mirror of
https://github.com/python/cpython.git
synced 2025-08-09 19:38:42 +00:00
[3.9] gh-102555: Fix comment parsing in HTMLParser according to the HTML5 standard (GH-135664) (GH-136276)
* "--!>" now ends the comment.
* "-- >" no longer ends the comment.
* Support abnormally ended empty comments "<-->" and "<--->".
---------
(cherry picked from commit 8ac7613dc8
)
Co-author: Kerim Kabirov <the.privat33r+gh@pm.me>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Co-authored-by: Ezio Melotti <ezio.melotti@gmail.com>
This commit is contained in:
parent
8d1b3dfa09
commit
a63f2294b7
3 changed files with 50 additions and 3 deletions
|
@ -27,7 +27,8 @@ 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]')
|
||||||
endtagopen = re.compile('</[a-zA-Z]')
|
endtagopen = re.compile('</[a-zA-Z]')
|
||||||
piclose = re.compile('>')
|
piclose = re.compile('>')
|
||||||
commentclose = re.compile(r'--\s*>')
|
commentclose = re.compile(r'--!?>')
|
||||||
|
commentabruptclose = re.compile(r'-?>')
|
||||||
# Note:
|
# Note:
|
||||||
# 1) if you change tagfind/attrfind remember to update locatestarttagend too;
|
# 1) if you change tagfind/attrfind remember to update locatestarttagend too;
|
||||||
# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will
|
# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will
|
||||||
|
@ -290,6 +291,21 @@ class HTMLParser(_markupbase.ParserBase):
|
||||||
else:
|
else:
|
||||||
return self.parse_bogus_comment(i)
|
return self.parse_bogus_comment(i)
|
||||||
|
|
||||||
|
# Internal -- parse comment, return length or -1 if not terminated
|
||||||
|
# see https://html.spec.whatwg.org/multipage/parsing.html#comment-start-state
|
||||||
|
def parse_comment(self, i, report=True):
|
||||||
|
rawdata = self.rawdata
|
||||||
|
assert rawdata.startswith('<!--', i), 'unexpected call to parse_comment()'
|
||||||
|
match = commentclose.search(rawdata, i+4)
|
||||||
|
if not match:
|
||||||
|
match = commentabruptclose.match(rawdata, i+4)
|
||||||
|
if not match:
|
||||||
|
return -1
|
||||||
|
if report:
|
||||||
|
j = match.start()
|
||||||
|
self.handle_comment(rawdata[i+4: j])
|
||||||
|
return match.end()
|
||||||
|
|
||||||
# Internal -- parse bogus comment, return length or -1 if not terminated
|
# Internal -- parse bogus comment, return length or -1 if not terminated
|
||||||
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
|
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
|
||||||
def parse_bogus_comment(self, i, report=1):
|
def parse_bogus_comment(self, i, report=1):
|
||||||
|
|
|
@ -321,17 +321,45 @@ text
|
||||||
html = ("<!-- I'm a valid comment -->"
|
html = ("<!-- I'm a valid comment -->"
|
||||||
'<!--me too!-->'
|
'<!--me too!-->'
|
||||||
'<!------>'
|
'<!------>'
|
||||||
|
'<!----->'
|
||||||
'<!---->'
|
'<!---->'
|
||||||
|
# abrupt-closing-of-empty-comment
|
||||||
|
'<!--->'
|
||||||
|
'<!-->'
|
||||||
'<!----I have many hyphens---->'
|
'<!----I have many hyphens---->'
|
||||||
'<!-- I have a > in the middle -->'
|
'<!-- I have a > in the middle -->'
|
||||||
'<!-- and I have -- in the middle! -->')
|
'<!-- and I have -- in the middle! -->'
|
||||||
|
'<!--incorrectly-closed-comment--!>'
|
||||||
|
'<!----!>'
|
||||||
|
'<!----!-->'
|
||||||
|
'<!---- >-->'
|
||||||
|
'<!---!>-->'
|
||||||
|
'<!--!>-->'
|
||||||
|
# nested-comment
|
||||||
|
'<!-- <!-- nested --> -->'
|
||||||
|
'<!--<!-->'
|
||||||
|
'<!--<!--!>'
|
||||||
|
)
|
||||||
expected = [('comment', " I'm a valid comment "),
|
expected = [('comment', " I'm a valid comment "),
|
||||||
('comment', 'me too!'),
|
('comment', 'me too!'),
|
||||||
('comment', '--'),
|
('comment', '--'),
|
||||||
|
('comment', '-'),
|
||||||
|
('comment', ''),
|
||||||
|
('comment', ''),
|
||||||
('comment', ''),
|
('comment', ''),
|
||||||
('comment', '--I have many hyphens--'),
|
('comment', '--I have many hyphens--'),
|
||||||
('comment', ' I have a > in the middle '),
|
('comment', ' I have a > in the middle '),
|
||||||
('comment', ' and I have -- in the middle! ')]
|
('comment', ' and I have -- in the middle! '),
|
||||||
|
('comment', 'incorrectly-closed-comment'),
|
||||||
|
('comment', ''),
|
||||||
|
('comment', '--!'),
|
||||||
|
('comment', '-- >'),
|
||||||
|
('comment', '-!>'),
|
||||||
|
('comment', '!>'),
|
||||||
|
('comment', ' <!-- nested '), ('data', ' -->'),
|
||||||
|
('comment', '<!'),
|
||||||
|
('comment', '<!'),
|
||||||
|
]
|
||||||
self._run_check(html, expected)
|
self._run_check(html, expected)
|
||||||
|
|
||||||
def test_condcoms(self):
|
def test_condcoms(self):
|
||||||
|
|
|
@ -0,0 +1,3 @@
|
||||||
|
Fix comment parsing in :class:`html.parser.HTMLParser` according to the
|
||||||
|
HTML5 standard. ``--!>`` now ends the comment. ``-- >`` no longer ends the
|
||||||
|
comment. Support abnormally ended empty comments ``<-->`` and ``<--->``.
|
Loading…
Add table
Add a link
Reference in a new issue