Repository navigation
Expand file tree
/
Copy pathtest__header_value_parser.py
More file actions
3030 lines (2619 loc) · 126 KB
/
Copy pathtest__header_value_parser.py
File metadata and controls
3030 lines (2619 loc) · 126 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
import string
import unittest
from email import _header_value_parser as parser
from email import errors
from email import policy
from test.test_email import TestEmailBase, parameterize
class TestTokens(TestEmailBase):
# EWWhiteSpaceTerminal
def test_EWWhiteSpaceTerminal(self):
x = parser.EWWhiteSpaceTerminal(' \t', 'fws')
self.assertEqual(x, ' \t')
self.assertEqual(str(x), '')
self.assertEqual(x.value, '')
self.assertEqual(x.token_type, 'fws')
class TestParserMixin:
def _assert_results(self, tl, rest, string, value, defects, remainder,
comments=None):
self.assertEqual(str(tl), string)
self.assertEqual(tl.value, value)
self.assertDefectsEqual(tl.all_defects, defects)
self.assertEqual(rest, remainder)
if comments is not None:
self.assertEqual(tl.comments, comments)
def _test_get_x(self, method, source, string, value, defects,
remainder, comments=None):
tl, rest = method(source)
self._assert_results(tl, rest, string, value, defects, remainder,
comments=None)
return tl
def _test_parse_x(self, method, input, string, value, defects,
comments=None):
tl = method(input)
self._assert_results(tl, '', string, value, defects, '', comments)
return tl
class TestParser(TestParserMixin, TestEmailBase):
# _wsp_splitter
rfc_printable_ascii = bytes(range(33, 127)).decode('ascii')
rfc_atext_chars = (string.ascii_letters + string.digits +
"!#$%&\'*+-/=?^_`{}|~")
rfc_dtext_chars = rfc_printable_ascii.translate(str.maketrans('','',r'\[]'))
def test__wsp_splitter_one_word(self):
self.assertEqual(parser._wsp_splitter('foo', 1), ['foo'])
def test__wsp_splitter_two_words(self):
self.assertEqual(parser._wsp_splitter('foo def', 1),
['foo', ' ', 'def'])
def test__wsp_splitter_ws_runs(self):
self.assertEqual(parser._wsp_splitter('foo \t def jik', 1),
['foo', ' \t ', 'def jik'])
# get_fws
def test_get_fws_only(self):
fws = self._test_get_x(parser.get_fws, ' \t ', ' \t ', ' ', [], '')
self.assertEqual(fws.token_type, 'fws')
def test_get_fws_space(self):
self._test_get_x(parser.get_fws, ' foo', ' ', ' ', [], 'foo')
def test_get_fws_ws_run(self):
self._test_get_x(parser.get_fws, ' \t foo ', ' \t ', ' ', [], 'foo ')
# get_encoded_word
def test_get_encoded_word_missing_start_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_encoded_word('abc')
def test_get_encoded_word_missing_end_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_encoded_word('=?abc')
def test_get_encoded_word_missing_middle_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_encoded_word('=?abc?=')
def test_get_encoded_word_invalid_cte(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_encoded_word('=?utf-8?X?somevalue?=')
def test_get_encoded_word_valid_ew(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?this_is_a_test?= bird',
'this is a test',
'this is a test',
[],
' bird')
def test_get_encoded_word_internal_spaces(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?this is a test?= bird',
'this is a test',
'this is a test',
[errors.InvalidHeaderDefect],
' bird')
def test_get_encoded_word_gets_first(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?first?= =?utf-8?q?second?=',
'first',
'first',
[],
' =?utf-8?q?second?=')
def test_get_encoded_word_gets_first_even_if_no_space(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?first?==?utf-8?q?second?=',
'first',
'first',
[errors.InvalidHeaderDefect],
'=?utf-8?q?second?=')
def test_get_encoded_word_sets_extra_attributes(self):
ew = self._test_get_x(parser.get_encoded_word,
'=?us-ascii*jive?q?first_second?=',
'first second',
'first second',
[],
'')
self.assertEqual(ew.charset, 'us-ascii')
self.assertEqual(ew.lang, 'jive')
def test_get_encoded_word_lang_default_is_blank(self):
ew = self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?first_second?=',
'first second',
'first second',
[],
'')
self.assertEqual(ew.charset, 'us-ascii')
self.assertEqual(ew.lang, '')
def test_get_encoded_word_non_printable_defect(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?first\x02second?=',
'first\x02second',
'first\x02second',
[errors.NonPrintableDefect],
'')
