[Python-checkins] cpython (3.2): Make sure that the tolerant parser still parses valid HTML correctly.
ezio.melotti
python-checkins at python.org
Tue Nov 1 17:58:31 CET 2011
http://hg.python.org/cpython/rev/8f9f490b4777
changeset: 73289:8f9f490b4777
branch: 3.2
parent: 73279:4404e784918c
user: Ezio Melotti <ezio.melotti at gmail.com>
date: Tue Nov 01 18:57:15 2011 +0200
summary:
Make sure that the tolerant parser still parses valid HTML correctly.
files:
Lib/test/test_htmlparser.py | 36 +++++++++++++-----------
1 files changed, 19 insertions(+), 17 deletions(-)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -72,9 +72,12 @@
class TestCaseBase(unittest.TestCase):
+ def get_collector(self):
+ raise NotImplementedError
+
def _run_check(self, source, expected_events, collector=None):
if collector is None:
- collector = EventCollector()
+ collector = self.get_collector()
parser = collector
for s in source:
parser.feed(s)
@@ -96,7 +99,10 @@
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):
self._run_check("<?processing instruction>", [
@@ -353,12 +359,11 @@
def test_entityrefs_in_attributes(self):
- self._run_check("<html foo='€&aa&unsupported;'>", [
- ("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])
- ])
+ self._run_check("<html foo='€&aa&unsupported;'>",
+ [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])])
-class HTMLParserTolerantTestCase(TestCaseBase):
+class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
def get_collector(self):
return EventCollector(strict=False)
@@ -374,8 +379,7 @@
('endtag', 'a'),
('endtag', 'html'),
('data', '\n<img src="URL><//img></html'),
- ('endtag', 'html')],
- collector=self.get_collector())
+ ('endtag', 'html')])
def test_with_unquoted_attributes(self):
# see #12008
@@ -399,22 +403,19 @@
('starttag', 'span', [('class', 'en')]), ('data', ' library'),
('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table')
]
-
- self._run_check(html, expected, collector=self.get_collector())
+ self._run_check(html, expected)
def test_comma_between_attributes(self):
self._run_check('<form action="/xxx.php?a=1&b=2&", '
'method="post">', [
('starttag', 'form',
[('action', '/xxx.php?a=1&b=2&'),
- ('method', 'post')])],
- collector=self.get_collector())
+ ('method', 'post')])])
def test_weird_chars_in_unquoted_attribute_values(self):
self._run_check('<form action=bogus|&#()value>', [
('starttag', 'form',
- [('action', 'bogus|&#()value')])],
- collector=self.get_collector())
+ [('action', 'bogus|&#()value')])])
def test_correct_detection_of_start_tags(self):
# see #13273
@@ -436,7 +437,7 @@
('endtag', 'b'),
('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>'
expected = [
@@ -447,7 +448,7 @@
('data', 'rain'),
('endtag', 'a'),
]
- self._run_check(html, expected, collector=self.get_collector())
+ self._run_check(html, expected)
def test_unescape_function(self):
p = html.parser.HTMLParser()
@@ -456,8 +457,9 @@
# see #12888
self.assertEqual(p.unescape('{ ' * 1050), '{ ' * 1050)
+
def test_main():
- support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)
+ support.run_unittest(HTMLParserStrictTestCase, HTMLParserTolerantTestCase)
if __name__ == "__main__":
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list