Source

cpython / Lib / test / test_re.py

Full commit
  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
from test.support import verbose, run_unittest, gc_collect
import io
import re
from re import Scanner
import sys
import string
import traceback
from weakref import proxy

# Misc tests from Tim Peters' re.doc

# WARNING: Don't change details in these tests if you don't know
# what you're doing. Some of these tests were carefully modeled to
# cover most of the code.

import unittest

class ReTests(unittest.TestCase):

    def test_keep_buffer(self):
        # See bug 14212
        b = bytearray(b'x')
        it = re.finditer(b'a', b)
        with self.assertRaises(BufferError):
            b.extend(b'x'*400)
        list(it)
        del it
        gc_collect()
        b.extend(b'x'*400)

    def test_weakref(self):
        s = 'QabbbcR'
        x = re.compile('ab+c')
        y = proxy(x)
        self.assertEqual(x.findall('QabbbcR'), y.findall('QabbbcR'))

    def test_search_star_plus(self):
        self.assertEqual(re.search('x*', 'axx').span(0), (0, 0))
        self.assertEqual(re.search('x*', 'axx').span(), (0, 0))
        self.assertEqual(re.search('x+', 'axx').span(0), (1, 3))
        self.assertEqual(re.search('x+', 'axx').span(), (1, 3))
        self.assertEqual(re.search('x', 'aaa'), None)
        self.assertEqual(re.match('a*', 'xxx').span(0), (0, 0))
        self.assertEqual(re.match('a*', 'xxx').span(), (0, 0))
        self.assertEqual(re.match('x*', 'xxxa').span(0), (0, 3))
        self.assertEqual(re.match('x*', 'xxxa').span(), (0, 3))
        self.assertEqual(re.match('a+', 'xxx'), None)

    def bump_num(self, matchobj):
        int_value = int(matchobj.group(0))
        return str(int_value + 1)

    def test_basic_re_sub(self):
        self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'),
                         '9.3 -3 24x100y')
        self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3),
                         '9.3 -3 23x99y')

        self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n')
        self.assertEqual(re.sub('.', r"\n", 'x'), '\n')

        s = r"\1\1"
        self.assertEqual(re.sub('(.)', s, 'x'), 'xx')
        self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s)
        self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s)

        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx')
        self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx')

        self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'),
                         '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a')
        self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'),
                         (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)))

        self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')

    def test_bug_449964(self):
        # fails for group followed by other escape
        self.assertEqual(re.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx'),
                         'xx\bxx\b')

    def test_bug_449000(self):
        # Test for sub() on escaped characters
        self.assertEqual(re.sub(r'\r\n', r'\n', 'abc\r\ndef\r\n'),
                         'abc\ndef\n')
        self.assertEqual(re.sub('\r\n', r'\n', 'abc\r\ndef\r\n'),
                         'abc\ndef\n')
        self.assertEqual(re.sub(r'\r\n', '\n', 'abc\r\ndef\r\n'),
                         'abc\ndef\n')
        self.assertEqual(re.sub('\r\n', '\n', 'abc\r\ndef\r\n'),
                         'abc\ndef\n')

    def test_bug_1661(self):
        # Verify that flags do not get silently ignored with compiled patterns
        pattern = re.compile('.')
        self.assertRaises(ValueError, re.match, pattern, 'A', re.I)
        self.assertRaises(ValueError, re.search, pattern, 'A', re.I)
        self.assertRaises(ValueError, re.findall, pattern, 'A', re.I)
        self.assertRaises(ValueError, re.compile, pattern, re.I)

    def test_bug_3629(self):
        # A regex that triggered a bug in the sre-code validator
        re.compile("(?P<quote>)(?(quote))")

    def test_sub_template_numeric_escape(self):
        # bug 776311 and friends
        self.assertEqual(re.sub('x', r'\0', 'x'), '\0')
        self.assertEqual(re.sub('x', r'\000', 'x'), '\000')
        self.assertEqual(re.sub('x', r'\001', 'x'), '\001')
        self.assertEqual(re.sub('x', r'\008', 'x'), '\0' + '8')
        self.assertEqual(re.sub('x', r'\009', 'x'), '\0' + '9')
        self.assertEqual(re.sub('x', r'\111', 'x'), '\111')
        self.assertEqual(re.sub('x', r'\117', 'x'), '\117')

        self.assertEqual(re.sub('x', r'\1111', 'x'), '\1111')
        self.assertEqual(re.sub('x', r'\1111', 'x'), '\111' + '1')

        self.assertEqual(re.sub('x', r'\00', 'x'), '\x00')
        self.assertEqual(re.sub('x', r'\07', 'x'), '\x07')
        self.assertEqual(re.sub('x', r'\08', 'x'), '\0' + '8')
        self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
        self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')

        self.assertEqual(re.sub('x', r'\400', 'x'), '\0')
        self.assertEqual(re.sub('x', r'\777', 'x'), '\377')

        self.assertRaises(re.error, re.sub, 'x', r'\1', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\8', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\9', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\11', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\18', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\1a', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\90', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\99', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\118', 'x') # r'\11' + '8'
        self.assertRaises(re.error, re.sub, 'x', r'\11a', 'x')
        self.assertRaises(re.error, re.sub, 'x', r'\181', 'x') # r'\18' + '1'
        self.assertRaises(re.error, re.sub, 'x', r'\800', 'x') # r'\80' + '0'

