././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.599321
lazr.uri-1.0.6/ 0000755 0001750 0001750 00000000000 00000000000 014767 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1326800465.0
lazr.uri-1.0.6/COPYING.txt 0000644 0001750 0001750 00000016725 00000000000 016653 0 ustar 00cjwatson cjwatson 0000000 0000000 GNU LESSER GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc.
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
This version of the GNU Lesser General Public License incorporates
the terms and conditions of version 3 of the GNU General Public
License, supplemented by the additional permissions listed below.
0. Additional Definitions.
As used herein, "this License" refers to version 3 of the GNU Lesser
General Public License, and the "GNU GPL" refers to version 3 of the GNU
General Public License.
"The Library" refers to a covered work governed by this License,
other than an Application or a Combined Work as defined below.
An "Application" is any work that makes use of an interface provided
by the Library, but which is not otherwise based on the Library.
Defining a subclass of a class defined by the Library is deemed a mode
of using an interface provided by the Library.
A "Combined Work" is a work produced by combining or linking an
Application with the Library. The particular version of the Library
with which the Combined Work was made is also called the "Linked
Version".
The "Minimal Corresponding Source" for a Combined Work means the
Corresponding Source for the Combined Work, excluding any source code
for portions of the Combined Work that, considered in isolation, are
based on the Application, and not on the Linked Version.
The "Corresponding Application Code" for a Combined Work means the
object code and/or source code for the Application, including any data
and utility programs needed for reproducing the Combined Work from the
Application, but excluding the System Libraries of the Combined Work.
1. Exception to Section 3 of the GNU GPL.
You may convey a covered work under sections 3 and 4 of this License
without being bound by section 3 of the GNU GPL.
2. Conveying Modified Versions.
If you modify a copy of the Library, and, in your modifications, a
facility refers to a function or data to be supplied by an Application
that uses the facility (other than as an argument passed when the
facility is invoked), then you may convey a copy of the modified
version:
a) under this License, provided that you make a good faith effort to
ensure that, in the event an Application does not supply the
function or data, the facility still operates, and performs
whatever part of its purpose remains meaningful, or
b) under the GNU GPL, with none of the additional permissions of
this License applicable to that copy.
3. Object Code Incorporating Material from Library Header Files.
The object code form of an Application may incorporate material from
a header file that is part of the Library. You may convey such object
code under terms of your choice, provided that, if the incorporated
material is not limited to numerical parameters, data structure
layouts and accessors, or small macros, inline functions and templates
(ten or fewer lines in length), you do both of the following:
a) Give prominent notice with each copy of the object code that the
Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the object code with a copy of the GNU GPL and this license
document.
4. Combined Works.
You may convey a Combined Work under terms of your choice that,
taken together, effectively do not restrict modification of the
portions of the Library contained in the Combined Work and reverse
engineering for debugging such modifications, if you also do each of
the following:
a) Give prominent notice with each copy of the Combined Work that
the Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the Combined Work with a copy of the GNU GPL and this license
document.
c) For a Combined Work that displays copyright notices during
execution, include the copyright notice for the Library among
these notices, as well as a reference directing the user to the
copies of the GNU GPL and this license document.
d) Do one of the following:
0) Convey the Minimal Corresponding Source under the terms of this
License, and the Corresponding Application Code in a form
suitable for, and under terms that permit, the user to
recombine or relink the Application with a modified version of
the Linked Version to produce a modified Combined Work, in the
manner specified by section 6 of the GNU GPL for conveying
Corresponding Source.
1) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (a) uses at run time
a copy of the Library already present on the user's computer
system, and (b) will operate properly with a modified version
of the Library that is interface-compatible with the Linked
Version.
e) Provide Installation Information, but only if you would otherwise
be required to provide such information under section 6 of the
GNU GPL, and only to the extent that such information is
necessary to install and execute a modified version of the
Combined Work produced by recombining or relinking the
Application with a modified version of the Linked Version. (If
you use option 4d0, the Installation Information must accompany
the Minimal Corresponding Source and Corresponding Application
Code. If you use option 4d1, you must provide the Installation
Information in the manner specified by section 6 of the GNU GPL
for conveying Corresponding Source.)
5. Combined Libraries.
You may place library facilities that are a work based on the
Library side by side in a single library together with other library
facilities that are not Applications and are not covered by this
License, and convey such a combined library under terms of your
choice, if you do both of the following:
a) Accompany the combined library with a copy of the same work based
on the Library, uncombined with any other library facilities,
conveyed under the terms of this License.
b) Give prominent notice with the combined library that part of it
is a work based on the Library, and explaining where to find the
accompanying uncombined form of the same work.
6. Revised Versions of the GNU Lesser General Public License.
The Free Software Foundation may publish revised and/or new versions
of the GNU Lesser General Public License from time to time. Such new
versions will be similar in spirit to the present version, but may
differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the
Library as you received it specifies that a certain numbered version
of the GNU Lesser General Public License "or any later version"
applies to it, you have the option of following the terms and
conditions either of that published version or of any later version
published by the Free Software Foundation. If the Library as you
received it does not specify a version number of the GNU Lesser
General Public License, you may choose any version of the GNU Lesser
General Public License ever published by the Free Software Foundation.
If the Library as you received it specifies that a proxy can decide
whether future versions of the GNU Lesser General Public License shall
apply, that proxy's public statement of acceptance of any version is
permanent authorization for you to choose that version for the
Library.
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1591959939.0
lazr.uri-1.0.6/HACKING.rst 0000644 0001750 0001750 00000002067 00000000000 016572 0 ustar 00cjwatson cjwatson 0000000 0000000 ..
This file is part of lazr.uri.
lazr.uri is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, version 3 of the License.
lazr.uri is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with lazr.uri. If not, see .
============
Introduction
============
To run this project's tests, use `tox `.
Getting help
------------
If you find bugs in this package, you can report them here:
https://launchpad.net/lazr.uri
If you want to discuss this package, join the team and mailing list here:
https://launchpad.net/~lazr-developers
or send a message to:
lazr-developers@lists.launchpad.net
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1591959939.0
lazr.uri-1.0.6/MANIFEST.in 0000644 0001750 0001750 00000000247 00000000000 016530 0 ustar 00cjwatson cjwatson 0000000 0000000 include COPYING.txt HACKING.rst NEWS.rst
recursive-include src *.txt *.rst *.zcml
include src/lazr/uri/docs/Makefile
prune src/lazr/uri/docs/_build
exclude .bzrignore
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547700.0
lazr.uri-1.0.6/NEWS.rst 0000644 0001750 0001750 00000001356 00000000000 016302 0 ustar 00cjwatson cjwatson 0000000 0000000 =================
NEWS for lazr.uri
=================
1.0.6 (2021-09-13)
==================
- Adjust versioning strategy to avoid importing pkg_resources, which is slow
in large environments.
