summaryrefslogtreecommitdiffstats
path: root/tests/string.test
blob: 64427e47b96b5dfacce5ac9b151c0c82aa1f5158 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
# Commands covered:  string
#
# This file contains a collection of tests for one or more of the Tcl
# built-in commands.  Sourcing this file into Tcl runs the tests and
# generates output for errors.  No output means no errors were found.
#
# Copyright (c) 1991-1993 The Regents of the University of California.
# Copyright (c) 1994 Sun Microsystems, Inc.
# Copyright (c) 1998-1999 by Scriptics Corporation.
# Copyright (c) 2001 by Kevin B. Kenny.  All rights reserved.
#
# See the file "license.terms" for information on usage and redistribution
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
#
# RCS: @(#) $Id: string.test,v 1.71.2.1 2009/01/06 15:12:42 dkf Exp $

if {[lsearch [namespace children] ::tcltest] == -1} {
    package require tcltest
    namespace import -force ::tcltest::*
}

# Some tests require the testobj command

testConstraint testobj [expr {[info commands testobj] != {}}]
testConstraint testindexobj [expr {[info commands testindexobj] != {}}]

test string-1.1 {error conditions} {
    list [catch {string gorp a b} msg] $msg
} {1 {unknown or ambiguous subcommand "gorp": must be bytelength, compare, equal, first, index, is, last, length, map, match, range, repeat, replace, reverse, tolower, totitle, toupper, trim, trimleft, trimright, wordend, or wordstart}}
test string-1.2 {error conditions} {
    list [catch {string} msg] $msg
} {1 {wrong # args: should be "string subcommand ?argument ...?"}}

test string-2.1 {string compare, too few args} {
    list [catch {string compare a} msg] $msg
} {1 {wrong # args: should be "string compare ?-nocase? ?-length int? string1 string2"}}
test string-2.2 {string compare, bad args} {
    list [catch {string compare a b c} msg] $msg
} {1 {bad option "a": must be -nocase or -length}}
test string-2.3 {string compare, bad args} {
    list [catch {string compare -length -nocase str1 str2} msg] $msg
} {1 {expected integer but got "-nocase"}}
test string-2.4 {string compare, too many args} {
    list [catch {string compare -length 10 -nocase str1 str2 str3} msg] $msg
} {1 {wrong # args: should be "string compare ?-nocase? ?-length int? string1 string2"}}
test string-2.5 {string compare with length unspecified} {
    list [catch {string compare -length 10 10} msg] $msg
} {1 {wrong # args: should be "string compare ?-nocase? ?-length int? string1 string2"}}
test string-2.6 {string compare} {
    string compare abcde abdef
} -1
test string-2.7 {string compare, shortest method name} {
    string c abcde ABCDE
} 1
test string-2.8 {string compare} {
    string compare abcde abcde
} 0
test string-2.9 {string compare with length} {
    string compare -length 2 abcde abxyz
} 0
test string-2.10 {string compare with special index} {
    list [catch {string compare -length end-3 abcde abxyz} msg] $msg
} {1 {expected integer but got "end-3"}}
test string-2.11 {string compare, unicode} {
    string compare ab\u7266 ab\u7267
} -1
test string-2.12 {string compare, high bit} {
    # This test will fail if the underlying comparaison
    # is using signed chars instead of unsigned chars.
    # (like SunOS's default memcmp thus the compat/memcmp.c)
    string compare "\x80" "@"
    # Nb this tests works also in utf8 space because \x80 is
    # translated into a 2 or more bytelength but whose first byte has
    # the high bit set.
} 1
test string-2.13 {string compare -nocase} {
    string compare -nocase abcde abdef
} -1
test string-2.14 {string compare -nocase} {
    string c -nocase abcde ABCDE
} 0
test string-2.15 {string compare -nocase} {
    string compare -nocase abcde abcde
} 0
test string-2.16 {string compare -nocase with length} {
    string compare -length 2 -nocase abcde Abxyz
} 0
test string-2.17 {string compare -nocase with length} {
    string compare -nocase -length 3 abcde Abxyz
} -1
test string-2.18 {string compare -nocase with length <= 0} {
    string compare -nocase -length -1 abcde AbCdEf
} -1
test string-2.19 {string compare -nocase with excessive length} {
    string compare -nocase -length 50 AbCdEf abcde
} 1
test string-2.20 {string compare -len unicode} {
    # These are strings that are 6 BYTELENGTH long, but the length
    # shouldn't make a different because there are actually 3 CHARS long
    string compare -len 5 \334\334\334 \334\334\374
} -1
test string-2.21 {string compare -nocase with special index} {
    list [catch {string compare -nocase -length end-3 Abcde abxyz} msg] $msg
} {1 {expected integer but got "end-3"}}
test string-2.22 {string compare, null strings} {
    string compare "" ""
} 0
test string-2.23 {string compare, null strings} {
    string compare "" foo
} -1
test string-2.24 {string compare, null strings} {
    string compare foo ""
} 1
test string-2.25 {string compare -nocase, null strings} {
    string compare -nocase "" ""
} 0
test string-2.26 {string compare -nocase, null strings} {
    string compare -nocase "" foo
} -1
test string-2.27 {string compare -nocase, null strings} {
    string compare -nocase foo ""
} 1
test string-2.28 {string compare with length, unequal strings} {
    string compare -length 2 abc abde
} 0
test string-2.29 {string compare with length, unequal strings} {
    string compare -length 2 ab abde
} 0
test string-2.30 {string compare with NUL character vs. other ASCII} {
    # Be careful here, since UTF-8 rep comparison with memcmp() of
    # these puts chars in the wrong order
    string compare \x00 \x01
} -1
test string-2.31 {string compare, high bit} {
    proc foo {} {string compare "a\x80" "a@"}
    foo
} 1
test string-2.32 {string compare, high bit} {
    proc foo {} {string compare "a\x00" "a\x01"}
    foo
} -1
test string-2.33 {string compare, high bit} {
    proc foo {} {string compare "\x00\x00" "\x00\x01"}
    foo
} -1

# only need a few tests on equal, since it uses the same code as
# string compare, but just modifies the return output
test string-3.1 {string equal} {
    string equal abcde abdef
} 0
test string-3.2 {string equal} {
    string eq abcde ABCDE
} 0
test string-3.3 {string equal} {
    string equal abcde abcde
} 1
test string-3.4 {string equal -nocase} {
    string equal -nocase \334\334\334\334\374\374\374\374 \334\334\334\334\334\334\334\334
} 1
test string-3.5 {string equal -nocase} {
    string equal -nocase abcde abdef
} 0
test string-3.6 {string equal -nocase} {
    string eq -nocase abcde ABCDE
} 1
test string-3.7 {string equal -nocase} {
    string equal -nocase abcde abcde
} 1
test string-3.8 {string equal with length, unequal strings} {
    string equal -length 2 abc abde
} 1

test string-4.1 {string first, too few args} {
    list [catch {string first a} msg] $msg
} {1 {wrong # args: should be "string first needleString haystackString ?startIndex?"}}
test string-4.2 {string first, bad args} {
    list [catch {string first a b c} msg] $msg
} {1 {bad index "c": must be integer?[+-]integer? or end?[+-]integer?}}
test string-4.3 {string first, too many args} {
    list [catch {string first a b 5 d} msg] $msg
} {1 {wrong # args: should be "string first needleString haystackString ?startIndex?"}}
test string-4.4 {string first} {
    string first bq abcdefgbcefgbqrs
} 12
test string-4.5 {string first} {
    string fir bcd abcdefgbcefgbqrs
} 1
test string-4.6 {string first} {
    string f b abcdefgbcefgbqrs
} 1
test string-4.7 {string first} {
    string first xxx x123xx345xxx789xxx012
} 9
test string-4.8 {string first} {
    string first "" x123xx345xxx789xxx012
} -1
test string-4.9 {string first, unicode} {
    string first x abc\u7266x
} 4
test string-4.10 {string first, unicode} {
    string first \u7266 abc\u7266x
} 3
test string-4.11 {string first, start index} {
    string first \u7266 abc\u7266x 3
} 3
test string-4.12 {string first, start index} {
    string first \u7266 abc\u7266x 4
} -1
test string-4.13 {string first, start index} {
    string first \u7266 abc\u7266x end-2
} 3
test string-4.14 {string first, negative start index} {
    string first b abc -1
} 1
test string-4.15 {string first, ability to two-byte encoded utf-8 chars} {
    # Test for a bug in Tcl 8.3 where test for all-single-byte-encoded
    # strings was incorrect, leading to an index returned by [string first] 
    # which pointed past the end of the string.
    set uchar \u057e    ;# character with two-byte encoding in utf-8
    string first % %#$uchar$uchar#$uchar$uchar#% 3
} 8

test string-5.1 {string index} {
    list [catch {string index} msg] $msg
} {1 {wrong # args: should be "string index string charIndex"}}
test string-5.2 {string index} {
    list [catch {string index a b c} msg] $msg
} {1 {wrong # args: should be "string index string charIndex"}}
test string-5.3 {string index} {
    string index abcde 0
} a
test string-5.4 {string index} {
    string in abcde 4
} e
test string-5.5 {string index} {
    string index abcde 5
} {}
test string-5.6 {string index} {
    list [catch {string index abcde -10} msg] $msg
} {0 {}}
test string-5.7 {string index} {
    list [catch {string index a xyz} msg] $msg
} {1 {bad index "xyz": must be integer?[+-]integer? or end?[+-]integer?}}
test string-5.8 {string index} {
    string index abc end
} c
test string-5.9 {string index} {
    string index abc end-1
} b
test string-5.10 {string index, unicode} {
    string index abc\u7266d 4
} d
test string-5.11 {string index, unicode} {
    string index abc\u7266d 3
} \u7266
test string-5.12 {string index, unicode over char length, under byte length} {
    string index \334\374\334\374 6
} {}
test string-5.13 {string index, bytearray object} {
    string index [binary format a5 fuz] 0
} f
test string-5.14 {string index, bytearray object} {
    string index [binary format I* {0x50515253 0x52}] 3
} S
test string-5.15 {string index, bytearray object} {
    set b [binary format I* {0x50515253 0x52}]
    set i1 [string index $b end-6]
    set i2 [string index $b 1]
    string compare $i1 $i2
} 0
test string-5.16 {string index, bytearray object with string obj shimmering} {
    set str "0123456789\x00 abcdedfghi"
    binary scan $str H* dump
    string compare [string index $str 10] \x00
} 0
test string-5.17 {string index, bad integer} -body {
    list [catch {string index "abc" 0o8} msg] $msg
} -match glob -result {1 {*invalid octal number*}}
test string-5.18 {string index, bad integer} -body {
    list [catch {string index "abc" end-0o0289} msg] $msg
} -match glob -result {1 {*invalid octal number*}}
test string-5.19 {string index, bytearray object out of bounds} {
    string index [binary format I* {0x50515253 0x52}] -1
} {}
test string-5.20 {string index, bytearray object out of bounds} {
    string index [binary format I* {0x50515253 0x52}] 20
} {}


proc largest_int {} {
    # This will give us what the largest valid int on this machine is,
    # so we can test for overflow properly below on >32 bit systems
    set int 1
    set exp 7; # assume we get at least 8 bits
    while {wide($int) > 0} { set int [expr {wide(1) << [incr exp]}] }
    return [expr {$int-1}]
}

test string-6.1 {string is, too few args} {
    list [catch {string is} msg] $msg
} {1 {wrong # args: should be "string is class ?-strict? ?-failindex var? str"}}
test string-6.2 {string is, too few args} {
    list [catch {string is alpha} msg] $msg
} {1 {wrong # args: should be "string is class ?-strict? ?-failindex var? str"}}
test string-6.3 {string is, bad args} {
    list [catch {string is alpha -failin str} msg] $msg
} {1 {wrong # args: should be "string is alpha ?-strict? ?-failindex var? str"}}
test string-6.4 {string is, too many args} {
    list [catch {string is alpha -failin var -strict str more} msg] $msg
} {1 {wrong # args: should be "string is class ?-strict? ?-failindex var? str"}}
test string-6.5 {string is, class check} {
    list [catch {string is bogus str} msg] $msg
} {1 {bad class "bogus": must be alnum, alpha, ascii, control, boolean, digit, double, false, graph, integer, list, lower, print, punct, space, true, upper, wideinteger, wordchar, or xdigit}}
test string-6.6 {string is, ambiguous class} {
    list [catch {string is al str} msg] $msg
} {1 {ambiguous class "al": must be alnum, alpha, ascii, control, boolean, digit, double, false, graph, integer, list, lower, print, punct, space, true, upper, wideinteger, wordchar, or xdigit}}
test string-6.7 {string is alpha, all ok} {
    string is alpha -strict -failindex var abc
} 1
test string-6.8 {string is, error in var} {
    list [string is alpha -failindex var abc5def] $var
} {0 3}
test string-6.9 {string is, var shouldn't get set} {
    catch {unset var}
    list [catch {string is alpha -failindex var abc; set var} msg] $msg
} {1 {can't read "var": no such variable}}
test string-6.10 {string is, ok on empty} {
    string is alpha {}
} 1
test string-6.11 {string is, -strict check against empty} {
    string is alpha -strict {}
} 0
test string-6.12 {string is alnum, true} {
    string is alnum abc123
} 1
test string-6.13 {string is alnum, false} {
    list [string is alnum -failindex var abc1.23] $var
} {0 4}
test string-6.14 {string is alnum, unicode} {
    string is alnum abc\u00fc
} 1
test string-6.15 {string is alpha, true} {
    string is alpha abc
} 1
test string-6.16 {string is alpha, false} {
    list [string is alpha -fail var a1bcde] $var
} {0 1}
test string-6.17 {string is alpha, unicode} {
    string is alpha abc\374
} 1
test string-6.18 {string is ascii, true} {
    string is ascii abc\u007Fend\u0000
} 1
test string-6.19 {string is ascii, false} {
    list [string is ascii -fail var abc\u0000def\u0080more] $var
} {0 7}
test string-6.20 {string is boolean, true} {
    string is boolean true
} 1
test string-6.21 {string is boolean, true} {
    string is boolean f
} 1
test string-6.22 {string is boolean, true based on type} {
    string is bool [string compare a a]
} 1
test string-6.23 {string is boolean, false} {
    list [string is bool -fail var yada] $var
} {0 0}
test string-6.24 {string is digit, true} {
    string is digit 0123456789
} 1
test string-6.25 {string is digit, false} {
    list [string is digit -fail var 0123\u00dc567] $var
} {0 4}
test string-6.26 {string is digit, false} {
    list [string is digit -fail var +123567] $var
} {0 0}
test string-6.27 {string is double, true} {
    string is double 1
} 1
test string-6.28 {string is double, true} {
    string is double [expr double(1)]
} 1
test string-6.29 {string is double, true} {
    string is double 1.0
} 1
test string-6.30 {string is double, true} {
    string is double [string compare a a]
} 1
test string-6.31 {string is double, true} {
    string is double "   +1.0e-1  "
} 1
test string-6.32 {string is double, true} {
    string is double "\n1.0\v"
} 1
test string-6.33 {string is double, false} {
    list [string is double -fail var 1abc] $var
} {0 1}
test string-6.34 {string is double, false} {
    list [string is double -fail var abc] $var
} {0 0}
test string-6.35 {string is double, false} {
    list [string is double -fail var "   1.0e4e4  "] $var
} {0 8}
test string-6.36 {string is double, false} {
    list [string is double -fail var "\n"] $var
} {0 0}
test string-6.37 {string is double, false on int overflow} {
    # Make it the largest int recognizable, with one more digit for overflow
    # Since bignums arrived in Tcl 8.5, the sense of this test changed.
    # Now integer values that exceed native limits become bignums, and
    # bignums can convert to doubles without error.
    list [string is double -fail var [largest_int]0] $var
} {1 0}
# string-6.38 removed, underflow on input is no longer an error.
test string-6.39 {string is double, false} {
    # This test is non-portable because IRIX thinks 
    # that .e1 is a valid double - this is really a bug
    # on IRIX as .e1 should NOT be a valid double
    #
    # Portable now. Tcl 8.5 does its own double parsing.