        # in python2.3 (etc), these loop endlessly in sre_parser.py
        self.assertEqual(re.sub('(((((((((((x)))))))))))', r'\11', 'x'), 'x')
        self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\118', 'xyz'),
                         'xz8')
        self.assertEqual(re.sub('((((((((((y))))))))))(.)', r'\11a', 'xyz'),
                         'xza')

    def test_qualified_re_sub(self):
        self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb')
        self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa')

    def test_bug_114660(self):
        self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello  there'),
                         'hello there')

    def test_bug_462270(self):
        # Test for empty sub() behaviour, see SF bug #462270
        self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
        self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')

    def test_symbolic_refs(self):
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx')
        self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx')
        self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx')

    def test_re_subn(self):
        self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2))
        self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1))
        self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0))
        self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4))
        self.assertEqual(re.subn("b*", "x", "xyz", 2), ('xxxyz', 2))

    def test_re_split(self):
        self.assertEqual(re.split(":", ":a:b::c"), ['', 'a', 'b', '', 'c'])
        self.assertEqual(re.split(":*", ":a:b::c"), ['', 'a', 'b', 'c'])
        self.assertEqual(re.split("(:*)", ":a:b::c"),
                         ['', ':', 'a', ':', 'b', '::', 'c'])
        self.assertEqual(re.split("(?::*)", ":a:b::c"), ['', 'a', 'b', 'c'])
        self.assertEqual(re.split("(:)*", ":a:b::c"),
                         ['', ':', 'a', ':', 'b', ':', 'c'])
        self.assertEqual(re.split("([b:]+)", ":a:b::c"),
                         ['', ':', 'a', ':b::', 'c'])
        self.assertEqual(re.split("(b)|(:+)", ":a:b::c"),
                         ['', None, ':', 'a', None, ':', '', 'b', None, '',
                          None, '::', 'c'])
        self.assertEqual(re.split("(?:b)|(?::+)", ":a:b::c"),
                         ['', 'a', '', '', 'c'])

    def test_qualified_re_split(self):
        self.assertEqual(re.split(":", ":a:b::c", 2), ['', 'a', 'b::c'])
        self.assertEqual(re.split(':', 'a:b:c:d', 2), ['a', 'b', 'c:d'])
        self.assertEqual(re.split("(:)", ":a:b::c", 2),
                         ['', ':', 'a', ':', 'b::c'])
        self.assertEqual(re.split("(:*)", ":a:b::c", 2),
                         ['', ':', 'a', ':', 'b::c'])

    def test_re_findall(self):
        self.assertEqual(re.findall(":+", "abc"), [])
        self.assertEqual(re.findall(":+", "a:b::c:::d"), [":", "::", ":::"])
        self.assertEqual(re.findall("(:+)", "a:b::c:::d"), [":", "::", ":::"])
        self.assertEqual(re.findall("(:)(:*)", "a:b::c:::d"), [(":", ""),
                                                               (":", ":"),
                                                               (":", "::")])

    def test_bug_117612(self):
        self.assertEqual(re.findall(r"(a|(b))", "aba"),
                         [("a", ""),("b", "b"),("a", "")])

    def test_re_match(self):
        self.assertEqual(re.match('a', 'a').groups(), ())
        self.assertEqual(re.match('(a)', 'a').groups(), ('a',))
        self.assertEqual(re.match(r'(a)', 'a').group(0), 'a')
        self.assertEqual(re.match(r'(a)', 'a').group(1), 'a')
        self.assertEqual(re.match(r'(a)', 'a').group(1, 1), ('a', 'a'))

        pat = re.compile('((a)|(b))(c)?')
        self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None))
        self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None))
        self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c'))
        self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c'))
        self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c'))

        # A single group
        m = re.match('(a)', 'a')
        self.assertEqual(m.group(0), 'a')
        self.assertEqual(m.group(0), 'a')
        self.assertEqual(m.group(1), 'a')
        self.assertEqual(m.group(1, 1), ('a', 'a'))

        pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?')
        self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None))
        self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'),
                         (None, 'b', None))
        self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))

    def test_re_groupref_exists(self):
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
                         ('(', 'a'))
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
                         (None, 'a'))
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None)
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None)
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
                         ('a', 'b'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
                         ('a', ''))

