cpython/Lib/_markupbase.py

396 lines
14 KiB
Python
Raw Normal View History

"""Shared support for scanning document type declarations in HTML and XHTML.
This module is used as a foundation for the html.parser module. It has no
documented public API and should not be used directly.
"""
import re
_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
_commentclose = re.compile(r'--\s*>')
_markedsectionclose = re.compile(r']\s*]\s*>')
# An analysis of the MS-Word extensions is available at
# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf
_msmarkedsectionclose = re.compile(r']\s*>')
del re
class ParserBase:
"""Parser base class which provides some common support methods used
by the SGML/HTML and XHTML parsers."""
def __init__(self):
if self.__class__ is ParserBase:
raise RuntimeError(
2007-12-07 07:10:11 -04:00
"_markupbase.ParserBase must be subclassed")
def error(self, message):
raise NotImplementedError(
"subclasses of ParserBase must override error()")
def reset(self):
self.lineno = 1
self.offset = 0
def getpos(self):
"""Return current line number and offset."""
return self.lineno, self.offset
# Internal -- update line number and offset. This should be
# called for each piece of data exactly once, in order -- in other
# words the concatenation of all the input strings to this
# function should be exactly the entire input.
def updatepos(self, i, j):
if i >= j:
return j
rawdata = self.rawdata
nlines = rawdata.count("\n", i, j)
if nlines:
self.lineno = self.lineno + nlines
pos = rawdata.rindex("\n", i, j) # Should not fail
self.offset = j-(pos+1)
else:
self.offset = self.offset + j-i
return j
_decl_otherchars = ''
# Internal -- parse declaration (for use by subclasses).
def parse_declaration(self, i):
# This is some sort of declaration; in "HTML as
# deployed," this should only be the document type
# declaration ("<!DOCTYPE html...>").
2003-04-24 13:02:54 -03:00
# ISO 8879:1986, however, has more complex
# declaration syntax for elements in <!...>, including:
# --comment--
# [marked section]
2003-04-24 13:02:54 -03:00
# name in the following list: ENTITY, DOCTYPE, ELEMENT,
# ATTLIST, NOTATION, SHORTREF, USEMAP,
# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
rawdata = self.rawdata
j = i + 2
assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
if rawdata[j:j+1] == ">":
# the empty comment <!>
return j + 1
if rawdata[j:j+1] in ("-", ""):
# Start of comment followed by buffer boundary,
# or just a buffer boundary.
return -1
# A simple, practical version could look like: ((name|stringlit) S*) + '>'
n = len(rawdata)
if rawdata[j:j+2] == '--': #comment
# Locate --.*-- as the body of the comment
return self.parse_comment(i)
elif rawdata[j] == '[': #marked section
# Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
# Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
# Note that this is extended by Microsoft Office "Save as Web" function
# to include [if...] and [endif].
return self.parse_marked_section(i)
else: #all other declaration elements
decltype, j = self._scan_name(j, i)
if j < 0:
return j
if decltype == "doctype":
self._decl_otherchars = ''
while j < n:
c = rawdata[j]
if c == ">":
# end of declaration syntax
data = rawdata[i+2:j]
if decltype == "doctype":
self.handle_decl(data)
else:
# According to the HTML5 specs sections "8.2.4.44 Bogus
# comment state" and "8.2.4.45 Markup declaration open
# state", a comment token should be emitted.
# Calling unknown_decl provides more flexibility though.
self.unknown_decl(data)
return j + 1
if c in "\"'":
m = _declstringlit_match(rawdata, j)
if not m:
return -1 # incomplete
j = m.end()
elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
name, j = self._scan_name(j, i)
elif c in self._decl_otherchars:
j = j + 1
elif c == "[":
# this could be handled in a separate doctype parser
if decltype == "doctype":
j = self._parse_doctype_subset(j + 1, i)
elif decltype in {"attlist", "linktype", "link", "element"}:
# must tolerate []'d groups in a content model in an element declaration
# also in data attribute specifications of attlist declaration
# also link type declaration subsets in linktype declarations
# also link attribute specification lists in link declarations
self.error("unsupported '[' char in %s declaration" % decltype)
else:
self.error("unexpected '[' char in declaration")
else:
self.error(
"unexpected %r char in declaration" % rawdata[j])
if j < 0:
return j
return -1 # incomplete
# Internal -- parse a marked section
# Override this to handle MS-word extension syntax <![if word]>content<![endif]>
Merge the rest of the trunk. Merged revisions 46490-46494,46496,46498,46500,46506,46521,46538,46558,46563-46567,46570-46571,46583,46593,46595-46598,46604,46606,46609-46753 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r46610 | martin.v.loewis | 2006-06-03 09:42:26 +0200 (Sat, 03 Jun 2006) | 2 lines Updated version (win32-icons2.zip) from #1490384. ........ r46612 | andrew.kuchling | 2006-06-03 20:09:41 +0200 (Sat, 03 Jun 2006) | 1 line [Bug #1472084] Fix description of do_tag ........ r46614 | andrew.kuchling | 2006-06-03 20:33:35 +0200 (Sat, 03 Jun 2006) | 1 line [Bug #1475554] Strengthen text to say 'must' instead of 'should' ........ r46616 | andrew.kuchling | 2006-06-03 20:41:28 +0200 (Sat, 03 Jun 2006) | 1 line [Bug #1441864] Clarify description of 'data' argument ........ r46617 | andrew.kuchling | 2006-06-03 20:43:24 +0200 (Sat, 03 Jun 2006) | 1 line Minor rewording ........ r46619 | andrew.kuchling | 2006-06-03 21:02:35 +0200 (Sat, 03 Jun 2006) | 9 lines [Bug #1497414] _self is a reserved word in the WATCOM 10.6 C compiler. Fix by renaming the variable. In a different module, Neal fixed it by renaming _self to self. There's already a variable named 'self' here, so I used selfptr. (I'm committing this on a Mac without Tk, but it's a simple search-and-replace. <crosses fingers>, so I'll watch the buildbots and see what happens.) ........ r46621 | fredrik.lundh | 2006-06-03 23:56:05 +0200 (Sat, 03 Jun 2006) | 5 lines "_self" is a said to be a reserved word in Watcom C 10.6. I'm not sure that's really standard compliant behaviour, but I guess we have to fix that anyway... ........ r46622 | andrew.kuchling | 2006-06-04 00:44:42 +0200 (Sun, 04 Jun 2006) | 1 line Update readme ........ r46623 | andrew.kuchling | 2006-06-04 00:59:23 +0200 (Sun, 04 Jun 2006) | 1 line Drop 0 parameter ........ r46624 | andrew.kuchling | 2006-06-04 00:59:59 +0200 (Sun, 04 Jun 2006) | 1 line Some code tidying; use curses.wrapper ........ r46625 | andrew.kuchling | 2006-06-04 01:02:15 +0200 (Sun, 04 Jun 2006) | 1 line Use True; value returned from main is unused ........ r46626 | andrew.kuchling | 2006-06-04 01:07:21 +0200 (Sun, 04 Jun 2006) | 1 line Use true division, and the True value ........ r46627 | andrew.kuchling | 2006-06-04 01:09:58 +0200 (Sun, 04 Jun 2006) | 1 line Docstring fix; use True ........ r46628 | andrew.kuchling | 2006-06-04 01:15:56 +0200 (Sun, 04 Jun 2006) | 1 line Put code in a main() function; loosen up the spacing to match current code style ........ r46629 | andrew.kuchling | 2006-06-04 01:39:07 +0200 (Sun, 04 Jun 2006) | 1 line Use functions; modernize code ........ r46630 | andrew.kuchling | 2006-06-04 01:43:22 +0200 (Sun, 04 Jun 2006) | 1 line This demo requires Medusa (not just asyncore); remove it ........ r46631 | andrew.kuchling | 2006-06-04 01:46:36 +0200 (Sun, 04 Jun 2006) | 2 lines Remove xmlrpc demo -- it duplicates the SimpleXMLRPCServer module. ........ r46632 | andrew.kuchling | 2006-06-04 01:47:22 +0200 (Sun, 04 Jun 2006) | 1 line Remove xmlrpc/ directory ........ r46633 | andrew.kuchling | 2006-06-04 01:51:21 +0200 (Sun, 04 Jun 2006) | 1 line Remove dangling reference ........ r46634 | andrew.kuchling | 2006-06-04 01:59:36 +0200 (Sun, 04 Jun 2006) | 1 line Add more whitespace; use a better socket name ........ r46635 | tim.peters | 2006-06-04 03:22:53 +0200 (Sun, 04 Jun 2006) | 2 lines Whitespace normalization. ........ r46637 | tim.peters | 2006-06-04 05:26:02 +0200 (Sun, 04 Jun 2006) | 16 lines In a PYMALLOC_DEBUG build obmalloc adds extra debugging info to each allocated block. This was using 4 bytes for each such piece of info regardless of platform. This didn't really matter before (proof: no bug reports, and the debug-build obmalloc would have assert-failed if it was ever asked for a chunk of memory >= 2**32 bytes), since container indices were plain ints. But after the Py_ssize_t changes, it's at least theoretically possible to allocate a list or string whose guts exceed 2**32 bytes, and the PYMALLOC_DEBUG routines would fail then (having only 4 bytes to record the originally requested size). Now we use sizeof(size_t) bytes for each of a PYMALLOC_DEBUG build's extra debugging fields. This won't make any difference on 32-bit boxes, but will add 16 bytes to each allocation in a debug build on a 64-bit box. ........ r46638 | tim.peters | 2006-06-04 05:38:04 +0200 (Sun, 04 Jun 2006) | 4 lines _PyObject_DebugMalloc(): The return value should add 2*sizeof(size_t) now, not 8. This probably accounts for current disasters on the 64-bit buildbot slaves. ........ r46639 | neal.norwitz | 2006-06-04 08:19:31 +0200 (Sun, 04 Jun 2006) | 1 line SF #1499797, Fix for memory leak in WindowsError_str ........ r46640 | andrew.macintyre | 2006-06-04 14:31:09 +0200 (Sun, 04 Jun 2006) | 2 lines Patch #1454481: Make thread stack size runtime tunable. ........ r46641 | andrew.macintyre | 2006-06-04 14:59:59 +0200 (Sun, 04 Jun 2006) | 2 lines clean up function declarations to conform to PEP-7 style. ........ r46642 | martin.blais | 2006-06-04 15:49:49 +0200 (Sun, 04 Jun 2006) | 15 lines Fixes in struct and socket from merge reviews. - Following Guido's comments, renamed * pack_to -> pack_into * recv_buf -> recv_into * recvfrom_buf -> recvfrom_into - Made fixes to _struct.c according to Neal Norwitz comments on the checkins list. - Converted some ints into the appropriate -- I hope -- ssize_t and size_t. ........ r46643 | ronald.oussoren | 2006-06-04 16:05:28 +0200 (Sun, 04 Jun 2006) | 3 lines "Import" LDFLAGS in Mac/OSX/Makefile.in to ensure pythonw gets build with the right compiler flags. ........ r46644 | ronald.oussoren | 2006-06-04 16:24:59 +0200 (Sun, 04 Jun 2006) | 2 lines Drop Mac wrappers for the WASTE library. ........ r46645 | tim.peters | 2006-06-04 17:49:07 +0200 (Sun, 04 Jun 2006) | 3 lines s_methods[]: Stop compiler warnings by casting s_unpack_from to PyCFunction. ........ r46646 | george.yoshida | 2006-06-04 19:04:12 +0200 (Sun, 04 Jun 2006) | 2 lines Remove a redundant word ........ r46647 | george.yoshida | 2006-06-04 19:17:25 +0200 (Sun, 04 Jun 2006) | 2 lines Markup fix ........ r46648 | martin.v.loewis | 2006-06-04 21:36:28 +0200 (Sun, 04 Jun 2006) | 2 lines Patch #1359618: Speed-up charmap encoder. ........ r46649 | georg.brandl | 2006-06-04 23:46:16 +0200 (Sun, 04 Jun 2006) | 3 lines Repair refleaks in unicodeobject. ........ r46650 | georg.brandl | 2006-06-04 23:56:52 +0200 (Sun, 04 Jun 2006) | 4 lines Patch #1346214: correctly optimize away "if 0"-style stmts (thanks to Neal for review) ........ r46651 | georg.brandl | 2006-06-05 00:15:37 +0200 (Mon, 05 Jun 2006) | 2 lines Bug #1500293: fix memory leaks in _subprocess module. ........ r46654 | tim.peters | 2006-06-05 01:43:53 +0200 (Mon, 05 Jun 2006) | 2 lines Whitespace normalization. ........ r46655 | tim.peters | 2006-06-05 01:52:47 +0200 (Mon, 05 Jun 2006) | 16 lines Revert revisions: 46640 Patch #1454481: Make thread stack size runtime tunable. 46647 Markup fix The first is causing many buildbots to fail test runs, and there are multiple causes with seemingly no immediate prospects for repairing them. See python-dev discussion. Note that a branch can (and should) be created for resolving these problems, like svn copy svn+ssh://svn.python.org/python/trunk -r46640 svn+ssh://svn.python.org/python/branches/NEW_BRANCH followed by merging rev 46647 to the new branch. ........ r46656 | andrew.kuchling | 2006-06-05 02:08:09 +0200 (Mon, 05 Jun 2006) | 1 line Mention second encoding speedup ........ r46657 | gregory.p.smith | 2006-06-05 02:31:01 +0200 (Mon, 05 Jun 2006) | 7 lines bugfix: when log_archive was called with the DB_ARCH_REMOVE flag present in BerkeleyDB >= 4.2 it tried to construct a list out of an uninitialized char **log_list. feature: export the DB_ARCH_REMOVE flag by name in the module on BerkeleyDB >= 4.2. ........ r46658 | gregory.p.smith | 2006-06-05 02:33:35 +0200 (Mon, 05 Jun 2006) | 5 lines fix a bug in the previous commit. don't leak empty list on error return and fix the additional rare (out of memory only) bug that it was supposed to fix of not freeing log_list when the python allocator failed. ........ r46660 | tim.peters | 2006-06-05 02:55:26 +0200 (Mon, 05 Jun 2006) | 9 lines "Flat is better than nested." Move the long-winded, multiply-nested -R support out of runtest() and into some module-level helper functions. This makes runtest() and the -R code easier to follow. That in turn allowed seeing some opportunities for code simplification, and made it obvious that reglog.txt never got closed. ........ r46661 | hyeshik.chang | 2006-06-05 02:59:54 +0200 (Mon, 05 Jun 2006) | 3 lines Fix a potentially invalid memory access of CJKCodecs' shift-jis decoder. (found by Neal Norwitz) ........ r46663 | gregory.p.smith | 2006-06-05 03:39:52 +0200 (Mon, 05 Jun 2006) | 3 lines * support DBEnv.log_stat() method on BerkeleyDB >= 4.0 [patch #1494885] ........ r46664 | tim.peters | 2006-06-05 03:43:03 +0200 (Mon, 05 Jun 2006) | 3 lines Remove doctest.testmod's deprecated (in 2.4) `isprivate` argument. A lot of hair went into supporting that! ........ r46665 | tim.peters | 2006-06-05 03:47:24 +0200 (Mon, 05 Jun 2006) | 2 lines Whitespace normalization. ........ r46666 | tim.peters | 2006-06-05 03:48:21 +0200 (Mon, 05 Jun 2006) | 2 lines Make doctest news more accurate. ........ r46667 | gregory.p.smith | 2006-06-05 03:56:15 +0200 (Mon, 05 Jun 2006) | 3 lines * support DBEnv.lsn_reset() method on BerkeleyDB >= 4.4 [patch #1494902] ........ r46668 | gregory.p.smith | 2006-06-05 04:02:25 +0200 (Mon, 05 Jun 2006) | 3 lines mention the just committed bsddb changes ........ r46671 | gregory.p.smith | 2006-06-05 19:38:04 +0200 (Mon, 05 Jun 2006) | 3 lines * add support for DBSequence objects [patch #1466734] ........ r46672 | gregory.p.smith | 2006-06-05 20:20:07 +0200 (Mon, 05 Jun 2006) | 3 lines forgot to add this file in previous commit ........ r46673 | tim.peters | 2006-06-05 20:36:12 +0200 (Mon, 05 Jun 2006) | 2 lines Whitespace normalization. ........ r46674 | tim.peters | 2006-06-05 20:36:54 +0200 (Mon, 05 Jun 2006) | 2 lines Add missing svn:eol-style property to text files. ........ r46675 | gregory.p.smith | 2006-06-05 20:48:21 +0200 (Mon, 05 Jun 2006) | 4 lines * fix DBCursor.pget() bug with keyword argument names when no data= is supplied [SF pybsddb bug #1477863] ........ r46676 | andrew.kuchling | 2006-06-05 21:05:32 +0200 (Mon, 05 Jun 2006) | 1 line Remove use of Trove name, which isn't very helpful to users ........ r46677 | andrew.kuchling | 2006-06-05 21:08:25 +0200 (Mon, 05 Jun 2006) | 1 line [Bug #1470026] Include link to list of classifiers ........ r46679 | tim.peters | 2006-06-05 22:48:49 +0200 (Mon, 05 Jun 2006) | 10 lines Access _struct attributes directly instead of mucking with getattr. string_reverse(): Simplify. assertRaises(): Raise TestFailed on failure. test_unpack_from(), test_pack_into(), test_pack_into_fn(): never use `assert` to test for an expected result (it doesn't test anything when Python is run with -O). ........ r46680 | tim.peters | 2006-06-05 22:49:27 +0200 (Mon, 05 Jun 2006) | 2 lines Add missing svn:eol-style property to text files. ........ r46681 | gregory.p.smith | 2006-06-06 01:38:06 +0200 (Tue, 06 Jun 2006) | 3 lines add depends = ['md5.h'] to the _md5 module extension for correctness sake. ........ r46682 | brett.cannon | 2006-06-06 01:51:55 +0200 (Tue, 06 Jun 2006) | 4 lines Add 3 more bytes to a buffer to cover constants in string and null byte on top of 10 possible digits for an int. Closes bug #1501223. ........ r46684 | gregory.p.smith | 2006-06-06 01:59:37 +0200 (Tue, 06 Jun 2006) | 5 lines - bsddb: the __len__ method of a DB object has been fixed to return correct results. It could previously incorrectly return 0 in some cases. Fixes SF bug 1493322 (pybsddb bug 1184012). ........ r46686 | tim.peters | 2006-06-06 02:25:07 +0200 (Tue, 06 Jun 2006) | 7 lines _PySys_Init(): It's rarely a good idea to size a buffer to the exact maximum size someone guesses is needed. In this case, if we're really worried about extreme integers, then "cp%d" can actually need 14 bytes (2 for "cp" + 1 for \0 at the end + 11 for -(2**31-1)). So reserve 128 bytes instead -- nothing is actually saved by making a stack-local buffer tiny. ........ r46687 | neal.norwitz | 2006-06-06 09:22:08 +0200 (Tue, 06 Jun 2006) | 1 line Remove unused variable (and stop compiler warning) ........ r46688 | neal.norwitz | 2006-06-06 09:23:01 +0200 (Tue, 06 Jun 2006) | 1 line Fix a bunch of parameter strings ........ r46689 | thomas.heller | 2006-06-06 13:34:33 +0200 (Tue, 06 Jun 2006) | 6 lines Convert CFieldObject tp_members to tp_getset, since there is no structmember typecode for Py_ssize_t fields. This should fix some of the errors on the PPC64 debian machine (64-bit, big endian). Assigning to readonly fields now raises AttributeError instead of TypeError, so the testcase has to be changed as well. ........ r46690 | thomas.heller | 2006-06-06 13:54:32 +0200 (Tue, 06 Jun 2006) | 1 line Damn - the sentinel was missing. And fix another silly mistake. ........ r46691 | martin.blais | 2006-06-06 14:46:55 +0200 (Tue, 06 Jun 2006) | 13 lines Normalized a few cases of whitespace in function declarations. Found them using:: find . -name '*.py' | while read i ; do grep 'def[^(]*( ' $i /dev/null ; done find . -name '*.py' | while read i ; do grep ' ):' $i /dev/null ; done (I was doing this all over my own code anyway, because I'd been using spaces in all defs, so I thought I'd make a run on the Python code as well. If you need to do such fixes in your own code, you can use xx-rename or parenregu.el within emacs.) ........ r46693 | thomas.heller | 2006-06-06 17:34:18 +0200 (Tue, 06 Jun 2006) | 1 line Specify argtypes for all test functions. Maybe that helps on strange ;-) architectures ........ r46694 | tim.peters | 2006-06-06 17:50:17 +0200 (Tue, 06 Jun 2006) | 5 lines BSequence_set_range(): Rev 46688 ("Fix a bunch of parameter strings") changed this function's signature seemingly by mistake, which is causing buildbots to fail test_bsddb3. Restored the pre-46688 signature. ........ r46695 | tim.peters | 2006-06-06 17:52:35 +0200 (Tue, 06 Jun 2006) | 4 lines On python-dev Thomas Heller said these were committed by mistake in rev 46693, so reverting this part of rev 46693. ........ r46696 | andrew.kuchling | 2006-06-06 19:10:41 +0200 (Tue, 06 Jun 2006) | 1 line Fix comment typo ........ r46697 | brett.cannon | 2006-06-06 20:08:16 +0200 (Tue, 06 Jun 2006) | 2 lines Fix coding style guide bug. ........ r46698 | thomas.heller | 2006-06-06 20:50:46 +0200 (Tue, 06 Jun 2006) | 2 lines Add a hack so that foreign functions returning float now do work on 64-bit big endian platforms. ........ r46699 | thomas.heller | 2006-06-06 21:25:13 +0200 (Tue, 06 Jun 2006) | 3 lines Use the same big-endian hack as in _ctypes/callproc.c for callback functions. This fixes the callback function tests that return float. ........ r46700 | ronald.oussoren | 2006-06-06 21:50:24 +0200 (Tue, 06 Jun 2006) | 5 lines * Ensure that "make altinstall" works when the tree was configured with --enable-framework * Also for --enable-framework: allow users to use --prefix to specify the location of the compatibility symlinks (such as /usr/local/bin/python) ........ r46701 | ronald.oussoren | 2006-06-06 21:56:00 +0200 (Tue, 06 Jun 2006) | 3 lines A quick hack to ensure the right key-bindings for IDLE on osx: install patched configuration files during a framework install. ........ r46702 | tim.peters | 2006-06-07 03:04:59 +0200 (Wed, 07 Jun 2006) | 4 lines dash_R_cleanup(): Clear filecmp._cache. This accounts for different results across -R runs (at least on Windows) of test_filecmp. ........ r46705 | tim.peters | 2006-06-07 08:57:51 +0200 (Wed, 07 Jun 2006) | 17 lines SF patch 1501987: Remove randomness from test_exceptions, from ?iga Seilnacht (sorry about the name, but Firefox on my box can't display the first character of the name -- the SF "Unix name" is zseil). This appears to cure the oddball intermittent leaks across runs when running test_exceptions under -R. I'm not sure why, but I'm too sleepy to care ;-) The thrust of the SF patch was to remove randomness in the pickle protocol used. I changed the patch to use range(pickle.HIGHEST_PROTOCOL + 1), to try both pickle and cPickle, and randomly mucked with other test lines to put statements on their own lines. Not a bugfix candidate (this is fiddling new-in-2.5 code). ........ r46706 | andrew.kuchling | 2006-06-07 15:55:33 +0200 (Wed, 07 Jun 2006) | 1 line Add an SQLite introduction, taken from the 'What's New' text ........ r46708 | andrew.kuchling | 2006-06-07 19:02:52 +0200 (Wed, 07 Jun 2006) | 1 line Mention other placeholders ........ r46709 | andrew.kuchling | 2006-06-07 19:03:46 +0200 (Wed, 07 Jun 2006) | 1 line Add an item; also, escape % ........ r46710 | andrew.kuchling | 2006-06-07 19:04:01 +0200 (Wed, 07 Jun 2006) | 1 line Mention other placeholders ........ r46716 | ronald.oussoren | 2006-06-07 20:57:44 +0200 (Wed, 07 Jun 2006) | 2 lines Move Mac/OSX/Tools one level up ........ r46717 | ronald.oussoren | 2006-06-07 20:58:01 +0200 (Wed, 07 Jun 2006) | 2 lines Move Mac/OSX/PythonLauncher one level up ........ r46718 | ronald.oussoren | 2006-06-07 20:58:42 +0200 (Wed, 07 Jun 2006) | 2 lines mv Mac/OSX/BuildScript one level up ........ r46719 | ronald.oussoren | 2006-06-07 21:02:03 +0200 (Wed, 07 Jun 2006) | 2 lines Move Mac/OSX/* one level up ........ r46720 | ronald.oussoren | 2006-06-07 21:06:01 +0200 (Wed, 07 Jun 2006) | 2 lines And the last bit: move IDLE one level up and adjust makefiles ........ r46723 | ronald.oussoren | 2006-06-07 21:38:53 +0200 (Wed, 07 Jun 2006) | 4 lines - Patch the correct version of python in the Info.plists at build time, instead of relying on a maintainer to update them before releases. - Remove the now empty Mac/OSX directory ........ r46727 | ronald.oussoren | 2006-06-07 22:18:44 +0200 (Wed, 07 Jun 2006) | 7 lines * If BuildApplet.py is used as an applet it starts with a version of sys.exutable that isn't usuable on an #!-line. That results in generated applets that don't actually work. Work around this problem by resetting sys.executable. * argvemulator.py didn't work on intel macs. This patch fixes this (bug #1491468) ........ r46728 | tim.peters | 2006-06-07 22:40:06 +0200 (Wed, 07 Jun 2006) | 2 lines Whitespace normalization. ........ r46729 | tim.peters | 2006-06-07 22:40:54 +0200 (Wed, 07 Jun 2006) | 2 lines Add missing svn:eol-style property to text files. ........ r46730 | thomas.heller | 2006-06-07 22:43:06 +0200 (Wed, 07 Jun 2006) | 7 lines Fix for foreign functions returning small structures on 64-bit big endian machines. Should fix the remaininf failure in the PPC64 Debian buildbot. Thanks to Matthias Klose for providing access to a machine to debug and test this. ........ r46731 | brett.cannon | 2006-06-07 23:48:17 +0200 (Wed, 07 Jun 2006) | 2 lines Clarify documentation for bf_getcharbuffer. ........ r46735 | neal.norwitz | 2006-06-08 07:12:45 +0200 (Thu, 08 Jun 2006) | 1 line Fix a refleak in recvfrom_into ........ r46736 | gregory.p.smith | 2006-06-08 07:17:08 +0200 (Thu, 08 Jun 2006) | 9 lines - bsddb: the bsddb.dbtables Modify method now raises the proper error and aborts the db transaction safely when a modifier callback fails. Fixes SF python patch/bug #1408584. Also cleans up the bsddb.dbtables docstrings since thats the only documentation that exists for that unadvertised module. (people really should really just use sqlite3) ........ r46737 | gregory.p.smith | 2006-06-08 07:38:11 +0200 (Thu, 08 Jun 2006) | 4 lines * Turn the deadlock situation described in SF bug #775414 into a DBDeadLockError exception. * add the test case for my previous dbtables commit. ........ r46738 | gregory.p.smith | 2006-06-08 07:39:54 +0200 (Thu, 08 Jun 2006) | 2 lines pasted set_lk_detect line in wrong spot in previous commit. fixed. passes tests this time. ........ r46739 | armin.rigo | 2006-06-08 12:56:24 +0200 (Thu, 08 Jun 2006) | 6 lines (arre, arigo) SF bug #1350060 Give a consistent behavior for comparison and hashing of method objects (both user- and built-in methods). Now compares the 'self' recursively. The hash was already asking for the hash of 'self'. ........ r46740 | andrew.kuchling | 2006-06-08 13:56:44 +0200 (Thu, 08 Jun 2006) | 1 line Typo fix ........ r46741 | georg.brandl | 2006-06-08 14:45:01 +0200 (Thu, 08 Jun 2006) | 2 lines Bug #1502750: Fix getargs "i" format to use LONG_MIN and LONG_MAX for bounds checking. ........ r46743 | georg.brandl | 2006-06-08 14:54:13 +0200 (Thu, 08 Jun 2006) | 2 lines Bug #1502728: Correctly link against librt library on HP-UX. ........ r46745 | georg.brandl | 2006-06-08 14:55:47 +0200 (Thu, 08 Jun 2006) | 3 lines Add news for recent bugfix. ........ r46746 | georg.brandl | 2006-06-08 15:31:07 +0200 (Thu, 08 Jun 2006) | 4 lines Argh. "integer" is a very confusing word ;) Actually, checking for INT_MAX and INT_MIN is correct since the format code explicitly handles a C "int". ........ r46748 | nick.coghlan | 2006-06-08 15:54:49 +0200 (Thu, 08 Jun 2006) | 1 line Add functools.update_wrapper() and functools.wraps() as described in PEP 356 ........ r46751 | georg.brandl | 2006-06-08 16:50:21 +0200 (Thu, 08 Jun 2006) | 4 lines Bug #1502805: don't alias file.__exit__ to file.close since the latter can return something that's true. ........ r46752 | georg.brandl | 2006-06-08 16:50:53 +0200 (Thu, 08 Jun 2006) | 3 lines Convert test_file to unittest. ........
2006-06-08 12:35:45 -03:00
def parse_marked_section(self, i, report=1):
rawdata= self.rawdata
assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
sectName, j = self._scan_name( i+3, i )
if j < 0:
return j
if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
# look for standard ]]> ending
match= _markedsectionclose.search(rawdata, i+3)
elif sectName in {"if", "else", "endif"}:
# look for MS Office ]> ending
match= _msmarkedsectionclose.search(rawdata, i+3)
else:
self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
if not match:
return -1
if report:
j = match.start(0)
self.unknown_decl(rawdata[i+3: j])
return match.end(0)
2003-04-24 13:02:54 -03:00
# Internal -- parse comment, return length or -1 if not terminated
def parse_comment(self, i, report=1):
rawdata = self.rawdata
if rawdata[i:i+4] != '<!--':
self.error('unexpected call to parse_comment()')
match = _commentclose.search(rawdata, i+4)
if not match:
return -1
if report:
j = match.start(0)
self.handle_comment(rawdata[i+4: j])
return match.end(0)