    list [string is double -fail var .e1] $var
} {0 0}
test string-6.40 {string is false, true} {
    string is false false
} 1
test string-6.41 {string is false, true} {
    string is false FaLsE
} 1
test string-6.42 {string is false, true} {
    string is false N
} 1
test string-6.43 {string is false, true} {
    string is false 0
} 1
test string-6.44 {string is false, true} {
    string is false off
} 1
test string-6.45 {string is false, false} {
    list [string is false -fail var abc] $var
} {0 0}
test string-6.46 {string is false, false} {
    catch {unset var}
    list [string is false -fail var Y] $var
} {0 0}
test string-6.47 {string is false, false} {
    catch {unset var}
    list [string is false -fail var offensive] $var
} {0 0}
test string-6.48 {string is integer, true} {
    string is integer +1234567890
} 1
test string-6.49 {string is integer, true on type} {
    string is integer [expr int(50.0)]
} 1
test string-6.50 {string is integer, true} {
    string is integer [list -10]
} 1
test string-6.51 {string is integer, true as hex} {
    string is integer 0xabcdef
} 1
test string-6.52 {string is integer, true as octal} {
    string is integer 012345
} 1
test string-6.53 {string is integer, true with whitespace} {
    string is integer "  \n1234\v"
} 1
test string-6.54 {string is integer, false} {
    list [string is integer -fail var 123abc] $var
} {0 3}
test string-6.55 {string is integer, false on overflow} {
    list [string is integer -fail var +[largest_int]0] $var
} {0 -1}
test string-6.56 {string is integer, false} {
    list [string is integer -fail var [expr double(1)]] $var
} {0 1}
test string-6.57 {string is integer, false} {
    list [string is integer -fail var "    "] $var
} {0 0}
test string-6.58 {string is integer, false on bad octal} {
    list [string is integer -fail var 0o36963] $var
} {0 4}
test string-6.58.1 {string is integer, false on bad octal} {
    list [string is integer -fail var 0o36963] $var
} {0 4}
test string-6.59 {string is integer, false on bad hex} {
    list [string is integer -fail var 0X345XYZ] $var
} {0 5}
test string-6.60 {string is lower, true} {
    string is lower abc
} 1
test string-6.61 {string is lower, unicode true} {
    string is lower abc\u00fcue
} 1
test string-6.62 {string is lower, false} {
    list [string is lower -fail var aBc] $var
} {0 1}
test string-6.63 {string is lower, false} {
    list [string is lower -fail var abc1] $var
} {0 3}
test string-6.64 {string is lower, unicode false} {
    list [string is lower -fail var ab\u00dcUE] $var
} {0 2}
test string-6.65 {string is space, true} {
    string is space " \t\n\v\f"
} 1
test string-6.66 {string is space, false} {
    list [string is space -fail var " \t\n\v1\f"] $var
} {0 4}
test string-6.67 {string is true, true} {
    string is true true
} 1
test string-6.68 {string is true, true} {
    string is true TrU
} 1
test string-6.69 {string is true, true} {
    string is true ye
} 1
test string-6.70 {string is true, true} {
    string is true 1
} 1
test string-6.71 {string is true, true} {
    string is true on
} 1
test string-6.72 {string is true, false} {
    list [string is true -fail var onto] $var
} {0 0}
test string-6.73 {string is true, false} {
    catch {unset var}
    list [string is true -fail var 25] $var
} {0 0}
test string-6.74 {string is true, false} {
    catch {unset var}
    list [string is true -fail var no] $var
} {0 0}
test string-6.75 {string is upper, true} {
    string is upper ABC
} 1
test string-6.76 {string is upper, unicode true} {
    string is upper ABC\u00dcUE
} 1
test string-6.77 {string is upper, false} {
    list [string is upper -fail var AbC] $var
} {0 1}
test string-6.78 {string is upper, false} {
    list [string is upper -fail var AB2C] $var
} {0 2}
test string-6.79 {string is upper, unicode false} {
    list [string is upper -fail var ABC\u00fcue] $var
} {0 3}
test string-6.80 {string is wordchar, true} {
    string is wordchar abc_123
} 1
test string-6.81 {string is wordchar, unicode true} {
    string is wordchar abc\u00fcab\u00dcAB\u5001
} 1
test string-6.82 {string is wordchar, false} {
    list [string is wordchar -fail var abcd.ef] $var
} {0 4}
test string-6.83 {string is wordchar, unicode false} {
    list [string is wordchar -fail var abc\u0080def] $var
} {0 3}
test string-6.84 {string is control} {
    ## Control chars are in the ranges
    ## 00..1F && 7F..9F
    list [string is control -fail var \x00\x01\x10\x1F\x7F\x80\x9F\x60] $var
} {0 7}
test string-6.85 {string is control} {
    string is control \u0100
} 0
test string-6.86 {string is graph} {
    ## graph is any print char, except space
    list [string is gra -fail var "0123abc!@#\$\u0100 "] $var
} {0 12}
test string-6.87 {string is print} {
    ## basically any printable char
    list [string is print -fail var "0123abc!@#\$\u0100 \u0010"] $var
} {0 13}
test string-6.88 {string is punct} {
    ## any graph char that isn't alnum
    list [string is punct -fail var "_!@#\u00beq0"] $var
} {0 4}
test string-6.89 {string is xdigit} {
    list [string is xdigit -fail var 0123456789\u0061bcdefABCDEFg] $var
} {0 22}

