diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2012-02-13 12:11:27 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2012-02-13 12:11:27 (GMT) |
| commit | 86f67123befc7f5fe76c97d7e08502846f04722d (patch) | |
| tree | 568ed36878317b729f0583d5f171619d565a6e7c /Lib/test | |
| parent | 5211ffe4df8ea41423c1a37635f7c1263a1db754 (diff) | |
| download | cpython-86f67123befc7f5fe76c97d7e08502846f04722d.zip cpython-86f67123befc7f5fe76c97d7e08502846f04722d.tar.gz cpython-86f67123befc7f5fe76c97d7e08502846f04722d.tar.bz2 | |
Fix htmlparser tests to always use the right collector.
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/test_htmlparser.py | 28 |
1 files changed, 26 insertions, 2 deletions
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 2e7277e..3d3f859 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -93,7 +93,7 @@ class TestCaseBase(unittest.TestCase): def _parse_error(self, source): def parse(source=source): - parser = html.parser.HTMLParser() + parser = self.get_collector() parser.feed(source) parser.close() self.assertRaises(html.parser.HTMLParseError, parse) @@ -368,6 +368,30 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): ('comment', '/img'), ('endtag', 'html<')]) + def test_starttag_junk_chars(self): + self._run_check("</>", []) + 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>", [('endtag', 'a<a')]) + self._run_check("<!", [('data', '<!')]) + self._run_check("<a", [('data', '<a')]) + self._run_check("<a foo='bar'", [('data', "<a foo='bar'")]) + 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='>")]) + + def test_declaration_junk_chars(self): + # XXX this is wrong + self._run_check("<!DOCTYPE foo $ >", [('comment', 'DOCTYPE foo $ ')]) + + def test_illegal_declarations(self): + # XXX this might be wrong + self._run_check('<!spacer type="block" height="25">', + [('comment', 'spacer type="block" height="25"')]) + def test_with_unquoted_attributes(self): # see #12008 html = ("<html><body bgcolor=d0ca90 text='181008'>" @@ -476,7 +500,7 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): self._run_check(html, expected) def test_unescape_function(self): - p = html.parser.HTMLParser() + p = self.get_collector() self.assertEqual(p.unescape('&#bad;'),'&#bad;') self.assertEqual(p.unescape('&'),'&') # see #12888 |