# Internal -- scan past the internal subset in a <!DOCTYPE declaration,
# returning the index just past any whitespace following the trailing ']'.
def _parse_doctype_subset(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
j = i
while j < n:
c = rawdata[j]
if c == "<":
s = rawdata[j:j+2]
if s == "<":
# end of buffer; incomplete
return -1
if s != "<!":
self.updatepos(declstartpos, j + 1)
self.error("unexpected char in internal subset (in %r)" % s)
if (j + 2) == n:
# end of buffer; incomplete
return -1
if (j + 4) > n:
# end of buffer; incomplete
return -1
if rawdata[j:j+4] == "<!--":
j = self.parse_comment(j, report=0)
if j < 0:
return j
continue
name, j = self._scan_name(j + 2, declstartpos)
if j == -1:
return -1
if name not in {"attlist", "element", "entity", "notation"}:
self.updatepos(declstartpos, j + 2)
self.error(
"unknown declaration %r in internal subset" % name)
# handle the individual names
meth = getattr(self, "_parse_doctype_" + name)
j = meth(j, declstartpos)
if j < 0:
return j
elif c == "%":
# parameter entity reference
if (j + 1) == n:
# end of buffer; incomplete
return -1
s, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
if rawdata[j] == ";":
j = j + 1
elif c == "]":
j = j + 1
while j < n and rawdata[j].isspace():
j = j + 1
if j < n:
if rawdata[j] == ">":
return j
self.updatepos(declstartpos, j)
self.error("unexpected char after internal subset")
else:
return -1
elif c.isspace():
j = j + 1
else:
self.updatepos(declstartpos, j)
self.error("unexpected char %r in internal subset" % c)
# end of buffer reached
return -1
# Internal -- scan past <!ELEMENT declarations
def _parse_doctype_element(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j == -1:
return -1
# style content model; just skip until '>'
rawdata = self.rawdata
if '>' in rawdata[j:]:
return rawdata.find(">", j) + 1
return -1
# Internal -- scan past <!ATTLIST declarations
def _parse_doctype_attlist(self, i, declstartpos):
rawdata = self.rawdata
name, j = self._scan_name(i, declstartpos)
c = rawdata[j:j+1]
if c == "":
return -1
if c == ">":
return j + 1
while 1:
# scan a series of attribute descriptions; simplified:
# name type [value] [#constraint]
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if c == "":
return -1
if c == "(":
# an enumerated type; look for ')'
if ")" in rawdata[j:]:
j = rawdata.find(")", j) + 1
else:
return -1
while rawdata[j:j+1].isspace():
j = j + 1
if not rawdata[j:]:
# end of buffer, incomplete
return -1
else:
name, j = self._scan_name(j, declstartpos)
c = rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1
c = rawdata[j:j+1]
if not c:
return -1
if c == "#":
if rawdata[j:] == "#":
# end of buffer
return -1
name, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if not c:
return -1
if c == '>':
# all done
return j + 1
# Internal -- scan past <!NOTATION declarations
def _parse_doctype_notation(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j < 0:
return j
rawdata = self.rawdata
while 1:
c = rawdata[j:j+1]
if not c:
# end of buffer; incomplete
return -1
if c == '>':
return j + 1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if not m:
return -1
j = m.end()
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan past <!ENTITY declarations
def _parse_doctype_entity(self, i, declstartpos):
rawdata = self.rawdata
if rawdata[i:i+1] == "%":
j = i + 1
while 1:
c = rawdata[j:j+1]
if not c:
return -1
if c.isspace():
j = j + 1
else:
break
else:
j = i
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
while 1:
c = self.rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1 # incomplete
elif c == ">":
return j + 1
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan a name token and the new position and the token, or
# return -1 if we've reached the end of the buffer.
def _scan_name(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
if i == n:
return None, -1
m = _declname_match(rawdata, i)
if m:
s = m.group()
name = s.strip()
if (i + len(s)) == n:
return None, -1 # end of buffer
return name.lower(), m.end()
else:
self.updatepos(declstartpos, i)
self.error("expected name token at %r"
% rawdata[declstartpos:declstartpos+20])
# To be overridden -- handlers for unknown objects
def unknown_decl(self, data):
pass