test string-6.90 {string is integer, bad integers} {
    # SF bug #634856
    set result ""
    set numbers [list 1 +1 ++1 +-1 -+1 -1 --1 "- +1"]
    foreach num $numbers {
	lappend result [string is int -strict $num]
    }
    set result
} {1 1 0 0 0 1 0 0}
test string-6.91 {string is double, bad doubles} {
    set result ""
    set numbers [list 1.0 +1.0 ++1.0 +-1.0 -+1.0 -1.0 --1.0 "- +1.0"]
    foreach num $numbers {
	lappend result [string is double -strict $num]
    }
    set result
} {1 1 0 0 0 1 0 0}
test string-6.92 {string is double, 32-bit overflow} {
    # Bug 718878
    set x 0x100000000
    list [string is integer -failindex var $x] $var
} {0 -1}
test string-6.93 {string is double, 32-bit overflow} {
    # Bug 718878
    set x 0x100000000
    append x ""
    list [string is integer -failindex var $x] $var
} {0 -1}
test string-6.94 {string is double, 32-bit overflow} {
    # Bug 718878
    set x 0x100000000
    list [string is integer -failindex var [expr {$x}]] $var
} {0 -1}
test string-6.95 {string is wideinteger, true} {
    string is wideinteger +1234567890
} 1
test string-6.96 {string is wideinteger, true on type} {
    string is wideinteger [expr wide(50.0)]
} 1
test string-6.97 {string is wideinteger, true} {
    string is wideinteger [list -10]
} 1
test string-6.98 {string is wideinteger, true as hex} {
    string is wideinteger 0xabcdef
} 1
test string-6.99 {string is wideinteger, true as octal} {
    string is wideinteger 0123456
} 1
test string-6.100 {string is wideinteger, true with whitespace} {
    string is wideinteger "  \n1234\v"
} 1
test string-6.101 {string is wideinteger, false} {
    list [string is wideinteger -fail var 123abc] $var
} {0 3}
test string-6.102 {string is wideinteger, false on overflow} {
    list [string is wideinteger -fail var +[largest_int]0] $var
} {0 -1}
test string-6.103 {string is wideinteger, false} {
    list [string is wideinteger -fail var [expr double(1)]] $var
} {0 1}
test string-6.104 {string is wideinteger, false} {
    list [string is wideinteger -fail var "    "] $var
} {0 0}
test string-6.105 {string is wideinteger, false on bad octal} {
    list [string is wideinteger -fail var 0o36963] $var
} {0 4}
test string-6.105.1 {string is wideinteger, false on bad octal} {
    list [string is wideinteger -fail var 0o36963] $var
} {0 4}
test string-6.106 {string is wideinteger, false on bad hex} {
    list [string is wideinteger -fail var 0X345XYZ] $var
} {0 5}
test string-6.107 {string is integer, bad integers} {
    # SF bug #634856
    set result ""
    set numbers [list 1 +1 ++1 +-1 -+1 -1 --1 "- +1"]
    foreach num $numbers {
	lappend result [string is wideinteger -strict $num]
    }
    set result
} {1 1 0 0 0 1 0 0}
test string-6.108 {string is double, Bug 1382287} {
    set x 2turtledoves
    string is double $x
    string is double $x
} 0
test string-6.109 {string is double, Bug 1360532} {
    string is double 1\u00a0
} 0

catch {rename largest_int {}}

test string-7.1 {string last, too few args} {
    list [catch {string last a} msg] $msg
} {1 {wrong # args: should be "string last needleString haystackString ?startIndex?"}}
test string-7.2 {string last, bad args} {
    list [catch {string last a b c} msg] $msg
} {1 {bad index "c": must be integer?[+-]integer? or end?[+-]integer?}}
test string-7.3 {string last, too many args} {
    list [catch {string last a b c d} msg] $msg
} {1 {wrong # args: should be "string last needleString haystackString ?startIndex?"}}
test string-7.4 {string last} {
    string la xxx xxxx123xx345x678
} 1
test string-7.5 {string last} {
    string last xx xxxx123xx345x678
} 7
test string-7.6 {string last} {
    string las x xxxx123xx345x678
} 12
test string-7.7 {string last, unicode} {
    string las x xxxx12\u7266xx345x678
} 12
test string-7.8 {string last, unicode} {
    string las \u7266 xxxx12\u7266xx345x678
} 6
test string-7.9 {string last, stop index} {
    string las \u7266 xxxx12\u7266xx345x678
} 6
test string-7.10 {string last, unicode} {
    string las \u7266 xxxx12\u7266xx345x678
} 6
test string-7.11 {string last, start index} {
    string last \u7266 abc\u7266x 3
} 3
test string-7.12 {string last, start index} {
    string last \u7266 abc\u7266x 2
} -1
test string-7.13 {string last, start index} {
    ## Constrain to last 'a' should work
    string last ba badbad end-1
} 3
test string-7.14 {string last, start index} {
    ## Constrain to last 'b' should skip last 'ba'
    string last ba badbad end-2
} 0
test string-7.15 {string last, start index} {
    string last \334a \334ad\334ad 0
} -1
test string-7.16 {string last, start index} {
    string last \334a \334ad\334ad end-1
} 3

test string-8.1 {string bytelength} {
    list [catch {string bytelength} msg] $msg
} {1 {wrong # args: should be "string bytelength string"}}
test string-8.2 {string bytelength} {
    list [catch {string bytelength a b} msg] $msg
} {1 {wrong # args: should be "string bytelength string"}}
test string-8.3 {string bytelength} {
    string bytelength "\u00c7"
} 2
test string-8.4 {string bytelength} {
    string b ""
} 0

test string-9.1 {string length} {
    list [catch {string length} msg] $msg
} {1 {wrong # args: should be "string length string"}}
test string-9.2 {string length} {
    list [catch {string length a b} msg] $msg
} {1 {wrong # args: should be "string length string"}}
test string-9.3 {string length} {
    string length "a little string"
} 15
test string-9.4 {string length} {
    string le ""
} 0
test string-9.5 {string length, unicode} {
    string le "abcd\u7266"
} 5
test string-9.6 {string length, bytearray object} {
    string length [binary format a5 foo]
} 5
test string-9.7 {string length, bytearray object} {
    string length [binary format I* {0x50515253 0x52}]
} 8

