance(input, unicode): labels = dots.split(input) else: # Must be ASCII string input = str(input) unicode(input, "ascii") labels = input.split(".") trailing_dot = u'' if labels: if not labels[-1]: trailing_dot = u'.' del labels[-1] elif not final: # Keep potentially unfinished label until the next call del labels[-1] if labels: trailing_dot = u'.' result = [] size = 0 for label in labels: result.append(ToUnicode(label)) if size: size += 1 size += len(label) result = u".".join(result) + trailing_dot size += len(trailing_dot) return (result, size) class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='idna', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp.py0000644000076500000240000000203512612565546024063 0ustar jmstaff00000000000000# # iso2022_jp.py: Python Unicode Codec for ISO2022_JP # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp_1.py0000644000076500000240000000204512612565546024304 0ustar jmstaff00000000000000# # iso2022_jp_1.py: Python Unicode Codec for ISO2022_JP_1 # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_1') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_1', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp_2.py0000644000076500000240000000204512612565546024305 0ustar jmstaff00000000000000# # iso2022_jp_2.py: Python Unicode Codec for ISO2022_JP_2 # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_2') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_2', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp_2004.py0000644000076500000240000000206112612565546024527 0ustar jmstaff00000000000000# # iso2022_jp_2004.py: Python Unicode Codec for ISO2022_JP_2004 # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_2004') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_2004', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp_3.py0000644000076500000240000000204512612565546024306 0ustar jmstaff00000000000000# # iso2022_jp_3.py: Python Unicode Codec for ISO2022_JP_3 # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_3') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_3', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_jp_ext.py0000644000076500000240000000205512612565546024745 0ustar jmstaff00000000000000# # iso2022_jp_ext.py: Python Unicode Codec for ISO2022_JP_EXT # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_jp_ext') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_jp_ext', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso2022_kr.py0000644000076500000240000000203512612565546024066 0ustar jmstaff00000000000000# # iso2022_kr.py: Python Unicode Codec for ISO2022_KR # # Written by Hye-Shik Chang # import _codecs_iso2022, codecs import _multibytecodec as mbc codec = _codecs_iso2022.getcodec('iso2022_kr') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='iso2022_kr', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_1.py0000644000076500000240000003217012612565546023645 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_1 generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-1', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_10.py0000644000076500000240000003302512612565546023725 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_10 generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-10', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u0112' # 0xA2 -> LATIN CAPITAL LETTER E WITH MACRON u'\u0122' # 0xA3 -> LATIN CAPITAL LETTER G WITH CEDILLA u'\u012a' # 0xA4 -> LATIN CAPITAL LETTER I WITH MACRON u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE u'\u0136' # 0xA6 -> LATIN CAPITAL LETTER K WITH CEDILLA u'\xa7' # 0xA7 -> SECTION SIGN u'\u013b' # 0xA8 -> LATIN CAPITAL LETTER L WITH CEDILLA u'\u0110' # 0xA9 -> LATIN CAPITAL LETTER D WITH STROKE u'\u0160' # 0xAA -> LATIN CAPITAL LETTER S WITH CARON u'\u0166' # 0xAB -> LATIN CAPITAL LETTER T WITH STROKE u'\u017d' # 0xAC -> LATIN CAPITAL LETTER Z WITH CARON u'\xad' # 0xAD -> SOFT HYPHEN u'\u016a' # 0xAE -> LATIN CAPITAL LETTER U WITH MACRON u'\u014a' # 0xAF -> LATIN CAPITAL LETTER ENG u'\xb0' # 0xB0 -> DEGREE SIGN u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK u'\u0113' # 0xB2 -> LATIN SMALL LETTER E WITH MACRON u'\u0123' # 0xB3 -> LATIN SMALL LETTER G WITH CEDILLA u'\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE u'\u0137' # 0xB6 -> LATIN SMALL LETTER K WITH CEDILLA u'\xb7' # 0xB7 -> MIDDLE DOT u'\u013c' # 0xB8 -> LATIN SMALL LETTER L WITH CEDILLA u'\u0111' # 0xB9 -> LATIN SMALL LETTER D WITH STROKE u'\u0161' # 0xBA -> LATIN SMALL LETTER S WITH CARON u'\u0167' # 0xBB -> LATIN SMALL LETTER T WITH STROKE u'\u017e' # 0xBC -> LATIN SMALL LETTER Z WITH CARON u'\u2015' # 0xBD -> HORIZONTAL BAR u'\u016b' # 0xBE -> LATIN SMALL LETTER U WITH MACRON u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\u0168' # 0xD7 -> LATIN CAPITAL LETTER U WITH TILDE u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\u0169' # 0xF7 -> LATIN SMALL LETTER U WITH TILDE u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) u'\u0138' # 0xFF -> LATIN SMALL LETTER KRA ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_11.py0000644000076500000240000003045712612565546023734 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_11 generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-11', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA u'\u0e24' # 0xC4 -> THAI CHARACTER RU u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING u'\u0e26' # 0xC6 -> THAI CHARACTER LU u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN u'\u0e50' # 0xF0 -> THAI DIGIT ZERO u'\u0e51' # 0xF1 -> THAI DIGIT ONE u'\u0e52' # 0xF2 -> THAI DIGIT TWO u'\u0e53' # 0xF3 -> THAI DIGIT THREE u'\u0e54' # 0xF4 -> THAI DIGIT FOUR u'\u0e55' # 0xF5 -> THAI DIGIT FIVE u'\u0e56' # 0xF6 -> THAI DIGIT SIX u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT u'\u0e59' # 0xF9 -> THAI DIGIT NINE u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_13.py0000644000076500000240000003232712612565546023734 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_13 generated from 'MAPPINGS/ISO8859/8859-13.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-13', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u201d' # 0xA1 -> RIGHT DOUBLE QUOTATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\u201c' # 0xB4 -> LEFT DOUBLE QUOTATION MARK u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xe6' # 0xBF -> LATIN SMALL LETTER AE u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON u'\u2019' # 0xFF -> RIGHT SINGLE QUOTATION MARK ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_14.py0000644000076500000240000003312412612565546023731 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_14 generated from 'MAPPINGS/ISO8859/8859-14.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-14', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u1e02' # 0xA1 -> LATIN CAPITAL LETTER B WITH DOT ABOVE u'\u1e03' # 0xA2 -> LATIN SMALL LETTER B WITH DOT ABOVE u'\xa3' # 0xA3 -> POUND SIGN u'\u010a' # 0xA4 -> LATIN CAPITAL LETTER C WITH DOT ABOVE u'\u010b' # 0xA5 -> LATIN SMALL LETTER C WITH DOT ABOVE u'\u1e0a' # 0xA6 -> LATIN CAPITAL LETTER D WITH DOT ABOVE u'\xa7' # 0xA7 -> SECTION SIGN u'\u1e80' # 0xA8 -> LATIN CAPITAL LETTER W WITH GRAVE u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u1e82' # 0xAA -> LATIN CAPITAL LETTER W WITH ACUTE u'\u1e0b' # 0xAB -> LATIN SMALL LETTER D WITH DOT ABOVE u'\u1ef2' # 0xAC -> LATIN CAPITAL LETTER Y WITH GRAVE u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\u0178' # 0xAF -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u1e1e' # 0xB0 -> LATIN CAPITAL LETTER F WITH DOT ABOVE u'\u1e1f' # 0xB1 -> LATIN SMALL LETTER F WITH DOT ABOVE u'\u0120' # 0xB2 -> LATIN CAPITAL LETTER G WITH DOT ABOVE u'\u0121' # 0xB3 -> LATIN SMALL LETTER G WITH DOT ABOVE u'\u1e40' # 0xB4 -> LATIN CAPITAL LETTER M WITH DOT ABOVE u'\u1e41' # 0xB5 -> LATIN SMALL LETTER M WITH DOT ABOVE u'\xb6' # 0xB6 -> PILCROW SIGN u'\u1e56' # 0xB7 -> LATIN CAPITAL LETTER P WITH DOT ABOVE u'\u1e81' # 0xB8 -> LATIN SMALL LETTER W WITH GRAVE u'\u1e57' # 0xB9 -> LATIN SMALL LETTER P WITH DOT ABOVE u'\u1e83' # 0xBA -> LATIN SMALL LETTER W WITH ACUTE u'\u1e60' # 0xBB -> LATIN CAPITAL LETTER S WITH DOT ABOVE u'\u1ef3' # 0xBC -> LATIN SMALL LETTER Y WITH GRAVE u'\u1e84' # 0xBD -> LATIN CAPITAL LETTER W WITH DIAERESIS u'\u1e85' # 0xBE -> LATIN SMALL LETTER W WITH DIAERESIS u'\u1e61' # 0xBF -> LATIN SMALL LETTER S WITH DOT ABOVE u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u0174' # 0xD0 -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\u1e6a' # 0xD7 -> LATIN CAPITAL LETTER T WITH DOT ABOVE u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\u0176' # 0xDE -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u0175' # 0xF0 -> LATIN SMALL LETTER W WITH CIRCUMFLEX u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\u1e6b' # 0xF7 -> LATIN SMALL LETTER T WITH DOT ABOVE u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\u0177' # 0xFE -> LATIN SMALL LETTER Y WITH CIRCUMFLEX u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_15.py0000644000076500000240000003223412612565546023733 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_15 generated from 'MAPPINGS/ISO8859/8859-15.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-15', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\u20ac' # 0xA4 -> EURO SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON u'\xa7' # 0xA7 -> SECTION SIGN u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_16.py0000644000076500000240000003276512612565546023745 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_16 generated from 'MAPPINGS/ISO8859/8859-16.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-16', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u0105' # 0xA2 -> LATIN SMALL LETTER A WITH OGONEK u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE u'\u20ac' # 0xA4 -> EURO SIGN u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON u'\xa7' # 0xA7 -> SECTION SIGN u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u0218' # 0xAA -> LATIN CAPITAL LETTER S WITH COMMA BELOW u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE u'\xad' # 0xAD -> SOFT HYPHEN u'\u017a' # 0xAE -> LATIN SMALL LETTER Z WITH ACUTE u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u010c' # 0xB2 -> LATIN CAPITAL LETTER C WITH CARON u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON u'\u201d' # 0xB5 -> RIGHT DOUBLE QUOTATION MARK u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON u'\u010d' # 0xB9 -> LATIN SMALL LETTER C WITH CARON u'\u0219' # 0xBA -> LATIN SMALL LETTER S WITH COMMA BELOW u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0106' # 0xC5 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\u015a' # 0xD7 -> LATIN CAPITAL LETTER S WITH ACUTE u'\u0170' # 0xD8 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0118' # 0xDD -> LATIN CAPITAL LETTER E WITH OGONEK u'\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u0107' # 0xE5 -> LATIN SMALL LETTER C WITH ACUTE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\u015b' # 0xF7 -> LATIN SMALL LETTER S WITH ACUTE u'\u0171' # 0xF8 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u0119' # 0xFD -> LATIN SMALL LETTER E WITH OGONEK u'\u021b' # 0xFE -> LATIN SMALL LETTER T WITH COMMA BELOW u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_2.py0000644000076500000240000003253412612565546023652 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_2 generated from 'MAPPINGS/ISO8859/8859-2.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-2', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u02d8' # 0xA2 -> BREVE u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE u'\xa4' # 0xA4 -> CURRENCY SIGN u'\u013d' # 0xA5 -> LATIN CAPITAL LETTER L WITH CARON u'\u015a' # 0xA6 -> LATIN CAPITAL LETTER S WITH ACUTE u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA u'\u0164' # 0xAB -> LATIN CAPITAL LETTER T WITH CARON u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE u'\xad' # 0xAD -> SOFT HYPHEN u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\xb0' # 0xB0 -> DEGREE SIGN u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK u'\u02db' # 0xB2 -> OGONEK u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\u013e' # 0xB5 -> LATIN SMALL LETTER L WITH CARON u'\u015b' # 0xB6 -> LATIN SMALL LETTER S WITH ACUTE u'\u02c7' # 0xB7 -> CARON u'\xb8' # 0xB8 -> CEDILLA u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA u'\u0165' # 0xBB -> LATIN SMALL LETTER T WITH CARON u'\u017a' # 0xBC -> LATIN SMALL LETTER Z WITH ACUTE u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_3.py0000644000076500000240000003204112612565546023644 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_3 generated from 'MAPPINGS/ISO8859/8859-3.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-3', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0126' # 0xA1 -> LATIN CAPITAL LETTER H WITH STROKE u'\u02d8' # 0xA2 -> BREVE u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\ufffe' u'\u0124' # 0xA6 -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\u0130' # 0xA9 -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA u'\u011e' # 0xAB -> LATIN CAPITAL LETTER G WITH BREVE u'\u0134' # 0xAC -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\xb0' # 0xB0 -> DEGREE SIGN u'\u0127' # 0xB1 -> LATIN SMALL LETTER H WITH STROKE u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\u0125' # 0xB6 -> LATIN SMALL LETTER H WITH CIRCUMFLEX u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\u0131' # 0xB9 -> LATIN SMALL LETTER DOTLESS I u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA u'\u011f' # 0xBB -> LATIN SMALL LETTER G WITH BREVE u'\u0135' # 0xBC -> LATIN SMALL LETTER J WITH CIRCUMFLEX u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\ufffe' u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\ufffe' u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u010a' # 0xC5 -> LATIN CAPITAL LETTER C WITH DOT ABOVE u'\u0108' # 0xC6 -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\ufffe' u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0120' # 0xD5 -> LATIN CAPITAL LETTER G WITH DOT ABOVE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\u011c' # 0xD8 -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u016c' # 0xDD -> LATIN CAPITAL LETTER U WITH BREVE u'\u015c' # 0xDE -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\ufffe' u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\u010b' # 0xE5 -> LATIN SMALL LETTER C WITH DOT ABOVE u'\u0109' # 0xE6 -> LATIN SMALL LETTER C WITH CIRCUMFLEX u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\ufffe' u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\u0121' # 0xF5 -> LATIN SMALL LETTER G WITH DOT ABOVE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\u011d' # 0xF8 -> LATIN SMALL LETTER G WITH CIRCUMFLEX u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u016d' # 0xFD -> LATIN SMALL LETTER U WITH BREVE u'\u015d' # 0xFE -> LATIN SMALL LETTER S WITH CIRCUMFLEX u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_4.py0000644000076500000240000003250012612565546023645 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_4 generated from 'MAPPINGS/ISO8859/8859-4.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-4', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK u'\u0138' # 0xA2 -> LATIN SMALL LETTER KRA u'\u0156' # 0xA3 -> LATIN CAPITAL LETTER R WITH CEDILLA u'\xa4' # 0xA4 -> CURRENCY SIGN u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE u'\u013b' # 0xA6 -> LATIN CAPITAL LETTER L WITH CEDILLA u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON u'\u0112' # 0xAA -> LATIN CAPITAL LETTER E WITH MACRON u'\u0122' # 0xAB -> LATIN CAPITAL LETTER G WITH CEDILLA u'\u0166' # 0xAC -> LATIN CAPITAL LETTER T WITH STROKE u'\xad' # 0xAD -> SOFT HYPHEN u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK u'\u02db' # 0xB2 -> OGONEK u'\u0157' # 0xB3 -> LATIN SMALL LETTER R WITH CEDILLA u'\xb4' # 0xB4 -> ACUTE ACCENT u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE u'\u013c' # 0xB6 -> LATIN SMALL LETTER L WITH CEDILLA u'\u02c7' # 0xB7 -> CARON u'\xb8' # 0xB8 -> CEDILLA u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON u'\u0113' # 0xBA -> LATIN SMALL LETTER E WITH MACRON u'\u0123' # 0xBB -> LATIN SMALL LETTER G WITH CEDILLA u'\u0167' # 0xBC -> LATIN SMALL LETTER T WITH STROKE u'\u014a' # 0xBD -> LATIN CAPITAL LETTER ENG u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\u012a' # 0xCF -> LATIN CAPITAL LETTER I WITH MACRON u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON u'\u0136' # 0xD3 -> LATIN CAPITAL LETTER K WITH CEDILLA u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0168' # 0xDD -> LATIN CAPITAL LETTER U WITH TILDE u'\u016a' # 0xDE -> LATIN CAPITAL LETTER U WITH MACRON u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\u012b' # 0xEF -> LATIN SMALL LETTER I WITH MACRON u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON u'\u0137' # 0xF3 -> LATIN SMALL LETTER K WITH CEDILLA u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u0169' # 0xFD -> LATIN SMALL LETTER U WITH TILDE u'\u016b' # 0xFE -> LATIN SMALL LETTER U WITH MACRON u'\u02d9' # 0xFF -> DOT ABOVE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_5.py0000644000076500000240000003172712612565546023660 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_5 generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-5', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u0401' # 0xA1 -> CYRILLIC CAPITAL LETTER IO u'\u0402' # 0xA2 -> CYRILLIC CAPITAL LETTER DJE u'\u0403' # 0xA3 -> CYRILLIC CAPITAL LETTER GJE u'\u0404' # 0xA4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\u0405' # 0xA5 -> CYRILLIC CAPITAL LETTER DZE u'\u0406' # 0xA6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0407' # 0xA7 -> CYRILLIC CAPITAL LETTER YI u'\u0408' # 0xA8 -> CYRILLIC CAPITAL LETTER JE u'\u0409' # 0xA9 -> CYRILLIC CAPITAL LETTER LJE u'\u040a' # 0xAA -> CYRILLIC CAPITAL LETTER NJE u'\u040b' # 0xAB -> CYRILLIC CAPITAL LETTER TSHE u'\u040c' # 0xAC -> CYRILLIC CAPITAL LETTER KJE u'\xad' # 0xAD -> SOFT HYPHEN u'\u040e' # 0xAE -> CYRILLIC CAPITAL LETTER SHORT U u'\u040f' # 0xAF -> CYRILLIC CAPITAL LETTER DZHE u'\u0410' # 0xB0 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0xB1 -> CYRILLIC CAPITAL LETTER BE u'\u0412' # 0xB2 -> CYRILLIC CAPITAL LETTER VE u'\u0413' # 0xB3 -> CYRILLIC CAPITAL LETTER GHE u'\u0414' # 0xB4 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0xB5 -> CYRILLIC CAPITAL LETTER IE u'\u0416' # 0xB6 -> CYRILLIC CAPITAL LETTER ZHE u'\u0417' # 0xB7 -> CYRILLIC CAPITAL LETTER ZE u'\u0418' # 0xB8 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0xB9 -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0xBA -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0xBB -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0xBC -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0xBD -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0xBE -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0xBF -> CYRILLIC CAPITAL LETTER PE u'\u0420' # 0xC0 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0xC1 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0xC2 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0xC3 -> CYRILLIC CAPITAL LETTER U u'\u0424' # 0xC4 -> CYRILLIC CAPITAL LETTER EF u'\u0425' # 0xC5 -> CYRILLIC CAPITAL LETTER HA u'\u0426' # 0xC6 -> CYRILLIC CAPITAL LETTER TSE u'\u0427' # 0xC7 -> CYRILLIC CAPITAL LETTER CHE u'\u0428' # 0xC8 -> CYRILLIC CAPITAL LETTER SHA u'\u0429' # 0xC9 -> CYRILLIC CAPITAL LETTER SHCHA u'\u042a' # 0xCA -> CYRILLIC CAPITAL LETTER HARD SIGN u'\u042b' # 0xCB -> CYRILLIC CAPITAL LETTER YERU u'\u042c' # 0xCC -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042d' # 0xCD -> CYRILLIC CAPITAL LETTER E u'\u042e' # 0xCE -> CYRILLIC CAPITAL LETTER YU u'\u042f' # 0xCF -> CYRILLIC CAPITAL LETTER YA u'\u0430' # 0xD0 -> CYRILLIC SMALL LETTER A u'\u0431' # 0xD1 -> CYRILLIC SMALL LETTER BE u'\u0432' # 0xD2 -> CYRILLIC SMALL LETTER VE u'\u0433' # 0xD3 -> CYRILLIC SMALL LETTER GHE u'\u0434' # 0xD4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0xD5 -> CYRILLIC SMALL LETTER IE u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE u'\u0437' # 0xD7 -> CYRILLIC SMALL LETTER ZE u'\u0438' # 0xD8 -> CYRILLIC SMALL LETTER I u'\u0439' # 0xD9 -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0xDA -> CYRILLIC SMALL LETTER KA u'\u043b' # 0xDB -> CYRILLIC SMALL LETTER EL u'\u043c' # 0xDC -> CYRILLIC SMALL LETTER EM u'\u043d' # 0xDD -> CYRILLIC SMALL LETTER EN u'\u043e' # 0xDE -> CYRILLIC SMALL LETTER O u'\u043f' # 0xDF -> CYRILLIC SMALL LETTER PE u'\u0440' # 0xE0 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0xE1 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0xE2 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0xE3 -> CYRILLIC SMALL LETTER U u'\u0444' # 0xE4 -> CYRILLIC SMALL LETTER EF u'\u0445' # 0xE5 -> CYRILLIC SMALL LETTER HA u'\u0446' # 0xE6 -> CYRILLIC SMALL LETTER TSE u'\u0447' # 0xE7 -> CYRILLIC SMALL LETTER CHE u'\u0448' # 0xE8 -> CYRILLIC SMALL LETTER SHA u'\u0449' # 0xE9 -> CYRILLIC SMALL LETTER SHCHA u'\u044a' # 0xEA -> CYRILLIC SMALL LETTER HARD SIGN u'\u044b' # 0xEB -> CYRILLIC SMALL LETTER YERU u'\u044c' # 0xEC -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044d' # 0xED -> CYRILLIC SMALL LETTER E u'\u044e' # 0xEE -> CYRILLIC SMALL LETTER YU u'\u044f' # 0xEF -> CYRILLIC SMALL LETTER YA u'\u2116' # 0xF0 -> NUMERO SIGN u'\u0451' # 0xF1 -> CYRILLIC SMALL LETTER IO u'\u0452' # 0xF2 -> CYRILLIC SMALL LETTER DJE u'\u0453' # 0xF3 -> CYRILLIC SMALL LETTER GJE u'\u0454' # 0xF4 -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\u0455' # 0xF5 -> CYRILLIC SMALL LETTER DZE u'\u0456' # 0xF6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0457' # 0xF7 -> CYRILLIC SMALL LETTER YI u'\u0458' # 0xF8 -> CYRILLIC SMALL LETTER JE u'\u0459' # 0xF9 -> CYRILLIC SMALL LETTER LJE u'\u045a' # 0xFA -> CYRILLIC SMALL LETTER NJE u'\u045b' # 0xFB -> CYRILLIC SMALL LETTER TSHE u'\u045c' # 0xFC -> CYRILLIC SMALL LETTER KJE u'\xa7' # 0xFD -> SECTION SIGN u'\u045e' # 0xFE -> CYRILLIC SMALL LETTER SHORT U u'\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_6.py0000644000076500000240000002552112612565546023654 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_6 generated from 'MAPPINGS/ISO8859/8859-6.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-6', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\ufffe' u'\ufffe' u'\ufffe' u'\xa4' # 0xA4 -> CURRENCY SIGN u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u060c' # 0xAC -> ARABIC COMMA u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u061b' # 0xBB -> ARABIC SEMICOLON u'\ufffe' u'\ufffe' u'\ufffe' u'\u061f' # 0xBF -> ARABIC QUESTION MARK u'\ufffe' u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE u'\u0627' # 0xC7 -> ARABIC LETTER ALEF u'\u0628' # 0xC8 -> ARABIC LETTER BEH u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA u'\u062a' # 0xCA -> ARABIC LETTER TEH u'\u062b' # 0xCB -> ARABIC LETTER THEH u'\u062c' # 0xCC -> ARABIC LETTER JEEM u'\u062d' # 0xCD -> ARABIC LETTER HAH u'\u062e' # 0xCE -> ARABIC LETTER KHAH u'\u062f' # 0xCF -> ARABIC LETTER DAL u'\u0630' # 0xD0 -> ARABIC LETTER THAL u'\u0631' # 0xD1 -> ARABIC LETTER REH u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN u'\u0633' # 0xD3 -> ARABIC LETTER SEEN u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN u'\u0635' # 0xD5 -> ARABIC LETTER SAD u'\u0636' # 0xD6 -> ARABIC LETTER DAD u'\u0637' # 0xD7 -> ARABIC LETTER TAH u'\u0638' # 0xD8 -> ARABIC LETTER ZAH u'\u0639' # 0xD9 -> ARABIC LETTER AIN u'\u063a' # 0xDA -> ARABIC LETTER GHAIN u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u0640' # 0xE0 -> ARABIC TATWEEL u'\u0641' # 0xE1 -> ARABIC LETTER FEH u'\u0642' # 0xE2 -> ARABIC LETTER QAF u'\u0643' # 0xE3 -> ARABIC LETTER KAF u'\u0644' # 0xE4 -> ARABIC LETTER LAM u'\u0645' # 0xE5 -> ARABIC LETTER MEEM u'\u0646' # 0xE6 -> ARABIC LETTER NOON u'\u0647' # 0xE7 -> ARABIC LETTER HEH u'\u0648' # 0xE8 -> ARABIC LETTER WAW u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA u'\u064a' # 0xEA -> ARABIC LETTER YEH u'\u064b' # 0xEB -> ARABIC FATHATAN u'\u064c' # 0xEC -> ARABIC DAMMATAN u'\u064d' # 0xED -> ARABIC KASRATAN u'\u064e' # 0xEE -> ARABIC FATHA u'\u064f' # 0xEF -> ARABIC DAMMA u'\u0650' # 0xF0 -> ARABIC KASRA u'\u0651' # 0xF1 -> ARABIC SHADDA u'\u0652' # 0xF2 -> ARABIC SUKUN u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_7.py0000644000076500000240000003145412612565546023657 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_7 generated from 'MAPPINGS/ISO8859/8859-7.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-7', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\u2018' # 0xA1 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xA2 -> RIGHT SINGLE QUOTATION MARK u'\xa3' # 0xA3 -> POUND SIGN u'\u20ac' # 0xA4 -> EURO SIGN u'\u20af' # 0xA5 -> DRACHMA SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u037a' # 0xAA -> GREEK YPOGEGRAMMENI u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\ufffe' u'\u2015' # 0xAF -> HORIZONTAL BAR u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\u0384' # 0xB4 -> GREEK TONOS u'\u0385' # 0xB5 -> GREEK DIALYTIKA TONOS u'\u0386' # 0xB6 -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\xb7' # 0xB7 -> MIDDLE DOT u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO u'\ufffe' u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU u'\u03bd' # 0xED -> GREEK SMALL LETTER NU u'\u03be' # 0xEE -> GREEK SMALL LETTER XI u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS u'\ufffe' ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_8.py0000644000076500000240000002603412612565546023656 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_8 generated from 'MAPPINGS/ISO8859/8859-8.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-8', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\ufffe' u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xd7' # 0xAA -> MULTIPLICATION SIGN u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xf7' # 0xBA -> DIVISION SIGN u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u2017' # 0xDF -> DOUBLE LOW LINE u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF u'\u05d1' # 0xE1 -> HEBREW LETTER BET u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL u'\u05d3' # 0xE3 -> HEBREW LETTER DALET u'\u05d4' # 0xE4 -> HEBREW LETTER HE u'\u05d5' # 0xE5 -> HEBREW LETTER VAV u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN u'\u05d7' # 0xE7 -> HEBREW LETTER HET u'\u05d8' # 0xE8 -> HEBREW LETTER TET u'\u05d9' # 0xE9 -> HEBREW LETTER YOD u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF u'\u05db' # 0xEB -> HEBREW LETTER KAF u'\u05dc' # 0xEC -> HEBREW LETTER LAMED u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM u'\u05de' # 0xEE -> HEBREW LETTER MEM u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN u'\u05e0' # 0xF0 -> HEBREW LETTER NUN u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE u'\u05e4' # 0xF4 -> HEBREW LETTER PE u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI u'\u05e7' # 0xF7 -> HEBREW LETTER QOF u'\u05e8' # 0xF8 -> HEBREW LETTER RESH u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN u'\u05ea' # 0xFA -> HEBREW LETTER TAV u'\ufffe' u'\ufffe' u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK u'\ufffe' ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/iso8859_9.py0000644000076500000240000003214412612565546023656 0ustar jmstaff00000000000000""" Python Character Mapping Codec iso8859_9 generated from 'MAPPINGS/ISO8859/8859-9.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-9', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\xa0' # 0xA0 -> NO-BREAK SPACE u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa4' # 0xA4 -> CURRENCY SIGN u'\xa5' # 0xA5 -> YEN SIGN u'\xa6' # 0xA6 -> BROKEN BAR u'\xa7' # 0xA7 -> SECTION SIGN u'\xa8' # 0xA8 -> DIAERESIS u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xac' # 0xAC -> NOT SIGN u'\xad' # 0xAD -> SOFT HYPHEN u'\xae' # 0xAE -> REGISTERED SIGN u'\xaf' # 0xAF -> MACRON u'\xb0' # 0xB0 -> DEGREE SIGN u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\xb2' # 0xB2 -> SUPERSCRIPT TWO u'\xb3' # 0xB3 -> SUPERSCRIPT THREE u'\xb4' # 0xB4 -> ACUTE ACCENT u'\xb5' # 0xB5 -> MICRO SIGN u'\xb6' # 0xB6 -> PILCROW SIGN u'\xb7' # 0xB7 -> MIDDLE DOT u'\xb8' # 0xB8 -> CEDILLA u'\xb9' # 0xB9 -> SUPERSCRIPT ONE u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS u'\xbf' # 0xBF -> INVERTED QUESTION MARK u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xd7' # 0xD7 -> MULTIPLICATION SIGN u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0xF7 -> DIVISION SIGN u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/johab.py0000644000076500000240000000177712612565546023371 0ustar jmstaff00000000000000# # johab.py: Python Unicode Codec for JOHAB # # Written by Hye-Shik Chang # import _codecs_kr, codecs import _multibytecodec as mbc codec = _codecs_kr.getcodec('johab') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='johab', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/koi8_r.py0000644000076500000240000003332312612565546023471 0ustar jmstaff00000000000000""" Python Character Mapping Codec koi8_r generated from 'MAPPINGS/VENDORS/MISC/KOI8-R.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='koi8-r', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL u'\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2510' # 0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2518' # 0x85 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u251c' # 0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u2580' # 0x8B -> UPPER HALF BLOCK u'\u2584' # 0x8C -> LOWER HALF BLOCK u'\u2588' # 0x8D -> FULL BLOCK u'\u258c' # 0x8E -> LEFT HALF BLOCK u'\u2590' # 0x8F -> RIGHT HALF BLOCK u'\u2591' # 0x90 -> LIGHT SHADE u'\u2592' # 0x91 -> MEDIUM SHADE u'\u2593' # 0x92 -> DARK SHADE u'\u2320' # 0x93 -> TOP HALF INTEGRAL u'\u25a0' # 0x94 -> BLACK SQUARE u'\u2219' # 0x95 -> BULLET OPERATOR u'\u221a' # 0x96 -> SQUARE ROOT u'\u2248' # 0x97 -> ALMOST EQUAL TO u'\u2264' # 0x98 -> LESS-THAN OR EQUAL TO u'\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO u'\xa0' # 0x9A -> NO-BREAK SPACE u'\u2321' # 0x9B -> BOTTOM HALF INTEGRAL u'\xb0' # 0x9C -> DEGREE SIGN u'\xb2' # 0x9D -> SUPERSCRIPT TWO u'\xb7' # 0x9E -> MIDDLE DOT u'\xf7' # 0x9F -> DIVISION SIGN u'\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL u'\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO u'\u2553' # 0xA4 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE u'\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u2555' # 0xA6 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE u'\u2556' # 0xA7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE u'\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u255c' # 0xAD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE u'\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO u'\u2562' # 0xB4 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE u'\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u2564' # 0xB6 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE u'\u2565' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE u'\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u256b' # 0xBD -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE u'\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa9' # 0xBF -> COPYRIGHT SIGN u'\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU u'\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A u'\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE u'\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE u'\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE u'\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF u'\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE u'\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA u'\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I u'\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA u'\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL u'\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM u'\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN u'\u043e' # 0xCF -> CYRILLIC SMALL LETTER O u'\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE u'\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA u'\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE u'\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE u'\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU u'\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE u'\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA u'\u044d' # 0xDC -> CYRILLIC SMALL LETTER E u'\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA u'\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE u'\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN u'\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU u'\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE u'\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE u'\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE u'\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF u'\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE u'\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA u'\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE u'\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA u'\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U u'\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE u'\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE u'\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU u'\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE u'\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA u'\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E u'\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA u'\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/koi8_u.py0000644000076500000240000003330212612565546023471 0ustar jmstaff00000000000000""" Python Character Mapping Codec koi8_u generated from 'python-mappings/KOI8-U.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='koi8-u', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL u'\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL u'\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT u'\u2510' # 0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT u'\u2514' # 0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT u'\u2518' # 0x85 -> BOX DRAWINGS LIGHT UP AND LEFT u'\u251c' # 0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT u'\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT u'\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL u'\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL u'\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL u'\u2580' # 0x8B -> UPPER HALF BLOCK u'\u2584' # 0x8C -> LOWER HALF BLOCK u'\u2588' # 0x8D -> FULL BLOCK u'\u258c' # 0x8E -> LEFT HALF BLOCK u'\u2590' # 0x8F -> RIGHT HALF BLOCK u'\u2591' # 0x90 -> LIGHT SHADE u'\u2592' # 0x91 -> MEDIUM SHADE u'\u2593' # 0x92 -> DARK SHADE u'\u2320' # 0x93 -> TOP HALF INTEGRAL u'\u25a0' # 0x94 -> BLACK SQUARE u'\u2219' # 0x95 -> BULLET OPERATOR u'\u221a' # 0x96 -> SQUARE ROOT u'\u2248' # 0x97 -> ALMOST EQUAL TO u'\u2264' # 0x98 -> LESS-THAN OR EQUAL TO u'\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO u'\xa0' # 0x9A -> NO-BREAK SPACE u'\u2321' # 0x9B -> BOTTOM HALF INTEGRAL u'\xb0' # 0x9C -> DEGREE SIGN u'\xb2' # 0x9D -> SUPERSCRIPT TWO u'\xb7' # 0x9E -> MIDDLE DOT u'\xf7' # 0x9F -> DIVISION SIGN u'\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL u'\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL u'\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE u'\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO u'\u0454' # 0xA4 -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT u'\u0456' # 0xA6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0457' # 0xA7 -> CYRILLIC SMALL LETTER YI (UKRAINIAN) u'\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT u'\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE u'\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE u'\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT u'\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE u'\u0491' # 0xAD -> CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN u'\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT u'\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE u'\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE u'\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT u'\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE u'\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO u'\u0404' # 0xB4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT u'\u0406' # 0xB6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I u'\u0407' # 0xB7 -> CYRILLIC CAPITAL LETTER YI (UKRAINIAN) u'\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL u'\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE u'\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE u'\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL u'\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE u'\u0490' # 0xBD -> CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN u'\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL u'\xa9' # 0xBF -> COPYRIGHT SIGN u'\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU u'\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A u'\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE u'\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE u'\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE u'\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF u'\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE u'\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA u'\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I u'\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA u'\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL u'\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM u'\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN u'\u043e' # 0xCF -> CYRILLIC SMALL LETTER O u'\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE u'\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA u'\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE u'\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE u'\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU u'\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE u'\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA u'\u044d' # 0xDC -> CYRILLIC SMALL LETTER E u'\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA u'\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE u'\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN u'\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU u'\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE u'\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE u'\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE u'\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF u'\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE u'\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA u'\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE u'\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA u'\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U u'\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE u'\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE u'\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU u'\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE u'\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA u'\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E u'\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA u'\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE u'\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/latin_1.py0000644000076500000240000000236012612565546023622 0ustar jmstaff00000000000000""" Python 'latin-1' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.latin_1_encode decode = codecs.latin_1_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.latin_1_encode(input,self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.latin_1_decode(input,self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass class StreamConverter(StreamWriter,StreamReader): encode = codecs.latin_1_decode decode = codecs.latin_1_encode ### encodings module API def getregentry(): return codecs.CodecInfo( name='iso8859-1', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_arabic.py0000644000076500000240000010756312612565547024350 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'VENDORS/APPLE/ARABIC.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-arabic', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x0081: 0x00a0, # NO-BREAK SPACE, right-left 0x0082: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0084: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x0087: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x0088: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE 0x0089: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x008b: 0x06ba, # ARABIC LETTER NOON GHUNNA 0x008c: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x008d: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x008f: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE 0x0090: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x0091: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS 0x0092: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x0093: 0x2026, # HORIZONTAL ELLIPSIS, right-left 0x0094: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x0095: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS 0x0096: 0x00f1, # LATIN SMALL LETTER N WITH TILDE 0x0097: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x0098: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x009b: 0x00f7, # DIVISION SIGN, right-left 0x009c: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x009d: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE 0x009e: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x00a0: 0x0020, # SPACE, right-left 0x00a1: 0x0021, # EXCLAMATION MARK, right-left 0x00a2: 0x0022, # QUOTATION MARK, right-left 0x00a3: 0x0023, # NUMBER SIGN, right-left 0x00a4: 0x0024, # DOLLAR SIGN, right-left 0x00a5: 0x066a, # ARABIC PERCENT SIGN 0x00a6: 0x0026, # AMPERSAND, right-left 0x00a7: 0x0027, # APOSTROPHE, right-left 0x00a8: 0x0028, # LEFT PARENTHESIS, right-left 0x00a9: 0x0029, # RIGHT PARENTHESIS, right-left 0x00aa: 0x002a, # ASTERISK, right-left 0x00ab: 0x002b, # PLUS SIGN, right-left 0x00ac: 0x060c, # ARABIC COMMA 0x00ad: 0x002d, # HYPHEN-MINUS, right-left 0x00ae: 0x002e, # FULL STOP, right-left 0x00af: 0x002f, # SOLIDUS, right-left 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO, right-left (need override) 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE, right-left (need override) 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO, right-left (need override) 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE, right-left (need override) 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR, right-left (need override) 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE, right-left (need override) 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX, right-left (need override) 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE, right-left (need override) 0x00ba: 0x003a, # COLON, right-left 0x00bb: 0x061b, # ARABIC SEMICOLON 0x00bc: 0x003c, # LESS-THAN SIGN, right-left 0x00bd: 0x003d, # EQUALS SIGN, right-left 0x00be: 0x003e, # GREATER-THAN SIGN, right-left 0x00bf: 0x061f, # ARABIC QUESTION MARK 0x00c0: 0x274a, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left 0x00c1: 0x0621, # ARABIC LETTER HAMZA 0x00c2: 0x0622, # ARABIC LETTER ALEF WITH MADDA ABOVE 0x00c3: 0x0623, # ARABIC LETTER ALEF WITH HAMZA ABOVE 0x00c4: 0x0624, # ARABIC LETTER WAW WITH HAMZA ABOVE 0x00c5: 0x0625, # ARABIC LETTER ALEF WITH HAMZA BELOW 0x00c6: 0x0626, # ARABIC LETTER YEH WITH HAMZA ABOVE 0x00c7: 0x0627, # ARABIC LETTER ALEF 0x00c8: 0x0628, # ARABIC LETTER BEH 0x00c9: 0x0629, # ARABIC LETTER TEH MARBUTA 0x00ca: 0x062a, # ARABIC LETTER TEH 0x00cb: 0x062b, # ARABIC LETTER THEH 0x00cc: 0x062c, # ARABIC LETTER JEEM 0x00cd: 0x062d, # ARABIC LETTER HAH 0x00ce: 0x062e, # ARABIC LETTER KHAH 0x00cf: 0x062f, # ARABIC LETTER DAL 0x00d0: 0x0630, # ARABIC LETTER THAL 0x00d1: 0x0631, # ARABIC LETTER REH 0x00d2: 0x0632, # ARABIC LETTER ZAIN 0x00d3: 0x0633, # ARABIC LETTER SEEN 0x00d4: 0x0634, # ARABIC LETTER SHEEN 0x00d5: 0x0635, # ARABIC LETTER SAD 0x00d6: 0x0636, # ARABIC LETTER DAD 0x00d7: 0x0637, # ARABIC LETTER TAH 0x00d8: 0x0638, # ARABIC LETTER ZAH 0x00d9: 0x0639, # ARABIC LETTER AIN 0x00da: 0x063a, # ARABIC LETTER GHAIN 0x00db: 0x005b, # LEFT SQUARE BRACKET, right-left 0x00dc: 0x005c, # REVERSE SOLIDUS, right-left 0x00dd: 0x005d, # RIGHT SQUARE BRACKET, right-left 0x00de: 0x005e, # CIRCUMFLEX ACCENT, right-left 0x00df: 0x005f, # LOW LINE, right-left 0x00e0: 0x0640, # ARABIC TATWEEL 0x00e1: 0x0641, # ARABIC LETTER FEH 0x00e2: 0x0642, # ARABIC LETTER QAF 0x00e3: 0x0643, # ARABIC LETTER KAF 0x00e4: 0x0644, # ARABIC LETTER LAM 0x00e5: 0x0645, # ARABIC LETTER MEEM 0x00e6: 0x0646, # ARABIC LETTER NOON 0x00e7: 0x0647, # ARABIC LETTER HEH 0x00e8: 0x0648, # ARABIC LETTER WAW 0x00e9: 0x0649, # ARABIC LETTER ALEF MAKSURA 0x00ea: 0x064a, # ARABIC LETTER YEH 0x00eb: 0x064b, # ARABIC FATHATAN 0x00ec: 0x064c, # ARABIC DAMMATAN 0x00ed: 0x064d, # ARABIC KASRATAN 0x00ee: 0x064e, # ARABIC FATHA 0x00ef: 0x064f, # ARABIC DAMMA 0x00f0: 0x0650, # ARABIC KASRA 0x00f1: 0x0651, # ARABIC SHADDA 0x00f2: 0x0652, # ARABIC SUKUN 0x00f3: 0x067e, # ARABIC LETTER PEH 0x00f4: 0x0679, # ARABIC LETTER TTEH 0x00f5: 0x0686, # ARABIC LETTER TCHEH 0x00f6: 0x06d5, # ARABIC LETTER AE 0x00f7: 0x06a4, # ARABIC LETTER VEH 0x00f8: 0x06af, # ARABIC LETTER GAF 0x00f9: 0x0688, # ARABIC LETTER DDAL 0x00fa: 0x0691, # ARABIC LETTER RREH 0x00fb: 0x007b, # LEFT CURLY BRACKET, right-left 0x00fc: 0x007c, # VERTICAL LINE, right-left 0x00fd: 0x007d, # RIGHT CURLY BRACKET, right-left 0x00fe: 0x0698, # ARABIC LETTER JEH 0x00ff: 0x06d2, # ARABIC LETTER YEH BARREE }) ### Decoding Table decoding_table = ( u'\x00' # 0x0000 -> CONTROL CHARACTER u'\x01' # 0x0001 -> CONTROL CHARACTER u'\x02' # 0x0002 -> CONTROL CHARACTER u'\x03' # 0x0003 -> CONTROL CHARACTER u'\x04' # 0x0004 -> CONTROL CHARACTER u'\x05' # 0x0005 -> CONTROL CHARACTER u'\x06' # 0x0006 -> CONTROL CHARACTER u'\x07' # 0x0007 -> CONTROL CHARACTER u'\x08' # 0x0008 -> CONTROL CHARACTER u'\t' # 0x0009 -> CONTROL CHARACTER u'\n' # 0x000a -> CONTROL CHARACTER u'\x0b' # 0x000b -> CONTROL CHARACTER u'\x0c' # 0x000c -> CONTROL CHARACTER u'\r' # 0x000d -> CONTROL CHARACTER u'\x0e' # 0x000e -> CONTROL CHARACTER u'\x0f' # 0x000f -> CONTROL CHARACTER u'\x10' # 0x0010 -> CONTROL CHARACTER u'\x11' # 0x0011 -> CONTROL CHARACTER u'\x12' # 0x0012 -> CONTROL CHARACTER u'\x13' # 0x0013 -> CONTROL CHARACTER u'\x14' # 0x0014 -> CONTROL CHARACTER u'\x15' # 0x0015 -> CONTROL CHARACTER u'\x16' # 0x0016 -> CONTROL CHARACTER u'\x17' # 0x0017 -> CONTROL CHARACTER u'\x18' # 0x0018 -> CONTROL CHARACTER u'\x19' # 0x0019 -> CONTROL CHARACTER u'\x1a' # 0x001a -> CONTROL CHARACTER u'\x1b' # 0x001b -> CONTROL CHARACTER u'\x1c' # 0x001c -> CONTROL CHARACTER u'\x1d' # 0x001d -> CONTROL CHARACTER u'\x1e' # 0x001e -> CONTROL CHARACTER u'\x1f' # 0x001f -> CONTROL CHARACTER u' ' # 0x0020 -> SPACE, left-right u'!' # 0x0021 -> EXCLAMATION MARK, left-right u'"' # 0x0022 -> QUOTATION MARK, left-right u'#' # 0x0023 -> NUMBER SIGN, left-right u'$' # 0x0024 -> DOLLAR SIGN, left-right u'%' # 0x0025 -> PERCENT SIGN, left-right u'&' # 0x0026 -> AMPERSAND, left-right u"'" # 0x0027 -> APOSTROPHE, left-right u'(' # 0x0028 -> LEFT PARENTHESIS, left-right u')' # 0x0029 -> RIGHT PARENTHESIS, left-right u'*' # 0x002a -> ASTERISK, left-right u'+' # 0x002b -> PLUS SIGN, left-right u',' # 0x002c -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR u'-' # 0x002d -> HYPHEN-MINUS, left-right u'.' # 0x002e -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR u'/' # 0x002f -> SOLIDUS, left-right u'0' # 0x0030 -> DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO u'1' # 0x0031 -> DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE u'2' # 0x0032 -> DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO u'3' # 0x0033 -> DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE u'4' # 0x0034 -> DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR u'5' # 0x0035 -> DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE u'6' # 0x0036 -> DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX u'7' # 0x0037 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN u'8' # 0x0038 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT u'9' # 0x0039 -> DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE u':' # 0x003a -> COLON, left-right u';' # 0x003b -> SEMICOLON, left-right u'<' # 0x003c -> LESS-THAN SIGN, left-right u'=' # 0x003d -> EQUALS SIGN, left-right u'>' # 0x003e -> GREATER-THAN SIGN, left-right u'?' # 0x003f -> QUESTION MARK, left-right u'@' # 0x0040 -> COMMERCIAL AT u'A' # 0x0041 -> LATIN CAPITAL LETTER A u'B' # 0x0042 -> LATIN CAPITAL LETTER B u'C' # 0x0043 -> LATIN CAPITAL LETTER C u'D' # 0x0044 -> LATIN CAPITAL LETTER D u'E' # 0x0045 -> LATIN CAPITAL LETTER E u'F' # 0x0046 -> LATIN CAPITAL LETTER F u'G' # 0x0047 -> LATIN CAPITAL LETTER G u'H' # 0x0048 -> LATIN CAPITAL LETTER H u'I' # 0x0049 -> LATIN CAPITAL LETTER I u'J' # 0x004a -> LATIN CAPITAL LETTER J u'K' # 0x004b -> LATIN CAPITAL LETTER K u'L' # 0x004c -> LATIN CAPITAL LETTER L u'M' # 0x004d -> LATIN CAPITAL LETTER M u'N' # 0x004e -> LATIN CAPITAL LETTER N u'O' # 0x004f -> LATIN CAPITAL LETTER O u'P' # 0x0050 -> LATIN CAPITAL LETTER P u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q u'R' # 0x0052 -> LATIN CAPITAL LETTER R u'S' # 0x0053 -> LATIN CAPITAL LETTER S u'T' # 0x0054 -> LATIN CAPITAL LETTER T u'U' # 0x0055 -> LATIN CAPITAL LETTER U u'V' # 0x0056 -> LATIN CAPITAL LETTER V u'W' # 0x0057 -> LATIN CAPITAL LETTER W u'X' # 0x0058 -> LATIN CAPITAL LETTER X u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y u'Z' # 0x005a -> LATIN CAPITAL LETTER Z u'[' # 0x005b -> LEFT SQUARE BRACKET, left-right u'\\' # 0x005c -> REVERSE SOLIDUS, left-right u']' # 0x005d -> RIGHT SQUARE BRACKET, left-right u'^' # 0x005e -> CIRCUMFLEX ACCENT, left-right u'_' # 0x005f -> LOW LINE, left-right u'`' # 0x0060 -> GRAVE ACCENT u'a' # 0x0061 -> LATIN SMALL LETTER A u'b' # 0x0062 -> LATIN SMALL LETTER B u'c' # 0x0063 -> LATIN SMALL LETTER C u'd' # 0x0064 -> LATIN SMALL LETTER D u'e' # 0x0065 -> LATIN SMALL LETTER E u'f' # 0x0066 -> LATIN SMALL LETTER F u'g' # 0x0067 -> LATIN SMALL LETTER G u'h' # 0x0068 -> LATIN SMALL LETTER H u'i' # 0x0069 -> LATIN SMALL LETTER I u'j' # 0x006a -> LATIN SMALL LETTER J u'k' # 0x006b -> LATIN SMALL LETTER K u'l' # 0x006c -> LATIN SMALL LETTER L u'm' # 0x006d -> LATIN SMALL LETTER M u'n' # 0x006e -> LATIN SMALL LETTER N u'o' # 0x006f -> LATIN SMALL LETTER O u'p' # 0x0070 -> LATIN SMALL LETTER P u'q' # 0x0071 -> LATIN SMALL LETTER Q u'r' # 0x0072 -> LATIN SMALL LETTER R u's' # 0x0073 -> LATIN SMALL LETTER S u't' # 0x0074 -> LATIN SMALL LETTER T u'u' # 0x0075 -> LATIN SMALL LETTER U u'v' # 0x0076 -> LATIN SMALL LETTER V u'w' # 0x0077 -> LATIN SMALL LETTER W u'x' # 0x0078 -> LATIN SMALL LETTER X u'y' # 0x0079 -> LATIN SMALL LETTER Y u'z' # 0x007a -> LATIN SMALL LETTER Z u'{' # 0x007b -> LEFT CURLY BRACKET, left-right u'|' # 0x007c -> VERTICAL LINE, left-right u'}' # 0x007d -> RIGHT CURLY BRACKET, left-right u'~' # 0x007e -> TILDE u'\x7f' # 0x007f -> CONTROL CHARACTER u'\xc4' # 0x0080 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xa0' # 0x0081 -> NO-BREAK SPACE, right-left u'\xc7' # 0x0082 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x0083 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x0084 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x0085 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x0086 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x0087 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x0088 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x0089 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x008a -> LATIN SMALL LETTER A WITH DIAERESIS u'\u06ba' # 0x008b -> ARABIC LETTER NOON GHUNNA u'\xab' # 0x008c -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left u'\xe7' # 0x008d -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x008e -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x008f -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x0090 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x0091 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x0092 -> LATIN SMALL LETTER I WITH ACUTE u'\u2026' # 0x0093 -> HORIZONTAL ELLIPSIS, right-left u'\xee' # 0x0094 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x0095 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x0096 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x0097 -> LATIN SMALL LETTER O WITH ACUTE u'\xbb' # 0x0098 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left u'\xf4' # 0x0099 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x009a -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0x009b -> DIVISION SIGN, right-left u'\xfa' # 0x009c -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x009d -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x009e -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x009f -> LATIN SMALL LETTER U WITH DIAERESIS u' ' # 0x00a0 -> SPACE, right-left u'!' # 0x00a1 -> EXCLAMATION MARK, right-left u'"' # 0x00a2 -> QUOTATION MARK, right-left u'#' # 0x00a3 -> NUMBER SIGN, right-left u'$' # 0x00a4 -> DOLLAR SIGN, right-left u'\u066a' # 0x00a5 -> ARABIC PERCENT SIGN u'&' # 0x00a6 -> AMPERSAND, right-left u"'" # 0x00a7 -> APOSTROPHE, right-left u'(' # 0x00a8 -> LEFT PARENTHESIS, right-left u')' # 0x00a9 -> RIGHT PARENTHESIS, right-left u'*' # 0x00aa -> ASTERISK, right-left u'+' # 0x00ab -> PLUS SIGN, right-left u'\u060c' # 0x00ac -> ARABIC COMMA u'-' # 0x00ad -> HYPHEN-MINUS, right-left u'.' # 0x00ae -> FULL STOP, right-left u'/' # 0x00af -> SOLIDUS, right-left u'\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO, right-left (need override) u'\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE, right-left (need override) u'\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO, right-left (need override) u'\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE, right-left (need override) u'\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR, right-left (need override) u'\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE, right-left (need override) u'\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX, right-left (need override) u'\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN, right-left (need override) u'\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT, right-left (need override) u'\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE, right-left (need override) u':' # 0x00ba -> COLON, right-left u'\u061b' # 0x00bb -> ARABIC SEMICOLON u'<' # 0x00bc -> LESS-THAN SIGN, right-left u'=' # 0x00bd -> EQUALS SIGN, right-left u'>' # 0x00be -> GREATER-THAN SIGN, right-left u'\u061f' # 0x00bf -> ARABIC QUESTION MARK u'\u274a' # 0x00c0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left u'\u0621' # 0x00c1 -> ARABIC LETTER HAMZA u'\u0622' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE u'\u0623' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE u'\u0624' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE u'\u0625' # 0x00c5 -> ARABIC LETTER ALEF WITH HAMZA BELOW u'\u0626' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE u'\u0627' # 0x00c7 -> ARABIC LETTER ALEF u'\u0628' # 0x00c8 -> ARABIC LETTER BEH u'\u0629' # 0x00c9 -> ARABIC LETTER TEH MARBUTA u'\u062a' # 0x00ca -> ARABIC LETTER TEH u'\u062b' # 0x00cb -> ARABIC LETTER THEH u'\u062c' # 0x00cc -> ARABIC LETTER JEEM u'\u062d' # 0x00cd -> ARABIC LETTER HAH u'\u062e' # 0x00ce -> ARABIC LETTER KHAH u'\u062f' # 0x00cf -> ARABIC LETTER DAL u'\u0630' # 0x00d0 -> ARABIC LETTER THAL u'\u0631' # 0x00d1 -> ARABIC LETTER REH u'\u0632' # 0x00d2 -> ARABIC LETTER ZAIN u'\u0633' # 0x00d3 -> ARABIC LETTER SEEN u'\u0634' # 0x00d4 -> ARABIC LETTER SHEEN u'\u0635' # 0x00d5 -> ARABIC LETTER SAD u'\u0636' # 0x00d6 -> ARABIC LETTER DAD u'\u0637' # 0x00d7 -> ARABIC LETTER TAH u'\u0638' # 0x00d8 -> ARABIC LETTER ZAH u'\u0639' # 0x00d9 -> ARABIC LETTER AIN u'\u063a' # 0x00da -> ARABIC LETTER GHAIN u'[' # 0x00db -> LEFT SQUARE BRACKET, right-left u'\\' # 0x00dc -> REVERSE SOLIDUS, right-left u']' # 0x00dd -> RIGHT SQUARE BRACKET, right-left u'^' # 0x00de -> CIRCUMFLEX ACCENT, right-left u'_' # 0x00df -> LOW LINE, right-left u'\u0640' # 0x00e0 -> ARABIC TATWEEL u'\u0641' # 0x00e1 -> ARABIC LETTER FEH u'\u0642' # 0x00e2 -> ARABIC LETTER QAF u'\u0643' # 0x00e3 -> ARABIC LETTER KAF u'\u0644' # 0x00e4 -> ARABIC LETTER LAM u'\u0645' # 0x00e5 -> ARABIC LETTER MEEM u'\u0646' # 0x00e6 -> ARABIC LETTER NOON u'\u0647' # 0x00e7 -> ARABIC LETTER HEH u'\u0648' # 0x00e8 -> ARABIC LETTER WAW u'\u0649' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA u'\u064a' # 0x00ea -> ARABIC LETTER YEH u'\u064b' # 0x00eb -> ARABIC FATHATAN u'\u064c' # 0x00ec -> ARABIC DAMMATAN u'\u064d' # 0x00ed -> ARABIC KASRATAN u'\u064e' # 0x00ee -> ARABIC FATHA u'\u064f' # 0x00ef -> ARABIC DAMMA u'\u0650' # 0x00f0 -> ARABIC KASRA u'\u0651' # 0x00f1 -> ARABIC SHADDA u'\u0652' # 0x00f2 -> ARABIC SUKUN u'\u067e' # 0x00f3 -> ARABIC LETTER PEH u'\u0679' # 0x00f4 -> ARABIC LETTER TTEH u'\u0686' # 0x00f5 -> ARABIC LETTER TCHEH u'\u06d5' # 0x00f6 -> ARABIC LETTER AE u'\u06a4' # 0x00f7 -> ARABIC LETTER VEH u'\u06af' # 0x00f8 -> ARABIC LETTER GAF u'\u0688' # 0x00f9 -> ARABIC LETTER DDAL u'\u0691' # 0x00fa -> ARABIC LETTER RREH u'{' # 0x00fb -> LEFT CURLY BRACKET, right-left u'|' # 0x00fc -> VERTICAL LINE, right-left u'}' # 0x00fd -> RIGHT CURLY BRACKET, right-left u'\u0698' # 0x00fe -> ARABIC LETTER JEH u'\u06d2' # 0x00ff -> ARABIC LETTER YEH BARREE ) ### Encoding Map encoding_map = { 0x0000: 0x0000, # CONTROL CHARACTER 0x0001: 0x0001, # CONTROL CHARACTER 0x0002: 0x0002, # CONTROL CHARACTER 0x0003: 0x0003, # CONTROL CHARACTER 0x0004: 0x0004, # CONTROL CHARACTER 0x0005: 0x0005, # CONTROL CHARACTER 0x0006: 0x0006, # CONTROL CHARACTER 0x0007: 0x0007, # CONTROL CHARACTER 0x0008: 0x0008, # CONTROL CHARACTER 0x0009: 0x0009, # CONTROL CHARACTER 0x000a: 0x000a, # CONTROL CHARACTER 0x000b: 0x000b, # CONTROL CHARACTER 0x000c: 0x000c, # CONTROL CHARACTER 0x000d: 0x000d, # CONTROL CHARACTER 0x000e: 0x000e, # CONTROL CHARACTER 0x000f: 0x000f, # CONTROL CHARACTER 0x0010: 0x0010, # CONTROL CHARACTER 0x0011: 0x0011, # CONTROL CHARACTER 0x0012: 0x0012, # CONTROL CHARACTER 0x0013: 0x0013, # CONTROL CHARACTER 0x0014: 0x0014, # CONTROL CHARACTER 0x0015: 0x0015, # CONTROL CHARACTER 0x0016: 0x0016, # CONTROL CHARACTER 0x0017: 0x0017, # CONTROL CHARACTER 0x0018: 0x0018, # CONTROL CHARACTER 0x0019: 0x0019, # CONTROL CHARACTER 0x001a: 0x001a, # CONTROL CHARACTER 0x001b: 0x001b, # CONTROL CHARACTER 0x001c: 0x001c, # CONTROL CHARACTER 0x001d: 0x001d, # CONTROL CHARACTER 0x001e: 0x001e, # CONTROL CHARACTER 0x001f: 0x001f, # CONTROL CHARACTER 0x0020: 0x0020, # SPACE, left-right 0x0020: 0x00a0, # SPACE, right-left 0x0021: 0x0021, # EXCLAMATION MARK, left-right 0x0021: 0x00a1, # EXCLAMATION MARK, right-left 0x0022: 0x0022, # QUOTATION MARK, left-right 0x0022: 0x00a2, # QUOTATION MARK, right-left 0x0023: 0x0023, # NUMBER SIGN, left-right 0x0023: 0x00a3, # NUMBER SIGN, right-left 0x0024: 0x0024, # DOLLAR SIGN, left-right 0x0024: 0x00a4, # DOLLAR SIGN, right-left 0x0025: 0x0025, # PERCENT SIGN, left-right 0x0026: 0x0026, # AMPERSAND, left-right 0x0026: 0x00a6, # AMPERSAND, right-left 0x0027: 0x0027, # APOSTROPHE, left-right 0x0027: 0x00a7, # APOSTROPHE, right-left 0x0028: 0x0028, # LEFT PARENTHESIS, left-right 0x0028: 0x00a8, # LEFT PARENTHESIS, right-left 0x0029: 0x0029, # RIGHT PARENTHESIS, left-right 0x0029: 0x00a9, # RIGHT PARENTHESIS, right-left 0x002a: 0x002a, # ASTERISK, left-right 0x002a: 0x00aa, # ASTERISK, right-left 0x002b: 0x002b, # PLUS SIGN, left-right 0x002b: 0x00ab, # PLUS SIGN, right-left 0x002c: 0x002c, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR 0x002d: 0x002d, # HYPHEN-MINUS, left-right 0x002d: 0x00ad, # HYPHEN-MINUS, right-left 0x002e: 0x002e, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR 0x002e: 0x00ae, # FULL STOP, right-left 0x002f: 0x002f, # SOLIDUS, left-right 0x002f: 0x00af, # SOLIDUS, right-left 0x0030: 0x0030, # DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO 0x0031: 0x0031, # DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE 0x0032: 0x0032, # DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO 0x0033: 0x0033, # DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE 0x0034: 0x0034, # DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR 0x0035: 0x0035, # DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE 0x0036: 0x0036, # DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX 0x0037: 0x0037, # DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN 0x0038: 0x0038, # DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT 0x0039: 0x0039, # DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE 0x003a: 0x003a, # COLON, left-right 0x003a: 0x00ba, # COLON, right-left 0x003b: 0x003b, # SEMICOLON, left-right 0x003c: 0x003c, # LESS-THAN SIGN, left-right 0x003c: 0x00bc, # LESS-THAN SIGN, right-left 0x003d: 0x003d, # EQUALS SIGN, left-right 0x003d: 0x00bd, # EQUALS SIGN, right-left 0x003e: 0x003e, # GREATER-THAN SIGN, left-right 0x003e: 0x00be, # GREATER-THAN SIGN, right-left 0x003f: 0x003f, # QUESTION MARK, left-right 0x0040: 0x0040, # COMMERCIAL AT 0x0041: 0x0041, # LATIN CAPITAL LETTER A 0x0042: 0x0042, # LATIN CAPITAL LETTER B 0x0043: 0x0043, # LATIN CAPITAL LETTER C 0x0044: 0x0044, # LATIN CAPITAL LETTER D 0x0045: 0x0045, # LATIN CAPITAL LETTER E 0x0046: 0x0046, # LATIN CAPITAL LETTER F 0x0047: 0x0047, # LATIN CAPITAL LETTER G 0x0048: 0x0048, # LATIN CAPITAL LETTER H 0x0049: 0x0049, # LATIN CAPITAL LETTER I 0x004a: 0x004a, # LATIN CAPITAL LETTER J 0x004b: 0x004b, # LATIN CAPITAL LETTER K 0x004c: 0x004c, # LATIN CAPITAL LETTER L 0x004d: 0x004d, # LATIN CAPITAL LETTER M 0x004e: 0x004e, # LATIN CAPITAL LETTER N 0x004f: 0x004f, # LATIN CAPITAL LETTER O 0x0050: 0x0050, # LATIN CAPITAL LETTER P 0x0051: 0x0051, # LATIN CAPITAL LETTER Q 0x0052: 0x0052, # LATIN CAPITAL LETTER R 0x0053: 0x0053, # LATIN CAPITAL LETTER S 0x0054: 0x0054, # LATIN CAPITAL LETTER T 0x0055: 0x0055, # LATIN CAPITAL LETTER U 0x0056: 0x0056, # LATIN CAPITAL LETTER V 0x0057: 0x0057, # LATIN CAPITAL LETTER W 0x0058: 0x0058, # LATIN CAPITAL LETTER X 0x0059: 0x0059, # LATIN CAPITAL LETTER Y 0x005a: 0x005a, # LATIN CAPITAL LETTER Z 0x005b: 0x005b, # LEFT SQUARE BRACKET, left-right 0x005b: 0x00db, # LEFT SQUARE BRACKET, right-left 0x005c: 0x005c, # REVERSE SOLIDUS, left-right 0x005c: 0x00dc, # REVERSE SOLIDUS, right-left 0x005d: 0x005d, # RIGHT SQUARE BRACKET, left-right 0x005d: 0x00dd, # RIGHT SQUARE BRACKET, right-left 0x005e: 0x005e, # CIRCUMFLEX ACCENT, left-right 0x005e: 0x00de, # CIRCUMFLEX ACCENT, right-left 0x005f: 0x005f, # LOW LINE, left-right 0x005f: 0x00df, # LOW LINE, right-left 0x0060: 0x0060, # GRAVE ACCENT 0x0061: 0x0061, # LATIN SMALL LETTER A 0x0062: 0x0062, # LATIN SMALL LETTER B 0x0063: 0x0063, # LATIN SMALL LETTER C 0x0064: 0x0064, # LATIN SMALL LETTER D 0x0065: 0x0065, # LATIN SMALL LETTER E 0x0066: 0x0066, # LATIN SMALL LETTER F 0x0067: 0x0067, # LATIN SMALL LETTER G 0x0068: 0x0068, # LATIN SMALL LETTER H 0x0069: 0x0069, # LATIN SMALL LETTER I 0x006a: 0x006a, # LATIN SMALL LETTER J 0x006b: 0x006b, # LATIN SMALL LETTER K 0x006c: 0x006c, # LATIN SMALL LETTER L 0x006d: 0x006d, # LATIN SMALL LETTER M 0x006e: 0x006e, # LATIN SMALL LETTER N 0x006f: 0x006f, # LATIN SMALL LETTER O 0x0070: 0x0070, # LATIN SMALL LETTER P 0x0071: 0x0071, # LATIN SMALL LETTER Q 0x0072: 0x0072, # LATIN SMALL LETTER R 0x0073: 0x0073, # LATIN SMALL LETTER S 0x0074: 0x0074, # LATIN SMALL LETTER T 0x0075: 0x0075, # LATIN SMALL LETTER U 0x0076: 0x0076, # LATIN SMALL LETTER V 0x0077: 0x0077, # LATIN SMALL LETTER W 0x0078: 0x0078, # LATIN SMALL LETTER X 0x0079: 0x0079, # LATIN SMALL LETTER Y 0x007a: 0x007a, # LATIN SMALL LETTER Z 0x007b: 0x007b, # LEFT CURLY BRACKET, left-right 0x007b: 0x00fb, # LEFT CURLY BRACKET, right-left 0x007c: 0x007c, # VERTICAL LINE, left-right 0x007c: 0x00fc, # VERTICAL LINE, right-left 0x007d: 0x007d, # RIGHT CURLY BRACKET, left-right 0x007d: 0x00fd, # RIGHT CURLY BRACKET, right-left 0x007e: 0x007e, # TILDE 0x007f: 0x007f, # CONTROL CHARACTER 0x00a0: 0x0081, # NO-BREAK SPACE, right-left 0x00ab: 0x008c, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x00bb: 0x0098, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left 0x00c4: 0x0080, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x00c7: 0x0082, # LATIN CAPITAL LETTER C WITH CEDILLA 0x00c9: 0x0083, # LATIN CAPITAL LETTER E WITH ACUTE 0x00d1: 0x0084, # LATIN CAPITAL LETTER N WITH TILDE 0x00d6: 0x0085, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x00dc: 0x0086, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x00e0: 0x0088, # LATIN SMALL LETTER A WITH GRAVE 0x00e1: 0x0087, # LATIN SMALL LETTER A WITH ACUTE 0x00e2: 0x0089, # LATIN SMALL LETTER A WITH CIRCUMFLEX 0x00e4: 0x008a, # LATIN SMALL LETTER A WITH DIAERESIS 0x00e7: 0x008d, # LATIN SMALL LETTER C WITH CEDILLA 0x00e8: 0x008f, # LATIN SMALL LETTER E WITH GRAVE 0x00e9: 0x008e, # LATIN SMALL LETTER E WITH ACUTE 0x00ea: 0x0090, # LATIN SMALL LETTER E WITH CIRCUMFLEX 0x00eb: 0x0091, # LATIN SMALL LETTER E WITH DIAERESIS 0x00ed: 0x0092, # LATIN SMALL LETTER I WITH ACUTE 0x00ee: 0x0094, # LATIN SMALL LETTER I WITH CIRCUMFLEX 0x00ef: 0x0095, # LATIN SMALL LETTER I WITH DIAERESIS 0x00f1: 0x0096, # LATIN SMALL LETTER N WITH TILDE 0x00f3: 0x0097, # LATIN SMALL LETTER O WITH ACUTE 0x00f4: 0x0099, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x00f6: 0x009a, # LATIN SMALL LETTER O WITH DIAERESIS 0x00f7: 0x009b, # DIVISION SIGN, right-left 0x00f9: 0x009d, # LATIN SMALL LETTER U WITH GRAVE 0x00fa: 0x009c, # LATIN SMALL LETTER U WITH ACUTE 0x00fb: 0x009e, # LATIN SMALL LETTER U WITH CIRCUMFLEX 0x00fc: 0x009f, # LATIN SMALL LETTER U WITH DIAERESIS 0x060c: 0x00ac, # ARABIC COMMA 0x061b: 0x00bb, # ARABIC SEMICOLON 0x061f: 0x00bf, # ARABIC QUESTION MARK 0x0621: 0x00c1, # ARABIC LETTER HAMZA 0x0622: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE 0x0623: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE 0x0624: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE 0x0625: 0x00c5, # ARABIC LETTER ALEF WITH HAMZA BELOW 0x0626: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE 0x0627: 0x00c7, # ARABIC LETTER ALEF 0x0628: 0x00c8, # ARABIC LETTER BEH 0x0629: 0x00c9, # ARABIC LETTER TEH MARBUTA 0x062a: 0x00ca, # ARABIC LETTER TEH 0x062b: 0x00cb, # ARABIC LETTER THEH 0x062c: 0x00cc, # ARABIC LETTER JEEM 0x062d: 0x00cd, # ARABIC LETTER HAH 0x062e: 0x00ce, # ARABIC LETTER KHAH 0x062f: 0x00cf, # ARABIC LETTER DAL 0x0630: 0x00d0, # ARABIC LETTER THAL 0x0631: 0x00d1, # ARABIC LETTER REH 0x0632: 0x00d2, # ARABIC LETTER ZAIN 0x0633: 0x00d3, # ARABIC LETTER SEEN 0x0634: 0x00d4, # ARABIC LETTER SHEEN 0x0635: 0x00d5, # ARABIC LETTER SAD 0x0636: 0x00d6, # ARABIC LETTER DAD 0x0637: 0x00d7, # ARABIC LETTER TAH 0x0638: 0x00d8, # ARABIC LETTER ZAH 0x0639: 0x00d9, # ARABIC LETTER AIN 0x063a: 0x00da, # ARABIC LETTER GHAIN 0x0640: 0x00e0, # ARABIC TATWEEL 0x0641: 0x00e1, # ARABIC LETTER FEH 0x0642: 0x00e2, # ARABIC LETTER QAF 0x0643: 0x00e3, # ARABIC LETTER KAF 0x0644: 0x00e4, # ARABIC LETTER LAM 0x0645: 0x00e5, # ARABIC LETTER MEEM 0x0646: 0x00e6, # ARABIC LETTER NOON 0x0647: 0x00e7, # ARABIC LETTER HEH 0x0648: 0x00e8, # ARABIC LETTER WAW 0x0649: 0x00e9, # ARABIC LETTER ALEF MAKSURA 0x064a: 0x00ea, # ARABIC LETTER YEH 0x064b: 0x00eb, # ARABIC FATHATAN 0x064c: 0x00ec, # ARABIC DAMMATAN 0x064d: 0x00ed, # ARABIC KASRATAN 0x064e: 0x00ee, # ARABIC FATHA 0x064f: 0x00ef, # ARABIC DAMMA 0x0650: 0x00f0, # ARABIC KASRA 0x0651: 0x00f1, # ARABIC SHADDA 0x0652: 0x00f2, # ARABIC SUKUN 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO, right-left (need override) 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE, right-left (need override) 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO, right-left (need override) 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE, right-left (need override) 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR, right-left (need override) 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE, right-left (need override) 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX, right-left (need override) 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE, right-left (need override) 0x066a: 0x00a5, # ARABIC PERCENT SIGN 0x0679: 0x00f4, # ARABIC LETTER TTEH 0x067e: 0x00f3, # ARABIC LETTER PEH 0x0686: 0x00f5, # ARABIC LETTER TCHEH 0x0688: 0x00f9, # ARABIC LETTER DDAL 0x0691: 0x00fa, # ARABIC LETTER RREH 0x0698: 0x00fe, # ARABIC LETTER JEH 0x06a4: 0x00f7, # ARABIC LETTER VEH 0x06af: 0x00f8, # ARABIC LETTER GAF 0x06ba: 0x008b, # ARABIC LETTER NOON GHUNNA 0x06d2: 0x00ff, # ARABIC LETTER YEH BARREE 0x06d5: 0x00f6, # ARABIC LETTER AE 0x2026: 0x0093, # HORIZONTAL ELLIPSIS, right-left 0x274a: 0x00c0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left } feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_centeuro.py0000644000076500000240000003402612612565547024744 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_centeuro generated from 'MAPPINGS/VENDORS/APPLE/CENTEURO.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-centeuro', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\u0100' # 0x81 -> LATIN CAPITAL LETTER A WITH MACRON u'\u0101' # 0x82 -> LATIN SMALL LETTER A WITH MACRON u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\u0104' # 0x84 -> LATIN CAPITAL LETTER A WITH OGONEK u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\u0105' # 0x88 -> LATIN SMALL LETTER A WITH OGONEK u'\u010c' # 0x89 -> LATIN CAPITAL LETTER C WITH CARON u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\u010d' # 0x8B -> LATIN SMALL LETTER C WITH CARON u'\u0106' # 0x8C -> LATIN CAPITAL LETTER C WITH ACUTE u'\u0107' # 0x8D -> LATIN SMALL LETTER C WITH ACUTE u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE u'\u017a' # 0x90 -> LATIN SMALL LETTER Z WITH ACUTE u'\u010e' # 0x91 -> LATIN CAPITAL LETTER D WITH CARON u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\u010f' # 0x93 -> LATIN SMALL LETTER D WITH CARON u'\u0112' # 0x94 -> LATIN CAPITAL LETTER E WITH MACRON u'\u0113' # 0x95 -> LATIN SMALL LETTER E WITH MACRON u'\u0116' # 0x96 -> LATIN CAPITAL LETTER E WITH DOT ABOVE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\u0117' # 0x98 -> LATIN SMALL LETTER E WITH DOT ABOVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\u011a' # 0x9D -> LATIN CAPITAL LETTER E WITH CARON u'\u011b' # 0x9E -> LATIN SMALL LETTER E WITH CARON u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\u0118' # 0xA2 -> LATIN CAPITAL LETTER E WITH OGONEK u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\u0119' # 0xAB -> LATIN SMALL LETTER E WITH OGONEK u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\u0123' # 0xAE -> LATIN SMALL LETTER G WITH CEDILLA u'\u012e' # 0xAF -> LATIN CAPITAL LETTER I WITH OGONEK u'\u012f' # 0xB0 -> LATIN SMALL LETTER I WITH OGONEK u'\u012a' # 0xB1 -> LATIN CAPITAL LETTER I WITH MACRON u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON u'\u0136' # 0xB5 -> LATIN CAPITAL LETTER K WITH CEDILLA u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u0142' # 0xB8 -> LATIN SMALL LETTER L WITH STROKE u'\u013b' # 0xB9 -> LATIN CAPITAL LETTER L WITH CEDILLA u'\u013c' # 0xBA -> LATIN SMALL LETTER L WITH CEDILLA u'\u013d' # 0xBB -> LATIN CAPITAL LETTER L WITH CARON u'\u013e' # 0xBC -> LATIN SMALL LETTER L WITH CARON u'\u0139' # 0xBD -> LATIN CAPITAL LETTER L WITH ACUTE u'\u013a' # 0xBE -> LATIN SMALL LETTER L WITH ACUTE u'\u0145' # 0xBF -> LATIN CAPITAL LETTER N WITH CEDILLA u'\u0146' # 0xC0 -> LATIN SMALL LETTER N WITH CEDILLA u'\u0143' # 0xC1 -> LATIN CAPITAL LETTER N WITH ACUTE u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0144' # 0xC4 -> LATIN SMALL LETTER N WITH ACUTE u'\u0147' # 0xC5 -> LATIN CAPITAL LETTER N WITH CARON u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\u0148' # 0xCB -> LATIN SMALL LETTER N WITH CARON u'\u0150' # 0xCC -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0151' # 0xCE -> LATIN SMALL LETTER O WITH DOUBLE ACUTE u'\u014c' # 0xCF -> LATIN CAPITAL LETTER O WITH MACRON u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\u014d' # 0xD8 -> LATIN SMALL LETTER O WITH MACRON u'\u0154' # 0xD9 -> LATIN CAPITAL LETTER R WITH ACUTE u'\u0155' # 0xDA -> LATIN SMALL LETTER R WITH ACUTE u'\u0158' # 0xDB -> LATIN CAPITAL LETTER R WITH CARON u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u0159' # 0xDE -> LATIN SMALL LETTER R WITH CARON u'\u0156' # 0xDF -> LATIN CAPITAL LETTER R WITH CEDILLA u'\u0157' # 0xE0 -> LATIN SMALL LETTER R WITH CEDILLA u'\u0160' # 0xE1 -> LATIN CAPITAL LETTER S WITH CARON u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u0161' # 0xE4 -> LATIN SMALL LETTER S WITH CARON u'\u015a' # 0xE5 -> LATIN CAPITAL LETTER S WITH ACUTE u'\u015b' # 0xE6 -> LATIN SMALL LETTER S WITH ACUTE u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\u0164' # 0xE8 -> LATIN CAPITAL LETTER T WITH CARON u'\u0165' # 0xE9 -> LATIN SMALL LETTER T WITH CARON u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\u017d' # 0xEB -> LATIN CAPITAL LETTER Z WITH CARON u'\u017e' # 0xEC -> LATIN SMALL LETTER Z WITH CARON u'\u016a' # 0xED -> LATIN CAPITAL LETTER U WITH MACRON u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u016b' # 0xF0 -> LATIN SMALL LETTER U WITH MACRON u'\u016e' # 0xF1 -> LATIN CAPITAL LETTER U WITH RING ABOVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\u016f' # 0xF3 -> LATIN SMALL LETTER U WITH RING ABOVE u'\u0170' # 0xF4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE u'\u0171' # 0xF5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE u'\u0172' # 0xF6 -> LATIN CAPITAL LETTER U WITH OGONEK u'\u0173' # 0xF7 -> LATIN SMALL LETTER U WITH OGONEK u'\xdd' # 0xF8 -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xfd' # 0xF9 -> LATIN SMALL LETTER Y WITH ACUTE u'\u0137' # 0xFA -> LATIN SMALL LETTER K WITH CEDILLA u'\u017b' # 0xFB -> LATIN CAPITAL LETTER Z WITH DOT ABOVE u'\u0141' # 0xFC -> LATIN CAPITAL LETTER L WITH STROKE u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE u'\u0122' # 0xFE -> LATIN CAPITAL LETTER G WITH CEDILLA u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_croatian.py0000644000076500000240000003310112612565547024711 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_croatian generated from 'MAPPINGS/VENDORS/APPLE/CROATIAN.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-croatian', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON u'\u2122' # 0xAA -> TRADE MARK SIGN u'\xb4' # 0xAB -> ACUTE ACCENT u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\u2206' # 0xB4 -> INCREMENT u'\xb5' # 0xB5 -> MICRO SIGN u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u220f' # 0xB8 -> N-ARY PRODUCT u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON u'\u222b' # 0xBA -> INTEGRAL u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE u'\xbf' # 0xC0 -> INVERTED QUESTION MARK u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\uf8ff' # 0xD8 -> Apple logo u'\xa9' # 0xD9 -> COPYRIGHT SIGN u'\u2044' # 0xDA -> FRACTION SLASH u'\u20ac' # 0xDB -> EURO SIGN u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\xc6' # 0xDE -> LATIN CAPITAL LETTER AE u'\xbb' # 0xDF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2013' # 0xE0 -> EN DASH u'\xb7' # 0xE1 -> MIDDLE DOT u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u2030' # 0xE4 -> PER MILLE SIGN u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u02dc' # 0xF7 -> SMALL TILDE u'\xaf' # 0xF8 -> MACRON u'\u03c0' # 0xF9 -> GREEK SMALL LETTER PI u'\xcb' # 0xFA -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\u02da' # 0xFB -> RING ABOVE u'\xb8' # 0xFC -> CEDILLA u'\xca' # 0xFD -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xe6' # 0xFE -> LATIN SMALL LETTER AE u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_cyrillic.py0000644000076500000240000003261612612565547024735 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_cyrillic generated from 'MAPPINGS/VENDORS/APPLE/CYRILLIC.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-cyrillic', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\u0410' # 0x80 -> CYRILLIC CAPITAL LETTER A u'\u0411' # 0x81 -> CYRILLIC CAPITAL LETTER BE u'\u0412' # 0x82 -> CYRILLIC CAPITAL LETTER VE u'\u0413' # 0x83 -> CYRILLIC CAPITAL LETTER GHE u'\u0414' # 0x84 -> CYRILLIC CAPITAL LETTER DE u'\u0415' # 0x85 -> CYRILLIC CAPITAL LETTER IE u'\u0416' # 0x86 -> CYRILLIC CAPITAL LETTER ZHE u'\u0417' # 0x87 -> CYRILLIC CAPITAL LETTER ZE u'\u0418' # 0x88 -> CYRILLIC CAPITAL LETTER I u'\u0419' # 0x89 -> CYRILLIC CAPITAL LETTER SHORT I u'\u041a' # 0x8A -> CYRILLIC CAPITAL LETTER KA u'\u041b' # 0x8B -> CYRILLIC CAPITAL LETTER EL u'\u041c' # 0x8C -> CYRILLIC CAPITAL LETTER EM u'\u041d' # 0x8D -> CYRILLIC CAPITAL LETTER EN u'\u041e' # 0x8E -> CYRILLIC CAPITAL LETTER O u'\u041f' # 0x8F -> CYRILLIC CAPITAL LETTER PE u'\u0420' # 0x90 -> CYRILLIC CAPITAL LETTER ER u'\u0421' # 0x91 -> CYRILLIC CAPITAL LETTER ES u'\u0422' # 0x92 -> CYRILLIC CAPITAL LETTER TE u'\u0423' # 0x93 -> CYRILLIC CAPITAL LETTER U u'\u0424' # 0x94 -> CYRILLIC CAPITAL LETTER EF u'\u0425' # 0x95 -> CYRILLIC CAPITAL LETTER HA u'\u0426' # 0x96 -> CYRILLIC CAPITAL LETTER TSE u'\u0427' # 0x97 -> CYRILLIC CAPITAL LETTER CHE u'\u0428' # 0x98 -> CYRILLIC CAPITAL LETTER SHA u'\u0429' # 0x99 -> CYRILLIC CAPITAL LETTER SHCHA u'\u042a' # 0x9A -> CYRILLIC CAPITAL LETTER HARD SIGN u'\u042b' # 0x9B -> CYRILLIC CAPITAL LETTER YERU u'\u042c' # 0x9C -> CYRILLIC CAPITAL LETTER SOFT SIGN u'\u042d' # 0x9D -> CYRILLIC CAPITAL LETTER E u'\u042e' # 0x9E -> CYRILLIC CAPITAL LETTER YU u'\u042f' # 0x9F -> CYRILLIC CAPITAL LETTER YA u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\u0490' # 0xA2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\u0406' # 0xA7 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\u0402' # 0xAB -> CYRILLIC CAPITAL LETTER DJE u'\u0452' # 0xAC -> CYRILLIC SMALL LETTER DJE u'\u2260' # 0xAD -> NOT EQUAL TO u'\u0403' # 0xAE -> CYRILLIC CAPITAL LETTER GJE u'\u0453' # 0xAF -> CYRILLIC SMALL LETTER GJE u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\u0456' # 0xB4 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I u'\xb5' # 0xB5 -> MICRO SIGN u'\u0491' # 0xB6 -> CYRILLIC SMALL LETTER GHE WITH UPTURN u'\u0408' # 0xB7 -> CYRILLIC CAPITAL LETTER JE u'\u0404' # 0xB8 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE u'\u0454' # 0xB9 -> CYRILLIC SMALL LETTER UKRAINIAN IE u'\u0407' # 0xBA -> CYRILLIC CAPITAL LETTER YI u'\u0457' # 0xBB -> CYRILLIC SMALL LETTER YI u'\u0409' # 0xBC -> CYRILLIC CAPITAL LETTER LJE u'\u0459' # 0xBD -> CYRILLIC SMALL LETTER LJE u'\u040a' # 0xBE -> CYRILLIC CAPITAL LETTER NJE u'\u045a' # 0xBF -> CYRILLIC SMALL LETTER NJE u'\u0458' # 0xC0 -> CYRILLIC SMALL LETTER JE u'\u0405' # 0xC1 -> CYRILLIC CAPITAL LETTER DZE u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\u040b' # 0xCB -> CYRILLIC CAPITAL LETTER TSHE u'\u045b' # 0xCC -> CYRILLIC SMALL LETTER TSHE u'\u040c' # 0xCD -> CYRILLIC CAPITAL LETTER KJE u'\u045c' # 0xCE -> CYRILLIC SMALL LETTER KJE u'\u0455' # 0xCF -> CYRILLIC SMALL LETTER DZE u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u201e' # 0xD7 -> DOUBLE LOW-9 QUOTATION MARK u'\u040e' # 0xD8 -> CYRILLIC CAPITAL LETTER SHORT U u'\u045e' # 0xD9 -> CYRILLIC SMALL LETTER SHORT U u'\u040f' # 0xDA -> CYRILLIC CAPITAL LETTER DZHE u'\u045f' # 0xDB -> CYRILLIC SMALL LETTER DZHE u'\u2116' # 0xDC -> NUMERO SIGN u'\u0401' # 0xDD -> CYRILLIC CAPITAL LETTER IO u'\u0451' # 0xDE -> CYRILLIC SMALL LETTER IO u'\u044f' # 0xDF -> CYRILLIC SMALL LETTER YA u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU u'\u20ac' # 0xFF -> EURO SIGN ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_farsi.py0000644000076500000240000003610212612565547024221 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_farsi generated from 'MAPPINGS/VENDORS/APPLE/FARSI.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-farsi', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE, left-right u'!' # 0x21 -> EXCLAMATION MARK, left-right u'"' # 0x22 -> QUOTATION MARK, left-right u'#' # 0x23 -> NUMBER SIGN, left-right u'$' # 0x24 -> DOLLAR SIGN, left-right u'%' # 0x25 -> PERCENT SIGN, left-right u'&' # 0x26 -> AMPERSAND, left-right u"'" # 0x27 -> APOSTROPHE, left-right u'(' # 0x28 -> LEFT PARENTHESIS, left-right u')' # 0x29 -> RIGHT PARENTHESIS, left-right u'*' # 0x2A -> ASTERISK, left-right u'+' # 0x2B -> PLUS SIGN, left-right u',' # 0x2C -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR u'-' # 0x2D -> HYPHEN-MINUS, left-right u'.' # 0x2E -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR u'/' # 0x2F -> SOLIDUS, left-right u'0' # 0x30 -> DIGIT ZERO; in Arabic-script context, displayed as 0x06F0 EXTENDED ARABIC-INDIC DIGIT ZERO u'1' # 0x31 -> DIGIT ONE; in Arabic-script context, displayed as 0x06F1 EXTENDED ARABIC-INDIC DIGIT ONE u'2' # 0x32 -> DIGIT TWO; in Arabic-script context, displayed as 0x06F2 EXTENDED ARABIC-INDIC DIGIT TWO u'3' # 0x33 -> DIGIT THREE; in Arabic-script context, displayed as 0x06F3 EXTENDED ARABIC-INDIC DIGIT THREE u'4' # 0x34 -> DIGIT FOUR; in Arabic-script context, displayed as 0x06F4 EXTENDED ARABIC-INDIC DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE; in Arabic-script context, displayed as 0x06F5 EXTENDED ARABIC-INDIC DIGIT FIVE u'6' # 0x36 -> DIGIT SIX; in Arabic-script context, displayed as 0x06F6 EXTENDED ARABIC-INDIC DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x06F7 EXTENDED ARABIC-INDIC DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x06F8 EXTENDED ARABIC-INDIC DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE; in Arabic-script context, displayed as 0x06F9 EXTENDED ARABIC-INDIC DIGIT NINE u':' # 0x3A -> COLON, left-right u';' # 0x3B -> SEMICOLON, left-right u'<' # 0x3C -> LESS-THAN SIGN, left-right u'=' # 0x3D -> EQUALS SIGN, left-right u'>' # 0x3E -> GREATER-THAN SIGN, left-right u'?' # 0x3F -> QUESTION MARK, left-right u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET, left-right u'\\' # 0x5C -> REVERSE SOLIDUS, left-right u']' # 0x5D -> RIGHT SQUARE BRACKET, left-right u'^' # 0x5E -> CIRCUMFLEX ACCENT, left-right u'_' # 0x5F -> LOW LINE, left-right u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET, left-right u'|' # 0x7C -> VERTICAL LINE, left-right u'}' # 0x7D -> RIGHT CURLY BRACKET, left-right u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xa0' # 0x81 -> NO-BREAK SPACE, right-left u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\u06ba' # 0x8B -> ARABIC LETTER NOON GHUNNA u'\xab' # 0x8C -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\u2026' # 0x93 -> HORIZONTAL ELLIPSIS, right-left u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xbb' # 0x98 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf7' # 0x9B -> DIVISION SIGN, right-left u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u' ' # 0xA0 -> SPACE, right-left u'!' # 0xA1 -> EXCLAMATION MARK, right-left u'"' # 0xA2 -> QUOTATION MARK, right-left u'#' # 0xA3 -> NUMBER SIGN, right-left u'$' # 0xA4 -> DOLLAR SIGN, right-left u'\u066a' # 0xA5 -> ARABIC PERCENT SIGN u'&' # 0xA6 -> AMPERSAND, right-left u"'" # 0xA7 -> APOSTROPHE, right-left u'(' # 0xA8 -> LEFT PARENTHESIS, right-left u')' # 0xA9 -> RIGHT PARENTHESIS, right-left u'*' # 0xAA -> ASTERISK, right-left u'+' # 0xAB -> PLUS SIGN, right-left u'\u060c' # 0xAC -> ARABIC COMMA u'-' # 0xAD -> HYPHEN-MINUS, right-left u'.' # 0xAE -> FULL STOP, right-left u'/' # 0xAF -> SOLIDUS, right-left u'\u06f0' # 0xB0 -> EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) u'\u06f1' # 0xB1 -> EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) u'\u06f2' # 0xB2 -> EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) u'\u06f3' # 0xB3 -> EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) u'\u06f4' # 0xB4 -> EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) u'\u06f5' # 0xB5 -> EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) u'\u06f6' # 0xB6 -> EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) u'\u06f7' # 0xB7 -> EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) u'\u06f8' # 0xB8 -> EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) u'\u06f9' # 0xB9 -> EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) u':' # 0xBA -> COLON, right-left u'\u061b' # 0xBB -> ARABIC SEMICOLON u'<' # 0xBC -> LESS-THAN SIGN, right-left u'=' # 0xBD -> EQUALS SIGN, right-left u'>' # 0xBE -> GREATER-THAN SIGN, right-left u'\u061f' # 0xBF -> ARABIC QUESTION MARK u'\u274a' # 0xC0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE u'\u0627' # 0xC7 -> ARABIC LETTER ALEF u'\u0628' # 0xC8 -> ARABIC LETTER BEH u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA u'\u062a' # 0xCA -> ARABIC LETTER TEH u'\u062b' # 0xCB -> ARABIC LETTER THEH u'\u062c' # 0xCC -> ARABIC LETTER JEEM u'\u062d' # 0xCD -> ARABIC LETTER HAH u'\u062e' # 0xCE -> ARABIC LETTER KHAH u'\u062f' # 0xCF -> ARABIC LETTER DAL u'\u0630' # 0xD0 -> ARABIC LETTER THAL u'\u0631' # 0xD1 -> ARABIC LETTER REH u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN u'\u0633' # 0xD3 -> ARABIC LETTER SEEN u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN u'\u0635' # 0xD5 -> ARABIC LETTER SAD u'\u0636' # 0xD6 -> ARABIC LETTER DAD u'\u0637' # 0xD7 -> ARABIC LETTER TAH u'\u0638' # 0xD8 -> ARABIC LETTER ZAH u'\u0639' # 0xD9 -> ARABIC LETTER AIN u'\u063a' # 0xDA -> ARABIC LETTER GHAIN u'[' # 0xDB -> LEFT SQUARE BRACKET, right-left u'\\' # 0xDC -> REVERSE SOLIDUS, right-left u']' # 0xDD -> RIGHT SQUARE BRACKET, right-left u'^' # 0xDE -> CIRCUMFLEX ACCENT, right-left u'_' # 0xDF -> LOW LINE, right-left u'\u0640' # 0xE0 -> ARABIC TATWEEL u'\u0641' # 0xE1 -> ARABIC LETTER FEH u'\u0642' # 0xE2 -> ARABIC LETTER QAF u'\u0643' # 0xE3 -> ARABIC LETTER KAF u'\u0644' # 0xE4 -> ARABIC LETTER LAM u'\u0645' # 0xE5 -> ARABIC LETTER MEEM u'\u0646' # 0xE6 -> ARABIC LETTER NOON u'\u0647' # 0xE7 -> ARABIC LETTER HEH u'\u0648' # 0xE8 -> ARABIC LETTER WAW u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA u'\u064a' # 0xEA -> ARABIC LETTER YEH u'\u064b' # 0xEB -> ARABIC FATHATAN u'\u064c' # 0xEC -> ARABIC DAMMATAN u'\u064d' # 0xED -> ARABIC KASRATAN u'\u064e' # 0xEE -> ARABIC FATHA u'\u064f' # 0xEF -> ARABIC DAMMA u'\u0650' # 0xF0 -> ARABIC KASRA u'\u0651' # 0xF1 -> ARABIC SHADDA u'\u0652' # 0xF2 -> ARABIC SUKUN u'\u067e' # 0xF3 -> ARABIC LETTER PEH u'\u0679' # 0xF4 -> ARABIC LETTER TTEH u'\u0686' # 0xF5 -> ARABIC LETTER TCHEH u'\u06d5' # 0xF6 -> ARABIC LETTER AE u'\u06a4' # 0xF7 -> ARABIC LETTER VEH u'\u06af' # 0xF8 -> ARABIC LETTER GAF u'\u0688' # 0xF9 -> ARABIC LETTER DDAL u'\u0691' # 0xFA -> ARABIC LETTER RREH u'{' # 0xFB -> LEFT CURLY BRACKET, right-left u'|' # 0xFC -> VERTICAL LINE, right-left u'}' # 0xFD -> RIGHT CURLY BRACKET, right-left u'\u0698' # 0xFE -> ARABIC LETTER JEH u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_greek.py0000644000076500000240000003323112612565547024212 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_greek generated from 'MAPPINGS/VENDORS/APPLE/GREEK.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-greek', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xb9' # 0x81 -> SUPERSCRIPT ONE u'\xb2' # 0x82 -> SUPERSCRIPT TWO u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xb3' # 0x84 -> SUPERSCRIPT THREE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\u0385' # 0x87 -> GREEK DIALYTIKA TONOS u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\u0384' # 0x8B -> GREEK TONOS u'\xa8' # 0x8C -> DIAERESIS u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xa3' # 0x92 -> POUND SIGN u'\u2122' # 0x93 -> TRADE MARK SIGN u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\u2022' # 0x96 -> BULLET u'\xbd' # 0x97 -> VULGAR FRACTION ONE HALF u'\u2030' # 0x98 -> PER MILLE SIGN u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xa6' # 0x9B -> BROKEN BAR u'\u20ac' # 0x9C -> EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\u0393' # 0xA1 -> GREEK CAPITAL LETTER GAMMA u'\u0394' # 0xA2 -> GREEK CAPITAL LETTER DELTA u'\u0398' # 0xA3 -> GREEK CAPITAL LETTER THETA u'\u039b' # 0xA4 -> GREEK CAPITAL LETTER LAMDA u'\u039e' # 0xA5 -> GREEK CAPITAL LETTER XI u'\u03a0' # 0xA6 -> GREEK CAPITAL LETTER PI u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u03a3' # 0xAA -> GREEK CAPITAL LETTER SIGMA u'\u03aa' # 0xAB -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA u'\xa7' # 0xAC -> SECTION SIGN u'\u2260' # 0xAD -> NOT EQUAL TO u'\xb0' # 0xAE -> DEGREE SIGN u'\xb7' # 0xAF -> MIDDLE DOT u'\u0391' # 0xB0 -> GREEK CAPITAL LETTER ALPHA u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\xa5' # 0xB4 -> YEN SIGN u'\u0392' # 0xB5 -> GREEK CAPITAL LETTER BETA u'\u0395' # 0xB6 -> GREEK CAPITAL LETTER EPSILON u'\u0396' # 0xB7 -> GREEK CAPITAL LETTER ZETA u'\u0397' # 0xB8 -> GREEK CAPITAL LETTER ETA u'\u0399' # 0xB9 -> GREEK CAPITAL LETTER IOTA u'\u039a' # 0xBA -> GREEK CAPITAL LETTER KAPPA u'\u039c' # 0xBB -> GREEK CAPITAL LETTER MU u'\u03a6' # 0xBC -> GREEK CAPITAL LETTER PHI u'\u03ab' # 0xBD -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA u'\u03a8' # 0xBE -> GREEK CAPITAL LETTER PSI u'\u03a9' # 0xBF -> GREEK CAPITAL LETTER OMEGA u'\u03ac' # 0xC0 -> GREEK SMALL LETTER ALPHA WITH TONOS u'\u039d' # 0xC1 -> GREEK CAPITAL LETTER NU u'\xac' # 0xC2 -> NOT SIGN u'\u039f' # 0xC3 -> GREEK CAPITAL LETTER OMICRON u'\u03a1' # 0xC4 -> GREEK CAPITAL LETTER RHO u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u03a4' # 0xC6 -> GREEK CAPITAL LETTER TAU u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\u03a5' # 0xCB -> GREEK CAPITAL LETTER UPSILON u'\u03a7' # 0xCC -> GREEK CAPITAL LETTER CHI u'\u0386' # 0xCD -> GREEK CAPITAL LETTER ALPHA WITH TONOS u'\u0388' # 0xCE -> GREEK CAPITAL LETTER EPSILON WITH TONOS u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u2013' # 0xD0 -> EN DASH u'\u2015' # 0xD1 -> HORIZONTAL BAR u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u0389' # 0xD7 -> GREEK CAPITAL LETTER ETA WITH TONOS u'\u038a' # 0xD8 -> GREEK CAPITAL LETTER IOTA WITH TONOS u'\u038c' # 0xD9 -> GREEK CAPITAL LETTER OMICRON WITH TONOS u'\u038e' # 0xDA -> GREEK CAPITAL LETTER UPSILON WITH TONOS u'\u03ad' # 0xDB -> GREEK SMALL LETTER EPSILON WITH TONOS u'\u03ae' # 0xDC -> GREEK SMALL LETTER ETA WITH TONOS u'\u03af' # 0xDD -> GREEK SMALL LETTER IOTA WITH TONOS u'\u03cc' # 0xDE -> GREEK SMALL LETTER OMICRON WITH TONOS u'\u038f' # 0xDF -> GREEK CAPITAL LETTER OMEGA WITH TONOS u'\u03cd' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH TONOS u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA u'\u03c8' # 0xE3 -> GREEK SMALL LETTER PSI u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON u'\u03c6' # 0xE6 -> GREEK SMALL LETTER PHI u'\u03b3' # 0xE7 -> GREEK SMALL LETTER GAMMA u'\u03b7' # 0xE8 -> GREEK SMALL LETTER ETA u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA u'\u03be' # 0xEA -> GREEK SMALL LETTER XI u'\u03ba' # 0xEB -> GREEK SMALL LETTER KAPPA u'\u03bb' # 0xEC -> GREEK SMALL LETTER LAMDA u'\u03bc' # 0xED -> GREEK SMALL LETTER MU u'\u03bd' # 0xEE -> GREEK SMALL LETTER NU u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI u'\u03ce' # 0xF1 -> GREEK SMALL LETTER OMEGA WITH TONOS u'\u03c1' # 0xF2 -> GREEK SMALL LETTER RHO u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU u'\u03b8' # 0xF5 -> GREEK SMALL LETTER THETA u'\u03c9' # 0xF6 -> GREEK SMALL LETTER OMEGA u'\u03c2' # 0xF7 -> GREEK SMALL LETTER FINAL SIGMA u'\u03c7' # 0xF8 -> GREEK SMALL LETTER CHI u'\u03c5' # 0xF9 -> GREEK SMALL LETTER UPSILON u'\u03b6' # 0xFA -> GREEK SMALL LETTER ZETA u'\u03ca' # 0xFB -> GREEK SMALL LETTER IOTA WITH DIALYTIKA u'\u03cb' # 0xFC -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA u'\u0390' # 0xFD -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS u'\u03b0' # 0xFE -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS u'\xad' # 0xFF -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_iceland.py0000644000076500000240000003267212612565547024524 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_iceland generated from 'MAPPINGS/VENDORS/APPLE/ICELAND.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-iceland', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\xdd' # 0xA0 -> LATIN CAPITAL LETTER Y WITH ACUTE u'\xb0' # 0xA1 -> DEGREE SIGN u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\xb4' # 0xAB -> ACUTE ACCENT u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\xa5' # 0xB4 -> YEN SIGN u'\xb5' # 0xB5 -> MICRO SIGN u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u220f' # 0xB8 -> N-ARY PRODUCT u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI u'\u222b' # 0xBA -> INTEGRAL u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA u'\xe6' # 0xBE -> LATIN SMALL LETTER AE u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE u'\xbf' # 0xC0 -> INVERTED QUESTION MARK u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u2044' # 0xDA -> FRACTION SLASH u'\u20ac' # 0xDB -> EURO SIGN u'\xd0' # 0xDC -> LATIN CAPITAL LETTER ETH u'\xf0' # 0xDD -> LATIN SMALL LETTER ETH u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN u'\xfe' # 0xDF -> LATIN SMALL LETTER THORN u'\xfd' # 0xE0 -> LATIN SMALL LETTER Y WITH ACUTE u'\xb7' # 0xE1 -> MIDDLE DOT u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u2030' # 0xE4 -> PER MILLE SIGN u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\uf8ff' # 0xF0 -> Apple logo u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u02dc' # 0xF7 -> SMALL TILDE u'\xaf' # 0xF8 -> MACRON u'\u02d8' # 0xF9 -> BREVE u'\u02d9' # 0xFA -> DOT ABOVE u'\u02da' # 0xFB -> RING ABOVE u'\xb8' # 0xFC -> CEDILLA u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT u'\u02db' # 0xFE -> OGONEK u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_latin2.py0000644000076500000240000002056512612565547024314 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'LATIN2.TXT' with gencodec.py. Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. (c) Copyright 2000 Guido van Rossum. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_map)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-latin2', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS 0x0081: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON 0x0082: 0x0101, # LATIN SMALL LETTER A WITH MACRON 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE 0x0084: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS 0x0087: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE 0x0088: 0x0105, # LATIN SMALL LETTER A WITH OGONEK 0x0089: 0x010c, # LATIN CAPITAL LETTER C WITH CARON 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS 0x008b: 0x010d, # LATIN SMALL LETTER C WITH CARON 0x008c: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE 0x008d: 0x0107, # LATIN SMALL LETTER C WITH ACUTE 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE 0x008f: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE 0x0090: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE 0x0091: 0x010e, # LATIN CAPITAL LETTER D WITH CARON 0x0092: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE 0x0093: 0x010f, # LATIN SMALL LETTER D WITH CARON 0x0094: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON 0x0095: 0x0113, # LATIN SMALL LETTER E WITH MACRON 0x0096: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE 0x0097: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE 0x0098: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS 0x009b: 0x00f5, # LATIN SMALL LETTER O WITH TILDE 0x009c: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE 0x009d: 0x011a, # LATIN CAPITAL LETTER E WITH CARON 0x009e: 0x011b, # LATIN SMALL LETTER E WITH CARON 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS 0x00a0: 0x2020, # DAGGER 0x00a1: 0x00b0, # DEGREE SIGN 0x00a2: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK 0x00a4: 0x00a7, # SECTION SIGN 0x00a5: 0x2022, # BULLET 0x00a6: 0x00b6, # PILCROW SIGN 0x00a7: 0x00df, # LATIN SMALL LETTER SHARP S 0x00a8: 0x00ae, # REGISTERED SIGN 0x00aa: 0x2122, # TRADE MARK SIGN 0x00ab: 0x0119, # LATIN SMALL LETTER E WITH OGONEK 0x00ac: 0x00a8, # DIAERESIS 0x00ad: 0x2260, # NOT EQUAL TO 0x00ae: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA 0x00af: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK 0x00b0: 0x012f, # LATIN SMALL LETTER I WITH OGONEK 0x00b1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON 0x00b2: 0x2264, # LESS-THAN OR EQUAL TO 0x00b3: 0x2265, # GREATER-THAN OR EQUAL TO 0x00b4: 0x012b, # LATIN SMALL LETTER I WITH MACRON 0x00b5: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA 0x00b6: 0x2202, # PARTIAL DIFFERENTIAL 0x00b7: 0x2211, # N-ARY SUMMATION 0x00b8: 0x0142, # LATIN SMALL LETTER L WITH STROKE 0x00b9: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA 0x00ba: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA 0x00bb: 0x013d, # LATIN CAPITAL LETTER L WITH CARON 0x00bc: 0x013e, # LATIN SMALL LETTER L WITH CARON 0x00bd: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE 0x00be: 0x013a, # LATIN SMALL LETTER L WITH ACUTE 0x00bf: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA 0x00c0: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA 0x00c1: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE 0x00c2: 0x00ac, # NOT SIGN 0x00c3: 0x221a, # SQUARE ROOT 0x00c4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE 0x00c5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON 0x00c6: 0x2206, # INCREMENT 0x00c7: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00c8: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK 0x00c9: 0x2026, # HORIZONTAL ELLIPSIS 0x00ca: 0x00a0, # NO-BREAK SPACE 0x00cb: 0x0148, # LATIN SMALL LETTER N WITH CARON 0x00cc: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE 0x00cd: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE 0x00ce: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE 0x00cf: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON 0x00d0: 0x2013, # EN DASH 0x00d1: 0x2014, # EM DASH 0x00d2: 0x201c, # LEFT DOUBLE QUOTATION MARK 0x00d3: 0x201d, # RIGHT DOUBLE QUOTATION MARK 0x00d4: 0x2018, # LEFT SINGLE QUOTATION MARK 0x00d5: 0x2019, # RIGHT SINGLE QUOTATION MARK 0x00d6: 0x00f7, # DIVISION SIGN 0x00d7: 0x25ca, # LOZENGE 0x00d8: 0x014d, # LATIN SMALL LETTER O WITH MACRON 0x00d9: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE 0x00da: 0x0155, # LATIN SMALL LETTER R WITH ACUTE 0x00db: 0x0158, # LATIN CAPITAL LETTER R WITH CARON 0x00dc: 0x2039, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK 0x00dd: 0x203a, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK 0x00de: 0x0159, # LATIN SMALL LETTER R WITH CARON 0x00df: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA 0x00e0: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA 0x00e1: 0x0160, # LATIN CAPITAL LETTER S WITH CARON 0x00e2: 0x201a, # SINGLE LOW-9 QUOTATION MARK 0x00e3: 0x201e, # DOUBLE LOW-9 QUOTATION MARK 0x00e4: 0x0161, # LATIN SMALL LETTER S WITH CARON 0x00e5: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE 0x00e6: 0x015b, # LATIN SMALL LETTER S WITH ACUTE 0x00e7: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE 0x00e8: 0x0164, # LATIN CAPITAL LETTER T WITH CARON 0x00e9: 0x0165, # LATIN SMALL LETTER T WITH CARON 0x00ea: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE 0x00eb: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON 0x00ec: 0x017e, # LATIN SMALL LETTER Z WITH CARON 0x00ed: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON 0x00ee: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE 0x00ef: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX 0x00f0: 0x016b, # LATIN SMALL LETTER U WITH MACRON 0x00f1: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE 0x00f2: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE 0x00f3: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE 0x00f4: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE 0x00f5: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE 0x00f6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK 0x00f7: 0x0173, # LATIN SMALL LETTER U WITH OGONEK 0x00f8: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE 0x00f9: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE 0x00fa: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA 0x00fb: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x00fc: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE 0x00fd: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE 0x00fe: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA 0x00ff: 0x02c7, # CARON }) ### Encoding Map encoding_map = codecs.make_encoding_map(decoding_map) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_roman.py0000644000076500000240000003265012612565547024235 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_roman generated from 'MAPPINGS/VENDORS/APPLE/ROMAN.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-roman', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\xb4' # 0xAB -> ACUTE ACCENT u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\xa5' # 0xB4 -> YEN SIGN u'\xb5' # 0xB5 -> MICRO SIGN u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u220f' # 0xB8 -> N-ARY PRODUCT u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI u'\u222b' # 0xBA -> INTEGRAL u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA u'\xe6' # 0xBE -> LATIN SMALL LETTER AE u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE u'\xbf' # 0xC0 -> INVERTED QUESTION MARK u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u2044' # 0xDA -> FRACTION SLASH u'\u20ac' # 0xDB -> EURO SIGN u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\ufb01' # 0xDE -> LATIN SMALL LIGATURE FI u'\ufb02' # 0xDF -> LATIN SMALL LIGATURE FL u'\u2021' # 0xE0 -> DOUBLE DAGGER u'\xb7' # 0xE1 -> MIDDLE DOT u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u2030' # 0xE4 -> PER MILLE SIGN u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\uf8ff' # 0xF0 -> Apple logo u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u02dc' # 0xF7 -> SMALL TILDE u'\xaf' # 0xF8 -> MACRON u'\u02d8' # 0xF9 -> BREVE u'\u02d9' # 0xFA -> DOT ABOVE u'\u02da' # 0xFB -> RING ABOVE u'\xb8' # 0xFC -> CEDILLA u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT u'\u02db' # 0xFE -> OGONEK u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_romanian.py0000644000076500000240000003313512612565547024724 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_romanian generated from 'MAPPINGS/VENDORS/APPLE/ROMANIAN.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-romanian', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\xb4' # 0xAB -> ACUTE ACCENT u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\u0102' # 0xAE -> LATIN CAPITAL LETTER A WITH BREVE u'\u0218' # 0xAF -> LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\xa5' # 0xB4 -> YEN SIGN u'\xb5' # 0xB5 -> MICRO SIGN u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u220f' # 0xB8 -> N-ARY PRODUCT u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI u'\u222b' # 0xBA -> INTEGRAL u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA u'\u0103' # 0xBE -> LATIN SMALL LETTER A WITH BREVE u'\u0219' # 0xBF -> LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later u'\xbf' # 0xC0 -> INVERTED QUESTION MARK u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u2044' # 0xDA -> FRACTION SLASH u'\u20ac' # 0xDB -> EURO SIGN u'\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK u'\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK u'\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later u'\u021b' # 0xDF -> LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later u'\u2021' # 0xE0 -> DOUBLE DAGGER u'\xb7' # 0xE1 -> MIDDLE DOT u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u2030' # 0xE4 -> PER MILLE SIGN u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\uf8ff' # 0xF0 -> Apple logo u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE u'\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u02dc' # 0xF7 -> SMALL TILDE u'\xaf' # 0xF8 -> MACRON u'\u02d8' # 0xF9 -> BREVE u'\u02d9' # 0xFA -> DOT ABOVE u'\u02da' # 0xFB -> RING ABOVE u'\xb8' # 0xFC -> CEDILLA u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT u'\u02db' # 0xFE -> OGONEK u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mac_turkish.py0000644000076500000240000003271112612565547024610 0ustar jmstaff00000000000000""" Python Character Mapping Codec mac_turkish generated from 'MAPPINGS/VENDORS/APPLE/TURKISH.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='mac-turkish', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> CONTROL CHARACTER u'\x01' # 0x01 -> CONTROL CHARACTER u'\x02' # 0x02 -> CONTROL CHARACTER u'\x03' # 0x03 -> CONTROL CHARACTER u'\x04' # 0x04 -> CONTROL CHARACTER u'\x05' # 0x05 -> CONTROL CHARACTER u'\x06' # 0x06 -> CONTROL CHARACTER u'\x07' # 0x07 -> CONTROL CHARACTER u'\x08' # 0x08 -> CONTROL CHARACTER u'\t' # 0x09 -> CONTROL CHARACTER u'\n' # 0x0A -> CONTROL CHARACTER u'\x0b' # 0x0B -> CONTROL CHARACTER u'\x0c' # 0x0C -> CONTROL CHARACTER u'\r' # 0x0D -> CONTROL CHARACTER u'\x0e' # 0x0E -> CONTROL CHARACTER u'\x0f' # 0x0F -> CONTROL CHARACTER u'\x10' # 0x10 -> CONTROL CHARACTER u'\x11' # 0x11 -> CONTROL CHARACTER u'\x12' # 0x12 -> CONTROL CHARACTER u'\x13' # 0x13 -> CONTROL CHARACTER u'\x14' # 0x14 -> CONTROL CHARACTER u'\x15' # 0x15 -> CONTROL CHARACTER u'\x16' # 0x16 -> CONTROL CHARACTER u'\x17' # 0x17 -> CONTROL CHARACTER u'\x18' # 0x18 -> CONTROL CHARACTER u'\x19' # 0x19 -> CONTROL CHARACTER u'\x1a' # 0x1A -> CONTROL CHARACTER u'\x1b' # 0x1B -> CONTROL CHARACTER u'\x1c' # 0x1C -> CONTROL CHARACTER u'\x1d' # 0x1D -> CONTROL CHARACTER u'\x1e' # 0x1E -> CONTROL CHARACTER u'\x1f' # 0x1F -> CONTROL CHARACTER u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> CONTROL CHARACTER u'\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS u'\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE u'\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA u'\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE u'\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE u'\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS u'\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS u'\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE u'\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE u'\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX u'\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS u'\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE u'\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE u'\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA u'\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE u'\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE u'\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX u'\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS u'\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE u'\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE u'\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX u'\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS u'\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE u'\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE u'\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE u'\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX u'\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS u'\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE u'\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE u'\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE u'\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX u'\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS u'\u2020' # 0xA0 -> DAGGER u'\xb0' # 0xA1 -> DEGREE SIGN u'\xa2' # 0xA2 -> CENT SIGN u'\xa3' # 0xA3 -> POUND SIGN u'\xa7' # 0xA4 -> SECTION SIGN u'\u2022' # 0xA5 -> BULLET u'\xb6' # 0xA6 -> PILCROW SIGN u'\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S u'\xae' # 0xA8 -> REGISTERED SIGN u'\xa9' # 0xA9 -> COPYRIGHT SIGN u'\u2122' # 0xAA -> TRADE MARK SIGN u'\xb4' # 0xAB -> ACUTE ACCENT u'\xa8' # 0xAC -> DIAERESIS u'\u2260' # 0xAD -> NOT EQUAL TO u'\xc6' # 0xAE -> LATIN CAPITAL LETTER AE u'\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE u'\u221e' # 0xB0 -> INFINITY u'\xb1' # 0xB1 -> PLUS-MINUS SIGN u'\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO u'\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO u'\xa5' # 0xB4 -> YEN SIGN u'\xb5' # 0xB5 -> MICRO SIGN u'\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL u'\u2211' # 0xB7 -> N-ARY SUMMATION u'\u220f' # 0xB8 -> N-ARY PRODUCT u'\u03c0' # 0xB9 -> GREEK SMALL LETTER PI u'\u222b' # 0xBA -> INTEGRAL u'\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR u'\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR u'\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA u'\xe6' # 0xBE -> LATIN SMALL LETTER AE u'\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE u'\xbf' # 0xC0 -> INVERTED QUESTION MARK u'\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK u'\xac' # 0xC2 -> NOT SIGN u'\u221a' # 0xC3 -> SQUARE ROOT u'\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK u'\u2248' # 0xC5 -> ALMOST EQUAL TO u'\u2206' # 0xC6 -> INCREMENT u'\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK u'\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK u'\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS u'\xa0' # 0xCA -> NO-BREAK SPACE u'\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE u'\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE u'\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE u'\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE u'\u0153' # 0xCF -> LATIN SMALL LIGATURE OE u'\u2013' # 0xD0 -> EN DASH u'\u2014' # 0xD1 -> EM DASH u'\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK u'\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK u'\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK u'\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK u'\xf7' # 0xD6 -> DIVISION SIGN u'\u25ca' # 0xD7 -> LOZENGE u'\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS u'\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS u'\u011e' # 0xDA -> LATIN CAPITAL LETTER G WITH BREVE u'\u011f' # 0xDB -> LATIN SMALL LETTER G WITH BREVE u'\u0130' # 0xDC -> LATIN CAPITAL LETTER I WITH DOT ABOVE u'\u0131' # 0xDD -> LATIN SMALL LETTER DOTLESS I u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA u'\u015f' # 0xDF -> LATIN SMALL LETTER S WITH CEDILLA u'\u2021' # 0xE0 -> DOUBLE DAGGER u'\xb7' # 0xE1 -> MIDDLE DOT u'\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK u'\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK u'\u2030' # 0xE4 -> PER MILLE SIGN u'\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX u'\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX u'\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE u'\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS u'\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE u'\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE u'\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX u'\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS u'\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE u'\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX u'\uf8ff' # 0xF0 -> Apple logo u'\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE u'\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE u'\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX u'\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE u'\uf8a0' # 0xF5 -> undefined1 u'\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT u'\u02dc' # 0xF7 -> SMALL TILDE u'\xaf' # 0xF8 -> MACRON u'\u02d8' # 0xF9 -> BREVE u'\u02d9' # 0xFA -> DOT ABOVE u'\u02da' # 0xFB -> RING ABOVE u'\xb8' # 0xFC -> CEDILLA u'\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT u'\u02db' # 0xFE -> OGONEK u'\u02c7' # 0xFF -> CARON ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/mbcs.py0000644000076500000240000000227312612565547023223 0ustar jmstaff00000000000000""" Python 'mbcs' Codec for Windows Cloned by Mark Hammond (mhammond@skippinet.com.au) from ascii.py, which was written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ # Import them explicitly to cause an ImportError # on non-Windows systems from codecs import mbcs_encode, mbcs_decode # for IncrementalDecoder, IncrementalEncoder, ... import codecs ### Codec APIs encode = mbcs_encode def decode(input, errors='strict'): return mbcs_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return mbcs_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = mbcs_decode class StreamWriter(codecs.StreamWriter): encode = mbcs_encode class StreamReader(codecs.StreamReader): decode = mbcs_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='mbcs', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/palmos.py0000644000076500000240000000557012612565547023575 0ustar jmstaff00000000000000""" Python Character Mapping Codec for PalmOS 3.5. Written by Sjoerd Mullender (sjoerd@acm.org); based on iso8859_15.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_map)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='palmos', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) # The PalmOS character set is mostly iso-8859-1 with some differences. decoding_map.update({ 0x0080: 0x20ac, # EURO SIGN 0x0082: 0x201a, # SINGLE LOW-9 QUOTATION MARK 0x0083: 0x0192, # LATIN SMALL LETTER F WITH HOOK 0x0084: 0x201e, # DOUBLE LOW-9 QUOTATION MARK 0x0085: 0x2026, # HORIZONTAL ELLIPSIS 0x0086: 0x2020, # DAGGER 0x0087: 0x2021, # DOUBLE DAGGER 0x0088: 0x02c6, # MODIFIER LETTER CIRCUMFLEX ACCENT 0x0089: 0x2030, # PER MILLE SIGN 0x008a: 0x0160, # LATIN CAPITAL LETTER S WITH CARON 0x008b: 0x2039, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK 0x008c: 0x0152, # LATIN CAPITAL LIGATURE OE 0x008d: 0x2666, # BLACK DIAMOND SUIT 0x008e: 0x2663, # BLACK CLUB SUIT 0x008f: 0x2665, # BLACK HEART SUIT 0x0090: 0x2660, # BLACK SPADE SUIT 0x0091: 0x2018, # LEFT SINGLE QUOTATION MARK 0x0092: 0x2019, # RIGHT SINGLE QUOTATION MARK 0x0093: 0x201c, # LEFT DOUBLE QUOTATION MARK 0x0094: 0x201d, # RIGHT DOUBLE QUOTATION MARK 0x0095: 0x2022, # BULLET 0x0096: 0x2013, # EN DASH 0x0097: 0x2014, # EM DASH 0x0098: 0x02dc, # SMALL TILDE 0x0099: 0x2122, # TRADE MARK SIGN 0x009a: 0x0161, # LATIN SMALL LETTER S WITH CARON 0x009c: 0x0153, # LATIN SMALL LIGATURE OE 0x009f: 0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS }) ### Encoding Map encoding_map = codecs.make_encoding_map(decoding_map) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/ptcp154.py0000644000076500000240000002136612612565547023503 0ustar jmstaff00000000000000""" Python Character Mapping Codec generated from 'PTCP154.txt' with gencodec.py. Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. (c) Copyright 2000 Guido van Rossum. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_map)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='ptcp154', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0080: 0x0496, # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER 0x0081: 0x0492, # CYRILLIC CAPITAL LETTER GHE WITH STROKE 0x0082: 0x04ee, # CYRILLIC CAPITAL LETTER U WITH MACRON 0x0083: 0x0493, # CYRILLIC SMALL LETTER GHE WITH STROKE 0x0084: 0x201e, # DOUBLE LOW-9 QUOTATION MARK 0x0085: 0x2026, # HORIZONTAL ELLIPSIS 0x0086: 0x04b6, # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER 0x0087: 0x04ae, # CYRILLIC CAPITAL LETTER STRAIGHT U 0x0088: 0x04b2, # CYRILLIC CAPITAL LETTER HA WITH DESCENDER 0x0089: 0x04af, # CYRILLIC SMALL LETTER STRAIGHT U 0x008a: 0x04a0, # CYRILLIC CAPITAL LETTER BASHKIR KA 0x008b: 0x04e2, # CYRILLIC CAPITAL LETTER I WITH MACRON 0x008c: 0x04a2, # CYRILLIC CAPITAL LETTER EN WITH DESCENDER 0x008d: 0x049a, # CYRILLIC CAPITAL LETTER KA WITH DESCENDER 0x008e: 0x04ba, # CYRILLIC CAPITAL LETTER SHHA 0x008f: 0x04b8, # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE 0x0090: 0x0497, # CYRILLIC SMALL LETTER ZHE WITH DESCENDER 0x0091: 0x2018, # LEFT SINGLE QUOTATION MARK 0x0092: 0x2019, # RIGHT SINGLE QUOTATION MARK 0x0093: 0x201c, # LEFT DOUBLE QUOTATION MARK 0x0094: 0x201d, # RIGHT DOUBLE QUOTATION MARK 0x0095: 0x2022, # BULLET 0x0096: 0x2013, # EN DASH 0x0097: 0x2014, # EM DASH 0x0098: 0x04b3, # CYRILLIC SMALL LETTER HA WITH DESCENDER 0x0099: 0x04b7, # CYRILLIC SMALL LETTER CHE WITH DESCENDER 0x009a: 0x04a1, # CYRILLIC SMALL LETTER BASHKIR KA 0x009b: 0x04e3, # CYRILLIC SMALL LETTER I WITH MACRON 0x009c: 0x04a3, # CYRILLIC SMALL LETTER EN WITH DESCENDER 0x009d: 0x049b, # CYRILLIC SMALL LETTER KA WITH DESCENDER 0x009e: 0x04bb, # CYRILLIC SMALL LETTER SHHA 0x009f: 0x04b9, # CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE 0x00a1: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U (Byelorussian) 0x00a2: 0x045e, # CYRILLIC SMALL LETTER SHORT U (Byelorussian) 0x00a3: 0x0408, # CYRILLIC CAPITAL LETTER JE 0x00a4: 0x04e8, # CYRILLIC CAPITAL LETTER BARRED O 0x00a5: 0x0498, # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER 0x00a6: 0x04b0, # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE 0x00a8: 0x0401, # CYRILLIC CAPITAL LETTER IO 0x00aa: 0x04d8, # CYRILLIC CAPITAL LETTER SCHWA 0x00ad: 0x04ef, # CYRILLIC SMALL LETTER U WITH MACRON 0x00af: 0x049c, # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE 0x00b1: 0x04b1, # CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE 0x00b2: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I 0x00b3: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 0x00b4: 0x0499, # CYRILLIC SMALL LETTER ZE WITH DESCENDER 0x00b5: 0x04e9, # CYRILLIC SMALL LETTER BARRED O 0x00b8: 0x0451, # CYRILLIC SMALL LETTER IO 0x00b9: 0x2116, # NUMERO SIGN 0x00ba: 0x04d9, # CYRILLIC SMALL LETTER SCHWA 0x00bc: 0x0458, # CYRILLIC SMALL LETTER JE 0x00bd: 0x04aa, # CYRILLIC CAPITAL LETTER ES WITH DESCENDER 0x00be: 0x04ab, # CYRILLIC SMALL LETTER ES WITH DESCENDER 0x00bf: 0x049d, # CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE 0x00c0: 0x0410, # CYRILLIC CAPITAL LETTER A 0x00c1: 0x0411, # CYRILLIC CAPITAL LETTER BE 0x00c2: 0x0412, # CYRILLIC CAPITAL LETTER VE 0x00c3: 0x0413, # CYRILLIC CAPITAL LETTER GHE 0x00c4: 0x0414, # CYRILLIC CAPITAL LETTER DE 0x00c5: 0x0415, # CYRILLIC CAPITAL LETTER IE 0x00c6: 0x0416, # CYRILLIC CAPITAL LETTER ZHE 0x00c7: 0x0417, # CYRILLIC CAPITAL LETTER ZE 0x00c8: 0x0418, # CYRILLIC CAPITAL LETTER I 0x00c9: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I 0x00ca: 0x041a, # CYRILLIC CAPITAL LETTER KA 0x00cb: 0x041b, # CYRILLIC CAPITAL LETTER EL 0x00cc: 0x041c, # CYRILLIC CAPITAL LETTER EM 0x00cd: 0x041d, # CYRILLIC CAPITAL LETTER EN 0x00ce: 0x041e, # CYRILLIC CAPITAL LETTER O 0x00cf: 0x041f, # CYRILLIC CAPITAL LETTER PE 0x00d0: 0x0420, # CYRILLIC CAPITAL LETTER ER 0x00d1: 0x0421, # CYRILLIC CAPITAL LETTER ES 0x00d2: 0x0422, # CYRILLIC CAPITAL LETTER TE 0x00d3: 0x0423, # CYRILLIC CAPITAL LETTER U 0x00d4: 0x0424, # CYRILLIC CAPITAL LETTER EF 0x00d5: 0x0425, # CYRILLIC CAPITAL LETTER HA 0x00d6: 0x0426, # CYRILLIC CAPITAL LETTER TSE 0x00d7: 0x0427, # CYRILLIC CAPITAL LETTER CHE 0x00d8: 0x0428, # CYRILLIC CAPITAL LETTER SHA 0x00d9: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA 0x00da: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN 0x00db: 0x042b, # CYRILLIC CAPITAL LETTER YERU 0x00dc: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN 0x00dd: 0x042d, # CYRILLIC CAPITAL LETTER E 0x00de: 0x042e, # CYRILLIC CAPITAL LETTER YU 0x00df: 0x042f, # CYRILLIC CAPITAL LETTER YA 0x00e0: 0x0430, # CYRILLIC SMALL LETTER A 0x00e1: 0x0431, # CYRILLIC SMALL LETTER BE 0x00e2: 0x0432, # CYRILLIC SMALL LETTER VE 0x00e3: 0x0433, # CYRILLIC SMALL LETTER GHE 0x00e4: 0x0434, # CYRILLIC SMALL LETTER DE 0x00e5: 0x0435, # CYRILLIC SMALL LETTER IE 0x00e6: 0x0436, # CYRILLIC SMALL LETTER ZHE 0x00e7: 0x0437, # CYRILLIC SMALL LETTER ZE 0x00e8: 0x0438, # CYRILLIC SMALL LETTER I 0x00e9: 0x0439, # CYRILLIC SMALL LETTER SHORT I 0x00ea: 0x043a, # CYRILLIC SMALL LETTER KA 0x00eb: 0x043b, # CYRILLIC SMALL LETTER EL 0x00ec: 0x043c, # CYRILLIC SMALL LETTER EM 0x00ed: 0x043d, # CYRILLIC SMALL LETTER EN 0x00ee: 0x043e, # CYRILLIC SMALL LETTER O 0x00ef: 0x043f, # CYRILLIC SMALL LETTER PE 0x00f0: 0x0440, # CYRILLIC SMALL LETTER ER 0x00f1: 0x0441, # CYRILLIC SMALL LETTER ES 0x00f2: 0x0442, # CYRILLIC SMALL LETTER TE 0x00f3: 0x0443, # CYRILLIC SMALL LETTER U 0x00f4: 0x0444, # CYRILLIC SMALL LETTER EF 0x00f5: 0x0445, # CYRILLIC SMALL LETTER HA 0x00f6: 0x0446, # CYRILLIC SMALL LETTER TSE 0x00f7: 0x0447, # CYRILLIC SMALL LETTER CHE 0x00f8: 0x0448, # CYRILLIC SMALL LETTER SHA 0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA 0x00fa: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN 0x00fb: 0x044b, # CYRILLIC SMALL LETTER YERU 0x00fc: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN 0x00fd: 0x044d, # CYRILLIC SMALL LETTER E 0x00fe: 0x044e, # CYRILLIC SMALL LETTER YU 0x00ff: 0x044f, # CYRILLIC SMALL LETTER YA }) ### Encoding Map encoding_map = codecs.make_encoding_map(decoding_map) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/punycode.py0000644000076500000240000001523512612565547024127 0ustar jmstaff00000000000000# -*- coding: iso-8859-1 -*- """ Codec for the Punicode encoding, as specified in RFC 3492 Written by Martin v. Lwis. """ import codecs ##################### Encoding ##################################### def segregate(str): """3.1 Basic code point segregation""" base = [] extended = {} for c in str: if ord(c) < 128: base.append(c) else: extended[c] = 1 extended = extended.keys() extended.sort() return "".join(base).encode("ascii"),extended def selective_len(str, max): """Return the length of str, considering only characters below max.""" res = 0 for c in str: if ord(c) < max: res += 1 return res def selective_find(str, char, index, pos): """Return a pair (index, pos), indicating the next occurrence of char in str. index is the position of the character considering only ordinals up to and including char, and pos is the position in the full string. index/pos is the starting position in the full string.""" l = len(str) while 1: pos += 1 if pos == l: return (-1, -1) c = str[pos] if c == char: return index+1, pos elif c < char: index += 1 def insertion_unsort(str, extended): """3.2 Insertion unsort coding""" oldchar = 0x80 result = [] oldindex = -1 for c in extended: index = pos = -1 char = ord(c) curlen = selective_len(str, char) delta = (curlen+1) * (char - oldchar) while 1: index,pos = selective_find(str,c,index,pos) if index == -1: break delta += index - oldindex result.append(delta-1) oldindex = index delta = 0 oldchar = char return result def T(j, bias): # Punycode parameters: tmin = 1, tmax = 26, base = 36 res = 36 * (j + 1) - bias if res < 1: return 1 if res > 26: return 26 return res digits = "abcdefghijklmnopqrstuvwxyz0123456789" def generate_generalized_integer(N, bias): """3.3 Generalized variable-length integers""" result = [] j = 0 while 1: t = T(j, bias) if N < t: result.append(digits[N]) return result result.append(digits[t + ((N - t) % (36 - t))]) N = (N - t) // (36 - t) j += 1 def adapt(delta, first, numchars): if first: delta //= 700 else: delta //= 2 delta += delta // numchars # ((base - tmin) * tmax) // 2 == 455 divisions = 0 while delta > 455: delta = delta // 35 # base - tmin divisions += 36 bias = divisions + (36 * delta // (delta + 38)) return bias def generate_integers(baselen, deltas): """3.4 Bias adaptation""" # Punycode parameters: initial bias = 72, damp = 700, skew = 38 result = [] bias = 72 for points, delta in enumerate(deltas): s = generate_generalized_integer(delta, bias) result.extend(s) bias = adapt(delta, points==0, baselen+points+1) return "".join(result) def punycode_encode(text): base, extended = segregate(text) base = base.encode("ascii") deltas = insertion_unsort(text, extended) extended = generate_integers(len(base), deltas) if base: return base + "-" + extended return extended ##################### Decoding ##################################### def decode_generalized_number(extended, extpos, bias, errors): """3.3 Generalized variable-length integers""" result = 0 w = 1 j = 0 while 1: try: char = ord(extended[extpos]) except IndexError: if errors == "strict": raise UnicodeError, "incomplete punicode string" return extpos + 1, None extpos += 1 if 0x41 <= char <= 0x5A: # A-Z digit = char - 0x41 elif 0x30 <= char <= 0x39: digit = char - 22 # 0x30-26 elif errors == "strict": raise UnicodeError("Invalid extended code point '%s'" % extended[extpos]) else: return extpos, None t = T(j, bias) result += digit * w if digit < t: return extpos, result w = w * (36 - t) j += 1 def insertion_sort(base, extended, errors): """3.2 Insertion unsort coding""" char = 0x80 pos = -1 bias = 72 extpos = 0 while extpos < len(extended): newpos, delta = decode_generalized_number(extended, extpos, bias, errors) if delta is None: # There was an error in decoding. We can't continue because # synchronization is lost. return base pos += delta+1 char += pos // (len(base) + 1) if char > 0x10FFFF: if errors == "strict": raise UnicodeError, ("Invalid character U+%x" % char) char = ord('?') pos = pos % (len(base) + 1) base = base[:pos] + unichr(char) + base[pos:] bias = adapt(delta, (extpos == 0), len(base)) extpos = newpos return base def punycode_decode(text, errors): pos = text.rfind("-") if pos == -1: base = "" extended = text else: base = text[:pos] extended = text[pos+1:] base = unicode(base, "ascii", errors) extended = extended.upper() return insertion_sort(base, extended, errors) ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): res = punycode_encode(input) return res, len(input) def decode(self,input,errors='strict'): if errors not in ('strict', 'replace', 'ignore'): raise UnicodeError, "Unsupported error handling "+errors res = punycode_decode(input, errors) return res, len(input) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return punycode_encode(input) class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): if self.errors not in ('strict', 'replace', 'ignore'): raise UnicodeError, "Unsupported error handling "+self.errors return punycode_decode(input, self.errors) class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='punycode', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/quopri_codec.py0000644000076500000240000000414312612565547024751 0ustar jmstaff00000000000000"""Codec for quoted-printable encoding. Like base64 and rot13, this returns Python strings, not Unicode. """ import codecs, quopri try: from cStringIO import StringIO except ImportError: from StringIO import StringIO def quopri_encode(input, errors='strict'): """Encode the input, returning a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' # using str() because of cStringIO's Unicode undesired Unicode behavior. f = StringIO(str(input)) g = StringIO() quopri.encode(f, g, 1) output = g.getvalue() return (output, len(input)) def quopri_decode(input, errors='strict'): """Decode the input, returning a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' f = StringIO(str(input)) g = StringIO() quopri.decode(f, g) output = g.getvalue() return (output, len(input)) class Codec(codecs.Codec): def encode(self, input,errors='strict'): return quopri_encode(input,errors) def decode(self, input,errors='strict'): return quopri_decode(input,errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return quopri_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return quopri_decode(input, self.errors)[0] class StreamWriter(Codec, codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass # encodings module API def getregentry(): return codecs.CodecInfo( name='quopri', encode=quopri_encode, decode=quopri_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/raw_unicode_escape.py0000644000076500000240000000227012612565547026113 0ustar jmstaff00000000000000""" Python 'raw-unicode-escape' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.raw_unicode_escape_encode decode = codecs.raw_unicode_escape_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.raw_unicode_escape_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.raw_unicode_escape_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='raw-unicode-escape', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/rot_13.py0000644000076500000240000000502312612565547023402 0ustar jmstaff00000000000000#!