cpython-lru_cache-weakref: Lib/test/test

annotate Lib/test/test_htmlparser.py @ 64166:d0e9febfa00a 3.1

Merged revisions 84172 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r84172 | martin.v.loewis | 2010-08-18 18:12:23 +0200 (Mi, 18 Aug 2010) | 2 lines Restore GIL in nis_cat in case of error. ........

author	Martin v. Löwis <martin@v.loewis.de>
date	Thu, 19 Aug 2010 09:03:03 +0000
parents	6144760e8350
children	3546ce1aa355 1cbfeffea19f

rev	line source
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	1 """Tests for HTMLParser.py."""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	2
47205 7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser Mark Dickinson <dickinsm@gmail.com> parents: 47201 diff changeset	3 import html.parser
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	4 import pprint
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	5 import unittest
47201 9c930a32cebb #2621 rename test.test_support to test.support Benjamin Peterson <benjamin@python.org> parents: 45471 diff changeset	6 from test import support
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	7
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	8
47205 7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser Mark Dickinson <dickinsm@gmail.com> parents: 47201 diff changeset	9 class EventCollector(html.parser.HTMLParser):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	10
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	11 def __init__(self):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	12 self.events = []
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	13 self.append = self.events.append
47205 7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser Mark Dickinson <dickinsm@gmail.com> parents: 47201 diff changeset	14 html.parser.HTMLParser.__init__(self)
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	15
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	16 def get_events(self):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	17 # Normalize the list of events so that buffer artefacts don't
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	18 # separate runs of contiguous characters.
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	19 L = []
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	20 prevtype = None
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	21 for event in self.events:
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	22 type = event[0]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	23 if type == prevtype == "data":
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	24 L[-1] = ("data", L[-1][1] + event[1])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	25 else:
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	26 L.append(event)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	27 prevtype = type
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	28 self.events = L
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	29 return L
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	30
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	31 # structure markup
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	32
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	33 def handle_starttag(self, tag, attrs):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	34 self.append(("starttag", tag, attrs))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	35
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	36 def handle_startendtag(self, tag, attrs):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	37 self.append(("startendtag", tag, attrs))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	38
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	39 def handle_endtag(self, tag):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	40 self.append(("endtag", tag))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	41
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	42 # all other markup
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	43
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	44 def handle_comment(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	45 self.append(("comment", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	46
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	47 def handle_charref(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	48 self.append(("charref", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	49
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	50 def handle_data(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	51 self.append(("data", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	52
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	53 def handle_decl(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	54 self.append(("decl", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	55
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	56 def handle_entityref(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	57 self.append(("entityref", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	58
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	59 def handle_pi(self, data):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	60 self.append(("pi", data))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	61
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	62 def unknown_decl(self, decl):
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	63 self.append(("unknown decl", decl))
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	64
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	65
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	66 class EventCollectorExtra(EventCollector):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	67
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	68 def handle_starttag(self, tag, attrs):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	69 EventCollector.handle_starttag(self, tag, attrs)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	70 self.append(("starttag_text", self.get_starttag_text()))
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	71
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	72
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	73 class TestCaseBase(unittest.TestCase):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	74
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	75 def _run_check(self, source, expected_events, collector=EventCollector):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	76 parser = collector()
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	77 for s in source:
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	78 parser.feed(s)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	79 parser.close()
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	80 events = parser.get_events()
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	81 if events != expected_events:
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	82 self.fail("received events did not match expected events\n"
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	83 "Expected:\n" + pprint.pformat(expected_events) +
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	84 "\nReceived:\n" + pprint.pformat(events))
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	85
