Repository navigation
Expand file tree
/
Copy pathtest_unicode.py
More file actions
3136 lines (2789 loc) · 137 KB
/
Copy pathtest_unicode.py
File metadata and controls
3136 lines (2789 loc) · 137 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
""" Test script for the Unicode implementation.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
import _string
import codecs
import itertools
import operator
import pickle
import struct
import sys
import textwrap
import unicodedata
import unittest
import warnings
from test.support import import_helper
from test.support import warnings_helper
from test import support, string_tests
from test.support.script_helper import assert_python_failure
try:
import _testcapi
except ImportError:
_testcapi = None
# Error handling (bad decoder return)
def search_function(encoding):
def decode1(input, errors="strict"):
return 42 # not a tuple
def encode1(input, errors="strict"):
return 42 # not a tuple
def encode2(input, errors="strict"):
return (42, 42) # no unicode
def decode2(input, errors="strict"):
return (42, 42) # no unicode
if encoding=="test.unicode1":
return (encode1, decode1, None, None)
elif encoding=="test.unicode2":
return (encode2, decode2, None, None)
else:
return None
def duplicate_string(text):
"""
Try to get a fresh clone of the specified text:
new object with a reference count of 1.
This is a best-effort: latin1 single letters and the empty
string ('') are singletons and cannot be cloned.
"""
return text.encode().decode()
class StrSubclass(str):
pass
class UnicodeTest(string_tests.CommonTest,
string_tests.MixinStrUnicodeUserStringTest,
string_tests.MixinStrUnicodeTest,
unittest.TestCase):
type2test = str
def setUp(self):
codecs.register(search_function)
self.addCleanup(codecs.unregister, search_function)
def checkequalnofix(self, result, object, methodname, *args):
method = getattr(object, methodname)
realresult = method(*args)
self.assertEqual(realresult, result)
self.assertTrue(type(realresult) is type(result))
# if the original is returned make sure that
# this doesn't happen with subclasses
if realresult is object:
class usub(str):
def __repr__(self):
return 'usub(%r)' % str.__repr__(self)
object = usub(object)
method = getattr(object, methodname)
realresult = method(*args)
self.assertEqual(realresult, result)
self.assertTrue(object is not realresult)
def test_literals(self):
self.assertEqual('\xff', '\u00ff')
self.assertEqual('\uffff', '\U0000ffff')
self.assertRaises(SyntaxError, eval, '\'\\Ufffffffe\'')
self.assertRaises(SyntaxError, eval, '\'\\Uffffffff\'')
self.assertRaises(SyntaxError, eval, '\'\\U%08x\'' % 0x110000)
# raw strings should not have unicode escapes
self.assertNotEqual(r"\u0020", " ")
def test_ascii(self):
if not sys.platform.startswith('java'):
# Test basic sanity of repr()
self.assertEqual(ascii('abc'), "'abc'")
self.assertEqual(ascii('ab\\c'), "'ab\\\\c'")
self.assertEqual(ascii('ab\\'), "'ab\\\\'")
self.assertEqual(ascii('\\c'), "'\\\\c'")
self.assertEqual(ascii('\\'), "'\\\\'")
self.assertEqual(ascii('\n'), "'\\n'")
self.assertEqual(ascii('\r'), "'\\r'")
self.assertEqual(ascii('\t'), "'\\t'")
self.assertEqual(ascii('\b'), "'\\x08'")
self.assertEqual(ascii("'\""), """'\\'"'""")
self.assertEqual(ascii("'\""), """'\\'"'""")
self.assertEqual(ascii("'"), '''"'"''')
self.assertEqual(ascii('"'), """'"'""")
latin1repr = (
"'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
"\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
"\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
"JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
"\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
"\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
"\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
"\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
"\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
"\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
"\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
"\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
"\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
"\\xfe\\xff'")
testrepr = ascii(''.join(map(chr, range(256))))
self.assertEqual(testrepr, latin1repr)
# Test ascii works on wide unicode escapes without overflow.
self.assertEqual(ascii("\U00010000" * 39 + "\uffff" * 4096),
ascii("\U00010000" * 39 + "\uffff" * 4096))
class WrongRepr:
def __repr__(self):
return b'byte-repr'
self.assertRaises(TypeError, ascii, WrongRepr())
def test_repr(self):
if not sys.platform.startswith('java'):
# Test basic sanity of repr()
self.assertEqual(repr('abc'), "'abc'")
self.assertEqual(repr('ab\\c'), "'ab\\\\c'")
self.assertEqual(repr('ab\\'), "'ab\\\\'")
self.assertEqual(repr('\\c'), "'\\\\c'")
self.assertEqual(repr('\\'), "'\\\\'")
self.assertEqual(repr('\n'), "'\\n'")
self.assertEqual(repr('\r'), "'\\r'")
self.assertEqual(repr('\t'), "'\\t'")
self.assertEqual(repr('\b'), "'\\x08'")
self.assertEqual(repr("'\""), """'\\'"'""")
self.assertEqual(repr("'\""), """'\\'"'""")
self.assertEqual(repr("'"), '''"'"''')
self.assertEqual(repr('"'), """'"'""")
latin1repr = (
"'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
"\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
"\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
"JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
"\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
"\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
"\\x9c\\x9d\\x9e\\x9f\\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9"
"\xaa\xab\xac\\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
"\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5"
"\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3"
"\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1"
"\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd"
"\xfe\xff'")
testrepr = repr(''.join(map(chr, range(256))))
self.assertEqual(testrepr, latin1repr)
