mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-22 17:55:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

#19480: HTMLParser now accepts all valid start-tag names as defined by the HTML5 standard.

Browse source
This commit is contained in:
Ezio Melotti 2013-11-07 18:33:24 +02:00
parent d5a2f0b3a1
commit 7165d8b9ba
3 changed files with 28 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

17
Lib/test/test_htmlparser.py
View file

@ -229,6 +229,11 @@ text
self._parse_error("<a foo='bar")
self._parse_error("<a foo='>'")
self._parse_error("<a foo='>")
self._parse_error("<a$>")
self._parse_error("<a$b>")
self._parse_error("<a$b/>")
self._parse_error("<a$b >")
self._parse_error("<a$b />")
def test_valid_doctypes(self):
# from http://www.w3.org/QA/2002/04/valid-dtd-list.html
@ -368,8 +373,8 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
('starttag', 'html', [('<html', None)]),
('data', 'te>>xt'),
('entityref', 'a'),
('data', '<<bc'),
('endtag', 'a'),
('data', '<'),
('starttag', 'bc<', [('a', None)]),
('endtag', 'html'),
('data', '\n<img src="URL>'),
('comment', '/img'),
@ -380,8 +385,7 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
self._run_check("</$>", [('comment', '$')])
self._run_check("</", [('data', '</')])
self._run_check("</a", [('data', '</a')])
# XXX this might be wrong
self._run_check("<a<a>", [('data', '<a'), ('starttag', 'a', [])])
self._run_check("<a<a>", [('starttag', 'a<a', [])])
self._run_check("</a<a>", [('endtag', 'a<a')])
self._run_check("<!", [('data', '<!')])
self._run_check("<a", [('data', '<a')])
@ -389,6 +393,11 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
self._run_check("<a foo='bar", [('data', "<a foo='bar")])
self._run_check("<a foo='>'", [('data', "<a foo='>'")])
self._run_check("<a foo='>", [('data', "<a foo='>")])
self._run_check("<a$>", [('starttag', 'a$', [])])
self._run_check("<a$b>", [('starttag', 'a$b', [])])
self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
self._run_check("<a$b >", [('starttag', 'a$b', [])])
self._run_check("<a$b />", [('startendtag', 'a$b', [])])
def test_slashes_in_starttag(self):
self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])