        # Tests for bug #1177831: exercise groups other than the first group
        p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
        self.assertEqual(p.match('abc').groups(),
                         ('a', 'b', 'c'))
        self.assertEqual(p.match('ad').groups(),
                         ('a', None, 'd'))
        self.assertEqual(p.match('abd'), None)
        self.assertEqual(p.match('ac'), None)


    def test_re_groupref(self):
        self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(),
                         ('|', 'a'))
        self.assertEqual(re.match(r'^(\|)?([^()]+)\1?$', 'a').groups(),
                         (None, 'a'))
        self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', 'a|'), None)
        self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a'), None)
        self.assertEqual(re.match(r'^(?:(a)|c)(\1)$', 'aa').groups(),
                         ('a', 'a'))
        self.assertEqual(re.match(r'^(?:(a)|c)(\1)?$', 'c').groups(),
                         (None, None))

    def test_groupdict(self):
        self.assertEqual(re.match('(?P<first>first) (?P<second>second)',
                                  'first second').groupdict(),
                         {'first':'first', 'second':'second'})

    def test_expand(self):
        self.assertEqual(re.match("(?P<first>first) (?P<second>second)",
                                  "first second")
                                  .expand(r"\2 \1 \g<second> \g<first>"),
                         "second first second first")

    def test_repeat_minmax(self):
        self.assertEqual(re.match("^(\w){1}$", "abc"), None)
        self.assertEqual(re.match("^(\w){1}?$", "abc"), None)
        self.assertEqual(re.match("^(\w){1,2}$", "abc"), None)
        self.assertEqual(re.match("^(\w){1,2}?$", "abc"), None)

        self.assertEqual(re.match("^(\w){3}$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){1,3}$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){1,4}$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){3}?$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){1,3}?$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){1,4}?$", "abc").group(1), "c")
        self.assertEqual(re.match("^(\w){3,4}?$", "abc").group(1), "c")

        self.assertEqual(re.match("^x{1}$", "xxx"), None)
        self.assertEqual(re.match("^x{1}?$", "xxx"), None)
        self.assertEqual(re.match("^x{1,2}$", "xxx"), None)
        self.assertEqual(re.match("^x{1,2}?$", "xxx"), None)

        self.assertNotEqual(re.match("^x{3}$", "xxx"), None)
        self.assertNotEqual(re.match("^x{1,3}$", "xxx"), None)
        self.assertNotEqual(re.match("^x{1,4}$", "xxx"), None)
        self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)
        self.assertNotEqual(re.match("^x{3}?$", "xxx"), None)
        self.assertNotEqual(re.match("^x{1,3}?$", "xxx"), None)
        self.assertNotEqual(re.match("^x{1,4}?$", "xxx"), None)
        self.assertNotEqual(re.match("^x{3,4}?$", "xxx"), None)

        self.assertEqual(re.match("^x{}$", "xxx"), None)
        self.assertNotEqual(re.match("^x{}$", "x{}"), None)

    def test_getattr(self):
        self.assertEqual(re.compile("(?i)(a)(b)").pattern, "(?i)(a)(b)")
        self.assertEqual(re.compile("(?i)(a)(b)").flags, re.I | re.U)
        self.assertEqual(re.compile("(?i)(a)(b)").groups, 2)
        self.assertEqual(re.compile("(?i)(a)(b)").groupindex, {})
        self.assertEqual(re.compile("(?i)(?P<first>a)(?P<other>b)").groupindex,
                         {'first': 1, 'other': 2})

        self.assertEqual(re.match("(a)", "a").pos, 0)
        self.assertEqual(re.match("(a)", "a").endpos, 1)
        self.assertEqual(re.match("(a)", "a").string, "a")
        self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1)))
        self.assertNotEqual(re.match("(a)", "a").re, None)

    def test_special_escapes(self):
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx").group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd").group(1), "bx")
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx", re.LOCALE).group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd", re.LOCALE).group(1), "bx")
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx", re.UNICODE).group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd", re.UNICODE).group(1), "bx")
        self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc")
        self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc")
        self.assertEqual(re.search(r"^\Aabc\Z$", "\nabc\n", re.M), None)
        self.assertEqual(re.search(r"\b(b.)\b",
                                   "abcd abc bcd bx").group(1), "bx")
        self.assertEqual(re.search(r"\B(b.)\B",
                                   "abc bcd bc abxd").group(1), "bx")
        self.assertEqual(re.search(r"^abc$", "\nabc\n", re.M).group(0), "abc")
        self.assertEqual(re.search(r"^\Aabc\Z$", "abc", re.M).group(0), "abc")
        self.assertEqual(re.search(r"^\Aabc\Z$", "\nabc\n", re.M), None)
        self.assertEqual(re.search(r"\d\D\w\W\s\S",
                                   "1aa! a").group(0), "1aa! a")
        self.assertEqual(re.search(r"\d\D\w\W\s\S",
                                   "1aa! a", re.LOCALE).group(0), "1aa! a")
        self.assertEqual(re.search(r"\d\D\w\W\s\S",
                                   "1aa! a", re.UNICODE).group(0), "1aa! a")

    def test_string_boundaries(self):
        # See http://bugs.python.org/issue10713
        self.assertEqual(re.search(r"\b(abc)\b", "abc").group(1),
                         "abc")
        # There's a word boundary at the start of a string.
        self.assertTrue(re.match(r"\b", "abc"))
        # A non-empty string includes a non-boundary zero-length match.
        self.assertTrue(re.search(r"\B", "abc"))
        # There is no non-boundary match at the start of a string.
        self.assertFalse(re.match(r"\B", "abc"))
        # However, an empty string contains no word boundaries, and also no
        # non-boundaries.
        self.assertEqual(re.search(r"\B", ""), None)
        # This one is questionable and different from the perlre behaviour,
        # but describes current behavior.
        self.assertEqual(re.search(r"\b", ""), None)
        # A single word-character string has two boundaries, but no
        # non-boundary gaps.
        self.assertEqual(len(re.findall(r"\b", "a")), 2)
        self.assertEqual(len(re.findall(r"\B", "a")), 0)
        # If there are no words, there are no boundaries
        self.assertEqual(len(re.findall(r"\b", " ")), 0)
        self.assertEqual(len(re.findall(r"\b", "   ")), 0)
        # Can match around the whitespace.
        self.assertEqual(len(re.findall(r"\B", " ")), 2)