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	86 def _run_check_extra(self, source, events):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	87 self._run_check(source, events, EventCollectorExtra)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	88
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	89 def _parse_error(self, source):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	90 def parse(source=source):
47205 7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser Mark Dickinson <dickinsm@gmail.com> parents: 47201 diff changeset	91 parser = html.parser.HTMLParser()
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	92 parser.feed(source)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	93 parser.close()
47205 7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser Mark Dickinson <dickinsm@gmail.com> parents: 47201 diff changeset	94 self.assertRaises(html.parser.HTMLParseError, parse)
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	95
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	96
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	97 class HTMLParserTestCase(TestCaseBase):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	98
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	99 def test_processing_instruction_only(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	100 self._run_check("<?processing instruction>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	101 ("pi", "processing instruction"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	102 ])
28660 5f1ef1882b25 Add test that demonstrates SGML-style handling of processing Fred Drake <fdrake@acm.org> parents: 28297 diff changeset	103 self._run_check("<?processing instruction ?>", [
5f1ef1882b25 Add test that demonstrates SGML-style handling of processing Fred Drake <fdrake@acm.org> parents: 28297 diff changeset	104 ("pi", "processing instruction ?"),
5f1ef1882b25 Add test that demonstrates SGML-style handling of processing Fred Drake <fdrake@acm.org> parents: 28297 diff changeset	105 ])
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	106
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	107 def test_simple_html(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	108 self._run_check("""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	109 <!DOCTYPE html PUBLIC 'foo'>
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	110 <HTML>&entity;
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	111 <!--comment1a
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	112 -></foo><bar><<?pi?></foo<bar
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	113 comment1b-->
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	114 <Img sRc='Bar' isMAP>sample
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	115 text
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	116 “
36914 f1eaae7f962d Bug #1442874: handle "<!>", the empty SGML comment Georg Brandl <georg@python.org> parents: 33432 diff changeset	117 <!--comment2a-- --comment2b--><!>
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	118 </Html>
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	119 """, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	120 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	121 ("decl", "DOCTYPE html PUBLIC 'foo'"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	122 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	123 ("starttag", "html", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	124 ("entityref", "entity"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	125 ("charref", "32"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	126 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	127 ("comment", "comment1a\n-></foo><bar><<?pi?></foo<bar\ncomment1b"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	128 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	129 ("starttag", "img", [("src", "Bar"), ("ismap", None)]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	130 ("data", "sample\ntext\n"),
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	131 ("charref", "x201C"),
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	132 ("data", "\n"),
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	133 ("comment", "comment2a-- --comment2b"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	134 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	135 ("endtag", "html"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	136 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	137 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	138
61890 6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	139 def test_malformatted_charref(self):
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	140 self._run_check("<p>&#bad;</p>", [
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	141 ("starttag", "p", []),
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	142 ("data", "&#bad;"),
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	143 ("endtag", "p"),
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	144 ])
6144760e8350 Merged revisions 81504 via svnmerge from Victor Stinner <victor.stinner@haypocalc.com> parents: 47205 diff changeset	145
21157 e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	146 def test_unclosed_entityref(self):
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	147 self._run_check("&entityref foo", [
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	148 ("entityref", "entityref"),
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	149 ("data", " foo"),
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	150 ])
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently. Fred Drake <fdrake@acm.org> parents: 20069 diff changeset	151
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	152 def test_doctype_decl(self):
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	153 inside = """\
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	154 DOCTYPE html [
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	155 <!ELEMENT html - O EMPTY>
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	156 <!ATTLIST html
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	157 version CDATA #IMPLIED
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	158 profile CDATA 'DublinCore'>
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	159 <!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	160 <!ENTITY myEntity 'internal parsed entity'>
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	161 <!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	162 <!ENTITY % paramEntity 'name\|name\|name'>
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	163 %paramEntity;
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	164 <!-- comment -->
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	165 ]"""
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	166 self._run_check("<!%s>" % inside, [
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	167 ("decl", inside),
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	168 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	169
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	170 def test_bad_nesting(self):
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	171 # Strangely, this is supposed to test that overlapping
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	172 # elements are allowed. HTMLParser is more geared toward
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	173 # lexing the input that parsing the structure.
