Improve handling of declarations in HTMLParser.

This commit is contained in:
Ezio Melotti 2012-02-13 15:50:37 +02:00
parent 86f67123be
commit f4ab491901
2 changed files with 51 additions and 29 deletions

View file

@ -187,17 +187,10 @@ class HTMLParser(_markupbase.ParserBase):
elif startswith("<?", i):
k = self.parse_pi(i)
elif startswith("<!", 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)
k = self.parse_html_declaration(i)
elif (i + 1) < n:
self.handle_data("<")
k = i + 1
@ -269,6 +262,27 @@ class HTMLParser(_markupbase.ParserBase):
i = self.updatepos(i, n)
self.rawdata = rawdata[i:]
# Internal -- parse html declarations, return length or -1 if not terminated
# See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
# See also parse_declaration in _markupbase
def parse_html_declaration(self, i):
rawdata = self.rawdata
if rawdata[i:i+2] != '<!':
self.error('unexpected call to parse_html_declaration()')
if rawdata[i:i+4] == '<!--':
return self.parse_comment(i)
elif rawdata[i:i+3] == '<![':
return self.parse_marked_section(i)
elif rawdata[i:i+9].lower() == '<!doctype':
# find the closing >
gtpos = rawdata.find('>', 9)
if gtpos == -1:
return -1
self.handle_decl(rawdata[i+2:gtpos])
return gtpos+1
else:
return self.parse_bogus_comment(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):