lazr.uri-1.0.3/0000775000175000017500000000000011705552223013517 5ustar gavingavin00000000000000lazr.uri-1.0.3/HACKING.txt0000644000175000017500000000226011233347210015314 0ustar gavingavin00000000000000.. 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 project uses zc.buildout for development. ============ Introduction ============ These are guidelines for hacking on the lazr.uri project. But first, please see the common hacking guidelines at: http://dev.launchpad.net/Hacking 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 lazr.uri-1.0.3/ez_setup.py0000644000175000017500000002246611233347210015731 0ustar gavingavin00000000000000#!python """Bootstrap setuptools installation If you want to use setuptools in your package's setup.py, just include this file in the same directory with it, and add this to the top of your setup.py:: from ez_setup import use_setuptools use_setuptools() If you want to require a specific version of setuptools, set a download mirror, or use an alternate download directory, you can do so by supplying the appropriate options to ``use_setuptools()``. This file can also be run as a script to install or upgrade setuptools. """ import sys DEFAULT_VERSION = "0.6c8" DEFAULT_URL = "http://pypi.python.org/packages/%s/s/setuptools/" % sys.version[:3] md5_data = { 'setuptools-0.6b1-py2.3.egg': '8822caf901250d848b996b7f25c6e6ca', 'setuptools-0.6b1-py2.4.egg': 'b79a8a403e4502fbb85ee3f1941735cb', 'setuptools-0.6b2-py2.3.egg': '5657759d8a6d8fc44070a9d07272d99b', 'setuptools-0.6b2-py2.4.egg': '4996a8d169d2be661fa32a6e52e4f82a', 'setuptools-0.6b3-py2.3.egg': 'bb31c0fc7399a63579975cad9f5a0618', 'setuptools-0.6b3-py2.4.egg': '38a8c6b3d6ecd22247f179f7da669fac', 'setuptools-0.6b4-py2.3.egg': '62045a24ed4e1ebc77fe039aa4e6f7e5', 'setuptools-0.6b4-py2.4.egg': '4cb2a185d228dacffb2d17f103b3b1c4', 'setuptools-0.6c1-py2.3.egg': 'b3f2b5539d65cb7f74ad79127f1a908c', 'setuptools-0.6c1-py2.4.egg': 'b45adeda0667d2d2ffe14009364f2a4b', 'setuptools-0.6c2-py2.3.egg': 'f0064bf6aa2b7d0f3ba0b43f20817c27', 'setuptools-0.6c2-py2.4.egg': '616192eec35f47e8ea16cd6a122b7277', 'setuptools-0.6c3-py2.3.egg': 'f181fa125dfe85a259c9cd6f1d7b78fa', 'setuptools-0.6c3-py2.4.egg': 'e0ed74682c998bfb73bf803a50e7b71e', 'setuptools-0.6c3-py2.5.egg': 'abef16fdd61955514841c7c6bd98965e', 'setuptools-0.6c4-py2.3.egg': 'b0b9131acab32022bfac7f44c5d7971f', 'setuptools-0.6c4-py2.4.egg': '2a1f9656d4fbf3c97bf946c0a124e6e2', 'setuptools-0.6c4-py2.5.egg': '8f5a052e32cdb9c72bcf4b5526f28afc', 'setuptools-0.6c5-py2.3.egg': 'ee9fd80965da04f2f3e6b3576e9d8167', 'setuptools-0.6c5-py2.4.egg': 'afe2adf1c01701ee841761f5bcd8aa64', 'setuptools-0.6c5-py2.5.egg': 'a8d3f61494ccaa8714dfed37bccd3d5d', 'setuptools-0.6c6-py2.3.egg': '35686b78116a668847237b69d549ec20', 'setuptools-0.6c6-py2.4.egg': '3c56af57be3225019260a644430065ab', 'setuptools-0.6c6-py2.5.egg': 'b2f8a7520709a5b34f80946de5f02f53', 'setuptools-0.6c7-py2.3.egg': '209fdf9adc3a615e5115b725658e13e2', 'setuptools-0.6c7-py2.4.egg': '5a8f954807d46a0fb67cf1f26c55a82e', 'setuptools-0.6c7-py2.5.egg': '45d2ad28f9750e7434111fde831e8372', 'setuptools-0.6c8-py2.3.egg': '50759d29b349db8cfd807ba8303f1902', 'setuptools-0.6c8-py2.4.egg': 'cba38d74f7d483c06e9daa6070cce6de', 'setuptools-0.6c8-py2.5.egg': '1721747ee329dc150590a58b3e1ac95b', } import sys, os def _validate_md5(egg_name, data): if egg_name in md5_data: from md5 import md5 digest = md5(data).hexdigest() if digest != md5_data[egg_name]: print >>sys.stderr, ( "md5 validation of %s failed! (Possible download problem?)" % egg_name ) sys.exit(2) return data def use_setuptools( version=DEFAULT_VERSION, download_base=DEFAULT_URL, to_dir=os.curdir, download_delay=15, min_version=None ): """Automatically find/download setuptools and make it available on sys.path `version` should be a valid setuptools version number that is available as an egg for download under the `download_base` URL (which should end with a '/'). `to_dir` is the directory where setuptools will be downloaded, if it is not already available. If `download_delay` is specified, it should be the