1.0.5 (2020-06-29)
==================
- Add an explicit __hash__ method to lazr.uri.URI.
1.0.4 (2020-06-12)
==================
- Install version.txt with package_data (Stefano Rivera,
https://bugs.launchpad.net/lazr.uri/+bug/918660).
- Switch from buildout to tox.
1.0.3 (2012-01-18)
==================
- Add compatibility with Python 3 (Thomas Kluyver).
1.0.1 (2009-06-01)
==================
- Eliminate dependency on setuptools_bzr so sdists do not bring bzr ini, among
others.
1.0 (2009-03-23)
================
- Initial release on PyPI
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.599321
lazr.uri-1.0.6/PKG-INFO 0000644 0001750 0001750 00000016035 00000000000 016071 0 ustar 00cjwatson cjwatson 0000000 0000000 Metadata-Version: 2.1
Name: lazr.uri
Version: 1.0.6
Summary: A self-contained, easily reusable library for parsing, manipulating,
Home-page: https://launchpad.net/lazr.uri
Maintainer: LAZR Developers
Maintainer-email: lazr-developers@lists.launchpad.net
License: LGPL v3
Download-URL: https://launchpad.net/lazr.uri/+download
Description: ..
This file is part of lazr.uri.
lazr.uri is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, version 3 of the License.
lazr.uri is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with lazr.uri. If not, see .
lazr.uri
********
The lazr.uri package includes code for parsing and dealing with URIs.
>>> import lazr.uri
>>> print('VERSION:', lazr.uri.__version__)
VERSION: ...
=============
The URI class
=============
>>> from lazr.uri import URI
>>> uri1 = URI('http://localhost/foo/bar?123')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
These next two are equivalent, so the answer should be True, even through
the "outside" one is shorter than the "inside" one.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
True
The next two are exactly the same. We consider a url to be inside itself.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/')
>>> uri1.contains(uri2)
True
In the next case, the string of url2 starts with the string of url1. But,
because url2 continues within the same path step, url2 is not inside url1.
>>> uri1 = URI('http://localhost/foo/ba')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
False
Here, url2 is url1 plus an extra path step. So, url2 is inside url1.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
Once the URI is parsed, its parts are accessible.
>>> uri = URI('https://fish.tree:8666/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'fish.tree'
>>> uri.port
'8666'
>>> uri.authority
'fish.tree:8666'
>>> uri.path
'/blee/blah'
>>> uri = URI('https://localhost/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'localhost'
>>> uri.port is None
True
>>> uri.authority
'localhost'
>>> uri.path
'/blee/blah'
The grammar from RFC 3986 does not allow for square brackets in the
query component, but Section 3.4 does say how such delimeter
characters should be handled if found in the component.
>>> uri = URI('http://www.apple.com/store?delivery=[slow]#horse+cart')
>>> uri.scheme
'http'
>>> uri.host
'www.apple.com'
>>> uri.port is None
True
>>> uri.path
'/store'
>>> uri.query
'delivery=[slow]'
>>> uri.fragment
'horse+cart'
====================
Finding URIs in Text
====================
lazr.uri also knows how to retrieve a list of URIs from a block of
text. This is intended for uses like finding bug tracker URIs or
similar.
The find_uris_in_text() function returns an iterator that yields URI
objects for each URI found in the text. Note that the returned URIs
have been canonicalised by the URI class:
>>> from lazr.uri import find_uris_in_text
>>> text = '''
... A list of URIs:
... * http://localhost/a/b
... * http://launchpad.net
... * MAILTO:joe@example.com
... * xmpp:fred@example.org
... * http://bazaar.launchpad.net/%7ename12/firefox/foo
... * http://somewhere.in/time?track=[02]#wasted-years
... '''
>>> for uri in find_uris_in_text(text):
... print(uri)
http://localhost/a/b
http://launchpad.net/
mailto:joe@example.com
xmpp:fred@example.org
http://bazaar.launchpad.net/~name12/firefox/foo
http://somewhere.in/time?track=[02]#wasted-years
=================
NEWS for lazr.uri
=================
1.0.6 (2021-09-13)
==================
- Adjust versioning strategy to avoid importing pkg_resources, which is slow
in large environments.
1.0.5 (2020-06-29)
==================
- Add an explicit __hash__ method to lazr.uri.URI.
1.0.4 (2020-06-12)
==================
- Install version.txt with package_data (Stefano Rivera,
https://bugs.launchpad.net/lazr.uri/+bug/918660).
- Switch from buildout to tox.
1.0.3 (2012-01-18)
==================
- Add compatibility with Python 3 (Thomas Kluyver).
1.0.1 (2009-06-01)
==================
- Eliminate dependency on setuptools_bzr so sdists do not bring bzr ini, among
others.
1.0 (2009-03-23)
================
- Initial release on PyPI
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/x-rst
Provides-Extra: docs
Provides-Extra: test
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1326908693.0
lazr.uri-1.0.6/README.rst 0000644 0001750 0001750 00000001345 00000000000 016461 0 ustar 00cjwatson cjwatson 0000000 0000000 A self-contained, easily reusable library for parsing, manipulating,
and generating URIs.
..
This file is part of lazr.uri.
lazr.uri is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, version 3 of the License.
lazr.uri is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with lazr.uri. If not, see .
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.599321
lazr.uri-1.0.6/setup.cfg 0000644 0001750 0001750 00000000046 00000000000 016610 0 ustar 00cjwatson cjwatson 0000000 0000000 [egg_info]
tag_build =
tag_date = 0
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547683.0
lazr.uri-1.0.6/setup.py 0000755 0001750 0001750 00000005323 00000000000 016507 0 ustar 00cjwatson cjwatson 0000000 0000000 #!/usr/bin/env python
# Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
from setuptools import setup, find_packages
# generic helpers primarily for the long_description
def generate(*docname_or_string):
marker = '.. pypi description ends here'
res = []
for value in docname_or_string:
if value.endswith('.rst'):
with open(value) as f:
value = f.read()
idx = value.find(marker)
if idx >= 0:
value = value[:idx]
res.append(value)
if not value.endswith('\n'):
res.append('')
return '\n'.join(res)
# end generic helpers
setup(
name='lazr.uri',
version='1.0.6',
namespace_packages=['lazr'],
packages=find_packages('src'),
package_dir={'':'src'},
include_package_data=True,
zip_safe=False,
maintainer='LAZR Developers',
maintainer_email='lazr-developers@lists.launchpad.net',
download_url= 'https://launchpad.net/lazr.uri/+download',
description=open('README.rst').readline().strip(),
long_description=generate(
'src/lazr/uri/docs/index.rst',
'NEWS.rst'),
long_description_content_type='text/x-rst',
license='LGPL v3',
install_requires=[
'importlib-metadata; python_version < "3.8"',
'setuptools',
],
url='https://launchpad.net/lazr.uri',
classifiers=[
"Development Status :: 5 - Production/Stable",
"Intended Audience :: Developers",
"License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)",
"Operating System :: OS Independent",
"Programming Language :: Python",
"Programming Language :: Python :: 2",
"Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.5",
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Programming Language :: Python :: 3.8",
],
extras_require=dict(
docs=['Sphinx'],
test=['zope.testrunner'],
),
test_suite='lazr.uri.tests',
)
././@PaxHeader 0000000 0000000 0000000 00000000034 00000000000 011452 x ustar 00 0000000 0000000 28 mtime=1631547713.5913208
lazr.uri-1.0.6/src/ 0000755 0001750 0001750 00000000000 00000000000 015556 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.595321
lazr.uri-1.0.6/src/lazr/ 0000755 0001750 0001750 00000000000 00000000000 016526 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1326800465.0
lazr.uri-1.0.6/src/lazr/__init__.py 0000644 0001750 0001750 00000001567 00000000000 020650 0 ustar 00cjwatson cjwatson 0000000 0000000 # Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri.