# Test repr works on wide unicode escapes without overflow.
self.assertEqual(repr("\U00010000" * 39 + "\uffff" * 4096),
repr("\U00010000" * 39 + "\uffff" * 4096))
class WrongRepr:
def __repr__(self):
return b'byte-repr'
self.assertRaises(TypeError, repr, WrongRepr())
def test_iterators(self):
# Make sure unicode objects have an __iter__ method
it = "\u1111\u2222\u3333".__iter__()
self.assertEqual(next(it), "\u1111")
self.assertEqual(next(it), "\u2222")
self.assertEqual(next(it), "\u3333")
self.assertRaises(StopIteration, next, it)
def test_iterators_invocation(self):
cases = [type(iter('abc')), type(iter('🚀'))]
for cls in cases:
with self.subTest(cls=cls):
self.assertRaises(TypeError, cls)
def test_iteration(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(string=case):
self.assertEqual(case, "".join(iter(case)))
def test_exhausted_iterator(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(case=case):
iterator = iter(case)
tuple(iterator)
self.assertRaises(StopIteration, next, iterator)
def test_pickle_iterator(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(case=case):
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
it = iter(case)
with self.subTest(proto=proto):
pickled = "".join(pickle.loads(pickle.dumps(it, proto)))
self.assertEqual(case, pickled)
def test_count(self):
string_tests.CommonTest.test_count(self)
# check mixed argument types
self.checkequalnofix(3, 'aaa', 'count', 'a')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(3, 'aaa', 'count', 'a')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(1, 'aaa', 'count', 'a', -1)
self.checkequalnofix(3, 'aaa', 'count', 'a', -10)
self.checkequalnofix(2, 'aaa', 'count', 'a', 0, -1)
self.checkequalnofix(0, 'aaa', 'count', 'a', 0, -10)
# test mixed kinds
self.checkequal(10, '\u0102' + 'a' * 10, 'count', 'a')
self.checkequal(10, '\U00100304' + 'a' * 10, 'count', 'a')
self.checkequal(10, '\U00100304' + '\u0102' * 10, 'count', '\u0102')
self.checkequal(0, 'a' * 10, 'count', '\u0102')
self.checkequal(0, 'a' * 10, 'count', '\U00100304')
self.checkequal(0, '\u0102' * 10, 'count', '\U00100304')
self.checkequal(10, '\u0102' + 'a_' * 10, 'count', 'a_')
self.checkequal(10, '\U00100304' + 'a_' * 10, 'count', 'a_')
self.checkequal(10, '\U00100304' + '\u0102_' * 10, 'count', '\u0102_')
self.checkequal(0, 'a' * 10, 'count', 'a\u0102')
self.checkequal(0, 'a' * 10, 'count', 'a\U00100304')
self.checkequal(0, '\u0102' * 10, 'count', '\u0102\U00100304')
def test_find(self):
string_tests.CommonTest.test_find(self)
# test implementation details of the memchr fast path
self.checkequal(100, 'a' * 100 + '\u0102', 'find', '\u0102')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0201')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0120')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0220')
self.checkequal(100, 'a' * 100 + '\U00100304', 'find', '\U00100304')
self.checkequal(-1, 'a' * 100 + '\U00100304', 'find', '\U00100204')
self.checkequal(-1, 'a' * 100 + '\U00100304', 'find', '\U00102004')
# check mixed argument types
self.checkequalnofix(0, 'abcdefghiabc', 'find', 'abc')
self.checkequalnofix(9, 'abcdefghiabc', 'find', 'abc', 1)
self.checkequalnofix(-1, 'abcdefghiabc', 'find', 'def', 4)
self.assertRaises(TypeError, 'hello'.find)
self.assertRaises(TypeError, 'hello'.find, 42)
# test mixed kinds
self.checkequal(100, '\u0102' * 100 + 'a', 'find', 'a')
self.checkequal(100, '\U00100304' * 100 + 'a', 'find', 'a')
self.checkequal(100, '\U00100304' * 100 + '\u0102', 'find', '\u0102')
self.checkequal(-1, 'a' * 100, 'find', '\u0102')
self.checkequal(-1, 'a' * 100, 'find', '\U00100304')
self.checkequal(-1, '\u0102' * 100, 'find', '\U00100304')
self.checkequal(100, '\u0102' * 100 + 'a_', 'find', 'a_')
self.checkequal(100, '\U00100304' * 100 + 'a_', 'find', 'a_')
self.checkequal(100, '\U00100304' * 100 + '\u0102_', 'find', '\u0102_')
self.checkequal(-1, 'a' * 100, 'find', 'a\u0102')
self.checkequal(-1, 'a' * 100, 'find', 'a\U00100304')
self.checkequal(-1, '\u0102' * 100, 'find', '\u0102\U00100304')
def test_rfind(self):
string_tests.CommonTest.test_rfind(self)
# test implementation details of the memrchr fast path
self.checkequal(0, '\u0102' + 'a' * 100 , 'rfind', '\u0102')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0201')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0120')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0220')
