cpython/Lib/urllib/parse.py

978 lines
34 KiB
Python
Raw Normal View History

"""Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
Merged revisions 80605-80609,80642-80646,80651-80652,80674,80684-80686,80748,80852,80854,80870,80872-80873,80907,80915-80916,80951-80952,80976-80977,80985,81038-81040,81042,81053,81070,81104-81105,81114,81125,81245,81285,81402,81463,81516,81562-81563,81567,81593,81635,81680-81681,81684,81801,81888,81931-81933,81939-81942,81963,81984,81991,82120,82188,82264-82267 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r80605 | andrew.kuchling | 2010-04-28 19:22:16 -0500 (Wed, 28 Apr 2010) | 1 line Add various items ........ r80606 | andrew.kuchling | 2010-04-28 20:44:30 -0500 (Wed, 28 Apr 2010) | 6 lines Fix doubled 'the'. Markup fixes to use :exc:, :option: in a few places. (Glitch: unittest.main's -c ends up a link to the Python interpreter's -c option. Should we skip using :option: for that switch, or disable the auto-linking somehow?) ........ r80607 | andrew.kuchling | 2010-04-28 20:45:41 -0500 (Wed, 28 Apr 2010) | 1 line Add various unittest items ........ r80608 | benjamin.peterson | 2010-04-28 22:18:05 -0500 (Wed, 28 Apr 2010) | 1 line update pypy description ........ r80609 | benjamin.peterson | 2010-04-28 22:30:59 -0500 (Wed, 28 Apr 2010) | 1 line update pypy url ........ r80642 | andrew.kuchling | 2010-04-29 19:49:09 -0500 (Thu, 29 Apr 2010) | 1 line Always add space after RFC; reword paragraph ........ r80643 | andrew.kuchling | 2010-04-29 19:52:31 -0500 (Thu, 29 Apr 2010) | 6 lines Reword paragraph to make its meaning clearer. Antoine Pitrou: is my version of the paragraph still correct? R. David Murray: is this more understandable than the previous version? ........ r80644 | andrew.kuchling | 2010-04-29 20:02:15 -0500 (Thu, 29 Apr 2010) | 1 line Fix typos ........ r80645 | andrew.kuchling | 2010-04-29 20:32:47 -0500 (Thu, 29 Apr 2010) | 1 line Markup fix; clarify by adding 'in that order' ........ r80646 | andrew.kuchling | 2010-04-29 20:33:40 -0500 (Thu, 29 Apr 2010) | 1 line Add various items; rearrange unittest section a bit ........ r80651 | andrew.kuchling | 2010-04-30 08:46:55 -0500 (Fri, 30 Apr 2010) | 1 line Minor grammar re-wording ........ r80652 | andrew.kuchling | 2010-04-30 08:47:34 -0500 (Fri, 30 Apr 2010) | 1 line Add item ........ r80674 | andrew.kuchling | 2010-04-30 20:19:16 -0500 (Fri, 30 Apr 2010) | 1 line Add various items ........ r80684 | andrew.kuchling | 2010-05-01 07:05:52 -0500 (Sat, 01 May 2010) | 1 line Minor grammar fix ........ r80685 | andrew.kuchling | 2010-05-01 07:06:51 -0500 (Sat, 01 May 2010) | 1 line Describe memoryview ........ r80686 | antoine.pitrou | 2010-05-01 07:16:39 -0500 (Sat, 01 May 2010) | 4 lines Fix attribution. Travis didn't do much and he did a bad work. (yes, this is a sensitive subject, sorry) ........ r80748 | andrew.kuchling | 2010-05-03 20:24:22 -0500 (Mon, 03 May 2010) | 1 line Add some more items; the urlparse change is added twice ........ r80852 | andrew.kuchling | 2010-05-05 20:09:47 -0500 (Wed, 05 May 2010) | 1 line Reword paragraph; fix filename, which should be pyconfig.h ........ r80854 | andrew.kuchling | 2010-05-05 20:10:56 -0500 (Wed, 05 May 2010) | 1 line Add various items ........ r80870 | andrew.kuchling | 2010-05-06 09:14:09 -0500 (Thu, 06 May 2010) | 1 line Describe ElementTree 1.3; rearrange new-module sections; describe dict views as sets; small edits and items ........ r80872 | andrew.kuchling | 2010-05-06 12:21:59 -0500 (Thu, 06 May 2010) | 1 line Add 2 items; record ideas for two initial sections; clarify wording ........ r80873 | andrew.kuchling | 2010-05-06 12:27:57 -0500 (Thu, 06 May 2010) | 1 line Change section title; point to unittest2 ........ r80907 | andrew.kuchling | 2010-05-06 20:45:14 -0500 (Thu, 06 May 2010) | 1 line Add a new section on the development plan; add an item ........ r80915 | antoine.pitrou | 2010-05-07 05:15:51 -0500 (Fri, 07 May 2010) | 3 lines Fix some markup and a class name. Also, wrap a long line. ........ r80916 | andrew.kuchling | 2010-05-07 06:30:47 -0500 (Fri, 07 May 2010) | 1 line Re-word text ........ r80951 | andrew.kuchling | 2010-05-07 20:15:26 -0500 (Fri, 07 May 2010) | 1 line Add two items ........ r80952 | andrew.kuchling | 2010-05-07 20:35:55 -0500 (Fri, 07 May 2010) | 1 line Get accents correct ........ r80976 | andrew.kuchling | 2010-05-08 08:28:03 -0500 (Sat, 08 May 2010) | 1 line Add logging.dictConfig example; give up on writing a Ttk example ........ r80977 | andrew.kuchling | 2010-05-08 08:29:46 -0500 (Sat, 08 May 2010) | 1 line Markup fixes ........ r80985 | andrew.kuchling | 2010-05-08 10:39:46 -0500 (Sat, 08 May 2010) | 7 lines Write summary of the 2.7 release; rewrite the future section some more; mention PYTHONWARNINGS env. var; tweak some examples for readability. And with this commit, the "What's New" is done... except for a complete read-through to polish the text, and fixing any reported errors, but those tasks can easily wait until after beta2. ........ r81038 | benjamin.peterson | 2010-05-09 16:09:40 -0500 (Sun, 09 May 2010) | 1 line finish clause ........ r81039 | andrew.kuchling | 2010-05-10 09:18:27 -0500 (Mon, 10 May 2010) | 1 line Markup fix; re-word a sentence ........ r81040 | andrew.kuchling | 2010-05-10 09:20:12 -0500 (Mon, 10 May 2010) | 1 line Use title case ........ r81042 | andrew.kuchling | 2010-05-10 10:03:35 -0500 (Mon, 10 May 2010) | 1 line Link to unittest2 article ........ r81053 | florent.xicluna | 2010-05-10 14:59:22 -0500 (Mon, 10 May 2010) | 2 lines Add a link on maketrans(). ........ r81070 | andrew.kuchling | 2010-05-10 18:13:41 -0500 (Mon, 10 May 2010) | 1 line Fix typo ........ r81104 | andrew.kuchling | 2010-05-11 19:38:44 -0500 (Tue, 11 May 2010) | 1 line Revision pass: lots of edits, typo fixes, rearrangements ........ r81105 | andrew.kuchling | 2010-05-11 19:40:47 -0500 (Tue, 11 May 2010) | 1 line Let's call this done ........ r81114 | andrew.kuchling | 2010-05-12 08:56:07 -0500 (Wed, 12 May 2010) | 1 line Grammar fix ........ r81125 | andrew.kuchling | 2010-05-12 13:56:48 -0500 (Wed, 12 May 2010) | 1 line #8696: add documentation for logging.config.dictConfig (PEP 391) ........ r81245 | andrew.kuchling | 2010-05-16 18:31:16 -0500 (Sun, 16 May 2010) | 1 line Add cross-reference to later section ........ r81285 | vinay.sajip | 2010-05-18 03:16:27 -0500 (Tue, 18 May 2010) | 1 line Fixed minor typo in ReST markup. ........ r81402 | vinay.sajip | 2010-05-21 12:41:34 -0500 (Fri, 21 May 2010) | 1 line Updated logging documentation with more dictConfig information. ........ r81463 | georg.brandl | 2010-05-22 03:17:23 -0500 (Sat, 22 May 2010) | 1 line #8785: less confusing description of regex.find*. ........ r81516 | andrew.kuchling | 2010-05-25 08:34:08 -0500 (Tue, 25 May 2010) | 1 line Add three items ........ r81562 | andrew.kuchling | 2010-05-27 08:22:53 -0500 (Thu, 27 May 2010) | 1 line Rewrite wxWidgets section ........ r81563 | andrew.kuchling | 2010-05-27 08:30:09 -0500 (Thu, 27 May 2010) | 1 line Remove top-level 'General Questions' section, pushing up the questions it contains ........ r81567 | andrew.kuchling | 2010-05-27 16:29:59 -0500 (Thu, 27 May 2010) | 1 line Add item ........ r81593 | georg.brandl | 2010-05-29 03:46:18 -0500 (Sat, 29 May 2010) | 1 line #8616: add new turtle demo "nim". ........ r81635 | georg.brandl | 2010-06-01 02:25:23 -0500 (Tue, 01 Jun 2010) | 1 line Put docs for RegexObject.search() before RegexObject.match() to mirror re.search() and re.match() order. ........ r81680 | vinay.sajip | 2010-06-03 17:34:42 -0500 (Thu, 03 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files. ........ r81681 | sean.reifschneider | 2010-06-03 20:51:26 -0500 (Thu, 03 Jun 2010) | 2 lines Issue8810: Clearing up docstring for tzinfo.utcoffset. ........ r81684 | vinay.sajip | 2010-06-04 08:41:02 -0500 (Fri, 04 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files - other cases covered. ........ r81801 | andrew.kuchling | 2010-06-07 08:38:40 -0500 (Mon, 07 Jun 2010) | 1 line #8875: Remove duplicated paragraph ........ r81888 | andrew.kuchling | 2010-06-10 20:54:58 -0500 (Thu, 10 Jun 2010) | 1 line Add a few more items ........ r81931 | georg.brandl | 2010-06-12 01:26:54 -0500 (Sat, 12 Jun 2010) | 1 line Fix punctuation. ........ r81932 | georg.brandl | 2010-06-12 01:28:58 -0500 (Sat, 12 Jun 2010) | 1 line Document that an existing directory raises in mkdir(). ........ r81933 | georg.brandl | 2010-06-12 01:45:33 -0500 (Sat, 12 Jun 2010) | 1 line Update version in README. ........ r81939 | georg.brandl | 2010-06-12 04:45:01 -0500 (Sat, 12 Jun 2010) | 1 line Use newer toctree syntax. ........ r81940 | georg.brandl | 2010-06-12 04:45:28 -0500 (Sat, 12 Jun 2010) | 1 line Add document on how to build. ........ r81941 | georg.brandl | 2010-06-12 04:45:58 -0500 (Sat, 12 Jun 2010) | 1 line Fix gratuitous indentation. ........ r81942 | georg.brandl | 2010-06-12 04:46:03 -0500 (Sat, 12 Jun 2010) | 1 line Update README. ........ r81963 | andrew.kuchling | 2010-06-12 15:00:55 -0500 (Sat, 12 Jun 2010) | 1 line Grammar fix ........ r81984 | georg.brandl | 2010-06-14 10:58:39 -0500 (Mon, 14 Jun 2010) | 1 line #8993: fix reference. ........ r81991 | andrew.kuchling | 2010-06-14 19:38:58 -0500 (Mon, 14 Jun 2010) | 1 line Add another bunch of items ........ r82120 | andrew.kuchling | 2010-06-20 16:45:45 -0500 (Sun, 20 Jun 2010) | 1 line Note that Python 3.x isn't covered; add forward ref. for UTF-8; note error in 2.5 and up ........ r82188 | benjamin.peterson | 2010-06-23 19:02:46 -0500 (Wed, 23 Jun 2010) | 1 line remove reverted changed ........ r82264 | georg.brandl | 2010-06-27 05:47:47 -0500 (Sun, 27 Jun 2010) | 1 line Confusing punctuation. ........ r82265 | georg.brandl | 2010-06-27 05:49:23 -0500 (Sun, 27 Jun 2010) | 1 line Use designated syntax for optional grammar element. ........ r82266 | georg.brandl | 2010-06-27 05:51:44 -0500 (Sun, 27 Jun 2010) | 1 line Fix URL. ........ r82267 | georg.brandl | 2010-06-27 05:55:38 -0500 (Sun, 27 Jun 2010) | 1 line Two typos. ........
2010-06-27 19:32:30 -03:00
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
Merged revisions 80605-80609,80642-80646,80651-80652,80674,80684-80686,80748,80852,80854,80870,80872-80873,80907,80915-80916,80951-80952,80976-80977,80985,81038-81040,81042,81053,81070,81104-81105,81114,81125,81245,81285,81402,81463,81516,81562-81563,81567,81593,81635,81680-81681,81684,81801,81888,81931-81933,81939-81942,81963,81984,81991,82120,82188,82264-82267 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r80605 | andrew.kuchling | 2010-04-28 19:22:16 -0500 (Wed, 28 Apr 2010) | 1 line Add various items ........ r80606 | andrew.kuchling | 2010-04-28 20:44:30 -0500 (Wed, 28 Apr 2010) | 6 lines Fix doubled 'the'. Markup fixes to use :exc:, :option: in a few places. (Glitch: unittest.main's -c ends up a link to the Python interpreter's -c option. Should we skip using :option: for that switch, or disable the auto-linking somehow?) ........ r80607 | andrew.kuchling | 2010-04-28 20:45:41 -0500 (Wed, 28 Apr 2010) | 1 line Add various unittest items ........ r80608 | benjamin.peterson | 2010-04-28 22:18:05 -0500 (Wed, 28 Apr 2010) | 1 line update pypy description ........ r80609 | benjamin.peterson | 2010-04-28 22:30:59 -0500 (Wed, 28 Apr 2010) | 1 line update pypy url ........ r80642 | andrew.kuchling | 2010-04-29 19:49:09 -0500 (Thu, 29 Apr 2010) | 1 line Always add space after RFC; reword paragraph ........ r80643 | andrew.kuchling | 2010-04-29 19:52:31 -0500 (Thu, 29 Apr 2010) | 6 lines Reword paragraph to make its meaning clearer. Antoine Pitrou: is my version of the paragraph still correct? R. David Murray: is this more understandable than the previous version? ........ r80644 | andrew.kuchling | 2010-04-29 20:02:15 -0500 (Thu, 29 Apr 2010) | 1 line Fix typos ........ r80645 | andrew.kuchling | 2010-04-29 20:32:47 -0500 (Thu, 29 Apr 2010) | 1 line Markup fix; clarify by adding 'in that order' ........ r80646 | andrew.kuchling | 2010-04-29 20:33:40 -0500 (Thu, 29 Apr 2010) | 1 line Add various items; rearrange unittest section a bit ........ r80651 | andrew.kuchling | 2010-04-30 08:46:55 -0500 (Fri, 30 Apr 2010) | 1 line Minor grammar re-wording ........ r80652 | andrew.kuchling | 2010-04-30 08:47:34 -0500 (Fri, 30 Apr 2010) | 1 line Add item ........ r80674 | andrew.kuchling | 2010-04-30 20:19:16 -0500 (Fri, 30 Apr 2010) | 1 line Add various items ........ r80684 | andrew.kuchling | 2010-05-01 07:05:52 -0500 (Sat, 01 May 2010) | 1 line Minor grammar fix ........ r80685 | andrew.kuchling | 2010-05-01 07:06:51 -0500 (Sat, 01 May 2010) | 1 line Describe memoryview ........ r80686 | antoine.pitrou | 2010-05-01 07:16:39 -0500 (Sat, 01 May 2010) | 4 lines Fix attribution. Travis didn't do much and he did a bad work. (yes, this is a sensitive subject, sorry) ........ r80748 | andrew.kuchling | 2010-05-03 20:24:22 -0500 (Mon, 03 May 2010) | 1 line Add some more items; the urlparse change is added twice ........ r80852 | andrew.kuchling | 2010-05-05 20:09:47 -0500 (Wed, 05 May 2010) | 1 line Reword paragraph; fix filename, which should be pyconfig.h ........ r80854 | andrew.kuchling | 2010-05-05 20:10:56 -0500 (Wed, 05 May 2010) | 1 line Add various items ........ r80870 | andrew.kuchling | 2010-05-06 09:14:09 -0500 (Thu, 06 May 2010) | 1 line Describe ElementTree 1.3; rearrange new-module sections; describe dict views as sets; small edits and items ........ r80872 | andrew.kuchling | 2010-05-06 12:21:59 -0500 (Thu, 06 May 2010) | 1 line Add 2 items; record ideas for two initial sections; clarify wording ........ r80873 | andrew.kuchling | 2010-05-06 12:27:57 -0500 (Thu, 06 May 2010) | 1 line Change section title; point to unittest2 ........ r80907 | andrew.kuchling | 2010-05-06 20:45:14 -0500 (Thu, 06 May 2010) | 1 line Add a new section on the development plan; add an item ........ r80915 | antoine.pitrou | 2010-05-07 05:15:51 -0500 (Fri, 07 May 2010) | 3 lines Fix some markup and a class name. Also, wrap a long line. ........ r80916 | andrew.kuchling | 2010-05-07 06:30:47 -0500 (Fri, 07 May 2010) | 1 line Re-word text ........ r80951 | andrew.kuchling | 2010-05-07 20:15:26 -0500 (Fri, 07 May 2010) | 1 line Add two items ........ r80952 | andrew.kuchling | 2010-05-07 20:35:55 -0500 (Fri, 07 May 2010) | 1 line Get accents correct ........ r80976 | andrew.kuchling | 2010-05-08 08:28:03 -0500 (Sat, 08 May 2010) | 1 line Add logging.dictConfig example; give up on writing a Ttk example ........ r80977 | andrew.kuchling | 2010-05-08 08:29:46 -0500 (Sat, 08 May 2010) | 1 line Markup fixes ........ r80985 | andrew.kuchling | 2010-05-08 10:39:46 -0500 (Sat, 08 May 2010) | 7 lines Write summary of the 2.7 release; rewrite the future section some more; mention PYTHONWARNINGS env. var; tweak some examples for readability. And with this commit, the "What's New" is done... except for a complete read-through to polish the text, and fixing any reported errors, but those tasks can easily wait until after beta2. ........ r81038 | benjamin.peterson | 2010-05-09 16:09:40 -0500 (Sun, 09 May 2010) | 1 line finish clause ........ r81039 | andrew.kuchling | 2010-05-10 09:18:27 -0500 (Mon, 10 May 2010) | 1 line Markup fix; re-word a sentence ........ r81040 | andrew.kuchling | 2010-05-10 09:20:12 -0500 (Mon, 10 May 2010) | 1 line Use title case ........ r81042 | andrew.kuchling | 2010-05-10 10:03:35 -0500 (Mon, 10 May 2010) | 1 line Link to unittest2 article ........ r81053 | florent.xicluna | 2010-05-10 14:59:22 -0500 (Mon, 10 May 2010) | 2 lines Add a link on maketrans(). ........ r81070 | andrew.kuchling | 2010-05-10 18:13:41 -0500 (Mon, 10 May 2010) | 1 line Fix typo ........ r81104 | andrew.kuchling | 2010-05-11 19:38:44 -0500 (Tue, 11 May 2010) | 1 line Revision pass: lots of edits, typo fixes, rearrangements ........ r81105 | andrew.kuchling | 2010-05-11 19:40:47 -0500 (Tue, 11 May 2010) | 1 line Let's call this done ........ r81114 | andrew.kuchling | 2010-05-12 08:56:07 -0500 (Wed, 12 May 2010) | 1 line Grammar fix ........ r81125 | andrew.kuchling | 2010-05-12 13:56:48 -0500 (Wed, 12 May 2010) | 1 line #8696: add documentation for logging.config.dictConfig (PEP 391) ........ r81245 | andrew.kuchling | 2010-05-16 18:31:16 -0500 (Sun, 16 May 2010) | 1 line Add cross-reference to later section ........ r81285 | vinay.sajip | 2010-05-18 03:16:27 -0500 (Tue, 18 May 2010) | 1 line Fixed minor typo in ReST markup. ........ r81402 | vinay.sajip | 2010-05-21 12:41:34 -0500 (Fri, 21 May 2010) | 1 line Updated logging documentation with more dictConfig information. ........ r81463 | georg.brandl | 2010-05-22 03:17:23 -0500 (Sat, 22 May 2010) | 1 line #8785: less confusing description of regex.find*. ........ r81516 | andrew.kuchling | 2010-05-25 08:34:08 -0500 (Tue, 25 May 2010) | 1 line Add three items ........ r81562 | andrew.kuchling | 2010-05-27 08:22:53 -0500 (Thu, 27 May 2010) | 1 line Rewrite wxWidgets section ........ r81563 | andrew.kuchling | 2010-05-27 08:30:09 -0500 (Thu, 27 May 2010) | 1 line Remove top-level 'General Questions' section, pushing up the questions it contains ........ r81567 | andrew.kuchling | 2010-05-27 16:29:59 -0500 (Thu, 27 May 2010) | 1 line Add item ........ r81593 | georg.brandl | 2010-05-29 03:46:18 -0500 (Sat, 29 May 2010) | 1 line #8616: add new turtle demo "nim". ........ r81635 | georg.brandl | 2010-06-01 02:25:23 -0500 (Tue, 01 Jun 2010) | 1 line Put docs for RegexObject.search() before RegexObject.match() to mirror re.search() and re.match() order. ........ r81680 | vinay.sajip | 2010-06-03 17:34:42 -0500 (Thu, 03 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files. ........ r81681 | sean.reifschneider | 2010-06-03 20:51:26 -0500 (Thu, 03 Jun 2010) | 2 lines Issue8810: Clearing up docstring for tzinfo.utcoffset. ........ r81684 | vinay.sajip | 2010-06-04 08:41:02 -0500 (Fri, 04 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files - other cases covered. ........ r81801 | andrew.kuchling | 2010-06-07 08:38:40 -0500 (Mon, 07 Jun 2010) | 1 line #8875: Remove duplicated paragraph ........ r81888 | andrew.kuchling | 2010-06-10 20:54:58 -0500 (Thu, 10 Jun 2010) | 1 line Add a few more items ........ r81931 | georg.brandl | 2010-06-12 01:26:54 -0500 (Sat, 12 Jun 2010) | 1 line Fix punctuation. ........ r81932 | georg.brandl | 2010-06-12 01:28:58 -0500 (Sat, 12 Jun 2010) | 1 line Document that an existing directory raises in mkdir(). ........ r81933 | georg.brandl | 2010-06-12 01:45:33 -0500 (Sat, 12 Jun 2010) | 1 line Update version in README. ........ r81939 | georg.brandl | 2010-06-12 04:45:01 -0500 (Sat, 12 Jun 2010) | 1 line Use newer toctree syntax. ........ r81940 | georg.brandl | 2010-06-12 04:45:28 -0500 (Sat, 12 Jun 2010) | 1 line Add document on how to build. ........ r81941 | georg.brandl | 2010-06-12 04:45:58 -0500 (Sat, 12 Jun 2010) | 1 line Fix gratuitous indentation. ........ r81942 | georg.brandl | 2010-06-12 04:46:03 -0500 (Sat, 12 Jun 2010) | 1 line Update README. ........ r81963 | andrew.kuchling | 2010-06-12 15:00:55 -0500 (Sat, 12 Jun 2010) | 1 line Grammar fix ........ r81984 | georg.brandl | 2010-06-14 10:58:39 -0500 (Mon, 14 Jun 2010) | 1 line #8993: fix reference. ........ r81991 | andrew.kuchling | 2010-06-14 19:38:58 -0500 (Mon, 14 Jun 2010) | 1 line Add another bunch of items ........ r82120 | andrew.kuchling | 2010-06-20 16:45:45 -0500 (Sun, 20 Jun 2010) | 1 line Note that Python 3.x isn't covered; add forward ref. for UTF-8; note error in 2.5 and up ........ r82188 | benjamin.peterson | 2010-06-23 19:02:46 -0500 (Wed, 23 Jun 2010) | 1 line remove reverted changed ........ r82264 | georg.brandl | 2010-06-27 05:47:47 -0500 (Sun, 27 Jun 2010) | 1 line Confusing punctuation. ........ r82265 | georg.brandl | 2010-06-27 05:49:23 -0500 (Sun, 27 Jun 2010) | 1 line Use designated syntax for optional grammar element. ........ r82266 | georg.brandl | 2010-06-27 05:51:44 -0500 (Sun, 27 Jun 2010) | 1 line Fix URL. ........ r82267 | georg.brandl | 2010-06-27 05:55:38 -0500 (Sun, 27 Jun 2010) | 1 line Two typos. ........
2010-06-27 19:32:30 -03:00
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
Merged revisions 80605-80609,80642-80646,80651-80652,80674,80684-80686,80748,80852,80854,80870,80872-80873,80907,80915-80916,80951-80952,80976-80977,80985,81038-81040,81042,81053,81070,81104-81105,81114,81125,81245,81285,81402,81463,81516,81562-81563,81567,81593,81635,81680-81681,81684,81801,81888,81931-81933,81939-81942,81963,81984,81991,82120,82188,82264-82267 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r80605 | andrew.kuchling | 2010-04-28 19:22:16 -0500 (Wed, 28 Apr 2010) | 1 line Add various items ........ r80606 | andrew.kuchling | 2010-04-28 20:44:30 -0500 (Wed, 28 Apr 2010) | 6 lines Fix doubled 'the'. Markup fixes to use :exc:, :option: in a few places. (Glitch: unittest.main's -c ends up a link to the Python interpreter's -c option. Should we skip using :option: for that switch, or disable the auto-linking somehow?) ........ r80607 | andrew.kuchling | 2010-04-28 20:45:41 -0500 (Wed, 28 Apr 2010) | 1 line Add various unittest items ........ r80608 | benjamin.peterson | 2010-04-28 22:18:05 -0500 (Wed, 28 Apr 2010) | 1 line update pypy description ........ r80609 | benjamin.peterson | 2010-04-28 22:30:59 -0500 (Wed, 28 Apr 2010) | 1 line update pypy url ........ r80642 | andrew.kuchling | 2010-04-29 19:49:09 -0500 (Thu, 29 Apr 2010) | 1 line Always add space after RFC; reword paragraph ........ r80643 | andrew.kuchling | 2010-04-29 19:52:31 -0500 (Thu, 29 Apr 2010) | 6 lines Reword paragraph to make its meaning clearer. Antoine Pitrou: is my version of the paragraph still correct? R. David Murray: is this more understandable than the previous version? ........ r80644 | andrew.kuchling | 2010-04-29 20:02:15 -0500 (Thu, 29 Apr 2010) | 1 line Fix typos ........ r80645 | andrew.kuchling | 2010-04-29 20:32:47 -0500 (Thu, 29 Apr 2010) | 1 line Markup fix; clarify by adding 'in that order' ........ r80646 | andrew.kuchling | 2010-04-29 20:33:40 -0500 (Thu, 29 Apr 2010) | 1 line Add various items; rearrange unittest section a bit ........ r80651 | andrew.kuchling | 2010-04-30 08:46:55 -0500 (Fri, 30 Apr 2010) | 1 line Minor grammar re-wording ........ r80652 | andrew.kuchling | 2010-04-30 08:47:34 -0500 (Fri, 30 Apr 2010) | 1 line Add item ........ r80674 | andrew.kuchling | 2010-04-30 20:19:16 -0500 (Fri, 30 Apr 2010) | 1 line Add various items ........ r80684 | andrew.kuchling | 2010-05-01 07:05:52 -0500 (Sat, 01 May 2010) | 1 line Minor grammar fix ........ r80685 | andrew.kuchling | 2010-05-01 07:06:51 -0500 (Sat, 01 May 2010) | 1 line Describe memoryview ........ r80686 | antoine.pitrou | 2010-05-01 07:16:39 -0500 (Sat, 01 May 2010) | 4 lines Fix attribution. Travis didn't do much and he did a bad work. (yes, this is a sensitive subject, sorry) ........ r80748 | andrew.kuchling | 2010-05-03 20:24:22 -0500 (Mon, 03 May 2010) | 1 line Add some more items; the urlparse change is added twice ........ r80852 | andrew.kuchling | 2010-05-05 20:09:47 -0500 (Wed, 05 May 2010) | 1 line Reword paragraph; fix filename, which should be pyconfig.h ........ r80854 | andrew.kuchling | 2010-05-05 20:10:56 -0500 (Wed, 05 May 2010) | 1 line Add various items ........ r80870 | andrew.kuchling | 2010-05-06 09:14:09 -0500 (Thu, 06 May 2010) | 1 line Describe ElementTree 1.3; rearrange new-module sections; describe dict views as sets; small edits and items ........ r80872 | andrew.kuchling | 2010-05-06 12:21:59 -0500 (Thu, 06 May 2010) | 1 line Add 2 items; record ideas for two initial sections; clarify wording ........ r80873 | andrew.kuchling | 2010-05-06 12:27:57 -0500 (Thu, 06 May 2010) | 1 line Change section title; point to unittest2 ........ r80907 | andrew.kuchling | 2010-05-06 20:45:14 -0500 (Thu, 06 May 2010) | 1 line Add a new section on the development plan; add an item ........ r80915 | antoine.pitrou | 2010-05-07 05:15:51 -0500 (Fri, 07 May 2010) | 3 lines Fix some markup and a class name. Also, wrap a long line. ........ r80916 | andrew.kuchling | 2010-05-07 06:30:47 -0500 (Fri, 07 May 2010) | 1 line Re-word text ........ r80951 | andrew.kuchling | 2010-05-07 20:15:26 -0500 (Fri, 07 May 2010) | 1 line Add two items ........ r80952 | andrew.kuchling | 2010-05-07 20:35:55 -0500 (Fri, 07 May 2010) | 1 line Get accents correct ........ r80976 | andrew.kuchling | 2010-05-08 08:28:03 -0500 (Sat, 08 May 2010) | 1 line Add logging.dictConfig example; give up on writing a Ttk example ........ r80977 | andrew.kuchling | 2010-05-08 08:29:46 -0500 (Sat, 08 May 2010) | 1 line Markup fixes ........ r80985 | andrew.kuchling | 2010-05-08 10:39:46 -0500 (Sat, 08 May 2010) | 7 lines Write summary of the 2.7 release; rewrite the future section some more; mention PYTHONWARNINGS env. var; tweak some examples for readability. And with this commit, the "What's New" is done... except for a complete read-through to polish the text, and fixing any reported errors, but those tasks can easily wait until after beta2. ........ r81038 | benjamin.peterson | 2010-05-09 16:09:40 -0500 (Sun, 09 May 2010) | 1 line finish clause ........ r81039 | andrew.kuchling | 2010-05-10 09:18:27 -0500 (Mon, 10 May 2010) | 1 line Markup fix; re-word a sentence ........ r81040 | andrew.kuchling | 2010-05-10 09:20:12 -0500 (Mon, 10 May 2010) | 1 line Use title case ........ r81042 | andrew.kuchling | 2010-05-10 10:03:35 -0500 (Mon, 10 May 2010) | 1 line Link to unittest2 article ........ r81053 | florent.xicluna | 2010-05-10 14:59:22 -0500 (Mon, 10 May 2010) | 2 lines Add a link on maketrans(). ........ r81070 | andrew.kuchling | 2010-05-10 18:13:41 -0500 (Mon, 10 May 2010) | 1 line Fix typo ........ r81104 | andrew.kuchling | 2010-05-11 19:38:44 -0500 (Tue, 11 May 2010) | 1 line Revision pass: lots of edits, typo fixes, rearrangements ........ r81105 | andrew.kuchling | 2010-05-11 19:40:47 -0500 (Tue, 11 May 2010) | 1 line Let's call this done ........ r81114 | andrew.kuchling | 2010-05-12 08:56:07 -0500 (Wed, 12 May 2010) | 1 line Grammar fix ........ r81125 | andrew.kuchling | 2010-05-12 13:56:48 -0500 (Wed, 12 May 2010) | 1 line #8696: add documentation for logging.config.dictConfig (PEP 391) ........ r81245 | andrew.kuchling | 2010-05-16 18:31:16 -0500 (Sun, 16 May 2010) | 1 line Add cross-reference to later section ........ r81285 | vinay.sajip | 2010-05-18 03:16:27 -0500 (Tue, 18 May 2010) | 1 line Fixed minor typo in ReST markup. ........ r81402 | vinay.sajip | 2010-05-21 12:41:34 -0500 (Fri, 21 May 2010) | 1 line Updated logging documentation with more dictConfig information. ........ r81463 | georg.brandl | 2010-05-22 03:17:23 -0500 (Sat, 22 May 2010) | 1 line #8785: less confusing description of regex.find*. ........ r81516 | andrew.kuchling | 2010-05-25 08:34:08 -0500 (Tue, 25 May 2010) | 1 line Add three items ........ r81562 | andrew.kuchling | 2010-05-27 08:22:53 -0500 (Thu, 27 May 2010) | 1 line Rewrite wxWidgets section ........ r81563 | andrew.kuchling | 2010-05-27 08:30:09 -0500 (Thu, 27 May 2010) | 1 line Remove top-level 'General Questions' section, pushing up the questions it contains ........ r81567 | andrew.kuchling | 2010-05-27 16:29:59 -0500 (Thu, 27 May 2010) | 1 line Add item ........ r81593 | georg.brandl | 2010-05-29 03:46:18 -0500 (Sat, 29 May 2010) | 1 line #8616: add new turtle demo "nim". ........ r81635 | georg.brandl | 2010-06-01 02:25:23 -0500 (Tue, 01 Jun 2010) | 1 line Put docs for RegexObject.search() before RegexObject.match() to mirror re.search() and re.match() order. ........ r81680 | vinay.sajip | 2010-06-03 17:34:42 -0500 (Thu, 03 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files. ........ r81681 | sean.reifschneider | 2010-06-03 20:51:26 -0500 (Thu, 03 Jun 2010) | 2 lines Issue8810: Clearing up docstring for tzinfo.utcoffset. ........ r81684 | vinay.sajip | 2010-06-04 08:41:02 -0500 (Fri, 04 Jun 2010) | 1 line Issue #8890: Documentation changed to avoid reference to temporary files - other cases covered. ........ r81801 | andrew.kuchling | 2010-06-07 08:38:40 -0500 (Mon, 07 Jun 2010) | 1 line #8875: Remove duplicated paragraph ........ r81888 | andrew.kuchling | 2010-06-10 20:54:58 -0500 (Thu, 10 Jun 2010) | 1 line Add a few more items ........ r81931 | georg.brandl | 2010-06-12 01:26:54 -0500 (Sat, 12 Jun 2010) | 1 line Fix punctuation. ........ r81932 | georg.brandl | 2010-06-12 01:28:58 -0500 (Sat, 12 Jun 2010) | 1 line Document that an existing directory raises in mkdir(). ........ r81933 | georg.brandl | 2010-06-12 01:45:33 -0500 (Sat, 12 Jun 2010) | 1 line Update version in README. ........ r81939 | georg.brandl | 2010-06-12 04:45:01 -0500 (Sat, 12 Jun 2010) | 1 line Use newer toctree syntax. ........ r81940 | georg.brandl | 2010-06-12 04:45:28 -0500 (Sat, 12 Jun 2010) | 1 line Add document on how to build. ........ r81941 | georg.brandl | 2010-06-12 04:45:58 -0500 (Sat, 12 Jun 2010) | 1 line Fix gratuitous indentation. ........ r81942 | georg.brandl | 2010-06-12 04:46:03 -0500 (Sat, 12 Jun 2010) | 1 line Update README. ........ r81963 | andrew.kuchling | 2010-06-12 15:00:55 -0500 (Sat, 12 Jun 2010) | 1 line Grammar fix ........ r81984 | georg.brandl | 2010-06-14 10:58:39 -0500 (Mon, 14 Jun 2010) | 1 line #8993: fix reference. ........ r81991 | andrew.kuchling | 2010-06-14 19:38:58 -0500 (Mon, 14 Jun 2010) | 1 line Add another bunch of items ........ r82120 | andrew.kuchling | 2010-06-20 16:45:45 -0500 (Sun, 20 Jun 2010) | 1 line Note that Python 3.x isn't covered; add forward ref. for UTF-8; note error in 2.5 and up ........ r82188 | benjamin.peterson | 2010-06-23 19:02:46 -0500 (Wed, 23 Jun 2010) | 1 line remove reverted changed ........ r82264 | georg.brandl | 2010-06-27 05:47:47 -0500 (Sun, 27 Jun 2010) | 1 line Confusing punctuation. ........ r82265 | georg.brandl | 2010-06-27 05:49:23 -0500 (Sun, 27 Jun 2010) | 1 line Use designated syntax for optional grammar element. ........ r82266 | georg.brandl | 2010-06-27 05:51:44 -0500 (Sun, 27 Jun 2010) | 1 line Fix URL. ........ r82267 | georg.brandl | 2010-06-27 05:55:38 -0500 (Sun, 27 Jun 2010) | 1 line Two typos. ........