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
# this is a namespace package
try:
import pkg_resources
pkg_resources.declare_namespace(__name__)
except ImportError:
import pkgutil
__path__ = pkgutil.extend_path(__path__, __name__)
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.595321
lazr.uri-1.0.6/src/lazr/uri/ 0000755 0001750 0001750 00000000000 00000000000 017325 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547683.0
lazr.uri-1.0.6/src/lazr/uri/__init__.py 0000644 0001750 0001750 00000002406 00000000000 021440 0 ustar 00cjwatson cjwatson 0000000 0000000 # Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
"""Functions for working with generic syntax URIs."""
try:
import importlib.metadata as importlib_metadata
except ImportError:
import importlib_metadata
__version__ = importlib_metadata.version("lazr.uri")
# Re-export in such a way that __version__ can still be imported if
# dependencies are not yet available.
try:
# While we generally frown on "*" imports, this, combined with the fact we
# only test code from this module, means that we can verify what has been
# exported.
from lazr.uri._uri import *
from lazr.uri._uri import __all__
except ImportError:
pass
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1593429789.0
lazr.uri-1.0.6/src/lazr/uri/_uri.py 0000644 0001750 0001750 00000045405 00000000000 020645 0 ustar 00cjwatson cjwatson 0000000 0000000 # Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
"""Functions for working with generic syntax URIs."""
__metaclass__ = type
__all__ = [
'URI',
'InvalidURIError',
'find_uris_in_text',
'possible_uri_re',
'merge',
'remove_dot_segments',
]
import re
try:
unicode
except NameError:
unicode = str
# Default port numbers for different URI schemes
# The registered URI schemes comes from
# http://www.iana.org/assignments/uri-schemes.html
# The default ports come from the relevant RFCs
_default_port = {
# Official schemes
'acap': '674',
'dav': '80',
'dict': '2628',
'dns': '53',
'ftp': '21',
'go': '1096',
'gopher': '70',
'h323': '1720',
'http': '80',
'https': '443',
'imap': '143',
'ipp': '631',
'iris.beep': '702',
'ldap': '389',
'mtqp': '1038',
'mupdate': '3905',
'nfs': '2049',
'nntp': '119',
'pop': '110',
'rtsp': '554',
'sip': '5060',
'sips': '5061',
'snmp': '161',
'soap.beep': '605',
'soap.beeps': '605',
'telnet': '23',
'tftp': '69',
'tip': '3372',
'vemmi': '575',
'xmlrpc.beep': '602',
'xmlrpc.beeps': '602',
'z39.50r': '210',
'z39.50s': '210',
# Historical schemes
'prospero': '1525',
'wais': '210',
# Common but unregistered schemes
'bzr+http': '80',
'bzr+ssh': '22',
'irc': '6667',
'sftp': '22',
'ssh': '22',
'svn': '3690',
'svn+ssh': '22',
}
# Regular expressions adapted from the ABNF in the RFC
scheme_re = r"(?P[a-z][-a-z0-9+.]*)"
userinfo_re = r"(?P(?:[-a-z0-9._~!$&\'()*+,;=:]|%[0-9a-f]{2})*)"
# The following regular expression will match some IP address style
# host names that the RFC would not (e.g. leading zeros on the
# components), but is signficantly simpler.
host_re = (r"(?P[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}|"
r"(?:[-a-z0-9._~!$&\'()*+,;=]|%[0-9a-f]{2})*|"
r"\[[0-9a-z:.]+\])")
port_re = r"(?P[0-9]*)"
authority_re = r"(?P(?:%s@)?%s(?::%s)?)" % (
userinfo_re, host_re, port_re)
path_abempty_re = r"(?:/(?:[-a-z0-9._~!$&\'()*+,;=:@]|%[0-9a-f]{2})*)*"
path_noscheme_re = (r"(?:[-a-z0-9._~!$&\'()*+,;=@]|%[0-9a-f]{2})+"
r"(?:/(?:[-a-z0-9._~!$&\'()*+,;=:@]|%[0-9a-f]{2})*)*")
path_rootless_re = (r"(?:[-a-z0-9._~!$&\'()*+,;=:@]|%[0-9a-f]{2})+"
r"(?:/(?:[-a-z0-9._~!$&\'()*+,;=:@]|%[0-9a-f]{2})*)*")
path_absolute_re = r"/(?:%s)?" % path_rootless_re
path_empty_re = r""
hier_part_re = r"(?P//%s%s|%s|%s|%s)" % (
authority_re, path_abempty_re, path_absolute_re, path_rootless_re,
path_empty_re)
relative_part_re = r"(?P//%s%s|%s|%s|%s)" % (
authority_re, path_abempty_re, path_absolute_re, path_noscheme_re,
path_empty_re)
# Additionally we also permit square braces in the query portion to
# accomodate real-world URIs.
query_re = r"(?P(?:[-a-z0-9._~!$&\'()*+,;=:@/?\[\]]|%[0-9a-f]{2})*)"
fragment_re = r"(?P(?:[-a-z0-9._~!$&\'()*+,;=:@/?]|%[0-9a-f]{2})*)"
uri_re = r"%s:%s(?:\?%s)?(?:#%s)?$" % (
scheme_re, hier_part_re, query_re, fragment_re)
relative_ref_re = r"%s(?:\?%s)?(?:#%s)?$" % (
relative_part_re, query_re, fragment_re)
uri_pat = re.compile(uri_re, re.IGNORECASE)
relative_ref_pat = re.compile(relative_ref_re, re.IGNORECASE)
def merge(basepath, relpath, has_authority):
"""Merge two URI path components into a single path component.