    def test_bigcharset(self):
        self.assertEqual(re.match("([\u2222\u2223])",
                                  "\u2222").group(1), "\u2222")
        self.assertEqual(re.match("([\u2222\u2223])",
                                  "\u2222", re.UNICODE).group(1), "\u2222")

    def test_anyall(self):
        self.assertEqual(re.match("a.b", "a\nb", re.DOTALL).group(0),
                         "a\nb")
        self.assertEqual(re.match("a.*b", "a\n\nb", re.DOTALL).group(0),
                         "a\n\nb")

    def test_non_consuming(self):
        self.assertEqual(re.match("(a(?=\s[^a]))", "a b").group(1), "a")
        self.assertEqual(re.match("(a(?=\s[^a]*))", "a b").group(1), "a")
        self.assertEqual(re.match("(a(?=\s[abc]))", "a b").group(1), "a")
        self.assertEqual(re.match("(a(?=\s[abc]*))", "a bc").group(1), "a")
        self.assertEqual(re.match(r"(a)(?=\s\1)", "a a").group(1), "a")
        self.assertEqual(re.match(r"(a)(?=\s\1*)", "a aa").group(1), "a")
        self.assertEqual(re.match(r"(a)(?=\s(abc|a))", "a a").group(1), "a")

        self.assertEqual(re.match(r"(a(?!\s[^a]))", "a a").group(1), "a")
        self.assertEqual(re.match(r"(a(?!\s[abc]))", "a d").group(1), "a")
        self.assertEqual(re.match(r"(a)(?!\s\1)", "a b").group(1), "a")
        self.assertEqual(re.match(r"(a)(?!\s(abc|a))", "a b").group(1), "a")

    def test_ignore_case(self):
        self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
        self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
        self.assertEqual(re.match(r"(a\s[^a])", "a b", re.I).group(1), "a b")
        self.assertEqual(re.match(r"(a\s[^a]*)", "a bb", re.I).group(1), "a bb")
        self.assertEqual(re.match(r"(a\s[abc])", "a b", re.I).group(1), "a b")
        self.assertEqual(re.match(r"(a\s[abc]*)", "a bb", re.I).group(1), "a bb")
        self.assertEqual(re.match(r"((a)\s\2)", "a a", re.I).group(1), "a a")
        self.assertEqual(re.match(r"((a)\s\2*)", "a aa", re.I).group(1), "a aa")
        self.assertEqual(re.match(r"((a)\s(abc|a))", "a a", re.I).group(1), "a a")
        self.assertEqual(re.match(r"((a)\s(abc|a)*)", "a aa", re.I).group(1), "a aa")

    def test_category(self):
        self.assertEqual(re.match(r"(\s)", " ").group(1), " ")

    def test_getlower(self):
        import _sre
        self.assertEqual(_sre.getlower(ord('A'), 0), ord('a'))
        self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a'))
        self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a'))

        self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")
        self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC")

    def test_not_literal(self):
        self.assertEqual(re.search("\s([^a])", " b").group(1), "b")
        self.assertEqual(re.search("\s([^a]*)", " bb").group(1), "bb")

    def test_search_coverage(self):
        self.assertEqual(re.search("\s(b)", " b").group(1), "b")
        self.assertEqual(re.search("a\s", "a ").group(0), "a ")

    def assertMatch(self, pattern, text, match=None, span=None,
                    matcher=re.match):
        if match is None and span is None:
            # the pattern matches the whole text
            match = text
            span = (0, len(text))
        elif match is None or span is None:
            raise ValueError('If match is not None, span should be specified '
                             '(and vice versa).')
        m = matcher(pattern, text)
        self.assertTrue(m)
        self.assertEqual(m.group(), match)
        self.assertEqual(m.span(), span)

    def test_re_escape(self):
        alnum_chars = string.ascii_letters + string.digits + '_'
        p = ''.join(chr(i) for i in range(256))
        for c in p:
            if c in alnum_chars:
                self.assertEqual(re.escape(c), c)
            elif c == '\x00':
                self.assertEqual(re.escape(c), '\\000')
            else:
                self.assertEqual(re.escape(c), '\\' + c)
            self.assertMatch(re.escape(c), c)
        self.assertMatch(re.escape(p), p)

    def test_re_escape_byte(self):
        alnum_chars = (string.ascii_letters + string.digits + '_').encode('ascii')
        p = bytes(range(256))
        for i in p:
            b = bytes([i])
            if b in alnum_chars:
                self.assertEqual(re.escape(b), b)
            elif i == 0:
                self.assertEqual(re.escape(b), b'\\000')
            else:
                self.assertEqual(re.escape(b), b'\\' + b)
            self.assertMatch(re.escape(b), b)
        self.assertMatch(re.escape(p), p)