test string-10.1 {string map, too few args} {
    list [catch {string map} msg] $msg
} {1 {wrong # args: should be "string map ?-nocase? charMap string"}}
test string-10.2 {string map, bad args} {
    list [catch {string map {a b} abba oops} msg] $msg
} {1 {bad option "a b": must be -nocase}}
test string-10.3 {string map, too many args} {
    list [catch {string map -nocase {a b} str1 str2} msg] $msg
} {1 {wrong # args: should be "string map ?-nocase? charMap string"}}
test string-10.4 {string map} {
    string map {a b} abba
} {bbbb}
test string-10.5 {string map} {
    string map {a b} a
} {b}
test string-10.6 {string map -nocase} {
    string map -nocase {a b} Abba
} {bbbb}
test string-10.7 {string map} {
    string map {abc 321 ab * a A} aabcabaababcab
} {A321*A*321*}
test string-10.8 {string map -nocase} {
    string map -nocase {aBc 321 Ab * a A} aabcabaababcab
} {A321*A*321*}
test string-10.9 {string map -nocase} {
    string map -no {abc 321 Ab * a A} aAbCaBaAbAbcAb
} {A321*A*321*}
test string-10.10 {string map} {
    list [catch {string map {a b c} abba} msg] $msg
} {1 {char map list unbalanced}}
test string-10.11 {string map, nulls} {
    string map {\x00 NULL blah \x00nix} {qwerty}
} {qwerty}
test string-10.12 {string map, unicode} {
    string map [list \374 ue UE \334] "a\374ueUE\000EU"
} aueue\334\0EU
test string-10.13 {string map, -nocase unicode} {
    string map -nocase [list \374 ue UE \334] "a\374ueUE\000EU"
} aue\334\334\0EU
test string-10.14 {string map, -nocase null arguments} {
    string map -nocase {{} abc} foo
} foo
test string-10.15 {string map, one pair case} {
    string map -nocase {abc 32} aAbCaBaAbAbcAb
} {a32aBaAb32Ab}
test string-10.16 {string map, one pair case} {
    string map -nocase {ab 4321} aAbCaBaAbAbcAb
} {a4321C4321a43214321c4321}
test string-10.17 {string map, one pair case} {
    string map {Ab 4321} aAbCaBaAbAbcAb
} {a4321CaBa43214321c4321}
test string-10.18 {string map, empty argument} {
    string map -nocase {{} abc} foo
} foo
test string-10.19 {string map, empty arguments} {
    string map -nocase {{} abc f bar {} def} foo
} baroo
test string-10.20 {string map, dictionaries don't alter map ordering} {
    set map {aa X a Y}
    list [string map [dict create aa X a Y] aaa] [string map $map aaa] [dict size $map] [string map $map aaa]
} {XY XY 2 XY}
test string-10.21 {string map, ABR checks} {
    string map {longstring foob} long
} long
test string-10.22 {string map, ABR checks} {
    string map {long foob} long
} foob
test string-10.23 {string map, ABR checks} {
    string map {lon foob} long
} foobg
test string-10.24 {string map, ABR checks} {
    string map {lon foob} longlo
} foobglo
test string-10.25 {string map, ABR checks} {
    string map {lon foob} longlon
} foobgfoob
test string-10.26 {string map, ABR checks} {
    string map {longstring foob longstring bar} long
} long
test string-10.27 {string map, ABR checks} {
    string map {long foob longstring bar} long
} foob
test string-10.28 {string map, ABR checks} {
    string map {lon foob longstring bar} long
} foobg
test string-10.29 {string map, ABR checks} {
    string map {lon foob longstring bar} longlo
} foobglo
test string-10.30 {string map, ABR checks} {
    string map {lon foob longstring bar} longlon
} foobgfoob
test string-10.31 {string map, nasty sharing crash from [Bug 1018562]} {
    set a {a b}
    string map $a $a
} {b b}