Follows rules specified in Section 5.2.3 of RFC 3986.
The algorithm in the RFC treats the empty basepath edge case
differently for URIs with and without an authority section, which
is why the third argument is necessary.
"""
if has_authority and basepath == '':
return '/' + relpath
slash = basepath.rfind('/')
return basepath[:slash+1] + relpath
def remove_dot_segments(path):
"""Remove '.' and '..' segments from a URI path.
Follows the rules specified in Section 5.2.4 of RFC 3986.
"""
output = []
while path:
if path.startswith('../'):
path = path[3:]
elif path.startswith('./'):
path = path[2:]
elif path.startswith('/./') or path == '/.':
path = '/' + path[3:]
elif path.startswith('/../') or path == '/..':
path = '/' + path[4:]
if len(output) > 0:
del output[-1]
elif path in ['.', '..']:
path = ''
else:
if path.startswith('/'):
slash = path.find('/', 1)
else:
slash = path.find('/')
if slash < 0:
slash = len(path)
output.append(path[:slash])
path = path[slash:]
return ''.join(output)
def normalise_unreserved(string):
"""Return a version of 's' where no unreserved characters are encoded.
Unreserved characters are defined in Section 2.3 of RFC 3986.
Percent encoded sequences are normalised to upper case.
"""
result = string.split('%')
unreserved = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ'
'abcdefghijklmnopqrstuvwxyz'
'0123456789-._~')
for index, item in enumerate(result):
if index == 0:
continue
try:
ch = int(item[:2], 16)
except ValueError:
continue
if chr(ch) in unreserved:
result[index] = chr(ch) + item[2:]
else:
result[index] = '%%%02X%s' % (ch, item[2:])
return ''.join(result)
class InvalidURIError(Exception):
"""Invalid URI"""
class URI:
"""A class that represents a URI.
This class can represent arbitrary URIs that conform to the
generic syntax described in RFC 3986.
"""
def __init__(self, uri=None, scheme=None, userinfo=None, host=None,
port=None, path=None, query=None, fragment=None):
"""Create a URI instance.
Can be called with either a string URI or the component parts
of the URI as keyword arguments.
In either case, all arguments are expected to be appropriately
URI encoded.
"""
assert (uri is not None and scheme is None and userinfo is None and
host is None and port is None and path is None and
query is None and fragment is None) or uri is None, (
"URI() must be called with a single string argument or "
"with URI components given as keyword arguments.")
if uri is not None:
if isinstance(uri, unicode):
try:
uri.encode('ASCII')
except UnicodeEncodeError:
raise InvalidURIError(
'URIs must consist of ASCII characters')
match = uri_pat.match(uri)
if match is None:
raise InvalidURIError('"%s" is not a valid URI' % uri)
self.scheme = match.group('scheme')
self.userinfo = match.group('userinfo')
self.host = match.group('host')
self.port = match.group('port')
hierpart = match.group('hierpart')
authority = match.group('authority')
if authority is None:
self.path = hierpart
else:
# Skip past the //authority part
self.path = hierpart[2+len(authority):]
self.query = match.group('query')
self.fragment = match.group('fragment')
else:
if scheme is None:
raise InvalidURIError('URIs must have a scheme')
if host is None and (userinfo is not None or port is not None):
raise InvalidURIError(
'host must be given if userinfo or port are')
if path is None:
raise InvalidURIError('URIs must have a path')
self.scheme = scheme
self.userinfo = userinfo
self.host = host
self.port = port
self.path = path
self.query = query
self.fragment = fragment
self._normalise()
if (self.scheme in ['http', 'https', 'ftp', 'gopher', 'telnet',
'imap', 'mms', 'rtsp', 'svn', 'svn+ssh',
'bzr', 'bzr+http', 'bzr+ssh'] and
not self.host):
raise InvalidURIError('%s URIs must have a host name' %
self.scheme)
def _normalise(self):
"""Perform normalisation of URI components."""
self.scheme = self.scheme.lower()
if self.userinfo is not None:
self.userinfo = normalise_unreserved(self.userinfo)
if self.host is not None:
self.host = normalise_unreserved(self.host.lower())
if self.port == '':
self.port = None
elif self.port is not None:
if self.port == _default_port.get(self.scheme):
self.port = None
if self.host is not None and self.path == '':
self.path = '/'
self.path = normalise_unreserved(remove_dot_segments(self.path))
if self.query is not None:
self.query = normalise_unreserved(self.query)
if self.fragment is not None:
self.fragment = normalise_unreserved(self.fragment)
@property
def authority(self):
"""The authority part of the URI"""
if self.host is None:
return None
authority = self.host
if self.userinfo is not None:
authority = '%s@%s' % (self.userinfo, authority)
if self.port is not None:
authority = '%s:%s' % (authority, self.port)
return authority
@property
def hier_part(self):
"""The hierarchical part of the URI"""
authority = self.authority
if authority is None:
return self.path
else:
return '//%s%s' % (authority, self.path)
def __str__(self):
uri = '%s:%s' % (self.scheme, self.hier_part)
if self.query is not None:
uri += '?%s' % self.query
if self.fragment is not None:
uri += '#%s' % self.fragment
return uri
def __repr__(self):
return '%s(%r)' % (self.__class__.__name__, str(self))
def __eq__(self, other):
if isinstance(other, self.__class__):
return (self.scheme == other.scheme and
self.authority == other.authority and
self.path == other.path and
self.query == other.query and
self.fragment == other.fragment)
else:
return NotImplemented
def __ne__(self, other):
equal = self.__eq__(other)
if equal == NotImplemented:
return NotImplemented
else:
return not equal
def __hash__(self):
return hash((
self.scheme, self.authority, self.path, self.query, self.fragment))
def replace(self, **parts):
"""Replace one or more parts of the URI, returning the result."""
if not parts:
return self
baseparts = dict(
scheme=self.scheme,
userinfo=self.userinfo,
host=self.host,
port=self.port,
path=self.path,
query=self.query,
fragment=self.fragment)
baseparts.update(parts)
return self.__class__(**baseparts)
def resolve(self, reference):
"""Resolve the given URI reference relative to this URI.
Uses the rules from Section 5.2 of RFC 3986 to resolve the new
URI.