def test_get_encoded_word_leading_internal_space(self):
self._test_get_x(parser.get_encoded_word,
'=?us-ascii?q?=20foo?=',
' foo',
' foo',
[],
'')
def test_get_encoded_word_quopri_utf_escape_follows_cte(self):
# Issue 18044
self._test_get_x(parser.get_encoded_word,
'=?utf-8?q?=C3=89ric?=',
'Éric',
'Éric',
[],
'')
# get_unstructured
def _get_unst(self, value):
token = parser.get_unstructured(value)
return token, ''
def test_get_unstructured_null(self):
self._test_get_x(self._get_unst, '', '', '', [], '')
def test_get_unstructured_one_word(self):
self._test_get_x(self._get_unst, 'foo', 'foo', 'foo', [], '')
def test_get_unstructured_normal_phrase(self):
self._test_get_x(self._get_unst, 'foo bar bird',
'foo bar bird',
'foo bar bird',
[],
'')
def test_get_unstructured_normal_phrase_with_whitespace(self):
self._test_get_x(self._get_unst, 'foo \t bar bird',
'foo \t bar bird',
'foo bar bird',
[],
'')
def test_get_unstructured_leading_whitespace(self):
self._test_get_x(self._get_unst, ' foo bar',
' foo bar',
' foo bar',
[],
'')
def test_get_unstructured_trailing_whitespace(self):
self._test_get_x(self._get_unst, 'foo bar ',
'foo bar ',
'foo bar ',
[],
'')
def test_get_unstructured_leading_and_trailing_whitespace(self):
self._test_get_x(self._get_unst, ' foo bar ',
' foo bar ',
' foo bar ',
[],
'')
def test_get_unstructured_one_valid_ew_no_ws(self):
self._test_get_x(self._get_unst, '=?us-ascii?q?bar?=',
'bar',
'bar',
[],
'')
def test_get_unstructured_one_ew_trailing_ws(self):
self._test_get_x(self._get_unst, '=?us-ascii?q?bar?= ',
'bar ',
'bar ',
[],
'')
def test_get_unstructured_one_valid_ew_trailing_text(self):
self._test_get_x(self._get_unst, '=?us-ascii?q?bar?= bird',
'bar bird',
'bar bird',
[],
'')
def test_get_unstructured_phrase_with_ew_in_middle_of_text(self):
self._test_get_x(self._get_unst, 'foo =?us-ascii?q?bar?= bird',
'foo bar bird',
'foo bar bird',
[],
'')
def test_get_unstructured_phrase_with_two_ew(self):
self._test_get_x(self._get_unst,
'foo =?us-ascii?q?bar?= =?us-ascii?q?bird?=',
'foo barbird',
'foo barbird',
[],
'')
def test_get_unstructured_phrase_with_two_ew_trailing_ws(self):
self._test_get_x(self._get_unst,
'foo =?us-ascii?q?bar?= =?us-ascii?q?bird?= ',
'foo barbird ',
'foo barbird ',
[],
'')
def test_get_unstructured_phrase_with_ew_with_leading_ws(self):
self._test_get_x(self._get_unst,
' =?us-ascii?q?bar?=',
' bar',
' bar',
[],
'')
def test_get_unstructured_phrase_with_two_ew_extra_ws(self):
self._test_get_x(self._get_unst,
'foo =?us-ascii?q?bar?= \t =?us-ascii?q?bird?=',
'foo barbird',
'foo barbird',
[],
'')
def test_get_unstructured_two_ew_extra_ws_trailing_text(self):
self._test_get_x(self._get_unst,
'=?us-ascii?q?test?= =?us-ascii?q?foo?= val',
'testfoo val',
'testfoo val',
[],
'')
def test_get_unstructured_ew_with_internal_ws(self):
self._test_get_x(self._get_unst,
'=?iso-8859-1?q?hello=20world?=',
'hello world',
'hello world',
[],
'')
def test_get_unstructured_ew_with_internal_leading_ws(self):
self._test_get_x(self._get_unst,
' =?us-ascii?q?=20test?= =?us-ascii?q?=20foo?= val',
' test foo val',
' test foo val',
[],
'')
def test_get_unstructured_invalid_ew(self):
self._test_get_x(self._get_unst,
'=?test val',
'=?test val',
'=?test val',
[],
'')
def test_get_unstructured_undecodable_bytes(self):
self._test_get_x(self._get_unst,
b'test \xACfoo val'.decode('ascii', 'surrogateescape'),
'test \uDCACfoo val',
'test \uDCACfoo val',
[errors.UndecodableBytesDefect],
'')
def test_get_unstructured_undecodable_bytes_in_EW(self):
self._test_get_x(self._get_unst,
(b'=?us-ascii?q?=20test?= =?us-ascii?q?=20\xACfoo?='
b' val').decode('ascii', 'surrogateescape'),
' test \uDCACfoo val',
' test \uDCACfoo val',
[errors.UndecodableBytesDefect]*2,
'')
def test_get_unstructured_missing_base64_padding(self):
self._test_get_x(self._get_unst,
'=?utf-8?b?dmk?=',
'vi',
'vi',
[errors.InvalidBase64PaddingDefect],
'')
def test_get_unstructured_invalid_base64_character(self):
self._test_get_x(self._get_unst,
'=?utf-8?b?dm\x01k===?=',
'vi',
'vi',
[errors.InvalidBase64CharactersDefect],
'')
def test_get_unstructured_invalid_base64_character_and_bad_padding(self):
self._test_get_x(self._get_unst,
'=?utf-8?b?dm\x01k?=',
'vi',
'vi',
[errors.InvalidBase64CharactersDefect,
errors.InvalidBase64PaddingDefect],
'')
def test_get_unstructured_invalid_base64_length(self):