test string-11.1 {string match, too few args} {
    list [catch {string match a} msg] $msg
} {1 {wrong # args: should be "string match ?-nocase? pattern string"}}
test string-11.2 {string match, too many args} {
    list [catch {string match a b c d} msg] $msg
} {1 {wrong # args: should be "string match ?-nocase? pattern string"}}
test string-11.3 {string match} {
    string match abc abc
} 1
test string-11.4 {string match} {
    string mat abc abd
} 0
test string-11.5 {string match} {
    string match ab*c abc
} 1
test string-11.6 {string match} {
    string match ab**c abc
} 1
test string-11.7 {string match} {
    string match ab* abcdef
} 1
test string-11.8 {string match} {
    string match *c abc
} 1
test string-11.9 {string match} {
    string match *3*6*9 0123456789
} 1
test string-11.9.1 {string match} {
    string match *3*6*89 0123456789
} 1
test string-11.9.2 {string match} {
    string match *3*456*89 0123456789
} 1
test string-11.9.3 {string match} {
    string match *3*6* 0123456789
} 1
test string-11.9.4 {string match} {
    string match *3*56* 0123456789
} 1
test string-11.9.5 {string match} {
    string match *3*456*** 0123456789
} 1
test string-11.9.6 {string match} {
    string match **3*456** 0123456789
} 1
test string-11.9.7 {string match} {
    string match *3***456* 0123456789
} 1
test string-11.9.8 {string match} {
    string match *3***\[456]* 0123456789
} 1
test string-11.9.9 {string match} {
    string match *3***\[4-6]* 0123456789
} 1
test string-11.9.10 {string match} {
    string match *3***\[4-6] 0123456789
} 0
test string-11.9.11 {string match} {
    string match *3***\[4-6] 0123456
} 1
test string-11.10 {string match} {
    string match *3*6*9 01234567890
} 0
test string-11.10.1 {string match} {
    string match *3*6*89 01234567890
} 0
test string-11.10.2 {string match} {
    string match *3*456*89 01234567890
} 0
test string-11.10.3 {string match} {
    string match **3*456*89 01234567890
} 0
test string-11.10.4 {string match} {
    string match *3*456***89 01234567890
} 0
test string-11.11 {string match} {
    string match a?c abc
} 1
test string-11.12 {string match} {
    string match a??c abc
} 0
test string-11.13 {string match} {
    string match ?1??4???8? 0123456789
} 1
test string-11.14 {string match} {
    string match {[abc]bc} abc
} 1
test string-11.15 {string match} {
    string match {a[abc]c} abc
} 1
test string-11.16 {string match} {
    string match {a[xyz]c} abc
} 0
test string-11.17 {string match} {
    string match {12[2-7]45} 12345
} 1
test string-11.18 {string match} {
    string match {12[ab2-4cd]45} 12345
} 1
test string-11.19 {string match} {
    string match {12[ab2-4cd]45} 12b45
} 1
test string-11.20 {string match} {
    string match {12[ab2-4cd]45} 12d45
} 1
test string-11.21 {string match} {
    string match {12[ab2-4cd]45} 12145
} 0
test string-11.22 {string match} {
    string match {12[ab2-4cd]45} 12545
} 0
test string-11.23 {string match} {
    string match {a\*b} a*b
} 1
test string-11.24 {string match} {
    string match {a\*b} ab
} 0
test string-11.25 {string match} {
    string match {a\*\?\[\]\\\x} "a*?\[\]\\x"
} 1
test string-11.26 {string match} {
    string match ** ""
} 1
test string-11.27 {string match} {
    string match *. ""
} 0
test string-11.28 {string match} {
    string match "" ""
} 1
test string-11.29 {string match} {
    string match \[a a
} 1
test string-11.30 {string match, bad args} {
    list [catch {string match - b c} msg] $msg
} {1 {bad option "-": must be -nocase}}
test string-11.31 {string match case} {
    string match a A
} 0
test string-11.32 {string match nocase} {
    string match -n a A
} 1
test string-11.33 {string match nocase} {
    string match -nocase a\334 A\374
} 1
test string-11.34 {string match nocase} {
    string match -nocase a*f ABCDEf
} 1
test string-11.35 {string match case, false hope} {
    # This is true because '_' lies between the A-Z and a-z ranges
    string match {[A-z]} _
} 1
test string-11.36 {string match nocase range} {
    # This is false because although '_' lies between the A-Z and a-z ranges,
    # we lower case the end points before checking the ranges.
    string match -nocase {[A-z]} _
} 0
test string-11.37 {string match nocase} {
    string match -nocase {[A-fh-Z]} g
} 0
test string-11.38 {string match case, reverse range} {
    string match {[A-fh-Z]} g
} 1
test string-11.39 {string match, *\ case} {
    string match {*\abc} abc
} 1
test string-11.39.1 {string match, *\ case} {
    string match {*ab\c} abc
} 1
test string-11.39.2 {string match, *\ case} {
    string match {*ab\*} ab*
} 1
test string-11.39.3 {string match, *\ case} {
    string match {*ab\*} abc
} 0
test string-11.39.4 {string match, *\ case} {
    string match {*ab\\*} {ab\c}
} 1
test string-11.39.5 {string match, *\ case} {
    string match {*ab\\*} {ab\*}
} 1
test string-11.40 {string match, *special case} {
    string match {*[ab]} abc
} 0
test string-11.41 {string match, *special case} {
    string match {*[ab]*} abc
} 1
test string-11.42 {string match, *special case} {
    string match "*\\" "\\"
} 0
test string-11.43 {string match, *special case} {
    string match "*\\\\" "\\"
} 1
test string-11.44 {string match, *special case} {
    string match "*???" "12345"
} 1
test string-11.45 {string match, *special case} {
    string match "*???" "12"
} 0
test string-11.46 {string match, *special case} {
    string match "*\\*" "abc*"
} 1
test string-11.47 {string match, *special case} {
    string match "*\\*" "*"
} 1
test string-11.48 {string match, *special case} {
    string match "*\\*" "*abc"
} 0
test string-11.49 {string match, *special case} {
    string match "?\\*" "a*"
} 1
test string-11.50 {string match, *special case} {
    string match "\\" "\\"
} 0
test string-11.51 {string match; *, -nocase and UTF-8} {
    string match -nocase [binary format I 717316707] \
	    [binary format I 2028036707]
} 1
test string-11.52 {string match, null char in string} {
    set out ""
    set ptn "*abc*"
    foreach elem [list "\u0000@abc" "@abc" "\u0000@abc\u0000" "blahabcblah"] {
	lappend out [string match $ptn $elem]
    }
    set out
} {1 1 1 1}
test string-11.53 {string match, null char in pattern} {
    set out ""
    foreach {ptn elem} [list \
	    "*\u0000abc\u0000"  "\u0000abc\u0000" \
	    "*\u0000abc\u0000"  "\u0000abc\u0000ef" \
	    "*\u0000abc\u0000*" "\u0000abc\u0000ef" \
	    "*\u0000abc\u0000"  "@\u0000abc\u0000ef" \
	    "*\u0000abc\u0000*"  "@\u0000abc\u0000ef" \
	    ] {
	lappend out [string match $ptn $elem]
    }
    set out
} {1 0 1 0 1}
test string-11.54 {string match, failure} {
    set longString ""
    for {set i 0} {$i < 10} {incr i} {
	append longString "abcdefghijklmnopqrstuvwxy\u0000z01234567890123"
    }
    string first $longString 123
    list [string match *cba* $longString] \
	    [string match *a*l*\u0000* $longString] \
	    [string match *a*l*\u0000*123 $longString] \
	    [string match *a*l*\u0000*123* $longString] \
	    [string match *a*l*\u0000*cba* $longString] \
	    [string match *===* $longString]
} {0 1 1 1 0 0}

test string-12.1 {string range} {
    list [catch {string range} msg] $msg
} {1 {wrong # args: should be "string range string first last"}}
test string-12.2 {string range} {
    list [catch {string range a 1} msg] $msg
} {1 {wrong # args: should be "string range string first last"}}
test string-12.3 {string range} {
    list [catch {string range a 1 2 3} msg] $msg
} {1 {wrong # args: should be "string range string first last"}}
test string-12.4 {string range} {
    string range abcdefghijklmnop 2 14
} {cdefghijklmno}
test string-12.5 {string range, last > length} {
    string range abcdefghijklmnop 7 1000
} {hijklmnop}
test string-12.6 {string range} {
    string range abcdefghijklmnop 10 end
} {klmnop}
test string-12.7 {string range, last < first} {
    string range abcdefghijklmnop 10 9
} {}
test string-12.8 {string range, first < 0} {
    string range abcdefghijklmnop -3 2
} {abc}
test string-12.9 {string range} {
    string range abcdefghijklmnop -3 -2
} {}
test string-12.10 {string range} {
    string range abcdefghijklmnop 1000 1010
} {}
test string-12.11 {string range} {
    string range abcdefghijklmnop -100 end
} {abcdefghijklmnop}
test string-12.12 {string range} {
    list [catch {string range abc abc 1} msg] $msg
} {1 {bad index "abc": must be integer?[+-]integer? or end?[+-]integer?}}
test string-12.13 {string range} {
    list [catch {string range abc 1 eof} msg] $msg
} {1 {bad index "eof": must be integer?[+-]integer? or end?[+-]integer?}}
test string-12.14 {string range} {
    string range abcdefghijklmnop end-1 end
} {op}
test string-12.15 {string range} {
    string range abcdefghijklmnop end 1000
} {p}
test string-12.16 {string range} {
    string range abcdefghijklmnop end end-1
} {}
test string-12.17 {string range, unicode} {
    string range ab\u7266cdefghijklmnop 5 5
} e
test string-12.18 {string range, unicode} {
    string range ab\u7266cdefghijklmnop 2 3
} \u7266c
test string-12.19 {string range, bytearray object} {
    set b [binary format I* {0x50515253 0x52}]
    set r1 [string range $b 1 end-1]
    set r2 [string range $b 1 6]
    string equal $r1 $r2
} 1
test string-12.20 {string range, out of bounds indices} {
    string range \u00ff 0 1
} \u00ff
# Bug 1410553
test string-12.21 {string range, regenerates correct reps, bug 1410553} {
    set bytes "\x00 \x03 \x41"
    set rxBuffer {}
    foreach ch $bytes {
	append rxBuffer $ch
	if {$ch eq "\x03"} {
	    string length $rxBuffer
	}
    }
    set rxCRC [string range $rxBuffer end-1 end]
    binary scan [join $bytes {}] "H*" input_hex
    binary scan $rxBuffer "H*" rxBuffer_hex
    binary scan $rxCRC "H*" rxCRC_hex
    list $input_hex $rxBuffer_hex $rxCRC_hex
} {000341 000341 0341}
test string-12.22 {string range, shimmering binary/index} {
    set s 0000000001
    binary scan $s a* x
    string range $s $s end
} 000000001

test string-13.1 {string repeat} {
    list [catch {string repeat} msg] $msg
} {1 {wrong # args: should be "string repeat string count"}}
test string-13.2 {string repeat} {
    list [catch {string repeat abc 10 oops} msg] $msg
} {1 {wrong # args: should be "string repeat string count"}}
test string-13.3 {string repeat} {
    string repeat {} 100
} {}
test string-13.4 {string repeat} {
    string repeat { } 5
} {     }
test string-13.5 {string repeat} {
    string repeat abc 3
} {abcabcabc}
test string-13.6 {string repeat} {
    string repeat abc -1
} {}
test string-13.7 {string repeat} {
    list [catch {string repeat abc end} msg] $msg
} {1 {expected integer but got "end"}}
test string-13.8 {string repeat} {
    string repeat {} -1000
} {}
test string-13.9 {string repeat} {
    string repeat {} 0
} {}
test string-13.10 {string repeat} {
    string repeat def 0
} {}
test string-13.11 {string repeat} {
    string repeat def 1
} def
test string-13.12 {string repeat} {
    string repeat ab\u7266cd 3
} ab\u7266cdab\u7266cdab\u7266cd
test string-13.13 {string repeat} {
    string repeat \x00 3
} \x00\x00\x00
test string-13.14 {string repeat} {
    # The string range will ensure us that string repeat gets a unicode string
    string repeat [string range ab\u7266cd 2 3] 3
} \u7266c\u7266c\u7266c

test string-14.1 {string replace} {
    list [catch {string replace} msg] $msg
} {1 {wrong # args: should be "string replace string first last ?string?"}}
test string-14.2 {string replace} {
    list [catch {string replace a 1} msg] $msg
} {1 {wrong # args: should be "string replace string first last ?string?"}}
test string-14.3 {string replace} {
    list [catch {string replace a 1 2 3 4} msg] $msg
} {1 {wrong # args: should be "string replace string first last ?string?"}}
test string-14.4 {string replace} {
} {}
test string-14.5 {string replace} {
    string replace abcdefghijklmnop 2 14
} {abp}
test string-14.6 {string replace} {
    string replace abcdefghijklmnop 7 1000
} {abcdefg}
test string-14.7 {string replace} {
    string replace abcdefghijklmnop 10 end
} {abcdefghij}
test string-14.8 {string replace} {
    string replace abcdefghijklmnop 10 9
} {abcdefghijklmnop}
test string-14.9 {string replace} {
    string replace abcdefghijklmnop -3 2
} {defghijklmnop}
test string-14.10 {string replace} {
    string replace abcdefghijklmnop -3 -2
} {abcdefghijklmnop}
test string-14.11 {string replace} {
    string replace abcdefghijklmnop 1000 1010
} {abcdefghijklmnop}
test string-14.12 {string replace} {
    string replace abcdefghijklmnop -100 end
} {}
test string-14.13 {string replace} {
    list [catch {string replace abc abc 1} msg] $msg
} {1 {bad index "abc": must be integer?[+-]integer? or end?[+-]integer?}}
test string-14.14 {string replace} {
    list [catch {string replace abc 1 eof} msg] $msg
} {1 {bad index "eof": must be integer?[+-]integer? or end?[+-]integer?}}
test string-14.15 {string replace} {
    string replace abcdefghijklmnop end-10 end-2 NEW
} {abcdeNEWop}
test string-14.16 {string replace} {
    string replace abcdefghijklmnop 0 end foo
} {foo}
test string-14.17 {string replace} {
    string replace abcdefghijklmnop end end-1
} {abcdefghijklmnop}

test string-15.1 {string tolower too few args} {
    list [catch {string tolower} msg] $msg
} {1 {wrong # args: should be "string tolower string ?first? ?last?"}}
test string-15.2 {string tolower bad args} {
    list [catch {string tolower a b} msg] $msg
} {1 {bad index "b": must be integer?[+-]integer? or end?[+-]integer?}}
test string-15.3 {string tolower too many args} {
    list [catch {string tolower ABC 1 end oops} msg] $msg
} {1 {wrong # args: should be "string tolower string ?first? ?last?"}}
test string-15.4 {string tolower} {
    string tolower ABCDeF
} {abcdef}
test string-15.5 {string tolower} {
    string tolower "ABC  XyZ"
} {abc  xyz}
test string-15.6 {string tolower} {
    string tolower {123#$&*()}
} {123#$&*()}
test string-15.7 {string tolower} {
    string tolower ABC 1
} AbC
test string-15.8 {string tolower} {
    string tolower ABC 1 end
} Abc
test string-15.9 {string tolower} {
    string tolower ABC 0 end-1
} abC
test string-15.10 {string tolower, unicode} {
     string tolower ABCabc\xc7\xe7
} "abcabc\xe7\xe7"

test string-16.1 {string toupper} {
    list [catch {string toupper} msg] $msg
} {1 {wrong # args: should be "string toupper string ?first? ?last?"}}
test string-16.2 {string toupper} {
    list [catch {string toupper a b} msg] $msg
} {1 {bad index "b": must be integer?[+-]integer? or end?[+-]integer?}}
test string-16.3 {string toupper} {
    list [catch {string toupper a 1 end oops} msg] $msg
} {1 {wrong # args: should be "string toupper string ?first? ?last?"}}
test string-16.4 {string toupper} {
    string toupper abCDEf
} {ABCDEF}
test string-16.5 {string toupper} {
    string toupper "abc xYz"
} {ABC XYZ}
test string-16.6 {string toupper} {
    string toupper {123#$&*()}
} {123#$&*()}
test string-16.7 {string toupper} {
    string toupper abc 1
} aBc
test string-16.8 {string toupper} {
    string toupper abc 1 end
} aBC
test string-16.9 {string toupper} {
    string toupper abc 0 end-1
} ABc
test string-16.10 {string toupper, unicode} {
    string toupper ABCabc\xc7\xe7
} "ABCABC\xc7\xc7"

test string-17.1 {string totitle} {
    list [catch {string totitle} msg] $msg
} {1 {wrong # args: should be "string totitle string ?first? ?last?"}}
test string-17.2 {string totitle} {
    list [catch {string totitle a b} msg] $msg
} {1 {bad index "b": must be integer?[+-]integer? or end?[+-]integer?}}
test string-17.3 {string totitle} {
    string totitle abCDEf
} {Abcdef}
test string-17.4 {string totitle} {
    string totitle "abc xYz"
} {Abc xyz}
test string-17.5 {string totitle} {
    string totitle {123#$&*()}
} {123#$&*()}
test string-17.6 {string totitle, unicode} {
    string totitle ABCabc\xc7\xe7
} "Abcabc\xe7\xe7"
test string-17.7 {string totitle, unicode} {
    string totitle \u01f3BCabc\xc7\xe7
} "\u01f2bcabc\xe7\xe7"