    def test_re_escape_non_ascii(self):
        s = 'xxx\u2620\u2620\u2620xxx'
        s_escaped = re.escape(s)
        self.assertEqual(s_escaped, 'xxx\\\u2620\\\u2620\\\u2620xxx')
        self.assertMatch(s_escaped, s)
        self.assertMatch('.%s+.' % re.escape('\u2620'), s,
                         'x\u2620\u2620\u2620x', (2, 7), re.search)

    def test_re_escape_non_ascii_bytes(self):
        b = 'y\u2620y\u2620y'.encode('utf-8')
        b_escaped = re.escape(b)
        self.assertEqual(b_escaped, b'y\\\xe2\\\x98\\\xa0y\\\xe2\\\x98\\\xa0y')
        self.assertMatch(b_escaped, b)
        res = re.findall(re.escape('\u2620'.encode('utf-8')), b)
        self.assertEqual(len(res), 2)

    def pickle_test(self, pickle):
        oldpat = re.compile('a(?:b|(c|e){1,2}?|d)+?(.)')
        s = pickle.dumps(oldpat)
        newpat = pickle.loads(s)
        self.assertEqual(oldpat, newpat)

    def test_constants(self):
        self.assertEqual(re.I, re.IGNORECASE)
        self.assertEqual(re.L, re.LOCALE)
        self.assertEqual(re.M, re.MULTILINE)
        self.assertEqual(re.S, re.DOTALL)
        self.assertEqual(re.X, re.VERBOSE)

    def test_flags(self):
        for flag in [re.I, re.M, re.X, re.S, re.L]:
            self.assertNotEqual(re.compile('^pattern$', flag), None)

    def test_sre_character_literals(self):
        for i in [0, 8, 16, 32, 64, 127, 128, 255]:
            self.assertNotEqual(re.match(r"\%03o" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"\%03o0" % i, chr(i)+"0"), None)
            self.assertNotEqual(re.match(r"\%03o8" % i, chr(i)+"8"), None)
            self.assertNotEqual(re.match(r"\x%02x" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"\x%02x0" % i, chr(i)+"0"), None)
            self.assertNotEqual(re.match(r"\x%02xz" % i, chr(i)+"z"), None)
        self.assertRaises(re.error, re.match, "\911", "")

    def test_sre_character_class_literals(self):
        for i in [0, 8, 16, 32, 64, 127, 128, 255]:
            self.assertNotEqual(re.match(r"[\%03o]" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"[\%03o0]" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"[\%03o8]" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"[\x%02x]" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"[\x%02x0]" % i, chr(i)), None)
            self.assertNotEqual(re.match(r"[\x%02xz]" % i, chr(i)), None)
        self.assertRaises(re.error, re.match, "[\911]", "")

    def test_bug_113254(self):
        self.assertEqual(re.match(r'(a)|(b)', 'b').start(1), -1)
        self.assertEqual(re.match(r'(a)|(b)', 'b').end(1), -1)
        self.assertEqual(re.match(r'(a)|(b)', 'b').span(1), (-1, -1))

    def test_bug_527371(self):
        # bug described in patches 527371/672491
        self.assertEqual(re.match(r'(a)?a','a').lastindex, None)
        self.assertEqual(re.match(r'(a)(b)?b','ab').lastindex, 1)
        self.assertEqual(re.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup, 'a')
        self.assertEqual(re.match("(?P<a>a(b))", "ab").lastgroup, 'a')
        self.assertEqual(re.match("((a))", "a").lastindex, 1)

    def test_bug_545855(self):
        # bug 545855 -- This pattern failed to cause a compile error as it
        # should, instead provoking a TypeError.
        self.assertRaises(re.error, re.compile, 'foo[a-')

    def test_bug_418626(self):
        # bugs 418626 at al. -- Testing Greg Chapman's addition of op code
        # SRE_OP_MIN_REPEAT_ONE for eliminating recursion on simple uses of
        # pattern '*?' on a long string.
        self.assertEqual(re.match('.*?c', 10000*'ab'+'cd').end(0), 20001)
        self.assertEqual(re.match('.*?cd', 5000*'ab'+'c'+5000*'ab'+'cde').end(0),
                         20003)
        self.assertEqual(re.match('.*?cd', 20000*'abc'+'de').end(0), 60001)
        # non-simple '*?' still used to hit the recursion limit, before the
        # non-recursive scheme was implemented.
        self.assertEqual(re.search('(a|b)*?c', 10000*'ab'+'cd').end(0), 20001)

    def test_bug_612074(self):
        pat="["+re.escape("\u2039")+"]"
        self.assertEqual(re.compile(pat) and 1, 1)

    def test_stack_overflow(self):
        # nasty cases that used to overflow the straightforward recursive
        # implementation of repeated groups.
        self.assertEqual(re.match('(x)*', 50000*'x').group(1), 'x')
        self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x')
        self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x')

    def test_scanner(self):
        def s_ident(scanner, token): return token
        def s_operator(scanner, token): return "op%s" % token
        def s_float(scanner, token): return float(token)
        def s_int(scanner, token): return int(token)

        scanner = Scanner([
            (r"[a-zA-Z_]\w*", s_ident),
            (r"\d+\.\d*", s_float),
            (r"\d+", s_int),
            (r"=|\+|-|\*|/", s_operator),
            (r"\s+", None),
            ])

        self.assertNotEqual(scanner.scanner.scanner("").pattern, None)

        self.assertEqual(scanner.scan("sum = 3*foo + 312.50 + bar"),
                         (['sum', 'op=', 3, 'op*', 'foo', 'op+', 312.5,
                           'op+', 'bar'], ''))

    def test_bug_448951(self):
        # bug 448951 (similar to 429357, but with single char match)
        # (Also test greedy matches.)
        for op in '','?','*':
            self.assertEqual(re.match(r'((.%s):)?z'%op, 'z').groups(),
                             (None, None))
            self.assertEqual(re.match(r'((.%s):)?z'%op, 'a:z').groups(),
                             ('a:', 'a'))

    def test_bug_725106(self):
        # capturing groups in alternatives in repeats
        self.assertEqual(re.match('^((a)|b)*', 'abc').groups(),
                         ('b', 'a'))
        self.assertEqual(re.match('^(([ab])|c)*', 'abc').groups(),
                         ('c', 'b'))
        self.assertEqual(re.match('^((d)|[ab])*', 'abc').groups(),
                         ('b', None))
        self.assertEqual(re.match('^((a)c|[ab])*', 'abc').groups(),
                         ('b', None))
        self.assertEqual(re.match('^((a)|b)*?c', 'abc').groups(),
                         ('b', 'a'))
        self.assertEqual(re.match('^(([ab])|c)*?d', 'abcd').groups(),
                         ('c', 'b'))
        self.assertEqual(re.match('^((d)|[ab])*?c', 'abc').groups(),
                         ('b', None))
        self.assertEqual(re.match('^((a)c|[ab])*?c', 'abc').groups(),
                         ('b', None))

    def test_bug_725149(self):
        # mark_stack_base restoring before restoring marks
        self.assertEqual(re.match('(a)(?:(?=(b)*)c)*', 'abb').groups(),
                         ('a', None))
        self.assertEqual(re.match('(a)((?!(b)*))*', 'abb').groups(),
                         ('a', None, None))

    def test_bug_764548(self):
        # bug 764548, re.compile() barfs on str/unicode subclasses
        class my_unicode(str): pass
        pat = re.compile(my_unicode("abc"))
        self.assertEqual(pat.match("xyz"), None)

    def test_finditer(self):
        iter = re.finditer(r":+", "a:b::c:::d")
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", 1, 10)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", pos=1, endpos=10)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", endpos=10, pos=1)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", pos=3, endpos=8)
        self.assertEqual([item.group(0) for item in iter],
                         ["::", "::"])

    def test_bug_926075(self):
        self.assertTrue(re.compile('bug_926075') is not
                     re.compile(b'bug_926075'))

    def test_bug_931848(self):
        pattern = eval('"[\u002E\u3002\uFF0E\uFF61]"')
        self.assertEqual(re.compile(pattern).split("a.b.c"),
                         ['a','b','c'])

    def test_bug_581080(self):
        iter = re.finditer(r"\s", "a b")
        self.assertEqual(next(iter).span(), (1,2))
        self.assertRaises(StopIteration, next, iter)

        scanner = re.compile(r"\s").scanner("a b")
        self.assertEqual(scanner.search().span(), (1, 2))
        self.assertEqual(scanner.search(), None)

    def test_bug_817234(self):
        iter = re.finditer(r".*", "asdf")
        self.assertEqual(next(iter).span(), (0, 4))
        self.assertEqual(next(iter).span(), (4, 4))
        self.assertRaises(StopIteration, next, iter)

    def test_bug_6561(self):
        # '\d' should match characters in Unicode category 'Nd'
        # (Number, Decimal Digit), but not those in 'Nl' (Number,
        # Letter) or 'No' (Number, Other).
        decimal_digits = [
            '\u0037', # '\N{DIGIT SEVEN}', category 'Nd'
            '\u0e58', # '\N{THAI DIGIT SIX}', category 'Nd'
            '\uff10', # '\N{FULLWIDTH DIGIT ZERO}', category 'Nd'
            ]
        for x in decimal_digits:
            self.assertEqual(re.match('^\d$', x).group(0), x)

        not_decimal_digits = [
            '\u2165', # '\N{ROMAN NUMERAL SIX}', category 'Nl'
            '\u3039', # '\N{HANGZHOU NUMERAL TWENTY}', category 'Nl'
            '\u2082', # '\N{SUBSCRIPT TWO}', category 'No'
            '\u32b4', # '\N{CIRCLED NUMBER THIRTY NINE}', category 'No'
            ]
        for x in not_decimal_digits:
            self.assertIsNone(re.match('^\d$', x))

    def test_empty_array(self):
        # SF buf 1647541
        import array
        for typecode in 'bBuhHiIlLfd':
            a = array.array(typecode)
            self.assertEqual(re.compile(b"bla").match(a), None)
            self.assertEqual(re.compile(b"").match(a).groups(), ())

    def test_inline_flags(self):
        # Bug #1700
        upper_char = chr(0x1ea0) # Latin Capital Letter A with Dot Bellow
        lower_char = chr(0x1ea1) # Latin Small Letter A with Dot Bellow