"""
# If the reference is a full URI, then return it as is.
try:
return self.__class__(reference)
except InvalidURIError:
pass
match = relative_ref_pat.match(reference)
if match is None:
raise InvalidURIError("Invalid relative reference")
parts = dict(scheme=self.scheme)
authority = match.group('authority')
if authority is not None:
parts['userinfo'] = match.group('userinfo')
parts['host'] = match.group('host')
parts['port'] = match.group('port')
# Skip over the //authority part
parts['path'] = remove_dot_segments(
match.group('relativepart')[2+len(authority):])
parts['query'] = match.group('query')
else:
path = match.group('relativepart')
query = match.group('query')
if path == '':
parts['path'] = self.path
if query is not None:
parts['query'] = query
else:
parts['query'] = self.query
else:
if path.startswith('/'):
parts['path'] = remove_dot_segments(path)
else:
parts['path'] = merge(self.path, path,
has_authority=self.host is not None)
parts['path'] = remove_dot_segments(parts['path'])
parts['query'] = query
parts['userinfo'] = self.userinfo
parts['host'] = self.host
parts['port'] = self.port
parts['fragment'] = match.group('fragment')
return self.__class__(**parts)
def append(self, path):
"""Append the given path to this URI.
The path must not start with a slash, but a slash is added to
base URI (before appending the path), in case it doesn't end
with a slash.
"""
assert not path.startswith('/')
return self.ensureSlash().resolve(path)
def contains(self, other):
"""Returns True if the URI 'other' is contained by this one."""
if (self.scheme != other.scheme or
self.authority != other.authority):
return False
if self.path == other.path:
return True
basepath = self.path
if not basepath.endswith('/'):
basepath += '/'
otherpath = other.path
if not otherpath.endswith('/'):
otherpath += '/'
return otherpath.startswith(basepath)
def underDomain(self, domain):
"""Return True if the given domain name a parent of the URL's host."""
if len(domain) == 0:
return True
our_segments = self.host.split('.')
domain_segments = domain.split('.')
return our_segments[-len(domain_segments):] == domain_segments
def ensureSlash(self):
"""Return a URI with the path normalised to end with a slash."""
if self.path.endswith('/'):
return self
else:
return self.replace(path=self.path + '/')
def ensureNoSlash(self):
"""Return a URI with the path normalised to not end with a slash."""
if self.path.endswith('/'):
return self.replace(path=self.path.rstrip('/'))
else:
return self
# Regular expression for finding URIs in a body of text:
#
# From RFC 3986 ABNF for URIs:
#
# URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
# hier-part = "//" authority path-abempty
# / path-absolute
# / path-rootless
# / path-empty
#
# authority = [ userinfo "@" ] host [ ":" port ]
# userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
# host = IP-literal / IPv4address / reg-name
# reg-name = *( unreserved / pct-encoded / sub-delims )
# port = *DIGIT
#
# path-abempty = *( "/" segment )
# path-absolute = "/" [ segment-nz *( "/" segment ) ]
# path-rootless = segment-nz *( "/" segment )
# path-empty = 0
#
# segment = *pchar
# segment-nz = 1*pchar
# pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
#
# query = *( pchar / "/" / "?" )
# fragment = *( pchar / "/" / "?" )
#
# unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
# pct-encoded = "%" HEXDIG HEXDIG
# sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
# / "*" / "+" / "," / ";" / "="
#
# We only match a set of known scheme names. We don't handle
# IP-literal either.
#
# We will simplify "unreserved / pct-encoded / sub-delims" as the
# following regular expression:
# [-a-zA-Z0-9._~%!$&'()*+,;=]
#
# We also require that the path-rootless form not begin with a
# colon to avoid matching strings like "http::foo" (to avoid bug
# #40255).
#
# The path-empty pattern is not matched either, due to false
# positives.
#
# Some allowed URI punctuation characters will be trimmed if they
# appear at the end of the URI since they may be incidental in the
# flow of the text.
#
# apport has at one time produced query strings containing sqaure
# braces (that are not percent-encoded). In RFC 2986 they seem to be
# allowed by section 2.2 "Reserved Characters", yet section 3.4
# "Query" appears to provide a strict definition of the query string
# that would forbid square braces. Either way, links with
# non-percent-encoded square braces are being used on Launchpad so
# it's probably best to accomodate them.
possible_uri_re = r'''
\b
(?:about|gopher|http|https|sftp|news|ftp|mailto|file|irc|jabber|xmpp)
:
(?:
(?:
# "//" authority path-abempty
//
(?: # userinfo
[%(unreserved)s:]*
@
)?
(?: # host
\d+\.\d+\.\d+\.\d+ |
[%(unreserved)s]*
)
(?: # port
: \d*
)?
(?: / [%(unreserved)s:@]* )*
) | (?:
# path-absolute
/
(?: [%(unreserved)s:@]+
(?: / [%(unreserved)s:@]* )* )?
) | (?:
# path-rootless
[%(unreserved)s@]
[%(unreserved)s:@]*
(?: / [%(unreserved)s:@]* )*
)
)
(?: # query
\?
[%(unreserved)s:@/\?\[\]]*
)?
(?: # fragment
\#
[%(unreserved)s:@/\?]*
)?
''' % {'unreserved': "-a-zA-Z0-9._~%!$&'()*+,;="}
possible_uri_pat = re.compile(possible_uri_re, re.IGNORECASE | re.VERBOSE)
uri_trailers_pat = re.compile(r'([,.?:);>]+)$')
def find_uris_in_text(text):
"""Scan a block of text for URIs, and yield the ones found."""
for match in possible_uri_pat.finditer(text):
uri_string = match.group()
# remove characters from end of URI that are not likely to be
# part of the URI.
uri_string = uri_trailers_pat.sub('', uri_string)
try:
uri = URI(uri_string)
except InvalidURIError:
continue
yield uri
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1326800465.0
lazr.uri-1.0.6/src/lazr/uri/configure.zcml 0000644 0001750 0001750 00000000720 00000000000 022174 0 ustar 00cjwatson cjwatson 0000000 0000000
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.595321
lazr.uri-1.0.6/src/lazr/uri/docs/ 0000755 0001750 0001750 00000000000 00000000000 020255 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1591959939.0
lazr.uri-1.0.6/src/lazr/uri/docs/Makefile 0000644 0001750 0001750 00000001134 00000000000 021714 0 ustar 00cjwatson cjwatson 0000000 0000000 # Minimal makefile for Sphinx documentation
#
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
SPHINXPROJ = lazruri
SOURCEDIR = .
BUILDDIR = _build
# Put it first so that "make" without argument is like "make help".
help:
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
.PHONY: help Makefile
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547700.0
lazr.uri-1.0.6/src/lazr/uri/docs/NEWS.rst 0000644 0001750 0001750 00000001356 00000000000 021570 0 ustar 00cjwatson cjwatson 0000000 0000000 =================
NEWS for lazr.uri
=================
1.0.6 (2021-09-13)
==================
- Adjust versioning strategy to avoid importing pkg_resources, which is slow
in large environments.
1.0.5 (2020-06-29)
==================
- Add an explicit __hash__ method to lazr.uri.URI.
