mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-09 16:34:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 17

Make sure that the tolerant parser still parses valid HTML correctly.

Browse source
This commit is contained in:
Ezio Melotti 2011-11-01 18:57:15 +02:00
parent b9a48f7144
commit c1e73c30e9
1 changed files with 19 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

36
Lib/test/test_htmlparser.py
View file

@ -72,9 +72,12 @@ class EventCollectorExtra(EventCollector):
class TestCaseBase(unittest.TestCase): class TestCaseBase(unittest.TestCase):
def get_collector(self):
raise NotImplementedError
def _run_check(self, source, expected_events, collector=None): def _run_check(self, source, expected_events, collector=None):
if collector is None: if collector is None:
collector = EventCollector() collector = self.get_collector()
parser = collector parser = collector
for s in source: for s in source:
parser.feed(s) parser.feed(s)
@ -96,7 +99,10 @@ class TestCaseBase(unittest.TestCase):
self.assertRaises(html.parser.HTMLParseError, parse) self.assertRaises(html.parser.HTMLParseError, parse)
class HTMLParserTestCase(TestCaseBase): class HTMLParserStrictTestCase(TestCaseBase):
def get_collector(self):
return EventCollector(strict=True)
def test_processing_instruction_only(self): def test_processing_instruction_only(self):
self._run_check("<?processing instruction>", [ self._run_check("<?processing instruction>", [
@ -353,12 +359,11 @@ DOCTYPE html [
def test_entityrefs_in_attributes(self): def test_entityrefs_in_attributes(self):
self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>", [ self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>",
("starttag", "html", [("foo", "\u20AC&aa&unsupported;")]) [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])])
])
class HTMLParserTolerantTestCase(TestCaseBase): class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
def get_collector(self): def get_collector(self):
return EventCollector(strict=False) return EventCollector(strict=False)
@ -374,8 +379,7 @@ class HTMLParserTolerantTestCase(TestCaseBase):
('endtag', 'a'), ('endtag', 'a'),
('endtag', 'html'), ('endtag', 'html'),
('data', '\n<img src="URL><//img></html'), ('data', '\n<img src="URL><//img></html'),
('endtag', 'html')], ('endtag', 'html')])
collector=self.get_collector())
def test_with_unquoted_attributes(self): def test_with_unquoted_attributes(self):
# see #12008 # see #12008
@ -399,22 +403,19 @@ class HTMLParserTolerantTestCase(TestCaseBase):
('starttag', 'span', [('class', 'en')]), ('data', ' library'), ('starttag', 'span', [('class', 'en')]), ('data', ' library'),
('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table') ('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table')
] ]
self._run_check(html, expected)
self._run_check(html, expected, collector=self.get_collector())
def test_comma_between_attributes(self): def test_comma_between_attributes(self):
self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", ' self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", '
'method="post">', [ 'method="post">', [
('starttag', 'form', ('starttag', 'form',
[('action', '/xxx.php?a=1&b=2&amp'), [('action', '/xxx.php?a=1&b=2&amp'),
('method', 'post')])], ('method', 'post')])])
collector=self.get_collector())
def test_weird_chars_in_unquoted_attribute_values(self): def test_weird_chars_in_unquoted_attribute_values(self):
self._run_check('<form action=bogus|&#()value>', [ self._run_check('<form action=bogus|&#()value>', [
('starttag', 'form', ('starttag', 'form',
[('action', 'bogus|&#()value')])], [('action', 'bogus|&#()value')])])
collector=self.get_collector())
def test_correct_detection_of_start_tags(self): def test_correct_detection_of_start_tags(self):
# see #13273 # see #13273
@ -436,7 +437,7 @@ class HTMLParserTolerantTestCase(TestCaseBase):
('endtag', 'b'), ('endtag', 'b'),
('endtag', 'div') ('endtag', 'div')
] ]
self._run_check(html, expected, collector=self.get_collector()) self._run_check(html, expected)
html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>' html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>'
expected = [ expected = [
@ -447,7 +448,7 @@ class HTMLParserTolerantTestCase(TestCaseBase):
('data', 'rain'), ('data', 'rain'),
('endtag', 'a'), ('endtag', 'a'),
] ]
self._run_check(html, expected, collector=self.get_collector()) self._run_check(html, expected)
def test_unescape_function(self): def test_unescape_function(self):
p = html.parser.HTMLParser() p = html.parser.HTMLParser()
@ -456,8 +457,9 @@ class HTMLParserTolerantTestCase(TestCaseBase):
# see #12888 # see #12888
self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050) self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050)
def test_main(): def test_main():
support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase) support.run_unittest(HTMLParserStrictTestCase, HTMLParserTolerantTestCase)
if __name__ == "__main__": if __name__ == "__main__":