number of seconds that will be paused before initiating a download, should one be required. If an older version of setuptools is installed, this routine will print a message to ``sys.stderr`` and raise SystemExit in an attempt to abort the calling script. """ # Work around a hack in the ez_setup.py file from simplejson==1.7.3. if min_version: version = min_version was_imported = 'pkg_resources' in sys.modules or 'setuptools' in sys.modules def do_download(): egg = download_setuptools(version, download_base, to_dir, download_delay) sys.path.insert(0, egg) import setuptools; setuptools.bootstrap_install_from = egg try: import pkg_resources except ImportError: return do_download() try: pkg_resources.require("setuptools>="+version); return except pkg_resources.VersionConflict, e: if was_imported: print >>sys.stderr, ( "The required version of setuptools (>=%s) is not available, and\n" "can't be installed while this script is running. Please install\n" " a more recent version first, using 'easy_install -U setuptools'." "\n\n(Currently using %r)" ) % (version, e.args[0]) sys.exit(2) else: del pkg_resources, sys.modules['pkg_resources'] # reload ok return do_download() except pkg_resources.DistributionNotFound: return do_download() def download_setuptools( version=DEFAULT_VERSION, download_base=DEFAULT_URL, to_dir=os.curdir, delay = 15 ): """Download setuptools from a specified location and return its filename `version` should be a valid setuptools version number that is available as an egg for download under the `download_base` URL (which should end with a '/'). `to_dir` is the directory where the egg will be downloaded. `delay` is the number of seconds to pause before an actual download attempt. """ import urllib2, shutil egg_name = "setuptools-%s-py%s.egg" % (version,sys.version[:3]) url = download_base + egg_name saveto = os.path.join(to_dir, egg_name) src = dst = None if not os.path.exists(saveto): # Avoid repeated downloads try: from distutils import log if delay: log.warn(""" --------------------------------------------------------------------------- This script requires setuptools version %s to run (even to display help). I will attempt to download it for you (from %s), but you may need to enable firewall access for this script first. I will start the download in %d seconds. (Note: if this machine does not have network access, please obtain the file %s and place it in this directory before rerunning this script.) ---------------------------------------------------------------------------""", version, download_base, delay, url ); from time import sleep; sleep(delay) log.warn("Downloading %s", url) src = urllib2.urlopen(url) # Read/write all in one block, so we don't create a corrupt file # if the download is interrupted. data = _validate_md5(egg_name, src.read()) dst = open(saveto,"wb"); dst.write(data) finally: if src: src.close() if dst: dst.close() return os.path.realpath(saveto) def main(argv, version=DEFAULT_VERSION): """Install or upgrade setuptools and EasyInstall""" try: import setuptools except ImportError: egg = None try: egg = download_setuptools(version, delay=0) sys.path.insert(0,egg) from setuptools.command.easy_install import main return main(list(argv)+[egg]) # we're done here finally: if egg and os.path.exists(egg): os.unlink(egg) else: if setuptools.__version__ == '0.0.1': print >>sys.stderr, ( "You have an obsolete version of setuptools installed. Please\n" "remove it from your system entirely before rerunning this script." ) sys.exit(2) req = "setuptools>="+version import pkg_resources try: pkg_resources.require(req) except pkg_resources.VersionConflict: try: from setuptools.command.easy_install import main except ImportError: from easy_install import main main(list(argv)+[download_setuptools(delay=0)]) sys.exit(0) # try to force an exit else: if argv: from setuptools.command.easy_install import main main(argv) else: print "Setuptools version",version,"or greater has been installed." print '(Run "ez_setup.py -U setuptools" to reinstall or upgrade.)' def update_md5(filenames): """Update