        p = re.compile(upper_char, re.I | re.U)
        q = p.match(lower_char)
        self.assertNotEqual(q, None)

        p = re.compile(lower_char, re.I | re.U)
        q = p.match(upper_char)
        self.assertNotEqual(q, None)

        p = re.compile('(?i)' + upper_char, re.U)
        q = p.match(lower_char)
        self.assertNotEqual(q, None)

        p = re.compile('(?i)' + lower_char, re.U)
        q = p.match(upper_char)
        self.assertNotEqual(q, None)

        p = re.compile('(?iu)' + upper_char)
        q = p.match(lower_char)
        self.assertNotEqual(q, None)

        p = re.compile('(?iu)' + lower_char)
        q = p.match(upper_char)
        self.assertNotEqual(q, None)

    def test_dollar_matches_twice(self):
        "$ matches the end of string, and just before the terminating \n"
        pattern = re.compile('$')
        self.assertEqual(pattern.sub('#', 'a\nb\n'), 'a\nb#\n#')
        self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a\nb\nc#')
        self.assertEqual(pattern.sub('#', '\n'), '#\n#')

        pattern = re.compile('$', re.MULTILINE)
        self.assertEqual(pattern.sub('#', 'a\nb\n' ), 'a#\nb#\n#' )
        self.assertEqual(pattern.sub('#', 'a\nb\nc'), 'a#\nb#\nc#')
        self.assertEqual(pattern.sub('#', '\n'), '#\n#')

    def test_bytes_str_mixing(self):
        # Mixing str and bytes is disallowed
        pat = re.compile('.')
        bpat = re.compile(b'.')
        self.assertRaises(TypeError, pat.match, b'b')
        self.assertRaises(TypeError, bpat.match, 'b')
        self.assertRaises(TypeError, pat.sub, b'b', 'c')
        self.assertRaises(TypeError, pat.sub, 'b', b'c')
        self.assertRaises(TypeError, pat.sub, b'b', b'c')
        self.assertRaises(TypeError, bpat.sub, b'b', 'c')
        self.assertRaises(TypeError, bpat.sub, 'b', b'c')
        self.assertRaises(TypeError, bpat.sub, 'b', 'c')

    def test_ascii_and_unicode_flag(self):
        # String patterns
        for flags in (0, re.UNICODE):
            pat = re.compile('\xc0', flags | re.IGNORECASE)
            self.assertNotEqual(pat.match('\xe0'), None)
            pat = re.compile('\w', flags)
            self.assertNotEqual(pat.match('\xe0'), None)
        pat = re.compile('\xc0', re.ASCII | re.IGNORECASE)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('(?a)\xc0', re.IGNORECASE)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('\w', re.ASCII)
        self.assertEqual(pat.match('\xe0'), None)
        pat = re.compile('(?a)\w')
        self.assertEqual(pat.match('\xe0'), None)
        # Bytes patterns
        for flags in (0, re.ASCII):
            pat = re.compile(b'\xc0', re.IGNORECASE)
            self.assertEqual(pat.match(b'\xe0'), None)
            pat = re.compile(b'\w')
            self.assertEqual(pat.match(b'\xe0'), None)
        # Incompatibilities
        self.assertRaises(ValueError, re.compile, b'\w', re.UNICODE)
        self.assertRaises(ValueError, re.compile, b'(?u)\w')
        self.assertRaises(ValueError, re.compile, '\w', re.UNICODE | re.ASCII)
        self.assertRaises(ValueError, re.compile, '(?u)\w', re.ASCII)
        self.assertRaises(ValueError, re.compile, '(?a)\w', re.UNICODE)
        self.assertRaises(ValueError, re.compile, '(?au)\w')

    def test_bug_6509(self):
        # Replacement strings of both types must parse properly.
        # all strings
        pat = re.compile('a(\w)')
        self.assertEqual(pat.sub('b\\1', 'ac'), 'bc')
        pat = re.compile('a(.)')
        self.assertEqual(pat.sub('b\\1', 'a\u1234'), 'b\u1234')
        pat = re.compile('..')
        self.assertEqual(pat.sub(lambda m: 'str', 'a5'), 'str')

        # all bytes
        pat = re.compile(b'a(\w)')
        self.assertEqual(pat.sub(b'b\\1', b'ac'), b'bc')
        pat = re.compile(b'a(.)')
        self.assertEqual(pat.sub(b'b\\1', b'a\xCD'), b'b\xCD')
        pat = re.compile(b'..')
        self.assertEqual(pat.sub(lambda m: b'bytes', b'a5'), b'bytes')

    def test_dealloc(self):
        # issue 3299: check for segfault in debug build
        import _sre
        # the overflow limit is different on wide and narrow builds and it
        # depends on the definition of SRE_CODE (see sre.h).
        # 2**128 should be big enough to overflow on both. For smaller values
        # a RuntimeError is raised instead of OverflowError.
        long_overflow = 2**128
        self.assertRaises(TypeError, re.finditer, "a", {})
        self.assertRaises(OverflowError, _sre.compile, "abc", 0, [long_overflow])
        self.assertRaises(TypeError, _sre.compile, {}, 0, [])