/usr/bin/env python """ Python Character Mapping Codec for ROT13. See http://ucsub.colorado.edu/~kominek/rot13/ for details. Written by Marc-Andre Lemburg (mal@lemburg.com). """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_map)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_map)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='rot-13', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) decoding_map.update({ 0x0041: 0x004e, 0x0042: 0x004f, 0x0043: 0x0050, 0x0044: 0x0051, 0x0045: 0x0052, 0x0046: 0x0053, 0x0047: 0x0054, 0x0048: 0x0055, 0x0049: 0x0056, 0x004a: 0x0057, 0x004b: 0x0058, 0x004c: 0x0059, 0x004d: 0x005a, 0x004e: 0x0041, 0x004f: 0x0042, 0x0050: 0x0043, 0x0051: 0x0044, 0x0052: 0x0045, 0x0053: 0x0046, 0x0054: 0x0047, 0x0055: 0x0048, 0x0056: 0x0049, 0x0057: 0x004a, 0x0058: 0x004b, 0x0059: 0x004c, 0x005a: 0x004d, 0x0061: 0x006e, 0x0062: 0x006f, 0x0063: 0x0070, 0x0064: 0x0071, 0x0065: 0x0072, 0x0066: 0x0073, 0x0067: 0x0074, 0x0068: 0x0075, 0x0069: 0x0076, 0x006a: 0x0077, 0x006b: 0x0078, 0x006c: 0x0079, 0x006d: 0x007a, 0x006e: 0x0061, 0x006f: 0x0062, 0x0070: 0x0063, 0x0071: 0x0064, 0x0072: 0x0065, 0x0073: 0x0066, 0x0074: 0x0067, 0x0075: 0x0068, 0x0076: 0x0069, 0x0077: 0x006a, 0x0078: 0x006b, 0x0079: 0x006c, 0x007a: 0x006d, }) ### Encoding Map encoding_map = codecs.make_encoding_map(decoding_map) ### Filter API def rot13(infile, outfile): outfile.write(infile.read().encode('rot-13')) if __name__ == '__main__': import sys rot13(sys.stdin, sys.stdout) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/shift_jis.py0000644000076500000240000000201712612565547024255 0ustar jmstaff00000000000000# # shift_jis.py: Python Unicode Codec for SHIFT_JIS # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('shift_jis') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='shift_jis', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/shift_jis_2004.py0000644000076500000240000000204312612565547024721 0ustar jmstaff00000000000000# # shift_jis_2004.py: Python Unicode Codec for SHIFT_JIS_2004 # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('shift_jis_2004') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='shift_jis_2004', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/shift_jisx0213.py0000644000076500000240000000204312612565547024752 0ustar jmstaff00000000000000# # shift_jisx0213.py: Python Unicode Codec for SHIFT_JISX0213 # # Written by Hye-Shik Chang # import _codecs_jp, codecs import _multibytecodec as mbc codec = _codecs_jp.getcodec('shift_jisx0213') class Codec(codecs.Codec): encode = codec.encode decode = codec.decode class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, codecs.IncrementalEncoder): codec = codec class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, codecs.IncrementalDecoder): codec = codec class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): codec = codec class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): codec = codec def getregentry(): return codecs.CodecInfo( name='shift_jisx0213', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/string_escape.py0000644000076500000240000000167112612565547025126 0ustar jmstaff00000000000000# -*- coding: iso-8859-1 -*- """ Python 'escape' Codec Written by Martin v. Lwis (martin@v.loewis.de). """ import codecs class Codec(codecs.Codec): encode = codecs.escape_encode decode = codecs.escape_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.escape_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.escape_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass def getregentry(): return codecs.CodecInfo( name='string-escape', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/tis_620.py0000644000076500000240000003041412612565547023463 0ustar jmstaff00000000000000""" Python Character Mapping Codec tis_620 generated from 'python-mappings/TIS-620.TXT' with gencodec.py. """#" import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): return codecs.charmap_encode(input,errors,encoding_table) def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_table) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.charmap_encode(input,self.errors,encoding_table)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.charmap_decode(input,self.errors,decoding_table)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='tis-620', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) ### Decoding Table decoding_table = ( u'\x00' # 0x00 -> NULL u'\x01' # 0x01 -> START OF HEADING u'\x02' # 0x02 -> START OF TEXT u'\x03' # 0x03 -> END OF TEXT u'\x04' # 0x04 -> END OF TRANSMISSION u'\x05' # 0x05 -> ENQUIRY u'\x06' # 0x06 -> ACKNOWLEDGE u'\x07' # 0x07 -> BELL u'\x08' # 0x08 -> BACKSPACE u'\t' # 0x09 -> HORIZONTAL TABULATION u'\n' # 0x0A -> LINE FEED u'\x0b' # 0x0B -> VERTICAL TABULATION u'\x0c' # 0x0C -> FORM FEED u'\r' # 0x0D -> CARRIAGE RETURN u'\x0e' # 0x0E -> SHIFT OUT u'\x0f' # 0x0F -> SHIFT IN u'\x10' # 0x10 -> DATA LINK ESCAPE u'\x11' # 0x11 -> DEVICE CONTROL ONE u'\x12' # 0x12 -> DEVICE CONTROL TWO u'\x13' # 0x13 -> DEVICE CONTROL THREE u'\x14' # 0x14 -> DEVICE CONTROL FOUR u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE u'\x16' # 0x16 -> SYNCHRONOUS IDLE u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK u'\x18' # 0x18 -> CANCEL u'\x19' # 0x19 -> END OF MEDIUM u'\x1a' # 0x1A -> SUBSTITUTE u'\x1b' # 0x1B -> ESCAPE u'\x1c' # 0x1C -> FILE SEPARATOR u'\x1d' # 0x1D -> GROUP SEPARATOR u'\x1e' # 0x1E -> RECORD SEPARATOR u'\x1f' # 0x1F -> UNIT SEPARATOR u' ' # 0x20 -> SPACE u'!' # 0x21 -> EXCLAMATION MARK u'"' # 0x22 -> QUOTATION MARK u'#' # 0x23 -> NUMBER SIGN u'$' # 0x24 -> DOLLAR SIGN u'%' # 0x25 -> PERCENT SIGN u'&' # 0x26 -> AMPERSAND u"'" # 0x27 -> APOSTROPHE u'(' # 0x28 -> LEFT PARENTHESIS u')' # 0x29 -> RIGHT PARENTHESIS u'*' # 0x2A -> ASTERISK u'+' # 0x2B -> PLUS SIGN u',' # 0x2C -> COMMA u'-' # 0x2D -> HYPHEN-MINUS u'.' # 0x2E -> FULL STOP u'/' # 0x2F -> SOLIDUS u'0' # 0x30 -> DIGIT ZERO u'1' # 0x31 -> DIGIT ONE u'2' # 0x32 -> DIGIT TWO u'3' # 0x33 -> DIGIT THREE u'4' # 0x34 -> DIGIT FOUR u'5' # 0x35 -> DIGIT FIVE u'6' # 0x36 -> DIGIT SIX u'7' # 0x37 -> DIGIT SEVEN u'8' # 0x38 -> DIGIT EIGHT u'9' # 0x39 -> DIGIT NINE u':' # 0x3A -> COLON u';' # 0x3B -> SEMICOLON u'<' # 0x3C -> LESS-THAN SIGN u'=' # 0x3D -> EQUALS SIGN u'>' # 0x3E -> GREATER-THAN SIGN u'?' # 0x3F -> QUESTION MARK u'@' # 0x40 -> COMMERCIAL AT u'A' # 0x41 -> LATIN CAPITAL LETTER A u'B' # 0x42 -> LATIN CAPITAL LETTER B u'C' # 0x43 -> LATIN CAPITAL LETTER C u'D' # 0x44 -> LATIN CAPITAL LETTER D u'E' # 0x45 -> LATIN CAPITAL LETTER E u'F' # 0x46 -> LATIN CAPITAL LETTER F u'G' # 0x47 -> LATIN CAPITAL LETTER G u'H' # 0x48 -> LATIN CAPITAL LETTER H u'I' # 0x49 -> LATIN CAPITAL LETTER I u'J' # 0x4A -> LATIN CAPITAL LETTER J u'K' # 0x4B -> LATIN CAPITAL LETTER K u'L' # 0x4C -> LATIN CAPITAL LETTER L u'M' # 0x4D -> LATIN CAPITAL LETTER M u'N' # 0x4E -> LATIN CAPITAL LETTER N u'O' # 0x4F -> LATIN CAPITAL LETTER O u'P' # 0x50 -> LATIN CAPITAL LETTER P u'Q' # 0x51 -> LATIN CAPITAL LETTER Q u'R' # 0x52 -> LATIN CAPITAL LETTER R u'S' # 0x53 -> LATIN CAPITAL LETTER S u'T' # 0x54 -> LATIN CAPITAL LETTER T u'U' # 0x55 -> LATIN CAPITAL LETTER U u'V' # 0x56 -> LATIN CAPITAL LETTER V u'W' # 0x57 -> LATIN CAPITAL LETTER W u'X' # 0x58 -> LATIN CAPITAL LETTER X u'Y' # 0x59 -> LATIN CAPITAL LETTER Y u'Z' # 0x5A -> LATIN CAPITAL LETTER Z u'[' # 0x5B -> LEFT SQUARE BRACKET u'\\' # 0x5C -> REVERSE SOLIDUS u']' # 0x5D -> RIGHT SQUARE BRACKET u'^' # 0x5E -> CIRCUMFLEX ACCENT u'_' # 0x5F -> LOW LINE u'`' # 0x60 -> GRAVE ACCENT u'a' # 0x61 -> LATIN SMALL LETTER A u'b' # 0x62 -> LATIN SMALL LETTER B u'c' # 0x63 -> LATIN SMALL LETTER C u'd' # 0x64 -> LATIN SMALL LETTER D u'e' # 0x65 -> LATIN SMALL LETTER E u'f' # 0x66 -> LATIN SMALL LETTER F u'g' # 0x67 -> LATIN SMALL LETTER G u'h' # 0x68 -> LATIN SMALL LETTER H u'i' # 0x69 -> LATIN SMALL LETTER I u'j' # 0x6A -> LATIN SMALL LETTER J u'k' # 0x6B -> LATIN SMALL LETTER K u'l' # 0x6C -> LATIN SMALL LETTER L u'm' # 0x6D -> LATIN SMALL LETTER M u'n' # 0x6E -> LATIN SMALL LETTER N u'o' # 0x6F -> LATIN SMALL LETTER O u'p' # 0x70 -> LATIN SMALL LETTER P u'q' # 0x71 -> LATIN SMALL LETTER Q u'r' # 0x72 -> LATIN SMALL LETTER R u's' # 0x73 -> LATIN SMALL LETTER S u't' # 0x74 -> LATIN SMALL LETTER T u'u' # 0x75 -> LATIN SMALL LETTER U u'v' # 0x76 -> LATIN SMALL LETTER V u'w' # 0x77 -> LATIN SMALL LETTER W u'x' # 0x78 -> LATIN SMALL LETTER X u'y' # 0x79 -> LATIN SMALL LETTER Y u'z' # 0x7A -> LATIN SMALL LETTER Z u'{' # 0x7B -> LEFT CURLY BRACKET u'|' # 0x7C -> VERTICAL LINE u'}' # 0x7D -> RIGHT CURLY BRACKET u'~' # 0x7E -> TILDE u'\x7f' # 0x7F -> DELETE u'\x80' # 0x80 -> u'\x81' # 0x81 -> u'\x82' # 0x82 -> u'\x83' # 0x83 -> u'\x84' # 0x84 -> u'\x85' # 0x85 -> u'\x86' # 0x86 -> u'\x87' # 0x87 -> u'\x88' # 0x88 -> u'\x89' # 0x89 -> u'\x8a' # 0x8A -> u'\x8b' # 0x8B -> u'\x8c' # 0x8C -> u'\x8d' # 0x8D -> u'\x8e' # 0x8E -> u'\x8f' # 0x8F -> u'\x90' # 0x90 -> u'\x91' # 0x91 -> u'\x92' # 0x92 -> u'\x93' # 0x93 -> u'\x94' # 0x94 -> u'\x95' # 0x95 -> u'\x96' # 0x96 -> u'\x97' # 0x97 -> u'\x98' # 0x98 -> u'\x99' # 0x99 -> u'\x9a' # 0x9A -> u'\x9b' # 0x9B -> u'\x9c' # 0x9C -> u'\x9d' # 0x9D -> u'\x9e' # 0x9E -> u'\x9f' # 0x9F -> u'\ufffe' u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA u'\u0e24' # 0xC4 -> THAI CHARACTER RU u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING u'\u0e26' # 0xC6 -> THAI CHARACTER LU u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN u'\u0e50' # 0xF0 -> THAI DIGIT ZERO u'\u0e51' # 0xF1 -> THAI DIGIT ONE u'\u0e52' # 0xF2 -> THAI DIGIT TWO u'\u0e53' # 0xF3 -> THAI DIGIT THREE u'\u0e54' # 0xF4 -> THAI DIGIT FOUR u'\u0e55' # 0xF5 -> THAI DIGIT FIVE u'\u0e56' # 0xF6 -> THAI DIGIT SIX u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT u'\u0e59' # 0xF9 -> THAI DIGIT NINE u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT u'\ufffe' u'\ufffe' u'\ufffe' u'\ufffe' ) ### Encoding table encoding_table=codecs.charmap_build(decoding_table) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/undefined.py0000644000076500000240000000242312612565547024235 0ustar jmstaff00000000000000""" Python 'undefined' Codec This codec will always raise a ValueError exception when being used. It is intended for use by the site.py file to switch off automatic string to Unicode coercion. Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): def encode(self,input,errors='strict'): raise UnicodeError("undefined encoding") def decode(self,input,errors='strict'): raise UnicodeError("undefined encoding") class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): raise UnicodeError("undefined encoding") class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): raise UnicodeError("undefined encoding") class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='undefined', encode=Codec().encode, decode=Codec().decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/unicode_escape.py0000644000076500000240000000224012612565547025237 0ustar jmstaff00000000000000""" Python 'unicode-escape' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.unicode_escape_encode decode = codecs.unicode_escape_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.unicode_escape_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.unicode_escape_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='unicode-escape', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/unicode_internal.py0000644000076500000240000000225412612565547025620 0ustar jmstaff00000000000000""" Python 'unicode-internal' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs class Codec(codecs.Codec): # Note: Binding these as C functions will result in the class not # converting them to methods. This is intended. encode = codecs.unicode_internal_encode decode = codecs.unicode_internal_decode class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.unicode_internal_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return codecs.unicode_internal_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='unicode-internal', encode=Codec.encode, decode=Codec.decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamwriter=StreamWriter, streamreader=StreamReader, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_16.py0000644000076500000240000000762012612565547023404 0ustar jmstaff00000000000000""" Python 'utf-16' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs, sys ### Codec APIs encode = codecs.utf_16_encode def decode(input, errors='strict'): return codecs.utf_16_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): codecs.IncrementalEncoder.__init__(self, errors) self.encoder = None def encode(self, input, final=False): if self.encoder is None: result = codecs.utf_16_encode(input, self.errors)[0] if sys.byteorder == 'little': self.encoder = codecs.utf_16_le_encode else: self.encoder = codecs.utf_16_be_encode return result return self.encoder(input, self.errors)[0] def reset(self): codecs.IncrementalEncoder.reset(self) self.encoder = None def getstate(self): # state info we return to the caller: # 0: stream is in natural order for this platform # 2: endianness hasn't been determined yet # (we're never writing in unnatural order) return (2 if self.encoder is None else 0) def setstate(self, state): if state: self.encoder = None else: if sys.byteorder == 'little': self.encoder = codecs.utf_16_le_encode else: self.encoder = codecs.utf_16_be_encode class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def __init__(self, errors='strict'): codecs.BufferedIncrementalDecoder.__init__(self, errors) self.decoder = None def _buffer_decode(self, input, errors, final): if self.decoder is None: (output, consumed, byteorder) = \ codecs.utf_16_ex_decode(input, errors, 0, final) if byteorder == -1: self.decoder = codecs.utf_16_le_decode elif byteorder == 1: self.decoder = codecs.utf_16_be_decode elif consumed >= 2: raise UnicodeError("UTF-16 stream does not start with BOM") return (output, consumed) return self.decoder(input, self.errors, final) def reset(self): codecs.BufferedIncrementalDecoder.reset(self) self.decoder = None class StreamWriter(codecs.StreamWriter): def __init__(self, stream, errors='strict'): codecs.StreamWriter.__init__(self, stream, errors) self.encoder = None def reset(self): codecs.StreamWriter.reset(self) self.encoder = None def encode(self, input, errors='strict'): if self.encoder is None: result = codecs.utf_16_encode(input, errors) if sys.byteorder == 'little': self.encoder = codecs.utf_16_le_encode else: self.encoder = codecs.utf_16_be_encode return result else: return self.encoder(input, errors) class StreamReader(codecs.StreamReader): def reset(self): codecs.StreamReader.reset(self) try: del self.decode except AttributeError: pass def decode(self, input, errors='strict'): (object, consumed, byteorder) = \ codecs.utf_16_ex_decode(input, errors, 0, False) if byteorder == -1: self.decode = codecs.utf_16_le_decode elif byteorder == 1: self.decode = codecs.utf_16_be_decode elif consumed>=2: raise UnicodeError,"UTF-16 stream does not start with BOM" return (object, consumed) ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-16', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_16_be.py0000644000076500000240000000201512612565547024043 0ustar jmstaff00000000000000""" Python 'utf-16-be' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs encode = codecs.utf_16_be_encode def decode(input, errors='strict'): return codecs.utf_16_be_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_16_be_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_16_be_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_16_be_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_16_be_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-16-be', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_16_le.py0000644000076500000240000000201512612565547024055 0ustar jmstaff00000000000000""" Python 'utf-16-le' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs encode = codecs.utf_16_le_encode def decode(input, errors='strict'): return codecs.utf_16_le_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_16_le_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_16_le_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_16_le_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_16_le_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-16-le', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_32.py0000644000076500000240000001200712612565547023375 0ustar jmstaff00000000000000""" Python 'utf-32' Codec """ import codecs, sys ### Codec APIs encode = codecs.utf_32_encode def decode(input, errors='strict'): return codecs.utf_32_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): codecs.IncrementalEncoder.__init__(self, errors) self.encoder = None def encode(self, input, final=False): if self.encoder is None: result = codecs.utf_32_encode(input, self.errors)[0] if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode return result return self.encoder(input, self.errors)[0] def reset(self): codecs.IncrementalEncoder.reset(self) self.encoder = None def getstate(self): # state info we return to the caller: # 0: stream is in natural order for this platform # 2: endianness hasn't been determined yet # (we're never writing in unnatural order) return (2 if self.encoder is None else 0) def setstate(self, state): if state: self.encoder = None else: if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def __init__(self, errors='strict'): codecs.BufferedIncrementalDecoder.__init__(self, errors) self.decoder = None def _buffer_decode(self, input, errors, final): if self.decoder is None: (output, consumed, byteorder) = \ codecs.utf_32_ex_decode(input, errors, 0, final) if byteorder == -1: self.decoder = codecs.utf_32_le_decode elif byteorder == 1: self.decoder = codecs.utf_32_be_decode elif consumed >= 4: raise UnicodeError("UTF-32 stream does not start with BOM") return (output, consumed) return self.decoder(input, self.errors, final) def reset(self): codecs.BufferedIncrementalDecoder.reset(self) self.decoder = None def getstate(self): # additonal state info from the base class must be None here, # as it isn't passed along to the caller state = codecs.BufferedIncrementalDecoder.getstate(self)[0] # additional state info we pass to the caller: # 0: stream is in natural order for this platform # 1: stream is in unnatural order # 2: endianness hasn't been determined yet if self.decoder is None: return (state, 2) addstate = int((sys.byteorder == "big") != (self.decoder is codecs.utf_32_be_decode)) return (state, addstate) def setstate(self, state): # state[1] will be ignored by BufferedIncrementalDecoder.setstate() codecs.BufferedIncrementalDecoder.setstate(self, state) state = state[1] if state == 0: self.decoder = (codecs.utf_32_be_decode if sys.byteorder == "big" else codecs.utf_32_le_decode) elif state == 1: self.decoder = (codecs.utf_32_le_decode if sys.byteorder == "big" else codecs.utf_32_be_decode) else: self.decoder = None class StreamWriter(codecs.StreamWriter): def __init__(self, stream, errors='strict'): self.encoder = None codecs.StreamWriter.__init__(self, stream, errors) def reset(self): codecs.StreamWriter.reset(self) self.encoder = None def encode(self, input, errors='strict'): if self.encoder is None: result = codecs.utf_32_encode(input, errors) if sys.byteorder == 'little': self.encoder = codecs.utf_32_le_encode else: self.encoder = codecs.utf_32_be_encode return result else: return self.encoder(input, errors) class StreamReader(codecs.StreamReader): def reset(self): codecs.StreamReader.reset(self) try: del self.decode except AttributeError: pass def decode(self, input, errors='strict'): (object, consumed, byteorder) = \ codecs.utf_32_ex_decode(input, errors, 0, False) if byteorder == -1: self.decode = codecs.utf_32_le_decode elif byteorder == 1: self.decode = codecs.utf_32_be_decode elif consumed>=4: raise UnicodeError,"UTF-32 stream does not start with BOM" return (object, consumed) ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-32', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_32_be.py0000644000076500000240000000164212612565547024046 0ustar jmstaff00000000000000""" Python 'utf-32-be' Codec """ import codecs ### Codec APIs encode = codecs.utf_32_be_encode def decode(input, errors='strict'): return codecs.utf_32_be_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_32_be_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_32_be_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_32_be_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_32_be_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-32-be', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_32_le.py0000644000076500000240000000164212612565547024060 0ustar jmstaff00000000000000""" Python 'utf-32-le' Codec """ import codecs ### Codec APIs encode = codecs.utf_32_le_encode def decode(input, errors='strict'): return codecs.utf_32_le_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_32_le_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_32_le_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_32_le_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_32_le_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-32-le', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_7.py0000644000076500000240000000166212612565547023324 0ustar jmstaff00000000000000""" Python 'utf-7' Codec Written by Brian Quinlan (brian@sweetapp.com). """ import codecs ### Codec APIs encode = codecs.utf_7_encode def decode(input, errors='strict'): return codecs.utf_7_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_7_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_7_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_7_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_7_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-7', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_8.py0000644000076500000240000000175512612565547023330 0ustar jmstaff00000000000000""" Python 'utf-8' Codec Written by Marc-Andre Lemburg (mal@lemburg.com). (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. """ import codecs ### Codec APIs encode = codecs.utf_8_encode def decode(input, errors='strict'): return codecs.utf_8_decode(input, errors, True) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return codecs.utf_8_encode(input, self.errors)[0] class IncrementalDecoder(codecs.BufferedIncrementalDecoder): _buffer_decode = codecs.utf_8_decode class StreamWriter(codecs.StreamWriter): encode = codecs.utf_8_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_8_decode ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-8', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/utf_8_sig.py0000644000076500000240000000714512612565547024171 0ustar jmstaff00000000000000""" Python 'utf-8-sig' Codec This work similar to UTF-8 with the following changes: * On encoding/writing a UTF-8 encoded BOM will be prepended/written as the first three bytes. * On decoding/reading if the first three bytes are a UTF-8 encoded BOM, these bytes will be skipped. """ import codecs ### Codec APIs def encode(input, errors='strict'): return (codecs.BOM_UTF8 + codecs.utf_8_encode(input, errors)[0], len(input)) def decode(input, errors='strict'): prefix = 0 if input[:3] == codecs.BOM_UTF8: input = input[3:] prefix = 3 (output, consumed) = codecs.utf_8_decode(input, errors, True) return (output, consumed+prefix) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): codecs.IncrementalEncoder.__init__(self, errors) self.first = 1 def encode(self, input, final=False): if self.first: self.first = 0 return codecs.BOM_UTF8 + codecs.utf_8_encode(input, self.errors)[0] else: return codecs.utf_8_encode(input, self.errors)[0] def reset(self): codecs.IncrementalEncoder.reset(self) self.first = 1 def getstate(self): return self.first def setstate(self, state): self.first = state class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def __init__(self, errors='strict'): codecs.BufferedIncrementalDecoder.__init__(self, errors) self.first = True def _buffer_decode(self, input, errors, final): if self.first: if len(input) < 3: if codecs.BOM_UTF8.startswith(input): # not enough data to decide if this really is a BOM # => try again on the next call return (u"", 0) else: self.first = None else: self.first = None if input[:3] == codecs.BOM_UTF8: (output, consumed) = codecs.utf_8_decode(input[3:], errors, final) return (output, consumed+3) return codecs.utf_8_decode(input, errors, final) def reset(self): codecs.BufferedIncrementalDecoder.reset(self) self.first = True class StreamWriter(codecs.StreamWriter): def reset(self): codecs.StreamWriter.reset(self) try: del self.encode except AttributeError: pass def encode(self, input, errors='strict'): self.encode = codecs.utf_8_encode return encode(input, errors) class StreamReader(codecs.StreamReader): def reset(self): codecs.StreamReader.reset(self) try: del self.decode except AttributeError: pass def decode(self, input, errors='strict'): if len(input) < 3: if codecs.BOM_UTF8.startswith(input): # not enough data to decide if this is a BOM # => try again on the next call return (u"", 0) elif input[:3] == codecs.BOM_UTF8: self.decode = codecs.utf_8_decode (output, consumed) = codecs.utf_8_decode(input[3:],errors) return (output, consumed+3) # (else) no BOM present self.decode = codecs.utf_8_decode return codecs.utf_8_decode(input, errors) ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-8-sig', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/uu_codec.py0000644000076500000240000000723212612565547024065 0ustar jmstaff00000000000000""" Python 'uu_codec' Codec - UU content transfer encoding Unlike most of the other codecs which target Unicode, this codec will return Python string objects for both encode and decode. Written by Marc-Andre Lemburg (mal@lemburg.com). Some details were adapted from uu.py which was written by Lance Ellinghouse and modified by Jack Jansen and Fredrik Lundh. """ import codecs, binascii ### Codec APIs def uu_encode(input,errors='strict',filename='',mode=0666): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' from cStringIO import StringIO from binascii import b2a_uu # using str() because of cStringIO's Unicode undesired Unicode behavior. infile = StringIO(str(input)) outfile = StringIO() read = infile.read write = outfile.write # Encode write('begin %o %s\n' % (mode & 0777, filename)) chunk = read(45) while chunk: write(b2a_uu(chunk)) chunk = read(45) write(' \nend\n') return (outfile.getvalue(), len(input)) def uu_decode(input,errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. Note: filename and file mode information in the input data is ignored. """ assert errors == 'strict' from cStringIO import StringIO from binascii import a2b_uu infile = StringIO(str(input)) outfile = StringIO() readline = infile.readline write = outfile.write # Find start of encoded data while 1: s = readline() if not s: raise ValueError, 'Missing "begin" line in input data' if s[:5] == 'begin': break # Decode while 1: s = readline() if not s or \ s == 'end\n': break try: data = a2b_uu(s) except binascii.Error, v: # Workaround for broken uuencoders by /Fredrik Lundh nbytes = (((ord(s[0])-32) & 63) * 4 + 5) / 3 data = a2b_uu(s[:nbytes]) #sys.stderr.write("Warning: %s\n" % str(v)) write(data) if not s: raise ValueError, 'Truncated input data' return (outfile.getvalue(), len(input)) class Codec(codecs.Codec): def encode(self,input,errors='strict'): return uu_encode(input,errors) def decode(self,input,errors='strict'): return uu_decode(input,errors) class IncrementalEncoder(codecs.IncrementalEncoder): def encode(self, input, final=False): return uu_encode(input, self.errors)[0] class IncrementalDecoder(codecs.IncrementalDecoder): def decode(self, input, final=False): return uu_decode(input, self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='uu', encode=uu_encode, decode=uu_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/encodings/zlib_codec.py0000644000076500000240000000570712612565547024401 0ustar jmstaff00000000000000""" Python 'zlib_codec' Codec - zlib compression encoding Unlike most of the other codecs which target Unicode, this codec will return Python string objects for both encode and decode. Written by Marc-Andre Lemburg (mal@lemburg.com). """ import codecs import zlib # this codec needs the optional zlib module ! ### Codec APIs def zlib_encode(input,errors='strict'): """ Encodes the object input and returns a tuple (output object, length consumed). errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = zlib.compress(input) return (output, len(input)) def zlib_decode(input,errors='strict'): """ Decodes the object input and returns a tuple (output object, length consumed). input must be an object which provides the bf_getreadbuf buffer slot. Python strings, buffer objects and memory mapped files are examples of objects providing this slot. errors defines the error handling to apply. It defaults to 'strict' handling which is the only currently supported error handling for this codec. """ assert errors == 'strict' output = zlib.decompress(input) return (output, len(input)) class Codec(codecs.Codec): def encode(self, input, errors='strict'): return zlib_encode(input, errors) def decode(self, input, errors='strict'): return zlib_decode(input, errors) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): assert errors == 'strict' self.errors = errors self.compressobj = zlib.compressobj() def encode(self, input, final=False): if final: c = self.compressobj.compress(input) return c + self.compressobj.flush() else: return self.compressobj.compress(input) def reset(self): self.compressobj = zlib.compressobj() class IncrementalDecoder(codecs.IncrementalDecoder): def __init__(self, errors='strict'): assert errors == 'strict' self.errors = errors self.decompressobj = zlib.decompressobj() def decode(self, input, final=False): if final: c = self.decompressobj.decompress(input) return c + self.decompressobj.flush() else: return self.decompressobj.decompress(input) def reset(self): self.decompressobj = zlib.decompressobj() class StreamWriter(Codec,codecs.StreamWriter): pass class StreamReader(Codec,codecs.StreamReader): pass ### encodings module API def getregentry(): return codecs.CodecInfo( name='zlib', encode=zlib_encode, decode=zlib_decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, ) feedgenerator-1.9/.tox/py26/lib/python2.6/fnmatch.py0000644000076500000240000000624712612565535021750 0ustar jmstaff00000000000000"""Filename matching with shell patterns. fnmatch(FILENAME, PATTERN) matches according to the local convention. fnmatchcase(FILENAME, PATTERN) always takes case in account. The functions operate by translating the pattern into a regular expression. They cache the compiled regular expressions for speed. The function translate(PATTERN) returns a regular expression corresponding to PATTERN. (It does not compile it.) """ import re __all__ = ["filter", "fnmatch", "fnmatchcase", "translate"] _cache = {} _MAXCACHE = 100 def _purge(): """Clear the pattern cache""" _cache.clear() def fnmatch(name, pat): """Test whether FILENAME matches PATTERN. Patterns are Unix shell style: * matches everything ? matches any single character [seq] matches any character in seq [!seq] matches any char not in seq An initial period in FILENAME is not special. Both FILENAME and PATTERN are first case-normalized if the operating system requires it. If you don't want this, use fnmatchcase(FILENAME, PATTERN). """ import os name = os.path.normcase(name) pat = os.path.normcase(pat) return fnmatchcase(name, pat) def filter(names, pat): """Return the subset of the list NAMES that match PAT""" import os,posixpath result=[] pat=os.path.normcase(pat) if not pat in _cache: res = translate(pat) if len(_cache) >= _MAXCACHE: _cache.clear() _cache[pat] = re.compile(res) match=_cache[pat].match if os.path is posixpath: # normcase on posix is NOP. Optimize it away from the loop. for name in names: if match(name): result.append(name) else: for name in names: if match(os.path.normcase(name)): result.append(name) return result def fnmatchcase(name, pat): """Test whether FILENAME matches PATTERN, including case. This is a version of fnmatch() which doesn't case-normalize its arguments. """ if not pat in _cache: res = translate(pat) if len(_cache) >= _MAXCACHE: _cache.clear() _cache[pat] = re.compile(res) return _cache[pat].match(name) is not None def translate(pat): """Translate a shell PATTERN to a regular expression. There is no way to quote meta-characters. """ i, n = 0, len(pat) res = '' while i < n: c = pat[i] i = i+1 if c == '*': res = res + '.*' elif c == '?': res = res + '.' elif c == '[': j = i if j < n and pat[j] == '!': j = j+1 if j < n and pat[j] == ']': j = j+1 while j < n and pat[j] != ']': j = j+1 if j >= n: res = res + '\\[' else: stuff = pat[i:j].replace('\\','\\\\') i = j+1 if stuff[0] == '!': stuff = '^' + stuff[1:] elif stuff[0] == '^': stuff = '\\' + stuff res = '%s[%s]' % (res, stuff) else: res = res + re.escape(c) return res + '\Z(?ms)' feedgenerator-1.9/.tox/py26/lib/python2.6/genericpath.py0000644000076500000240000000571412612565536022620 0ustar jmstaff00000000000000""" Path operations common to more than one OS Do not use directly. The OS specific modules import the appropriate functions from this module themselves. """ import os import stat __all__ = ['commonprefix', 'exists', 'getatime', 'getctime', 'getmtime', 'getsize', 'isdir', 'isfile'] # Does a path exist? # This is false for dangling symbolic links on systems that support them. def exists(path): """Test whether a path exists. Returns False for broken symbolic links""" try: st = os.stat(path) except os.error: return False return True # This follows symbolic links, so both islink() and isdir() can be true # for the same path ono systems that support symlinks def isfile(path): """Test whether a path is a regular file""" try: st = os.stat(path) except os.error: return False return stat.S_ISREG(st.st_mode) # Is a path a directory? # This follows symbolic links, so both islink() and isdir() # can be true for the same path on systems that support symlinks def isdir(s): """Return true if the pathname refers to an existing directory.""" try: st = os.stat(s) except os.error: return False return stat.S_ISDIR(st.st_mode) def getsize(filename): """Return the size of a file, reported by os.stat().""" return os.stat(filename).st_size def getmtime(filename): """Return the last modification time of a file, reported by os.stat().""" return os.stat(filename).st_mtime def getatime(filename): """Return the last access time of a file, reported by os.stat().""" return os.stat(filename).st_atime def getctime(filename): """Return the metadata change time of a file, reported by os.stat().""" return os.stat(filename).st_ctime # Return the longest prefix of all list elements. def commonprefix(m): "Given a list of pathnames, returns the longest common leading component" if not m: return '' s1 = min(m) s2 = max(m) for i, c in enumerate(s1): if c != s2[i]: return s1[:i] return s1 # Split a path in root and extension. # The extension is everything starting at the last dot in the last # pathname component; the root is everything before that. # It is always true that root + ext == p. # Generic implementation of splitext, to be parametrized with # the separators def _splitext(p, sep, altsep, extsep): """Split the extension from a pathname. Extension is everything from the last dot to the end, ignoring leading dots. Returns "(root, ext)"; ext may be empty.""" sepIndex = p.rfind(sep) if altsep: altsepIndex = p.rfind(altsep) sepIndex = max(sepIndex, altsepIndex) dotIndex = p.rfind(extsep) if dotIndex > sepIndex: # skip all leading dots filenameIndex = sepIndex + 1 while filenameIndex < dotIndex: if p[filenameIndex] != extsep: return p[:dotIndex], p[dotIndex:] filenameIndex += 1 return p, '' feedgenerator-1.9/.tox/py26/lib/python2.6/linecache.py0000644000076500000240000001004012612565536022226 0ustar jmstaff00000000000000"""Cache lines from files. This is intended to read lines from modules imported -- hence if a filename is not found, it will look down the module search path for a file by that name. """ import sys import os __all__ = ["getline", "clearcache", "checkcache"] def getline(filename, lineno, module_globals=None): lines = getlines(filename, module_globals) if 1 <= lineno <= len(lines): return lines[lineno-1] else: return '' # The cache cache = {} # The cache def clearcache(): """Clear the cache entirely.""" global cache cache = {} def getlines(filename, module_globals=None): """Get the lines for a file from the cache. Update the cache if it doesn't contain an entry for this file already.""" if filename in cache: return cache[filename][2] else: return updatecache(filename, module_globals) def checkcache(filename=None): """Discard cache entries that are out of date. (This is not checked upon each call!)""" if filename is None: filenames = cache.keys() else: if filename in cache: filenames = [filename] else: return for filename in filenames: size, mtime, lines, fullname = cache[filename] if mtime is None: continue # no-op for files loaded via a __loader__ try: stat = os.stat(fullname) except os.error: del cache[filename] continue if size != stat.st_size or mtime != stat.st_mtime: del cache[filename] def updatecache(filename, module_globals=None): """Update a cache entry and return its list of lines. If something's wrong, print a message, discard the cache entry, and return an empty list.""" if filename in cache: del cache[filename] if not filename or filename[0] + filename[-1] == '<>': return [] fullname = filename try: stat = os.stat(fullname) except os.error, msg: basename = filename # Try for a __loader__, if available if module_globals and '__loader__' in module_globals: name = module_globals.get('__name__') loader = module_globals['__loader__'] get_source = getattr(loader, 'get_source', None) if name and get_source: try: data = get_source(name) except (ImportError, IOError): pass else: if data is None: # No luck, the PEP302 loader cannot find the source # for this module. return [] cache[filename] = ( len(data), None, [line+'\n' for line in data.splitlines()], fullname ) return cache[filename][2] # Try looking through the module search path, which is only useful # when handling a relative filename. if os.path.isabs(filename): return [] for dirname in sys.path: # When using imputil, sys.path may contain things other than # strings; ignore them when it happens. try: fullname = os.path.join(dirname, basename) except (TypeError, AttributeError): # Not sufficiently string-like to do anything useful with. pass else: try: stat = os.stat(fullname) break except os.error: pass else: # No luck ## print '*** Cannot stat', filename, ':', msg return [] try: fp = open(fullname, 'rU') lines = fp.readlines() fp.close() except IOError, msg: ## print '*** Cannot open', fullname, ':', msg return [] if lines and not lines[-1].endswith('\n'): lines[-1] += '\n' size, mtime = stat.st_size, stat.st_mtime cache[filename] = size, mtime, lines, fullname return lines feedgenerator-1.9/.tox/py26/lib/python2.6/locale.py0000644000076500000240000024135012612565536021564 0ustar jmstaff00000000000000""" Locale support. The module provides low-level access to the C lib's locale APIs and adds high level number formatting APIs as well as a locale aliasing engine to complement these. The aliasing engine includes support for many commonly used locale names and maps them to values suitable for passing to the C lib's setlocale() function. It also includes default encodings for all supported locale names. """ import sys, encodings, encodings.aliases import functools # Try importing the _locale module. # # If this fails, fall back on a basic 'C' locale emulation. # Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before # trying the import. So __all__ is also fiddled at the end of the file. __all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error", "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm", "str", "atof", "atoi", "format", "format_string", "currency", "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY", "LC_NUMERIC", "LC_ALL", "CHAR_MAX"] try: from _locale import * except ImportError: # Locale emulation CHAR_MAX = 127 LC_ALL = 6 LC_COLLATE = 3 LC_CTYPE = 0 LC_MESSAGES = 5 LC_MONETARY = 4 LC_NUMERIC = 1 LC_TIME = 2 Error = ValueError def localeconv(): """ localeconv() -> dict. Returns numeric and monetary locale-specific parameters. """ # 'C' locale default values return {'grouping': [127], 'currency_symbol': '', 'n_sign_posn': 127, 'p_cs_precedes': 127, 'n_cs_precedes': 127, 'mon_grouping': [], 'n_sep_by_space': 127, 'decimal_point': '.', 'negative_sign': '', 'positive_sign': '', 'p_sep_by_space': 127, 'int_curr_symbol': '', 'p_sign_posn': 127, 'thousands_sep': '', 'mon_thousands_sep': '', 'frac_digits': 127, 'mon_decimal_point': '', 'int_frac_digits': 127} def setlocale(category, value=None): """ setlocale(integer,string=None) -> string. Activates/queries locale processing. """ if value not in (None, '', 'C'): raise Error, '_locale emulation only supports "C" locale' return 'C' def strcoll(a,b): """ strcoll(string,string) -> int. Compares two strings according to the locale. """ return cmp(a,b) def strxfrm(s): """ strxfrm(string) -> string. Returns a string that behaves for cmp locale-aware. """ return s _localeconv = localeconv # With this dict, you can override some items of localeconv's return value. # This is useful for testing purposes. _override_localeconv = {} @functools.wraps(_localeconv) def localeconv(): d = _localeconv() if _override_localeconv: d.update(_override_localeconv) return d ### Number formatting APIs # Author: Martin von Loewis # improved by Georg Brandl # Iterate over grouping intervals def _grouping_intervals(grouping): for interval in grouping: # if grouping is -1, we are done if interval == CHAR_MAX: return # 0: re-use last group ad infinitum if interval == 0: while True: yield last_interval yield interval last_interval = interval #perform the grouping from right to left def _group(s, monetary=False): conv = localeconv() thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep'] grouping = conv[monetary and 'mon_grouping' or 'grouping'] if not grouping: return (s, 0) result = "" seps = 0 if s[-1] == ' ': stripped = s.rstrip() right_spaces = s[len(stripped):] s = stripped else: right_spaces = '' left_spaces = '' groups = [] for interval in _grouping_intervals(grouping): if not s or s[-1] not in "0123456789": # only non-digit characters remain (sign, spaces) left_spaces = s s = '' break groups.append(s[-interval:]) s = s[:-interval] if s: groups.append(s) groups.reverse() return ( left_spaces + thousands_sep.join(groups) + right_spaces, len(thousands_sep) * (len(groups) - 1) ) # Strip a given amount of excess padding from the given string def _strip_padding(s, amount): lpos = 0 while amount and s[lpos] == ' ': lpos += 1 amount -= 1 rpos = len(s) - 1 while amount and s[rpos] == ' ': rpos -= 1 amount -= 1 return s[lpos:rpos+1] def format(percent, value, grouping=False, monetary=False, *additional): """Returns the locale-aware substitution of a %? specifier (percent). additional is for format strings which contain one or more '*' modifiers.""" # this is only for one-percent-specifier strings and this should be checked if percent[0] != '%': raise ValueError("format() must be given exactly one %char " "format specifier") if additional: formatted = percent % ((value,) + additional) else: formatted = percent % value # floats and decimal ints need special action! if percent[-1] in 'eEfFgG': seps = 0 parts = formatted.split('.') if grouping: parts[0], seps = _group(parts[0], monetary=monetary) decimal_point = localeconv()[monetary and 'mon_decimal_point' or 'decimal_point'] formatted = decimal_point.join(parts) if seps: formatted = _strip_padding(formatted, seps) elif percent[-1] in 'diu': seps = 0 if grouping: formatted, seps = _group(formatted, monetary=monetary) if seps: formatted = _strip_padding(formatted, seps) return formatted import re, operator _percent_re = re.compile(r'%(?:\((?P.*?)\))?' r'(?P[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]') def format_string(f, val, grouping=False): """Formats a string in the same way that the % formatting would use, but takes the current locale into account. Grouping is applied if the third parameter is true.""" percents = list(_percent_re.finditer(f)) new_f = _percent_re.sub('%s', f) if isinstance(val, tuple): new_val = list(val) i = 0 for perc in percents: starcount = perc.group('modifiers').count('*') new_val[i] = format(perc.group(), new_val[i], grouping, False, *new_val[i+1:i+1+starcount]) del new_val[i+1:i+1+starcount] i += (1 + starcount) val = tuple(new_val) elif operator.isMappingType(val): for perc in percents: key = perc.group("key") val[key] = format(perc.group(), val[key], grouping) else: # val is a single value val = format(percents[0].group(), val, grouping) return new_f % val def currency(val, symbol=True, grouping=False, international=False): """Formats val according to the currency settings in the current locale.""" conv = localeconv() # check for illegal values digits = conv[international and 'int_frac_digits' or 'frac_digits'] if digits == 127: raise ValueError("Currency formatting is not possible using " "the 'C' locale.") s = format('%%.%if' % digits, abs(val), grouping, monetary=True) # '<' and '>' are markers if the sign must be inserted between symbol and value s = '<' + s + '>' if symbol: smb = conv[international and 'int_curr_symbol' or 'currency_symbol'] precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes'] separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space'] if precedes: s = smb + (separated and ' ' or '') + s else: s = s + (separated and ' ' or '') + smb sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn'] sign = conv[val<0 and 'negative_sign' or 'positive_sign'] if sign_pos == 0: s = '(' + s + ')' elif sign_pos == 1: s = sign + s elif sign_pos == 2: s = s + sign elif sign_pos == 3: s = s.replace('<', sign) elif sign_pos == 4: s = s.replace('>', sign) else: # the default if nothing specified; # this should be the most fitting sign position s = sign + s return s.replace('<', '').replace('>', '') def str(val): """Convert float to integer, taking the locale into account.""" return format("%.12g", val) def atof(string, func=float): "Parses a string as a float according to the locale settings." #First, get rid of the grouping ts = localeconv()['thousands_sep'] if ts: string = string.replace(ts, '') #next, replace the decimal point with a dot dd = localeconv()['decimal_point'] if dd: string = string.replace(dd, '.') #finally, parse the string return func(string) def atoi(str): "Converts a string to an integer according to the locale settings." return atof(str, int) def _test(): setlocale(LC_ALL, "") #do grouping s1 = format("%d", 123456789,1) print s1, "is", atoi(s1) #standard formatting s1 = str(3.14) print s1, "is", atof(s1) ### Locale name aliasing engine # Author: Marc-Andre Lemburg, mal@lemburg.com # Various tweaks by Fredrik Lundh # store away the low-level version of setlocale (it's # overridden below) _setlocale = setlocale def normalize(localename): """ Returns a normalized locale code for the given locale name. The returned locale code is formatted for use with setlocale(). If normalization fails, the original name is returned unchanged. If the given encoding is not known, the function defaults to the default encoding for the locale code just like setlocale() does. """ # Normalize the locale name and extract the encoding fullname = localename.lower() if ':' in fullname: # ':' is sometimes used as encoding delimiter. fullname = fullname.replace(':', '.') if '.' in fullname: langname, encoding = fullname.split('.')[:2] fullname = langname + '.' + encoding else: langname = fullname encoding = '' # First lookup: fullname (possibly with encoding) norm_encoding = encoding.replace('-', '') norm_encoding = norm_encoding.replace('_', '') lookup_name = langname + '.' + encoding code = locale_alias.get(lookup_name, None) if code is not None: return code #print 'first lookup failed' # Second try: langname (without encoding) code = locale_alias.get(langname, None) if code is not None: #print 'langname lookup succeeded' if '.' in code: langname, defenc = code.split('.') else: langname = code defenc = '' if encoding: # Convert the encoding to a C lib compatible encoding string norm_encoding = encodings.normalize_encoding(encoding) #print 'norm encoding: %r' % norm_encoding norm_encoding = encodings.aliases.aliases.get(norm_encoding, norm_encoding) #print 'aliased encoding: %r' % norm_encoding encoding = locale_encoding_alias.get(norm_encoding, norm_encoding) else: encoding = defenc #print 'found encoding %r' % encoding if encoding: return langname + '.' + encoding else: return langname else: return localename def _parse_localename(localename): """ Parses the locale code for localename and returns the result as tuple (language code, encoding). The localename is normalized and passed through the locale alias engine. A ValueError is raised in case the locale name cannot be parsed. The language code corresponds to RFC 1766. code and encoding can be None in case the values cannot be determined or are unknown to this implementation. """ code = normalize(localename) if '@' in code: # Deal with locale modifiers code, modifier = code.split('@') if modifier == 'euro' and '.' not in code: # Assume Latin-9 for @euro locales. This is bogus, # since some systems may use other encodings for these # locales. Also, we ignore other modifiers. return code, 'iso-8859-15' if '.' in code: return tuple(code.split('.')[:2]) elif code == 'C': return None, None raise ValueError, 'unknown locale: %s' % localename def _build_localename(localetuple): """ Builds a locale code from the given tuple (language code, encoding). No aliasing or normalizing takes place. """ language, encoding = localetuple if language is None: language = 'C' if encoding is None: return language else: return language + '.' + encoding def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')): """ Tries to determine the default locale settings and returns them as tuple (language code, encoding). According to POSIX, a program which has not called setlocale(LC_ALL, "") runs using the portable 'C' locale. Calling setlocale(LC_ALL, "") lets it use the default locale as defined by the LANG variable. Since we don't want to interfere with the current locale setting we thus emulate the behavior in the way described above. To maintain compatibility with other platforms, not only the LANG variable is tested, but a list of variables given as envvars parameter. The first found to be defined will be used. envvars defaults to the search path used in GNU gettext; it must always contain the variable name 'LANG'. Except for the code 'C', the language code corresponds to RFC 1766. code and encoding can be None in case the values cannot be determined. """ try: # check if it's supported by the _locale module import _locale code, encoding = _locale._getdefaultlocale() except (ImportError, AttributeError): pass else: # make sure the code/encoding values are valid if sys.platform == "win32" and code and code[:2] == "0x": # map windows language identifier to language name code = windows_locale.get(int(code, 0)) # ...add other platform-specific processing here, if # necessary... return code, encoding # fall back on POSIX behaviour import os lookup = os.environ.get for variable in envvars: localename = lookup(variable,None) if localename: if variable == 'LANGUAGE': localename = localename.split(':')[0] break else: localename = 'C' return _parse_localename(localename) def getlocale(category=LC_CTYPE): """ Returns the current setting for the given locale category as tuple (language code, encoding). category may be one of the LC_* value except LC_ALL. It defaults to LC_CTYPE. Except for the code 'C', the language code corresponds to RFC 1766. code and encoding can be None in case the values cannot be determined. """ localename = _setlocale(category) if category == LC_ALL and ';' in localename: raise TypeError, 'category LC_ALL is not supported' return _parse_localename(localename) def setlocale(category, locale=None): """ Set the locale for the given category. The locale can be a string, a locale tuple (language code, encoding), or None. Locale tuples are converted to strings the locale aliasing engine. Locale strings are passed directly to the C lib. category may be given as one of the LC_* values. """ if locale and type(locale) is not type(""): # convert to string locale = normalize(_build_localename(locale)) return _setlocale(category, locale) def resetlocale(category=LC_ALL): """ Sets the locale for category to the default setting. The default setting is determined by calling getdefaultlocale(). category defaults to LC_ALL. """ _setlocale(category, _build_localename(getdefaultlocale())) if sys.platform in ('win32', 'mac'): # On Win32, this will return the ANSI code page # On the Mac, it should return the system encoding; # it might return "ascii" instead def getpreferredencoding(do_setlocale = True): """Return the charset that the user is likely using.""" import _locale return _locale._getdefaultlocale()[1] else: # On Unix, if CODESET is available, use that. try: CODESET except NameError: # Fall back to parsing environment variables :-( def getpreferredencoding(do_setlocale = True): """Return the charset that the user is likely using, by looking at environment variables.""" return getdefaultlocale()[1] else: def getpreferredencoding(do_setlocale = True): """Return the charset that the user is likely using, according to the system configuration.""" if do_setlocale: oldloc = setlocale(LC_CTYPE) try: setlocale(LC_CTYPE, "") except Error: pass result = nl_langinfo(CODESET) setlocale(LC_CTYPE, oldloc) return result else: return nl_langinfo(CODESET) ### Database # # The following data was extracted from the locale.alias file which # comes with X11 and then hand edited removing the explicit encoding # definitions and adding some more aliases. The file is usually # available as /usr/lib/X11/locale/locale.alias. # # # The local_encoding_alias table maps lowercase encoding alias names # to C locale encoding names (case-sensitive). Note that normalize() # first looks up the encoding in the encodings.aliases dictionary and # then applies this mapping to find the correct C lib name for the # encoding. # locale_encoding_alias = { # Mappings for non-standard encoding names used in locale names '437': 'C', 'c': 'C', 'en': 'ISO8859-1', 'jis': 'JIS7', 'jis7': 'JIS7', 'ajec': 'eucJP', # Mappings from Python codec names to C lib encoding names 'ascii': 'ISO8859-1', 'latin_1': 'ISO8859-1', 'iso8859_1': 'ISO8859-1', 'iso8859_10': 'ISO8859-10', 'iso8859_11': 'ISO8859-11', 'iso8859_13': 'ISO8859-13', 'iso8859_14': 'ISO8859-14', 'iso8859_15': 'ISO8859-15', 'iso8859_2': 'ISO8859-2', 'iso8859_3': 'ISO8859-3', 'iso8859_4': 'ISO8859-4', 'iso8859_5': 'ISO8859-5', 'iso8859_6': 'ISO8859-6', 'iso8859_7': 'ISO8859-7', 'iso8859_8': 'ISO8859-8', 'iso8859_9': 'ISO8859-9', 'iso2022_jp': 'JIS7', 'shift_jis': 'SJIS', 'tactis': 'TACTIS', 'euc_jp': 'eucJP', 'euc_kr': 'eucKR', 'utf_8': 'UTF8', 'koi8_r': 'KOI8-R', 'koi8_u': 'KOI8-U', # XXX This list is still incomplete. If you know more # mappings, please file a bug report. Thanks. } # # The locale_alias table maps lowercase alias names to C locale names # (case-sensitive). Encodings are always separated from the locale # name using a dot ('.'); they should only be given in case the # language name is needed to interpret the given encoding alias # correctly (CJK codes often have this need). # # Note that the normalize() function which uses this tables # removes '_' and '-' characters from the encoding part of the # locale name before doing the lookup. This saves a lot of # space in the table. # # MAL 2004-12-10: # Updated alias mapping to most recent locale.alias file # from X.org distribution using makelocalealias.py. # # These are the differences compared to the old mapping (Python 2.4 # and older): # # updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251' # updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251' # updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251' # updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2' # updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2' # updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2' # updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1' # updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15' # updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15' # updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15' # updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15' # updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8' # updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8' # updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP' # updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13' # updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13' # updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2' # updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2' # updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11' # updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312' # updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5' # updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5' # # MAL 2008-05-30: # Updated alias mapping to most recent locale.alias file # from X.org distribution using makelocalealias.py. # # These are the differences compared to the old mapping (Python 2.5 # and older): # # updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2' # updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2' # updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251' # updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2' # updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' # updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251' # updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8' # updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5' locale_alias = { 'a3': 'a3_AZ.KOI8-C', 'a3_az': 'a3_AZ.KOI8-C', 'a3_az.koi8c': 'a3_AZ.KOI8-C', 'af': 'af_ZA.ISO8859-1', 'af_za': 'af_ZA.ISO8859-1', 'af_za.iso88591': 'af_ZA.ISO8859-1', 'am': 'am_ET.UTF-8', 'am_et': 'am_ET.UTF-8', 'american': 'en_US.ISO8859-1', 'american.iso88591': 'en_US.ISO8859-1', 'ar': 'ar_AA.ISO8859-6', 'ar_aa': 'ar_AA.ISO8859-6', 'ar_aa.iso88596': 'ar_AA.ISO8859-6', 'ar_ae': 'ar_AE.ISO8859-6', 'ar_ae.iso88596': 'ar_AE.ISO8859-6', 'ar_bh': 'ar_BH.ISO8859-6', 'ar_bh.iso88596': 'ar_BH.ISO8859-6', 'ar_dz': 'ar_DZ.ISO8859-6', 'ar_dz.iso88596': 'ar_DZ.ISO8859-6', 'ar_eg': 'ar_EG.ISO8859-6', 'ar_eg.iso88596': 'ar_EG.ISO8859-6', 'ar_iq': 'ar_IQ.ISO8859-6', 'ar_iq.iso88596': 'ar_IQ.ISO8859-6', 'ar_jo': 'ar_JO.ISO8859-6', 'ar_jo.iso88596': 'ar_JO.ISO8859-6', 'ar_kw': 'ar_KW.ISO8859-6', 'ar_kw.iso88596': 'ar_KW.ISO8859-6', 'ar_lb': 'ar_LB.ISO8859-6', 'ar_lb.iso88596': 'ar_LB.ISO8859-6', 'ar_ly': 'ar_LY.ISO8859-6', 'ar_ly.iso88596': 'ar_LY.ISO8859-6', 'ar_ma': 'ar_MA.ISO8859-6', 'ar_ma.iso88596': 'ar_MA.ISO8859-6', 'ar_om': 'ar_OM.ISO8859-6', 'ar_om.iso88596': 'ar_OM.ISO8859-6', 'ar_qa': 'ar_QA.ISO8859-6', 'ar_qa.iso88596': 'ar_QA.ISO8859-6', 'ar_sa': 'ar_SA.ISO8859-6', 'ar_sa.iso88596': 'ar_SA.ISO8859-6', 'ar_sd': 'ar_SD.ISO8859-6', 'ar_sd.iso88596': 'ar_SD.ISO8859-6', 'ar_sy': 'ar_SY.ISO8859-6', 'ar_sy.iso88596': 'ar_SY.ISO8859-6', 'ar_tn': 'ar_TN.ISO8859-6', 'ar_tn.iso88596': 'ar_TN.ISO8859-6', 'ar_ye': 'ar_YE.ISO8859-6', 'ar_ye.iso88596': 'ar_YE.ISO8859-6', 'arabic': 'ar_AA.ISO8859-6', 'arabic.iso88596': 'ar_AA.ISO8859-6', 'az': 'az_AZ.ISO8859-9E', 'az_az': 'az_AZ.ISO8859-9E', 'az_az.iso88599e': 'az_AZ.ISO8859-9E', 'be': 'be_BY.CP1251', 'be_by': 'be_BY.CP1251', 'be_by.cp1251': 'be_BY.CP1251', 'be_by.microsoftcp1251': 'be_BY.CP1251', 'bg': 'bg_BG.CP1251', 'bg_bg': 'bg_BG.CP1251', 'bg_bg.cp1251': 'bg_BG.CP1251', 'bg_bg.iso88595': 'bg_BG.ISO8859-5', 'bg_bg.koi8r': 'bg_BG.KOI8-R', 'bg_bg.microsoftcp1251': 'bg_BG.CP1251', 'bn_in': 'bn_IN.UTF-8', 'bokmal': 'nb_NO.ISO8859-1', 'bokm\xe5l': 'nb_NO.ISO8859-1', 'br': 'br_FR.ISO8859-1', 'br_fr': 'br_FR.ISO8859-1', 'br_fr.iso88591': 'br_FR.ISO8859-1', 'br_fr.iso885914': 'br_FR.ISO8859-14', 'br_fr.iso885915': 'br_FR.ISO8859-15', 'br_fr.iso885915@euro': 'br_FR.ISO8859-15', 'br_fr.utf8@euro': 'br_FR.UTF-8', 'br_fr@euro': 'br_FR.ISO8859-15', 'bs': 'bs_BA.ISO8859-2', 'bs_ba': 'bs_BA.ISO8859-2', 'bs_ba.iso88592': 'bs_BA.ISO8859-2', 'bulgarian': 'bg_BG.CP1251', 'c': 'C', 'c-french': 'fr_CA.ISO8859-1', 'c-french.iso88591': 'fr_CA.ISO8859-1', 'c.en': 'C', 'c.iso88591': 'en_US.ISO8859-1', 'c_c': 'C', 'c_c.c': 'C', 'ca': 'ca_ES.ISO8859-1', 'ca_es': 'ca_ES.ISO8859-1', 'ca_es.iso88591': 'ca_ES.ISO8859-1', 'ca_es.iso885915': 'ca_ES.ISO8859-15', 'ca_es.iso885915@euro': 'ca_ES.ISO8859-15', 'ca_es.utf8@euro': 'ca_ES.UTF-8', 'ca_es@euro': 'ca_ES.ISO8859-15', 'catalan': 'ca_ES.ISO8859-1', 'cextend': 'en_US.ISO8859-1', 'cextend.en': 'en_US.ISO8859-1', 'chinese-s': 'zh_CN.eucCN', 'chinese-t': 'zh_TW.eucTW', 'croatian': 'hr_HR.ISO8859-2', 'cs': 'cs_CZ.ISO8859-2', 'cs_cs': 'cs_CZ.ISO8859-2', 'cs_cs.iso88592': 'cs_CS.ISO8859-2', 'cs_cz': 'cs_CZ.ISO8859-2', 'cs_cz.iso88592': 'cs_CZ.ISO8859-2', 'cy': 'cy_GB.ISO8859-1', 'cy_gb': 'cy_GB.ISO8859-1', 'cy_gb.iso88591': 'cy_GB.ISO8859-1', 'cy_gb.iso885914': 'cy_GB.ISO8859-14', 'cy_gb.iso885915': 'cy_GB.ISO8859-15', 'cy_gb@euro': 'cy_GB.ISO8859-15', 'cz': 'cs_CZ.ISO8859-2', 'cz_cz': 'cs_CZ.ISO8859-2', 'czech': 'cs_CZ.ISO8859-2', 'da': 'da_DK.ISO8859-1', 'da_dk': 'da_DK.ISO8859-1', 'da_dk.88591': 'da_DK.ISO8859-1', 'da_dk.885915': 'da_DK.ISO8859-15', 'da_dk.iso88591': 'da_DK.ISO8859-1', 'da_dk.iso885915': 'da_DK.ISO8859-15', 'da_dk@euro': 'da_DK.ISO8859-15', 'danish': 'da_DK.ISO8859-1', 'danish.iso88591': 'da_DK.ISO8859-1', 'dansk': 'da_DK.ISO8859-1', 'de': 'de_DE.ISO8859-1', 'de_at': 'de_AT.ISO8859-1', 'de_at.iso88591': 'de_AT.ISO8859-1', 'de_at.iso885915': 'de_AT.ISO8859-15', 'de_at.iso885915@euro': 'de_AT.ISO8859-15', 'de_at.utf8@euro': 'de_AT.UTF-8', 'de_at@euro': 'de_AT.ISO8859-15', 'de_be': 'de_BE.ISO8859-1', 'de_be.iso88591': 'de_BE.ISO8859-1', 'de_be.iso885915': 'de_BE.ISO8859-15', 'de_be.iso885915@euro': 'de_BE.ISO8859-15', 'de_be.utf8@euro': 'de_BE.UTF-8', 'de_be@euro': 'de_BE.ISO8859-15', 'de_ch': 'de_CH.ISO8859-1', 'de_ch.iso88591': 'de_CH.ISO8859-1', 'de_ch.iso885915': 'de_CH.ISO8859-15', 'de_ch@euro': 'de_CH.ISO8859-15', 'de_de': 'de_DE.ISO8859-1', 'de_de.88591': 'de_DE.ISO8859-1', 'de_de.885915': 'de_DE.ISO8859-15', 'de_de.885915@euro': 'de_DE.ISO8859-15', 'de_de.iso88591': 'de_DE.ISO8859-1', 'de_de.iso885915': 'de_DE.ISO8859-15', 'de_de.iso885915@euro': 'de_DE.ISO8859-15', 'de_de.utf8@euro': 'de_DE.UTF-8', 'de_de@euro': 'de_DE.ISO8859-15', 'de_lu': 'de_LU.ISO8859-1', 'de_lu.iso88591': 'de_LU.ISO8859-1', 'de_lu.iso885915': 'de_LU.ISO8859-15', 'de_lu.iso885915@euro': 'de_LU.ISO8859-15', 'de_lu.utf8@euro': 'de_LU.UTF-8', 'de_lu@euro': 'de_LU.ISO8859-15', 'deutsch': 'de_DE.ISO8859-1', 'dutch': 'nl_NL.ISO8859-1', 'dutch.iso88591': 'nl_BE.ISO8859-1', 'ee': 'ee_EE.ISO8859-4', 'ee_ee': 'ee_EE.ISO8859-4', 'ee_ee.iso88594': 'ee_EE.ISO8859-4', 'eesti': 'et_EE.ISO8859-1', 'el': 'el_GR.ISO8859-7', 'el_gr': 'el_GR.ISO8859-7', 'el_gr.iso88597': 'el_GR.ISO8859-7', 'el_gr@euro': 'el_GR.ISO8859-15', 'en': 'en_US.ISO8859-1', 'en.iso88591': 'en_US.ISO8859-1', 'en_au': 'en_AU.ISO8859-1', 'en_au.iso88591': 'en_AU.ISO8859-1', 'en_be': 'en_BE.ISO8859-1', 'en_be@euro': 'en_BE.ISO8859-15', 'en_bw': 'en_BW.ISO8859-1', 'en_bw.iso88591': 'en_BW.ISO8859-1', 'en_ca': 'en_CA.ISO8859-1', 'en_ca.iso88591': 'en_CA.ISO8859-1', 'en_gb': 'en_GB.ISO8859-1', 'en_gb.88591': 'en_GB.ISO8859-1', 'en_gb.iso88591': 'en_GB.ISO8859-1', 'en_gb.iso885915': 'en_GB.ISO8859-15', 'en_gb@euro': 'en_GB.ISO8859-15', 'en_hk': 'en_HK.ISO8859-1', 'en_hk.iso88591': 'en_HK.ISO8859-1', 'en_ie': 'en_IE.ISO8859-1', 'en_ie.iso88591': 'en_IE.ISO8859-1', 'en_ie.iso885915': 'en_IE.ISO8859-15', 'en_ie.iso885915@euro': 'en_IE.ISO8859-15', 'en_ie.utf8@euro': 'en_IE.UTF-8', 'en_ie@euro': 'en_IE.ISO8859-15', 'en_in': 'en_IN.ISO8859-1', 'en_nz': 'en_NZ.ISO8859-1', 'en_nz.iso88591': 'en_NZ.ISO8859-1', 'en_ph': 'en_PH.ISO8859-1', 'en_ph.iso88591': 'en_PH.ISO8859-1', 'en_sg': 'en_SG.ISO8859-1', 'en_sg.iso88591': 'en_SG.ISO8859-1', 'en_uk': 'en_GB.ISO8859-1', 'en_us': 'en_US.ISO8859-1', 'en_us.88591': 'en_US.ISO8859-1', 'en_us.885915': 'en_US.ISO8859-15', 'en_us.iso88591': 'en_US.ISO8859-1', 'en_us.iso885915': 'en_US.ISO8859-15', 'en_us.iso885915@euro': 'en_US.ISO8859-15', 'en_us@euro': 'en_US.ISO8859-15', 'en_us@euro@euro': 'en_US.ISO8859-15', 'en_za': 'en_ZA.ISO8859-1', 'en_za.88591': 'en_ZA.ISO8859-1', 'en_za.iso88591': 'en_ZA.ISO8859-1', 'en_za.iso885915': 'en_ZA.ISO8859-15', 'en_za@euro': 'en_ZA.ISO8859-15', 'en_zw': 'en_ZW.ISO8859-1', 'en_zw.iso88591': 'en_ZW.ISO8859-1', 'eng_gb': 'en_GB.ISO8859-1', 'eng_gb.8859': 'en_GB.ISO8859-1', 'english': 'en_EN.ISO8859-1', 'english.iso88591': 'en_EN.ISO8859-1', 'english_uk': 'en_GB.ISO8859-1', 'english_uk.8859': 'en_GB.ISO8859-1', 'english_united-states': 'en_US.ISO8859-1', 'english_united-states.437': 'C', 'english_us': 'en_US.ISO8859-1', 'english_us.8859': 'en_US.ISO8859-1', 'english_us.ascii': 'en_US.ISO8859-1', 'eo': 'eo_XX.ISO8859-3', 'eo_eo': 'eo_EO.ISO8859-3', 'eo_eo.iso88593': 'eo_EO.ISO8859-3', 'eo_xx': 'eo_XX.ISO8859-3', 'eo_xx.iso88593': 'eo_XX.ISO8859-3', 'es': 'es_ES.ISO8859-1', 'es_ar': 'es_AR.ISO8859-1', 'es_ar.iso88591': 'es_AR.ISO8859-1', 'es_bo': 'es_BO.ISO8859-1', 'es_bo.iso88591': 'es_BO.ISO8859-1', 'es_cl': 'es_CL.ISO8859-1', 'es_cl.iso88591': 'es_CL.ISO8859-1', 'es_co': 'es_CO.ISO8859-1', 'es_co.iso88591': 'es_CO.ISO8859-1', 'es_cr': 'es_CR.ISO8859-1', 'es_cr.iso88591': 'es_CR.ISO8859-1', 'es_do': 'es_DO.ISO8859-1', 'es_do.iso88591': 'es_DO.ISO8859-1', 'es_ec': 'es_EC.ISO8859-1', 'es_ec.iso88591': 'es_EC.ISO8859-1', 'es_es': 'es_ES.ISO8859-1', 'es_es.88591': 'es_ES.ISO8859-1', 'es_es.iso88591': 'es_ES.ISO8859-1', 'es_es.iso885915': 'es_ES.ISO8859-15', 'es_es.iso885915@euro': 'es_ES.ISO8859-15', 'es_es.utf8@euro': 'es_ES.UTF-8', 'es_es@euro': 'es_ES.ISO8859-15', 'es_gt': 'es_GT.ISO8859-1', 'es_gt.iso88591': 'es_GT.ISO8859-1', 'es_hn': 'es_HN.ISO8859-1', 'es_hn.iso88591': 'es_HN.ISO8859-1', 'es_mx': 'es_MX.ISO8859-1', 'es_mx.iso88591': 'es_MX.ISO8859-1', 'es_ni': 'es_NI.ISO8859-1', 'es_ni.iso88591': 'es_NI.ISO8859-1', 'es_pa': 'es_PA.ISO8859-1', 'es_pa.iso88591': 'es_PA.ISO8859-1', 'es_pa.iso885915': 'es_PA.ISO8859-15', 'es_pa@euro': 'es_PA.ISO8859-15', 'es_pe': 'es_PE.ISO8859-1', 'es_pe.iso88591': 'es_PE.ISO8859-1', 'es_pe.iso885915': 'es_PE.ISO8859-15', 'es_pe@euro': 'es_PE.ISO8859-15', 'es_pr': 'es_PR.ISO8859-1', 'es_pr.iso88591': 'es_PR.ISO8859-1', 'es_py': 'es_PY.ISO8859-1', 'es_py.iso88591': 'es_PY.ISO8859-1', 'es_py.iso885915': 'es_PY.ISO8859-15', 'es_py@euro': 'es_PY.ISO8859-15', 'es_sv': 'es_SV.ISO8859-1', 'es_sv.iso88591': 'es_SV.ISO8859-1', 'es_sv.iso885915': 'es_SV.ISO8859-15', 'es_sv@euro': 'es_SV.ISO8859-15', 'es_us': 'es_US.ISO8859-1', 'es_us.iso88591': 'es_US.ISO8859-1', 'es_uy': 'es_UY.ISO8859-1', 'es_uy.iso88591': 'es_UY.ISO8859-1', 'es_uy.iso885915': 'es_UY.ISO8859-15', 'es_uy@euro': 'es_UY.ISO8859-15', 'es_ve': 'es_VE.ISO8859-1', 'es_ve.iso88591': 'es_VE.ISO8859-1', 'es_ve.iso885915': 'es_VE.ISO8859-15', 'es_ve@euro': 'es_VE.ISO8859-15', 'estonian': 'et_EE.ISO8859-1', 'et': 'et_EE.ISO8859-15', 'et_ee': 'et_EE.ISO8859-15', 'et_ee.iso88591': 'et_EE.ISO8859-1', 'et_ee.iso885913': 'et_EE.ISO8859-13', 'et_ee.iso885915': 'et_EE.ISO8859-15', 'et_ee.iso88594': 'et_EE.ISO8859-4', 'et_ee@euro': 'et_EE.ISO8859-15', 'eu': 'eu_ES.ISO8859-1', 'eu_es': 'eu_ES.ISO8859-1', 'eu_es.iso88591': 'eu_ES.ISO8859-1', 'eu_es.iso885915': 'eu_ES.ISO8859-15', 'eu_es.iso885915@euro': 'eu_ES.ISO8859-15', 'eu_es.utf8@euro': 'eu_ES.UTF-8', 'eu_es@euro': 'eu_ES.ISO8859-15', 'fa': 'fa_IR.UTF-8', 'fa_ir': 'fa_IR.UTF-8', 'fa_ir.isiri3342': 'fa_IR.ISIRI-3342', 'fi': 'fi_FI.ISO8859-15', 'fi_fi': 'fi_FI.ISO8859-15', 'fi_fi.88591': 'fi_FI.ISO8859-1', 'fi_fi.iso88591': 'fi_FI.ISO8859-1', 'fi_fi.iso885915': 'fi_FI.ISO8859-15', 'fi_fi.iso885915@euro': 'fi_FI.ISO8859-15', 'fi_fi.utf8@euro': 'fi_FI.UTF-8', 'fi_fi@euro': 'fi_FI.ISO8859-15', 'finnish': 'fi_FI.ISO8859-1', 'finnish.iso88591': 'fi_FI.ISO8859-1', 'fo': 'fo_FO.ISO8859-1', 'fo_fo': 'fo_FO.ISO8859-1', 'fo_fo.iso88591': 'fo_FO.ISO8859-1', 'fo_fo.iso885915': 'fo_FO.ISO8859-15', 'fo_fo@euro': 'fo_FO.ISO8859-15', 'fr': 'fr_FR.ISO8859-1', 'fr_be': 'fr_BE.ISO8859-1', 'fr_be.88591': 'fr_BE.ISO8859-1', 'fr_be.iso88591': 'fr_BE.ISO8859-1', 'fr_be.iso885915': 'fr_BE.ISO8859-15', 'fr_be.iso885915@euro': 'fr_BE.ISO8859-15', 'fr_be.utf8@euro': 'fr_BE.UTF-8', 'fr_be@euro': 'fr_BE.ISO8859-15', 'fr_ca': 'fr_CA.ISO8859-1', 'fr_ca.88591': 'fr_CA.ISO8859-1', 'fr_ca.iso88591': 'fr_CA.ISO8859-1', 'fr_ca.iso885915': 'fr_CA.ISO8859-15', 'fr_ca@euro': 'fr_CA.ISO8859-15', 'fr_ch': 'fr_CH.ISO8859-1', 'fr_ch.88591': 'fr_CH.ISO8859-1', 'fr_ch.iso88591': 'fr_CH.ISO8859-1', 'fr_ch.iso885915': 'fr_CH.ISO8859-15', 'fr_ch@euro': 'fr_CH.ISO8859-15', 'fr_fr': 'fr_FR.ISO8859-1', 'fr_fr.88591': 'fr_FR.ISO8859-1', 'fr_fr.iso88591': 'fr_FR.ISO8859-1', 'fr_fr.iso885915': 'fr_FR.ISO8859-15', 'fr_fr.iso885915@euro': 'fr_FR.ISO8859-15', 'fr_fr.utf8@euro': 'fr_FR.UTF-8', 'fr_fr@euro': 'fr_FR.ISO8859-15', 'fr_lu': 'fr_LU.ISO8859-1', 'fr_lu.88591': 'fr_LU.ISO8859-1', 'fr_lu.iso88591': 'fr_LU.ISO8859-1', 'fr_lu.iso885915': 'fr_LU.ISO8859-15', 'fr_lu.iso885915@euro': 'fr_LU.ISO8859-15', 'fr_lu.utf8@euro': 'fr_LU.UTF-8', 'fr_lu@euro': 'fr_LU.ISO8859-15', 'fran\xe7ais': 'fr_FR.ISO8859-1', 'fre_fr': 'fr_FR.ISO8859-1', 'fre_fr.8859': 'fr_FR.ISO8859-1', 'french': 'fr_FR.ISO8859-1', 'french.iso88591': 'fr_CH.ISO8859-1', 'french_france': 'fr_FR.ISO8859-1', 'french_france.8859': 'fr_FR.ISO8859-1', 'ga': 'ga_IE.ISO8859-1', 'ga_ie': 'ga_IE.ISO8859-1', 'ga_ie.iso88591': 'ga_IE.ISO8859-1', 'ga_ie.iso885914': 'ga_IE.ISO8859-14', 'ga_ie.iso885915': 'ga_IE.ISO8859-15', 'ga_ie.iso885915@euro': 'ga_IE.ISO8859-15', 'ga_ie.utf8@euro': 'ga_IE.UTF-8', 'ga_ie@euro': 'ga_IE.ISO8859-15', 'galego': 'gl_ES.ISO8859-1', 'galician': 'gl_ES.ISO8859-1', 'gd': 'gd_GB.ISO8859-1', 'gd_gb': 'gd_GB.ISO8859-1', 'gd_gb.iso88591': 'gd_GB.ISO8859-1', 'gd_gb.iso885914': 'gd_GB.ISO8859-14', 'gd_gb.iso885915': 'gd_GB.ISO8859-15', 'gd_gb@euro': 'gd_GB.ISO8859-15', 'ger_de': 'de_DE.ISO8859-1', 'ger_de.8859': 'de_DE.ISO8859-1', 'german': 'de_DE.ISO8859-1', 'german.iso88591': 'de_CH.ISO8859-1', 'german_germany': 'de_DE.ISO8859-1', 'german_germany.8859': 'de_DE.ISO8859-1', 'gl': 'gl_ES.ISO8859-1', 'gl_es': 'gl_ES.ISO8859-1', 'gl_es.iso88591': 'gl_ES.ISO8859-1', 'gl_es.iso885915': 'gl_ES.ISO8859-15', 'gl_es.iso885915@euro': 'gl_ES.ISO8859-15', 'gl_es.utf8@euro': 'gl_ES.UTF-8', 'gl_es@euro': 'gl_ES.ISO8859-15', 'greek': 'el_GR.ISO8859-7', 'greek.iso88597': 'el_GR.ISO8859-7', 'gu_in': 'gu_IN.UTF-8', 'gv': 'gv_GB.ISO8859-1', 'gv_gb': 'gv_GB.ISO8859-1', 'gv_gb.iso88591': 'gv_GB.ISO8859-1', 'gv_gb.iso885914': 'gv_GB.ISO8859-14', 'gv_gb.iso885915': 'gv_GB.ISO8859-15', 'gv_gb@euro': 'gv_GB.ISO8859-15', 'he': 'he_IL.ISO8859-8', 'he_il': 'he_IL.ISO8859-8', 'he_il.cp1255': 'he_IL.CP1255', 'he_il.iso88598': 'he_IL.ISO8859-8', 'he_il.microsoftcp1255': 'he_IL.CP1255', 'hebrew': 'iw_IL.ISO8859-8', 'hebrew.iso88598': 'iw_IL.ISO8859-8', 'hi': 'hi_IN.ISCII-DEV', 'hi_in': 'hi_IN.ISCII-DEV', 'hi_in.isciidev': 'hi_IN.ISCII-DEV', 'hr': 'hr_HR.ISO8859-2', 'hr_hr': 'hr_HR.ISO8859-2', 'hr_hr.iso88592': 'hr_HR.ISO8859-2', 'hrvatski': 'hr_HR.ISO8859-2', 'hu': 'hu_HU.ISO8859-2', 'hu_hu': 'hu_HU.ISO8859-2', 'hu_hu.iso88592': 'hu_HU.ISO8859-2', 'hungarian': 'hu_HU.ISO8859-2', 'icelandic': 'is_IS.ISO8859-1', 'icelandic.iso88591': 'is_IS.ISO8859-1', 'id': 'id_ID.ISO8859-1', 'id_id': 'id_ID.ISO8859-1', 'in': 'id_ID.ISO8859-1', 'in_id': 'id_ID.ISO8859-1', 'is': 'is_IS.ISO8859-1', 'is_is': 'is_IS.ISO8859-1', 'is_is.iso88591': 'is_IS.ISO8859-1', 'is_is.iso885915': 'is_IS.ISO8859-15', 'is_is@euro': 'is_IS.ISO8859-15', 'iso-8859-1': 'en_US.ISO8859-1', 'iso-8859-15': 'en_US.ISO8859-15', 'iso8859-1': 'en_US.ISO8859-1', 'iso8859-15': 'en_US.ISO8859-15', 'iso_8859_1': 'en_US.ISO8859-1', 'iso_8859_15': 'en_US.ISO8859-15', 'it': 'it_IT.ISO8859-1', 'it_ch': 'it_CH.ISO8859-1', 'it_ch.iso88591': 'it_CH.ISO8859-1', 'it_ch.iso885915': 'it_CH.ISO8859-15', 'it_ch@euro': 'it_CH.ISO8859-15', 'it_it': 'it_IT.ISO8859-1', 'it_it.88591': 'it_IT.ISO8859-1', 'it_it.iso88591': 'it_IT.ISO8859-1', 'it_it.iso885915': 'it_IT.ISO8859-15', 'it_it.iso885915@euro': 'it_IT.ISO8859-15', 'it_it.utf8@euro': 'it_IT.UTF-8', 'it_it@euro': 'it_IT.ISO8859-15', 'italian': 'it_IT.ISO8859-1', 'italian.iso88591': 'it_IT.ISO8859-1', 'iu': 'iu_CA.NUNACOM-8', 'iu_ca': 'iu_CA.NUNACOM-8', 'iu_ca.nunacom8': 'iu_CA.NUNACOM-8', 'iw': 'he_IL.ISO8859-8', 'iw_il': 'he_IL.ISO8859-8', 'iw_il.iso88598': 'he_IL.ISO8859-8', 'ja': 'ja_JP.eucJP', 'ja.jis': 'ja_JP.JIS7', 'ja.sjis': 'ja_JP.SJIS', 'ja_jp': 'ja_JP.eucJP', 'ja_jp.ajec': 'ja_JP.eucJP', 'ja_jp.euc': 'ja_JP.eucJP', 'ja_jp.eucjp': 'ja_JP.eucJP', 'ja_jp.iso-2022-jp': 'ja_JP.JIS7', 'ja_jp.iso2022jp': 'ja_JP.JIS7', 'ja_jp.jis': 'ja_JP.JIS7', 'ja_jp.jis7': 'ja_JP.JIS7', 'ja_jp.mscode': 'ja_JP.SJIS', 'ja_jp.sjis': 'ja_JP.SJIS', 'ja_jp.ujis': 'ja_JP.eucJP', 'japan': 'ja_JP.eucJP', 'japanese': 'ja_JP.eucJP', 'japanese-euc': 'ja_JP.eucJP', 'japanese.euc': 'ja_JP.eucJP', 'japanese.sjis': 'ja_JP.SJIS', 'jp_jp': 'ja_JP.eucJP', 'ka': 'ka_GE.GEORGIAN-ACADEMY', 'ka_ge': 'ka_GE.GEORGIAN-ACADEMY', 'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY', 'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS', 'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY', 'kl': 'kl_GL.ISO8859-1', 'kl_gl': 'kl_GL.ISO8859-1', 'kl_gl.iso88591': 'kl_GL.ISO8859-1', 'kl_gl.iso885915': 'kl_GL.ISO8859-15', 'kl_gl@euro': 'kl_GL.ISO8859-15', 'km_kh': 'km_KH.UTF-8', 'kn_in': 'kn_IN.UTF-8', 'ko': 'ko_KR.eucKR', 'ko_kr': 'ko_KR.eucKR', 'ko_kr.euc': 'ko_KR.eucKR', 'ko_kr.euckr': 'ko_KR.eucKR', 'korean': 'ko_KR.eucKR', 'korean.euc': 'ko_KR.eucKR', 'kw': 'kw_GB.ISO8859-1', 'kw_gb': 'kw_GB.ISO8859-1', 'kw_gb.iso88591': 'kw_GB.ISO8859-1', 'kw_gb.iso885914': 'kw_GB.ISO8859-14', 'kw_gb.iso885915': 'kw_GB.ISO8859-15', 'kw_gb@euro': 'kw_GB.ISO8859-15', 'ky': 'ky_KG.UTF-8', 'ky_kg': 'ky_KG.UTF-8', 'lithuanian': 'lt_LT.ISO8859-13', 'lo': 'lo_LA.MULELAO-1', 'lo_la': 'lo_LA.MULELAO-1', 'lo_la.cp1133': 'lo_LA.IBM-CP1133', 'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133', 'lo_la.mulelao1': 'lo_LA.MULELAO-1', 'lt': 'lt_LT.ISO8859-13', 'lt_lt': 'lt_LT.ISO8859-13', 'lt_lt.iso885913': 'lt_LT.ISO8859-13', 'lt_lt.iso88594': 'lt_LT.ISO8859-4', 'lv': 'lv_LV.ISO8859-13', 'lv_lv': 'lv_LV.ISO8859-13', 'lv_lv.iso885913': 'lv_LV.ISO8859-13', 'lv_lv.iso88594': 'lv_LV.ISO8859-4', 'mi': 'mi_NZ.ISO8859-1', 'mi_nz': 'mi_NZ.ISO8859-1', 'mi_nz.iso88591': 'mi_NZ.ISO8859-1', 'mk': 'mk_MK.ISO8859-5', 'mk_mk': 'mk_MK.ISO8859-5', 'mk_mk.cp1251': 'mk_MK.CP1251', 'mk_mk.iso88595': 'mk_MK.ISO8859-5', 'mk_mk.microsoftcp1251': 'mk_MK.CP1251', 'mr_in': 'mr_IN.UTF-8', 'ms': 'ms_MY.ISO8859-1', 'ms_my': 'ms_MY.ISO8859-1', 'ms_my.iso88591': 'ms_MY.ISO8859-1', 'mt': 'mt_MT.ISO8859-3', 'mt_mt': 'mt_MT.ISO8859-3', 'mt_mt.iso88593': 'mt_MT.ISO8859-3', 'nb': 'nb_NO.ISO8859-1', 'nb_no': 'nb_NO.ISO8859-1', 'nb_no.88591': 'nb_NO.ISO8859-1', 'nb_no.iso88591': 'nb_NO.ISO8859-1', 'nb_no.iso885915': 'nb_NO.ISO8859-15', 'nb_no@euro': 'nb_NO.ISO8859-15', 'nl': 'nl_NL.ISO8859-1', 'nl_be': 'nl_BE.ISO8859-1', 'nl_be.88591': 'nl_BE.ISO8859-1', 'nl_be.iso88591': 'nl_BE.ISO8859-1', 'nl_be.iso885915': 'nl_BE.ISO8859-15', 'nl_be.iso885915@euro': 'nl_BE.ISO8859-15', 'nl_be.utf8@euro': 'nl_BE.UTF-8', 'nl_be@euro': 'nl_BE.ISO8859-15', 'nl_nl': 'nl_NL.ISO8859-1', 'nl_nl.88591': 'nl_NL.ISO8859-1', 'nl_nl.iso88591': 'nl_NL.ISO8859-1', 'nl_nl.iso885915': 'nl_NL.ISO8859-15', 'nl_nl.iso885915@euro': 'nl_NL.ISO8859-15', 'nl_nl.utf8@euro': 'nl_NL.UTF-8', 'nl_nl@euro': 'nl_NL.ISO8859-15', 'nn': 'nn_NO.ISO8859-1', 'nn_no': 'nn_NO.ISO8859-1', 'nn_no.88591': 'nn_NO.ISO8859-1', 'nn_no.iso88591': 'nn_NO.ISO8859-1', 'nn_no.iso885915': 'nn_NO.ISO8859-15', 'nn_no@euro': 'nn_NO.ISO8859-15', 'no': 'no_NO.ISO8859-1', 'no@nynorsk': 'ny_NO.ISO8859-1', 'no_no': 'no_NO.ISO8859-1', 'no_no.88591': 'no_NO.ISO8859-1', 'no_no.iso88591': 'no_NO.ISO8859-1', 'no_no.iso885915': 'no_NO.ISO8859-15', 'no_no@euro': 'no_NO.ISO8859-15', 'norwegian': 'no_NO.ISO8859-1', 'norwegian.iso88591': 'no_NO.ISO8859-1', 'nr': 'nr_ZA.ISO8859-1', 'nr_za': 'nr_ZA.ISO8859-1', 'nr_za.iso88591': 'nr_ZA.ISO8859-1', 'nso': 'nso_ZA.ISO8859-15', 'nso_za': 'nso_ZA.ISO8859-15', 'nso_za.iso885915': 'nso_ZA.ISO8859-15', 'ny': 'ny_NO.ISO8859-1', 'ny_no': 'ny_NO.ISO8859-1', 'ny_no.88591': 'ny_NO.ISO8859-1', 'ny_no.iso88591': 'ny_NO.ISO8859-1', 'ny_no.iso885915': 'ny_NO.ISO8859-15', 'ny_no@euro': 'ny_NO.ISO8859-15', 'nynorsk': 'nn_NO.ISO8859-1', 'oc': 'oc_FR.ISO8859-1', 'oc_fr': 'oc_FR.ISO8859-1', 'oc_fr.iso88591': 'oc_FR.ISO8859-1', 'oc_fr.iso885915': 'oc_FR.ISO8859-15', 'oc_fr@euro': 'oc_FR.ISO8859-15', 'pa_in': 'pa_IN.UTF-8', 'pd': 'pd_US.ISO8859-1', 'pd_de': 'pd_DE.ISO8859-1', 'pd_de.iso88591': 'pd_DE.ISO8859-1', 'pd_de.iso885915': 'pd_DE.ISO8859-15', 'pd_de@euro': 'pd_DE.ISO8859-15', 'pd_us': 'pd_US.ISO8859-1', 'pd_us.iso88591': 'pd_US.ISO8859-1', 'pd_us.iso885915': 'pd_US.ISO8859-15', 'pd_us@euro': 'pd_US.ISO8859-15', 'ph': 'ph_PH.ISO8859-1', 'ph_ph': 'ph_PH.ISO8859-1', 'ph_ph.iso88591': 'ph_PH.ISO8859-1', 'pl': 'pl_PL.ISO8859-2', 'pl_pl': 'pl_PL.ISO8859-2', 'pl_pl.iso88592': 'pl_PL.ISO8859-2', 'polish': 'pl_PL.ISO8859-2', 'portuguese': 'pt_PT.ISO8859-1', 'portuguese.iso88591': 'pt_PT.ISO8859-1', 'portuguese_brazil': 'pt_BR.ISO8859-1', 'portuguese_brazil.8859': 'pt_BR.ISO8859-1', 'posix': 'C', 'posix-utf2': 'C', 'pp': 'pp_AN.ISO8859-1', 'pp_an': 'pp_AN.ISO8859-1', 'pp_an.iso88591': 'pp_AN.ISO8859-1', 'pt': 'pt_PT.ISO8859-1', 'pt_br': 'pt_BR.ISO8859-1', 'pt_br.88591': 'pt_BR.ISO8859-1', 'pt_br.iso88591': 'pt_BR.ISO8859-1', 'pt_br.iso885915': 'pt_BR.ISO8859-15', 'pt_br@euro': 'pt_BR.ISO8859-15', 'pt_pt': 'pt_PT.ISO8859-1', 'pt_pt.88591': 'pt_PT.ISO8859-1', 'pt_pt.iso88591': 'pt_PT.ISO8859-1', 'pt_pt.iso885915': 'pt_PT.ISO8859-15', 'pt_pt.iso885915@euro': 'pt_PT.ISO8859-15', 'pt_pt.utf8@euro': 'pt_PT.UTF-8', 'pt_pt@euro': 'pt_PT.ISO8859-15', 'ro': 'ro_RO.ISO8859-2', 'ro_ro': 'ro_RO.ISO8859-2', 'ro_ro.iso88592': 'ro_RO.ISO8859-2', 'romanian': 'ro_RO.ISO8859-2', 'ru': 'ru_RU.ISO8859-5', 'ru_ru': 'ru_RU.ISO8859-5', 'ru_ru.cp1251': 'ru_RU.CP1251', 'ru_ru.iso88595': 'ru_RU.ISO8859-5', 'ru_ru.koi8r': 'ru_RU.KOI8-R', 'ru_ru.microsoftcp1251': 'ru_RU.CP1251', 'ru_ua': 'ru_UA.KOI8-U', 'ru_ua.cp1251': 'ru_UA.CP1251', 'ru_ua.koi8u': 'ru_UA.KOI8-U', 'ru_ua.microsoftcp1251': 'ru_UA.CP1251', 'rumanian': 'ro_RO.ISO8859-2', 'russian': 'ru_RU.ISO8859-5', 'rw': 'rw_RW.ISO8859-1', 'rw_rw': 'rw_RW.ISO8859-1', 'rw_rw.iso88591': 'rw_RW.ISO8859-1', 'se_no': 'se_NO.UTF-8', 'serbocroatian': 'sr_CS.ISO8859-2', 'sh': 'sr_CS.ISO8859-2', 'sh_hr': 'sh_HR.ISO8859-2', 'sh_hr.iso88592': 'hr_HR.ISO8859-2', 'sh_sp': 'sr_CS.ISO8859-2', 'sh_yu': 'sr_CS.ISO8859-2', 'si': 'si_LK.UTF-8', 'si_lk': 'si_LK.UTF-8', 'sinhala': 'si_LK.UTF-8', 'sk': 'sk_SK.ISO8859-2', 'sk_sk': 'sk_SK.ISO8859-2', 'sk_sk.iso88592': 'sk_SK.ISO8859-2', 'sl': 'sl_SI.ISO8859-2', 'sl_cs': 'sl_CS.ISO8859-2', 'sl_si': 'sl_SI.ISO8859-2', 'sl_si.iso88592': 'sl_SI.ISO8859-2', 'slovak': 'sk_SK.ISO8859-2', 'slovene': 'sl_SI.ISO8859-2', 'slovenian': 'sl_SI.ISO8859-2', 'sp': 'sr_CS.ISO8859-5', 'sp_yu': 'sr_CS.ISO8859-5', 'spanish': 'es_ES.ISO8859-1', 'spanish.iso88591': 'es_ES.ISO8859-1', 'spanish_spain': 'es_ES.ISO8859-1', 'spanish_spain.8859': 'es_ES.ISO8859-1', 'sq': 'sq_AL.ISO8859-2', 'sq_al': 'sq_AL.ISO8859-2', 'sq_al.iso88592': 'sq_AL.ISO8859-2', 'sr': 'sr_CS.ISO8859-5', 'sr@cyrillic': 'sr_CS.ISO8859-5', 'sr@latn': 'sr_CS.ISO8859-2', 'sr_cs.iso88592': 'sr_CS.ISO8859-2', 'sr_cs.iso88592@latn': 'sr_CS.ISO8859-2', 'sr_cs.iso88595': 'sr_CS.ISO8859-5', 'sr_cs.utf8@latn': 'sr_CS.UTF-8', 'sr_cs@latn': 'sr_CS.ISO8859-2', 'sr_sp': 'sr_CS.ISO8859-2', 'sr_yu': 'sr_CS.ISO8859-5', 'sr_yu.cp1251@cyrillic': 'sr_CS.CP1251', 'sr_yu.iso88592': 'sr_CS.ISO8859-2', 'sr_yu.iso88595': 'sr_CS.ISO8859-5', 'sr_yu.iso88595@cyrillic': 'sr_CS.ISO8859-5', 'sr_yu.microsoftcp1251@cyrillic': 'sr_CS.CP1251', 'sr_yu.utf8@cyrillic': 'sr_CS.UTF-8', 'sr_yu@cyrillic': 'sr_CS.ISO8859-5', 'ss': 'ss_ZA.ISO8859-1', 'ss_za': 'ss_ZA.ISO8859-1', 'ss_za.iso88591': 'ss_ZA.ISO8859-1', 'st': 'st_ZA.ISO8859-1', 'st_za': 'st_ZA.ISO8859-1', 'st_za.iso88591': 'st_ZA.ISO8859-1', 'sv': 'sv_SE.ISO8859-1', 'sv_fi': 'sv_FI.ISO8859-1', 'sv_fi.iso88591': 'sv_FI.ISO8859-1', 'sv_fi.iso885915': 'sv_FI.ISO8859-15', 'sv_fi.iso885915@euro': 'sv_FI.ISO8859-15', 'sv_fi.utf8@euro': 'sv_FI.UTF-8', 'sv_fi@euro': 'sv_FI.ISO8859-15', 'sv_se': 'sv_SE.ISO8859-1', 'sv_se.88591': 'sv_SE.ISO8859-1', 'sv_se.iso88591': 'sv_SE.ISO8859-1', 'sv_se.iso885915': 'sv_SE.ISO8859-15', 'sv_se@euro': 'sv_SE.ISO8859-15', 'swedish': 'sv_SE.ISO8859-1', 'swedish.iso88591': 'sv_SE.ISO8859-1', 'ta': 'ta_IN.TSCII-0', 'ta_in': 'ta_IN.TSCII-0', 'ta_in.tscii': 'ta_IN.TSCII-0', 'ta_in.tscii0': 'ta_IN.TSCII-0', 'tg': 'tg_TJ.KOI8-C', 'tg_tj': 'tg_TJ.KOI8-C', 'tg_tj.koi8c': 'tg_TJ.KOI8-C', 'th': 'th_TH.ISO8859-11', 'th_th': 'th_TH.ISO8859-11', 'th_th.iso885911': 'th_TH.ISO8859-11', 'th_th.tactis': 'th_TH.TIS620', 'th_th.tis620': 'th_TH.TIS620', 'thai': 'th_TH.ISO8859-11', 'tl': 'tl_PH.ISO8859-1', 'tl_ph': 'tl_PH.ISO8859-1', 'tl_ph.iso88591': 'tl_PH.ISO8859-1', 'tn': 'tn_ZA.ISO8859-15', 'tn_za': 'tn_ZA.ISO8859-15', 'tn_za.iso885915': 'tn_ZA.ISO8859-15', 'tr': 'tr_TR.ISO8859-9', 'tr_tr': 'tr_TR.ISO8859-9', 'tr_tr.iso88599': 'tr_TR.ISO8859-9', 'ts': 'ts_ZA.ISO8859-1', 'ts_za': 'ts_ZA.ISO8859-1', 'ts_za.iso88591': 'ts_ZA.ISO8859-1', 'tt': 'tt_RU.TATAR-CYR', 'tt_ru': 'tt_RU.TATAR-CYR', 'tt_ru.koi8c': 'tt_RU.KOI8-C', 'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR', 'turkish': 'tr_TR.ISO8859-9', 'turkish.iso88599': 'tr_TR.ISO8859-9', 'uk': 'uk_UA.KOI8-U', 'uk_ua': 'uk_UA.KOI8-U', 'uk_ua.cp1251': 'uk_UA.CP1251', 'uk_ua.iso88595': 'uk_UA.ISO8859-5', 'uk_ua.koi8u': 'uk_UA.KOI8-U', 'uk_ua.microsoftcp1251': 'uk_UA.CP1251', 'univ': 'en_US.utf', 'universal': 'en_US.utf', 'universal.utf8@ucs4': 'en_US.UTF-8', 'ur': 'ur_PK.CP1256', 'ur_pk': 'ur_PK.CP1256', 'ur_pk.cp1256': 'ur_PK.CP1256', 'ur_pk.microsoftcp1256': 'ur_PK.CP1256', 'uz': 'uz_UZ.UTF-8', 'uz_uz': 'uz_UZ.UTF-8', 'uz_uz.iso88591': 'uz_UZ.ISO8859-1', 'uz_uz.utf8@cyrillic': 'uz_UZ.UTF-8', 'uz_uz@cyrillic': 'uz_UZ.UTF-8', 've': 've_ZA.UTF-8', 've_za': 've_ZA.UTF-8', 'vi': 'vi_VN.TCVN', 'vi_vn': 'vi_VN.TCVN', 'vi_vn.tcvn': 'vi_VN.TCVN', 'vi_vn.tcvn5712': 'vi_VN.TCVN', 'vi_vn.viscii': 'vi_VN.VISCII', 'vi_vn.viscii111': 'vi_VN.VISCII', 'wa': 'wa_BE.ISO8859-1', 'wa_be': 'wa_BE.ISO8859-1', 'wa_be.iso88591': 'wa_BE.ISO8859-1', 'wa_be.iso885915': 'wa_BE.ISO8859-15', 'wa_be.iso885915@euro': 'wa_BE.ISO8859-15', 'wa_be@euro': 'wa_BE.ISO8859-15', 'xh': 'xh_ZA.ISO8859-1', 'xh_za': 'xh_ZA.ISO8859-1', 'xh_za.iso88591': 'xh_ZA.ISO8859-1', 'yi': 'yi_US.CP1255', 'yi_us': 'yi_US.CP1255', 'yi_us.cp1255': 'yi_US.CP1255', 'yi_us.microsoftcp1255': 'yi_US.CP1255', 'zh': 'zh_CN.eucCN', 'zh_cn': 'zh_CN.gb2312', 'zh_cn.big5': 'zh_TW.big5', 'zh_cn.euc': 'zh_CN.eucCN', 'zh_cn.gb18030': 'zh_CN.gb18030', 'zh_cn.gb2312': 'zh_CN.gb2312', 'zh_cn.gbk': 'zh_CN.gbk', 'zh_hk': 'zh_HK.big5hkscs', 'zh_hk.big5': 'zh_HK.big5', 'zh_hk.big5hkscs': 'zh_HK.big5hkscs', 'zh_tw': 'zh_TW.big5', 'zh_tw.big5': 'zh_TW.big5', 'zh_tw.euc': 'zh_TW.eucTW', 'zh_tw.euctw': 'zh_TW.eucTW', 'zu': 'zu_ZA.ISO8859-1', 'zu_za': 'zu_ZA.ISO8859-1', 'zu_za.iso88591': 'zu_ZA.ISO8859-1', } # # This maps Windows language identifiers to locale strings. # # This list has been updated from # http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp # to include every locale up to Windows XP. # # NOTE: this mapping is incomplete. If your language is missing, please # submit a bug report to Python bug manager, which you can find via: # http://www.python.org/dev/ # Make sure you include the missing language identifier and the suggested # locale code. # windows_locale = { 0x0436: "af_ZA", # Afrikaans 0x041c: "sq_AL", # Albanian 0x0401: "ar_SA", # Arabic - Saudi Arabia 0x0801: "ar_IQ", # Arabic - Iraq 0x0c01: "ar_EG", # Arabic - Egypt 0x1001: "ar_LY", # Arabic - Libya 0x1401: "ar_DZ", # Arabic - Algeria 0x1801: "ar_MA", # Arabic - Morocco 0x1c01: "ar_TN", # Arabic - Tunisia 0x2001: "ar_OM", # Arabic - Oman 0x2401: "ar_YE", # Arabic - Yemen 0x2801: "ar_SY", # Arabic - Syria 0x2c01: "ar_JO", # Arabic - Jordan 0x3001: "ar_LB", # Arabic - Lebanon 0x3401: "ar_KW", # Arabic - Kuwait 0x3801: "ar_AE", # Arabic - United Arab Emirates 0x3c01: "ar_BH", # Arabic - Bahrain 0x4001: "ar_QA", # Arabic - Qatar 0x042b: "hy_AM", # Armenian 0x042c: "az_AZ", # Azeri Latin 0x082c: "az_AZ", # Azeri - Cyrillic 0x042d: "eu_ES", # Basque 0x0423: "be_BY", # Belarusian 0x0445: "bn_IN", # Begali 0x201a: "bs_BA", # Bosnian 0x141a: "bs_BA", # Bosnian - Cyrillic 0x047e: "br_FR", # Breton - France 0x0402: "bg_BG", # Bulgarian 0x0403: "ca_ES", # Catalan 0x0004: "zh_CHS",# Chinese - Simplified 0x0404: "zh_TW", # Chinese - Taiwan 0x0804: "zh_CN", # Chinese - PRC 0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R. 0x1004: "zh_SG", # Chinese - Singapore 0x1404: "zh_MO", # Chinese - Macao S.A.R. 0x7c04: "zh_CHT",# Chinese - Traditional 0x041a: "hr_HR", # Croatian 0x101a: "hr_BA", # Croatian - Bosnia 0x0405: "cs_CZ", # Czech 0x0406: "da_DK", # Danish 0x048c: "gbz_AF",# Dari - Afghanistan 0x0465: "div_MV",# Divehi - Maldives 0x0413: "nl_NL", # Dutch - The Netherlands 0x0813: "nl_BE", # Dutch - Belgium 0x0409: "en_US", # English - United States 0x0809: "en_GB", # English - United Kingdom 0x0c09: "en_AU", # English - Australia 0x1009: "en_CA", # English - Canada 0x1409: "en_NZ", # English - New Zealand 0x1809: "en_IE", # English - Ireland 0x1c09: "en_ZA", # English - South Africa 0x2009: "en_JA", # English - Jamaica 0x2409: "en_CB", # English - Carribbean 0x2809: "en_BZ", # English - Belize 0x2c09: "en_TT", # English - Trinidad 0x3009: "en_ZW", # English - Zimbabwe 0x3409: "en_PH", # English - Phillippines 0x0425: "et_EE", # Estonian 0x0438: "fo_FO", # Faroese 0x0464: "fil_PH",# Filipino 0x040b: "fi_FI", # Finnish 0x040c: "fr_FR", # French - France 0x080c: "fr_BE", # French - Belgium 0x0c0c: "fr_CA", # French - Canada 0x100c: "fr_CH", # French - Switzerland 0x140c: "fr_LU", # French - Luxembourg 0x180c: "fr_MC", # French - Monaco 0x0462: "fy_NL", # Frisian - Netherlands 0x0456: "gl_ES", # Galician 0x0437: "ka_GE", # Georgian 0x0407: "de_DE", # German - Germany 0x0807: "de_CH", # German - Switzerland 0x0c07: "de_AT", # German - Austria 0x1007: "de_LU", # German - Luxembourg 0x1407: "de_LI", # German - Liechtenstein 0x0408: "el_GR", # Greek 0x0447: "gu_IN", # Gujarati 0x040d: "he_IL", # Hebrew 0x0439: "hi_IN", # Hindi 0x040e: "hu_HU", # Hungarian 0x040f: "is_IS", # Icelandic 0x0421: "id_ID", # Indonesian 0x045d: "iu_CA", # Inuktitut 0x085d: "iu_CA", # Inuktitut - Latin 0x083c: "ga_IE", # Irish - Ireland 0x0434: "xh_ZA", # Xhosa - South Africa 0x0435: "zu_ZA", # Zulu 0x0410: "it_IT", # Italian - Italy 0x0810: "it_CH", # Italian - Switzerland 0x0411: "ja_JP", # Japanese 0x044b: "kn_IN", # Kannada - India 0x043f: "kk_KZ", # Kazakh 0x0457: "kok_IN",# Konkani 0x0412: "ko_KR", # Korean 0x0440: "ky_KG", # Kyrgyz 0x0426: "lv_LV", # Latvian 0x0427: "lt_LT", # Lithuanian 0x046e: "lb_LU", # Luxembourgish 0x042f: "mk_MK", # FYRO Macedonian 0x043e: "ms_MY", # Malay - Malaysia 0x083e: "ms_BN", # Malay - Brunei 0x044c: "ml_IN", # Malayalam - India 0x043a: "mt_MT", # Maltese 0x0481: "mi_NZ", # Maori 0x047a: "arn_CL",# Mapudungun 0x044e: "mr_IN", # Marathi 0x047c: "moh_CA",# Mohawk - Canada 0x0450: "mn_MN", # Mongolian 0x0461: "ne_NP", # Nepali 0x0414: "nb_NO", # Norwegian - Bokmal 0x0814: "nn_NO", # Norwegian - Nynorsk 0x0482: "oc_FR", # Occitan - France 0x0448: "or_IN", # Oriya - India 0x0463: "ps_AF", # Pashto - Afghanistan 0x0429: "fa_IR", # Persian 0x0415: "pl_PL", # Polish 0x0416: "pt_BR", # Portuguese - Brazil 0x0816: "pt_PT", # Portuguese - Portugal 0x0446: "pa_IN", # Punjabi 0x046b: "quz_BO",# Quechua (Bolivia) 0x086b: "quz_EC",# Quechua (Ecuador) 0x0c6b: "quz_PE",# Quechua (Peru) 0x0418: "ro_RO", # Romanian - Romania 0x0417: "rm_CH", # Raeto-Romanese 0x0419: "ru_RU", # Russian 0x243b: "smn_FI",# Sami Finland 0x103b: "smj_NO",# Sami Norway 0x143b: "smj_SE",# Sami Sweden 0x043b: "se_NO", # Sami Northern Norway 0x083b: "se_SE", # Sami Northern Sweden 0x0c3b: "se_FI", # Sami Northern Finland 0x203b: "sms_FI",# Sami Skolt 0x183b: "sma_NO",# Sami Southern Norway 0x1c3b: "sma_SE",# Sami Southern Sweden 0x044f: "sa_IN", # Sanskrit 0x0c1a: "sr_SP", # Serbian - Cyrillic 0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic 0x081a: "sr_SP", # Serbian - Latin 0x181a: "sr_BA", # Serbian - Bosnia Latin 0x046c: "ns_ZA", # Northern Sotho 0x0432: "tn_ZA", # Setswana - Southern Africa 0x041b: "sk_SK", # Slovak 0x0424: "sl_SI", # Slovenian 0x040a: "es_ES", # Spanish - Spain 0x080a: "es_MX", # Spanish - Mexico 0x0c0a: "es_ES", # Spanish - Spain (Modern) 0x100a: "es_GT", # Spanish - Guatemala 0x140a: "es_CR", # Spanish - Costa Rica 0x180a: "es_PA", # Spanish - Panama 0x1c0a: "es_DO", # Spanish - Dominican Republic 0x200a: "es_VE", # Spanish - Venezuela 0x240a: "es_CO", # Spanish - Colombia 0x280a: "es_PE", # Spanish - Peru 0x2c0a: "es_AR", # Spanish - Argentina 0x300a: "es_EC", # Spanish - Ecuador 0x340a: "es_CL", # Spanish - Chile 0x380a: "es_UR", # Spanish - Uruguay 0x3c0a: "es_PY", # Spanish - Paraguay 0x400a: "es_BO", # Spanish - Bolivia 0x440a: "es_SV", # Spanish - El Salvador 0x480a: "es_HN", # Spanish - Honduras 0x4c0a: "es_NI", # Spanish - Nicaragua 0x500a: "es_PR", # Spanish - Puerto Rico 0x0441: "sw_KE", # Swahili 0x041d: "sv_SE", # Swedish - Sweden 0x081d: "sv_FI", # Swedish - Finland 0x045a: "syr_SY",# Syriac 0x0449: "ta_IN", # Tamil 0x0444: "tt_RU", # Tatar 0x044a: "te_IN", # Telugu 0x041e: "th_TH", # Thai 0x041f: "tr_TR", # Turkish 0x0422: "uk_UA", # Ukrainian 0x0420: "ur_PK", # Urdu 0x0820: "ur_IN", # Urdu - India 0x0443: "uz_UZ", # Uzbek - Latin 0x0843: "uz_UZ", # Uzbek - Cyrillic 0x042a: "vi_VN", # Vietnamese 0x0452: "cy_GB", # Welsh } def _print_locale(): """ Test function. """ categories = {} def _init_categories(categories=categories): for k,v in globals().items(): if k[:3] == 'LC_': categories[k] = v _init_categories() del categories['LC_ALL'] print 'Locale defaults as determined by getdefaultlocale():' print '-'*72 lang, enc = getdefaultlocale() print 'Language: ', lang or '(undefined)' print 'Encoding: ', enc or '(undefined)' print print 'Locale settings on startup:' print '-'*72 for name,category in categories.items(): print name, '...' lang, enc = getlocale(category) print ' Language: ', lang or '(undefined)' print ' Encoding: ', enc or '(undefined)' print print print 'Locale settings after calling resetlocale():' print '-'*72 resetlocale() for name,category in categories.items(): print name, '...' lang, enc = getlocale(category) print ' Language: ', lang or '(undefined)' print ' Encoding: ', enc or '(undefined)' print try: setlocale(LC_ALL, "") except: print 'NOTE:' print 'setlocale(LC_ALL, "") does not support the default locale' print 'given in the OS environment variables.' else: print print 'Locale settings after calling setlocale(LC_ALL, ""):' print '-'*72 for name,category in categories.items(): print name, '...' lang, enc = getlocale(category) print ' Language: ', lang or '(undefined)' print ' Encoding: ', enc or '(undefined)' print ### try: LC_MESSAGES except NameError: pass else: __all__.append("LC_MESSAGES") if __name__=='__main__': print 'Locale aliasing:' print _print_locale() print print 'Number formatting:' print _test() feedgenerator-1.9/.tox/py26/lib/python2.6/ntpath.py0000644000076500000240000004253012612565536021622 0ustar jmstaff00000000000000# Module 'ntpath' -- common operations on WinNT/Win95 pathnames """Common pathname manipulations, WindowsNT/95 version. Instead of importing this module directly, import os and refer to this module as os.path. """ import os import sys import stat import genericpath import warnings from genericpath import * __all__ = ["normcase","isabs","join","splitdrive","split","splitext", "basename","dirname","commonprefix","getsize","getmtime", "getatime","getctime", "islink","exists","lexists","isdir","isfile", "ismount","walk","expanduser","expandvars","normpath","abspath", "splitunc","curdir","pardir","sep","pathsep","defpath","altsep", "extsep","devnull","realpath","supports_unicode_filenames","relpath"] # strings representing various path-related bits and pieces curdir = '.' pardir = '..' extsep = '.' sep = '\\' pathsep = ';' altsep = '/' defpath = '.;C:\\bin' if 'ce' in sys.builtin_module_names: defpath = '\\Windows' elif 'os2' in sys.builtin_module_names: # OS/2 w/ VACPP altsep = '/' devnull = 'nul' # Normalize the case of a pathname and map slashes to backslashes. # Other normalizations (such as optimizing '../' away) are not done # (this is done by normpath). def normcase(s): """Normalize case of pathname. Makes all characters lowercase and all slashes into backslashes.""" return s.replace("/", "\\").lower() # Return whether a path is absolute. # Trivial in Posix, harder on the Mac or MS-DOS. # For DOS it is absolute if it starts with a slash or backslash (current # volume), or if a pathname after the volume letter and colon / UNC resource # starts with a slash or backslash. def isabs(s): """Test whether a path is absolute""" s = splitdrive(s)[1] return s != '' and s[:1] in '/\\' # Join two (or more) paths. def join(a, *p): """Join two or more pathname components, inserting "\\" as needed. If any component is an absolute path, all previous path components will be discarded.""" path = a for b in p: b_wins = 0 # set to 1 iff b makes path irrelevant if path == "": b_wins = 1 elif isabs(b): # This probably wipes out path so far. However, it's more # complicated if path begins with a drive letter: # 1. join('c:', '/a') == 'c:/a' # 2. join('c:/', '/a') == 'c:/a' # But # 3. join('c:/a', '/b') == '/b' # 4. join('c:', 'd:/') = 'd:/' # 5. join('c:/', 'd:/') = 'd:/' if path[1:2] != ":" or b[1:2] == ":": # Path doesn't start with a drive letter, or cases 4 and 5. b_wins = 1 # Else path has a drive letter, and b doesn't but is absolute. elif len(path) > 3 or (len(path) == 3 and path[-1] not in "/\\"): # case 3 b_wins = 1 if b_wins: path = b else: # Join, and ensure there's a separator. assert len(path) > 0 if path[-1] in "/\\": if b and b[0] in "/\\": path += b[1:] else: path += b elif path[-1] == ":": path += b elif b: if b[0] in "/\\": path += b else: path += "\\" + b else: # path is not empty and does not end with a backslash, # but b is empty; since, e.g., split('a/') produces # ('a', ''), it's best if join() adds a backslash in # this case. path += '\\' return path # Split a path in a drive specification (a drive letter followed by a # colon) and the path specification. # It is always true that drivespec + pathspec == p def splitdrive(p): """Split a pathname into drive and path specifiers. Returns a 2-tuple "(drive,path)"; either part may be empty""" if p[1:2] == ':': return p[0:2], p[2:] return '', p # Parse UNC paths def splitunc(p): """Split a pathname into UNC mount point and relative path specifiers. Return a 2-tuple (unc, rest); either part may be empty. If unc is not empty, it has the form '//host/mount' (or similar using backslashes). unc+rest is always the input path. Paths containing drive letters never have an UNC part. """ if p[1:2] == ':': return '', p # Drive letter present firstTwo = p[0:2] if firstTwo == '//' or firstTwo == '\\\\': # is a UNC path: # vvvvvvvvvvvvvvvvvvvv equivalent to drive letter # \\machine\mountpoint\directories... # directory ^^^^^^^^^^^^^^^ normp = normcase(p) index = normp.find('\\', 2) if index == -1: ##raise RuntimeError, 'illegal UNC path: "' + p + '"' return ("", p) index = normp.find('\\', index + 1) if index == -1: index = len(p) return p[:index], p[index:] return '', p # Split a path in head (everything up to the last '/') and tail (the # rest). After the trailing '/' is stripped, the invariant # join(head, tail) == p holds. # The resulting head won't end in '/' unless it is the root. def split(p): """Split a pathname. Return tuple (head, tail) where tail is everything after the final slash. Either part may be empty.""" d, p = splitdrive(p) # set i to index beyond p's last slash i = len(p) while i and p[i-1] not in '/\\': i = i - 1 head, tail = p[:i], p[i:] # now tail has no slashes # remove trailing slashes from head, unless it's all slashes head2 = head while head2 and head2[-1] in '/\\': head2 = head2[:-1] head = head2 or head return d + head, tail # Split a path in root and extension. # The extension is everything starting at the last dot in the last # pathname component; the root is everything before that. # It is always true that root + ext == p. def splitext(p): return genericpath._splitext(p, sep, altsep, extsep) splitext.__doc__ = genericpath._splitext.__doc__ # Return the tail (basename) part of a path. def basename(p): """Returns the final component of a pathname""" return split(p)[1] # Return the head (dirname) part of a path. def dirname(p): """Returns the directory component of a pathname""" return split(p)[0] # Is a path a symbolic link? # This will always return false on systems where posix.lstat doesn't exist. def islink(path): """Test for symbolic link. On WindowsNT/95 and OS/2 always returns false """ return False # alias exists to lexists lexists = exists # Is a path a mount point? Either a root (with or without drive letter) # or an UNC path with at most a / or \ after the mount point. def ismount(path): """Test whether a path is a mount point (defined as root of drive)""" unc, rest = splitunc(path) if unc: return rest in ("", "/", "\\") p = splitdrive(path)[1] return len(p) == 1 and p[0] in '/\\' # Directory tree walk. # For each directory under top (including top itself, but excluding # '.' and '..'), func(arg, dirname, filenames) is called, where # dirname is the name of the directory and filenames is the list # of files (and subdirectories etc.) in the directory. # The func may modify the filenames list, to implement a filter, # or to impose a different order of visiting. def walk(top, func, arg): """Directory tree walk with callback function. For each directory in the directory tree rooted at top (including top itself, but excluding '.' and '..'), call func(arg, dirname, fnames). dirname is the name of the directory, and fnames a list of the names of the files and subdirectories in dirname (excluding '.' and '..'). func may modify the fnames list in-place (e.g. via del or slice assignment), and walk will only recurse into the subdirectories whose names remain in fnames; this can be used to implement a filter, or to impose a specific order of visiting. No semantics are defined for, or required of, arg, beyond that arg is always passed to func. It can be used, e.g., to pass a filename pattern, or a mutable object designed to accumulate statistics. Passing None for arg is common.""" warnings.warnpy3k("In 3.x, os.path.walk is removed in favor of os.walk.", stacklevel=2) try: names = os.listdir(top) except os.error: return func(arg, top, names) for name in names: name = join(top, name) if isdir(name): walk(name, func, arg) # Expand paths beginning with '~' or '~user'. # '~' means $HOME; '~user' means that user's home directory. # If the path doesn't begin with '~', or if the user or $HOME is unknown, # the path is returned unchanged (leaving error reporting to whatever # function is called with the expanded path as argument). # See also module 'glob' for expansion of *, ? and [...] in pathnames. # (A function should also be defined to do full *sh-style environment # variable expansion.) def expanduser(path): """Expand ~ and ~user constructs. If user or $HOME is unknown, do nothing.""" if path[:1] != '~': return path i, n = 1, len(path) while i < n and path[i] not in '/\\': i = i + 1 if 'HOME' in os.environ: userhome = os.environ['HOME'] elif 'USERPROFILE' in os.environ: userhome = os.environ['USERPROFILE'] elif not 'HOMEPATH' in os.environ: return path else: try: drive = os.environ['HOMEDRIVE'] except KeyError: drive = '' userhome = join(drive, os.environ['HOMEPATH']) if i != 1: #~user userhome = join(dirname(userhome), path[1:i]) return userhome + path[i:] # Expand paths containing shell variable substitutions. # The following rules apply: # - no expansion within single quotes # - '$$' is translated into '$' # - '%%' is translated into '%' if '%%' are not seen in %var1%%var2% # - ${varname} is accepted. # - $varname is accepted. # - %varname% is accepted. # - varnames can be made out of letters, digits and the characters '_-' # (though is not verifed in the ${varname} and %varname% cases) # XXX With COMMAND.COM you can use any characters in a variable name, # XXX except '^|<>='. def expandvars(path): """Expand shell variables of the forms $var, ${var} and %var%. Unknown variables are left unchanged.""" if '$' not in path and '%' not in path: return path import string varchars = string.ascii_letters + string.digits + '_-' res = '' index = 0 pathlen = len(path) while index < pathlen: c = path[index] if c == '\'': # no expansion within single quotes path = path[index + 1:] pathlen = len(path) try: index = path.index('\'') res = res + '\'' + path[:index + 1] except ValueError: res = res + path index = pathlen - 1 elif c == '%': # variable or '%' if path[index + 1:index + 2] == '%': res = res + c index = index + 1 else: path = path[index+1:] pathlen = len(path) try: index = path.index('%') except ValueError: res = res + '%' + path index = pathlen - 1 else: var = path[:index] if var in os.environ: res = res + os.environ[var] else: res = res + '%' + var + '%' elif c == '$': # variable or '$$' if path[index + 1:index + 2] == '$': res = res + c index = index + 1 elif path[index + 1:index + 2] == '{': path = path[index+2:] pathlen = len(path) try: index = path.index('}') var = path[:index] if var in os.environ: res = res + os.environ[var] else: res = res + '${' + var + '}' except ValueError: res = res + '${' + path index = pathlen - 1 else: var = '' index = index + 1 c = path[index:index + 1] while c != '' and c in varchars: var = var + c index = index + 1 c = path[index:index + 1] if var in os.environ: res = res + os.environ[var] else: res = res + '$' + var if c != '': index = index - 1 else: res = res + c index = index + 1 return res # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A\B. # Previously, this function also truncated pathnames to 8+3 format, # but as this module is called "ntpath", that's obviously wrong! def normpath(path): """Normalize path, eliminating double slashes, etc.""" # Preserve unicode (if path is unicode) backslash, dot = (u'\\', u'.') if isinstance(path, unicode) else ('\\', '.') if path.startswith(('\\\\.\\', '\\\\?\\')): # in the case of paths with these prefixes: # \\.\ -> device names # \\?\ -> literal paths # do not do any normalization, but return the path unchanged return path path = path.replace("/", "\\") prefix, path = splitdrive(path) # We need to be careful here. If the prefix is empty, and the path starts # with a backslash, it could either be an absolute path on the current # drive (\dir1\dir2\file) or a UNC filename (\\server\mount\dir1\file). It # is therefore imperative NOT to collapse multiple backslashes blindly in # that case. # The code below preserves multiple backslashes when there is no drive # letter. This means that the invalid filename \\\a\b is preserved # unchanged, where a\\\b is normalised to a\b. It's not clear that there # is any better behaviour for such edge cases. if prefix == '': # No drive letter - preserve initial backslashes while path[:1] == "\\": prefix = prefix + backslash path = path[1:] else: # We have a drive letter - collapse initial backslashes if path.startswith("\\"): prefix = prefix + backslash path = path.lstrip("\\") comps = path.split("\\") i = 0 while i < len(comps): if comps[i] in ('.', ''): del comps[i] elif comps[i] == '..': if i > 0 and comps[i-1] != '..': del comps[i-1:i+1] i -= 1 elif i == 0 and prefix.endswith("\\"): del comps[i] else: i += 1 else: i += 1 # If the path is now empty, substitute '.' if not prefix and not comps: comps.append(dot) return prefix + backslash.join(comps) # Return an absolute path. try: from nt import _getfullpathname except ImportError: # not running on Windows - mock up something sensible def abspath(path): """Return the absolute version of a path.""" if not isabs(path): if isinstance(path, unicode): cwd = os.getcwdu() else: cwd = os.getcwd() path = join(cwd, path) return normpath(path) else: # use native Windows method on Windows def abspath(path): """Return the absolute version of a path.""" if path: # Empty path must return current working directory. try: path = _getfullpathname(path) except WindowsError: pass # Bad path - return unchanged. elif isinstance(path, unicode): path = os.getcwdu() else: path = os.getcwd() return normpath(path) # realpath is a no-op on systems without islink support realpath = abspath # Win9x family and earlier have no Unicode filename support. supports_unicode_filenames = (hasattr(sys, "getwindowsversion") and sys.getwindowsversion()[3] >= 2) def relpath(path, start=curdir): """Return a relative version of a path""" if not path: raise ValueError("no path specified") start_list = abspath(start).split(sep) path_list = abspath(path).split(sep) if start_list[0].lower() != path_list[0].lower(): unc_path, rest = splitunc(path) unc_start, rest = splitunc(start) if bool(unc_path) ^ bool(unc_start): raise ValueError("Cannot mix UNC and non-UNC paths (%s and %s)" % (path, start)) else: raise ValueError("path is on drive %s, start on drive %s" % (path_list[0], start_list[0])) # Work out how much of the filepath is shared by start and path. for i in range(min(len(start_list), len(path_list))): if start_list[i].lower() != path_list[i].lower(): break else: i += 1 rel_list = [pardir] * (len(start_list)-i) + path_list[i:] if not rel_list: return curdir return join(*rel_list) feedgenerator-1.9/.tox/py26/lib/python2.6/os.py0000644000076500000240000006233712612565536020754 0ustar jmstaff00000000000000r"""OS routines for Mac, NT, or Posix depending on what system we're on. This exports: - all functions from posix, nt, os2, or ce, e.g. unlink, stat, etc. - os.path is one of the modules posixpath, or ntpath - os.name is 'posix', 'nt', 'os2', 'ce' or 'riscos' - os.curdir is a string representing the current directory ('.' or ':') - os.pardir is a string representing the parent directory ('..' or '::') - os.sep is the (or a most common) pathname separator ('/' or ':' or '\\') - os.extsep is the extension separator ('.' or '/') - os.altsep is the alternate pathname separator (None or '/') - os.pathsep is the component separator used in $PATH etc - os.linesep is the line separator in text files ('\r' or '\n' or '\r\n') - os.defpath is the default search path for executables - os.devnull is the file path of the null device ('/dev/null', etc.) Programs that import and use 'os' stand a better chance of being portable between different platforms. Of course, they must then only use functions that are defined by all platforms (e.g., unlink and opendir), and leave all pathname manipulation to os.path (e.g., split and join). """ #' import sys, errno _names = sys.builtin_module_names # Note: more names are added to __all__ later. __all__ = ["altsep", "curdir", "pardir", "sep", "extsep", "pathsep", "linesep", "defpath", "name", "path", "devnull", "SEEK_SET", "SEEK_CUR", "SEEK_END"] def _get_exports_list(module): try: return list(module.__all__) except AttributeError: return [n for n in dir(module) if n[0] != '_'] if 'posix' in _names: name = 'posix' linesep = '\n' from posix import * try: from posix import _exit except ImportError: pass import posixpath as path import posix __all__.extend(_get_exports_list(posix)) del posix elif 'nt' in _names: name = 'nt' linesep = '\r\n' from nt import * try: from nt import _exit except ImportError: pass import ntpath as path import nt __all__.extend(_get_exports_list(nt)) del nt elif 'os2' in _names: name = 'os2' linesep = '\r\n' from os2 import * try: from os2 import _exit except ImportError: pass if sys.version.find('EMX GCC') == -1: import ntpath as path else: import os2emxpath as path from _emx_link import link import os2 __all__.extend(_get_exports_list(os2)) del os2 elif 'ce' in _names: name = 'ce' linesep = '\r\n' from ce import * try: from ce import _exit except ImportError: pass # We can use the standard Windows path. import ntpath as path import ce __all__.extend(_get_exports_list(ce)) del ce elif 'riscos' in _names: name = 'riscos' linesep = '\n' from riscos import * try: from riscos import _exit except ImportError: pass import riscospath as path import riscos __all__.extend(_get_exports_list(riscos)) del riscos else: raise ImportError, 'no os specific module found' sys.modules['os.path'] = path from os.path import (curdir, pardir, sep, pathsep, defpath, extsep, altsep, devnull) del _names # Python uses fixed values for the SEEK_ constants; they are mapped # to native constants if necessary in posixmodule.c SEEK_SET = 0 SEEK_CUR = 1 SEEK_END = 2 #' # Super directory utilities. # (Inspired by Eric Raymond; the doc strings are mostly his) def makedirs(name, mode=0777): """makedirs(path [, mode=0777]) Super-mkdir; create a leaf directory and all intermediate ones. Works like mkdir, except that any intermediate path segment (not just the rightmost) will be created if it does not exist. This is recursive. """ head, tail = path.split(name) if not tail: head, tail = path.split(head) if head and tail and not path.exists(head): try: makedirs(head, mode) except OSError, e: # be happy if someone already created the path if e.errno != errno.EEXIST: raise if tail == curdir: # xxx/newdir/. exists if xxx/newdir exists return mkdir(name, mode) def removedirs(name): """removedirs(path) Super-rmdir; remove a leaf directory and all empty intermediate ones. Works like rmdir except that, if the leaf directory is successfully removed, directories corresponding to rightmost path segments will be pruned away until either the whole path is consumed or an error occurs. Errors during this latter phase are ignored -- they generally mean that a directory was not empty. """ rmdir(name) head, tail = path.split(name) if not tail: head, tail = path.split(head) while head and tail: try: rmdir(head) except error: break head, tail = path.split(head) def renames(old, new): """renames(old, new) Super-rename; create directories as necessary and delete any left empty. Works like rename, except creation of any intermediate directories needed to make the new pathname good is attempted first. After the rename, directories corresponding to rightmost path segments of the old name will be pruned way until either the whole path is consumed or a nonempty directory is found. Note: this function can fail with the new directory structure made if you lack permissions needed to unlink the leaf directory or file. """ head, tail = path.split(new) if head and tail and not path.exists(head): makedirs(head) rename(old, new) head, tail = path.split(old) if head and tail: try: removedirs(head) except error: pass __all__.extend(["makedirs", "removedirs", "renames"]) def walk(top, topdown=True, onerror=None, followlinks=False): """Directory tree generator. For each directory in the directory tree rooted at top (including top itself, but excluding '.' and '..'), yields a 3-tuple dirpath, dirnames, filenames dirpath is a string, the path to the directory. dirnames is a list of the names of the subdirectories in dirpath (excluding '.' and '..'). filenames is a list of the names of the non-directory files in dirpath. Note that the names in the lists are just names, with no path components. To get a full path (which begins with top) to a file or directory in dirpath, do os.path.join(dirpath, name). If optional arg 'topdown' is true or not specified, the triple for a directory is generated before the triples for any of its subdirectories (directories are generated top down). If topdown is false, the triple for a directory is generated after the triples for all of its subdirectories (directories are generated bottom up). When topdown is true, the caller can modify the dirnames list in-place (e.g., via del or slice assignment), and walk will only recurse into the subdirectories whose names remain in dirnames; this can be used to prune the search, or to impose a specific order of visiting. Modifying dirnames when topdown is false is ineffective, since the directories in dirnames have already been generated by the time dirnames itself is generated. By default errors from the os.listdir() call are ignored. If optional arg 'onerror' is specified, it should be a function; it will be called with one argument, an os.error instance. It can report the error to continue with the walk, or raise the exception to abort the walk. Note that the filename is available as the filename attribute of the exception object. By default, os.walk does not follow symbolic links to subdirectories on systems that support them. In order to get this functionality, set the optional argument 'followlinks' to true. Caution: if you pass a relative pathname for top, don't change the current working directory between resumptions of walk. walk never changes the current directory, and assumes that the client doesn't either. Example: import os from os.path import join, getsize for root, dirs, files in os.walk('python/Lib/email'): print root, "consumes", print sum([getsize(join(root, name)) for name in files]), print "bytes in", len(files), "non-directory files" if 'CVS' in dirs: dirs.remove('CVS') # don't visit CVS directories """ from os.path import join, isdir, islink # We may not have read permission for top, in which case we can't # get a list of the files the directory contains. os.path.walk # always suppressed the exception then, rather than blow up for a # minor reason when (say) a thousand readable directories are still # left to visit. That logic is copied here. try: # Note that listdir and error are globals in this module due # to earlier import-*. names = listdir(top) except error, err: if onerror is not None: onerror(err) return dirs, nondirs = [], [] for name in names: if isdir(join(top, name)): dirs.append(name) else: nondirs.append(name) if topdown: yield top, dirs, nondirs for name in dirs: path = join(top, name) if followlinks or not islink(path): for x in walk(path, topdown, onerror, followlinks): yield x if not topdown: yield top, dirs, nondirs __all__.append("walk") # Make sure os.environ exists, at least try: environ except NameError: environ = {} def execl(file, *args): """execl(file, *args) Execute the executable file with argument list args, replacing the current process. """ execv(file, args) def execle(file, *args): """execle(file, *args, env) Execute the executable file with argument list args and environment env, replacing the current process. """ env = args[-1] execve(file, args[:-1], env) def execlp(file, *args): """execlp(file, *args) Execute the executable file (which is searched for along $PATH) with argument list args, replacing the current process. """ execvp(file, args) def execlpe(file, *args): """execlpe(file, *args, env) Execute the executable file (which is searched for along $PATH) with argument list args and environment env, replacing the current process. """ env = args[-1] execvpe(file, args[:-1], env) def execvp(file, args): """execvp(file, args) Execute the executable file (which is searched for along $PATH) with argument list args, replacing the current process. args may be a list or tuple of strings. """ _execvpe(file, args) def execvpe(file, args, env): """execvpe(file, args, env) Execute the executable file (which is searched for along $PATH) with argument list args and environment env , replacing the current process. args may be a list or tuple of strings. """ _execvpe(file, args, env) __all__.extend(["execl","execle","execlp","execlpe","execvp","execvpe"]) def _execvpe(file, args, env=None): if env is not None: func = execve argrest = (args, env) else: func = execv argrest = (args,) env = environ head, tail = path.split(file) if head: func(file, *argrest) return if 'PATH' in env: envpath = env['PATH'] else: envpath = defpath PATH = envpath.split(pathsep) saved_exc = None saved_tb = None for dir in PATH: fullname = path.join(dir, file) try: func(fullname, *argrest) except error, e: tb = sys.exc_info()[2] if (e.errno != errno.ENOENT and e.errno != errno.ENOTDIR and saved_exc is None): saved_exc = e saved_tb = tb if saved_exc: raise error, saved_exc, saved_tb raise error, e, tb # Change environ to automatically call putenv() if it exists try: # This will fail if there's no putenv putenv except NameError: pass else: import UserDict # Fake unsetenv() for Windows # not sure about os2 here but # I'm guessing they are the same. if name in ('os2', 'nt'): def unsetenv(key): putenv(key, "") if name == "riscos": # On RISC OS, all env access goes through getenv and putenv from riscosenviron import _Environ elif name in ('os2', 'nt'): # Where Env Var Names Must Be UPPERCASE # But we store them as upper case class _Environ(UserDict.IterableUserDict): def __init__(self, environ): UserDict.UserDict.__init__(self) data = self.data for k, v in environ.items(): data[k.upper()] = v def __setitem__(self, key, item): putenv(key, item) self.data[key.upper()] = item def __getitem__(self, key): return self.data[key.upper()] try: unsetenv except NameError: def __delitem__(self, key): del self.data[key.upper()] else: def __delitem__(self, key): unsetenv(key) del self.data[key.upper()] def clear(self): for key in self.data.keys(): unsetenv(key) del self.data[key] def pop(self, key, *args): unsetenv(key) return self.data.pop(key.upper(), *args) def has_key(self, key): return key.upper() in self.data def __contains__(self, key): return key.upper() in self.data def get(self, key, failobj=None): return self.data.get(key.upper(), failobj) def update(self, dict=None, **kwargs): if dict: try: keys = dict.keys() except AttributeError: # List of (key, value) for k, v in dict: self[k] = v else: # got keys # cannot use items(), since mappings # may not have them. for k in keys: self[k] = dict[k] if kwargs: self.update(kwargs) def copy(self): return dict(self) else: # Where Env Var Names Can Be Mixed Case class _Environ(UserDict.IterableUserDict): def __init__(self, environ): UserDict.UserDict.__init__(self) self.data = environ def __setitem__(self, key, item): putenv(key, item) self.data[key] = item def update(self, dict=None, **kwargs): if dict: try: keys = dict.keys() except AttributeError: # List of (key, value) for k, v in dict: self[k] = v else: # got keys # cannot use items(), since mappings # may not have them. for k in keys: self[k] = dict[k] if kwargs: self.update(kwargs) try: unsetenv except NameError: pass else: def __delitem__(self, key): unsetenv(key) del self.data[key] def clear(self): for key in self.data.keys(): unsetenv(key) del self.data[key] def pop(self, key, *args): unsetenv(key) return self.data.pop(key, *args) def copy(self): return dict(self) environ = _Environ(environ) def getenv(key, default=None): """Get an environment variable, return None if it doesn't exist. The optional second argument can specify an alternate default.""" return environ.get(key, default) __all__.append("getenv") def _exists(name): try: eval(name) return True except NameError: return False # Supply spawn*() (probably only for Unix) if _exists("fork") and not _exists("spawnv") and _exists("execv"): P_WAIT = 0 P_NOWAIT = P_NOWAITO = 1 # XXX Should we support P_DETACH? I suppose it could fork()**2 # and close the std I/O streams. Also, P_OVERLAY is the same # as execv*()? def _spawnvef(mode, file, args, env, func): # Internal helper; func is the exec*() function to use pid = fork() if not pid: # Child try: if env is None: func(file, args) else: func(file, args, env) except: _exit(127) else: # Parent if mode == P_NOWAIT: return pid # Caller is responsible for waiting! while 1: wpid, sts = waitpid(pid, 0) if WIFSTOPPED(sts): continue elif WIFSIGNALED(sts): return -WTERMSIG(sts) elif WIFEXITED(sts): return WEXITSTATUS(sts) else: raise error, "Not stopped, signaled or exited???" def spawnv(mode, file, args): """spawnv(mode, file, args) -> integer Execute file with arguments from args in a subprocess. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return _spawnvef(mode, file, args, None, execv) def spawnve(mode, file, args, env): """spawnve(mode, file, args, env) -> integer Execute file with arguments from args in a subprocess with the specified environment. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return _spawnvef(mode, file, args, env, execve) # Note: spawnvp[e] is't currently supported on Windows def spawnvp(mode, file, args): """spawnvp(mode, file, args) -> integer Execute file (which is looked for along $PATH) with arguments from args in a subprocess. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return _spawnvef(mode, file, args, None, execvp) def spawnvpe(mode, file, args, env): """spawnvpe(mode, file, args, env) -> integer Execute file (which is looked for along $PATH) with arguments from args in a subprocess with the supplied environment. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return _spawnvef(mode, file, args, env, execvpe) if _exists("spawnv"): # These aren't supplied by the basic Windows code # but can be easily implemented in Python def spawnl(mode, file, *args): """spawnl(mode, file, *args) -> integer Execute file with arguments from args in a subprocess. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return spawnv(mode, file, args) def spawnle(mode, file, *args): """spawnle(mode, file, *args, env) -> integer Execute file with arguments from args in a subprocess with the supplied environment. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ env = args[-1] return spawnve(mode, file, args[:-1], env) __all__.extend(["spawnv", "spawnve", "spawnl", "spawnle",]) if _exists("spawnvp"): # At the moment, Windows doesn't implement spawnvp[e], # so it won't have spawnlp[e] either. def spawnlp(mode, file, *args): """spawnlp(mode, file, *args) -> integer Execute file (which is looked for along $PATH) with arguments from args in a subprocess with the supplied environment. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ return spawnvp(mode, file, args) def spawnlpe(mode, file, *args): """spawnlpe(mode, file, *args, env) -> integer Execute file (which is looked for along $PATH) with arguments from args in a subprocess with the supplied environment. If mode == P_NOWAIT return the pid of the process. If mode == P_WAIT return the process's exit code if it exits normally; otherwise return -SIG, where SIG is the signal that killed it. """ env = args[-1] return spawnvpe(mode, file, args[:-1], env) __all__.extend(["spawnvp", "spawnvpe", "spawnlp", "spawnlpe",]) # Supply popen2 etc. (for Unix) if _exists("fork"): if not _exists("popen2"): def popen2(cmd, mode="t", bufsize=-1): """Execute the shell command 'cmd' in a sub-process. On UNIX, 'cmd' may be a sequence, in which case arguments will be passed directly to the program without shell intervention (as with os.spawnv()). If 'cmd' is a string it will be passed to the shell (as with os.system()). If 'bufsize' is specified, it sets the buffer size for the I/O pipes. The file objects (child_stdin, child_stdout) are returned.""" import warnings msg = "os.popen2 is deprecated. Use the subprocess module." warnings.warn(msg, DeprecationWarning, stacklevel=2) import subprocess, types PIPE = subprocess.PIPE p = subprocess.Popen(cmd, shell=isinstance(cmd, basestring), bufsize=bufsize, stdin=PIPE, stdout=PIPE, close_fds=True) return p.stdin, p.stdout __all__.append("popen2") if not _exists("popen3"): def popen3(cmd, mode="t", bufsize=-1): """Execute the shell command 'cmd' in a sub-process. On UNIX, 'cmd' may be a sequence, in which case arguments will be passed directly to the program without shell intervention (as with os.spawnv()). If 'cmd' is a string it will be passed to the shell (as with os.system()). If 'bufsize' is specified, it sets the buffer size for the I/O pipes. The file objects (child_stdin, child_stdout, child_stderr) are returned.""" import warnings msg = "os.popen3 is deprecated. Use the subprocess module." warnings.warn(msg, DeprecationWarning, stacklevel=2) import subprocess, types PIPE = subprocess.PIPE p = subprocess.Popen(cmd, shell=isinstance(cmd, basestring), bufsize=bufsize, stdin=PIPE, stdout=PIPE, stderr=PIPE, close_fds=True) return p.stdin, p.stdout, p.stderr __all__.append("popen3") if not _exists("popen4"): def popen4(cmd, mode="t", bufsize=-1): """Execute the shell command 'cmd' in a sub-process. On UNIX, 'cmd' may be a sequence, in which case arguments will be passed directly to the program without shell intervention (as with os.spawnv()). If 'cmd' is a string it will be passed to the shell (as with os.system()). If 'bufsize' is specified, it sets the buffer size for the I/O pipes. The file objects (child_stdin, child_stdout_stderr) are returned.""" import warnings msg = "os.popen4 is deprecated. Use the subprocess module." warnings.warn(msg, DeprecationWarning, stacklevel=2) import subprocess, types PIPE = subprocess.PIPE p = subprocess.Popen(cmd, shell=isinstance(cmd, basestring), bufsize=bufsize, stdin=PIPE, stdout=PIPE, stderr=subprocess.STDOUT, close_fds=True) return p.stdin, p.stdout __all__.append("popen4") import copy_reg as _copy_reg def _make_stat_result(tup, dict): return stat_result(tup, dict) def _pickle_stat_result(sr): (type, args) = sr.__reduce__() return (_make_stat_result, args) try: _copy_reg.pickle(stat_result, _pickle_stat_result, _make_stat_result) except NameError: # stat_result may not exist pass def _make_statvfs_result(tup, dict): return statvfs_result(tup, dict) def _pickle_statvfs_result(sr): (type, args) = sr.__reduce__() return (_make_statvfs_result, args) try: _copy_reg.pickle(statvfs_result, _pickle_statvfs_result, _make_statvfs_result) except NameError: # statvfs_result may not exist pass feedgenerator-1.9/.tox/py26/lib/python2.6/posixpath.py0000644000076500000240000003147712612565536022353 0ustar jmstaff00000000000000"""Common operations on Posix pathnames. Instead of importing this module directly, import os and refer to this module as os.path. The "os.path" name is an alias for this module on Posix systems; on other systems (e.g. Mac, Windows), os.path provides the same operations in a manner specific to that platform, and is an alias to another module (e.g. macpath, ntpath). Some of this can actually be useful on non-Posix systems too, e.g. for manipulation of the pathname component of URLs. """ import os import stat import genericpath import warnings from genericpath import * __all__ = ["normcase","isabs","join","splitdrive","split","splitext", "basename","dirname","commonprefix","getsize","getmtime", "getatime","getctime","islink","exists","lexists","isdir","isfile", "ismount","walk","expanduser","expandvars","normpath","abspath", "samefile","sameopenfile","samestat", "curdir","pardir","sep","pathsep","defpath","altsep","extsep", "devnull","realpath","supports_unicode_filenames","relpath"] # strings representing various path-related bits and pieces curdir = '.' pardir = '..' extsep = '.' sep = '/' pathsep = ':' defpath = ':/bin:/usr/bin' altsep = None devnull = '/dev/null' # Normalize the case of a pathname. Trivial in Posix, string.lower on Mac. # On MS-DOS this may also turn slashes into backslashes; however, other # normalizations (such as optimizing '../' away) are not allowed # (another function should be defined to do that). def normcase(s): """Normalize case of pathname. Has no effect under Posix""" return s # Return whether a path is absolute. # Trivial in Posix, harder on the Mac or MS-DOS. def isabs(s): """Test whether a path is absolute""" return s.startswith('/') # Join pathnames. # Ignore the previous parts if a part is absolute. # Insert a '/' unless the first part is empty or already ends in '/'. def join(a, *p): """Join two or more pathname components, inserting '/' as needed. If any component is an absolute path, all previous path components will be discarded.""" path = a for b in p: if b.startswith('/'): path = b elif path == '' or path.endswith('/'): path += b else: path += '/' + b return path # Split a path in head (everything up to the last '/') and tail (the # rest). If the path ends in '/', tail will be empty. If there is no # '/' in the path, head will be empty. # Trailing '/'es are stripped from head unless it is the root. def split(p): """Split a pathname. Returns tuple "(head, tail)" where "tail" is everything after the final slash. Either part may be empty.""" i = p.rfind('/') + 1 head, tail = p[:i], p[i:] if head and head != '/'*len(head): head = head.rstrip('/') return head, tail # Split a path in root and extension. # The extension is everything starting at the last dot in the last # pathname component; the root is everything before that. # It is always true that root + ext == p. def splitext(p): return genericpath._splitext(p, sep, altsep, extsep) splitext.__doc__ = genericpath._splitext.__doc__ # Split a pathname into a drive specification and the rest of the # path. Useful on DOS/Windows/NT; on Unix, the drive is always empty. def splitdrive(p): """Split a pathname into drive and path. On Posix, drive is always empty.""" return '', p # Return the tail (basename) part of a path, same as split(path)[1]. def basename(p): """Returns the final component of a pathname""" i = p.rfind('/') + 1 return p[i:] # Return the head (dirname) part of a path, same as split(path)[0]. def dirname(p): """Returns the directory component of a pathname""" i = p.rfind('/') + 1 head = p[:i] if head and head != '/'*len(head): head = head.rstrip('/') return head # Is a path a symbolic link? # This will always return false on systems where os.lstat doesn't exist. def islink(path): """Test whether a path is a symbolic link""" try: st = os.lstat(path) except (os.error, AttributeError): return False return stat.S_ISLNK(st.st_mode) # Being true for dangling symbolic links is also useful. def lexists(path): """Test whether a path exists. Returns True for broken symbolic links""" try: st = os.lstat(path) except os.error: return False return True # Are two filenames really pointing to the same file? def samefile(f1, f2): """Test whether two pathnames reference the same actual file""" s1 = os.stat(f1) s2 = os.stat(f2) return samestat(s1, s2) # Are two open files really referencing the same file? # (Not necessarily the same file descriptor!) def sameopenfile(fp1, fp2): """Test whether two open file objects reference the same file""" s1 = os.fstat(fp1) s2 = os.fstat(fp2) return samestat(s1, s2) # Are two stat buffers (obtained from stat, fstat or lstat) # describing the same file? def samestat(s1, s2): """Test whether two stat buffers reference the same file""" return s1.st_ino == s2.st_ino and \ s1.st_dev == s2.st_dev # Is a path a mount point? # (Does this work for all UNIXes? Is it even guaranteed to work by Posix?) def ismount(path): """Test whether a path is a mount point""" if islink(path): # A symlink can never be a mount point return False try: s1 = os.lstat(path) s2 = os.lstat(join(path, '..')) except os.error: return False # It doesn't exist -- so not a mount point :-) dev1 = s1.st_dev dev2 = s2.st_dev if dev1 != dev2: return True # path/.. on a different device as path ino1 = s1.st_ino ino2 = s2.st_ino if ino1 == ino2: return True # path/.. is the same i-node as path return False # Directory tree walk. # For each directory under top (including top itself, but excluding # '.' and '..'), func(arg, dirname, filenames) is called, where # dirname is the name of the directory and filenames is the list # of files (and subdirectories etc.) in the directory. # The func may modify the filenames list, to implement a filter, # or to impose a different order of visiting. def walk(top, func, arg): """Directory tree walk with callback function. For each directory in the directory tree rooted at top (including top itself, but excluding '.' and '..'), call func(arg, dirname, fnames). dirname is the name of the directory, and fnames a list of the names of the files and subdirectories in dirname (excluding '.' and '..'). func may modify the fnames list in-place (e.g. via del or slice assignment), and walk will only recurse into the subdirectories whose names remain in fnames; this can be used to implement a filter, or to impose a specific order of visiting. No semantics are defined for, or required of, arg, beyond that arg is always passed to func. It can be used, e.g., to pass a filename pattern, or a mutable object designed to accumulate statistics. Passing None for arg is common.""" warnings.warnpy3k("In 3.x, os.path.walk is removed in favor of os.walk.", stacklevel=2) try: names = os.listdir(top) except os.error: return func(arg, top, names) for name in names: name = join(top, name) try: st = os.lstat(name) except os.error: continue if stat.S_ISDIR(st.st_mode): walk(name, func, arg) # Expand paths beginning with '~' or '~user'. # '~' means $HOME; '~user' means that user's home directory. # If the path doesn't begin with '~', or if the user or $HOME is unknown, # the path is returned unchanged (leaving error reporting to whatever # function is called with the expanded path as argument). # See also module 'glob' for expansion of *, ? and [...] in pathnames. # (A function should also be defined to do full *sh-style environment # variable expansion.) def expanduser(path): """Expand ~ and ~user constructions. If user or $HOME is unknown, do nothing.""" if not path.startswith('~'): return path i = path.find('/', 1) if i < 0: i = len(path) if i == 1: if 'HOME' not in os.environ: import pwd userhome = pwd.getpwuid(os.getuid()).pw_dir else: userhome = os.environ['HOME'] else: import pwd try: pwent = pwd.getpwnam(path[1:i]) except KeyError: return path userhome = pwent.pw_dir userhome = userhome.rstrip('/') or userhome return userhome + path[i:] # Expand paths containing shell variable substitutions. # This expands the forms $variable and ${variable} only. # Non-existent variables are left unchanged. _varprog = None def expandvars(path): """Expand shell variables of form $var and ${var}. Unknown variables are left unchanged.""" global _varprog if '$' not in path: return path if not _varprog: import re _varprog = re.compile(r'\$(\w+|\{[^}]*\})') i = 0 while True: m = _varprog.search(path, i) if not m: break i, j = m.span(0) name = m.group(1) if name.startswith('{') and name.endswith('}'): name = name[1:-1] if name in os.environ: tail = path[j:] path = path[:i] + os.environ[name] i = len(path) path += tail else: i = j return path # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A/B. # It should be understood that this may change the meaning of the path # if it contains symbolic links! def normpath(path): """Normalize path, eliminating double slashes, etc.""" # Preserve unicode (if path is unicode) slash, dot = (u'/', u'.') if isinstance(path, unicode) else ('/', '.') if path == '': return dot initial_slashes = path.startswith('/') # POSIX allows one or two initial slashes, but treats three or more # as single slash. if (initial_slashes and path.startswith('//') and not path.startswith('///')): initial_slashes = 2 comps = path.split('/') new_comps = [] for comp in comps: if comp in ('', '.'): continue if (comp != '..' or (not initial_slashes and not new_comps) or (new_comps and new_comps[-1] == '..')): new_comps.append(comp) elif new_comps: new_comps.pop() comps = new_comps path = slash.join(comps) if initial_slashes: path = slash*initial_slashes + path return path or dot def abspath(path): """Return an absolute path.""" if not isabs(path): if isinstance(path, unicode): cwd = os.getcwdu() else: cwd = os.getcwd() path = join(cwd, path) return normpath(path) # Return a canonical path (i.e. the absolute location of a file on the # filesystem). def realpath(filename): """Return the canonical path of the specified filename, eliminating any symbolic links encountered in the path.""" if isabs(filename): bits = ['/'] + filename.split('/')[1:] else: bits = [''] + filename.split('/') for i in range(2, len(bits)+1): component = join(*bits[0:i]) # Resolve symbolic links. if islink(component): resolved = _resolve_link(component) if resolved is None: # Infinite loop -- return original component + rest of the path return abspath(join(*([component] + bits[i:]))) else: newpath = join(*([resolved] + bits[i:])) return realpath(newpath) return abspath(filename) def _resolve_link(path): """Internal helper function. Takes a path and follows symlinks until we either arrive at something that isn't a symlink, or encounter a path we've seen before (meaning that there's a loop). """ paths_seen = [] while islink(path): if path in paths_seen: # Already seen this path, so we must have a symlink loop return None paths_seen.append(path) # Resolve where the link points to resolved = os.readlink(path) if not isabs(resolved): dir = dirname(path) path = normpath(join(dir, resolved)) else: path = normpath(resolved) return path supports_unicode_filenames = False def relpath(path, start=curdir): """Return a relative version of a path""" if not path: raise ValueError("no path specified") start_list = abspath(start).split(sep) path_list = abspath(path).split(sep) # Work out how much of the filepath is shared by start and path. i = len(commonprefix([start_list, path_list])) rel_list = [pardir] * (len(start_list)-i) + path_list[i:] if not rel_list: return curdir return join(*rel_list) feedgenerator-1.9/.tox/py26/lib/python2.6/re.py0000644000076500000240000003124612612565536020734 0ustar jmstaff00000000000000# # Secret Labs' Regular Expression Engine # # re-compatible interface for the sre matching engine # # Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved. # # This version of the SRE library can be redistributed under CNRI's # Python 1.6 license. For any other use, please contact Secret Labs # AB (info@pythonware.com). # # Portions of this engine have been developed in cooperation with # CNRI. Hewlett-Packard provided funding for 1.6 integration and # other compatibility work. # r"""Support for regular expressions (RE). This module provides regular expression matching operations similar to those found in Perl. It supports both 8-bit and Unicode strings; both the pattern and the strings being processed can contain null bytes and characters outside the US ASCII range. Regular expressions can contain both special and ordinary characters. Most ordinary characters, like "A", "a", or "0", are the simplest regular expressions; they simply match themselves. You can concatenate ordinary characters, so last matches the string 'last'. The special characters are: "." Matches any character except a newline. "^" Matches the start of the string. "$" Matches the end of the string or just before the newline at the end of the string. "*" Matches 0 or more (greedy) repetitions of the preceding RE. Greedy means that it will match as many repetitions as possible. "+" Matches 1 or more (greedy) repetitions of the preceding RE. "?" Matches 0 or 1 (greedy) of the preceding RE. *?,+?,?? Non-greedy versions of the previous three special characters. {m,n} Matches from m to n repetitions of the preceding RE. {m,n}? Non-greedy version of the above. "\\" Either escapes special characters or signals a special sequence. [] Indicates a set of characters. A "^" as the first character indicates a complementing set. "|" A|B, creates an RE that will match either A or B. (...) Matches the RE inside the parentheses. The contents can be retrieved or matched later in the string. (?iLmsux) Set the I, L, M, S, U, or X flag for the RE (see below). (?:...) Non-grouping version of regular parentheses. (?P...) The substring matched by the group is accessible by name. (?P=name) Matches the text matched earlier by the group named name. (?#...) A comment; ignored. (?=...) Matches if ... matches next, but doesn't consume the string. (?!...) Matches if ... doesn't match next. (?<=...) Matches if preceded by ... (must be fixed length). (?= 0x02020000: __all__.append("finditer") def finditer(pattern, string, flags=0): """Return an iterator over all non-overlapping matches in the string. For each match, the iterator returns a match object. Empty matches are included in the result.""" return _compile(pattern, flags).finditer(string) def compile(pattern, flags=0): "Compile a regular expression pattern, returning a pattern object." return _compile(pattern, flags) def purge(): "Clear the regular expression cache" _cache.clear() _cache_repl.clear() def template(pattern, flags=0): "Compile a template pattern, returning a pattern object" return _compile(pattern, flags|T) _alphanum = {} for c in 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890': _alphanum[c] = 1 del c def escape(pattern): "Escape all non-alphanumeric characters in pattern." s = list(pattern) alphanum = _alphanum for i in range(len(pattern)): c = pattern[i] if c not in alphanum: if c == "\000": s[i] = "\\000" else: s[i] = "\\" + c return pattern[:0].join(s) # -------------------------------------------------------------------- # internals _cache = {} _cache_repl = {} _pattern_type = type(sre_compile.compile("", 0)) _MAXCACHE = 100 def _compile(*key): # internal: compile pattern cachekey = (type(key[0]),) + key p = _cache.get(cachekey) if p is not None: return p pattern, flags = key if isinstance(pattern, _pattern_type): if flags: raise ValueError('Cannot process flags argument with a compiled pattern') return pattern if not sre_compile.isstring(pattern): raise TypeError, "first argument must be string or compiled pattern" try: p = sre_compile.compile(pattern, flags) except error, v: raise error, v # invalid expression if len(_cache) >= _MAXCACHE: _cache.clear() _cache[cachekey] = p return p def _compile_repl(*key): # internal: compile replacement pattern p = _cache_repl.get(key) if p is not None: return p repl, pattern = key try: p = sre_parse.parse_template(repl, pattern) except error, v: raise error, v # invalid expression if len(_cache_repl) >= _MAXCACHE: _cache_repl.clear() _cache_repl[key] = p return p def _expand(pattern, match, template): # internal: match.expand implementation hook template = sre_parse.parse_template(template, pattern) return sre_parse.expand_template(template, match) def _subx(pattern, template): # internal: pattern.sub/subn implementation helper template = _compile_repl(template, pattern) if not template[0] and len(template[1]) == 1: # literal replacement return template[1][0] def filter(match, template=template): return sre_parse.expand_template(template, match) return filter # register myself for pickling import copy_reg def _pickle(p): return _compile, (p.pattern, p.flags) copy_reg.pickle(_pattern_type, _pickle, _compile) # -------------------------------------------------------------------- # experimental stuff (see python-dev discussions for details) class Scanner: def __init__(self, lexicon, flags=0): from sre_constants import BRANCH, SUBPATTERN self.lexicon = lexicon # combine phrases into a compound pattern p = [] s = sre_parse.Pattern() s.flags = flags for phrase, action in lexicon: p.append(sre_parse.SubPattern(s, [ (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))), ])) s.groups = len(p)+1 p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) self.scanner = sre_compile.compile(p) def scan(self, string): result = [] append = result.append match = self.scanner.scanner(string).match i = 0 while 1: m = match() if not m: break j = m.end() if i == j: break action = self.lexicon[m.lastindex-1][1] if hasattr(action, '__call__'): self.match = m action = action(self, m.group()) if action is not None: append(action) i = j return result, string[i:] feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/0000755000076500000240000000000012765362057022470 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/argparse.py0000644000076500000240000025617612700725533024656 0ustar jmstaff00000000000000# Author: Steven J. Bethard . # Maintainer: Thomas Waldmann """Command-line parsing library This module is an optparse-inspired command-line parsing library that: - handles both optional and positional arguments - produces highly informative usage messages - supports parsers that dispatch to sub-parsers The following is a simple usage example that sums integers from the command-line and writes the result to a file:: parser = argparse.ArgumentParser( description='sum the integers at the command line') parser.add_argument( 'integers', metavar='int', nargs='+', type=int, help='an integer to be summed') parser.add_argument( '--log', default=sys.stdout, type=argparse.FileType('w'), help='the file where the sum should be written') args = parser.parse_args() args.log.write('%s' % sum(args.integers)) args.log.close() The module contains the following public classes: - ArgumentParser -- The main entry point for command-line parsing. As the example above shows, the add_argument() method is used to populate the parser with actions for optional and positional arguments. Then the parse_args() method is invoked to convert the args at the command-line into an object with attributes. - ArgumentError -- The exception raised by ArgumentParser objects when there are errors with the parser's actions. Errors raised while parsing the command-line are caught by ArgumentParser and emitted as command-line messages. - FileType -- A factory for defining types of files to be created. As the example above shows, instances of FileType are typically passed as the type= argument of add_argument() calls. - Action -- The base class for parser actions. Typically actions are selected by passing strings like 'store_true' or 'append_const' to the action= argument of add_argument(). However, for greater customization of ArgumentParser actions, subclasses of Action may be defined and passed as the action= argument. - HelpFormatter, RawDescriptionHelpFormatter, RawTextHelpFormatter, ArgumentDefaultsHelpFormatter -- Formatter classes which may be passed as the formatter_class= argument to the ArgumentParser constructor. HelpFormatter is the default, RawDescriptionHelpFormatter and RawTextHelpFormatter tell the parser not to change the formatting for help text, and ArgumentDefaultsHelpFormatter adds information about argument defaults to the help. All other classes in this module are considered implementation details. (Also note that HelpFormatter and RawDescriptionHelpFormatter are only considered public as object names -- the API of the formatter objects is still considered an implementation detail.) """ __version__ = '1.4.0' # we use our own version number independant of the # one in stdlib and we release this on pypi. __external_lib__ = True # to make sure the tests really test THIS lib, # not the builtin one in Python stdlib __all__ = [ 'ArgumentParser', 'ArgumentError', 'ArgumentTypeError', 'FileType', 'HelpFormatter', 'ArgumentDefaultsHelpFormatter', 'RawDescriptionHelpFormatter', 'RawTextHelpFormatter', 'Namespace', 'Action', 'ONE_OR_MORE', 'OPTIONAL', 'PARSER', 'REMAINDER', 'SUPPRESS', 'ZERO_OR_MORE', ] import copy as _copy import os as _os import re as _re import sys as _sys import textwrap as _textwrap from gettext import gettext as _ try: set except NameError: # for python < 2.4 compatibility (sets module is there since 2.3): from sets import Set as set try: basestring except NameError: basestring = str try: sorted except NameError: # for python < 2.4 compatibility: def sorted(iterable, reverse=False): result = list(iterable) result.sort() if reverse: result.reverse() return result def _callable(obj): return hasattr(obj, '__call__') or hasattr(obj, '__bases__') SUPPRESS = '==SUPPRESS==' OPTIONAL = '?' ZERO_OR_MORE = '*' ONE_OR_MORE = '+' PARSER = 'A...' REMAINDER = '...' _UNRECOGNIZED_ARGS_ATTR = '_unrecognized_args' # ============================= # Utility functions and classes # ============================= class _AttributeHolder(object): """Abstract base class that provides __repr__. The __repr__ method returns a string in the format:: ClassName(attr=name, attr=name, ...) The attributes are determined either by a class-level attribute, '_kwarg_names', or by inspecting the instance __dict__. """ def __repr__(self): type_name = type(self).__name__ arg_strings = [] for arg in self._get_args(): arg_strings.append(repr(arg)) for name, value in self._get_kwargs(): arg_strings.append('%s=%r' % (name, value)) return '%s(%s)' % (type_name, ', '.join(arg_strings)) def _get_kwargs(self): return sorted(self.__dict__.items()) def _get_args(self): return [] def _ensure_value(namespace, name, value): if getattr(namespace, name, None) is None: setattr(namespace, name, value) return getattr(namespace, name) # =============== # Formatting Help # =============== class HelpFormatter(object): """Formatter for generating usage messages and argument help strings. Only the name of this class is considered a public API. All the methods provided by the class are considered an implementation detail. """ def __init__(self, prog, indent_increment=2, max_help_position=24, width=None): # default setting for width if width is None: try: width = int(_os.environ['COLUMNS']) except (KeyError, ValueError): width = 80 width -= 2 self._prog = prog self._indent_increment = indent_increment self._max_help_position = max_help_position self._width = width self._current_indent = 0 self._level = 0 self._action_max_length = 0 self._root_section = self._Section(self, None) self._current_section = self._root_section self._whitespace_matcher = _re.compile(r'\s+') self._long_break_matcher = _re.compile(r'\n\n\n+') # =============================== # Section and indentation methods # =============================== def _indent(self): self._current_indent += self._indent_increment self._level += 1 def _dedent(self): self._current_indent -= self._indent_increment assert self._current_indent >= 0, 'Indent decreased below 0.' self._level -= 1 class _Section(object): def __init__(self, formatter, parent, heading=None): self.formatter = formatter self.parent = parent self.heading = heading self.items = [] def format_help(self): # format the indented section if self.parent is not None: self.formatter._indent() join = self.formatter._join_parts for func, args in self.items: func(*args) item_help = join([func(*args) for func, args in self.items]) if self.parent is not None: self.formatter._dedent() # return nothing if the section was empty if not item_help: return '' # add the heading if the section was non-empty if self.heading is not SUPPRESS and self.heading is not None: current_indent = self.formatter._current_indent heading = '%*s%s:\n' % (current_indent, '', self.heading) else: heading = '' # join the section-initial newline, the heading and the help return join(['\n', heading, item_help, '\n']) def _add_item(self, func, args): self._current_section.items.append((func, args)) # ======================== # Message building methods # ======================== def start_section(self, heading): self._indent() section = self._Section(self, self._current_section, heading) self._add_item(section.format_help, []) self._current_section = section def end_section(self): self._current_section = self._current_section.parent self._dedent() def add_text(self, text): if text is not SUPPRESS and text is not None: self._add_item(self._format_text, [text]) def add_usage(self, usage, actions, groups, prefix=None): if usage is not SUPPRESS: args = usage, actions, groups, prefix self._add_item(self._format_usage, args) def add_argument(self, action): if action.help is not SUPPRESS: # find all invocations get_invocation = self._format_action_invocation invocations = [get_invocation(action)] for subaction in self._iter_indented_subactions(action): invocations.append(get_invocation(subaction)) # update the maximum item length invocation_length = max([len(s) for s in invocations]) action_length = invocation_length + self._current_indent self._action_max_length = max(self._action_max_length, action_length) # add the item to the list self._add_item(self._format_action, [action]) def add_arguments(self, actions): for action in actions: self.add_argument(action) # ======================= # Help-formatting methods # ======================= def format_help(self): help = self._root_section.format_help() if help: help = self._long_break_matcher.sub('\n\n', help) help = help.strip('\n') + '\n' return help def _join_parts(self, part_strings): return ''.join([part for part in part_strings if part and part is not SUPPRESS]) def _format_usage(self, usage, actions, groups, prefix): if prefix is None: prefix = _('usage: ') # if usage is specified, use that if usage is not None: usage = usage % dict(prog=self._prog) # if no optionals or positionals are available, usage is just prog elif usage is None and not actions: usage = '%(prog)s' % dict(prog=self._prog) # if optionals and positionals are available, calculate usage elif usage is None: prog = '%(prog)s' % dict(prog=self._prog) # split optionals from positionals optionals = [] positionals = [] for action in actions: if action.option_strings: optionals.append(action) else: positionals.append(action) # build full usage string format = self._format_actions_usage action_usage = format(optionals + positionals, groups) usage = ' '.join([s for s in [prog, action_usage] if s]) # wrap the usage parts if it's too long text_width = self._width - self._current_indent if len(prefix) + len(usage) > text_width: # break usage into wrappable parts part_regexp = r'\(.*?\)+|\[.*?\]+|\S+' opt_usage = format(optionals, groups) pos_usage = format(positionals, groups) opt_parts = _re.findall(part_regexp, opt_usage) pos_parts = _re.findall(part_regexp, pos_usage) assert ' '.join(opt_parts) == opt_usage assert ' '.join(pos_parts) == pos_usage # helper for wrapping lines def get_lines(parts, indent, prefix=None): lines = [] line = [] if prefix is not None: line_len = len(prefix) - 1 else: line_len = len(indent) - 1 for part in parts: if line_len + 1 + len(part) > text_width: lines.append(indent + ' '.join(line)) line = [] line_len = len(indent) - 1 line.append(part) line_len += len(part) + 1 if line: lines.append(indent + ' '.join(line)) if prefix is not None: lines[0] = lines[0][len(indent):] return lines # if prog is short, follow it with optionals or positionals if len(prefix) + len(prog) <= 0.75 * text_width: indent = ' ' * (len(prefix) + len(prog) + 1) if opt_parts: lines = get_lines([prog] + opt_parts, indent, prefix) lines.extend(get_lines(pos_parts, indent)) elif pos_parts: lines = get_lines([prog] + pos_parts, indent, prefix) else: lines = [prog] # if prog is long, put it on its own line else: indent = ' ' * len(prefix) parts = opt_parts + pos_parts lines = get_lines(parts, indent) if len(lines) > 1: lines = [] lines.extend(get_lines(opt_parts, indent)) lines.extend(get_lines(pos_parts, indent)) lines = [prog] + lines # join lines into usage usage = '\n'.join(lines) # prefix with 'usage:' return '%s%s\n\n' % (prefix, usage) def _format_actions_usage(self, actions, groups): # find group indices and identify actions in groups group_actions = set() inserts = {} for group in groups: try: start = actions.index(group._group_actions[0]) except ValueError: continue else: end = start + len(group._group_actions) if actions[start:end] == group._group_actions: for action in group._group_actions: group_actions.add(action) if not group.required: if start in inserts: inserts[start] += ' [' else: inserts[start] = '[' inserts[end] = ']' else: if start in inserts: inserts[start] += ' (' else: inserts[start] = '(' inserts[end] = ')' for i in range(start + 1, end): inserts[i] = '|' # collect all actions format strings parts = [] for i, action in enumerate(actions): # suppressed arguments are marked with None # remove | separators for suppressed arguments if action.help is SUPPRESS: parts.append(None) if inserts.get(i) == '|': inserts.pop(i) elif inserts.get(i + 1) == '|': inserts.pop(i + 1) # produce all arg strings elif not action.option_strings: part = self._format_args(action, action.dest) # if it's in a group, strip the outer [] if action in group_actions: if part[0] == '[' and part[-1] == ']': part = part[1:-1] # add the action string to the list parts.append(part) # produce the first way to invoke the option in brackets else: option_string = action.option_strings[0] # if the Optional doesn't take a value, format is: # -s or --long if action.nargs == 0: part = '%s' % option_string # if the Optional takes a value, format is: # -s ARGS or --long ARGS else: default = action.dest.upper() args_string = self._format_args(action, default) part = '%s %s' % (option_string, args_string) # make it look optional if it's not required or in a group if not action.required and action not in group_actions: part = '[%s]' % part # add the action string to the list parts.append(part) # insert things at the necessary indices for i in sorted(inserts, reverse=True): parts[i:i] = [inserts[i]] # join all the action items with spaces text = ' '.join([item for item in parts if item is not None]) # clean up separators for mutually exclusive groups open = r'[\[(]' close = r'[\])]' text = _re.sub(r'(%s) ' % open, r'\1', text) text = _re.sub(r' (%s)' % close, r'\1', text) text = _re.sub(r'%s *%s' % (open, close), r'', text) text = _re.sub(r'\(([^|]*)\)', r'\1', text) text = text.strip() # return the text return text def _format_text(self, text): if '%(prog)' in text: text = text % dict(prog=self._prog) text_width = self._width - self._current_indent indent = ' ' * self._current_indent return self._fill_text(text, text_width, indent) + '\n\n' def _format_action(self, action): # determine the required width and the entry label help_position = min(self._action_max_length + 2, self._max_help_position) help_width = self._width - help_position action_width = help_position - self._current_indent - 2 action_header = self._format_action_invocation(action) # ho nelp; start on same line and add a final newline if not action.help: tup = self._current_indent, '', action_header action_header = '%*s%s\n' % tup # short action name; start on the same line and pad two spaces elif len(action_header) <= action_width: tup = self._current_indent, '', action_width, action_header action_header = '%*s%-*s ' % tup indent_first = 0 # long action name; start on the next line else: tup = self._current_indent, '', action_header action_header = '%*s%s\n' % tup indent_first = help_position # collect the pieces of the action help parts = [action_header] # if there was help for the action, add lines of help text if action.help: help_text = self._expand_help(action) help_lines = self._split_lines(help_text, help_width) parts.append('%*s%s\n' % (indent_first, '', help_lines[0])) for line in help_lines[1:]: parts.append('%*s%s\n' % (help_position, '', line)) # or add a newline if the description doesn't end with one elif not action_header.endswith('\n'): parts.append('\n') # if there are any sub-actions, add their help as well for subaction in self._iter_indented_subactions(action): parts.append(self._format_action(subaction)) # return a single string return self._join_parts(parts) def _format_action_invocation(self, action): if not action.option_strings: metavar, = self._metavar_formatter(action, action.dest)(1) return metavar else: parts = [] # if the Optional doesn't take a value, format is: # -s, --long if action.nargs == 0: parts.extend(action.option_strings) # if the Optional takes a value, format is: # -s ARGS, --long ARGS else: default = action.dest.upper() args_string = self._format_args(action, default) for option_string in action.option_strings: parts.append('%s %s' % (option_string, args_string)) return ', '.join(parts) def _metavar_formatter(self, action, default_metavar): if action.metavar is not None: result = action.metavar elif action.choices is not None: choice_strs = [str(choice) for choice in action.choices] result = '{%s}' % ','.join(choice_strs) else: result = default_metavar def format(tuple_size): if isinstance(result, tuple): return result else: return (result, ) * tuple_size return format def _format_args(self, action, default_metavar): get_metavar = self._metavar_formatter(action, default_metavar) if action.nargs is None: result = '%s' % get_metavar(1) elif action.nargs == OPTIONAL: result = '[%s]' % get_metavar(1) elif action.nargs == ZERO_OR_MORE: result = '[%s [%s ...]]' % get_metavar(2) elif action.nargs == ONE_OR_MORE: result = '%s [%s ...]' % get_metavar(2) elif action.nargs == REMAINDER: result = '...' elif action.nargs == PARSER: result = '%s ...' % get_metavar(1) else: formats = ['%s' for _ in range(action.nargs)] result = ' '.join(formats) % get_metavar(action.nargs) return result def _expand_help(self, action): params = dict(vars(action), prog=self._prog) for name in list(params): if params[name] is SUPPRESS: del params[name] for name in list(params): if hasattr(params[name], '__name__'): params[name] = params[name].__name__ if params.get('choices') is not None: choices_str = ', '.join([str(c) for c in params['choices']]) params['choices'] = choices_str return self._get_help_string(action) % params def _iter_indented_subactions(self, action): try: get_subactions = action._get_subactions except AttributeError: pass else: self._indent() for subaction in get_subactions(): yield subaction self._dedent() def _split_lines(self, text, width): text = self._whitespace_matcher.sub(' ', text).strip() return _textwrap.wrap(text, width) def _fill_text(self, text, width, indent): text = self._whitespace_matcher.sub(' ', text).strip() return _textwrap.fill(text, width, initial_indent=indent, subsequent_indent=indent) def _get_help_string(self, action): return action.help class RawDescriptionHelpFormatter(HelpFormatter): """Help message formatter which retains any formatting in descriptions. Only the name of this class is considered a public API. All the methods provided by the class are considered an implementation detail. """ def _fill_text(self, text, width, indent): return ''.join([indent + line for line in text.splitlines(True)]) class RawTextHelpFormatter(RawDescriptionHelpFormatter): """Help message formatter which retains formatting of all help text. Only the name of this class is considered a public API. All the methods provided by the class are considered an implementation detail. """ def _split_lines(self, text, width): return text.splitlines() class ArgumentDefaultsHelpFormatter(HelpFormatter): """Help message formatter which adds default values to argument help. Only the name of this class is considered a public API. All the methods provided by the class are considered an implementation detail. """ def _get_help_string(self, action): help = action.help if '%(default)' not in action.help: if action.default is not SUPPRESS: defaulting_nargs = [OPTIONAL, ZERO_OR_MORE] if action.option_strings or action.nargs in defaulting_nargs: help += ' (default: %(default)s)' return help # ===================== # Options and Arguments # ===================== def _get_action_name(argument): if argument is None: return None elif argument.option_strings: return '/'.join(argument.option_strings) elif argument.metavar not in (None, SUPPRESS): return argument.metavar elif argument.dest not in (None, SUPPRESS): return argument.dest else: return None class ArgumentError(Exception): """An error from creating or using an argument (optional or positional). The string value of this exception is the message, augmented with information about the argument that caused it. """ def __init__(self, argument, message): self.argument_name = _get_action_name(argument) self.message = message def __str__(self): if self.argument_name is None: format = '%(message)s' else: format = 'argument %(argument_name)s: %(message)s' return format % dict(message=self.message, argument_name=self.argument_name) class ArgumentTypeError(Exception): """An error from trying to convert a command line string to a type.""" pass # ============== # Action classes # ============== class Action(_AttributeHolder): """Information about how to convert command line strings to Python objects. Action objects are used by an ArgumentParser to represent the information needed to parse a single argument from one or more strings from the command line. The keyword arguments to the Action constructor are also all attributes of Action instances. Keyword Arguments: - option_strings -- A list of command-line option strings which should be associated with this action. - dest -- The name of the attribute to hold the created object(s) - nargs -- The number of command-line arguments that should be consumed. By default, one argument will be consumed and a single value will be produced. Other values include: - N (an integer) consumes N arguments (and produces a list) - '?' consumes zero or one arguments - '*' consumes zero or more arguments (and produces a list) - '+' consumes one or more arguments (and produces a list) Note that the difference between the default and nargs=1 is that with the default, a single value will be produced, while with nargs=1, a list containing a single value will be produced. - const -- The value to be produced if the option is specified and the option uses an action that takes no values. - default -- The value to be produced if the option is not specified. - type -- The type which the command-line arguments should be converted to, should be one of 'string', 'int', 'float', 'complex' or a callable object that accepts a single string argument. If None, 'string' is assumed. - choices -- A container of values that should be allowed. If not None, after a command-line argument has been converted to the appropriate type, an exception will be raised if it is not a member of this collection. - required -- True if the action must always be specified at the command line. This is only meaningful for optional command-line arguments. - help -- The help string describing the argument. - metavar -- The name to be used for the option's argument with the help string. If None, the 'dest' value will be used as the name. """ def __init__(self, option_strings, dest, nargs=None, const=None, default=None, type=None, choices=None, required=False, help=None, metavar=None): self.option_strings = option_strings self.dest = dest self.nargs = nargs self.const = const self.default = default self.type = type self.choices = choices self.required = required self.help = help self.metavar = metavar def _get_kwargs(self): names = [ 'option_strings', 'dest', 'nargs', 'const', 'default', 'type', 'choices', 'help', 'metavar', ] return [(name, getattr(self, name)) for name in names] def __call__(self, parser, namespace, values, option_string=None): raise NotImplementedError(_('.__call__() not defined')) class _StoreAction(Action): def __init__(self, option_strings, dest, nargs=None, const=None, default=None, type=None, choices=None, required=False, help=None, metavar=None): if nargs == 0: raise ValueError('nargs for store actions must be > 0; if you ' 'have nothing to store, actions such as store ' 'true or store const may be more appropriate') if const is not None and nargs != OPTIONAL: raise ValueError('nargs must be %r to supply const' % OPTIONAL) super(_StoreAction, self).__init__( option_strings=option_strings, dest=dest, nargs=nargs, const=const, default=default, type=type, choices=choices, required=required, help=help, metavar=metavar) def __call__(self, parser, namespace, values, option_string=None): setattr(namespace, self.dest, values) class _StoreConstAction(Action): def __init__(self, option_strings, dest, const, default=None, required=False, help=None, metavar=None): super(_StoreConstAction, self).__init__( option_strings=option_strings, dest=dest, nargs=0, const=const, default=default, required=required, help=help) def __call__(self, parser, namespace, values, option_string=None): setattr(namespace, self.dest, self.const) class _StoreTrueAction(_StoreConstAction): def __init__(self, option_strings, dest, default=False, required=False, help=None): super(_StoreTrueAction, self).__init__( option_strings=option_strings, dest=dest, const=True, default=default, required=required, help=help) class _StoreFalseAction(_StoreConstAction): def __init__(self, option_strings, dest, default=True, required=False, help=None): super(_StoreFalseAction, self).__init__( option_strings=option_strings, dest=dest, const=False, default=default, required=required, help=help) class _AppendAction(Action): def __init__(self, option_strings, dest, nargs=None, const=None, default=None, type=None, choices=None, required=False, help=None, metavar=None): if nargs == 0: raise ValueError('nargs for append actions must be > 0; if arg ' 'strings are not supplying the value to append, ' 'the append const action may be more appropriate') if const is not None and nargs != OPTIONAL: raise ValueError('nargs must be %r to supply const' % OPTIONAL) super(_AppendAction, self).__init__( option_strings=option_strings, dest=dest, nargs=nargs, const=const, default=default, type=type, choices=choices, required=required, help=help, metavar=metavar) def __call__(self, parser, namespace, values, option_string=None): items = _copy.copy(_ensure_value(namespace, self.dest, [])) items.append(values) setattr(namespace, self.dest, items) class _AppendConstAction(Action): def __init__(self, option_strings, dest, const, default=None, required=False, help=None, metavar=None): super(_AppendConstAction, self).__init__( option_strings=option_strings, dest=dest, nargs=0, const=const, default=default, required=required, help=help, metavar=metavar) def __call__(self, parser, namespace, values, option_string=None): items = _copy.copy(_ensure_value(namespace, self.dest, [])) items.append(self.const) setattr(namespace, self.dest, items) class _CountAction(Action): def __init__(self, option_strings, dest, default=None, required=False, help=None): super(_CountAction, self).__init__( option_strings=option_strings, dest=dest, nargs=0, default=default, required=required, help=help) def __call__(self, parser, namespace, values, option_string=None): new_count = _ensure_value(namespace, self.dest, 0) + 1 setattr(namespace, self.dest, new_count) class _HelpAction(Action): def __init__(self, option_strings, dest=SUPPRESS, default=SUPPRESS, help=None): super(_HelpAction, self).__init__( option_strings=option_strings, dest=dest, default=default, nargs=0, help=help) def __call__(self, parser, namespace, values, option_string=None): parser.print_help() parser.exit() class _VersionAction(Action): def __init__(self, option_strings, version=None, dest=SUPPRESS, default=SUPPRESS, help="show program's version number and exit"): super(_VersionAction, self).__init__( option_strings=option_strings, dest=dest, default=default, nargs=0, help=help) self.version = version def __call__(self, parser, namespace, values, option_string=None): version = self.version if version is None: version = parser.version formatter = parser._get_formatter() formatter.add_text(version) parser.exit(message=formatter.format_help()) class _SubParsersAction(Action): class _ChoicesPseudoAction(Action): def __init__(self, name, aliases, help): metavar = dest = name if aliases: metavar += ' (%s)' % ', '.join(aliases) sup = super(_SubParsersAction._ChoicesPseudoAction, self) sup.__init__(option_strings=[], dest=dest, help=help, metavar=metavar) def __init__(self, option_strings, prog, parser_class, dest=SUPPRESS, help=None, metavar=None): self._prog_prefix = prog self._parser_class = parser_class self._name_parser_map = {} self._choices_actions = [] super(_SubParsersAction, self).__init__( option_strings=option_strings, dest=dest, nargs=PARSER, choices=self._name_parser_map, help=help, metavar=metavar) def add_parser(self, name, **kwargs): # set prog from the existing prefix if kwargs.get('prog') is None: kwargs['prog'] = '%s %s' % (self._prog_prefix, name) aliases = kwargs.pop('aliases', ()) # create a pseudo-action to hold the choice help if 'help' in kwargs: help = kwargs.pop('help') choice_action = self._ChoicesPseudoAction(name, aliases, help) self._choices_actions.append(choice_action) # create the parser and add it to the map parser = self._parser_class(**kwargs) self._name_parser_map[name] = parser # make parser available under aliases also for alias in aliases: self._name_parser_map[alias] = parser return parser def _get_subactions(self): return self._choices_actions def __call__(self, parser, namespace, values, option_string=None): parser_name = values[0] arg_strings = values[1:] # set the parser name if requested if self.dest is not SUPPRESS: setattr(namespace, self.dest, parser_name) # select the parser try: parser = self._name_parser_map[parser_name] except KeyError: tup = parser_name, ', '.join(self._name_parser_map) msg = _('unknown parser %r (choices: %s)' % tup) raise ArgumentError(self, msg) # parse all the remaining options into the namespace # store any unrecognized options on the object, so that the top # level parser can decide what to do with them namespace, arg_strings = parser.parse_known_args(arg_strings, namespace) if arg_strings: vars(namespace).setdefault(_UNRECOGNIZED_ARGS_ATTR, []) getattr(namespace, _UNRECOGNIZED_ARGS_ATTR).extend(arg_strings) # ============== # Type classes # ============== class FileType(object): """Factory for creating file object types Instances of FileType are typically passed as type= arguments to the ArgumentParser add_argument() method. Keyword Arguments: - mode -- A string indicating how the file is to be opened. Accepts the same values as the builtin open() function. - bufsize -- The file's desired buffer size. Accepts the same values as the builtin open() function. """ def __init__(self, mode='r', bufsize=None): self._mode = mode self._bufsize = bufsize def __call__(self, string): # the special argument "-" means sys.std{in,out} if string == '-': if 'r' in self._mode: return _sys.stdin elif 'w' in self._mode: return _sys.stdout else: msg = _('argument "-" with mode %r' % self._mode) raise ValueError(msg) try: # all other arguments are used as file names if self._bufsize: return open(string, self._mode, self._bufsize) else: return open(string, self._mode) except IOError: err = _sys.exc_info()[1] message = _("can't open '%s': %s") raise ArgumentTypeError(message % (string, err)) def __repr__(self): args = [self._mode, self._bufsize] args_str = ', '.join([repr(arg) for arg in args if arg is not None]) return '%s(%s)' % (type(self).__name__, args_str) # =========================== # Optional and Positional Parsing # =========================== class Namespace(_AttributeHolder): """Simple object for storing attributes. Implements equality by attribute names and values, and provides a simple string representation. """ def __init__(self, **kwargs): for name in kwargs: setattr(self, name, kwargs[name]) __hash__ = None def __eq__(self, other): return vars(self) == vars(other) def __ne__(self, other): return not (self == other) def __contains__(self, key): return key in self.__dict__ class _ActionsContainer(object): def __init__(self, description, prefix_chars, argument_default, conflict_handler): super(_ActionsContainer, self).__init__() self.description = description self.argument_default = argument_default self.prefix_chars = prefix_chars self.conflict_handler = conflict_handler # set up registries self._registries = {} # register actions self.register('action', None, _StoreAction) self.register('action', 'store', _StoreAction) self.register('action', 'store_const', _StoreConstAction) self.register('action', 'store_true', _StoreTrueAction) self.register('action', 'store_false', _StoreFalseAction) self.register('action', 'append', _AppendAction) self.register('action', 'append_const', _AppendConstAction) self.register('action', 'count', _CountAction) self.register('action', 'help', _HelpAction) self.register('action', 'version', _VersionAction) self.register('action', 'parsers', _SubParsersAction) # raise an exception if the conflict handler is invalid self._get_handler() # action storage self._actions = [] self._option_string_actions = {} # groups self._action_groups = [] self._mutually_exclusive_groups = [] # defaults storage self._defaults = {} # determines whether an "option" looks like a negative number self._negative_number_matcher = _re.compile(r'^-\d+$|^-\d*\.\d+$') # whether or not there are any optionals that look like negative # numbers -- uses a list so it can be shared and edited self._has_negative_number_optionals = [] # ==================== # Registration methods # ==================== def register(self, registry_name, value, object): registry = self._registries.setdefault(registry_name, {}) registry[value] = object def _registry_get(self, registry_name, value, default=None): return self._registries[registry_name].get(value, default) # ================================== # Namespace default accessor methods # ================================== def set_defaults(self, **kwargs): self._defaults.update(kwargs) # if these defaults match any existing arguments, replace # the previous default on the object with the new one for action in self._actions: if action.dest in kwargs: action.default = kwargs[action.dest] def get_default(self, dest): for action in self._actions: if action.dest == dest and action.default is not None: return action.default return self._defaults.get(dest, None) # ======================= # Adding argument actions # ======================= def add_argument(self, *args, **kwargs): """ add_argument(dest, ..., name=value, ...) add_argument(option_string, option_string, ..., name=value, ...) """ # if no positional args are supplied or only one is supplied and # it doesn't look like an option string, parse a positional # argument chars = self.prefix_chars if not args or len(args) == 1 and args[0][0] not in chars: if args and 'dest' in kwargs: raise ValueError('dest supplied twice for positional argument') kwargs = self._get_positional_kwargs(*args, **kwargs) # otherwise, we're adding an optional argument else: kwargs = self._get_optional_kwargs(*args, **kwargs) # if no default was supplied, use the parser-level default if 'default' not in kwargs: dest = kwargs['dest'] if dest in self._defaults: kwargs['default'] = self._defaults[dest] elif self.argument_default is not None: kwargs['default'] = self.argument_default # create the action object, and add it to the parser action_class = self._pop_action_class(kwargs) if not _callable(action_class): raise ValueError('unknown action "%s"' % action_class) action = action_class(**kwargs) # raise an error if the action type is not callable type_func = self._registry_get('type', action.type, action.type) if not _callable(type_func): raise ValueError('%r is not callable' % type_func) return self._add_action(action) def add_argument_group(self, *args, **kwargs): group = _ArgumentGroup(self, *args, **kwargs) self._action_groups.append(group) return group def add_mutually_exclusive_group(self, **kwargs): group = _MutuallyExclusiveGroup(self, **kwargs) self._mutually_exclusive_groups.append(group) return group def _add_action(self, action): # resolve any conflicts self._check_conflict(action) # add to actions list self._actions.append(action) action.container = self # index the action by any option strings it has for option_string in action.option_strings: self._option_string_actions[option_string] = action # set the flag if any option strings look like negative numbers for option_string in action.option_strings: if self._negative_number_matcher.match(option_string): if not self._has_negative_number_optionals: self._has_negative_number_optionals.append(True) # return the created action return action def _remove_action(self, action): self._actions.remove(action) def _add_container_actions(self, container): # collect groups by titles title_group_map = {} for group in self._action_groups: if group.title in title_group_map: msg = _('cannot merge actions - two groups are named %r') raise ValueError(msg % (group.title)) title_group_map[group.title] = group # map each action to its group group_map = {} for group in container._action_groups: # if a group with the title exists, use that, otherwise # create a new group matching the container's group if group.title not in title_group_map: title_group_map[group.title] = self.add_argument_group( title=group.title, description=group.description, conflict_handler=group.conflict_handler) # map the actions to their new group for action in group._group_actions: group_map[action] = title_group_map[group.title] # add container's mutually exclusive groups # NOTE: if add_mutually_exclusive_group ever gains title= and # description= then this code will need to be expanded as above for group in container._mutually_exclusive_groups: mutex_group = self.add_mutually_exclusive_group( required=group.required) # map the actions to their new mutex group for action in group._group_actions: group_map[action] = mutex_group # add all actions to this container or their group for action in container._actions: group_map.get(action, self)._add_action(action) def _get_positional_kwargs(self, dest, **kwargs): # make sure required is not specified if 'required' in kwargs: msg = _("'required' is an invalid argument for positionals") raise TypeError(msg) # mark positional arguments as required if at least one is # always required if kwargs.get('nargs') not in [OPTIONAL, ZERO_OR_MORE]: kwargs['required'] = True if kwargs.get('nargs') == ZERO_OR_MORE and 'default' not in kwargs: kwargs['required'] = True # return the keyword arguments with no option strings return dict(kwargs, dest=dest, option_strings=[]) def _get_optional_kwargs(self, *args, **kwargs): # determine short and long option strings option_strings = [] long_option_strings = [] for option_string in args: # error on strings that don't start with an appropriate prefix if not option_string[0] in self.prefix_chars: msg = _('invalid option string %r: ' 'must start with a character %r') tup = option_string, self.prefix_chars raise ValueError(msg % tup) # strings starting with two prefix characters are long options option_strings.append(option_string) if option_string[0] in self.prefix_chars: if len(option_string) > 1: if option_string[1] in self.prefix_chars: long_option_strings.append(option_string) # infer destination, '--foo-bar' -> 'foo_bar' and '-x' -> 'x' dest = kwargs.pop('dest', None) if dest is None: if long_option_strings: dest_option_string = long_option_strings[0] else: dest_option_string = option_strings[0] dest = dest_option_string.lstrip(self.prefix_chars) if not dest: msg = _('dest= is required for options like %r') raise ValueError(msg % option_string) dest = dest.replace('-', '_') # return the updated keyword arguments return dict(kwargs, dest=dest, option_strings=option_strings) def _pop_action_class(self, kwargs, default=None): action = kwargs.pop('action', default) return self._registry_get('action', action, action) def _get_handler(self): # determine function from conflict handler string handler_func_name = '_handle_conflict_%s' % self.conflict_handler try: return getattr(self, handler_func_name) except AttributeError: msg = _('invalid conflict_resolution value: %r') raise ValueError(msg % self.conflict_handler) def _check_conflict(self, action): # find all options that conflict with this option confl_optionals = [] for option_string in action.option_strings: if option_string in self._option_string_actions: confl_optional = self._option_string_actions[option_string] confl_optionals.append((option_string, confl_optional)) # resolve any conflicts if confl_optionals: conflict_handler = self._get_handler() conflict_handler(action, confl_optionals) def _handle_conflict_error(self, action, conflicting_actions): message = _('conflicting option string(s): %s') conflict_string = ', '.join([option_string for option_string, action in conflicting_actions]) raise ArgumentError(action, message % conflict_string) def _handle_conflict_resolve(self, action, conflicting_actions): # remove all conflicting options for option_string, action in conflicting_actions: # remove the conflicting option action.option_strings.remove(option_string) self._option_string_actions.pop(option_string, None) # if the option now has no option string, remove it from the # container holding it if not action.option_strings: action.container._remove_action(action) class _ArgumentGroup(_ActionsContainer): def __init__(self, container, title=None, description=None, **kwargs): # add any missing keyword arguments by checking the container update = kwargs.setdefault update('conflict_handler', container.conflict_handler) update('prefix_chars', container.prefix_chars) update('argument_default', container.argument_default) super_init = super(_ArgumentGroup, self).__init__ super_init(description=description, **kwargs) # group attributes self.title = title self._group_actions = [] # share most attributes with the container self._registries = container._registries self._actions = container._actions self._option_string_actions = container._option_string_actions self._defaults = container._defaults self._has_negative_number_optionals = \ container._has_negative_number_optionals def _add_action(self, action): action = super(_ArgumentGroup, self)._add_action(action) self._group_actions.append(action) return action def _remove_action(self, action): super(_ArgumentGroup, self)._remove_action(action) self._group_actions.remove(action) class _MutuallyExclusiveGroup(_ArgumentGroup): def __init__(self, container, required=False): super(_MutuallyExclusiveGroup, self).__init__(container) self.required = required self._container = container def _add_action(self, action): if action.required: msg = _('mutually exclusive arguments must be optional') raise ValueError(msg) action = self._container._add_action(action) self._group_actions.append(action) return action def _remove_action(self, action): self._container._remove_action(action) self._group_actions.remove(action) class ArgumentParser(_AttributeHolder, _ActionsContainer): """Object for parsing command line strings into Python objects. Keyword Arguments: - prog -- The name of the program (default: sys.argv[0]) - usage -- A usage message (default: auto-generated from arguments) - description -- A description of what the program does - epilog -- Text following the argument descriptions - parents -- Parsers whose arguments should be copied into this one - formatter_class -- HelpFormatter class for printing help messages - prefix_chars -- Characters that prefix optional arguments - fromfile_prefix_chars -- Characters that prefix files containing additional arguments - argument_default -- The default value for all arguments - conflict_handler -- String indicating how to handle conflicts - add_help -- Add a -h/-help option """ def __init__(self, prog=None, usage=None, description=None, epilog=None, version=None, parents=[], formatter_class=HelpFormatter, prefix_chars='-', fromfile_prefix_chars=None, argument_default=None, conflict_handler='error', add_help=True): if version is not None: import warnings warnings.warn( """The "version" argument to ArgumentParser is deprecated. """ """Please use """ """"add_argument(..., action='version', version="N", ...)" """ """instead""", DeprecationWarning) superinit = super(ArgumentParser, self).__init__ superinit(description=description, prefix_chars=prefix_chars, argument_default=argument_default, conflict_handler=conflict_handler) # default setting for prog if prog is None: prog = _os.path.basename(_sys.argv[0]) self.prog = prog self.usage = usage self.epilog = epilog self.version = version self.formatter_class = formatter_class self.fromfile_prefix_chars = fromfile_prefix_chars self.add_help = add_help add_group = self.add_argument_group self._positionals = add_group(_('positional arguments')) self._optionals = add_group(_('optional arguments')) self._subparsers = None # register types def identity(string): return string self.register('type', None, identity) # add help and version arguments if necessary # (using explicit default to override global argument_default) if '-' in prefix_chars: default_prefix = '-' else: default_prefix = prefix_chars[0] if self.add_help: self.add_argument( default_prefix+'h', default_prefix*2+'help', action='help', default=SUPPRESS, help=_('show this help message and exit')) if self.version: self.add_argument( default_prefix+'v', default_prefix*2+'version', action='version', default=SUPPRESS, version=self.version, help=_("show program's version number and exit")) # add parent arguments and defaults for parent in parents: self._add_container_actions(parent) try: defaults = parent._defaults except AttributeError: pass else: self._defaults.update(defaults) # ======================= # Pretty __repr__ methods # ======================= def _get_kwargs(self): names = [ 'prog', 'usage', 'description', 'version', 'formatter_class', 'conflict_handler', 'add_help', ] return [(name, getattr(self, name)) for name in names] # ================================== # Optional/Positional adding methods # ================================== def add_subparsers(self, **kwargs): if self._subparsers is not None: self.error(_('cannot have multiple subparser arguments')) # add the parser class to the arguments if it's not present kwargs.setdefault('parser_class', type(self)) if 'title' in kwargs or 'description' in kwargs: title = _(kwargs.pop('title', 'subcommands')) description = _(kwargs.pop('description', None)) self._subparsers = self.add_argument_group(title, description) else: self._subparsers = self._positionals # prog defaults to the usage message of this parser, skipping # optional arguments and with no "usage:" prefix if kwargs.get('prog') is None: formatter = self._get_formatter() positionals = self._get_positional_actions() groups = self._mutually_exclusive_groups formatter.add_usage(self.usage, positionals, groups, '') kwargs['prog'] = formatter.format_help().strip() # create the parsers action and add it to the positionals list parsers_class = self._pop_action_class(kwargs, 'parsers') action = parsers_class(option_strings=[], **kwargs) self._subparsers._add_action(action) # return the created parsers action return action def _add_action(self, action): if action.option_strings: self._optionals._add_action(action) else: self._positionals._add_action(action) return action def _get_optional_actions(self): return [action for action in self._actions if action.option_strings] def _get_positional_actions(self): return [action for action in self._actions if not action.option_strings] # ===================================== # Command line argument parsing methods # ===================================== def parse_args(self, args=None, namespace=None): args, argv = self.parse_known_args(args, namespace) if argv: msg = _('unrecognized arguments: %s') self.error(msg % ' '.join(argv)) return args def parse_known_args(self, args=None, namespace=None): # args default to the system args if args is None: args = _sys.argv[1:] # default Namespace built from parser defaults if namespace is None: namespace = Namespace() # add any action defaults that aren't present for action in self._actions: if action.dest is not SUPPRESS: if not hasattr(namespace, action.dest): if action.default is not SUPPRESS: setattr(namespace, action.dest, action.default) # add any parser defaults that aren't present for dest in self._defaults: if not hasattr(namespace, dest): setattr(namespace, dest, self._defaults[dest]) # parse the arguments and exit if there are any errors try: namespace, args = self._parse_known_args(args, namespace) if hasattr(namespace, _UNRECOGNIZED_ARGS_ATTR): args.extend(getattr(namespace, _UNRECOGNIZED_ARGS_ATTR)) delattr(namespace, _UNRECOGNIZED_ARGS_ATTR) return namespace, args except ArgumentError: err = _sys.exc_info()[1] self.error(str(err)) def _parse_known_args(self, arg_strings, namespace): # replace arg strings that are file references if self.fromfile_prefix_chars is not None: arg_strings = self._read_args_from_files(arg_strings) # map all mutually exclusive arguments to the other arguments # they can't occur with action_conflicts = {} for mutex_group in self._mutually_exclusive_groups: group_actions = mutex_group._group_actions for i, mutex_action in enumerate(mutex_group._group_actions): conflicts = action_conflicts.setdefault(mutex_action, []) conflicts.extend(group_actions[:i]) conflicts.extend(group_actions[i + 1:]) # find all option indices, and determine the arg_string_pattern # which has an 'O' if there is an option at an index, # an 'A' if there is an argument, or a '-' if there is a '--' option_string_indices = {} arg_string_pattern_parts = [] arg_strings_iter = iter(arg_strings) for i, arg_string in enumerate(arg_strings_iter): # all args after -- are non-options if arg_string == '--': arg_string_pattern_parts.append('-') for arg_string in arg_strings_iter: arg_string_pattern_parts.append('A') # otherwise, add the arg to the arg strings # and note the index if it was an option else: option_tuple = self._parse_optional(arg_string) if option_tuple is None: pattern = 'A' else: option_string_indices[i] = option_tuple pattern = 'O' arg_string_pattern_parts.append(pattern) # join the pieces together to form the pattern arg_strings_pattern = ''.join(arg_string_pattern_parts) # converts arg strings to the appropriate and then takes the action seen_actions = set() seen_non_default_actions = set() def take_action(action, argument_strings, option_string=None): seen_actions.add(action) argument_values = self._get_values(action, argument_strings) # error if this argument is not allowed with other previously # seen arguments, assuming that actions that use the default # value don't really count as "present" if argument_values is not action.default: seen_non_default_actions.add(action) for conflict_action in action_conflicts.get(action, []): if conflict_action in seen_non_default_actions: msg = _('not allowed with argument %s') action_name = _get_action_name(conflict_action) raise ArgumentError(action, msg % action_name) # take the action if we didn't receive a SUPPRESS value # (e.g. from a default) if argument_values is not SUPPRESS: action(self, namespace, argument_values, option_string) # function to convert arg_strings into an optional action def consume_optional(start_index): # get the optional identified at this index option_tuple = option_string_indices[start_index] action, option_string, explicit_arg = option_tuple # identify additional optionals in the same arg string # (e.g. -xyz is the same as -x -y -z if no args are required) match_argument = self._match_argument action_tuples = [] while True: # if we found no optional action, skip it if action is None: extras.append(arg_strings[start_index]) return start_index + 1 # if there is an explicit argument, try to match the # optional's string arguments to only this if explicit_arg is not None: arg_count = match_argument(action, 'A') # if the action is a single-dash option and takes no # arguments, try to parse more single-dash options out # of the tail of the option string chars = self.prefix_chars if arg_count == 0 and option_string[1] not in chars: action_tuples.append((action, [], option_string)) char = option_string[0] option_string = char + explicit_arg[0] new_explicit_arg = explicit_arg[1:] or None optionals_map = self._option_string_actions if option_string in optionals_map: action = optionals_map[option_string] explicit_arg = new_explicit_arg else: msg = _('ignored explicit argument %r') raise ArgumentError(action, msg % explicit_arg) # if the action expect exactly one argument, we've # successfully matched the option; exit the loop elif arg_count == 1: stop = start_index + 1 args = [explicit_arg] action_tuples.append((action, args, option_string)) break # error if a double-dash option did not use the # explicit argument else: msg = _('ignored explicit argument %r') raise ArgumentError(action, msg % explicit_arg) # if there is no explicit argument, try to match the # optional's string arguments with the following strings # if successful, exit the loop else: start = start_index + 1 selected_patterns = arg_strings_pattern[start:] arg_count = match_argument(action, selected_patterns) stop = start + arg_count args = arg_strings[start:stop] action_tuples.append((action, args, option_string)) break # add the Optional to the list and return the index at which # the Optional's string args stopped assert action_tuples for action, args, option_string in action_tuples: take_action(action, args, option_string) return stop # the list of Positionals left to be parsed; this is modified # by consume_positionals() positionals = self._get_positional_actions() # function to convert arg_strings into positional actions def consume_positionals(start_index): # match as many Positionals as possible match_partial = self._match_arguments_partial selected_pattern = arg_strings_pattern[start_index:] arg_counts = match_partial(positionals, selected_pattern) # slice off the appropriate arg strings for each Positional # and add the Positional and its args to the list for action, arg_count in zip(positionals, arg_counts): args = arg_strings[start_index: start_index + arg_count] start_index += arg_count take_action(action, args) # slice off the Positionals that we just parsed and return the # index at which the Positionals' string args stopped positionals[:] = positionals[len(arg_counts):] return start_index # consume Positionals and Optionals alternately, until we have # passed the last option string extras = [] start_index = 0 if option_string_indices: max_option_string_index = max(option_string_indices) else: max_option_string_index = -1 while start_index <= max_option_string_index: # consume any Positionals preceding the next option next_option_string_index = min([ index for index in option_string_indices if index >= start_index]) if start_index != next_option_string_index: positionals_end_index = consume_positionals(start_index) # only try to parse the next optional if we didn't consume # the option string during the positionals parsing if positionals_end_index > start_index: start_index = positionals_end_index continue else: start_index = positionals_end_index # if we consumed all the positionals we could and we're not # at the index of an option string, there were extra arguments if start_index not in option_string_indices: strings = arg_strings[start_index:next_option_string_index] extras.extend(strings) start_index = next_option_string_index # consume the next optional and any arguments for it start_index = consume_optional(start_index) # consume any positionals following the last Optional stop_index = consume_positionals(start_index) # if we didn't consume all the argument strings, there were extras extras.extend(arg_strings[stop_index:]) # if we didn't use all the Positional objects, there were too few # arg strings supplied. if positionals: self.error(_('too few arguments')) # make sure all required actions were present, and convert defaults. for action in self._actions: if action not in seen_actions: if action.required: name = _get_action_name(action) self.error(_('argument %s is required') % name) else: # Convert action default now instead of doing it before # parsing arguments to avoid calling convert functions # twice (which may fail) if the argument was given, but # only if it was defined already in the namespace if (action.default is not None and isinstance(action.default, basestring) and hasattr(namespace, action.dest) and action.default is getattr(namespace, action.dest)): setattr(namespace, action.dest, self._get_value(action, action.default)) # make sure all required groups had one option present for group in self._mutually_exclusive_groups: if group.required: for action in group._group_actions: if action in seen_non_default_actions: break # if no actions were used, report the error else: names = [_get_action_name(action) for action in group._group_actions if action.help is not SUPPRESS] msg = _('one of the arguments %s is required') self.error(msg % ' '.join(names)) # return the updated namespace and the extra arguments return namespace, extras def _read_args_from_files(self, arg_strings): # expand arguments referencing files new_arg_strings = [] for arg_string in arg_strings: # for regular arguments, just add them back into the list if arg_string[0] not in self.fromfile_prefix_chars: new_arg_strings.append(arg_string) # replace arguments referencing files with the file content else: try: args_file = open(arg_string[1:]) try: arg_strings = [] for arg_line in args_file.read().splitlines(): for arg in self.convert_arg_line_to_args(arg_line): arg_strings.append(arg) arg_strings = self._read_args_from_files(arg_strings) new_arg_strings.extend(arg_strings) finally: args_file.close() except IOError: err = _sys.exc_info()[1] self.error(str(err)) # return the modified argument list return new_arg_strings def convert_arg_line_to_args(self, arg_line): return [arg_line] def _match_argument(self, action, arg_strings_pattern): # match the pattern for this action to the arg strings nargs_pattern = self._get_nargs_pattern(action) match = _re.match(nargs_pattern, arg_strings_pattern) # raise an exception if we weren't able to find a match if match is None: nargs_errors = { None: _('expected one argument'), OPTIONAL: _('expected at most one argument'), ONE_OR_MORE: _('expected at least one argument'), } default = _('expected %s argument(s)') % action.nargs msg = nargs_errors.get(action.nargs, default) raise ArgumentError(action, msg) # return the number of arguments matched return len(match.group(1)) def _match_arguments_partial(self, actions, arg_strings_pattern): # progressively shorten the actions list by slicing off the # final actions until we find a match result = [] for i in range(len(actions), 0, -1): actions_slice = actions[:i] pattern = ''.join([self._get_nargs_pattern(action) for action in actions_slice]) match = _re.match(pattern, arg_strings_pattern) if match is not None: result.extend([len(string) for string in match.groups()]) break # return the list of arg string counts return result def _parse_optional(self, arg_string): # if it's an empty string, it was meant to be a positional if not arg_string: return None # if it doesn't start with a prefix, it was meant to be positional if not arg_string[0] in self.prefix_chars: return None # if the option string is present in the parser, return the action if arg_string in self._option_string_actions: action = self._option_string_actions[arg_string] return action, arg_string, None # if it's just a single character, it was meant to be positional if len(arg_string) == 1: return None # if the option string before the "=" is present, return the action if '=' in arg_string: option_string, explicit_arg = arg_string.split('=', 1) if option_string in self._option_string_actions: action = self._option_string_actions[option_string] return action, option_string, explicit_arg # search through all possible prefixes of the option string # and all actions in the parser for possible interpretations option_tuples = self._get_option_tuples(arg_string) # if multiple actions match, the option string was ambiguous if len(option_tuples) > 1: options = ', '.join([option_string for action, option_string, explicit_arg in option_tuples]) tup = arg_string, options self.error(_('ambiguous option: %s could match %s') % tup) # if exactly one action matched, this segmentation is good, # so return the parsed action elif len(option_tuples) == 1: option_tuple, = option_tuples return option_tuple # if it was not found as an option, but it looks like a negative # number, it was meant to be positional # unless there are negative-number-like options if self._negative_number_matcher.match(arg_string): if not self._has_negative_number_optionals: return None # if it contains a space, it was meant to be a positional if ' ' in arg_string: return None # it was meant to be an optional but there is no such option # in this parser (though it might be a valid option in a subparser) return None, arg_string, None def _get_option_tuples(self, option_string): result = [] # option strings starting with two prefix characters are only # split at the '=' chars = self.prefix_chars if option_string[0] in chars and option_string[1] in chars: if '=' in option_string: option_prefix, explicit_arg = option_string.split('=', 1) else: option_prefix = option_string explicit_arg = None for option_string in self._option_string_actions: if option_string.startswith(option_prefix): action = self._option_string_actions[option_string] tup = action, option_string, explicit_arg result.append(tup) # single character options can be concatenated with their arguments # but multiple character options always have to have their argument # separate elif option_string[0] in chars and option_string[1] not in chars: option_prefix = option_string explicit_arg = None short_option_prefix = option_string[:2] short_explicit_arg = option_string[2:] for option_string in self._option_string_actions: if option_string == short_option_prefix: action = self._option_string_actions[option_string] tup = action, option_string, short_explicit_arg result.append(tup) elif option_string.startswith(option_prefix): action = self._option_string_actions[option_string] tup = action, option_string, explicit_arg result.append(tup) # shouldn't ever get here else: self.error(_('unexpected option string: %s') % option_string) # return the collected option tuples return result def _get_nargs_pattern(self, action): # in all examples below, we have to allow for '--' args # which are represented as '-' in the pattern nargs = action.nargs # the default (None) is assumed to be a single argument if nargs is None: nargs_pattern = '(-*A-*)' # allow zero or one arguments elif nargs == OPTIONAL: nargs_pattern = '(-*A?-*)' # allow zero or more arguments elif nargs == ZERO_OR_MORE: nargs_pattern = '(-*[A-]*)' # allow one or more arguments elif nargs == ONE_OR_MORE: nargs_pattern = '(-*A[A-]*)' # allow any number of options or arguments elif nargs == REMAINDER: nargs_pattern = '([-AO]*)' # allow one argument followed by any number of options or arguments elif nargs == PARSER: nargs_pattern = '(-*A[-AO]*)' # all others should be integers else: nargs_pattern = '(-*%s-*)' % '-*'.join('A' * nargs) # if this is an optional action, -- is not allowed if action.option_strings: nargs_pattern = nargs_pattern.replace('-*', '') nargs_pattern = nargs_pattern.replace('-', '') # return the pattern return nargs_pattern # ======================== # Value conversion methods # ======================== def _get_values(self, action, arg_strings): # for everything but PARSER args, strip out '--' if action.nargs not in [PARSER, REMAINDER]: arg_strings = [s for s in arg_strings if s != '--'] # optional argument produces a default when not present if not arg_strings and action.nargs == OPTIONAL: if action.option_strings: value = action.const else: value = action.default if isinstance(value, basestring): value = self._get_value(action, value) self._check_value(action, value) # when nargs='*' on a positional, if there were no command-line # args, use the default if it is anything other than None elif (not arg_strings and action.nargs == ZERO_OR_MORE and not action.option_strings): if action.default is not None: value = action.default else: value = arg_strings self._check_value(action, value) # single argument or optional argument produces a single value elif len(arg_strings) == 1 and action.nargs in [None, OPTIONAL]: arg_string, = arg_strings value = self._get_value(action, arg_string) self._check_value(action, value) # REMAINDER arguments convert all values, checking none elif action.nargs == REMAINDER: value = [self._get_value(action, v) for v in arg_strings] # PARSER arguments convert all values, but check only the first elif action.nargs == PARSER: value = [self._get_value(action, v) for v in arg_strings] self._check_value(action, value[0]) # all other types of nargs produce a list else: value = [self._get_value(action, v) for v in arg_strings] for v in value: self._check_value(action, v) # return the converted value return value def _get_value(self, action, arg_string): type_func = self._registry_get('type', action.type, action.type) if not _callable(type_func): msg = _('%r is not callable') raise ArgumentError(action, msg % type_func) # convert the value to the appropriate type try: result = type_func(arg_string) # ArgumentTypeErrors indicate errors except ArgumentTypeError: name = getattr(action.type, '__name__', repr(action.type)) msg = str(_sys.exc_info()[1]) raise ArgumentError(action, msg) # TypeErrors or ValueErrors also indicate errors except (TypeError, ValueError): name = getattr(action.type, '__name__', repr(action.type)) msg = _('invalid %s value: %r') raise ArgumentError(action, msg % (name, arg_string)) # return the converted value return result def _check_value(self, action, value): # converted value must be one of the choices (if specified) if action.choices is not None and value not in action.choices: tup = value, ', '.join(map(repr, action.choices)) msg = _('invalid choice: %r (choose from %s)') % tup raise ArgumentError(action, msg) # ======================= # Help-formatting methods # ======================= def format_usage(self): formatter = self._get_formatter() formatter.add_usage(self.usage, self._actions, self._mutually_exclusive_groups) return formatter.format_help() def format_help(self): formatter = self._get_formatter() # usage formatter.add_usage(self.usage, self._actions, self._mutually_exclusive_groups) # description formatter.add_text(self.description) # positionals, optionals and user-defined groups for action_group in self._action_groups: formatter.start_section(action_group.title) formatter.add_text(action_group.description) formatter.add_arguments(action_group._group_actions) formatter.end_section() # epilog formatter.add_text(self.epilog) # determine help from format above return formatter.format_help() def format_version(self): import warnings warnings.warn( 'The format_version method is deprecated -- the "version" ' 'argument to ArgumentParser is no longer supported.', DeprecationWarning) formatter = self._get_formatter() formatter.add_text(self.version) return formatter.format_help() def _get_formatter(self): return self.formatter_class(prog=self.prog) # ===================== # Help-printing methods # ===================== def print_usage(self, file=None): if file is None: file = _sys.stdout self._print_message(self.format_usage(), file) def print_help(self, file=None): if file is None: file = _sys.stdout self._print_message(self.format_help(), file) def print_version(self, file=None): import warnings warnings.warn( 'The print_version method is deprecated -- the "version" ' 'argument to ArgumentParser is no longer supported.', DeprecationWarning) self._print_message(self.format_version(), file) def _print_message(self, message, file=None): if message: if file is None: file = _sys.stderr file.write(message) # =============== # Exiting methods # =============== def exit(self, status=0, message=None): if message: self._print_message(message, _sys.stderr) _sys.exit(status) def error(self, message): """error(message: string) Prints a usage message incorporating the message to stderr and exits. If you override this in a subclass, it should not return -- it should either exit or raise an exception. """ self.print_usage(_sys.stderr) self.exit(2, _('%s: error: %s\n') % (self.prog, message)) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/easy_install.py0000644000076500000240000000017612700725533025524 0ustar jmstaff00000000000000"""Run the EasyInstall command""" if __name__ == '__main__': from setuptools.command.easy_install import main main() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/0000755000076500000240000000000012765362057025302 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/__init__.py0000644000076500000240000000141412765356444027416 0ustar jmstaff00000000000000""" Syndication feed generation library -- used for generating RSS, etc. Sample usage: >>> import feedgenerator >>> feed = feedgenerator.Rss201rev2Feed( ... title="Poynter E-Media Tidbits", ... link="http://www.poynter.org/column.asp?id=31", ... description="A group Weblog by the sharpest minds in online media/journalism/publishing.", ... language="en", ... ) >>> feed.add_item( ... title="Hello", ... link="http://www.holovaty.com/test/", ... description="Testing." ... ) >>> with open('test.rss', 'w') as fp: ... feed.write(fp, 'utf-8') For definitions of the different versions of RSS, see: http://web.archive.org/web/20110718035220/http://diveintomark.org/archives/2004/02/04/incompatible-rss """ from .django.utils.feedgenerator import * feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/0000755000076500000240000000000012765362057026544 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/__init__.py0000644000076500000240000000000012765356444030646 0ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/0000755000076500000240000000000012765362057027704 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/__init__.py0000644000076500000240000000000012765356444032006 0ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/datetime_safe.py0000644000076500000240000000517512765356444033063 0ustar jmstaff00000000000000# Python's datetime strftime doesn't handle dates before 1900. # These classes override date and datetime to support the formatting of a date # through its full "proleptic Gregorian" date range. # # Based on code submitted to comp.lang.python by Andrew Dalke # # >>> datetime_safe.date(1850, 8, 2).strftime("%Y/%m/%d was a %A") # '1850/08/02 was a Friday' from datetime import date as real_date, datetime as real_datetime import re import time class date(real_date): def strftime(self, fmt): return strftime(self, fmt) class datetime(real_datetime): def strftime(self, fmt): return strftime(self, fmt) def combine(self, date, time): return datetime(date.year, date.month, date.day, time.hour, time.minute, time.microsecond, time.tzinfo) def date(self): return date(self.year, self.month, self.day) def new_date(d): "Generate a safe date from a datetime.date object." return date(d.year, d.month, d.day) def new_datetime(d): """ Generate a safe datetime from a datetime.date or datetime.datetime object. """ kw = [d.year, d.month, d.day] if isinstance(d, real_datetime): kw.extend([d.hour, d.minute, d.second, d.microsecond, d.tzinfo]) return datetime(*kw) # This library does not support strftime's "%s" or "%y" format strings. # Allowed if there's an even number of "%"s because they are escaped. _illegal_formatting = re.compile(r"((^|[^%])(%%)*%[sy])") def _findall(text, substr): # Also finds overlaps sites = [] i = 0 while 1: j = text.find(substr, i) if j == -1: break sites.append(j) i=j+1 return sites def strftime(dt, fmt): if dt.year >= 1900: return super(type(dt), dt).strftime(fmt) illegal_formatting = _illegal_formatting.search(fmt) if illegal_formatting: raise TypeError("strftime of dates before 1900 does not handle" + illegal_formatting.group(0)) year = dt.year # For every non-leap year century, advance by # 6 years to get into the 28-year repeat cycle delta = 2000 - year off = 6 * (delta // 100 + delta // 400) year = year + off # Move to around the year 2000 year = year + ((2000 - year) // 28) * 28 timetuple = dt.timetuple() s1 = time.strftime(fmt, (year,) + timetuple[1:]) sites1 = _findall(s1, str(year)) s2 = time.strftime(fmt, (year+28,) + timetuple[1:]) sites2 = _findall(s2, str(year+28)) sites = [] for site in sites1: if site in sites2: sites.append(site) s = s1 syear = "%04d" % (dt.year,) for site in sites: s = s[:site] + syear + s[site+4:] return s feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/encoding.py0000644000076500000240000002320312765356444032047 0ustar jmstaff00000000000000from __future__ import unicode_literals import codecs import datetime from decimal import Decimal import locale try: from urllib.parse import quote except ImportError: # Python 2 from urllib import quote import warnings from .functional import Promise from . import six class DjangoUnicodeDecodeError(UnicodeDecodeError): def __init__(self, obj, *args): self.obj = obj UnicodeDecodeError.__init__(self, *args) def __str__(self): original = UnicodeDecodeError.__str__(self) return '%s. You passed in %r (%s)' % (original, self.obj, type(self.obj)) class StrAndUnicode(object): """ A class that derives __str__ from __unicode__. On Python 2, __str__ returns the output of __unicode__ encoded as a UTF-8 bytestring. On Python 3, __str__ returns the output of __unicode__. Useful as a mix-in. If you support Python 2 and 3 with a single code base, you can inherit this mix-in and just define __unicode__. """ def __init__(self, *args, **kwargs): warnings.warn("StrAndUnicode is deprecated. Define a __str__ method " "and apply the @python_2_unicode_compatible decorator " "instead.", PendingDeprecationWarning, stacklevel=2) super(StrAndUnicode, self).__init__(*args, **kwargs) if six.PY3: def __str__(self): return self.__unicode__() else: def __str__(self): return self.__unicode__().encode('utf-8') def python_2_unicode_compatible(klass): """ A decorator that defines __unicode__ and __str__ methods under Python 2. Under Python 3 it does nothing. To support Python 2 and 3 with a single code base, define a __str__ method returning text and apply this decorator to the class. """ if not six.PY3: klass.__unicode__ = klass.__str__ klass.__str__ = lambda self: self.__unicode__().encode('utf-8') return klass def smart_text(s, encoding='utf-8', strings_only=False, errors='strict'): """ Returns a text object representing 's' -- unicode on Python 2 and str on Python 3. Treats bytestrings using the 'encoding' codec. If strings_only is True, don't convert (some) non-string-like objects. """ if isinstance(s, Promise): # The input is the result of a gettext_lazy() call. return s return force_text(s, encoding, strings_only, errors) def is_protected_type(obj): """Determine if the object instance is of a protected type. Objects of protected types are preserved as-is when passed to force_text(strings_only=True). """ return isinstance(obj, six.integer_types + (type(None), float, Decimal, datetime.datetime, datetime.date, datetime.time)) def force_text(s, encoding='utf-8', strings_only=False, errors='strict'): """ Similar to smart_text, except that lazy instances are resolved to strings, rather than kept as lazy objects. If strings_only is True, don't convert (some) non-string-like objects. """ # Handle the common case first, saves 30-40% when s is an instance of # six.text_type. This function gets called often in that setting. if isinstance(s, six.text_type): return s if strings_only and is_protected_type(s): return s try: if not isinstance(s, six.string_types): if hasattr(s, '__unicode__'): s = s.__unicode__() else: try: if six.PY3: if isinstance(s, bytes): s = six.text_type(s, encoding, errors) else: s = six.text_type(s) else: s = six.text_type(bytes(s), encoding, errors) except UnicodeEncodeError: if not isinstance(s, Exception): raise # If we get to here, the caller has passed in an Exception # subclass populated with non-ASCII data without special # handling to display as a string. We need to handle this # without raising a further exception. We do an # approximation to what the Exception's standard str() # output should be. s = ' '.join([force_text(arg, encoding, strings_only, errors) for arg in s]) else: # Note: We use .decode() here, instead of six.text_type(s, encoding, # errors), so that if s is a SafeBytes, it ends up being a # SafeText at the end. s = s.decode(encoding, errors) except UnicodeDecodeError as e: if not isinstance(s, Exception): raise DjangoUnicodeDecodeError(s, *e.args) else: # If we get to here, the caller has passed in an Exception # subclass populated with non-ASCII bytestring data without a # working unicode method. Try to handle this without raising a # further exception by individually forcing the exception args # to unicode. s = ' '.join([force_text(arg, encoding, strings_only, errors) for arg in s]) return s def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): """ Returns a bytestring version of 's', encoded as specified in 'encoding'. If strings_only is True, don't convert (some) non-string-like objects. """ if isinstance(s, Promise): # The input is the result of a gettext_lazy() call. return s return force_bytes(s, encoding, strings_only, errors) def force_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): """ Similar to smart_bytes, except that lazy instances are resolved to strings, rather than kept as lazy objects. If strings_only is True, don't convert (some) non-string-like objects. """ if isinstance(s, bytes): if encoding == 'utf-8': return s else: return s.decode('utf-8', errors).encode(encoding, errors) if strings_only and (s is None or isinstance(s, int)): return s if isinstance(s, Promise): return six.text_type(s).encode(encoding, errors) if not isinstance(s, six.string_types): try: if six.PY3: return six.text_type(s).encode(encoding) else: return bytes(s) except UnicodeEncodeError: if isinstance(s, Exception): # An Exception subclass containing non-ASCII data that doesn't # know how to print itself properly. We shouldn't raise a # further exception. return ' '.join([smart_bytes(arg, encoding, strings_only, errors) for arg in s]) return six.text_type(s).encode(encoding, errors) else: return s.encode(encoding, errors) if six.PY3: smart_str = smart_text force_str = force_text else: smart_str = smart_bytes force_str = force_bytes # backwards compatibility for Python 2 smart_unicode = smart_text force_unicode = force_text smart_str.__doc__ = """\ Apply smart_text in Python 3 and smart_bytes in Python 2. This is suitable for writing to sys.stdout (for instance). """ force_str.__doc__ = """\ Apply force_text in Python 3 and force_bytes in Python 2. """ def iri_to_uri(iri): """ Convert an Internationalized Resource Identifier (IRI) portion to a URI portion that is suitable for inclusion in a URL. This is the algorithm from section 3.1 of RFC 3987. However, since we are assuming input is either UTF-8 or unicode already, we can simplify things a little from the full method. Returns an ASCII string containing the encoded result. """ # The list of safe characters here is constructed from the "reserved" and # "unreserved" characters specified in sections 2.2 and 2.3 of RFC 3986: # reserved = gen-delims / sub-delims # gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@" # sub-delims = "!" / "$" / "&" / "'" / "(" / ")" # / "*" / "+" / "," / ";" / "=" # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" # Of the unreserved characters, urllib.quote already considers all but # the ~ safe. # The % character is also added to the list of safe characters here, as the # end of section 3.1 of RFC 3987 specifically mentions that % must not be # converted. if iri is None: return iri return quote(smart_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~") def filepath_to_uri(path): """Convert an file system path to a URI portion that is suitable for inclusion in a URL. We are assuming input is either UTF-8 or unicode already. This method will encode certain chars that would normally be recognized as special chars for URIs. Note that this method does not encode the ' character, as it is a valid character within URIs. See encodeURIComponent() JavaScript function for more details. Returns an ASCII string containing the encoded result. """ if path is None: return path # I know about `os.sep` and `os.altsep` but I want to leave # some flexibility for hardcoding separators. return quote(smart_bytes(path.replace("\\", "/")), safe=b"/~!*()'") # The encoding of the default system locale but falls back to the # given fallback encoding if the encoding is unsupported by python or could # not be determined. See tickets #10335 and #5846 try: DEFAULT_LOCALE_ENCODING = locale.getdefaultlocale()[1] or 'ascii' codecs.lookup(DEFAULT_LOCALE_ENCODING) except: DEFAULT_LOCALE_ENCODING = 'ascii' feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/feedgenerator.py0000644000076500000240000003746112765356444033106 0ustar jmstaff00000000000000""" Syndication feed generation library -- used for generating RSS, etc. Sample usage: >>> from django.utils import feedgenerator >>> feed = feedgenerator.Rss201rev2Feed( ... title="Poynter E-Media Tidbits", ... link="http://www.poynter.org/column.asp?id=31", ... description="A group Weblog by the sharpest minds in online media/journalism/publishing.", ... language="en", ... ) >>> feed.add_item( ... title="Hello", ... link="http://www.holovaty.com/test/", ... description="Testing." ... ) >>> with open('test.rss', 'w') as fp: ... feed.write(fp, 'utf-8') For definitions of the different versions of RSS, see: http://web.archive.org/web/20110718035220/http://diveintomark.org/archives/2004/02/04/incompatible-rss """ from __future__ import unicode_literals import datetime try: from urllib.parse import urlparse except ImportError: # Python 2 from urlparse import urlparse from .xmlutils import SimplerXMLGenerator from .encoding import force_text, iri_to_uri from . import datetime_safe from . import six from .six import StringIO from .timezone import is_aware def rfc2822_date(date): # We can't use strftime() because it produces locale-dependent results, so # we have to map english month and day names manually months = ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec',) days = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun') # Support datetime objects older than 1900 date = datetime_safe.new_datetime(date) # We do this ourselves to be timezone aware, email.Utils is not tz aware. dow = days[date.weekday()] month = months[date.month - 1] time_str = date.strftime('%s, %%d %s %%Y %%H:%%M:%%S ' % (dow, month)) if not six.PY3: # strftime returns a byte string in Python 2 time_str = time_str.decode('utf-8') if is_aware(date): offset = date.tzinfo.utcoffset(date) timezone = (offset.days * 24 * 60) + (offset.seconds // 60) hour, minute = divmod(timezone, 60) return time_str + '%+03d%02d' % (hour, minute) else: return time_str + '-0000' def rfc3339_date(date): # Support datetime objects older than 1900 date = datetime_safe.new_datetime(date) time_str = date.strftime('%Y-%m-%dT%H:%M:%S') if not six.PY3: # strftime returns a byte string in Python 2 time_str = time_str.decode('utf-8') if is_aware(date): offset = date.tzinfo.utcoffset(date) timezone = (offset.days * 24 * 60) + (offset.seconds // 60) hour, minute = divmod(timezone, 60) return time_str + '%+03d:%02d' % (hour, minute) else: return time_str + 'Z' def get_tag_uri(url, date): """ Creates a TagURI. See http://web.archive.org/web/20110514113830/http://diveintomark.org/archives/2004/05/28/howto-atom-id """ bits = urlparse(url) d = '' if date is not None: d = ',%s' % datetime_safe.new_datetime(date).strftime('%Y-%m-%d') fragment = '' if bits.fragment != '': fragment = '/%s' % (bits.fragment) return 'tag:%s%s:%s%s' % (bits.hostname, d, bits.path, fragment) class SyndicationFeed(object): "Base class for all syndication feeds. Subclasses should provide write()" def __init__(self, title, link, description, language=None, author_email=None, author_name=None, author_link=None, subtitle=None, categories=None, feed_url=None, feed_copyright=None, feed_guid=None, ttl=None, **kwargs): to_unicode = lambda s: force_text(s, strings_only=True) if categories: categories = [force_text(c) for c in categories] if ttl is not None: # Force ints to unicode ttl = force_text(ttl) self.feed = { 'title': to_unicode(title), 'link': iri_to_uri(link), 'description': to_unicode(description), 'language': to_unicode(language), 'author_email': to_unicode(author_email), 'author_name': to_unicode(author_name), 'author_link': iri_to_uri(author_link), 'subtitle': to_unicode(subtitle), 'categories': categories or (), 'feed_url': iri_to_uri(feed_url), 'feed_copyright': to_unicode(feed_copyright), 'id': feed_guid or link, 'ttl': ttl, } self.feed.update(kwargs) self.items = [] def add_item(self, title, link, description, author_email=None, author_name=None, author_link=None, pubdate=None, comments=None, unique_id=None, enclosure=None, categories=(), item_copyright=None, ttl=None, content=None, updateddate=None, **kwargs): """ Adds an item to the feed. All args are expected to be Python Unicode objects except pubdate and updateddate, which are datetime.datetime objects, and enclosure, which is an instance of the Enclosure class. """ to_unicode = lambda s: force_text(s, strings_only=True) if categories: categories = [to_unicode(c) for c in categories] if ttl is not None: # Force ints to unicode ttl = force_text(ttl) item = { 'title': to_unicode(title), 'link': iri_to_uri(link), 'description': to_unicode(description), 'content': to_unicode(content), 'author_email': to_unicode(author_email), 'author_name': to_unicode(author_name), 'author_link': iri_to_uri(author_link), 'pubdate': pubdate, 'updateddate': updateddate, 'comments': to_unicode(comments), 'unique_id': to_unicode(unique_id), 'enclosure': enclosure, 'categories': categories or (), 'item_copyright': to_unicode(item_copyright), 'ttl': ttl, } item.update(kwargs) self.items.append(item) def num_items(self): return len(self.items) def root_attributes(self): """ Return extra attributes to place on the root (i.e. feed/channel) element. Called from write(). """ return {} def add_root_elements(self, handler): """ Add elements in the root (i.e. feed/channel) element. Called from write(). """ pass def item_attributes(self, item): """ Return extra attributes to place on each item (i.e. item/entry) element. """ return {} def add_item_elements(self, handler, item): """ Add elements on each item (i.e. item/entry) element. """ pass def write(self, outfile, encoding): """ Outputs the feed in the given encoding to outfile, which is a file-like object. Subclasses should override this. """ raise NotImplementedError def writeString(self, encoding): """ Returns the feed in the given encoding as a string. """ s = StringIO() self.write(s, encoding) return s.getvalue() def latest_post_date(self): """ Returns the latest item's pubdate or updateddate. If no item has either date, returns the current date/time. """ updates = [i['pubdate'] for i in self.items if i['pubdate'] is not None] updates.extend(i['updateddate'] for i in self.items if i['updateddate'] is not None) if len(updates) > 0: updates.sort() return updates[-1] else: return datetime.datetime.now() class Enclosure(object): "Represents an RSS enclosure" def __init__(self, url, length, mime_type): "All args are expected to be Python Unicode objects" self.length, self.mime_type = length, mime_type self.url = iri_to_uri(url) class RssFeed(SyndicationFeed): mime_type = 'application/rss+xml; charset=utf-8' def write(self, outfile, encoding): handler = SimplerXMLGenerator(outfile, encoding) handler.startDocument() handler.startElement("rss", self.rss_attributes()) handler.startElement("channel", self.root_attributes()) self.add_root_elements(handler) self.write_items(handler) self.endChannelElement(handler) handler.endElement("rss") def rss_attributes(self): return {'version': self._version} def write_items(self, handler): for item in self.items: handler.startElement('item', self.item_attributes(item)) self.add_item_elements(handler, item) handler.endElement("item") def add_root_elements(self, handler): # Required Elements as per the specification handler.addQuickElement("title", self.feed['title']) handler.addQuickElement("link", self.feed['link']) handler.addQuickElement("description", self.feed['description']) # Optional Channel Elements if self.feed['language'] is not None: handler.addQuickElement("language", self.feed['language']) for cat in self.feed['categories']: handler.addQuickElement("category", cat) if self.feed['feed_copyright'] is not None: handler.addQuickElement("copyright", self.feed['feed_copyright']) handler.addQuickElement("lastBuildDate", rfc2822_date(self.latest_post_date())) if self.feed['ttl'] is not None: handler.addQuickElement("ttl", self.feed['ttl']) def endChannelElement(self, handler): handler.endElement("channel") class RssUserland091Feed(RssFeed): _version = "0.91" def add_item_elements(self, handler, item): handler.addQuickElement("title", item['title']) handler.addQuickElement("link", item['link']) if item['description'] is not None: handler.addQuickElement("description", item['description']) class Rss201rev2Feed(RssFeed): # Spec: http://blogs.law.harvard.edu/tech/rss _version = "2.0" def add_item_elements(self, handler, item): handler.addQuickElement("title", item['title']) handler.addQuickElement("link", item['link']) if item['description'] is not None: handler.addQuickElement("description", item['description']) # Author information. if item["author_name"] and item["author_email"]: handler.addQuickElement("author", "%s (%s)" % \ (item['author_email'], item['author_name'])) elif item["author_email"]: handler.addQuickElement("author", item["author_email"]) elif item["author_name"]: handler.addQuickElement("dc:creator", item["author_name"], {"xmlns:dc": "http://purl.org/dc/elements/1.1/"}) if item['pubdate'] is not None: handler.addQuickElement("pubDate", rfc2822_date(item['pubdate'])) if item['comments'] is not None: handler.addQuickElement("comments", item['comments']) if item['unique_id'] is not None: handler.addQuickElement("guid", item['unique_id'], attrs={'isPermaLink': 'false'}) if item['ttl'] is not None: handler.addQuickElement("ttl", item['ttl']) # Enclosure. if item['enclosure'] is not None: handler.addQuickElement("enclosure", '', {"url": item['enclosure'].url, "length": item['enclosure'].length, "type": item['enclosure'].mime_type}) # Categories. for cat in item['categories']: handler.addQuickElement("category", cat) class Atom1Feed(SyndicationFeed): # Spec: http://atompub.org/2005/07/11/draft-ietf-atompub-format-10.html mime_type = 'application/atom+xml; charset=utf-8' ns = "http://www.w3.org/2005/Atom" def write(self, outfile, encoding): handler = SimplerXMLGenerator(outfile, encoding) handler.startDocument() handler.startElement('feed', self.root_attributes()) self.add_root_elements(handler) self.write_items(handler) handler.endElement("feed") def root_attributes(self): if self.feed['language'] is not None: return {"xmlns": self.ns, "xml:lang": self.feed['language']} else: return {"xmlns": self.ns} def add_root_elements(self, handler): handler.addQuickElement("title", self.feed['title']) handler.addQuickElement("link", "", {"rel": "alternate", "href": self.feed['link']}) if self.feed['feed_url'] is not None: handler.addQuickElement("link", "", {"rel": "self", "href": self.feed['feed_url']}) handler.addQuickElement("id", self.feed['id']) handler.addQuickElement("updated", rfc3339_date(self.latest_post_date())) if self.feed['author_name'] is not None: handler.startElement("author", {}) handler.addQuickElement("name", self.feed['author_name']) if self.feed['author_email'] is not None: handler.addQuickElement("email", self.feed['author_email']) if self.feed['author_link'] is not None: handler.addQuickElement("uri", self.feed['author_link']) handler.endElement("author") if self.feed['subtitle'] is not None: handler.addQuickElement("subtitle", self.feed['subtitle']) for cat in self.feed['categories']: handler.addQuickElement("category", "", {"term": cat}) if self.feed['feed_copyright'] is not None: handler.addQuickElement("rights", self.feed['feed_copyright']) def write_items(self, handler): for item in self.items: handler.startElement("entry", self.item_attributes(item)) self.add_item_elements(handler, item) handler.endElement("entry") def add_item_elements(self, handler, item): handler.addQuickElement("title", item['title']) handler.addQuickElement("link", "", {"href": item['link'], "rel": "alternate"}) updateddate = datetime.datetime.now() if item['pubdate'] is not None: handler.addQuickElement("published", rfc3339_date(item['pubdate'])) updateddate = item['pubdate'] if item['updateddate'] is not None: updateddate = item['updateddate'] handler.addQuickElement("updated", rfc3339_date(updateddate)) # Author information. if item['author_name'] is not None: handler.startElement("author", {}) handler.addQuickElement("name", item['author_name']) if item['author_email'] is not None: handler.addQuickElement("email", item['author_email']) if item['author_link'] is not None: handler.addQuickElement("uri", item['author_link']) handler.endElement("author") # Unique ID. if item['unique_id'] is not None: unique_id = item['unique_id'] else: unique_id = get_tag_uri(item['link'], item['pubdate']) handler.addQuickElement("id", unique_id) # Summary. if item['description'] is not None: handler.addQuickElement("summary", item['description'], {"type": "html"}) # Full content. if item['content'] is not None: handler.addQuickElement("content", item['content'], {"type": "html"}) # Enclosure. if item['enclosure'] is not None: handler.addQuickElement("link", '', {"rel": "enclosure", "href": item['enclosure'].url, "length": item['enclosure'].length, "type": item['enclosure'].mime_type}) # Categories. for cat in item['categories']: handler.addQuickElement("category", "", {"term": cat}) # Rights. if item['item_copyright'] is not None: handler.addQuickElement("rights", item['item_copyright']) # This isolates the decision of what the system default is, so calling code can # do "feedgenerator.DefaultFeed" instead of "feedgenerator.Rss201rev2Feed". DefaultFeed = Rss201rev2Feed feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/functional.py0000644000076500000240000003267712765356444032442 0ustar jmstaff00000000000000import copy import operator from functools import wraps, update_wrapper import sys from . import six # You can't trivially replace this `functools.partial` because this binds to # classes and returns bound instances, whereas functools.partial (on CPython) # is a type and its instances don't bind. def curry(_curried_func, *args, **kwargs): def _curried(*moreargs, **morekwargs): return _curried_func(*(args+moreargs), **dict(kwargs, **morekwargs)) return _curried def memoize(func, cache, num_args): """ Wrap a function so that results for any argument tuple are stored in 'cache'. Note that the args to the function must be usable as dictionary keys. Only the first num_args are considered when creating the key. """ @wraps(func) def wrapper(*args): mem_args = args[:num_args] if mem_args in cache: return cache[mem_args] result = func(*args) cache[mem_args] = result return result return wrapper class cached_property(object): """ Decorator that creates converts a method with a single self argument into a property cached on the instance. """ def __init__(self, func): self.func = func def __get__(self, instance, type): res = instance.__dict__[self.func.__name__] = self.func(instance) return res class Promise(object): """ This is just a base class for the proxy class created in the closure of the lazy function. It can be used to recognize promises in code. """ pass def lazy(func, *resultclasses): """ Turns any callable into a lazy evaluated callable. You need to give result classes or types -- at least one is needed so that the automatic forcing of the lazy evaluation code is triggered. Results are not memoized; the function is evaluated on every access. """ @total_ordering class __proxy__(Promise): """ Encapsulate a function call and act as a proxy for methods that are called on the result of that function. The function is not evaluated until one of the methods on the result is called. """ __dispatch = None def __init__(self, args, kw): self.__args = args self.__kw = kw if self.__dispatch is None: self.__prepare_class__() def __reduce__(self): return ( _lazy_proxy_unpickle, (func, self.__args, self.__kw) + resultclasses ) def __prepare_class__(cls): cls.__dispatch = {} for resultclass in resultclasses: cls.__dispatch[resultclass] = {} for type_ in reversed(resultclass.mro()): for (k, v) in type_.__dict__.items(): # All __promise__ return the same wrapper method, but they # also do setup, inserting the method into the dispatch # dict. meth = cls.__promise__(resultclass, k, v) if hasattr(cls, k): continue setattr(cls, k, meth) cls._delegate_bytes = bytes in resultclasses cls._delegate_text = six.text_type in resultclasses assert not (cls._delegate_bytes and cls._delegate_text), "Cannot call lazy() with both bytes and text return types." if cls._delegate_text: if six.PY3: cls.__str__ = cls.__text_cast else: cls.__unicode__ = cls.__text_cast elif cls._delegate_bytes: if six.PY3: cls.__bytes__ = cls.__bytes_cast else: cls.__str__ = cls.__bytes_cast __prepare_class__ = classmethod(__prepare_class__) def __promise__(cls, klass, funcname, method): # Builds a wrapper around some magic method and registers that magic # method for the given type and method name. def __wrapper__(self, *args, **kw): # Automatically triggers the evaluation of a lazy value and # applies the given magic method of the result type. res = func(*self.__args, **self.__kw) for t in type(res).mro(): if t in self.__dispatch: return self.__dispatch[t][funcname](res, *args, **kw) raise TypeError("Lazy object returned unexpected type.") if klass not in cls.__dispatch: cls.__dispatch[klass] = {} cls.__dispatch[klass][funcname] = method return __wrapper__ __promise__ = classmethod(__promise__) def __text_cast(self): return func(*self.__args, **self.__kw) def __bytes_cast(self): return bytes(func(*self.__args, **self.__kw)) def __cast(self): if self._delegate_bytes: return self.__bytes_cast() elif self._delegate_text: return self.__text_cast() else: return func(*self.__args, **self.__kw) def __eq__(self, other): if isinstance(other, Promise): other = other.__cast() return self.__cast() == other def __lt__(self, other): if isinstance(other, Promise): other = other.__cast() return self.__cast() < other __hash__ = object.__hash__ def __mod__(self, rhs): if self._delegate_bytes and not six.PY3: return bytes(self) % rhs elif self._delegate_text: return six.text_type(self) % rhs else: raise AssertionError('__mod__ not supported for non-string types') def __deepcopy__(self, memo): # Instances of this class are effectively immutable. It's just a # collection of functions. So we don't need to do anything # complicated for copying. memo[id(self)] = self return self @wraps(func) def __wrapper__(*args, **kw): # Creates the proxy object, instead of the actual value. return __proxy__(args, kw) return __wrapper__ def _lazy_proxy_unpickle(func, args, kwargs, *resultclasses): return lazy(func, *resultclasses)(*args, **kwargs) def allow_lazy(func, *resultclasses): """ A decorator that allows a function to be called with one or more lazy arguments. If none of the args are lazy, the function is evaluated immediately, otherwise a __proxy__ is returned that will evaluate the function when needed. """ @wraps(func) def wrapper(*args, **kwargs): for arg in list(args) + list(six.itervalues(kwargs)): if isinstance(arg, Promise): break else: return func(*args, **kwargs) return lazy(func, *resultclasses)(*args, **kwargs) return wrapper empty = object() def new_method_proxy(func): def inner(self, *args): if self._wrapped is empty: self._setup() return func(self._wrapped, *args) return inner class LazyObject(object): """ A wrapper for another class that can be used to delay instantiation of the wrapped class. By subclassing, you have the opportunity to intercept and alter the instantiation. If you don't need to do that, use SimpleLazyObject. """ def __init__(self): self._wrapped = empty __getattr__ = new_method_proxy(getattr) def __setattr__(self, name, value): if name == "_wrapped": # Assign to __dict__ to avoid infinite __setattr__ loops. self.__dict__["_wrapped"] = value else: if self._wrapped is empty: self._setup() setattr(self._wrapped, name, value) def __delattr__(self, name): if name == "_wrapped": raise TypeError("can't delete _wrapped.") if self._wrapped is empty: self._setup() delattr(self._wrapped, name) def _setup(self): """ Must be implemented by subclasses to initialise the wrapped object. """ raise NotImplementedError # introspection support: __dir__ = new_method_proxy(dir) # Workaround for http://bugs.python.org/issue12370 _super = super class SimpleLazyObject(LazyObject): """ A lazy object initialised from any function. Designed for compound objects of unknown type. For builtins or objects of known type, use django.utils.functional.lazy. """ def __init__(self, func): """ Pass in a callable that returns the object to be wrapped. If copies are made of the resulting SimpleLazyObject, which can happen in various circumstances within Django, then you must ensure that the callable can be safely run more than once and will return the same value. """ self.__dict__['_setupfunc'] = func _super(SimpleLazyObject, self).__init__() def _setup(self): self._wrapped = self._setupfunc() if six.PY3: __bytes__ = new_method_proxy(bytes) __str__ = new_method_proxy(str) else: __str__ = new_method_proxy(str) __unicode__ = new_method_proxy(unicode) def __deepcopy__(self, memo): if self._wrapped is empty: # We have to use SimpleLazyObject, not self.