our built-in md5 registry""" import re from md5 import md5 for name in filenames: base = os.path.basename(name) f = open(name,'rb') md5_data[base] = md5(f.read()).hexdigest() f.close() data = [" %r: %r,\n" % it for it in md5_data.items()] data.sort() repl = "".join(data) import inspect srcfile = inspect.getsourcefile(sys.modules[__name__]) f = open(srcfile, 'rb'); src = f.read(); f.close() match = re.search("\nmd5_data = {\n([^}]+)}", src) if not match: print >>sys.stderr, "Internal error!" sys.exit(2) src = src[:match.start(1)] + repl + src[match.end(1):] f = open(srcfile,'w') f.write(src) f.close() if __name__=='__main__': if len(sys.argv)>2 and sys.argv[1]=='--md5update': update_md5(sys.argv[2:]) else: main(sys.argv[1:]) lazr.uri-1.0.3/README.txt0000644000175000017500000000134511705551374015224 0ustar gavingavin00000000000000A 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 . lazr.uri-1.0.3/src/0000775000175000017500000000000011705552223014306 5ustar gavingavin00000000000000lazr.uri-1.0.3/src/lazr/0000775000175000017500000000000011705552223015256 5ustar gavingavin00000000000000lazr.uri-1.0.3/src/lazr/uri/0000775000175000017500000000000011705552223016055 5ustar gavingavin00000000000000lazr.uri-1.0.3/src/lazr/uri/tests/0000775000175000017500000000000011705552223017217 5ustar gavingavin00000000000000lazr.uri-1.0.3/src/lazr/uri/tests/__init__.py0000644000175000017500000000130211233347210021314 0ustar gavingavin00000000000000# 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.""" lazr.uri-1.0.3/src/lazr/uri/tests/test_uri.py0000644000175000017500000001554011705531273021434 0ustar gavingavin00000000000000# 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', ] 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_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__) lazr.uri-1.0.3/src/lazr/uri/tests/test_docs.py0000644000175000017500000000346311705531273021566 0ustar gavingavin00000000000000# 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__ = [ 'additional_tests', ] import atexit import doctest import os import pkg_resources import unittest DOCTEST_FLAGS = ( doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF) def additional_tests(): "Run the doc tests (README.txt and docs/*, if any exist)" doctest_files = [ os.path.abspath( pkg_resources.resource_filename('lazr.uri', 'README.txt'))] if pkg_resources.resource_exists('lazr.uri', 'docs'): for name in pkg_resources.resource_listdir('lazr.uri', 'docs'): if name.endswith('.txt'): doctest_files.append( os.path.abspath( pkg_resources.resource_filename( 'lazr.uri', 'docs/%s' % name))) kwargs = dict( module_relative=False, optionflags=DOCTEST_FLAGS, globs={"print_function": print_function}, ) atexit.register(pkg_resources.cleanup_resources) return unittest.TestSuite(( doctest.DocFileSuite(*doctest_files, **kwargs))) lazr.uri-1.0.3/src/lazr/uri/README.txt0000644000175000017500000000771611705531273017566 0ustar gavingavin00000000000000.. 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 =============== Other Documents =============== .. toctree:: :glob: * docs/* lazr.uri-1.0.3/src/lazr/uri/configure.zcml0000644000175000017500000000072011233347210020714 0ustar gavingavin00000000000000 lazr.uri-1.0.3/src/lazr/uri/NEWS.txt0000644000175000017500000000052111705551313017365 0ustar gavingavin00000000000000================= NEWS for lazr.uri ================= 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 lazr.uri-1.0.3/src/lazr/uri/__init__.py0000644000175000017500000000231611236762510020167 0ustar gavingavin00000000000000# 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.""" import pkg_resources __version__ = pkg_resources.resource_string( "lazr.uri", "version.txt").strip() # 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 lazr.uri-1.0.3/src/lazr/uri/_uri.py0000644000175000017500000004520611705531273017374 0ustar gavingavin00000000000000# 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 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 lazr.uri-1.0.3/src/lazr/uri/version.txt0000644000175000017500000000000611705551313020274 