2010-06-27 19:32:30 -03:00
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
"""
import sys
import collections
2002-10-16 18:21:39 -03:00
__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
"urlsplit", "urlunsplit", "urlencode", "parse_qs",
"parse_qsl", "quote", "quote_plus", "quote_from_bytes",
"unquote", "unquote_plus", "unquote_to_bytes"]
# A classification of schemes ('' means apply by default)
2004-05-07 02:50:35 -03:00
uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap',
'wais', 'file', 'https', 'shttp', 'mms',
'prospero', 'rtsp', 'rtspu', '', 'sftp',
'svn', 'svn+ssh']
2004-05-07 02:50:35 -03:00
uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet',
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '',
'svn', 'svn+ssh', 'sftp', 'nfs', 'git', 'git+ssh']
2004-05-07 02:50:35 -03:00
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
2004-05-07 02:50:35 -03:00
uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap',
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
'mms', '', 'sftp']
2004-05-07 02:50:35 -03:00
uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms',
'gopher', 'rtsp', 'rtspu', 'sip', 'sips', '']
2004-05-07 02:50:35 -03:00
uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news',
'nntp', 'wais', 'https', 'shttp', 'snews',
'file', 'prospero', '']
# Characters valid in scheme names
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
'0123456789'
'+-.')
# XXX: Consider replacing with functools.lru_cache
MAX_CACHE_SIZE = 20
_parse_cache = {}
def clear_cache():
"""Clear the parse cache and the quoters cache."""
Merged revisions 59921-59932 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r59923 | raymond.hettinger | 2008-01-11 19:04:55 +0100 (Fri, 11 Jan 2008) | 1 line Speed-up and simplify code urlparse's result objects. ........ r59924 | andrew.kuchling | 2008-01-11 20:33:24 +0100 (Fri, 11 Jan 2008) | 1 line Bug #1790: update link; remove outdated paragraph ........ r59925 | thomas.heller | 2008-01-11 20:34:06 +0100 (Fri, 11 Jan 2008) | 5 lines Raise an error instead of crashing with a segfault when a NULL function pointer is called. Will backport to release25-maint. ........ r59927 | thomas.heller | 2008-01-11 21:29:19 +0100 (Fri, 11 Jan 2008) | 4 lines Fix a potential 'SystemError: NULL result without error'. NULL may be a valid return value from PyLong_AsVoidPtr. Will backport to release25-maint. ........ r59928 | raymond.hettinger | 2008-01-12 00:25:18 +0100 (Sat, 12 Jan 2008) | 1 line Update the opcode docs for STORE_MAP and BUILD_MAP ........ r59929 | mark.dickinson | 2008-01-12 02:56:00 +0100 (Sat, 12 Jan 2008) | 4 lines Issue 1780: Allow leading and trailing whitespace in Decimal constructor, when constructing from a string. Disallow trailing newlines in Context.create_decimal. ........ r59930 | georg.brandl | 2008-01-12 11:53:29 +0100 (Sat, 12 Jan 2008) | 3 lines Move OSError docs to exceptions doc, remove obsolete descriptions from os docs, rework posix docs. ........ r59931 | georg.brandl | 2008-01-12 14:47:57 +0100 (Sat, 12 Jan 2008) | 3 lines Patch #1700288: Method cache optimization, by Armin Rigo, ported to 2.6 by Kevin Jacobs. ........ r59932 | georg.brandl | 2008-01-12 17:11:09 +0100 (Sat, 12 Jan 2008) | 2 lines Fix editing glitch. ........
2008-01-12 15:39:10 -04:00
_parse_cache.clear()
_safe_quoters.clear()
# Helpers for bytes handling
# For 3.2, we deliberately require applications that
# handle improperly quoted URLs to do their own
# decoding and encoding. If valid use cases are
# presented, we may relax this by using latin-1
# decoding internally for 3.3
_implicit_encoding = 'ascii'
_implicit_errors = 'strict'
def _noop(obj):
return obj
def _encode_result(obj, encoding=_implicit_encoding,
errors=_implicit_errors):
return obj.encode(encoding, errors)
def _decode_args(args, encoding=_implicit_encoding,
errors=_implicit_errors):
return tuple(x.decode(encoding, errors) if x else '' for x in args)
def _coerce_args(*args):
# Invokes decode if necessary to create str args
# and returns the coerced inputs along with
# an appropriate result coercion function
# - noop for str inputs
# - encoding function otherwise
str_input = isinstance(args[0], str)
for arg in args[1:]:
# We special-case the empty string to support the
# "scheme=''" default argument to some functions
if arg and isinstance(arg, str) != str_input:
raise TypeError("Cannot mix str and non-str arguments")
if str_input:
return args + (_noop,)
return _decode_args(args) + (_encode_result,)
# Result objects are more helpful than simple tuples
class _ResultMixinStr(object):
"""Standard approach to encoding parsed results from str to bytes"""
__slots__ = ()
def encode(self, encoding='ascii', errors='strict'):
return self._encoded_counterpart(*(x.encode(encoding, errors) for x in self))
class _ResultMixinBytes(object):
"""Standard approach to decoding parsed results from bytes to str"""
__slots__ = ()
def decode(self, encoding='ascii', errors='strict'):
return self._decoded_counterpart(*(x.decode(encoding, errors) for x in self))
class _NetlocResultMixinBase(object):
"""Shared methods for the parsed result objects containing a netloc element"""
__slots__ = ()
@property
def username(self):
return self._userinfo[0]
@property
def password(self):
return self._userinfo[1]
@property
def hostname(self):
hostname = self._hostinfo[0]
if not hostname:
hostname = None
elif hostname is not None:
hostname = hostname.lower()
return hostname
@property
def port(self):
port = self._hostinfo[1]
if port is not None:
port = int(port, 10)
return port
class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):
__slots__ = ()
@property
def _userinfo(self):
netloc = self.netloc
userinfo, have_info, hostinfo = netloc.rpartition('@')
if have_info:
username, have_password, password = userinfo.partition(':')
if not have_password:
password = None
else:
username = password = None
return username, password
@property
def _hostinfo(self):
netloc = self.netloc
_, _, hostinfo = netloc.rpartition('@')
_, have_open_br, bracketed = hostinfo.partition('[')
if have_open_br:
hostname, _, port = bracketed.partition(']')
_, have_port, port = port.partition(':')
else:
hostname, have_port, port = hostinfo.partition(':')
if not have_port:
port = None
return hostname, port
class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):
__slots__ = ()
@property
def _userinfo(self):
netloc = self.netloc
userinfo, have_info, hostinfo = netloc.rpartition(b'@')
if have_info:
username, have_password, password = userinfo.partition(b':')
if not have_password:
password = None
else:
username = password = None
return username, password
@property
def _hostinfo(self):
netloc = self.netloc
_, _, hostinfo = netloc.rpartition(b'@')
_, have_open_br, bracketed = hostinfo.partition(b'[')
if have_open_br:
hostname, _, port = bracketed.partition(b']')
_, have_port, port = port.partition(b':')
else:
hostname, have_port, port = hostinfo.partition(b':')
if not have_port:
port = None
return hostname, port
Merged revisions 59921-59932 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r59923 | raymond.hettinger | 2008-01-11 19:04:55 +0100 (Fri, 11 Jan 2008) | 1 line Speed-up and simplify code urlparse's result objects. ........ r59924 | andrew.kuchling | 2008-01-11 20:33:24 +0100 (Fri, 11 Jan 2008) | 1 line Bug #1790: update link; remove outdated paragraph ........ r59925 | thomas.heller | 2008-01-11 20:34:06 +0100 (Fri, 11 Jan 2008) | 5 lines Raise an error instead of crashing with a segfault when a NULL function pointer is called. Will backport to release25-maint. ........ r59927 | thomas.heller | 2008-01-11 21:29:19 +0100 (Fri, 11 Jan 2008) | 4 lines Fix a potential 'SystemError: NULL result without error'. NULL may be a valid return value from PyLong_AsVoidPtr. Will backport to release25-maint. ........ r59928 | raymond.hettinger | 2008-01-12 00:25:18 +0100 (Sat, 12 Jan 2008) | 1 line Update the opcode docs for STORE_MAP and BUILD_MAP ........ r59929 | mark.dickinson | 2008-01-12 02:56:00 +0100 (Sat, 12 Jan 2008) | 4 lines Issue 1780: Allow leading and trailing whitespace in Decimal constructor, when constructing from a string. Disallow trailing newlines in Context.create_decimal. ........ r59930 | georg.brandl | 2008-01-12 11:53:29 +0100 (Sat, 12 Jan 2008) | 3 lines Move OSError docs to exceptions doc, remove obsolete descriptions from os docs, rework posix docs. ........ r59931 | georg.brandl | 2008-01-12 14:47:57 +0100 (Sat, 12 Jan 2008) | 3 lines Patch #1700288: Method cache optimization, by Armin Rigo, ported to 2.6 by Kevin Jacobs. ........ r59932 | georg.brandl | 2008-01-12 17:11:09 +0100 (Sat, 12 Jan 2008) | 2 lines Fix editing glitch. ........
