Mercurial > cpython-lru_cache-weakref

annotate Lib/test/test_htmlparser.py @ 70626:aa07c1237f4e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
(Merge 3.2) Issue #12016: Reindent decoders of HK and JP codecs
author Victor Stinner <victor.stinner@haypocalc.com>
date Fri, 03 Jun 2011 23:34:32 +0200
parents 225400cb6e84
children 9896fc2a8167
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
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
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
11 def __init__(self, *args, **kw):
17854
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
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
14 html.parser.HTMLParser.__init__(self, *args, **kw)
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
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
75 def _run_check(self, source, expected_events, collector=None):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
76 if collector is None:
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
77 collector = EventCollector()
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
78 parser = collector
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
79 for s in source:
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
80 parser.feed(s)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
81 parser.close()
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
82 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
83 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
84 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
85 "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
86 "\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
87
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
88 def _run_check_extra(self, source, events):
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
89 self._run_check(source, events, EventCollectorExtra())
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
90
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
91 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
92 def parse(source=source):
47205
7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser
Mark Dickinson <dickinsm@gmail.com>
parents: 47201
diff changeset
93 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
94 parser.feed(source)
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
95 parser.close()
47205
7aa9ad658014 Change test_htmlparser to reflect the HTMLParser -> html.parser
Mark Dickinson <dickinsm@gmail.com>
parents: 47201
diff changeset
96 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
97
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
98
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
99 class HTMLParserTestCase(TestCaseBase):
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
100
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
101 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
102 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
103 ("pi", "processing instruction"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
104 ])
28660
5f1ef1882b25 Add test that demonstrates SGML-style handling of processing
Fred Drake <fdrake@acm.org>
parents: 28297
diff changeset
105 self._run_check("<?processing instruction ?>", [
5f1ef1882b25 Add test that demonstrates SGML-style handling of processing
Fred Drake <fdrake@acm.org>
parents: 28297
diff changeset
106 ("pi", "processing instruction ?"),
5f1ef1882b25 Add test that demonstrates SGML-style handling of processing
Fred Drake <fdrake@acm.org>
parents: 28297
diff changeset
107 ])
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
108
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
109 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
110 self._run_check("""
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
111 <!DOCTYPE html PUBLIC 'foo'>
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
112 <HTML>&entity;&#32;
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
113 <!--comment1a
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
114 -></foo><bar>&lt;<?pi?></foo<bar
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
115 comment1b-->
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
116 <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
117 text
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
118 &#x201C;
36914
f1eaae7f962d Bug #1442874: handle "<!>", the empty SGML comment
Georg Brandl <georg@python.org>
parents: 33432
diff changeset
119 <!--comment2a-- --comment2b--><!>
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
120 </Html>
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
121 """, [
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 ("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
124 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
125 ("starttag", "html", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
126 ("entityref", "entity"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
127 ("charref", "32"),
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 ("comment", "comment1a\n-></foo><bar>&lt;<?pi?></foo<bar\ncomment1b"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
130 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
131 ("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
132 ("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
133 ("charref", "x201C"),
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
134 ("data", "\n"),
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
135 ("comment", "comment2a-- --comment2b"),
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 ("endtag", "html"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
138 ("data", "\n"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
139 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
140
61889
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
141 def test_malformatted_charref(self):
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
142 self._run_check("<p>&#bad;</p>", [
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
143 ("starttag", "p", []),
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
144 ("data", "&#bad;"),
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
145 ("endtag", "p"),
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
146 ])
bf04eaf1af74 Recorded merge of revisions 81500-81501 via svnmerge from
Victor Stinner <victor.stinner@haypocalc.com>
parents: 47205
diff changeset
147
21157
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently.
Fred Drake <fdrake@acm.org>
parents: 20069
diff changeset
148 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
149 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
150 ("entityref", "entityref"),
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently.
Fred Drake <fdrake@acm.org>
parents: 20069
diff changeset
151 ("data", " foo"),
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently.
Fred Drake <fdrake@acm.org>
parents: 20069
diff changeset
152 ])
e592472d55a3 Add a test that makes sure unclosed entity references are handled consitently.
Fred Drake <fdrake@acm.org>
parents: 20069
diff changeset
153
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
154 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
155 inside = """\
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
156 DOCTYPE html [
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
157 <!ELEMENT html - O EMPTY>
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
158 <!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
159 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
160 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
161 <!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
162 <!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
163 <!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
164 <!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
165 %paramEntity;
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
166 <!-- comment -->
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
167 ]"""
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
168 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
169 ("decl", inside),
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
170 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
171
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
172 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
173 # 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
174 # 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
175 # 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
176 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
177 ("starttag", "a", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
178 ("starttag", "b", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
179 ("endtag", "a"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
180 ("endtag", "b"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
181 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
182
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
183 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
184 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
185 ("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
186 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
187
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
188 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
189 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
190 ("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
191 ])
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18985
diff changeset
192
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
193 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
194 output = [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
195 ("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
196 ]
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 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
198 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
199 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
200 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
201
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
202 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
203 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
204 [("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
205 ("c", "yyy\t\nyyy"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
206 ("d", "\txyz\n")])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
207 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
208 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
209 ("starttag", "a", [("b", ""), ("c", "")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
210 ])
28297
2c22b5c09a58 Accept commas in unquoted attribute values.
Fred Drake <fdrake@acm.org>
parents: 24364
diff changeset
211 # Regression test for SF patch #669683.
2c22b5c09a58 Accept commas in unquoted attribute values.
Fred Drake <fdrake@acm.org>
parents: 24364
diff changeset
212 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
213 ("starttag", "e", [("a", "rgb(1,2,3)")]),
2c22b5c09a58 Accept commas in unquoted attribute values.
Fred Drake <fdrake@acm.org>
parents: 24364
diff changeset
214 ])
32538
4fab4a5cce2f Whitespace normalization.
Tim Peters <tim.peters@gmail.com>
parents: 32256
diff changeset
215 # 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
216 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
217 ("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
218 ])
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
219
69189
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
220 def test_attr_nonascii(self):
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
221 # see issue 7311
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
222 self._run_check("<img src=/foo/bar.png alt=\u4e2d\u6587>", [
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
223 ("starttag", "img", [("src", "/foo/bar.png"),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
224 ("alt", "\u4e2d\u6587")]),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
225 ])
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
226 self._run_check("<a title='\u30c6\u30b9\u30c8' "
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
227 "href='\u30c6\u30b9\u30c8.html'>", [
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
228 ("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
229 ("href", "\u30c6\u30b9\u30c8.html")]),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
230 ])
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
231 self._run_check('<a title="\u30c6\u30b9\u30c8" '
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
232 'href="\u30c6\u30b9\u30c8.html">', [
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
233 ("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
234 ("href", "\u30c6\u30b9\u30c8.html")]),
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
235 ])
225400cb6e84 #7311: fix html.parser to accept non-ASCII attribute values.
Ezio Melotti
parents: 68257
diff changeset
236
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
237 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
238 self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
239 ("starttag", "a", [("b", "&><\"'")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
240 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
241
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
242 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
243 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
244 ("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
245 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
246
19683
8cbc74f5586b Enhanced the test for DOCTYPE declarations, added a test for dealing with
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
247 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
248 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
249
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
250 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
251 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
252 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
253
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
254 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
255 output = [("starttag", "a", [("b", "<")])]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
256 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
257 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
258 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
259 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
260 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
261 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
262
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
263 output = [("starttag", "a", [("b", ">")])]
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
264 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
265 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
266 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
267 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
268 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
269 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
270
33432
4b708fa0a60a add tests that make sure buffer boundaries are handled properly for SGML comments
Fred Drake <fdrake@acm.org>
parents: 32538
diff changeset
271 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
272 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
273 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
274 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
275 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
276 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
277 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
278 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
279 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
280 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
281 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
282 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
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_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
285 self._parse_error("</>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
286 self._parse_error("</$>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
287 self._parse_error("</")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
288 self._parse_error("</a")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
289 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
290 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
291 self._parse_error("<!")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
292 self._parse_error("<a $>")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
293 self._parse_error("<a")
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
294 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
295 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
296 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
297 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
298 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
299
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
300 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
301 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
302
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
303 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
304 self._run_check("<p/>", [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
305 ("startendtag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
306 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
307 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
308 ("starttag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
309 ("endtag", "p"),
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 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
312 ("starttag", "p", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
313 ("startendtag", "img", [("src", "foo")]),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
314 ("endtag", "p"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
315 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
316
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
317 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
318 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
319 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
320 ("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
321 ("starttag_text", s)])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
322
18985
ba9e4f55133f Fix stupid bug: when migrating these tests from the Zope repository, the
Fred Drake <fdrake@acm.org>
parents: 18634
diff changeset
323 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
324 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
325 self._run_check(s, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
326 ("starttag", "script", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
327 ("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
328 ("endtag", "script"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
329 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
330 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
331 self._run_check(s, [
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
332 ("starttag", "script", []),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
333 ("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
334 ("endtag", "script"),
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
335 ])
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
336
41554
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 36914
diff changeset
337 def test_entityrefs_in_attributes(self):
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 36914
diff changeset
338 self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>", [
41575
beacf40b5960 Rip out all the u"..." literals and calls to unicode().
