forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 3
Expand file tree
/
Copy pathtest_htmlparser.py
More file actions
1019 lines (915 loc) · 42 KB
/
test_htmlparser.py
File metadata and controls
1019 lines (915 loc) · 42 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Tests for HTMLParser.py."""
import html.parser
import pprint
import unittest
from unittest.mock import patch
from test import support
class EventCollector(html.parser.HTMLParser):
def __init__(self, *args, **kw):
self.events = []
self.append = self.events.append
html.parser.HTMLParser.__init__(self, *args, **kw)
def get_events(self):
# Normalize the list of events so that buffer artefacts don't
# separate runs of contiguous characters.
L = []
prevtype = None
for event in self.events:
type = event[0]
if type == prevtype == "data":
L[-1] = ("data", L[-1][1] + event[1])
else:
L.append(event)
prevtype = type
self.events = L
return L
# structure markup
def handle_starttag(self, tag, attrs):
self.append(("starttag", tag, attrs))
def handle_startendtag(self, tag, attrs):
self.append(("startendtag", tag, attrs))
def handle_endtag(self, tag):
self.append(("endtag", tag))
# all other markup
def handle_comment(self, data):
self.append(("comment", data))
def handle_charref(self, data):
self.append(("charref", data))
def handle_data(self, data):
self.append(("data", data))
def handle_decl(self, data):
self.append(("decl", data))
def handle_entityref(self, data):
self.append(("entityref", data))
def handle_pi(self, data):
self.append(("pi", data))
def unknown_decl(self, decl):
self.append(("unknown decl", decl))
class EventCollectorExtra(EventCollector):
def handle_starttag(self, tag, attrs):
EventCollector.handle_starttag(self, tag, attrs)
self.append(("starttag_text", self.get_starttag_text()))
class EventCollectorCharrefs(EventCollector):
def handle_charref(self, data):
self.fail('This should never be called with convert_charrefs=True')
def handle_entityref(self, data):
self.fail('This should never be called with convert_charrefs=True')
# The normal event collector normalizes the events in get_events,
# so we override it to return the original list of events.
class EventCollectorNoNormalize(EventCollector):
def get_events(self):
return self.events
class TestCaseBase(unittest.TestCase):
def get_collector(self):
return EventCollector(convert_charrefs=False)
def _run_check(self, source, expected_events, collector=None):
if collector is None:
collector = self.get_collector()
parser = collector
for s in source:
parser.feed(s)
parser.close()
events = parser.get_events()
if events != expected_events:
self.fail("received events did not match expected events" +
"\nSource:\n" + repr(source) +
"\nExpected:\n" + pprint.pformat(expected_events) +
"\nReceived:\n" + pprint.pformat(events))
def _run_check_extra(self, source, events):
self._run_check(source, events,
EventCollectorExtra(convert_charrefs=False))
class HTMLParserTestCase(TestCaseBase):
def test_processing_instruction_only(self):
self._run_check("<?processing instruction>", [
("pi", "processing instruction"),
])
self._run_check("<?processing instruction ?>", [
("pi", "processing instruction ?"),
])
def test_simple_html(self):
self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity; 
<!--comment1a
-></foo><bar><<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
“
<!--comment2a-- --comment2b-->
</Html>
""", [
("data", "\n"),
("decl", "DOCTYPE html PUBLIC 'foo'"),
("data", "\n"),
("starttag", "html", []),
("entityref", "entity"),
("charref", "32"),
("data", "\n"),
("comment", "comment1a\n-></foo><bar><<?pi?></foo<bar\ncomment1b"),
("data", "\n"),
("starttag", "img", [("src", "Bar"), ("ismap", None)]),
("data", "sample\ntext\n"),
("charref", "x201C"),
("data", "\n"),
("comment", "comment2a-- --comment2b"),
("data", "\n"),
("endtag", "html"),
("data", "\n"),
])
def test_malformatted_charref(self):
self._run_check("<p>&#bad;</p>", [
("starttag", "p", []),
("data", "&#bad;"),
("endtag", "p"),
])
# add the [] as a workaround to avoid buffering (see #20288)
self._run_check(["<div>&#bad;</div>"], [
("starttag", "div", []),
("data", "&#bad;"),
("endtag", "div"),
])
def test_unclosed_entityref(self):
self._run_check("&entityref foo", [
("entityref", "entityref"),
("data", " foo"),
])
def test_bad_nesting(self):