1.0.4 (2020-06-12)
==================
- Install version.txt with package_data (Stefano Rivera,
https://bugs.launchpad.net/lazr.uri/+bug/918660).
- Switch from buildout to tox.
1.0.3 (2012-01-18)
==================
- Add compatibility with Python 3 (Thomas Kluyver).
1.0.1 (2009-06-01)
==================
- Eliminate dependency on setuptools_bzr so sdists do not bring bzr ini, among
others.
1.0 (2009-03-23)
================
- Initial release on PyPI
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1591959939.0
lazr.uri-1.0.6/src/lazr/uri/docs/index.rst 0000644 0001750 0001750 00000007665 00000000000 022134 0 ustar 00cjwatson cjwatson 0000000 0000000 ..
This file is part of lazr.uri.
lazr.uri is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, version 3 of the License.
lazr.uri is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with lazr.uri. If not, see .
lazr.uri
********
The lazr.uri package includes code for parsing and dealing with URIs.
>>> import lazr.uri
>>> print('VERSION:', lazr.uri.__version__)
VERSION: ...
=============
The URI class
=============
>>> from lazr.uri import URI
>>> uri1 = URI('http://localhost/foo/bar?123')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
These next two are equivalent, so the answer should be True, even through
the "outside" one is shorter than the "inside" one.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
True
The next two are exactly the same. We consider a url to be inside itself.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/')
>>> uri1.contains(uri2)
True
In the next case, the string of url2 starts with the string of url1. But,
because url2 continues within the same path step, url2 is not inside url1.
>>> uri1 = URI('http://localhost/foo/ba')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
False
Here, url2 is url1 plus an extra path step. So, url2 is inside url1.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
Once the URI is parsed, its parts are accessible.
>>> uri = URI('https://fish.tree:8666/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'fish.tree'
>>> uri.port
'8666'
>>> uri.authority
'fish.tree:8666'
>>> uri.path
'/blee/blah'
>>> uri = URI('https://localhost/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'localhost'
>>> uri.port is None
True
>>> uri.authority
'localhost'
>>> uri.path
'/blee/blah'
The grammar from RFC 3986 does not allow for square brackets in the
query component, but Section 3.4 does say how such delimeter
characters should be handled if found in the component.
>>> uri = URI('http://www.apple.com/store?delivery=[slow]#horse+cart')
>>> uri.scheme
'http'
>>> uri.host
'www.apple.com'
>>> uri.port is None
True
>>> uri.path
'/store'
>>> uri.query
'delivery=[slow]'
>>> uri.fragment
'horse+cart'
====================
Finding URIs in Text
====================
lazr.uri also knows how to retrieve a list of URIs from a block of
text. This is intended for uses like finding bug tracker URIs or
similar.
The find_uris_in_text() function returns an iterator that yields URI
objects for each URI found in the text. Note that the returned URIs
have been canonicalised by the URI class:
>>> from lazr.uri import find_uris_in_text
>>> text = '''
... A list of URIs:
... * http://localhost/a/b
... * http://launchpad.net
... * MAILTO:joe@example.com
... * xmpp:fred@example.org
... * http://bazaar.launchpad.net/%7ename12/firefox/foo
... * http://somewhere.in/time?track=[02]#wasted-years
... '''
>>> for uri in find_uris_in_text(text):
... print(uri)
http://localhost/a/b
http://launchpad.net/
mailto:joe@example.com
xmpp:fred@example.org
http://bazaar.launchpad.net/~name12/firefox/foo
http://somewhere.in/time?track=[02]#wasted-years
.. pypi description ends here
.. toctree::
:glob:
NEWS
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.595321
lazr.uri-1.0.6/src/lazr/uri/tests/ 0000755 0001750 0001750 00000000000 00000000000 020467 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1326800465.0
lazr.uri-1.0.6/src/lazr/uri/tests/__init__.py 0000644 0001750 0001750 00000001302 00000000000 022574 0 ustar 00cjwatson cjwatson 0000000 0000000 # Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
"""Test package."""
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1591959939.0
lazr.uri-1.0.6/src/lazr/uri/tests/test_docs.py 0000644 0001750 0001750 00000003476 00000000000 023042 0 ustar 00cjwatson cjwatson 0000000 0000000 # Copyright 2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
"""Test harness for doctests."""
from __future__ import print_function
__metaclass__ = type
__all__ = [
'load_tests',
]
import atexit
import doctest
import os
from pkg_resources import (
cleanup_resources,
resource_exists,
resource_filename,
resource_listdir,
)
DOCTEST_FLAGS = (
doctest.ELLIPSIS |
doctest.NORMALIZE_WHITESPACE |
doctest.REPORT_NDIFF)
def find_doctests(suffix):
"""Find doctests matching a certain suffix."""
doctest_files = []
# Match doctests against the suffix.
if resource_exists('lazr.uri', 'docs'):
for name in resource_listdir('lazr.uri', 'docs'):
if name.endswith(suffix):
doctest_files.append(
os.path.abspath(
resource_filename('lazr.uri', 'docs/%s' % name)))
return doctest_files
def load_tests(loader, tests, pattern):
"""Load all the doctests."""
atexit.register(cleanup_resources)
tests.addTest(doctest.DocFileSuite(
*find_doctests('.rst'),
module_relative=False, optionflags=DOCTEST_FLAGS,
globs={"print_function": print_function}))
return tests
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1593429789.0
lazr.uri-1.0.6/src/lazr/uri/tests/test_uri.py 0000644 0001750 0001750 00000017350 00000000000 022705 0 ustar 00cjwatson cjwatson 0000000 0000000 # coding: utf-8
# Copyright 2006-2009 Canonical Ltd. All rights reserved.
#
# This file is part of lazr.uri
#
# lazr.uri is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# lazr.uri is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with lazr.uri. If not, see .
"""Unit tests."""