# bpo-27397: Return the encoded string since there's no way to decode.
self._test_get_x(self._get_unst,
'=?utf-8?b?abcde?=',
'abcde',
'abcde',
[errors.InvalidBase64LengthDefect],
'')
def test_get_unstructured_no_whitespace_between_ews(self):
self._test_get_x(self._get_unst,
'=?utf-8?q?foo?==?utf-8?q?bar?=',
'foobar',
'foobar',
[errors.InvalidHeaderDefect,
errors.InvalidHeaderDefect],
'')
def test_get_unstructured_ew_without_leading_whitespace(self):
self._test_get_x(
self._get_unst,
'nowhitespace=?utf-8?q?somevalue?=',
'nowhitespacesomevalue',
'nowhitespacesomevalue',
[errors.InvalidHeaderDefect],
'')
def test_get_unstructured_ew_without_trailing_whitespace(self):
self._test_get_x(
self._get_unst,
'=?utf-8?q?somevalue?=nowhitespace',
'somevaluenowhitespace',
'somevaluenowhitespace',
[errors.InvalidHeaderDefect],
'')
def test_get_unstructured_without_trailing_whitespace_hang_case(self):
self._test_get_x(self._get_unst,
'=?utf-8?q?somevalue?=aa',
'somevalueaa',
'somevalueaa',
[errors.InvalidHeaderDefect],
'')
def test_get_unstructured_invalid_ew2(self):
self._test_get_x(self._get_unst,
'=?utf-8?q?=somevalue?=',
'=?utf-8?q?=somevalue?=',
'=?utf-8?q?=somevalue?=',
[],
'')
def test_get_unstructured_invalid_ew_cte(self):
self._test_get_x(self._get_unst,
'=?utf-8?X?=somevalue?=',
'=?utf-8?X?=somevalue?=',
'=?utf-8?X?=somevalue?=',
[],
'')
# get_qp_ctext
def test_get_qp_ctext_only(self):
ptext = self._test_get_x(parser.get_qp_ctext,
'foobar', 'foobar', ' ', [], '')
self.assertEqual(ptext.token_type, 'ptext')
def test_get_qp_ctext_all_printables(self):
with_qp = self.rfc_printable_ascii.replace('\\', '\\\\')
with_qp = with_qp. replace('(', r'\(')
with_qp = with_qp.replace(')', r'\)')
ptext = self._test_get_x(parser.get_qp_ctext,
with_qp, self.rfc_printable_ascii, ' ', [], '')
def test_get_qp_ctext_two_words_gets_first(self):
self._test_get_x(parser.get_qp_ctext,
'foo de', 'foo', ' ', [], ' de')
def test_get_qp_ctext_following_wsp_preserved(self):
self._test_get_x(parser.get_qp_ctext,
'foo \t\tde', 'foo', ' ', [], ' \t\tde')
def test_get_qp_ctext_up_to_close_paren_only(self):
self._test_get_x(parser.get_qp_ctext,
'foo)', 'foo', ' ', [], ')')
def test_get_qp_ctext_wsp_before_close_paren_preserved(self):
self._test_get_x(parser.get_qp_ctext,
'foo )', 'foo', ' ', [], ' )')
def test_get_qp_ctext_close_paren_mid_word(self):
self._test_get_x(parser.get_qp_ctext,
'foo)bar', 'foo', ' ', [], ')bar')
def test_get_qp_ctext_up_to_open_paren_only(self):
self._test_get_x(parser.get_qp_ctext,
'foo(', 'foo', ' ', [], '(')
def test_get_qp_ctext_wsp_before_open_paren_preserved(self):
self._test_get_x(parser.get_qp_ctext,
'foo (', 'foo', ' ', [], ' (')
def test_get_qp_ctext_open_paren_mid_word(self):
self._test_get_x(parser.get_qp_ctext,
'foo(bar', 'foo', ' ', [], '(bar')
def test_get_qp_ctext_non_printables(self):
ptext = self._test_get_x(parser.get_qp_ctext,
'foo\x00bar)', 'foo\x00bar', ' ',
[errors.NonPrintableDefect], ')')
self.assertEqual(ptext.defects[0].non_printables[0], '\x00')
# get_qcontent
def test_get_qcontent_only(self):
ptext = self._test_get_x(parser.get_qcontent,
'foobar', 'foobar', 'foobar', [], '')
self.assertEqual(ptext.token_type, 'ptext')
def test_get_qcontent_all_printables(self):
with_qp = self.rfc_printable_ascii.replace('\\', '\\\\')
with_qp = with_qp. replace('"', r'\"')
ptext = self._test_get_x(parser.get_qcontent, with_qp,
self.rfc_printable_ascii,
self.rfc_printable_ascii, [], '')
def test_get_qcontent_two_words_gets_first(self):
self._test_get_x(parser.get_qcontent,
