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

#13993: HTMLParser is now able to handle broken end tags when strict=False.

Browse source
This commit is contained in:
Ezio Melotti 2012-02-13 11:24:50 +02:00
parent efc66f9e36
commit 5211ffe4df
3 changed files with 71 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

43
Lib/test/test_htmlparser.py
View file

@ -364,8 +364,9 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
('data', '<<bc'),
('endtag', 'a'),
('endtag', 'html'),
('data', '\n<img src="URL><//img></html'),
('endtag', 'html')])
('data', '\n<img src="URL>'),
('comment', '/img'),
('endtag', 'html<')])
def test_with_unquoted_attributes(self):
# see #12008
@ -403,6 +404,44 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
('starttag', 'form',
[('action', 'bogus|&#()value')])])
def test_invalid_end_tags(self):
# A collection of broken end tags. <br> is used as separator.
# see http://www.w3.org/TR/html5/tokenization.html#end-tag-open-state
# and #13993
html = ('<br></label</p><br></div end tmAd-leaderBoard><br></<h4><br>'
'</li class="unit"><br></li\r\n\t\t\t\t\t\t</ul><br></><br>')
expected = [('starttag', 'br', []),
# < is part of the name, / is discarded, p is an attribute
('endtag', 'label<'),
('starttag', 'br', []),
# text and attributes are discarded
('endtag', 'div'),
('starttag', 'br', []),
# comment because the first char after </ is not a-zA-Z
('comment', '<h4'),
('starttag', 'br', []),
# attributes are discarded
('endtag', 'li'),
('starttag', 'br', []),
# everything till ul (included) is discarded
('endtag', 'li'),
('starttag', 'br', []),
# </> is ignored
('starttag', 'br', [])]
self._run_check(html, expected)
def test_broken_invalid_end_tag(self):
# This is technically wrong (the "> shouldn't be included in the 'data')
# but is probably not worth fixing it (in addition to all the cases of
# the previous test, it would require a full attribute parsing).
# see #13993
html = '<b>This</b attr=">"> confuses the parser'
expected = [('starttag', 'b', []),
('data', 'This'),
('endtag', 'b'),
('data', '"> confuses the parser')]
self._run_check(html, expected)
def test_correct_detection_of_start_tags(self):
# see #13273
html = ('<div style="" ><b>The <a href="some_url">rain</a> '