__class__, because the # latter is proxied. result = SimpleLazyObject(self._setupfunc) memo[id(self)] = result return result else: return copy.deepcopy(self._wrapped, memo) # Because we have messed with __class__ below, we confuse pickle as to what # class we are pickling. It also appears to stop __reduce__ from being # called. So, we define __getstate__ in a way that cooperates with the way # that pickle interprets this class. This fails when the wrapped class is a # builtin, but it is better than nothing. def __getstate__(self): if self._wrapped is empty: self._setup() return self._wrapped.__dict__ # Need to pretend to be the wrapped class, for the sake of objects that care # about this (especially in equality tests) __class__ = property(new_method_proxy(operator.attrgetter("__class__"))) __eq__ = new_method_proxy(operator.eq) __hash__ = new_method_proxy(hash) __bool__ = new_method_proxy(bool) # Python 3 __nonzero__ = __bool__ # Python 2 class lazy_property(property): """ A property that works with subclasses by wrapping the decorated functions of the base class. """ def __new__(cls, fget=None, fset=None, fdel=None, doc=None): if fget is not None: @wraps(fget) def fget(instance, instance_type=None, name=fget.__name__): return getattr(instance, name)() if fset is not None: @wraps(fset) def fset(instance, value, name=fset.__name__): return getattr(instance, name)(value) if fdel is not None: @wraps(fdel) def fdel(instance, name=fdel.__name__): return getattr(instance, name)() return property(fget, fset, fdel, doc) def partition(predicate, values): """ Splits the values into two sets, based on the return value of the function (True/False). e.g.: >>> partition(lambda x: x > 3, range(5)) [0, 1, 2, 3], [4] """ results = ([], []) for item in values: results[predicate(item)].append(item) return results if sys.version_info >= (2,7,2): from functools import total_ordering else: # For Python < 2.7.2. Python 2.6 does not have total_ordering, and # total_ordering in 2.7 versions prior to 2.7.2 is buggy. See # http://bugs.python.org/issue10042 for details. For these versions use # code borrowed from Python 2.7.3. def total_ordering(cls): """Class decorator that fills in missing ordering methods""" convert = { '__lt__': [('__gt__', lambda self, other: not (self < other or self == other)), ('__le__', lambda self, other: self < other or self == other), ('__ge__', lambda self, other: not self < other)], '__le__': [('__ge__', lambda self, other: not self <= other or self == other), ('__lt__', lambda self, other: self <= other and not self == other), ('__gt__', lambda self, other: not self <= other)], '__gt__': [('__lt__', lambda self, other: not (self > other or self == other)), ('__ge__', lambda self, other: self > other or self == other), ('__le__', lambda self, other: not self > other)], '__ge__': [('__le__', lambda self, other: (not self >= other) or self == other), ('__gt__', lambda self, other: self >= other and not self == other), ('__lt__', lambda self, other: not self >= other)] } roots = set(dir(cls)) & set(convert) if not roots: raise ValueError('must define at least one ordering operation: < > <= >=') root = max(roots) # prefer __lt__ to __le__ to __gt__ to __ge__ for opname, opfunc in convert[root]: if opname not in roots: opfunc.__name__ = opname opfunc.__doc__ = getattr(int, opname).__doc__ setattr(cls, opname, opfunc) return cls feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/six.py0000644000076500000240000002440112765356444031065 0ustar jmstaff00000000000000"""Utilities for writing code that runs on Python 2 and 3""" import operator import sys import types __author__ = "Benjamin Peterson " __version__ = "1.1.0" # True if we are running on Python 3. PY3 = sys.version_info[0] == 3 if PY3: string_types = str, integer_types = int, class_types = type, text_type = str binary_type = bytes MAXSIZE = sys.maxsize else: string_types = basestring, integer_types = (int, long) class_types = (type, types.ClassType) text_type = unicode binary_type = str # It's possible to have sizeof(long) != sizeof(Py_ssize_t). class X(object): def __len__(self): return 1 << 31 try: len(X()) except OverflowError: # 32-bit MAXSIZE = int((1 << 31) - 1) else: # 64-bit MAXSIZE = int((1 << 63) - 1) del X def _add_doc(func, doc): """Add documentation to a function.""" func.__doc__ = doc def _import_module(name): """Import module, returning the module after the last dot.""" __import__(name) return sys.modules[name] class _LazyDescr(object): def __init__(self, name): self.name = name def __get__(self, obj, tp): result = self._resolve() setattr(obj, self.name, result) # This is a bit ugly, but it avoids running this again. delattr(tp, self.name) return result class MovedModule(_LazyDescr): def __init__(self, name, old, new=None): super(MovedModule, self).__init__(name) if PY3: if new is None: new = name self.mod = new else: self.mod = old def _resolve(self): return _import_module(self.mod) class MovedAttribute(_LazyDescr): def __init__(self, name, old_mod, new_mod, old_attr=None, new_attr=None): super(MovedAttribute, self).__init__(name) if PY3: if new_mod is None: new_mod = name self.mod = new_mod if new_attr is None: if old_attr is None: new_attr = name else: new_attr = old_attr self.attr = new_attr else: self.mod = old_mod if old_attr is None: old_attr = name self.attr = old_attr def _resolve(self): module = _import_module(self.mod) return getattr(module, self.attr) class _MovedItems(types.ModuleType): """Lazy loading of moved objects""" _moved_attributes = [ MovedAttribute("cStringIO", "cStringIO", "io", "StringIO"), MovedAttribute("filter", "itertools", "builtins", "ifilter", "filter"), MovedAttribute("input", "__builtin__", "builtins", "raw_input", "input"), MovedAttribute("map", "itertools", "builtins", "imap", "map"), MovedAttribute("reload_module", "__builtin__", "imp", "reload"), MovedAttribute("reduce", "__builtin__", "functools"), MovedAttribute("StringIO", "StringIO", "io"), MovedAttribute("xrange", "__builtin__", "builtins", "xrange", "range"), MovedAttribute("zip", "itertools", "builtins", "izip", "zip"), MovedModule("builtins", "__builtin__"), MovedModule("configparser", "ConfigParser"), MovedModule("copyreg", "copy_reg"), MovedModule("http_cookiejar", "cookielib", "http.cookiejar"), MovedModule("http_cookies", "Cookie", "http.cookies"), MovedModule("html_entities", "htmlentitydefs", "html.entities"), MovedModule("html_parser", "HTMLParser", "html.parser"), MovedModule("http_client", "httplib", "http.client"), MovedModule("BaseHTTPServer", "BaseHTTPServer", "http.server"), MovedModule("CGIHTTPServer", "CGIHTTPServer", "http.server"), MovedModule("SimpleHTTPServer", "SimpleHTTPServer", "http.server"), MovedModule("cPickle", "cPickle", "pickle"), MovedModule("queue", "Queue"), MovedModule("reprlib", "repr"), MovedModule("socketserver", "SocketServer"), MovedModule("tkinter", "Tkinter"), MovedModule("tkinter_dialog", "Dialog", "tkinter.dialog"), MovedModule("tkinter_filedialog", "FileDialog", "tkinter.filedialog"), MovedModule("tkinter_scrolledtext", "ScrolledText", "tkinter.scrolledtext"), MovedModule("tkinter_simpledialog", "SimpleDialog", "tkinter.simpledialog"), MovedModule("tkinter_tix", "Tix", "tkinter.tix"), MovedModule("tkinter_constants", "Tkconstants", "tkinter.constants"), MovedModule("tkinter_dnd", "Tkdnd", "tkinter.dnd"), MovedModule("tkinter_colorchooser", "tkColorChooser", "tkinter.colorchooser"), MovedModule("tkinter_commondialog", "tkCommonDialog", "tkinter.commondialog"), MovedModule("tkinter_tkfiledialog", "tkFileDialog", "tkinter.filedialog"), MovedModule("tkinter_font", "tkFont", "tkinter.font"), MovedModule("tkinter_messagebox", "tkMessageBox", "tkinter.messagebox"), MovedModule("tkinter_tksimpledialog", "tkSimpleDialog", "tkinter.simpledialog"), MovedModule("urllib_robotparser", "robotparser", "urllib.robotparser"), MovedModule("winreg", "_winreg"), ] for attr in _moved_attributes: setattr(_MovedItems, attr.name, attr) del attr moves = sys.modules["django.utils.six.moves"] = _MovedItems("moves") def add_move(move): """Add an item to six.moves.""" setattr(_MovedItems, move.name, move) def remove_move(name): """Remove item from six.moves.""" try: delattr(_MovedItems, name) except AttributeError: try: del moves.__dict__[name] except KeyError: raise AttributeError("no such move, %r" % (name,)) if PY3: _meth_func = "__func__" _meth_self = "__self__" _func_code = "__code__" _func_defaults = "__defaults__" _iterkeys = "keys" _itervalues = "values" _iteritems = "items" else: _meth_func = "im_func" _meth_self = "im_self" _func_code = "func_code" _func_defaults = "func_defaults" _iterkeys = "iterkeys" _itervalues = "itervalues" _iteritems = "iteritems" if PY3: def get_unbound_function(unbound): return unbound advance_iterator = next def callable(obj): return any("__call__" in klass.__dict__ for klass in type(obj).__mro__) else: def get_unbound_function(unbound): return unbound.im_func def advance_iterator(it): return it.next() callable = callable _add_doc(get_unbound_function, """Get the function out of a possibly unbound function""") get_method_function = operator.attrgetter(_meth_func) get_method_self = operator.attrgetter(_meth_self) get_function_code = operator.attrgetter(_func_code) get_function_defaults = operator.attrgetter(_func_defaults) def iterkeys(d): """Return an iterator over the keys of a dictionary.""" return getattr(d, _iterkeys)() def itervalues(d): """Return an iterator over the values of a dictionary.""" return getattr(d, _itervalues)() def iteritems(d): """Return an iterator over the (key, value) pairs of a dictionary.""" return getattr(d, _iteritems)() if PY3: def b(s): return s.encode("latin-1") def u(s): return s if sys.version_info[1] <= 1: def int2byte(i): return bytes((i,)) else: # This is about 2x faster than the implementation above on 3.2+ int2byte = operator.methodcaller("to_bytes", 1, "big") import io StringIO = io.StringIO BytesIO = io.BytesIO else: def b(s): return s def u(s): return unicode(s, "unicode_escape") int2byte = chr import StringIO StringIO = BytesIO = StringIO.StringIO _add_doc(b, """Byte literal""") _add_doc(u, """Text literal""") if PY3: import builtins exec_ = getattr(builtins, "exec") def reraise(tp, value, tb=None): if value.__traceback__ is not tb: raise value.with_traceback(tb) raise value print_ = getattr(builtins, "print") del builtins else: def exec_(code, globs=None, locs=None): """Execute code in a namespace.""" if globs is None: frame = sys._getframe(1) globs = frame.f_globals if locs is None: locs = frame.f_locals del frame elif locs is None: locs = globs exec("""exec code in globs, locs""") exec_("""def reraise(tp, value, tb=None): raise tp, value, tb """) def print_(*args, **kwargs): """The new-style print function.""" fp = kwargs.pop("file", sys.stdout) if fp is None: return def write(data): if not isinstance(data, basestring): data = str(data) fp.write(data) want_unicode = False sep = kwargs.pop("sep", None) if sep is not None: if isinstance(sep, unicode): want_unicode = True elif not isinstance(sep, str): raise TypeError("sep must be None or a string") end = kwargs.pop("end", None) if end is not None: if isinstance(end, unicode): want_unicode = True elif not isinstance(end, str): raise TypeError("end must be None or a string") if kwargs: raise TypeError("invalid keyword arguments to print()") if not want_unicode: for arg in args: if isinstance(arg, unicode): want_unicode = True break if want_unicode: newline = unicode("\n") space = unicode(" ") else: newline = "\n" space = " " if sep is None: sep = space if end is None: end = newline for i, arg in enumerate(args): if i: write(sep) write(arg) write(end) _add_doc(reraise, """Reraise an exception.""") def with_metaclass(meta, base=object): """Create a base class with a metaclass.""" return meta("NewBase", (base,), {}) ### Additional customizations for Django ### if PY3: _iterlists = "lists" else: _iterlists = "iterlists" def iterlists(d): """Return an iterator over the values of a MultiValueDict.""" return getattr(d, _iterlists)() add_move(MovedModule("_dummy_thread", "dummy_thread")) add_move(MovedModule("_thread", "thread")) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/timezone.py0000644000076500000240000002052512765356444032117 0ustar jmstaff00000000000000"""Timezone helper functions. This module uses pytz when it's available and fallbacks when it isn't. """ from datetime import datetime, timedelta, tzinfo from threading import local import time as _time try: import pytz except ImportError: pytz = None # ### from django.conf import settings from . import six __all__ = [ 'utc', 'get_default_timezone', 'get_current_timezone', 'activate', 'deactivate', 'override', 'is_naive', 'is_aware', 'make_aware', 'make_naive', ] # UTC and local time zones ZERO = timedelta(0) class UTC(tzinfo): """ UTC implementation taken from Python's docs. Used only when pytz isn't available. """ def __repr__(self): return "" def utcoffset(self, dt): return ZERO def tzname(self, dt): return "UTC" def dst(self, dt): return ZERO class LocalTimezone(tzinfo): """ Local time implementation taken from Python's docs. Used only when pytz isn't available, and most likely inaccurate. If you're having trouble with this class, don't waste your time, just install pytz. """ def __init__(self): # This code is moved in __init__ to execute it as late as possible # See get_default_timezone(). self.STDOFFSET = timedelta(seconds=-_time.timezone) if _time.daylight: self.DSTOFFSET = timedelta(seconds=-_time.altzone) else: self.DSTOFFSET = self.STDOFFSET self.DSTDIFF = self.DSTOFFSET - self.STDOFFSET tzinfo.__init__(self) def __repr__(self): return "" def utcoffset(self, dt): if self._isdst(dt): return self.DSTOFFSET else: return self.STDOFFSET def dst(self, dt): if self._isdst(dt): return self.DSTDIFF else: return ZERO def tzname(self, dt): return _time.tzname[self._isdst(dt)] def _isdst(self, dt): tt = (dt.year, dt.month, dt.day, dt.hour, dt.minute, dt.second, dt.weekday(), 0, 0) stamp = _time.mktime(tt) tt = _time.localtime(stamp) return tt.tm_isdst > 0 utc = pytz.utc if pytz else UTC() """UTC time zone as a tzinfo instance.""" # ### # In order to avoid accessing the settings at compile time, # ### # wrap the expression in a function and cache the result. # ### _localtime = None # ### # ### def get_default_timezone(): # ### """ # ### Returns the default time zone as a tzinfo instance. # ### # ### This is the time zone defined by settings.TIME_ZONE. # ### # ### See also :func:`get_current_timezone`. # ### """ # ### global _localtime # ### if _localtime is None: # ### if isinstance(settings.TIME_ZONE, six.string_types) and pytz is not None: # ### _localtime = pytz.timezone(settings.TIME_ZONE) # ### else: # ### _localtime = LocalTimezone() # ### return _localtime # This function exists for consistency with get_current_timezone_name def get_default_timezone_name(): """ Returns the name of the default time zone. """ return _get_timezone_name(get_default_timezone()) _active = local() def get_current_timezone(): """ Returns the currently active time zone as a tzinfo instance. """ return getattr(_active, "value", get_default_timezone()) def get_current_timezone_name(): """ Returns the name of the currently active time zone. """ return _get_timezone_name(get_current_timezone()) def _get_timezone_name(timezone): """ Returns the name of ``timezone``. """ try: # for pytz timezones return timezone.zone except AttributeError: # for regular tzinfo objects local_now = datetime.now(timezone) return timezone.tzname(local_now) # Timezone selection functions. # These functions don't change os.environ['TZ'] and call time.tzset() # because it isn't thread safe. def activate(timezone): """ Sets the time zone for the current thread. The ``timezone`` argument must be an instance of a tzinfo subclass or a time zone name. If it is a time zone name, pytz is required. """ if isinstance(timezone, tzinfo): _active.value = timezone elif isinstance(timezone, six.string_types) and pytz is not None: _active.value = pytz.timezone(timezone) else: raise ValueError("Invalid timezone: %r" % timezone) def deactivate(): """ Unsets the time zone for the current thread. Django will then use the time zone defined by settings.TIME_ZONE. """ if hasattr(_active, "value"): del _active.value class override(object): """ Temporarily set the time zone for the current thread. This is a context manager that uses ``~django.utils.timezone.activate()`` to set the timezone on entry, and restores the previously active timezone on exit. The ``timezone`` argument must be an instance of a ``tzinfo`` subclass, a time zone name, or ``None``. If is it a time zone name, pytz is required. If it is ``None``, Django enables the default time zone. """ def __init__(self, timezone): self.timezone = timezone self.old_timezone = getattr(_active, 'value', None) def __enter__(self): if self.timezone is None: deactivate() else: activate(self.timezone) def __exit__(self, exc_type, exc_value, traceback): if self.old_timezone is not None: _active.value = self.old_timezone else: del _active.value # ### # Templates # ### # ### def template_localtime(value, use_tz=None): # ### """ # ### Checks if value is a datetime and converts it to local time if necessary. # ### # ### If use_tz is provided and is not None, that will force the value to # ### be converted (or not), overriding the value of settings.USE_TZ. # ### # ### This function is designed for use by the template engine. # ### """ # ### should_convert = (isinstance(value, datetime) # ### and (settings.USE_TZ if use_tz is None else use_tz) # ### and not is_naive(value) # ### and getattr(value, 'convert_to_local_time', True)) # ### return localtime(value) if should_convert else value # Utilities def localtime(value, timezone=None): """ Converts an aware datetime.datetime to local time. Local time is defined by the current time zone, unless another time zone is specified. """ if timezone is None: timezone = get_current_timezone() value = value.astimezone(timezone) if hasattr(timezone, 'normalize'): # available for pytz time zones value = timezone.normalize(value) return value # ### def now(): # ### """ # ### Returns an aware or naive datetime.datetime, depending on settings.USE_TZ. # ### """ # ### if settings.USE_TZ: # ### # timeit shows that datetime.now(tz=utc) is 24% slower # ### return datetime.utcnow().replace(tzinfo=utc) # ### else: # ### return datetime.now() # By design, these four functions don't perform any checks on their arguments. # The caller should ensure that they don't receive an invalid value like None. def is_aware(value): """ Determines if a given datetime.datetime is aware. The logic is described in Python's docs: http://docs.python.org/library/datetime.html#datetime.tzinfo """ return value.tzinfo is not None and value.tzinfo.utcoffset(value) is not None def is_naive(value): """ Determines if a given datetime.datetime is naive. The logic is described in Python's docs: http://docs.python.org/library/datetime.html#datetime.tzinfo """ return value.tzinfo is None or value.tzinfo.utcoffset(value) is None def make_aware(value, timezone): """ Makes a naive datetime.datetime in a given time zone aware. """ if hasattr(timezone, 'localize'): # available for pytz time zones return timezone.localize(value, is_dst=None) else: # may be wrong around DST changes return value.replace(tzinfo=timezone) def make_naive(value, timezone): """ Makes an aware datetime.datetime naive in a given time zone. """ value = value.astimezone(timezone) if hasattr(timezone, 'normalize'): # available for pytz time zones value = timezone.normalize(value) return value.replace(tzinfo=None) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/feedgenerator/django/utils/xmlutils.py0000644000076500000240000000133212765356444032141 0ustar jmstaff00000000000000""" Utilities for XML generation/parsing. """ import six from xml.sax.saxutils import XMLGenerator, quoteattr class SimplerXMLGenerator(XMLGenerator): def addQuickElement(self, name, contents=None, attrs=None): "Convenience method for adding an element with no children" if attrs is None: attrs = {} self.startElement(name, attrs) if contents is not None: self.characters(contents) self.endElement(name) def startElement(self, name, attrs): self._write('<' + name) # sort attributes for consistent output for (name, value) in sorted(attrs.items()): self._write(' %s=%s' % (name, quoteattr(value))) self._write(six.u('>')) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/0000755000076500000240000000000012765362057024465 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/__init__.py0000644000076500000240000002231512700725536026573 0ustar jmstaff00000000000000"""Cache lines from files. This is intended to read lines from modules imported -- hence if a filename is not found, it will look down the module search path for a file by that name. """ import functools import io import sys import os import tokenize __all__ = ["getline", "clearcache", "checkcache"] def getline(filename, lineno, module_globals=None): lines = getlines(filename, module_globals) if 1 <= lineno <= len(lines): return lines[lineno-1] else: return '' # The cache # The cache. Maps filenames to either a thunk which will provide source code, # or a tuple (size, mtime, lines, fullname) once loaded. cache = {} def clearcache(): """Clear the cache entirely.""" global cache cache = {} def getlines(filename, module_globals=None): """Get the lines for a file from the cache. Update the cache if it doesn't contain an entry for this file already.""" if filename in cache: entry = cache[filename] if len(entry) == 1: return updatecache(filename, module_globals) return cache[filename][2] else: return updatecache(filename, module_globals) def checkcache(filename=None): """Discard cache entries that are out of date. (This is not checked upon each call!)""" if filename is None: filenames = list(cache.keys()) else: if filename in cache: filenames = [filename] else: return for filename in filenames: entry = cache[filename] if len(entry) == 1: # lazy cache entry, leave it lazy. continue size, mtime, lines, fullname = entry if mtime is None: continue # no-op for files loaded via a __loader__ try: stat = os.stat(fullname) except OSError: del cache[filename] continue if size != stat.st_size or mtime != stat.st_mtime: del cache[filename] def updatecache(filename, module_globals=None): """Update a cache entry and return its list of lines. If something's wrong, print a message, discard the cache entry, and return an empty list.""" if filename in cache: if len(cache[filename]) != 1: del cache[filename] if not filename or (filename.startswith('<') and filename.endswith('>')): return [] fullname = filename try: stat = os.stat(fullname) except OSError: basename = filename # Realise a lazy loader based lookup if there is one # otherwise try to lookup right now. if lazycache(filename, module_globals): try: data = cache[filename][0]() except (ImportError, OSError): pass else: if data is None: # No luck, the PEP302 loader cannot find the source # for this module. return [] cache[filename] = ( len(data), None, [line+'\n' for line in data.splitlines()], fullname ) return cache[filename][2] # Try looking through the module search path, which is only useful # when handling a relative filename. if os.path.isabs(filename): return [] for dirname in sys.path: try: fullname = os.path.join(dirname, basename) except (TypeError, AttributeError): # Not sufficiently string-like to do anything useful with. continue try: stat = os.stat(fullname) break except OSError: pass else: return [] try: with _tokenize_open(fullname) as fp: lines = fp.readlines() except OSError: return [] if lines and not lines[-1].endswith('\n'): lines[-1] += '\n' size, mtime = stat.st_size, stat.st_mtime cache[filename] = size, mtime, lines, fullname return lines def lazycache(filename, module_globals): """Seed the cache for filename with module_globals. The module loader will be asked for the source only when getlines is called, not immediately. If there is an entry in the cache already, it is not altered. :return: True if a lazy load is registered in the cache, otherwise False. To register such a load a module loader with a get_source method must be found, the filename must be a cachable filename, and the filename must not be already cached. """ if filename in cache: if len(cache[filename]) == 1: return True else: return False if not filename or (filename.startswith('<') and filename.endswith('>')): return False # Try for a __loader__, if available if module_globals and '__loader__' in module_globals: name = module_globals.get('__name__') loader = module_globals['__loader__'] get_source = getattr(loader, 'get_source', None) if name and get_source: get_lines = functools.partial(get_source, name) cache[filename] = (get_lines,) return True return False #### ---- avoiding having a tokenize2 backport for now ---- from codecs import lookup, BOM_UTF8 import re cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)'.encode('utf8')) blank_re = re.compile(r'^[ \t\f]*(?:[#\r\n]|$)'.encode('utf8')) def _tokenize_open(filename): """Open a file in read only mode using the encoding detected by detect_encoding(). """ buffer = io.open(filename, 'rb') encoding, lines = _detect_encoding(buffer.readline) buffer.seek(0) text = io.TextIOWrapper(buffer, encoding, line_buffering=True) text.mode = 'r' return text def _get_normal_name(orig_enc): """Imitates get_normal_name in tokenizer.c.""" # Only care about the first 12 characters. enc = orig_enc[:12].lower().replace("_", "-") if enc == "utf-8" or enc.startswith("utf-8-"): return "utf-8" if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \ enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")): return "iso-8859-1" return orig_enc def _detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should be used to decode a Python source file. It requires one argument, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used (as a string) and a list of any lines (left as bytes) it has read in. It detects the encoding from the presence of a utf-8 bom or an encoding cookie as specified in pep-0263. If both a bom and a cookie are present, but disagree, a SyntaxError will be raised. If the encoding cookie is an invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. """ try: filename = readline.__self__.name except AttributeError: filename = None bom_found = False encoding = None default = 'utf-8' def read_or_stop(): try: return readline() except StopIteration: return b'' def find_cookie(line): try: # Decode as UTF-8. Either the line is an encoding declaration, # in which case it should be pure ASCII, or it must be UTF-8 # per default encoding. line_string = line.decode('utf-8') except UnicodeDecodeError: msg = "invalid or missing encoding declaration" if filename is not None: msg = '{0} for {1!r}'.format(msg, filename) raise SyntaxError(msg) match = cookie_re.match(line) if not match: return None encoding = _get_normal_name(match.group(1).decode('utf-8')) try: codec = lookup(encoding) except LookupError: # This behaviour mimics the Python interpreter if filename is None: msg = "unknown encoding: " + encoding else: msg = "unknown encoding for {!r}: {}".format(filename, encoding) raise SyntaxError(msg) if bom_found: if encoding != 'utf-8': # This behaviour mimics the Python interpreter if filename is None: msg = 'encoding problem: utf-8' else: msg = 'encoding problem for {!r}: utf-8'.format(filename) raise SyntaxError(msg) encoding += '-sig' return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] default = 'utf-8-sig' if not first: return default, [] encoding = find_cookie(first) if encoding: return encoding, [first] if not blank_re.match(first): return default, [first] second = read_or_stop() if not second: return default, [first] encoding = find_cookie(second) if encoding: return encoding, [first, second] return default, [first, second] feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/0000755000076500000240000000000012765362057025627 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/__init__.py0000644000076500000240000000000012700725536027720 0ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/inspect_fodder.py0000644000076500000240000000152612700725536031167 0ustar jmstaff00000000000000# line 1 'A module docstring.' import sys, inspect # line 5 # line 7 def spam(a, b, c, d=3, e=4, f=5, *g, **h): eggs(b + d, c + f) # line 11 def eggs(x, y): "A docstring." global fr, st fr = inspect.currentframe() st = inspect.stack() p = x q = y / 0 # line 20 class StupidGit: """A longer, indented docstring.""" # line 27 def abuse(self, a, b, c): """Another \tdocstring containing \ttabs \t """ self.argue(a, b, c) # line 40 def argue(self, a, b, c): try: spam(a, b, c) except: self.ex = sys.exc_info() self.tr = inspect.trace() # line 48 class MalodorousPervert(StupidGit): pass Tit = MalodorousPervert class ParrotDroppings: pass class FesteringGob(MalodorousPervert, ParrotDroppings): pass feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/inspect_fodder2.py0000644000076500000240000000306112700725536031245 0ustar jmstaff00000000000000# line 1 def wrap(foo=None): def wrapper(func): return func return wrapper # line 7 def replace(func): def insteadfunc(): print('hello') return insteadfunc # line 13 @wrap() @wrap(wrap) def wrapped(): pass # line 19 @replace def gone(): pass # line 24 oll = lambda m: m # line 27 tll = lambda g: g and \ g and \ g # line 32 tlli = lambda d: d and \ d # line 36 def onelinefunc(): pass # line 39 def manyargs(arg1, arg2, arg3, arg4): pass # line 43 def twolinefunc(m): return m and \ m # line 47 a = [None, lambda x: x, None] # line 52 def setfunc(func): globals()["anonymous"] = func setfunc(lambda x, y: x*y) # line 57 def with_comment(): # hello world # line 61 multiline_sig = [ lambda x, \ y: x+y, None, ] # line 68 def func69(): class cls70: def func71(): pass return cls70 extra74 = 74 # line 76 def func77(): pass (extra78, stuff78) = 'xy' extra79 = 'stop' # line 81 class cls82: def func83(): pass (extra84, stuff84) = 'xy' extra85 = 'stop' # line 87 def func88(): # comment return 90 # line 92 def f(): class X: def g(): "doc" return 42 return X method_in_dynamic_class = f().g #line 101 def keyworded(*arg1, arg2=1): pass #line 105 def annotated(arg1: list): pass #line 109 def keyword_only_arg(*, arg): pass from functools import wraps def decorator(func): @wraps(func) def fake(): return 42 return fake #line 121 @decorator def real(): return 20 feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/mapping_tests.py0000644000076500000240000005300012700725536031046 0ustar jmstaff00000000000000# tests common to dict and UserDict import unittest import collections class BasicTestMappingProtocol(unittest.TestCase): # This base class can be used to check that an object conforms to the # mapping protocol # Functions that can be useful to override to adapt to dictionary # semantics type2test = None # which class is being tested (overwrite in subclasses) def _reference(self): """Return a dictionary of values which are invariant by storage in the object under test.""" return {"1": "2", "key1":"value1", "key2":(1,2,3)} def _empty_mapping(self): """Return an empty mapping object""" return self.type2test() def _full_mapping(self, data): """Return a mapping object with the value contained in data dictionary""" x = self._empty_mapping() for key, value in data.items(): x[key] = value return x def __init__(self, *args, **kw): unittest.TestCase.__init__(self, *args, **kw) self.reference = self._reference().copy() # A (key, value) pair not in the mapping key, value = self.reference.popitem() self.other = {key:value} # A (key, value) pair in the mapping key, value = self.reference.popitem() self.inmapping = {key:value} self.reference[key] = value def test_read(self): # Test for read only operations on mapping p = self._empty_mapping() p1 = dict(p) #workaround for singleton objects d = self._full_mapping(self.reference) if d is p: p = p1 #Indexing for key, value in self.reference.items(): self.assertEqual(d[key], value) knownkey = list(self.other.keys())[0] self.assertRaises(KeyError, lambda:d[knownkey]) #len self.assertEqual(len(p), 0) self.assertEqual(len(d), len(self.reference)) #__contains__ for k in self.reference: self.assertIn(k, d) for k in self.other: self.assertNotIn(k, d) #cmp self.assertEqual(p, p) self.assertEqual(d, d) self.assertNotEqual(p, d) self.assertNotEqual(d, p) #__non__zero__ if p: self.fail("Empty mapping must compare to False") if not d: self.fail("Full mapping must compare to True") # keys(), items(), iterkeys() ... def check_iterandlist(iter, lst, ref): self.assertTrue(hasattr(iter, '__next__')) self.assertTrue(hasattr(iter, '__iter__')) x = list(iter) self.assertTrue(set(x)==set(lst)==set(ref)) check_iterandlist(iter(d.keys()), list(d.keys()), self.reference.keys()) check_iterandlist(iter(d), list(d.keys()), self.reference.keys()) check_iterandlist(iter(d.values()), list(d.values()), self.reference.values()) check_iterandlist(iter(d.items()), list(d.items()), self.reference.items()) #get key, value = next(iter(d.items())) knownkey, knownvalue = next(iter(self.other.items())) self.assertEqual(d.get(key, knownvalue), value) self.assertEqual(d.get(knownkey, knownvalue), knownvalue) self.assertNotIn(knownkey, d) def test_write(self): # Test for write operations on mapping p = self._empty_mapping() #Indexing for key, value in self.reference.items(): p[key] = value self.assertEqual(p[key], value) for key in self.reference.keys(): del p[key] self.assertRaises(KeyError, lambda:p[key]) p = self._empty_mapping() #update p.update(self.reference) self.assertEqual(dict(p), self.reference) items = list(p.items()) p = self._empty_mapping() p.update(items) self.assertEqual(dict(p), self.reference) d = self._full_mapping(self.reference) #setdefault key, value = next(iter(d.items())) knownkey, knownvalue = next(iter(self.other.items())) self.assertEqual(d.setdefault(key, knownvalue), value) self.assertEqual(d[key], value) self.assertEqual(d.setdefault(knownkey, knownvalue), knownvalue) self.assertEqual(d[knownkey], knownvalue) #pop self.assertEqual(d.pop(knownkey), knownvalue) self.assertNotIn(knownkey, d) self.assertRaises(KeyError, d.pop, knownkey) default = 909 d[knownkey] = knownvalue self.assertEqual(d.pop(knownkey, default), knownvalue) self.assertNotIn(knownkey, d) self.assertEqual(d.pop(knownkey, default), default) #popitem key, value = d.popitem() self.assertNotIn(key, d) self.assertEqual(value, self.reference[key]) p=self._empty_mapping() self.assertRaises(KeyError, p.popitem) def test_constructor(self): self.assertEqual(self._empty_mapping(), self._empty_mapping()) def test_bool(self): self.assertTrue(not self._empty_mapping()) self.assertTrue(self.reference) self.assertTrue(bool(self._empty_mapping()) is False) self.assertTrue(bool(self.reference) is True) def test_keys(self): d = self._empty_mapping() self.assertEqual(list(d.keys()), []) d = self.reference self.assertIn(list(self.inmapping.keys())[0], d.keys()) self.assertNotIn(list(self.other.keys())[0], d.keys()) self.assertRaises(TypeError, d.keys, None) def test_values(self): d = self._empty_mapping() self.assertEqual(list(d.values()), []) self.assertRaises(TypeError, d.values, None) def test_items(self): d = self._empty_mapping() self.assertEqual(list(d.items()), []) self.assertRaises(TypeError, d.items, None) def test_len(self): d = self._empty_mapping() self.assertEqual(len(d), 0) def test_getitem(self): d = self.reference self.assertEqual(d[list(self.inmapping.keys())[0]], list(self.inmapping.values())[0]) self.assertRaises(TypeError, d.__getitem__) def test_update(self): # mapping argument d = self._empty_mapping() d.update(self.other) self.assertEqual(list(d.items()), list(self.other.items())) # No argument d = self._empty_mapping() d.update() self.assertEqual(d, self._empty_mapping()) # item sequence d = self._empty_mapping() d.update(self.other.items()) self.assertEqual(list(d.items()), list(self.other.items())) # Iterator d = self._empty_mapping() d.update(self.other.items()) self.assertEqual(list(d.items()), list(self.other.items())) # FIXME: Doesn't work with UserDict # self.assertRaises((TypeError, AttributeError), d.update, None) self.assertRaises((TypeError, AttributeError), d.update, 42) outerself = self class SimpleUserDict: def __init__(self): self.d = outerself.reference def keys(self): return self.d.keys() def __getitem__(self, i): return self.d[i] d.clear() d.update(SimpleUserDict()) i1 = sorted(d.items()) i2 = sorted(self.reference.items()) self.assertEqual(i1, i2) class Exc(Exception): pass d = self._empty_mapping() class FailingUserDict: def keys(self): raise Exc self.assertRaises(Exc, d.update, FailingUserDict()) d.clear() class FailingUserDict: def keys(self): class BogonIter: def __init__(self): self.i = 1 def __iter__(self): return self def __next__(self): if self.i: self.i = 0 return 'a' raise Exc return BogonIter() def __getitem__(self, key): return key self.assertRaises(Exc, d.update, FailingUserDict()) class FailingUserDict: def keys(self): class BogonIter: def __init__(self): self.i = ord('a') def __iter__(self): return self def __next__(self): if self.i <= ord('z'): rtn = chr(self.i) self.i += 1 return rtn raise StopIteration return BogonIter() def __getitem__(self, key): raise Exc self.assertRaises(Exc, d.update, FailingUserDict()) d = self._empty_mapping() class badseq(object): def __iter__(self): return self def __next__(self): raise Exc() self.assertRaises(Exc, d.update, badseq()) self.assertRaises(ValueError, d.update, [(1, 2, 3)]) # no test_fromkeys or test_copy as both os.environ and selves don't support it def test_get(self): d = self._empty_mapping() self.assertTrue(d.get(list(self.other.keys())[0]) is None) self.assertEqual(d.get(list(self.other.keys())[0], 3), 3) d = self.reference self.assertTrue(d.get(list(self.other.keys())[0]) is None) self.assertEqual(d.get(list(self.other.keys())[0], 3), 3) self.assertEqual(d.get(list(self.inmapping.keys())[0]), list(self.inmapping.values())[0]) self.assertEqual(d.get(list(self.inmapping.keys())[0], 3), list(self.inmapping.values())[0]) self.assertRaises(TypeError, d.get) self.assertRaises(TypeError, d.get, None, None, None) def test_setdefault(self): d = self._empty_mapping() self.assertRaises(TypeError, d.setdefault) def test_popitem(self): d = self._empty_mapping() self.assertRaises(KeyError, d.popitem) self.assertRaises(TypeError, d.popitem, 42) def test_pop(self): d = self._empty_mapping() k, v = list(self.inmapping.items())[0] d[k] = v self.assertRaises(KeyError, d.pop, list(self.other.keys())[0]) self.assertEqual(d.pop(k), v) self.assertEqual(len(d), 0) self.assertRaises(KeyError, d.pop, k) class TestMappingProtocol(BasicTestMappingProtocol): def test_constructor(self): BasicTestMappingProtocol.test_constructor(self) self.assertTrue(self._empty_mapping() is not self._empty_mapping()) self.assertEqual(self.type2test(x=1, y=2), {"x": 1, "y": 2}) def test_bool(self): BasicTestMappingProtocol.test_bool(self) self.assertTrue(not self._empty_mapping()) self.assertTrue(self._full_mapping({"x": "y"})) self.assertTrue(bool(self._empty_mapping()) is False) self.assertTrue(bool(self._full_mapping({"x": "y"})) is True) def test_keys(self): BasicTestMappingProtocol.test_keys(self) d = self._empty_mapping() self.assertEqual(list(d.keys()), []) d = self._full_mapping({'a': 1, 'b': 2}) k = d.keys() self.assertIn('a', k) self.assertIn('b', k) self.assertNotIn('c', k) def test_values(self): BasicTestMappingProtocol.test_values(self) d = self._full_mapping({1:2}) self.assertEqual(list(d.values()), [2]) def test_items(self): BasicTestMappingProtocol.test_items(self) d = self._full_mapping({1:2}) self.assertEqual(list(d.items()), [(1, 2)]) def test_contains(self): d = self._empty_mapping() self.assertNotIn('a', d) self.assertTrue(not ('a' in d)) self.assertTrue('a' not in d) d = self._full_mapping({'a': 1, 'b': 2}) self.assertIn('a', d) self.assertIn('b', d) self.assertNotIn('c', d) self.assertRaises(TypeError, d.__contains__) def test_len(self): BasicTestMappingProtocol.test_len(self) d = self._full_mapping({'a': 1, 'b': 2}) self.assertEqual(len(d), 2) def test_getitem(self): BasicTestMappingProtocol.test_getitem(self) d = self._full_mapping({'a': 1, 'b': 2}) self.assertEqual(d['a'], 1) self.assertEqual(d['b'], 2) d['c'] = 3 d['a'] = 4 self.assertEqual(d['c'], 3) self.assertEqual(d['a'], 4) del d['b'] self.assertEqual(d, {'a': 4, 'c': 3}) self.assertRaises(TypeError, d.__getitem__) def test_clear(self): d = self._full_mapping({1:1, 2:2, 3:3}) d.clear() self.assertEqual(d, {}) self.assertRaises(TypeError, d.clear, None) def test_update(self): BasicTestMappingProtocol.test_update(self) # mapping argument d = self._empty_mapping() d.update({1:100}) d.update({2:20}) d.update({1:1, 2:2, 3:3}) self.assertEqual(d, {1:1, 2:2, 3:3}) # no argument d.update() self.assertEqual(d, {1:1, 2:2, 3:3}) # keyword arguments d = self._empty_mapping() d.update(x=100) d.update(y=20) d.update(x=1, y=2, z=3) self.assertEqual(d, {"x":1, "y":2, "z":3}) # item sequence d = self._empty_mapping() d.update([("x", 100), ("y", 20)]) self.assertEqual(d, {"x":100, "y":20}) # Both item sequence and keyword arguments d = self._empty_mapping() d.update([("x", 100), ("y", 20)], x=1, y=2) self.assertEqual(d, {"x":1, "y":2}) # iterator d = self._full_mapping({1:3, 2:4}) d.update(self._full_mapping({1:2, 3:4, 5:6}).items()) self.assertEqual(d, {1:2, 2:4, 3:4, 5:6}) class SimpleUserDict: def __init__(self): self.d = {1:1, 2:2, 3:3} def keys(self): return self.d.keys() def __getitem__(self, i): return self.d[i] d.clear() d.update(SimpleUserDict()) self.assertEqual(d, {1:1, 2:2, 3:3}) def test_fromkeys(self): self.assertEqual(self.type2test.fromkeys('abc'), {'a':None, 'b':None, 'c':None}) d = self._empty_mapping() self.assertTrue(not(d.fromkeys('abc') is d)) self.assertEqual(d.fromkeys('abc'), {'a':None, 'b':None, 'c':None}) self.assertEqual(d.fromkeys((4,5),0), {4:0, 5:0}) self.assertEqual(d.fromkeys([]), {}) def g(): yield 1 self.assertEqual(d.fromkeys(g()), {1:None}) self.assertRaises(TypeError, {}.fromkeys, 3) class dictlike(self.type2test): pass self.assertEqual(dictlike.fromkeys('a'), {'a':None}) self.assertEqual(dictlike().fromkeys('a'), {'a':None}) self.assertTrue(dictlike.fromkeys('a').__class__ is dictlike) self.assertTrue(dictlike().fromkeys('a').__class__ is dictlike) self.assertTrue(type(dictlike.fromkeys('a')) is dictlike) class mydict(self.type2test): def __new__(cls): return collections.UserDict() ud = mydict.fromkeys('ab') self.assertEqual(ud, {'a':None, 'b':None}) self.assertIsInstance(ud, collections.UserDict) self.assertRaises(TypeError, dict.fromkeys) class Exc(Exception): pass class baddict1(self.type2test): def __init__(self): raise Exc() self.assertRaises(Exc, baddict1.fromkeys, [1]) class BadSeq(object): def __iter__(self): return self def __next__(self): raise Exc() self.assertRaises(Exc, self.type2test.fromkeys, BadSeq()) class baddict2(self.type2test): def __setitem__(self, key, value): raise Exc() self.assertRaises(Exc, baddict2.fromkeys, [1]) def test_copy(self): d = self._full_mapping({1:1, 2:2, 3:3}) self.assertEqual(d.copy(), {1:1, 2:2, 3:3}) d = self._empty_mapping() self.assertEqual(d.copy(), d) self.assertIsInstance(d.copy(), d.__class__) self.assertRaises(TypeError, d.copy, None) def test_get(self): BasicTestMappingProtocol.test_get(self) d = self._empty_mapping() self.assertTrue(d.get('c') is None) self.assertEqual(d.get('c', 3), 3) d = self._full_mapping({'a' : 1, 'b' : 2}) self.assertTrue(d.get('c') is None) self.assertEqual(d.get('c', 3), 3) self.assertEqual(d.get('a'), 1) self.assertEqual(d.get('a', 3), 1) def test_setdefault(self): BasicTestMappingProtocol.test_setdefault(self) d = self._empty_mapping() self.assertTrue(d.setdefault('key0') is None) d.setdefault('key0', []) self.assertTrue(d.setdefault('key0') is None) d.setdefault('key', []).append(3) self.assertEqual(d['key'][0], 3) d.setdefault('key', []).append(4) self.assertEqual(len(d['key']), 2) def test_popitem(self): BasicTestMappingProtocol.test_popitem(self) for copymode in -1, +1: # -1: b has same structure as a # +1: b is a.copy() for log2size in range(12): size = 2**log2size a = self._empty_mapping() b = self._empty_mapping() for i in range(size): a[repr(i)] = i if copymode < 0: b[repr(i)] = i if copymode > 0: b = a.copy() for i in range(size): ka, va = ta = a.popitem() self.assertEqual(va, int(ka)) kb, vb = tb = b.popitem() self.assertEqual(vb, int(kb)) self.assertTrue(not(copymode < 0 and ta != tb)) self.assertTrue(not a) self.assertTrue(not b) def test_pop(self): BasicTestMappingProtocol.test_pop(self) # Tests for pop with specified key d = self._empty_mapping() k, v = 'abc', 'def' self.assertEqual(d.pop(k, v), v) d[k] = v self.assertEqual(d.pop(k, 1), v) class TestHashMappingProtocol(TestMappingProtocol): def test_getitem(self): TestMappingProtocol.test_getitem(self) class Exc(Exception): pass class BadEq(object): def __eq__(self, other): raise Exc() def __hash__(self): return 24 d = self._empty_mapping() d[BadEq()] = 42 self.assertRaises(KeyError, d.__getitem__, 23) class BadHash(object): fail = False def __hash__(self): if self.fail: raise Exc() else: return 42 d = self._empty_mapping() x = BadHash() d[x] = 42 x.fail = True self.assertRaises(Exc, d.__getitem__, x) def test_fromkeys(self): TestMappingProtocol.test_fromkeys(self) class mydict(self.type2test): def __new__(cls): return collections.UserDict() ud = mydict.fromkeys('ab') self.assertEqual(ud, {'a':None, 'b':None}) self.assertIsInstance(ud, collections.UserDict) def test_pop(self): TestMappingProtocol.test_pop(self) class Exc(Exception): pass class BadHash(object): fail = False def __hash__(self): if self.fail: raise Exc() else: return 42 d = self._empty_mapping() x = BadHash() d[x] = 42 x.fail = True self.assertRaises(Exc, d.pop, x) def test_mutatingiteration(self): d = self._empty_mapping() d[1] = 1 try: for i in d: d[i+1] = 1 except RuntimeError: pass else: self.fail("changing dict size during iteration doesn't raise Error") def test_repr(self): d = self._empty_mapping() self.assertEqual(repr(d), '{}') d[1] = 2 self.assertEqual(repr(d), '{1: 2}') d = self._empty_mapping() d[1] = d self.assertEqual(repr(d), '{1: {...}}') class Exc(Exception): pass class BadRepr(object): def __repr__(self): raise Exc() d = self._full_mapping({1: BadRepr()}) self.assertRaises(Exc, repr, d) def test_eq(self): self.assertEqual(self._empty_mapping(), self._empty_mapping()) self.assertEqual(self._full_mapping({1: 2}), self._full_mapping({1: 2})) class Exc(Exception): pass class BadCmp(object): def __eq__(self, other): raise Exc() def __hash__(self): return 1 d1 = self._full_mapping({BadCmp(): 1}) d2 = self._full_mapping({1: 1}) self.assertRaises(Exc, lambda: BadCmp()==1) self.assertRaises(Exc, lambda: d1==d2) def test_setdefault(self): TestMappingProtocol.test_setdefault(self) class Exc(Exception): pass class BadHash(object): fail = False def __hash__(self): if self.fail: raise Exc() else: return 42 d = self._empty_mapping() x = BadHash() d[x] = 42 x.fail = True self.assertRaises(Exc, d.setdefault, x, []) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/linecache2/tests/test_linecache.py0000644000076500000240000001455412700725536031156 0ustar jmstaff00000000000000""" Tests for the linecache module """ import linecache2 as linecache import unittest2 as unittest import os.path import tempfile from fixtures import NestedTempfile FILENAME = os.__file__ if FILENAME.endswith('.pyc'): FILENAME = FILENAME[:-1] NONEXISTENT_FILENAME = FILENAME + '.missing' INVALID_NAME = '!@$)(!@#_1' EMPTY = '' TESTS = 'inspect_fodder inspect_fodder2 mapping_tests' TESTS = TESTS.split() TEST_PATH = os.path.dirname(__file__) MODULES = "linecache abc".split() MODULE_PATH = os.path.dirname(FILENAME) SOURCE_1 = ''' " Docstring " def function(): return result ''' SOURCE_2 = ''' def f(): return 1 + 1 a = f() ''' SOURCE_3 = ''' def f(): return 3''' # No ending newline class LineCacheTests(unittest.TestCase): def setUp(self): tempdir = NestedTempfile() tempdir.setUp() self.addCleanup(tempdir.cleanUp) def test_getline(self): getline = linecache.getline # Bad values for line number should return an empty string self.assertEqual(getline(FILENAME, 2**15), EMPTY) self.assertEqual(getline(FILENAME, -1), EMPTY) # Float values currently raise TypeError, should it? self.assertRaises(TypeError, getline, FILENAME, 1.1) # Bad filenames should return an empty string self.assertEqual(getline(EMPTY, 1), EMPTY) self.assertEqual(getline(INVALID_NAME, 1), EMPTY) # Check whether lines correspond to those from file iteration for entry in TESTS: filename = os.path.join(TEST_PATH, entry) + '.py' with open(filename) as file: for index, line in enumerate(file): self.assertEqual(line, getline(filename, index + 1)) # Check module loading for entry in MODULES: filename = os.path.join(MODULE_PATH, entry) + '.py' with open(filename) as file: for index, line in enumerate(file): self.assertEqual(line, getline(filename, index + 1)) # Check that bogus data isn't returned (issue #1309567) empty = linecache.getlines('a/b/c/__init__.py') self.assertEqual(empty, []) def test_no_ending_newline(self): temp_file = tempfile.NamedTemporaryFile( suffix='.py', mode='w', delete=False) self.addCleanup(os.unlink, temp_file.name) with open(temp_file.name, "w") as fp: fp.write(SOURCE_3) lines = linecache.getlines(temp_file.name) self.assertEqual(lines, ["\n", "def f():\n", " return 3\n"]) def test_clearcache(self): cached = [] for entry in TESTS: filename = os.path.join(TEST_PATH, entry) + '.py' cached.append(filename) linecache.getline(filename, 1) # Are all files cached? cached_empty = [fn for fn in cached if fn not in linecache.cache] self.assertEqual(cached_empty, []) # Can we clear the cache? linecache.clearcache() cached_empty = [fn for fn in cached if fn in linecache.cache] self.assertEqual(cached_empty, []) def test_checkcache(self): getline = linecache.getline # Create a source file and cache its contents temp_file = tempfile.NamedTemporaryFile( suffix='.py', mode='w', delete=False) source_name = temp_file.name self.addCleanup(os.unlink, source_name) with open(source_name, 'w') as source: source.write(SOURCE_1) getline(source_name, 1) # Keep a copy of the old contents source_list = [] with open(source_name) as source: for index, line in enumerate(source): self.assertEqual(line, getline(source_name, index + 1)) source_list.append(line) with open(source_name, 'w') as source: source.write(SOURCE_2) # Try to update a bogus cache entry linecache.checkcache('dummy') # Check that the cache matches the old contents for index, line in enumerate(source_list): self.assertEqual(line, getline(source_name, index + 1)) # Update the cache and check whether it matches the new source file linecache.checkcache(source_name) with open(source_name) as source: for index, line in enumerate(source): self.assertEqual(line, getline(source_name, index + 1)) source_list.append(line) def test_lazycache_no_globals(self): lines = linecache.getlines(FILENAME) linecache.clearcache() self.assertEqual(False, linecache.lazycache(FILENAME, None)) self.assertEqual(lines, linecache.getlines(FILENAME)) @unittest.skipIf("__loader__" not in globals(), "Modules not PEP302 by default") def test_lazycache_smoke(self): lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) linecache.clearcache() self.assertEqual( True, linecache.lazycache(NONEXISTENT_FILENAME, globals())) self.assertEqual(1, len(linecache.cache[NONEXISTENT_FILENAME])) # Note here that we're looking up a non existant filename with no # globals: this would error if the lazy value wasn't resolved. self.assertEqual(lines, linecache.getlines(NONEXISTENT_FILENAME)) def test_lazycache_provide_after_failed_lookup(self): linecache.clearcache() lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) linecache.clearcache() linecache.getlines(NONEXISTENT_FILENAME) linecache.lazycache(NONEXISTENT_FILENAME, globals()) self.assertEqual(lines, linecache.updatecache(NONEXISTENT_FILENAME)) def test_lazycache_check(self): linecache.clearcache() linecache.lazycache(NONEXISTENT_FILENAME, globals()) linecache.checkcache() def test_lazycache_bad_filename(self): linecache.clearcache() self.assertEqual(False, linecache.lazycache('', globals())) self.assertEqual(False, linecache.lazycache('', globals())) @unittest.skipIf("__loader__" not in globals(), "Modules not PEP302 by default") def test_lazycache_already_cached(self): linecache.clearcache() lines = linecache.getlines(NONEXISTENT_FILENAME, globals()) self.assertEqual( False, linecache.lazycache(NONEXISTENT_FILENAME, globals())) self.assertEqual(4, len(linecache.cache[NONEXISTENT_FILENAME])) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/0000755000076500000240000000000012765362057023260 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/__init__.py0000644000076500000240000002427312700725533025370 0ustar jmstaff00000000000000#!/usr/bin/env python from __future__ import absolute_import import locale import logging import os import optparse import warnings import sys import re from pip.exceptions import InstallationError, CommandError, PipError from pip.utils import get_installed_distributions, get_prog from pip.utils import deprecation, dist_is_editable from pip.vcs import git, mercurial, subversion, bazaar # noqa from pip.baseparser import ConfigOptionParser, UpdatingDefaultsHelpFormatter from pip.commands import get_summaries, get_similar_commands from pip.commands import commands_dict from pip._vendor.requests.packages.urllib3.exceptions import ( InsecureRequestWarning, ) # assignment for flake8 to be happy # This fixes a peculiarity when importing via __import__ - as we are # initialising the pip module, "from pip import cmdoptions" is recursive # and appears not to work properly in that situation. import pip.cmdoptions cmdoptions = pip.cmdoptions # The version as used in the setup.py and the docs conf.py __version__ = "8.1.1" logger = logging.getLogger(__name__) # Hide the InsecureRequestWArning from urllib3 warnings.filterwarnings("ignore", category=InsecureRequestWarning) def autocomplete(): """Command and option completion for the main option parser (and options) and its subcommands (and options). Enable by sourcing one of the completion shell scripts (bash or zsh). """ # Don't complete if user hasn't sourced bash_completion file. if 'PIP_AUTO_COMPLETE' not in os.environ: return cwords = os.environ['COMP_WORDS'].split()[1:] cword = int(os.environ['COMP_CWORD']) try: current = cwords[cword - 1] except IndexError: current = '' subcommands = [cmd for cmd, summary in get_summaries()] options = [] # subcommand try: subcommand_name = [w for w in cwords if w in subcommands][0] except IndexError: subcommand_name = None parser = create_main_parser() # subcommand options if subcommand_name: # special case: 'help' subcommand has no options if subcommand_name == 'help': sys.exit(1) # special case: list locally installed dists for uninstall command if subcommand_name == 'uninstall' and not current.startswith('-'): installed = [] lc = current.lower() for dist in get_installed_distributions(local_only=True): if dist.key.startswith(lc) and dist.key not in cwords[1:]: installed.append(dist.key) # if there are no dists installed, fall back to option completion if installed: for dist in installed: print(dist) sys.exit(1) subcommand = commands_dict[subcommand_name]() options += [(opt.get_opt_string(), opt.nargs) for opt in subcommand.parser.option_list_all if opt.help != optparse.SUPPRESS_HELP] # filter out previously specified options from available options prev_opts = [x.split('=')[0] for x in cwords[1:cword - 1]] options = [(x, v) for (x, v) in options if x not in prev_opts] # filter options by current input options = [(k, v) for k, v in options if k.startswith(current)] for option in options: opt_label = option[0] # append '=' to options which require args if option[1]: opt_label += '=' print(opt_label) else: # show main parser options only when necessary if current.startswith('-') or current.startswith('--'): opts = [i.option_list for i in parser.option_groups] opts.append(parser.option_list) opts = (o for it in opts for o in it) subcommands += [i.get_opt_string() for i in opts if i.help != optparse.SUPPRESS_HELP] print(' '.join([x for x in subcommands if x.startswith(current)])) sys.exit(1) def create_main_parser(): parser_kw = { 'usage': '\n%prog [options]', 'add_help_option': False, 'formatter': UpdatingDefaultsHelpFormatter(), 'name': 'global', 'prog': get_prog(), } parser = ConfigOptionParser(**parser_kw) parser.disable_interspersed_args() pip_pkg_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) parser.version = 'pip %s from %s (python %s)' % ( __version__, pip_pkg_dir, sys.version[:3]) # add the general options gen_opts = cmdoptions.make_option_group(cmdoptions.general_group, parser) parser.add_option_group(gen_opts) parser.main = True # so the help formatter knows # create command listing for description command_summaries = get_summaries() description = [''] + ['%-27s %s' % (i, j) for i, j in command_summaries] parser.description = '\n'.join(description) return parser def parseopts(args): parser = create_main_parser() # Note: parser calls disable_interspersed_args(), so the result of this # call is to split the initial args into the general options before the # subcommand and everything else. # For example: # args: ['--timeout=5', 'install', '--user', 'INITools'] # general_options: ['--timeout==5'] # args_else: ['install', '--user', 'INITools'] general_options, args_else = parser.parse_args(args) # --version if general_options.version: sys.stdout.write(parser.version) sys.stdout.write(os.linesep) sys.exit() # pip || pip help -> print_help() if not args_else or (args_else[0] == 'help' and len(args_else) == 1): parser.print_help() sys.exit() # the subcommand name cmd_name = args_else[0] if cmd_name not in commands_dict: guess = get_similar_commands(cmd_name) msg = ['unknown command "%s"' % cmd_name] if guess: msg.append('maybe you meant "%s"' % guess) raise CommandError(' - '.join(msg)) # all the args without the subcommand cmd_args = args[:] cmd_args.remove(cmd_name) return cmd_name, cmd_args def check_isolated(args): isolated = False if "--isolated" in args: isolated = True return isolated def main(args=None): if args is None: args = sys.argv[1:] # Configure our deprecation warnings to be sent through loggers deprecation.install_warning_logger() autocomplete() try: cmd_name, cmd_args = parseopts(args) except PipError as exc: sys.stderr.write("ERROR: %s" % exc) sys.stderr.write(os.linesep) sys.exit(1) # Needed for locale.getpreferredencoding(False) to work # in pip.utils.encoding.auto_decode locale.setlocale(locale.LC_ALL, '') command = commands_dict[cmd_name](isolated=check_isolated(cmd_args)) return command.main(cmd_args) # ########################################################### # # Writing freeze files class FrozenRequirement(object): def __init__(self, name, req, editable, comments=()): self.name = name self.req = req self.editable = editable self.comments = comments _rev_re = re.compile(r'-r(\d+)$') _date_re = re.compile(r'-(20\d\d\d\d\d\d)$') @classmethod def from_dist(cls, dist, dependency_links): location = os.path.normcase(os.path.abspath(dist.location)) comments = [] from pip.vcs import vcs, get_src_requirement if dist_is_editable(dist) and vcs.get_backend_name(location): editable = True try: req = get_src_requirement(dist, location) except InstallationError as exc: logger.warning( "Error when trying to get requirement for VCS system %s, " "falling back to uneditable format", exc ) req = None if req is None: logger.warning( 'Could not determine repository location of %s', location ) comments.append( '## !! Could not determine repository location' ) req = dist.as_requirement() editable = False else: editable = False req = dist.as_requirement() specs = req.specs assert len(specs) == 1 and specs[0][0] in ["==", "==="], \ 'Expected 1 spec with == or ===; specs = %r; dist = %r' % \ (specs, dist) version = specs[0][1] ver_match = cls._rev_re.search(version) date_match = cls._date_re.search(version) if ver_match or date_match: svn_backend = vcs.get_backend('svn') if svn_backend: svn_location = svn_backend().get_location( dist, dependency_links, ) if not svn_location: logger.warning( 'Warning: cannot find svn location for %s', req) comments.append( '## FIXME: could not find svn URL in dependency_links ' 'for this package:' ) else: comments.append( '# Installing as editable to satisfy requirement %s:' % req ) if ver_match: rev = ver_match.group(1) else: rev = '{%s}' % date_match.group(1) editable = True req = '%s@%s#egg=%s' % ( svn_location, rev, cls.egg_name(dist) ) return cls(dist.project_name, req, editable, comments) @staticmethod def egg_name(dist): name = dist.egg_name() match = re.search(r'-py\d\.\d$', name) if match: name = name[:match.start()] return name def __str__(self): req = self.req if self.editable: req = '-e %s' % req return '\n'.join(list(self.comments) + [str(req)]) + '\n' if __name__ == '__main__': sys.exit(main()) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/__main__.py0000644000076500000240000000111012700725533025332 0ustar jmstaff00000000000000from __future__ import absolute_import import os import sys # If we are running from a wheel, add the wheel to sys.path # This allows the usage python pip-*.whl/pip install pip-*.whl if __package__ == '': # __file__ is pip-*.whl/pip/__main__.py # first dirname call strips of '/__main__.py', second strips off '/pip' # Resulting path is the name of the wheel itself # Add that to sys.path so we can import pip path = os.path.dirname(os.path.dirname(__file__)) sys.path.insert(0, path) import pip # noqa if __name__ == '__main__': sys.exit(pip.main()) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/0000755000076500000240000000000012765362057024714 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/__init__.py0000644000076500000240000001104712700725533027017 0ustar jmstaff00000000000000""" pip._vendor is for vendoring dependencies of pip to prevent needing pip to depend on something external. Files inside of pip._vendor should be considered immutable and should only be updated to versions from upstream. """ from __future__ import absolute_import import glob import os.path import sys # Downstream redistributors which have debundled our dependencies should also # patch this value to be true. This will trigger the additional patching # to cause things like "six" to be available as pip. DEBUNDLED = False # By default, look in this directory for a bunch of .whl files which we will # add to the beginning of sys.path before attempting to import anything. This # is done to support downstream re-distributors like Debian and Fedora who # wish to create their own Wheels for our dependencies to aid in debundling. WHEEL_DIR = os.path.abspath(os.path.dirname(__file__)) # Define a small helper function to alias our vendored modules to the real ones # if the vendored ones do not exist. This idea of this was taken from # https://github.com/kennethreitz/requests/pull/2567. def vendored(modulename): vendored_name = "{0}.{1}".format(__name__, modulename) try: __import__(vendored_name, globals(), locals(), level=0) except ImportError: try: __import__(modulename, globals(), locals(), level=0) except ImportError: # We can just silently allow import failures to pass here. If we # got to this point it means that ``import pip._vendor.whatever`` # failed and so did ``import whatever``. Since we're importing this # upfront in an attempt to alias imports, not erroring here will # just mean we get a regular import error whenever pip *actually* # tries to import one of these modules to use it, which actually # gives us a better error message than we would have otherwise # gotten. pass else: sys.modules[vendored_name] = sys.modules[modulename] base, head = vendored_name.rsplit(".", 1) setattr(sys.modules[base], head, sys.modules[modulename]) # If we're operating in a debundled setup, then we want to go ahead and trigger # the aliasing of our vendored libraries as well as looking for wheels to add # to our sys.path. This will cause all of this code to be a no-op typically # however downstream redistributors can enable it in a consistent way across # all platforms. if DEBUNDLED: # Actually look inside of WHEEL_DIR to find .whl files and add them to the # front of our sys.path. sys.path[:] = glob.glob(os.path.join(WHEEL_DIR, "*.whl")) + sys.path # Actually alias all of our vendored dependencies. vendored("cachecontrol") vendored("colorama") vendored("distlib") vendored("html5lib") vendored("lockfile") vendored("six") vendored("six.moves") vendored("six.moves.urllib") vendored("packaging") vendored("packaging.version") vendored("packaging.specifiers") vendored("pkg_resources") vendored("progress") vendored("retrying") vendored("requests") vendored("requests.packages") vendored("requests.packages.urllib3") vendored("requests.packages.urllib3._collections") vendored("requests.packages.urllib3.connection") vendored("requests.packages.urllib3.connectionpool") vendored("requests.packages.urllib3.contrib") vendored("requests.packages.urllib3.contrib.ntlmpool") vendored("requests.packages.urllib3.contrib.pyopenssl") vendored("requests.packages.urllib3.exceptions") vendored("requests.packages.urllib3.fields") vendored("requests.packages.urllib3.filepost") vendored("requests.packages.urllib3.packages") vendored("requests.packages.urllib3.packages.ordered_dict") vendored("requests.packages.urllib3.packages.six") vendored("requests.packages.urllib3.packages.ssl_match_hostname") vendored("requests.packages.urllib3.packages.ssl_match_hostname." "_implementation") vendored("requests.packages.urllib3.poolmanager") vendored("requests.packages.urllib3.request") vendored("requests.packages.urllib3.response") vendored("requests.packages.urllib3.util") vendored("requests.packages.urllib3.util.connection") vendored("requests.packages.urllib3.util.request") vendored("requests.packages.urllib3.util.response") vendored("requests.packages.urllib3.util.retry") vendored("requests.packages.urllib3.util.ssl_") vendored("requests.packages.urllib3.util.timeout") vendored("requests.packages.urllib3.util.url") feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/_markerlib/0000755000076500000240000000000012765362057027023 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/_markerlib/__init__.py0000644000076500000240000000106412700725533031124 0ustar jmstaff00000000000000try: import ast from pip._vendor._markerlib.markers import default_environment, compile, interpret except ImportError: if 'ast' in globals(): raise def default_environment(): return {} def compile(marker): def marker_fn(environment=None, override=None): # 'empty markers are True' heuristic won't install extra deps. return not marker.strip() marker_fn.__doc__ = marker return marker_fn def interpret(marker, environment=None, override=None): return compile(marker)() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/_markerlib/markers.py0000644000076500000240000000761312700725533031037 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- """Interpret PEP 345 environment markers. EXPR [in|==|!=|not in] EXPR [or|and] ... where EXPR belongs to any of those: python_version = '%s.%s' % (sys.version_info[0], sys.version_info[1]) python_full_version = sys.version.split()[0] os.name = os.name sys.platform = sys.platform platform.version = platform.version() platform.machine = platform.machine() platform.python_implementation = platform.python_implementation() a free string, like '2.6', or 'win32' """ __all__ = ['default_environment', 'compile', 'interpret'] import ast import os import platform import sys import weakref _builtin_compile = compile try: from platform import python_implementation except ImportError: if os.name == "java": # Jython 2.5 has ast module, but not platform.python_implementation() function. def python_implementation(): return "Jython" else: raise # restricted set of variables _VARS = {'sys.platform': sys.platform, 'python_version': '%s.%s' % sys.version_info[:2], # FIXME parsing sys.platform is not reliable, but there is no other # way to get e.g. 2.7.2+, and the PEP is defined with sys.version 'python_full_version': sys.version.split(' ', 1)[0], 'os.name': os.name, 'platform.version': platform.version(), 'platform.machine': platform.machine(), 'platform.python_implementation': python_implementation(), 'extra': None # wheel extension } for var in list(_VARS.keys()): if '.' in var: _VARS[var.replace('.', '_')] = _VARS[var] def default_environment(): """Return copy of default PEP 385 globals dictionary.""" return dict(_VARS) class ASTWhitelist(ast.NodeTransformer): def __init__(self, statement): self.statement = statement # for error messages ALLOWED = (ast.Compare, ast.BoolOp, ast.Attribute, ast.Name, ast.Load, ast.Str) # Bool operations ALLOWED += (ast.And, ast.Or) # Comparison operations ALLOWED += (ast.Eq, ast.Gt, ast.GtE, ast.In, ast.Is, ast.IsNot, ast.Lt, ast.LtE, ast.NotEq, ast.NotIn) def visit(self, node): """Ensure statement only contains allowed nodes.""" if not isinstance(node, self.ALLOWED): raise SyntaxError('Not allowed in environment markers.\n%s\n%s' % (self.statement, (' ' * node.col_offset) + '^')) return ast.NodeTransformer.visit(self, node) def visit_Attribute(self, node): """Flatten one level of attribute access.""" new_node = ast.Name("%s.%s" % (node.value.id, node.attr), node.ctx) return ast.copy_location(new_node, node) def parse_marker(marker): tree = ast.parse(marker, mode='eval') new_tree = ASTWhitelist(marker).generic_visit(tree) return new_tree def compile_marker(parsed_marker): return _builtin_compile(parsed_marker, '', 'eval', dont_inherit=True) _cache = weakref.WeakValueDictionary() def compile(marker): """Return compiled marker as a function accepting an environment dict.""" try: return _cache[marker] except KeyError: pass if not marker.strip(): def marker_fn(environment=None, override=None): """""" return True else: compiled_marker = compile_marker(parse_marker(marker)) def marker_fn(environment=None, override=None): """override updates environment""" if override is None: override = {} if environment is None: environment = default_environment() environment.update(override) return eval(compiled_marker, environment) marker_fn.__doc__ = marker _cache[marker] = marker_fn return _cache[marker] def interpret(marker, environment=None): return compile(marker)(environment) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/0000755000076500000240000000000012765362057027360 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/__init__.py0000644000076500000240000000045612700725533031465 0ustar jmstaff00000000000000"""CacheControl import Interface. Make it easy to import from cachecontrol without long namespaces. """ __author__ = 'Eric Larson' __email__ = 'eric@ionrock.org' __version__ = '0.11.6' from .wrapper import CacheControl from .adapter import CacheControlAdapter from .controller import CacheController feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/_cmd.py0000644000076500000240000000245012700725533030624 0ustar jmstaff00000000000000import logging from pip._vendor import requests from pip._vendor.cachecontrol.adapter import CacheControlAdapter from pip._vendor.cachecontrol.cache import DictCache from pip._vendor.cachecontrol.controller import logger from argparse import ArgumentParser def setup_logging(): logger.setLevel(logging.DEBUG) handler = logging.StreamHandler() logger.addHandler(handler) def get_session(): adapter = CacheControlAdapter( DictCache(), cache_etags=True, serializer=None, heuristic=None, ) sess = requests.Session() sess.mount('http://', adapter) sess.mount('https://', adapter) sess.cache_controller = adapter.controller return sess def get_args(): parser = ArgumentParser() parser.add_argument('url', help='The URL to try and cache') return parser.parse_args() def main(args=None): args = get_args() sess = get_session() # Make a request to get a response resp = sess.get(args.url) # Turn on logging setup_logging() # try setting the cache sess.cache_controller.cache_response(resp.request, resp.raw) # Now try to get it if sess.cache_controller.cached_request(resp.request): print('Cached!') else: print('Not cached :(') if __name__ == '__main__': main() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/adapter.py0000644000076500000240000001014412700725533031341 0ustar jmstaff00000000000000import functools from pip._vendor.requests.adapters import HTTPAdapter from .controller import CacheController from .cache import DictCache from .filewrapper import CallbackFileWrapper class CacheControlAdapter(HTTPAdapter): invalidating_methods = set(['PUT', 'DELETE']) def __init__(self, cache=None, cache_etags=True, controller_class=None, serializer=None, heuristic=None, *args, **kw): super(CacheControlAdapter, self).__init__(*args, **kw) self.cache = cache or DictCache() self.heuristic = heuristic controller_factory = controller_class or CacheController self.controller = controller_factory( self.cache, cache_etags=cache_etags, serializer=serializer, ) def send(self, request, **kw): """ Send a request. Use the request information to see if it exists in the cache and cache the response if we need to and can. """ if request.method == 'GET': cached_response = self.controller.cached_request(request) if cached_response: return self.build_response(request, cached_response, from_cache=True) # check for etags and add headers if appropriate request.headers.update( self.controller.conditional_headers(request) ) resp = super(CacheControlAdapter, self).send(request, **kw) return resp def build_response(self, request, response, from_cache=False): """ Build a response by making a request or using the cache. This will end up calling send and returning a potentially cached response """ if not from_cache and request.method == 'GET': # apply any expiration heuristics if response.status == 304: # We must have sent an ETag request. This could mean # that we've been expired already or that we simply # have an etag. In either case, we want to try and # update the cache if that is the case. cached_response = self.controller.update_cached_response( request, response ) if cached_response is not response: from_cache = True # We are done with the server response, read a # possible response body (compliant servers will # not return one, but we cannot be 100% sure) and # release the connection back to the pool. response.read(decode_content=False) response.release_conn() response = cached_response # We always cache the 301 responses elif response.status == 301: self.controller.cache_response(request, response) else: # Check for any heuristics that might update headers # before trying to cache. if self.heuristic: response = self.heuristic.apply(response) # Wrap the response file with a wrapper that will cache the # response when the stream has been consumed. response._fp = CallbackFileWrapper( response._fp, functools.partial( self.controller.cache_response, request, response, ) ) resp = super(CacheControlAdapter, self).build_response( request, response ) # See if we should invalidate the cache. if request.method in self.invalidating_methods and resp.ok: cache_url = self.controller.cache_url(request.url) self.cache.delete(cache_url) # Give the request a from_cache attr to let people use it resp.from_cache = from_cache return resp def close(self): self.cache.close() super(CacheControlAdapter, self).close() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/cache.py0000644000076500000240000000142612700725533030767 0ustar jmstaff00000000000000""" The cache object API for implementing caches. The default is a thread safe in-memory dictionary. """ from threading import Lock class BaseCache(object): def get(self, key): raise NotImplemented() def set(self, key, value): raise NotImplemented() def delete(self, key): raise NotImplemented() def close(self): pass class DictCache(BaseCache): def __init__(self, init_dict=None): self.lock = Lock() self.data = init_dict or {} def get(self, key): return self.data.get(key, None) def set(self, key, value): with self.lock: self.data.update({key: value}) def delete(self, key): with self.lock: if key in self.data: self.data.pop(key) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/0000755000076500000240000000000012765362057030606 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/__init__.py0000644000076500000240000000056112700725533032710 0ustar jmstaff00000000000000from textwrap import dedent try: from .file_cache import FileCache except ImportError: notice = dedent(''' NOTE: In order to use the FileCache you must have lockfile installed. You can install it via pip: pip install lockfile ''') print(notice) try: import redis from .redis_cache import RedisCache except ImportError: pass ././@LongLink0000000000000000000000000000014600000000000011216 Lustar 00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/file_cache.pyfeedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/file_cache.p0000644000076500000240000000671412700725533033030 0ustar jmstaff00000000000000import hashlib import os from pip._vendor.lockfile import LockFile from pip._vendor.lockfile.mkdirlockfile import MkdirLockFile from ..cache import BaseCache from ..controller import CacheController def _secure_open_write(filename, fmode): # We only want to write to this file, so open it in write only mode flags = os.O_WRONLY # os.O_CREAT | os.O_EXCL will fail if the file already exists, so we only # will open *new* files. # We specify this because we want to ensure that the mode we pass is the # mode of the file. flags |= os.O_CREAT | os.O_EXCL # Do not follow symlinks to prevent someone from making a symlink that # we follow and insecurely open a cache file. if hasattr(os, "O_NOFOLLOW"): flags |= os.O_NOFOLLOW # On Windows we'll mark this file as binary if hasattr(os, "O_BINARY"): flags |= os.O_BINARY # Before we open our file, we want to delete any existing file that is # there try: os.remove(filename) except (IOError, OSError): # The file must not exist already, so we can just skip ahead to opening pass # Open our file, the use of os.O_CREAT | os.O_EXCL will ensure that if a # race condition happens between the os.remove and this line, that an # error will be raised. Because we utilize a lockfile this should only # happen if someone is attempting to attack us. fd = os.open(filename, flags, fmode) try: return os.fdopen(fd, "wb") except: # An error occurred wrapping our FD in a file object os.close(fd) raise class FileCache(BaseCache): def __init__(self, directory, forever=False, filemode=0o0600, dirmode=0o0700, use_dir_lock=None, lock_class=None): if use_dir_lock is not None and lock_class is not None: raise ValueError("Cannot use use_dir_lock and lock_class together") if use_dir_lock: lock_class = MkdirLockFile if lock_class is None: lock_class = LockFile self.directory = directory self.forever = forever self.filemode = filemode self.dirmode = dirmode self.lock_class = lock_class @staticmethod def encode(x): return hashlib.sha224(x.encode()).hexdigest() def _fn(self, name): # NOTE: This method should not change as some may depend on it. # See: https://github.com/ionrock/cachecontrol/issues/63 hashed = self.encode(name) parts = list(hashed[:5]) + [hashed] return os.path.join(self.directory, *parts) def get(self, key): name = self._fn(key) if not os.path.exists(name): return None with open(name, 'rb') as fh: return fh.read() def set(self, key, value): name = self._fn(key) # Make sure the directory exists try: os.makedirs(os.path.dirname(name), self.dirmode) except (IOError, OSError): pass with self.lock_class(name) as lock: # Write our actual file with _secure_open_write(lock.path, self.filemode) as fh: fh.write(value) def delete(self, key): name = self._fn(key) if not self.forever: os.remove(name) def url_to_file_path(url, filecache): """Return the file cache path based on the URL. This does not ensure the file exists! """ key = CacheController.cache_url(url) return filecache._fn(key) ././@LongLink0000000000000000000000000000014700000000000011217 Lustar 00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/redis_cache.pyfeedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/caches/redis_cache.0000644000076500000240000000171512700725533033033 0ustar jmstaff00000000000000from __future__ import division from datetime import datetime def total_seconds(td): """Python 2.6 compatability""" if hasattr(td, 'total_seconds'): return td.total_seconds() ms = td.microseconds secs = (td.seconds + td.days * 24 * 3600) return (ms + secs * 10**6) / 10**6 class RedisCache(object): def __init__(self, conn): self.conn = conn def get(self, key): return self.conn.get(key) def set(self, key, value, expires=None): if not expires: self.conn.set(key, value) else: expires = expires - datetime.now() self.conn.setex(key, total_seconds(expires), value) def delete(self, key): self.conn.delete(key) def clear(self): """Helper for clearing all the keys in a database. Use with caution!""" for key in self.conn.keys(): self.conn.delete(key) def close(self): self.conn.disconnect() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/compat.py0000644000076500000240000000064012700725533031204 0ustar jmstaff00000000000000try: from urllib.parse import urljoin except ImportError: from urlparse import urljoin try: import cPickle as pickle except ImportError: import pickle from pip._vendor.requests.packages.urllib3.response import HTTPResponse from pip._vendor.requests.packages.urllib3.util import is_fp_closed # Replicate some six behaviour try: text_type = (unicode,) except NameError: text_type = (str,) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/controller.py0000644000076500000240000003130412700725533032105 0ustar jmstaff00000000000000""" The httplib2 algorithms ported for use with requests. """ import logging import re import calendar import time from email.utils import parsedate_tz from pip._vendor.requests.structures import CaseInsensitiveDict from .cache import DictCache from .serialize import Serializer logger = logging.getLogger(__name__) URI = re.compile(r"^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?") def parse_uri(uri): """Parses a URI using the regex given in Appendix B of RFC 3986. (scheme, authority, path, query, fragment) = parse_uri(uri) """ groups = URI.match(uri).groups() return (groups[1], groups[3], groups[4], groups[6], groups[8]) class CacheController(object): """An interface to see if request should cached or not. """ def __init__(self, cache=None, cache_etags=True, serializer=None): self.cache = cache or DictCache() self.cache_etags = cache_etags self.serializer = serializer or Serializer() @classmethod def _urlnorm(cls, uri): """Normalize the URL to create a safe key for the cache""" (scheme, authority, path, query, fragment) = parse_uri(uri) if not scheme or not authority: raise Exception("Only absolute URIs are allowed. uri = %s" % uri) scheme = scheme.lower() authority = authority.lower() if not path: path = "/" # Could do syntax based normalization of the URI before # computing the digest. See Section 6.2.2 of Std 66. request_uri = query and "?".join([path, query]) or path defrag_uri = scheme + "://" + authority + request_uri return defrag_uri @classmethod def cache_url(cls, uri): return cls._urlnorm(uri) def parse_cache_control(self, headers): """ Parse the cache control headers returning a dictionary with values for the different directives. """ retval = {} cc_header = 'cache-control' if 'Cache-Control' in headers: cc_header = 'Cache-Control' if cc_header in headers: parts = headers[cc_header].split(',') parts_with_args = [ tuple([x.strip().lower() for x in part.split("=", 1)]) for part in parts if -1 != part.find("=") ] parts_wo_args = [ (name.strip().lower(), 1) for name in parts if -1 == name.find("=") ] retval = dict(parts_with_args + parts_wo_args) return retval def cached_request(self, request): """ Return a cached response if it exists in the cache, otherwise return False. """ cache_url = self.cache_url(request.url) logger.debug('Looking up "%s" in the cache', cache_url) cc = self.parse_cache_control(request.headers) # Bail out if the request insists on fresh data if 'no-cache' in cc: logger.debug('Request header has "no-cache", cache bypassed') return False if 'max-age' in cc and cc['max-age'] == 0: logger.debug('Request header has "max_age" as 0, cache bypassed') return False # Request allows serving from the cache, let's see if we find something cache_data = self.cache.get(cache_url) if cache_data is None: logger.debug('No cache entry available') return False # Check whether it can be deserialized resp = self.serializer.loads(request, cache_data) if not resp: logger.warning('Cache entry deserialization failed, entry ignored') return False # If we have a cached 301, return it immediately. We don't # need to test our response for other headers b/c it is # intrinsically "cacheable" as it is Permanent. # See: # https://tools.ietf.org/html/rfc7231#section-6.4.2 # # Client can try to refresh the value by repeating the request # with cache busting headers as usual (ie no-cache). if resp.status == 301: msg = ('Returning cached "301 Moved Permanently" response ' '(ignoring date and etag information)') logger.debug(msg) return resp headers = CaseInsensitiveDict(resp.headers) if not headers or 'date' not in headers: if 'etag' not in headers: # Without date or etag, the cached response can never be used # and should be deleted. logger.debug('Purging cached response: no date or etag') self.cache.delete(cache_url) logger.debug('Ignoring cached response: no date') return False now = time.time() date = calendar.timegm( parsedate_tz(headers['date']) ) current_age = max(0, now - date) logger.debug('Current age based on date: %i', current_age) # TODO: There is an assumption that the result will be a # urllib3 response object. This may not be best since we # could probably avoid instantiating or constructing the # response until we know we need it. resp_cc = self.parse_cache_control(headers) # determine freshness freshness_lifetime = 0 # Check the max-age pragma in the cache control header if 'max-age' in resp_cc and resp_cc['max-age'].isdigit(): freshness_lifetime = int(resp_cc['max-age']) logger.debug('Freshness lifetime from max-age: %i', freshness_lifetime) # If there isn't a max-age, check for an expires header elif 'expires' in headers: expires = parsedate_tz(headers['expires']) if expires is not None: expire_time = calendar.timegm(expires) - date freshness_lifetime = max(0, expire_time) logger.debug("Freshness lifetime from expires: %i", freshness_lifetime) # Determine if we are setting freshness limit in the # request. Note, this overrides what was in the response. if 'max-age' in cc: try: freshness_lifetime = int(cc['max-age']) logger.debug('Freshness lifetime from request max-age: %i', freshness_lifetime) except ValueError: freshness_lifetime = 0 if 'min-fresh' in cc: try: min_fresh = int(cc['min-fresh']) except ValueError: min_fresh = 0 # adjust our current age by our min fresh current_age += min_fresh logger.debug('Adjusted current age from min-fresh: %i', current_age) # Return entry if it is fresh enough if freshness_lifetime > current_age: logger.debug('The response is "fresh", returning cached response') logger.debug('%i > %i', freshness_lifetime, current_age) return resp # we're not fresh. If we don't have an Etag, clear it out if 'etag' not in headers: logger.debug( 'The cached response is "stale" with no etag, purging' ) self.cache.delete(cache_url) # return the original handler return False def conditional_headers(self, request): cache_url = self.cache_url(request.url) resp = self.serializer.loads(request, self.cache.get(cache_url)) new_headers = {} if resp: headers = CaseInsensitiveDict(resp.headers) if 'etag' in headers: new_headers['If-None-Match'] = headers['ETag'] if 'last-modified' in headers: new_headers['If-Modified-Since'] = headers['Last-Modified'] return new_headers def cache_response(self, request, response, body=None): """ Algorithm for caching requests. This assumes a requests Response object. """ # From httplib2: Don't cache 206's since we aren't going to # handle byte range requests cacheable_status_codes = [200, 203, 300, 301] if response.status not in cacheable_status_codes: logger.debug( 'Status code %s not in %s', response.status, cacheable_status_codes ) return response_headers = CaseInsensitiveDict(response.headers) # If we've been given a body, our response has a Content-Length, that # Content-Length is valid then we can check to see if the body we've # been given matches the expected size, and if it doesn't we'll just # skip trying to cache it. if (body is not None and "content-length" in response_headers and response_headers["content-length"].isdigit() and int(response_headers["content-length"]) != len(body)): return cc_req = self.parse_cache_control(request.headers) cc = self.parse_cache_control(response_headers) cache_url = self.cache_url(request.url) logger.debug('Updating cache with response from "%s"', cache_url) # Delete it from the cache if we happen to have it stored there no_store = False if cc.get('no-store'): no_store = True logger.debug('Response header has "no-store"') if cc_req.get('no-store'): no_store = True logger.debug('Request header has "no-store"') if no_store and self.cache.get(cache_url): logger.debug('Purging existing cache entry to honor "no-store"') self.cache.delete(cache_url) # If we've been given an etag, then keep the response if self.cache_etags and 'etag' in response_headers: logger.debug('Caching due to etag') self.cache.set( cache_url, self.serializer.dumps(request, response, body=body), ) # Add to the cache any 301s. We do this before looking that # the Date headers. elif response.status == 301: logger.debug('Caching permanant redirect') self.cache.set( cache_url, self.serializer.dumps(request, response) ) # Add to the cache if the response headers demand it. If there # is no date header then we can't do anything about expiring # the cache. elif 'date' in response_headers: # cache when there is a max-age > 0 if cc and cc.get('max-age'): if int(cc['max-age']) > 0: logger.debug('Caching b/c date exists and max-age > 0') self.cache.set( cache_url, self.serializer.dumps(request, response, body=body), ) # If the request can expire, it means we should cache it # in the meantime. elif 'expires' in response_headers: if response_headers['expires']: logger.debug('Caching b/c of expires header') self.cache.set( cache_url, self.serializer.dumps(request, response, body=body), ) def update_cached_response(self, request, response): """On a 304 we will get a new set of headers that we want to update our cached value with, assuming we have one. This should only ever be called when we've sent an ETag and gotten a 304 as the response. """ cache_url = self.cache_url(request.url) cached_response = self.serializer.loads( request, self.cache.get(cache_url) ) if not cached_response: # we didn't have a cached response return response # Lets update our headers with the headers from the new request: # http://tools.ietf.org/html/draft-ietf-httpbis-p4-conditional-26#section-4.1 # # The server isn't supposed to send headers that would make # the cached body invalid. But... just in case, we'll be sure # to strip out ones we know that might be problmatic due to # typical assumptions. excluded_headers = [ "content-length", ] cached_response.headers.update( dict((k, v) for k, v in response.headers.items() if k.lower() not in excluded_headers) ) # we want a 200 b/c we have content via the cache cached_response.status = 200 # update our cache self.cache.set( cache_url, self.serializer.dumps(request, cached_response), ) return cached_response feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/filewrapper.py0000644000076500000240000000417012700725533032243 0ustar jmstaff00000000000000from io import BytesIO class CallbackFileWrapper(object): """ Small wrapper around a fp object which will tee everything read into a buffer, and when that file is closed it will execute a callback with the contents of that buffer. All attributes are proxied to the underlying file object. This class uses members with a double underscore (__) leading prefix so as not to accidentally shadow an attribute. """ def __init__(self, fp, callback): self.__buf = BytesIO() self.__fp = fp self.__callback = callback def __getattr__(self, name): # The vaguaries of garbage collection means that self.__fp is # not always set. By using __getattribute__ and the private # name[0] allows looking up the attribute value and raising an # AttributeError when it doesn't exist. This stop thigns from # infinitely recursing calls to getattr in the case where # self.__fp hasn't been set. # # [0] https://docs.python.org/2/reference/expressions.html#atom-identifiers fp = self.__getattribute__('_CallbackFileWrapper__fp') return getattr(fp, name) def __is_fp_closed(self): try: return self.__fp.fp is None except AttributeError: pass try: return self.__fp.closed except AttributeError: pass # We just don't cache it then. # TODO: Add some logging here... return False def read(self, amt=None): data = self.__fp.read(amt) self.__buf.write(data) if self.__is_fp_closed(): if self.__callback: self.__callback(self.__buf.getvalue()) # We assign this to None here, because otherwise we can get into # really tricky problems where the CPython interpreter dead locks # because the callback is holding a reference to something which # has a __del__ method. Setting this to None breaks the cycle # and allows the garbage collector to do it's thing normally. self.__callback = None return data feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/heuristics.py0000644000076500000240000001005512700725533032104 0ustar jmstaff00000000000000import calendar import time from email.utils import formatdate, parsedate, parsedate_tz from datetime import datetime, timedelta TIME_FMT = "%a, %d %b %Y %H:%M:%S GMT" def expire_after(delta, date=None): date = date or datetime.now() return date + delta def datetime_to_header(dt): return formatdate(calendar.timegm(dt.timetuple())) class BaseHeuristic(object): def warning(self, response): """ Return a valid 1xx warning header value describing the cache adjustments. The response is provided too allow warnings like 113 http://tools.ietf.org/html/rfc7234#section-5.5.4 where we need to explicitly say response is over 24 hours old. """ return '110 - "Response is Stale"' def update_headers(self, response): """Update the response headers with any new headers. NOTE: This SHOULD always include some Warning header to signify that the response was cached by the client, not by way of the provided headers. """ return {} def apply(self, response): updated_headers = self.update_headers(response) if updated_headers: response.headers.update(updated_headers) warning_header_value = self.warning(response) if warning_header_value is not None: response.headers.update({'Warning': warning_header_value}) return response class OneDayCache(BaseHeuristic): """ Cache the response by providing an expires 1 day in the future. """ def update_headers(self, response): headers = {} if 'expires' not in response.headers: date = parsedate(response.headers['date']) expires = expire_after(timedelta(days=1), date=datetime(*date[:6])) headers['expires'] = datetime_to_header(expires) headers['cache-control'] = 'public' return headers class ExpiresAfter(BaseHeuristic): """ Cache **all** requests for a defined time period. """ def __init__(self, **kw): self.delta = timedelta(**kw) def update_headers(self, response): expires = expire_after(self.delta) return { 'expires': datetime_to_header(expires), 'cache-control': 'public', } def warning(self, response): tmpl = '110 - Automatically cached for %s. Response might be stale' return tmpl % self.delta class LastModified(BaseHeuristic): """ If there is no Expires header already, fall back on Last-Modified using the heuristic from http://tools.ietf.org/html/rfc7234#section-4.2.2 to calculate a reasonable value. Firefox also does something like this per https://developer.mozilla.org/en-US/docs/Web/HTTP/Caching_FAQ http://lxr.mozilla.org/mozilla-release/source/netwerk/protocol/http/nsHttpResponseHead.cpp#397 Unlike mozilla we limit this to 24-hr. """ cacheable_by_default_statuses = set([ 200, 203, 204, 206, 300, 301, 404, 405, 410, 414, 501 ]) def update_headers(self, resp): headers = resp.headers if 'expires' in headers: return {} if 'cache-control' in headers and headers['cache-control'] != 'public': return {} if resp.status not in self.cacheable_by_default_statuses: return {} if 'date' not in headers or 'last-modified' not in headers: return {} date = calendar.timegm(parsedate_tz(headers['date'])) last_modified = parsedate(headers['last-modified']) if date is None or last_modified is None: return {} now = time.time() current_age = max(0, now - date) delta = date - calendar.timegm(last_modified) freshness_lifetime = max(0, min(delta / 10, 24 * 3600)) if freshness_lifetime <= current_age: return {} expires = date + freshness_lifetime return {'expires': time.strftime(TIME_FMT, time.gmtime(expires))} def warning(self, resp): return None feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/serialize.py0000644000076500000240000001424112700725533031712 0ustar jmstaff00000000000000import base64 import io import json import zlib from pip._vendor.requests.structures import CaseInsensitiveDict from .compat import HTTPResponse, pickle, text_type def _b64_encode_bytes(b): return base64.b64encode(b).decode("ascii") def _b64_encode_str(s): return _b64_encode_bytes(s.encode("utf8")) def _b64_encode(s): if isinstance(s, text_type): return _b64_encode_str(s) return _b64_encode_bytes(s) def _b64_decode_bytes(b): return base64.b64decode(b.encode("ascii")) def _b64_decode_str(s): return _b64_decode_bytes(s).decode("utf8") class Serializer(object): def dumps(self, request, response, body=None): response_headers = CaseInsensitiveDict(response.headers) if body is None: body = response.read(decode_content=False) # NOTE: 99% sure this is dead code. I'm only leaving it # here b/c I don't have a test yet to prove # it. Basically, before using # `cachecontrol.filewrapper.CallbackFileWrapper`, # this made an effort to reset the file handle. The # `CallbackFileWrapper` short circuits this code by # setting the body as the content is consumed, the # result being a `body` argument is *always* passed # into cache_response, and in turn, # `Serializer.dump`. response._fp = io.BytesIO(body) data = { "response": { "body": _b64_encode_bytes(body), "headers": dict( (_b64_encode(k), _b64_encode(v)) for k, v in response.headers.items() ), "status": response.status, "version": response.version, "reason": _b64_encode_str(response.reason), "strict": response.strict, "decode_content": response.decode_content, }, } # Construct our vary headers data["vary"] = {} if "vary" in response_headers: varied_headers = response_headers['vary'].split(',') for header in varied_headers: header = header.strip() data["vary"][header] = request.headers.get(header, None) # Encode our Vary headers to ensure they can be serialized as JSON data["vary"] = dict( (_b64_encode(k), _b64_encode(v) if v is not None else v) for k, v in data["vary"].items() ) return b",".join([ b"cc=2", zlib.compress( json.dumps( data, separators=(",", ":"), sort_keys=True, ).encode("utf8"), ), ]) def loads(self, request, data): # Short circuit if we've been given an empty set of data if not data: return # Determine what version of the serializer the data was serialized # with try: ver, data = data.split(b",", 1) except ValueError: ver = b"cc=0" # Make sure that our "ver" is actually a version and isn't a false # positive from a , being in the data stream. if ver[:3] != b"cc=": data = ver + data ver = b"cc=0" # Get the version number out of the cc=N ver = ver.split(b"=", 1)[-1].decode("ascii") # Dispatch to the actual load method for the given version try: return getattr(self, "_loads_v{0}".format(ver))(request, data) except AttributeError: # This is a version we don't have a loads function for, so we'll # just treat it as a miss and return None return def prepare_response(self, request, cached): """Verify our vary headers match and construct a real urllib3 HTTPResponse object. """ # Special case the '*' Vary value as it means we cannot actually # determine if the cached response is suitable for this request. if "*" in cached.get("vary", {}): return # Ensure that the Vary headers for the cached response match our # request for header, value in cached.get("vary", {}).items(): if request.headers.get(header, None) != value: return body_raw = cached["response"].pop("body") try: body = io.BytesIO(body_raw) except TypeError: # This can happen if cachecontrol serialized to v1 format (pickle) # using Python 2. A Python 2 str(byte string) will be unpickled as # a Python 3 str (unicode string), which will cause the above to # fail with: # # TypeError: 'str' does not support the buffer interface body = io.BytesIO(body_raw.encode('utf8')) return HTTPResponse( body=body, preload_content=False, **cached["response"] ) def _loads_v0(self, request, data): # The original legacy cache data. This doesn't contain enough # information to construct everything we need, so we'll treat this as # a miss. return def _loads_v1(self, request, data): try: cached = pickle.loads(data) except ValueError: return return self.prepare_response(request, cached) def _loads_v2(self, request, data): try: cached = json.loads(zlib.decompress(data).decode("utf8")) except ValueError: return # We need to decode the items that we've base64 encoded cached["response"]["body"] = _b64_decode_bytes( cached["response"]["body"] ) cached["response"]["headers"] = dict( (_b64_decode_str(k), _b64_decode_str(v)) for k, v in cached["response"]["headers"].items() ) cached["response"]["reason"] = _b64_decode_str( cached["response"]["reason"], ) cached["vary"] = dict( (_b64_decode_str(k), _b64_decode_str(v) if v is not None else v) for k, v in cached["vary"].items() ) return self.prepare_response(request, cached) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/cachecontrol/wrapper.py0000644000076500000240000000076212700725533031406 0ustar jmstaff00000000000000from .adapter import CacheControlAdapter from .cache import DictCache def CacheControl(sess, cache=None, cache_etags=True, serializer=None, heuristic=None): cache = cache or DictCache() adapter = CacheControlAdapter( cache, cache_etags=cache_etags, serializer=serializer, heuristic=heuristic, ) sess.mount('http://', adapter) sess.mount('https://', adapter) return sess feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/0000755000076500000240000000000012765362057026511 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/__init__.py0000644000076500000240000000036012700725533030610 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. from .initialise import init, deinit, reinit, colorama_text from .ansi import Fore, Back, Style, Cursor from .ansitowin32 import AnsiToWin32 __version__ = '0.3.6' feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/ansi.py0000644000076500000240000000473412700725533030014 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. ''' This module generates ANSI character codes to printing colors to terminals. See: http://en.wikipedia.org/wiki/ANSI_escape_code ''' CSI = '\033[' OSC = '\033]' BEL = '\007' def code_to_chars(code): return CSI + str(code) + 'm' def set_title(title): return OSC + '2;' + title + BEL def clear_screen(mode=2): return CSI + str(mode) + 'J' def clear_line(mode=2): return CSI + str(mode) + 'K' class AnsiCodes(object): def __init__(self): # the subclasses declare class attributes which are numbers. # Upon instantiation we define instance attributes, which are the same # as the class attributes but wrapped with the ANSI escape sequence for name in dir(self): if not name.startswith('_'): value = getattr(self, name) setattr(self, name, code_to_chars(value)) class AnsiCursor(object): def UP(self, n=1): return CSI + str(n) + 'A' def DOWN(self, n=1): return CSI + str(n) + 'B' def FORWARD(self, n=1): return CSI + str(n) + 'C' def BACK(self, n=1): return CSI + str(n) + 'D' def POS(self, x=1, y=1): return CSI + str(y) + ';' + str(x) + 'H' class AnsiFore(AnsiCodes): BLACK = 30 RED = 31 GREEN = 32 YELLOW = 33 BLUE = 34 MAGENTA = 35 CYAN = 36 WHITE = 37 RESET = 39 # These are fairly well supported, but not part of the standard. LIGHTBLACK_EX = 90 LIGHTRED_EX = 91 LIGHTGREEN_EX = 92 LIGHTYELLOW_EX = 93 LIGHTBLUE_EX = 94 LIGHTMAGENTA_EX = 95 LIGHTCYAN_EX = 96 LIGHTWHITE_EX = 97 class AnsiBack(AnsiCodes): BLACK = 40 RED = 41 GREEN = 42 YELLOW = 43 BLUE = 44 MAGENTA = 45 CYAN = 46 WHITE = 47 RESET = 49 # These are fairly well supported, but not part of the standard. LIGHTBLACK_EX = 100 LIGHTRED_EX = 101 LIGHTGREEN_EX = 102 LIGHTYELLOW_EX = 103 LIGHTBLUE_EX = 104 LIGHTMAGENTA_EX = 105 LIGHTCYAN_EX = 106 LIGHTWHITE_EX = 107 class AnsiStyle(AnsiCodes): BRIGHT = 1 DIM = 2 NORMAL = 22 RESET_ALL = 0 Fore = AnsiFore() Back = AnsiBack() Style = AnsiStyle() Cursor = AnsiCursor() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/ansitowin32.py0000644000076500000240000002251112700725533031233 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. import re import sys import os from .ansi import AnsiFore, AnsiBack, AnsiStyle, Style from .winterm import WinTerm, WinColor, WinStyle from .win32 import windll, winapi_test winterm = None if windll is not None: winterm = WinTerm() def is_a_tty(stream): return hasattr(stream, 'isatty') and stream.isatty() class StreamWrapper(object): ''' Wraps a stream (such as stdout), acting as a transparent proxy for all attribute access apart from method 'write()', which is delegated to our Converter instance. ''' def __init__(self, wrapped, converter): # double-underscore everything to prevent clashes with names of # attributes on the wrapped stream object. self.__wrapped = wrapped self.__convertor = converter def __getattr__(self, name): return getattr(self.__wrapped, name) def write(self, text): self.__convertor.write(text) class AnsiToWin32(object): ''' Implements a 'write()' method which, on Windows, will strip ANSI character sequences from the text, and if outputting to a tty, will convert them into win32 function calls. ''' ANSI_CSI_RE = re.compile('\001?\033\[((?:\d|;)*)([a-zA-Z])\002?') # Control Sequence Introducer ANSI_OSC_RE = re.compile('\001?\033\]((?:.|;)*?)(\x07)\002?') # Operating System Command def __init__(self, wrapped, convert=None, strip=None, autoreset=False): # The wrapped stream (normally sys.stdout or sys.stderr) self.wrapped = wrapped # should we reset colors to defaults after every .write() self.autoreset = autoreset # create the proxy wrapping our output stream self.stream = StreamWrapper(wrapped, self) on_windows = os.name == 'nt' # We test if the WinAPI works, because even if we are on Windows # we may be using a terminal that doesn't support the WinAPI # (e.g. Cygwin Terminal). In this case it's up to the terminal # to support the ANSI codes. conversion_supported = on_windows and winapi_test() # should we strip ANSI sequences from our output? if strip is None: strip = conversion_supported or (not wrapped.closed and not is_a_tty(wrapped)) self.strip = strip # should we should convert ANSI sequences into win32 calls? if convert is None: convert = conversion_supported and not wrapped.closed and is_a_tty(wrapped) self.convert = convert # dict of ansi codes to win32 functions and parameters self.win32_calls = self.get_win32_calls() # are we wrapping stderr? self.on_stderr = self.wrapped is sys.stderr def should_wrap(self): ''' True if this class is actually needed. If false, then the output stream will not be affected, nor will win32 calls be issued, so wrapping stdout is not actually required. This will generally be False on non-Windows platforms, unless optional functionality like autoreset has been requested using kwargs to init() ''' return self.convert or self.strip or self.autoreset def get_win32_calls(self): if self.convert and winterm: return { AnsiStyle.RESET_ALL: (winterm.reset_all, ), AnsiStyle.BRIGHT: (winterm.style, WinStyle.BRIGHT), AnsiStyle.DIM: (winterm.style, WinStyle.NORMAL), AnsiStyle.NORMAL: (winterm.style, WinStyle.NORMAL), AnsiFore.BLACK: (winterm.fore, WinColor.BLACK), AnsiFore.RED: (winterm.fore, WinColor.RED), AnsiFore.GREEN: (winterm.fore, WinColor.GREEN), AnsiFore.YELLOW: (winterm.fore, WinColor.YELLOW), AnsiFore.BLUE: (winterm.fore, WinColor.BLUE), AnsiFore.MAGENTA: (winterm.fore, WinColor.MAGENTA), AnsiFore.CYAN: (winterm.fore, WinColor.CYAN), AnsiFore.WHITE: (winterm.fore, WinColor.GREY), AnsiFore.RESET: (winterm.fore, ), AnsiFore.LIGHTBLACK_EX: (winterm.fore, WinColor.BLACK, True), AnsiFore.LIGHTRED_EX: (winterm.fore, WinColor.RED, True), AnsiFore.LIGHTGREEN_EX: (winterm.fore, WinColor.GREEN, True), AnsiFore.LIGHTYELLOW_EX: (winterm.fore, WinColor.YELLOW, True), AnsiFore.LIGHTBLUE_EX: (winterm.fore, WinColor.BLUE, True), AnsiFore.LIGHTMAGENTA_EX: (winterm.fore, WinColor.MAGENTA, True), AnsiFore.LIGHTCYAN_EX: (winterm.fore, WinColor.CYAN, True), AnsiFore.LIGHTWHITE_EX: (winterm.fore, WinColor.GREY, True), AnsiBack.BLACK: (winterm.back, WinColor.BLACK), AnsiBack.RED: (winterm.back, WinColor.RED), AnsiBack.GREEN: (winterm.back, WinColor.GREEN), AnsiBack.YELLOW: (winterm.back, WinColor.YELLOW), AnsiBack.BLUE: (winterm.back, WinColor.BLUE), AnsiBack.MAGENTA: (winterm.back, WinColor.MAGENTA), AnsiBack.CYAN: (winterm.back, WinColor.CYAN), AnsiBack.WHITE: (winterm.back, WinColor.GREY), AnsiBack.RESET: (winterm.back, ), AnsiBack.LIGHTBLACK_EX: (winterm.back, WinColor.BLACK, True), AnsiBack.LIGHTRED_EX: (winterm.back, WinColor.RED, True), AnsiBack.LIGHTGREEN_EX: (winterm.back, WinColor.GREEN, True), AnsiBack.LIGHTYELLOW_EX: (winterm.back, WinColor.YELLOW, True), AnsiBack.LIGHTBLUE_EX: (winterm.back, WinColor.BLUE, True), AnsiBack.LIGHTMAGENTA_EX: (winterm.back, WinColor.MAGENTA, True), AnsiBack.LIGHTCYAN_EX: (winterm.back, WinColor.CYAN, True), AnsiBack.LIGHTWHITE_EX: (winterm.back, WinColor.GREY, True), } return dict() def write(self, text): if self.strip or self.convert: self.write_and_convert(text) else: self.wrapped.write(text) self.wrapped.flush() if self.autoreset: self.reset_all() def reset_all(self): if self.convert: self.call_win32('m', (0,)) elif not self.strip and not self.wrapped.closed: self.wrapped.write(Style.RESET_ALL) def write_and_convert(self, text): ''' Write the given text to our wrapped stream, stripping any ANSI sequences from the text, and optionally converting them into win32 calls. ''' cursor = 0 text = self.convert_osc(text) for match in self.ANSI_CSI_RE.finditer(text): start, end = match.span() self.write_plain_text(text, cursor, start) self.convert_ansi(*match.groups()) cursor = end self.write_plain_text(text, cursor, len(text)) def write_plain_text(self, text, start, end): if start < end: self.wrapped.write(text[start:end]) self.wrapped.flush() def convert_ansi(self, paramstring, command): if self.convert: params = self.extract_params(command, paramstring) self.call_win32(command, params) def extract_params(self, command, paramstring): if command in 'Hf': params = tuple(int(p) if len(p) != 0 else 1 for p in paramstring.split(';')) while len(params) < 2: # defaults: params = params + (1,) else: params = tuple(int(p) for p in paramstring.split(';') if len(p) != 0) if len(params) == 0: # defaults: if command in 'JKm': params = (0,) elif command in 'ABCD': params = (1,) return params def call_win32(self, command, params): if command == 'm': for param in params: if param in self.win32_calls: func_args = self.win32_calls[param] func = func_args[0] args = func_args[1:] kwargs = dict(on_stderr=self.on_stderr) func(*args, **kwargs) elif command in 'J': winterm.erase_screen(params[0], on_stderr=self.on_stderr) elif command in 'K': winterm.erase_line(params[0], on_stderr=self.on_stderr) elif command in 'Hf': # cursor position - absolute winterm.set_cursor_position(params, on_stderr=self.on_stderr) elif command in 'ABCD': # cursor position - relative n = params[0] # A - up, B - down, C - forward, D - back x, y = {'A': (0, -n), 'B': (0, n), 'C': (n, 0), 'D': (-n, 0)}[command] winterm.cursor_adjust(x, y, on_stderr=self.on_stderr) def convert_osc(self, text): for match in self.ANSI_OSC_RE.finditer(text): start, end = match.span() text = text[:start] + text[end:] paramstring, command = match.groups() if command in '\x07': # \x07 = BEL params = paramstring.split(";") # 0 - change title and icon (we will only change title) # 1 - change icon (we don't support this) # 2 - change title if params[0] in '02': winterm.set_title(params[1]) return text feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/initialise.py0000644000076500000240000000344712700725533031214 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. import atexit import contextlib import sys from .ansitowin32 import AnsiToWin32 orig_stdout = None orig_stderr = None wrapped_stdout = None wrapped_stderr = None atexit_done = False def reset_all(): AnsiToWin32(orig_stdout).reset_all() def init(autoreset=False, convert=None, strip=None, wrap=True): if not wrap and any([autoreset, convert, strip]): raise ValueError('wrap=False conflicts with any other arg=True') global wrapped_stdout, wrapped_stderr global orig_stdout, orig_stderr orig_stdout = sys.stdout orig_stderr = sys.stderr if sys.stdout is None: wrapped_stdout = None else: sys.stdout = wrapped_stdout = \ wrap_stream(orig_stdout, convert, strip, autoreset, wrap) if sys.stderr is None: wrapped_stderr = None else: sys.stderr = wrapped_stderr = \ wrap_stream(orig_stderr, convert, strip, autoreset, wrap) global atexit_done if not atexit_done: atexit.register(reset_all) atexit_done = True def deinit(): if orig_stdout is not None: sys.stdout = orig_stdout if orig_stderr is not None: sys.stderr = orig_stderr @contextlib.contextmanager def colorama_text(*args, **kwargs): init(*args, **kwargs) try: yield finally: deinit() def reinit(): if wrapped_stdout is not None: sys.stdout = wrapped_stdout if wrapped_stderr is not None: sys.stderr = wrapped_stderr def wrap_stream(stream, convert, strip, autoreset, wrap): if wrap: wrapper = AnsiToWin32(stream, convert=convert, strip=strip, autoreset=autoreset) if wrapper.should_wrap(): stream = wrapper.stream return stream feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/win32.py0000644000076500000240000001236512700725533030023 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. # from winbase.h STDOUT = -11 STDERR = -12 try: import ctypes from ctypes import LibraryLoader windll = LibraryLoader(ctypes.WinDLL) from ctypes import wintypes except (AttributeError, ImportError): windll = None SetConsoleTextAttribute = lambda *_: None winapi_test = lambda *_: None else: from ctypes import byref, Structure, c_char, POINTER COORD = wintypes._COORD class CONSOLE_SCREEN_BUFFER_INFO(Structure): """struct in wincon.h.""" _fields_ = [ ("dwSize", COORD), ("dwCursorPosition", COORD), ("wAttributes", wintypes.WORD), ("srWindow", wintypes.SMALL_RECT), ("dwMaximumWindowSize", COORD), ] def __str__(self): return '(%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d)' % ( self.dwSize.Y, self.dwSize.X , self.dwCursorPosition.Y, self.dwCursorPosition.X , self.wAttributes , self.srWindow.Top, self.srWindow.Left, self.srWindow.Bottom, self.srWindow.Right , self.dwMaximumWindowSize.Y, self.dwMaximumWindowSize.X ) _GetStdHandle = windll.kernel32.GetStdHandle _GetStdHandle.argtypes = [ wintypes.DWORD, ] _GetStdHandle.restype = wintypes.HANDLE _GetConsoleScreenBufferInfo = windll.kernel32.GetConsoleScreenBufferInfo _GetConsoleScreenBufferInfo.argtypes = [ wintypes.HANDLE, POINTER(CONSOLE_SCREEN_BUFFER_INFO), ] _GetConsoleScreenBufferInfo.restype = wintypes.BOOL _SetConsoleTextAttribute = windll.kernel32.SetConsoleTextAttribute _SetConsoleTextAttribute.argtypes = [ wintypes.HANDLE, wintypes.WORD, ] _SetConsoleTextAttribute.restype = wintypes.BOOL _SetConsoleCursorPosition = windll.kernel32.SetConsoleCursorPosition _SetConsoleCursorPosition.argtypes = [ wintypes.HANDLE, COORD, ] _SetConsoleCursorPosition.restype = wintypes.BOOL _FillConsoleOutputCharacterA = windll.kernel32.FillConsoleOutputCharacterA _FillConsoleOutputCharacterA.argtypes = [ wintypes.HANDLE, c_char, wintypes.DWORD, COORD, POINTER(wintypes.DWORD), ] _FillConsoleOutputCharacterA.restype = wintypes.BOOL _FillConsoleOutputAttribute = windll.kernel32.FillConsoleOutputAttribute _FillConsoleOutputAttribute.argtypes = [ wintypes.HANDLE, wintypes.WORD, wintypes.DWORD, COORD, POINTER(wintypes.DWORD), ] _FillConsoleOutputAttribute.restype = wintypes.BOOL _SetConsoleTitleW = windll.kernel32.SetConsoleTitleA _SetConsoleTitleW.argtypes = [ wintypes.LPCSTR ] _SetConsoleTitleW.restype = wintypes.BOOL handles = { STDOUT: _GetStdHandle(STDOUT), STDERR: _GetStdHandle(STDERR), } def winapi_test(): handle = handles[STDOUT] csbi = CONSOLE_SCREEN_BUFFER_INFO() success = _GetConsoleScreenBufferInfo( handle, byref(csbi)) return bool(success) def GetConsoleScreenBufferInfo(stream_id=STDOUT): handle = handles[stream_id] csbi = CONSOLE_SCREEN_BUFFER_INFO() success = _GetConsoleScreenBufferInfo( handle, byref(csbi)) return csbi def SetConsoleTextAttribute(stream_id, attrs): handle = handles[stream_id] return _SetConsoleTextAttribute(handle, attrs) def SetConsoleCursorPosition(stream_id, position, adjust=True): position = COORD(*position) # If the position is out of range, do nothing. if position.Y <= 0 or position.X <= 0: return # Adjust for Windows' SetConsoleCursorPosition: # 1. being 0-based, while ANSI is 1-based. # 2. expecting (x,y), while ANSI uses (y,x). adjusted_position = COORD(position.Y - 1, position.X - 1) if adjust: # Adjust for viewport's scroll position sr = GetConsoleScreenBufferInfo(STDOUT).srWindow adjusted_position.Y += sr.Top adjusted_position.X += sr.Left # Resume normal processing handle = handles[stream_id] return _SetConsoleCursorPosition(handle, adjusted_position) def FillConsoleOutputCharacter(stream_id, char, length, start): handle = handles[stream_id] char = c_char(char.encode()) length = wintypes.DWORD(length) num_written = wintypes.DWORD(0) # Note that this is hard-coded for ANSI (vs wide) bytes. success = _FillConsoleOutputCharacterA( handle, char, length, start, byref(num_written)) return num_written.value def FillConsoleOutputAttribute(stream_id, attr, length, start): ''' FillConsoleOutputAttribute( hConsole, csbi.wAttributes, dwConSize, coordScreen, &cCharsWritten )''' handle = handles[stream_id] attribute = wintypes.WORD(attr) length = wintypes.DWORD(length) num_written = wintypes.DWORD(0) # Note that this is hard-coded for ANSI (vs wide) bytes. return _FillConsoleOutputAttribute( handle, attribute, length, start, byref(num_written)) def SetConsoleTitle(title): return _SetConsoleTitleW(title) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/colorama/winterm.py0000644000076500000240000001422212700725533030540 0ustar jmstaff00000000000000# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file. from . import win32 # from wincon.h class WinColor(object): BLACK = 0 BLUE = 1 GREEN = 2 CYAN = 3 RED = 4 MAGENTA = 5 YELLOW = 6 GREY = 7 # from wincon.h class WinStyle(object): NORMAL = 0x00 # dim text, dim background BRIGHT = 0x08 # bright text, dim background BRIGHT_BACKGROUND = 0x80 # dim text, bright background class WinTerm(object): def __init__(self): self._default = win32.GetConsoleScreenBufferInfo(win32.STDOUT).wAttributes self.set_attrs(self._default) self._default_fore = self._fore self._default_back = self._back self._default_style = self._style # In order to emulate LIGHT_EX in windows, we borrow the BRIGHT style. # So that LIGHT_EX colors and BRIGHT style do not clobber each other, # we track them separately, since LIGHT_EX is overwritten by Fore/Back # and BRIGHT is overwritten by Style codes. self._light = 0 def get_attrs(self): return self._fore + self._back * 16 + (self._style | self._light) def set_attrs(self, value): self._fore = value & 7 self._back = (value >> 4) & 7 self._style = value & (WinStyle.BRIGHT | WinStyle.BRIGHT_BACKGROUND) def reset_all(self, on_stderr=None): self.set_attrs(self._default) self.set_console(attrs=self._default) def fore(self, fore=None, light=False, on_stderr=False): if fore is None: fore = self._default_fore self._fore = fore # Emulate LIGHT_EX with BRIGHT Style if light: self._light |= WinStyle.BRIGHT else: self._light &= ~WinStyle.BRIGHT self.set_console(on_stderr=on_stderr) def back(self, back=None, light=False, on_stderr=False): if back is None: back = self._default_back self._back = back # Emulate LIGHT_EX with BRIGHT_BACKGROUND Style if light: self._light |= WinStyle.BRIGHT_BACKGROUND else: self._light &= ~WinStyle.BRIGHT_BACKGROUND self.set_console(on_stderr=on_stderr) def style(self, style=None, on_stderr=False): if style is None: style = self._default_style self._style = style self.set_console(on_stderr=on_stderr) def set_console(self, attrs=None, on_stderr=False): if attrs is None: attrs = self.get_attrs() handle = win32.STDOUT if on_stderr: handle = win32.STDERR win32.SetConsoleTextAttribute(handle, attrs) def get_position(self, handle): position = win32.GetConsoleScreenBufferInfo(handle).dwCursorPosition # Because Windows coordinates are 0-based, # and win32.SetConsoleCursorPosition expects 1-based. position.X += 1 position.Y += 1 return position def set_cursor_position(self, position=None, on_stderr=False): if position is None: # I'm not currently tracking the position, so there is no default. # position = self.get_position() return handle = win32.STDOUT if on_stderr: handle = win32.STDERR win32.SetConsoleCursorPosition(handle, position) def cursor_adjust(self, x, y, on_stderr=False): handle = win32.STDOUT if on_stderr: handle = win32.STDERR position = self.get_position(handle) adjusted_position = (position.Y + y, position.X + x) win32.SetConsoleCursorPosition(handle, adjusted_position, adjust=False) def erase_screen(self, mode=0, on_stderr=False): # 0 should clear from the cursor to the end of the screen. # 1 should clear from the cursor to the beginning of the screen. # 2 should clear the entire screen, and move cursor to (1,1) handle = win32.STDOUT if on_stderr: handle = win32.STDERR csbi = win32.GetConsoleScreenBufferInfo(handle) # get the number of character cells in the current buffer cells_in_screen = csbi.dwSize.X * csbi.dwSize.Y # get number of character cells before current cursor position cells_before_cursor = csbi.dwSize.X * csbi.dwCursorPosition.Y + csbi.dwCursorPosition.X if mode == 0: from_coord = csbi.dwCursorPosition cells_to_erase = cells_in_screen - cells_before_cursor if mode == 1: from_coord = win32.COORD(0, 0) cells_to_erase = cells_before_cursor elif mode == 2: from_coord = win32.COORD(0, 0) cells_to_erase = cells_in_screen # fill the entire screen with blanks win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord) # now set the buffer's attributes accordingly win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord) if mode == 2: # put the cursor where needed win32.SetConsoleCursorPosition(handle, (1, 1)) def erase_line(self, mode=0, on_stderr=False): # 0 should clear from the cursor to the end of the line. # 1 should clear from the cursor to the beginning of the line. # 2 should clear the entire line. handle = win32.STDOUT if on_stderr: handle = win32.STDERR csbi = win32.GetConsoleScreenBufferInfo(handle) if mode == 0: from_coord = csbi.dwCursorPosition cells_to_erase = csbi.dwSize.X - csbi.dwCursorPosition.X if mode == 1: from_coord = win32.COORD(0, csbi.dwCursorPosition.Y) cells_to_erase = csbi.dwCursorPosition.X elif mode == 2: from_coord = win32.COORD(0, csbi.dwCursorPosition.Y) cells_to_erase = csbi.dwSize.X # fill the entire screen with blanks win32.FillConsoleOutputCharacter(handle, ' ', cells_to_erase, from_coord) # now set the buffer's attributes accordingly win32.FillConsoleOutputAttribute(handle, self.get_attrs(), cells_to_erase, from_coord) def set_title(self, title): win32.SetConsoleTitle(title) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/0000755000076500000240000000000012765362057026346 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/__init__.py0000644000076500000240000000110512700725533030443 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012-2016 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # import logging __version__ = '0.2.2' class DistlibException(Exception): pass try: from logging import NullHandler except ImportError: # pragma: no cover class NullHandler(logging.Handler): def handle(self, record): pass def emit(self, record): pass def createLock(self): self.lock = None logger = logging.getLogger(__name__) logger.addHandler(NullHandler()) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/0000755000076500000240000000000012765362057030312 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/__init__.py0000644000076500000240000000042212700725533032410 0ustar jmstaff00000000000000"""Modules copied from Python 3 standard libraries, for internal use only. Individual classes and functions are found in d2._backport.misc. Intended usage is to always import things missing from 3.1 from that module: the built-in/stdlib objects will be used if found. """ feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/misc.py0000644000076500000240000000171312700725533031610 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """Backports for individual classes and functions.""" import os import sys __all__ = ['cache_from_source', 'callable', 'fsencode'] try: from imp import cache_from_source except ImportError: def cache_from_source(py_file, debug=__debug__): ext = debug and 'c' or 'o' return py_file + ext try: callable = callable except NameError: from collections import Callable def callable(obj): return isinstance(obj, Callable) try: fsencode = os.fsencode except AttributeError: def fsencode(filename): if isinstance(filename, bytes): return filename elif isinstance(filename, str): return filename.encode(sys.getfilesystemencoding()) else: raise TypeError("expect bytes or str, not %s" % type(filename).