# Strangely, this *is* supposed to test that overlapping
# elements are allowed. HTMLParser is more geared toward
# lexing the input that parsing the structure.
self._run_check("<a><b></a></b>", [
("starttag", "a", []),
("starttag", "b", []),
("endtag", "a"),
("endtag", "b"),
])
def test_bare_ampersands(self):
self._run_check("this text & contains & ampersands &", [
("data", "this text & contains & ampersands &"),
])
def test_bare_pointy_brackets(self):
self._run_check("this < text > contains < bare>pointy< brackets", [
("data", "this < text > contains < bare>pointy< brackets"),
])
def test_starttag_end_boundary(self):
self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])
def test_buffer_artefacts(self):
output = [("starttag", "a", [("b", "<")])]
self._run_check(["<a b='<'>"], output)
self._run_check(["<a ", "b='<'>"], output)
self._run_check(["<a b", "='<'>"], output)
self._run_check(["<a b=", "'<'>"], output)
self._run_check(["<a b='<", "'>"], output)
self._run_check(["<a b='<'", ">"], output)
output = [("starttag", "a", [("b", ">")])]
self._run_check(["<a b='>'>"], output)
self._run_check(["<a ", "b='>'>"], output)
self._run_check(["<a b", "='>'>"], output)
self._run_check(["<a b=", "'>'>"], output)
self._run_check(["<a b='>", "'>"], output)
self._run_check(["<a b='>'", ">"], output)
output = [("comment", "abc")]
self._run_check(["", "<!--abc-->"], output)
self._run_check(["<", "!--abc-->"], output)
self._run_check(["<!", "--abc-->"], output)
self._run_check(["<!-", "-abc-->"], output)
self._run_check(["<!--", "abc-->"], output)
self._run_check(["<!--a", "bc-->"], output)
self._run_check(["<!--ab", "c-->"], output)
self._run_check(["<!--abc", "-->"], output)
self._run_check(["<!--abc-", "->"], output)
self._run_check(["<!--abc--", ">"], output)
self._run_check(["<!--abc-->", ""], output)
def test_valid_doctypes(self):
# from http://www.w3.org/QA/2002/04/valid-dtd-list.html
dtds = ['HTML', # HTML5 doctype
('HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
'"http://www.w3.org/TR/html4/strict.dtd"'),
('HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" '
'"http://www.w3.org/TR/html4/loose.dtd"'),
('html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" '
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"'),
('html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" '
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"'),
('math PUBLIC "-//W3C//DTD MathML 2.0//EN" '
'"http://www.w3.org/Math/DTD/mathml2/mathml2.dtd"'),
('html PUBLIC "-//W3C//DTD '
'XHTML 1.1 plus MathML 2.0 plus SVG 1.1//EN" '
'"http://www.w3.org/2002/04/xhtml-math-svg/xhtml-math-svg.dtd"'),
('svg PUBLIC "-//W3C//DTD SVG 1.1//EN" '
'"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"'),
'html PUBLIC "-//IETF//DTD HTML 2.0//EN"',
'html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"']
for dtd in dtds:
self._run_check("<!DOCTYPE %s>" % dtd,
[('decl', 'DOCTYPE ' + dtd)])
def test_startendtag(self):
self._run_check("<p/>", [
("startendtag", "p", []),
])
self._run_check("<p></p>", [
("starttag", "p", []),
("endtag", "p"),
])
self._run_check("<p><img src='foo' /></p>", [
("starttag", "p", []),
("startendtag", "img", [("src", "foo")]),
("endtag", "p"),
])
def test_get_starttag_text(self):
s = """<foo:bar \n one="1"\ttwo=2 >"""
self._run_check_extra(s, [
("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
("starttag_text", s)])
@support.subTests('content', [
'<!-- not a comment --> ¬-an-entity-ref;',
"<not a='start tag'>",
'<a href="" /> <p> <span></span>',
'foo = "</scr" + "ipt>";',
'foo = "</SCRIPT" + ">";',
'foo = <\n/script> ',
'<!-- document.write("</scr" + "ipt>"); -->',
('\n//<![CDATA[\n'
'document.write(\'<s\'+\'cript type="text/javascript" '
'src="http://www.example.org/r=\'+new '
'Date().getTime()+\'"><\\/s\'+\'cript>\');\n//]]>'),
'\n<!-- //\nvar foo = 3.14;\n// -->\n',
'<!-- \u2603 -->',
'foo = "</ script>"',
'foo = "</scripture>"',
'foo = "</script\v>"',
'foo = "</script\xa0>"',
'foo = "</ſcript>"',
'foo = "</scrıpt>"',
])
def test_script_content(self, content):
s = f'<script>{content}</script>'
self._run_check(s, [("starttag", "script", []),
("data", content),
("endtag", "script")])
@support.subTests('content', [
'a::before { content: "<!-- not a comment -->"; }',
'a::before { content: "¬-an-entity-ref;"; }',
'a::before { content: "<not a=\'start tag\'>"; }',
'a::before { content: "\u2603"; }',
'a::before { content: "< /style>"; }',
'a::before { content: "</ style>"; }',
'a::before { content: "</styled>"; }',
'a::before { content: "</style\v>"; }',
'a::before { content: "</style\xa0>"; }',
'a::before { content: "</ſtyle>"; }',
])
def test_style_content(self, content):
s = f'<style>{content}</style>'
self._run_check(s, [("starttag", "style", []),
("data", content),
("endtag", "style")])
@support.subTests('endtag', ['script', 'SCRIPT', 'script ', 'script\n',
'script/', 'script foo=bar', 'script foo=">"'])
def test_script_closing_tag(self, endtag):
