Commit fa3702dc authored by Ezio Melotti's avatar Ezio Melotti

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

parent 5b14d732
......@@ -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
......
......@@ -323,6 +323,23 @@ DOCTYPE html [
("endtag", element_lower)],
collector=Collector())
def test_comments(self):
html = ("<!-- I'm a valid comment -->"
'<!--me too!-->'
'<!------>'
'<!---->'
'<!----I have many hyphens---->'
'<!-- I have a > in the middle -->'
'<!-- and I have -- in the middle! -->')
expected = [('comment', " I'm a valid comment "),
('comment', 'me too!'),
('comment', '--'),
('comment', ''),
('comment', '--I have many hyphens--'),
('comment', ' I have a > in the middle '),
('comment', ' and I have -- in the middle! ')]
self._run_check(html, expected)
def test_condcoms(self):
html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->'
'<!--[if IE 8]>condcoms<![endif]-->'
......@@ -426,6 +443,19 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
# see #12888
self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050)
def test_broken_comments(self):
html = ('<! not really a comment >'
'<! not a comment either -->'
'<! -- close enough -->'
'<!!! another bogus comment !!!>')
expected = [
('comment', ' not really a comment '),
('comment', ' not a comment either --'),
('comment', ' -- close enough --'),
('comment', '!! another bogus comment !!!'),
]
self._run_check(html, expected)
def test_broken_condcoms(self):
# these condcoms are missing the '--' after '<!' and before the '>'
html = ('<![if !(IE)]>broken condcom<![endif]>'
......
......@@ -113,6 +113,9 @@ Core and Builtins
Library
-------
- Issue #13960: HTMLParser is now able to handle broken comments when
strict=False.
- Issue #9021: Add an introduction to the copy module documentation.
- Issue #6005: Examples in the socket library documentation use sendall, where
......@@ -123,7 +126,7 @@ Library
- Issue #10881: Fix test_site failure with OS X framework builds.
- Issue #964437 Make IDLE help window non-modal.
- Issue #964437: Make IDLE help window non-modal.
Patch by Guilherme Polo and Roger Serwy.
- Issue #2945: Make the distutils upload command aware of bdist_rpm products.
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment