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
|
# -*- coding: iso-8859-1 -*-
""" Test script for the Unicode implementation.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
import unittest, sys, struct, codecs, new
from test import test_support, string_tests
# 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
codecs.register(search_function)
class UnicodeTest(
string_tests.CommonTest,
string_tests.MixinStrUnicodeUserStringTest,
string_tests.MixinStrUnicodeTest,
):
type2test = str
def checkequalnofix(self, result, object, methodname, *args):
method = getattr(object, methodname)
realresult = method(*args)
self.assertEqual(realresult, result)
self.assert_(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.assert_(object is not realresult)
def test_literals(self):
self.assertEqual('\xff', '\u00ff')
self.assertEqual('\uffff', '\U0000ffff')
self.assertRaises(UnicodeError, eval, '\'\\Ufffffffe\'')
self.assertRaises(UnicodeError, eval, '\'\\Uffffffff\'')
self.assertRaises(UnicodeError, eval, '\'\\U%08x\'' % 0x110000)
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))
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_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)
def test_find(self):
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)
def test_rfind(self):
string_tests.CommonTest.test_rfind(self)
# check mixed argument types
self.checkequalnofix(9, 'abcdefghiabc', 'rfind', 'abc')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
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)
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)
def test_translate(self):
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('<i><i><i>c', 'abababc', 'translate', {ord('a'):None, ord('b'):'<i>'})
self.checkequalnofix('c', 'abababc', 'translate', {ord('a'):None, ord('b'):''})
self.checkequalnofix('xyyx', 'xzx', 'translate', {ord('z'):'yy'})
self.assertRaises(TypeError, 'hello'.translate)
self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz')
def test_split(self):
string_tests.CommonTest.test_split(self)
# Mixed arguments
self.checkequalnofix(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequalnofix(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequalnofix(['endcase ', ''], 'endcase test', 'split', 'test')
def test_join(self):
string_tests.MixinStrUnicodeUserStringTest.test_join(self)
# 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'))
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)
def test_comparison(self):
# Comparisons:
self.assertEqual('abc', 'abc')
self.assertEqual('abc', 'abc')
self.assertEqual('abc', 'abc')
self.assert_('abcd' > 'abc')
self.assert_('abcd' > 'abc')
self.assert_('abcd' > 'abc')
self.assert_('abc' < 'abcd')
self.assert_('abc' < 'abcd')
self.assert_('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.assert_('\u0061' < '\u20ac')
# Non surrogate below surrogate value, no fixup required
self.assert_('\u0061' < '\ud800\udc02')
# Non surrogate above surrogate value, fixup required
def test_lecmp(s, s2):
self.assert_(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.assert_('\ud800\udc02' < '\ud84d\udc56')
def test_islower(self):
string_tests.MixinStrUnicodeUserStringTest.test_islower(self)
self.checkequalnofix(False, '\u1FFc', 'islower')
def test_isupper(self):
string_tests.MixinStrUnicodeUserStringTest.test_isupper(self)
if not sys.platform.startswith('java'):
self.checkequalnofix(False, '\u1FFc', 'isupper')
def test_istitle(self):
string_tests.MixinStrUnicodeUserStringTest.test_title(self)
self.checkequalnofix(True, '\u1FFc', 'istitle')
self.checkequalnofix(True, 'Greek \u1FFcitlecases ...', 'istitle')
def test_isspace(self):
string_tests.MixinStrUnicodeUserStringTest.test_isspace(self)
self.checkequalnofix(True, '\u2000', 'isspace')
self.checkequalnofix(True, '\u200a', 'isspace')
self.checkequalnofix(False, '\u2014', 'isspace')
def test_isalpha(self):
string_tests.MixinStrUnicodeUserStringTest.test_isalpha(self)
self.checkequalnofix(True, '\u1FFc', 'isalpha')
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)
def test_isdigit(self):
string_tests.MixinStrUnicodeUserStringTest.test_isdigit(self)
self.checkequalnofix(True, '\u2460', 'isdigit')
self.checkequalnofix(False, '\xbc', 'isdigit')
self.checkequalnofix(True, '\u0660', 'isdigit')
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)
def test_contains(self):
# Testing Unicode contains method
self.assert_('a' in 'abdb')
self.assert_('a' in 'bdab')
self.assert_('a' in 'bdaba')
self.assert_('a' in 'bdba')
self.assert_('a' not in 'bdb')
self.assert_('a' in 'bdba')
self.assert_('a' in ('a',1,None))
self.assert_('a' in (1,None,'a'))
self.assert_('a' in ('a',1,None))
self.assert_('a' in (1,None,'a'))
self.assert_('a' not in ('x',1,'y'))
self.assert_('a' not in ('x',1,None))
self.assert_('abcd' not in 'abcxxxx')
self.assert_('ab' in 'abcd')
self.assert_('ab' in 'abc')
self.assert_('ab' in (1,None,'ab'))
self.assert_('' in 'abc')
self.assert_('' in '')
self.assert_('' in 'abc')
self.assert_('\0' not in 'abc')
self.assert_('\0' in '\0abc')
self.assert_('\0' in 'abc\0')
self.assert_('a' in '\0abc')
self.assert_('asdf' in 'asdf')
self.assert_('asdf' not in 'asd')
self.assert_('asdf' not in '')
self.assertRaises(TypeError, "abc".__contains__)
def test_formatting(self):
string_tests.MixinStrUnicodeUserStringTest.test_formatting(self)
# Testing Unicode formatting strings...
self.assertEqual("%s, %s" % ("abc", "abc"), 'abc, abc')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", 1, 2, 3), 'abc, abc, 1, 2.000000, 3.00')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", 1, -2, 3), 'abc, abc, 1, -2.000000, 3.00')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 3.5), 'abc, abc, -1, -2.000000, 3.50')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 3.57), 'abc, abc, -1, -2.000000, 3.57')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 1003.57), 'abc, abc, -1, -2.000000, 1003.57')
if not sys.platform.startswith('java'):
self.assertEqual("%r, %r" % (b"abc", "abc"), "b'abc', 'abc'")
self.assertEqual("%(x)s, %(y)s" % {'x':"abc", 'y':"def"}, 'abc, def')
self.assertEqual("%(x)s, %(\xfc)s" % {'x':"abc", '\xfc':"def"}, 'abc, def')
self.assertEqual('%c' % 0x1234, '\u1234')
self.assertRaises(OverflowError, "%c".__mod__, (sys.maxunicode+1,))
# formatting jobs delegated from the string implementation:
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc",'def':123}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc",'def':123}, '...abc...')
self.assertEqual('...%s...%s...%s...%s...' % (1,2,3,"abc"), '...1...2...3...abc...')
self.assertEqual('...%%...%%s...%s...%s...%s...%s...' % (1,2,3,"abc"), '...%...%s...1...2...3...abc...')
self.assertEqual('...%s...' % "abc", '...abc...')
self.assertEqual('%*s' % (5,'abc',), ' abc')
self.assertEqual('%*s' % (-5,'abc',), 'abc ')
self.assertEqual('%*.*s' % (5,2,'abc',), ' ab')
self.assertEqual('%*.*s' % (5,3,'abc',), ' abc')
self.assertEqual('%i %*.*s' % (10, 5,3,'abc',), '10 abc')
self.assertEqual('%i%s %*.*s' % (10, 3, 5, 3, 'abc',), '103 abc')
self.assertEqual('%c' % 'a', 'a')
class Wrapper:
def __str__(self):
return '\u1234'
self.assertEqual('%s' % Wrapper(), '\u1234')
@test_support.run_with_locale('LC_ALL', 'de_DE', 'fr_FR')
def test_format_float(self):
# should not format with a comma, but always with C locale
self.assertEqual('1.0', '%.1f' % 1.0)
def test_constructor(self):
# unicode(obj) tests (this maps to PyObject_Unicode() at C level)
self.assertEqual(
str('unicode remains unicode'),
'unicode remains unicode'
)
class UnicodeSubclass(str):
pass
self.assertEqual(
str(UnicodeSubclass('unicode subclass becomes unicode')),
'unicode subclass becomes unicode'
)
self.assertEqual(
str('strings are converted to unicode'),
'strings are converted to unicode'
)
class UnicodeCompat:
def __init__(self, x):
self.x = x
def __unicode__(self):
return self.x
self.assertEqual(
str(UnicodeCompat('__unicode__ compatible objects are recognized')),
'__unicode__ compatible objects are recognized')
class StringCompat:
def __init__(self, x):
self.x = x
def __str__(self):
return self.x
self.assertEqual(
str(StringCompat('__str__ compatible objects are recognized')),
'__str__ compatible objects are recognized'
)
# unicode(obj) is compatible to str():
o = StringCompat('unicode(obj) is compatible to str()')
self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
# %-formatting and .__unicode__()
self.assertEqual('%s' %
UnicodeCompat("u'%s' % obj uses obj.__unicode__()"),
"u'%s' % obj uses obj.__unicode__()")
self.assertEqual('%s' %
UnicodeCompat("u'%s' % obj falls back to obj.__str__()"),
"u'%s' % obj falls back to obj.__str__()")
for obj in (123, 123.45, 123):
self.assertEqual(str(obj), str(str(obj)))
# unicode(obj, encoding, error) tests (this maps to
# PyUnicode_FromEncodedObject() at C level)
if not sys.platform.startswith('java'):
self.assertRaises(
TypeError,
str,
'decoding unicode is not supported',
'utf-8',
'strict'
)
self.assertEqual(
str(b'strings are decoded to unicode', 'utf-8', 'strict'),
'strings are decoded to unicode'
)
if not sys.platform.startswith('java'):
self.assertEqual(
str(
buffer('character buffers are decoded to unicode'),
'utf-8',
'strict'
),
'character buffers are decoded to unicode'
)
self.assertRaises(TypeError, str, 42, 42, 42)
def test_codecs_utf7(self):
utfTests = [
('A\u2262\u0391.', b'A+ImIDkQ.'), # RFC2152 example
('Hi Mom -\u263a-!', b'Hi Mom -+Jjo--!'), # RFC2152 example
('\u65E5\u672C\u8A9E', b'+ZeVnLIqe-'), # RFC2152 example
('Item 3 is \u00a31.', b'Item 3 is +AKM-1.'), # RFC2152 example
('+', b'+-'),
('+-', b'+--'),
('+?', b'+-?'),
('\?', b'+AFw?'),
('+?', b'+-?'),
(r'\\?', b'+AFwAXA?'),
(r'\\\?', b'+AFwAXABc?'),
(r'++--', b'+-+---')
]
for (x, y) in utfTests:
self.assertEqual(x.encode('utf-7'), y)
# surrogates not supported
self.assertRaises(UnicodeError, str, b'+3ADYAA-', 'utf-7')
self.assertEqual(str(b'+3ADYAA-', 'utf-7', 'replace'), '\ufffd')
def test_codecs_utf8(self):
self.assertEqual(''.encode('utf-8'), b'')
self.assertEqual('\u20ac'.encode('utf-8'), b'\xe2\x82\xac')
self.assertEqual('\ud800\udc02'.encode('utf-8'), b'\xf0\x90\x80\x82')
self.assertEqual('\ud84d\udc56'.encode('utf-8'), b'\xf0\xa3\x91\x96')
self.assertEqual('\ud800'.encode('utf-8'), b'\xed\xa0\x80')
self.assertEqual('\udc00'.encode('utf-8'), b'\xed\xb0\x80')
self.assertEqual(
('\ud800\udc02'*1000).encode('utf-8'),
b'\xf0\x90\x80\x82'*1000
)
self.assertEqual(
'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
' Nunstuck git und'.encode('utf-8'),
b'\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
b'\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
b'\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
b'\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
b'\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
b'\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
b'\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
b'\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
b'\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
b'\xe3\x80\x8cWenn ist das Nunstuck git und'
)
# UTF-8 specific decoding tests
self.assertEqual(str(b'\xf0\xa3\x91\x96', 'utf-8'), '\U00023456' )
self.assertEqual(str(b'\xf0\x90\x80\x82', 'utf-8'), '\U00010002' )
self.assertEqual(str(b'\xe2\x82\xac', 'utf-8'), '\u20ac' )
# Other possible utf-8 test cases:
# * strict decoding testing for all of the
# UTF8_ERROR cases in PyUnicode_DecodeUTF8
def test_codecs_idna(self):
# Test whether trailing dot is preserved
self.assertEqual("www.python.org.".encode("idna"), b"www.python.org.")