# see issue #13358
# make sure that HTMLParser calls handle_data only once for each CDATA.
content = """<!-- not a comment --> ¬-an-entity-ref;
<a href="" /> </p><p> <span></span></style>
'</script' + '>'"""
s = f'<ScrIPt>{content}</{endtag}>'
self._run_check(s, [("starttag", "script", []),
("data", content),
("endtag", "script")],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('endtag', ['style', 'STYLE', 'style ', 'style\n',
'style/', 'style foo=bar', 'style foo=">"'])
def test_style_closing_tag(self, endtag):
content = """
b::before { content: "<!-- not a comment -->"; }
p::before { content: "¬-an-entity-ref;"; }
a::before { content: "<i>"; }
a::after { content: "</i>"; }
"""
s = f'<StyLE>{content}</{endtag}>'
self._run_check(s, [("starttag", "style", []),
("data", content),
("endtag", "style")],
collector=EventCollectorNoNormalize(convert_charrefs=False))
@support.subTests('tail,end', [
('', False),
('<', False),
('</', False),
('</s', False),
('</script', False),
('</script ', True),
('</script foo=bar', True),
('</script foo=">', True),
])
def test_eof_in_script(self, tail, end):
content = "a = 123"
s = f'<ScrIPt>{content}{tail}'
self._run_check(s, [("starttag", "script", []),
("data", content if end else content + tail)],
collector=EventCollectorNoNormalize(convert_charrefs=False))
def test_comments(self):
html = ("<!-- I'm a valid comment -->"
'<!--me too!-->'
'<!------>'
'<!----->'
'<!---->'
# abrupt-closing-of-empty-comment
'<!--->'
'<!-->'
'<!----I have many hyphens---->'
'<!-- I have a > in the middle -->'
'<!-- and I have -- in the middle! -->'
'<!--incorrectly-closed-comment--!>'
'<!----!>'
'<!----!-->'
'<!---- >-->'
'<!---!>-->'
'<!--!>-->'
# nested-comment
'<!-- <!-- nested --> -->'
'<!--<!-->'
'<!--<!--!>'
)
expected = [('comment', " I'm a valid comment "),
('comment', 'me too!'),
('comment', '--'),
('comment', '-'),
('comment', ''),
('comment', ''),
('comment', ''),
('comment', '--I have many hyphens--'),
('comment', ' I have a > in the middle '),
('comment', ' and I have -- in the middle! '),
('comment', 'incorrectly-closed-comment'),
('comment', ''),
('comment', '--!'),
('comment', '-- >'),
('comment', '-!>'),
('comment', '!>'),
('comment', ' <!-- nested '), ('data', ' -->'),
('comment', '<!'),
('comment', '<!'),
]
self._run_check(html, expected)
def test_condcoms(self):
html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->'
'<!--[if IE 8]>condcoms<![endif]-->'
'<!--[if lte IE 7]>pretty?<![endif]-->')
expected = [('comment', "[if IE & !(lte IE 8)]>aren't<![endif]"),
('comment', '[if IE 8]>condcoms<![endif]'),
('comment', '[if lte IE 7]>pretty?<![endif]')]
self._run_check(html, expected)
def test_convert_charrefs(self):
# default value for convert_charrefs is now True
collector = lambda: EventCollectorCharrefs()
self.assertTrue(collector().convert_charrefs)
charrefs = ['"', '"', '"', '"', '"', '"']
# check charrefs in the middle of the text
expected = [('starttag', 'a', []), ('data', 'a"z'), ('endtag', 'a')]
for charref in charrefs:
self._run_check('<a>a{0}z</a>'.format(charref),
expected, collector=collector())
# check charrefs at the beginning/end of the text
expected = [('data', '"'), ('starttag', 'a', []),
('data', '"'), ('endtag', 'a'), ('data', '"')]
for charref in charrefs:
self._run_check('{0}<a>'
'{0}</a>{0}'.format(charref),
expected, collector=collector())
# check charrefs in <script>/<style> elements
for charref in charrefs:
text = 'X'.join([charref]*3)
expected = [('data', '"'),
('starttag', 'script', []), ('data', text),
('endtag', 'script'), ('data', '"'),
('starttag', 'style', []), ('data', text),
('endtag', 'style'), ('data', '"')]
self._run_check('{1}<script>{0}</script>{1}'
'<style>{0}</style>{1}'.format(text, charref),
expected, collector=collector())
# check truncated charrefs at the end of the file
html = '&quo &# &#x'
for x in range(1, len(html)):
self._run_check(html[:x], [('data', html[:x])],
collector=collector())
# check a string with no charrefs
self._run_check('no charrefs here', [('data', 'no charrefs here')],
collector=collector())
