diff options
| author | Thomas Wouters <thomas@python.org> | 2006-04-21 10:40:58 (GMT) |
|---|---|---|
| committer | Thomas Wouters <thomas@python.org> | 2006-04-21 10:40:58 (GMT) |
| commit | 49fd7fa4431da299196d74087df4a04f99f9c46f (patch) | |
| tree | 35ace5fe78d3d52c7a9ab356ab9f6dbf8d4b71f4 /Lib/sgmllib.py | |
| parent | 9ada3d6e29d5165dadacbe6be07bcd35cfbef59d (diff) | |
| download | cpython-49fd7fa4431da299196d74087df4a04f99f9c46f.zip cpython-49fd7fa4431da299196d74087df4a04f99f9c46f.tar.gz cpython-49fd7fa4431da299196d74087df4a04f99f9c46f.tar.bz2 | |
Merge p3yk branch with the trunk up to revision 45595. This breaks a fair
number of tests, all because of the codecs/_multibytecodecs issue described
here (it's not a Py3K issue, just something Py3K discovers):
http://mail.python.org/pipermail/python-dev/2006-April/064051.html
Hye-Shik Chang promised to look for a fix, so no need to fix it here. The
tests that are expected to break are:
test_codecencodings_cn
test_codecencodings_hk
test_codecencodings_jp
test_codecencodings_kr
test_codecencodings_tw
test_codecs
test_multibytecodec
This merge fixes an actual test failure (test_weakref) in this branch,
though, so I believe merging is the right thing to do anyway.
Diffstat (limited to 'Lib/sgmllib.py')
| -rw-r--r-- | Lib/sgmllib.py | 34 |
1 files changed, 31 insertions, 3 deletions
diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py index 08e365b..3e85a91 100644 --- a/Lib/sgmllib.py +++ b/Lib/sgmllib.py @@ -269,9 +269,37 @@ class SGMLParser(markupbase.ParserBase): attrname, rest, attrvalue = match.group(1, 2, 3) if not rest: attrvalue = attrname - elif attrvalue[:1] == '\'' == attrvalue[-1:] or \ - attrvalue[:1] == '"' == attrvalue[-1:]: - attrvalue = attrvalue[1:-1] + else: + if (attrvalue[:1] == "'" == attrvalue[-1:] or + attrvalue[:1] == '"' == attrvalue[-1:]): + # strip quotes + attrvalue = attrvalue[1:-1] + l = 0 + new_attrvalue = '' + while l < len(attrvalue): + av_match = entityref.match(attrvalue, l) + if (av_match and av_match.group(1) in self.entitydefs and + attrvalue[av_match.end(1)] == ';'): + # only substitute entityrefs ending in ';' since + # otherwise we may break <a href='?p=x&q=y'> + # which is very common + new_attrvalue += self.entitydefs[av_match.group(1)] + l = av_match.end(0) + continue + ch_match = charref.match(attrvalue, l) + if ch_match: + try: + char = chr(int(ch_match.group(1))) + new_attrvalue += char + l = ch_match.end(0) + continue + except ValueError: + # invalid character reference, don't substitute + pass + # all other cases + new_attrvalue += attrvalue[l] + l += 1 + attrvalue = new_attrvalue attrs.append((attrname.lower(), attrvalue)) k = match.end(0) if rawdata[j] == '>': |