2008-01-12 15:39:10 -04:00
from collections import namedtuple
_DefragResultBase = namedtuple('DefragResult', 'url fragment')
_SplitResultBase = namedtuple('SplitResult', 'scheme netloc path query fragment')
_ParseResultBase = namedtuple('ParseResult', 'scheme netloc path params query fragment')
# For backwards compatibility, alias _NetlocResultMixinStr
# ResultBase is no longer part of the documented API, but it is
# retained since deprecating it isn't worth the hassle
ResultBase = _NetlocResultMixinStr
# Structured result objects for string data
class DefragResult(_DefragResultBase, _ResultMixinStr):
__slots__ = ()
def geturl(self):
if self.fragment:
return self.url + '#' + self.fragment
else:
return self.url
class SplitResult(_SplitResultBase, _NetlocResultMixinStr):
__slots__ = ()
def geturl(self):
return urlunsplit(self)
class ParseResult(_ParseResultBase, _NetlocResultMixinStr):
__slots__ = ()
def geturl(self):
return urlunparse(self)
# Structured result objects for bytes data
class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):
__slots__ = ()
def geturl(self):
if self.fragment:
return self.url + b'#' + self.fragment
else:
return self.url
class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):
__slots__ = ()
def geturl(self):
return urlunsplit(self)
class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):
__slots__ = ()
def geturl(self):
return urlunparse(self)
# Set up the encode/decode result pairs
def _fix_result_transcoding():
_result_pairs = (
(DefragResult, DefragResultBytes),
(SplitResult, SplitResultBytes),
(ParseResult, ParseResultBytes),
)
for _decoded, _encoded in _result_pairs:
_decoded._encoded_counterpart = _encoded
_encoded._decoded_counterpart = _decoded
_fix_result_transcoding()
del _fix_result_transcoding
def urlparse(url, scheme='', allow_fragments=True):
"""Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
tuple = urlsplit(url, scheme, allow_fragments)
scheme, netloc, url, query, fragment = tuple
if scheme in uses_params and ';' in url:
url, params = _splitparams(url)
else:
params = ''
result = ParseResult(scheme, netloc, url, params, query, fragment)
return _coerce_result(result)
def _splitparams(url):
if '/' in url:
i = url.find(';', url.rfind('/'))
if i < 0:
return url, ''
else:
i = url.find(';')
return url[:i], url[i+1:]
def _splitnetloc(url, start=0):
Merged revisions 59703-59773 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r59704 | christian.heimes | 2008-01-04 04:15:05 +0100 (Fri, 04 Jan 2008) | 1 line Moved include "Python.h" in front of other imports to silence a warning. ........ r59706 | raymond.hettinger | 2008-01-04 04:22:53 +0100 (Fri, 04 Jan 2008) | 10 lines Minor fix-ups to named tuples: * Make the _replace() method respect subclassing. * Using property() to make _fields read-only wasn't a good idea. It caused len(Point._fields) to fail. * Add note to _cast() about length checking and alternative with the star-operator. ........ r59707 | jeffrey.yasskin | 2008-01-04 09:01:23 +0100 (Fri, 04 Jan 2008) | 3 lines Make math.{floor,ceil}({int,long}) return float again for backwards compatibility after r59671 made them return integral types. ........ r59709 | christian.heimes | 2008-01-04 14:21:07 +0100 (Fri, 04 Jan 2008) | 1 line Bug #1713: posixpath.ismount() claims symlink to a mountpoint is a mountpoint. ........ r59712 | lars.gustaebel | 2008-01-04 15:00:33 +0100 (Fri, 04 Jan 2008) | 5 lines Issue #1735: TarFile.extractall() now correctly sets directory permissions and times. (will backport to 2.5) ........ r59714 | andrew.kuchling | 2008-01-04 15:47:17 +0100 (Fri, 04 Jan 2008) | 1 line Update links to bug/patch tracker ........ r59716 | christian.heimes | 2008-01-04 16:23:30 +0100 (Fri, 04 Jan 2008) | 1 line Added interface to Windows' WSAIoctl and a simple example for a network sniffer. ........ r59717 | christian.heimes | 2008-01-04 16:29:00 +0100 (Fri, 04 Jan 2008) | 1 line And here is the rest of Hirokazu Yamamoto's patch for VS6.0 support. Thanks Hiro! ........ r59719 | christian.heimes | 2008-01-04 16:34:06 +0100 (Fri, 04 Jan 2008) | 1 line Reverted last transaction. It's the wrong branch. ........ r59721 | christian.heimes | 2008-01-04 16:48:06 +0100 (Fri, 04 Jan 2008) | 1 line socket.ioctl is only available on Windows ........ r59722 | andrew.kuchling | 2008-01-04 19:24:41 +0100 (Fri, 04 Jan 2008) | 1 line Fix markup ........ r59723 | andrew.kuchling | 2008-01-04 19:25:05 +0100 (Fri, 04 Jan 2008) | 1 line Fix markup ........ r59725 | guido.van.rossum | 2008-01-05 01:59:59 +0100 (Sat, 05 Jan 2008) | 3 lines Patch #1725 by Mark Dickinson, fixes incorrect conversion of -1e1000 and adds errors for -0x. ........ r59726 | guido.van.rossum | 2008-01-05 02:21:57 +0100 (Sat, 05 Jan 2008) | 2 lines Patch #1698 by Senthil: allow '@' in username when parsed by urlparse.py. ........ r59727 | raymond.hettinger | 2008-01-05 02:35:43 +0100 (Sat, 05 Jan 2008) | 1 line Improve namedtuple's _cast() method with a docstring, new name, and error-checking. ........ r59728 | raymond.hettinger | 2008-01-05 03:17:24 +0100 (Sat, 05 Jan 2008) | 1 line Add error-checking to namedtuple's _replace() method. ........ r59730 | fred.drake | 2008-01-05 05:38:38 +0100 (Sat, 05 Jan 2008) | 2 lines clean up a comment ........ r59731 | jeffrey.yasskin | 2008-01-05 09:47:13 +0100 (Sat, 05 Jan 2008) | 11 lines Continue rolling back pep-3141 changes that changed behavior from 2.5. This round included: * Revert round to its 2.6 behavior (half away from 0). * Because round, floor, and ceil always return float again, it's no longer necessary to have them delegate to __xxx___, so I've ripped that out of their implementations and the Real ABC. This also helps in implementing types that work in both 2.6 and 3.0: you return int from the __xxx__ methods, and let it get enabled by the version upgrade. * Make pow(-1, .5) raise a ValueError again. ........ r59736 | andrew.kuchling | 2008-01-05 16:13:49 +0100 (Sat, 05 Jan 2008) | 1 line Fix comment typo ........ r59738 | thomas.heller | 2008-01-05 18:15:44 +0100 (Sat, 05 Jan 2008) | 1 line Add myself. ........ r59739 | georg.brandl | 2008-01-05 18:49:17 +0100 (Sat, 05 Jan 2008) | 2 lines Fix C++-style comment. ........ r59742 | georg.brandl | 2008-01-05 20:28:16 +0100 (Sat, 05 Jan 2008) | 2 lines Remove with_statement future imports from 2.6 docs. ........ r59743 | georg.brandl | 2008-01-05 20:29:45 +0100 (Sat, 05 Jan 2008) | 2 lines Simplify index entries; fix #1712. ........ r59744 | georg.brandl | 2008-01-05 20:44:22 +0100 (Sat, 05 Jan 2008) | 2 lines Doc patch #1730 from Robin Stocker; minor corrections mostly to os.rst. ........ r59749 | georg.brandl | 2008-01-05 21:29:13 +0100 (Sat, 05 Jan 2008) | 2 lines Revert socket.rst to unix-eol. ........ r59750 | georg.brandl | 2008-01-05 21:33:46 +0100 (Sat, 05 Jan 2008) | 2 lines Set native svn:eol-style property for text files. ........ r59752 | georg.brandl | 2008-01-05 21:46:29 +0100 (Sat, 05 Jan 2008) | 2 lines #1719: capitalization error in "UuidCreate". ........ r59753 | georg.brandl | 2008-01-05 22:02:25 +0100 (Sat, 05 Jan 2008) | 2 lines Repair markup. ........ r59754 | georg.brandl | 2008-01-05 22:10:50 +0100 (Sat, 05 Jan 2008) | 2 lines Use markup. ........ r59757 | christian.heimes | 2008-01-05 22:35:52 +0100 (Sat, 05 Jan 2008) | 1 line Final adjustments for #1601 ........ r59758 | guido.van.rossum | 2008-01-05 23:19:06 +0100 (Sat, 05 Jan 2008) | 3 lines Patch #1637: fix urlparse for URLs like 'http://x.com?arg=/foo'. Fix by John Nagle. ........ r59759 | guido.van.rossum | 2008-01-05 23:20:01 +0100 (Sat, 05 Jan 2008) | 2 lines Add John Nagle (of issue #1637). ........ r59765 | raymond.hettinger | 2008-01-06 10:02:24 +0100 (Sun, 06 Jan 2008) | 1 line Small code simplification. Forgot that classmethods can be called from intances. ........ r59766 | martin.v.loewis | 2008-01-06 11:09:48 +0100 (Sun, 06 Jan 2008) | 2 lines Use vcbuild for VS 2009. ........ r59767 | martin.v.loewis | 2008-01-06 12:03:43 +0100 (Sun, 06 Jan 2008) | 2 lines Package using VS 2008. ........ r59768 | martin.v.loewis | 2008-01-06 12:13:16 +0100 (Sun, 06 Jan 2008) | 2 lines Don't try to package msvcr90 for the moment. ........ r59769 | georg.brandl | 2008-01-06 15:17:36 +0100 (Sun, 06 Jan 2008) | 4 lines #1696393: don't check for '.' and '..' in ntpath.walk since they aren't returned from os.listdir anymore. Reported by Michael Haggerty. ........ r59770 | georg.brandl | 2008-01-06 15:27:15 +0100 (Sun, 06 Jan 2008) | 3 lines #1742: don't raise exception on os.path.relpath("a", "a"), but return os.curdir. Reported by Jesse Towner. ........ r59771 | georg.brandl | 2008-01-06 15:33:52 +0100 (Sun, 06 Jan 2008) | 2 lines #1591: Clarify docstring of Popen3. ........ r59772 | georg.brandl | 2008-01-06 16:30:34 +0100 (Sun, 06 Jan 2008) | 2 lines #1680: fix context manager example function name. ........ r59773 | georg.brandl | 2008-01-06 16:34:57 +0100 (Sun, 06 Jan 2008) | 2 lines #1755097: document default values for [].sort() and sorted(). ........