'foo de', 'foo', 'foo', [], ' de')
def test_get_qcontent_following_wsp_preserved(self):
self._test_get_x(parser.get_qcontent,
'foo \t\tde', 'foo', 'foo', [], ' \t\tde')
def test_get_qcontent_up_to_dquote_only(self):
self._test_get_x(parser.get_qcontent,
'foo"', 'foo', 'foo', [], '"')
def test_get_qcontent_wsp_before_close_paren_preserved(self):
self._test_get_x(parser.get_qcontent,
'foo "', 'foo', 'foo', [], ' "')
def test_get_qcontent_close_paren_mid_word(self):
self._test_get_x(parser.get_qcontent,
'foo"bar', 'foo', 'foo', [], '"bar')
def test_get_qcontent_non_printables(self):
ptext = self._test_get_x(parser.get_qcontent,
'foo\x00fg"', 'foo\x00fg', 'foo\x00fg',
[errors.NonPrintableDefect], '"')
self.assertEqual(ptext.defects[0].non_printables[0], '\x00')
# get_atext
def test_get_atext_only(self):
atext = self._test_get_x(parser.get_atext,
'foobar', 'foobar', 'foobar', [], '')
self.assertEqual(atext.token_type, 'atext')
def test_get_atext_all_atext(self):
atext = self._test_get_x(parser.get_atext, self.rfc_atext_chars,
self.rfc_atext_chars,
self.rfc_atext_chars, [], '')
def test_get_atext_two_words_gets_first(self):
self._test_get_x(parser.get_atext,
'foo bar', 'foo', 'foo', [], ' bar')
def test_get_atext_following_wsp_preserved(self):
self._test_get_x(parser.get_atext,
'foo \t\tbar', 'foo', 'foo', [], ' \t\tbar')
def test_get_atext_up_to_special(self):
self._test_get_x(parser.get_atext,
'foo@bar', 'foo', 'foo', [], '@bar')
def test_get_atext_non_printables(self):
atext = self._test_get_x(parser.get_atext,
'foo\x00bar(', 'foo\x00bar', 'foo\x00bar',
[errors.NonPrintableDefect], '(')
self.assertEqual(atext.defects[0].non_printables[0], '\x00')
# get_bare_quoted_string
def test_get_bare_quoted_string_only(self):
bqs = self._test_get_x(parser.get_bare_quoted_string,
'"foo"', '"foo"', 'foo', [], '')
self.assertEqual(bqs.token_type, 'bare-quoted-string')
def test_get_bare_quoted_string_must_start_with_dquote(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_bare_quoted_string('foo"')
with self.assertRaises(errors.HeaderParseError):
parser.get_bare_quoted_string(' "foo"')
def test_get_bare_quoted_string_only_quotes(self):
self._test_get_x(parser.get_bare_quoted_string,
'""', '""', '', [], '')
def test_get_bare_quoted_string_missing_endquotes(self):
self._test_get_x(parser.get_bare_quoted_string,
'"', '""', '', [errors.InvalidHeaderDefect], '')
def test_get_bare_quoted_string_following_wsp_preserved(self):
self._test_get_x(parser.get_bare_quoted_string,
'"foo"\t bar', '"foo"', 'foo', [], '\t bar')
def test_get_bare_quoted_string_multiple_words(self):
self._test_get_x(parser.get_bare_quoted_string,
'"foo bar moo"', '"foo bar moo"', 'foo bar moo', [], '')
def test_get_bare_quoted_string_multiple_words_wsp_preserved(self):
self._test_get_x(parser.get_bare_quoted_string,
'" foo moo\t"', '" foo moo\t"', ' foo moo\t', [], '')
def test_get_bare_quoted_string_end_dquote_mid_word(self):
self._test_get_x(parser.get_bare_quoted_string,
'"foo"bar', '"foo"', 'foo', [], 'bar')
def test_get_bare_quoted_string_quoted_dquote(self):
self._test_get_x(parser.get_bare_quoted_string,
r'"foo\"in"a', r'"foo\"in"', 'foo"in', [], 'a')
def test_get_bare_quoted_string_non_printables(self):
self._test_get_x(parser.get_bare_quoted_string,
'"a\x01a"', '"a\x01a"', 'a\x01a',
[errors.NonPrintableDefect], '')
def test_get_bare_quoted_string_no_end_dquote(self):
self._test_get_x(parser.get_bare_quoted_string,
'"foo', '"foo"', 'foo',
[errors.InvalidHeaderDefect], '')
self._test_get_x(parser.get_bare_quoted_string,
'"foo ', '"foo "', 'foo ',
[errors.InvalidHeaderDefect], '')
def test_get_bare_quoted_string_empty_quotes(self):
self._test_get_x(parser.get_bare_quoted_string,
'""', '""', '', [], '')
# Issue 16983: apply postel's law to some bad encoding.
def test_encoded_word_inside_quotes(self):
self._test_get_x(parser.get_bare_quoted_string,
'"=?utf-8?Q?not_really_valid?="',
'"not really valid"',
'not really valid',
[errors.InvalidHeaderDefect,
errors.InvalidHeaderDefect],
'')
# get_comment
def test_get_comment_only(self):
comment = self._test_get_x(parser.get_comment,
'(comment)', '(comment)', ' ', [], '', ['comment'])
self.assertEqual(comment.token_type, 'comment')
def test_get_comment_must_start_with_paren(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_comment('foo"')
with self.assertRaises(errors.HeaderParseError):
parser.get_comment(' (foo"')
def test_get_comment_following_wsp_preserved(self):
self._test_get_x(parser.get_comment,
'(comment) \t', '(comment)', ' ', [], ' \t', ['comment'])
def test_get_comment_multiple_words(self):
self._test_get_x(parser.get_comment,
'(foo bar) \t', '(foo bar)', ' ', [], ' \t', ['foo bar'])
def test_get_comment_multiple_words_wsp_preserved(self):
self._test_get_x(parser.get_comment,
'( foo bar\t ) \t', '( foo bar\t )', ' ', [], ' \t',
[' foo bar\t '])
def test_get_comment_end_paren_mid_word(self):
self._test_get_x(parser.get_comment,
'(foo)bar', '(foo)', ' ', [], 'bar', ['foo'])
def test_get_comment_quoted_parens(self):
self._test_get_x(parser.get_comment,
r'(foo\) \(\)bar)', r'(foo\) \(\)bar)', ' ', [], '', ['foo) ()bar'])
def test_get_comment_non_printable(self):
self._test_get_x(parser.get_comment,
'(foo\x7Fbar)', '(foo\x7Fbar)', ' ',
[errors.NonPrintableDefect], '', ['foo\x7Fbar'])
def test_get_comment_no_end_paren(self):
self._test_get_x(parser.get_comment,
'(foo bar', '(foo bar)', ' ',
[errors.InvalidHeaderDefect], '', ['foo bar'])
self._test_get_x(parser.get_comment,
'(foo bar ', '(foo bar )', ' ',
[errors.InvalidHeaderDefect], '', ['foo bar '])
def test_get_comment_nested_comment(self):
comment = self._test_get_x(parser.get_comment,
'(foo(bar))', '(foo(bar))', ' ', [], '', ['foo(bar)'])
self.assertEqual(comment[1].content, 'bar')
def test_get_comment_nested_comment_wsp(self):
comment = self._test_get_x(parser.get_comment,
'(foo ( bar ) )', '(foo ( bar ) )', ' ', [], '', ['foo ( bar ) '])
self.assertEqual(comment[2].content, ' bar ')
def test_get_comment_empty_comment(self):
self._test_get_x(parser.get_comment,
'()', '()', ' ', [], '', [''])
def test_get_comment_multiple_nesting(self):
comment = self._test_get_x(parser.get_comment,
'(((((foo)))))', '(((((foo)))))', ' ', [], '', ['((((foo))))'])
for i in range(4, 0, -1):
self.assertEqual(comment[0].content, '('*(i-1)+'foo'+')'*(i-1))
comment = comment[0]
self.assertEqual(comment.content, 'foo')
def test_get_comment_missing_end_of_nesting(self):
self._test_get_x(parser.get_comment,
'(((((foo)))', '(((((foo)))))', ' ',
[errors.InvalidHeaderDefect]*2, '', ['((((foo))))'])
def test_get_comment_qs_in_nested_comment(self):
comment = self._test_get_x(parser.get_comment,
r'(foo (b\)))', r'(foo (b\)))', ' ', [], '', [r'foo (b\))'])
self.assertEqual(comment[2].content, 'b)')
# get_cfws
def test_get_cfws_only_ws(self):
cfws = self._test_get_x(parser.get_cfws,
' \t \t', ' \t \t', ' ', [], '', [])
self.assertEqual(cfws.token_type, 'cfws')
def test_get_cfws_only_comment(self):
cfws = self._test_get_x(parser.get_cfws,
'(foo)', '(foo)', ' ', [], '', ['foo'])