def test_codecs_errors(self):
# Error handling (encoding)
self.assertRaises(UnicodeError, 'Andr\202 x'.encode, 'ascii')
self.assertRaises(UnicodeError, 'Andr\202 x'.encode, 'ascii','strict')
self.assertEqual('Andr\202 x'.encode('ascii','ignore'), b"Andr x")
self.assertEqual('Andr\202 x'.encode('ascii','replace'), b"Andr? x")
# Error handling (decoding)
self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii')
self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii', 'strict')
self.assertEqual(str(b'Andr\202 x', 'ascii', 'ignore'), "Andr x")
self.assertEqual(str(b'Andr\202 x', 'ascii', 'replace'), 'Andr\uFFFD x')
# Error handling (unknown character names)
self.assertEqual("\\N{foo}xx".decode("unicode-escape", "ignore"), "xx")
# Error handling (truncated escape sequence)
self.assertRaises(UnicodeError, "\\".decode, "unicode-escape")
self.assertRaises(TypeError, "hello".decode, "test.unicode1")
self.assertRaises(TypeError, str, "hello", "test.unicode2")
self.assertRaises(TypeError, "hello".encode, "test.unicode1")
self.assertRaises(TypeError, "hello".encode, "test.unicode2")
# executes PyUnicode_Encode()
import imp
self.assertRaises(
ImportError,
imp.find_module,
"non-existing module",
["non-existing dir"]
)
# Error handling (wrong arguments)
self.assertRaises(TypeError, "hello".encode, 42, 42, 42)
# Error handling (PyUnicode_EncodeDecimal())
self.assertRaises(UnicodeError, int, "\u0200")
def test_codecs(self):
# Encoding
self.assertEqual('hello'.encode('ascii'), b'hello')
self.assertEqual('hello'.encode('utf-7'), b'hello')
self.assertEqual('hello'.encode('utf-8'), b'hello')
self.assertEqual('hello'.encode('utf8'), b'hello')
self.assertEqual('hello'.encode('utf-16-le'), b'h\000e\000l\000l\000o\000')
self.assertEqual('hello'.encode('utf-16-be'), b'\000h\000e\000l\000l\000o')
self.assertEqual('hello'.encode('latin-1'), b'hello')
# Roundtrip safety for BMP (just the first 1024 chars)
for c in range(1024):
u = chr(c)
for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
'utf-16-be', 'raw_unicode_escape',
'unicode_escape', 'unicode_internal'):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for BMP (just the first 256 chars)
for c in range(256):
u = chr(c)
for encoding in ('latin-1',):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for BMP (just the first 128 chars)
for c in range(128):
u = chr(c)
for encoding in ('ascii',):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for non-BMP (just a few chars)
u = '\U00010001\U00020002\U00030003\U00040004\U00050005'
for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
#'raw_unicode_escape',
'unicode_escape', 'unicode_internal'):
self.assertEqual(str(u.encode(encoding),encoding), u)
# UTF-8 must be roundtrip safe for all UCS-2 code points
# This excludes surrogates: in the full range, there would be
# a surrogate pair (\udbff\udc00), which gets converted back
# to a non-BMP character (\U0010fc00)
u = ''.join(map(chr, list(range(0,0xd800)) +
list(range(0xe000,0x10000))))
for encoding in ('utf-8',):
self.assertEqual(str(u.encode(encoding),encoding), u)
def test_codecs_charmap(self):
# 0-127
s = bytes(range(128))
for encoding in (
'cp037', 'cp1026',
'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
'cp863', 'cp865', 'cp866',
'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
'mac_cyrillic', 'mac_latin2',
'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
'cp1256', 'cp1257', 'cp1258',