def test_convert_charrefs_in_attribute_values(self):
# default value for convert_charrefs is now True
collector = lambda: EventCollectorCharrefs()
self.assertTrue(collector().convert_charrefs)
# always unescape terminated entity refs, numeric and hex char refs:
# - regardless whether they are at start, middle, end of attribute
# - or followed by alphanumeric, non-alphanumeric, or equals char
charrefs = ['¢', '¢', '¢', '¢', '¢']
expected = [('starttag', 'a',
[('x', '¢'), ('x', 'z¢'), ('x', '¢z'),
('x', 'z¢z'), ('x', '¢ z'), ('x', '¢=z')]),
('endtag', 'a')]
for charref in charrefs:
self._run_check('<a x="{0}" x="z{0}" x="{0}z" '
' x="z{0}z" x="{0} z" x="{0}=z"></a>'
.format(charref), expected, collector=collector())
# only unescape unterminated entity matches if they are not followed by
# an alphanumeric or an equals sign
charref = '¢'
expected = [('starttag', 'a',
[('x', '¢'), ('x', 'z¢'), ('x', '¢z'),
('x', 'z¢z'), ('x', '¢ z'), ('x', '¢=z')]),
('endtag', 'a')]
self._run_check('<a x="{0}" x="z{0}" x="{0}z" '
' x="z{0}z" x="{0} z" x="{0}=z"></a>'
.format(charref), expected, collector=collector())
# the remaining tests were for the "tolerant" parser (which is now
# the default), and check various kind of broken markup
def test_tolerant_parsing(self):
self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
'<img src="URL><//img></html</html>', [
('starttag', 'html', [('<html', None)]),
('data', 'te>>xt'),
('entityref', 'a'),
('data', '<'),
('starttag', 'bc<', [('a', None)]),
('endtag', 'html'),
('data', '\n')])
def test_starttag_junk_chars(self):
self._run_check("<", [('data', '<')])
self._run_check("<>", [('data', '<>')])
self._run_check("< >", [('data', '< >')])
self._run_check("< ", [('data', '< ')])
self._run_check("</>", [])
self._run_check("<$>", [('data', '<$>')])
self._run_check("</$>", [('comment', '$')])
self._run_check("</", [('data', '</')])
self._run_check("</a", [])
self._run_check("</ a>", [('comment', ' a')])
self._run_check("</ a", [('comment', ' a')])
self._run_check("<a<a>", [('starttag', 'a<a', [])])
self._run_check("</a<a>", [('endtag', 'a<a')])
self._run_check("<!", [('comment', '')])
self._run_check("<a", [])
self._run_check("<a foo='bar'", [])
self._run_check("<a foo='bar", [])
self._run_check("<a foo='>'", [])
self._run_check("<a foo='>", [])
self._run_check("<a$>", [('starttag', 'a$', [])])
self._run_check("<a$b>", [('starttag', 'a$b', [])])
self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
self._run_check("<a$b >", [('starttag', 'a$b', [])])
self._run_check("<a$b />", [('startendtag', 'a$b', [])])
self._run_check("</a$b>", [('endtag', 'a$b')])
def test_slashes_in_starttag(self):
self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])
html = ('<img width=902 height=250px '
'src="/sites/default/files/images/homepage/foo.jpg" '
'/*what am I doing here*/ />')
expected = [(
'startendtag', 'img',
[('width', '902'), ('height', '250px'),
('src', '/sites/default/files/images/homepage/foo.jpg'),
('*what', None), ('am', None), ('i', None),
('doing', None), ('here*', None)]
)]
self._run_check(html, expected)
html = ('<a / /foo/ / /=/ / /bar/ / />'
'<a / /foo/ / /=/ / /bar/ / >')
expected = [
('startendtag', 'a', [('foo', None), ('=', None), ('bar', None)]),
('starttag', 'a', [('foo', None), ('=', None), ('bar', None)])
]
self._run_check(html, expected)
#see issue #14538
html = ('<meta><meta / ><meta // ><meta / / >'
'<meta/><meta /><meta //><meta//>')
expected = [
('starttag', 'meta', []), ('starttag', 'meta', []),
('starttag', 'meta', []), ('starttag', 'meta', []),
('startendtag', 'meta', []), ('startendtag', 'meta', []),
('startendtag', 'meta', []), ('startendtag', 'meta', []),
]
self._run_check(html, expected)
def test_slashes_in_endtag(self):
self._run_check('</a/>', [('endtag', 'a')])
self._run_check('</a foo="var"/>', [('endtag', 'a')])
def test_declaration_junk_chars(self):
self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])
def test_illegal_declarations(self):
self._run_check('<!spacer type="block" height="25">',
[('comment', 'spacer type="block" height="25"')])
def test_invalid_end_tags(self):
