mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-18 14:40:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

#14538: HTMLParser can now parse correctly start tags that contain a bare /.

Browse source
This commit is contained in:
Ezio Melotti 2012-04-18 19:08:41 -06:00
parent a72aa843b6
commit c45868ec69
3 changed files with 16 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Lib/HTMLParser.py
View file

@ -22,13 +22,13 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen = re.compile('<[a-zA-Z]') starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>') piclose = re.compile('>')
commentclose = re.compile(r'--\s*>') commentclose = re.compile(r'--\s*>')
tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state # see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state # and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*') tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
attrfind = re.compile( attrfind = re.compile(
r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r""" locatestarttagend = re.compile(r"""
@ -289,7 +289,7 @@ class HTMLParser(markupbase.ParserBase):
match = tagfind.match(rawdata, i+1) match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()' assert match, 'unexpected call to parse_starttag()'
k = match.end() k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower() self.lasttag = tag = match.group(1).lower()
while k < endpos: while k < endpos:
m = attrfind.match(rawdata, k) m = attrfind.match(rawdata, k)

10
Lib/test/test_htmlparser.py
View file

@ -260,6 +260,16 @@ text
('starttag', 'a', [('foo', None), ('=', None), ('bar', None)]) ('starttag', 'a', [('foo', None), ('=', None), ('bar', None)])
] ]
self._run_check(html, expected) self._run_check(html, expected)
#see issue #14538
html = ('<meta><meta / ><meta // ><meta / / >'
'<meta/><meta /><meta //><meta//>')
expected = [
('starttag', 'meta', []), ('starttag', 'meta', []),
('starttag', 'meta', []), ('starttag', 'meta', []),
('startendtag', 'meta', []), ('startendtag', 'meta', []),
('startendtag', 'meta', []), ('startendtag', 'meta', []),
]
self._run_check(html, expected)
def test_declaration_junk_chars(self): def test_declaration_junk_chars(self):
self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')]) self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])

3
Misc/NEWS
View file

@ -50,6 +50,9 @@ Core and Builtins
Library Library
------- -------
- Issue #14538: HTMLParser can now parse correctly start tags that contain
a bare '/'.
- Issue #14452: SysLogHandler no longer inserts a UTF-8 BOM into the message. - Issue #14452: SysLogHandler no longer inserts a UTF-8 BOM into the message.
- Issue #13496: Fix potential overflow in bisect.bisect algorithm when applied - Issue #13496: Fix potential overflow in bisect.bisect algorithm when applied