    def test_search_dot_unicode(self):
        self.assertIsNotNone(re.search("123.*-", '123abc-'))
        self.assertIsNotNone(re.search("123.*-", '123\xe9-'))
        self.assertIsNotNone(re.search("123.*-", '123\u20ac-'))
        self.assertIsNotNone(re.search("123.*-", '123\U0010ffff-'))
        self.assertIsNotNone(re.search("123.*-", '123\xe9\u20ac\U0010ffff-'))

    def test_compile(self):
        # Test return value when given string and pattern as parameter
        pattern = re.compile('random pattern')
        self.assertIsInstance(pattern, re._pattern_type)
        same_pattern = re.compile(pattern)
        self.assertIsInstance(same_pattern, re._pattern_type)
        self.assertIs(same_pattern, pattern)
        # Test behaviour when not given a string or pattern as parameter
        self.assertRaises(TypeError, re.compile, 0)

def run_re_tests():
    from test.re_tests import tests, SUCCEED, FAIL, SYNTAX_ERROR
    if verbose:
        print('Running re_tests test suite')
    else:
        # To save time, only run the first and last 10 tests
        #tests = tests[:10] + tests[-10:]
        pass

    for t in tests:
        sys.stdout.flush()
        pattern = s = outcome = repl = expected = None
        if len(t) == 5:
            pattern, s, outcome, repl, expected = t
        elif len(t) == 3:
            pattern, s, outcome = t
        else:
            raise ValueError('Test tuples should have 3 or 5 fields', t)

        try:
            obj = re.compile(pattern)
        except re.error:
            if outcome == SYNTAX_ERROR: pass  # Expected a syntax error
            else:
                print('=== Syntax error:', t)
        except KeyboardInterrupt: raise KeyboardInterrupt
        except:
            print('*** Unexpected error ***', t)
            if verbose:
                traceback.print_exc(file=sys.stdout)
        else:
            try:
                result = obj.search(s)
            except re.error as msg:
                print('=== Unexpected exception', t, repr(msg))
            if outcome == SYNTAX_ERROR:
                # This should have been a syntax error; forget it.
                pass
            elif outcome == FAIL:
                if result is None: pass   # No match, as expected
                else: print('=== Succeeded incorrectly', t)
            elif outcome == SUCCEED:
                if result is not None:
                    # Matched, as expected, so now we compute the
                    # result string and compare it to our expected result.
                    start, end = result.span(0)
                    vardict={'found': result.group(0),
                             'groups': result.group(),
                             'flags': result.re.flags}
                    for i in range(1, 100):
                        try:
                            gi = result.group(i)
                            # Special hack because else the string concat fails:
                            if gi is None:
                                gi = "None"
                        except IndexError:
                            gi = "Error"
                        vardict['g%d' % i] = gi
                    for i in result.re.groupindex.keys():
                        try:
                            gi = result.group(i)
                            if gi is None:
                                gi = "None"
                        except IndexError:
                            gi = "Error"
                        vardict[i] = gi
                    repl = eval(repl, vardict)
                    if repl != expected:
                        print('=== grouping error', t, end=' ')
                        print(repr(repl) + ' should be ' + repr(expected))
                else:
                    print('=== Failed incorrectly', t)

                # Try the match with both pattern and string converted to
                # bytes, and check that it still succeeds.
                try:
                    bpat = bytes(pattern, "ascii")
                    bs = bytes(s, "ascii")
                except UnicodeEncodeError:
                    # skip non-ascii tests
                    pass
                else:
                    try:
                        bpat = re.compile(bpat)
                    except Exception:
                        print('=== Fails on bytes pattern compile', t)
                        if verbose:
                            traceback.print_exc(file=sys.stdout)
                    else:
                        bytes_result = bpat.search(bs)
                        if bytes_result is None:
                            print('=== Fails on bytes pattern match', t)

                # Try the match with the search area limited to the extent
                # of the match and see if it still succeeds.  \B will
                # break (because it won't match at the end or start of a
                # string), so we'll ignore patterns that feature it.

                if pattern[:2] != '\\B' and pattern[-2:] != '\\B' \
                               and result is not None:
                    obj = re.compile(pattern)
                    result = obj.search(s, result.start(0), result.end(0) + 1)
                    if result is None:
                        print('=== Failed on range-limited match', t)

                # Try the match with IGNORECASE enabled, and check that it
                # still succeeds.
                obj = re.compile(pattern, re.IGNORECASE)
                result = obj.search(s)
                if result is None:
                    print('=== Fails on case-insensitive match', t)

                # Try the match with LOCALE enabled, and check that it
                # still succeeds.
                if '(?u)' not in pattern:
                    obj = re.compile(pattern, re.LOCALE)
                    result = obj.search(s)
                    if result is None:
                        print('=== Fails on locale-sensitive match', t)

                # Try the match with UNICODE locale enabled, and check
                # that it still succeeds.
                obj = re.compile(pattern, re.UNICODE)
                result = obj.search(s)
                if result is None:
                    print('=== Fails on unicode-sensitive match', t)


def test_main():
    run_unittest(ReTests)
    run_re_tests()

if __name__ == "__main__":
    test_main()