2008-01-06 12:59:19 -04:00
delim = len(url) # position of end of domain part of url, default is end
for c in '/?#': # look for delimiters; the order is NOT important
wdelim = url.find(c, start) # find first of this delim
if wdelim >= 0: # if found
delim = min(delim, wdelim) # use earliest delim position
return url[start:delim], url[delim:] # return (domain, rest)
def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
allow_fragments = bool(allow_fragments)
Merged revisions 59465-59487 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r59467 | georg.brandl | 2007-12-11 17:32:49 +0100 (Tue, 11 Dec 2007) | 2 lines Add another GHOP contributor. ........ r59468 | kurt.kaiser | 2007-12-11 20:35:12 +0100 (Tue, 11 Dec 2007) | 3 lines IDLE_tabbedpages.071101.patch Tal Einat Cosmetic changes, one bug. Remove tabpage.py, replaced by tabbedpages.py ........ r59471 | gerhard.haering | 2007-12-11 22:07:40 +0100 (Tue, 11 Dec 2007) | 9 lines Forward-port of commit 59184. - Backported a workaround for a bug in SQLite 3.2.x/3.3.x versions where a statement recompilation with no bound parameters lead to a segfault - Backported a fix necessary because of an SQLite API change in version 3.5. This prevents segfaults when executing empty queries, like our test suite does ........ r59475 | christian.heimes | 2007-12-12 19:09:06 +0100 (Wed, 12 Dec 2007) | 1 line Fixed a nasty problem in the xxmodule.c ........ r59478 | raymond.hettinger | 2007-12-13 01:08:37 +0100 (Thu, 13 Dec 2007) | 1 line Fix bug 1604. deque.__init__() did not clear existing contents like list.__init__. Not a backport candidate. ........ r59480 | alexandre.vassalotti | 2007-12-13 18:58:23 +0100 (Thu, 13 Dec 2007) | 2 lines Fix issue #1313119: urlparse "caches" parses regardless of encoding ........ r59482 | christian.heimes | 2007-12-13 20:23:16 +0100 (Thu, 13 Dec 2007) | 1 line Fixed bug #1613: Makefile's VPATH feature is broken ........ r59484 | guido.van.rossum | 2007-12-13 21:50:10 +0100 (Thu, 13 Dec 2007) | 3 lines Patch #1608. Someone with access to autoconf 2.61 or higher needs to run it and check in the resulting configure file. ........ r59485 | thomas.heller | 2007-12-13 22:20:29 +0100 (Thu, 13 Dec 2007) | 1 line Ran autoconf. ........ r59486 | raymond.hettinger | 2007-12-13 23:55:52 +0100 (Thu, 13 Dec 2007) | 1 line Simplify implementation of __replace__() ........ r59487 | raymond.hettinger | 2007-12-14 00:52:59 +0100 (Fri, 14 Dec 2007) | 1 line Small speedup ........
2007-12-13 21:24:44 -04:00
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
if cached:
return _coerce_result(cached)
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
clear_cache()
netloc = query = fragment = ''
i = url.find(':')
if i > 0:
if url[:i] == 'http': # optimize the common case
scheme = url[:i].lower()
url = url[i+1:]
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
if '?' in url:
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)
for c in url[:i]:
if c not in scheme_chars:
break
else:
try:
# make sure "url" is not actually a port number (in which case
# "scheme" is really part of the path
_testportnum = int(url[i+1:])
except ValueError:
scheme, url = url[:i].lower(), url[i+1:]
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and scheme in uses_fragment and '#' in url:
url, fragment = url.split('#', 1)
if scheme in uses_query and '?' in url:
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)
def urlunparse(components):
"""Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent)."""
scheme, netloc, url, params, query, fragment, _coerce_result = (
_coerce_args(*components))
if params:
url = "%s;%s" % (url, params)
return _coerce_result(urlunsplit((scheme, netloc, url, query, fragment)))
def urlunsplit(components):
"""Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent)."""
scheme, netloc, url, query, fragment, _coerce_result = (
_coerce_args(*components))
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
if url and url[:1] != '/': url = '/' + url
url = '//' + (netloc or '') + url
if scheme:
url = scheme + ':' + url
if query:
url = url + '?' + query
if fragment:
url = url + '#' + fragment
return _coerce_result(url)
def urljoin(base, url, allow_fragments=True):
"""Join a base URL and a possibly relative URL to form an absolute
interpretation of the latter."""
if not base:
return url
if not url:
return base
base, url, _coerce_result = _coerce_args(base, url)
bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
urlparse(base, '', allow_fragments)
scheme, netloc, path, params, query, fragment = \
urlparse(url, bscheme, allow_fragments)
if scheme != bscheme or scheme not in uses_relative:
return _coerce_result(url)
if scheme in uses_netloc:
if netloc:
return _coerce_result(urlunparse((scheme, netloc, path,
params, query, fragment)))
netloc = bnetloc
if path[:1] == '/':
return _coerce_result(urlunparse((scheme, netloc, path,
params, query, fragment)))
if not path and not params:
path = bpath
params = bparams
if not query:
query = bquery
return _coerce_result(urlunparse((scheme, netloc, path,
params, query, fragment)))
segments = bpath.split('/')[:-1] + path.split('/')
# XXX The stuff below is bogus in various ways...
if segments[-1] == '.':
segments[-1] = ''
while '.' in segments:
segments.remove('.')
while 1:
i = 1
n = len(segments) - 1
while i < n:
if (segments[i] == '..'
and segments[i-1] not in ('', '..')):
del segments[i-1:i+1]
break
i = i+1
else:
break
if segments == ['', '..']:
segments[-1] = ''
elif len(segments) >= 2 and segments[-1] == '..':
segments[-2:] = ['']
return _coerce_result(urlunparse((scheme, netloc, '/'.join(segments),
params, query, fragment)))
def urldefrag(url):
"""Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
"""
url, _coerce_result = _coerce_args(url)
if '#' in url:
s, n, p, a, q, frag = urlparse(url)
defrag = urlunparse((s, n, p, a, q, ''))
else:
frag = ''
defrag = url
return _coerce_result(DefragResult(defrag, frag))
def unquote_to_bytes(string):
"""unquote_to_bytes('abc%20def') -> b'abc def'."""
# Note: strings are encoded as UTF-8. This is only an issue if it contains
# unescaped non-ASCII characters, which URIs should not.
if not string:
# Is it a string-like object?
string.split
return b''
if isinstance(string, str):
string = string.encode('utf-8')
res = string.split(b'%')
if len(res) == 1:
return string
string = res[0]
for item in res[1:]:
try:
string += bytes([int(item[:2], 16)]) + item[2:]
except ValueError:
string += b'%' + item
return string
def unquote(string, encoding='utf-8', errors='replace'):
"""Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
"""
if string == '':
return string
res = string.split('%')
if len(res) == 1:
return string
if encoding is None:
encoding = 'utf-8'
if errors is None:
errors = 'replace'
# pct_sequence: contiguous sequence of percent-encoded bytes, decoded
pct_sequence = b''
string = res[0]
for item in res[1:]:
try:
if not item:
raise ValueError
pct_sequence += bytes.fromhex(item[:2])
rest = item[2:]
if not rest:
# This segment was just a single percent-encoded character.
# May be part of a sequence of code units, so delay decoding.
# (Stored in pct_sequence).
continue
except ValueError:
rest = '%' + item
# Encountered non-percent-encoded characters. Flush the current
# pct_sequence.
string += pct_sequence.decode(encoding, errors) + rest
pct_sequence = b''
if pct_sequence:
# Flush the final pct_sequence
string += pct_sequence.decode(encoding, errors)
return string
def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
"""Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
"""
dict = {}
pairs = parse_qsl(qs, keep_blank_values, strict_parsing,
encoding=encoding, errors=errors)
for name, value in pairs:
if name in dict:
dict[name].append(value)
else:
dict[name] = [value]
return dict
def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
"""Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings. A
true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
Returns a list, as G-d intended.