__metaclass__ = type
__all__ = [
'test_suite',
]
from collections import defaultdict
import unittest
from lazr.uri import (
InvalidURIError, URI, find_uris_in_text, merge, remove_dot_segments)
class URITestCase(unittest.TestCase):
def test_normalisation(self):
# URI normalisation examples from Section 6.2.2 of RFC 3986.
self.assertEqual(str(URI('eXAMPLE://a/./b/../b/%63/%7bfoo%7d')),
'example://a/b/c/%7Bfoo%7D')
self.assertEqual(str(URI('http://www.EXAMPLE.com/')),
'http://www.example.com/')
self.assertEqual(str(URI('http://www.gnome.org/%7ejamesh/')),
'http://www.gnome.org/~jamesh/')
# Port number normalisation, and adding missing slash for URIs
# with authority:
self.assertEqual(str(URI('http://example.com')),
'http://example.com/')
self.assertEqual(str(URI('http://example.com:/')),
'http://example.com/')
self.assertEqual(str(URI('http://example.com:80/')),
'http://example.com/')
def test_hashable(self):
uri_groups = [
['eXAMPLE://a/./b/../b/%63/%7bfoo%7d',
'example://a/b/c/%7Bfoo%7D'],
['http://www.EXAMPLE.com/',
'http://www.example.com/'],
['http://www.gnome.org/%7ejamesh/',
'http://www.gnome.org/~jamesh/'],
['http://example.com',
'http://example.com/',
'http://example.com:/',
'http://example.com:80/'],
]
uri_hashes = defaultdict(list)
for uri_group in uri_groups:
for uri in uri_group:
uri_hashes[hash(URI(uri))].append(uri)
self.assertEqual(len(uri_groups), len(uri_hashes))
for uri_group in uri_groups:
self.assertEqual(
sorted(uri_group),
sorted(uri_hashes[hash(URI(uri_group[0]))]))
def test_invalid_uri(self):
self.assertRaises(InvalidURIError, URI, 'http://€xample.com/')
def test_merge(self):
# Test that the merge() function performs as described in
# Section 5.2.3 of RFC 3986
self.assertEqual(merge('', 'foo', has_authority=True), '/foo')
self.assertEqual(merge('', 'foo', has_authority=False), 'foo')
self.assertEqual(merge('/a/b/c', 'foo', has_authority=True),
'/a/b/foo')
self.assertEqual(merge('/a/b/', 'foo', has_authority=True),
'/a/b/foo')
def test_remove_dot_segments(self):
# remove_dot_segments() examples from Section 5.2.4 of RFC 3986:
self.assertEqual(remove_dot_segments('/a/b/c/./../../g'), '/a/g')
self.assertEqual(remove_dot_segments('mid/content=5/../6'), 'mid/6')
def test_normal_resolution(self):
# Normal URI resolution examples from Section 5.4.1 of RFC 3986:
base = URI('http://a/b/c/d;p?q')
def resolve(relative):
return str(base.resolve(relative))
self.assertEqual(resolve('g:h'), 'g:h')
self.assertEqual(resolve('g'), 'http://a/b/c/g')
self.assertEqual(resolve('./g'), 'http://a/b/c/g')
self.assertEqual(resolve('g/'), 'http://a/b/c/g/')
self.assertEqual(resolve('/g'), 'http://a/g')
# The extra slash here comes from normalisation:
self.assertEqual(resolve('//g'), 'http://g/')
self.assertEqual(resolve('?y'), 'http://a/b/c/d;p?y')
self.assertEqual(resolve('g?y'), 'http://a/b/c/g?y')
self.assertEqual(resolve('#s'), 'http://a/b/c/d;p?q#s')
self.assertEqual(resolve('g#s'), 'http://a/b/c/g#s')
self.assertEqual(resolve('g?y#s'), 'http://a/b/c/g?y#s')
self.assertEqual(resolve(';x'), 'http://a/b/c/;x')
self.assertEqual(resolve('g;x'), 'http://a/b/c/g;x')
self.assertEqual(resolve('g;x?y#s'), 'http://a/b/c/g;x?y#s')
self.assertEqual(resolve(''), 'http://a/b/c/d;p?q')
self.assertEqual(resolve('.'), 'http://a/b/c/')
self.assertEqual(resolve('./'), 'http://a/b/c/')
self.assertEqual(resolve('..'), 'http://a/b/')
self.assertEqual(resolve('../'), 'http://a/b/')
self.assertEqual(resolve('../g'), 'http://a/b/g')
self.assertEqual(resolve('../..'), 'http://a/')
self.assertEqual(resolve('../../'), 'http://a/')
self.assertEqual(resolve('../../g'), 'http://a/g')
def test_abnormal_resolution(self):
# Abnormal URI resolution examples from Section 5.4.2 of RFC 3986:
base = URI('http://a/b/c/d;p?q')
def resolve(relative):
return str(base.resolve(relative))
self.assertEqual(resolve('../../../g'), 'http://a/g')
self.assertEqual(resolve('../../../../g'),'http://a/g')
self.assertEqual(resolve('/./g'), 'http://a/g')
self.assertEqual(resolve('/../g'), 'http://a/g')
self.assertEqual(resolve('g.'), 'http://a/b/c/g.')
self.assertEqual(resolve('.g'), 'http://a/b/c/.g')
self.assertEqual(resolve('g..'), 'http://a/b/c/g..')
self.assertEqual(resolve('..g'), 'http://a/b/c/..g')
self.assertEqual(resolve('./../g'), 'http://a/b/g')
self.assertEqual(resolve('./g/.'), 'http://a/b/c/g/')
self.assertEqual(resolve('g/./h'), 'http://a/b/c/g/h')
self.assertEqual(resolve('g/../h'), 'http://a/b/c/h')
self.assertEqual(resolve('g;x=1/./y'), 'http://a/b/c/g;x=1/y')
self.assertEqual(resolve('g;x=1/../y'), 'http://a/b/c/y')
self.assertEqual(resolve('g?y/./x'), 'http://a/b/c/g?y/./x')
self.assertEqual(resolve('g?y/../x'), 'http://a/b/c/g?y/../x')
self.assertEqual(resolve('g#s/./x'), 'http://a/b/c/g#s/./x')
self.assertEqual(resolve('g#s/../x'), 'http://a/b/c/g#s/../x')
# XXX 2009-01-30 jamesh:
# I've disabled this test since we refuse to accept HTTP URIs
# without a hostname component.
#self.assertEqual(resolve('http:g'), 'http:g')
def test_underDomain_matches_subdomain(self):
# URI.underDomain should return True when asked whether the url is
# under one of its parent domains.
uri = URI('http://code.launchpad.dev/foo')
self.assertTrue(uri.underDomain('code.launchpad.dev'))
self.assertTrue(uri.underDomain('launchpad.dev'))
self.assertTrue(uri.underDomain(''))
def test_underDomain_doesnt_match_non_subdomain(self):
# URI.underDomain should return False when asked whether the url is
# under a domain which isn't one of its parents.
uri = URI('http://code.launchpad.dev/foo')
self.assertFalse(uri.underDomain('beta.code.launchpad.dev'))
self.assertFalse(uri.underDomain('google.com'))
self.assertFalse(uri.underDomain('unchpad.dev'))
def additional_tests():
return unittest.TestLoader().loadTestsFromName(__name__)
././@PaxHeader 0000000 0000000 0000000 00000000033 00000000000 011451 x ustar 00 0000000 0000000 27 mtime=1631547713.595321
lazr.uri-1.0.6/src/lazr.uri.egg-info/ 0000755 0001750 0001750 00000000000 00000000000 021016 5 ustar 00cjwatson cjwatson 0000000 0000000 ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/PKG-INFO 0000644 0001750 0001750 00000016035 00000000000 022120 0 ustar 00cjwatson cjwatson 0000000 0000000 Metadata-Version: 2.1
Name: lazr.uri
Version: 1.0.6
Summary: A self-contained, easily reusable library for parsing, manipulating,
Home-page: https://launchpad.net/lazr.uri
Maintainer: LAZR Developers
Maintainer-email: lazr-developers@lists.launchpad.net
License: LGPL v3
Download-URL: https://launchpad.net/lazr.uri/+download
Description: ..