__name__) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/shutil.py0000644000076500000240000006206212700725533032171 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """Utility functions for copying and archiving files and directory trees. XXX The functions here don't copy the resource fork or other metadata on Mac. """ import os import sys import stat from os.path import abspath import fnmatch import collections import errno from . import tarfile try: import bz2 _BZ2_SUPPORTED = True except ImportError: _BZ2_SUPPORTED = False try: from pwd import getpwnam except ImportError: getpwnam = None try: from grp import getgrnam except ImportError: getgrnam = None __all__ = ["copyfileobj", "copyfile", "copymode", "copystat", "copy", "copy2", "copytree", "move", "rmtree", "Error", "SpecialFileError", "ExecError", "make_archive", "get_archive_formats", "register_archive_format", "unregister_archive_format", "get_unpack_formats", "register_unpack_format", "unregister_unpack_format", "unpack_archive", "ignore_patterns"] class Error(EnvironmentError): pass class SpecialFileError(EnvironmentError): """Raised when trying to do a kind of operation (e.g. copying) which is not supported on a special file (e.g. a named pipe)""" class ExecError(EnvironmentError): """Raised when a command could not be executed""" class ReadError(EnvironmentError): """Raised when an archive cannot be read""" class RegistryError(Exception): """Raised when a registery operation with the archiving and unpacking registeries fails""" try: WindowsError except NameError: WindowsError = None def copyfileobj(fsrc, fdst, length=16*1024): """copy data from file-like object fsrc to file-like object fdst""" while 1: buf = fsrc.read(length) if not buf: break fdst.write(buf) def _samefile(src, dst): # Macintosh, Unix. if hasattr(os.path, 'samefile'): try: return os.path.samefile(src, dst) except OSError: return False # All other platforms: check for same pathname. return (os.path.normcase(os.path.abspath(src)) == os.path.normcase(os.path.abspath(dst))) def copyfile(src, dst): """Copy data from src to dst""" if _samefile(src, dst): raise Error("`%s` and `%s` are the same file" % (src, dst)) for fn in [src, dst]: try: st = os.stat(fn) except OSError: # File most likely does not exist pass else: # XXX What about other special files? (sockets, devices...) if stat.S_ISFIFO(st.st_mode): raise SpecialFileError("`%s` is a named pipe" % fn) with open(src, 'rb') as fsrc: with open(dst, 'wb') as fdst: copyfileobj(fsrc, fdst) def copymode(src, dst): """Copy mode bits from src to dst""" if hasattr(os, 'chmod'): st = os.stat(src) mode = stat.S_IMODE(st.st_mode) os.chmod(dst, mode) def copystat(src, dst): """Copy all stat info (mode bits, atime, mtime, flags) from src to dst""" st = os.stat(src) mode = stat.S_IMODE(st.st_mode) if hasattr(os, 'utime'): os.utime(dst, (st.st_atime, st.st_mtime)) if hasattr(os, 'chmod'): os.chmod(dst, mode) if hasattr(os, 'chflags') and hasattr(st, 'st_flags'): try: os.chflags(dst, st.st_flags) except OSError as why: if (not hasattr(errno, 'EOPNOTSUPP') or why.errno != errno.EOPNOTSUPP): raise def copy(src, dst): """Copy data and mode bits ("cp src dst"). The destination may be a directory. """ if os.path.isdir(dst): dst = os.path.join(dst, os.path.basename(src)) copyfile(src, dst) copymode(src, dst) def copy2(src, dst): """Copy data and all stat info ("cp -p src dst"). The destination may be a directory. """ if os.path.isdir(dst): dst = os.path.join(dst, os.path.basename(src)) copyfile(src, dst) copystat(src, dst) def ignore_patterns(*patterns): """Function that can be used as copytree() ignore parameter. Patterns is a sequence of glob-style patterns that are used to exclude files""" def _ignore_patterns(path, names): ignored_names = [] for pattern in patterns: ignored_names.extend(fnmatch.filter(names, pattern)) return set(ignored_names) return _ignore_patterns def copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2, ignore_dangling_symlinks=False): """Recursively copy a directory tree. The destination directory must not already exist. If exception(s) occur, an Error is raised with a list of reasons. If the optional symlinks flag is true, symbolic links in the source tree result in symbolic links in the destination tree; if it is false, the contents of the files pointed to by symbolic links are copied. If the file pointed by the symlink doesn't exist, an exception will be added in the list of errors raised in an Error exception at the end of the copy process. You can set the optional ignore_dangling_symlinks flag to true if you want to silence this exception. Notice that this has no effect on platforms that don't support os.symlink. The optional ignore argument is a callable. If given, it is called with the `src` parameter, which is the directory being visited by copytree(), and `names` which is the list of `src` contents, as returned by os.listdir(): callable(src, names) -> ignored_names Since copytree() is called recursively, the callable will be called once for each directory that is copied. It returns a list of names relative to the `src` directory that should not be copied. The optional copy_function argument is a callable that will be used to copy each file. It will be called with the source path and the destination path as arguments. By default, copy2() is used, but any function that supports the same signature (like copy()) can be used. """ names = os.listdir(src) if ignore is not None: ignored_names = ignore(src, names) else: ignored_names = set() os.makedirs(dst) errors = [] for name in names: if name in ignored_names: continue srcname = os.path.join(src, name) dstname = os.path.join(dst, name) try: if os.path.islink(srcname): linkto = os.readlink(srcname) if symlinks: os.symlink(linkto, dstname) else: # ignore dangling symlink if the flag is on if not os.path.exists(linkto) and ignore_dangling_symlinks: continue # otherwise let the copy occurs. copy2 will raise an error copy_function(srcname, dstname) elif os.path.isdir(srcname): copytree(srcname, dstname, symlinks, ignore, copy_function) else: # Will raise a SpecialFileError for unsupported file types copy_function(srcname, dstname) # catch the Error from the recursive copytree so that we can # continue with other files except Error as err: errors.extend(err.args[0]) except EnvironmentError as why: errors.append((srcname, dstname, str(why))) try: copystat(src, dst) except OSError as why: if WindowsError is not None and isinstance(why, WindowsError): # Copying file access times may fail on Windows pass else: errors.extend((src, dst, str(why))) if errors: raise Error(errors) def rmtree(path, ignore_errors=False, onerror=None): """Recursively delete a directory tree. If ignore_errors is set, errors are ignored; otherwise, if onerror is set, it is called to handle the error with arguments (func, path, exc_info) where func is os.listdir, os.remove, or os.rmdir; path is the argument to that function that caused it to fail; and exc_info is a tuple returned by sys.exc_info(). If ignore_errors is false and onerror is None, an exception is raised. """ if ignore_errors: def onerror(*args): pass elif onerror is None: def onerror(*args): raise try: if os.path.islink(path): # symlinks to directories are forbidden, see bug #1669 raise OSError("Cannot call rmtree on a symbolic link") except OSError: onerror(os.path.islink, path, sys.exc_info()) # can't continue even if onerror hook returns return names = [] try: names = os.listdir(path) except os.error: onerror(os.listdir, path, sys.exc_info()) for name in names: fullname = os.path.join(path, name) try: mode = os.lstat(fullname).st_mode except os.error: mode = 0 if stat.S_ISDIR(mode): rmtree(fullname, ignore_errors, onerror) else: try: os.remove(fullname) except os.error: onerror(os.remove, fullname, sys.exc_info()) try: os.rmdir(path) except os.error: onerror(os.rmdir, path, sys.exc_info()) def _basename(path): # A basename() variant which first strips the trailing slash, if present. # Thus we always get the last component of the path, even for directories. return os.path.basename(path.rstrip(os.path.sep)) def move(src, dst): """Recursively move a file or directory to another location. This is similar to the Unix "mv" command. If the destination is a directory or a symlink to a directory, the source is moved inside the directory. The destination path must not already exist. If the destination already exists but is not a directory, it may be overwritten depending on os.rename() semantics. If the destination is on our current filesystem, then rename() is used. Otherwise, src is copied to the destination and then removed. A lot more could be done here... A look at a mv.c shows a lot of the issues this implementation glosses over. """ real_dst = dst if os.path.isdir(dst): if _samefile(src, dst): # We might be on a case insensitive filesystem, # perform the rename anyway. os.rename(src, dst) return real_dst = os.path.join(dst, _basename(src)) if os.path.exists(real_dst): raise Error("Destination path '%s' already exists" % real_dst) try: os.rename(src, real_dst) except OSError: if os.path.isdir(src): if _destinsrc(src, dst): raise Error("Cannot move a directory '%s' into itself '%s'." % (src, dst)) copytree(src, real_dst, symlinks=True) rmtree(src) else: copy2(src, real_dst) os.unlink(src) def _destinsrc(src, dst): src = abspath(src) dst = abspath(dst) if not src.endswith(os.path.sep): src += os.path.sep if not dst.endswith(os.path.sep): dst += os.path.sep return dst.startswith(src) def _get_gid(name): """Returns a gid, given a group name.""" if getgrnam is None or name is None: return None try: result = getgrnam(name) except KeyError: result = None if result is not None: return result[2] return None def _get_uid(name): """Returns an uid, given a user name.""" if getpwnam is None or name is None: return None try: result = getpwnam(name) except KeyError: result = None if result is not None: return result[2] return None def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0, owner=None, group=None, logger=None): """Create a (possibly compressed) tar file from all the files under 'base_dir'. 'compress' must be "gzip" (the default), "bzip2", or None. 'owner' and 'group' can be used to define an owner and a group for the archive that is being built. If not provided, the current owner and group will be used. The output tar file will be named 'base_name' + ".tar", possibly plus the appropriate compression extension (".gz", or ".bz2"). Returns the output filename. """ tar_compression = {'gzip': 'gz', None: ''} compress_ext = {'gzip': '.gz'} if _BZ2_SUPPORTED: tar_compression['bzip2'] = 'bz2' compress_ext['bzip2'] = '.bz2' # flags for compression program, each element of list will be an argument if compress is not None and compress not in compress_ext: raise ValueError("bad value for 'compress', or compression format not " "supported : {0}".format(compress)) archive_name = base_name + '.tar' + compress_ext.get(compress, '') archive_dir = os.path.dirname(archive_name) if not os.path.exists(archive_dir): if logger is not None: logger.info("creating %s", archive_dir) if not dry_run: os.makedirs(archive_dir) # creating the tarball if logger is not None: logger.info('Creating tar archive') uid = _get_uid(owner) gid = _get_gid(group) def _set_uid_gid(tarinfo): if gid is not None: tarinfo.gid = gid tarinfo.gname = group if uid is not None: tarinfo.uid = uid tarinfo.uname = owner return tarinfo if not dry_run: tar = tarfile.open(archive_name, 'w|%s' % tar_compression[compress]) try: tar.add(base_dir, filter=_set_uid_gid) finally: tar.close() return archive_name def _call_external_zip(base_dir, zip_filename, verbose=False, dry_run=False): # XXX see if we want to keep an external call here if verbose: zipoptions = "-r" else: zipoptions = "-rq" from distutils.errors import DistutilsExecError from distutils.spawn import spawn try: spawn(["zip", zipoptions, zip_filename, base_dir], dry_run=dry_run) except DistutilsExecError: # XXX really should distinguish between "couldn't find # external 'zip' command" and "zip failed". raise ExecError("unable to create zip file '%s': " "could neither import the 'zipfile' module nor " "find a standalone zip utility") % zip_filename def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None): """Create a zip file from all the files under 'base_dir'. The output zip file will be named 'base_name' + ".zip". Uses either the "zipfile" Python module (if available) or the InfoZIP "zip" utility (if installed and found on the default search path). If neither tool is available, raises ExecError. Returns the name of the output zip file. """ zip_filename = base_name + ".zip" archive_dir = os.path.dirname(base_name) if not os.path.exists(archive_dir): if logger is not None: logger.info("creating %s", archive_dir) if not dry_run: os.makedirs(archive_dir) # If zipfile module is not available, try spawning an external 'zip' # command. try: import zipfile except ImportError: zipfile = None if zipfile is None: _call_external_zip(base_dir, zip_filename, verbose, dry_run) else: if logger is not None: logger.info("creating '%s' and adding '%s' to it", zip_filename, base_dir) if not dry_run: zip = zipfile.ZipFile(zip_filename, "w", compression=zipfile.ZIP_DEFLATED) for dirpath, dirnames, filenames in os.walk(base_dir): for name in filenames: path = os.path.normpath(os.path.join(dirpath, name)) if os.path.isfile(path): zip.write(path, path) if logger is not None: logger.info("adding '%s'", path) zip.close() return zip_filename _ARCHIVE_FORMATS = { 'gztar': (_make_tarball, [('compress', 'gzip')], "gzip'ed tar-file"), 'bztar': (_make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file"), 'tar': (_make_tarball, [('compress', None)], "uncompressed tar file"), 'zip': (_make_zipfile, [], "ZIP file"), } if _BZ2_SUPPORTED: _ARCHIVE_FORMATS['bztar'] = (_make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file") def get_archive_formats(): """Returns a list of supported formats for archiving and unarchiving. Each element of the returned sequence is a tuple (name, description) """ formats = [(name, registry[2]) for name, registry in _ARCHIVE_FORMATS.items()] formats.sort() return formats def register_archive_format(name, function, extra_args=None, description=''): """Registers an archive format. name is the name of the format. function is the callable that will be used to create archives. If provided, extra_args is a sequence of (name, value) tuples that will be passed as arguments to the callable. description can be provided to describe the format, and will be returned by the get_archive_formats() function. """ if extra_args is None: extra_args = [] if not isinstance(function, collections.Callable): raise TypeError('The %s object is not callable' % function) if not isinstance(extra_args, (tuple, list)): raise TypeError('extra_args needs to be a sequence') for element in extra_args: if not isinstance(element, (tuple, list)) or len(element) !=2: raise TypeError('extra_args elements are : (arg_name, value)') _ARCHIVE_FORMATS[name] = (function, extra_args, description) def unregister_archive_format(name): del _ARCHIVE_FORMATS[name] def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0, dry_run=0, owner=None, group=None, logger=None): """Create an archive file (eg. zip or tar). 'base_name' is the name of the file to create, minus any format-specific extension; 'format' is the archive format: one of "zip", "tar", "bztar" or "gztar". 'root_dir' is a directory that will be the root directory of the archive; ie. we typically chdir into 'root_dir' before creating the archive. 'base_dir' is the directory where we start archiving from; ie. 'base_dir' will be the common prefix of all files and directories in the archive. 'root_dir' and 'base_dir' both default to the current directory. Returns the name of the archive file. 'owner' and 'group' are used when creating a tar archive. By default, uses the current owner and group. """ save_cwd = os.getcwd() if root_dir is not None: if logger is not None: logger.debug("changing into '%s'", root_dir) base_name = os.path.abspath(base_name) if not dry_run: os.chdir(root_dir) if base_dir is None: base_dir = os.curdir kwargs = {'dry_run': dry_run, 'logger': logger} try: format_info = _ARCHIVE_FORMATS[format] except KeyError: raise ValueError("unknown archive format '%s'" % format) func = format_info[0] for arg, val in format_info[1]: kwargs[arg] = val if format != 'zip': kwargs['owner'] = owner kwargs['group'] = group try: filename = func(base_name, base_dir, **kwargs) finally: if root_dir is not None: if logger is not None: logger.debug("changing back to '%s'", save_cwd) os.chdir(save_cwd) return filename def get_unpack_formats(): """Returns a list of supported formats for unpacking. Each element of the returned sequence is a tuple (name, extensions, description) """ formats = [(name, info[0], info[3]) for name, info in _UNPACK_FORMATS.items()] formats.sort() return formats def _check_unpack_options(extensions, function, extra_args): """Checks what gets registered as an unpacker.""" # first make sure no other unpacker is registered for this extension existing_extensions = {} for name, info in _UNPACK_FORMATS.items(): for ext in info[0]: existing_extensions[ext] = name for extension in extensions: if extension in existing_extensions: msg = '%s is already registered for "%s"' raise RegistryError(msg % (extension, existing_extensions[extension])) if not isinstance(function, collections.Callable): raise TypeError('The registered function must be a callable') def register_unpack_format(name, extensions, function, extra_args=None, description=''): """Registers an unpack format. `name` is the name of the format. `extensions` is a list of extensions corresponding to the format. `function` is the callable that will be used to unpack archives. The callable will receive archives to unpack. If it's unable to handle an archive, it needs to raise a ReadError exception. If provided, `extra_args` is a sequence of (name, value) tuples that will be passed as arguments to the callable. description can be provided to describe the format, and will be returned by the get_unpack_formats() function. """ if extra_args is None: extra_args = [] _check_unpack_options(extensions, function, extra_args) _UNPACK_FORMATS[name] = extensions, function, extra_args, description def unregister_unpack_format(name): """Removes the pack format from the registery.""" del _UNPACK_FORMATS[name] def _ensure_directory(path): """Ensure that the parent directory of `path` exists""" dirname = os.path.dirname(path) if not os.path.isdir(dirname): os.makedirs(dirname) def _unpack_zipfile(filename, extract_dir): """Unpack zip `filename` to `extract_dir` """ try: import zipfile except ImportError: raise ReadError('zlib not supported, cannot unpack this archive.') if not zipfile.is_zipfile(filename): raise ReadError("%s is not a zip file" % filename) zip = zipfile.ZipFile(filename) try: for info in zip.infolist(): name = info.filename # don't extract absolute paths or ones with .. in them if name.startswith('/') or '..' in name: continue target = os.path.join(extract_dir, *name.split('/')) if not target: continue _ensure_directory(target) if not name.endswith('/'): # file data = zip.read(info.filename) f = open(target, 'wb') try: f.write(data) finally: f.close() del data finally: zip.close() def _unpack_tarfile(filename, extract_dir): """Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir` """ try: tarobj = tarfile.open(filename) except tarfile.TarError: raise ReadError( "%s is not a compressed or uncompressed tar file" % filename) try: tarobj.extractall(extract_dir) finally: tarobj.close() _UNPACK_FORMATS = { 'gztar': (['.tar.gz', '.tgz'], _unpack_tarfile, [], "gzip'ed tar-file"), 'tar': (['.tar'], _unpack_tarfile, [], "uncompressed tar file"), 'zip': (['.zip'], _unpack_zipfile, [], "ZIP file") } if _BZ2_SUPPORTED: _UNPACK_FORMATS['bztar'] = (['.bz2'], _unpack_tarfile, [], "bzip2'ed tar-file") def _find_unpack_format(filename): for name, info in _UNPACK_FORMATS.items(): for extension in info[0]: if filename.endswith(extension): return name return None def unpack_archive(filename, extract_dir=None, format=None): """Unpack an archive. `filename` is the name of the archive. `extract_dir` is the name of the target directory, where the archive is unpacked. If not provided, the current working directory is used. `format` is the archive format: one of "zip", "tar", or "gztar". Or any other registered format. If not provided, unpack_archive will use the filename extension and see if an unpacker was registered for that extension. In case none is found, a ValueError is raised. """ if extract_dir is None: extract_dir = os.getcwd() if format is not None: try: format_info = _UNPACK_FORMATS[format] except KeyError: raise ValueError("Unknown unpack format '{0}'".format(format)) func = format_info[1] func(filename, extract_dir, **dict(format_info[2])) else: # we need to look at the registered unpackers supported extensions format = _find_unpack_format(filename) if format is None: raise ReadError("Unknown archive format '{0}'".format(filename)) func = _UNPACK_FORMATS[format][1] kwargs = dict(_UNPACK_FORMATS[format][2]) func(filename, extract_dir, **kwargs) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/sysconfig.py0000644000076500000240000006451612700725533032673 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """Access to Python's configuration information.""" import codecs import os import re import sys from os.path import pardir, realpath try: import configparser except ImportError: import ConfigParser as configparser __all__ = [ 'get_config_h_filename', 'get_config_var', 'get_config_vars', 'get_makefile_filename', 'get_path', 'get_path_names', 'get_paths', 'get_platform', 'get_python_version', 'get_scheme_names', 'parse_config_h', ] def _safe_realpath(path): try: return realpath(path) except OSError: return path if sys.executable: _PROJECT_BASE = os.path.dirname(_safe_realpath(sys.executable)) else: # sys.executable can be empty if argv[0] has been changed and Python is # unable to retrieve the real program name _PROJECT_BASE = _safe_realpath(os.getcwd()) if os.name == "nt" and "pcbuild" in _PROJECT_BASE[-8:].lower(): _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir)) # PC/VS7.1 if os.name == "nt" and "\\pc\\v" in _PROJECT_BASE[-10:].lower(): _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir)) # PC/AMD64 if os.name == "nt" and "\\pcbuild\\amd64" in _PROJECT_BASE[-14:].lower(): _PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir)) def is_python_build(): for fn in ("Setup.dist", "Setup.local"): if os.path.isfile(os.path.join(_PROJECT_BASE, "Modules", fn)): return True return False _PYTHON_BUILD = is_python_build() _cfg_read = False def _ensure_cfg_read(): global _cfg_read if not _cfg_read: from ..resources import finder backport_package = __name__.rsplit('.', 1)[0] _finder = finder(backport_package) _cfgfile = _finder.find('sysconfig.cfg') assert _cfgfile, 'sysconfig.cfg exists' with _cfgfile.as_stream() as s: _SCHEMES.readfp(s) if _PYTHON_BUILD: for scheme in ('posix_prefix', 'posix_home'): _SCHEMES.set(scheme, 'include', '{srcdir}/Include') _SCHEMES.set(scheme, 'platinclude', '{projectbase}/.') _cfg_read = True _SCHEMES = configparser.RawConfigParser() _VAR_REPL = re.compile(r'\{([^{]*?)\}') def _expand_globals(config): _ensure_cfg_read() if config.has_section('globals'): globals = config.items('globals') else: globals = tuple() sections = config.sections() for section in sections: if section == 'globals': continue for option, value in globals: if config.has_option(section, option): continue config.set(section, option, value) config.remove_section('globals') # now expanding local variables defined in the cfg file # for section in config.sections(): variables = dict(config.items(section)) def _replacer(matchobj): name = matchobj.group(1) if name in variables: return variables[name] return matchobj.group(0) for option, value in config.items(section): config.set(section, option, _VAR_REPL.sub(_replacer, value)) #_expand_globals(_SCHEMES) # FIXME don't rely on sys.version here, its format is an implementation detail # of CPython, use sys.version_info or sys.hexversion _PY_VERSION = sys.version.split()[0] _PY_VERSION_SHORT = sys.version[:3] _PY_VERSION_SHORT_NO_DOT = _PY_VERSION[0] + _PY_VERSION[2] _PREFIX = os.path.normpath(sys.prefix) _EXEC_PREFIX = os.path.normpath(sys.exec_prefix) _CONFIG_VARS = None _USER_BASE = None def _subst_vars(path, local_vars): """In the string `path`, replace tokens like {some.thing} with the corresponding value from the map `local_vars`. If there is no corresponding value, leave the token unchanged. """ def _replacer(matchobj): name = matchobj.group(1) if name in local_vars: return local_vars[name] elif name in os.environ: return os.environ[name] return matchobj.group(0) return _VAR_REPL.sub(_replacer, path) def _extend_dict(target_dict, other_dict): target_keys = target_dict.keys() for key, value in other_dict.items(): if key in target_keys: continue target_dict[key] = value def _expand_vars(scheme, vars): res = {} if vars is None: vars = {} _extend_dict(vars, get_config_vars()) for key, value in _SCHEMES.items(scheme): if os.name in ('posix', 'nt'): value = os.path.expanduser(value) res[key] = os.path.normpath(_subst_vars(value, vars)) return res def format_value(value, vars): def _replacer(matchobj): name = matchobj.group(1) if name in vars: return vars[name] return matchobj.group(0) return _VAR_REPL.sub(_replacer, value) def _get_default_scheme(): if os.name == 'posix': # the default scheme for posix is posix_prefix return 'posix_prefix' return os.name def _getuserbase(): env_base = os.environ.get("PYTHONUSERBASE", None) def joinuser(*args): return os.path.expanduser(os.path.join(*args)) # what about 'os2emx', 'riscos' ? if os.name == "nt": base = os.environ.get("APPDATA") or "~" if env_base: return env_base else: return joinuser(base, "Python") if sys.platform == "darwin": framework = get_config_var("PYTHONFRAMEWORK") if framework: if env_base: return env_base else: return joinuser("~", "Library", framework, "%d.%d" % sys.version_info[:2]) if env_base: return env_base else: return joinuser("~", ".local") def _parse_makefile(filename, vars=None): """Parse a Makefile-style file. A dictionary containing name/value pairs is returned. If an optional dictionary is passed in as the second argument, it is used instead of a new dictionary. """ # Regexes needed for parsing Makefile (and similar syntaxes, # like old-style Setup files). _variable_rx = re.compile("([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*(.*)") _findvar1_rx = re.compile(r"\$\(([A-Za-z][A-Za-z0-9_]*)\)") _findvar2_rx = re.compile(r"\${([A-Za-z][A-Za-z0-9_]*)}") if vars is None: vars = {} done = {} notdone = {} with codecs.open(filename, encoding='utf-8', errors="surrogateescape") as f: lines = f.readlines() for line in lines: if line.startswith('#') or line.strip() == '': continue m = _variable_rx.match(line) if m: n, v = m.group(1, 2) v = v.strip() # `$$' is a literal `$' in make tmpv = v.replace('$$', '') if "$" in tmpv: notdone[n] = v else: try: v = int(v) except ValueError: # insert literal `$' done[n] = v.replace('$$', '$') else: done[n] = v # do variable interpolation here variables = list(notdone.keys()) # Variables with a 'PY_' prefix in the makefile. These need to # be made available without that prefix through sysconfig. # Special care is needed to ensure that variable expansion works, even # if the expansion uses the name without a prefix. renamed_variables = ('CFLAGS', 'LDFLAGS', 'CPPFLAGS') while len(variables) > 0: for name in tuple(variables): value = notdone[name] m = _findvar1_rx.search(value) or _findvar2_rx.search(value) if m is not None: n = m.group(1) found = True if n in done: item = str(done[n]) elif n in notdone: # get it on a subsequent round found = False elif n in os.environ: # do it like make: fall back to environment item = os.environ[n] elif n in renamed_variables: if (name.startswith('PY_') and name[3:] in renamed_variables): item = "" elif 'PY_' + n in notdone: found = False else: item = str(done['PY_' + n]) else: done[n] = item = "" if found: after = value[m.end():] value = value[:m.start()] + item + after if "$" in after: notdone[name] = value else: try: value = int(value) except ValueError: done[name] = value.strip() else: done[name] = value variables.remove(name) if (name.startswith('PY_') and name[3:] in renamed_variables): name = name[3:] if name not in done: done[name] = value else: # bogus variable reference (e.g. "prefix=$/opt/python"); # just drop it since we can't deal done[name] = value variables.remove(name) # strip spurious spaces for k, v in done.items(): if isinstance(v, str): done[k] = v.strip() # save the results in the global dictionary vars.update(done) return vars def get_makefile_filename(): """Return the path of the Makefile.""" if _PYTHON_BUILD: return os.path.join(_PROJECT_BASE, "Makefile") if hasattr(sys, 'abiflags'): config_dir_name = 'config-%s%s' % (_PY_VERSION_SHORT, sys.abiflags) else: config_dir_name = 'config' return os.path.join(get_path('stdlib'), config_dir_name, 'Makefile') def _init_posix(vars): """Initialize the module as appropriate for POSIX systems.""" # load the installed Makefile: makefile = get_makefile_filename() try: _parse_makefile(makefile, vars) except IOError as e: msg = "invalid Python installation: unable to open %s" % makefile if hasattr(e, "strerror"): msg = msg + " (%s)" % e.strerror raise IOError(msg) # load the installed pyconfig.h: config_h = get_config_h_filename() try: with open(config_h) as f: parse_config_h(f, vars) except IOError as e: msg = "invalid Python installation: unable to open %s" % config_h if hasattr(e, "strerror"): msg = msg + " (%s)" % e.strerror raise IOError(msg) # On AIX, there are wrong paths to the linker scripts in the Makefile # -- these paths are relative to the Python source, but when installed # the scripts are in another directory. if _PYTHON_BUILD: vars['LDSHARED'] = vars['BLDSHARED'] def _init_non_posix(vars): """Initialize the module as appropriate for NT""" # set basic install directories vars['LIBDEST'] = get_path('stdlib') vars['BINLIBDEST'] = get_path('platstdlib') vars['INCLUDEPY'] = get_path('include') vars['SO'] = '.pyd' vars['EXE'] = '.exe' vars['VERSION'] = _PY_VERSION_SHORT_NO_DOT vars['BINDIR'] = os.path.dirname(_safe_realpath(sys.executable)) # # public APIs # def parse_config_h(fp, vars=None): """Parse a config.h-style file. A dictionary containing name/value pairs is returned. If an optional dictionary is passed in as the second argument, it is used instead of a new dictionary. """ if vars is None: vars = {} define_rx = re.compile("#define ([A-Z][A-Za-z0-9_]+) (.*)\n") undef_rx = re.compile("/[*] #undef ([A-Z][A-Za-z0-9_]+) [*]/\n") while True: line = fp.readline() if not line: break m = define_rx.match(line) if m: n, v = m.group(1, 2) try: v = int(v) except ValueError: pass vars[n] = v else: m = undef_rx.match(line) if m: vars[m.group(1)] = 0 return vars def get_config_h_filename(): """Return the path of pyconfig.h.""" if _PYTHON_BUILD: if os.name == "nt": inc_dir = os.path.join(_PROJECT_BASE, "PC") else: inc_dir = _PROJECT_BASE else: inc_dir = get_path('platinclude') return os.path.join(inc_dir, 'pyconfig.h') def get_scheme_names(): """Return a tuple containing the schemes names.""" return tuple(sorted(_SCHEMES.sections())) def get_path_names(): """Return a tuple containing the paths names.""" # xxx see if we want a static list return _SCHEMES.options('posix_prefix') def get_paths(scheme=_get_default_scheme(), vars=None, expand=True): """Return a mapping containing an install scheme. ``scheme`` is the install scheme name. If not provided, it will return the default scheme for the current platform. """ _ensure_cfg_read() if expand: return _expand_vars(scheme, vars) else: return dict(_SCHEMES.items(scheme)) def get_path(name, scheme=_get_default_scheme(), vars=None, expand=True): """Return a path corresponding to the scheme. ``scheme`` is the install scheme name. """ return get_paths(scheme, vars, expand)[name] def get_config_vars(*args): """With no arguments, return a dictionary of all configuration variables relevant for the current platform. On Unix, this means every variable defined in Python's installed Makefile; On Windows and Mac OS it's a much smaller set. With arguments, return a list of values that result from looking up each argument in the configuration variable dictionary. """ global _CONFIG_VARS if _CONFIG_VARS is None: _CONFIG_VARS = {} # Normalized versions of prefix and exec_prefix are handy to have; # in fact, these are the standard versions used most places in the # distutils2 module. _CONFIG_VARS['prefix'] = _PREFIX _CONFIG_VARS['exec_prefix'] = _EXEC_PREFIX _CONFIG_VARS['py_version'] = _PY_VERSION _CONFIG_VARS['py_version_short'] = _PY_VERSION_SHORT _CONFIG_VARS['py_version_nodot'] = _PY_VERSION[0] + _PY_VERSION[2] _CONFIG_VARS['base'] = _PREFIX _CONFIG_VARS['platbase'] = _EXEC_PREFIX _CONFIG_VARS['projectbase'] = _PROJECT_BASE try: _CONFIG_VARS['abiflags'] = sys.abiflags except AttributeError: # sys.abiflags may not be defined on all platforms. _CONFIG_VARS['abiflags'] = '' if os.name in ('nt', 'os2'): _init_non_posix(_CONFIG_VARS) if os.name == 'posix': _init_posix(_CONFIG_VARS) # Setting 'userbase' is done below the call to the # init function to enable using 'get_config_var' in # the init-function. if sys.version >= '2.6': _CONFIG_VARS['userbase'] = _getuserbase() if 'srcdir' not in _CONFIG_VARS: _CONFIG_VARS['srcdir'] = _PROJECT_BASE else: _CONFIG_VARS['srcdir'] = _safe_realpath(_CONFIG_VARS['srcdir']) # Convert srcdir into an absolute path if it appears necessary. # Normally it is relative to the build directory. However, during # testing, for example, we might be running a non-installed python # from a different directory. if _PYTHON_BUILD and os.name == "posix": base = _PROJECT_BASE try: cwd = os.getcwd() except OSError: cwd = None if (not os.path.isabs(_CONFIG_VARS['srcdir']) and base != cwd): # srcdir is relative and we are not in the same directory # as the executable. Assume executable is in the build # directory and make srcdir absolute. srcdir = os.path.join(base, _CONFIG_VARS['srcdir']) _CONFIG_VARS['srcdir'] = os.path.normpath(srcdir) if sys.platform == 'darwin': kernel_version = os.uname()[2] # Kernel version (8.4.3) major_version = int(kernel_version.split('.')[0]) if major_version < 8: # On Mac OS X before 10.4, check if -arch and -isysroot # are in CFLAGS or LDFLAGS and remove them if they are. # This is needed when building extensions on a 10.3 system # using a universal build of python. for key in ('LDFLAGS', 'BASECFLAGS', # a number of derived variables. These need to be # patched up as well. 'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'): flags = _CONFIG_VARS[key] flags = re.sub('-arch\s+\w+\s', ' ', flags) flags = re.sub('-isysroot [^ \t]*', ' ', flags) _CONFIG_VARS[key] = flags else: # Allow the user to override the architecture flags using # an environment variable. # NOTE: This name was introduced by Apple in OSX 10.5 and # is used by several scripting languages distributed with # that OS release. if 'ARCHFLAGS' in os.environ: arch = os.environ['ARCHFLAGS'] for key in ('LDFLAGS', 'BASECFLAGS', # a number of derived variables. These need to be # patched up as well. 'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'): flags = _CONFIG_VARS[key] flags = re.sub('-arch\s+\w+\s', ' ', flags) flags = flags + ' ' + arch _CONFIG_VARS[key] = flags # If we're on OSX 10.5 or later and the user tries to # compiles an extension using an SDK that is not present # on the current machine it is better to not use an SDK # than to fail. # # The major usecase for this is users using a Python.org # binary installer on OSX 10.6: that installer uses # the 10.4u SDK, but that SDK is not installed by default # when you install Xcode. # CFLAGS = _CONFIG_VARS.get('CFLAGS', '') m = re.search('-isysroot\s+(\S+)', CFLAGS) if m is not None: sdk = m.group(1) if not os.path.exists(sdk): for key in ('LDFLAGS', 'BASECFLAGS', # a number of derived variables. These need to be # patched up as well. 'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'): flags = _CONFIG_VARS[key] flags = re.sub('-isysroot\s+\S+(\s|$)', ' ', flags) _CONFIG_VARS[key] = flags if args: vals = [] for name in args: vals.append(_CONFIG_VARS.get(name)) return vals else: return _CONFIG_VARS def get_config_var(name): """Return the value of a single variable using the dictionary returned by 'get_config_vars()'. Equivalent to get_config_vars().get(name) """ return get_config_vars().get(name) def get_platform(): """Return a string that identifies the current platform. This is used mainly to distinguish platform-specific build directories and platform-specific built distributions. Typically includes the OS name and version and the architecture (as supplied by 'os.uname()'), although the exact information included depends on the OS; eg. for IRIX the architecture isn't particularly important (IRIX only runs on SGI hardware), but for Linux the kernel version isn't particularly important. Examples of returned values: linux-i586 linux-alpha (?) solaris-2.6-sun4u irix-5.3 irix64-6.2 Windows will return one of: win-amd64 (64bit Windows on AMD64 (aka x86_64, Intel64, EM64T, etc) win-ia64 (64bit Windows on Itanium) win32 (all others - specifically, sys.platform is returned) For other non-POSIX platforms, currently just returns 'sys.platform'. """ if os.name == 'nt': # sniff sys.version for architecture. prefix = " bit (" i = sys.version.find(prefix) if i == -1: return sys.platform j = sys.version.find(")", i) look = sys.version[i+len(prefix):j].lower() if look == 'amd64': return 'win-amd64' if look == 'itanium': return 'win-ia64' return sys.platform if os.name != "posix" or not hasattr(os, 'uname'): # XXX what about the architecture? NT is Intel or Alpha, # Mac OS is M68k or PPC, etc. return sys.platform # Try to distinguish various flavours of Unix osname, host, release, version, machine = os.uname() # Convert the OS name to lowercase, remove '/' characters # (to accommodate BSD/OS), and translate spaces (for "Power Macintosh") osname = osname.lower().replace('/', '') machine = machine.replace(' ', '_') machine = machine.replace('/', '-') if osname[:5] == "linux": # At least on Linux/Intel, 'machine' is the processor -- # i386, etc. # XXX what about Alpha, SPARC, etc? return "%s-%s" % (osname, machine) elif osname[:5] == "sunos": if release[0] >= "5": # SunOS 5 == Solaris 2 osname = "solaris" release = "%d.%s" % (int(release[0]) - 3, release[2:]) # fall through to standard osname-release-machine representation elif osname[:4] == "irix": # could be "irix64"! return "%s-%s" % (osname, release) elif osname[:3] == "aix": return "%s-%s.%s" % (osname, version, release) elif osname[:6] == "cygwin": osname = "cygwin" rel_re = re.compile(r'[\d.]+') m = rel_re.match(release) if m: release = m.group() elif osname[:6] == "darwin": # # For our purposes, we'll assume that the system version from # distutils' perspective is what MACOSX_DEPLOYMENT_TARGET is set # to. This makes the compatibility story a bit more sane because the # machine is going to compile and link as if it were # MACOSX_DEPLOYMENT_TARGET. cfgvars = get_config_vars() macver = cfgvars.get('MACOSX_DEPLOYMENT_TARGET') if True: # Always calculate the release of the running machine, # needed to determine if we can build fat binaries or not. macrelease = macver # Get the system version. Reading this plist is a documented # way to get the system version (see the documentation for # the Gestalt Manager) try: f = open('/System/Library/CoreServices/SystemVersion.plist') except IOError: # We're on a plain darwin box, fall back to the default # behaviour. pass else: try: m = re.search(r'ProductUserVisibleVersion\s*' r'(.*?)', f.read()) finally: f.close() if m is not None: macrelease = '.'.join(m.group(1).split('.')[:2]) # else: fall back to the default behaviour if not macver: macver = macrelease if macver: release = macver osname = "macosx" if ((macrelease + '.') >= '10.4.' and '-arch' in get_config_vars().get('CFLAGS', '').strip()): # The universal build will build fat binaries, but not on # systems before 10.4 # # Try to detect 4-way universal builds, those have machine-type # 'universal' instead of 'fat'. machine = 'fat' cflags = get_config_vars().get('CFLAGS') archs = re.findall('-arch\s+(\S+)', cflags) archs = tuple(sorted(set(archs))) if len(archs) == 1: machine = archs[0] elif archs == ('i386', 'ppc'): machine = 'fat' elif archs == ('i386', 'x86_64'): machine = 'intel' elif archs == ('i386', 'ppc', 'x86_64'): machine = 'fat3' elif archs == ('ppc64', 'x86_64'): machine = 'fat64' elif archs == ('i386', 'ppc', 'ppc64', 'x86_64'): machine = 'universal' else: raise ValueError( "Don't know machine value for archs=%r" % (archs,)) elif machine == 'i386': # On OSX the machine type returned by uname is always the # 32-bit variant, even if the executable architecture is # the 64-bit variant if sys.maxsize >= 2**32: machine = 'x86_64' elif machine in ('PowerPC', 'Power_Macintosh'): # Pick a sane name for the PPC architecture. # See 'i386' case if sys.maxsize >= 2**32: machine = 'ppc64' else: machine = 'ppc' return "%s-%s-%s" % (osname, release, machine) def get_python_version(): return _PY_VERSION_SHORT def _print_dict(title, data): for index, (key, value) in enumerate(sorted(data.items())): if index == 0: print('%s: ' % (title)) print('\t%s = "%s"' % (key, value)) def _main(): """Display all information sysconfig detains.""" print('Platform: "%s"' % get_platform()) print('Python version: "%s"' % get_python_version()) print('Current installation scheme: "%s"' % _get_default_scheme()) print() _print_dict('Paths', get_paths()) print() _print_dict('Variables', get_config_vars()) if __name__ == '__main__': _main() feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/_backport/tarfile.py0000644000076500000240000026472312700725533032317 0ustar jmstaff00000000000000#------------------------------------------------------------------- # tarfile.py #------------------------------------------------------------------- # Copyright (C) 2002 Lars Gustaebel # All rights reserved. # # Permission is hereby granted, free of charge, to any person # obtaining a copy of this software and associated documentation # files (the "Software"), to deal in the Software without # restriction, including without limitation the rights to use, # copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the # Software is furnished to do so, subject to the following # conditions: # # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES # OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND # NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT # HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, # WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR # OTHER DEALINGS IN THE SOFTWARE. # from __future__ import print_function """Read from and write to tar format archives. """ __version__ = "$Revision$" version = "0.9.0" __author__ = "Lars Gust\u00e4bel (lars@gustaebel.de)" __date__ = "$Date: 2011-02-25 17:42:01 +0200 (Fri, 25 Feb 2011) $" __cvsid__ = "$Id: tarfile.py 88586 2011-02-25 15:42:01Z marc-andre.lemburg $" __credits__ = "Gustavo Niemeyer, Niels Gust\u00e4bel, Richard Townsend." #--------- # Imports #--------- import sys import os import stat import errno import time import struct import copy import re try: import grp, pwd except ImportError: grp = pwd = None # os.symlink on Windows prior to 6.0 raises NotImplementedError symlink_exception = (AttributeError, NotImplementedError) try: # WindowsError (1314) will be raised if the caller does not hold the # SeCreateSymbolicLinkPrivilege privilege symlink_exception += (WindowsError,) except NameError: pass # from tarfile import * __all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError"] if sys.version_info[0] < 3: import __builtin__ as builtins else: import builtins _open = builtins.open # Since 'open' is TarFile.open #--------------------------------------------------------- # tar constants #--------------------------------------------------------- NUL = b"\0" # the null character BLOCKSIZE = 512 # length of processing blocks RECORDSIZE = BLOCKSIZE * 20 # length of records GNU_MAGIC = b"ustar \0" # magic gnu tar string POSIX_MAGIC = b"ustar\x0000" # magic posix tar string LENGTH_NAME = 100 # maximum length of a filename LENGTH_LINK = 100 # maximum length of a linkname LENGTH_PREFIX = 155 # maximum length of the prefix field REGTYPE = b"0" # regular file AREGTYPE = b"\0" # regular file LNKTYPE = b"1" # link (inside tarfile) SYMTYPE = b"2" # symbolic link CHRTYPE = b"3" # character special device BLKTYPE = b"4" # block special device DIRTYPE = b"5" # directory FIFOTYPE = b"6" # fifo special device CONTTYPE = b"7" # contiguous file GNUTYPE_LONGNAME = b"L" # GNU tar longname GNUTYPE_LONGLINK = b"K" # GNU tar longlink GNUTYPE_SPARSE = b"S" # GNU tar sparse file XHDTYPE = b"x" # POSIX.1-2001 extended header XGLTYPE = b"g" # POSIX.1-2001 global header SOLARIS_XHDTYPE = b"X" # Solaris extended header USTAR_FORMAT = 0 # POSIX.1-1988 (ustar) format GNU_FORMAT = 1 # GNU tar format PAX_FORMAT = 2 # POSIX.1-2001 (pax) format DEFAULT_FORMAT = GNU_FORMAT #--------------------------------------------------------- # tarfile constants #--------------------------------------------------------- # File types that tarfile supports: SUPPORTED_TYPES = (REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, CONTTYPE, CHRTYPE, BLKTYPE, GNUTYPE_LONGNAME, GNUTYPE_LONGLINK, GNUTYPE_SPARSE) # File types that will be treated as a regular file. REGULAR_TYPES = (REGTYPE, AREGTYPE, CONTTYPE, GNUTYPE_SPARSE) # File types that are part of the GNU tar format. GNU_TYPES = (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK, GNUTYPE_SPARSE) # Fields from a pax header that override a TarInfo attribute. PAX_FIELDS = ("path", "linkpath", "size", "mtime", "uid", "gid", "uname", "gname") # Fields from a pax header that are affected by hdrcharset. PAX_NAME_FIELDS = set(("path", "linkpath", "uname", "gname")) # Fields in a pax header that are numbers, all other fields # are treated as strings. PAX_NUMBER_FIELDS = { "atime": float, "ctime": float, "mtime": float, "uid": int, "gid": int, "size": int } #--------------------------------------------------------- # Bits used in the mode field, values in octal. #--------------------------------------------------------- S_IFLNK = 0o120000 # symbolic link S_IFREG = 0o100000 # regular file S_IFBLK = 0o060000 # block device S_IFDIR = 0o040000 # directory S_IFCHR = 0o020000 # character device S_IFIFO = 0o010000 # fifo TSUID = 0o4000 # set UID on execution TSGID = 0o2000 # set GID on execution TSVTX = 0o1000 # reserved TUREAD = 0o400 # read by owner TUWRITE = 0o200 # write by owner TUEXEC = 0o100 # execute/search by owner TGREAD = 0o040 # read by group TGWRITE = 0o020 # write by group TGEXEC = 0o010 # execute/search by group TOREAD = 0o004 # read by other TOWRITE = 0o002 # write by other TOEXEC = 0o001 # execute/search by other #--------------------------------------------------------- # initialization #--------------------------------------------------------- if os.name in ("nt", "ce"): ENCODING = "utf-8" else: ENCODING = sys.getfilesystemencoding() #--------------------------------------------------------- # Some useful functions #--------------------------------------------------------- def stn(s, length, encoding, errors): """Convert a string to a null-terminated bytes object. """ s = s.encode(encoding, errors) return s[:length] + (length - len(s)) * NUL def nts(s, encoding, errors): """Convert a null-terminated bytes object to a string. """ p = s.find(b"\0") if p != -1: s = s[:p] return s.decode(encoding, errors) def nti(s): """Convert a number field to a python number. """ # There are two possible encodings for a number field, see # itn() below. if s[0] != chr(0o200): try: n = int(nts(s, "ascii", "strict") or "0", 8) except ValueError: raise InvalidHeaderError("invalid header") else: n = 0 for i in range(len(s) - 1): n <<= 8 n += ord(s[i + 1]) return n def itn(n, digits=8, format=DEFAULT_FORMAT): """Convert a python number to a number field. """ # POSIX 1003.1-1988 requires numbers to be encoded as a string of # octal digits followed by a null-byte, this allows values up to # (8**(digits-1))-1. GNU tar allows storing numbers greater than # that if necessary. A leading 0o200 byte indicates this particular # encoding, the following digits-1 bytes are a big-endian # representation. This allows values up to (256**(digits-1))-1. if 0 <= n < 8 ** (digits - 1): s = ("%0*o" % (digits - 1, n)).encode("ascii") + NUL else: if format != GNU_FORMAT or n >= 256 ** (digits - 1): raise ValueError("overflow in number field") if n < 0: # XXX We mimic GNU tar's behaviour with negative numbers, # this could raise OverflowError. n = struct.unpack("L", struct.pack("l", n))[0] s = bytearray() for i in range(digits - 1): s.insert(0, n & 0o377) n >>= 8 s.insert(0, 0o200) return s def calc_chksums(buf): """Calculate the checksum for a member's header by summing up all characters except for the chksum field which is treated as if it was filled with spaces. According to the GNU tar sources, some tars (Sun and NeXT) calculate chksum with signed char, which will be different if there are chars in the buffer with the high bit set. So we calculate two checksums, unsigned and signed. """ unsigned_chksum = 256 + sum(struct.unpack("148B", buf[:148]) + struct.unpack("356B", buf[156:512])) signed_chksum = 256 + sum(struct.unpack("148b", buf[:148]) + struct.unpack("356b", buf[156:512])) return unsigned_chksum, signed_chksum def copyfileobj(src, dst, length=None): """Copy length bytes from fileobj src to fileobj dst. If length is None, copy the entire content. """ if length == 0: return if length is None: while True: buf = src.read(16*1024) if not buf: break dst.write(buf) return BUFSIZE = 16 * 1024 blocks, remainder = divmod(length, BUFSIZE) for b in range(blocks): buf = src.read(BUFSIZE) if len(buf) < BUFSIZE: raise IOError("end of file reached") dst.write(buf) if remainder != 0: buf = src.read(remainder) if len(buf) < remainder: raise IOError("end of file reached") dst.write(buf) return filemode_table = ( ((S_IFLNK, "l"), (S_IFREG, "-"), (S_IFBLK, "b"), (S_IFDIR, "d"), (S_IFCHR, "c"), (S_IFIFO, "p")), ((TUREAD, "r"),), ((TUWRITE, "w"),), ((TUEXEC|TSUID, "s"), (TSUID, "S"), (TUEXEC, "x")), ((TGREAD, "r"),), ((TGWRITE, "w"),), ((TGEXEC|TSGID, "s"), (TSGID, "S"), (TGEXEC, "x")), ((TOREAD, "r"),), ((TOWRITE, "w"),), ((TOEXEC|TSVTX, "t"), (TSVTX, "T"), (TOEXEC, "x")) ) def filemode(mode): """Convert a file's mode to a string of the form -rwxrwxrwx. Used by TarFile.list() """ perm = [] for table in filemode_table: for bit, char in table: if mode & bit == bit: perm.append(char) break else: perm.append("-") return "".join(perm) class TarError(Exception): """Base exception.""" pass class ExtractError(TarError): """General exception for extract errors.""" pass class ReadError(TarError): """Exception for unreadble tar archives.""" pass class CompressionError(TarError): """Exception for unavailable compression methods.""" pass class StreamError(TarError): """Exception for unsupported operations on stream-like TarFiles.""" pass class HeaderError(TarError): """Base exception for header errors.""" pass class EmptyHeaderError(HeaderError): """Exception for empty headers.""" pass class TruncatedHeaderError(HeaderError): """Exception for truncated headers.""" pass class EOFHeaderError(HeaderError): """Exception for end of file headers.""" pass class InvalidHeaderError(HeaderError): """Exception for invalid headers.""" pass class SubsequentHeaderError(HeaderError): """Exception for missing and invalid extended headers.""" pass #--------------------------- # internal stream interface #--------------------------- class _LowLevelFile(object): """Low-level file object. Supports reading and writing. It is used instead of a regular file object for streaming access. """ def __init__(self, name, mode): mode = { "r": os.O_RDONLY, "w": os.O_WRONLY | os.O_CREAT | os.O_TRUNC, }[mode] if hasattr(os, "O_BINARY"): mode |= os.O_BINARY self.fd = os.open(name, mode, 0o666) def close(self): os.close(self.fd) def read(self, size): return os.read(self.fd, size) def write(self, s): os.write(self.fd, s) class _Stream(object): """Class that serves as an adapter between TarFile and a stream-like object. The stream-like object only needs to have a read() or write() method and is accessed blockwise. Use of gzip or bzip2 compression is possible. A stream-like object could be for example: sys.stdin, sys.stdout, a socket, a tape device etc. _Stream is intended to be used only internally. """ def __init__(self, name, mode, comptype, fileobj, bufsize): """Construct a _Stream object. """ self._extfileobj = True if fileobj is None: fileobj = _LowLevelFile(name, mode) self._extfileobj = False if comptype == '*': # Enable transparent compression detection for the # stream interface fileobj = _StreamProxy(fileobj) comptype = fileobj.getcomptype() self.name = name or "" self.mode = mode self.comptype = comptype self.fileobj = fileobj self.bufsize = bufsize self.buf = b"" self.pos = 0 self.closed = False try: if comptype == "gz": try: import zlib except ImportError: raise CompressionError("zlib module is not available") self.zlib = zlib self.crc = zlib.crc32(b"") if mode == "r": self._init_read_gz() else: self._init_write_gz() if comptype == "bz2": try: import bz2 except ImportError: raise CompressionError("bz2 module is not available") if mode == "r": self.dbuf = b"" self.cmp = bz2.BZ2Decompressor() else: self.cmp = bz2.BZ2Compressor() except: if not self._extfileobj: self.fileobj.close() self.closed = True raise def __del__(self): if hasattr(self, "closed") and not self.closed: self.close() def _init_write_gz(self): """Initialize for writing with gzip compression. """ self.cmp = self.zlib.compressobj(9, self.zlib.DEFLATED, -self.zlib.MAX_WBITS, self.zlib.DEF_MEM_LEVEL, 0) timestamp = struct.pack(" self.bufsize: self.fileobj.write(self.buf[:self.bufsize]) self.buf = self.buf[self.bufsize:] def close(self): """Close the _Stream object. No operation should be done on it afterwards. """ if self.closed: return if self.mode == "w" and self.comptype != "tar": self.buf += self.cmp.flush() if self.mode == "w" and self.buf: self.fileobj.write(self.buf) self.buf = b"" if self.comptype == "gz": # The native zlib crc is an unsigned 32-bit integer, but # the Python wrapper implicitly casts that to a signed C # long. So, on a 32-bit box self.crc may "look negative", # while the same crc on a 64-bit box may "look positive". # To avoid irksome warnings from the `struct` module, force # it to look positive on all boxes. self.fileobj.write(struct.pack("= 0: blocks, remainder = divmod(pos - self.pos, self.bufsize) for i in range(blocks): self.read(self.bufsize) self.read(remainder) else: raise StreamError("seeking backwards is not allowed") return self.pos def read(self, size=None): """Return the next size number of bytes from the stream. If size is not defined, return all bytes of the stream up to EOF. """ if size is None: t = [] while True: buf = self._read(self.bufsize) if not buf: break t.append(buf) buf = "".join(t) else: buf = self._read(size) self.pos += len(buf) return buf def _read(self, size): """Return size bytes from the stream. """ if self.comptype == "tar": return self.__read(size) c = len(self.dbuf) while c < size: buf = self.__read(self.bufsize) if not buf: break try: buf = self.cmp.decompress(buf) except IOError: raise ReadError("invalid compressed data") self.dbuf += buf c += len(buf) buf = self.dbuf[:size] self.dbuf = self.dbuf[size:] return buf def __read(self, size): """Return size bytes from stream. If internal buffer is empty, read another block from the stream. """ c = len(self.buf) while c < size: buf = self.fileobj.read(self.bufsize) if not buf: break self.buf += buf c += len(buf) buf = self.buf[:size] self.buf = self.buf[size:] return buf # class _Stream class _StreamProxy(object): """Small proxy class that enables transparent compression detection for the Stream interface (mode 'r|*'). """ def __init__(self, fileobj): self.fileobj = fileobj self.buf = self.fileobj.read(BLOCKSIZE) def read(self, size): self.read = self.fileobj.read return self.buf def getcomptype(self): if self.buf.startswith(b"\037\213\010"): return "gz" if self.buf.startswith(b"BZh91"): return "bz2" return "tar" def close(self): self.fileobj.close() # class StreamProxy class _BZ2Proxy(object): """Small proxy class that enables external file object support for "r:bz2" and "w:bz2" modes. This is actually a workaround for a limitation in bz2 module's BZ2File class which (unlike gzip.GzipFile) has no support for a file object argument. """ blocksize = 16 * 1024 def __init__(self, fileobj, mode): self.fileobj = fileobj self.mode = mode self.name = getattr(self.fileobj, "name", None) self.init() def init(self): import bz2 self.pos = 0 if self.mode == "r": self.bz2obj = bz2.BZ2Decompressor() self.fileobj.seek(0) self.buf = b"" else: self.bz2obj = bz2.BZ2Compressor() def read(self, size): x = len(self.buf) while x < size: raw = self.fileobj.read(self.blocksize) if not raw: break data = self.bz2obj.decompress(raw) self.buf += data x += len(data) buf = self.buf[:size] self.buf = self.buf[size:] self.pos += len(buf) return buf def seek(self, pos): if pos < self.pos: self.init() self.read(pos - self.pos) def tell(self): return self.pos def write(self, data): self.pos += len(data) raw = self.bz2obj.compress(data) self.fileobj.write(raw) def close(self): if self.mode == "w": raw = self.bz2obj.flush() self.fileobj.write(raw) # class _BZ2Proxy #------------------------ # Extraction file object #------------------------ class _FileInFile(object): """A thin wrapper around an existing file object that provides a part of its data as an individual file object. """ def __init__(self, fileobj, offset, size, blockinfo=None): self.fileobj = fileobj self.offset = offset self.size = size self.position = 0 if blockinfo is None: blockinfo = [(0, size)] # Construct a map with data and zero blocks. self.map_index = 0 self.map = [] lastpos = 0 realpos = self.offset for offset, size in blockinfo: if offset > lastpos: self.map.append((False, lastpos, offset, None)) self.map.append((True, offset, offset + size, realpos)) realpos += size lastpos = offset + size if lastpos < self.size: self.map.append((False, lastpos, self.size, None)) def seekable(self): if not hasattr(self.fileobj, "seekable"): # XXX gzip.GzipFile and bz2.BZ2File return True return self.fileobj.seekable() def tell(self): """Return the current file position. """ return self.position def seek(self, position): """Seek to a position in the file. """ self.position = position def read(self, size=None): """Read data from the file. """ if size is None: size = self.size - self.position else: size = min(size, self.size - self.position) buf = b"" while size > 0: while True: data, start, stop, offset = self.map[self.map_index] if start <= self.position < stop: break else: self.map_index += 1 if self.map_index == len(self.map): self.map_index = 0 length = min(size, stop - self.position) if data: self.fileobj.seek(offset + (self.position - start)) buf += self.fileobj.read(length) else: buf += NUL * length size -= length self.position += length return buf #class _FileInFile class ExFileObject(object): """File-like object for reading an archive member. Is returned by TarFile.extractfile(). """ blocksize = 1024 def __init__(self, tarfile, tarinfo): self.fileobj = _FileInFile(tarfile.fileobj, tarinfo.offset_data, tarinfo.size, tarinfo.sparse) self.name = tarinfo.name self.mode = "r" self.closed = False self.size = tarinfo.size self.position = 0 self.buffer = b"" def readable(self): return True def writable(self): return False def seekable(self): return self.fileobj.seekable() def read(self, size=None): """Read at most size bytes from the file. If size is not present or None, read all data until EOF is reached. """ if self.closed: raise ValueError("I/O operation on closed file") buf = b"" if self.buffer: if size is None: buf = self.buffer self.buffer = b"" else: buf = self.buffer[:size] self.buffer = self.buffer[size:] if size is None: buf += self.fileobj.read() else: buf += self.fileobj.read(size - len(buf)) self.position += len(buf) return buf # XXX TextIOWrapper uses the read1() method. read1 = read def readline(self, size=-1): """Read one entire line from the file. If size is present and non-negative, return a string with at most that size, which may be an incomplete line. """ if self.closed: raise ValueError("I/O operation on closed file") pos = self.buffer.find(b"\n") + 1 if pos == 0: # no newline found. while True: buf = self.fileobj.read(self.blocksize) self.buffer += buf if not buf or b"\n" in buf: pos = self.buffer.find(b"\n") + 1 if pos == 0: # no newline found. pos = len(self.buffer) break if size != -1: pos = min(size, pos) buf = self.buffer[:pos] self.buffer = self.buffer[pos:] self.position += len(buf) return buf def readlines(self): """Return a list with all remaining lines. """ result = [] while True: line = self.readline() if not line: break result.append(line) return result def tell(self): """Return the current file position. """ if self.closed: raise ValueError("I/O operation on closed file") return self.position def seek(self, pos, whence=os.SEEK_SET): """Seek to a position in the file. """ if self.closed: raise ValueError("I/O operation on closed file") if whence == os.SEEK_SET: self.position = min(max(pos, 0), self.size) elif whence == os.SEEK_CUR: if pos < 0: self.position = max(self.position + pos, 0) else: self.position = min(self.position + pos, self.size) elif whence == os.SEEK_END: self.position = max(min(self.size + pos, self.size), 0) else: raise ValueError("Invalid argument") self.buffer = b"" self.fileobj.seek(self.position) def close(self): """Close the file object. """ self.closed = True def __iter__(self): """Get an iterator over the file's lines. """ while True: line = self.readline() if not line: break yield line #class ExFileObject #------------------ # Exported Classes #------------------ class TarInfo(object): """Informational class which holds the details about an archive member given by a tar header block. TarInfo objects are returned by TarFile.getmember(), TarFile.getmembers() and TarFile.gettarinfo() and are usually created internally. """ __slots__ = ("name", "mode", "uid", "gid", "size", "mtime", "chksum", "type", "linkname", "uname", "gname", "devmajor", "devminor", "offset", "offset_data", "pax_headers", "sparse", "tarfile", "_sparse_structs", "_link_target") def __init__(self, name=""): """Construct a TarInfo object. name is the optional name of the member. """ self.name = name # member name self.mode = 0o644 # file permissions self.uid = 0 # user id self.gid = 0 # group id self.size = 0 # file size self.mtime = 0 # modification time self.chksum = 0 # header checksum self.type = REGTYPE # member type self.linkname = "" # link name self.uname = "" # user name self.gname = "" # group name self.devmajor = 0 # device major number self.devminor = 0 # device minor number self.offset = 0 # the tar header starts here self.offset_data = 0 # the file's data starts here self.sparse = None # sparse member information self.pax_headers = {} # pax header information # In pax headers the "name" and "linkname" field are called # "path" and "linkpath". def _getpath(self): return self.name def _setpath(self, name): self.name = name path = property(_getpath, _setpath) def _getlinkpath(self): return self.linkname def _setlinkpath(self, linkname): self.linkname = linkname linkpath = property(_getlinkpath, _setlinkpath) def __repr__(self): return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self)) def get_info(self): """Return the TarInfo's attributes as a dictionary. """ info = { "name": self.name, "mode": self.mode & 0o7777, "uid": self.uid, "gid": self.gid, "size": self.size, "mtime": self.mtime, "chksum": self.chksum, "type": self.type, "linkname": self.linkname, "uname": self.uname, "gname": self.gname, "devmajor": self.devmajor, "devminor": self.devminor } if info["type"] == DIRTYPE and not info["name"].endswith("/"): info["name"] += "/" return info def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="surrogateescape"): """Return a tar header as a string of 512 byte blocks. """ info = self.get_info() if format == USTAR_FORMAT: return self.create_ustar_header(info, encoding, errors) elif format == GNU_FORMAT: return self.create_gnu_header(info, encoding, errors) elif format == PAX_FORMAT: return self.create_pax_header(info, encoding) else: raise ValueError("invalid format") def create_ustar_header(self, info, encoding, errors): """Return the object as a ustar header block. """ info["magic"] = POSIX_MAGIC if len(info["linkname"]) > LENGTH_LINK: raise ValueError("linkname is too long") if len(info["name"]) > LENGTH_NAME: info["prefix"], info["name"] = self._posix_split_name(info["name"]) return self._create_header(info, USTAR_FORMAT, encoding, errors) def create_gnu_header(self, info, encoding, errors): """Return the object as a GNU header block sequence. """ info["magic"] = GNU_MAGIC buf = b"" if len(info["linkname"]) > LENGTH_LINK: buf += self._create_gnu_long_header(info["linkname"], GNUTYPE_LONGLINK, encoding, errors) if len(info["name"]) > LENGTH_NAME: buf += self._create_gnu_long_header(info["name"], GNUTYPE_LONGNAME, encoding, errors) return buf + self._create_header(info, GNU_FORMAT, encoding, errors) def create_pax_header(self, info, encoding): """Return the object as a ustar header block. If it cannot be represented this way, prepend a pax extended header sequence with supplement information. """ info["magic"] = POSIX_MAGIC pax_headers = self.pax_headers.copy() # Test string fields for values that exceed the field length or cannot # be represented in ASCII encoding. for name, hname, length in ( ("name", "path", LENGTH_NAME), ("linkname", "linkpath", LENGTH_LINK), ("uname", "uname", 32), ("gname", "gname", 32)): if hname in pax_headers: # The pax header has priority. continue # Try to encode the string as ASCII. try: info[name].encode("ascii", "strict") except UnicodeEncodeError: pax_headers[hname] = info[name] continue if len(info[name]) > length: pax_headers[hname] = info[name] # Test number fields for values that exceed the field limit or values # that like to be stored as float. for name, digits in (("uid", 8), ("gid", 8), ("size", 12), ("mtime", 12)): if name in pax_headers: # The pax header has priority. Avoid overflow. info[name] = 0 continue val = info[name] if not 0 <= val < 8 ** (digits - 1) or isinstance(val, float): pax_headers[name] = str(val) info[name] = 0 # Create a pax extended header if necessary. if pax_headers: buf = self._create_pax_generic_header(pax_headers, XHDTYPE, encoding) else: buf = b"" return buf + self._create_header(info, USTAR_FORMAT, "ascii", "replace") @classmethod def create_pax_global_header(cls, pax_headers): """Return the object as a pax global header block sequence. """ return cls._create_pax_generic_header(pax_headers, XGLTYPE, "utf8") def _posix_split_name(self, name): """Split a name longer than 100 chars into a prefix and a name part. """ prefix = name[:LENGTH_PREFIX + 1] while prefix and prefix[-1] != "/": prefix = prefix[:-1] name = name[len(prefix):] prefix = prefix[:-1] if not prefix or len(name) > LENGTH_NAME: raise ValueError("name is too long") return prefix, name @staticmethod def _create_header(info, format, encoding, errors): """Return a header block. info is a dictionary with file information, format must be one of the *_FORMAT constants. """ parts = [ stn(info.get("name", ""), 100, encoding, errors), itn(info.get("mode", 0) & 0o7777, 8, format), itn(info.get("uid", 0), 8, format), itn(info.get("gid", 0), 8, format), itn(info.get("size", 0), 12, format), itn(info.get("mtime", 0), 12, format), b" ", # checksum field info.get("type", REGTYPE), stn(info.get("linkname", ""), 100, encoding, errors), info.get("magic", POSIX_MAGIC), stn(info.get("uname", ""), 32, encoding, errors), stn(info.get("gname", ""), 32, encoding, errors), itn(info.get("devmajor", 0), 8, format), itn(info.get("devminor", 0), 8, format), stn(info.get("prefix", ""), 155, encoding, errors) ] buf = struct.pack("%ds" % BLOCKSIZE, b"".join(parts)) chksum = calc_chksums(buf[-BLOCKSIZE:])[0] buf = buf[:-364] + ("%06o\0" % chksum).encode("ascii") + buf[-357:] return buf @staticmethod def _create_payload(payload): """Return the string payload filled with zero bytes up to the next 512 byte border. """ blocks, remainder = divmod(len(payload), BLOCKSIZE) if remainder > 0: payload += (BLOCKSIZE - remainder) * NUL return payload @classmethod def _create_gnu_long_header(cls, name, type, encoding, errors): """Return a GNUTYPE_LONGNAME or GNUTYPE_LONGLINK sequence for name. """ name = name.encode(encoding, errors) + NUL info = {} info["name"] = "././@LongLink" info["type"] = type info["size"] = len(name) info["magic"] = GNU_MAGIC # create extended header + name blocks. return cls._create_header(info, USTAR_FORMAT, encoding, errors) + \ cls._create_payload(name) @classmethod def _create_pax_generic_header(cls, pax_headers, type, encoding): """Return a POSIX.1-2008 extended or global header sequence that contains a list of keyword, value pairs. The values must be strings. """ # Check if one of the fields contains surrogate characters and thereby # forces hdrcharset=BINARY, see _proc_pax() for more information. binary = False for keyword, value in pax_headers.items(): try: value.encode("utf8", "strict") except UnicodeEncodeError: binary = True break records = b"" if binary: # Put the hdrcharset field at the beginning of the header. records += b"21 hdrcharset=BINARY\n" for keyword, value in pax_headers.items(): keyword = keyword.encode("utf8") if binary: # Try to restore the original byte representation of `value'. # Needless to say, that the encoding must match the string. value = value.encode(encoding, "surrogateescape") else: value = value.encode("utf8") l = len(keyword) + len(value) + 3 # ' ' + '=' + '\n' n = p = 0 while True: n = l + len(str(p)) if n == p: break p = n records += bytes(str(p), "ascii") + b" " + keyword + b"=" + value + b"\n" # We use a hardcoded "././@PaxHeader" name like star does # instead of the one that POSIX recommends. info = {} info["name"] = "././@PaxHeader" info["type"] = type info["size"] = len(records) info["magic"] = POSIX_MAGIC # Create pax header + record blocks. return cls._create_header(info, USTAR_FORMAT, "ascii", "replace") + \ cls._create_payload(records) @classmethod def frombuf(cls, buf, encoding, errors): """Construct a TarInfo object from a 512 byte bytes object. """ if len(buf) == 0: raise EmptyHeaderError("empty header") if len(buf) != BLOCKSIZE: raise TruncatedHeaderError("truncated header") if buf.count(NUL) == BLOCKSIZE: raise EOFHeaderError("end of file header") chksum = nti(buf[148:156]) if chksum not in calc_chksums(buf): raise InvalidHeaderError("bad checksum") obj = cls() obj.name = nts(buf[0:100], encoding, errors) obj.mode = nti(buf[100:108]) obj.uid = nti(buf[108:116]) obj.gid = nti(buf[116:124]) obj.size = nti(buf[124:136]) obj.mtime = nti(buf[136:148]) obj.chksum = chksum obj.type = buf[156:157] obj.linkname = nts(buf[157:257], encoding, errors) obj.uname = nts(buf[265:297], encoding, errors) obj.gname = nts(buf[297:329], encoding, errors) obj.devmajor = nti(buf[329:337]) obj.devminor = nti(buf[337:345]) prefix = nts(buf[345:500], encoding, errors) # Old V7 tar format represents a directory as a regular # file with a trailing slash. if obj.type == AREGTYPE and obj.name.endswith("/"): obj.type = DIRTYPE # The old GNU sparse format occupies some of the unused # space in the buffer for up to 4 sparse structures. # Save the them for later processing in _proc_sparse(). if obj.type == GNUTYPE_SPARSE: pos = 386 structs = [] for i in range(4): try: offset = nti(buf[pos:pos + 12]) numbytes = nti(buf[pos + 12:pos + 24]) except ValueError: break structs.append((offset, numbytes)) pos += 24 isextended = bool(buf[482]) origsize = nti(buf[483:495]) obj._sparse_structs = (structs, isextended, origsize) # Remove redundant slashes from directories. if obj.isdir(): obj.name = obj.name.rstrip("/") # Reconstruct a ustar longname. if prefix and obj.type not in GNU_TYPES: obj.name = prefix + "/" + obj.name return obj @classmethod def fromtarfile(cls, tarfile): """Return the next TarInfo object from TarFile object tarfile. """ buf = tarfile.fileobj.read(BLOCKSIZE) obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors) obj.offset = tarfile.fileobj.tell() - BLOCKSIZE return obj._proc_member(tarfile) #-------------------------------------------------------------------------- # The following are methods that are called depending on the type of a # member. The entry point is _proc_member() which can be overridden in a # subclass to add custom _proc_*() methods. A _proc_*() method MUST # implement the following # operations: # 1. Set self.offset_data to the position where the data blocks begin, # if there is data that follows. # 2. Set tarfile.offset to the position where the next member's header will # begin. # 3. Return self or another valid TarInfo object. def _proc_member(self, tarfile): """Choose the right processing method depending on the type and call it. """ if self.type in (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK): return self._proc_gnulong(tarfile) elif self.type == GNUTYPE_SPARSE: return self._proc_sparse(tarfile) elif self.type in (XHDTYPE, XGLTYPE, SOLARIS_XHDTYPE): return self._proc_pax(tarfile) else: return self._proc_builtin(tarfile) def _proc_builtin(self, tarfile): """Process a builtin type or an unknown type which will be treated as a regular file. """ self.offset_data = tarfile.fileobj.tell() offset = self.offset_data if self.isreg() or self.type not in SUPPORTED_TYPES: # Skip the following data blocks. offset += self._block(self.size) tarfile.offset = offset # Patch the TarInfo object with saved global # header information. self._apply_pax_info(tarfile.pax_headers, tarfile.encoding, tarfile.errors) return self def _proc_gnulong(self, tarfile): """Process the blocks that hold a GNU longname or longlink member. """ buf = tarfile.fileobj.read(self._block(self.size)) # Fetch the next header and process it. try: next = self.fromtarfile(tarfile) except HeaderError: raise SubsequentHeaderError("missing or bad subsequent header") # Patch the TarInfo object from the next header with # the longname information. next.offset = self.offset if self.type == GNUTYPE_LONGNAME: next.name = nts(buf, tarfile.encoding, tarfile.errors) elif self.type == GNUTYPE_LONGLINK: next.linkname = nts(buf, tarfile.encoding, tarfile.errors) return next def _proc_sparse(self, tarfile): """Process a GNU sparse header plus extra headers. """ # We already collected some sparse structures in frombuf(). structs, isextended, origsize = self._sparse_structs del self._sparse_structs # Collect sparse structures from extended header blocks. while isextended: buf = tarfile.fileobj.read(BLOCKSIZE) pos = 0 for i in range(21): try: offset = nti(buf[pos:pos + 12]) numbytes = nti(buf[pos + 12:pos + 24]) except ValueError: break if offset and numbytes: structs.append((offset, numbytes)) pos += 24 isextended = bool(buf[504]) self.sparse = structs self.offset_data = tarfile.fileobj.tell() tarfile.offset = self.offset_data + self._block(self.size) self.size = origsize return self def _proc_pax(self, tarfile): """Process an extended or global header as described in POSIX.1-2008. """ # Read the header information. buf = tarfile.fileobj.read(self._block(self.size)) # A pax header stores supplemental information for either # the following file (extended) or all following files # (global). if self.type == XGLTYPE: pax_headers = tarfile.pax_headers else: pax_headers = tarfile.pax_headers.copy() # Check if the pax header contains a hdrcharset field. This tells us # the encoding of the path, linkpath, uname and gname fields. Normally, # these fields are UTF-8 encoded but since POSIX.1-2008 tar # implementations are allowed to store them as raw binary strings if # the translation to UTF-8 fails. match = re.search(br"\d+ hdrcharset=([^\n]+)\n", buf) if match is not None: pax_headers["hdrcharset"] = match.group(1).decode("utf8") # For the time being, we don't care about anything other than "BINARY". # The only other value that is currently allowed by the standard is # "ISO-IR 10646 2000 UTF-8" in other words UTF-8. hdrcharset = pax_headers.get("hdrcharset") if hdrcharset == "BINARY": encoding = tarfile.encoding else: encoding = "utf8" # Parse pax header information. A record looks like that: # "%d %s=%s\n" % (length, keyword, value). length is the size # of the complete record including the length field itself and # the newline. keyword and value are both UTF-8 encoded strings. regex = re.compile(br"(\d+) ([^=]+)=") pos = 0 while True: match = regex.match(buf, pos) if not match: break length, keyword = match.groups() length = int(length) value = buf[match.end(2) + 1:match.start(1) + length - 1] # Normally, we could just use "utf8" as the encoding and "strict" # as the error handler, but we better not take the risk. For # example, GNU tar <= 1.23 is known to store filenames it cannot # translate to UTF-8 as raw strings (unfortunately without a # hdrcharset=BINARY header). # We first try the strict standard encoding, and if that fails we # fall back on the user's encoding and error handler. keyword = self._decode_pax_field(keyword, "utf8", "utf8", tarfile.errors) if keyword in PAX_NAME_FIELDS: value = self._decode_pax_field(value, encoding, tarfile.encoding, tarfile.errors) else: value = self._decode_pax_field(value, "utf8", "utf8", tarfile.errors) pax_headers[keyword] = value pos += length # Fetch the next header. try: next = self.fromtarfile(tarfile) except HeaderError: raise SubsequentHeaderError("missing or bad subsequent header") # Process GNU sparse information. if "GNU.sparse.map" in pax_headers: # GNU extended sparse format version 0.1. self._proc_gnusparse_01(next, pax_headers) elif "GNU.sparse.size" in pax_headers: # GNU extended sparse format version 0.0. self._proc_gnusparse_00(next, pax_headers, buf) elif pax_headers.get("GNU.sparse.major") == "1" and pax_headers.get("GNU.sparse.minor") == "0": # GNU extended sparse format version 1.0. self._proc_gnusparse_10(next, pax_headers, tarfile) if self.type in (XHDTYPE, SOLARIS_XHDTYPE): # Patch the TarInfo object with the extended header info. next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors) next.offset = self.offset if "size" in pax_headers: # If the extended header replaces the size field, # we need to recalculate the offset where the next # header starts. offset = next.offset_data if next.isreg() or next.type not in SUPPORTED_TYPES: offset += next._block(next.size) tarfile.offset = offset return next def _proc_gnusparse_00(self, next, pax_headers, buf): """Process a GNU tar extended sparse header, version 0.0. """ offsets = [] for match in re.finditer(br"\d+ GNU.sparse.offset=(\d+)\n", buf): offsets.append(int(match.group(1))) numbytes = [] for match in re.finditer(br"\d+ GNU.sparse.numbytes=(\d+)\n", buf): numbytes.append(int(match.group(1))) next.sparse = list(zip(offsets, numbytes)) def _proc_gnusparse_01(self, next, pax_headers): """Process a GNU tar extended sparse header, version 0.1. """ sparse = [int(x) for x in pax_headers["GNU.sparse.map"].split(",")] next.sparse = list(zip(sparse[::2], sparse[1::2])) def _proc_gnusparse_10(self, next, pax_headers, tarfile): """Process a GNU tar extended sparse header, version 1.0. """ fields = None sparse = [] buf = tarfile.fileobj.read(BLOCKSIZE) fields, buf = buf.split(b"\n", 1) fields = int(fields) while len(sparse) < fields * 2: if b"\n" not in buf: buf += tarfile.fileobj.read(BLOCKSIZE) number, buf = buf.split(b"\n", 1) sparse.append(int(number)) next.offset_data = tarfile.fileobj.tell() next.sparse = list(zip(sparse[::2], sparse[1::2])) def _apply_pax_info(self, pax_headers, encoding, errors): """Replace fields with supplemental information from a previous pax extended or global header. """ for keyword, value in pax_headers.items(): if keyword == "GNU.sparse.name": setattr(self, "path", value) elif keyword == "GNU.sparse.size": setattr(self, "size", int(value)) elif keyword == "GNU.sparse.realsize": setattr(self, "size", int(value)) elif keyword in PAX_FIELDS: if keyword in PAX_NUMBER_FIELDS: try: value = PAX_NUMBER_FIELDS[keyword](value) except ValueError: value = 0 if keyword == "path": value = value.rstrip("/") setattr(self, keyword, value) self.pax_headers = pax_headers.copy() def _decode_pax_field(self, value, encoding, fallback_encoding, fallback_errors): """Decode a single field from a pax record. """ try: return value.decode(encoding, "strict") except UnicodeDecodeError: return value.decode(fallback_encoding, fallback_errors) def _block(self, count): """Round up a byte count by BLOCKSIZE and return it, e.g. _block(834) => 1024. """ blocks, remainder = divmod(count, BLOCKSIZE) if remainder: blocks += 1 return blocks * BLOCKSIZE def isreg(self): return self.type in REGULAR_TYPES def isfile(self): return self.isreg() def isdir(self): return self.type == DIRTYPE def issym(self): return self.type == SYMTYPE def islnk(self): return self.type == LNKTYPE def ischr(self): return self.type == CHRTYPE def isblk(self): return self.type == BLKTYPE def isfifo(self): return self.type == FIFOTYPE def issparse(self): return self.sparse is not None def isdev(self): return self.type in (CHRTYPE, BLKTYPE, FIFOTYPE) # class TarInfo class TarFile(object): """The TarFile Class provides an interface to tar archives. """ debug = 0 # May be set from 0 (no msgs) to 3 (all msgs) dereference = False # If true, add content of linked file to the # tar file, else the link. ignore_zeros = False # If true, skips empty or invalid blocks and # continues processing. errorlevel = 1 # If 0, fatal errors only appear in debug # messages (if debug >= 0). If > 0, errors # are passed to the caller as exceptions. format = DEFAULT_FORMAT # The format to use when creating an archive. encoding = ENCODING # Encoding for 8-bit character strings. errors = None # Error handler for unicode conversion. tarinfo = TarInfo # The default TarInfo class to use. fileobject = ExFileObject # The default ExFileObject class to use. def __init__(self, name=None, mode="r", fileobj=None, format=None, tarinfo=None, dereference=None, ignore_zeros=None, encoding=None, errors="surrogateescape", pax_headers=None, debug=None, errorlevel=None): """Open an (uncompressed) tar archive `name'. `mode' is either 'r' to read from an existing archive, 'a' to append data to an existing file or 'w' to create a new file overwriting an existing one. `mode' defaults to 'r'. If `fileobj' is given, it is used for reading or writing data. If it can be determined, `mode' is overridden by `fileobj's mode. `fileobj' is not closed, when TarFile is closed. """ if len(mode) > 1 or mode not in "raw": raise ValueError("mode must be 'r', 'a' or 'w'") self.mode = mode self._mode = {"r": "rb", "a": "r+b", "w": "wb"}[mode] if not fileobj: if self.mode == "a" and not os.path.exists(name): # Create nonexistent files in append mode. self.mode = "w" self._mode = "wb" fileobj = bltn_open(name, self._mode) self._extfileobj = False else: if name is None and hasattr(fileobj, "name"): name = fileobj.name if hasattr(fileobj, "mode"): self._mode = fileobj.mode self._extfileobj = True self.name = os.path.abspath(name) if name else None self.fileobj = fileobj # Init attributes. if format is not None: self.format = format if tarinfo is not None: self.tarinfo = tarinfo if dereference is not None: self.dereference = dereference if ignore_zeros is not None: self.ignore_zeros = ignore_zeros if encoding is not None: self.encoding = encoding self.errors = errors if pax_headers is not None and self.format == PAX_FORMAT: self.pax_headers = pax_headers else: self.pax_headers = {} if debug is not None: self.debug = debug if errorlevel is not None: self.errorlevel = errorlevel # Init datastructures. self.closed = False self.members = [] # list of members as TarInfo objects self._loaded = False # flag if all members have been read self.offset = self.fileobj.tell() # current position in the archive file self.inodes = {} # dictionary caching the inodes of # archive members already added try: if self.mode == "r": self.firstmember = None self.firstmember = self.next() if self.mode == "a": # Move to the end of the archive, # before the first empty block. while True: self.fileobj.seek(self.offset) try: tarinfo = self.tarinfo.fromtarfile(self) self.members.append(tarinfo) except EOFHeaderError: self.fileobj.seek(self.offset) break except HeaderError as e: raise ReadError(str(e)) if self.mode in "aw": self._loaded = True if self.pax_headers: buf = self.tarinfo.create_pax_global_header(self.pax_headers.copy()) self.fileobj.write(buf) self.offset += len(buf) except: if not self._extfileobj: self.fileobj.close() self.closed = True raise #-------------------------------------------------------------------------- # Below are the classmethods which act as alternate constructors to the # TarFile class. The open() method is the only one that is needed for # public use; it is the "super"-constructor and is able to select an # adequate "sub"-constructor for a particular compression using the mapping # from OPEN_METH. # # This concept allows one to subclass TarFile without losing the comfort of # the super-constructor. A sub-constructor is registered and made available # by adding it to the mapping in OPEN_METH. @classmethod def open(cls, name=None, mode="r", fileobj=None, bufsize=RECORDSIZE, **kwargs): """Open a tar archive for reading, writing or appending. Return an appropriate TarFile class. mode: 'r' or 'r:*' open for reading with transparent compression 'r:' open for reading exclusively uncompressed 'r:gz' open for reading with gzip compression 'r:bz2' open for reading with bzip2 compression 'a' or 'a:' open for appending, creating the file if necessary 'w' or 'w:' open for writing without compression 'w:gz' open for writing with gzip compression 'w:bz2' open for writing with bzip2 compression 'r|*' open a stream of tar blocks with transparent compression 'r|' open an uncompressed stream of tar blocks for reading 'r|gz' open a gzip compressed stream of tar blocks 'r|bz2' open a bzip2 compressed stream of tar blocks 'w|' open an uncompressed stream for writing 'w|gz' open a gzip compressed stream for writing 'w|bz2' open a bzip2 compressed stream for writing """ if not name and not fileobj: raise ValueError("nothing to open") if mode in ("r", "r:*"): # Find out which *open() is appropriate for opening the file. for comptype in cls.OPEN_METH: func = getattr(cls, cls.OPEN_METH[comptype]) if fileobj is not None: saved_pos = fileobj.tell() try: return func(name, "r", fileobj, **kwargs) except (ReadError, CompressionError) as e: if fileobj is not None: fileobj.seek(saved_pos) continue raise ReadError("file could not be opened successfully") elif ":" in mode: filemode, comptype = mode.split(":", 1) filemode = filemode or "r" comptype = comptype or "tar" # Select the *open() function according to # given compression. if comptype in cls.OPEN_METH: func = getattr(cls, cls.OPEN_METH[comptype]) else: raise CompressionError("unknown compression type %r" % comptype) return func(name, filemode, fileobj, **kwargs) elif "|" in mode: filemode, comptype = mode.split("|", 1) filemode = filemode or "r" comptype = comptype or "tar" if filemode not in "rw": raise ValueError("mode must be 'r' or 'w'") stream = _Stream(name, filemode, comptype, fileobj, bufsize) try: t = cls(name, filemode, stream, **kwargs) except: stream.close() raise t._extfileobj = False return t elif mode in "aw": return cls.taropen(name, mode, fileobj, **kwargs) raise ValueError("undiscernible mode") @classmethod def taropen(cls, name, mode="r", fileobj=None, **kwargs): """Open uncompressed tar archive name for reading or writing. """ if len(mode) > 1 or mode not in "raw": raise ValueError("mode must be 'r', 'a' or 'w'") return cls(name, mode, fileobj, **kwargs) @classmethod def gzopen(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs): """Open gzip compressed tar archive name for reading or writing. Appending is not allowed. """ if len(mode) > 1 or mode not in "rw": raise ValueError("mode must be 'r' or 'w'") try: import gzip gzip.GzipFile except (ImportError, AttributeError): raise CompressionError("gzip module is not available") extfileobj = fileobj is not None try: fileobj = gzip.GzipFile(name, mode + "b", compresslevel, fileobj) t = cls.taropen(name, mode, fileobj, **kwargs) except IOError: if not extfileobj and fileobj is not None: fileobj.close() if fileobj is None: raise raise ReadError("not a gzip file") except: if not extfileobj and fileobj is not None: fileobj.close() raise t._extfileobj = extfileobj return t @classmethod def bz2open(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs): """Open bzip2 compressed tar archive name for reading or writing. Appending is not allowed. """ if len(mode) > 1 or mode not in "rw": raise ValueError("mode must be 'r' or 'w'.") try: import bz2 except ImportError: raise CompressionError("bz2 module is not available") if fileobj is not None: fileobj = _BZ2Proxy(fileobj, mode) else: fileobj = bz2.BZ2File(name, mode, compresslevel=compresslevel) try: t = cls.taropen(name, mode, fileobj, **kwargs) except (IOError, EOFError): fileobj.close() raise ReadError("not a bzip2 file") t._extfileobj = False return t # All *open() methods are registered here. OPEN_METH = { "tar": "taropen", # uncompressed tar "gz": "gzopen", # gzip compressed tar "bz2": "bz2open" # bzip2 compressed tar } #-------------------------------------------------------------------------- # The public methods which TarFile provides: def close(self): """Close the TarFile. In write-mode, two finishing zero blocks are appended to the archive. """ if self.closed: return if self.mode in "aw": self.fileobj.write(NUL * (BLOCKSIZE * 2)) self.offset += (BLOCKSIZE * 2) # fill up the end with zero-blocks # (like option -b20 for tar does) blocks, remainder = divmod(self.offset, RECORDSIZE) if remainder > 0: self.fileobj.write(NUL * (RECORDSIZE - remainder)) if not self._extfileobj: self.fileobj.close() self.closed = True def getmember(self, name): """Return a TarInfo object for member `name'. If `name' can not be found in the archive, KeyError is raised. If a member occurs more than once in the archive, its last occurrence is assumed to be the most up-to-date version. """ tarinfo = self._getmember(name) if tarinfo is None: raise KeyError("filename %r not found" % name) return tarinfo def getmembers(self): """Return the members of the archive as a list of TarInfo objects. The list has the same order as the members in the archive. """ self._check() if not self._loaded: # if we want to obtain a list of self._load() # all members, we first have to # scan the whole archive. return self.members def getnames(self): """Return the members of the archive as a list of their names. It has the same order as the list returned by getmembers(). """ return [tarinfo.name for tarinfo in self.getmembers()] def gettarinfo(self, name=None, arcname=None, fileobj=None): """Create a TarInfo object for either the file `name' or the file object `fileobj' (using os.fstat on its file descriptor). You can modify some of the TarInfo's attributes before you add it using addfile(). If given, `arcname' specifies an alternative name for the file in the archive. """ self._check("aw") # When fileobj is given, replace name by # fileobj's real name. if fileobj is not None: name = fileobj.name # Building the name of the member in the archive. # Backward slashes are converted to forward slashes, # Absolute paths are turned to relative paths. if arcname is None: arcname = name drv, arcname = os.path.splitdrive(arcname) arcname = arcname.replace(os.sep, "/") arcname = arcname.lstrip("/") # Now, fill the TarInfo object with # information specific for the file. tarinfo = self.tarinfo() tarinfo.tarfile = self # Use os.stat or os.lstat, depending on platform # and if symlinks shall be resolved. if fileobj is None: if hasattr(os, "lstat") and not self.dereference: statres = os.lstat(name) else: statres = os.stat(name) else: statres = os.fstat(fileobj.fileno()) linkname = "" stmd = statres.st_mode if stat.S_ISREG(stmd): inode = (statres.st_ino, statres.st_dev) if not self.dereference and statres.st_nlink > 1 and \ inode in self.inodes and arcname != self.inodes[inode]: # Is it a hardlink to an already # archived file? type = LNKTYPE linkname = self.inodes[inode] else: # The inode is added only if its valid. # For win32 it is always 0. type = REGTYPE if inode[0]: self.inodes[inode] = arcname elif stat.S_ISDIR(stmd): type = DIRTYPE elif stat.S_ISFIFO(stmd): type = FIFOTYPE elif stat.S_ISLNK(stmd): type = SYMTYPE linkname = os.readlink(name) elif stat.S_ISCHR(stmd): type = CHRTYPE elif stat.S_ISBLK(stmd): type = BLKTYPE else: return None # Fill the TarInfo object with all # information we can get. tarinfo.name = arcname tarinfo.mode = stmd tarinfo.uid = statres.st_uid tarinfo.gid = statres.st_gid if type == REGTYPE: tarinfo.size = statres.st_size else: tarinfo.size = 0 tarinfo.mtime = statres.st_mtime tarinfo.type = type tarinfo.linkname = linkname if pwd: try: tarinfo.uname = pwd.getpwuid(tarinfo.uid)[0] except KeyError: pass if grp: try: tarinfo.gname = grp.getgrgid(tarinfo.gid)[0] except KeyError: pass if type in (CHRTYPE, BLKTYPE): if hasattr(os, "major") and hasattr(os, "minor"): tarinfo.devmajor = os.major(statres.st_rdev) tarinfo.devminor = os.minor(statres.st_rdev) return tarinfo def list(self, verbose=True): """Print a table of contents to sys.stdout. If `verbose' is False, only the names of the members are printed. If it is True, an `ls -l'-like output is produced. """ self._check() for tarinfo in self: if verbose: print(filemode(tarinfo.mode), end=' ') print("%s/%s" % (tarinfo.uname or tarinfo.uid, tarinfo.gname or tarinfo.gid), end=' ') if tarinfo.ischr() or tarinfo.isblk(): print("%10s" % ("%d,%d" \ % (tarinfo.devmajor, tarinfo.devminor)), end=' ') else: print("%10d" % tarinfo.size, end=' ') print("%d-%02d-%02d %02d:%02d:%02d" \ % time.localtime(tarinfo.mtime)[:6], end=' ') print(tarinfo.name + ("/" if tarinfo.isdir() else ""), end=' ') if verbose: if tarinfo.issym(): print("->", tarinfo.linkname, end=' ') if tarinfo.islnk(): print("link to", tarinfo.linkname, end=' ') print() def add(self, name, arcname=None, recursive=True, exclude=None, filter=None): """Add the file `name' to the archive. `name' may be any type of file (directory, fifo, symbolic link, etc.). If given, `arcname' specifies an alternative name for the file in the archive. Directories are added recursively by default. This can be avoided by setting `recursive' to False. `exclude' is a function that should return True for each filename to be excluded. `filter' is a function that expects a TarInfo object argument and returns the changed TarInfo object, if it returns None the TarInfo object will be excluded from the archive. """ self._check("aw") if arcname is None: arcname = name # Exclude pathnames. if exclude is not None: import warnings warnings.warn("use the filter argument instead", DeprecationWarning, 2) if exclude(name): self._dbg(2, "tarfile: Excluded %r" % name) return # Skip if somebody tries to archive the archive... if self.name is not None and os.path.abspath(name) == self.name: self._dbg(2, "tarfile: Skipped %r" % name) return self._dbg(1, name) # Create a TarInfo object from the file. tarinfo = self.gettarinfo(name, arcname) if tarinfo is None: self._dbg(1, "tarfile: Unsupported type %r" % name) return # Change or exclude the TarInfo object. if filter is not None: tarinfo = filter(tarinfo) if tarinfo is None: self._dbg(2, "tarfile: Excluded %r" % name) return # Append the tar header and data to the archive. if tarinfo.isreg(): f = bltn_open(name, "rb") self.addfile(tarinfo, f) f.close() elif tarinfo.isdir(): self.addfile(tarinfo) if recursive: for f in os.listdir(name): self.add(os.path.join(name, f), os.path.join(arcname, f), recursive, exclude, filter=filter) else: self.addfile(tarinfo) def addfile(self, tarinfo, fileobj=None): """Add the TarInfo object `tarinfo' to the archive. If `fileobj' is given, tarinfo.size bytes are read from it and added to the archive. You can create TarInfo objects using gettarinfo(). On Windows platforms, `fileobj' should always be opened with mode 'rb' to avoid irritation about the file size. """ self._check("aw") tarinfo = copy.copy(tarinfo) buf = tarinfo.tobuf(self.format, self.encoding, self.errors) self.fileobj.write(buf) self.offset += len(buf) # If there's data to follow, append it. if fileobj is not None: copyfileobj(fileobj, self.fileobj, tarinfo.size) blocks, remainder = divmod(tarinfo.size, BLOCKSIZE) if remainder > 0: self.fileobj.write(NUL * (BLOCKSIZE - remainder)) blocks += 1 self.offset += blocks * BLOCKSIZE self.members.append(tarinfo) def extractall(self, path=".", members=None): """Extract all members from the archive to the current working directory and set owner, modification time and permissions on directories afterwards. `path' specifies a different directory to extract to. `members' is optional and must be a subset of the list returned by getmembers(). """ directories = [] if members is None: members = self for tarinfo in members: if tarinfo.isdir(): # Extract directories with a safe mode. directories.append(tarinfo) tarinfo = copy.copy(tarinfo) tarinfo.mode = 0o700 # Do not set_attrs directories, as we will do that further down self.extract(tarinfo, path, set_attrs=not tarinfo.isdir()) # Reverse sort directories. directories.sort(key=lambda a: a.name) directories.reverse() # Set correct owner, mtime and filemode on directories. for tarinfo in directories: dirpath = os.path.join(path, tarinfo.name) try: self.chown(tarinfo, dirpath) self.utime(tarinfo, dirpath) self.chmod(tarinfo, dirpath) except ExtractError as e: if self.errorlevel > 1: raise else: self._dbg(1, "tarfile: %s" % e) def extract(self, member, path="", set_attrs=True): """Extract a member from the archive to the current working directory, using its full name. Its file information is extracted as accurately as possible. `member' may be a filename or a TarInfo object. You can specify a different directory using `path'. File attributes (owner, mtime, mode) are set unless `set_attrs' is False. """ self._check("r") if isinstance(member, str): tarinfo = self.getmember(member) else: tarinfo = member # Prepare the link target for makelink(). if tarinfo.islnk(): tarinfo._link_target = os.path.join(path, tarinfo.linkname) try: self._extract_member(tarinfo, os.path.join(path, tarinfo.name), set_attrs=set_attrs) except EnvironmentError as e: if self.errorlevel > 0: raise else: if e.filename is None: self._dbg(1, "tarfile: %s" % e.strerror) else: self._dbg(1, "tarfile: %s %r" % (e.strerror, e.filename)) except ExtractError as e: if self.errorlevel > 1: raise else: self._dbg(1, "tarfile: %s" % e) def extractfile(self, member): """Extract a member from the archive as a file object. `member' may be a filename or a TarInfo object. If `member' is a regular file, a file-like object is returned. If `member' is a link, a file-like object is constructed from the link's target. If `member' is none of the above, None is returned. The file-like object is read-only and provides the following methods: read(), readline(), readlines(), seek() and tell() """ self._check("r") if isinstance(member, str): tarinfo = self.getmember(member) else: tarinfo = member if tarinfo.isreg(): return self.fileobject(self, tarinfo) elif tarinfo.type not in SUPPORTED_TYPES: # If a member's type is unknown, it is treated as a # regular file. return self.fileobject(self, tarinfo) elif tarinfo.islnk() or tarinfo.issym(): if isinstance(self.fileobj, _Stream): # A small but ugly workaround for the case that someone tries # to extract a (sym)link as a file-object from a non-seekable # stream of tar blocks. raise StreamError("cannot extract (sym)link as file object") else: # A (sym)link's file object is its target's file object. return self.extractfile(self._find_link_target(tarinfo)) else: # If there's no data associated with the member (directory, chrdev, # blkdev, etc.), return None instead of a file object. return None def _extract_member(self, tarinfo, targetpath, set_attrs=True): """Extract the TarInfo object tarinfo to a physical file called targetpath. """ # Fetch the TarInfo object for the given name # and build the destination pathname, replacing # forward slashes to platform specific separators. targetpath = targetpath.rstrip("/") targetpath = targetpath.replace("/", os.sep) # Create all upper directories. upperdirs = os.path.dirname(targetpath) if upperdirs and not os.path.exists(upperdirs): # Create directories that are not part of the archive with # default permissions. os.makedirs(upperdirs) if tarinfo.islnk() or tarinfo.issym(): self._dbg(1, "%s -> %s" % (tarinfo.name, tarinfo.linkname)) else: self._dbg(1, tarinfo.name) if tarinfo.isreg(): self.makefile(tarinfo, targetpath) elif tarinfo.isdir(): self.makedir(tarinfo, targetpath) elif tarinfo.isfifo(): self.makefifo(tarinfo, targetpath) elif tarinfo.ischr() or tarinfo.isblk(): self.makedev(tarinfo, targetpath) elif tarinfo.islnk() or tarinfo.issym(): self.makelink(tarinfo, targetpath) elif tarinfo.type not in SUPPORTED_TYPES: self.makeunknown(tarinfo, targetpath) else: self.makefile(tarinfo, targetpath) if set_attrs: self.chown(tarinfo, targetpath) if not tarinfo.issym(): self.chmod(tarinfo, targetpath) self.utime(tarinfo, targetpath) #-------------------------------------------------------------------------- # Below are the different file methods. They are called via # _extract_member() when extract() is called. They can be replaced in a # subclass to implement other functionality. def makedir(self, tarinfo, targetpath): """Make a directory called targetpath. """ try: # Use a safe mode for the directory, the real mode is set # later in _extract_member(). os.mkdir(targetpath, 0o700) except EnvironmentError as e: if e.errno != errno.EEXIST: raise def makefile(self, tarinfo, targetpath): """Make a file called targetpath. """ source = self.fileobj source.seek(tarinfo.offset_data) target = bltn_open(targetpath, "wb") if tarinfo.sparse is not None: for offset, size in tarinfo.sparse: target.seek(offset) copyfileobj(source, target, size) else: copyfileobj(source, target, tarinfo.size) target.seek(tarinfo.size) target.truncate() target.close() def makeunknown(self, tarinfo, targetpath): """Make a file from a TarInfo object with an unknown type at targetpath. """ self.makefile(tarinfo, targetpath) self._dbg(1, "tarfile: Unknown file type %r, " \ "extracted as regular file." % tarinfo.type) def makefifo(self, tarinfo, targetpath): """Make a fifo called targetpath. """ if hasattr(os, "mkfifo"): os.mkfifo(targetpath) else: raise ExtractError("fifo not supported by system") def makedev(self, tarinfo, targetpath): """Make a character or block device called targetpath. """ if not hasattr(os, "mknod") or not hasattr(os, "makedev"): raise ExtractError("special devices not supported by system") mode = tarinfo.mode if tarinfo.isblk(): mode |= stat.S_IFBLK else: mode |= stat.S_IFCHR os.mknod(targetpath, mode, os.makedev(tarinfo.devmajor, tarinfo.devminor)) def makelink(self, tarinfo, targetpath): """Make a (symbolic) link called targetpath. If it cannot be created (platform limitation), we try to make a copy of the referenced file instead of a link. """ try: # For systems that support symbolic and hard links. if tarinfo.issym(): os.symlink(tarinfo.linkname, targetpath) else: # See extract(). if os.path.exists(tarinfo._link_target): os.link(tarinfo._link_target, targetpath) else: self._extract_member(self._find_link_target(tarinfo), targetpath) except symlink_exception: if tarinfo.issym(): linkpath = os.path.join(os.path.dirname(tarinfo.name), tarinfo.linkname) else: linkpath = tarinfo.linkname else: try: self._extract_member(self._find_link_target(tarinfo), targetpath) except KeyError: raise ExtractError("unable to resolve link inside archive") def chown(self, tarinfo, targetpath): """Set owner of targetpath according to tarinfo. """ if pwd and hasattr(os, "geteuid") and os.geteuid() == 0: # We have to be root to do so. try: g = grp.getgrnam(tarinfo.gname)[2] except KeyError: g = tarinfo.gid try: u = pwd.getpwnam(tarinfo.uname)[2] except KeyError: u = tarinfo.uid try: if tarinfo.issym() and hasattr(os, "lchown"): os.lchown(targetpath, u, g) else: if sys.platform != "os2emx": os.chown(targetpath, u, g) except EnvironmentError as e: raise ExtractError("could not change owner") def chmod(self, tarinfo, targetpath): """Set file permissions of targetpath according to tarinfo. """ if hasattr(os, 'chmod'): try: os.chmod(targetpath, tarinfo.mode) except EnvironmentError as e: raise ExtractError("could not change mode") def utime(self, tarinfo, targetpath): """Set modification time of targetpath according to tarinfo. """ if not hasattr(os, 'utime'): return try: os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime)) except EnvironmentError as e: raise ExtractError("could not change modification time") #-------------------------------------------------------------------------- def next(self): """Return the next member of the archive as a TarInfo object, when TarFile is opened for reading. Return None if there is no more available. """ self._check("ra") if self.firstmember is not None: m = self.firstmember self.firstmember = None return m # Read the next block. self.fileobj.seek(self.offset) tarinfo = None while True: try: tarinfo = self.tarinfo.fromtarfile(self) except EOFHeaderError as e: if self.ignore_zeros: self._dbg(2, "0x%X: %s" % (self.offset, e)) self.offset += BLOCKSIZE continue except InvalidHeaderError as e: if self.ignore_zeros: self._dbg(2, "0x%X: %s" % (self.offset, e)) self.offset += BLOCKSIZE continue elif self.offset == 0: raise ReadError(str(e)) except EmptyHeaderError: if self.offset == 0: raise ReadError("empty file") except TruncatedHeaderError as e: if self.offset == 0: raise ReadError(str(e)) except SubsequentHeaderError as e: raise ReadError(str(e)) break if tarinfo is not None: self.members.append(tarinfo) else: self._loaded = True return tarinfo #-------------------------------------------------------------------------- # Little helper methods: def _getmember(self, name, tarinfo=None, normalize=False): """Find an archive member by name from bottom to top. If tarinfo is given, it is used as the starting point. """ # Ensure that all members have been loaded. members = self.getmembers() # Limit the member search list up to tarinfo. if tarinfo is not None: members = members[:members.index(tarinfo)] if normalize: name = os.path.normpath(name) for member in reversed(members): if normalize: member_name = os.path.normpath(member.name) else: member_name = member.name if name == member_name: return member def _load(self): """Read through the entire archive file and look for readable members. """ while True: tarinfo = self.next() if tarinfo is None: break self._loaded = True def _check(self, mode=None): """Check if TarFile is still open, and if the operation's mode corresponds to TarFile's mode. """ if self.closed: raise IOError("%s is closed" % self.__class__.__name__) if mode is not None and self.mode not in mode: raise IOError("bad operation for mode %r" % self.mode) def _find_link_target(self, tarinfo): """Find the target member of a symlink or hardlink member in the archive. """ if tarinfo.issym(): # Always search the entire archive. linkname = os.path.dirname(tarinfo.name) + "/" + tarinfo.linkname limit = None else: # Search the archive before the link, because a hard link is # just a reference to an already archived file. linkname = tarinfo.linkname limit = tarinfo member = self._getmember(linkname, tarinfo=limit, normalize=True) if member is None: raise KeyError("linkname %r not found" % linkname) return member def __iter__(self): """Provide an iterator object. """ if self._loaded: return iter(self.members) else: return TarIter(self) def _dbg(self, level, msg): """Write debugging output to sys.stderr. """ if level <= self.debug: print(msg, file=sys.stderr) def __enter__(self): self._check() return self def __exit__(self, type, value, traceback): if type is None: self.close() else: # An exception occurred. We must not call close() because # it would try to write end-of-archive blocks and padding. if not self._extfileobj: self.fileobj.close() self.closed = True # class TarFile class TarIter(object): """Iterator Class. for tarinfo in TarFile(...): suite... """ def __init__(self, tarfile): """Construct a TarIter object. """ self.tarfile = tarfile self.index = 0 def __iter__(self): """Return iterator object. """ return self def __next__(self): """Return the next item using TarFile's next() method. When all members have been read, set TarFile as _loaded. """ # Fix for SF #1100429: Under rare circumstances it can # happen that getmembers() is called during iteration, # which will cause TarIter to stop prematurely. if not self.tarfile._loaded: tarinfo = self.tarfile.next() if not tarinfo: self.tarfile._loaded = True raise StopIteration else: try: tarinfo = self.tarfile.members[self.index] except IndexError: raise StopIteration self.index += 1 return tarinfo next = __next__ # for Python 2.x #-------------------- # exported functions #-------------------- def is_tarfile(name): """Return True if name points to a tar archive that we are able to handle, else return False. """ try: t = open(name) t.close() return True except TarError: return False bltn_open = open open = TarFile.open feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/compat.py0000644000076500000240000011732412700725533030202 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2013-2016 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # from __future__ import absolute_import import os import re import sys if sys.version_info[0] < 3: # pragma: no cover from StringIO import StringIO string_types = basestring, text_type = unicode from types import FileType as file_type import __builtin__ as builtins import ConfigParser as configparser from ._backport import shutil from urlparse import urlparse, urlunparse, urljoin, urlsplit, urlunsplit from urllib import (urlretrieve, quote as _quote, unquote, url2pathname, pathname2url, ContentTooShortError, splittype) def quote(s): if isinstance(s, unicode): s = s.encode('utf-8') return _quote(s) import urllib2 from urllib2 import (Request, urlopen, URLError, HTTPError, HTTPBasicAuthHandler, HTTPPasswordMgr, HTTPSHandler, HTTPHandler, HTTPRedirectHandler, build_opener) import httplib import xmlrpclib import Queue as queue from HTMLParser import HTMLParser import htmlentitydefs raw_input = raw_input from itertools import ifilter as filter from itertools import ifilterfalse as filterfalse _userprog = None def splituser(host): """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.""" global _userprog if _userprog is None: import re _userprog = re.compile('^(.*)@(.*)$') match = _userprog.match(host) if match: return match.group(1, 2) return None, host else: # pragma: no cover from io import StringIO string_types = str, text_type = str from io import TextIOWrapper as file_type import builtins import configparser import shutil from urllib.parse import (urlparse, urlunparse, urljoin, splituser, quote, unquote, urlsplit, urlunsplit, splittype) from urllib.request import (urlopen, urlretrieve, Request, url2pathname, pathname2url, HTTPBasicAuthHandler, HTTPPasswordMgr, HTTPSHandler, HTTPHandler, HTTPRedirectHandler, build_opener) from urllib.error import HTTPError, URLError, ContentTooShortError import http.client as httplib import urllib.request as urllib2 import xmlrpc.client as xmlrpclib import queue from html.parser import HTMLParser import html.entities as htmlentitydefs raw_input = input from itertools import filterfalse filter = filter try: from ssl import match_hostname, CertificateError except ImportError: # pragma: no cover class CertificateError(ValueError): pass def _dnsname_match(dn, hostname, max_wildcards=1): """Matching according to RFC 6125, section 6.4.3 http://tools.ietf.org/html/rfc6125#section-6.4.3 """ pats = [] if not dn: return False parts = dn.split('.') leftmost, remainder = parts[0], parts[1:] wildcards = leftmost.count('*') if wildcards > max_wildcards: # Issue #17980: avoid denials of service by refusing more # than one wildcard per fragment. A survery of established # policy among SSL implementations showed it to be a # reasonable choice. raise CertificateError( "too many wildcards in certificate DNS name: " + repr(dn)) # speed up common case w/o wildcards if not wildcards: return dn.lower() == hostname.lower() # RFC 6125, section 6.4.3, subitem 1. # The client SHOULD NOT attempt to match a presented identifier in which # the wildcard character comprises a label other than the left-most label. if leftmost == '*': # When '*' is a fragment by itself, it matches a non-empty dotless # fragment. pats.append('[^.]+') elif leftmost.startswith('xn--') or hostname.startswith('xn--'): # RFC 6125, section 6.4.3, subitem 3. # The client SHOULD NOT attempt to match a presented identifier # where the wildcard character is embedded within an A-label or # U-label of an internationalized domain name. pats.append(re.escape(leftmost)) else: # Otherwise, '*' matches any dotless string, e.g. www* pats.append(re.escape(leftmost).replace(r'\*', '[^.]*')) # add the remaining fragments, ignore any wildcards for frag in remainder: pats.append(re.escape(frag)) pat = re.compile(r'\A' + r'\.'.join(pats) + r'\Z', re.IGNORECASE) return pat.match(hostname) def match_hostname(cert, hostname): """Verify that *cert* (in decoded format as returned by SSLSocket.getpeercert()) matches the *hostname*. RFC 2818 and RFC 6125 rules are followed, but IP addresses are not accepted for *hostname*. CertificateError is raised on failure. On success, the function returns nothing. """ if not cert: raise ValueError("empty or no certificate, match_hostname needs a " "SSL socket or SSL context with either " "CERT_OPTIONAL or CERT_REQUIRED") dnsnames = [] san = cert.get('subjectAltName', ()) for key, value in san: if key == 'DNS': if _dnsname_match(value, hostname): return dnsnames.append(value) if not dnsnames: # The subject is only checked when there is no dNSName entry # in subjectAltName for sub in cert.get('subject', ()): for key, value in sub: # XXX according to RFC 2818, the most specific Common Name # must be used. if key == 'commonName': if _dnsname_match(value, hostname): return dnsnames.append(value) if len(dnsnames) > 1: raise CertificateError("hostname %r " "doesn't match either of %s" % (hostname, ', '.join(map(repr, dnsnames)))) elif len(dnsnames) == 1: raise CertificateError("hostname %r " "doesn't match %r" % (hostname, dnsnames[0])) else: raise CertificateError("no appropriate commonName or " "subjectAltName fields were found") try: from types import SimpleNamespace as Container except ImportError: # pragma: no cover class Container(object): """ A generic container for when multiple values need to be returned """ def __init__(self, **kwargs): self.__dict__.update(kwargs) try: from shutil import which except ImportError: # pragma: no cover # Implementation from Python 3.3 def which(cmd, mode=os.F_OK | os.X_OK, path=None): """Given a command, mode, and a PATH string, return the path which conforms to the given mode on the PATH, or None if there is no such file. `mode` defaults to os.F_OK | os.X_OK. `path` defaults to the result of os.environ.get("PATH"), or can be overridden with a custom search path. """ # Check that a given file can be accessed with the correct mode. # Additionally check that `file` is not a directory, as on Windows # directories pass the os.access check. def _access_check(fn, mode): return (os.path.exists(fn) and os.access(fn, mode) and not os.path.isdir(fn)) # If we're given a path with a directory part, look it up directly rather # than referring to PATH directories. This includes checking relative to the # current directory, e.g. ./script if os.path.dirname(cmd): if _access_check(cmd, mode): return cmd return None if path is None: path = os.environ.get("PATH", os.defpath) if not path: return None path = path.split(os.pathsep) if sys.platform == "win32": # The current directory takes precedence on Windows. if not os.curdir in path: path.insert(0, os.curdir) # PATHEXT is necessary to check on Windows. pathext = os.environ.get("PATHEXT", "").split(os.pathsep) # See if the given file matches any of the expected path extensions. # This will allow us to short circuit when given "python.exe". # If it does match, only test that one, otherwise we have to try # others. if any(cmd.lower().endswith(ext.lower()) for ext in pathext): files = [cmd] else: files = [cmd + ext for ext in pathext] else: # On other platforms you don't have things like PATHEXT to tell you # what file suffixes are executable, so just pass on cmd as-is. files = [cmd] seen = set() for dir in path: normdir = os.path.normcase(dir) if not normdir in seen: seen.add(normdir) for thefile in files: name = os.path.join(dir, thefile) if _access_check(name, mode): return name return None # ZipFile is a context manager in 2.7, but not in 2.6 from zipfile import ZipFile as BaseZipFile if hasattr(BaseZipFile, '__enter__'): # pragma: no cover ZipFile = BaseZipFile else: from zipfile import ZipExtFile as BaseZipExtFile class ZipExtFile(BaseZipExtFile): def __init__(self, base): self.__dict__.update(base.__dict__) def __enter__(self): return self def __exit__(self, *exc_info): self.close() # return None, so if an exception occurred, it will propagate class ZipFile(BaseZipFile): def __enter__(self): return self def __exit__(self, *exc_info): self.close() # return None, so if an exception occurred, it will propagate def open(self, *args, **kwargs): base = BaseZipFile.open(self, *args, **kwargs) return ZipExtFile(base) try: from platform import python_implementation except ImportError: # pragma: no cover def python_implementation(): """Return a string identifying the Python implementation.""" if 'PyPy' in sys.version: return 'PyPy' if os.name == 'java': return 'Jython' if sys.version.startswith('IronPython'): return 'IronPython' return 'CPython' try: import sysconfig except ImportError: # pragma: no cover from ._backport import sysconfig try: callable = callable except NameError: # pragma: no cover from collections import Callable def callable(obj): return isinstance(obj, Callable) try: fsencode = os.fsencode fsdecode = os.fsdecode except AttributeError: # pragma: no cover _fsencoding = sys.getfilesystemencoding() if _fsencoding == 'mbcs': _fserrors = 'strict' else: _fserrors = 'surrogateescape' def fsencode(filename): if isinstance(filename, bytes): return filename elif isinstance(filename, text_type): return filename.encode(_fsencoding, _fserrors) else: raise TypeError("expect bytes or str, not %s" % type(filename).__name__) def fsdecode(filename): if isinstance(filename, text_type): return filename elif isinstance(filename, bytes): return filename.decode(_fsencoding, _fserrors) else: raise TypeError("expect bytes or str, not %s" % type(filename).__name__) try: from tokenize import detect_encoding except ImportError: # pragma: no cover from codecs import BOM_UTF8, lookup import re cookie_re = re.compile("coding[:=]\s*([-\w.]+)") def _get_normal_name(orig_enc): """Imitates get_normal_name in tokenizer.c.""" # Only care about the first 12 characters. enc = orig_enc[:12].lower().replace("_", "-") if enc == "utf-8" or enc.startswith("utf-8-"): return "utf-8" if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \ enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")): return "iso-8859-1" return orig_enc def detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should be used to decode a Python source file. It requires one argment, readline, in the same way as the tokenize() generator. It will call readline a maximum of twice, and return the encoding used (as a string) and a list of any lines (left as bytes) it has read in. It detects the encoding from the presence of a utf-8 bom or an encoding cookie as specified in pep-0263. If both a bom and a cookie are present, but disagree, a SyntaxError will be raised. If the encoding cookie is an invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, 'utf-8-sig' is returned. If no encoding is specified, then the default of 'utf-8' will be returned. """ try: filename = readline.__self__.name except AttributeError: filename = None bom_found = False encoding = None default = 'utf-8' def read_or_stop(): try: return readline() except StopIteration: return b'' def find_cookie(line): try: # Decode as UTF-8. Either the line is an encoding declaration, # in which case it should be pure ASCII, or it must be UTF-8 # per default encoding. line_string = line.decode('utf-8') except UnicodeDecodeError: msg = "invalid or missing encoding declaration" if filename is not None: msg = '{} for {!r}'.format(msg, filename) raise SyntaxError(msg) matches = cookie_re.findall(line_string) if not matches: return None encoding = _get_normal_name(matches[0]) try: codec = lookup(encoding) except LookupError: # This behaviour mimics the Python interpreter if filename is None: msg = "unknown encoding: " + encoding else: msg = "unknown encoding for {!r}: {}".format(filename, encoding) raise SyntaxError(msg) if bom_found: if codec.name != 'utf-8': # This behaviour mimics the Python interpreter if filename is None: msg = 'encoding problem: utf-8' else: msg = 'encoding problem for {!r}: utf-8'.format(filename) raise SyntaxError(msg) encoding += '-sig' return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] default = 'utf-8-sig' if not first: return default, [] encoding = find_cookie(first) if encoding: return encoding, [first] second = read_or_stop() if not second: return default, [first] encoding = find_cookie(second) if encoding: return encoding, [first, second] return default, [first, second] # For converting & <-> & etc. try: from html import escape except ImportError: from cgi import escape if sys.version_info[:2] < (3, 4): unescape = HTMLParser().unescape else: from html import unescape try: from collections import ChainMap except ImportError: # pragma: no cover from collections import MutableMapping try: from reprlib import recursive_repr as _recursive_repr except ImportError: def _recursive_repr(fillvalue='...'): ''' Decorator to make a repr function return fillvalue for a recursive call ''' def decorating_function(user_function): repr_running = set() def wrapper(self): key = id(self), get_ident() if key in repr_running: return fillvalue repr_running.add(key) try: result = user_function(self) finally: repr_running.discard(key) return result # Can't use functools.wraps() here because of bootstrap issues wrapper.