self.assertEqual(cfws[0].content, 'foo')
def test_get_cfws_only_mixed(self):
cfws = self._test_get_x(parser.get_cfws,
' (foo ) ( bar) ', ' (foo ) ( bar) ', ' ', [], '',
['foo ', ' bar'])
self.assertEqual(cfws[1].content, 'foo ')
self.assertEqual(cfws[3].content, ' bar')
def test_get_cfws_ends_at_non_leader(self):
cfws = self._test_get_x(parser.get_cfws,
'(foo) bar', '(foo) ', ' ', [], 'bar', ['foo'])
self.assertEqual(cfws[0].content, 'foo')
def test_get_cfws_ends_at_non_printable(self):
cfws = self._test_get_x(parser.get_cfws,
'(foo) \x07', '(foo) ', ' ', [], '\x07', ['foo'])
self.assertEqual(cfws[0].content, 'foo')
def test_get_cfws_non_printable_in_comment(self):
cfws = self._test_get_x(parser.get_cfws,
'(foo \x07) "test"', '(foo \x07) ', ' ',
[errors.NonPrintableDefect], '"test"', ['foo \x07'])
self.assertEqual(cfws[0].content, 'foo \x07')
def test_get_cfws_header_ends_in_comment(self):
cfws = self._test_get_x(parser.get_cfws,
' (foo ', ' (foo )', ' ',
[errors.InvalidHeaderDefect], '', ['foo '])
self.assertEqual(cfws[1].content, 'foo ')
def test_get_cfws_multiple_nested_comments(self):
cfws = self._test_get_x(parser.get_cfws,
'(foo (bar)) ((a)(a))', '(foo (bar)) ((a)(a))', ' ', [],
'', ['foo (bar)', '(a)(a)'])
self.assertEqual(cfws[0].comments, ['foo (bar)'])
self.assertEqual(cfws[2].comments, ['(a)(a)'])
# get_quoted_string
def test_get_quoted_string_only(self):
qs = self._test_get_x(parser.get_quoted_string,
'"bob"', '"bob"', 'bob', [], '')
self.assertEqual(qs.token_type, 'quoted-string')
self.assertEqual(qs.quoted_value, '"bob"')
self.assertEqual(qs.content, 'bob')
def test_get_quoted_string_with_wsp(self):
qs = self._test_get_x(parser.get_quoted_string,
'\t "bob" ', '\t "bob" ', ' bob ', [], '')
self.assertEqual(qs.quoted_value, ' "bob" ')
self.assertEqual(qs.content, 'bob')
def test_get_quoted_string_with_comments_and_wsp(self):
qs = self._test_get_x(parser.get_quoted_string,
' (foo) "bob"(bar)', ' (foo) "bob"(bar)', ' bob ', [], '')
self.assertEqual(qs[0][1].content, 'foo')
self.assertEqual(qs[2][0].content, 'bar')
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob" ')
def test_get_quoted_string_with_multiple_comments(self):
qs = self._test_get_x(parser.get_quoted_string,
' (foo) (bar) "bob"(bird)', ' (foo) (bar) "bob"(bird)', ' bob ',
[], '')
self.assertEqual(qs[0].comments, ['foo', 'bar'])
self.assertEqual(qs[2].comments, ['bird'])
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob" ')
def test_get_quoted_string_non_printable_in_comment(self):
qs = self._test_get_x(parser.get_quoted_string,
' (\x0A) "bob"', ' (\x0A) "bob"', ' bob',
[errors.NonPrintableDefect], '')
self.assertEqual(qs[0].comments, ['\x0A'])
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob"')
def test_get_quoted_string_non_printable_in_qcontent(self):
qs = self._test_get_x(parser.get_quoted_string,
' (a) "a\x0B"', ' (a) "a\x0B"', ' a\x0B',
[errors.NonPrintableDefect], '')
self.assertEqual(qs[0].comments, ['a'])
self.assertEqual(qs.content, 'a\x0B')
self.assertEqual(qs.quoted_value, ' "a\x0B"')
def test_get_quoted_string_internal_ws(self):
qs = self._test_get_x(parser.get_quoted_string,
' (a) "foo bar "', ' (a) "foo bar "', ' foo bar ',
[], '')
self.assertEqual(qs[0].comments, ['a'])
self.assertEqual(qs.content, 'foo bar ')
self.assertEqual(qs.quoted_value, ' "foo bar "')
def test_get_quoted_string_header_ends_in_comment(self):
qs = self._test_get_x(parser.get_quoted_string,
' (a) "bob" (a', ' (a) "bob" (a)', ' bob ',
[errors.InvalidHeaderDefect], '')