This file is part of lazr.uri.
lazr.uri is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, version 3 of the License.
lazr.uri is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with lazr.uri. If not, see .
lazr.uri
********
The lazr.uri package includes code for parsing and dealing with URIs.
>>> import lazr.uri
>>> print('VERSION:', lazr.uri.__version__)
VERSION: ...
=============
The URI class
=============
>>> from lazr.uri import URI
>>> uri1 = URI('http://localhost/foo/bar?123')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
These next two are equivalent, so the answer should be True, even through
the "outside" one is shorter than the "inside" one.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
True
The next two are exactly the same. We consider a url to be inside itself.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/')
>>> uri1.contains(uri2)
True
In the next case, the string of url2 starts with the string of url1. But,
because url2 continues within the same path step, url2 is not inside url1.
>>> uri1 = URI('http://localhost/foo/ba')
>>> uri2 = URI('http://localhost/foo/bar')
>>> uri1.contains(uri2)
False
Here, url2 is url1 plus an extra path step. So, url2 is inside url1.
>>> uri1 = URI('http://localhost/foo/bar/')
>>> uri2 = URI('http://localhost/foo/bar/baz')
>>> uri1.contains(uri2)
True
Once the URI is parsed, its parts are accessible.
>>> uri = URI('https://fish.tree:8666/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'fish.tree'
>>> uri.port
'8666'
>>> uri.authority
'fish.tree:8666'
>>> uri.path
'/blee/blah'
>>> uri = URI('https://localhost/blee/blah')
>>> uri.scheme
'https'
>>> uri.host
'localhost'
>>> uri.port is None
True
>>> uri.authority
'localhost'
>>> uri.path
'/blee/blah'
The grammar from RFC 3986 does not allow for square brackets in the
query component, but Section 3.4 does say how such delimeter
characters should be handled if found in the component.
>>> uri = URI('http://www.apple.com/store?delivery=[slow]#horse+cart')
>>> uri.scheme
'http'
>>> uri.host
'www.apple.com'
>>> uri.port is None
True
>>> uri.path
'/store'
>>> uri.query
'delivery=[slow]'
>>> uri.fragment
'horse+cart'
====================
Finding URIs in Text
====================
lazr.uri also knows how to retrieve a list of URIs from a block of
text. This is intended for uses like finding bug tracker URIs or
similar.
The find_uris_in_text() function returns an iterator that yields URI
objects for each URI found in the text. Note that the returned URIs
have been canonicalised by the URI class:
>>> from lazr.uri import find_uris_in_text
>>> text = '''
... A list of URIs:
... * http://localhost/a/b
... * http://launchpad.net
... * MAILTO:joe@example.com
... * xmpp:fred@example.org
... * http://bazaar.launchpad.net/%7ename12/firefox/foo
... * http://somewhere.in/time?track=[02]#wasted-years
... '''
>>> for uri in find_uris_in_text(text):
... print(uri)
http://localhost/a/b
http://launchpad.net/
mailto:joe@example.com
xmpp:fred@example.org
http://bazaar.launchpad.net/~name12/firefox/foo
http://somewhere.in/time?track=[02]#wasted-years
=================
NEWS for lazr.uri
=================
1.0.6 (2021-09-13)
==================
- Adjust versioning strategy to avoid importing pkg_resources, which is slow
in large environments.
1.0.5 (2020-06-29)
==================
- Add an explicit __hash__ method to lazr.uri.URI.
1.0.4 (2020-06-12)
==================
- Install version.txt with package_data (Stefano Rivera,
https://bugs.launchpad.net/lazr.uri/+bug/918660).
- Switch from buildout to tox.
1.0.3 (2012-01-18)
==================
- Add compatibility with Python 3 (Thomas Kluyver).
1.0.1 (2009-06-01)
==================
- Eliminate dependency on setuptools_bzr so sdists do not bring bzr ini, among
others.
1.0 (2009-03-23)
================
- Initial release on PyPI
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/x-rst
Provides-Extra: docs
Provides-Extra: test
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/SOURCES.txt 0000644 0001750 0001750 00000001122 00000000000 022676 0 ustar 00cjwatson cjwatson 0000000 0000000 COPYING.txt
HACKING.rst
MANIFEST.in
NEWS.rst
README.rst
setup.py
src/lazr/__init__.py
src/lazr.uri.egg-info/PKG-INFO
src/lazr.uri.egg-info/SOURCES.txt
src/lazr.uri.egg-info/dependency_links.txt
src/lazr.uri.egg-info/namespace_packages.txt
src/lazr.uri.egg-info/not-zip-safe
src/lazr.uri.egg-info/requires.txt
src/lazr.uri.egg-info/top_level.txt
src/lazr/uri/__init__.py
src/lazr/uri/_uri.py
src/lazr/uri/configure.zcml
src/lazr/uri/docs/Makefile
src/lazr/uri/docs/NEWS.rst
src/lazr/uri/docs/index.rst
src/lazr/uri/tests/__init__.py
src/lazr/uri/tests/test_docs.py
src/lazr/uri/tests/test_uri.py ././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/dependency_links.txt 0000644 0001750 0001750 00000000001 00000000000 025064 0 ustar 00cjwatson cjwatson 0000000 0000000
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/namespace_packages.txt 0000644 0001750 0001750 00000000005 00000000000 025344 0 ustar 00cjwatson cjwatson 0000000 0000000 lazr
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1420463711.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/not-zip-safe 0000644 0001750 0001750 00000000001 00000000000 023244 0 ustar 00cjwatson cjwatson 0000000 0000000
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/requires.txt 0000644 0001750 0001750 00000000140 00000000000 023411 0 ustar 00cjwatson cjwatson 0000000 0000000 setuptools
[:python_version < "3.8"]
importlib-metadata
[docs]
Sphinx
[test]
zope.testrunner
././@PaxHeader 0000000 0000000 0000000 00000000026 00000000000 011453 x ustar 00 0000000 0000000 22 mtime=1631547713.0
lazr.uri-1.0.6/src/lazr.uri.egg-info/top_level.txt 0000644 0001750 0001750 00000000005 00000000000 023543 0 ustar 00cjwatson cjwatson 0000000 0000000 lazr