"""
qs, _coerce_result = _coerce_args(qs)
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError("bad query field: %r" % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = unquote(name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = unquote(value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
return r
def unquote_plus(string, encoding='utf-8', errors='replace'):
"""Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
"""
string = string.replace('+', ' ')
return unquote(string, encoding, errors)
_ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
b'abcdefghijklmnopqrstuvwxyz'
b'0123456789'
b'_.-')
_ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE)
_safe_quoters = {}
class Quoter(collections.defaultdict):
"""A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
"""
# Keeps a cache internally, using defaultdict, for efficiency (lookups
# of cached keys don't call Python code at all).
def __init__(self, safe):
"""safe: bytes object."""
self.safe = _ALWAYS_SAFE.union(safe)
def __repr__(self):
# Without this, will just display as a defaultdict
return "<Quoter %r>" % dict(self)
def __missing__(self, b):
# Handle a cache miss. Store quoted string in cache and return.
res = chr(b) if b in self.safe else '%{:02X}'.format(b)
self[b] = res
return res
def quote(string, safe='/', encoding=None, errors=None):
"""quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted.
RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
the following reserved characters.
reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
"$" | ","
Each of these characters is reserved in some component of a URL,
but not necessarily in all of them.
By default, the quote function is intended for quoting the path
section of a URL. Thus, it will not encode '/'. This character
is reserved, but in typical usage the quote function is being
called on a path where the existing slash characters are used as
reserved characters.
string and safe may be either str or bytes objects. encoding must
not be specified if string is a str.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
"""
if isinstance(string, str):
if not string:
return string
if encoding is None:
encoding = 'utf-8'
if errors is None:
errors = 'strict'
string = string.encode(encoding, errors)
else:
if encoding is not None:
raise TypeError("quote() doesn't support 'encoding' for bytes")
if errors is not None:
raise TypeError("quote() doesn't support 'errors' for bytes")
return quote_from_bytes(string, safe)
def quote_plus(string, safe='', encoding=None, errors=None):
"""Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
"""
# Check if ' ' in string, where string may either be a str or bytes. If
# there are no spaces, the regular quote will produce the right answer.
if ((isinstance(string, str) and ' ' not in string) or
(isinstance(string, bytes) and b' ' not in string)):
return quote(string, safe, encoding, errors)
if isinstance(safe, str):
space = ' '
else:
space = b' '
string = quote(string, safe + space, encoding, errors)
return string.replace(' ', '+')
def quote_from_bytes(bs, safe='/'):
"""Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def\xab') -> 'abc%20def%AB'
"""
if not isinstance(bs, (bytes, bytearray)):
raise TypeError("quote_from_bytes() expected bytes")
if not bs:
return ''
if isinstance(safe, str):
# Normalize 'safe' by converting to bytes and removing non-ASCII chars
safe = safe.encode('ascii', 'ignore')
else:
safe = bytes([c for c in safe if c < 128])
if not bs.rstrip(_ALWAYS_SAFE_BYTES + safe):
return bs.decode()
try:
quoter = _safe_quoters[safe]
except KeyError:
_safe_quoters[safe] = quoter = Quoter(safe).__getitem__
return ''.join([quoter(char) for char in bs])
def urlencode(query, doseq=False, safe='', encoding=None, errors=None):
"""Encode a sequence of two-element tuples or dictionary into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The query arg may be either a string or a bytes type. When query arg is a
string, the safe, encoding and error parameters are sent the quote_plus for
encoding.
"""
2009-03-26 11:49:26 -03:00
if hasattr(query, "items"):
query = query.items()
else:
# It's a bother at times that strings and string-like objects are
# sequences.
try:
# non-sequence items should not work with len()
# non-empty strings will fail this
if len(query) and not isinstance(query[0], tuple):
raise TypeError
# Zero-length sequences of all types will get here and succeed,
# but that's a minor nit. Since the original implementation
# allowed empty dicts that type of behavior probably should be
# preserved for consistency
except TypeError:
2009-03-26 11:49:26 -03:00
ty, va, tb = sys.exc_info()
raise TypeError("not a valid non-string sequence "
"or mapping object").with_traceback(tb)
l = []
if not doseq:
for k, v in query:
if isinstance(k, bytes):
k = quote_plus(k, safe)
else:
k = quote_plus(str(k), safe, encoding, errors)
if isinstance(v, bytes):
v = quote_plus(v, safe)
else:
v = quote_plus(str(v), safe, encoding, errors)
l.append(k + '=' + v)
else:
for k, v in query:
if isinstance(k, bytes):
k = quote_plus(k, safe)
else:
k = quote_plus(str(k), safe, encoding, errors)
if isinstance(v, bytes):
v = quote_plus(v, safe)
l.append(k + '=' + v)
elif isinstance(v, str):
v = quote_plus(v, safe, encoding, errors)
l.append(k + '=' + v)
else:
try:
# Is this a sufficient test for sequence-ness?
x = len(v)
except TypeError:
# not a sequence
v = quote_plus(str(v), safe, encoding, errors)
l.append(k + '=' + v)
else:
# loop over the sequence
for elt in v:
if isinstance(elt, bytes):
elt = quote_plus(elt, safe)
else:
elt = quote_plus(str(elt), safe, encoding, errors)
l.append(k + '=' + elt)
return '&'.join(l)
# Utilities to parse URLs (most of these return None for missing parts):
# unwrap('<URL:type://host/path>') --> 'type://host/path'
# splittype('type:opaquestring') --> 'type', 'opaquestring'
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'
# splitpasswd('user:passwd') -> 'user', 'passwd'
# splitport('host:port') --> 'host', 'port'
# splitquery('/path?query') --> '/path', 'query'
# splittag('/path#tag') --> '/path', 'tag'
# splitattr('/path;attr1=value1;attr2=value2;...') ->
# '/path', ['attr1=value1', 'attr2=value2', ...]
# splitvalue('attr=value') --> 'attr', 'value'
# urllib.parse.unquote('abc%20def') -> 'abc def'
# quote('abc def') -> 'abc%20def')
def to_bytes(url):
"""to_bytes(u"URL") --> 'URL'."""
# Most URL schemes require ASCII. If that changes, the conversion
# can be relaxed.
# XXX get rid of to_bytes()
if isinstance(url, str):
try:
url = url.encode("ASCII").decode()
except UnicodeError:
raise UnicodeError("URL " + repr(url) +
" contains non-ASCII characters")
return url
def unwrap(url):
"""unwrap('<URL:type://host/path>') --> 'type://host/path'."""
url = str(url).strip()
if url[:1] == '<' and url[-1:] == '>':
url = url[1:-1].strip()
if url[:4] == 'URL:': url = url[4:].strip()
return url
_typeprog = None
def splittype(url):
"""splittype('type:opaquestring') --> 'type', 'opaquestring'."""
global _typeprog
if _typeprog is None:
import re
_typeprog = re.compile('^([^/:]+):')
match = _typeprog.match(url)
if match:
scheme = match.group(1)
return scheme.lower(), url[len(scheme) + 1:]
return None, url
_hostprog = None
def splithost(url):
"""splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
global _hostprog
if _hostprog is None:
import re
_hostprog = re.compile('^//([^/?]*)(.*)$')
match = _hostprog.match(url)
if match:
host_port = match.group(1)
path = match.group(2)
if path and not path.startswith('/'):
path = '/' + path
return host_port, path
return None, url
_userprog = None
def splituser(host):
"""splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
global _userprog
if _userprog is None:
import re
_userprog = re.compile('^(.*)@(.*)$')
match = _userprog.match(host)
if match: return match.group(1, 2)
return None, host
_passwdprog = None
def splitpasswd(user):
"""splitpasswd('user:passwd') -> 'user', 'passwd'."""
global _passwdprog
if _passwdprog is None:
import re
2009-03-30 18:54:41 -03:00
_passwdprog = re.compile('^([^:]*):(.*)$',re.S)
match = _passwdprog.match(user)
if match: return match.group(1, 2)
return user, None
# splittag('/path#tag') --> '/path', 'tag'
_portprog = None
def splitport(host):
"""splitport('host:port') --> 'host', 'port'."""
global _portprog
if _portprog is None:
import re
_portprog = re.compile('^(.*):([0-9]+)$')
match = _portprog.match(host)
if match: return match.group(1, 2)
return host, None
_nportprog = None
def splitnport(host, defport=-1):
"""Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number."""
global _nportprog
if _nportprog is None:
import re
_nportprog = re.compile('^(.*):(.*)$')
match = _nportprog.match(host)
if match:
host, port = match.group(1, 2)
try:
if not port: raise ValueError("no digits")
nport = int(port)
except ValueError:
nport = None
return host, nport
return host, defport
_queryprog = None
def splitquery(url):
"""splitquery('/path?query') --> '/path', 'query'."""
global _queryprog
if _queryprog is None:
import re
_queryprog = re.compile('^(.*)\?([^?]*)$')
match = _queryprog.match(url)
if match: return match.group(1, 2)
return url, None
_tagprog = None
def splittag(url):
"""splittag('/path#tag') --> '/path', 'tag'."""
global _tagprog
if _tagprog is None:
import re
_tagprog = re.compile('^(.*)#([^#]*)$')
match = _tagprog.match(url)
if match: return match.group(1, 2)
return url, None
def splitattr(url):
"""splitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...]."""
words = url.split(';')
return words[0], words[1:]
_valueprog = None
def splitvalue(attr):
"""splitvalue('attr=value') --> 'attr', 'value'."""
global _valueprog
if _valueprog is None:
import re
_valueprog = re.compile('^([^=]*)=(.*)$')
match = _valueprog.match(attr)
if match: return match.group(1, 2)
return attr, None