self.assertEqual(qs[0].comments, ['a'])
self.assertEqual(qs[2].comments, ['a'])
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob" ')
def test_get_quoted_string_header_ends_in_qcontent(self):
qs = self._test_get_x(parser.get_quoted_string,
' (a) "bob', ' (a) "bob"', ' bob',
[errors.InvalidHeaderDefect], '')
self.assertEqual(qs[0].comments, ['a'])
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob"')
def test_get_quoted_string_no_quoted_string(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_quoted_string(' (ab) xyz')
def test_get_quoted_string_qs_ends_at_noncfws(self):
qs = self._test_get_x(parser.get_quoted_string,
'\t "bob" fee', '\t "bob" ', ' bob ', [], 'fee')
self.assertEqual(qs.content, 'bob')
self.assertEqual(qs.quoted_value, ' "bob" ')
# get_atom
def test_get_atom_only(self):
atom = self._test_get_x(parser.get_atom,
'bob', 'bob', 'bob', [], '')
self.assertEqual(atom.token_type, 'atom')
def test_get_atom_with_wsp(self):
self._test_get_x(parser.get_atom,
'\t bob ', '\t bob ', ' bob ', [], '')
def test_get_atom_with_comments_and_wsp(self):
atom = self._test_get_x(parser.get_atom,
' (foo) bob(bar)', ' (foo) bob(bar)', ' bob ', [], '')
self.assertEqual(atom[0][1].content, 'foo')
self.assertEqual(atom[2][0].content, 'bar')
def test_get_atom_with_multiple_comments(self):
atom = self._test_get_x(parser.get_atom,
' (foo) (bar) bob(bird)', ' (foo) (bar) bob(bird)', ' bob ',
[], '')
self.assertEqual(atom[0].comments, ['foo', 'bar'])
self.assertEqual(atom[2].comments, ['bird'])
def test_get_atom_non_printable_in_comment(self):
atom = self._test_get_x(parser.get_atom,
' (\x0A) bob', ' (\x0A) bob', ' bob',
[errors.NonPrintableDefect], '')
self.assertEqual(atom[0].comments, ['\x0A'])
def test_get_atom_non_printable_in_atext(self):
atom = self._test_get_x(parser.get_atom,
' (a) a\x0B', ' (a) a\x0B', ' a\x0B',
[errors.NonPrintableDefect], '')
self.assertEqual(atom[0].comments, ['a'])
def test_get_atom_header_ends_in_comment(self):
atom = self._test_get_x(parser.get_atom,
' (a) bob (a', ' (a) bob (a)', ' bob ',
[errors.InvalidHeaderDefect], '')
self.assertEqual(atom[0].comments, ['a'])
self.assertEqual(atom[2].comments, ['a'])
def test_get_atom_no_atom(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_atom(' (ab) ')
def test_get_atom_no_atom_before_special(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_atom(' (ab) @')
def test_get_atom_atom_ends_at_special(self):
atom = self._test_get_x(parser.get_atom,
' (foo) bob(bar) @bang', ' (foo) bob(bar) ', ' bob ', [], '@bang')
self.assertEqual(atom[0].comments, ['foo'])
self.assertEqual(atom[2].comments, ['bar'])
def test_get_atom_atom_ends_at_noncfws(self):
self._test_get_x(parser.get_atom,
'bob fred', 'bob ', 'bob ', [], 'fred')
def test_get_atom_rfc2047_atom(self):
self._test_get_x(parser.get_atom,
'=?utf-8?q?=20bob?=', ' bob', ' bob', [], '')
# get_dot_atom_text
def test_get_dot_atom_text(self):
dot_atom_text = self._test_get_x(parser.get_dot_atom_text,
'foo.bar.bang', 'foo.bar.bang', 'foo.bar.bang', [], '')
self.assertEqual(dot_atom_text.token_type, 'dot-atom-text')
self.assertEqual(len(dot_atom_text), 5)
def test_get_dot_atom_text_lone_atom_is_valid(self):
dot_atom_text = self._test_get_x(parser.get_dot_atom_text,
'foo', 'foo', 'foo', [], '')
def test_get_dot_atom_text_raises_on_leading_dot(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom_text('.foo.bar')
def test_get_dot_atom_text_raises_on_trailing_dot(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom_text('foo.bar.')