0ustar gavingavin000000000000001.0.3 lazr.uri-1.0.3/src/lazr/__init__.py0000644000175000017500000000156711233347210017370 0ustar gavingavin00000000000000# 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__) lazr.uri-1.0.3/src/lazr.uri.egg-info/0000775000175000017500000000000011705552223017546 5ustar gavingavin00000000000000lazr.uri-1.0.3/src/lazr.uri.egg-info/dependency_links.txt0000664000175000017500000000000111705552223023614 0ustar gavingavin00000000000000 lazr.uri-1.0.3/src/lazr.uri.egg-info/namespace_packages.txt0000664000175000017500000000000511705552223024074 0ustar gavingavin00000000000000lazr lazr.uri-1.0.3/src/lazr.uri.egg-info/requires.txt0000664000175000017500000000005611705552223022147 0ustar gavingavin00000000000000setuptools [docs] Sphinx z3c.recipe.sphinxdoclazr.uri-1.0.3/src/lazr.uri.egg-info/not-zip-safe0000664000175000017500000000000111705531304021771 0ustar gavingavin00000000000000 lazr.uri-1.0.3/src/lazr.uri.egg-info/PKG-INFO0000664000175000017500000001447711705552223020660 0ustar gavingavin00000000000000Metadata-Version: 1.1 Name: lazr.uri Version: 1.0.3 Summary: A self-contained, easily reusable library for parsing, manipulating, Home-page: https://launchpad.net/lazr.uri Author: LAZR Developers Author-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 =============== Other Documents =============== .. toctree:: :glob: * docs/* ================= NEWS for lazr.uri ================= 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 :: 3 lazr.uri-1.0.3/src/lazr.uri.egg-info/top_level.txt0000664000175000017500000000000511705552223022273 0ustar gavingavin00000000000000lazr lazr.uri-1.0.3/src/lazr.uri.egg-info/SOURCES.txt0000664000175000017500000000107611705552223021436 0ustar gavingavin00000000000000COPYING.txt HACKING.txt README.txt ez_setup.py 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/NEWS.txt src/lazr/uri/README.txt src/lazr/uri/__init__.py src/lazr/uri/_uri.py src/lazr/uri/configure.zcml src/lazr/uri/version.txt src/lazr/uri/tests/__init__.py src/lazr/uri/tests/test_docs.py src/lazr/uri/tests/test_uri.pylazr.uri-1.0.3/PKG-INFO0000664000175000017500000001447711705552223014631 0ustar gavingavin00000000000000Metadata-Version: 1.1 Name: lazr.uri Version: 1.0.3 Summary: A self-contained, easily reusable library for parsing, manipulating, Home-page: https://launchpad.net/lazr.uri Author: LAZR Developers Author-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 =============== Other Documents =============== .. toctree:: :glob: * docs/* ================= NEWS for lazr.uri ================= 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 :: 3 lazr.uri-1.0.3/COPYING.txt0000644000175000017500000001672511233347210015373 0ustar gavingavin00000000000000 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. lazr.uri-1.0.3/setup.py0000755000175000017500000000471611705531273015244 0ustar gavingavin00000000000000#!/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 . import sys try: from setuptools import setup, find_packages except ImportError: import ez_setup ez_setup.use_setuptools() from setuptools import setup, find_packages # generic helpers primarily for the long_description def generate(*docname_or_string): res = [] for value in docname_or_string: if value.endswith('.txt'): f = open(value) value = f.read() f.close() res.append(value) if not value.endswith('\n'): res.append('') return '\n'.join(res) # end generic helpers __version__ = open("src/lazr/uri/version.txt").read().strip() setup( name='lazr.uri', version=__version__, 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.txt').readline().strip(), long_description=generate( 'src/lazr/uri/README.txt', 'src/lazr/uri/NEWS.txt'), license='LGPL v3', install_requires=[ '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 :: 3", ], extras_require=dict( docs=['Sphinx', 'z3c.recipe.sphinxdoc'] ), test_suite='lazr.uri.tests', ) lazr.uri-1.0.3/setup.cfg0000664000175000017500000000007311705552223015340 0ustar gavingavin00000000000000[egg_info] tag_build = tag_date = 0 tag_svn_revision = 0