# A collection of broken end tags. <br> is used as separator.
# see http://www.w3.org/TR/html5/tokenization.html#end-tag-open-state
# and #13993
html = ('<br></label</p><br></div end tmAd-leaderBoard><br></<h4><br>'
'</li class="unit"><br></li\r\n\t\t\t\t\t\t</ul><br></><br>')
expected = [('starttag', 'br', []),
# < is part of the name, / is discarded, p is an attribute
('endtag', 'label<'),
('starttag', 'br', []),
# text and attributes are discarded
('endtag', 'div'),
('starttag', 'br', []),
# comment because the first char after </ is not a-zA-Z
('comment', '<h4'),
('starttag', 'br', []),
# attributes are discarded
('endtag', 'li'),
('starttag', 'br', []),
# everything till ul (included) is discarded
('endtag', 'li'),
('starttag', 'br', []),
# </> is ignored
('starttag', 'br', [])]
self._run_check(html, expected)
def test_broken_invalid_end_tag(self):
html = '<b>This</b attr=">"> confuses the parser'
expected = [('starttag', 'b', []),
('data', 'This'),
('endtag', 'b'),
('data', ' confuses the parser')]
self._run_check(html, expected)
def test_correct_detection_of_start_tags(self):
# see #13273
html = ('<div style="" ><b>The <a href="some_url">rain</a> '
'<br /> in <span>Spain</span></b></div>')
expected = [
('starttag', 'div', [('style', '')]),
('starttag', 'b', []),
('data', 'The '),
('starttag', 'a', [('href', 'some_url')]),
('data', 'rain'),
('endtag', 'a'),
('data', ' '),
('startendtag', 'br', []),
('data', ' in '),
('starttag', 'span', []),
('data', 'Spain'),
('endtag', 'span'),
('endtag', 'b'),
('endtag', 'div')
]
self._run_check(html, expected)
html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>'
expected = [
('starttag', 'div', [('style', ''), (',', None), ('foo', None), ('=', None), ('"bar"', None)]),
('starttag', 'b', []),
('data', 'The '),
('starttag', 'a', [('href', 'some_url')]),
('data', 'rain'),
('endtag', 'a'),
]
self._run_check(html, expected)
def test_EOF_in_charref(self):