self.checkequal(0, '\U00100304' + 'a' * 100, 'rfind', '\U00100304')
self.checkequal(-1, '\U00100304' + 'a' * 100, 'rfind', '\U00100204')
self.checkequal(-1, '\U00100304' + 'a' * 100, 'rfind', '\U00102004')
# check mixed argument types
self.checkequalnofix(9, 'abcdefghiabc', 'rfind', 'abc')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
# test mixed kinds
self.checkequal(0, 'a' + '\u0102' * 100, 'rfind', 'a')
self.checkequal(0, 'a' + '\U00100304' * 100, 'rfind', 'a')
self.checkequal(0, '\u0102' + '\U00100304' * 100, 'rfind', '\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\U00100304')
self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304')
self.checkequal(0, '_a' + '\u0102' * 100, 'rfind', '_a')
self.checkequal(0, '_a' + '\U00100304' * 100, 'rfind', '_a')
self.checkequal(0, '_\u0102' + '\U00100304' * 100, 'rfind', '_\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\u0102a')
self.checkequal(-1, 'a' * 100, 'rfind', '\U00100304a')
self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304\u0102')
def test_index(self):
string_tests.CommonTest.test_index(self)
self.checkequalnofix(0, 'abcdefghiabc', 'index', '')
self.checkequalnofix(3, 'abcdefghiabc', 'index', 'def')
self.checkequalnofix(0, 'abcdefghiabc', 'index', 'abc')
self.checkequalnofix(9, 'abcdefghiabc', 'index', 'abc', 1)
self.assertRaises(ValueError, 'abcdefghiabc'.index, 'hib')
self.assertRaises(ValueError, 'abcdefghiab'.index, 'abc', 1)
self.assertRaises(ValueError, 'abcdefghi'.index, 'ghi', 8)
self.assertRaises(ValueError, 'abcdefghi'.index, 'ghi', -1)
# test mixed kinds
self.checkequal(100, '\u0102' * 100 + 'a', 'index', 'a')
self.checkequal(100, '\U00100304' * 100 + 'a', 'index', 'a')
self.checkequal(100, '\U00100304' * 100 + '\u0102', 'index', '\u0102')
self.assertRaises(ValueError, ('a' * 100).index, '\u0102')
self.assertRaises(ValueError, ('a' * 100).index, '\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).index, '\U00100304')
self.checkequal(100, '\u0102' * 100 + 'a_', 'index', 'a_')
self.checkequal(100, '\U00100304' * 100 + 'a_', 'index', 'a_')
self.checkequal(100, '\U00100304' * 100 + '\u0102_', 'index', '\u0102_')
self.assertRaises(ValueError, ('a' * 100).index, 'a\u0102')
self.assertRaises(ValueError, ('a' * 100).index, 'a\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).index, '\u0102\U00100304')
def test_rindex(self):
string_tests.CommonTest.test_rindex(self)
self.checkequalnofix(12, 'abcdefghiabc', 'rindex', '')
self.checkequalnofix(3, 'abcdefghiabc', 'rindex', 'def')
self.checkequalnofix(9, 'abcdefghiabc', 'rindex', 'abc')
self.checkequalnofix(0, 'abcdefghiabc', 'rindex', 'abc', 0, -1)
self.assertRaises(ValueError, 'abcdefghiabc'.rindex, 'hib')
self.assertRaises(ValueError, 'defghiabc'.rindex, 'def', 1)
self.assertRaises(ValueError, 'defghiabc'.rindex, 'abc', 0, -1)
self.assertRaises(ValueError, 'abcdefghi'.rindex, 'ghi', 0, 8)
self.assertRaises(ValueError, 'abcdefghi'.rindex, 'ghi', 0, -1)
# test mixed kinds
self.checkequal(0, 'a' + '\u0102' * 100, 'rindex', 'a')
self.checkequal(0, 'a' + '\U00100304' * 100, 'rindex', 'a')
self.checkequal(0, '\u0102' + '\U00100304' * 100, 'rindex', '\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304')
self.checkequal(0, '_a' + '\u0102' * 100, 'rindex', '_a')
self.checkequal(0, '_a' + '\U00100304' * 100, 'rindex', '_a')
self.checkequal(0, '_\u0102' + '\U00100304' * 100, 'rindex', '_\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\u0102a')
self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304a')
self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304\u0102')
def test_maketrans_translate(self):
# these work with plain translate()
self.checkequalnofix('bbbc', 'abababc', 'translate',
{ord('a'): None})
self.checkequalnofix('iiic', 'abababc', 'translate',
{ord('a'): None, ord('b'): ord('i')})
self.checkequalnofix('iiix', 'abababc', 'translate',
{ord('a'): None, ord('b'): ord('i'), ord('c'): 'x'})
self.checkequalnofix('c', 'abababc', 'translate',
{ord('a'): None, ord('b'): ''})
self.checkequalnofix('xyyx', 'xzx', 'translate',
{ord('z'): 'yy'})
# this needs maketrans()
self.checkequalnofix('abababc', 'abababc', 'translate',
{'b': '<i>'})
tbl = self.type2test.maketrans({'a': None, 'b': '<i>'})
self.checkequalnofix('<i><i><i>c', 'abababc', 'translate', tbl)
# test alternative way of calling maketrans()
tbl = self.type2test.maketrans('abc', 'xyz', 'd')
self.checkequalnofix('xyzzy', 'abdcdcbdddd', 'translate', tbl)