__module__ = getattr(user_function, '__module__') wrapper.__doc__ = getattr(user_function, '__doc__') wrapper.__name__ = getattr(user_function, '__name__') wrapper.__annotations__ = getattr(user_function, '__annotations__', {}) return wrapper return decorating_function class ChainMap(MutableMapping): ''' A ChainMap groups multiple dicts (or other mappings) together to create a single, updateable view. The underlying mappings are stored in a list. That list is public and can accessed or updated using the *maps* attribute. There is no other state. Lookups search the underlying mappings successively until a key is found. In contrast, writes, updates, and deletions only operate on the first mapping. ''' def __init__(self, *maps): '''Initialize a ChainMap by setting *maps* to the given mappings. If no mappings are provided, a single empty dictionary is used. ''' self.maps = list(maps) or [{}] # always at least one map def __missing__(self, key): raise KeyError(key) def __getitem__(self, key): for mapping in self.maps: try: return mapping[key] # can't use 'key in mapping' with defaultdict except KeyError: pass return self.__missing__(key) # support subclasses that define __missing__ def get(self, key, default=None): return self[key] if key in self else default def __len__(self): return len(set().union(*self.maps)) # reuses stored hash values if possible def __iter__(self): return iter(set().union(*self.maps)) def __contains__(self, key): return any(key in m for m in self.maps) def __bool__(self): return any(self.maps) @_recursive_repr() def __repr__(self): return '{0.__class__.__name__}({1})'.format( self, ', '.join(map(repr, self.maps))) @classmethod def fromkeys(cls, iterable, *args): 'Create a ChainMap with a single dict created from the iterable.' return cls(dict.fromkeys(iterable, *args)) def copy(self): 'New ChainMap or subclass with a new copy of maps[0] and refs to maps[1:]' return self.__class__(self.maps[0].copy(), *self.maps[1:]) __copy__ = copy def new_child(self): # like Django's Context.push() 'New ChainMap with a new dict followed by all previous maps.' return self.__class__({}, *self.maps) @property def parents(self): # like Django's Context.pop() 'New ChainMap from maps[1:].' return self.__class__(*self.maps[1:]) def __setitem__(self, key, value): self.maps[0][key] = value def __delitem__(self, key): try: del self.maps[0][key] except KeyError: raise KeyError('Key not found in the first mapping: {!r}'.format(key)) def popitem(self): 'Remove and return an item pair from maps[0]. Raise KeyError is maps[0] is empty.' try: return self.maps[0].popitem() except KeyError: raise KeyError('No keys found in the first mapping.') def pop(self, key, *args): 'Remove *key* from maps[0] and return its value. Raise KeyError if *key* not in maps[0].' try: return self.maps[0].pop(key, *args) except KeyError: raise KeyError('Key not found in the first mapping: {!r}'.format(key)) def clear(self): 'Clear maps[0], leaving maps[1:] intact.' self.maps[0].clear() try: from imp import cache_from_source except ImportError: # pragma: no cover def cache_from_source(path, debug_override=None): assert path.endswith('.py') if debug_override is None: debug_override = __debug__ if debug_override: suffix = 'c' else: suffix = 'o' return path + suffix try: from collections import OrderedDict except ImportError: # pragma: no cover ## {{{ http://code.activestate.com/recipes/576693/ (r9) # Backport of OrderedDict() class that runs on Python 2.4, 2.5, 2.6, 2.7 and pypy. # Passes Python2.7's test suite and incorporates all the latest updates. try: from thread import get_ident as _get_ident except ImportError: from dummy_thread import get_ident as _get_ident try: from _abcoll import KeysView, ValuesView, ItemsView except ImportError: pass class OrderedDict(dict): 'Dictionary that remembers insertion order' # An inherited dict maps keys to values. # The inherited dict provides __getitem__, __len__, __contains__, and get. # The remaining methods are order-aware. # Big-O running times for all methods are the same as for regular dictionaries. # The internal self.__map dictionary maps keys to links in a doubly linked list. # The circular doubly linked list starts and ends with a sentinel element. # The sentinel element never gets deleted (this simplifies the algorithm). # Each link is stored as a list of length three: [PREV, NEXT, KEY]. def __init__(self, *args, **kwds): '''Initialize an ordered dictionary. Signature is the same as for regular dictionaries, but keyword arguments are not recommended because their insertion order is arbitrary. ''' if len(args) > 1: raise TypeError('expected at most 1 arguments, got %d' % len(args)) try: self.__root except AttributeError: self.__root = root = [] # sentinel node root[:] = [root, root, None] self.__map = {} self.__update(*args, **kwds) def __setitem__(self, key, value, dict_setitem=dict.__setitem__): 'od.__setitem__(i, y) <==> od[i]=y' # Setting a new item creates a new link which goes at the end of the linked # list, and the inherited dictionary is updated with the new key/value pair. if key not in self: root = self.__root last = root[0] last[1] = root[0] = self.__map[key] = [last, root, key] dict_setitem(self, key, value) def __delitem__(self, key, dict_delitem=dict.__delitem__): 'od.__delitem__(y) <==> del od[y]' # Deleting an existing item uses self.__map to find the link which is # then removed by updating the links in the predecessor and successor nodes. dict_delitem(self, key) link_prev, link_next, key = self.__map.pop(key) link_prev[1] = link_next link_next[0] = link_prev def __iter__(self): 'od.__iter__() <==> iter(od)' root = self.__root curr = root[1] while curr is not root: yield curr[2] curr = curr[1] def __reversed__(self): 'od.__reversed__() <==> reversed(od)' root = self.__root curr = root[0] while curr is not root: yield curr[2] curr = curr[0] def clear(self): 'od.clear() -> None. Remove all items from od.' try: for node in self.__map.itervalues(): del node[:] root = self.__root root[:] = [root, root, None] self.__map.clear() except AttributeError: pass dict.clear(self) def popitem(self, last=True): '''od.popitem() -> (k, v), return and remove a (key, value) pair. Pairs are returned in LIFO order if last is true or FIFO order if false. ''' if not self: raise KeyError('dictionary is empty') root = self.__root if last: link = root[0] link_prev = link[0] link_prev[1] = root root[0] = link_prev else: link = root[1] link_next = link[1] root[1] = link_next link_next[0] = root key = link[2] del self.__map[key] value = dict.pop(self, key) return key, value # -- the following methods do not depend on the internal structure -- def keys(self): 'od.keys() -> list of keys in od' return list(self) def values(self): 'od.values() -> list of values in od' return [self[key] for key in self] def items(self): 'od.items() -> list of (key, value) pairs in od' return [(key, self[key]) for key in self] def iterkeys(self): 'od.iterkeys() -> an iterator over the keys in od' return iter(self) def itervalues(self): 'od.itervalues -> an iterator over the values in od' for k in self: yield self[k] def iteritems(self): 'od.iteritems -> an iterator over the (key, value) items in od' for k in self: yield (k, self[k]) def update(*args, **kwds): '''od.update(E, **F) -> None. Update od from dict/iterable E and F. If E is a dict instance, does: for k in E: od[k] = E[k] If E has a .keys() method, does: for k in E.keys(): od[k] = E[k] Or if E is an iterable of items, does: for k, v in E: od[k] = v In either case, this is followed by: for k, v in F.items(): od[k] = v ''' if len(args) > 2: raise TypeError('update() takes at most 2 positional ' 'arguments (%d given)' % (len(args),)) elif not args: raise TypeError('update() takes at least 1 argument (0 given)') self = args[0] # Make progressively weaker assumptions about "other" other = () if len(args) == 2: other = args[1] if isinstance(other, dict): for key in other: self[key] = other[key] elif hasattr(other, 'keys'): for key in other.keys(): self[key] = other[key] else: for key, value in other: self[key] = value for key, value in kwds.items(): self[key] = value __update = update # let subclasses override update without breaking __init__ __marker = object() def pop(self, key, default=__marker): '''od.pop(k[,d]) -> v, remove specified key and return the corresponding value. If key is not found, d is returned if given, otherwise KeyError is raised. ''' if key in self: result = self[key] del self[key] return result if default is self.__marker: raise KeyError(key) return default def setdefault(self, key, default=None): 'od.setdefault(k[,d]) -> od.get(k,d), also set od[k]=d if k not in od' if key in self: return self[key] self[key] = default return default def __repr__(self, _repr_running=None): 'od.__repr__() <==> repr(od)' if not _repr_running: _repr_running = {} call_key = id(self), _get_ident() if call_key in _repr_running: return '...' _repr_running[call_key] = 1 try: if not self: return '%s()' % (self.__class__.__name__,) return '%s(%r)' % (self.__class__.__name__, self.items()) finally: del _repr_running[call_key] def __reduce__(self): 'Return state information for pickling' items = [[k, self[k]] for k in self] inst_dict = vars(self).copy() for k in vars(OrderedDict()): inst_dict.pop(k, None) if inst_dict: return (self.__class__, (items,), inst_dict) return self.__class__, (items,) def copy(self): 'od.copy() -> a shallow copy of od' return self.__class__(self) @classmethod def fromkeys(cls, iterable, value=None): '''OD.fromkeys(S[, v]) -> New ordered dictionary with keys from S and values equal to v (which defaults to None). ''' d = cls() for key in iterable: d[key] = value return d def __eq__(self, other): '''od.__eq__(y) <==> od==y. Comparison to another OD is order-sensitive while comparison to a regular mapping is order-insensitive. ''' if isinstance(other, OrderedDict): return len(self)==len(other) and self.items() == other.items() return dict.__eq__(self, other) def __ne__(self, other): return not self == other # -- the following methods are only used in Python 2.7 -- def viewkeys(self): "od.viewkeys() -> a set-like object providing a view on od's keys" return KeysView(self) def viewvalues(self): "od.viewvalues() -> an object providing a view on od's values" return ValuesView(self) def viewitems(self): "od.viewitems() -> a set-like object providing a view on od's items" return ItemsView(self) try: from logging.config import BaseConfigurator, valid_ident except ImportError: # pragma: no cover IDENTIFIER = re.compile('^[a-z_][a-z0-9_]*$', re.I) def valid_ident(s): m = IDENTIFIER.match(s) if not m: raise ValueError('Not a valid Python identifier: %r' % s) return True # The ConvertingXXX classes are wrappers around standard Python containers, # and they serve to convert any suitable values in the container. The # conversion converts base dicts, lists and tuples to their wrapped # equivalents, whereas strings which match a conversion format are converted # appropriately. # # Each wrapper should have a configurator attribute holding the actual # configurator to use for conversion. class ConvertingDict(dict): """A converting dictionary wrapper.""" def __getitem__(self, key): value = dict.__getitem__(self, key) result = self.configurator.convert(value) #If the converted value is different, save for next time if value is not result: self[key] = result if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self result.key = key return result def get(self, key, default=None): value = dict.get(self, key, default) result = self.configurator.convert(value) #If the converted value is different, save for next time if value is not result: self[key] = result if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self result.key = key return result def pop(self, key, default=None): value = dict.pop(self, key, default) result = self.configurator.convert(value) if value is not result: if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self result.key = key return result class ConvertingList(list): """A converting list wrapper.""" def __getitem__(self, key): value = list.__getitem__(self, key) result = self.configurator.convert(value) #If the converted value is different, save for next time if value is not result: self[key] = result if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self result.key = key return result def pop(self, idx=-1): value = list.pop(self, idx) result = self.configurator.convert(value) if value is not result: if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self return result class ConvertingTuple(tuple): """A converting tuple wrapper.""" def __getitem__(self, key): value = tuple.__getitem__(self, key) result = self.configurator.convert(value) if value is not result: if type(result) in (ConvertingDict, ConvertingList, ConvertingTuple): result.parent = self result.key = key return result class BaseConfigurator(object): """ The configurator base class which defines some useful defaults. """ CONVERT_PATTERN = re.compile(r'^(?P[a-z]+)://(?P.*)$') WORD_PATTERN = re.compile(r'^\s*(\w+)\s*') DOT_PATTERN = re.compile(r'^\.\s*(\w+)\s*') INDEX_PATTERN = re.compile(r'^\[\s*(\w+)\s*\]\s*') DIGIT_PATTERN = re.compile(r'^\d+$') value_converters = { 'ext' : 'ext_convert', 'cfg' : 'cfg_convert', } # We might want to use a different one, e.g. importlib importer = staticmethod(__import__) def __init__(self, config): self.config = ConvertingDict(config) self.config.configurator = self def resolve(self, s): """ Resolve strings to objects using standard import and attribute syntax. """ name = s.split('.') used = name.pop(0) try: found = self.importer(used) for frag in name: used += '.' + frag try: found = getattr(found, frag) except AttributeError: self.importer(used) found = getattr(found, frag) return found except ImportError: e, tb = sys.exc_info()[1:] v = ValueError('Cannot resolve %r: %s' % (s, e)) v.__cause__, v.__traceback__ = e, tb raise v def ext_convert(self, value): """Default converter for the ext:// protocol.""" return self.resolve(value) def cfg_convert(self, value): """Default converter for the cfg:// protocol.""" rest = value m = self.WORD_PATTERN.match(rest) if m is None: raise ValueError("Unable to convert %r" % value) else: rest = rest[m.end():] d = self.config[m.groups()[0]] #print d, rest while rest: m = self.DOT_PATTERN.match(rest) if m: d = d[m.groups()[0]] else: m = self.INDEX_PATTERN.match(rest) if m: idx = m.groups()[0] if not self.DIGIT_PATTERN.match(idx): d = d[idx] else: try: n = int(idx) # try as number first (most likely) d = d[n] except TypeError: d = d[idx] if m: rest = rest[m.end():] else: raise ValueError('Unable to convert ' '%r at %r' % (value, rest)) #rest should be empty return d def convert(self, value): """ Convert values to an appropriate type. dicts, lists and tuples are replaced by their converting alternatives. Strings are checked to see if they have a conversion format and are converted if they do. """ if not isinstance(value, ConvertingDict) and isinstance(value, dict): value = ConvertingDict(value) value.configurator = self elif not isinstance(value, ConvertingList) and isinstance(value, list): value = ConvertingList(value) value.configurator = self elif not isinstance(value, ConvertingTuple) and\ isinstance(value, tuple): value = ConvertingTuple(value) value.configurator = self elif isinstance(value, string_types): m = self.CONVERT_PATTERN.match(value) if m: d = m.groupdict() prefix = d['prefix'] converter = self.value_converters.get(prefix, None) if converter: suffix = d['suffix'] converter = getattr(self, converter) value = converter(suffix) return value def configure_custom(self, config): """Configure an object with a user-supplied factory.""" c = config.pop('()') if not callable(c): c = self.resolve(c) props = config.pop('.', None) # Check for valid identifiers kwargs = dict([(k, config[k]) for k in config if valid_ident(k)]) result = c(**kwargs) if props: for name, value in props.items(): setattr(result, name, value) return result def as_tuple(self, value): """Utility function which converts lists to tuples.""" if isinstance(value, list): value = tuple(value) return value feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/database.py0000644000076500000240000014100712700725533030456 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012-2016 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """PEP 376 implementation.""" from __future__ import unicode_literals import base64 import codecs import contextlib import hashlib import logging import os import posixpath import sys import zipimport from . import DistlibException, resources from .compat import StringIO from .version import get_scheme, UnsupportedVersionError from .metadata import Metadata, METADATA_FILENAME, WHEEL_METADATA_FILENAME from .util import (parse_requirement, cached_property, parse_name_and_version, read_exports, write_exports, CSVReader, CSVWriter) __all__ = ['Distribution', 'BaseInstalledDistribution', 'InstalledDistribution', 'EggInfoDistribution', 'DistributionPath'] logger = logging.getLogger(__name__) EXPORTS_FILENAME = 'pydist-exports.json' COMMANDS_FILENAME = 'pydist-commands.json' DIST_FILES = ('INSTALLER', METADATA_FILENAME, 'RECORD', 'REQUESTED', 'RESOURCES', EXPORTS_FILENAME, 'SHARED') DISTINFO_EXT = '.dist-info' class _Cache(object): """ A simple cache mapping names and .dist-info paths to distributions """ def __init__(self): """ Initialise an instance. There is normally one for each DistributionPath. """ self.name = {} self.path = {} self.generated = False def clear(self): """ Clear the cache, setting it to its initial state. """ self.name.clear() self.path.clear() self.generated = False def add(self, dist): """ Add a distribution to the cache. :param dist: The distribution to add. """ if dist.path not in self.path: self.path[dist.path] = dist self.name.setdefault(dist.key, []).append(dist) class DistributionPath(object): """ Represents a set of distributions installed on a path (typically sys.path). """ def __init__(self, path=None, include_egg=False): """ Create an instance from a path, optionally including legacy (distutils/ setuptools/distribute) distributions. :param path: The path to use, as a list of directories. If not specified, sys.path is used. :param include_egg: If True, this instance will look for and return legacy distributions as well as those based on PEP 376. """ if path is None: path = sys.path self.path = path self._include_dist = True self._include_egg = include_egg self._cache = _Cache() self._cache_egg = _Cache() self._cache_enabled = True self._scheme = get_scheme('default') def _get_cache_enabled(self): return self._cache_enabled def _set_cache_enabled(self, value): self._cache_enabled = value cache_enabled = property(_get_cache_enabled, _set_cache_enabled) def clear_cache(self): """ Clears the internal cache. """ self._cache.clear() self._cache_egg.clear() def _yield_distributions(self): """ Yield .dist-info and/or .egg(-info) distributions. """ # We need to check if we've seen some resources already, because on # some Linux systems (e.g. some Debian/Ubuntu variants) there are # symlinks which alias other files in the environment. seen = set() for path in self.path: finder = resources.finder_for_path(path) if finder is None: continue r = finder.find('') if not r or not r.is_container: continue rset = sorted(r.resources) for entry in rset: r = finder.find(entry) if not r or r.path in seen: continue if self._include_dist and entry.endswith(DISTINFO_EXT): possible_filenames = [METADATA_FILENAME, WHEEL_METADATA_FILENAME] for metadata_filename in possible_filenames: metadata_path = posixpath.join(entry, metadata_filename) pydist = finder.find(metadata_path) if pydist: break else: continue with contextlib.closing(pydist.as_stream()) as stream: metadata = Metadata(fileobj=stream, scheme='legacy') logger.debug('Found %s', r.path) seen.add(r.path) yield new_dist_class(r.path, metadata=metadata, env=self) elif self._include_egg and entry.endswith(('.egg-info', '.egg')): logger.debug('Found %s', r.path) seen.add(r.path) yield old_dist_class(r.path, self) def _generate_cache(self): """ Scan the path for distributions and populate the cache with those that are found. """ gen_dist = not self._cache.generated gen_egg = self._include_egg and not self._cache_egg.generated if gen_dist or gen_egg: for dist in self._yield_distributions(): if isinstance(dist, InstalledDistribution): self._cache.add(dist) else: self._cache_egg.add(dist) if gen_dist: self._cache.generated = True if gen_egg: self._cache_egg.generated = True @classmethod def distinfo_dirname(cls, name, version): """ The *name* and *version* parameters are converted into their filename-escaped form, i.e. any ``'-'`` characters are replaced with ``'_'`` other than the one in ``'dist-info'`` and the one separating the name from the version number. :parameter name: is converted to a standard distribution name by replacing any runs of non- alphanumeric characters with a single ``'-'``. :type name: string :parameter version: is converted to a standard version string. Spaces become dots, and all other non-alphanumeric characters (except dots) become dashes, with runs of multiple dashes condensed to a single dash. :type version: string :returns: directory name :rtype: string""" name = name.replace('-', '_') return '-'.join([name, version]) + DISTINFO_EXT def get_distributions(self): """ Provides an iterator that looks for distributions and returns :class:`InstalledDistribution` or :class:`EggInfoDistribution` instances for each one of them. :rtype: iterator of :class:`InstalledDistribution` and :class:`EggInfoDistribution` instances """ if not self._cache_enabled: for dist in self._yield_distributions(): yield dist else: self._generate_cache() for dist in self._cache.path.values(): yield dist if self._include_egg: for dist in self._cache_egg.path.values(): yield dist def get_distribution(self, name): """ Looks for a named distribution on the path. This function only returns the first result found, as no more than one value is expected. If nothing is found, ``None`` is returned. :rtype: :class:`InstalledDistribution`, :class:`EggInfoDistribution` or ``None`` """ result = None name = name.lower() if not self._cache_enabled: for dist in self._yield_distributions(): if dist.key == name: result = dist break else: self._generate_cache() if name in self._cache.name: result = self._cache.name[name][0] elif self._include_egg and name in self._cache_egg.name: result = self._cache_egg.name[name][0] return result def provides_distribution(self, name, version=None): """ Iterates over all distributions to find which distributions provide *name*. If a *version* is provided, it will be used to filter the results. This function only returns the first result found, since no more than one values are expected. If the directory is not found, returns ``None``. :parameter version: a version specifier that indicates the version required, conforming to the format in ``PEP-345`` :type name: string :type version: string """ matcher = None if not version is None: try: matcher = self._scheme.matcher('%s (%s)' % (name, version)) except ValueError: raise DistlibException('invalid name or version: %r, %r' % (name, version)) for dist in self.get_distributions(): provided = dist.provides for p in provided: p_name, p_ver = parse_name_and_version(p) if matcher is None: if p_name == name: yield dist break else: if p_name == name and matcher.match(p_ver): yield dist break def get_file_path(self, name, relative_path): """ Return the path to a resource file. """ dist = self.get_distribution(name) if dist is None: raise LookupError('no distribution named %r found' % name) return dist.get_resource_path(relative_path) def get_exported_entries(self, category, name=None): """ Return all of the exported entries in a particular category. :param category: The category to search for entries. :param name: If specified, only entries with that name are returned. """ for dist in self.get_distributions(): r = dist.exports if category in r: d = r[category] if name is not None: if name in d: yield d[name] else: for v in d.values(): yield v class Distribution(object): """ A base class for distributions, whether installed or from indexes. Either way, it must have some metadata, so that's all that's needed for construction. """ build_time_dependency = False """ Set to True if it's known to be only a build-time dependency (i.e. not needed after installation). """ requested = False """A boolean that indicates whether the ``REQUESTED`` metadata file is present (in other words, whether the package was installed by user request or it was installed as a dependency).""" def __init__(self, metadata): """ Initialise an instance. :param metadata: The instance of :class:`Metadata` describing this distribution. """ self.metadata = metadata self.name = metadata.name self.key = self.name.lower() # for case-insensitive comparisons self.version = metadata.version self.locator = None self.digest = None self.extras = None # additional features requested self.context = None # environment marker overrides self.download_urls = set() self.digests = {} @property def source_url(self): """ The source archive download URL for this distribution. """ return self.metadata.source_url download_url = source_url # Backward compatibility @property def name_and_version(self): """ A utility property which displays the name and version in parentheses. """ return '%s (%s)' % (self.name, self.version) @property def provides(self): """ A set of distribution names and versions provided by this distribution. :return: A set of "name (version)" strings. """ plist = self.metadata.provides s = '%s (%s)' % (self.name, self.version) if s not in plist: plist.append(s) return plist def _get_requirements(self, req_attr): md = self.metadata logger.debug('Getting requirements from metadata %r', md.todict()) reqts = getattr(md, req_attr) return set(md.get_requirements(reqts, extras=self.extras, env=self.context)) @property def run_requires(self): return self._get_requirements('run_requires') @property def meta_requires(self): return self._get_requirements('meta_requires') @property def build_requires(self): return self._get_requirements('build_requires') @property def test_requires(self): return self._get_requirements('test_requires') @property def dev_requires(self): return self._get_requirements('dev_requires') def matches_requirement(self, req): """ Say if this instance matches (fulfills) a requirement. :param req: The requirement to match. :rtype req: str :return: True if it matches, else False. """ # Requirement may contain extras - parse to lose those # from what's passed to the matcher r = parse_requirement(req) scheme = get_scheme(self.metadata.scheme) try: matcher = scheme.matcher(r.requirement) except UnsupportedVersionError: # XXX compat-mode if cannot read the version logger.warning('could not read version %r - using name only', req) name = req.split()[0] matcher = scheme.matcher(name) name = matcher.key # case-insensitive result = False for p in self.provides: p_name, p_ver = parse_name_and_version(p) if p_name != name: continue try: result = matcher.match(p_ver) break except UnsupportedVersionError: pass return result def __repr__(self): """ Return a textual representation of this instance, """ if self.source_url: suffix = ' [%s]' % self.source_url else: suffix = '' return '' % (self.name, self.version, suffix) def __eq__(self, other): """ See if this distribution is the same as another. :param other: The distribution to compare with. To be equal to one another. distributions must have the same type, name, version and source_url. :return: True if it is the same, else False. """ if type(other) is not type(self): result = False else: result = (self.name == other.name and self.version == other.version and self.source_url == other.source_url) return result def __hash__(self): """ Compute hash in a way which matches the equality test. """ return hash(self.name) + hash(self.version) + hash(self.source_url) class BaseInstalledDistribution(Distribution): """ This is the base class for installed distributions (whether PEP 376 or legacy). """ hasher = None def __init__(self, metadata, path, env=None): """ Initialise an instance. :param metadata: An instance of :class:`Metadata` which describes the distribution. This will normally have been initialised from a metadata file in the ``path``. :param path: The path of the ``.dist-info`` or ``.egg-info`` directory for the distribution. :param env: This is normally the :class:`DistributionPath` instance where this distribution was found. """ super(BaseInstalledDistribution, self).__init__(metadata) self.path = path self.dist_path = env def get_hash(self, data, hasher=None): """ Get the hash of some data, using a particular hash algorithm, if specified. :param data: The data to be hashed. :type data: bytes :param hasher: The name of a hash implementation, supported by hashlib, or ``None``. Examples of valid values are ``'sha1'``, ``'sha224'``, ``'sha384'``, '``sha256'``, ``'md5'`` and ``'sha512'``. If no hasher is specified, the ``hasher`` attribute of the :class:`InstalledDistribution` instance is used. If the hasher is determined to be ``None``, MD5 is used as the hashing algorithm. :returns: The hash of the data. If a hasher was explicitly specified, the returned hash will be prefixed with the specified hasher followed by '='. :rtype: str """ if hasher is None: hasher = self.hasher if hasher is None: hasher = hashlib.md5 prefix = '' else: hasher = getattr(hashlib, hasher) prefix = '%s=' % self.hasher digest = hasher(data).digest() digest = base64.urlsafe_b64encode(digest).rstrip(b'=').decode('ascii') return '%s%s' % (prefix, digest) class InstalledDistribution(BaseInstalledDistribution): """ Created with the *path* of the ``.dist-info`` directory provided to the constructor. It reads the metadata contained in ``pydist.json`` when it is instantiated., or uses a passed in Metadata instance (useful for when dry-run mode is being used). """ hasher = 'sha256' def __init__(self, path, metadata=None, env=None): self.finder = finder = resources.finder_for_path(path) if finder is None: import pdb; pdb.set_trace () if env and env._cache_enabled and path in env._cache.path: metadata = env._cache.path[path].metadata elif metadata is None: r = finder.find(METADATA_FILENAME) # Temporary - for Wheel 0.23 support if r is None: r = finder.find(WHEEL_METADATA_FILENAME) # Temporary - for legacy support if r is None: r = finder.find('METADATA') if r is None: raise ValueError('no %s found in %s' % (METADATA_FILENAME, path)) with contextlib.closing(r.as_stream()) as stream: metadata = Metadata(fileobj=stream, scheme='legacy') super(InstalledDistribution, self).__init__(metadata, path, env) if env and env._cache_enabled: env._cache.add(self) try: r = finder.find('REQUESTED') except AttributeError: import pdb; pdb.set_trace () self.requested = r is not None def __repr__(self): return '' % ( self.name, self.version, self.path) def __str__(self): return "%s %s" % (self.name, self.version) def _get_records(self): """ Get the list of installed files for the distribution :return: A list of tuples of path, hash and size. Note that hash and size might be ``None`` for some entries. The path is exactly as stored in the file (which is as in PEP 376). """ results = [] r = self.get_distinfo_resource('RECORD') with contextlib.closing(r.as_stream()) as stream: with CSVReader(stream=stream) as record_reader: # Base location is parent dir of .dist-info dir #base_location = os.path.dirname(self.path) #base_location = os.path.abspath(base_location) for row in record_reader: missing = [None for i in range(len(row), 3)] path, checksum, size = row + missing #if not os.path.isabs(path): # path = path.replace('/', os.sep) # path = os.path.join(base_location, path) results.append((path, checksum, size)) return results @cached_property def exports(self): """ Return the information exported by this distribution. :return: A dictionary of exports, mapping an export category to a dict of :class:`ExportEntry` instances describing the individual export entries, and keyed by name. """ result = {} r = self.get_distinfo_resource(EXPORTS_FILENAME) if r: result = self.read_exports() return result def read_exports(self): """ Read exports data from a file in .ini format. :return: A dictionary of exports, mapping an export category to a list of :class:`ExportEntry` instances describing the individual export entries. """ result = {} r = self.get_distinfo_resource(EXPORTS_FILENAME) if r: with contextlib.closing(r.as_stream()) as stream: result = read_exports(stream) return result def write_exports(self, exports): """ Write a dictionary of exports to a file in .ini format. :param exports: A dictionary of exports, mapping an export category to a list of :class:`ExportEntry` instances describing the individual export entries. """ rf = self.get_distinfo_file(EXPORTS_FILENAME) with open(rf, 'w') as f: write_exports(exports, f) def get_resource_path(self, relative_path): """ NOTE: This API may change in the future. Return the absolute path to a resource file with the given relative path. :param relative_path: The path, relative to .dist-info, of the resource of interest. :return: The absolute path where the resource is to be found. """ r = self.get_distinfo_resource('RESOURCES') with contextlib.closing(r.as_stream()) as stream: with CSVReader(stream=stream) as resources_reader: for relative, destination in resources_reader: if relative == relative_path: return destination raise KeyError('no resource file with relative path %r ' 'is installed' % relative_path) def list_installed_files(self): """ Iterates over the ``RECORD`` entries and returns a tuple ``(path, hash, size)`` for each line. :returns: iterator of (path, hash, size) """ for result in self._get_records(): yield result def write_installed_files(self, paths, prefix, dry_run=False): """ Writes the ``RECORD`` file, using the ``paths`` iterable passed in. Any existing ``RECORD`` file is silently overwritten. prefix is used to determine when to write absolute paths. """ prefix = os.path.join(prefix, '') base = os.path.dirname(self.path) base_under_prefix = base.startswith(prefix) base = os.path.join(base, '') record_path = self.get_distinfo_file('RECORD') logger.info('creating %s', record_path) if dry_run: return None with CSVWriter(record_path) as writer: for path in paths: if os.path.isdir(path) or path.endswith(('.pyc', '.pyo')): # do not put size and hash, as in PEP-376 hash_value = size = '' else: size = '%d' % os.path.getsize(path) with open(path, 'rb') as fp: hash_value = self.get_hash(fp.read()) if path.startswith(base) or (base_under_prefix and path.startswith(prefix)): path = os.path.relpath(path, base) writer.writerow((path, hash_value, size)) # add the RECORD file itself if record_path.startswith(base): record_path = os.path.relpath(record_path, base) writer.writerow((record_path, '', '')) return record_path def check_installed_files(self): """ Checks that the hashes and sizes of the files in ``RECORD`` are matched by the files themselves. Returns a (possibly empty) list of mismatches. Each entry in the mismatch list will be a tuple consisting of the path, 'exists', 'size' or 'hash' according to what didn't match (existence is checked first, then size, then hash), the expected value and the actual value. """ mismatches = [] base = os.path.dirname(self.path) record_path = self.get_distinfo_file('RECORD') for path, hash_value, size in self.list_installed_files(): if not os.path.isabs(path): path = os.path.join(base, path) if path == record_path: continue if not os.path.exists(path): mismatches.append((path, 'exists', True, False)) elif os.path.isfile(path): actual_size = str(os.path.getsize(path)) if size and actual_size != size: mismatches.append((path, 'size', size, actual_size)) elif hash_value: if '=' in hash_value: hasher = hash_value.split('=', 1)[0] else: hasher = None with open(path, 'rb') as f: actual_hash = self.get_hash(f.read(), hasher) if actual_hash != hash_value: mismatches.append((path, 'hash', hash_value, actual_hash)) return mismatches @cached_property def shared_locations(self): """ A dictionary of shared locations whose keys are in the set 'prefix', 'purelib', 'platlib', 'scripts', 'headers', 'data' and 'namespace'. The corresponding value is the absolute path of that category for this distribution, and takes into account any paths selected by the user at installation time (e.g. via command-line arguments). In the case of the 'namespace' key, this would be a list of absolute paths for the roots of namespace packages in this distribution. The first time this property is accessed, the relevant information is read from the SHARED file in the .dist-info directory. """ result = {} shared_path = os.path.join(self.path, 'SHARED') if os.path.isfile(shared_path): with codecs.open(shared_path, 'r', encoding='utf-8') as f: lines = f.read().splitlines() for line in lines: key, value = line.split('=', 1) if key == 'namespace': result.setdefault(key, []).append(value) else: result[key] = value return result def write_shared_locations(self, paths, dry_run=False): """ Write shared location information to the SHARED file in .dist-info. :param paths: A dictionary as described in the documentation for :meth:`shared_locations`. :param dry_run: If True, the action is logged but no file is actually written. :return: The path of the file written to. """ shared_path = os.path.join(self.path, 'SHARED') logger.info('creating %s', shared_path) if dry_run: return None lines = [] for key in ('prefix', 'lib', 'headers', 'scripts', 'data'): path = paths[key] if os.path.isdir(paths[key]): lines.append('%s=%s' % (key, path)) for ns in paths.get('namespace', ()): lines.append('namespace=%s' % ns) with codecs.open(shared_path, 'w', encoding='utf-8') as f: f.write('\n'.join(lines)) return shared_path def get_distinfo_resource(self, path): if path not in DIST_FILES: raise DistlibException('invalid path for a dist-info file: ' '%r at %r' % (path, self.path)) finder = resources.finder_for_path(self.path) if finder is None: raise DistlibException('Unable to get a finder for %s' % self.path) return finder.find(path) def get_distinfo_file(self, path): """ Returns a path located under the ``.dist-info`` directory. Returns a string representing the path. :parameter path: a ``'/'``-separated path relative to the ``.dist-info`` directory or an absolute path; If *path* is an absolute path and doesn't start with the ``.dist-info`` directory path, a :class:`DistlibException` is raised :type path: str :rtype: str """ # Check if it is an absolute path # XXX use relpath, add tests if path.find(os.sep) >= 0: # it's an absolute path? distinfo_dirname, path = path.split(os.sep)[-2:] if distinfo_dirname != self.path.split(os.sep)[-1]: raise DistlibException( 'dist-info file %r does not belong to the %r %s ' 'distribution' % (path, self.name, self.version)) # The file must be relative if path not in DIST_FILES: raise DistlibException('invalid path for a dist-info file: ' '%r at %r' % (path, self.path)) return os.path.join(self.path, path) def list_distinfo_files(self): """ Iterates over the ``RECORD`` entries and returns paths for each line if the path is pointing to a file located in the ``.dist-info`` directory or one of its subdirectories. :returns: iterator of paths """ base = os.path.dirname(self.path) for path, checksum, size in self._get_records(): # XXX add separator or use real relpath algo if not os.path.isabs(path): path = os.path.join(base, path) if path.startswith(self.path): yield path def __eq__(self, other): return (isinstance(other, InstalledDistribution) and self.path == other.path) # See http://docs.python.org/reference/datamodel#object.__hash__ __hash__ = object.__hash__ class EggInfoDistribution(BaseInstalledDistribution): """Created with the *path* of the ``.egg-info`` directory or file provided to the constructor. It reads the metadata contained in the file itself, or if the given path happens to be a directory, the metadata is read from the file ``PKG-INFO`` under that directory.""" requested = True # as we have no way of knowing, assume it was shared_locations = {} def __init__(self, path, env=None): def set_name_and_version(s, n, v): s.name = n s.key = n.lower() # for case-insensitive comparisons s.version = v self.path = path self.dist_path = env if env and env._cache_enabled and path in env._cache_egg.path: metadata = env._cache_egg.path[path].metadata set_name_and_version(self, metadata.name, metadata.version) else: metadata = self._get_metadata(path) # Need to be set before caching set_name_and_version(self, metadata.name, metadata.version) if env and env._cache_enabled: env._cache_egg.add(self) super(EggInfoDistribution, self).__init__(metadata, path, env) def _get_metadata(self, path): requires = None def parse_requires_data(data): """Create a list of dependencies from a requires.txt file. *data*: the contents of a setuptools-produced requires.txt file. """ reqs = [] lines = data.splitlines() for line in lines: line = line.strip() if line.startswith('['): logger.warning('Unexpected line: quitting requirement scan: %r', line) break r = parse_requirement(line) if not r: logger.warning('Not recognised as a requirement: %r', line) continue if r.extras: logger.warning('extra requirements in requires.txt are ' 'not supported') if not r.constraints: reqs.append(r.name) else: cons = ', '.join('%s%s' % c for c in r.constraints) reqs.append('%s (%s)' % (r.name, cons)) return reqs def parse_requires_path(req_path): """Create a list of dependencies from a requires.txt file. *req_path*: the path to a setuptools-produced requires.txt file. """ reqs = [] try: with codecs.open(req_path, 'r', 'utf-8') as fp: reqs = parse_requires_data(fp.read()) except IOError: pass return reqs if path.endswith('.egg'): if os.path.isdir(path): meta_path = os.path.join(path, 'EGG-INFO', 'PKG-INFO') metadata = Metadata(path=meta_path, scheme='legacy') req_path = os.path.join(path, 'EGG-INFO', 'requires.txt') requires = parse_requires_path(req_path) else: # FIXME handle the case where zipfile is not available zipf = zipimport.zipimporter(path) fileobj = StringIO( zipf.get_data('EGG-INFO/PKG-INFO').decode('utf8')) metadata = Metadata(fileobj=fileobj, scheme='legacy') try: data = zipf.get_data('EGG-INFO/requires.txt') requires = parse_requires_data(data.decode('utf-8')) except IOError: requires = None elif path.endswith('.egg-info'): if os.path.isdir(path): req_path = os.path.join(path, 'requires.txt') requires = parse_requires_path(req_path) path = os.path.join(path, 'PKG-INFO') metadata = Metadata(path=path, scheme='legacy') else: raise DistlibException('path must end with .egg-info or .egg, ' 'got %r' % path) if requires: metadata.add_requirements(requires) return metadata def __repr__(self): return '' % ( self.name, self.version, self.path) def __str__(self): return "%s %s" % (self.name, self.version) def check_installed_files(self): """ Checks that the hashes and sizes of the files in ``RECORD`` are matched by the files themselves. Returns a (possibly empty) list of mismatches. Each entry in the mismatch list will be a tuple consisting of the path, 'exists', 'size' or 'hash' according to what didn't match (existence is checked first, then size, then hash), the expected value and the actual value. """ mismatches = [] record_path = os.path.join(self.path, 'installed-files.txt') if os.path.exists(record_path): for path, _, _ in self.list_installed_files(): if path == record_path: continue if not os.path.exists(path): mismatches.append((path, 'exists', True, False)) return mismatches def list_installed_files(self): """ Iterates over the ``installed-files.txt`` entries and returns a tuple ``(path, hash, size)`` for each line. :returns: a list of (path, hash, size) """ def _md5(path): f = open(path, 'rb') try: content = f.read() finally: f.close() return hashlib.md5(content).hexdigest() def _size(path): return os.stat(path).st_size record_path = os.path.join(self.path, 'installed-files.txt') result = [] if os.path.exists(record_path): with codecs.open(record_path, 'r', encoding='utf-8') as f: for line in f: line = line.strip() p = os.path.normpath(os.path.join(self.path, line)) # "./" is present as a marker between installed files # and installation metadata files if not os.path.exists(p): logger.warning('Non-existent file: %s', p) if p.endswith(('.pyc', '.pyo')): continue #otherwise fall through and fail if not os.path.isdir(p): result.append((p, _md5(p), _size(p))) result.append((record_path, None, None)) return result def list_distinfo_files(self, absolute=False): """ Iterates over the ``installed-files.txt`` entries and returns paths for each line if the path is pointing to a file located in the ``.egg-info`` directory or one of its subdirectories. :parameter absolute: If *absolute* is ``True``, each returned path is transformed into a local absolute path. Otherwise the raw value from ``installed-files.txt`` is returned. :type absolute: boolean :returns: iterator of paths """ record_path = os.path.join(self.path, 'installed-files.txt') skip = True with codecs.open(record_path, 'r', encoding='utf-8') as f: for line in f: line = line.strip() if line == './': skip = False continue if not skip: p = os.path.normpath(os.path.join(self.path, line)) if p.startswith(self.path): if absolute: yield p else: yield line def __eq__(self, other): return (isinstance(other, EggInfoDistribution) and self.path == other.path) # See http://docs.python.org/reference/datamodel#object.__hash__ __hash__ = object.__hash__ new_dist_class = InstalledDistribution old_dist_class = EggInfoDistribution class DependencyGraph(object): """ Represents a dependency graph between distributions. The dependency relationships are stored in an ``adjacency_list`` that maps distributions to a list of ``(other, label)`` tuples where ``other`` is a distribution and the edge is labeled with ``label`` (i.e. the version specifier, if such was provided). Also, for more efficient traversal, for every distribution ``x``, a list of predecessors is kept in ``reverse_list[x]``. An edge from distribution ``a`` to distribution ``b`` means that ``a`` depends on ``b``. If any missing dependencies are found, they are stored in ``missing``, which is a dictionary that maps distributions to a list of requirements that were not provided by any other distributions. """ def __init__(self): self.adjacency_list = {} self.reverse_list = {} self.missing = {} def add_distribution(self, distribution): """Add the *distribution* to the graph. :type distribution: :class:`distutils2.database.InstalledDistribution` or :class:`distutils2.database.EggInfoDistribution` """ self.adjacency_list[distribution] = [] self.reverse_list[distribution] = [] #self.missing[distribution] = [] def add_edge(self, x, y, label=None): """Add an edge from distribution *x* to distribution *y* with the given *label*. :type x: :class:`distutils2.database.InstalledDistribution` or :class:`distutils2.database.EggInfoDistribution` :type y: :class:`distutils2.database.InstalledDistribution` or :class:`distutils2.database.EggInfoDistribution` :type label: ``str`` or ``None`` """ self.adjacency_list[x].append((y, label)) # multiple edges are allowed, so be careful if x not in self.reverse_list[y]: self.reverse_list[y].append(x) def add_missing(self, distribution, requirement): """ Add a missing *requirement* for the given *distribution*. :type distribution: :class:`distutils2.database.InstalledDistribution` or :class:`distutils2.database.EggInfoDistribution` :type requirement: ``str`` """ logger.debug('%s missing %r', distribution, requirement) self.missing.setdefault(distribution, []).append(requirement) def _repr_dist(self, dist): return '%s %s' % (dist.name, dist.version) def repr_node(self, dist, level=1): """Prints only a subgraph""" output = [self._repr_dist(dist)] for other, label in self.adjacency_list[dist]: dist = self._repr_dist(other) if label is not None: dist = '%s [%s]' % (dist, label) output.append(' ' * level + str(dist)) suboutput = self.repr_node(other, level + 1) subs = suboutput.split('\n') output.extend(subs[1:]) return '\n'.join(output) def to_dot(self, f, skip_disconnected=True): """Writes a DOT output for the graph to the provided file *f*. If *skip_disconnected* is set to ``True``, then all distributions that are not dependent on any other distribution are skipped. :type f: has to support ``file``-like operations :type skip_disconnected: ``bool`` """ disconnected = [] f.write("digraph dependencies {\n") for dist, adjs in self.adjacency_list.items(): if len(adjs) == 0 and not skip_disconnected: disconnected.append(dist) for other, label in adjs: if not label is None: f.write('"%s" -> "%s" [label="%s"]\n' % (dist.name, other.name, label)) else: f.write('"%s" -> "%s"\n' % (dist.name, other.name)) if not skip_disconnected and len(disconnected) > 0: f.write('subgraph disconnected {\n') f.write('label = "Disconnected"\n') f.write('bgcolor = red\n') for dist in disconnected: f.write('"%s"' % dist.name) f.write('\n') f.write('}\n') f.write('}\n') def topological_sort(self): """ Perform a topological sort of the graph. :return: A tuple, the first element of which is a topologically sorted list of distributions, and the second element of which is a list of distributions that cannot be sorted because they have circular dependencies and so form a cycle. """ result = [] # Make a shallow copy of the adjacency list alist = {} for k, v in self.adjacency_list.items(): alist[k] = v[:] while True: # See what we can remove in this run to_remove = [] for k, v in list(alist.items())[:]: if not v: to_remove.append(k) del alist[k] if not to_remove: # What's left in alist (if anything) is a cycle. break # Remove from the adjacency list of others for k, v in alist.items(): alist[k] = [(d, r) for d, r in v if d not in to_remove] logger.debug('Moving to result: %s', ['%s (%s)' % (d.name, d.version) for d in to_remove]) result.extend(to_remove) return result, list(alist.keys()) def __repr__(self): """Representation of the graph""" output = [] for dist, adjs in self.adjacency_list.items(): output.append(self.repr_node(dist)) return '\n'.join(output) def make_graph(dists, scheme='default'): """Makes a dependency graph from the given distributions. :parameter dists: a list of distributions :type dists: list of :class:`distutils2.database.InstalledDistribution` and :class:`distutils2.database.EggInfoDistribution` instances :rtype: a :class:`DependencyGraph` instance """ scheme = get_scheme(scheme) graph = DependencyGraph() provided = {} # maps names to lists of (version, dist) tuples # first, build the graph and find out what's provided for dist in dists: graph.add_distribution(dist) for p in dist.provides: name, version = parse_name_and_version(p) logger.debug('Add to provided: %s, %s, %s', name, version, dist) provided.setdefault(name, []).append((version, dist)) # now make the edges for dist in dists: requires = (dist.run_requires | dist.meta_requires | dist.build_requires | dist.dev_requires) for req in requires: try: matcher = scheme.matcher(req) except UnsupportedVersionError: # XXX compat-mode if cannot read the version logger.warning('could not read version %r - using name only', req) name = req.split()[0] matcher = scheme.matcher(name) name = matcher.key # case-insensitive matched = False if name in provided: for version, provider in provided[name]: try: match = matcher.match(version) except UnsupportedVersionError: match = False if match: graph.add_edge(dist, provider, req) matched = True break if not matched: graph.add_missing(dist, req) return graph def get_dependent_dists(dists, dist): """Recursively generate a list of distributions from *dists* that are dependent on *dist*. :param dists: a list of distributions :param dist: a distribution, member of *dists* for which we are interested """ if dist not in dists: raise DistlibException('given distribution %r is not a member ' 'of the list' % dist.name) graph = make_graph(dists) dep = [dist] # dependent distributions todo = graph.reverse_list[dist] # list of nodes we should inspect while todo: d = todo.pop() dep.append(d) for succ in graph.reverse_list[d]: if succ not in dep: todo.append(succ) dep.pop(0) # remove dist from dep, was there to prevent infinite loops return dep def get_required_dists(dists, dist): """Recursively generate a list of distributions from *dists* that are required by *dist*. :param dists: a list of distributions :param dist: a distribution, member of *dists* for which we are interested """ if dist not in dists: raise DistlibException('given distribution %r is not a member ' 'of the list' % dist.name) graph = make_graph(dists) req = [] # required distributions todo = graph.adjacency_list[dist] # list of nodes we should inspect while todo: d = todo.pop()[0] req.append(d) for pred in graph.adjacency_list[d]: if pred not in req: todo.append(pred) return req def make_dist(name, version, **kwargs): """ A convenience method for making a dist given just a name and version. """ summary = kwargs.pop('summary', 'Placeholder for summary') md = Metadata(**kwargs) md.name = name md.version = version md.summary = summary or 'Plaeholder for summary' return Distribution(md) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/index.py0000644000076500000240000005076012700725533030026 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2013 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # import hashlib import logging import os import shutil import subprocess import tempfile try: from threading import Thread except ImportError: from dummy_threading import Thread from . import DistlibException from .compat import (HTTPBasicAuthHandler, Request, HTTPPasswordMgr, urlparse, build_opener, string_types) from .util import cached_property, zip_dir, ServerProxy logger = logging.getLogger(__name__) DEFAULT_INDEX = 'https://pypi.python.org/pypi' DEFAULT_REALM = 'pypi' class PackageIndex(object): """ This class represents a package index compatible with PyPI, the Python Package Index. """ boundary = b'----------ThIs_Is_tHe_distlib_index_bouNdaRY_$' def __init__(self, url=None): """ Initialise an instance. :param url: The URL of the index. If not specified, the URL for PyPI is used. """ self.url = url or DEFAULT_INDEX self.read_configuration() scheme, netloc, path, params, query, frag = urlparse(self.url) if params or query or frag or scheme not in ('http', 'https'): raise DistlibException('invalid repository: %s' % self.url) self.password_handler = None self.ssl_verifier = None self.gpg = None self.gpg_home = None self.rpc_proxy = None with open(os.devnull, 'w') as sink: for s in ('gpg2', 'gpg'): try: rc = subprocess.check_call([s, '--version'], stdout=sink, stderr=sink) if rc == 0: self.gpg = s break except OSError: pass def _get_pypirc_command(self): """ Get the distutils command for interacting with PyPI configurations. :return: the command. """ from distutils.core import Distribution from distutils.config import PyPIRCCommand d = Distribution() return PyPIRCCommand(d) def read_configuration(self): """ Read the PyPI access configuration as supported by distutils, getting PyPI to do the acutal work. This populates ``username``, ``password``, ``realm`` and ``url`` attributes from the configuration. """ # get distutils to do the work c = self._get_pypirc_command() c.repository = self.url cfg = c._read_pypirc() self.username = cfg.get('username') self.password = cfg.get('password') self.realm = cfg.get('realm', 'pypi') self.url = cfg.get('repository', self.url) def save_configuration(self): """ Save the PyPI access configuration. You must have set ``username`` and ``password`` attributes before calling this method. Again, distutils is used to do the actual work. """ self.check_credentials() # get distutils to do the work c = self._get_pypirc_command() c._store_pypirc(self.username, self.password) def check_credentials(self): """ Check that ``username`` and ``password`` have been set, and raise an exception if not. """ if self.username is None or self.password is None: raise DistlibException('username and password must be set') pm = HTTPPasswordMgr() _, netloc, _, _, _, _ = urlparse(self.url) pm.add_password(self.realm, netloc, self.username, self.password) self.password_handler = HTTPBasicAuthHandler(pm) def register(self, metadata): """ Register a distribution on PyPI, using the provided metadata. :param metadata: A :class:`Metadata` instance defining at least a name and version number for the distribution to be registered. :return: The HTTP response received from PyPI upon submission of the request. """ self.check_credentials() metadata.validate() d = metadata.todict() d[':action'] = 'verify' request = self.encode_request(d.items(), []) response = self.send_request(request) d[':action'] = 'submit' request = self.encode_request(d.items(), []) return self.send_request(request) def _reader(self, name, stream, outbuf): """ Thread runner for reading lines of from a subprocess into a buffer. :param name: The logical name of the stream (used for logging only). :param stream: The stream to read from. This will typically a pipe connected to the output stream of a subprocess. :param outbuf: The list to append the read lines to. """ while True: s = stream.readline() if not s: break s = s.decode('utf-8').rstrip() outbuf.append(s) logger.debug('%s: %s' % (name, s)) stream.close() def get_sign_command(self, filename, signer, sign_password, keystore=None): """ Return a suitable command for signing a file. :param filename: The pathname to the file to be signed. :param signer: The identifier of the signer of the file. :param sign_password: The passphrase for the signer's private key used for signing. :param keystore: The path to a directory which contains the keys used in verification. If not specified, the instance's ``gpg_home`` attribute is used instead. :return: The signing command as a list suitable to be passed to :class:`subprocess.Popen`. """ cmd = [self.gpg, '--status-fd', '2', '--no-tty'] if keystore is None: keystore = self.gpg_home if keystore: cmd.extend(['--homedir', keystore]) if sign_password is not None: cmd.extend(['--batch', '--passphrase-fd', '0']) td = tempfile.mkdtemp() sf = os.path.join(td, os.path.basename(filename) + '.asc') cmd.extend(['--detach-sign', '--armor', '--local-user', signer, '--output', sf, filename]) logger.debug('invoking: %s', ' '.join(cmd)) return cmd, sf def run_command(self, cmd, input_data=None): """ Run a command in a child process , passing it any input data specified. :param cmd: The command to run. :param input_data: If specified, this must be a byte string containing data to be sent to the child process. :return: A tuple consisting of the subprocess' exit code, a list of lines read from the subprocess' ``stdout``, and a list of lines read from the subprocess' ``stderr``. """ kwargs = { 'stdout': subprocess.PIPE, 'stderr': subprocess.PIPE, } if input_data is not None: kwargs['stdin'] = subprocess.PIPE stdout = [] stderr = [] p = subprocess.Popen(cmd, **kwargs) # We don't use communicate() here because we may need to # get clever with interacting with the command t1 = Thread(target=self._reader, args=('stdout', p.stdout, stdout)) t1.start() t2 = Thread(target=self._reader, args=('stderr', p.stderr, stderr)) t2.start() if input_data is not None: p.stdin.write(input_data) p.stdin.close() p.wait() t1.join() t2.join() return p.returncode, stdout, stderr def sign_file(self, filename, signer, sign_password, keystore=None): """ Sign a file. :param filename: The pathname to the file to be signed. :param signer: The identifier of the signer of the file. :param sign_password: The passphrase for the signer's private key used for signing. :param keystore: The path to a directory which contains the keys used in signing. If not specified, the instance's ``gpg_home`` attribute is used instead. :return: The absolute pathname of the file where the signature is stored. """ cmd, sig_file = self.get_sign_command(filename, signer, sign_password, keystore) rc, stdout, stderr = self.run_command(cmd, sign_password.encode('utf-8')) if rc != 0: raise DistlibException('sign command failed with error ' 'code %s' % rc) return sig_file def upload_file(self, metadata, filename, signer=None, sign_password=None, filetype='sdist', pyversion='source', keystore=None): """ Upload a release file to the index. :param metadata: A :class:`Metadata` instance defining at least a name and version number for the file to be uploaded. :param filename: The pathname of the file to be uploaded. :param signer: The identifier of the signer of the file. :param sign_password: The passphrase for the signer's private key used for signing. :param filetype: The type of the file being uploaded. This is the distutils command which produced that file, e.g. ``sdist`` or ``bdist_wheel``. :param pyversion: The version of Python which the release relates to. For code compatible with any Python, this would be ``source``, otherwise it would be e.g. ``3.2``. :param keystore: The path to a directory which contains the keys used in signing. If not specified, the instance's ``gpg_home`` attribute is used instead. :return: The HTTP response received from PyPI upon submission of the request. """ self.check_credentials() if not os.path.exists(filename): raise DistlibException('not found: %s' % filename) metadata.validate() d = metadata.todict() sig_file = None if signer: if not self.gpg: logger.warning('no signing program available - not signed') else: sig_file = self.sign_file(filename, signer, sign_password, keystore) with open(filename, 'rb') as f: file_data = f.read() md5_digest = hashlib.md5(file_data).hexdigest() sha256_digest = hashlib.sha256(file_data).hexdigest() d.update({ ':action': 'file_upload', 'protcol_version': '1', 'filetype': filetype, 'pyversion': pyversion, 'md5_digest': md5_digest, 'sha256_digest': sha256_digest, }) files = [('content', os.path.basename(filename), file_data)] if sig_file: with open(sig_file, 'rb') as f: sig_data = f.read() files.append(('gpg_signature', os.path.basename(sig_file), sig_data)) shutil.rmtree(os.path.dirname(sig_file)) request = self.encode_request(d.items(), files) return self.send_request(request) def upload_documentation(self, metadata, doc_dir): """ Upload documentation to the index. :param metadata: A :class:`Metadata` instance defining at least a name and version number for the documentation to be uploaded. :param doc_dir: The pathname of the directory which contains the documentation. This should be the directory that contains the ``index.html`` for the documentation. :return: The HTTP response received from PyPI upon submission of the request. """ self.check_credentials() if not os.path.isdir(doc_dir): raise DistlibException('not a directory: %r' % doc_dir) fn = os.path.join(doc_dir, 'index.html') if not os.path.exists(fn): raise DistlibException('not found: %r' % fn) metadata.validate() name, version = metadata.name, metadata.version zip_data = zip_dir(doc_dir).getvalue() fields = [(':action', 'doc_upload'), ('name', name), ('version', version)] files = [('content', name, zip_data)] request = self.encode_request(fields, files) return self.send_request(request) def get_verify_command(self, signature_filename, data_filename, keystore=None): """ Return a suitable command for verifying a file. :param signature_filename: The pathname to the file containing the signature. :param data_filename: The pathname to the file containing the signed data. :param keystore: The path to a directory which contains the keys used in verification. If not specified, the instance's ``gpg_home`` attribute is used instead. :return: The verifying command as a list suitable to be passed to :class:`subprocess.Popen`. """ cmd = [self.gpg, '--status-fd', '2', '--no-tty'] if keystore is None: keystore = self.gpg_home if keystore: cmd.extend(['--homedir', keystore]) cmd.extend(['--verify', signature_filename, data_filename]) logger.debug('invoking: %s', ' '.join(cmd)) return cmd def verify_signature(self, signature_filename, data_filename, keystore=None): """ Verify a signature for a file. :param signature_filename: The pathname to the file containing the signature. :param data_filename: The pathname to the file containing the signed data. :param keystore: The path to a directory which contains the keys used in verification. If not specified, the instance's ``gpg_home`` attribute is used instead. :return: True if the signature was verified, else False. """ if not self.gpg: raise DistlibException('verification unavailable because gpg ' 'unavailable') cmd = self.get_verify_command(signature_filename, data_filename, keystore) rc, stdout, stderr = self.run_command(cmd) if rc not in (0, 1): raise DistlibException('verify command failed with error ' 'code %s' % rc) return rc == 0 def download_file(self, url, destfile, digest=None, reporthook=None): """ This is a convenience method for downloading a file from an URL. Normally, this will be a file from the index, though currently no check is made for this (i.e. a file can be downloaded from anywhere). The method is just like the :func:`urlretrieve` function in the standard library, except that it allows digest computation to be done during download and checking that the downloaded data matched any expected value. :param url: The URL of the file to be downloaded (assumed to be available via an HTTP GET request). :param destfile: The pathname where the downloaded file is to be saved. :param digest: If specified, this must be a (hasher, value) tuple, where hasher is the algorithm used (e.g. ``'md5'``) and ``value`` is the expected value. :param reporthook: The same as for :func:`urlretrieve` in the standard library. """ if digest is None: digester = None logger.debug('No digest specified') else: if isinstance(digest, (list, tuple)): hasher, digest = digest else: hasher = 'md5' digester = getattr(hashlib, hasher)() logger.debug('Digest specified: %s' % digest) # The following code is equivalent to urlretrieve. # We need to do it this way so that we can compute the # digest of the file as we go. with open(destfile, 'wb') as dfp: # addinfourl is not a context manager on 2.x # so we have to use try/finally sfp = self.send_request(Request(url)) try: headers = sfp.info() blocksize = 8192 size = -1 read = 0 blocknum = 0 if "content-length" in headers: size = int(headers["Content-Length"]) if reporthook: reporthook(blocknum, blocksize, size) while True: block = sfp.read(blocksize) if not block: break read += len(block) dfp.write(block) if digester: digester.update(block) blocknum += 1 if reporthook: reporthook(blocknum, blocksize, size) finally: sfp.close() # check that we got the whole file, if we can if size >= 0 and read < size: raise DistlibException( 'retrieval incomplete: got only %d out of %d bytes' % (read, size)) # if we have a digest, it must match. if digester: actual = digester.hexdigest() if digest != actual: raise DistlibException('%s digest mismatch for %s: expected ' '%s, got %s' % (hasher, destfile, digest, actual)) logger.debug('Digest verified: %s', digest) def send_request(self, req): """ Send a standard library :class:`Request` to PyPI and return its response. :param req: The request to send. :return: The HTTP response from PyPI (a standard library HTTPResponse). """ handlers = [] if self.password_handler: handlers.append(self.password_handler) if self.ssl_verifier: handlers.append(self.ssl_verifier) opener = build_opener(*handlers) return opener.open(req) def encode_request(self, fields, files): """ Encode fields and files for posting to an HTTP server. :param fields: The fields to send as a list of (fieldname, value) tuples. :param files: The files to send as a list of (fieldname, filename, file_bytes) tuple. """ # Adapted from packaging, which in turn was adapted from # http://code.activestate.com/recipes/146306 parts = [] boundary = self.boundary for k, values in fields: if not isinstance(values, (list, tuple)): values = [values] for v in values: parts.extend(( b'--' + boundary, ('Content-Disposition: form-data; name="%s"' % k).encode('utf-8'), b'', v.encode('utf-8'))) for key, filename, value in files: parts.extend(( b'--' + boundary, ('Content-Disposition: form-data; name="%s"; filename="%s"' % (key, filename)).encode('utf-8'), b'', value)) parts.extend((b'--' + boundary + b'--', b'')) body = b'\r\n'.join(parts) ct = b'multipart/form-data; boundary=' + boundary headers = { 'Content-type': ct, 'Content-length': str(len(body)) } return Request(self.url, body, headers) def search(self, terms, operator=None): if isinstance(terms, string_types): terms = {'name': terms} if self.rpc_proxy is None: self.rpc_proxy = ServerProxy(self.url, timeout=3.0) return self.rpc_proxy.search(terms, operator or 'and') feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/locators.py0000644000076500000240000014247512700725533030552 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012-2015 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # import gzip from io import BytesIO import json import logging import os import posixpath import re try: import threading except ImportError: # pragma: no cover import dummy_threading as threading import zlib from . import DistlibException from .compat import (urljoin, urlparse, urlunparse, url2pathname, pathname2url, queue, quote, unescape, string_types, build_opener, HTTPRedirectHandler as BaseRedirectHandler, Request, HTTPError, URLError) from .database import Distribution, DistributionPath, make_dist from .metadata import Metadata from .util import (cached_property, parse_credentials, ensure_slash, split_filename, get_project_data, parse_requirement, parse_name_and_version, ServerProxy) from .version import get_scheme, UnsupportedVersionError from .wheel import Wheel, is_compatible logger = logging.getLogger(__name__) HASHER_HASH = re.compile('^(\w+)=([a-f0-9]+)') CHARSET = re.compile(r';\s*charset\s*=\s*(.*)\s*$', re.I) HTML_CONTENT_TYPE = re.compile('text/html|application/x(ht)?ml') DEFAULT_INDEX = 'https://pypi.python.org/pypi' def get_all_distribution_names(url=None): """ Return all distribution names known by an index. :param url: The URL of the index. :return: A list of all known distribution names. """ if url is None: url = DEFAULT_INDEX client = ServerProxy(url, timeout=3.0) return client.list_packages() class RedirectHandler(BaseRedirectHandler): """ A class to work around a bug in some Python 3.2.x releases. """ # There's a bug in the base version for some 3.2.x # (e.g. 3.2.2 on Ubuntu Oneiric). If a Location header # returns e.g. /abc, it bails because it says the scheme '' # is bogus, when actually it should use the request's # URL for the scheme. See Python issue #13696. def http_error_302(self, req, fp, code, msg, headers): # Some servers (incorrectly) return multiple Location headers # (so probably same goes for URI). Use first header. newurl = None for key in ('location', 'uri'): if key in headers: newurl = headers[key] break if newurl is None: return urlparts = urlparse(newurl) if urlparts.scheme == '': newurl = urljoin(req.get_full_url(), newurl) if hasattr(headers, 'replace_header'): headers.replace_header(key, newurl) else: headers[key] = newurl return BaseRedirectHandler.http_error_302(self, req, fp, code, msg, headers) http_error_301 = http_error_303 = http_error_307 = http_error_302 class Locator(object): """ A base class for locators - things that locate distributions. """ source_extensions = ('.tar.gz', '.tar.bz2', '.tar', '.zip', '.tgz', '.tbz') binary_extensions = ('.egg', '.exe', '.whl') excluded_extensions = ('.pdf',) # A list of tags indicating which wheels you want to match. The default # value of None matches against the tags compatible with the running # Python. If you want to match other values, set wheel_tags on a locator # instance to a list of tuples (pyver, abi, arch) which you want to match. wheel_tags = None downloadable_extensions = source_extensions + ('.whl',) def __init__(self, scheme='default'): """ Initialise an instance. :param scheme: Because locators look for most recent versions, they need to know the version scheme to use. This specifies the current PEP-recommended scheme - use ``'legacy'`` if you need to support existing distributions on PyPI. """ self._cache = {} self.scheme = scheme # Because of bugs in some of the handlers on some of the platforms, # we use our own opener rather than just using urlopen. self.opener = build_opener(RedirectHandler()) # If get_project() is called from locate(), the matcher instance # is set from the requirement passed to locate(). See issue #18 for # why this can be useful to know. self.matcher = None def clear_cache(self): self._cache.clear() def _get_scheme(self): return self._scheme def _set_scheme(self, value): self._scheme = value scheme = property(_get_scheme, _set_scheme) def _get_project(self, name): """ For a given project, get a dictionary mapping available versions to Distribution instances. This should be implemented in subclasses. If called from a locate() request, self.matcher will be set to a matcher for the requirement to satisfy, otherwise it will be None. """ raise NotImplementedError('Please implement in the subclass') def get_distribution_names(self): """ Return all the distribution names known to this locator. """ raise NotImplementedError('Please implement in the subclass') def get_project(self, name): """ For a given project, get a dictionary mapping available versions to Distribution instances. This calls _get_project to do all the work, and just implements a caching layer on top. """ if self._cache is None: result = self._get_project(name) elif name in self._cache: result = self._cache[name] else: result = self._get_project(name) self._cache[name] = result return result def score_url(self, url): """ Give an url a score which can be used to choose preferred URLs for a given project release. """ t = urlparse(url) basename = posixpath.basename(t.path) compatible = True is_wheel = basename.endswith('.whl') if is_wheel: compatible = is_compatible(Wheel(basename), self.wheel_tags) return (t.scheme != 'https', 'pypi.python.org' in t.netloc, is_wheel, compatible, basename) def prefer_url(self, url1, url2): """ Choose one of two URLs where both are candidates for distribution archives for the same version of a distribution (for example, .tar.gz vs. zip). The current implementation favours https:// URLs over http://, archives from PyPI over those from other locations, wheel compatibility (if a wheel) and then the archive name. """ result = url2 if url1: s1 = self.score_url(url1) s2 = self.score_url(url2) if s1 > s2: result = url1 if result != url2: logger.debug('Not replacing %r with %r', url1, url2) else: logger.debug('Replacing %r with %r', url1, url2) return result def split_filename(self, filename, project_name): """ Attempt to split a filename in project name, version and Python version. """ return split_filename(filename, project_name) def convert_url_to_download_info(self, url, project_name): """ See if a URL is a candidate for a download URL for a project (the URL has typically been scraped from an HTML page). If it is, a dictionary is returned with keys "name", "version", "filename" and "url"; otherwise, None is returned. """ def same_project(name1, name2): name1, name2 = name1.lower(), name2.lower() if name1 == name2: result = True else: # distribute replaces '-' by '_' in project names, so it # can tell where the version starts in a filename. result = name1.replace('_', '-') == name2.replace('_', '-') return result result = None scheme, netloc, path, params, query, frag = urlparse(url) if frag.lower().startswith('egg='): logger.debug('%s: version hint in fragment: %r', project_name, frag) m = HASHER_HASH.match(frag) if m: algo, digest = m.groups() else: algo, digest = None, None origpath = path if path and path[-1] == '/': path = path[:-1] if path.endswith('.whl'): try: wheel = Wheel(path) if is_compatible(wheel, self.wheel_tags): if project_name is None: include = True else: include = same_project(wheel.name, project_name) if include: result = { 'name': wheel.name, 'version': wheel.version, 'filename': wheel.filename, 'url': urlunparse((scheme, netloc, origpath, params, query, '')), 'python-version': ', '.join( ['.'.join(list(v[2:])) for v in wheel.pyver]), } except Exception as e: logger.warning('invalid path for wheel: %s', path) elif path.endswith(self.downloadable_extensions): path = filename = posixpath.basename(path) for ext in self.downloadable_extensions: if path.endswith(ext): path = path[:-len(ext)] t = self.split_filename(path, project_name) if not t: logger.debug('No match for project/version: %s', path) else: name, version, pyver = t if not project_name or same_project(project_name, name): result = { 'name': name, 'version': version, 'filename': filename, 'url': urlunparse((scheme, netloc, origpath, params, query, '')), #'packagetype': 'sdist', } if pyver: result['python-version'] = pyver break if result and algo: result['%s_digest' % algo] = digest return result def _get_digest(self, info): """ Get a digest from a dictionary by looking at keys of the form 'algo_digest'. Returns a 2-tuple (algo, digest) if found, else None. Currently looks only for SHA256, then MD5. """ result = None for algo in ('sha256', 'md5'): key = '%s_digest' % algo if key in info: result = (algo, info[key]) break return result def _update_version_data(self, result, info): """ Update a result dictionary (the final result from _get_project) with a dictionary for a specific version, which typically holds information gleaned from a filename or URL for an archive for the distribution. """ name = info.pop('name') version = info.pop('version') if version in result: dist = result[version] md = dist.metadata else: dist = make_dist(name, version, scheme=self.scheme) md = dist.metadata dist.digest = digest = self._get_digest(info) url = info['url'] result['digests'][url] = digest if md.source_url != info['url']: md.source_url = self.prefer_url(md.source_url, url) result['urls'].setdefault(version, set()).add(url) dist.locator = self result[version] = dist def locate(self, requirement, prereleases=False): """ Find the most recent distribution which matches the given requirement. :param requirement: A requirement of the form 'foo (1.0)' or perhaps 'foo (>= 1.0, < 2.0, != 1.3)' :param prereleases: If ``True``, allow pre-release versions to be located. Otherwise, pre-release versions are not returned. :return: A :class:`Distribution` instance, or ``None`` if no such distribution could be located. """ result = None r = parse_requirement(requirement) if r is None: raise DistlibException('Not a valid requirement: %r' % requirement) scheme = get_scheme(self.scheme) self.matcher = matcher = scheme.matcher(r.requirement) logger.debug('matcher: %s (%s)', matcher, type(matcher).__name__) versions = self.get_project(r.name) if len(versions) > 2: # urls and digests keys are present # sometimes, versions are invalid slist = [] vcls = matcher.version_class for k in versions: if k in ('urls', 'digests'): continue try: if not matcher.match(k): logger.debug('%s did not match %r', matcher, k) else: if prereleases or not vcls(k).is_prerelease: slist.append(k) else: logger.debug('skipping pre-release ' 'version %s of %s', k, matcher.name) except Exception: # pragma: no cover logger.warning('error matching %s with %r', matcher, k) pass # slist.append(k) if len(slist) > 1: slist = sorted(slist, key=scheme.key) if slist: logger.debug('sorted list: %s', slist) version = slist[-1] result = versions[version] if result: if r.extras: result.extras = r.extras result.download_urls = versions.get('urls', {}).get(version, set()) d = {} sd = versions.get('digests', {}) for url in result.download_urls: if url in sd: d[url] = sd[url] result.digests = d self.matcher = None return result class PyPIRPCLocator(Locator): """ This locator uses XML-RPC to locate distributions. It therefore cannot be used with simple mirrors (that only mirror file content). """ def __init__(self, url, **kwargs): """ Initialise an instance. :param url: The URL to use for XML-RPC. :param kwargs: Passed to the superclass constructor. """ super(PyPIRPCLocator, self).__init__(**kwargs) self.base_url = url self.client = ServerProxy(url, timeout=3.0) def get_distribution_names(self): """ Return all the distribution names known to this locator. """ return set(self.client.list_packages()) def _get_project(self, name): result = {'urls': {}, 'digests': {}} versions = self.client.package_releases(name, True) for v in versions: urls = self.client.release_urls(name, v) data = self.client.release_data(name, v) metadata = Metadata(scheme=self.scheme) metadata.name = data['name'] metadata.version = data['version'] metadata.license = data.get('license') metadata.keywords = data.get('keywords', []) metadata.summary = data.get('summary') dist = Distribution(metadata) if urls: info = urls[0] metadata.source_url = info['url'] dist.digest = self._get_digest(info) dist.locator = self result[v] = dist for info in urls: url = info['url'] digest = self._get_digest(info) result['urls'].setdefault(v, set()).add(url) result['digests'][url] = digest return result class PyPIJSONLocator(Locator): """ This locator uses PyPI's JSON interface. It's very limited in functionality and probably not worth using. """ def __init__(self, url, **kwargs): super(PyPIJSONLocator, self).__init__(**kwargs) self.base_url = ensure_slash(url) def get_distribution_names(self): """ Return all the distribution names known to this locator. """ raise NotImplementedError('Not available from this locator') def _get_project(self, name): result = {'urls': {}, 'digests': {}} url = urljoin(self.base_url, '%s/json' % quote(name)) try: resp = self.opener.open(url) data = resp.read().decode() # for now d = json.loads(data) md = Metadata(scheme=self.scheme) data = d['info'] md.name = data['name'] md.version = data['version'] md.license = data.get('license') md.keywords = data.get('keywords', []) md.summary = data.get('summary') dist = Distribution(md) dist.locator = self urls = d['urls'] result[md.version] = dist for info in d['urls']: url = info['url'] dist.download_urls.add(url) dist.digests[url] = self._get_digest(info) result['urls'].setdefault(md.version, set()).add(url) result['digests'][url] = self._get_digest(info) # Now get other releases for version, infos in d['releases'].items(): if version == md.version: continue # already done omd = Metadata(scheme=self.scheme) omd.name = md.name omd.version = version odist = Distribution(omd) odist.locator = self result[version] = odist for info in infos: url = info['url'] odist.download_urls.add(url) odist.digests[url] = self._get_digest(info) result['urls'].setdefault(version, set()).add(url) result['digests'][url] = self._get_digest(info) # for info in urls: # md.source_url = info['url'] # dist.digest = self._get_digest(info) # dist.locator = self # for info in urls: # url = info['url'] # result['urls'].setdefault(md.version, set()).add(url) # result['digests'][url] = self._get_digest(info) except Exception as e: logger.exception('JSON fetch failed: %s', e) return result class Page(object): """ This class represents a scraped HTML page. """ # The following slightly hairy-looking regex just looks for the contents of # an anchor link, which has an attribute "href" either immediately preceded # or immediately followed by a "rel" attribute. The attribute values can be # declared with double quotes, single quotes or no quotes - which leads to # the length of the expression. _href = re.compile(""" (rel\s*=\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\s\n]*))\s+)? href\s*=\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\s\n]*)) (\s+rel\s*=\s*(?:"(?P[^"]*)"|'(?P[^']*)'|(?P[^>\s\n]*)))? """, re.I | re.S | re.X) _base = re.compile(r"""]+)""", re.I | re.S) def __init__(self, data, url): """ Initialise an instance with the Unicode page contents and the URL they came from. """ self.data = data self.base_url = self.url = url m = self._base.search(self.data) if m: self.base_url = m.group(1) _clean_re = re.compile(r'[^a-z0-9$&+,/:;=?@.#%_\\|-]', re.I) @cached_property def links(self): """ Return the URLs of all the links on a page together with information about their "rel" attribute, for determining which ones to treat as downloads and which ones to queue for further scraping. """ def clean(url): "Tidy up an URL." scheme, netloc, path, params, query, frag = urlparse(url) return urlunparse((scheme, netloc, quote(path), params, query, frag)) result = set() for match in self._href.finditer(self.data): d = match.groupdict('') rel = (d['rel1'] or d['rel2'] or d['rel3'] or d['rel4'] or d['rel5'] or d['rel6']) url = d['url1'] or d['url2'] or d['url3'] url = urljoin(self.base_url, url) url = unescape(url) url = self._clean_re.sub(lambda m: '%%%2x' % ord(m.group(0)), url) result.add((url, rel)) # We sort the result, hoping to bring the most recent versions # to the front result = sorted(result, key=lambda t: t[0], reverse=True) return result class SimpleScrapingLocator(Locator): """ A locator which scrapes HTML pages to locate downloads for a distribution. This runs multiple threads to do the I/O; performance is at least as good as pip's PackageFinder, which works in an analogous fashion. """ # These are used to deal with various Content-Encoding schemes. decoders = { 'deflate': zlib.decompress, 'gzip': lambda b: gzip.GzipFile(fileobj=BytesIO(d)).read(), 'none': lambda b: b, } def __init__(self, url, timeout=None, num_workers=10, **kwargs): """ Initialise an instance. :param url: The root URL to use for scraping. :param timeout: The timeout, in seconds, to be applied to requests. This defaults to ``None`` (no timeout specified). :param num_workers: The number of worker threads you want to do I/O, This defaults to 10. :param kwargs: Passed to the superclass. """ super(SimpleScrapingLocator, self).__init__(**kwargs) self.base_url = ensure_slash(url) self.timeout = timeout self._page_cache = {} self._seen = set() self._to_fetch = queue.Queue() self._bad_hosts = set() self.skip_externals = False self.num_workers = num_workers self._lock = threading.RLock() # See issue #45: we need to be resilient when the locator is used # in a thread, e.g. with concurrent.futures. We can't use self._lock # as it is for coordinating our internal threads - the ones created # in _prepare_threads. self._gplock = threading.RLock() def _prepare_threads(self): """ Threads are created only when get_project is called, and terminate before it returns. They are there primarily to parallelise I/O (i.e. fetching web pages). """ self._threads = [] for i in range(self.num_workers): t = threading.Thread(target=self._fetch) t.setDaemon(True) t.start() self._threads.append(t) def _wait_threads(self): """ Tell all the threads to terminate (by sending a sentinel value) and wait for them to do so. """ # Note that you need two loops, since you can't say which # thread will get each sentinel for t in self._threads: self._to_fetch.put(None) # sentinel for t in self._threads: t.join() self._threads = [] def _get_project(self, name): result = {'urls': {}, 'digests': {}} with self._gplock: self.result = result self.project_name = name url = urljoin(self.base_url, '%s/' % quote(name)) self._seen.clear() self._page_cache.clear() self._prepare_threads() try: logger.debug('Queueing %s', url) self._to_fetch.put(url) self._to_fetch.join() finally: self._wait_threads() del self.result return result platform_dependent = re.compile(r'\b(linux-(i\d86|x86_64|arm\w+)|' r'win(32|-amd64)|macosx-?\d+)\b', re.I) def _is_platform_dependent(self, url): """ Does an URL refer to a platform-specific download? """ return self.platform_dependent.search(url) def _process_download(self, url): """ See if an URL is a suitable download for a project. If it is, register information in the result dictionary (for _get_project) about the specific version it's for. Note that the return value isn't actually used other than as a boolean value. """ if self._is_platform_dependent(url): info = None else: info = self.convert_url_to_download_info(url, self.project_name) logger.debug('process_download: %s -> %s', url, info) if info: with self._lock: # needed because self.result is shared self._update_version_data(self.result, info) return info def _should_queue(self, link, referrer, rel): """ Determine whether a link URL from a referring page and with a particular "rel" attribute should be queued for scraping. """ scheme, netloc, path, _, _, _ = urlparse(link) if path.endswith(self.source_extensions + self.binary_extensions + self.excluded_extensions): result = False elif self.skip_externals and not link.startswith(self.base_url): result = False elif not referrer.startswith(self.base_url): result = False elif rel not in ('homepage', 'download'): result = False elif scheme not in ('http', 'https', 'ftp'): result = False elif self._is_platform_dependent(link): result = False else: host = netloc.split(':', 1)[0] if host.lower() == 'localhost': result = False else: result = True logger.debug('should_queue: %s (%s) from %s -> %s', link, rel, referrer, result) return result def _fetch(self): """ Get a URL to fetch from the work queue, get the HTML page, examine its links for download candidates and candidates for further scraping. This is a handy method to run in a thread. """ while True: url = self._to_fetch.get() try: if url: page = self.get_page(url) if page is None: # e.g. after an error continue for link, rel in page.links: if link not in self._seen: self._seen.add(link) if (not self._process_download(link) and self._should_queue(link, url, rel)): logger.debug('Queueing %s from %s', link, url) self._to_fetch.put(link) finally: # always do this, to avoid hangs :-) self._to_fetch.task_done() if not url: #logger.debug('Sentinel seen, quitting.') break def get_page(self, url): """ Get the HTML for an URL, possibly from an in-memory cache. XXX TODO Note: this cache is never actually cleared. It's assumed that the data won't get stale over the lifetime of a locator instance (not necessarily true for the default_locator). """ # http://peak.telecommunity.com/DevCenter/EasyInstall#package-index-api scheme, netloc, path, _, _, _ = urlparse(url) if scheme == 'file' and os.path.isdir(url2pathname(path)): url = urljoin(ensure_slash(url), 'index.html') if url in self._page_cache: result = self._page_cache[url] logger.debug('Returning %s from cache: %s', url, result) else: host = netloc.split(':', 1)[0] result = None if host in self._bad_hosts: logger.debug('Skipping %s due to bad host %s', url, host) else: req = Request(url, headers={'Accept-encoding': 'identity'}) try: logger.debug('Fetching %s', url) resp = self.opener.open(req, timeout=self.timeout) logger.debug('Fetched %s', url) headers = resp.info() content_type = headers.get('Content-Type', '') if HTML_CONTENT_TYPE.match(content_type): final_url = resp.geturl() data = resp.read() encoding = headers.get('Content-Encoding') if encoding: decoder = self.decoders[encoding] # fail if not found data = decoder(data) encoding = 'utf-8' m = CHARSET.search(content_type) if m: encoding = m.group(1) try: data = data.decode(encoding) except UnicodeError: # pragma: no cover data = data.decode('latin-1') # fallback result = Page(data, final_url) self._page_cache[final_url] = result except HTTPError as e: if e.code != 404: logger.exception('Fetch failed: %s: %s', url, e) except URLError as e: # pragma: no cover logger.exception('Fetch failed: %s: %s', url, e) with self._lock: self._bad_hosts.add(host) except Exception as e: # pragma: no cover logger.exception('Fetch failed: %s: %s', url, e) finally: self._page_cache[url] = result # even if None (failure) return result _distname_re = re.compile(']*>([^<]+)<') def get_distribution_names(self): """ Return all the distribution names known to this locator. """ result = set() page = self.get_page(self.base_url) if not page: raise DistlibException('Unable to get %s' % self.base_url) for match in self._distname_re.finditer(page.data): result.add(match.group(1)) return result class DirectoryLocator(Locator): """ This class locates distributions in a directory tree. """ def __init__(self, path, **kwargs): """ Initialise an instance. :param path: The root of the directory tree to search. :param kwargs: Passed to the superclass constructor, except for: * recursive - if True (the default), subdirectories are recursed into. If False, only the top-level directory is searched, """ self.recursive = kwargs.pop('recursive', True) super(DirectoryLocator, self).__init__(**kwargs) path = os.path.abspath(path) if not os.path.isdir(path): # pragma: no cover raise DistlibException('Not a directory: %r' % path) self.base_dir = path def should_include(self, filename, parent): """ Should a filename be considered as a candidate for a distribution archive? As well as the filename, the directory which contains it is provided, though not used by the current implementation. """ return filename.endswith(self.downloadable_extensions) def _get_project(self, name): result = {'urls': {}, 'digests': {}} for root, dirs, files in os.walk(self.base_dir): for fn in files: if self.should_include(fn, root): fn = os.path.join(root, fn) url = urlunparse(('file', '', pathname2url(os.path.abspath(fn)), '', '', '')) info = self.convert_url_to_download_info(url, name) if info: self._update_version_data(result, info) if not self.recursive: break return result def get_distribution_names(self): """ Return all the distribution names known to this locator. """ result = set() for root, dirs, files in os.walk(self.base_dir): for fn in files: if self.should_include(fn, root): fn = os.path.join(root, fn) url = urlunparse(('file', '', pathname2url(os.path.abspath(fn)), '', '', '')) info = self.convert_url_to_download_info(url, None) if info: result.add(info['name']) if not self.recursive: break return result class JSONLocator(Locator): """ This locator uses special extended metadata (not available on PyPI) and is the basis of performant dependency resolution in distlib. Other locators require archive downloads before dependencies can be determined! As you might imagine, that can be slow. """ def get_distribution_names(self): """ Return all the distribution names known to this locator. """ raise NotImplementedError('Not available from this locator') def _get_project(self, name): result = {'urls': {}, 'digests': {}} data = get_project_data(name) if data: for info in data.get('files', []): if info['ptype'] != 'sdist' or info['pyversion'] != 'source': continue # We don't store summary in project metadata as it makes # the data bigger for no benefit during dependency # resolution dist = make_dist(data['name'], info['version'], summary=data.get('summary', 'Placeholder for summary'), scheme=self.scheme) md = dist.metadata md.source_url = info['url'] # TODO SHA256 digest if 'digest' in info and info['digest']: dist.digest = ('md5', info['digest']) md.dependencies = info.get('requirements', {}) dist.exports = info.get('exports', {}) result[dist.version] = dist result['urls'].setdefault(dist.version, set()).add(info['url']) return result class DistPathLocator(Locator): """ This locator finds installed distributions in a path. It can be useful for adding to an :class:`AggregatingLocator`. """ def __init__(self, distpath, **kwargs): """ Initialise an instance. :param distpath: A :class:`DistributionPath` instance to search. """ super(DistPathLocator, self).__init__(**kwargs) assert isinstance(distpath, DistributionPath) self.distpath = distpath def _get_project(self, name): dist = self.distpath.get_distribution(name) if dist is None: result = {'urls': {}, 'digests': {}} else: result = { dist.version: dist, 'urls': {dist.version: set([dist.source_url])}, 'digests': {dist.version: set([None])} } return result class AggregatingLocator(Locator): """ This class allows you to chain and/or merge a list of locators. """ def __init__(self, *locators, **kwargs): """ Initialise an instance. :param locators: The list of locators to search. :param kwargs: Passed to the superclass constructor, except for: * merge - if False (the default), the first successful search from any of the locators is returned. If True, the results from all locators are merged (this can be slow). """ self.merge = kwargs.pop('merge', False) self.locators = locators super(AggregatingLocator, self).__init__(**kwargs) def clear_cache(self): super(AggregatingLocator, self).clear_cache() for locator in self.locators: locator.clear_cache() def _set_scheme(self, value): self._scheme = value for locator in self.locators: locator.scheme = value scheme = property(Locator.scheme.fget, _set_scheme) def _get_project(self, name): result = {} for locator in self.locators: d = locator.get_project(name) if d: if self.merge: files = result.get('urls', {}) digests = result.get('digests', {}) # next line could overwrite result['urls'], result['digests'] result.update(d) df = result.get('urls') if files and df: for k, v in files.items(): if k in df: df[k] |= v else: df[k] = v dd = result.get('digests') if digests and dd: dd.update(digests) else: # See issue #18. If any dists are found and we're looking # for specific constraints, we only return something if # a match is found. For example, if a DirectoryLocator # returns just foo (1.0) while we're looking for # foo (>= 2.0), we'll pretend there was nothing there so # that subsequent locators can be queried. Otherwise we # would just return foo (1.0) which would then lead to a # failure to find foo (>= 2.0), because other locators # weren't searched. Note that this only matters when # merge=False. if self.matcher is None: found = True else: found = False for k in d: if self.matcher.match(k): found = True break if found: result = d break return result def get_distribution_names(self): """ Return all the distribution names known to this locator. """ result = set() for locator in self.locators: try: result |= locator.get_distribution_names() except NotImplementedError: pass return result # We use a legacy scheme simply because most of the dists on PyPI use legacy # versions which don't conform to PEP 426 / PEP 440. default_locator = AggregatingLocator( JSONLocator(), SimpleScrapingLocator('https://pypi.python.org/simple/', timeout=3.0), scheme='legacy') locate = default_locator.locate NAME_VERSION_RE = re.compile(r'(?P[\w-]+)\s*' r'\(\s*(==\s*)?(?P[^)]+)\)$') class DependencyFinder(object): """ Locate dependencies for distributions. """ def __init__(self, locator=None): """ Initialise an instance, using the specified locator to locate distributions. """ self.locator = locator or default_locator self.scheme = get_scheme(self.locator.scheme) def add_distribution(self, dist): """ Add a distribution to the finder. This will update internal information about who provides what. :param dist: The distribution to add. """ logger.debug('adding distribution %s', dist) name = dist.key self.dists_by_name[name] = dist self.dists[(name, dist.version)] = dist for p in dist.provides: name, version = parse_name_and_version(p) logger.debug('Add to provided: %s, %s, %s', name, version, dist) self.provided.setdefault(name, set()).add((version, dist)) def remove_distribution(self, dist): """ Remove a distribution from the finder. This will update internal information about who provides what. :param dist: The distribution to remove. """ logger.debug('removing distribution %s', dist) name = dist.key del self.dists_by_name[name] del self.dists[(name, dist.version)] for p in dist.provides: name, version = parse_name_and_version(p) logger.debug('Remove from provided: %s, %s, %s', name, version, dist) s = self.provided[name] s.remove((version, dist)) if not s: del self.provided[name] def get_matcher(self, reqt): """ Get a version matcher for a requirement. :param reqt: The requirement :type reqt: str :return: A version matcher (an instance of :class:`distlib.version.Matcher`). """ try: matcher = self.scheme.matcher(reqt) except UnsupportedVersionError: # pragma: no cover # XXX compat-mode if cannot read the version name = reqt.split()[0] matcher = self.scheme.matcher(name) return matcher def find_providers(self, reqt): """ Find the distributions which can fulfill a requirement. :param reqt: The requirement. :type reqt: str :return: A set of distribution which can fulfill the requirement. """ matcher = self.get_matcher(reqt) name = matcher.key # case-insensitive result = set() provided = self.provided if name in provided: for version, provider in provided[name]: try: match = matcher.match(version) except UnsupportedVersionError: match = False if match: result.add(provider) break return result def try_to_replace(self, provider, other, problems): """ Attempt to replace one provider with another. This is typically used when resolving dependencies from multiple sources, e.g. A requires (B >= 1.0) while C requires (B >= 1.1). For successful replacement, ``provider`` must meet all the requirements which ``other`` fulfills. :param provider: The provider we are trying to replace with. :param other: The provider we're trying to replace. :param problems: If False is returned, this will contain what problems prevented replacement. This is currently a tuple of the literal string 'cantreplace', ``provider``, ``other`` and the set of requirements that ``provider`` couldn't fulfill. :return: True if we can replace ``other`` with ``provider``, else False. """ rlist = self.reqts[other] unmatched = set() for s in rlist: matcher = self.get_matcher(s) if not matcher.match(provider.version): unmatched.add(s) if unmatched: # can't replace other with provider problems.add(('cantreplace', provider, other, frozenset(unmatched))) result = False else: # can replace other with provider self.remove_distribution(other) del self.reqts[other] for s in rlist: self.reqts.setdefault(provider, set()).add(s) self.add_distribution(provider) result = True return result def find(self, requirement, meta_extras=None, prereleases=False): """ Find a distribution and all distributions it depends on. :param requirement: The requirement specifying the distribution to find, or a Distribution instance. :param meta_extras: A list of meta extras such as :test:, :build: and so on. :param prereleases: If ``True``, allow pre-release versions to be returned - otherwise, don't return prereleases unless they're all that's available. Return a set of :class:`Distribution` instances and a set of problems. The distributions returned should be such that they have the :attr:`required` attribute set to ``True`` if they were from the ``requirement`` passed to ``find()``, and they have the :attr:`build_time_dependency` attribute set to ``True`` unless they are post-installation dependencies of the ``requirement``. The problems should be a tuple consisting of the string ``'unsatisfied'`` and the requirement which couldn't be satisfied by any distribution known to the locator. """ self.provided = {} self.dists = {} self.dists_by_name = {} self.reqts = {} meta_extras = set(meta_extras or []) if ':*:' in meta_extras: meta_extras.remove(':*:') # :meta: and :run: are implicitly included meta_extras |= set([':test:', ':build:', ':dev:']) if isinstance(requirement, Distribution): dist = odist = requirement logger.debug('passed %s as requirement', odist) else: dist = odist = self.locator.locate(requirement, prereleases=prereleases) if dist is None: raise DistlibException('Unable to locate %r' % requirement) logger.debug('located %s', odist) dist.requested = True problems = set() todo = set([dist]) install_dists = set([odist]) while todo: dist = todo.pop() name = dist.key # case-insensitive if name not in self.dists_by_name: self.add_distribution(dist) else: #import pdb; pdb.set_trace() other = self.dists_by_name[name] if other != dist: self.try_to_replace(dist, other, problems) ireqts = dist.run_requires | dist.meta_requires sreqts = dist.build_requires ereqts = set() if dist in install_dists: for key in ('test', 'build', 'dev'): e = ':%s:' % key if e in meta_extras: ereqts |= getattr(dist, '%s_requires' % key) all_reqts = ireqts | sreqts | ereqts for r in all_reqts: providers = self.find_providers(r) if not providers: logger.debug('No providers found for %r', r) provider = self.locator.locate(r, prereleases=prereleases) # If no provider is found and we didn't consider # prereleases, consider them now. if provider is None and not prereleases: provider = self.locator.locate(r, prereleases=True) if provider is None: logger.debug('Cannot satisfy %r', r) problems.add(('unsatisfied', r)) else: n, v = provider.key, provider.version if (n, v) not in self.dists: todo.add(provider) providers.add(provider) if r in ireqts and dist in install_dists: install_dists.add(provider) logger.debug('Adding %s to install_dists', provider.name_and_version) for p in providers: name = p.key if name not in self.dists_by_name: self.reqts.setdefault(p, set()).add(r) else: other = self.dists_by_name[name] if other != p: # see if other can be replaced by p self.try_to_replace(p, other, problems) dists = set(self.dists.values()) for dist in dists: dist.build_time_dependency = dist not in install_dists if dist.build_time_dependency: logger.debug('%s is a build-time dependency only.', dist.name_and_version) logger.debug('find done for %s', odist) return dists, problems feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/manifest.py0000644000076500000240000003243612700725533030525 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012-2013 Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """ Class representing the list of files in a distribution. Equivalent to distutils.filelist, but fixes some problems. """ import fnmatch import logging import os import re from . import DistlibException from .compat import fsdecode from .util import convert_path __all__ = ['Manifest'] logger = logging.getLogger(__name__) # a \ followed by some spaces + EOL _COLLAPSE_PATTERN = re.compile('\\\w*\n', re.M) _COMMENTED_LINE = re.compile('#.*?(?=\n)|\n(?=$)', re.M | re.S) class Manifest(object): """A list of files built by on exploring the filesystem and filtered by applying various patterns to what we find there. """ def __init__(self, base=None): """ Initialise an instance. :param base: The base directory to explore under. """ self.base = os.path.abspath(os.path.normpath(base or os.getcwd())) self.prefix = self.base + os.sep self.allfiles = None self.files = set() # # Public API # def findall(self): """Find all files under the base and set ``allfiles`` to the absolute pathnames of files found. """ from stat import S_ISREG, S_ISDIR, S_ISLNK self.allfiles = allfiles = [] root = self.base stack = [root] pop = stack.pop push = stack.append while stack: root = pop() names = os.listdir(root) for name in names: fullname = os.path.join(root, name) # Avoid excess stat calls -- just one will do, thank you! stat = os.stat(fullname) mode = stat.st_mode if S_ISREG(mode): allfiles.append(fsdecode(fullname)) elif S_ISDIR(mode) and not S_ISLNK(mode): push(fullname) def add(self, item): """ Add a file to the manifest. :param item: The pathname to add. This can be relative to the base. """ if not item.startswith(self.prefix): item = os.path.join(self.base, item) self.files.add(os.path.normpath(item)) def add_many(self, items): """ Add a list of files to the manifest. :param items: The pathnames to add. These can be relative to the base. """ for item in items: self.add(item) def sorted(self, wantdirs=False): """ Return sorted files in directory order """ def add_dir(dirs, d): dirs.add(d) logger.debug('add_dir added %s', d) if d != self.base: parent, _ = os.path.split(d) assert parent not in ('', '/') add_dir(dirs, parent) result = set(self.files) # make a copy! if wantdirs: dirs = set() for f in result: add_dir(dirs, os.path.dirname(f)) result |= dirs return [os.path.join(*path_tuple) for path_tuple in sorted(os.path.split(path) for path in result)] def clear(self): """Clear all collected files.""" self.files = set() self.allfiles = [] def process_directive(self, directive): """ Process a directive which either adds some files from ``allfiles`` to ``files``, or removes some files from ``files``. :param directive: The directive to process. This should be in a format compatible with distutils ``MANIFEST.in`` files: http://docs.python.org/distutils/sourcedist.html#commands """ # Parse the line: split it up, make sure the right number of words # is there, and return the relevant words. 'action' is always # defined: it's the first word of the line. Which of the other # three are defined depends on the action; it'll be either # patterns, (dir and patterns), or (dirpattern). action, patterns, thedir, dirpattern = self._parse_directive(directive) # OK, now we know that the action is valid and we have the # right number of words on the line for that action -- so we # can proceed with minimal error-checking. if action == 'include': for pattern in patterns: if not self._include_pattern(pattern, anchor=True): logger.warning('no files found matching %r', pattern) elif action == 'exclude': for pattern in patterns: found = self._exclude_pattern(pattern, anchor=True) #if not found: # logger.warning('no previously-included files ' # 'found matching %r', pattern) elif action == 'global-include': for pattern in patterns: if not self._include_pattern(pattern, anchor=False): logger.warning('no files found matching %r ' 'anywhere in distribution', pattern) elif action == 'global-exclude': for pattern in patterns: found = self._exclude_pattern(pattern, anchor=False) #if not found: # logger.warning('no previously-included files ' # 'matching %r found anywhere in ' # 'distribution', pattern) elif action == 'recursive-include': for pattern in patterns: if not self._include_pattern(pattern, prefix=thedir): logger.warning('no files found matching %r ' 'under directory %r', pattern, thedir) elif action == 'recursive-exclude': for pattern in patterns: found = self._exclude_pattern(pattern, prefix=thedir) #if not found: # logger.warning('no previously-included files ' # 'matching %r found under directory %r', # pattern, thedir) elif action == 'graft': if not self._include_pattern(None, prefix=dirpattern): logger.warning('no directories found matching %r', dirpattern) elif action == 'prune': if not self._exclude_pattern(None, prefix=dirpattern): logger.warning('no previously-included directories found ' 'matching %r', dirpattern) else: # pragma: no cover # This should never happen, as it should be caught in # _parse_template_line raise DistlibException( 'invalid action %r' % action) # # Private API # def _parse_directive(self, directive): """ Validate a directive. :param directive: The directive to validate. :return: A tuple of action, patterns, thedir, dir_patterns """ words = directive.split() if len(words) == 1 and words[0] not in ('include', 'exclude', 'global-include', 'global-exclude', 'recursive-include', 'recursive-exclude', 'graft', 'prune'): # no action given, let's use the default 'include' words.insert(0, 'include') action = words[0] patterns = thedir = dir_pattern = None if action in ('include', 'exclude', 'global-include', 'global-exclude'): if len(words) < 2: raise DistlibException( '%r expects ...' % action) patterns = [convert_path(word) for word in words[1:]] elif action in ('recursive-include', 'recursive-exclude'): if len(words) < 3: raise DistlibException( '%r expects ...' % action) thedir = convert_path(words[1]) patterns = [convert_path(word) for word in words[2:]] elif action in ('graft', 'prune'): if len(words) != 2: raise DistlibException( '%r expects a single ' % action) dir_pattern = convert_path(words[1]) else: raise DistlibException('unknown action %r' % action) return action, patterns, thedir, dir_pattern def _include_pattern(self, pattern, anchor=True, prefix=None, is_regex=False): """Select strings (presumably filenames) from 'self.files' that match 'pattern', a Unix-style wildcard (glob) pattern. Patterns are not quite the same as implemented by the 'fnmatch' module: '*' and '?' match non-special characters, where "special" is platform-dependent: slash on Unix; colon, slash, and backslash on DOS/Windows; and colon on Mac OS. If 'anchor' is true (the default), then the pattern match is more stringent: "*.py" will match "foo.py" but not "foo/bar.py". If 'anchor' is false, both of these will match. If 'prefix' is supplied, then only filenames starting with 'prefix' (itself a pattern) and ending with 'pattern', with anything in between them, will match. 'anchor' is ignored in this case. If 'is_regex' is true, 'anchor' and 'prefix' are ignored, and 'pattern' is assumed to be either a string containing a regex or a regex object -- no translation is done, the regex is just compiled and used as-is. Selected strings will be added to self.files. Return True if files are found. """ # XXX docstring lying about what the special chars are? found = False pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex) # delayed loading of allfiles list if self.allfiles is None: self.findall() for name in self.allfiles: if pattern_re.search(name): self.files.add(name) found = True return found def _exclude_pattern(self, pattern, anchor=True, prefix=None, is_regex=False): """Remove strings (presumably filenames) from 'files' that match 'pattern'. Other parameters are the same as for 'include_pattern()', above. The list 'self.files' is modified in place. Return True if files are found. This API is public to allow e.g. exclusion of SCM subdirs, e.g. when packaging source distributions """ found = False pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex) for f in list(self.files): if pattern_re.search(f): self.files.remove(f) found = True return found def _translate_pattern(self, pattern, anchor=True, prefix=None, is_regex=False): """Translate a shell-like wildcard pattern to a compiled regular expression. Return the compiled regex. If 'is_regex' true, then 'pattern' is directly compiled to a regex (if it's a string) or just returned as-is (assumes it's a regex object). """ if is_regex: if isinstance(pattern, str): return re.compile(pattern) else: return pattern if pattern: pattern_re = self._glob_to_re(pattern) else: pattern_re = '' base = re.escape(os.path.join(self.base, '')) if prefix is not None: # ditch end of pattern character empty_pattern = self._glob_to_re('') prefix_re = self._glob_to_re(prefix)[:-len(empty_pattern)] sep = os.sep if os.sep == '\\': sep = r'\\' pattern_re = '^' + base + sep.join((prefix_re, '.*' + pattern_re)) else: # no prefix -- respect anchor flag if anchor: pattern_re = '^' + base + pattern_re return re.compile(pattern_re) def _glob_to_re(self, pattern): """Translate a shell-like glob pattern to a regular expression. Return a string containing the regex. Differs from 'fnmatch.translate()' in that '*' does not match "special characters" (which are platform-specific). """ pattern_re = fnmatch.translate(pattern) # '?' and '*' in the glob pattern become '.' and '.*' in the RE, which # IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix, # and by extension they shouldn't match such "special characters" under # any OS. So change all non-escaped dots in the RE to match any # character except the special characters (currently: just os.sep). sep = os.sep if os.sep == '\\': # we're using a regex to manipulate a regex, so we need # to escape the backslash twice sep = r'\\\\' escaped = r'\1[^%s]' % sep pattern_re = re.sub(r'((? y, 'gte': lambda x, y: x >= y, 'in': lambda x, y: x in y, 'lt': lambda x, y: x < y, 'lte': lambda x, y: x <= y, 'not': lambda x: not x, 'noteq': lambda x, y: x != y, 'notin': lambda x, y: x not in y, } allowed_values = { 'sys_platform': sys.platform, 'python_version': '%s.%s' % sys.version_info[:2], # parsing sys.platform is not reliable, but there is no other # way to get e.g. 2.7.2+, and the PEP is defined with sys.version 'python_full_version': sys.version.split(' ', 1)[0], 'os_name': os.name, 'platform_in_venv': str(in_venv()), 'platform_release': platform.release(), 'platform_version': platform.version(), 'platform_machine': platform.machine(), 'platform_python_implementation': python_implementation(), } def __init__(self, context=None): """ Initialise an instance. :param context: If specified, names are looked up in this mapping. """ self.context = context or {} self.source = None def get_fragment(self, offset): """ Get the part of the source which is causing a problem. """ fragment_len = 10 s = '%r' % (self.source[offset:offset + fragment_len]) if offset + fragment_len < len(self.source): s += '...' return s def get_handler(self, node_type): """ Get a handler for the specified AST node type. """ return getattr(self, 'do_%s' % node_type, None) def evaluate(self, node, filename=None): """ Evaluate a source string or node, using ``filename`` when displaying errors. """ if isinstance(node, string_types): self.source = node kwargs = {'mode': 'eval'} if filename: kwargs['filename'] = filename try: node = ast.parse(node, **kwargs) except SyntaxError as e: s = self.get_fragment(e.offset) raise SyntaxError('syntax error %s' % s) node_type = node.__class__.__name__.lower() handler = self.get_handler(node_type) if handler is None: if self.source is None: s = '(source not available)' else: s = self.get_fragment(node.col_offset) raise SyntaxError("don't know how to evaluate %r %s" % ( node_type, s)) return handler(node) def get_attr_key(self, node): assert isinstance(node, ast.Attribute), 'attribute node expected' return '%s.%s' % (node.value.id, node.attr) def do_attribute(self, node): if not isinstance(node.value, ast.Name): valid = False else: key = self.get_attr_key(node) valid = key in self.context or key in self.allowed_values if not valid: raise SyntaxError('invalid expression: %s' % key) if key in self.context: result = self.context[key] else: result = self.allowed_values[key] return result def do_boolop(self, node): result = self.evaluate(node.values[0]) is_or = node.op.__class__ is ast.Or is_and = node.op.__class__ is ast.And assert is_or or is_and if (is_and and result) or (is_or and not result): for n in node.values[1:]: result = self.evaluate(n) if (is_or and result) or (is_and and not result): break return result def do_compare(self, node): def sanity_check(lhsnode, rhsnode): valid = True if isinstance(lhsnode, ast.Str) and isinstance(rhsnode, ast.Str): valid = False #elif (isinstance(lhsnode, ast.Attribute) # and isinstance(rhsnode, ast.Attribute)): # klhs = self.get_attr_key(lhsnode) # krhs = self.get_attr_key(rhsnode) # valid = klhs != krhs if not valid: s = self.get_fragment(node.col_offset) raise SyntaxError('Invalid comparison: %s' % s) lhsnode = node.left lhs = self.evaluate(lhsnode) result = True for op, rhsnode in zip(node.ops, node.comparators): sanity_check(lhsnode, rhsnode) op = op.__class__.__name__.lower() if op not in self.operators: raise SyntaxError('unsupported operation: %r' % op) rhs = self.evaluate(rhsnode) result = self.operators[op](lhs, rhs) if not result: break lhs = rhs lhsnode = rhsnode return result def do_expression(self, node): return self.evaluate(node.body) def do_name(self, node): valid = False if node.id in self.context: valid = True result = self.context[node.id] elif node.id in self.allowed_values: valid = True result = self.allowed_values[node.id] if not valid: raise SyntaxError('invalid expression: %s' % node.id) return result def do_str(self, node): return node.s def interpret(marker, execution_context=None): """ Interpret a marker and return a result depending on environment. :param marker: The marker to interpret. :type marker: str :param execution_context: The context used for name lookup. :type execution_context: mapping """ return Evaluator(execution_context).evaluate(marker.strip()) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/metadata.py0000644000076500000240000011345612700725533030501 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """Implementation of the Metadata for Python packages PEPs. Supports all metadata formats (1.0, 1.1, 1.2, and 2.0 experimental). """ from __future__ import unicode_literals import codecs from email import message_from_file import json import logging import re from . import DistlibException, __version__ from .compat import StringIO, string_types, text_type from .markers import interpret from .util import extract_by_key, get_extras from .version import get_scheme, PEP440_VERSION_RE logger = logging.getLogger(__name__) class MetadataMissingError(DistlibException): """A required metadata is missing""" class MetadataConflictError(DistlibException): """Attempt to read or write metadata fields that are conflictual.""" class MetadataUnrecognizedVersionError(DistlibException): """Unknown metadata version number.""" class MetadataInvalidError(DistlibException): """A metadata value is invalid""" # public API of this module __all__ = ['Metadata', 'PKG_INFO_ENCODING', 'PKG_INFO_PREFERRED_VERSION'] # Encoding used for the PKG-INFO files PKG_INFO_ENCODING = 'utf-8' # preferred version. Hopefully will be changed # to 1.2 once PEP 345 is supported everywhere PKG_INFO_PREFERRED_VERSION = '1.1' _LINE_PREFIX_1_2 = re.compile('\n \|') _LINE_PREFIX_PRE_1_2 = re.compile('\n ') _241_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Summary', 'Description', 'Keywords', 'Home-page', 'Author', 'Author-email', 'License') _314_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', 'Keywords', 'Home-page', 'Author', 'Author-email', 'License', 'Classifier', 'Download-URL', 'Obsoletes', 'Provides', 'Requires') _314_MARKERS = ('Obsoletes', 'Provides', 'Requires', 'Classifier', 'Download-URL') _345_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', 'Keywords', 'Home-page', 'Author', 'Author-email', 'Maintainer', 'Maintainer-email', 'License', 'Classifier', 'Download-URL', 'Obsoletes-Dist', 'Project-URL', 'Provides-Dist', 'Requires-Dist', 'Requires-Python', 'Requires-External') _345_MARKERS = ('Provides-Dist', 'Requires-Dist', 'Requires-Python', 'Obsoletes-Dist', 'Requires-External', 'Maintainer', 'Maintainer-email', 'Project-URL') _426_FIELDS = ('Metadata-Version', 'Name', 'Version', 'Platform', 'Supported-Platform', 'Summary', 'Description', 'Keywords', 'Home-page', 'Author', 'Author-email', 'Maintainer', 'Maintainer-email', 'License', 'Classifier', 'Download-URL', 'Obsoletes-Dist', 'Project-URL', 'Provides-Dist', 'Requires-Dist', 'Requires-Python', 'Requires-External', 'Private-Version', 'Obsoleted-By', 'Setup-Requires-Dist', 'Extension', 'Provides-Extra') _426_MARKERS = ('Private-Version', 'Provides-Extra', 'Obsoleted-By', 'Setup-Requires-Dist', 'Extension') _ALL_FIELDS = set() _ALL_FIELDS.update(_241_FIELDS) _ALL_FIELDS.update(_314_FIELDS) _ALL_FIELDS.update(_345_FIELDS) _ALL_FIELDS.update(_426_FIELDS) EXTRA_RE = re.compile(r'''extra\s*==\s*("([^"]+)"|'([^']+)')''') def _version2fieldlist(version): if version == '1.0': return _241_FIELDS elif version == '1.1': return _314_FIELDS elif version == '1.2': return _345_FIELDS elif version == '2.0': return _426_FIELDS raise MetadataUnrecognizedVersionError(version) def _best_version(fields): """Detect the best version depending on the fields used.""" def _has_marker(keys, markers): for marker in markers: if marker in keys: return True return False keys = [] for key, value in fields.items(): if value in ([], 'UNKNOWN', None): continue keys.append(key) possible_versions = ['1.0', '1.1', '1.2', '2.0'] # first let's try to see if a field is not part of one of the version for key in keys: if key not in _241_FIELDS and '1.0' in possible_versions: possible_versions.remove('1.0') if key not in _314_FIELDS and '1.1' in possible_versions: possible_versions.remove('1.1') if key not in _345_FIELDS and '1.2' in possible_versions: possible_versions.remove('1.2') if key not in _426_FIELDS and '2.0' in possible_versions: possible_versions.remove('2.0') # possible_version contains qualified versions if len(possible_versions) == 1: return possible_versions[0] # found ! elif len(possible_versions) == 0: raise MetadataConflictError('Unknown metadata set') # let's see if one unique marker is found is_1_1 = '1.1' in possible_versions and _has_marker(keys, _314_MARKERS) is_1_2 = '1.2' in possible_versions and _has_marker(keys, _345_MARKERS) is_2_0 = '2.0' in possible_versions and _has_marker(keys, _426_MARKERS) if int(is_1_1) + int(is_1_2) + int(is_2_0) > 1: raise MetadataConflictError('You used incompatible 1.1/1.2/2.0 fields') # we have the choice, 1.0, or 1.2, or 2.0 # - 1.0 has a broken Summary field but works with all tools # - 1.1 is to avoid # - 1.2 fixes Summary but has little adoption # - 2.0 adds more features and is very new if not is_1_1 and not is_1_2 and not is_2_0: # we couldn't find any specific marker if PKG_INFO_PREFERRED_VERSION in possible_versions: return PKG_INFO_PREFERRED_VERSION if is_1_1: return '1.1' if is_1_2: return '1.2' return '2.0' _ATTR2FIELD = { 'metadata_version': 'Metadata-Version', 'name': 'Name', 'version': 'Version', 'platform': 'Platform', 'supported_platform': 'Supported-Platform', 'summary': 'Summary', 'description': 'Description', 'keywords': 'Keywords', 'home_page': 'Home-page', 'author': 'Author', 'author_email': 'Author-email', 'maintainer': 'Maintainer', 'maintainer_email': 'Maintainer-email', 'license': 'License', 'classifier': 'Classifier', 'download_url': 'Download-URL', 'obsoletes_dist': 'Obsoletes-Dist', 'provides_dist': 'Provides-Dist', 'requires_dist': 'Requires-Dist', 'setup_requires_dist': 'Setup-Requires-Dist', 'requires_python': 'Requires-Python', 'requires_external': 'Requires-External', 'requires': 'Requires', 'provides': 'Provides', 'obsoletes': 'Obsoletes', 'project_url': 'Project-URL', 'private_version': 'Private-Version', 'obsoleted_by': 'Obsoleted-By', 'extension': 'Extension', 'provides_extra': 'Provides-Extra', } _PREDICATE_FIELDS = ('Requires-Dist', 'Obsoletes-Dist', 'Provides-Dist') _VERSIONS_FIELDS = ('Requires-Python',) _VERSION_FIELDS = ('Version',) _LISTFIELDS = ('Platform', 'Classifier', 'Obsoletes', 'Requires', 'Provides', 'Obsoletes-Dist', 'Provides-Dist', 'Requires-Dist', 'Requires-External', 'Project-URL', 'Supported-Platform', 'Setup-Requires-Dist', 'Provides-Extra', 'Extension') _LISTTUPLEFIELDS = ('Project-URL',) _ELEMENTSFIELD = ('Keywords',) _UNICODEFIELDS = ('Author', 'Maintainer', 'Summary', 'Description') _MISSING = object() _FILESAFE = re.compile('[^A-Za-z0-9.]