# see #17802
# This test checks that the UnboundLocalError reported in the issue
# is not raised, however I'm not sure the returned values are correct.
# Maybe HTMLParser should use self.unescape for these
data = [
('a&', [('data', 'a&')]),
('a&b', [('data', 'ab')]),
('a&b ', [('data', 'a'), ('entityref', 'b'), ('data', ' ')]),
('a&b;', [('data', 'a'), ('entityref', 'b')]),
]
for html, expected in data:
self._run_check(html, expected)
def test_eof_in_comments(self):
data = [
('<!--', [('comment', '')]),
('<!---', [('comment', '')]),
('<!----', [('comment', '')]),
('<!-----', [('comment', '-')]),
('<!------', [('comment', '--')]),
('<!----!', [('comment', '')]),
('<!---!', [('comment', '-!')]),
('<!---!>', [('comment', '-!>')]),
('<!--foo', [('comment', 'foo')]),
('<!--foo-', [('comment', 'foo')]),
('<!--foo--', [('comment', 'foo')]),
('<!--foo--!', [('comment', 'foo')]),
('<!--<!--', [('comment', '<!')]),
('<!--<!--!', [('comment', '<!')]),
]
for html, expected in data:
self._run_check(html, expected)
def test_eof_in_declarations(self):
data = [
('<!', [('comment', '')]),
('<!-', [('comment', '-')]),
('<![', [('comment', '[')]),
('<![CDATA[', [('unknown decl', 'CDATA[')]),
('<![CDATA[x', [('unknown decl', 'CDATA[x')]),
('<![CDATA[x]', [('unknown decl', 'CDATA[x]')]),
('<![CDATA[x]]', [('unknown decl', 'CDATA[x]]')]),
('<!DOCTYPE', [('decl', 'DOCTYPE')]),
('<!DOCTYPE ', [('decl', 'DOCTYPE ')]),
('<!DOCTYPE html', [('decl', 'DOCTYPE html')]),
('<!DOCTYPE html ', [('decl', 'DOCTYPE html ')]),
('<!DOCTYPE html PUBLIC', [('decl', 'DOCTYPE html PUBLIC')]),
('<!DOCTYPE html PUBLIC "foo', [('decl', 'DOCTYPE html PUBLIC "foo')]),
('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo',
[('decl', 'DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo')]),
]
for html, expected in data:
self._run_check(html, expected)
def test_bogus_comments(self):
html = ('<!ELEMENT br EMPTY>'
'<! not really a comment >'
'<! not a comment either -->'
'<! -- close enough -->'
'<!><!<-- this was an empty comment>'
'<!!! another bogus comment !!!>'
# see #32876
'<![with square brackets]!>'
'<![\nmultiline\nbogusness\n]!>'
'<![more brackets]-[and a hyphen]!>'
'<![cdata[should be uppercase]]>'
'<![CDATA [whitespaces are not ignored]]>'
'<![CDATA]]>' # required '[' after CDATA
)
expected = [
('comment', 'ELEMENT br EMPTY'),
('comment', ' not really a comment '),
('comment', ' not a comment either --'),
('comment', ' -- close enough --'),
('comment', ''),
('comment', '<-- this was an empty comment'),
('comment', '!! another bogus comment !!!'),
('comment', '[with square brackets]!'),
('comment', '[\nmultiline\nbogusness\n]!'),
('comment', '[more brackets]-[and a hyphen]!'),
('comment', '[cdata[should be uppercase]]'),
('comment', '[CDATA [whitespaces are not ignored]]'),
('comment', '[CDATA]]'),
]
self._run_check(html, expected)
def test_broken_condcoms(self):
# these condcoms are missing the '--' after '<!' and before the '>'
# and they are considered bogus comments according to
# "8.2.4.42. Markup declaration open state"
html = ('<![if !(IE)]>broken condcom<![endif]>'
'<![if ! IE]><link href="favicon.tiff"/><![endif]>'
'<![if !IE 6]><img src="firefox.png" /><![endif]>'
'<![if !ie 6]><b>foo</b><![endif]>'
'<![if (!IE)|(lt IE 9)]><img src="mammoth.bmp" /><![endif]>')
expected = [
('comment', '[if !(IE)]'),
('data', 'broken condcom'),
('comment', '[endif]'),
('comment', '[if ! IE]'),
('startendtag', 'link', [('href', 'favicon.tiff')]),
('comment', '[endif]'),
('comment', '[if !IE 6]'),
('startendtag', 'img', [('src', 'firefox.png')]),
('comment', '[endif]'),
('comment', '[if !ie 6]'),
('starttag', 'b', []),
('data', 'foo'),
('endtag', 'b'),
('comment', '[endif]'),
('comment', '[if (!IE)|(lt IE 9)]'),
('startendtag', 'img', [('src', 'mammoth.bmp')]),
('comment', '[endif]')
]
self._run_check(html, expected)
def test_cdata_declarations(self):
# More tests should be added. See also "8.2.4.42. Markup
# declaration open state", "8.2.4.69. CDATA section state",
# and issue 32876
html = ('<![CDATA[just some plain text]]>')
expected = [('unknown decl', 'CDATA[just some plain text')]
self._run_check(html, expected)
def test_cdata_declarations_multiline(self):
html = ('<code><![CDATA['
' if (a < b && a > b) {'
' printf("[<marquee>How?</marquee>]");'
' }'
']]></code>')
expected = [
('starttag', 'code', []),
('unknown decl',
'CDATA[ if (a < b && a > b) { '
'printf("[<marquee>How?</marquee>]"); }'),
('endtag', 'code')
]
self._run_check(html, expected)
def test_convert_charrefs_dropped_text(self):
# #23144: make sure that all the events are triggered when
# convert_charrefs is True, even if we don't call .close()
parser = EventCollector(convert_charrefs=True)
# before the fix, bar & baz was missing
parser.feed("foo <a>link</a> bar & baz")
self.assertEqual(
parser.get_events(),
[('data', 'foo '), ('starttag', 'a', []), ('data', 'link'),
('endtag', 'a'), ('data', ' bar & baz')]
)
@support.requires_resource('cpu')
def test_eof_no_quadratic_complexity(self):