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	174 self._run_check("<a><b></a></b>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	175 ("starttag", "a", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	176 ("starttag", "b", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	177 ("endtag", "a"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	178 ("endtag", "b"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	179 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	180
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	181 def test_bare_ampersands(self):
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	182 self._run_check("this text & contains & ampersands &", [
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	183 ("data", "this text & contains & ampersands &"),
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	184 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	185
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	186 def test_bare_pointy_brackets(self):
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	187 self._run_check("this < text > contains < bare>pointy< brackets", [
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	188 ("data", "this < text > contains < bare>pointy< brackets"),
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	189 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18985 diff changeset	190
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	191 def test_attr_syntax(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	192 output = [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	193 ("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	194 ]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	195 self._run_check("""<a b='v' c="v" d=v e>""", output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	196 self._run_check("""<a b = 'v' c = "v" d = v e>""", output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	197 self._run_check("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	198 self._run_check("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	199
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	200 def test_attr_values(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	201 self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	202 [("starttag", "a", [("b", "xxx\n\txxx"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	203 ("c", "yyy\t\nyyy"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	204 ("d", "\txyz\n")])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	205 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	206 self._run_check("""<a b='' c="">""", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	207 ("starttag", "a", [("b", ""), ("c", "")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	208 ])
28297 2c22b5c09a58 Accept commas in unquoted attribute values. Fred Drake <fdrake@acm.org> parents: 24364 diff changeset	209 # Regression test for SF patch #669683.
2c22b5c09a58 Accept commas in unquoted attribute values. Fred Drake <fdrake@acm.org> parents: 24364 diff changeset	210 self._run_check("<e a=rgb(1,2,3)>", [
2c22b5c09a58 Accept commas in unquoted attribute values. Fred Drake <fdrake@acm.org> parents: 24364 diff changeset	211 ("starttag", "e", [("a", "rgb(1,2,3)")]),
2c22b5c09a58 Accept commas in unquoted attribute values. Fred Drake <fdrake@acm.org> parents: 24364 diff changeset	212 ])
32538 4fab4a5cce2f Whitespace normalization. Tim Peters <tim.peters@gmail.com> parents: 32256 diff changeset	213 # Regression test for SF bug #921657.
32256 2f5f38f4bc2b [Bug #921657] Allow '@' in unquoted HTML attributes. Not strictly legal according to the HTML REC, but HTMLParser is already a pretty loose parser. Reported by Bernd Zimmermann. Andrew M. Kuchling <amk@amk.ca> parents: 28660 diff changeset	214 self._run_check("<a href=mailto:xyz@example.com>", [
2f5f38f4bc2b [Bug #921657] Allow '@' in unquoted HTML attributes. Not strictly legal according to the HTML REC, but HTMLParser is already a pretty loose parser. Reported by Bernd Zimmermann. Andrew M. Kuchling <amk@amk.ca> parents: 28660 diff changeset	215 ("starttag", "a", [("href", "mailto:xyz@example.com")]),
2f5f38f4bc2b [Bug #921657] Allow '@' in unquoted HTML attributes. Not strictly legal according to the HTML REC, but HTMLParser is already a pretty loose parser. Reported by Bernd Zimmermann. Andrew M. Kuchling <amk@amk.ca> parents: 28660 diff changeset	216 ])
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	217
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	218 def test_attr_entity_replacement(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	219 self._run_check("""<a b='&><"''>""", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	220 ("starttag", "a", [("b", "&><\"'")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	221 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	222
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	223 def test_attr_funky_names(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	224 self._run_check("""<a a.b='v' c:d=v e-f=v>""", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	225 ("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	226 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	227
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	228 def test_illegal_declarations(self):
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19683 diff changeset	229 self._parse_error('<!spacer type="block" height="25">')
19683 8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	230
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	231 def test_starttag_end_boundary(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	232 self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	233 self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	234
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	235 def test_buffer_artefacts(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	236 output = [("starttag", "a", [("b", "<")])]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	237 self._run_check(["<a b='<'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	238 self._run_check(["<a ", "b='<'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	239 self._run_check(["<a b", "='<'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	240 self._run_check(["<a b=", "'<'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	241 self._run_check(["<a b='<", "'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	242 self._run_check(["<a b='<'", ">"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	243
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	244 output = [("starttag", "a", [("b", ">")])]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	245 self._run_check(["<a b='>'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	246 self._run_check(["<a ", "b='>'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	247 self._run_check(["<a b", "='>'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	248 self._run_check(["<a b=", "'>'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	249 self._run_check(["<a b='>", "'>"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	250 self._run_check(["<a b='>'", ">"], output)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	251
