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

This commit is contained in:
Ezio Melotti 2012-04-18 19:18:22 -06:00
parent cc19140607
commit 0780b6bc58
3 changed files with 16 additions and 3 deletions

View File

@ -22,7 +22,7 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>')
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
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
@ -36,7 +36,7 @@ attrfind = re.compile(
r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
attrfind_tolerant = re.compile(
r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
@ -327,7 +327,7 @@ class HTMLParser(_markupbase.ParserBase):
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
self.lasttag = tag = match.group(1).lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)

View File

@ -409,6 +409,16 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
('starttag', 'a', [('foo', None), ('=', None), ('bar', None)])
]
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):
self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])

View File

@ -47,6 +47,9 @@ Core and Builtins
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 #13496: Fix potential overflow in bisect.bisect algorithm when applied