# Each of these examples used to take about an hour.
# Now they take a fraction of a second.
def check(source):
parser = html.parser.HTMLParser()
parser.feed(source)
parser.close()
n = 120_000
check("<a " * n)
check("<a a=" * n)
check("</a " * 14 * n)
check("</a a=" * 11 * n)
check("<!--" * 4 * n)
check("<!" * 60 * n)
check("<?" * 19 * n)
check("</$" * 15 * n)
check("<![CDATA[" * 9 * n)
check("<!doctype" * 35 * n)
class AttributesTestCase(TestCaseBase):
def test_attr_syntax(self):
output = [
("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
]
self._run_check("""<a b='v' c="v" d=v e>""", output)
self._run_check("<a foo==bar>", [('starttag', 'a', [('foo', '=bar')])])
self._run_check("<a foo =bar>", [('starttag', 'a', [('foo', None), ('=bar', None)])])
self._run_check("<a foo\t=bar>", [('starttag', 'a', [('foo', None), ('=bar', None)])])
self._run_check("<a foo\v=bar>", [('starttag', 'a', [('foo\v', 'bar')])])
self._run_check("<a foo\xa0=bar>", [('starttag', 'a', [('foo\xa0', 'bar')])])
self._run_check("<a foo= bar>", [('starttag', 'a', [('foo', ''), ('bar', None)])])
self._run_check("<a foo=\tbar>", [('starttag', 'a', [('foo', ''), ('bar', None)])])
self._run_check("<a foo=\vbar>", [('starttag', 'a', [('foo', '\vbar')])])
self._run_check("<a foo=\xa0bar>", [('starttag', 'a', [('foo', '\xa0bar')])])
def test_attr_values(self):
self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
[("starttag", "a", [("b", "xxx\n\txxx"),
("c", "yyy\t\nyyy"),
("d", "\txyz\n")])])
self._run_check("""<a b='' c="">""",
[("starttag", "a", [("b", ""), ("c", "")])])
self._run_check("<a b=\t c=\n>",
[("starttag", "a", [("b", ""), ("c", "")])])
self._run_check("<a b=\v c=\xa0>",
[("starttag", "a", [("b", "\v"), ("c", "\xa0")])])
# Regression test for SF patch #669683.
self._run_check("<e a=rgb(1,2,3)>",
[("starttag", "e", [("a", "rgb(1,2,3)")])])
# Regression test for SF bug #921657.
self._run_check(
"<a href=mailto:xyz@example.com>",
[("starttag", "a", [("href", "mailto:xyz@example.com")])])
def test_attr_nonascii(self):
# see issue 7311
self._run_check(
"<img src=/foo/bar.png alt=\u4e2d\u6587>",
[("starttag", "img", [("src", "/foo/bar.png"),
("alt", "\u4e2d\u6587")])])
self._run_check(
"<a title='\u30c6\u30b9\u30c8' href='\u30c6\u30b9\u30c8.html'>",
[("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
("href", "\u30c6\u30b9\u30c8.html")])])
self._run_check(
'<a title="\u30c6\u30b9\u30c8" href="\u30c6\u30b9\u30c8.html">',
[("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
("href", "\u30c6\u30b9\u30c8.html")])])
def test_attr_entity_replacement(self):
self._run_check(
"<a b='&><"''>",
[("starttag", "a", [("b", "&><\"'")])])
def test_attr_funky_names(self):
self._run_check(
"<a a.b='v' c:d=v e-f=v>",
[("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")])])
def test_entityrefs_in_attributes(self):
self._run_check(
"<html foo='€&aa&unsupported;'>",
[("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])])
def test_attr_funky_names2(self):
self._run_check(
r"<a $><b $=%><c \=/>",
[("starttag", "a", [("$", None)]),
("starttag", "b", [("$", "%")]),
("starttag", "c", [("\\", "/")])])
def test_entities_in_attribute_value(self):
# see #1200313
for entity in ['&', '&', '&', '&']:
self._run_check('<a href="%s">' % entity,
[("starttag", "a", [("href", "&")])])
self._run_check("<a href='%s'>" % entity,
[("starttag", "a", [("href", "&")])])
self._run_check("<a href=%s>" % entity,
[("starttag", "a", [("href", "&")])])
def test_malformed_attributes(self):
# see #13357
html = (
"<a href=test'style='color:red;bad1'>test - bad1</a>"
"<a href=test'+style='color:red;ba2'>test - bad2</a>"
"<a href=test' style='color:red;bad3'>test - bad3</a>"
"<a href = test' style='color:red;bad4' >test - bad4</a>"
)
expected = [
('starttag', 'a', [('href', "test'style='color:red;bad1'")]),