33432 4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	252 output = [("comment", "abc")]
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	253 self._run_check(["", "<!--abc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	254 self._run_check(["<", "!--abc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	255 self._run_check(["<!", "--abc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	256 self._run_check(["<!-", "-abc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	257 self._run_check(["<!--", "abc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	258 self._run_check(["<!--a", "bc-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	259 self._run_check(["<!--ab", "c-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	260 self._run_check(["<!--abc", "-->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	261 self._run_check(["<!--abc-", "->"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	262 self._run_check(["<!--abc--", ">"], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	263 self._run_check(["<!--abc-->", ""], output)
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments Fred Drake <fdrake@acm.org> parents: 32538 diff changeset	264
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	265 def test_starttag_junk_chars(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	266 self._parse_error("</>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	267 self._parse_error("</$>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	268 self._parse_error("</")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	269 self._parse_error("</a")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	270 self._parse_error("<a<a>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	271 self._parse_error("</a<a>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	272 self._parse_error("<!")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	273 self._parse_error("<a $>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	274 self._parse_error("<a")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	275 self._parse_error("<a foo='bar'")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	276 self._parse_error("<a foo='bar")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	277 self._parse_error("<a foo='>'")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	278 self._parse_error("<a foo='>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	279 self._parse_error("<a foo=>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	280
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	281 def test_declaration_junk_chars(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	282 self._parse_error("<!DOCTYPE foo $ >")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	283
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	284 def test_startendtag(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	285 self._run_check("<p/>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	286 ("startendtag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	287 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	288 self._run_check("<p></p>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	289 ("starttag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	290 ("endtag", "p"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	291 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	292 self._run_check("<p><img src='foo' /></p>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	293 ("starttag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	294 ("startendtag", "img", [("src", "foo")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	295 ("endtag", "p"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	296 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	297
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	298 def test_get_starttag_text(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	299 s = """<foo:bar \n one="1"\ttwo=2 >"""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	300 self._run_check_extra(s, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	301 ("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	302 ("starttag_text", s)])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	303
18985 ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the Fred Drake <fdrake@acm.org> parents: 18634 diff changeset	304 def test_cdata_content(self):
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	305 s = """<script> <!-- not a comment --> &not-an-entity-ref; </script>"""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	306 self._run_check(s, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	307 ("starttag", "script", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	308 ("data", " <!-- not a comment --> &not-an-entity-ref; "),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	309 ("endtag", "script"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	310 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	311 s = """<script> <not a='start tag'> </script>"""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	312 self._run_check(s, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	313 ("starttag", "script", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	314 ("data", " <not a='start tag'> "),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	315 ("endtag", "script"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	316 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	317
41554 06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from Guido van Rossum <guido@python.org> parents: 36914 diff changeset	318 def test_entityrefs_in_attributes(self):
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from Guido van Rossum <guido@python.org> parents: 36914 diff changeset	319 self._run_check("<html foo='€&aa&unsupported;'>", [
41575 beacf40b5960 Rip out all the u"..." literals and calls to unicode(). Guido van Rossum <guido@python.org> parents: 41554 diff changeset	320 ("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])
41554 06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from Guido van Rossum <guido@python.org> parents: 36914 diff changeset	321 ])
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from Guido van Rossum <guido@python.org> parents: 36914 diff changeset	322
17854 028a1d39efb6 Added test suite for the new HTMLParser module, originally from the Fred Drake <fdrake@acm.org> parents: diff changeset	323
20069 90a4f23abda7 Adapt to use the test_main() approach. Fred Drake <fdrake@acm.org> parents: 19687 diff changeset	324 def test_main():
47201 9c930a32cebb #2621 rename test.test_support to test.support Benjamin Peterson <benjamin@python.org> parents: 45471 diff changeset	325 support.run_unittest(HTMLParserTestCase)
20069 90a4f23abda7 Adapt to use the test_main() approach. Fred Drake <fdrake@acm.org> parents: 19687 diff changeset	326
90a4f23abda7 Adapt to use the test_main() approach. Fred Drake <fdrake@acm.org> parents: 19687 diff changeset	327
90a4f23abda7 Adapt to use the test_main() approach. Fred Drake <fdrake@acm.org> parents: 19687 diff changeset	328 if __name__ == "__main__":
90a4f23abda7 Adapt to use the test_main() approach. Fred Drake <fdrake@acm.org> parents: 19687 diff changeset	329 test_main()

Mercurial > cpython-lru_cache-weakref

annotate Lib/test/test_htmlparser.py @ 64166:d0e9febfa00a 3.1