+') def _get_name_and_version(name, version, for_filename=False): """Return the distribution name with version. If for_filename is true, return a filename-escaped form.""" if for_filename: # For both name and version any runs of non-alphanumeric or '.' # characters are replaced with a single '-'. Additionally any # spaces in the version string become '.' name = _FILESAFE.sub('-', name) version = _FILESAFE.sub('-', version.replace(' ', '.')) return '%s-%s' % (name, version) class LegacyMetadata(object): """The legacy metadata of a release. Supports versions 1.0, 1.1 and 1.2 (auto-detected). You can instantiate the class with one of these arguments (or none): - *path*, the path to a metadata file - *fileobj* give a file-like object with metadata as content - *mapping* is a dict-like object - *scheme* is a version scheme name """ # TODO document the mapping API and UNKNOWN default key def __init__(self, path=None, fileobj=None, mapping=None, scheme='default'): if [path, fileobj, mapping].count(None) < 2: raise TypeError('path, fileobj and mapping are exclusive') self._fields = {} self.requires_files = [] self._dependencies = None self.scheme = scheme if path is not None: self.read(path) elif fileobj is not None: self.read_file(fileobj) elif mapping is not None: self.update(mapping) self.set_metadata_version() def set_metadata_version(self): self._fields['Metadata-Version'] = _best_version(self._fields) def _write_field(self, fileobj, name, value): fileobj.write('%s: %s\n' % (name, value)) def __getitem__(self, name): return self.get(name) def __setitem__(self, name, value): return self.set(name, value) def __delitem__(self, name): field_name = self._convert_name(name) try: del self._fields[field_name] except KeyError: raise KeyError(name) def __contains__(self, name): return (name in self._fields or self._convert_name(name) in self._fields) def _convert_name(self, name): if name in _ALL_FIELDS: return name name = name.replace('-', '_').lower() return _ATTR2FIELD.get(name, name) def _default_value(self, name): if name in _LISTFIELDS or name in _ELEMENTSFIELD: return [] return 'UNKNOWN' def _remove_line_prefix(self, value): if self.metadata_version in ('1.0', '1.1'): return _LINE_PREFIX_PRE_1_2.sub('\n', value) else: return _LINE_PREFIX_1_2.sub('\n', value) def __getattr__(self, name): if name in _ATTR2FIELD: return self[name] raise AttributeError(name) # # Public API # # dependencies = property(_get_dependencies, _set_dependencies) def get_fullname(self, filesafe=False): """Return the distribution name with version. If filesafe is true, return a filename-escaped form.""" return _get_name_and_version(self['Name'], self['Version'], filesafe) def is_field(self, name): """return True if name is a valid metadata key""" name = self._convert_name(name) return name in _ALL_FIELDS def is_multi_field(self, name): name = self._convert_name(name) return name in _LISTFIELDS def read(self, filepath): """Read the metadata values from a file path.""" fp = codecs.open(filepath, 'r', encoding='utf-8') try: self.read_file(fp) finally: fp.close() def read_file(self, fileob): """Read the metadata values from a file object.""" msg = message_from_file(fileob) self._fields['Metadata-Version'] = msg['metadata-version'] # When reading, get all the fields we can for field in _ALL_FIELDS: if field not in msg: continue if field in _LISTFIELDS: # we can have multiple lines values = msg.get_all(field) if field in _LISTTUPLEFIELDS and values is not None: values = [tuple(value.split(',')) for value in values] self.set(field, values) else: # single line value = msg[field] if value is not None and value != 'UNKNOWN': self.set(field, value) self.set_metadata_version() def write(self, filepath, skip_unknown=False): """Write the metadata fields to filepath.""" fp = codecs.open(filepath, 'w', encoding='utf-8') try: self.write_file(fp, skip_unknown) finally: fp.close() def write_file(self, fileobject, skip_unknown=False): """Write the PKG-INFO format data to a file object.""" self.set_metadata_version() for field in _version2fieldlist(self['Metadata-Version']): values = self.get(field) if skip_unknown and values in ('UNKNOWN', [], ['UNKNOWN']): continue if field in _ELEMENTSFIELD: self._write_field(fileobject, field, ','.join(values)) continue if field not in _LISTFIELDS: if field == 'Description': if self.metadata_version in ('1.0', '1.1'): values = values.replace('\n', '\n ') else: values = values.replace('\n', '\n |') values = [values] if field in _LISTTUPLEFIELDS: values = [','.join(value) for value in values] for value in values: self._write_field(fileobject, field, value) def update(self, other=None, **kwargs): """Set metadata values from the given iterable `other` and kwargs. Behavior is like `dict.update`: If `other` has a ``keys`` method, they are looped over and ``self[key]`` is assigned ``other[key]``. Else, ``other`` is an iterable of ``(key, value)`` iterables. Keys that don't match a metadata field or that have an empty value are dropped. """ def _set(key, value): if key in _ATTR2FIELD and value: self.set(self._convert_name(key), value) if not other: # other is None or empty container pass elif hasattr(other, 'keys'): for k in other.keys(): _set(k, other[k]) else: for k, v in other: _set(k, v) if kwargs: for k, v in kwargs.items(): _set(k, v) def set(self, name, value): """Control then set a metadata field.""" name = self._convert_name(name) if ((name in _ELEMENTSFIELD or name == 'Platform') and not isinstance(value, (list, tuple))): if isinstance(value, string_types): value = [v.strip() for v in value.split(',')] else: value = [] elif (name in _LISTFIELDS and not isinstance(value, (list, tuple))): if isinstance(value, string_types): value = [value] else: value = [] if logger.isEnabledFor(logging.WARNING): project_name = self['Name'] scheme = get_scheme(self.scheme) if name in _PREDICATE_FIELDS and value is not None: for v in value: # check that the values are valid if not scheme.is_valid_matcher(v.split(';')[0]): logger.warning( '%r: %r is not valid (field %r)', project_name, v, name) # FIXME this rejects UNKNOWN, is that right? elif name in _VERSIONS_FIELDS and value is not None: if not scheme.is_valid_constraint_list(value): logger.warning('%r: %r is not a valid version (field %r)', project_name, value, name) elif name in _VERSION_FIELDS and value is not None: if not scheme.is_valid_version(value): logger.warning('%r: %r is not a valid version (field %r)', project_name, value, name) if name in _UNICODEFIELDS: if name == 'Description': value = self._remove_line_prefix(value) self._fields[name] = value def get(self, name, default=_MISSING): """Get a metadata field.""" name = self._convert_name(name) if name not in self._fields: if default is _MISSING: default = self._default_value(name) return default if name in _UNICODEFIELDS: value = self._fields[name] return value elif name in _LISTFIELDS: value = self._fields[name] if value is None: return [] res = [] for val in value: if name not in _LISTTUPLEFIELDS: res.append(val) else: # That's for Project-URL res.append((val[0], val[1])) return res elif name in _ELEMENTSFIELD: value = self._fields[name] if isinstance(value, string_types): return value.split(',') return self._fields[name] def check(self, strict=False): """Check if the metadata is compliant. If strict is True then raise if no Name or Version are provided""" self.set_metadata_version() # XXX should check the versions (if the file was loaded) missing, warnings = [], [] for attr in ('Name', 'Version'): # required by PEP 345 if attr not in self: missing.append(attr) if strict and missing != []: msg = 'missing required metadata: %s' % ', '.join(missing) raise MetadataMissingError(msg) for attr in ('Home-page', 'Author'): if attr not in self: missing.append(attr) # checking metadata 1.2 (XXX needs to check 1.1, 1.0) if self['Metadata-Version'] != '1.2': return missing, warnings scheme = get_scheme(self.scheme) def are_valid_constraints(value): for v in value: if not scheme.is_valid_matcher(v.split(';')[0]): return False return True for fields, controller in ((_PREDICATE_FIELDS, are_valid_constraints), (_VERSIONS_FIELDS, scheme.is_valid_constraint_list), (_VERSION_FIELDS, scheme.is_valid_version)): for field in fields: value = self.get(field, None) if value is not None and not controller(value): warnings.append('Wrong value for %r: %s' % (field, value)) return missing, warnings def todict(self, skip_missing=False): """Return fields as a dict. Field names will be converted to use the underscore-lowercase style instead of hyphen-mixed case (i.e. home_page instead of Home-page). """ self.set_metadata_version() mapping_1_0 = ( ('metadata_version', 'Metadata-Version'), ('name', 'Name'), ('version', 'Version'), ('summary', 'Summary'), ('home_page', 'Home-page'), ('author', 'Author'), ('author_email', 'Author-email'), ('license', 'License'), ('description', 'Description'), ('keywords', 'Keywords'), ('platform', 'Platform'), ('classifiers', 'Classifier'), ('download_url', 'Download-URL'), ) data = {} for key, field_name in mapping_1_0: if not skip_missing or field_name in self._fields: data[key] = self[field_name] if self['Metadata-Version'] == '1.2': mapping_1_2 = ( ('requires_dist', 'Requires-Dist'), ('requires_python', 'Requires-Python'), ('requires_external', 'Requires-External'), ('provides_dist', 'Provides-Dist'), ('obsoletes_dist', 'Obsoletes-Dist'), ('project_url', 'Project-URL'), ('maintainer', 'Maintainer'), ('maintainer_email', 'Maintainer-email'), ) for key, field_name in mapping_1_2: if not skip_missing or field_name in self._fields: if key != 'project_url': data[key] = self[field_name] else: data[key] = [','.join(u) for u in self[field_name]] elif self['Metadata-Version'] == '1.1': mapping_1_1 = ( ('provides', 'Provides'), ('requires', 'Requires'), ('obsoletes', 'Obsoletes'), ) for key, field_name in mapping_1_1: if not skip_missing or field_name in self._fields: data[key] = self[field_name] return data def add_requirements(self, requirements): if self['Metadata-Version'] == '1.1': # we can't have 1.1 metadata *and* Setuptools requires for field in ('Obsoletes', 'Requires', 'Provides'): if field in self: del self[field] self['Requires-Dist'] += requirements # Mapping API # TODO could add iter* variants def keys(self): return list(_version2fieldlist(self['Metadata-Version'])) def __iter__(self): for key in self.keys(): yield key def values(self): return [self[key] for key in self.keys()] def items(self): return [(key, self[key]) for key in self.keys()] def __repr__(self): return '<%s %s %s>' % (self.__class__.__name__, self.name, self.version) METADATA_FILENAME = 'pydist.json' WHEEL_METADATA_FILENAME = 'metadata.json' class Metadata(object): """ The metadata of a release. This implementation uses 2.0 (JSON) metadata where possible. If not possible, it wraps a LegacyMetadata instance which handles the key-value metadata format. """ METADATA_VERSION_MATCHER = re.compile('^\d+(\.\d+)*$') NAME_MATCHER = re.compile('^[0-9A-Z]([0-9A-Z_.-]*[0-9A-Z])?$', re.I) VERSION_MATCHER = PEP440_VERSION_RE SUMMARY_MATCHER = re.compile('.{1,2047}') METADATA_VERSION = '2.0' GENERATOR = 'distlib (%s)' % __version__ MANDATORY_KEYS = { 'name': (), 'version': (), 'summary': ('legacy',), } INDEX_KEYS = ('name version license summary description author ' 'author_email keywords platform home_page classifiers ' 'download_url') DEPENDENCY_KEYS = ('extras run_requires test_requires build_requires ' 'dev_requires provides meta_requires obsoleted_by ' 'supports_environments') SYNTAX_VALIDATORS = { 'metadata_version': (METADATA_VERSION_MATCHER, ()), 'name': (NAME_MATCHER, ('legacy',)), 'version': (VERSION_MATCHER, ('legacy',)), 'summary': (SUMMARY_MATCHER, ('legacy',)), } __slots__ = ('_legacy', '_data', 'scheme') def __init__(self, path=None, fileobj=None, mapping=None, scheme='default'): if [path, fileobj, mapping].count(None) < 2: raise TypeError('path, fileobj and mapping are exclusive') self._legacy = None self._data = None self.scheme = scheme #import pdb; pdb.set_trace() if mapping is not None: try: self._validate_mapping(mapping, scheme) self._data = mapping except MetadataUnrecognizedVersionError: self._legacy = LegacyMetadata(mapping=mapping, scheme=scheme) self.validate() else: data = None if path: with open(path, 'rb') as f: data = f.read() elif fileobj: data = fileobj.read() if data is None: # Initialised with no args - to be added self._data = { 'metadata_version': self.METADATA_VERSION, 'generator': self.GENERATOR, } else: if not isinstance(data, text_type): data = data.decode('utf-8') try: self._data = json.loads(data) self._validate_mapping(self._data, scheme) except ValueError: # Note: MetadataUnrecognizedVersionError does not # inherit from ValueError (it's a DistlibException, # which should not inherit from ValueError). # The ValueError comes from the json.load - if that # succeeds and we get a validation error, we want # that to propagate self._legacy = LegacyMetadata(fileobj=StringIO(data), scheme=scheme) self.validate() common_keys = set(('name', 'version', 'license', 'keywords', 'summary')) none_list = (None, list) none_dict = (None, dict) mapped_keys = { 'run_requires': ('Requires-Dist', list), 'build_requires': ('Setup-Requires-Dist', list), 'dev_requires': none_list, 'test_requires': none_list, 'meta_requires': none_list, 'extras': ('Provides-Extra', list), 'modules': none_list, 'namespaces': none_list, 'exports': none_dict, 'commands': none_dict, 'classifiers': ('Classifier', list), 'source_url': ('Download-URL', None), 'metadata_version': ('Metadata-Version', None), } del none_list, none_dict def __getattribute__(self, key): common = object.__getattribute__(self, 'common_keys') mapped = object.__getattribute__(self, 'mapped_keys') if key in mapped: lk, maker = mapped[key] if self._legacy: if lk is None: result = None if maker is None else maker() else: result = self._legacy.get(lk) else: value = None if maker is None else maker() if key not in ('commands', 'exports', 'modules', 'namespaces', 'classifiers'): result = self._data.get(key, value) else: # special cases for PEP 459 sentinel = object() result = sentinel d = self._data.get('extensions') if d: if key == 'commands': result = d.get('python.commands', value) elif key == 'classifiers': d = d.get('python.details') if d: result = d.get(key, value) else: d = d.get('python.exports') if d: result = d.get(key, value) if result is sentinel: result = value elif key not in common: result = object.__getattribute__(self, key) elif self._legacy: result = self._legacy.get(key) else: result = self._data.get(key) return result def _validate_value(self, key, value, scheme=None): if key in self.SYNTAX_VALIDATORS: pattern, exclusions = self.SYNTAX_VALIDATORS[key] if (scheme or self.scheme) not in exclusions: m = pattern.match(value) if not m: raise MetadataInvalidError('%r is an invalid value for ' 'the %r property' % (value, key)) def __setattr__(self, key, value): self._validate_value(key, value) common = object.__getattribute__(self, 'common_keys') mapped = object.__getattribute__(self, 'mapped_keys') if key in mapped: lk, _ = mapped[key] if self._legacy: if lk is None: raise NotImplementedError self._legacy[lk] = value elif key not in ('commands', 'exports', 'modules', 'namespaces', 'classifiers'): self._data[key] = value else: # special cases for PEP 459 d = self._data.setdefault('extensions', {}) if key == 'commands': d['python.commands'] = value elif key == 'classifiers': d = d.setdefault('python.details', {}) d[key] = value else: d = d.setdefault('python.exports', {}) d[key] = value elif key not in common: object.__setattr__(self, key, value) else: if key == 'keywords': if isinstance(value, string_types): value = value.strip() if value: value = value.split() else: value = [] if self._legacy: self._legacy[key] = value else: self._data[key] = value @property def name_and_version(self): return _get_name_and_version(self.name, self.version, True) @property def provides(self): if self._legacy: result = self._legacy['Provides-Dist'] else: result = self._data.setdefault('provides', []) s = '%s (%s)' % (self.name, self.version) if s not in result: result.append(s) return result @provides.setter def provides(self, value): if self._legacy: self._legacy['Provides-Dist'] = value else: self._data['provides'] = value def get_requirements(self, reqts, extras=None, env=None): """ Base method to get dependencies, given a set of extras to satisfy and an optional environment context. :param reqts: A list of sometimes-wanted dependencies, perhaps dependent on extras and environment. :param extras: A list of optional components being requested. :param env: An optional environment for marker evaluation. """ if self._legacy: result = reqts else: result = [] extras = get_extras(extras or [], self.extras) for d in reqts: if 'extra' not in d and 'environment' not in d: # unconditional include = True else: if 'extra' not in d: # Not extra-dependent - only environment-dependent include = True else: include = d.get('extra') in extras if include: # Not excluded because of extras, check environment marker = d.get('environment') if marker: include = interpret(marker, env) if include: result.extend(d['requires']) for key in ('build', 'dev', 'test'): e = ':%s:' % key if e in extras: extras.remove(e) # A recursive call, but it should terminate since 'test' # has been removed from the extras reqts = self._data.get('%s_requires' % key, []) result.extend(self.get_requirements(reqts, extras=extras, env=env)) return result @property def dictionary(self): if self._legacy: return self._from_legacy() return self._data @property def dependencies(self): if self._legacy: raise NotImplementedError else: return extract_by_key(self._data, self.DEPENDENCY_KEYS) @dependencies.setter def dependencies(self, value): if self._legacy: raise NotImplementedError else: self._data.update(value) def _validate_mapping(self, mapping, scheme): if mapping.get('metadata_version') != self.METADATA_VERSION: raise MetadataUnrecognizedVersionError() missing = [] for key, exclusions in self.MANDATORY_KEYS.items(): if key not in mapping: if scheme not in exclusions: missing.append(key) if missing: msg = 'Missing metadata items: %s' % ', '.join(missing) raise MetadataMissingError(msg) for k, v in mapping.items(): self._validate_value(k, v, scheme) def validate(self): if self._legacy: missing, warnings = self._legacy.check(True) if missing or warnings: logger.warning('Metadata: missing: %s, warnings: %s', missing, warnings) else: self._validate_mapping(self._data, self.scheme) def todict(self): if self._legacy: return self._legacy.todict(True) else: result = extract_by_key(self._data, self.INDEX_KEYS) return result def _from_legacy(self): assert self._legacy and not self._data result = { 'metadata_version': self.METADATA_VERSION, 'generator': self.GENERATOR, } lmd = self._legacy.todict(True) # skip missing ones for k in ('name', 'version', 'license', 'summary', 'description', 'classifier'): if k in lmd: if k == 'classifier': nk = 'classifiers' else: nk = k result[nk] = lmd[k] kw = lmd.get('Keywords', []) if kw == ['']: kw = [] result['keywords'] = kw keys = (('requires_dist', 'run_requires'), ('setup_requires_dist', 'build_requires')) for ok, nk in keys: if ok in lmd and lmd[ok]: result[nk] = [{'requires': lmd[ok]}] result['provides'] = self.provides author = {} maintainer = {} return result LEGACY_MAPPING = { 'name': 'Name', 'version': 'Version', 'license': 'License', 'summary': 'Summary', 'description': 'Description', 'classifiers': 'Classifier', } def _to_legacy(self): def process_entries(entries): reqts = set() for e in entries: extra = e.get('extra') env = e.get('environment') rlist = e['requires'] for r in rlist: if not env and not extra: reqts.add(r) else: marker = '' if extra: marker = 'extra == "%s"' % extra if env: if marker: marker = '(%s) and %s' % (env, marker) else: marker = env reqts.add(';'.join((r, marker))) return reqts assert self._data and not self._legacy result = LegacyMetadata() nmd = self._data for nk, ok in self.LEGACY_MAPPING.items(): if nk in nmd: result[ok] = nmd[nk] r1 = process_entries(self.run_requires + self.meta_requires) r2 = process_entries(self.build_requires + self.dev_requires) if self.extras: result['Provides-Extra'] = sorted(self.extras) result['Requires-Dist'] = sorted(r1) result['Setup-Requires-Dist'] = sorted(r2) # TODO: other fields such as contacts return result def write(self, path=None, fileobj=None, legacy=False, skip_unknown=True): if [path, fileobj].count(None) != 1: raise ValueError('Exactly one of path and fileobj is needed') self.validate() if legacy: if self._legacy: legacy_md = self._legacy else: legacy_md = self._to_legacy() if path: legacy_md.write(path, skip_unknown=skip_unknown) else: legacy_md.write_file(fileobj, skip_unknown=skip_unknown) else: if self._legacy: d = self._from_legacy() else: d = self._data if fileobj: json.dump(d, fileobj, ensure_ascii=True, indent=2, sort_keys=True) else: with codecs.open(path, 'w', 'utf-8') as f: json.dump(d, f, ensure_ascii=True, indent=2, sort_keys=True) def add_requirements(self, requirements): if self._legacy: self._legacy.add_requirements(requirements) else: run_requires = self._data.setdefault('run_requires', []) always = None for entry in run_requires: if 'environment' not in entry and 'extra' not in entry: always = entry break if always is None: always = { 'requires': requirements } run_requires.insert(0, always) else: rset = set(always['requires']) | set(requirements) always['requires'] = sorted(rset) def __repr__(self): name = self.name or '(no name)' version = self.version or 'no version' return '<%s %s %s (%s)>' % (self.__class__.__name__, self.metadata_version, name, version) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/resources.py0000644000076500000240000002457412700725533030735 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2013-2016 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # from __future__ import unicode_literals import bisect import io import logging import os import pkgutil import shutil import sys import types import zipimport from . import DistlibException from .util import cached_property, get_cache_base, path_to_cache_dir, Cache logger = logging.getLogger(__name__) cache = None # created when needed class ResourceCache(Cache): def __init__(self, base=None): if base is None: # Use native string to avoid issues on 2.x: see Python #20140. base = os.path.join(get_cache_base(), str('resource-cache')) super(ResourceCache, self).__init__(base) def is_stale(self, resource, path): """ Is the cache stale for the given resource? :param resource: The :class:`Resource` being cached. :param path: The path of the resource in the cache. :return: True if the cache is stale. """ # Cache invalidation is a hard problem :-) return True def get(self, resource): """ Get a resource into the cache, :param resource: A :class:`Resource` instance. :return: The pathname of the resource in the cache. """ prefix, path = resource.finder.get_cache_info(resource) if prefix is None: result = path else: result = os.path.join(self.base, self.prefix_to_dir(prefix), path) dirname = os.path.dirname(result) if not os.path.isdir(dirname): os.makedirs(dirname) if not os.path.exists(result): stale = True else: stale = self.is_stale(resource, path) if stale: # write the bytes of the resource to the cache location with open(result, 'wb') as f: f.write(resource.bytes) return result class ResourceBase(object): def __init__(self, finder, name): self.finder = finder self.name = name class Resource(ResourceBase): """ A class representing an in-package resource, such as a data file. This is not normally instantiated by user code, but rather by a :class:`ResourceFinder` which manages the resource. """ is_container = False # Backwards compatibility def as_stream(self): """ Get the resource as a stream. This is not a property to make it obvious that it returns a new stream each time. """ return self.finder.get_stream(self) @cached_property def file_path(self): global cache if cache is None: cache = ResourceCache() return cache.get(self) @cached_property def bytes(self): return self.finder.get_bytes(self) @cached_property def size(self): return self.finder.get_size(self) class ResourceContainer(ResourceBase): is_container = True # Backwards compatibility @cached_property def resources(self): return self.finder.get_resources(self) class ResourceFinder(object): """ Resource finder for file system resources. """ if sys.platform.startswith('java'): skipped_extensions = ('.pyc', '.pyo', '.class') else: skipped_extensions = ('.pyc', '.pyo') def __init__(self, module): self.module = module self.loader = getattr(module, '__loader__', None) self.base = os.path.dirname(getattr(module, '__file__', '')) def _adjust_path(self, path): return os.path.realpath(path) def _make_path(self, resource_name): # Issue #50: need to preserve type of path on Python 2.x # like os.path._get_sep if isinstance(resource_name, bytes): # should only happen on 2.x sep = b'/' else: sep = '/' parts = resource_name.split(sep) parts.insert(0, self.base) result = os.path.join(*parts) return self._adjust_path(result) def _find(self, path): return os.path.exists(path) def get_cache_info(self, resource): return None, resource.path def find(self, resource_name): path = self._make_path(resource_name) if not self._find(path): result = None else: if self._is_directory(path): result = ResourceContainer(self, resource_name) else: result = Resource(self, resource_name) result.path = path return result def get_stream(self, resource): return open(resource.path, 'rb') def get_bytes(self, resource): with open(resource.path, 'rb') as f: return f.read() def get_size(self, resource): return os.path.getsize(resource.path) def get_resources(self, resource): def allowed(f): return (f != '__pycache__' and not f.endswith(self.skipped_extensions)) return set([f for f in os.listdir(resource.path) if allowed(f)]) def is_container(self, resource): return self._is_directory(resource.path) _is_directory = staticmethod(os.path.isdir) def iterator(self, resource_name): resource = self.find(resource_name) if resource is not None: todo = [resource] while todo: resource = todo.pop(0) yield resource if resource.is_container: rname = resource.name for name in resource.resources: if not rname: new_name = name else: new_name = '/'.join([rname, name]) child = self.find(new_name) if child.is_container: todo.append(child) else: yield child class ZipResourceFinder(ResourceFinder): """ Resource finder for resources in .zip files. """ def __init__(self, module): super(ZipResourceFinder, self).__init__(module) archive = self.loader.archive self.prefix_len = 1 + len(archive) # PyPy doesn't have a _files attr on zipimporter, and you can't set one if hasattr(self.loader, '_files'): self._files = self.loader._files else: self._files = zipimport._zip_directory_cache[archive] self.index = sorted(self._files) def _adjust_path(self, path): return path def _find(self, path): path = path[self.prefix_len:] if path in self._files: result = True else: if path and path[-1] != os.sep: path = path + os.sep i = bisect.bisect(self.index, path) try: result = self.index[i].startswith(path) except IndexError: result = False if not result: logger.debug('_find failed: %r %r', path, self.loader.prefix) else: logger.debug('_find worked: %r %r', path, self.loader.prefix) return result def get_cache_info(self, resource): prefix = self.loader.archive path = resource.path[1 + len(prefix):] return prefix, path def get_bytes(self, resource): return self.loader.get_data(resource.path) def get_stream(self, resource): return io.BytesIO(self.get_bytes(resource)) def get_size(self, resource): path = resource.path[self.prefix_len:] return self._files[path][3] def get_resources(self, resource): path = resource.path[self.prefix_len:] if path and path[-1] != os.sep: path += os.sep plen = len(path) result = set() i = bisect.bisect(self.index, path) while i < len(self.index): if not self.index[i].startswith(path): break s = self.index[i][plen:] result.add(s.split(os.sep, 1)[0]) # only immediate children i += 1 return result def _is_directory(self, path): path = path[self.prefix_len:] if path and path[-1] != os.sep: path += os.sep i = bisect.bisect(self.index, path) try: result = self.index[i].startswith(path) except IndexError: result = False return result _finder_registry = { type(None): ResourceFinder, zipimport.zipimporter: ZipResourceFinder } try: import _frozen_importlib _finder_registry[_frozen_importlib.SourceFileLoader] = ResourceFinder _finder_registry[_frozen_importlib.FileFinder] = ResourceFinder except (ImportError, AttributeError): pass def register_finder(loader, finder_maker): _finder_registry[type(loader)] = finder_maker _finder_cache = {} def finder(package): """ Return a resource finder for a package. :param package: The name of the package. :return: A :class:`ResourceFinder` instance for the package. """ if package in _finder_cache: result = _finder_cache[package] else: if package not in sys.modules: __import__(package) module = sys.modules[package] path = getattr(module, '__path__', None) if path is None: raise DistlibException('You cannot get a finder for a module, ' 'only for a package') loader = getattr(module, '__loader__', None) finder_maker = _finder_registry.get(type(loader)) if finder_maker is None: raise DistlibException('Unable to locate finder for %r' % package) result = finder_maker(module) _finder_cache[package] = result return result _dummy_module = types.ModuleType(str('__dummy__')) def finder_for_path(path): """ Return a resource finder for a path, which should represent a container. :param path: The path. :return: A :class:`ResourceFinder` instance for the path. """ result = None # calls any path hooks, gets importer into cache pkgutil.get_importer(path) loader = sys.path_importer_cache.get(path) finder = _finder_registry.get(type(loader)) if finder: module = _dummy_module module.__file__ = os.path.join(path, '') module.__loader__ = loader result = finder(module) return result feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/scripts.py0000644000076500000240000003556712700725533030416 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2013-2015 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # from io import BytesIO import logging import os import re import struct import sys from .compat import sysconfig, detect_encoding, ZipFile from .resources import finder from .util import (FileOperator, get_export_entry, convert_path, get_executable, in_venv) logger = logging.getLogger(__name__) _DEFAULT_MANIFEST = ''' '''.strip() # check if Python is called on the first line with this expression FIRST_LINE_RE = re.compile(b'^#!.*pythonw?[0-9.]*([ \t].*)?$') SCRIPT_TEMPLATE = '''# -*- coding: utf-8 -*- if __name__ == '__main__': import sys, re def _resolve(module, func): __import__(module) mod = sys.modules[module] parts = func.split('.') result = getattr(mod, parts.pop(0)) for p in parts: result = getattr(result, p) return result try: sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) func = _resolve('%(module)s', '%(func)s') rc = func() # None interpreted as 0 except Exception as e: # only supporting Python >= 2.6 sys.stderr.write('%%s\\n' %% e) rc = 1 sys.exit(rc) ''' def _enquote_executable(executable): if ' ' in executable: # make sure we quote only the executable in case of env # for example /usr/bin/env "/dir with spaces/bin/jython" # instead of "/usr/bin/env /dir with spaces/bin/jython" # otherwise whole if executable.startswith('/usr/bin/env '): env, _executable = executable.split(' ', 1) if ' ' in _executable and not _executable.startswith('"'): executable = '%s "%s"' % (env, _executable) else: if not executable.startswith('"'): executable = '"%s"' % executable return executable class ScriptMaker(object): """ A class to copy or create scripts from source scripts or callable specifications. """ script_template = SCRIPT_TEMPLATE executable = None # for shebangs def __init__(self, source_dir, target_dir, add_launchers=True, dry_run=False, fileop=None): self.source_dir = source_dir self.target_dir = target_dir self.add_launchers = add_launchers self.force = False self.clobber = False # It only makes sense to set mode bits on POSIX. self.set_mode = (os.name == 'posix') or (os.name == 'java' and os._name == 'posix') self.variants = set(('', 'X.Y')) self._fileop = fileop or FileOperator(dry_run) self._is_nt = os.name == 'nt' or ( os.name == 'java' and os._name == 'nt') def _get_alternate_executable(self, executable, options): if options.get('gui', False) and self._is_nt: # pragma: no cover dn, fn = os.path.split(executable) fn = fn.replace('python', 'pythonw') executable = os.path.join(dn, fn) return executable if sys.platform.startswith('java'): # pragma: no cover def _is_shell(self, executable): """ Determine if the specified executable is a script (contains a #! line) """ try: with open(executable) as fp: return fp.read(2) == '#!' except (OSError, IOError): logger.warning('Failed to open %s', executable) return False def _fix_jython_executable(self, executable): if self._is_shell(executable): # Workaround for Jython is not needed on Linux systems. import java if java.lang.System.getProperty('os.name') == 'Linux': return executable elif executable.lower().endswith('jython.exe'): # Use wrapper exe for Jython on Windows return executable return '/usr/bin/env %s' % executable def _get_shebang(self, encoding, post_interp=b'', options=None): enquote = True if self.executable: executable = self.executable enquote = False # assume this will be taken care of elif not sysconfig.is_python_build(): executable = get_executable() elif in_venv(): # pragma: no cover executable = os.path.join(sysconfig.get_path('scripts'), 'python%s' % sysconfig.get_config_var('EXE')) else: # pragma: no cover executable = os.path.join( sysconfig.get_config_var('BINDIR'), 'python%s%s' % (sysconfig.get_config_var('VERSION'), sysconfig.get_config_var('EXE'))) if options: executable = self._get_alternate_executable(executable, options) if sys.platform.startswith('java'): # pragma: no cover executable = self._fix_jython_executable(executable) # Normalise case for Windows executable = os.path.normcase(executable) # If the user didn't specify an executable, it may be necessary to # cater for executable paths with spaces (not uncommon on Windows) if enquote: executable = _enquote_executable(executable) # Issue #51: don't use fsencode, since we later try to # check that the shebang is decodable using utf-8. executable = executable.encode('utf-8') # in case of IronPython, play safe and enable frames support if (sys.platform == 'cli' and '-X:Frames' not in post_interp and '-X:FullFrames' not in post_interp): # pragma: no cover post_interp += b' -X:Frames' shebang = b'#!' + executable + post_interp + b'\n' # Python parser starts to read a script using UTF-8 until # it gets a #coding:xxx cookie. The shebang has to be the # first line of a file, the #coding:xxx cookie cannot be # written before. So the shebang has to be decodable from # UTF-8. try: shebang.decode('utf-8') except UnicodeDecodeError: # pragma: no cover raise ValueError( 'The shebang (%r) is not decodable from utf-8' % shebang) # If the script is encoded to a custom encoding (use a # #coding:xxx cookie), the shebang has to be decodable from # the script encoding too. if encoding != 'utf-8': try: shebang.decode(encoding) except UnicodeDecodeError: # pragma: no cover raise ValueError( 'The shebang (%r) is not decodable ' 'from the script encoding (%r)' % (shebang, encoding)) return shebang def _get_script_text(self, entry): return self.script_template % dict(module=entry.prefix, func=entry.suffix) manifest = _DEFAULT_MANIFEST def get_manifest(self, exename): base = os.path.basename(exename) return self.manifest % base def _write_script(self, names, shebang, script_bytes, filenames, ext): use_launcher = self.add_launchers and self._is_nt linesep = os.linesep.encode('utf-8') if not use_launcher: script_bytes = shebang + linesep + script_bytes else: # pragma: no cover if ext == 'py': launcher = self._get_launcher('t') else: launcher = self._get_launcher('w') stream = BytesIO() with ZipFile(stream, 'w') as zf: zf.writestr('__main__.py', script_bytes) zip_data = stream.getvalue() script_bytes = launcher + shebang + linesep + zip_data for name in names: outname = os.path.join(self.target_dir, name) if use_launcher: # pragma: no cover n, e = os.path.splitext(outname) if e.startswith('.py'): outname = n outname = '%s.exe' % outname try: self._fileop.write_binary_file(outname, script_bytes) except Exception: # Failed writing an executable - it might be in use. logger.warning('Failed to write executable - trying to ' 'use .deleteme logic') dfname = '%s.deleteme' % outname if os.path.exists(dfname): os.remove(dfname) # Not allowed to fail here os.rename(outname, dfname) # nor here self._fileop.write_binary_file(outname, script_bytes) logger.debug('Able to replace executable using ' '.deleteme logic') try: os.remove(dfname) except Exception: pass # still in use - ignore error else: if self._is_nt and not outname.endswith('.' + ext): # pragma: no cover outname = '%s.%s' % (outname, ext) if os.path.exists(outname) and not self.clobber: logger.warning('Skipping existing file %s', outname) continue self._fileop.write_binary_file(outname, script_bytes) if self.set_mode: self._fileop.set_executable_mode([outname]) filenames.append(outname) def _make_script(self, entry, filenames, options=None): post_interp = b'' if options: args = options.get('interpreter_args', []) if args: args = ' %s' % ' '.join(args) post_interp = args.encode('utf-8') shebang = self._get_shebang('utf-8', post_interp, options=options) script = self._get_script_text(entry).encode('utf-8') name = entry.name scriptnames = set() if '' in self.variants: scriptnames.add(name) if 'X' in self.variants: scriptnames.add('%s%s' % (name, sys.version[0])) if 'X.Y' in self.variants: scriptnames.add('%s-%s' % (name, sys.version[:3])) if options and options.get('gui', False): ext = 'pyw' else: ext = 'py' self._write_script(scriptnames, shebang, script, filenames, ext) def _copy_script(self, script, filenames): adjust = False script = os.path.join(self.source_dir, convert_path(script)) outname = os.path.join(self.target_dir, os.path.basename(script)) if not self.force and not self._fileop.newer(script, outname): logger.debug('not copying %s (up-to-date)', script) return # Always open the file, but ignore failures in dry-run mode -- # that way, we'll get accurate feedback if we can read the # script. try: f = open(script, 'rb') except IOError: # pragma: no cover if not self.dry_run: raise f = None else: first_line = f.readline() if not first_line: # pragma: no cover logger.warning('%s: %s is an empty file (skipping)', self.get_command_name(), script) return match = FIRST_LINE_RE.match(first_line.replace(b'\r\n', b'\n')) if match: adjust = True post_interp = match.group(1) or b'' if not adjust: if f: f.close() self._fileop.copy_file(script, outname) if self.set_mode: self._fileop.set_executable_mode([outname]) filenames.append(outname) else: logger.info('copying and adjusting %s -> %s', script, self.target_dir) if not self._fileop.dry_run: encoding, lines = detect_encoding(f.readline) f.seek(0) shebang = self._get_shebang(encoding, post_interp) if b'pythonw' in first_line: # pragma: no cover ext = 'pyw' else: ext = 'py' n = os.path.basename(outname) self._write_script([n], shebang, f.read(), filenames, ext) if f: f.close() @property def dry_run(self): return self._fileop.dry_run @dry_run.setter def dry_run(self, value): self._fileop.dry_run = value if os.name == 'nt' or (os.name == 'java' and os._name == 'nt'): # pragma: no cover # Executable launcher support. # Launchers are from https://bitbucket.org/vinay.sajip/simple_launcher/ def _get_launcher(self, kind): if struct.calcsize('P') == 8: # 64-bit bits = '64' else: bits = '32' name = '%s%s.exe' % (kind, bits) # Issue 31: don't hardcode an absolute package name, but # determine it relative to the current package distlib_package = __name__.rsplit('.', 1)[0] result = finder(distlib_package).find(name).bytes return result # Public API follows def make(self, specification, options=None): """ Make a script. :param specification: The specification, which is either a valid export entry specification (to make a script from a callable) or a filename (to make a script by copying from a source location). :param options: A dictionary of options controlling script generation. :return: A list of all absolute pathnames written to. """ filenames = [] entry = get_export_entry(specification) if entry is None: self._copy_script(specification, filenames) else: self._make_script(entry, filenames, options=options) return filenames def make_multiple(self, specifications, options=None): """ Take a list of specifications and make scripts from them, :param specifications: A list of specifications. :return: A list of all absolute pathnames written to, """ filenames = [] for specification in specifications: filenames.extend(self.make(specification, options)) return filenames feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/util.py0000644000076500000240000014523412700725533027675 0ustar jmstaff00000000000000# # Copyright (C) 2012-2016 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # import codecs from collections import deque import contextlib import csv from glob import iglob as std_iglob import io import json import logging import os import py_compile import re import shutil import socket import ssl import subprocess import sys import tarfile import tempfile import textwrap try: import threading except ImportError: import dummy_threading as threading import time from . import DistlibException from .compat import (string_types, text_type, shutil, raw_input, StringIO, cache_from_source, urlopen, urljoin, httplib, xmlrpclib, splittype, HTTPHandler, HTTPSHandler as BaseHTTPSHandler, BaseConfigurator, valid_ident, Container, configparser, URLError, match_hostname, CertificateError, ZipFile) logger = logging.getLogger(__name__) # # Requirement parsing code for name + optional constraints + optional extras # # e.g. 'foo >= 1.2, < 2.0 [bar, baz]' # # The regex can seem a bit hairy, so we build it up out of smaller pieces # which are manageable. # COMMA = r'\s*,\s*' COMMA_RE = re.compile(COMMA) IDENT = r'(\w|[.-])+' EXTRA_IDENT = r'(\*|:(\*|\w+):|' + IDENT + ')' VERSPEC = IDENT + r'\*?' RELOP = '([<>=!~]=)|[<>]' # # The first relop is optional - if absent, will be taken as '~=' # BARE_CONSTRAINTS = ('(' + RELOP + r')?\s*(' + VERSPEC + ')(' + COMMA + '(' + RELOP + r')\s*(' + VERSPEC + '))*') DIRECT_REF = '(from\s+(?P.*))' # # Either the bare constraints or the bare constraints in parentheses # CONSTRAINTS = (r'\(\s*(?P' + BARE_CONSTRAINTS + '|' + DIRECT_REF + r')\s*\)|(?P' + BARE_CONSTRAINTS + '\s*)') EXTRA_LIST = EXTRA_IDENT + '(' + COMMA + EXTRA_IDENT + ')*' EXTRAS = r'\[\s*(?P' + EXTRA_LIST + r')?\s*\]' REQUIREMENT = ('(?P' + IDENT + r')\s*(' + EXTRAS + r'\s*)?(\s*' + CONSTRAINTS + ')?$') REQUIREMENT_RE = re.compile(REQUIREMENT) # # Used to scan through the constraints # RELOP_IDENT = '(?P' + RELOP + r')\s*(?P' + VERSPEC + ')' RELOP_IDENT_RE = re.compile(RELOP_IDENT) def parse_requirement(s): def get_constraint(m): d = m.groupdict() return d['op'], d['vn'] result = None m = REQUIREMENT_RE.match(s) if m: d = m.groupdict() name = d['dn'] cons = d['c1'] or d['c2'] if not d['diref']: url = None else: # direct reference cons = None url = d['diref'].strip() if not cons: cons = None constr = '' rs = d['dn'] else: if cons[0] not in '<>!=': cons = '~=' + cons iterator = RELOP_IDENT_RE.finditer(cons) cons = [get_constraint(m) for m in iterator] rs = '%s (%s)' % (name, ', '.join(['%s %s' % con for con in cons])) if not d['ex']: extras = None else: extras = COMMA_RE.split(d['ex']) result = Container(name=name, constraints=cons, extras=extras, requirement=rs, source=s, url=url) return result def get_resources_dests(resources_root, rules): """Find destinations for resources files""" def get_rel_path(base, path): # normalizes and returns a lstripped-/-separated path base = base.replace(os.path.sep, '/') path = path.replace(os.path.sep, '/') assert path.startswith(base) return path[len(base):].lstrip('/') destinations = {} for base, suffix, dest in rules: prefix = os.path.join(resources_root, base) for abs_base in iglob(prefix): abs_glob = os.path.join(abs_base, suffix) for abs_path in iglob(abs_glob): resource_file = get_rel_path(resources_root, abs_path) if dest is None: # remove the entry if it was here destinations.pop(resource_file, None) else: rel_path = get_rel_path(abs_base, abs_path) rel_dest = dest.replace(os.path.sep, '/').rstrip('/') destinations[resource_file] = rel_dest + '/' + rel_path return destinations def in_venv(): if hasattr(sys, 'real_prefix'): # virtualenv venvs result = True else: # PEP 405 venvs result = sys.prefix != getattr(sys, 'base_prefix', sys.prefix) return result def get_executable(): # The __PYVENV_LAUNCHER__ dance is apparently no longer needed, as # changes to the stub launcher mean that sys.executable always points # to the stub on OS X # if sys.platform == 'darwin' and ('__PYVENV_LAUNCHER__' # in os.environ): # result = os.environ['__PYVENV_LAUNCHER__'] # else: # result = sys.executable # return result return os.path.normcase(sys.executable) def proceed(prompt, allowed_chars, error_prompt=None, default=None): p = prompt while True: s = raw_input(p) p = prompt if not s and default: s = default if s: c = s[0].lower() if c in allowed_chars: break if error_prompt: p = '%c: %s\n%s' % (c, error_prompt, prompt) return c def extract_by_key(d, keys): if isinstance(keys, string_types): keys = keys.split() result = {} for key in keys: if key in d: result[key] = d[key] return result def read_exports(stream): if sys.version_info[0] >= 3: # needs to be a text stream stream = codecs.getreader('utf-8')(stream) # Try to load as JSON, falling back on legacy format data = stream.read() stream = StringIO(data) try: jdata = json.load(stream) result = jdata['extensions']['python.exports']['exports'] for group, entries in result.items(): for k, v in entries.items(): s = '%s = %s' % (k, v) entry = get_export_entry(s) assert entry is not None entries[k] = entry return result except Exception: stream.seek(0, 0) def read_stream(cp, stream): if hasattr(cp, 'read_file'): cp.read_file(stream) else: cp.readfp(stream) cp = configparser.ConfigParser() try: read_stream(cp, stream) except configparser.MissingSectionHeaderError: stream.close() data = textwrap.dedent(data) stream = StringIO(data) read_stream(cp, stream) result = {} for key in cp.sections(): result[key] = entries = {} for name, value in cp.items(key): s = '%s = %s' % (name, value) entry = get_export_entry(s) assert entry is not None #entry.dist = self entries[name] = entry return result def write_exports(exports, stream): if sys.version_info[0] >= 3: # needs to be a text stream stream = codecs.getwriter('utf-8')(stream) cp = configparser.ConfigParser() for k, v in exports.items(): # TODO check k, v for valid values cp.add_section(k) for entry in v.values(): if entry.suffix is None: s = entry.prefix else: s = '%s:%s' % (entry.prefix, entry.suffix) if entry.flags: s = '%s [%s]' % (s, ', '.join(entry.flags)) cp.set(k, entry.name, s) cp.write(stream) @contextlib.contextmanager def tempdir(): td = tempfile.mkdtemp() try: yield td finally: shutil.rmtree(td) @contextlib.contextmanager def chdir(d): cwd = os.getcwd() try: os.chdir(d) yield finally: os.chdir(cwd) @contextlib.contextmanager def socket_timeout(seconds=15): cto = socket.getdefaulttimeout() try: socket.setdefaulttimeout(seconds) yield finally: socket.setdefaulttimeout(cto) class cached_property(object): def __init__(self, func): self.func = func #for attr in ('__name__', '__module__', '__doc__'): # setattr(self, attr, getattr(func, attr, None)) def __get__(self, obj, cls=None): if obj is None: return self value = self.func(obj) object.__setattr__(obj, self.func.__name__, value) #obj.__dict__[self.func.__name__] = value = self.func(obj) return value def convert_path(pathname): """Return 'pathname' as a name that will work on the native filesystem. The path is split on '/' and put back together again using the current directory separator. Needed because filenames in the setup script are always supplied in Unix style, and have to be converted to the local convention before we can actually use them in the filesystem. Raises ValueError on non-Unix-ish systems if 'pathname' either starts or ends with a slash. """ if os.sep == '/': return pathname if not pathname: return pathname if pathname[0] == '/': raise ValueError("path '%s' cannot be absolute" % pathname) if pathname[-1] == '/': raise ValueError("path '%s' cannot end with '/'" % pathname) paths = pathname.split('/') while os.curdir in paths: paths.remove(os.curdir) if not paths: return os.curdir return os.path.join(*paths) class FileOperator(object): def __init__(self, dry_run=False): self.dry_run = dry_run self.ensured = set() self._init_record() def _init_record(self): self.record = False self.files_written = set() self.dirs_created = set() def record_as_written(self, path): if self.record: self.files_written.add(path) def newer(self, source, target): """Tell if the target is newer than the source. Returns true if 'source' exists and is more recently modified than 'target', or if 'source' exists and 'target' doesn't. Returns false if both exist and 'target' is the same age or younger than 'source'. Raise PackagingFileError if 'source' does not exist. Note that this test is not very accurate: files created in the same second will have the same "age". """ if not os.path.exists(source): raise DistlibException("file '%r' does not exist" % os.path.abspath(source)) if not os.path.exists(target): return True return os.stat(source).st_mtime > os.stat(target).st_mtime def copy_file(self, infile, outfile, check=True): """Copy a file respecting dry-run and force flags. """ self.ensure_dir(os.path.dirname(outfile)) logger.info('Copying %s to %s', infile, outfile) if not self.dry_run: msg = None if check: if os.path.islink(outfile): msg = '%s is a symlink' % outfile elif os.path.exists(outfile) and not os.path.isfile(outfile): msg = '%s is a non-regular file' % outfile if msg: raise ValueError(msg + ' which would be overwritten') shutil.copyfile(infile, outfile) self.record_as_written(outfile) def copy_stream(self, instream, outfile, encoding=None): assert not os.path.isdir(outfile) self.ensure_dir(os.path.dirname(outfile)) logger.info('Copying stream %s to %s', instream, outfile) if not self.dry_run: if encoding is None: outstream = open(outfile, 'wb') else: outstream = codecs.open(outfile, 'w', encoding=encoding) try: shutil.copyfileobj(instream, outstream) finally: outstream.close() self.record_as_written(outfile) def write_binary_file(self, path, data): self.ensure_dir(os.path.dirname(path)) if not self.dry_run: with open(path, 'wb') as f: f.write(data) self.record_as_written(path) def write_text_file(self, path, data, encoding): self.ensure_dir(os.path.dirname(path)) if not self.dry_run: with open(path, 'wb') as f: f.write(data.encode(encoding)) self.record_as_written(path) def set_mode(self, bits, mask, files): if os.name == 'posix' or (os.name == 'java' and os._name == 'posix'): # Set the executable bits (owner, group, and world) on # all the files specified. for f in files: if self.dry_run: logger.info("changing mode of %s", f) else: mode = (os.stat(f).st_mode | bits) & mask logger.info("changing mode of %s to %o", f, mode) os.chmod(f, mode) set_executable_mode = lambda s, f: s.set_mode(0o555, 0o7777, f) def ensure_dir(self, path): path = os.path.abspath(path) if path not in self.ensured and not os.path.exists(path): self.ensured.add(path) d, f = os.path.split(path) self.ensure_dir(d) logger.info('Creating %s' % path) if not self.dry_run: os.mkdir(path) if self.record: self.dirs_created.add(path) def byte_compile(self, path, optimize=False, force=False, prefix=None): dpath = cache_from_source(path, not optimize) logger.info('Byte-compiling %s to %s', path, dpath) if not self.dry_run: if force or self.newer(path, dpath): if not prefix: diagpath = None else: assert path.startswith(prefix) diagpath = path[len(prefix):] py_compile.compile(path, dpath, diagpath, True) # raise error self.record_as_written(dpath) return dpath def ensure_removed(self, path): if os.path.exists(path): if os.path.isdir(path) and not os.path.islink(path): logger.debug('Removing directory tree at %s', path) if not self.dry_run: shutil.rmtree(path) if self.record: if path in self.dirs_created: self.dirs_created.remove(path) else: if os.path.islink(path): s = 'link' else: s = 'file' logger.debug('Removing %s %s', s, path) if not self.dry_run: os.remove(path) if self.record: if path in self.files_written: self.files_written.remove(path) def is_writable(self, path): result = False while not result: if os.path.exists(path): result = os.access(path, os.W_OK) break parent = os.path.dirname(path) if parent == path: break path = parent return result def commit(self): """ Commit recorded changes, turn off recording, return changes. """ assert self.record result = self.files_written, self.dirs_created self._init_record() return result def rollback(self): if not self.dry_run: for f in list(self.files_written): if os.path.exists(f): os.remove(f) # dirs should all be empty now, except perhaps for # __pycache__ subdirs # reverse so that subdirs appear before their parents dirs = sorted(self.dirs_created, reverse=True) for d in dirs: flist = os.listdir(d) if flist: assert flist == ['__pycache__'] sd = os.path.join(d, flist[0]) os.rmdir(sd) os.rmdir(d) # should fail if non-empty self._init_record() def resolve(module_name, dotted_path): if module_name in sys.modules: mod = sys.modules[module_name] else: mod = __import__(module_name) if dotted_path is None: result = mod else: parts = dotted_path.split('.') result = getattr(mod, parts.pop(0)) for p in parts: result = getattr(result, p) return result class ExportEntry(object): def __init__(self, name, prefix, suffix, flags): self.name = name self.prefix = prefix self.suffix = suffix self.flags = flags @cached_property def value(self): return resolve(self.prefix, self.suffix) def __repr__(self): return '' % (self.name, self.prefix, self.suffix, self.flags) def __eq__(self, other): if not isinstance(other, ExportEntry): result = False else: result = (self.name == other.name and self.prefix == other.prefix and self.suffix == other.suffix and self.flags == other.flags) return result __hash__ = object.__hash__ ENTRY_RE = re.compile(r'''(?P(\w|[-.])+) \s*=\s*(?P(\w+)([:\.]\w+)*) \s*(\[\s*(?P\w+(=\w+)?(,\s*\w+(=\w+)?)*)\s*\])? ''', re.VERBOSE) def get_export_entry(specification): m = ENTRY_RE.search(specification) if not m: result = None if '[' in specification or ']' in specification: raise DistlibException('Invalid specification ' '%r' % specification) else: d = m.groupdict() name = d['name'] path = d['callable'] colons = path.count(':') if colons == 0: prefix, suffix = path, None else: if colons != 1: raise DistlibException('Invalid specification ' '%r' % specification) prefix, suffix = path.split(':') flags = d['flags'] if flags is None: if '[' in specification or ']' in specification: raise DistlibException('Invalid specification ' '%r' % specification) flags = [] else: flags = [f.strip() for f in flags.split(',')] result = ExportEntry(name, prefix, suffix, flags) return result def get_cache_base(suffix=None): """ Return the default base location for distlib caches. If the directory does not exist, it is created. Use the suffix provided for the base directory, and default to '.distlib' if it isn't provided. On Windows, if LOCALAPPDATA is defined in the environment, then it is assumed to be a directory, and will be the parent directory of the result. On POSIX, and on Windows if LOCALAPPDATA is not defined, the user's home directory - using os.expanduser('~') - will be the parent directory of the result. The result is just the directory '.distlib' in the parent directory as determined above, or with the name specified with ``suffix``. """ if suffix is None: suffix = '.distlib' if os.name == 'nt' and 'LOCALAPPDATA' in os.environ: result = os.path.expandvars('$localappdata') else: # Assume posix, or old Windows result = os.path.expanduser('~') # we use 'isdir' instead of 'exists', because we want to # fail if there's a file with that name if os.path.isdir(result): usable = os.access(result, os.W_OK) if not usable: logger.warning('Directory exists but is not writable: %s', result) else: try: os.makedirs(result) usable = True except OSError: logger.warning('Unable to create %s', result, exc_info=True) usable = False if not usable: result = tempfile.mkdtemp() logger.warning('Default location unusable, using %s', result) return os.path.join(result, suffix) def path_to_cache_dir(path): """ Convert an absolute path to a directory name for use in a cache. The algorithm used is: #. On Windows, any ``':'`` in the drive is replaced with ``'---'``. #. Any occurrence of ``os.sep`` is replaced with ``'--'``. #. ``'.cache'`` is appended. """ d, p = os.path.splitdrive(os.path.abspath(path)) if d: d = d.replace(':', '---') p = p.replace(os.sep, '--') return d + p + '.cache' def ensure_slash(s): if not s.endswith('/'): return s + '/' return s def parse_credentials(netloc): username = password = None if '@' in netloc: prefix, netloc = netloc.split('@', 1) if ':' not in prefix: username = prefix else: username, password = prefix.split(':', 1) return username, password, netloc def get_process_umask(): result = os.umask(0o22) os.umask(result) return result def is_string_sequence(seq): result = True i = None for i, s in enumerate(seq): if not isinstance(s, string_types): result = False break assert i is not None return result PROJECT_NAME_AND_VERSION = re.compile('([a-z0-9_]+([.-][a-z_][a-z0-9_]*)*)-' '([a-z0-9_.+-]+)', re.I) PYTHON_VERSION = re.compile(r'-py(\d\.?\d?)') def split_filename(filename, project_name=None): """ Extract name, version, python version from a filename (no extension) Return name, version, pyver or None """ result = None pyver = None m = PYTHON_VERSION.search(filename) if m: pyver = m.group(1) filename = filename[:m.start()] if project_name and len(filename) > len(project_name) + 1: m = re.match(re.escape(project_name) + r'\b', filename) if m: n = m.end() result = filename[:n], filename[n + 1:], pyver if result is None: m = PROJECT_NAME_AND_VERSION.match(filename) if m: result = m.group(1), m.group(3), pyver return result # Allow spaces in name because of legacy dists like "Twisted Core" NAME_VERSION_RE = re.compile(r'(?P[\w .-]+)\s*' r'\(\s*(?P[^\s)]+)\)$') def parse_name_and_version(p): """ A utility method used to get name and version from a string. From e.g. a Provides-Dist value. :param p: A value in a form 'foo (1.0)' :return: The name and version as a tuple. """ m = NAME_VERSION_RE.match(p) if not m: raise DistlibException('Ill-formed name/version string: \'%s\'' % p) d = m.groupdict() return d['name'].strip().lower(), d['ver'] def get_extras(requested, available): result = set() requested = set(requested or []) available = set(available or []) if '*' in requested: requested.remove('*') result |= available for r in requested: if r == '-': result.add(r) elif r.startswith('-'): unwanted = r[1:] if unwanted not in available: logger.warning('undeclared extra: %s' % unwanted) if unwanted in result: result.remove(unwanted) else: if r not in available: logger.warning('undeclared extra: %s' % r) result.add(r) return result # # Extended metadata functionality # def _get_external_data(url): result = {} try: # urlopen might fail if it runs into redirections, # because of Python issue #13696. Fixed in locators # using a custom redirect handler. resp = urlopen(url) headers = resp.info() if headers.get('Content-Type') != 'application/json': logger.debug('Unexpected response for JSON request') else: reader = codecs.getreader('utf-8')(resp) #data = reader.read().decode('utf-8') #result = json.loads(data) result = json.load(reader) except Exception as e: logger.exception('Failed to get external data for %s: %s', url, e) return result _external_data_base_url = 'https://www.red-dove.com/pypi/projects/' def get_project_data(name): url = '%s/%s/project.json' % (name[0].upper(), name) url = urljoin(_external_data_base_url, url) result = _get_external_data(url) return result def get_package_data(name, version): url = '%s/%s/package-%s.json' % (name[0].upper(), name, version) url = urljoin(_external_data_base_url, url) return _get_external_data(url) class Cache(object): """ A class implementing a cache for resources that need to live in the file system e.g. shared libraries. This class was moved from resources to here because it could be used by other modules, e.g. the wheel module. """ def __init__(self, base): """ Initialise an instance. :param base: The base directory where the cache should be located. """ # we use 'isdir' instead of 'exists', because we want to # fail if there's a file with that name if not os.path.isdir(base): os.makedirs(base) if (os.stat(base).st_mode & 0o77) != 0: logger.warning('Directory \'%s\' is not private', base) self.base = os.path.abspath(os.path.normpath(base)) def prefix_to_dir(self, prefix): """ Converts a resource prefix to a directory name in the cache. """ return path_to_cache_dir(prefix) def clear(self): """ Clear the cache. """ not_removed = [] for fn in os.listdir(self.base): fn = os.path.join(self.base, fn) try: if os.path.islink(fn) or os.path.isfile(fn): os.remove(fn) elif os.path.isdir(fn): shutil.rmtree(fn) except Exception: not_removed.append(fn) return not_removed class EventMixin(object): """ A very simple publish/subscribe system. """ def __init__(self): self._subscribers = {} def add(self, event, subscriber, append=True): """ Add a subscriber for an event. :param event: The name of an event. :param subscriber: The subscriber to be added (and called when the event is published). :param append: Whether to append or prepend the subscriber to an existing subscriber list for the event. """ subs = self._subscribers if event not in subs: subs[event] = deque([subscriber]) else: sq = subs[event] if append: sq.append(subscriber) else: sq.appendleft(subscriber) def remove(self, event, subscriber): """ Remove a subscriber for an event. :param event: The name of an event. :param subscriber: The subscriber to be removed. """ subs = self._subscribers if event not in subs: raise ValueError('No subscribers: %r' % event) subs[event].remove(subscriber) def get_subscribers(self, event): """ Return an iterator for the subscribers for an event. :param event: The event to return subscribers for. """ return iter(self._subscribers.get(event, ())) def publish(self, event, *args, **kwargs): """ Publish a event and return a list of values returned by its subscribers. :param event: The event to publish. :param args: The positional arguments to pass to the event's subscribers. :param kwargs: The keyword arguments to pass to the event's subscribers. """ result = [] for subscriber in self.get_subscribers(event): try: value = subscriber(event, *args, **kwargs) except Exception: logger.exception('Exception during event publication') value = None result.append(value) logger.debug('publish %s: args = %s, kwargs = %s, result = %s', event, args, kwargs, result) return result # # Simple sequencing # class Sequencer(object): def __init__(self): self._preds = {} self._succs = {} self._nodes = set() # nodes with no preds/succs def add_node(self, node): self._nodes.add(node) def remove_node(self, node, edges=False): if node in self._nodes: self._nodes.remove(node) if edges: for p in set(self._preds.get(node, ())): self.remove(p, node) for s in set(self._succs.get(node, ())): self.remove(node, s) # Remove empties for k, v in list(self._preds.items()): if not v: del self._preds[k] for k, v in list(self._succs.items()): if not v: del self._succs[k] def add(self, pred, succ): assert pred != succ self._preds.setdefault(succ, set()).add(pred) self._succs.setdefault(pred, set()).add(succ) def remove(self, pred, succ): assert pred != succ try: preds = self._preds[succ] succs = self._succs[pred] except KeyError: raise ValueError('%r not a successor of anything' % succ) try: preds.remove(pred) succs.remove(succ) except KeyError: raise ValueError('%r not a successor of %r' % (succ, pred)) def is_step(self, step): return (step in self._preds or step in self._succs or step in self._nodes) def get_steps(self, final): if not self.is_step(final): raise ValueError('Unknown: %r' % final) result = [] todo = [] seen = set() todo.append(final) while todo: step = todo.pop(0) if step in seen: # if a step was already seen, # move it to the end (so it will appear earlier # when reversed on return) ... but not for the # final step, as that would be confusing for # users if step != final: result.remove(step) result.append(step) else: seen.add(step) result.append(step) preds = self._preds.get(step, ()) todo.extend(preds) return reversed(result) @property def strong_connections(self): #http://en.wikipedia.org/wiki/Tarjan%27s_strongly_connected_components_algorithm index_counter = [0] stack = [] lowlinks = {} index = {} result = [] graph = self._succs def strongconnect(node): # set the depth index for this node to the smallest unused index index[node] = index_counter[0] lowlinks[node] = index_counter[0] index_counter[0] += 1 stack.append(node) # Consider successors try: successors = graph[node] except Exception: successors = [] for successor in successors: if successor not in lowlinks: # Successor has not yet been visited strongconnect(successor) lowlinks[node] = min(lowlinks[node],lowlinks[successor]) elif successor in stack: # the successor is in the stack and hence in the current # strongly connected component (SCC) lowlinks[node] = min(lowlinks[node],index[successor]) # If `node` is a root node, pop the stack and generate an SCC if lowlinks[node] == index[node]: connected_component = [] while True: successor = stack.pop() connected_component.append(successor) if successor == node: break component = tuple(connected_component) # storing the result result.append(component) for node in graph: if node not in lowlinks: strongconnect(node) return result @property def dot(self): result = ['digraph G {'] for succ in self._preds: preds = self._preds[succ] for pred in preds: result.append(' %s -> %s;' % (pred, succ)) for node in self._nodes: result.append(' %s;' % node) result.append('}') return '\n'.join(result) # # Unarchiving functionality for zip, tar, tgz, tbz, whl # ARCHIVE_EXTENSIONS = ('.tar.gz', '.tar.bz2', '.tar', '.zip', '.tgz', '.tbz', '.whl') def unarchive(archive_filename, dest_dir, format=None, check=True): def check_path(path): if not isinstance(path, text_type): path = path.decode('utf-8') p = os.path.abspath(os.path.join(dest_dir, path)) if not p.startswith(dest_dir) or p[plen] != os.sep: raise ValueError('path outside destination: %r' % p) dest_dir = os.path.abspath(dest_dir) plen = len(dest_dir) archive = None if format is None: if archive_filename.endswith(('.zip', '.whl')): format = 'zip' elif archive_filename.endswith(('.tar.gz', '.tgz')): format = 'tgz' mode = 'r:gz' elif archive_filename.endswith(('.tar.bz2', '.tbz')): format = 'tbz' mode = 'r:bz2' elif archive_filename.endswith('.tar'): format = 'tar' mode = 'r' else: raise ValueError('Unknown format for %r' % archive_filename) try: if format == 'zip': archive = ZipFile(archive_filename, 'r') if check: names = archive.namelist() for name in names: check_path(name) else: archive = tarfile.open(archive_filename, mode) if check: names = archive.getnames() for name in names: check_path(name) if format != 'zip' and sys.version_info[0] < 3: # See Python issue 17153. If the dest path contains Unicode, # tarfile extraction fails on Python 2.x if a member path name # contains non-ASCII characters - it leads to an implicit # bytes -> unicode conversion using ASCII to decode. for tarinfo in archive.getmembers(): if not isinstance(tarinfo.name, text_type): tarinfo.name = tarinfo.name.decode('utf-8') archive.extractall(dest_dir) finally: if archive: archive.close() def zip_dir(directory): """zip a directory tree into a BytesIO object""" result = io.BytesIO() dlen = len(directory) with ZipFile(result, "w") as zf: for root, dirs, files in os.walk(directory): for name in files: full = os.path.join(root, name) rel = root[dlen:] dest = os.path.join(rel, name) zf.write(full, dest) return result # # Simple progress bar # UNITS = ('', 'K', 'M', 'G','T','P') class Progress(object): unknown = 'UNKNOWN' def __init__(self, minval=0, maxval=100): assert maxval is None or maxval >= minval self.min = self.cur = minval self.max = maxval self.started = None self.elapsed = 0 self.done = False def update(self, curval): assert self.min <= curval assert self.max is None or curval <= self.max self.cur = curval now = time.time() if self.started is None: self.started = now else: self.elapsed = now - self.started def increment(self, incr): assert incr >= 0 self.update(self.cur + incr) def start(self): self.update(self.min) return self def stop(self): if self.max is not None: self.update(self.max) self.done = True @property def maximum(self): return self.unknown if self.max is None else self.max @property def percentage(self): if self.done: result = '100 %' elif self.max is None: result = ' ?? %' else: v = 100.0 * (self.cur - self.min) / (self.max - self.min) result = '%3d %%' % v return result def format_duration(self, duration): if (duration <= 0) and self.max is None or self.cur == self.min: result = '??:??:??' #elif duration < 1: # result = '--:--:--' else: result = time.strftime('%H:%M:%S', time.gmtime(duration)) return result @property def ETA(self): if self.done: prefix = 'Done' t = self.elapsed #import pdb; pdb.set_trace() else: prefix = 'ETA ' if self.max is None: t = -1 elif self.elapsed == 0 or (self.cur == self.min): t = 0 else: #import pdb; pdb.set_trace() t = float(self.max - self.min) t /= self.cur - self.min t = (t - 1) * self.elapsed return '%s: %s' % (prefix, self.format_duration(t)) @property def speed(self): if self.elapsed == 0: result = 0.0 else: result = (self.cur - self.min) / self.elapsed for unit in UNITS: if result < 1000: break result /= 1000.0 return '%d %sB/s' % (result, unit) # # Glob functionality # RICH_GLOB = re.compile(r'\{([^}]*)\}') _CHECK_RECURSIVE_GLOB = re.compile(r'[^/\\,{]\*\*|\*\*[^/\\,}]') _CHECK_MISMATCH_SET = re.compile(r'^[^{]*\}|\{[^}]*$') def iglob(path_glob): """Extended globbing function that supports ** and {opt1,opt2,opt3}.""" if _CHECK_RECURSIVE_GLOB.search(path_glob): msg = """invalid glob %r: recursive glob "**" must be used alone""" raise ValueError(msg % path_glob) if _CHECK_MISMATCH_SET.search(path_glob): msg = """invalid glob %r: mismatching set marker '{' or '}'""" raise ValueError(msg % path_glob) return _iglob(path_glob) def _iglob(path_glob): rich_path_glob = RICH_GLOB.split(path_glob, 1) if len(rich_path_glob) > 1: assert len(rich_path_glob) == 3, rich_path_glob prefix, set, suffix = rich_path_glob for item in set.split(','): for path in _iglob(''.join((prefix, item, suffix))): yield path else: if '**' not in path_glob: for item in std_iglob(path_glob): yield item else: prefix, radical = path_glob.split('**', 1) if prefix == '': prefix = '.' if radical == '': radical = '*' else: # we support both radical = radical.lstrip('/') radical = radical.lstrip('\\') for path, dir, files in os.walk(prefix): path = os.path.normpath(path) for fn in _iglob(os.path.join(path, radical)): yield fn # # HTTPSConnection which verifies certificates/matches domains # class HTTPSConnection(httplib.HTTPSConnection): ca_certs = None # set this to the path to the certs file (.pem) check_domain = True # only used if ca_certs is not None # noinspection PyPropertyAccess def connect(self): sock = socket.create_connection((self.host, self.port), self.timeout) if getattr(self, '_tunnel_host', False): self.sock = sock self._tunnel() if not hasattr(ssl, 'SSLContext'): # For 2.x if self.ca_certs: cert_reqs = ssl.CERT_REQUIRED else: cert_reqs = ssl.CERT_NONE self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, cert_reqs=cert_reqs, ssl_version=ssl.PROTOCOL_SSLv23, ca_certs=self.ca_certs) else: context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) context.options |= ssl.OP_NO_SSLv2 if self.cert_file: context.load_cert_chain(self.cert_file, self.key_file) kwargs = {} if self.ca_certs: context.verify_mode = ssl.CERT_REQUIRED context.load_verify_locations(cafile=self.ca_certs) if getattr(ssl, 'HAS_SNI', False): kwargs['server_hostname'] = self.host self.sock = context.wrap_socket(sock, **kwargs) if self.ca_certs and self.check_domain: try: match_hostname(self.sock.getpeercert(), self.host) logger.debug('Host verified: %s', self.host) except CertificateError: self.sock.shutdown(socket.SHUT_RDWR) self.sock.close() raise class HTTPSHandler(BaseHTTPSHandler): def __init__(self, ca_certs, check_domain=True): BaseHTTPSHandler.__init__(self) self.ca_certs = ca_certs self.check_domain = check_domain def _conn_maker(self, *args, **kwargs): """ This is called to create a connection instance. Normally you'd pass a connection class to do_open, but it doesn't actually check for a class, and just expects a callable. As long as we behave just as a constructor would have, we should be OK. If it ever changes so that we *must* pass a class, we'll create an UnsafeHTTPSConnection class which just sets check_domain to False in the class definition, and choose which one to pass to do_open. """ result = HTTPSConnection(*args, **kwargs) if self.ca_certs: result.ca_certs = self.ca_certs result.check_domain = self.check_domain return result def https_open(self, req): try: return self.do_open(self._conn_maker, req) except URLError as e: if 'certificate verify failed' in str(e.reason): raise CertificateError('Unable to verify server certificate ' 'for %s' % req.host) else: raise # # To prevent against mixing HTTP traffic with HTTPS (examples: A Man-In-The- # Middle proxy using HTTP listens on port 443, or an index mistakenly serves # HTML containing a http://xyz link when it should be https://xyz), # you can use the following handler class, which does not allow HTTP traffic. # # It works by inheriting from HTTPHandler - so build_opener won't add a # handler for HTTP itself. # class HTTPSOnlyHandler(HTTPSHandler, HTTPHandler): def http_open(self, req): raise URLError('Unexpected HTTP request on what should be a secure ' 'connection: %s' % req) # # XML-RPC with timeouts # _ver_info = sys.version_info[:2] if _ver_info == (2, 6): class HTTP(httplib.HTTP): def __init__(self, host='', port=None, **kwargs): if port == 0: # 0 means use port 0, not the default port port = None self._setup(self._connection_class(host, port, **kwargs)) class HTTPS(httplib.HTTPS): def __init__(self, host='', port=None, **kwargs): if port == 0: # 0 means use port 0, not the default port port = None self._setup(self._connection_class(host, port, **kwargs)) class Transport(xmlrpclib.Transport): def __init__(self, timeout, use_datetime=0): self.timeout = timeout xmlrpclib.Transport.__init__(self, use_datetime) def make_connection(self, host): h, eh, x509 = self.get_host_info(host) if _ver_info == (2, 6): result = HTTP(h, timeout=self.timeout) else: if not self._connection or host != self._connection[0]: self._extra_headers = eh self._connection = host, httplib.HTTPConnection(h) result = self._connection[1] return result class SafeTransport(xmlrpclib.SafeTransport): def __init__(self, timeout, use_datetime=0): self.timeout = timeout xmlrpclib.SafeTransport.__init__(self, use_datetime) def make_connection(self, host): h, eh, kwargs = self.get_host_info(host) if not kwargs: kwargs = {} kwargs['timeout'] = self.timeout if _ver_info == (2, 6): result = HTTPS(host, None, **kwargs) else: if not self._connection or host != self._connection[0]: self._extra_headers = eh self._connection = host, httplib.HTTPSConnection(h, None, **kwargs) result = self._connection[1] return result class ServerProxy(xmlrpclib.ServerProxy): def __init__(self, uri, **kwargs): self.timeout = timeout = kwargs.pop('timeout', None) # The above classes only come into play if a timeout # is specified if timeout is not None: scheme, _ = splittype(uri) use_datetime = kwargs.get('use_datetime', 0) if scheme == 'https': tcls = SafeTransport else: tcls = Transport kwargs['transport'] = t = tcls(timeout, use_datetime=use_datetime) self.transport = t xmlrpclib.ServerProxy.__init__(self, uri, **kwargs) # # CSV functionality. This is provided because on 2.x, the csv module can't # handle Unicode. However, we need to deal with Unicode in e.g. RECORD files. # def _csv_open(fn, mode, **kwargs): if sys.version_info[0] < 3: mode += 'b' else: kwargs['newline'] = '' return open(fn, mode, **kwargs) class CSVBase(object): defaults = { 'delimiter': str(','), # The strs are used because we need native 'quotechar': str('"'), # str in the csv API (2.x won't take 'lineterminator': str('\n') # Unicode) } def __enter__(self): return self def __exit__(self, *exc_info): self.stream.close() class CSVReader(CSVBase): def __init__(self, **kwargs): if 'stream' in kwargs: stream = kwargs['stream'] if sys.version_info[0] >= 3: # needs to be a text stream stream = codecs.getreader('utf-8')(stream) self.stream = stream else: self.stream = _csv_open(kwargs['path'], 'r') self.reader = csv.reader(self.stream, **self.defaults) def __iter__(self): return self def next(self): result = next(self.reader) if sys.version_info[0] < 3: for i, item in enumerate(result): if not isinstance(item, text_type): result[i] = item.decode('utf-8') return result __next__ = next class CSVWriter(CSVBase): def __init__(self, fn, **kwargs): self.stream = _csv_open(fn, 'w') self.writer = csv.writer(self.stream, **self.defaults) def writerow(self, row): if sys.version_info[0] < 3: r = [] for item in row: if isinstance(item, text_type): item = item.encode('utf-8') r.append(item) row = r self.writer.writerow(row) # # Configurator functionality # class Configurator(BaseConfigurator): value_converters = dict(BaseConfigurator.value_converters) value_converters['inc'] = 'inc_convert' def __init__(self, config, base=None): super(Configurator, self).__init__(config) self.base = base or os.getcwd() def configure_custom(self, config): def convert(o): if isinstance(o, (list, tuple)): result = type(o)([convert(i) for i in o]) elif isinstance(o, dict): if '()' in o: result = self.configure_custom(o) else: result = {} for k in o: result[k] = convert(o[k]) else: result = self.convert(o) return result c = config.pop('()') if not callable(c): c = self.resolve(c) props = config.pop('.', None) # Check for valid identifiers args = config.pop('[]', ()) if args: args = tuple([convert(o) for o in args]) items = [(k, convert(config[k])) for k in config if valid_ident(k)] kwargs = dict(items) result = c(*args, **kwargs) if props: for n, v in props.items(): setattr(result, n, convert(v)) return result def __getitem__(self, key): result = self.config[key] if isinstance(result, dict) and '()' in result: self.config[key] = result = self.configure_custom(result) return result def inc_convert(self, value): """Default converter for the inc:// protocol.""" if not os.path.isabs(value): value = os.path.join(self.base, value) with codecs.open(value, 'r', encoding='utf-8') as f: result = json.load(f) return result # # Mixin for running subprocesses and capturing their output # class SubprocessMixin(object): def __init__(self, verbose=False, progress=None): self.verbose = verbose self.progress = progress def reader(self, stream, context): """ Read lines from a subprocess' output stream and either pass to a progress callable (if specified) or write progress information to sys.stderr. """ progress = self.progress verbose = self.verbose while True: s = stream.readline() if not s: break if progress is not None: progress(s, context) else: if not verbose: sys.stderr.write('.') else: sys.stderr.write(s.decode('utf-8')) sys.stderr.flush() stream.close() def run_command(self, cmd, **kwargs): p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, **kwargs) t1 = threading.Thread(target=self.reader, args=(p.stdout, 'stdout')) t1.start() t2 = threading.Thread(target=self.reader, args=(p.stderr, 'stderr')) t2.start() p.wait() t1.join() t2.join() if self.progress is not None: self.progress('done.', 'main') elif self.verbose: sys.stderr.write('done.\n') return p feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/version.py0000644000076500000240000005623712700725533030411 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2012-2016 The Python Software Foundation. # See LICENSE.txt and CONTRIBUTORS.txt. # """ Implementation of a flexible versioning scheme providing support for PEP-440, setuptools-compatible and semantic versioning. """ import logging import re from .compat import string_types __all__ = ['NormalizedVersion', 'NormalizedMatcher', 'LegacyVersion', 'LegacyMatcher', 'SemanticVersion', 'SemanticMatcher', 'UnsupportedVersionError', 'get_scheme'] logger = logging.getLogger(__name__) class UnsupportedVersionError(ValueError): """This is an unsupported version.""" pass class Version(object): def __init__(self, s): self._string = s = s.strip() self._parts = parts = self.parse(s) assert isinstance(parts, tuple) assert len(parts) > 0 def parse(self, s): raise NotImplementedError('please implement in a subclass') def _check_compatible(self, other): if type(self) != type(other): raise TypeError('cannot compare %r and %r' % (self, other)) def __eq__(self, other): self._check_compatible(other) return self._parts == other._parts def __ne__(self, other): return not self.__eq__(other) def __lt__(self, other): self._check_compatible(other) return self._parts < other._parts def __gt__(self, other): return not (self.__lt__(other) or self.__eq__(other)) def __le__(self, other): return self.__lt__(other) or self.__eq__(other) def __ge__(self, other): return self.__gt__(other) or self.__eq__(other) # See http://docs.python.org/reference/datamodel#object.__hash__ def __hash__(self): return hash(self._parts) def __repr__(self): return "%s('%s')" % (self.__class__.__name__, self._string) def __str__(self): return self._string @property def is_prerelease(self): raise NotImplementedError('Please implement in subclasses.') class Matcher(object): version_class = None dist_re = re.compile(r"^(\w[\s\w'.-]*)(\((.*)\))?") comp_re = re.compile(r'^(<=|>=|<|>|!=|={2,3}|~=)?\s*([^\s,]+)$') num_re = re.compile(r'^\d+(\.\d+)*$') # value is either a callable or the name of a method _operators = { '<': lambda v, c, p: v < c, '>': lambda v, c, p: v > c, '<=': lambda v, c, p: v == c or v < c, '>=': lambda v, c, p: v == c or v > c, '==': lambda v, c, p: v == c, '===': lambda v, c, p: v == c, # by default, compatible => >=. '~=': lambda v, c, p: v == c or v > c, '!=': lambda v, c, p: v != c, } def __init__(self, s): if self.version_class is None: raise ValueError('Please specify a version class') self._string = s = s.strip() m = self.dist_re.match(s) if not m: raise ValueError('Not valid: %r' % s) groups = m.groups('') self.name = groups[0].strip() self.key = self.name.lower() # for case-insensitive comparisons clist = [] if groups[2]: constraints = [c.strip() for c in groups[2].split(',')] for c in constraints: m = self.comp_re.match(c) if not m: raise ValueError('Invalid %r in %r' % (c, s)) groups = m.groups() op = groups[0] or '~=' s = groups[1] if s.endswith('.*'): if op not in ('==', '!='): raise ValueError('\'.*\' not allowed for ' '%r constraints' % op) # Could be a partial version (e.g. for '2.*') which # won't parse as a version, so keep it as a string vn, prefix = s[:-2], True if not self.num_re.match(vn): # Just to check that vn is a valid version self.version_class(vn) else: # Should parse as a version, so we can create an # instance for the comparison vn, prefix = self.version_class(s), False clist.append((op, vn, prefix)) self._parts = tuple(clist) def match(self, version): """ Check if the provided version matches the constraints. :param version: The version to match against this instance. :type version: Strring or :class:`Version` instance. """ if isinstance(version, string_types): version = self.version_class(version) for operator, constraint, prefix in self._parts: f = self._operators.get(operator) if isinstance(f, string_types): f = getattr(self, f) if not f: msg = ('%r not implemented ' 'for %s' % (operator, self.__class__.__name__)) raise NotImplementedError(msg) if not f(version, constraint, prefix): return False return True @property def exact_version(self): result = None if len(self._parts) == 1 and self._parts[0][0] in ('==', '==='): result = self._parts[0][1] return result def _check_compatible(self, other): if type(self) != type(other) or self.name != other.name: raise TypeError('cannot compare %s and %s' % (self, other)) def __eq__(self, other): self._check_compatible(other) return self.key == other.key and self._parts == other._parts def __ne__(self, other): return not self.__eq__(other) # See http://docs.python.org/reference/datamodel#object.__hash__ def __hash__(self): return hash(self.key) + hash(self._parts) def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._string) def __str__(self): return self._string PEP440_VERSION_RE = re.compile(r'^v?(\d+!)?(\d+(\.\d+)*)((a|b|c|rc)(\d+))?' r'(\.(post)(\d+))?(\.(dev)(\d+))?' r'(\+([a-zA-Z\d]+(\.[a-zA-Z\d]+)?))?$') def _pep_440_key(s): s = s.strip() m = PEP440_VERSION_RE.match(s) if not m: raise UnsupportedVersionError('Not a valid version: %s' % s) groups = m.groups() nums = tuple(int(v) for v in groups[1].split('.')) while len(nums) > 1 and nums[-1] == 0: nums = nums[:-1] if not groups[0]: epoch = 0 else: epoch = int(groups[0]) pre = groups[4:6] post = groups[7:9] dev = groups[10:12] local = groups[13] if pre == (None, None): pre = () else: pre = pre[0], int(pre[1]) if post == (None, None): post = () else: post = post[0], int(post[1]) if dev == (None, None): dev = () else: dev = dev[0], int(dev[1]) if local is None: local = () else: parts = [] for part in local.split('.'): # to ensure that numeric compares as > lexicographic, avoid # comparing them directly, but encode a tuple which ensures # correct sorting if part.isdigit(): part = (1, int(part)) else: part = (0, part) parts.append(part) local = tuple(parts) if not pre: # either before pre-release, or final release and after if not post and dev: # before pre-release pre = ('a', -1) # to sort before a0 else: pre = ('z',) # to sort after all pre-releases # now look at the state of post and dev. if not post: post = ('_',) # sort before 'a' if not dev: dev = ('final',) #print('%s -> %s' % (s, m.groups())) return epoch, nums, pre, post, dev, local _normalized_key = _pep_440_key class NormalizedVersion(Version): """A rational version. Good: 1.2 # equivalent to "1.2.0" 1.2.0 1.2a1 1.2.3a2 1.2.3b1 1.2.3c1 1.2.3.4 TODO: fill this out Bad: 1 # mininum two numbers 1.2a # release level must have a release serial 1.2.3b """ def parse(self, s): result = _normalized_key(s) # _normalized_key loses trailing zeroes in the release # clause, since that's needed to ensure that X.Y == X.Y.0 == X.Y.0.0 # However, PEP 440 prefix matching needs it: for example, # (~= 1.4.5.0) matches differently to (~= 1.4.5.0.0). m = PEP440_VERSION_RE.match(s) # must succeed groups = m.groups() self._release_clause = tuple(int(v) for v in groups[1].split('.')) return result PREREL_TAGS = set(['a', 'b', 'c', 'rc', 'dev']) @property def is_prerelease(self): return any(t[0] in self.PREREL_TAGS for t in self._parts if t) def _match_prefix(x, y): x = str(x) y = str(y) if x == y: return True if not x.startswith(y): return False n = len(y) return x[n] == '.' class NormalizedMatcher(Matcher): version_class = NormalizedVersion # value is either a callable or the name of a method _operators = { '~=': '_match_compatible', '<': '_match_lt', '>': '_match_gt', '<=': '_match_le', '>=': '_match_ge', '==': '_match_eq', '===': '_match_arbitrary', '!=': '_match_ne', } def _adjust_local(self, version, constraint, prefix): if prefix: strip_local = '+' not in constraint and version._parts[-1] else: # both constraint and version are # NormalizedVersion instances. # If constraint does not have a local component, # ensure the version doesn't, either. strip_local = not constraint._parts[-1] and version._parts[-1] if strip_local: s = version._string.split('+', 1)[0] version = self.version_class(s) return version, constraint def _match_lt(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) if version >= constraint: return False release_clause = constraint._release_clause pfx = '.'.join([str(i) for i in release_clause]) return not _match_prefix(version, pfx) def _match_gt(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) if version <= constraint: return False release_clause = constraint._release_clause pfx = '.'.join([str(i) for i in release_clause]) return not _match_prefix(version, pfx) def _match_le(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) return version <= constraint def _match_ge(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) return version >= constraint def _match_eq(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) if not prefix: result = (version == constraint) else: result = _match_prefix(version, constraint) return result def _match_arbitrary(self, version, constraint, prefix): return str(version) == str(constraint) def _match_ne(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) if not prefix: result = (version != constraint) else: result = not _match_prefix(version, constraint) return result def _match_compatible(self, version, constraint, prefix): version, constraint = self._adjust_local(version, constraint, prefix) if version == constraint: return True if version < constraint: return False # if not prefix: # return True release_clause = constraint._release_clause if len(release_clause) > 1: release_clause = release_clause[:-1] pfx = '.'.join([str(i) for i in release_clause]) return _match_prefix(version, pfx) _REPLACEMENTS = ( (re.compile('[.+-]$'), ''), # remove trailing puncts (re.compile(r'^[.](\d)'), r'0.\1'), # .N -> 0.N at start (re.compile('^[.-]'), ''), # remove leading puncts (re.compile(r'^\((.*)\)$'), r'\1'), # remove parentheses (re.compile(r'^v(ersion)?\s*(\d+)'), r'\2'), # remove leading v(ersion) (re.compile(r'^r(ev)?\s*(\d+)'), r'\2'), # remove leading v(ersion) (re.compile('[.]{2,}'), '.'), # multiple runs of '.' (re.compile(r'\b(alfa|apha)\b'), 'alpha'), # misspelt alpha (re.compile(r'\b(pre-alpha|prealpha)\b'), 'pre.alpha'), # standardise (re.compile(r'\(beta\)$'), 'beta'), # remove parentheses ) _SUFFIX_REPLACEMENTS = ( (re.compile('^[:~._+-]+'), ''), # remove leading puncts (re.compile('[,*")([\]]'), ''), # remove unwanted chars (re.compile('[~:+_ -]'), '.'), # replace illegal chars (re.compile('[.]{2,}'), '.'), # multiple runs of '.' (re.compile(r'\.$'), ''), # trailing '.' ) _NUMERIC_PREFIX = re.compile(r'(\d+(\.\d+)*)') def _suggest_semantic_version(s): """ Try to suggest a semantic form for a version for which _suggest_normalized_version couldn't come up with anything. """ result = s.strip().lower() for pat, repl in _REPLACEMENTS: result = pat.sub(repl, result) if not result: result = '0.0.0' # Now look for numeric prefix, and separate it out from # the rest. #import pdb; pdb.set_trace() m = _NUMERIC_PREFIX.match(result) if not m: prefix = '0.0.0' suffix = result else: prefix = m.groups()[0].split('.') prefix = [int(i) for i in prefix] while len(prefix) < 3: prefix.append(0) if len(prefix) == 3: suffix = result[m.end():] else: suffix = '.'.join([str(i) for i in prefix[3:]]) + result[m.end():] prefix = prefix[:3] prefix = '.'.join([str(i) for i in prefix]) suffix = suffix.strip() if suffix: #import pdb; pdb.set_trace() # massage the suffix. for pat, repl in _SUFFIX_REPLACEMENTS: suffix = pat.sub(repl, suffix) if not suffix: result = prefix else: sep = '-' if 'dev' in suffix else '+' result = prefix + sep + suffix if not is_semver(result): result = None return result def _suggest_normalized_version(s): """Suggest a normalized version close to the given version string. If you have a version string that isn't rational (i.e. NormalizedVersion doesn't like it) then you might be able to get an equivalent (or close) rational version from this function. This does a number of simple normalizations to the given string, based on observation of versions currently in use on PyPI. Given a dump of those version during PyCon 2009, 4287 of them: - 2312 (53.93%) match NormalizedVersion without change with the automatic suggestion - 3474 (81.04%) match when using this suggestion method @param s {str} An irrational version string. @returns A rational version string, or None, if couldn't determine one. """ try: _normalized_key(s) return s # already rational except UnsupportedVersionError: pass rs = s.lower() # part of this could use maketrans for orig, repl in (('-alpha', 'a'), ('-beta', 'b'), ('alpha', 'a'), ('beta', 'b'), ('rc', 'c'), ('-final', ''), ('-pre', 'c'), ('-release', ''), ('.release', ''), ('-stable', ''), ('+', '.'), ('_', '.'), (' ', ''), ('.final', ''), ('final', '')): rs = rs.replace(orig, repl) # if something ends with dev or pre, we add a 0 rs = re.sub(r"pre$", r"pre0", rs) rs = re.sub(r"dev$", r"dev0", rs) # if we have something like "b-2" or "a.2" at the end of the # version, that is pobably beta, alpha, etc # let's remove the dash or dot rs = re.sub(r"([abc]|rc)[\-\.](\d+)$", r"\1\2", rs) # 1.0-dev-r371 -> 1.0.dev371 # 0.1-dev-r79 -> 0.1.dev79 rs = re.sub(r"[\-\.](dev)[\-\.]?r?(\d+)$", r".\1\2", rs) # Clean: 2.0.a.3, 2.0.b1, 0.9.0~c1 rs = re.sub(r"[.~]?([abc])\.?", r"\1", rs) # Clean: v0.3, v1.0 if rs.startswith('v'): rs = rs[1:] # Clean leading '0's on numbers. #TODO: unintended side-effect on, e.g., "2003.05.09" # PyPI stats: 77 (~2%) better rs = re.sub(r"\b0+(\d+)(?!\d)", r"\1", rs) # Clean a/b/c with no version. E.g. "1.0a" -> "1.0a0". Setuptools infers # zero. # PyPI stats: 245 (7.56%) better rs = re.sub(r"(\d+[abc])$", r"\g<1>0", rs) # the 'dev-rNNN' tag is a dev tag rs = re.sub(r"\.?(dev-r|dev\.r)\.?(\d+)$", r".dev\2", rs) # clean the - when used as a pre delimiter rs = re.sub(r"-(a|b|c)(\d+)$", r"\1\2", rs) # a terminal "dev" or "devel" can be changed into ".dev0" rs = re.sub(r"[\.\-](dev|devel)$", r".dev0", rs) # a terminal "dev" can be changed into ".dev0" rs = re.sub(r"(?![\.\-])dev$", r".dev0", rs) # a terminal "final" or "stable" can be removed rs = re.sub(r"(final|stable)$", "", rs) # The 'r' and the '-' tags are post release tags # 0.4a1.r10 -> 0.4a1.post10 # 0.9.33-17222 -> 0.9.33.post17222 # 0.9.33-r17222 -> 0.9.33.post17222 rs = re.sub(r"\.?(r|-|-r)\.?(\d+)$", r".post\2", rs) # Clean 'r' instead of 'dev' usage: # 0.9.33+r17222 -> 0.9.33.dev17222 # 1.0dev123 -> 1.0.dev123 # 1.0.git123 -> 1.0.dev123 # 1.0.bzr123 -> 1.0.dev123 # 0.1a0dev.123 -> 0.1a0.dev123 # PyPI stats: ~150 (~4%) better rs = re.sub(r"\.?(dev|git|bzr)\.?(\d+)$", r".dev\2", rs) # Clean '.pre' (normalized from '-pre' above) instead of 'c' usage: # 0.2.pre1 -> 0.2c1 # 0.2-c1 -> 0.2c1 # 1.0preview123 -> 1.0c123 # PyPI stats: ~21 (0.62%) better rs = re.sub(r"\.?(pre|preview|-c)(\d+)$", r"c\g<2>", rs) # Tcl/Tk uses "px" for their post release markers rs = re.sub(r"p(\d+)$", r".post\1", rs) try: _normalized_key(rs) except UnsupportedVersionError: rs = None return rs # # Legacy version processing (distribute-compatible) # _VERSION_PART = re.compile(r'([a-z]+|\d+|[\.-])', re.I) _VERSION_REPLACE = { 'pre': 'c', 'preview': 'c', '-': 'final-', 'rc': 'c', 'dev': '@', '': None, '.': None, } def _legacy_key(s): def get_parts(s): result = [] for p in _VERSION_PART.split(s.lower()): p = _VERSION_REPLACE.get(p, p) if p: if '0' <= p[:1] <= '9': p = p.zfill(8) else: p = '*' + p result.append(p) result.append('*final') return result result = [] for p in get_parts(s): if p.startswith('*'): if p < '*final': while result and result[-1] == '*final-': result.pop() while result and result[-1] == '00000000': result.pop() result.append(p) return tuple(result) class LegacyVersion(Version): def parse(self, s): return _legacy_key(s) @property def is_prerelease(self): result = False for x in self._parts: if (isinstance(x, string_types) and x.startswith('*') and x < '*final'): result = True break return result class LegacyMatcher(Matcher): version_class = LegacyVersion _operators = dict(Matcher._operators) _operators['~='] = '_match_compatible' numeric_re = re.compile('^(\d+(\.\d+)*)') def _match_compatible(self, version, constraint, prefix): if version < constraint: return False m = self.numeric_re.match(str(constraint)) if not m: logger.warning('Cannot compute compatible match for version %s ' ' and constraint %s', version, constraint) return True s = m.groups()[0] if '.' in s: s = s.rsplit('.', 1)[0] return _match_prefix(version, s) # # Semantic versioning # _SEMVER_RE = re.compile(r'^(\d+)\.(\d+)\.(\d+)' r'(-[a-z0-9]+(\.[a-z0-9-]+)*)?' r'(\+[a-z0-9]+(\.[a-z0-9-]+)*)?$', re.I) def is_semver(s): return _SEMVER_RE.match(s) def _semantic_key(s): def make_tuple(s, absent): if s is None: result = (absent,) else: parts = s[1:].split('.') # We can't compare ints and strings on Python 3, so fudge it # by zero-filling numeric values so simulate a numeric comparison result = tuple([p.zfill(8) if p.isdigit() else p for p in parts]) return result m = is_semver(s) if not m: raise UnsupportedVersionError(s) groups = m.groups() major, minor, patch = [int(i) for i in groups[:3]] # choose the '|' and '*' so that versions sort correctly pre, build = make_tuple(groups[3], '|'), make_tuple(groups[5], '*') return (major, minor, patch), pre, build class SemanticVersion(Version): def parse(self, s): return _semantic_key(s) @property def is_prerelease(self): return self._parts[1][0] != '|' class SemanticMatcher(Matcher): version_class = SemanticVersion class VersionScheme(object): def __init__(self, key, matcher, suggester=None): self.key = key self.matcher = matcher self.suggester = suggester def is_valid_version(self, s): try: self.matcher.version_class(s) result = True except UnsupportedVersionError: result = False return result def is_valid_matcher(self, s): try: self.matcher(s) result = True except UnsupportedVersionError: result = False return result def is_valid_constraint_list(self, s): """ Used for processing some metadata fields """ return self.is_valid_matcher('dummy_name (%s)' % s) def suggest(self, s): if self.suggester is None: result = None else: result = self.suggester(s) return result _SCHEMES = { 'normalized': VersionScheme(_normalized_key, NormalizedMatcher, _suggest_normalized_version), 'legacy': VersionScheme(_legacy_key, LegacyMatcher, lambda self, s: s), 'semantic': VersionScheme(_semantic_key, SemanticMatcher, _suggest_semantic_version), } _SCHEMES['default'] = _SCHEMES['normalized'] def get_scheme(name): if name not in _SCHEMES: raise ValueError('unknown scheme name: %r' % name) return _SCHEMES[name] feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/distlib/wheel.py0000644000076500000240000011420312700725533030014 0ustar jmstaff00000000000000# -*- coding: utf-8 -*- # # Copyright (C) 2013-2016 Vinay Sajip. # Licensed to the Python Software Foundation under a contributor agreement. # See LICENSE.txt and CONTRIBUTORS.txt. # from __future__ import unicode_literals import base64 import codecs import datetime import distutils.util from email import message_from_file import hashlib import imp import json import logging import os import posixpath import re import shutil import sys import tempfile import zipfile from . import __version__, DistlibException from .compat import sysconfig, ZipFile, fsdecode, text_type, filter from .database import InstalledDistribution from .metadata import Metadata, METADATA_FILENAME from .util import (FileOperator, convert_path, CSVReader, CSVWriter, Cache, cached_property, get_cache_base, read_exports, tempdir) from .version import NormalizedVersion, UnsupportedVersionError logger = logging.getLogger(__name__) cache = None # created when needed if hasattr(sys, 'pypy_version_info'): IMP_PREFIX = 'pp' elif sys.platform.startswith('java'): IMP_PREFIX = 'jy' elif sys.platform == 'cli': IMP_PREFIX = 'ip' else: IMP_PREFIX = 'cp' VER_SUFFIX = sysconfig.get_config_var('py_version_nodot') if not VER_SUFFIX: # pragma: no cover VER_SUFFIX = '%s%s' % sys.version_info[:2] PYVER = 'py' + VER_SUFFIX IMPVER = IMP_PREFIX + VER_SUFFIX ARCH = distutils.util.get_platform().replace('-', '_').replace('.', '_') ABI = sysconfig.get_config_var('SOABI') if ABI and ABI.startswith('cpython-'): ABI = ABI.replace('cpython-', 'cp') else: def _derive_abi(): parts = ['cp', VER_SUFFIX] if sysconfig.get_config_var('Py_DEBUG'): parts.append('d') if sysconfig.get_config_var('WITH_PYMALLOC'): parts.append('m') if sysconfig.get_config_var('Py_UNICODE_SIZE') == 4: parts.append('u') return ''.join(parts) ABI = _derive_abi() del _derive_abi FILENAME_RE = re.compile(r''' (?P[^-]+) -(?P\d+[^-]*) (-(?P\d+[^-]*))? -(?P\w+\d+(\.\w+\d+)*) -(?P\w+) -(?P\w+(\.\w+)*) \.whl$ ''', re.IGNORECASE | re.VERBOSE) NAME_VERSION_RE = re.compile(r''' (?P[^-]+) -(?P\d+[^-]*) (-(?P\d+[^-]*))?$ ''', re.IGNORECASE | re.VERBOSE) SHEBANG_RE = re.compile(br'\s*#![^\r\n]*') SHEBANG_DETAIL_RE = re.compile(br'^(\s*#!("[^"]+"|\S+))\s+(.*)$') SHEBANG_PYTHON = b'#!python' SHEBANG_PYTHONW = b'#!pythonw' if os.sep == '/': to_posix = lambda o: o else: to_posix = lambda o: o.replace(os.sep, '/') class Mounter(object): def __init__(self): self.impure_wheels = {} self.libs = {} def add(self, pathname, extensions): self.impure_wheels[pathname] = extensions self.libs.update(extensions) def remove(self, pathname): extensions = self.impure_wheels.pop(pathname) for k, v in extensions: if k in self.libs: del self.libs[k] def find_module(self, fullname, path=None): if fullname in self.libs: result = self else: result = None return result def load_module(self, fullname): if fullname in sys.modules: result = sys.modules[fullname] else: if fullname not in self.libs: raise ImportError('unable to find extension for %s' % fullname) result = imp.load_dynamic(fullname, self.libs[fullname]) result.__loader__ = self parts = fullname.rsplit('.', 1) if len(parts) > 1: result.__package__ = parts[0] return result _hook = Mounter() class Wheel(object): """ Class to build and install from Wheel files (PEP 427). """ wheel_version = (1, 1) hash_kind = 'sha256' def __init__(self, filename=None, sign=False, verify=False): """ Initialise an instance using a (valid) filename. """ self.sign = sign self.should_verify = verify self.buildver = '' self.pyver = [PYVER] self.abi = ['none'] self.arch = ['any'] self.dirname = os.getcwd() if filename is None: self.name = 'dummy' self.version = '0.1' self._filename = self.filename else: m = NAME_VERSION_RE.match(filename) if m: info = m.groupdict('') self.name = info['nm'] # Reinstate the local version separator self.version = info['vn'].replace('_', '-') self.buildver = info['bn'] self._filename = self.filename else: dirname, filename = os.path.split(filename) m = FILENAME_RE.match(filename) if not m: raise DistlibException('Invalid name or ' 'filename: %r' % filename) if dirname: self.dirname = os.path.abspath(dirname) self._filename = filename info = m.groupdict('') self.name = info['nm'] self.version = info['vn'] self.buildver = info['bn'] self.pyver = info['py'].split('.') self.abi = info['bi'].split('.') self.arch = info['ar'].split('.') @property def filename(self): """ Build and return a filename from the various components. """ if self.buildver: buildver = '-' + self.buildver else: buildver = '' pyver = '.'.join(self.pyver) abi = '.'.join(self.abi) arch = '.'.join(self.arch) # replace - with _ as a local version separator version = self.version.replace('-', '_') return '%s-%s%s-%s-%s-%s.whl' % (self.name, version, buildver, pyver, abi, arch) @property def exists(self): path = os.path.join(self.dirname, self.filename) return os.path.isfile(path) @property def tags(self): for pyver in self.pyver: for abi in self.abi: for arch in self.arch: yield pyver, abi, arch @cached_property def metadata(self): pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) info_dir = '%s.dist-info' % name_ver wrapper = codecs.getreader('utf-8') with ZipFile(pathname, 'r') as zf: wheel_metadata = self.get_wheel_metadata(zf) wv = wheel_metadata['Wheel-Version'].split('.', 1) file_version = tuple([int(i) for i in wv]) if file_version < (1, 1): fn = 'METADATA' else: fn = METADATA_FILENAME try: metadata_filename = posixpath.join(info_dir, fn) with zf.open(metadata_filename) as bf: wf = wrapper(bf) result = Metadata(fileobj=wf) except KeyError: raise ValueError('Invalid wheel, because %s is ' 'missing' % fn) return result def get_wheel_metadata(self, zf): name_ver = '%s-%s' % (self.name, self.version) info_dir = '%s.dist-info' % name_ver metadata_filename = posixpath.join(info_dir, 'WHEEL') with zf.open(metadata_filename) as bf: wf = codecs.getreader('utf-8')(bf) message = message_from_file(wf) return dict(message) @cached_property def info(self): pathname = os.path.join(self.dirname, self.filename) with ZipFile(pathname, 'r') as zf: result = self.get_wheel_metadata(zf) return result def process_shebang(self, data): m = SHEBANG_RE.match(data) if m: end = m.end() shebang, data_after_shebang = data[:end], data[end:] # Preserve any arguments after the interpreter if b'pythonw' in shebang.lower(): shebang_python = SHEBANG_PYTHONW else: shebang_python = SHEBANG_PYTHON m = SHEBANG_DETAIL_RE.match(shebang) if m: args = b' ' + m.groups()[-1] else: args = b'' shebang = shebang_python + args data = shebang + data_after_shebang else: cr = data.find(b'\r') lf = data.find(b'\n') if cr < 0 or cr > lf: term = b'\n' else: if data[cr:cr + 2] == b'\r\n': term = b'\r\n' else: term = b'\r' data = SHEBANG_PYTHON + term + data return data def get_hash(self, data, hash_kind=None): if hash_kind is None: hash_kind = self.hash_kind try: hasher = getattr(hashlib, hash_kind) except AttributeError: raise DistlibException('Unsupported hash algorithm: %r' % hash_kind) result = hasher(data).digest() result = base64.urlsafe_b64encode(result).rstrip(b'=').decode('ascii') return hash_kind, result def write_record(self, records, record_path, base): with CSVWriter(record_path) as writer: for row in records: writer.writerow(row) p = to_posix(os.path.relpath(record_path, base)) writer.writerow((p, '', '')) def write_records(self, info, libdir, archive_paths): records = [] distinfo, info_dir = info hasher = getattr(hashlib, self.hash_kind) for ap, p in archive_paths: with open(p, 'rb') as f: data = f.read() digest = '%s=%s' % self.get_hash(data) size = os.path.getsize(p) records.append((ap, digest, size)) p = os.path.join(distinfo, 'RECORD') self.write_record(records, p, libdir) ap = to_posix(os.path.join(info_dir, 'RECORD')) archive_paths.append((ap, p)) def build_zip(self, pathname, archive_paths): with ZipFile(pathname, 'w', zipfile.ZIP_DEFLATED) as zf: for ap, p in archive_paths: logger.debug('Wrote %s to %s in wheel', p, ap) zf.write(p, ap) def build(self, paths, tags=None, wheel_version=None): """ Build a wheel from files in specified paths, and use any specified tags when determining the name of the wheel. """ if tags is None: tags = {} libkey = list(filter(lambda o: o in paths, ('purelib', 'platlib')))[0] if libkey == 'platlib': is_pure = 'false' default_pyver = [IMPVER] default_abi = [ABI] default_arch = [ARCH] else: is_pure = 'true' default_pyver = [PYVER] default_abi = ['none'] default_arch = ['any'] self.pyver = tags.get('pyver', default_pyver) self.abi = tags.get('abi', default_abi) self.arch = tags.get('arch', default_arch) libdir = paths[libkey] name_ver = '%s-%s' % (self.name, self.version) data_dir = '%s.data' % name_ver info_dir = '%s.dist-info' % name_ver archive_paths = [] # First, stuff which is not in site-packages for key in ('data', 'headers', 'scripts'): if key not in paths: continue path = paths[key] if os.path.isdir(path): for root, dirs, files in os.walk(path): for fn in files: p = fsdecode(os.path.join(root, fn)) rp = os.path.relpath(p, path) ap = to_posix(os.path.join(data_dir, key, rp)) archive_paths.append((ap, p)) if key == 'scripts' and not p.endswith('.exe'): with open(p, 'rb') as f: data = f.read() data = self.process_shebang(data) with open(p, 'wb') as f: f.write(data) # Now, stuff which is in site-packages, other than the # distinfo stuff. path = libdir distinfo = None for root, dirs, files in os.walk(path): if root == path: # At the top level only, save distinfo for later # and skip it for now for i, dn in enumerate(dirs): dn = fsdecode(dn) if dn.endswith('.dist-info'): distinfo = os.path.join(root, dn) del dirs[i] break assert distinfo, '.dist-info directory expected, not found' for fn in files: # comment out next suite to leave .pyc files in if fsdecode(fn).endswith(('.pyc', '.pyo')): continue p = os.path.join(root, fn) rp = to_posix(os.path.relpath(p, path)) archive_paths.append((rp, p)) # Now distinfo. Assumed to be flat, i.e. os.listdir is enough. files = os.listdir(distinfo) for fn in files: if fn not in ('RECORD', 'INSTALLER', 'SHARED', 'WHEEL'): p = fsdecode(os.path.join(distinfo, fn)) ap = to_posix(os.path.join(info_dir, fn)) archive_paths.append((ap, p)) wheel_metadata = [ 'Wheel-Version: %d.%d' % (wheel_version or self.wheel_version), 'Generator: distlib %s' % __version__, 'Root-Is-Purelib: %s' % is_pure, ] for pyver, abi, arch in self.tags: wheel_metadata.append('Tag: %s-%s-%s' % (pyver, abi, arch)) p = os.path.join(distinfo, 'WHEEL') with open(p, 'w') as f: f.write('\n'.join(wheel_metadata)) ap = to_posix(os.path.join(info_dir, 'WHEEL')) archive_paths.append((ap, p)) # Now, at last, RECORD. # Paths in here are archive paths - nothing else makes sense. self.write_records((distinfo, info_dir), libdir, archive_paths) # Now, ready to build the zip file pathname = os.path.join(self.dirname, self.filename) self.build_zip(pathname, archive_paths) return pathname def install(self, paths, maker, **kwargs): """ Install a wheel to the specified paths. If kwarg ``warner`` is specified, it should be a callable, which will be called with two tuples indicating the wheel version of this software and the wheel version in the file, if there is a discrepancy in the versions. This can be used to issue any warnings to raise any exceptions. If kwarg ``lib_only`` is True, only the purelib/platlib files are installed, and the headers, scripts, data and dist-info metadata are not written. The return value is a :class:`InstalledDistribution` instance unless ``options.lib_only`` is True, in which case the return value is ``None``. """ dry_run = maker.dry_run warner = kwargs.get('warner') lib_only = kwargs.get('lib_only', False) pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) data_dir = '%s.data' % name_ver info_dir = '%s.dist-info' % name_ver metadata_name = posixpath.join(info_dir, METADATA_FILENAME) wheel_metadata_name = posixpath.join(info_dir, 'WHEEL') record_name = posixpath.join(info_dir, 'RECORD') wrapper = codecs.getreader('utf-8') with ZipFile(pathname, 'r') as zf: with zf.open(wheel_metadata_name) as bwf: wf = wrapper(bwf) message = message_from_file(wf) wv = message['Wheel-Version'].split('.', 1) file_version = tuple([int(i) for i in wv]) if (file_version != self.wheel_version) and warner: warner(self.wheel_version, file_version) if message['Root-Is-Purelib'] == 'true': libdir = paths['purelib'] else: libdir = paths['platlib'] records = {} with zf.open(record_name) as bf: with CSVReader(stream=bf) as reader: for row in reader: p = row[0] records[p] = row data_pfx = posixpath.join(data_dir, '') info_pfx = posixpath.join(info_dir, '') script_pfx = posixpath.join(data_dir, 'scripts', '') # make a new instance rather than a copy of maker's, # as we mutate it fileop = FileOperator(dry_run=dry_run) fileop.record = True # so we can rollback if needed bc = not sys.dont_write_bytecode # Double negatives. Lovely! outfiles = [] # for RECORD writing # for script copying/shebang processing workdir = tempfile.mkdtemp() # set target dir later # we default add_launchers to False, as the # Python Launcher should be used instead maker.source_dir = workdir maker.target_dir = None try: for zinfo in zf.infolist(): arcname = zinfo.filename if isinstance(arcname, text_type): u_arcname = arcname else: u_arcname = arcname.decode('utf-8') # The signature file won't be in RECORD, # and we don't currently don't do anything with it if u_arcname.endswith('/RECORD.jws'): continue row = records[u_arcname] if row[2] and str(zinfo.file_size) != row[2]: raise DistlibException('size mismatch for ' '%s' % u_arcname) if row[1]: kind, value = row[1].split('=', 1) with zf.open(arcname) as bf: data = bf.read() _, digest = self.get_hash(data, kind) if digest != value: raise DistlibException('digest mismatch for ' '%s' % arcname) if lib_only and u_arcname.startswith((info_pfx, data_pfx)): logger.debug('lib_only: skipping %s', u_arcname) continue is_script = (u_arcname.startswith(script_pfx) and not u_arcname.endswith('.exe')) if u_arcname.startswith(data_pfx): _, where, rp = u_arcname.split('/', 2) outfile = os.path.join(paths[where], convert_path(rp)) else: # meant for site-packages. if u_arcname in (wheel_metadata_name, record_name): continue outfile = os.path.join(libdir, convert_path(u_arcname)) if not is_script: with zf.open(arcname) as bf: fileop.copy_stream(bf, outfile) outfiles.append(outfile) # Double check the digest of the written file if not dry_run and row[1]: with open(outfile, 'rb') as bf: data = bf.read() _, newdigest = self.get_hash(data, kind) if newdigest != digest: raise DistlibException('digest mismatch ' 'on write for ' '%s' % outfile) if bc and outfile.endswith('.py'): try: pyc = fileop.byte_compile(outfile) outfiles.append(pyc) except Exception: # Don't give up if byte-compilation fails, # but log it and perhaps warn the user logger.warning('Byte-compilation failed', exc_info=True) else: fn = os.path.basename(convert_path(arcname)) workname = os.path.join(workdir, fn) with zf.open(arcname) as bf: fileop.copy_stream(bf, workname) dn, fn = os.path.split(outfile) maker.target_dir = dn filenames = maker.make(fn) fileop.set_executable_mode(filenames) outfiles.extend(filenames) if lib_only: logger.debug('lib_only: returning None') dist = None else: # Generate scripts # Try to get pydist.json so we can see if there are # any commands to generate. If this fails (e.g. because # of a legacy wheel), log a warning but don't give up. commands = None file_version = self.info['Wheel-Version'] if file_version == '1.0': # Use legacy info ep = posixpath.join(info_dir, 'entry_points.txt') try: with zf.open(ep) as bwf: epdata = read_exports(bwf) commands = {} for key in ('console', 'gui'): k = '%s_scripts' % key if k in epdata: commands['wrap_%s' % key] = d = {} for v in epdata[k].values(): s = '%s:%s' % (v.prefix, v.suffix) if v.flags: s += ' %s' % v.flags d[v.name] = s except Exception: logger.warning('Unable to read legacy script ' 'metadata, so cannot generate ' 'scripts') else: try: with zf.open(metadata_name) as bwf: wf = wrapper(bwf) commands = json.load(wf).get('extensions') if commands: commands = commands.get('python.commands') except Exception: logger.warning('Unable to read JSON metadata, so ' 'cannot generate scripts') if commands: console_scripts = commands.get('wrap_console', {}) gui_scripts = commands.get('wrap_gui', {}) if console_scripts or gui_scripts: script_dir = paths.get('scripts', '') if not os.path.isdir(script_dir): raise ValueError('Valid script path not ' 'specified') maker.target_dir = script_dir for k, v in console_scripts.items(): script = '%s = %s' % (k, v) filenames = maker.make(script) fileop.set_executable_mode(filenames) if gui_scripts: options = {'gui': True } for k, v in gui_scripts.items(): script = '%s = %s' % (k, v) filenames = maker.make(script, options) fileop.set_executable_mode(filenames) p = os.path.join(libdir, info_dir) dist = InstalledDistribution(p) # Write SHARED paths = dict(paths) # don't change passed in dict del paths['purelib'] del paths['platlib'] paths['lib'] = libdir p = dist.write_shared_locations(paths, dry_run) if p: outfiles.append(p) # Write RECORD dist.write_installed_files(outfiles, paths['prefix'], dry_run) return dist except Exception: # pragma: no cover logger.exception('installation failed.') fileop.rollback() raise finally: shutil.rmtree(workdir) def _get_dylib_cache(self): global cache if cache is None: # Use native string to avoid issues on 2.x: see Python #20140. base = os.path.join(get_cache_base(), str('dylib-cache'), sys.version[:3]) cache = Cache(base) return cache def _get_extensions(self): pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) info_dir = '%s.dist-info' % name_ver arcname = posixpath.join(info_dir, 'EXTENSIONS') wrapper = codecs.getreader('utf-8') result = [] with ZipFile(pathname, 'r') as zf: try: with zf.open(arcname) as bf: wf = wrapper(bf) extensions = json.load(wf) cache = self._get_dylib_cache() prefix = cache.prefix_to_dir(pathname) cache_base = os.path.join(cache.base, prefix) if not os.path.isdir(cache_base): os.makedirs(cache_base) for name, relpath in extensions.items(): dest = os.path.join(cache_base, convert_path(relpath)) if not os.path.exists(dest): extract = True else: file_time = os.stat(dest).st_mtime file_time = datetime.datetime.fromtimestamp(file_time) info = zf.getinfo(relpath) wheel_time = datetime.datetime(*info.date_time) extract = wheel_time > file_time if extract: zf.extract(relpath, cache_base) result.append((name, dest)) except KeyError: pass return result def is_compatible(self): """ Determine if a wheel is compatible with the running system. """ return is_compatible(self) def is_mountable(self): """ Determine if a wheel is asserted as mountable by its metadata. """ return True # for now - metadata details TBD def mount(self, append=False): pathname = os.path.abspath(os.path.join(self.dirname, self.filename)) if not self.is_compatible(): msg = 'Wheel %s not compatible with this Python.' % pathname raise DistlibException(msg) if not self.is_mountable(): msg = 'Wheel %s is marked as not mountable.' % pathname raise DistlibException(msg) if pathname in sys.path: logger.debug('%s already in path', pathname) else: if append: sys.path.append(pathname) else: sys.path.insert(0, pathname) extensions = self._get_extensions() if extensions: if _hook not in sys.meta_path: sys.meta_path.append(_hook) _hook.add(pathname, extensions) def unmount(self): pathname = os.path.abspath(os.path.join(self.dirname, self.filename)) if pathname not in sys.path: logger.debug('%s not in path', pathname) else: sys.path.remove(pathname) if pathname in _hook.impure_wheels: _hook.remove(pathname) if not _hook.impure_wheels: if _hook in sys.meta_path: sys.meta_path.remove(_hook) def verify(self): pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) data_dir = '%s.data' % name_ver info_dir = '%s.dist-info' % name_ver metadata_name = posixpath.join(info_dir, METADATA_FILENAME) wheel_metadata_name = posixpath.join(info_dir, 'WHEEL') record_name = posixpath.join(info_dir, 'RECORD') wrapper = codecs.getreader('utf-8') with ZipFile(pathname, 'r') as zf: with zf.open(wheel_metadata_name) as bwf: wf = wrapper(bwf) message = message_from_file(wf) wv = message['Wheel-Version'].split('.', 1) file_version = tuple([int(i) for i in wv]) # TODO version verification records = {} with zf.open(record_name) as bf: with CSVReader(stream=bf) as reader: for row in reader: p = row[0] records[p] = row for zinfo in zf.infolist(): arcname = zinfo.filename if isinstance(arcname, text_type): u_arcname = arcname else: u_arcname = arcname.decode('utf-8') if '..' in u_arcname: raise DistlibException('invalid entry in ' 'wheel: %r' % u_arcname) # The signature file won't be in RECORD, # and we don't currently don't do anything with it if u_arcname.endswith('/RECORD.jws'): continue row = records[u_arcname] if row[2] and str(zinfo.file_size) != row[2]: raise DistlibException('size mismatch for ' '%s' % u_arcname) if row[1]: kind, value = row[1].split('=', 1) with zf.open(arcname) as bf: data = bf.read() _, digest = self.get_hash(data, kind) if digest != value: raise DistlibException('digest mismatch for ' '%s' % arcname) def update(self, modifier, dest_dir=None, **kwargs): """ Update the contents of a wheel in a generic way. The modifier should be a callable which expects a dictionary argument: its keys are archive-entry paths, and its values are absolute filesystem paths where the contents the corresponding archive entries can be found. The modifier is free to change the contents of the files pointed to, add new entries and remove entries, before returning. This method will extract the entire contents of the wheel to a temporary location, call the modifier, and then use the passed (and possibly updated) dictionary to write a new wheel. If ``dest_dir`` is specified, the new wheel is written there -- otherwise, the original wheel is overwritten. The modifier should return True if it updated the wheel, else False. This method returns the same value the modifier returns. """ def get_version(path_map, info_dir): version = path = None key = '%s/%s' % (info_dir, METADATA_FILENAME) if key not in path_map: key = '%s/PKG-INFO' % info_dir if key in path_map: path = path_map[key] version = Metadata(path=path).version return version, path def update_version(version, path): updated = None try: v = NormalizedVersion(version) i = version.find('-') if i < 0: updated = '%s+1' % version else: parts = [int(s) for s in version[i + 1:].split('.')] parts[-1] += 1 updated = '%s+%s' % (version[:i], '.'