def test_get_dot_atom_text_raises_on_leading_non_atext(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom_text(' foo.bar')
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom_text('@foo.bar')
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom_text('"foo.bar"')
def test_get_dot_atom_text_trailing_text_preserved(self):
dot_atom_text = self._test_get_x(parser.get_dot_atom_text,
'foo@bar', 'foo', 'foo', [], '@bar')
def test_get_dot_atom_text_trailing_ws_preserved(self):
dot_atom_text = self._test_get_x(parser.get_dot_atom_text,
'foo .bar', 'foo', 'foo', [], ' .bar')
# get_dot_atom
def test_get_dot_atom_only(self):
dot_atom = self._test_get_x(parser.get_dot_atom,
'foo.bar.bing', 'foo.bar.bing', 'foo.bar.bing', [], '')
self.assertEqual(dot_atom.token_type, 'dot-atom')
self.assertEqual(len(dot_atom), 1)
def test_get_dot_atom_with_wsp(self):
self._test_get_x(parser.get_dot_atom,
'\t foo.bar.bing ', '\t foo.bar.bing ', ' foo.bar.bing ', [], '')
def test_get_dot_atom_with_comments_and_wsp(self):
self._test_get_x(parser.get_dot_atom,
' (sing) foo.bar.bing (here) ', ' (sing) foo.bar.bing (here) ',
' foo.bar.bing ', [], '')
def test_get_dot_atom_space_ends_dot_atom(self):
self._test_get_x(parser.get_dot_atom,
' (sing) foo.bar .bing (here) ', ' (sing) foo.bar ',
' foo.bar ', [], '.bing (here) ')
def test_get_dot_atom_no_atom_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom(' (foo) ')
def test_get_dot_atom_leading_dot_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom(' (foo) .bar')
def test_get_dot_atom_two_dots_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom('bar..bang')
def test_get_dot_atom_trailing_dot_raises(self):
with self.assertRaises(errors.HeaderParseError):
parser.get_dot_atom(' (foo) bar.bang. foo')
def test_get_dot_atom_rfc2047_atom(self):
self._test_get_x(parser.get_dot_atom,
'=?utf-8?q?=20bob?=', ' bob', ' bob', [], '')
# get_word (if this were black box we'd repeat all the qs/atom tests)
def test_get_word_atom_yields_atom(self):
word = self._test_get_x(parser.get_word,
' (foo) bar (bang) :ah', ' (foo) bar (bang) ', ' bar ', [], ':ah')
self.assertEqual(word.token_type, 'atom')
self.assertEqual(word[0].token_type, 'cfws')
def test_get_word_all_CFWS(self):
# bpo-29412: Test that we don't raise IndexError when parsing CFWS only
# token.
with self.assertRaises(errors.HeaderParseError):
parser.get_word('(Recipients list suppressed')
def test_get_word_qs_yields_qs(self):
word = self._test_get_x(parser.get_word,
'"bar " (bang) ah', '"bar " (bang) ', 'bar ', [], 'ah')
self.assertEqual(word.token_type, 'quoted-string')
self.assertEqual(word[0].token_type, 'bare-quoted-string')
self.assertEqual(word[0].value, 'bar ')
self.assertEqual(word.content, 'bar ')
def test_get_word_ends_at_dot(self):
self._test_get_x(parser.get_word,
'foo.', 'foo', 'foo', [], '.')
# get_phrase
def test_get_phrase_simple(self):
phrase = self._test_get_x(parser.get_phrase,
'"Fred A. Johnson" is his name, oh.',
'"Fred A. Johnson" is his name',
'Fred A. Johnson is his name',
[],
', oh.')
self.assertEqual(phrase.token_type, 'phrase')
def test_get_phrase_complex(self):
phrase = self._test_get_x(parser.get_phrase,
' (A) bird (in (my|your)) "hand " is messy\t<>\t',
' (A) bird (in (my|your)) "hand " is messy\t',
' bird hand is messy ',
[],
'<>\t')