('data', 'test - bad1'), ('endtag', 'a'),
('starttag', 'a', [('href', "test'+style='color:red;ba2'")]),
('data', 'test - bad2'), ('endtag', 'a'),
('starttag', 'a', [('href', "test'\xa0style='color:red;bad3'")]),
('data', 'test - bad3'), ('endtag', 'a'),
('starttag', 'a', [('href', None), ('=', None), ("test' style", 'color:red;bad4')]),
('data', 'test - bad4'), ('endtag', 'a')
]
self._run_check(html, expected)
def test_malformed_adjacent_attributes(self):
# see #12629
self._run_check('<x><y z=""o"" /></x>',
[('starttag', 'x', []),
('startendtag', 'y', [('z', ''), ('o""', None)]),
('endtag', 'x')])
self._run_check('<x><y z="""" /></x>',
[('starttag', 'x', []),
('startendtag', 'y', [('z', ''), ('""', None)]),
('endtag', 'x')])
# see #755670 for the following 3 tests
def test_adjacent_attributes(self):
self._run_check('<a width="100%"cellspacing=0>',
[("starttag", "a",
[("width", "100%"), ("cellspacing","0")])])
self._run_check('<a id="foo"class="bar">',
[("starttag", "a",
[("id", "foo"), ("class","bar")])])
def test_missing_attribute_value(self):
self._run_check('<a v=>',
[("starttag", "a", [("v", "")])])
def test_javascript_attribute_value(self):
self._run_check("<a href=javascript:popup('/popup/help.html')>",
[("starttag", "a",
[("href", "javascript:popup('/popup/help.html')")])])
def test_end_tag_in_attribute_value(self):
# see #1745761
self._run_check("<a href='http://www.example.org/\">;'>spam</a>",
[("starttag", "a",
[("href", "http://www.example.org/\">;")]),
("data", "spam"), ("endtag", "a")])
def test_with_unquoted_attributes(self):
# see #12008
html = ("<html><body bgcolor=d0ca90 text='181008'>"
"<table cellspacing=0 cellpadding=1 width=100% ><tr>"
"<td align=left><font size=-1>"
"- <a href=/rabota/><span class=en> software-and-i</span></a>"
"- <a href='/1/'><span class=en> library</span></a></table>")
expected = [
('starttag', 'html', []),
('starttag', 'body', [('bgcolor', 'd0ca90'), ('text', '181008')]),
('starttag', 'table',
[('cellspacing', '0'), ('cellpadding', '1'), ('width', '100%')]),
('starttag', 'tr', []),
('starttag', 'td', [('align', 'left')]),
('starttag', 'font', [('size', '-1')]),
('data', '- '), ('starttag', 'a', [('href', '/rabota/')]),
('starttag', 'span', [('class', 'en')]), ('data', ' software-and-i'),
('endtag', 'span'), ('endtag', 'a'),
('data', '- '), ('starttag', 'a', [('href', '/1/')]),
('starttag', 'span', [('class', 'en')]), ('data', ' library'),
('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table')
]
self._run_check(html, expected)
def test_comma_between_attributes(self):
# see bpo 41478
# HTMLParser preserves duplicate attributes, leaving the task of
# removing duplicate attributes to a conformant html tree builder
html = ('<div class=bar,baz=asd>' # between attrs (unquoted)
'<div class="bar",baz="asd">' # between attrs (quoted)
'<div class=bar, baz=asd,>' # after values (unquoted)
'<div class="bar", baz="asd",>' # after values (quoted)
'<div class="bar",>' # one comma values (quoted)
'<div class=,bar baz=,asd>' # before values (unquoted)
'<div class=,"bar" baz=,"asd">' # before values (quoted)
'<div ,class=bar ,baz=asd>' # before names
'<div class,="bar" baz,="asd">' # after names
)
expected = [
('starttag', 'div', [('class', 'bar,baz=asd'),]),
('starttag', 'div', [('class', 'bar'), (',baz', 'asd')]),
('starttag', 'div', [('class', 'bar,'), ('baz', 'asd,')]),
('starttag', 'div', [('class', 'bar'), (',', None),
('baz', 'asd'), (',', None)]),
('starttag', 'div', [('class', 'bar'), (',', None)]),
('starttag', 'div', [('class', ',bar'), ('baz', ',asd')]),
('starttag', 'div', [('class', ',"bar"'), ('baz', ',"asd"')]),
('starttag', 'div', [(',class', 'bar'), (',baz', 'asd')]),
('starttag', 'div', [('class,', 'bar'), ('baz,', 'asd')]),
]
self._run_check(html, expected)