.join(str(i) for i in parts)) except UnsupportedVersionError: logger.debug('Cannot update non-compliant (PEP-440) ' 'version %r', version) if updated: md = Metadata(path=path) md.version = updated legacy = not path.endswith(METADATA_FILENAME) md.write(path=path, legacy=legacy) logger.debug('Version updated from %r to %r', version, updated) pathname = os.path.join(self.dirname, self.filename) name_ver = '%s-%s' % (self.name, self.version) info_dir = '%s.dist-info' % name_ver record_name = posixpath.join(info_dir, 'RECORD') with tempdir() as workdir: with ZipFile(pathname, 'r') as zf: path_map = {} for zinfo in zf.infolist(): arcname = zinfo.filename if isinstance(arcname, text_type): u_arcname = arcname else: u_arcname = arcname.decode('utf-8') if u_arcname == record_name: continue if '..' in u_arcname: raise DistlibException('invalid entry in ' 'wheel: %r' % u_arcname) zf.extract(zinfo, workdir) path = os.path.join(workdir, convert_path(u_arcname)) path_map[u_arcname] = path # Remember the version. original_version, _ = get_version(path_map, info_dir) # Files extracted. Call the modifier. modified = modifier(path_map, **kwargs) if modified: # Something changed - need to build a new wheel. current_version, path = get_version(path_map, info_dir) if current_version and (current_version == original_version): # Add or update local version to signify changes. update_version(current_version, path) # Decide where the new wheel goes. if dest_dir is None: fd, newpath = tempfile.mkstemp(suffix='.whl', prefix='wheel-update-', dir=workdir) os.close(fd) else: if not os.path.isdir(dest_dir): raise DistlibException('Not a directory: %r' % dest_dir) newpath = os.path.join(dest_dir, self.filename) archive_paths = list(path_map.items()) distinfo = os.path.join(workdir, info_dir) info = distinfo, info_dir self.write_records(info, workdir, archive_paths) self.build_zip(newpath, archive_paths) if dest_dir is None: shutil.copyfile(newpath, pathname) return modified def compatible_tags(): """ Return (pyver, abi, arch) tuples compatible with this Python. """ versions = [VER_SUFFIX] major = VER_SUFFIX[0] for minor in range(sys.version_info[1] - 1, - 1, -1): versions.append(''.join([major, str(minor)])) abis = [] for suffix, _, _ in imp.get_suffixes(): if suffix.startswith('.abi'): abis.append(suffix.split('.', 2)[1]) abis.sort() if ABI != 'none': abis.insert(0, ABI) abis.append('none') result = [] arches = [ARCH] if sys.platform == 'darwin': m = re.match('(\w+)_(\d+)_(\d+)_(\w+)$', ARCH) if m: name, major, minor, arch = m.groups() minor = int(minor) matches = [arch] if arch in ('i386', 'ppc'): matches.append('fat') if arch in ('i386', 'ppc', 'x86_64'): matches.append('fat3') if arch in ('ppc64', 'x86_64'): matches.append('fat64') if arch in ('i386', 'x86_64'): matches.append('intel') if arch in ('i386', 'x86_64', 'intel', 'ppc', 'ppc64'): matches.append('universal') while minor >= 0: for match in matches: s = '%s_%s_%s_%s' % (name, major, minor, match) if s != ARCH: # already there arches.append(s) minor -= 1 # Most specific - our Python version, ABI and arch for abi in abis: for arch in arches: result.append((''.join((IMP_PREFIX, versions[0])), abi, arch)) # where no ABI / arch dependency, but IMP_PREFIX dependency for i, version in enumerate(versions): result.append((''.join((IMP_PREFIX, version)), 'none', 'any')) if i == 0: result.append((''.join((IMP_PREFIX, version[0])), 'none', 'any')) # no IMP_PREFIX, ABI or arch dependency for i, version in enumerate(versions): result.append((''.join(('py', version)), 'none', 'any')) if i == 0: result.append((''.join(('py', version[0])), 'none', 'any')) return set(result) COMPATIBLE_TAGS = compatible_tags() del compatible_tags def is_compatible(wheel, tags=None): if not isinstance(wheel, Wheel): wheel = Wheel(wheel) # assume it's a filename result = False if tags is None: tags = COMPATIBLE_TAGS for ver, abi, arch in tags: if ver in wheel.pyver and abi in wheel.abi and arch in wheel.arch: result = True break return result feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/0000755000076500000240000000000012765362057026434 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/__init__.py0000644000076500000240000000141312700725533030533 0ustar jmstaff00000000000000""" HTML parsing library based on the WHATWG "HTML5" specification. The parser is designed to be compatible with existing HTML found in the wild and implements well-defined error recovery that is largely compatible with modern desktop web browsers. Example usage: import html5lib f = open("my_document.html") tree = html5lib.parse(f) """ from __future__ import absolute_import, division, unicode_literals from .html5parser import HTMLParser, parse, parseFragment from .treebuilders import getTreeBuilder from .treewalkers import getTreeWalker from .serializer import serialize __all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder", "getTreeWalker", "serialize"] # this has to be at the top level, see how setup.py parses this __version__ = "1.0b8" feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/constants.py0000644000076500000240000025153112700725533031020 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals import string EOF = None E = { "null-character": "Null character in input stream, replaced with U+FFFD.", "invalid-codepoint": "Invalid codepoint in stream.", "incorrectly-placed-solidus": "Solidus (/) incorrectly placed in tag.", "incorrect-cr-newline-entity": "Incorrect CR newline entity, replaced with LF.", "illegal-windows-1252-entity": "Entity used with illegal number (windows-1252 reference).", "cant-convert-numeric-entity": "Numeric entity couldn't be converted to character " "(codepoint U+%(charAsInt)08x).", "illegal-codepoint-for-numeric-entity": "Numeric entity represents an illegal codepoint: " "U+%(charAsInt)08x.", "numeric-entity-without-semicolon": "Numeric entity didn't end with ';'.", "expected-numeric-entity-but-got-eof": "Numeric entity expected. Got end of file instead.", "expected-numeric-entity": "Numeric entity expected but none found.", "named-entity-without-semicolon": "Named entity didn't end with ';'.", "expected-named-entity": "Named entity expected. Got none.", "attributes-in-end-tag": "End tag contains unexpected attributes.", 'self-closing-flag-on-end-tag': "End tag contains unexpected self-closing flag.", "expected-tag-name-but-got-right-bracket": "Expected tag name. Got '>' instead.", "expected-tag-name-but-got-question-mark": "Expected tag name. Got '?' instead. (HTML doesn't " "support processing instructions.)", "expected-tag-name": "Expected tag name. Got something else instead", "expected-closing-tag-but-got-right-bracket": "Expected closing tag. Got '>' instead. Ignoring ''.", "expected-closing-tag-but-got-eof": "Expected closing tag. Unexpected end of file.", "expected-closing-tag-but-got-char": "Expected closing tag. Unexpected character '%(data)s' found.", "eof-in-tag-name": "Unexpected end of file in the tag name.", "expected-attribute-name-but-got-eof": "Unexpected end of file. Expected attribute name instead.", "eof-in-attribute-name": "Unexpected end of file in attribute name.", "invalid-character-in-attribute-name": "Invalid character in attribute name", "duplicate-attribute": "Dropped duplicate attribute on tag.", "expected-end-of-tag-name-but-got-eof": "Unexpected end of file. Expected = or end of tag.", "expected-attribute-value-but-got-eof": "Unexpected end of file. Expected attribute value.", "expected-attribute-value-but-got-right-bracket": "Expected attribute value. Got '>' instead.", 'equals-in-unquoted-attribute-value': "Unexpected = in unquoted attribute", 'unexpected-character-in-unquoted-attribute-value': "Unexpected character in unquoted attribute", "invalid-character-after-attribute-name": "Unexpected character after attribute name.", "unexpected-character-after-attribute-value": "Unexpected character after attribute value.", "eof-in-attribute-value-double-quote": "Unexpected end of file in attribute value (\").", "eof-in-attribute-value-single-quote": "Unexpected end of file in attribute value (').", "eof-in-attribute-value-no-quotes": "Unexpected end of file in attribute value.", "unexpected-EOF-after-solidus-in-tag": "Unexpected end of file in tag. Expected >", "unexpected-character-after-solidus-in-tag": "Unexpected character after / in tag. Expected >", "expected-dashes-or-doctype": "Expected '--' or 'DOCTYPE'. Not found.", "unexpected-bang-after-double-dash-in-comment": "Unexpected ! after -- in comment", "unexpected-space-after-double-dash-in-comment": "Unexpected space after -- in comment", "incorrect-comment": "Incorrect comment.", "eof-in-comment": "Unexpected end of file in comment.", "eof-in-comment-end-dash": "Unexpected end of file in comment (-)", "unexpected-dash-after-double-dash-in-comment": "Unexpected '-' after '--' found in comment.", "eof-in-comment-double-dash": "Unexpected end of file in comment (--).", "eof-in-comment-end-space-state": "Unexpected end of file in comment.", "eof-in-comment-end-bang-state": "Unexpected end of file in comment.", "unexpected-char-in-comment": "Unexpected character in comment found.", "need-space-after-doctype": "No space after literal string 'DOCTYPE'.", "expected-doctype-name-but-got-right-bracket": "Unexpected > character. Expected DOCTYPE name.", "expected-doctype-name-but-got-eof": "Unexpected end of file. Expected DOCTYPE name.", "eof-in-doctype-name": "Unexpected end of file in DOCTYPE name.", "eof-in-doctype": "Unexpected end of file in DOCTYPE.", "expected-space-or-right-bracket-in-doctype": "Expected space or '>'. Got '%(data)s'", "unexpected-end-of-doctype": "Unexpected end of DOCTYPE.", "unexpected-char-in-doctype": "Unexpected character in DOCTYPE.", "eof-in-innerhtml": "XXX innerHTML EOF", "unexpected-doctype": "Unexpected DOCTYPE. Ignored.", "non-html-root": "html needs to be the first start tag.", "expected-doctype-but-got-eof": "Unexpected End of file. Expected DOCTYPE.", "unknown-doctype": "Erroneous DOCTYPE.", "expected-doctype-but-got-chars": "Unexpected non-space characters. Expected DOCTYPE.", "expected-doctype-but-got-start-tag": "Unexpected start tag (%(name)s). Expected DOCTYPE.", "expected-doctype-but-got-end-tag": "Unexpected end tag (%(name)s). Expected DOCTYPE.", "end-tag-after-implied-root": "Unexpected end tag (%(name)s) after the (implied) root element.", "expected-named-closing-tag-but-got-eof": "Unexpected end of file. Expected end tag (%(name)s).", "two-heads-are-not-better-than-one": "Unexpected start tag head in existing head. Ignored.", "unexpected-end-tag": "Unexpected end tag (%(name)s). Ignored.", "unexpected-start-tag-out-of-my-head": "Unexpected start tag (%(name)s) that can be in head. Moved.", "unexpected-start-tag": "Unexpected start tag (%(name)s).", "missing-end-tag": "Missing end tag (%(name)s).", "missing-end-tags": "Missing end tags (%(name)s).", "unexpected-start-tag-implies-end-tag": "Unexpected start tag (%(startName)s) " "implies end tag (%(endName)s).", "unexpected-start-tag-treated-as": "Unexpected start tag (%(originalName)s). Treated as %(newName)s.", "deprecated-tag": "Unexpected start tag %(name)s. Don't use it!", "unexpected-start-tag-ignored": "Unexpected start tag %(name)s. Ignored.", "expected-one-end-tag-but-got-another": "Unexpected end tag (%(gotName)s). " "Missing end tag (%(expectedName)s).", "end-tag-too-early": "End tag (%(name)s) seen too early. Expected other end tag.", "end-tag-too-early-named": "Unexpected end tag (%(gotName)s). Expected end tag (%(expectedName)s).", "end-tag-too-early-ignored": "End tag (%(name)s) seen too early. Ignored.", "adoption-agency-1.1": "End tag (%(name)s) violates step 1, " "paragraph 1 of the adoption agency algorithm.", "adoption-agency-1.2": "End tag (%(name)s) violates step 1, " "paragraph 2 of the adoption agency algorithm.", "adoption-agency-1.3": "End tag (%(name)s) violates step 1, " "paragraph 3 of the adoption agency algorithm.", "adoption-agency-4.4": "End tag (%(name)s) violates step 4, " "paragraph 4 of the adoption agency algorithm.", "unexpected-end-tag-treated-as": "Unexpected end tag (%(originalName)s). Treated as %(newName)s.", "no-end-tag": "This element (%(name)s) has no end tag.", "unexpected-implied-end-tag-in-table": "Unexpected implied end tag (%(name)s) in the table phase.", "unexpected-implied-end-tag-in-table-body": "Unexpected implied end tag (%(name)s) in the table body phase.", "unexpected-char-implies-table-voodoo": "Unexpected non-space characters in " "table context caused voodoo mode.", "unexpected-hidden-input-in-table": "Unexpected input with type hidden in table context.", "unexpected-form-in-table": "Unexpected form in table context.", "unexpected-start-tag-implies-table-voodoo": "Unexpected start tag (%(name)s) in " "table context caused voodoo mode.", "unexpected-end-tag-implies-table-voodoo": "Unexpected end tag (%(name)s) in " "table context caused voodoo mode.", "unexpected-cell-in-table-body": "Unexpected table cell start tag (%(name)s) " "in the table body phase.", "unexpected-cell-end-tag": "Got table cell end tag (%(name)s) " "while required end tags are missing.", "unexpected-end-tag-in-table-body": "Unexpected end tag (%(name)s) in the table body phase. Ignored.", "unexpected-implied-end-tag-in-table-row": "Unexpected implied end tag (%(name)s) in the table row phase.", "unexpected-end-tag-in-table-row": "Unexpected end tag (%(name)s) in the table row phase. Ignored.", "unexpected-select-in-select": "Unexpected select start tag in the select phase " "treated as select end tag.", "unexpected-input-in-select": "Unexpected input start tag in the select phase.", "unexpected-start-tag-in-select": "Unexpected start tag token (%(name)s in the select phase. " "Ignored.", "unexpected-end-tag-in-select": "Unexpected end tag (%(name)s) in the select phase. Ignored.", "unexpected-table-element-start-tag-in-select-in-table": "Unexpected table element start tag (%(name)s) in the select in table phase.", "unexpected-table-element-end-tag-in-select-in-table": "Unexpected table element end tag (%(name)s) in the select in table phase.", "unexpected-char-after-body": "Unexpected non-space characters in the after body phase.", "unexpected-start-tag-after-body": "Unexpected start tag token (%(name)s)" " in the after body phase.", "unexpected-end-tag-after-body": "Unexpected end tag token (%(name)s)" " in the after body phase.", "unexpected-char-in-frameset": "Unexpected characters in the frameset phase. Characters ignored.", "unexpected-start-tag-in-frameset": "Unexpected start tag token (%(name)s)" " in the frameset phase. Ignored.", "unexpected-frameset-in-frameset-innerhtml": "Unexpected end tag token (frameset) " "in the frameset phase (innerHTML).", "unexpected-end-tag-in-frameset": "Unexpected end tag token (%(name)s)" " in the frameset phase. Ignored.", "unexpected-char-after-frameset": "Unexpected non-space characters in the " "after frameset phase. Ignored.", "unexpected-start-tag-after-frameset": "Unexpected start tag (%(name)s)" " in the after frameset phase. Ignored.", "unexpected-end-tag-after-frameset": "Unexpected end tag (%(name)s)" " in the after frameset phase. Ignored.", "unexpected-end-tag-after-body-innerhtml": "Unexpected end tag after body(innerHtml)", "expected-eof-but-got-char": "Unexpected non-space characters. Expected end of file.", "expected-eof-but-got-start-tag": "Unexpected start tag (%(name)s)" ". Expected end of file.", "expected-eof-but-got-end-tag": "Unexpected end tag (%(name)s)" ". Expected end of file.", "eof-in-table": "Unexpected end of file. Expected table content.", "eof-in-select": "Unexpected end of file. Expected select content.", "eof-in-frameset": "Unexpected end of file. Expected frameset content.", "eof-in-script-in-script": "Unexpected end of file. Expected script content.", "eof-in-foreign-lands": "Unexpected end of file. Expected foreign content", "non-void-element-with-trailing-solidus": "Trailing solidus not allowed on element %(name)s", "unexpected-html-element-in-foreign-content": "Element %(name)s not allowed in a non-html context", "unexpected-end-tag-before-html": "Unexpected end tag (%(name)s) before html.", "XXX-undefined-error": "Undefined error (this sucks and should be fixed)", } namespaces = { "html": "http://www.w3.org/1999/xhtml", "mathml": "http://www.w3.org/1998/Math/MathML", "svg": "http://www.w3.org/2000/svg", "xlink": "http://www.w3.org/1999/xlink", "xml": "http://www.w3.org/XML/1998/namespace", "xmlns": "http://www.w3.org/2000/xmlns/" } scopingElements = frozenset([ (namespaces["html"], "applet"), (namespaces["html"], "caption"), (namespaces["html"], "html"), (namespaces["html"], "marquee"), (namespaces["html"], "object"), (namespaces["html"], "table"), (namespaces["html"], "td"), (namespaces["html"], "th"), (namespaces["mathml"], "mi"), (namespaces["mathml"], "mo"), (namespaces["mathml"], "mn"), (namespaces["mathml"], "ms"), (namespaces["mathml"], "mtext"), (namespaces["mathml"], "annotation-xml"), (namespaces["svg"], "foreignObject"), (namespaces["svg"], "desc"), (namespaces["svg"], "title"), ]) formattingElements = frozenset([ (namespaces["html"], "a"), (namespaces["html"], "b"), (namespaces["html"], "big"), (namespaces["html"], "code"), (namespaces["html"], "em"), (namespaces["html"], "font"), (namespaces["html"], "i"), (namespaces["html"], "nobr"), (namespaces["html"], "s"), (namespaces["html"], "small"), (namespaces["html"], "strike"), (namespaces["html"], "strong"), (namespaces["html"], "tt"), (namespaces["html"], "u") ]) specialElements = frozenset([ (namespaces["html"], "address"), (namespaces["html"], "applet"), (namespaces["html"], "area"), (namespaces["html"], "article"), (namespaces["html"], "aside"), (namespaces["html"], "base"), (namespaces["html"], "basefont"), (namespaces["html"], "bgsound"), (namespaces["html"], "blockquote"), (namespaces["html"], "body"), (namespaces["html"], "br"), (namespaces["html"], "button"), (namespaces["html"], "caption"), (namespaces["html"], "center"), (namespaces["html"], "col"), (namespaces["html"], "colgroup"), (namespaces["html"], "command"), (namespaces["html"], "dd"), (namespaces["html"], "details"), (namespaces["html"], "dir"), (namespaces["html"], "div"), (namespaces["html"], "dl"), (namespaces["html"], "dt"), (namespaces["html"], "embed"), (namespaces["html"], "fieldset"), (namespaces["html"], "figure"), (namespaces["html"], "footer"), (namespaces["html"], "form"), (namespaces["html"], "frame"), (namespaces["html"], "frameset"), (namespaces["html"], "h1"), (namespaces["html"], "h2"), (namespaces["html"], "h3"), (namespaces["html"], "h4"), (namespaces["html"], "h5"), (namespaces["html"], "h6"), (namespaces["html"], "head"), (namespaces["html"], "header"), (namespaces["html"], "hr"), (namespaces["html"], "html"), (namespaces["html"], "iframe"), # Note that image is commented out in the spec as "this isn't an # element that can end up on the stack, so it doesn't matter," (namespaces["html"], "image"), (namespaces["html"], "img"), (namespaces["html"], "input"), (namespaces["html"], "isindex"), (namespaces["html"], "li"), (namespaces["html"], "link"), (namespaces["html"], "listing"), (namespaces["html"], "marquee"), (namespaces["html"], "menu"), (namespaces["html"], "meta"), (namespaces["html"], "nav"), (namespaces["html"], "noembed"), (namespaces["html"], "noframes"), (namespaces["html"], "noscript"), (namespaces["html"], "object"), (namespaces["html"], "ol"), (namespaces["html"], "p"), (namespaces["html"], "param"), (namespaces["html"], "plaintext"), (namespaces["html"], "pre"), (namespaces["html"], "script"), (namespaces["html"], "section"), (namespaces["html"], "select"), (namespaces["html"], "style"), (namespaces["html"], "table"), (namespaces["html"], "tbody"), (namespaces["html"], "td"), (namespaces["html"], "textarea"), (namespaces["html"], "tfoot"), (namespaces["html"], "th"), (namespaces["html"], "thead"), (namespaces["html"], "title"), (namespaces["html"], "tr"), (namespaces["html"], "ul"), (namespaces["html"], "wbr"), (namespaces["html"], "xmp"), (namespaces["svg"], "foreignObject") ]) htmlIntegrationPointElements = frozenset([ (namespaces["mathml"], "annotaion-xml"), (namespaces["svg"], "foreignObject"), (namespaces["svg"], "desc"), (namespaces["svg"], "title") ]) mathmlTextIntegrationPointElements = frozenset([ (namespaces["mathml"], "mi"), (namespaces["mathml"], "mo"), (namespaces["mathml"], "mn"), (namespaces["mathml"], "ms"), (namespaces["mathml"], "mtext") ]) adjustForeignAttributes = { "xlink:actuate": ("xlink", "actuate", namespaces["xlink"]), "xlink:arcrole": ("xlink", "arcrole", namespaces["xlink"]), "xlink:href": ("xlink", "href", namespaces["xlink"]), "xlink:role": ("xlink", "role", namespaces["xlink"]), "xlink:show": ("xlink", "show", namespaces["xlink"]), "xlink:title": ("xlink", "title", namespaces["xlink"]), "xlink:type": ("xlink", "type", namespaces["xlink"]), "xml:base": ("xml", "base", namespaces["xml"]), "xml:lang": ("xml", "lang", namespaces["xml"]), "xml:space": ("xml", "space", namespaces["xml"]), "xmlns": (None, "xmlns", namespaces["xmlns"]), "xmlns:xlink": ("xmlns", "xlink", namespaces["xmlns"]) } unadjustForeignAttributes = dict([((ns, local), qname) for qname, (prefix, local, ns) in adjustForeignAttributes.items()]) spaceCharacters = frozenset([ "\t", "\n", "\u000C", " ", "\r" ]) tableInsertModeElements = frozenset([ "table", "tbody", "tfoot", "thead", "tr" ]) asciiLowercase = frozenset(string.ascii_lowercase) asciiUppercase = frozenset(string.ascii_uppercase) asciiLetters = frozenset(string.ascii_letters) digits = frozenset(string.digits) hexDigits = frozenset(string.hexdigits) asciiUpper2Lower = dict([(ord(c), ord(c.lower())) for c in string.ascii_uppercase]) # Heading elements need to be ordered headingElements = ( "h1", "h2", "h3", "h4", "h5", "h6" ) voidElements = frozenset([ "base", "command", "event-source", "link", "meta", "hr", "br", "img", "embed", "param", "area", "col", "input", "source", "track" ]) cdataElements = frozenset(['title', 'textarea']) rcdataElements = frozenset([ 'style', 'script', 'xmp', 'iframe', 'noembed', 'noframes', 'noscript' ]) booleanAttributes = { "": frozenset(["irrelevant"]), "style": frozenset(["scoped"]), "img": frozenset(["ismap"]), "audio": frozenset(["autoplay", "controls"]), "video": frozenset(["autoplay", "controls"]), "script": frozenset(["defer", "async"]), "details": frozenset(["open"]), "datagrid": frozenset(["multiple", "disabled"]), "command": frozenset(["hidden", "disabled", "checked", "default"]), "hr": frozenset(["noshade"]), "menu": frozenset(["autosubmit"]), "fieldset": frozenset(["disabled", "readonly"]), "option": frozenset(["disabled", "readonly", "selected"]), "optgroup": frozenset(["disabled", "readonly"]), "button": frozenset(["disabled", "autofocus"]), "input": frozenset(["disabled", "readonly", "required", "autofocus", "checked", "ismap"]), "select": frozenset(["disabled", "readonly", "autofocus", "multiple"]), "output": frozenset(["disabled", "readonly"]), } # entitiesWindows1252 has to be _ordered_ and needs to have an index. It # therefore can't be a frozenset. entitiesWindows1252 = ( 8364, # 0x80 0x20AC EURO SIGN 65533, # 0x81 UNDEFINED 8218, # 0x82 0x201A SINGLE LOW-9 QUOTATION MARK 402, # 0x83 0x0192 LATIN SMALL LETTER F WITH HOOK 8222, # 0x84 0x201E DOUBLE LOW-9 QUOTATION MARK 8230, # 0x85 0x2026 HORIZONTAL ELLIPSIS 8224, # 0x86 0x2020 DAGGER 8225, # 0x87 0x2021 DOUBLE DAGGER 710, # 0x88 0x02C6 MODIFIER LETTER CIRCUMFLEX ACCENT 8240, # 0x89 0x2030 PER MILLE SIGN 352, # 0x8A 0x0160 LATIN CAPITAL LETTER S WITH CARON 8249, # 0x8B 0x2039 SINGLE LEFT-POINTING ANGLE QUOTATION MARK 338, # 0x8C 0x0152 LATIN CAPITAL LIGATURE OE 65533, # 0x8D UNDEFINED 381, # 0x8E 0x017D LATIN CAPITAL LETTER Z WITH CARON 65533, # 0x8F UNDEFINED 65533, # 0x90 UNDEFINED 8216, # 0x91 0x2018 LEFT SINGLE QUOTATION MARK 8217, # 0x92 0x2019 RIGHT SINGLE QUOTATION MARK 8220, # 0x93 0x201C LEFT DOUBLE QUOTATION MARK 8221, # 0x94 0x201D RIGHT DOUBLE QUOTATION MARK 8226, # 0x95 0x2022 BULLET 8211, # 0x96 0x2013 EN DASH 8212, # 0x97 0x2014 EM DASH 732, # 0x98 0x02DC SMALL TILDE 8482, # 0x99 0x2122 TRADE MARK SIGN 353, # 0x9A 0x0161 LATIN SMALL LETTER S WITH CARON 8250, # 0x9B 0x203A SINGLE RIGHT-POINTING ANGLE QUOTATION MARK 339, # 0x9C 0x0153 LATIN SMALL LIGATURE OE 65533, # 0x9D UNDEFINED 382, # 0x9E 0x017E LATIN SMALL LETTER Z WITH CARON 376 # 0x9F 0x0178 LATIN CAPITAL LETTER Y WITH DIAERESIS ) xmlEntities = frozenset(['lt;', 'gt;', 'amp;', 'apos;', 'quot;']) entities = { "AElig": "\xc6", "AElig;": "\xc6", "AMP": "&", "AMP;": "&", "Aacute": "\xc1", "Aacute;": "\xc1", "Abreve;": "\u0102", "Acirc": "\xc2", "Acirc;": "\xc2", "Acy;": "\u0410", "Afr;": "\U0001d504", "Agrave": "\xc0", "Agrave;": "\xc0", "Alpha;": "\u0391", "Amacr;": "\u0100", "And;": "\u2a53", "Aogon;": "\u0104", "Aopf;": "\U0001d538", "ApplyFunction;": "\u2061", "Aring": "\xc5", "Aring;": "\xc5", "Ascr;": "\U0001d49c", "Assign;": "\u2254", "Atilde": "\xc3", "Atilde;": "\xc3", "Auml": "\xc4", "Auml;": "\xc4", "Backslash;": "\u2216", "Barv;": "\u2ae7", "Barwed;": "\u2306", "Bcy;": "\u0411", "Because;": "\u2235", "Bernoullis;": "\u212c", "Beta;": "\u0392", "Bfr;": "\U0001d505", "Bopf;": "\U0001d539", "Breve;": "\u02d8", "Bscr;": "\u212c", "Bumpeq;": "\u224e", "CHcy;": "\u0427", "COPY": "\xa9", "COPY;": "\xa9", "Cacute;": "\u0106", "Cap;": "\u22d2", "CapitalDifferentialD;": "\u2145", "Cayleys;": "\u212d", "Ccaron;": "\u010c", "Ccedil": "\xc7", "Ccedil;": "\xc7", "Ccirc;": "\u0108", "Cconint;": "\u2230", "Cdot;": "\u010a", "Cedilla;": "\xb8", "CenterDot;": "\xb7", "Cfr;": "\u212d", "Chi;": "\u03a7", "CircleDot;": "\u2299", "CircleMinus;": "\u2296", "CirclePlus;": "\u2295", "CircleTimes;": "\u2297", "ClockwiseContourIntegral;": "\u2232", "CloseCurlyDoubleQuote;": "\u201d", "CloseCurlyQuote;": "\u2019", "Colon;": "\u2237", "Colone;": "\u2a74", "Congruent;": "\u2261", "Conint;": "\u222f", "ContourIntegral;": "\u222e", "Copf;": "\u2102", "Coproduct;": "\u2210", "CounterClockwiseContourIntegral;": "\u2233", "Cross;": "\u2a2f", "Cscr;": "\U0001d49e", "Cup;": "\u22d3", "CupCap;": "\u224d", "DD;": "\u2145", "DDotrahd;": "\u2911", "DJcy;": "\u0402", "DScy;": "\u0405", "DZcy;": "\u040f", "Dagger;": "\u2021", "Darr;": "\u21a1", "Dashv;": "\u2ae4", "Dcaron;": "\u010e", "Dcy;": "\u0414", "Del;": "\u2207", "Delta;": "\u0394", "Dfr;": "\U0001d507", "DiacriticalAcute;": "\xb4", "DiacriticalDot;": "\u02d9", "DiacriticalDoubleAcute;": "\u02dd", "DiacriticalGrave;": "`", "DiacriticalTilde;": "\u02dc", "Diamond;": "\u22c4", "DifferentialD;": "\u2146", "Dopf;": "\U0001d53b", "Dot;": "\xa8", "DotDot;": "\u20dc", "DotEqual;": "\u2250", "DoubleContourIntegral;": "\u222f", "DoubleDot;": "\xa8", "DoubleDownArrow;": "\u21d3", "DoubleLeftArrow;": "\u21d0", "DoubleLeftRightArrow;": "\u21d4", "DoubleLeftTee;": "\u2ae4", "DoubleLongLeftArrow;": "\u27f8", "DoubleLongLeftRightArrow;": "\u27fa", "DoubleLongRightArrow;": "\u27f9", "DoubleRightArrow;": "\u21d2", "DoubleRightTee;": "\u22a8", "DoubleUpArrow;": "\u21d1", "DoubleUpDownArrow;": "\u21d5", "DoubleVerticalBar;": "\u2225", "DownArrow;": "\u2193", "DownArrowBar;": "\u2913", "DownArrowUpArrow;": "\u21f5", "DownBreve;": "\u0311", "DownLeftRightVector;": "\u2950", "DownLeftTeeVector;": "\u295e", "DownLeftVector;": "\u21bd", "DownLeftVectorBar;": "\u2956", "DownRightTeeVector;": "\u295f", "DownRightVector;": "\u21c1", "DownRightVectorBar;": "\u2957", "DownTee;": "\u22a4", "DownTeeArrow;": "\u21a7", "Downarrow;": "\u21d3", "Dscr;": "\U0001d49f", "Dstrok;": "\u0110", "ENG;": "\u014a", "ETH": "\xd0", "ETH;": "\xd0", "Eacute": "\xc9", "Eacute;": "\xc9", "Ecaron;": "\u011a", "Ecirc": "\xca", "Ecirc;": "\xca", "Ecy;": "\u042d", "Edot;": "\u0116", "Efr;": "\U0001d508", "Egrave": "\xc8", "Egrave;": "\xc8", "Element;": "\u2208", "Emacr;": "\u0112", "EmptySmallSquare;": "\u25fb", "EmptyVerySmallSquare;": "\u25ab", "Eogon;": "\u0118", "Eopf;": "\U0001d53c", "Epsilon;": "\u0395", "Equal;": "\u2a75", "EqualTilde;": "\u2242", "Equilibrium;": "\u21cc", "Escr;": "\u2130", "Esim;": "\u2a73", "Eta;": "\u0397", "Euml": "\xcb", "Euml;": "\xcb", "Exists;": "\u2203", "ExponentialE;": "\u2147", "Fcy;": "\u0424", "Ffr;": "\U0001d509", "FilledSmallSquare;": "\u25fc", "FilledVerySmallSquare;": "\u25aa", "Fopf;": "\U0001d53d", "ForAll;": "\u2200", "Fouriertrf;": "\u2131", "Fscr;": "\u2131", "GJcy;": "\u0403", "GT": ">", "GT;": ">", "Gamma;": "\u0393", "Gammad;": "\u03dc", "Gbreve;": "\u011e", "Gcedil;": "\u0122", "Gcirc;": "\u011c", "Gcy;": "\u0413", "Gdot;": "\u0120", "Gfr;": "\U0001d50a", "Gg;": "\u22d9", "Gopf;": "\U0001d53e", "GreaterEqual;": "\u2265", "GreaterEqualLess;": "\u22db", "GreaterFullEqual;": "\u2267", "GreaterGreater;": "\u2aa2", "GreaterLess;": "\u2277", "GreaterSlantEqual;": "\u2a7e", "GreaterTilde;": "\u2273", "Gscr;": "\U0001d4a2", "Gt;": "\u226b", "HARDcy;": "\u042a", "Hacek;": "\u02c7", "Hat;": "^", "Hcirc;": "\u0124", "Hfr;": "\u210c", "HilbertSpace;": "\u210b", "Hopf;": "\u210d", "HorizontalLine;": "\u2500", "Hscr;": "\u210b", "Hstrok;": "\u0126", "HumpDownHump;": "\u224e", "HumpEqual;": "\u224f", "IEcy;": "\u0415", "IJlig;": "\u0132", "IOcy;": "\u0401", "Iacute": "\xcd", "Iacute;": "\xcd", "Icirc": "\xce", "Icirc;": "\xce", "Icy;": "\u0418", "Idot;": "\u0130", "Ifr;": "\u2111", "Igrave": "\xcc", "Igrave;": "\xcc", "Im;": "\u2111", "Imacr;": "\u012a", "ImaginaryI;": "\u2148", "Implies;": "\u21d2", "Int;": "\u222c", "Integral;": "\u222b", "Intersection;": "\u22c2", "InvisibleComma;": "\u2063", "InvisibleTimes;": "\u2062", "Iogon;": "\u012e", "Iopf;": "\U0001d540", "Iota;": "\u0399", "Iscr;": "\u2110", "Itilde;": "\u0128", "Iukcy;": "\u0406", "Iuml": "\xcf", "Iuml;": "\xcf", "Jcirc;": "\u0134", "Jcy;": "\u0419", "Jfr;": "\U0001d50d", "Jopf;": "\U0001d541", "Jscr;": "\U0001d4a5", "Jsercy;": "\u0408", "Jukcy;": "\u0404", "KHcy;": "\u0425", "KJcy;": "\u040c", "Kappa;": "\u039a", "Kcedil;": "\u0136", "Kcy;": "\u041a", "Kfr;": "\U0001d50e", "Kopf;": "\U0001d542", "Kscr;": "\U0001d4a6", "LJcy;": "\u0409", "LT": "<", "LT;": "<", "Lacute;": "\u0139", "Lambda;": "\u039b", "Lang;": "\u27ea", "Laplacetrf;": "\u2112", "Larr;": "\u219e", "Lcaron;": "\u013d", "Lcedil;": "\u013b", "Lcy;": "\u041b", "LeftAngleBracket;": "\u27e8", "LeftArrow;": "\u2190", "LeftArrowBar;": "\u21e4", "LeftArrowRightArrow;": "\u21c6", "LeftCeiling;": "\u2308", "LeftDoubleBracket;": "\u27e6", "LeftDownTeeVector;": "\u2961", "LeftDownVector;": "\u21c3", "LeftDownVectorBar;": "\u2959", "LeftFloor;": "\u230a", "LeftRightArrow;": "\u2194", "LeftRightVector;": "\u294e", "LeftTee;": "\u22a3", "LeftTeeArrow;": "\u21a4", "LeftTeeVector;": "\u295a", "LeftTriangle;": "\u22b2", "LeftTriangleBar;": "\u29cf", "LeftTriangleEqual;": "\u22b4", "LeftUpDownVector;": "\u2951", "LeftUpTeeVector;": "\u2960", "LeftUpVector;": "\u21bf", "LeftUpVectorBar;": "\u2958", "LeftVector;": "\u21bc", "LeftVectorBar;": "\u2952", "Leftarrow;": "\u21d0", "Leftrightarrow;": "\u21d4", "LessEqualGreater;": "\u22da", "LessFullEqual;": "\u2266", "LessGreater;": "\u2276", "LessLess;": "\u2aa1", "LessSlantEqual;": "\u2a7d", "LessTilde;": "\u2272", "Lfr;": "\U0001d50f", "Ll;": "\u22d8", "Lleftarrow;": "\u21da", "Lmidot;": "\u013f", "LongLeftArrow;": "\u27f5", "LongLeftRightArrow;": "\u27f7", "LongRightArrow;": "\u27f6", "Longleftarrow;": "\u27f8", "Longleftrightarrow;": "\u27fa", "Longrightarrow;": "\u27f9", "Lopf;": "\U0001d543", "LowerLeftArrow;": "\u2199", "LowerRightArrow;": "\u2198", "Lscr;": "\u2112", "Lsh;": "\u21b0", "Lstrok;": "\u0141", "Lt;": "\u226a", "Map;": "\u2905", "Mcy;": "\u041c", "MediumSpace;": "\u205f", "Mellintrf;": "\u2133", "Mfr;": "\U0001d510", "MinusPlus;": "\u2213", "Mopf;": "\U0001d544", "Mscr;": "\u2133", "Mu;": "\u039c", "NJcy;": "\u040a", "Nacute;": "\u0143", "Ncaron;": "\u0147", "Ncedil;": "\u0145", "Ncy;": "\u041d", "NegativeMediumSpace;": "\u200b", "NegativeThickSpace;": "\u200b", "NegativeThinSpace;": "\u200b", "NegativeVeryThinSpace;": "\u200b", "NestedGreaterGreater;": "\u226b", "NestedLessLess;": "\u226a", "NewLine;": "\n", "Nfr;": "\U0001d511", "NoBreak;": "\u2060", "NonBreakingSpace;": "\xa0", "Nopf;": "\u2115", "Not;": "\u2aec", "NotCongruent;": "\u2262", "NotCupCap;": "\u226d", "NotDoubleVerticalBar;": "\u2226", "NotElement;": "\u2209", "NotEqual;": "\u2260", "NotEqualTilde;": "\u2242\u0338", "NotExists;": "\u2204", "NotGreater;": "\u226f", "NotGreaterEqual;": "\u2271", "NotGreaterFullEqual;": "\u2267\u0338", "NotGreaterGreater;": "\u226b\u0338", "NotGreaterLess;": "\u2279", "NotGreaterSlantEqual;": "\u2a7e\u0338", "NotGreaterTilde;": "\u2275", "NotHumpDownHump;": "\u224e\u0338", "NotHumpEqual;": "\u224f\u0338", "NotLeftTriangle;": "\u22ea", "NotLeftTriangleBar;": "\u29cf\u0338", "NotLeftTriangleEqual;": "\u22ec", "NotLess;": "\u226e", "NotLessEqual;": "\u2270", "NotLessGreater;": "\u2278", "NotLessLess;": "\u226a\u0338", "NotLessSlantEqual;": "\u2a7d\u0338", "NotLessTilde;": "\u2274", "NotNestedGreaterGreater;": "\u2aa2\u0338", "NotNestedLessLess;": "\u2aa1\u0338", "NotPrecedes;": "\u2280", "NotPrecedesEqual;": "\u2aaf\u0338", "NotPrecedesSlantEqual;": "\u22e0", "NotReverseElement;": "\u220c", "NotRightTriangle;": "\u22eb", "NotRightTriangleBar;": "\u29d0\u0338", "NotRightTriangleEqual;": "\u22ed", "NotSquareSubset;": "\u228f\u0338", "NotSquareSubsetEqual;": "\u22e2", "NotSquareSuperset;": "\u2290\u0338", "NotSquareSupersetEqual;": "\u22e3", "NotSubset;": "\u2282\u20d2", "NotSubsetEqual;": "\u2288", "NotSucceeds;": "\u2281", "NotSucceedsEqual;": "\u2ab0\u0338", "NotSucceedsSlantEqual;": "\u22e1", "NotSucceedsTilde;": "\u227f\u0338", "NotSuperset;": "\u2283\u20d2", "NotSupersetEqual;": "\u2289", "NotTilde;": "\u2241", "NotTildeEqual;": "\u2244", "NotTildeFullEqual;": "\u2247", "NotTildeTilde;": "\u2249", "NotVerticalBar;": "\u2224", "Nscr;": "\U0001d4a9", "Ntilde": "\xd1", "Ntilde;": "\xd1", "Nu;": "\u039d", "OElig;": "\u0152", "Oacute": "\xd3", "Oacute;": "\xd3", "Ocirc": "\xd4", "Ocirc;": "\xd4", "Ocy;": "\u041e", "Odblac;": "\u0150", "Ofr;": "\U0001d512", "Ograve": "\xd2", "Ograve;": "\xd2", "Omacr;": "\u014c", "Omega;": "\u03a9", "Omicron;": "\u039f", "Oopf;": "\U0001d546", "OpenCurlyDoubleQuote;": "\u201c", "OpenCurlyQuote;": "\u2018", "Or;": "\u2a54", "Oscr;": "\U0001d4aa", "Oslash": "\xd8", "Oslash;": "\xd8", "Otilde": "\xd5", "Otilde;": "\xd5", "Otimes;": "\u2a37", "Ouml": "\xd6", "Ouml;": "\xd6", "OverBar;": "\u203e", "OverBrace;": "\u23de", "OverBracket;": "\u23b4", "OverParenthesis;": "\u23dc", "PartialD;": "\u2202", "Pcy;": "\u041f", "Pfr;": "\U0001d513", "Phi;": "\u03a6", "Pi;": "\u03a0", "PlusMinus;": "\xb1", "Poincareplane;": "\u210c", "Popf;": "\u2119", "Pr;": "\u2abb", "Precedes;": "\u227a", "PrecedesEqual;": "\u2aaf", "PrecedesSlantEqual;": "\u227c", "PrecedesTilde;": "\u227e", "Prime;": "\u2033", "Product;": "\u220f", "Proportion;": "\u2237", "Proportional;": "\u221d", "Pscr;": "\U0001d4ab", "Psi;": "\u03a8", "QUOT": "\"", "QUOT;": "\"", "Qfr;": "\U0001d514", "Qopf;": "\u211a", "Qscr;": "\U0001d4ac", "RBarr;": "\u2910", "REG": "\xae", "REG;": "\xae", "Racute;": "\u0154", "Rang;": "\u27eb", "Rarr;": "\u21a0", "Rarrtl;": "\u2916", "Rcaron;": "\u0158", "Rcedil;": "\u0156", "Rcy;": "\u0420", "Re;": "\u211c", "ReverseElement;": "\u220b", "ReverseEquilibrium;": "\u21cb", "ReverseUpEquilibrium;": "\u296f", "Rfr;": "\u211c", "Rho;": "\u03a1", "RightAngleBracket;": "\u27e9", "RightArrow;": "\u2192", "RightArrowBar;": "\u21e5", "RightArrowLeftArrow;": "\u21c4", "RightCeiling;": "\u2309", "RightDoubleBracket;": "\u27e7", "RightDownTeeVector;": "\u295d", "RightDownVector;": "\u21c2", "RightDownVectorBar;": "\u2955", "RightFloor;": "\u230b", "RightTee;": "\u22a2", "RightTeeArrow;": "\u21a6", "RightTeeVector;": "\u295b", "RightTriangle;": "\u22b3", "RightTriangleBar;": "\u29d0", "RightTriangleEqual;": "\u22b5", "RightUpDownVector;": "\u294f", "RightUpTeeVector;": "\u295c", "RightUpVector;": "\u21be", "RightUpVectorBar;": "\u2954", "RightVector;": "\u21c0", "RightVectorBar;": "\u2953", "Rightarrow;": "\u21d2", "Ropf;": "\u211d", "RoundImplies;": "\u2970", "Rrightarrow;": "\u21db", "Rscr;": "\u211b", "Rsh;": "\u21b1", "RuleDelayed;": "\u29f4", "SHCHcy;": "\u0429", "SHcy;": "\u0428", "SOFTcy;": "\u042c", "Sacute;": "\u015a", "Sc;": "\u2abc", "Scaron;": "\u0160", "Scedil;": "\u015e", "Scirc;": "\u015c", "Scy;": "\u0421", "Sfr;": "\U0001d516", "ShortDownArrow;": "\u2193", "ShortLeftArrow;": "\u2190", "ShortRightArrow;": "\u2192", "ShortUpArrow;": "\u2191", "Sigma;": "\u03a3", "SmallCircle;": "\u2218", "Sopf;": "\U0001d54a", "Sqrt;": "\u221a", "Square;": "\u25a1", "SquareIntersection;": "\u2293", "SquareSubset;": "\u228f", "SquareSubsetEqual;": "\u2291", "SquareSuperset;": "\u2290", "SquareSupersetEqual;": "\u2292", "SquareUnion;": "\u2294", "Sscr;": "\U0001d4ae", "Star;": "\u22c6", "Sub;": "\u22d0", "Subset;": "\u22d0", "SubsetEqual;": "\u2286", "Succeeds;": "\u227b", "SucceedsEqual;": "\u2ab0", "SucceedsSlantEqual;": "\u227d", "SucceedsTilde;": "\u227f", "SuchThat;": "\u220b", "Sum;": "\u2211", "Sup;": "\u22d1", "Superset;": "\u2283", "SupersetEqual;": "\u2287", "Supset;": "\u22d1", "THORN": "\xde", "THORN;": "\xde", "TRADE;": "\u2122", "TSHcy;": "\u040b", "TScy;": "\u0426", "Tab;": "\t", "Tau;": "\u03a4", "Tcaron;": "\u0164", "Tcedil;": "\u0162", "Tcy;": "\u0422", "Tfr;": "\U0001d517", "Therefore;": "\u2234", "Theta;": "\u0398", "ThickSpace;": "\u205f\u200a", "ThinSpace;": "\u2009", "Tilde;": "\u223c", "TildeEqual;": "\u2243", "TildeFullEqual;": "\u2245", "TildeTilde;": "\u2248", "Topf;": "\U0001d54b", "TripleDot;": "\u20db", "Tscr;": "\U0001d4af", "Tstrok;": "\u0166", "Uacute": "\xda", "Uacute;": "\xda", "Uarr;": "\u219f", "Uarrocir;": "\u2949", "Ubrcy;": "\u040e", "Ubreve;": "\u016c", "Ucirc": "\xdb", "Ucirc;": "\xdb", "Ucy;": "\u0423", "Udblac;": "\u0170", "Ufr;": "\U0001d518", "Ugrave": "\xd9", "Ugrave;": "\xd9", "Umacr;": "\u016a", "UnderBar;": "_", "UnderBrace;": "\u23df", "UnderBracket;": "\u23b5", "UnderParenthesis;": "\u23dd", "Union;": "\u22c3", "UnionPlus;": "\u228e", "Uogon;": "\u0172", "Uopf;": "\U0001d54c", "UpArrow;": "\u2191", "UpArrowBar;": "\u2912", "UpArrowDownArrow;": "\u21c5", "UpDownArrow;": "\u2195", "UpEquilibrium;": "\u296e", "UpTee;": "\u22a5", "UpTeeArrow;": "\u21a5", "Uparrow;": "\u21d1", "Updownarrow;": "\u21d5", "UpperLeftArrow;": "\u2196", "UpperRightArrow;": "\u2197", "Upsi;": "\u03d2", "Upsilon;": "\u03a5", "Uring;": "\u016e", "Uscr;": "\U0001d4b0", "Utilde;": "\u0168", "Uuml": "\xdc", "Uuml;": "\xdc", "VDash;": "\u22ab", "Vbar;": "\u2aeb", "Vcy;": "\u0412", "Vdash;": "\u22a9", "Vdashl;": "\u2ae6", "Vee;": "\u22c1", "Verbar;": "\u2016", "Vert;": "\u2016", "VerticalBar;": "\u2223", "VerticalLine;": "|", "VerticalSeparator;": "\u2758", "VerticalTilde;": "\u2240", "VeryThinSpace;": "\u200a", "Vfr;": "\U0001d519", "Vopf;": "\U0001d54d", "Vscr;": "\U0001d4b1", "Vvdash;": "\u22aa", "Wcirc;": "\u0174", "Wedge;": "\u22c0", "Wfr;": "\U0001d51a", "Wopf;": "\U0001d54e", "Wscr;": "\U0001d4b2", "Xfr;": "\U0001d51b", "Xi;": "\u039e", "Xopf;": "\U0001d54f", "Xscr;": "\U0001d4b3", "YAcy;": "\u042f", "YIcy;": "\u0407", "YUcy;": "\u042e", "Yacute": "\xdd", "Yacute;": "\xdd", "Ycirc;": "\u0176", "Ycy;": "\u042b", "Yfr;": "\U0001d51c", "Yopf;": "\U0001d550", "Yscr;": "\U0001d4b4", "Yuml;": "\u0178", "ZHcy;": "\u0416", "Zacute;": "\u0179", "Zcaron;": "\u017d", "Zcy;": "\u0417", "Zdot;": "\u017b", "ZeroWidthSpace;": "\u200b", "Zeta;": "\u0396", "Zfr;": "\u2128", "Zopf;": "\u2124", "Zscr;": "\U0001d4b5", "aacute": "\xe1", "aacute;": "\xe1", "abreve;": "\u0103", "ac;": "\u223e", "acE;": "\u223e\u0333", "acd;": "\u223f", "acirc": "\xe2", "acirc;": "\xe2", "acute": "\xb4", "acute;": "\xb4", "acy;": "\u0430", "aelig": "\xe6", "aelig;": "\xe6", "af;": "\u2061", "afr;": "\U0001d51e", "agrave": "\xe0", "agrave;": "\xe0", "alefsym;": "\u2135", "aleph;": "\u2135", "alpha;": "\u03b1", "amacr;": "\u0101", "amalg;": "\u2a3f", "amp": "&", "amp;": "&", "and;": "\u2227", "andand;": "\u2a55", "andd;": "\u2a5c", "andslope;": "\u2a58", "andv;": "\u2a5a", "ang;": "\u2220", "ange;": "\u29a4", "angle;": "\u2220", "angmsd;": "\u2221", "angmsdaa;": "\u29a8", "angmsdab;": "\u29a9", "angmsdac;": "\u29aa", "angmsdad;": "\u29ab", "angmsdae;": "\u29ac", "angmsdaf;": "\u29ad", "angmsdag;": "\u29ae", "angmsdah;": "\u29af", "angrt;": "\u221f", "angrtvb;": "\u22be", "angrtvbd;": "\u299d", "angsph;": "\u2222", "angst;": "\xc5", "angzarr;": "\u237c", "aogon;": "\u0105", "aopf;": "\U0001d552", "ap;": "\u2248", "apE;": "\u2a70", "apacir;": "\u2a6f", "ape;": "\u224a", "apid;": "\u224b", "apos;": "'", "approx;": "\u2248", "approxeq;": "\u224a", "aring": "\xe5", "aring;": "\xe5", "ascr;": "\U0001d4b6", "ast;": "*", "asymp;": "\u2248", "asympeq;": "\u224d", "atilde": "\xe3", "atilde;": "\xe3", "auml": "\xe4", "auml;": "\xe4", "awconint;": "\u2233", "awint;": "\u2a11", "bNot;": "\u2aed", "backcong;": "\u224c", "backepsilon;": "\u03f6", "backprime;": "\u2035", "backsim;": "\u223d", "backsimeq;": "\u22cd", "barvee;": "\u22bd", "barwed;": "\u2305", "barwedge;": "\u2305", "bbrk;": "\u23b5", "bbrktbrk;": "\u23b6", "bcong;": "\u224c", "bcy;": "\u0431", "bdquo;": "\u201e", "becaus;": "\u2235", "because;": "\u2235", "bemptyv;": "\u29b0", "bepsi;": "\u03f6", "bernou;": "\u212c", "beta;": "\u03b2", "beth;": "\u2136", "between;": "\u226c", "bfr;": "\U0001d51f", "bigcap;": "\u22c2", "bigcirc;": "\u25ef", "bigcup;": "\u22c3", "bigodot;": "\u2a00", "bigoplus;": "\u2a01", "bigotimes;": "\u2a02", "bigsqcup;": "\u2a06", "bigstar;": "\u2605", "bigtriangledown;": "\u25bd", "bigtriangleup;": "\u25b3", "biguplus;": "\u2a04", "bigvee;": "\u22c1", "bigwedge;": "\u22c0", "bkarow;": "\u290d", "blacklozenge;": "\u29eb", "blacksquare;": "\u25aa", "blacktriangle;": "\u25b4", "blacktriangledown;": "\u25be", "blacktriangleleft;": "\u25c2", "blacktriangleright;": "\u25b8", "blank;": "\u2423", "blk12;": "\u2592", "blk14;": "\u2591", "blk34;": "\u2593", "block;": "\u2588", "bne;": "=\u20e5", "bnequiv;": "\u2261\u20e5", "bnot;": "\u2310", "bopf;": "\U0001d553", "bot;": "\u22a5", "bottom;": "\u22a5", "bowtie;": "\u22c8", "boxDL;": "\u2557", "boxDR;": "\u2554", "boxDl;": "\u2556", "boxDr;": "\u2553", "boxH;": "\u2550", "boxHD;": "\u2566", "boxHU;": "\u2569", "boxHd;": "\u2564", "boxHu;": "\u2567", "boxUL;": "\u255d", "boxUR;": "\u255a", "boxUl;": "\u255c", "boxUr;": "\u2559", "boxV;": "\u2551", "boxVH;": "\u256c", "boxVL;": "\u2563", "boxVR;": "\u2560", "boxVh;": "\u256b", "boxVl;": "\u2562", "boxVr;": "\u255f", "boxbox;": "\u29c9", "boxdL;": "\u2555", "boxdR;": "\u2552", "boxdl;": "\u2510", "boxdr;": "\u250c", "boxh;": "\u2500", "boxhD;": "\u2565", "boxhU;": "\u2568", "boxhd;": "\u252c", "boxhu;": "\u2534", "boxminus;": "\u229f", "boxplus;": "\u229e", "boxtimes;": "\u22a0", "boxuL;": "\u255b", "boxuR;": "\u2558", "boxul;": "\u2518", "boxur;": "\u2514", "boxv;": "\u2502", "boxvH;": "\u256a", "boxvL;": "\u2561", "boxvR;": "\u255e", "boxvh;": "\u253c", "boxvl;": "\u2524", "boxvr;": "\u251c", "bprime;": "\u2035", "breve;": "\u02d8", "brvbar": "\xa6", "brvbar;": "\xa6", "bscr;": "\U0001d4b7", "bsemi;": "\u204f", "bsim;": "\u223d", "bsime;": "\u22cd", "bsol;": "\\", "bsolb;": "\u29c5", "bsolhsub;": "\u27c8", "bull;": "\u2022", "bullet;": "\u2022", "bump;": "\u224e", "bumpE;": "\u2aae", "bumpe;": "\u224f", "bumpeq;": "\u224f", "cacute;": "\u0107", "cap;": "\u2229", "capand;": "\u2a44", "capbrcup;": "\u2a49", "capcap;": "\u2a4b", "capcup;": "\u2a47", "capdot;": "\u2a40", "caps;": "\u2229\ufe00", "caret;": "\u2041", "caron;": "\u02c7", "ccaps;": "\u2a4d", "ccaron;": "\u010d", "ccedil": "\xe7", "ccedil;": "\xe7", "ccirc;": "\u0109", "ccups;": "\u2a4c", "ccupssm;": "\u2a50", "cdot;": "\u010b", "cedil": "\xb8", "cedil;": "\xb8", "cemptyv;": "\u29b2", "cent": "\xa2", "cent;": "\xa2", "centerdot;": "\xb7", "cfr;": "\U0001d520", "chcy;": "\u0447", "check;": "\u2713", "checkmark;": "\u2713", "chi;": "\u03c7", "cir;": "\u25cb", "cirE;": "\u29c3", "circ;": "\u02c6", "circeq;": "\u2257", "circlearrowleft;": "\u21ba", "circlearrowright;": "\u21bb", "circledR;": "\xae", "circledS;": "\u24c8", "circledast;": "\u229b", "circledcirc;": "\u229a", "circleddash;": "\u229d", "cire;": "\u2257", "cirfnint;": "\u2a10", "cirmid;": "\u2aef", "cirscir;": "\u29c2", "clubs;": "\u2663", "clubsuit;": "\u2663", "colon;": ":", "colone;": "\u2254", "coloneq;": "\u2254", "comma;": ",", "commat;": "@", "comp;": "\u2201", "compfn;": "\u2218", "complement;": "\u2201", "complexes;": "\u2102", "cong;": "\u2245", "congdot;": "\u2a6d", "conint;": "\u222e", "copf;": "\U0001d554", "coprod;": "\u2210", "copy": "\xa9", "copy;": "\xa9", "copysr;": "\u2117", "crarr;": "\u21b5", "cross;": "\u2717", "cscr;": "\U0001d4b8", "csub;": "\u2acf", "csube;": "\u2ad1", "csup;": "\u2ad0", "csupe;": "\u2ad2", "ctdot;": "\u22ef", "cudarrl;": "\u2938", "cudarrr;": "\u2935", "cuepr;": "\u22de", "cuesc;": "\u22df", "cularr;": "\u21b6", "cularrp;": "\u293d", "cup;": "\u222a", "cupbrcap;": "\u2a48", "cupcap;": "\u2a46", "cupcup;": "\u2a4a", "cupdot;": "\u228d", "cupor;": "\u2a45", "cups;": "\u222a\ufe00", "curarr;": "\u21b7", "curarrm;": "\u293c", "curlyeqprec;": "\u22de", "curlyeqsucc;": "\u22df", "curlyvee;": "\u22ce", "curlywedge;": "\u22cf", "curren": "\xa4", "curren;": "\xa4", "curvearrowleft;": "\u21b6", "curvearrowright;": "\u21b7", "cuvee;": "\u22ce", "cuwed;": "\u22cf", "cwconint;": "\u2232", "cwint;": "\u2231", "cylcty;": "\u232d", "dArr;": "\u21d3", "dHar;": "\u2965", "dagger;": "\u2020", "daleth;": "\u2138", "darr;": "\u2193", "dash;": "\u2010", "dashv;": "\u22a3", "dbkarow;": "\u290f", "dblac;": "\u02dd", "dcaron;": "\u010f", "dcy;": "\u0434", "dd;": "\u2146", "ddagger;": "\u2021", "ddarr;": "\u21ca", "ddotseq;": "\u2a77", "deg": "\xb0", "deg;": "\xb0", "delta;": "\u03b4", "demptyv;": "\u29b1", "dfisht;": "\u297f", "dfr;": "\U0001d521", "dharl;": "\u21c3", "dharr;": "\u21c2", "diam;": "\u22c4", "diamond;": "\u22c4", "diamondsuit;": "\u2666", "diams;": "\u2666", "die;": "\xa8", "digamma;": "\u03dd", "disin;": "\u22f2", "div;": "\xf7", "divide": "\xf7", "divide;": "\xf7", "divideontimes;": "\u22c7", "divonx;": "\u22c7", "djcy;": "\u0452", "dlcorn;": "\u231e", "dlcrop;": "\u230d", "dollar;": "$", "dopf;": "\U0001d555", "dot;": "\u02d9", "doteq;": "\u2250", "doteqdot;": "\u2251", "dotminus;": "\u2238", "dotplus;": "\u2214", "dotsquare;": "\u22a1", "doublebarwedge;": "\u2306", "downarrow;": "\u2193", "downdownarrows;": "\u21ca", "downharpoonleft;": "\u21c3", "downharpoonright;": "\u21c2", "drbkarow;": "\u2910", "drcorn;": "\u231f", "drcrop;": "\u230c", "dscr;": "\U0001d4b9", "dscy;": "\u0455", "dsol;": "\u29f6", "dstrok;": "\u0111", "dtdot;": "\u22f1", "dtri;": "\u25bf", "dtrif;": "\u25be", "duarr;": "\u21f5", "duhar;": "\u296f", "dwangle;": "\u29a6", "dzcy;": "\u045f", "dzigrarr;": "\u27ff", "eDDot;": "\u2a77", "eDot;": "\u2251", "eacute": "\xe9", "eacute;": "\xe9", "easter;": "\u2a6e", "ecaron;": "\u011b", "ecir;": "\u2256", "ecirc": "\xea", "ecirc;": "\xea", "ecolon;": "\u2255", "ecy;": "\u044d", "edot;": "\u0117", "ee;": "\u2147", "efDot;": "\u2252", "efr;": "\U0001d522", "eg;": "\u2a9a", "egrave": "\xe8", "egrave;": "\xe8", "egs;": "\u2a96", "egsdot;": "\u2a98", "el;": "\u2a99", "elinters;": "\u23e7", "ell;": "\u2113", "els;": "\u2a95", "elsdot;": "\u2a97", "emacr;": "\u0113", "empty;": "\u2205", "emptyset;": "\u2205", "emptyv;": "\u2205", "emsp13;": "\u2004", "emsp14;": "\u2005", "emsp;": "\u2003", "eng;": "\u014b", "ensp;": "\u2002", "eogon;": "\u0119", "eopf;": "\U0001d556", "epar;": "\u22d5", "eparsl;": "\u29e3", "eplus;": "\u2a71", "epsi;": "\u03b5", "epsilon;": "\u03b5", "epsiv;": "\u03f5", "eqcirc;": "\u2256", "eqcolon;": "\u2255", "eqsim;": "\u2242", "eqslantgtr;": "\u2a96", "eqslantless;": "\u2a95", "equals;": "=", "equest;": "\u225f", "equiv;": "\u2261", "equivDD;": "\u2a78", "eqvparsl;": "\u29e5", "erDot;": "\u2253", "erarr;": "\u2971", "escr;": "\u212f", "esdot;": "\u2250", "esim;": "\u2242", "eta;": "\u03b7", "eth": "\xf0", "eth;": "\xf0", "euml": "\xeb", "euml;": "\xeb", "euro;": "\u20ac", "excl;": "!", "exist;": "\u2203", "expectation;": "\u2130", "exponentiale;": "\u2147", "fallingdotseq;": "\u2252", "fcy;": "\u0444", "female;": "\u2640", "ffilig;": "\ufb03", "fflig;": "\ufb00", "ffllig;": "\ufb04", "ffr;": "\U0001d523", "filig;": "\ufb01", "fjlig;": "fj", "flat;": "\u266d", "fllig;": "\ufb02", "fltns;": "\u25b1", "fnof;": "\u0192", "fopf;": "\U0001d557", "forall;": "\u2200", "fork;": "\u22d4", "forkv;": "\u2ad9", "fpartint;": "\u2a0d", "frac12": "\xbd", "frac12;": "\xbd", "frac13;": "\u2153", "frac14": "\xbc", "frac14;": "\xbc", "frac15;": "\u2155", "frac16;": "\u2159", "frac18;": "\u215b", "frac23;": "\u2154", "frac25;": "\u2156", "frac34": "\xbe", "frac34;": "\xbe", "frac35;": "\u2157", "frac38;": "\u215c", "frac45;": "\u2158", "frac56;": "\u215a", "frac58;": "\u215d", "frac78;": "\u215e", "frasl;": "\u2044", "frown;": "\u2322", "fscr;": "\U0001d4bb", "gE;": "\u2267", "gEl;": "\u2a8c", "gacute;": "\u01f5", "gamma;": "\u03b3", "gammad;": "\u03dd", "gap;": "\u2a86", "gbreve;": "\u011f", "gcirc;": "\u011d", "gcy;": "\u0433", "gdot;": "\u0121", "ge;": "\u2265", "gel;": "\u22db", "geq;": "\u2265", "geqq;": "\u2267", "geqslant;": "\u2a7e", "ges;": "\u2a7e", "gescc;": "\u2aa9", "gesdot;": "\u2a80", "gesdoto;": "\u2a82", "gesdotol;": "\u2a84", "gesl;": "\u22db\ufe00", "gesles;": "\u2a94", "gfr;": "\U0001d524", "gg;": "\u226b", "ggg;": "\u22d9", "gimel;": "\u2137", "gjcy;": "\u0453", "gl;": "\u2277", "glE;": "\u2a92", "gla;": "\u2aa5", "glj;": "\u2aa4", "gnE;": "\u2269", "gnap;": "\u2a8a", "gnapprox;": "\u2a8a", "gne;": "\u2a88", "gneq;": "\u2a88", "gneqq;": "\u2269", "gnsim;": "\u22e7", "gopf;": "\U0001d558", "grave;": "`", "gscr;": "\u210a", "gsim;": "\u2273", "gsime;": "\u2a8e", "gsiml;": "\u2a90", "gt": ">", "gt;": ">", "gtcc;": "\u2aa7", "gtcir;": "\u2a7a", "gtdot;": "\u22d7", "gtlPar;": "\u2995", "gtquest;": "\u2a7c", "gtrapprox;": "\u2a86", "gtrarr;": "\u2978", "gtrdot;": "\u22d7", "gtreqless;": "\u22db", "gtreqqless;": "\u2a8c", "gtrless;": "\u2277", "gtrsim;": "\u2273", "gvertneqq;": "\u2269\ufe00", "gvnE;": "\u2269\ufe00", "hArr;": "\u21d4", "hairsp;": "\u200a", "half;": "\xbd", "hamilt;": "\u210b", "hardcy;": "\u044a", "harr;": "\u2194", "harrcir;": "\u2948", "harrw;": "\u21ad", "hbar;": "\u210f", "hcirc;": "\u0125", "hearts;": "\u2665", "heartsuit;": "\u2665", "hellip;": "\u2026", "hercon;": "\u22b9", "hfr;": "\U0001d525", "hksearow;": "\u2925", "hkswarow;": "\u2926", "hoarr;": "\u21ff", "homtht;": "\u223b", "hookleftarrow;": "\u21a9", "hookrightarrow;": "\u21aa", "hopf;": "\U0001d559", "horbar;": "\u2015", "hscr;": "\U0001d4bd", "hslash;": "\u210f", "hstrok;": "\u0127", "hybull;": "\u2043", "hyphen;": "\u2010", "iacute": "\xed", "iacute;": "\xed", "ic;": "\u2063", "icirc": "\xee", "icirc;": "\xee", "icy;": "\u0438", "iecy;": "\u0435", "iexcl": "\xa1", "iexcl;": "\xa1", "iff;": "\u21d4", "ifr;": "\U0001d526", "igrave": "\xec", "igrave;": "\xec", "ii;": "\u2148", "iiiint;": "\u2a0c", "iiint;": "\u222d", "iinfin;": "\u29dc", "iiota;": "\u2129", "ijlig;": "\u0133", "imacr;": "\u012b", "image;": "\u2111", "imagline;": "\u2110", "imagpart;": "\u2111", "imath;": "\u0131", "imof;": "\u22b7", "imped;": "\u01b5", "in;": "\u2208", "incare;": "\u2105", "infin;": "\u221e", "infintie;": "\u29dd", "inodot;": "\u0131", "int;": "\u222b", "intcal;": "\u22ba", "integers;": "\u2124", "intercal;": "\u22ba", "intlarhk;": "\u2a17", "intprod;": "\u2a3c", "iocy;": "\u0451", "iogon;": "\u012f", "iopf;": "\U0001d55a", "iota;": "\u03b9", "iprod;": "\u2a3c", "iquest": "\xbf", "iquest;": "\xbf", "iscr;": "\U0001d4be", "isin;": "\u2208", "isinE;": "\u22f9", "isindot;": "\u22f5", "isins;": "\u22f4", "isinsv;": "\u22f3", "isinv;": "\u2208", "it;": "\u2062", "itilde;": "\u0129", "iukcy;": "\u0456", "iuml": "\xef", "iuml;": "\xef", "jcirc;": "\u0135", "jcy;": "\u0439", "jfr;": "\U0001d527", "jmath;": "\u0237", "jopf;": "\U0001d55b", "jscr;": "\U0001d4bf", "jsercy;": "\u0458", "jukcy;": "\u0454", "kappa;": "\u03ba", "kappav;": "\u03f0", "kcedil;": "\u0137", "kcy;": "\u043a", "kfr;": "\U0001d528", "kgreen;": "\u0138", "khcy;": "\u0445", "kjcy;": "\u045c", "kopf;": "\U0001d55c", "kscr;": "\U0001d4c0", "lAarr;": "\u21da", "lArr;": "\u21d0", "lAtail;": "\u291b", "lBarr;": "\u290e", "lE;": "\u2266", "lEg;": "\u2a8b", "lHar;": "\u2962", "lacute;": "\u013a", "laemptyv;": "\u29b4", "lagran;": "\u2112", "lambda;": "\u03bb", "lang;": "\u27e8", "langd;": "\u2991", "langle;": "\u27e8", "lap;": "\u2a85", "laquo": "\xab", "laquo;": "\xab", "larr;": "\u2190", "larrb;": "\u21e4", "larrbfs;": "\u291f", "larrfs;": "\u291d", "larrhk;": "\u21a9", "larrlp;": "\u21ab", "larrpl;": "\u2939", "larrsim;": "\u2973", "larrtl;": "\u21a2", "lat;": "\u2aab", "latail;": "\u2919", "late;": "\u2aad", "lates;": "\u2aad\ufe00", "lbarr;": "\u290c", "lbbrk;": "\u2772", "lbrace;": "{", "lbrack;": "[", "lbrke;": "\u298b", "lbrksld;": "\u298f", "lbrkslu;": "\u298d", "lcaron;": "\u013e", "lcedil;": "\u013c", "lceil;": "\u2308", "lcub;": "{", "lcy;": "\u043b", "ldca;": "\u2936", "ldquo;": "\u201c", "ldquor;": "\u201e", "ldrdhar;": "\u2967", "ldrushar;": "\u294b", "ldsh;": "\u21b2", "le;": "\u2264", "leftarrow;": "\u2190", "leftarrowtail;": "\u21a2", "leftharpoondown;": "\u21bd", "leftharpoonup;": "\u21bc", "leftleftarrows;": "\u21c7", "leftrightarrow;": "\u2194", "leftrightarrows;": "\u21c6", "leftrightharpoons;": "\u21cb", "leftrightsquigarrow;": "\u21ad", "leftthreetimes;": "\u22cb", "leg;": "\u22da", "leq;": "\u2264", "leqq;": "\u2266", "leqslant;": "\u2a7d", "les;": "\u2a7d", "lescc;": "\u2aa8", "lesdot;": "\u2a7f", "lesdoto;": "\u2a81", "lesdotor;": "\u2a83", "lesg;": "\u22da\ufe00", "lesges;": "\u2a93", "lessapprox;": "\u2a85", "lessdot;": "\u22d6", "lesseqgtr;": "\u22da", "lesseqqgtr;": "\u2a8b", "lessgtr;": "\u2276", "lesssim;": "\u2272", "lfisht;": "\u297c", "lfloor;": "\u230a", "lfr;": "\U0001d529", "lg;": "\u2276", "lgE;": "\u2a91", "lhard;": "\u21bd", "lharu;": "\u21bc", "lharul;": "\u296a", "lhblk;": "\u2584", "ljcy;": "\u0459", "ll;": "\u226a", "llarr;": "\u21c7", "llcorner;": "\u231e", "llhard;": "\u296b", "lltri;": "\u25fa", "lmidot;": "\u0140", "lmoust;": "\u23b0", "lmoustache;": "\u23b0", "lnE;": "\u2268", "lnap;": "\u2a89", "lnapprox;": "\u2a89", "lne;": "\u2a87", "lneq;": "\u2a87", "lneqq;": "\u2268", "lnsim;": "\u22e6", "loang;": "\u27ec", "loarr;": "\u21fd", "lobrk;": "\u27e6", "longleftarrow;": "\u27f5", "longleftrightarrow;": "\u27f7", "longmapsto;": "\u27fc", "longrightarrow;": "\u27f6", "looparrowleft;": "\u21ab", "looparrowright;": "\u21ac", "lopar;": "\u2985", "lopf;": "\U0001d55d", "loplus;": "\u2a2d", "lotimes;": "\u2a34", "lowast;": "\u2217", "lowbar;": "_", "loz;": "\u25ca", "lozenge;": "\u25ca", "lozf;": "\u29eb", "lpar;": "(", "lparlt;": "\u2993", "lrarr;": "\u21c6", "lrcorner;": "\u231f", "lrhar;": "\u21cb", "lrhard;": "\u296d", "lrm;": "\u200e", "lrtri;": "\u22bf", "lsaquo;": "\u2039", "lscr;": "\U0001d4c1", "lsh;": "\u21b0", "lsim;": "\u2272", "lsime;": "\u2a8d", "lsimg;": "\u2a8f", "lsqb;": "[", "lsquo;": "\u2018", "lsquor;": "\u201a", "lstrok;": "\u0142", "lt": "<", "lt;": "<", "ltcc;": "\u2aa6", "ltcir;": "\u2a79", "ltdot;": "\u22d6", "lthree;": "\u22cb", "ltimes;": "\u22c9", "ltlarr;": "\u2976", "ltquest;": "\u2a7b", "ltrPar;": "\u2996", "ltri;": "\u25c3", "ltrie;": "\u22b4", "ltrif;": "\u25c2", "lurdshar;": "\u294a", "luruhar;": "\u2966", "lvertneqq;": "\u2268\ufe00", "lvnE;": "\u2268\ufe00", "mDDot;": "\u223a", "macr": "\xaf", "macr;": "\xaf", "male;": "\u2642", "malt;": "\u2720", "maltese;": "\u2720", "map;": "\u21a6", "mapsto;": "\u21a6", "mapstodown;": "\u21a7", "mapstoleft;": "\u21a4", "mapstoup;": "\u21a5", "marker;": "\u25ae", "mcomma;": "\u2a29", "mcy;": "\u043c", "mdash;": "\u2014", "measuredangle;": "\u2221", "mfr;": "\U0001d52a", "mho;": "\u2127", "micro": "\xb5", "micro;": "\xb5", "mid;": "\u2223", "midast;": "*", "midcir;": "\u2af0", "middot": "\xb7", "middot;": "\xb7", "minus;": "\u2212", "minusb;": "\u229f", "minusd;": "\u2238", "minusdu;": "\u2a2a", "mlcp;": "\u2adb", "mldr;": "\u2026", "mnplus;": "\u2213", "models;": "\u22a7", "mopf;": "\U0001d55e", "mp;": "\u2213", "mscr;": "\U0001d4c2", "mstpos;": "\u223e", "mu;": "\u03bc", "multimap;": "\u22b8", "mumap;": "\u22b8", "nGg;": "\u22d9\u0338", "nGt;": "\u226b\u20d2", "nGtv;": "\u226b\u0338", "nLeftarrow;": "\u21cd", "nLeftrightarrow;": "\u21ce", "nLl;": "\u22d8\u0338", "nLt;": "\u226a\u20d2", "nLtv;": "\u226a\u0338", "nRightarrow;": "\u21cf", "nVDash;": "\u22af", "nVdash;": "\u22ae", "nabla;": "\u2207", "nacute;": "\u0144", "nang;": "\u2220\u20d2", "nap;": "\u2249", "napE;": "\u2a70\u0338", "napid;": "\u224b\u0338", "napos;": "\u0149", "napprox;": "\u2249", "natur;": "\u266e", "natural;": "\u266e", "naturals;": "\u2115", "nbsp": "\xa0", "nbsp;": "\xa0", "nbump;": "\u224e\u0338", "nbumpe;": "\u224f\u0338", "ncap;": "\u2a43", "ncaron;": "\u0148", "ncedil;": "\u0146", "ncong;": "\u2247", "ncongdot;": "\u2a6d\u0338", "ncup;": "\u2a42", "ncy;": "\u043d", "ndash;": "\u2013", "ne;": "\u2260", "neArr;": "\u21d7", "nearhk;": "\u2924", "nearr;": "\u2197", "nearrow;": "\u2197", "nedot;": "\u2250\u0338", "nequiv;": "\u2262", "nesear;": "\u2928", "nesim;": "\u2242\u0338", "nexist;": "\u2204", "nexists;": "\u2204", "nfr;": "\U0001d52b", "ngE;": "\u2267\u0338", "nge;": "\u2271", "ngeq;": "\u2271", "ngeqq;": "\u2267\u0338", "ngeqslant;": "\u2a7e\u0338", "nges;": "\u2a7e\u0338", "ngsim;": "\u2275", "ngt;": "\u226f", "ngtr;": "\u226f", "nhArr;": "\u21ce", "nharr;": "\u21ae", "nhpar;": "\u2af2", "ni;": "\u220b", "nis;": "\u22fc", "nisd;": "\u22fa", "niv;": "\u220b", "njcy;": "\u045a", "nlArr;": "\u21cd", "nlE;": "\u2266\u0338", "nlarr;": "\u219a", "nldr;": "\u2025", "nle;": "\u2270", "nleftarrow;": "\u219a", "nleftrightarrow;": "\u21ae", "nleq;": "\u2270", "nleqq;": "\u2266\u0338", "nleqslant;": "\u2a7d\u0338", "nles;": "\u2a7d\u0338", "nless;": "\u226e", "nlsim;": "\u2274", "nlt;": "\u226e", "nltri;": "\u22ea", "nltrie;": "\u22ec", "nmid;": "\u2224", "nopf;": "\U0001d55f", "not": "\xac", "not;": "\xac", "notin;": "\u2209", "notinE;": "\u22f9\u0338", "notindot;": "\u22f5\u0338", "notinva;": "\u2209", "notinvb;": "\u22f7", "notinvc;": "\u22f6", "notni;": "\u220c", "notniva;": "\u220c", "notnivb;": "\u22fe", "notnivc;": "\u22fd", "npar;": "\u2226", "nparallel;": "\u2226", "nparsl;": "\u2afd\u20e5", "npart;": "\u2202\u0338", "npolint;": "\u2a14", "npr;": "\u2280", "nprcue;": "\u22e0", "npre;": "\u2aaf\u0338", "nprec;": "\u2280", "npreceq;": "\u2aaf\u0338", "nrArr;": "\u21cf", "nrarr;": "\u219b", "nrarrc;": "\u2933\u0338", "nrarrw;": "\u219d\u0338", "nrightarrow;": "\u219b", "nrtri;": "\u22eb", "nrtrie;": "\u22ed", "nsc;": "\u2281", "nsccue;": "\u22e1", "nsce;": "\u2ab0\u0338", "nscr;": "\U0001d4c3", "nshortmid;": "\u2224", "nshortparallel;": "\u2226", "nsim;": "\u2241", "nsime;": "\u2244", "nsimeq;": "\u2244", "nsmid;": "\u2224", "nspar;": "\u2226", "nsqsube;": "\u22e2", "nsqsupe;": "\u22e3", "nsub;": "\u2284", "nsubE;": "\u2ac5\u0338", "nsube;": "\u2288", "nsubset;": "\u2282\u20d2", "nsubseteq;": "\u2288", "nsubseteqq;": "\u2ac5\u0338", "nsucc;": "\u2281", "nsucceq;": "\u2ab0\u0338", "nsup;": "\u2285", "nsupE;": "\u2ac6\u0338", "nsupe;": "\u2289", "nsupset;": "\u2283\u20d2", "nsupseteq;": "\u2289", "nsupseteqq;": "\u2ac6\u0338", "ntgl;": "\u2279", "ntilde": "\xf1", "ntilde;": "\xf1", "ntlg;": "\u2278", "ntriangleleft;": "\u22ea", "ntrianglelefteq;": "\u22ec", "ntriangleright;": "\u22eb", "ntrianglerighteq;": "\u22ed", "nu;": "\u03bd", "num;": "#", "numero;": "\u2116", "numsp;": "\u2007", "nvDash;": "\u22ad", "nvHarr;": "\u2904", "nvap;": "\u224d\u20d2", "nvdash;": "\u22ac", "nvge;": "\u2265\u20d2", "nvgt;": ">\u20d2", "nvinfin;": "\u29de", "nvlArr;": "\u2902", "nvle;": "\u2264\u20d2", "nvlt;": "<\u20d2", "nvltrie;": "\u22b4\u20d2", "nvrArr;": "\u2903", "nvrtrie;": "\u22b5\u20d2", "nvsim;": "\u223c\u20d2", "nwArr;": "\u21d6", "nwarhk;": "\u2923", "nwarr;": "\u2196", "nwarrow;": "\u2196", "nwnear;": "\u2927", "oS;": "\u24c8", "oacute": "\xf3", "oacute;": "\xf3", "oast;": "\u229b", "ocir;": "\u229a", "ocirc": "\xf4", "ocirc;": "\xf4", "ocy;": "\u043e", "odash;": "\u229d", "odblac;": "\u0151", "odiv;": "\u2a38", "odot;": "\u2299", "odsold;": "\u29bc", "oelig;": "\u0153", "ofcir;": "\u29bf", "ofr;": "\U0001d52c", "ogon;": "\u02db", "ograve": "\xf2", "ograve;": "\xf2", "ogt;": "\u29c1", "ohbar;": "\u29b5", "ohm;": "\u03a9", "oint;": "\u222e", "olarr;": "\u21ba", "olcir;": "\u29be", "olcross;": "\u29bb", "oline;": "\u203e", "olt;": "\u29c0", "omacr;": "\u014d", "omega;": "\u03c9", "omicron;": "\u03bf", "omid;": "\u29b6", "ominus;": "\u2296", "oopf;": "\U0001d560", "opar;": "\u29b7", "operp;": "\u29b9", "oplus;": "\u2295", "or;": "\u2228", "orarr;": "\u21bb", "ord;": "\u2a5d", "order;": "\u2134", "orderof;": "\u2134", "ordf": "\xaa", "ordf;": "\xaa", "ordm": "\xba", "ordm;": "\xba", "origof;": "\u22b6", "oror;": "\u2a56", "orslope;": "\u2a57", "orv;": "\u2a5b", "oscr;": "\u2134", "oslash": "\xf8", "oslash;": "\xf8", "osol;": "\u2298", "otilde": "\xf5", "otilde;": "\xf5", "otimes;": "\u2297", "otimesas;": "\u2a36", "ouml": "\xf6", "ouml;": "\xf6", "ovbar;": "\u233d", "par;": "\u2225", "para": "\xb6", "para;": "\xb6", "parallel;": "\u2225", "parsim;": "\u2af3", "parsl;": "\u2afd", "part;": "\u2202", "pcy;": "\u043f", "percnt;": "%", "period;": ".", "permil;": "\u2030", "perp;": "\u22a5", "pertenk;": "\u2031", "pfr;": "\U0001d52d", "phi;": "\u03c6", "phiv;": "\u03d5", "phmmat;": "\u2133", "phone;": "\u260e", "pi;": "\u03c0", "pitchfork;": "\u22d4", "piv;": "\u03d6", "planck;": "\u210f", "planckh;": "\u210e", "plankv;": "\u210f", "plus;": "+", "plusacir;": "\u2a23", "plusb;": "\u229e", "pluscir;": "\u2a22", "plusdo;": "\u2214", "plusdu;": "\u2a25", "pluse;": "\u2a72", "plusmn": "\xb1", "plusmn;": "\xb1", "plussim;": "\u2a26", "plustwo;": "\u2a27", "pm;": "\xb1", "pointint;": "\u2a15", "popf;": "\U0001d561", "pound": "\xa3", "pound;": "\xa3", "pr;": "\u227a", "prE;": "\u2ab3", "prap;": "\u2ab7", "prcue;": "\u227c", "pre;": "\u2aaf", "prec;": "\u227a", "precapprox;": "\u2ab7", "preccurlyeq;": "\u227c", "preceq;": "\u2aaf", "precnapprox;": "\u2ab9", "precneqq;": "\u2ab5", "precnsim;": "\u22e8", "precsim;": "\u227e", "prime;": "\u2032", "primes;": "\u2119", "prnE;": "\u2ab5", "prnap;": "\u2ab9", "prnsim;": "\u22e8", "prod;": "\u220f", "profalar;": "\u232e", "profline;": "\u2312", "profsurf;": "\u2313", "prop;": "\u221d", "propto;": "\u221d", "prsim;": "\u227e", "prurel;": "\u22b0", "pscr;": "\U0001d4c5", "psi;": "\u03c8", "puncsp;": "\u2008", "qfr;": "\U0001d52e", "qint;": "\u2a0c", "qopf;": "\U0001d562", "qprime;": "\u2057", "qscr;": "\U0001d4c6", "quaternions;": "\u210d", "quatint;": "\u2a16", "quest;": "?", "questeq;": "\u225f", "quot": "\"", "quot;": "\"", "rAarr;": "\u21db", "rArr;": "\u21d2", "rAtail;": "\u291c", "rBarr;": "\u290f", "rHar;": "\u2964", "race;": "\u223d\u0331", "racute;": "\u0155", "radic;": "\u221a", "raemptyv;": "\u29b3", "rang;": "\u27e9", "rangd;": "\u2992", "range;": "\u29a5", "rangle;": "\u27e9", "raquo": "\xbb", "raquo;": "\xbb", "rarr;": "\u2192", "rarrap;": "\u2975", "rarrb;": "\u21e5", "rarrbfs;": "\u2920", "rarrc;": "\u2933", "rarrfs;": "\u291e", "rarrhk;": "\u21aa", "rarrlp;": "\u21ac", "rarrpl;": "\u2945", "rarrsim;": "\u2974", "rarrtl;": "\u21a3", "rarrw;": "\u219d", "ratail;": "\u291a", "ratio;": "\u2236", "rationals;": "\u211a", "rbarr;": "\u290d", "rbbrk;": "\u2773", "rbrace;": "}", "rbrack;": "]", "rbrke;": "\u298c", "rbrksld;": "\u298e", "rbrkslu;": "\u2990", "rcaron;": "\u0159", "rcedil;": "\u0157", "rceil;": "\u2309", "rcub;": "}", "rcy;": "\u0440", "rdca;": "\u2937", "rdldhar;": "\u2969", "rdquo;": "\u201d", "rdquor;": "\u201d", "rdsh;": "\u21b3", "real;": "\u211c", "realine;": "\u211b", "realpart;": "\u211c", "reals;": "\u211d", "rect;": "\u25ad", "reg": "\xae", "reg;": "\xae", "rfisht;": "\u297d", "rfloor;": "\u230b", "rfr;": "\U0001d52f", "rhard;": "\u21c1", "rharu;": "\u21c0", "rharul;": "\u296c", "rho;": "\u03c1", "rhov;": "\u03f1", "rightarrow;": "\u2192", "rightarrowtail;": "\u21a3", "rightharpoondown;": "\u21c1", "rightharpoonup;": "\u21c0", "rightleftarrows;": "\u21c4", "rightleftharpoons;": "\u21cc", "rightrightarrows;": "\u21c9", "rightsquigarrow;": "\u219d", "rightthreetimes;": "\u22cc", "ring;": "\u02da", "risingdotseq;": "\u2253", "rlarr;": "\u21c4", "rlhar;": "\u21cc", "rlm;": "\u200f", "rmoust;": "\u23b1", "rmoustache;": "\u23b1", "rnmid;": "\u2aee", "roang;": "\u27ed", "roarr;": "\u21fe", "robrk;": "\u27e7", "ropar;": "\u2986", "ropf;": "\U0001d563", "roplus;": "\u2a2e", "rotimes;": "\u2a35", "rpar;": ")", "rpargt;": "\u2994", "rppolint;": "\u2a12", "rrarr;": "\u21c9", "rsaquo;": "\u203a", "rscr;": "\U0001d4c7", "rsh;": "\u21b1", "rsqb;": "]", "rsquo;": "\u2019", "rsquor;": "\u2019", "rthree;": "\u22cc", "rtimes;": "\u22ca", "rtri;": "\u25b9", "rtrie;": "\u22b5", "rtrif;": "\u25b8", "rtriltri;": "\u29ce", "ruluhar;": "\u2968", "rx;": "\u211e", "sacute;": "\u015b", "sbquo;": "\u201a", "sc;": "\u227b", "scE;": "\u2ab4", "scap;": "\u2ab8", "scaron;": "\u0161", "sccue;": "\u227d", "sce;": "\u2ab0", "scedil;": "\u015f", "scirc;": "\u015d", "scnE;": "\u2ab6", "scnap;": "\u2aba", "scnsim;": "\u22e9", "scpolint;": "\u2a13", "scsim;": "\u227f", "scy;": "\u0441", "sdot;": "\u22c5", "sdotb;": "\u22a1", "sdote;": "\u2a66", "seArr;": "\u21d8", "searhk;": "\u2925", "searr;": "\u2198", "searrow;": "\u2198", "sect": "\xa7", "sect;": "\xa7", "semi;": ";", "seswar;": "\u2929", "setminus;": "\u2216", "setmn;": "\u2216", "sext;": "\u2736", "sfr;": "\U0001d530", "sfrown;": "\u2322", "sharp;": "\u266f", "shchcy;": "\u0449", "shcy;": "\u0448", "shortmid;": "\u2223", "shortparallel;": "\u2225", "shy": "\xad", "shy;": "\xad", "sigma;": "\u03c3", "sigmaf;": "\u03c2", "sigmav;": "\u03c2", "sim;": "\u223c", "simdot;": "\u2a6a", "sime;": "\u2243", "simeq;": "\u2243", "simg;": "\u2a9e", "simgE;": "\u2aa0", "siml;": "\u2a9d", "simlE;": "\u2a9f", "simne;": "\u2246", "simplus;": "\u2a24", "simrarr;": "\u2972", "slarr;": "\u2190", "smallsetminus;": "\u2216", "smashp;": "\u2a33", "smeparsl;": "\u29e4", "smid;": "\u2223", "smile;": "\u2323", "smt;": "\u2aaa", "smte;": "\u2aac", "smtes;": "\u2aac\ufe00", "softcy;": "\u044c", "sol;": "/", "solb;": "\u29c4", "solbar;": "\u233f", "sopf;": "\U0001d564", "spades;": "\u2660", "spadesuit;": "\u2660", "spar;": "\u2225", "sqcap;": "\u2293", "sqcaps;": "\u2293\ufe00", "sqcup;": "\u2294", "sqcups;": "\u2294\ufe00", "sqsub;": "\u228f", "sqsube;": "\u2291", "sqsubset;": "\u228f", "sqsubseteq;": "\u2291", "sqsup;": "\u2290", "sqsupe;": "\u2292", "sqsupset;": "\u2290", "sqsupseteq;": "\u2292", "squ;": "\u25a1", "square;": "\u25a1", "squarf;": "\u25aa", "squf;": "\u25aa", "srarr;": "\u2192", "sscr;": "\U0001d4c8", "ssetmn;": "\u2216", "ssmile;": "\u2323", "sstarf;": "\u22c6", "star;": "\u2606", "starf;": "\u2605", "straightepsilon;": "\u03f5", "straightphi;": "\u03d5", "strns;": "\xaf", "sub;": "\u2282", "subE;": "\u2ac5", "subdot;": "\u2abd", "sube;": "\u2286", "subedot;": "\u2ac3", "submult;": "\u2ac1", "subnE;": "\u2acb", "subne;": "\u228a", "subplus;": "\u2abf", "subrarr;": "\u2979", "subset;": "\u2282", "subseteq;": "\u2286", "subseteqq;": "\u2ac5", "subsetneq;": "\u228a", "subsetneqq;": "\u2acb", "subsim;": "\u2ac7", "subsub;": "\u2ad5", "subsup;": "\u2ad3", "succ;": "\u227b", "succapprox;": "\u2ab8", "succcurlyeq;": "\u227d", "succeq;": "\u2ab0", "succnapprox;": "\u2aba", "succneqq;": "\u2ab6", "succnsim;": "\u22e9", "succsim;": "\u227f", "sum;": "\u2211", "sung;": "\u266a", "sup1": "\xb9", "sup1;": "\xb9", "sup2": "\xb2", "sup2;": "\xb2", "sup3": "\xb3", "sup3;": "\xb3", "sup;": "\u2283", "supE;": "\u2ac6", "supdot;": "\u2abe", "supdsub;": "\u2ad8", "supe;": "\u2287", "supedot;": "\u2ac4", "suphsol;": "\u27c9", "suphsub;": "\u2ad7", "suplarr;": "\u297b", "supmult;": "\u2ac2", "supnE;": "\u2acc", "supne;": "\u228b", "supplus;": "\u2ac0", "supset;": "\u2283", "supseteq;": "\u2287", "supseteqq;": "\u2ac6", "supsetneq;": "\u228b", "supsetneqq;": "\u2acc", "supsim;": "\u2ac8", "supsub;": "\u2ad4", "supsup;": "\u2ad6", "swArr;": "\u21d9", "swarhk;": "\u2926", "swarr;": "\u2199", "swarrow;": "\u2199", "swnwar;": "\u292a", "szlig": "\xdf", "szlig;": "\xdf", "target;": "\u2316", "tau;": "\u03c4", "tbrk;": "\u23b4", "tcaron;": "\u0165", "tcedil;": "\u0163", "tcy;": "\u0442", "tdot;": "\u20db", "telrec;": "\u2315", "tfr;": "\U0001d531", "there4;": "\u2234", "therefore;": "\u2234", "theta;": "\u03b8", "thetasym;": "\u03d1", "thetav;": "\u03d1", "thickapprox;": "\u2248", "thicksim;": "\u223c", "thinsp;": "\u2009", "thkap;": "\u2248", "thksim;": "\u223c", "thorn": "\xfe", "thorn;": "\xfe", "tilde;": "\u02dc", "times": "\xd7", "times;": "\xd7", "timesb;": "\u22a0", "timesbar;": "\u2a31", "timesd;": "\u2a30", "tint;": "\u222d", "toea;": "\u2928", "top;": "\u22a4", "topbot;": "\u2336", "topcir;": "\u2af1", "topf;": "\U0001d565", "topfork;": "\u2ada", "tosa;": "\u2929", "tprime;": "\u2034", "trade;": "\u2122", "triangle;": "\u25b5", "triangledown;": "\u25bf", "triangleleft;": "\u25c3", "trianglelefteq;": "\u22b4", "triangleq;": "\u225c", "triangleright;": "\u25b9", "trianglerighteq;": "\u22b5", "tridot;": "\u25ec", "trie;": "\u225c", "triminus;": "\u2a3a", "triplus;": "\u2a39", "trisb;": "\u29cd", "tritime;": "\u2a3b", "trpezium;": "\u23e2", "tscr;": "\U0001d4c9", "tscy;": "\u0446", "tshcy;": "\u045b", "tstrok;": "\u0167", "twixt;": "\u226c", "twoheadleftarrow;": "\u219e", "twoheadrightarrow;": "\u21a0", "uArr;": "\u21d1", "uHar;": "\u2963", "uacute": "\xfa", "uacute;": "\xfa", "uarr;": "\u2191", "ubrcy;": "\u045e", "ubreve;": "\u016d", "ucirc": "\xfb", "ucirc;": "\xfb", "ucy;": "\u0443", "udarr;": "\u21c5", "udblac;": "\u0171", "udhar;": "\u296e", "ufisht;": "\u297e", "ufr;": "\U0001d532", "ugrave": "\xf9", "ugrave;": "\xf9", "uharl;": "\u21bf", "uharr;": "\u21be", "uhblk;": "\u2580", "ulcorn;": "\u231c", "ulcorner;": "\u231c", "ulcrop;": "\u230f", "ultri;": "\u25f8", "umacr;": "\u016b", "uml": "\xa8", "uml;": "\xa8", "uogon;": "\u0173", "uopf;": "\U0001d566", "uparrow;": "\u2191", "updownarrow;": "\u2195", "upharpoonleft;": "\u21bf", "upharpoonright;": "\u21be", "uplus;": "\u228e", "upsi;": "\u03c5", "upsih;": "\u03d2", "upsilon;": "\u03c5", "upuparrows;": "\u21c8", "urcorn;": "\u231d", "urcorner;": "\u231d", "urcrop;": "\u230e", "uring;": "\u016f", "urtri;": "\u25f9", "uscr;": "\U0001d4ca", "utdot;": "\u22f0", "utilde;": "\u0169", "utri;": "\u25b5", "utrif;": "\u25b4", "uuarr;": "\u21c8", "uuml": "\xfc", "uuml;": "\xfc", "uwangle;": "\u29a7", "vArr;": "\u21d5", "vBar;": "\u2ae8", "vBarv;": "\u2ae9", "vDash;": "\u22a8", "vangrt;": "\u299c", "varepsilon;": "\u03f5", "varkappa;": "\u03f0", "varnothing;": "\u2205", "varphi;": "\u03d5", "varpi;": "\u03d6", "varpropto;": "\u221d", "varr;": "\u2195", "varrho;": "\u03f1", "varsigma;": "\u03c2", "varsubsetneq;": "\u228a\ufe00", "varsubsetneqq;": "\u2acb\ufe00", "varsupsetneq;": "\u228b\ufe00", "varsupsetneqq;": "\u2acc\ufe00", "vartheta;": "\u03d1", "vartriangleleft;": "\u22b2", "vartriangleright;": "\u22b3", "vcy;": "\u0432", "vdash;": "\u22a2", "vee;": "\u2228", "veebar;": "\u22bb", "veeeq;": "\u225a", "vellip;": "\u22ee", "verbar;": "|", "vert;": "|", "vfr;": "\U0001d533", "vltri;": "\u22b2", "vnsub;": "\u2282\u20d2", "vnsup;": "\u2283\u20d2", "vopf;": "\U0001d567", "vprop;": "\u221d", "vrtri;": "\u22b3", "vscr;": "\U0001d4cb", "vsubnE;": "\u2acb\ufe00", "vsubne;": "\u228a\ufe00", "vsupnE;": "\u2acc\ufe00", "vsupne;": "\u228b\ufe00", "vzigzag;": "\u299a", "wcirc;": "\u0175", "wedbar;": "\u2a5f", "wedge;": "\u2227", "wedgeq;": "\u2259", "weierp;": "\u2118", "wfr;": "\U0001d534", "wopf;": "\U0001d568", "wp;": "\u2118", "wr;": "\u2240", "wreath;": "\u2240", "wscr;": "\U0001d4cc", "xcap;": "\u22c2", "xcirc;": "\u25ef", "xcup;": "\u22c3", "xdtri;": "\u25bd", "xfr;": "\U0001d535", "xhArr;": "\u27fa", "xharr;": "\u27f7", "xi;": "\u03be", "xlArr;": "\u27f8", "xlarr;": "\u27f5", "xmap;": "\u27fc", "xnis;": "\u22fb", "xodot;": "\u2a00", "xopf;": "\U0001d569", "xoplus;": "\u2a01", "xotime;": "\u2a02", "xrArr;": "\u27f9", "xrarr;": "\u27f6", "xscr;": "\U0001d4cd", "xsqcup;": "\u2a06", "xuplus;": "\u2a04", "xutri;": "\u25b3", "xvee;": "\u22c1", "xwedge;": "\u22c0", "yacute": "\xfd", "yacute;": "\xfd", "yacy;": "\u044f", "ycirc;": "\u0177", "ycy;": "\u044b", "yen": "\xa5", "yen;": "\xa5", "yfr;": "\U0001d536", "yicy;": "\u0457", "yopf;": "\U0001d56a", "yscr;": "\U0001d4ce", "yucy;": "\u044e", "yuml": "\xff", "yuml;": "\xff", "zacute;": "\u017a", "zcaron;": "\u017e", "zcy;": "\u0437", "zdot;": "\u017c", "zeetrf;": "\u2128", "zeta;": "\u03b6", "zfr;": "\U0001d537", "zhcy;": "\u0436", "zigrarr;": "\u21dd", "zopf;": "\U0001d56b", "zscr;": "\U0001d4cf", "zwj;": "\u200d", "zwnj;": "\u200c", } replacementCharacters = { 0x0: "\uFFFD", 0x0d: "\u000D", 0x80: "\u20AC", 0x81: "\u0081", 0x81: "\u0081", 0x82: "\u201A", 0x83: "\u0192", 0x84: "\u201E", 0x85: "\u2026", 0x86: "\u2020", 0x87: "\u2021", 0x88: "\u02C6", 0x89: "\u2030", 0x8A: "\u0160", 0x8B: "\u2039", 0x8C: "\u0152", 0x8D: "\u008D", 0x8E: "\u017D", 0x8F: "\u008F", 0x90: "\u0090", 0x91: "\u2018", 0x92: "\u2019", 0x93: "\u201C", 0x94: "\u201D", 0x95: "\u2022", 0x96: "\u2013", 0x97: "\u2014", 0x98: "\u02DC", 0x99: "\u2122", 0x9A: "\u0161", 0x9B: "\u203A", 0x9C: "\u0153", 0x9D: "\u009D", 0x9E: "\u017E", 0x9F: "\u0178", } encodings = { '437': 'cp437', '850': 'cp850', '852': 'cp852', '855': 'cp855', '857': 'cp857', '860': 'cp860', '861': 'cp861', '862': 'cp862', '863': 'cp863', '865': 'cp865', '866': 'cp866', '869': 'cp869', 'ansix341968': 'ascii', 'ansix341986': 'ascii', 'arabic': 'iso8859-6', 'ascii': 'ascii', 'asmo708': 'iso8859-6', 'big5': 'big5', 'big5hkscs': 'big5hkscs', 'chinese': 'gbk', 'cp037': 'cp037', 'cp1026': 'cp1026', 'cp154': 'ptcp154', 'cp367': 'ascii', 'cp424': 'cp424', 'cp437': 'cp437', 'cp500': 'cp500', 'cp775': 'cp775', 'cp819': 'windows-1252', 'cp850': 'cp850', 'cp852': 'cp852', 'cp855': 'cp855', 'cp857': 'cp857', 'cp860': 'cp860', 'cp861': 'cp861', 'cp862': 'cp862', 'cp863': 'cp863', 'cp864': 'cp864', 'cp865': 'cp865', 'cp866': 'cp866', 'cp869': 'cp869', 'cp936': 'gbk', 'cpgr': 'cp869', 'cpis': 'cp861', 'csascii': 'ascii', 'csbig5': 'big5', 'cseuckr': 'cp949', 'cseucpkdfmtjapanese': 'euc_jp', 'csgb2312': 'gbk', 'cshproman8': 'hp-roman8', 'csibm037': 'cp037', 'csibm1026': 'cp1026', 'csibm424': 'cp424', 'csibm500': 'cp500', 'csibm855': 'cp855', 'csibm857': 'cp857', 'csibm860': 'cp860', 'csibm861': 'cp861', 'csibm863': 'cp863', 'csibm864': 'cp864', 'csibm865': 'cp865', 'csibm866': 'cp866', 'csibm869': 'cp869', 'csiso2022jp': 'iso2022_jp', 'csiso2022jp2': 'iso2022_jp_2', 'csiso2022kr': 'iso2022_kr', 'csiso58gb231280': 'gbk', 'csisolatin1': 'windows-1252', 'csisolatin2': 'iso8859-2', 'csisolatin3': 'iso8859-3', 'csisolatin4': 'iso8859-4', 'csisolatin5': 'windows-1254', 'csisolatin6': 'iso8859-10', 'csisolatinarabic': 'iso8859-6', 'csisolatincyrillic': 'iso8859-5', 'csisolatingreek': 'iso8859-7', 'csisolatinhebrew': 'iso8859-8', 'cskoi8r': 'koi8-r', 'csksc56011987': 'cp949', 'cspc775baltic': 'cp775', 'cspc850multilingual': 'cp850', 'cspc862latinhebrew': 'cp862', 'cspc8codepage437': 'cp437', 'cspcp852': 'cp852', 'csptcp154': 'ptcp154', 'csshiftjis': 'shift_jis', 'csunicode11utf7': 'utf-7', 'cyrillic': 'iso8859-5', 'cyrillicasian': 'ptcp154', 'ebcdiccpbe': 'cp500', 'ebcdiccpca': 'cp037', 'ebcdiccpch': 'cp500', 'ebcdiccphe': 'cp424', 'ebcdiccpnl': 'cp037', 'ebcdiccpus': 'cp037', 'ebcdiccpwt': 'cp037', 'ecma114': 'iso8859-6', 'ecma118': 'iso8859-7', 'elot928': 'iso8859-7', 'eucjp': 'euc_jp', 'euckr': 'cp949', 'extendedunixcodepackedformatforjapanese': 'euc_jp', 'gb18030': 'gb18030', 'gb2312': 'gbk', 'gb231280': 'gbk', 'gbk': 'gbk', 'greek': 'iso8859-7', 'greek8': 'iso8859-7', 'hebrew': 'iso8859-8', 'hproman8': 'hp-roman8', 'hzgb2312': 'hz', 'ibm037': 'cp037', 'ibm1026': 'cp1026', 'ibm367': 'ascii', 'ibm424': 'cp424', 'ibm437': 'cp437', 'ibm500': 'cp500', 'ibm775': 'cp775', 'ibm819': 'windows-1252', 'ibm850': 'cp850', 'ibm852': 'cp852', 'ibm855': 'cp855', 'ibm857': 'cp857', 'ibm860': 'cp860', 'ibm861': 'cp861', 'ibm862': 'cp862', 'ibm863': 'cp863', 'ibm864': 'cp864', 'ibm865': 'cp865', 'ibm866': 'cp866', 'ibm869': 'cp869', 'iso2022jp': 'iso2022_jp', 'iso2022jp2': 'iso2022_jp_2', 'iso2022kr': 'iso2022_kr', 'iso646irv1991': 'ascii', 'iso646us': 'ascii', 'iso88591': 'windows-1252', 'iso885910': 'iso8859-10', 'iso8859101992': 'iso8859-10', 'iso885911987': 'windows-1252', 'iso885913': 'iso8859-13', 'iso885914': 'iso8859-14', 'iso8859141998': 'iso8859-14', 'iso885915': 'iso8859-15', 'iso885916': 'iso8859-16', 'iso8859162001': 'iso8859-16', 'iso88592': 'iso8859-2', 'iso885921987': 'iso8859-2', 'iso88593': 'iso8859-3', 'iso885931988': 'iso8859-3', 'iso88594': 'iso8859-4', 'iso885941988': 'iso8859-4', 'iso88595': 'iso8859-5', 'iso885951988': 'iso8859-5', 'iso88596': 'iso8859-6', 'iso885961987': 'iso8859-6', 'iso88597': 'iso8859-7', 'iso885971987': 'iso8859-7', 'iso88598': 'iso8859-8', 'iso885981988': 'iso8859-8', 'iso88599': 'windows-1254', 'iso885991989': 'windows-1254', 'isoceltic': 'iso8859-14', 'isoir100': 'windows-1252', 'isoir101': 'iso8859-2', 'isoir109': 'iso8859-3', 'isoir110': 'iso8859-4', 'isoir126': 'iso8859-7', 'isoir127': 'iso8859-6', 'isoir138': 'iso8859-8', 'isoir144': 'iso8859-5', 'isoir148': 'windows-1254', 'isoir149': 'cp949', 'isoir157': 'iso8859-10', 'isoir199': 'iso8859-14', 'isoir226': 'iso8859-16', 'isoir58': 'gbk', 'isoir6': 'ascii', 'koi8r': 'koi8-r', 'koi8u': 'koi8-u', 'korean': 'cp949', 'ksc5601': 'cp949', 'ksc56011987': 'cp949', 'ksc56011989': 'cp949', 'l1': 'windows-1252', 'l10': 'iso8859-16', 'l2': 'iso8859-2', 'l3': 'iso8859-3', 'l4': 'iso8859-4', 'l5': 'windows-1254', 'l6': 'iso8859-10', 'l8': 'iso8859-14', 'latin1': 'windows-1252', 'latin10': 'iso8859-16', 'latin2': 'iso8859-2', 'latin3': 'iso8859-3', 'latin4': 'iso8859-4', 'latin5': 'windows-1254', 'latin6': 'iso8859-10', 'latin8': 'iso8859-14', 'latin9': 'iso8859-15', 'ms936': 'gbk', 'mskanji': 'shift_jis', 'pt154': 'ptcp154', 'ptcp154': 'ptcp154', 'r8': 'hp-roman8', 'roman8': 'hp-roman8', 'shiftjis': 'shift_jis', 'tis620': 'cp874', 'unicode11utf7': 'utf-7', 'us': 'ascii', 'usascii': 'ascii', 'utf16': 'utf-16', 'utf16be': 'utf-16-be', 'utf16le': 'utf-16-le', 'utf8': 'utf-8', 'windows1250': 'cp1250', 'windows1251': 'cp1251', 'windows1252': 'cp1252', 'windows1253': 'cp1253', 'windows1254': 'cp1254', 'windows1255': 'cp1255', 'windows1256': 'cp1256', 'windows1257': 'cp1257', 'windows1258': 'cp1258', 'windows936': 'gbk', 'x-x-big5': 'big5'} tokenTypes = { "Doctype": 0, "Characters": 1, "SpaceCharacters": 2, "StartTag": 3, "EndTag": 4, "EmptyTag": 5, "Comment": 6, "ParseError": 7 } tagTokenTypes = frozenset([tokenTypes["StartTag"], tokenTypes["EndTag"], tokenTypes["EmptyTag"]]) prefixes = dict([(v, k) for k, v in namespaces.items()]) prefixes["http://www.w3.org/1998/Math/MathML"] = "math" class DataLossWarning(UserWarning): pass class ReparseException(Exception): pass feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/0000755000076500000240000000000012765362057030104 5ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/__init__.py0000644000076500000240000000000012700725533032172 0ustar jmstaff00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/_base.py0000644000076500000240000000043612700725533031521 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals class Filter(object): def __init__(self, source): self.source = source def __iter__(self): return iter(self.source) def __getattr__(self, name): return getattr(self.source, name) ././@LongLink0000000000000000000000000000015700000000000011220 Lustar 00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.pyfeedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/alphabeticalatt0000644000076500000240000000116012700725533033136 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from . import _base try: from collections import OrderedDict except ImportError: from ordereddict import OrderedDict class Filter(_base.Filter): def __iter__(self): for token in _base.Filter.__iter__(self): if token["type"] in ("StartTag", "EmptyTag"): attrs = OrderedDict() for name, value in sorted(token["data"].items(), key=lambda x: x[0]): attrs[name] = value token["data"] = attrs yield token ././@LongLink0000000000000000000000000000015400000000000011215 Lustar 00000000000000feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.pyfeedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/inject_meta_cha0000644000076500000240000000527212700725533033121 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from . import _base class Filter(_base.Filter): def __init__(self, source, encoding): _base.Filter.__init__(self, source) self.encoding = encoding def __iter__(self): state = "pre_head" meta_found = (self.encoding is None) pending = [] for token in _base.Filter.__iter__(self): type = token["type"] if type == "StartTag": if token["name"].lower() == "head": state = "in_head" elif type == "EmptyTag": if token["name"].lower() == "meta": # replace charset with actual encoding has_http_equiv_content_type = False for (namespace, name), value in token["data"].items(): if namespace is not None: continue elif name.lower() == 'charset': token["data"][(namespace, name)] = self.encoding meta_found = True break elif name == 'http-equiv' and value.lower() == 'content-type': has_http_equiv_content_type = True else: if has_http_equiv_content_type and (None, "content") in token["data"]: token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding meta_found = True elif token["name"].lower() == "head" and not meta_found: # insert meta into empty head yield {"type": "StartTag", "name": "head", "data": token["data"]} yield {"type": "EmptyTag", "name": "meta", "data": {(None, "charset"): self.encoding}} yield {"type": "EndTag", "name": "head"} meta_found = True continue elif type == "EndTag": if token["name"].lower() == "head" and pending: # insert meta into head (if necessary) and flush pending queue yield pending.pop(0) if not meta_found: yield {"type": "EmptyTag", "name": "meta", "data": {(None, "charset"): self.encoding}} while pending: yield pending.pop(0) meta_found = True state = "post_head" if state == "in_head": pending.append(token) else: yield token feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/lint.py0000644000076500000240000001016012700725533031411 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from . import _base from ..constants import cdataElements, rcdataElements, voidElements from ..constants import spaceCharacters spaceCharacters = "".join(spaceCharacters) class LintError(Exception): pass class Filter(_base.Filter): def __iter__(self): open_elements = [] contentModelFlag = "PCDATA" for token in _base.Filter.__iter__(self): type = token["type"] if type in ("StartTag", "EmptyTag"): name = token["name"] if contentModelFlag != "PCDATA": raise LintError("StartTag not in PCDATA content model flag: %(tag)s" % {"tag": name}) if not isinstance(name, str): raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) if not name: raise LintError("Empty tag name") if type == "StartTag" and name in voidElements: raise LintError("Void element reported as StartTag token: %(tag)s" % {"tag": name}) elif type == "EmptyTag" and name not in voidElements: raise LintError("Non-void element reported as EmptyTag token: %(tag)s" % {"tag": token["name"]}) if type == "StartTag": open_elements.append(name) for name, value in token["data"]: if not isinstance(name, str): raise LintError("Attribute name is not a string: %(name)r" % {"name": name}) if not name: raise LintError("Empty attribute name") if not isinstance(value, str): raise LintError("Attribute value is not a string: %(value)r" % {"value": value}) if name in cdataElements: contentModelFlag = "CDATA" elif name in rcdataElements: contentModelFlag = "RCDATA" elif name == "plaintext": contentModelFlag = "PLAINTEXT" elif type == "EndTag": name = token["name"] if not isinstance(name, str): raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) if not name: raise LintError("Empty tag name") if name in voidElements: raise LintError("Void element reported as EndTag token: %(tag)s" % {"tag": name}) start_name = open_elements.pop() if start_name != name: raise LintError("EndTag (%(end)s) does not match StartTag (%(start)s)" % {"end": name, "start": start_name}) contentModelFlag = "PCDATA" elif type == "Comment": if contentModelFlag != "PCDATA": raise LintError("Comment not in PCDATA content model flag") elif type in ("Characters", "SpaceCharacters"): data = token["data"] if not isinstance(data, str): raise LintError("Attribute name is not a string: %(name)r" % {"name": data}) if not data: raise LintError("%(type)s token with empty data" % {"type": type}) if type == "SpaceCharacters": data = data.strip(spaceCharacters) if data: raise LintError("Non-space character(s) found in SpaceCharacters token: %(token)r" % {"token": data}) elif type == "Doctype": name = token["name"] if contentModelFlag != "PCDATA": raise LintError("Doctype not in PCDATA content model flag: %(name)s" % {"name": name}) if not isinstance(name, str): raise LintError("Tag name is not a string: %(tag)r" % {"tag": name}) # XXX: what to do with token["data"] ? elif type in ("ParseError", "SerializeError"): pass else: raise LintError("Unknown token type: %(type)s" % {"type": type}) yield token feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/optionaltags.py0000644000076500000240000002440412700725533033155 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from . import _base class Filter(_base.Filter): def slider(self): previous1 = previous2 = None for token in self.source: if previous1 is not None: yield previous2, previous1, token previous2 = previous1 previous1 = token yield previous2, previous1, None def __iter__(self): for previous, token, next in self.slider(): type = token["type"] if type == "StartTag": if (token["data"] or not self.is_optional_start(token["name"], previous, next)): yield token elif type == "EndTag": if not self.is_optional_end(token["name"], next): yield token else: yield token def is_optional_start(self, tagname, previous, next): type = next and next["type"] or None if tagname in 'html': # An html element's start tag may be omitted if the first thing # inside the html element is not a space character or a comment. return type not in ("Comment", "SpaceCharacters") elif tagname == 'head': # A head element's start tag may be omitted if the first thing # inside the head element is an element. # XXX: we also omit the start tag if the head element is empty if type in ("StartTag", "EmptyTag"): return True elif type == "EndTag": return next["name"] == "head" elif tagname == 'body': # A body element's start tag may be omitted if the first thing # inside the body element is not a space character or a comment, # except if the first thing inside the body element is a script # or style element and the node immediately preceding the body # element is a head element whose end tag has been omitted. if type in ("Comment", "SpaceCharacters"): return False elif type == "StartTag": # XXX: we do not look at the preceding event, so we never omit # the body element's start tag if it's followed by a script or # a style element. return next["name"] not in ('script', 'style') else: return True elif tagname == 'colgroup': # A colgroup element's start tag may be omitted if the first thing # inside the colgroup element is a col element, and if the element # is not immediately preceeded by another colgroup element whose # end tag has been omitted. if type in ("StartTag", "EmptyTag"): # XXX: we do not look at the preceding event, so instead we never # omit the colgroup element's end tag when it is immediately # followed by another colgroup element. See is_optional_end. return next["name"] == "col" else: return False elif tagname == 'tbody': # A tbody element's start tag may be omitted if the first thing # inside the tbody element is a tr element, and if the element is # not immediately preceeded by a tbody, thead, or tfoot element # whose end tag has been omitted. if type == "StartTag": # omit the thead and tfoot elements' end tag when they are # immediately followed by a tbody element. See is_optional_end. if previous and previous['type'] == 'EndTag' and \ previous['name'] in ('tbody', 'thead', 'tfoot'): return False return next["name"] == 'tr' else: return False return False def is_optional_end(self, tagname, next): type = next and next["type"] or None if tagname in ('html', 'head', 'body'): # An html element's end tag may be omitted if the html element # is not immediately followed by a space character or a comment. return type not in ("Comment", "SpaceCharacters") elif tagname in ('li', 'optgroup', 'tr'): # A li element's end tag may be omitted if the li element is # immediately followed by another li element or if there is # no more content in the parent element. # An optgroup element's end tag may be omitted if the optgroup # element is immediately followed by another optgroup element, # or if there is no more content in the parent element. # A tr element's end tag may be omitted if the tr element is # immediately followed by another tr element, or if there is # no more content in the parent element. if type == "StartTag": return next["name"] == tagname else: return type == "EndTag" or type is None elif tagname in ('dt', 'dd'): # A dt element's end tag may be omitted if the dt element is # immediately followed by another dt element or a dd element. # A dd element's end tag may be omitted if the dd element is # immediately followed by another dd element or a dt element, # or if there is no more content in the parent element. if type == "StartTag": return next["name"] in ('dt', 'dd') elif tagname == 'dd': return type == "EndTag" or type is None else: return False elif tagname == 'p': # A p element's end tag may be omitted if the p element is # immediately followed by an address, article, aside, # blockquote, datagrid, dialog, dir, div, dl, fieldset, # footer, form, h1, h2, h3, h4, h5, h6, header, hr, menu, # nav, ol, p, pre, section, table, or ul, element, or if # there is no more content in the parent element. if type in ("StartTag", "EmptyTag"): return next["name"] in ('address', 'article', 'aside', 'blockquote', 'datagrid', 'dialog', 'dir', 'div', 'dl', 'fieldset', 'footer', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'header', 'hr', 'menu', 'nav', 'ol', 'p', 'pre', 'section', 'table', 'ul') else: return type == "EndTag" or type is None elif tagname == 'option': # An option element's end tag may be omitted if the option # element is immediately followed by another option element, # or if it is immediately followed by an optgroup # element, or if there is no more content in the parent # element. if type == "StartTag": return next["name"] in ('option', 'optgroup') else: return type == "EndTag" or type is None elif tagname in ('rt', 'rp'): # An rt element's end tag may be omitted if the rt element is # immediately followed by an rt or rp element, or if there is # no more content in the parent element. # An rp element's end tag may be omitted if the rp element is # immediately followed by an rt or rp element, or if there is # no more content in the parent element. if type == "StartTag": return next["name"] in ('rt', 'rp') else: return type == "EndTag" or type is None elif tagname == 'colgroup': # A colgroup element's end tag may be omitted if the colgroup # element is not immediately followed by a space character or # a comment. if type in ("Comment", "SpaceCharacters"): return False elif type == "StartTag": # XXX: we also look for an immediately following colgroup # element. See is_optional_start. return next["name"] != 'colgroup' else: return True elif tagname in ('thead', 'tbody'): # A thead element's end tag may be omitted if the thead element # is immediately followed by a tbody or tfoot element. # A tbody element's end tag may be omitted if the tbody element # is immediately followed by a tbody or tfoot element, or if # there is no more content in the parent element. # A tfoot element's end tag may be omitted if the tfoot element # is immediately followed by a tbody element, or if there is no # more content in the parent element. # XXX: we never omit the end tag when the following element is # a tbody. See is_optional_start. if type == "StartTag": return next["name"] in ['tbody', 'tfoot'] elif tagname == 'tbody': return type == "EndTag" or type is None else: return False elif tagname == 'tfoot': # A tfoot element's end tag may be omitted if the tfoot element # is immediately followed by a tbody element, or if there is no # more content in the parent element. # XXX: we never omit the end tag when the following element is # a tbody. See is_optional_start. if type == "StartTag": return next["name"] == 'tbody' else: return type == "EndTag" or type is None elif tagname in ('td', 'th'): # A td element's end tag may be omitted if the td element is # immediately followed by a td or th element, or if there is # no more content in the parent element. # A th element's end tag may be omitted if the th element is # immediately followed by a td or th element, or if there is # no more content in the parent element. if type == "StartTag": return next["name"] in ('td', 'th') else: return type == "EndTag" or type is None return False feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/sanitizer.py0000644000076500000240000000054012700725533032454 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from . import _base from ..sanitizer import HTMLSanitizerMixin class Filter(_base.Filter, HTMLSanitizerMixin): def __iter__(self): for token in _base.Filter.__iter__(self): token = self.sanitize_token(token) if token: yield token feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/filters/whitespace.py0000644000076500000240000000216612700725533032606 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals import re from . import _base from ..constants import rcdataElements, spaceCharacters spaceCharacters = "".join(spaceCharacters) SPACES_REGEX = re.compile("[%s]+" % spaceCharacters) class Filter(_base.Filter): spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements)) def __iter__(self): preserve = 0 for token in _base.Filter.__iter__(self): type = token["type"] if type == "StartTag" \ and (preserve or token["name"] in self.spacePreserveElements): preserve += 1 elif type == "EndTag" and preserve: preserve -= 1 elif not preserve and type == "SpaceCharacters" and token["data"]: # Test on token["data"] above to not introduce spaces where there were not token["data"] = " " elif not preserve and type == "Characters": token["data"] = collapse_spaces(token["data"]) yield token def collapse_spaces(text): return SPACES_REGEX.sub(' ', text) feedgenerator-1.9/.tox/py26/lib/python2.6/site-packages/pip/_vendor/html5lib/html5parser.py0000644000076500000240000034514312700725533031255 0ustar jmstaff00000000000000from __future__ import absolute_import, division, unicode_literals from pip._vendor.six import with_metaclass import types from . import inputstream from . import tokenizer from . import treebuilders from .treebuilders._base import Marker from . import utils from . import constants from .constants import spaceCharacters, asciiUpper2Lower from .constants import specialElements from .constants import headingElements from .constants import cdataElements, rcdataElements from .constants import tokenTypes, ReparseException, namespaces from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements from .constants import adjustForeignAttributes as adjustForeignAttributesMap from .constants import E def parse(doc, treebuilder="etree", encoding=None, namespaceHTMLElements=True): """Parse a string or file-like object into a tree""" tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) return p.parse(doc, encoding=encoding) def parseFragment(doc, container="div", treebuilder="etree", encoding=None, namespaceHTMLElements=True): tb = treebuilders.getTreeBuilder(treebuilder) p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) return p.parseFragment(doc, container=container, encoding=encoding) def method_decorator_metaclass(function): class Decorated(type): def __new__(meta, classname, bases, classDict): for attributeName, attribute in classDict.items(): if isinstance(attribute, types.FunctionType): attribute = function(attribute) classDict[attributeName] = attribute return type.__new__(meta, classname, bases, classDict) return Decorated class HTMLParser(object): """HTML parser. Generates a tree structure from a stream of (possibly malformed) HTML""" def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer, strict=False, namespaceHTMLElements=True, debug=False): """ strict - raise an exception when a parse error is encountered tree - a treebuilder class controlling the type of tree that will be returned. Built in treebuilders can be accessed through html5lib.treebuilders.getTreeBuilder(treeType) tokenizer - a class that provides a stream of tokens to the treebuilder. This may be replaced for e.g. a sanitizer which converts some tags to text """ # Raise an exception on the first error encountered self.strict = strict if tree is None: tree = treebuilders.getTreeBuilder("etree") self.tree = tree(namespaceHTMLElements) self.tokenizer_class = tokenizer self.errors = [] self.phases = dict([(name, cls(self, self.tree)) for name, cls in getPhases(debug).items()]) def _parse(self, stream, innerHTML=False, container="div", encoding=None, parseMeta=True, useChardet=True, **kwargs): self.innerHTMLMode = innerHTML self.container = container self.tokenizer = self.tokenizer_class(stream, encoding=encoding, parseMeta=parseMeta, useChardet=useChardet, parser=self, **kwargs) self.reset() while True: try: self.mainLoop() break except ReparseException: self.reset() def reset(self): self.tree.reset() self.firstStartTag = False self.errors = [] self.log = [] # only used with debug mode # "quirks" / "limited quirks" / "no quirks" self.compatMode = "no quirks" if self.innerHTMLMode: self.innerHTML = self.container.lower() if self.innerHTML in cdataElements: self.tokenizer.state = self.tokenizer.rcdataState elif self.innerHTML in rcdataElements: self.tokenizer.state = self.tokenizer.rawtextState elif self.innerHTML == 'plaintext': self.tokenizer.state = self.tokenizer.plaintextState else: # state already is data state # self.tokenizer.state = self.tokenizer.dataState pass self.phase = self.phases["beforeHtml"] self.phase.insertHtmlElement() self.resetInsertionMode() else: self.innerHTML = False self.phase = self.phases["initial"] self.lastPhase = None self.beforeRCDataPhase = None self.framesetOK = True @property def documentEncoding(self): """The name of the character encoding that was used to decode the input stream, or :obj:`None` if that is not determined yet. """ if not hasattr(self, 'tokenizer'): return None return self.tokenizer.stream.charEncoding[0] def isHTMLIntegrationPoint(self, element): if (element.name == "annotation-xml" and element.namespace == namespaces["mathml"]): return ("encoding" in element.attributes and element.attributes["encoding"].translate( asciiUpper2Lower) in ("text/html", "application/xhtml+xml")) else: return (element.namespace, element.name) in htmlIntegrationPointElements def isMathMLTextIntegrationPoint(self, element): return (element.namespace, element.name) in mathmlTextIntegrationPointElements def mainLoop(self): CharactersToken = tokenTypes["Characters"] SpaceCharactersToken = tokenTypes["SpaceCharacters"] StartTagToken = tokenTypes["StartTag"] EndTagToken = tokenTypes["EndTag"] CommentToken = tokenTypes["Comment"] DoctypeToken = tokenTypes["Doctype"] ParseErrorToken = tokenTypes["ParseError"] for token in self.normalizedTokens(): new_token = token while new_token is not None: currentNode = self.tree.openElements[-1] if self.tree.openElements else None currentNodeNamespace = currentNode.namespace if currentNode else None currentNodeName = currentNode.name if currentNode else None type = new_token["type"] if type == ParseErrorToken: self.parseError(new_token["data"], new_token.get("datavars", {})) new_token = None else: if (len(self.tree.openElements) == 0 or currentNodeNamespace == self.tree.defaultNamespace or (self.isMathMLTextIntegrationPoint(currentNode) and ((type == StartTagToken and token["name"] not in frozenset(["mglyph", "malignmark"])) or type in (CharactersToken, SpaceCharactersToken))) or (currentNodeNamespace == namespaces["mathml"] and currentNodeName == "annotation-xml" and token["name"] == "svg") or (self.isHTMLIntegrationPoint(currentNode) and type in (StartTagToken, CharactersToken, SpaceCharactersToken))): phase = self.phase else: phase = self.phases["inForeignContent"] if type == CharactersToken: new_token = phase.processCharacters(new_token) elif type == SpaceCharactersToken: new_token = phase.processSpaceCharacters(new_token) elif type == StartTagToken: new_token = phase.processStartTag(new_token) elif type == EndTagToken: new_token = phase.processEndTag(new_token) elif type == CommentToken: new_token = phase.processComment(new_token) elif type == DoctypeToken: new_token = phase.processDoctype(new_token) if (type == StartTagToken and token["selfClosing"] and not token["selfClosingAcknowledged"]): self.parseError("non-void-element-with-trailing-solidus", {"name": token["name"]}) # When the loop finishes it's EOF reprocess = True phases = [] while reprocess: phases.append(self.phase) reprocess = self.phase.processEOF() if reprocess: assert self.phase not in phases def normalizedTokens(self): for token in self.tokenizer: yield self.normalizeToken(token) def parse(self, stream, encoding=None, parseMeta=True, useChardet=True): """Parse a HTML document into a well-formed tree stream - a filelike object or string containing the HTML to be parsed The optional encoding parameter must be a string that indicates the encoding. If specified, that encoding will be used, regardless of any BOM or later declaration (such as in a meta element) """ self._parse(stream, innerHTML=False, encoding=encoding, parseMeta=parseMeta, useChardet=useChardet) return self.tree.getDocument() def parseFragment(self, stream, container="div", encoding=None, parseMeta=False, useChardet=True): """Parse a HTML fragment into a well-formed tree fragment container - name of the element we're setting the innerHTML property if set to None, default to 'div' stream - a filelike object or string containing the HTML to be parsed The optional encoding parameter must be a string that indicates the encoding. If specified, that encoding will be used, regardless of any BOM or later declaration (such as in a meta element) """ self._parse(stream, True, container=container, encoding=encoding) return self.tree.getFragment() def parseError(self, errorcode="XXX-undefined-error", datavars={}): # XXX The idea is to make errorcode mandatory. self.errors.append((self.tokenizer.stream.position(), errorcode, datavars)) if self.strict: raise ParseError(E[errorcode] % datavars) def normalizeToken(self, token): """ HTML5 specific normalizations to the token stream """ if token["type"] == tokenTypes["StartTag"]: token["data"] = dict(token["data"][::-1]) return token def adjustMathMLAttributes(self, token): replacements = {"definitionurl": "definitionURL"} for k, v in replacements.items(): if k in token["data"]: token["data"][v] = token["data"][k] del token["data"][k] def adjustSVGAttributes(self, token): replacements = { "attributename": "attributeName", "attributetype": "attributeType", "basefrequency": "baseFrequency", "baseprofile": "baseProfile", "calcmode": "calcMode", "clippathunits": "clipPathUnits", "contentscripttype": "contentScriptType", "contentstyletype": "contentStyleType", "diffuseconstant": "diffuseConstant", "edgemode": "edgeMode", "externalresourcesrequired": "externalResourcesRequired", "filterres": "filterRes", "filterunits": "filterUnits", "glyphref": "glyphRef", "gradienttransform": "gradientTransform", "gradientunits": "gradientUnits", "kernelmatrix": "kernelMatrix", "kernelunitlength": "kernelUnitLength", "keypoints": "keyPoints", "keysplines": "keySplines", "keytimes": "keyTimes", "lengthadjust": "lengthAdjust", "limitingconeangle": "limitingConeAngle", "markerheight": "markerHeight", "markerunits": "markerUnits", "markerwidth": "markerWidth", "maskcontentunits": "maskContentUnits", "maskunits": "maskUnits", "numoctaves": "numOctaves", "pathlength": "pathLength", "patterncontentunits": "patternContentUnits", "patterntransform": "patternTransform", "patternunits": "patternUnits", "pointsatx": "pointsAtX", "pointsaty": "pointsAtY", "pointsatz": "pointsAtZ", "preservealpha": "preserveAlpha", "preserveaspectratio": "preserveAspectRatio", "primitiveunits": "primitiveUnits", "refx": "refX", "refy": "refY", "repeatcount": "repeatCount", "repeatdur": "repeatDur", "requiredextensions": "requiredExtensions", "requiredfeatures": "requiredFeatures", "specularconstant": "specularConstant", "specularexponent": "specularExponent", "spreadmethod": "spreadMethod", "startoffset": "startOffset", "stddeviation": "stdDeviation", "stitchtiles": "stitchTiles", "surfacescale": "surfaceScale", "systemlanguage": "systemLanguage", "tablevalues": "tableValues", "targetx": "targetX", "targety": "targetY", "textlength": "textLength", "viewbox": "viewBox", "viewtarget": "viewTarget", "xchannelselector": "xChannelSelector", "ychannelselector": "yChannelSelector", "zoomandpan": "zoomAndPan" } for originalName in list(token["data"].keys()): if originalName in replacements: svgName = replacements[originalName] token["data"][svgName] = token["data"][originalName] del token["data"][originalName] def adjustForeignAttributes(self, token): replacements = adjustForeignAttributesMap for originalName in token["data"].keys(): if originalName in replacements: foreignName = replacements[originalName] token["data"][foreignName] = token["data"][originalName] del token["data"][originalName] def reparseTokenNormal(self, token): self.parser.phase() def resetInsertionMode(self): # The name of this method is mostly historical. (It's also used in the # specification.) last = False newModes = { "select": "inSelect", "td": "inCell", "th": "inCell", "tr": "inRow", "tbody": "inTableBody", "thead": "inTableBody", "tfoot": "inTableBody", "caption": "inCaption", "colgroup": "inColumnGroup", "table": "inTable", "head": "inBody", "body": "inBody", "frameset": "inFrameset", "html": "beforeHead" } for node in self.tree.openElements[::-1]: nodeName = node.name new_phase = None if node == self.tree.openElements[0]: assert self.innerHTML last = True nodeName = self.innerHTML # Check for conditions that should only happen in the innerHTML # case if nodeName in ("select", "colgroup", "head", "html"): assert self.innerHTML if not last and node.namespace != self.tree.defaultNamespace: continue if nodeName in newModes: new_phase = self.phases[newModes[nodeName]] break elif last: new_phase = self.phases["inBody"] break self.phase = new_phase def parseRCDataRawtext(self, token, contentType): """Generic RCDATA/RAWTEXT Parsing algorithm contentType - RCDATA or RAWTEXT """ assert contentType in ("RAWTEXT", "RCDATA") self.tree.insertElement(token) if contentType == "RAWTEXT": self.tokenizer.state = self.tokenizer.rawtextState else: self.tokenizer.state = self.tokenizer.rcdataState self.originalPhase = self.phase self.phase = self.phases["text"] def getPhases(debug): def log(function): """Logger that records which phase processes each token""" type_names = dict((value, key) for key, value in constants.tokenTypes.items()) def wrapped(self, *args, **kwargs): if function.__name__.startswith("process") and len(args) > 0: token = args[0] try: info = {"type": type_names[token['type']]} except: raise if token['type'] in constants.tagTokenTypes: info["name"] = token['name'] self.parser.log.append((self.parser.tokenizer.state.__name__, self.parser.phase.__class__.__name__, self.__class__.__name__, function.__name__, info)) return function(self, *args, **kwargs) else: return function(self, *args, **kwargs) return wrapped def getMetaclass(use_metaclass, metaclass_func): if use_metaclass: return method_decorator_metaclass(metaclass_func) else: return type class Phase(with_metaclass(getMetaclass(debug, log))): """Base class for helper object that implements each phase of processing """ def __init__(self, parser, tree): self.parser = parser self.tree = tree def processEOF(self): raise NotImplementedError def processComment(self, token): # For most phases the following is correct. Where it's not it will be # overridden. self.tree.insertComment(token, self.tree.openElements[-1]) def processDoctype(self, token): self.parser.parseError("unexpected-doctype") def processCharacters(self, token): self.tree.insertText(token["data"]) def processSpaceCharacters(self, token): self.tree.insertText(token["data"]) def processStartTag(self, token): return self.startTagHandler[token["name"]](token) def startTagHtml(self, token): if not self.parser.firstStartTag and token["name"] == "html": self.parser.parseError("non-html-root") # XXX Need a check here to see if the first start tag token emitted is # this token... If it's not, invoke self.parser.parseError(). for attr, value in token["data"].items(): if attr not in self.tree.openElements[0].attributes: self.tree.openElements[0].attributes[attr] = value self.parser.firstStartTag = False def processEndTag(self, token): return self.endTagHandler[token["name"]](token) class InitialPhase(Phase): def processSpaceCharacters(self, token): pass def processComment(self, token): self.tree.insertComment(token, self.tree.document) def processDoctype(self, token): name = token["name"] publicId = token["publicId"] systemId = token["systemId"] correct = token["correct"] if (name != "html" or publicId is not None or systemId is not None and systemId != "about:legacy-compat"): self.parser.parseError("unknown-doctype") if publicId is None: publicId = "" self.tree.insertDoctype(token) if publicId != "": publicId = publicId.translate(asciiUpper2Lower) if (not correct or token["name"] != "html" or publicId.startswith( ("+//silmaril//dtd html pro v0r11 19970101//", "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", "-//as//dtd html 3.0 aswedit + extensions//", "-//ietf//dtd html 2.0 level 1//", "-//ietf//dtd html 2.0 level 2//", "-//ietf//dtd html 2.0 strict level 1//", "-//ietf//dtd html 2.0 strict level 2//", "-//ietf//dtd html 2.0 strict//", "-//ietf//dtd html 2.0//", "-//ietf//dtd html 2.1e//", "-//ietf//dtd html 3.0//", "-//ietf//dtd html 3.2 final//", "-//ietf//dtd html 3.2//", "-//ietf//dtd html 3//", "-//ietf//dtd html level 0//", "-//ietf//dtd html level 1//", "-//ietf//dtd html level 2//", "-//ietf//dtd html level 3//", "-//ietf//dtd html strict level 0//", "-//ietf//dtd html strict level 1//", "-//ietf//dtd html strict level 2//", "-//ietf//dtd html strict level 3//", "-//ietf//dtd html strict//", "-//ietf//dtd html//", "-//metrius//dtd metrius presentational//", "-//microsoft//dtd internet explorer 2.0 html strict//", "-//microsoft//dtd internet explorer 2.0 html//", "-//microsoft//dtd internet explorer 2.0 tables//", "-//microsoft//dtd internet explorer 3.0 html strict//", "-//microsoft//dtd internet explorer 3.0 html//", "-//microsoft//dtd internet explorer 3.0 tables//", "-//netscape comm. corp.//dtd html//", "-//netscape comm. corp.//dtd strict html//", "-//o'reilly and associates//dtd html 2.0//", "-//o'reilly and associates//dtd html extended 1.0//", "-//o'reilly and associates//dtd html extended relaxed 1.0//", "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", "-//spyglass//dtd html 2.0 extended//", "-//sq//dtd html 2.0 hotmetal + extensions//", "-//sun microsystems corp.//dtd hotjava html//", "-//sun microsystems corp.//dtd hotjava strict html//", "-//w3c//dtd html 3 1995-03-24//", "-//w3c//dtd html 3.2 draft//", "-//w3c//dtd html 3.2 final//", "-//w3c//dtd html 3.2//", "-//w3c//dtd html 3.2s draft//", "-//w3c//dtd html 4.0 frameset//", "-//w3c//dtd html 4.0 transitional//", "-//w3c//dtd html experimental 19960712//", "-//w3c//dtd html experimental 970421//", "-//w3c//dtd w3 html//", "-//w3o//dtd w3 html 3.0//", "-//webtechs//dtd mozilla html 2.0//", "-//webtechs//dtd mozilla html//")) or publicId in ("-//w3o//dtd w3 html strict 3.0//en//", "-/w3c/dtd html 4.0 transitional/en", "html") or publicId.startswith( ("-//w3c//dtd html 4.01 frameset//", "-//w3c//dtd html 4.01 transitional//")) and systemId is None or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"): self.parser.compatMode = "quirks" elif (publicId.startswith( ("-//w3c//dtd xhtml 1.0 frameset//", "-//w3c//dtd xhtml 1.0 transitional//")) or publicId.startswith( ("-//w3c//dtd html 4.01 frameset//", "-//w3c//dtd html 4.01 transitional//")) and systemId is not None): self.parser.compatMode = "limited quirks" self.parser.phase = self.parser.phases["beforeHtml"] def anythingElse(self): self.parser.compatMode = "quirks" self.parser.phase = self.parser.phases["beforeHtml"] def processCharacters(self, token): self.parser.parseError("expected-doctype-but-got-chars") self.anythingElse() return token def processStartTag(self, token): self.parser.parseError("expected-doctype-but-got-start-tag", {"name": token["name"]}) self.anythingElse() return token def processEndTag(self, token): self.parser.parseError("expected-doctype-but-got-end-tag", {"name": token["name"]}) self.anythingElse() return token def processEOF(self): self.parser.parseError("expected-doctype-but-got-eof") self.anythingElse() return True class BeforeHtmlPhase(Phase): # helper methods def insertHtmlElement(self): self.tree.insertRoot(impliedTagToken("html", "StartTag")) self.parser.phase = self.parser.phases["beforeHead"] # other def processEOF(self): self.insertHtmlElement() return True def processComment(self, token): self.tree.insertComment(token, self.tree.document) def processSpaceCharacters(self, token): pass def processCharacters(self, token): self.insertHtmlElement() return token def processStartTag(self, token): if token["name"] == "html": self.parser.firstStartTag = True self.insertHtmlElement() return token def processEndTag(self, token): if token["name"] not in ("head", "body", "html", "br"): self.parser.parseError("unexpected-end-tag-before-html", {"name": token["name"]}) else: self.insertHtmlElement() return token class BeforeHeadPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self.endTagHandler = utils.MethodDispatcher([ (("head", "body", "html", "br"), self.endTagImplyHead) ]) self.endTagHandler.default = self.endTagOther def processEOF(self): self.startTagHead(impliedTagToken("head", "StartTag")) return True def processSpaceCharacters(self, token): pass def processCharacters(self, token): self.startTagHead(impliedTagToken("head", "StartTag")) return token def startTagHtml(self, token): return self.parser.phases["inBody"].processStartTag(token) def startTagHead(self, token): self.tree.insertElement(token) self.tree.headPointer = self.tree.openElements[-1] self.parser.phase = self.parser.phases["inHead"] def startTagOther(self, token): self.startTagHead(impliedTagToken("head", "StartTag")) return token def endTagImplyHead(self, token): self.startTagHead(impliedTagToken("head", "StartTag")) return token def endTagOther(self, token): self.parser.parseError("end-tag-after-implied-root", {"name": token["name"]}) class InHeadPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("title", self.startTagTitle), (("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle), ("script", self.startTagScript), (("base", "basefont", "bgsound", "command", "link"), self.startTagBaseLinkCommand), ("meta", self.startTagMeta), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self. endTagHandler = utils.MethodDispatcher([ ("head", self.endTagHead), (("br", "html", "body"), self.endTagHtmlBodyBr) ]) self.endTagHandler.default = self.endTagOther # the real thing def processEOF(self): self.anythingElse() return True def processCharacters(self, token): self.anythingElse() return token def startTagHtml(self, token): return self.parser.phases["inBody"].processStartTag(token) def startTagHead(self, token): self.parser.parseError("two-heads-are-not-better-than-one") def startTagBaseLinkCommand(self, token): self.tree.insertElement(token) self.tree.openElements.pop() token["selfClosingAcknowledged"] = True def startTagMeta(self, token): self.tree.insertElement(token) self.tree.openElements.pop() token["selfClosingAcknowledged"] = True attributes = token["data"] if self.parser.tokenizer.stream.charEncoding[1] == "tentative": if "charset" in attributes: self.parser.tokenizer.stream.changeEncoding(attributes["charset"]) elif ("content" in attributes and "http-equiv" in attributes and attributes["http-equiv"].lower() == "content-type"): # Encoding it as UTF-8 here is a hack, as really we should pass # the abstract Unicode string, and just use the # ContentAttrParser on that, but using UTF-8 allows all chars # to be encoded and as a ASCII-superset works. data = inputstream.EncodingBytes(attributes["content"].encode("utf-8")) parser = inputstream.ContentAttrParser(data) codec = parser.parse() self.parser.tokenizer.stream.changeEncoding(codec) def startTagTitle(self, token): self.parser.parseRCDataRawtext(token, "RCDATA") def startTagNoScriptNoFramesStyle(self, token): # Need to decide whether to implement the scripting-disabled case self.parser.parseRCDataRawtext(token, "RAWTEXT") def startTagScript(self, token): self.tree.insertElement(token) self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState self.parser.originalPhase = self.parser.phase self.parser.phase = self.parser.phases["text"] def startTagOther(self, token): self.anythingElse() return token def endTagHead(self, token): node = self.parser.tree.openElements.pop() assert node.name == "head", "Expected head got %s" % node.name self.parser.phase = self.parser.phases["afterHead"] def endTagHtmlBodyBr(self, token): self.anythingElse() return token def endTagOther(self, token): self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) def anythingElse(self): self.endTagHead(impliedTagToken("head")) # XXX If we implement a parser for which scripting is disabled we need to # implement this phase. # # class InHeadNoScriptPhase(Phase): class AfterHeadPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("body", self.startTagBody), ("frameset", self.startTagFrameset), (("base", "basefont", "bgsound", "link", "meta", "noframes", "script", "style", "title"), self.startTagFromHead), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"), self.endTagHtmlBodyBr)]) self.endTagHandler.default = self.endTagOther def processEOF(self): self.anythingElse() return True def processCharacters(self, token): self.anythingElse() return token def startTagHtml(self, token): return self.parser.phases["inBody"].processStartTag(token) def startTagBody(self, token): self.parser.framesetOK = False self.tree.insertElement(token) self.parser.phase = self.parser.phases["inBody"] def startTagFrameset(self, token): self.tree.insertElement(token) self.parser.phase = self.parser.phases["inFrameset"] def startTagFromHead(self, token): self.parser.parseError("unexpected-start-tag-out-of-my-head", {"name": token["name"]}) self.tree.openElements.append(self.tree.headPointer) self.parser.phases["inHead"].processStartTag(token) for node in self.tree.openElements[::-1]: if node.name == "head": self.tree.openElements.remove(node) break def startTagHead(self, token): self.parser.parseError("unexpected-start-tag", {"name": token["name"]}) def startTagOther(self, token): self.anythingElse() return token def endTagHtmlBodyBr(self, token): self.anythingElse() return token def endTagOther(self, token): self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) def anythingElse(self): self.tree.insertElement(impliedTagToken("body", "StartTag")) self.parser.phase = self.parser.phases["inBody"] self.parser.framesetOK = True class InBodyPhase(Phase): # http://www.whatwg.org/specs/web-apps/current-work/#parsing-main-inbody # the really-really-really-very crazy mode def __init__(self, parser, tree): Phase.__init__(self, parser, tree) # Keep a ref to this for special handling of whitespace in
            self.processSpaceCharactersNonPre = self.processSpaceCharacters

            self.startTagHandler = utils.MethodDispatcher([
                ("html", self.startTagHtml),
                (("base", "basefont", "bgsound", "command", "link", "meta",
                  "script", "style", "title"),
                 self.startTagProcessInHead),
                ("body", self.startTagBody),
                ("frameset", self.startTagFrameset),
                (("address", "article", "aside", "blockquote", "center", "details",
                  "details", "dir", "div", "dl", "fieldset", "figcaption", "figure",
                  "footer", "header", "hgroup", "main", "menu", "nav", "ol", "p",
                  "section", "summary", "ul"),
                 self.startTagCloseP),
                (headingElements, self.startTagHeading),
                (("pre", "listing"), self.startTagPreListing),
                ("form", self.startTagForm),
                (("li", "dd", "dt"), self.startTagListItem),
                ("plaintext", self.startTagPlaintext),
                ("a", self.startTagA),
                (("b", "big", "code", "em", "font", "i", "s", "small", "strike",
                  "strong", "tt", "u"), self.startTagFormatting),
                ("nobr", self.startTagNobr),
                ("button", self.startTagButton),
                (("applet", "marquee", "object"), self.startTagAppletMarqueeObject),
                ("xmp", self.startTagXmp),
                ("table", self.startTagTable),
                (("area", "br", "embed", "img", "keygen", "wbr"),
                 self.startTagVoidFormatting),
                (("param", "source", "track"), self.startTagParamSource),
                ("input", self.startTagInput),
                ("hr", self.startTagHr),
                ("image", self.startTagImage),
                ("isindex", self.startTagIsIndex),
                ("textarea", self.startTagTextarea),
                ("iframe", self.startTagIFrame),
                (("noembed", "noframes", "noscript"), self.startTagRawtext),
                ("select", self.startTagSelect),
                (("rp", "rt"), self.startTagRpRt),
                (("option", "optgroup"), self.startTagOpt),
                (("math"), self.startTagMath),
                (("svg"), self.startTagSvg),
                (("caption", "col", "colgroup", "frame", "head",
                  "tbody", "td", "tfoot", "th", "thead",
                  "tr"), self.startTagMisplaced)
            ])
            self.startTagHandler.default = self.startTagOther

            self.endTagHandler = utils.MethodDispatcher([
                ("body", self.endTagBody),
                ("html", self.endTagHtml),
                (("address", "article", "aside", "blockquote", "button", "center",
                  "details", "dialog", "dir", "div", "dl", "fieldset", "figcaption", "figure",
                  "footer", "header", "hgroup", "listing", "main", "menu", "nav", "ol", "pre",
                  "section", "summary", "ul"), self.endTagBlock),
                ("form", self.endTagForm),
                ("p", self.endTagP),
                (("dd", "dt", "li"), self.endTagListItem),
                (headingElements, self.endTagHeading),
                (("a", "b", "big", "code", "em", "font", "i", "nobr", "s", "small",
                  "strike", "strong", "tt", "u"), self.endTagFormatting),
                (("applet", "marquee", "object"), self.endTagAppletMarqueeObject),
                ("br", self.endTagBr),
            ])
            self.endTagHandler.default = self.endTagOther

        def isMatchingFormattingElement(self, node1, node2):
            if node1.name != node2.name or node1.namespace != node2.namespace:
                return False
            elif len(node1.attributes) != len(node2.attributes):
                return False
            else:
                attributes1 = sorted(node1.attributes.items())
                attributes2 = sorted(node2.attributes.items())
                for attr1, attr2 in zip(attributes1, attributes2):
                    if attr1 != attr2:
                        return False
            return True

        # helper
        def addFormattingElement(self, token):
            self.tree.insertElement(token)
            element = self.tree.openElements[-1]

            matchingElements = []
            for node in self.tree.activeFormattingElements[::-1]:
                if node is Marker:
                    break
                elif self.isMatchingFormattingElement(node, element):
                    matchingElements.append(node)

            assert len(matchingElements) <= 3
            if len(matchingElements) == 3:
                self.tree.activeFormattingElements.remove(matchingElements[-1])
            self.tree.activeFormattingElements.append(element)

        # the real deal
        def processEOF(self):
            allowed_elements = frozenset(("dd", "dt", "li", "p", "tbody", "td",
                                          "tfoot", "th", "thead", "tr", "body",
                                          "html"))
            for node in self.tree.openElements[::-1]:
                if node.name not in allowed_elements:
                    self.parser.parseError("expected-closing-tag-but-got-eof")
                    break
            # Stop parsing

        def processSpaceCharactersDropNewline(self, token):
            # Sometimes (start of 
, , and