# various tests switching from ASCII to latin1 or the opposite;
# same length, remove a letter, or replace with a longer string.
self.assertEqual("[a]".translate(str.maketrans('a', 'X')),
"[X]")
self.assertEqual("[a]".translate(str.maketrans({'a': 'X'})),
"[X]")
self.assertEqual("[a]".translate(str.maketrans({'a': None})),
"[]")
self.assertEqual("[a]".translate(str.maketrans({'a': 'XXX'})),
"[XXX]")
self.assertEqual("[a]".translate(str.maketrans({'a': '\xe9'})),
"[\xe9]")
self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '123'})),
"x123")
self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '\xe9'})),
"x\xe9")
# test non-ASCII (don't take the fast-path)
self.assertEqual("[a]".translate(str.maketrans({'a': '<\xe9>'})),
"[<\xe9>]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': 'a'})),
"[a]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': None})),
"[]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': '123'})),
"[123]")
self.assertEqual("[a\xe9]".translate(str.maketrans({'a': '<\u20ac>'})),
"[<\u20ac>\xe9]")
# invalid Unicode characters
invalid_char = 0x10ffff+1
for before in "a\xe9\u20ac\U0010ffff":
mapping = str.maketrans({before: invalid_char})
text = "[%s]" % before
self.assertRaises(ValueError, text.translate, mapping)
# errors
self.assertRaises(TypeError, self.type2test.maketrans)
self.assertRaises(ValueError, self.type2test.maketrans, 'abc', 'defg')
self.assertRaises(TypeError, self.type2test.maketrans, 2, 'def')
self.assertRaises(TypeError, self.type2test.maketrans, 'abc', 2)
self.assertRaises(TypeError, self.type2test.maketrans, 'abc', 'def', 2)
self.assertRaises(ValueError, self.type2test.maketrans, {'xy': 2})
self.assertRaises(TypeError, self.type2test.maketrans, {(1,): 2})
self.assertRaises(TypeError, 'hello'.translate)
self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz')
def test_split(self):
string_tests.CommonTest.test_split(self)
# test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal([left + right],
left + right, 'split', delim)
self.checkequal([left, right],
left + delim + right, 'split', delim)
self.checkequal([left + right],
left + right, 'split', delim * 2)
self.checkequal([left, right],
left + delim * 2 + right, 'split', delim *2)
def test_rsplit(self):
string_tests.CommonTest.test_rsplit(self)
# test mixed kinds
for left, right in ('ba', 'юё', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', 'ы', '\u0102', '\U00010302'):
self.checkequal([left + right],
left + right, 'rsplit', delim)
self.checkequal([left, right],
left + delim + right, 'rsplit', delim)
self.checkequal([left + right],
left + right, 'rsplit', delim * 2)
self.checkequal([left, right],
left + delim * 2 + right, 'rsplit', delim *2)
# Check `None` as well:
self.checkequal([left + right],
left + right, 'rsplit', None)
def test_partition(self):
string_tests.MixinStrUnicodeUserStringTest.test_partition(self)
# test mixed kinds
self.checkequal(('ABCDEFGH', '', ''), 'ABCDEFGH', 'partition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal((left + right, '', ''),
left + right, 'partition', delim)
self.checkequal((left, delim, right),
left + delim + right, 'partition', delim)
self.checkequal((left + right, '', ''),
left + right, 'partition', delim * 2)
self.checkequal((left, delim * 2, right),
left + delim * 2 + right, 'partition', delim * 2)
def test_rpartition(self):
string_tests.MixinStrUnicodeUserStringTest.test_rpartition(self)
# test mixed kinds
self.checkequal(('', '', 'ABCDEFGH'), 'ABCDEFGH', 'rpartition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal(('', '', left + right),
left + right, 'rpartition', delim)
self.checkequal((left, delim, right),
left + delim + right, 'rpartition', delim)
self.checkequal(('', '', left + right),
left + right, 'rpartition', delim * 2)
self.checkequal((left, delim * 2, right),
left + delim * 2 + right, 'rpartition', delim * 2)
def test_join(self):
string_tests.MixinStrUnicodeUserStringTest.test_join(self)
class MyWrapper:
def __init__(self, sval): self.sval = sval
def __str__(self): return self.sval
# mixed arguments
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd'))
self.checkequalnofix('w x y z', ' ', 'join', string_tests.Sequence('wxyz'))
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd'))
self.checkequalnofix('w x y z', ' ', 'join', string_tests.Sequence('wxyz'))
self.checkraises(TypeError, ' ', 'join', ['1', '2', MyWrapper('foo')])
self.checkraises(TypeError, ' ', 'join', ['1', '2', '3', bytes()])
self.checkraises(TypeError, ' ', 'join', [1, 2, 3])
self.checkraises(TypeError, ' ', 'join', ['1', '2', 3])
@unittest.skipIf(sys.maxsize > 2**32,
'needs too much memory on a 64-bit platform')
def test_join_overflow(self):
size = int(sys.maxsize**0.5) + 1
seq = ('A' * size,) * size