Guido van Rossum <guido@python.org>
parents: 41554
diff changeset
339 ("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
340 ])
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 36914
diff changeset
341
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
342
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
343 class HTMLParserTolerantTestCase(TestCaseBase):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
344
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
345 def setUp(self):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
346 self.collector = EventCollector(strict=False)
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
347
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
348 def test_tolerant_parsing(self):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
349 self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
350 '<img src="URL><//img></html</html>', [
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
351 ('data', '<html '),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
352 ('starttag', 'html', []),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
353 ('data', 'te>>xt'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
354 ('entityref', 'a'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
355 ('data', '<<bc'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
356 ('endtag', 'a'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
357 ('endtag', 'html'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
358 ('data', '\n<img src="URL><//img></html'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
359 ('endtag', 'html')],
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
360 collector = self.collector)
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
361
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
362 def test_comma_between_attributes(self):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
363 self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", '
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
364 'method="post">', [
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
365 ('starttag', 'form',
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
366 [('action', '/xxx.php?a=1&b=2&amp'),
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
367 ('method', 'post')])],
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
368 collector = self.collector)
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
369
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
370 def test_weird_chars_in_unquoted_attribute_values(self):
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
371 self._run_check('<form action=bogus|&#()value>', [
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
372 ('starttag', 'form',
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
373 [('action', 'bogus|&#()value')])],
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
374 collector = self.collector)
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
375
67189
3546ce1aa355 Merged revisions 87542 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 61889
diff changeset
376 def test_unescape_function(self):
3546ce1aa355 Merged revisions 87542 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 61889
diff changeset
377 p = html.parser.HTMLParser()
3546ce1aa355 Merged revisions 87542 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 61889
diff changeset
378 self.assertEqual(p.unescape('&#bad;'),'&#bad;')
3546ce1aa355 Merged revisions 87542 via svnmerge from
Senthil Kumaran <orsenthil@gmail.com>
parents: 61889
diff changeset
379 self.assertEqual(p.unescape('&#0038;'),'&')
41554
06145fbc7ab9 Merged revisions 53952-54987 via svnmerge from
Guido van Rossum <guido@python.org>
parents: 36914
diff changeset
380
17854
028a1d39efb6 Added test suite for the new HTMLParser module, originally from the
Fred Drake <fdrake@acm.org>
parents:
diff changeset
381
20069
90a4f23abda7 Adapt to use the test_main() approach.
Fred Drake <fdrake@acm.org>
parents: 19687
diff changeset
382 def test_main():
66623
1cbfeffea19f #1486713: Add a tolerant mode to HTMLParser.
R. David Murray <rdmurray@bitdance.com>
parents: 61889
diff changeset
383 support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)
20069
90a4f23abda7 Adapt to use the test_main() approach.
Fred Drake <fdrake@acm.org>
parents: 19687
diff changeset
384
90a4f23abda7 Adapt to use the test_main() approach.
Fred Drake <fdrake@acm.org>
parents: 19687
diff changeset
385
90a4f23abda7 Adapt to use the test_main() approach.
Fred Drake <fdrake@acm.org>
parents: 19687
diff changeset
386 if __name__ == "__main__":
90a4f23abda7 Adapt to use the test_main() approach.
Fred Drake <fdrake@acm.org>
parents: 19687
diff changeset
387 test_main()