mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 08:59:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

#13960: HTMLParser is now able to handle broken comments when strict=False.

Browse source
This commit is contained in:
Ezio Melotti 2012-02-10 10:45:44 +02:00
parent 5b14d732d8
commit fa3702dc28
3 changed files with 58 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

25
Lib/html/parser.py
View file

@ -184,7 +184,17 @@ class HTMLParser(_markupbase.ParserBase):
elif startswith("<?", i):
k = self.parse_pi(i)
elif startswith("<!", i):
k = self.parse_declaration(i)
# this might fail with things like <! not a comment > or
# <! -- space before '--' -->. When strict is True an
# error is raised, when it's False they will be considered
# as bogus comments and parsed (see parse_bogus_comment).
if self.strict:
k = self.parse_declaration(i)
else:
try:
k = self.parse_declaration(i)
except HTMLParseError:
k = self.parse_bogus_comment(i)
elif (i + 1) < n:
self.handle_data("<")
k = i + 1
@ -256,6 +266,19 @@ class HTMLParser(_markupbase.ParserBase):
i = self.updatepos(i, n)
self.rawdata = rawdata[i:]
# Internal -- parse bogus comment, return length or -1 if not terminated
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
def parse_bogus_comment(self, i, report=1):
rawdata = self.rawdata
if rawdata[i:i+2] != '<!':
self.error('unexpected call to parse_comment()')
pos = rawdata.find('>', i+2)
if pos == -1:
return -1
if report:
self.handle_comment(rawdata[i+2:pos])
return pos + 1
# Internal -- parse processing instr, return end or -1 if not terminated
def parse_pi(self, i):
rawdata = self.rawdata