self.assertRaises(OverflowError, ''.join, seq)
def test_replace(self):
string_tests.CommonTest.test_replace(self)
# method call forwarded from str implementation because of unicode argument
self.checkequalnofix('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
self.assertRaises(TypeError, 'replace'.replace, "r", 42)
# test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
for repl in ('d', '\u0103', '\U00010303'):
self.checkequal(left + right,
left + right, 'replace', delim, repl)
self.checkequal(left + repl + right,
left + delim + right,
'replace', delim, repl)
self.checkequal(left + right,
left + right, 'replace', delim * 2, repl)
self.checkequal(left + repl + right,
left + delim * 2 + right,
'replace', delim * 2, repl)
@support.cpython_only
def test_replace_id(self):
pattern = 'abc'
text = 'abc def'
self.assertIs(text.replace(pattern, pattern), text)
def test_repeat_id_preserving(self):
a = '123abc1@'
b = '456zyx-+'
self.assertEqual(id(a), id(a))
self.assertNotEqual(id(a), id(b))
self.assertNotEqual(id(a), id(a * -4))
self.assertNotEqual(id(a), id(a * 0))
self.assertEqual(id(a), id(a * 1))
self.assertEqual(id(a), id(1 * a))
self.assertNotEqual(id(a), id(a * 2))
class SubStr(str):
pass
s = SubStr('qwerty()')
self.assertEqual(id(s), id(s))
self.assertNotEqual(id(s), id(s * -4))
self.assertNotEqual(id(s), id(s * 0))
self.assertNotEqual(id(s), id(s * 1))
self.assertNotEqual(id(s), id(1 * s))
self.assertNotEqual(id(s), id(s * 2))
def test_bytes_comparison(self):
with warnings_helper.check_warnings():
warnings.simplefilter('ignore', BytesWarning)
self.assertEqual('abc' == b'abc', False)
self.assertEqual('abc' != b'abc', True)
self.assertEqual('abc' == bytearray(b'abc'), False)
self.assertEqual('abc' != bytearray(b'abc'), True)
def test_comparison(self):
# Comparisons:
self.assertEqual('abc', 'abc')
self.assertTrue('abcd' > 'abc')
self.assertTrue('abc' < 'abcd')
if 0:
# Move these tests to a Unicode collation module test...
# Testing UTF-16 code point order comparisons...
# No surrogates, no fixup required.
self.assertTrue('\u0061' < '\u20ac')
# Non surrogate below surrogate value, no fixup required
self.assertTrue('\u0061' < '\ud800\udc02')
# Non surrogate above surrogate value, fixup required
def test_lecmp(s, s2):
self.assertTrue(s < s2)
def test_fixup(s):
s2 = '\ud800\udc01'
test_lecmp(s, s2)
s2 = '\ud900\udc01'
test_lecmp(s, s2)
s2 = '\uda00\udc01'
test_lecmp(s, s2)
s2 = '\udb00\udc01'
test_lecmp(s, s2)
s2 = '\ud800\udd01'
test_lecmp(s, s2)
s2 = '\ud900\udd01'
test_lecmp(s, s2)
s2 = '\uda00\udd01'
test_lecmp(s, s2)
s2 = '\udb00\udd01'
test_lecmp(s, s2)
s2 = '\ud800\ude01'
test_lecmp(s, s2)
s2 = '\ud900\ude01'
test_lecmp(s, s2)
s2 = '\uda00\ude01'
test_lecmp(s, s2)
s2 = '\udb00\ude01'
test_lecmp(s, s2)
s2 = '\ud800\udfff'
test_lecmp(s, s2)
s2 = '\ud900\udfff'
test_lecmp(s, s2)
s2 = '\uda00\udfff'
test_lecmp(s, s2)
s2 = '\udb00\udfff'
test_lecmp(s, s2)
test_fixup('\ue000')
test_fixup('\uff61')
# Surrogates on both sides, no fixup required
self.assertTrue('\ud800\udc02' < '\ud84d\udc56')
def test_islower(self):
super().test_islower()
self.checkequalnofix(False, '\u1FFc', 'islower')
self.assertFalse('\u2167'.islower())
self.assertTrue('\u2177'.islower())
# non-BMP, uppercase
self.assertFalse('\U00010401'.islower())
self.assertFalse('\U00010427'.islower())
# non-BMP, lowercase
self.assertTrue('\U00010429'.islower())
self.assertTrue('\U0001044E'.islower())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.islower())
self.assertFalse('\U0001F46F'.islower())
def test_isupper(self):
super().test_isupper()
if not sys.platform.startswith('java'):
self.checkequalnofix(False, '\u1FFc', 'isupper')
self.assertTrue('\u2167'.isupper())
self.assertFalse('\u2177'.isupper())
# non-BMP, uppercase
self.assertTrue('\U00010401'.isupper())
self.assertTrue('\U00010427'.isupper())
# non-BMP, lowercase
self.assertFalse('\U00010429'.isupper())
self.assertFalse('\U0001044E'.isupper())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.isupper())
self.assertFalse('\U0001F46F'.isupper())
def test_istitle(self):
super().test_istitle()
self.checkequalnofix(True, '\u1FFc', 'istitle')
self.checkequalnofix(True, 'Greek \u1FFcitlecases ...', 'istitle')
# non-BMP, uppercase + lowercase
self.assertTrue('\U00010401\U00010429'.istitle())
self.assertTrue('\U00010427\U0001044E'.istitle())
# apparently there are no titlecased (Lt) non-BMP chars in Unicode 6
for ch in ['\U00010429', '\U0001044E', '\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.istitle(), '{!a} is not title'.format(ch))
def test_isspace(self):
super().test_isspace()
self.checkequalnofix(True, '\u2000', 'isspace')
self.checkequalnofix(True, '\u200a', 'isspace')
self.checkequalnofix(False, '\u2014', 'isspace')