'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
'cp1006', 'iso8859_8',
### These have undefined mappings:
#'cp424',
### These fail the round-trip:
#'cp875'
):
self.assertEqual(str(s, encoding).encode(encoding), s)
# 128-255
s = bytes(range(128, 256))
for encoding in (
'cp037', 'cp1026',
'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
'cp863', 'cp865', 'cp866',
'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_2', 'iso8859_4', 'iso8859_5',
'iso8859_9', 'koi8_r', 'latin_1',
'mac_cyrillic', 'mac_latin2',
### These have undefined mappings:
#'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
#'cp1256', 'cp1257', 'cp1258',
#'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
#'iso8859_3', 'iso8859_6', 'iso8859_7',
#'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
### These fail the round-trip:
#'cp1006', 'cp875', 'iso8859_8',
):
self.assertEqual(str(s, encoding).encode(encoding), s)
def test_concatenation(self):
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def" "ghi"), "abcdefghi")
self.assertEqual(("abc" "def" "ghi"), "abcdefghi")
def test_printing(self):
class BitBucket:
def write(self, text):
pass
out = BitBucket()
print('abc', file=out)
print('abc', 'def', file=out)
print('abc', 'def', file=out)
print('abc', 'def', file=out)
print('abc\n', file=out)
print('abc\n', end=' ', file=out)
print('abc\n', end=' ', file=out)
print('def\n', file=out)
print('def\n', file=out)
def test_ucs4(self):
if sys.maxunicode == 0xFFFF:
return
x = '\U00100000'
y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
self.assertEqual(x, y)
def test_conversion(self):
# Make sure __unicode__() works properly
class Foo0:
def __str__(self):
return "foo"
class Foo1:
def __unicode__(self):
return "foo"
class Foo2(object):
def __unicode__(self):
return "foo"
class Foo3(object):
def __unicode__(self):
return "foo"
class Foo4(str):
def __unicode__(self):
return "foo"
class Foo5(str):
def __unicode__(self):
return "foo"
class Foo6(str):
def __str__(self):
return "foos"
def __unicode__(self):
return "foou"
class Foo7(str):
def __str__(self):
return "foos"
def __unicode__(self):
return "foou"
class Foo8(str):
def __new__(cls, content=""):
return str.__new__(cls, 2*content)
def __unicode__(self):
return self
class Foo9(str):
def __str__(self):
return "string"
def __unicode__(self):
return "not unicode"
self.assertEqual(str(Foo0()), "foo")
self.assertEqual(str(Foo1()), "foo")
self.assertEqual(str(Foo2()), "foo")
self.assertEqual(str(Foo3()), "foo")
self.assertEqual(str(Foo4("bar")), "foo")
self.assertEqual(str(Foo5("bar")), "foo")
self.assertEqual(str(Foo6("bar")), "foou")
self.assertEqual(str(Foo7("bar")), "foou")
self.assertEqual(str(Foo8("foo")), "foofoo")
self.assertEqual(str(Foo9("foo")), "not unicode")
def test_unicode_repr(self):
class s1:
def __repr__(self):
return '\\n'
class s2:
def __repr__(self):
return '\\n'
self.assertEqual(repr(s1()), '\\n')
self.assertEqual(repr(s2()), '\\n')
def test_expandtabs_overflows_gracefully(self):
# This test only affects 32-bit platforms because expandtabs can only take
# an int as the max value, not a 64-bit C long. If expandtabs is changed
# to take a 64-bit long, this test should apply to all platforms.
if sys.maxint > (1 << 32) or struct.calcsize('P') != 4:
return
self.assertRaises(OverflowError, 't\tt\t'.expandtabs, sys.maxint)
def test_main():
test_support.run_unittest(__name__)
if __name__ == "__main__":
test_main()
|