# There are no non-BMP whitespace chars as of Unicode 12.
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.isspace(), '{!a} is not space.'.format(ch))
@support.requires_resource('cpu')
def test_isspace_invariant(self):
for codepoint in range(sys.maxunicode + 1):
char = chr(codepoint)
bidirectional = unicodedata.bidirectional(char)
category = unicodedata.category(char)
self.assertEqual(char.isspace(),
(bidirectional in ('WS', 'B', 'S')
or category == 'Zs'))
def test_isalnum(self):
super().test_isalnum()
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001D7F6', '\U00011066', '\U000104A0', '\U0001F107']:
self.assertTrue(ch.isalnum(), '{!a} is alnum.'.format(ch))
def test_isalpha(self):
super().test_isalpha()
self.checkequalnofix(True, '\u1FFc', 'isalpha')
# non-BMP, cased
self.assertTrue('\U00010401'.isalpha())
self.assertTrue('\U00010427'.isalpha())
self.assertTrue('\U00010429'.isalpha())
self.assertTrue('\U0001044E'.isalpha())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.isalpha())
self.assertFalse('\U0001F46F'.isalpha())
def test_isascii(self):
super().test_isascii()
self.assertFalse("\u20ac".isascii())
self.assertFalse("\U0010ffff".isascii())
def test_isdecimal(self):
self.checkequalnofix(False, '', 'isdecimal')
self.checkequalnofix(False, 'a', 'isdecimal')
self.checkequalnofix(True, '0', 'isdecimal')
self.checkequalnofix(False, '\u2460', 'isdecimal') # CIRCLED DIGIT ONE
self.checkequalnofix(False, '\xbc', 'isdecimal') # VULGAR FRACTION ONE QUARTER
self.checkequalnofix(True, '\u0660', 'isdecimal') # ARABIC-INDIC DIGIT ZERO
self.checkequalnofix(True, '0123456789', 'isdecimal')
self.checkequalnofix(False, '0123456789a', 'isdecimal')
self.checkraises(TypeError, 'abc', 'isdecimal', 42)
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F', '\U00011065', '\U0001F107']:
self.assertFalse(ch.isdecimal(), '{!a} is not decimal.'.format(ch))
for ch in ['\U0001D7F6', '\U00011066', '\U000104A0']:
self.assertTrue(ch.isdecimal(), '{!a} is decimal.'.format(ch))
def test_isdigit(self):
super().test_isdigit()
self.checkequalnofix(True, '\u2460', 'isdigit')
self.checkequalnofix(False, '\xbc', 'isdigit')
self.checkequalnofix(True, '\u0660', 'isdigit')
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F', '\U00011065']:
self.assertFalse(ch.isdigit(), '{!a} is not a digit.'.format(ch))
for ch in ['\U0001D7F6', '\U00011066', '\U000104A0', '\U0001F107']:
self.assertTrue(ch.isdigit(), '{!a} is a digit.'.format(ch))
def test_isnumeric(self):
self.checkequalnofix(False, '', 'isnumeric')
self.checkequalnofix(False, 'a', 'isnumeric')
self.checkequalnofix(True, '0', 'isnumeric')
self.checkequalnofix(True, '\u2460', 'isnumeric')
self.checkequalnofix(True, '\xbc', 'isnumeric')
self.checkequalnofix(True, '\u0660', 'isnumeric')
self.checkequalnofix(True, '0123456789', 'isnumeric')
self.checkequalnofix(False, '0123456789a', 'isnumeric')
self.assertRaises(TypeError, "abc".isnumeric, 42)
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.isnumeric(), '{!a} is not numeric.'.format(ch))
for ch in ['\U00011065', '\U0001D7F6', '\U00011066',
'\U000104A0', '\U0001F107']:
self.assertTrue(ch.isnumeric(), '{!a} is numeric.'.format(ch))
def test_isidentifier(self):
self.assertTrue("a".isidentifier())
self.assertTrue("Z".isidentifier())
self.assertTrue("_".isidentifier())
self.assertTrue("b0".isidentifier())
self.assertTrue("bc".isidentifier())
self.assertTrue("b_".isidentifier())
self.assertTrue("µ".isidentifier())
self.assertTrue("𝔘𝔫𝔦𝔠𝔬𝔡𝔢".isidentifier())
self.assertFalse(" ".isidentifier())
self.assertFalse("[".isidentifier())
self.assertFalse("©".isidentifier())
self.assertFalse("0".isidentifier())
@support.cpython_only
@support.requires_legacy_unicode_capi
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_isidentifier_legacy(self):
u = '𝖀𝖓𝖎𝖈𝖔𝖉𝖊'
self.assertTrue(u.isidentifier())
with warnings_helper.check_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
self.assertTrue(_testcapi.unicode_legacy_string(u).isidentifier())
def test_isprintable(self):
self.assertTrue("".isprintable())
self.assertTrue(" ".isprintable())
self.assertTrue("abcdefg".isprintable())
self.assertFalse("abcdefg\n".isprintable())
# some defined Unicode character
self.assertTrue("\u0374".isprintable())
# undefined character
self.assertFalse("\u0378".isprintable())
# single surrogate character
self.assertFalse("\ud800".isprintable())
self.assertTrue('\U0001F46F'.isprintable())
self.assertFalse('\U000E0020'.isprintable())
def test_surrogates(self):
for s in ('a\uD800b\uDFFF', 'a\uDFFFb\uD800',
'a\uD800b\uDFFFa', 'a\uDFFFb\uD800a'):
self.assertTrue(s.islower())
self.assertFalse(s.isupper())
self.assertFalse(s.istitle())
for s in ('A\uD800B\uDFFF', 'A\uDFFFB\uD800',
'A\uD800B\uDFFFA', 'A\uDFFFB\uD800A'):
self.assertFalse(s.islower())
self.assertTrue(s.isupper())
self.assertTrue(s.istitle())
for meth_name in ('islower', 'isupper', 'istitle'):
meth = getattr(str, meth_name)
for s in ('\uD800', '\uDFFF', '\uD800\uD800', '\uDFFF\uDFFF'):
self.assertFalse(meth(s), '%a.%s() is False' % (s, meth_name))
for meth_name in ('isalpha', 'isalnum', 'isdigit', 'isspace',
'isdecimal', 'isnumeric',
'isidentifier', 'isprintable'):
meth = getattr(str, meth_name)
for s in ('\uD800', '\uDFFF', '\uD800\uD800', '\uDFFF\uDFFF',
'a\uD800b\uDFFF', 'a\uDFFFb\uD800',
'a\uD800b\uDFFFa', 'a\uDFFFb\uD800a'):
self.assertFalse(meth(s), '%a.%s() is False' % (s, meth_name))
def test_lower(self):
string_tests.CommonTest.test_lower(self)
self.assertEqual('\U00010427'.lower(), '\U0001044F')
self.assertEqual('\U00010427\U00010427'.lower(),
'\U0001044F\U0001044F')
self.assertEqual('\U00010427\U0001044F'.lower(),
'\U0001044F\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.lower(),
'x\U0001044Fx\U0001044F')
self.assertEqual('fi'.lower(), 'fi')
self.assertEqual('\u0130'.lower(), '\u0069\u0307')
# Special case for GREEK CAPITAL LETTER SIGMA U+03A3
self.assertEqual('\u03a3'.lower(), '\u03c3')
self.assertEqual('\u0345\u03a3'.lower(), '\u0345\u03c3')
self.assertEqual('A\u0345\u03a3'.lower(), 'a\u0345\u03c2')
self.assertEqual('A\u0345\u03a3a'.lower(), 'a\u0345\u03c3a')
self.assertEqual('A\u0345\u03a3'.lower(), 'a\u0345\u03c2')
self.assertEqual('A\u03a3\u0345'.lower(), 'a\u03c2\u0345')
self.assertEqual('\u03a3\u0345 '.lower(), '\u03c3\u0345 ')
self.assertEqual('\U0008fffe'.lower(), '\U0008fffe')
self.assertEqual('\u2177'.lower(), '\u2177')
def test_casefold(self):
self.assertEqual('hello'.casefold(), 'hello')
self.assertEqual('hELlo'.casefold(), 'hello')
self.assertEqual('ß'.casefold(), 'ss')
self.assertEqual('fi'.casefold(), 'fi')
self.assertEqual('\u03a3'.casefold(), '\u03c3')
self.assertEqual('A\u0345\u03a3'.casefold(), 'a\u03b9\u03c3')
self.assertEqual('\u00b5'.casefold(), '\u03bc')
def test_upper(self):
string_tests.CommonTest.test_upper(self)
self.assertEqual('\U0001044F'.upper(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.upper(),
'\U00010427\U00010427')
self.assertEqual('\U00010427\U0001044F'.upper(),
'\U00010427\U00010427')
self.assertEqual('X\U00010427x\U0001044F'.upper(),
'X\U00010427X\U00010427')
self.assertEqual('fi'.upper(), 'FI')
self.assertEqual('\u0130'.upper(), '\u0130')
self.assertEqual('\u03a3'.upper(), '\u03a3')
self.assertEqual('ß'.upper(), 'SS')
self.assertEqual('\u1fd2'.upper(), '\u0399\u0308\u0300')
self.assertEqual('\U0008fffe'.upper(), '\U0008fffe')
self.assertEqual('\u2177'.upper(), '\u2167')
def test_capitalize(self):
string_tests.CommonTest.test_capitalize(self)
self.assertEqual('\U0001044F'.capitalize(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('\U00010427\U0001044F'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('\U0001044F\U00010427'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.capitalize(),
'X\U0001044Fx\U0001044F')
self.assertEqual('h\u0130'.capitalize(), 'H\u0069\u0307')
exp = '\u0399\u0308\u0300\u0069\u0307'
self.assertEqual('\u1fd2\u0130'.capitalize(), exp)
self.assertEqual('finnish'.capitalize(), 'Finnish')
self.assertEqual('A\u0345\u03a3'.capitalize(), 'A\u0345\u03c2')
def test_title(self):
super().test_title()
self.assertEqual('\U0001044F'.title(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.title(),
'\U00010427\U0001044F')
self.assertEqual('\U0001044F\U0001044F \U0001044F\U0001044F'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('\U00010427\U0001044F \U00010427\U0001044F'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('\U0001044F\U00010427 \U0001044F\U00010427'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F X\U00010427x\U0001044F'.title(),
'X\U0001044Fx\U0001044F X\U0001044Fx\U0001044F')
self.assertEqual('fiNNISH'.title(), 'Finnish')
self.assertEqual('A\u03a3 \u1fa1xy'.title(), 'A\u03c2 \u1fa9xy')
self.assertEqual('A\u03a3A'.title(), 'A\u03c3a')
def test_swapcase(self):
string_tests.CommonTest.test_swapcase(self)
self.assertEqual('\U0001044F'.swapcase(), '\U00010427')
self.assertEqual('\U00010427'.swapcase(), '\U0001044F')
self.assertEqual('\U0001044F\U0001044F'.swapcase(),
'\U00010427\U00010427')
self.assertEqual('\U00010427\U0001044F'.swapcase(),
'\U0001044F\U00010427')
self.assertEqual('\U0001044F\U00010427'.swapcase(),
'\U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.swapcase(),
'x\U0001044FX\U00010427')
self.assertEqual('fi'.swapcase(), 'FI')
self.assertEqual('\u0130'.swapcase(), '\u0069\u0307')
# Special case for GREEK CAPITAL LETTER SIGMA U+03A3
self.assertEqual('\u03a3'.swapcase(), '\u03c3')
self.assertEqual('\u0345\u03a3'.swapcase(), '\u0399\u03c3')
self.assertEqual('A\u0345\u03a3'.swapcase(), 'a\u0399\u03c2')
self.assertEqual('A\u0345\u03a3a'.swapcase(), 'a\u0399\u03c3A')
self.assertEqual('A\u0345\u03a3'.swapcase(), 'a\u0399\u03c2')
self.assertEqual('A\u03a3\u0345'.swapcase(), 'a\u03c2\u0399')
self.assertEqual('\u03a3\u0345 '.swapcase(), '\u03c3\u0399 ')
self.assertEqual('\u03a3'.swapcase(), '\u03c3')
self.assertEqual('ß'.swapcase(), 'SS')
self.assertEqual('\u1fd2'.swapcase(), '\u0399\u0308\u0300')
def test_center(self):
string_tests.CommonTest.test_center(self)
self.assertEqual('x'.center(2, '\U0010FFFF'),
'x\U0010FFFF')
self.assertEqual('x'.center(3, '\U0010FFFF'),
'\U0010FFFFx\U0010FFFF')
self.assertEqual('x'.center(4, '\U0010FFFF'),
'\U0010FFFFx\U0010FFFF\U0010FFFF')
@unittest.skipUnless(sys.maxsize == 2**31 - 1, "requires 32-bit system")
@support.cpython_only
def test_case_operation_overflow(self):
# Issue #22643
size = 2**32//12 + 1
try:
s = "ü" * size
except MemoryError:
self.skipTest('no enough memory (%.0f MiB required)' % (size / 2**20))
try:
self.assertRaises(OverflowError, s.upper)
finally:
del s
def test_contains(self):
# Testing Unicode contains method
self.assertIn('a', 'abdb')
self.assertIn('a', 'bdab')
self.assertIn('a', 'bdaba')
self.assertIn('a', 'bdba')
self.assertNotIn('a', 'bdb')
self.assertIn('a', 'bdba')
self.assertIn('a', ('a',1,None))
self.assertIn('a', (1,None,'a'))
self.assertIn('a', ('a',1,None))
self.assertIn('a', (1,None,'a'))
self.assertNotIn('a', ('x',1,'y'))
self.assertNotIn('a', ('x',1,None))
self.assertNotIn('abcd', 'abcxxxx')
self.assertIn('ab', 'abcd')
self.assertIn('ab', 'abc')
self.assertIn('ab', (1,None,'ab'))
self.assertIn('', 'abc')
self.assertIn('', '')
self.assertIn('', 'abc')
self.assertNotIn('\0', 'abc')
self.assertIn('\0', '\0abc')
self.assertIn('\0', 'abc\0')
self.assertIn('a', '\0abc')
self.assertIn('asdf', 'asdf')
self.assertNotIn('asdf', 'asd')
self.assertNotIn('asdf', '')