test string-18.1 {string trim} {
    list [catch {string trim} msg] $msg
} {1 {wrong # args: should be "string trim string ?chars?"}}
test string-18.2 {string trim} {
    list [catch {string trim a b c} msg] $msg
} {1 {wrong # args: should be "string trim string ?chars?"}}
test string-18.3 {string trim} {
    string trim "    XYZ      "
} {XYZ}
test string-18.4 {string trim} {
    string trim "\t\nXYZ\t\n\r\n"
} {XYZ}
test string-18.5 {string trim} {
    string trim "  A XYZ A    "
} {A XYZ A}
test string-18.6 {string trim} {
    string trim "XXYYZZABC XXYYZZ" ZYX
} {ABC }
test string-18.7 {string trim} {
    string trim "    \t\r      "
} {}
test string-18.8 {string trim} {
    string trim {abcdefg} {}
} {abcdefg}
test string-18.9 {string trim} {
    string trim {}
} {}
test string-18.10 {string trim} {
    string trim ABC DEF
} {ABC}
test string-18.11 {string trim, unicode} {
    string trim "\xe7\xe8 AB\xe7C \xe8\xe7" \xe7\xe8
} " AB\xe7C "

test string-19.1 {string trimleft} {
    list [catch {string trimleft} msg] $msg
} {1 {wrong # args: should be "string trimleft string ?chars?"}}
test string-19.2 {string trimleft} {
    string trimleft "    XYZ      "
} {XYZ      }

test string-20.1 {string trimright errors} {
    list [catch {string trimright} msg] $msg
} {1 {wrong # args: should be "string trimright string ?chars?"}}
test string-20.2 {string trimright errors} {
    list [catch {string trimg a} msg] $msg
} {1 {unknown or ambiguous subcommand "trimg": must be bytelength, compare, equal, first, index, is, last, length, map, match, range, repeat, replace, reverse, tolower, totitle, toupper, trim, trimleft, trimright, wordend, or wordstart}}
test string-20.3 {string trimright} {
    string trimright "    XYZ      "
} {    XYZ}
test string-20.4 {string trimright} {
    string trimright "   "
} {}
test string-20.5 {string trimright} {
    string trimright ""
} {}

test string-21.1 {string wordend} {
    list [catch {string wordend a} msg] $msg
} {1 {wrong # args: should be "string wordend string index"}}
test string-21.2 {string wordend} {
    list [catch {string wordend a b c} msg] $msg
} {1 {wrong # args: should be "string wordend string index"}}
test string-21.3 {string wordend} {
    list [catch {string wordend a gorp} msg] $msg
} {1 {bad index "gorp": must be integer?[+-]integer? or end?[+-]integer?}}
test string-21.4 {string wordend} {
    string wordend abc. -1
} 3
test string-21.5 {string wordend} {
    string wordend abc. 100
} 4
test string-21.6 {string wordend} {
    string wordend "word_one two three" 2
} 8
test string-21.7 {string wordend} {
    string wordend "one .&# three" 5
} 6
test string-21.8 {string wordend} {
    string worde "x.y" 0
} 1
test string-21.9 {string wordend} {
    string worde "x.y" end-1
} 2
test string-21.10 {string wordend, unicode} {
    string wordend "xyz\u00c7de fg" 0
} 6
test string-21.11 {string wordend, unicode} {
    string wordend "xyz\uc700de fg" 0
} 6
test string-21.12 {string wordend, unicode} {
    string wordend "xyz\u203fde fg" 0
} 6
test string-21.13 {string wordend, unicode} {
    string wordend "xyz\u2045de fg" 0
} 3
test string-21.14 {string wordend, unicode} {
    string wordend "\uc700\uc700 abc" 8
} 6

test string-22.1 {string wordstart} {
    list [catch {string word a} msg] $msg
} {1 {unknown or ambiguous subcommand "word": must be bytelength, compare, equal, first, index, is, last, length, map, match, range, repeat, replace, reverse, tolower, totitle, toupper, trim, trimleft, trimright, wordend, or wordstart}}
test string-22.2 {string wordstart} {
    list [catch {string wordstart a} msg] $msg
} {1 {wrong # args: should be "string wordstart string index"}}
test string-22.3 {string wordstart} {
    list [catch {string wordstart a b c} msg] $msg
} {1 {wrong # args: should be "string wordstart string index"}}
test string-22.4 {string wordstart} {
    list [catch {string wordstart a gorp} msg] $msg
} {1 {bad index "gorp": must be integer?[+-]integer? or end?[+-]integer?}}
test string-22.5 {string wordstart} {
    string wordstart "one two three_words" 400
} 8
test string-22.6 {string wordstart} {
    string wordstart "one two three_words" 2
} 0
test string-22.7 {string wordstart} {
    string wordstart "one two three_words" -2
} 0
test string-22.8 {string wordstart} {
    string wordstart "one .*&^ three" 6
} 6
test string-22.9 {string wordstart} {
    string wordstart "one two three" 4
} 4
test string-22.10 {string wordstart} {
    string wordstart "one two three" end-5
} 7
test string-22.11 {string wordstart, unicode} {
    string wordstart "one tw\u00c7o three" 7
} 4
test string-22.12 {string wordstart, unicode} {
    string wordstart "ab\uc700\uc700 cdef ghi" 12
} 10
test string-22.13 {string wordstart, unicode} {
    string wordstart "\uc700\uc700 abc" 8
} 3

test string-23.0 {string is boolean, Bug 1187123} testindexobj {
    set x 5
    catch {testindexobj $x foo bar soom}
    string is boolean $x
} 0
test string-23.1 {string is command with empty string} {
    set s ""
    list \
        [string is alnum $s] \
        [string is alpha $s] \
        [string is ascii $s] \
        [string is control $s] \
        [string is boolean $s] \
        [string is digit $s] \
        [string is double $s] \
        [string is false $s] \
        [string is graph $s] \
        [string is integer $s] \
        [string is lower $s] \
        [string is print $s] \
        [string is punct $s] \
        [string is space $s] \
        [string is true $s] \
        [string is upper $s] \
        [string is wordchar $s] \
        [string is xdigit $s] \

} {1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1}
test string-23.2 {string is command with empty string} {
    set s ""
    list \
        [string is alnum -strict $s] \
        [string is alpha -strict $s] \
        [string is ascii -strict $s] \
        [string is control -strict $s] \
        [string is boolean -strict $s] \
        [string is digit -strict $s] \
        [string is double -strict $s] \
        [string is false -strict $s] \
        [string is graph -strict $s] \
        [string is integer -strict $s] \
        [string is lower -strict $s] \
        [string is print -strict $s] \
        [string is punct -strict $s] \
        [string is space -strict $s] \
        [string is true -strict $s] \
        [string is upper -strict $s] \
        [string is wordchar -strict $s] \
        [string is xdigit -strict $s] \

} {0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0}

test string-24.1 {string reverse command} -body {
    string reverse
} -returnCodes error -result "wrong # args: should be \"string reverse string\""
test string-24.2 {string reverse command} -body {
    string reverse a b
} -returnCodes error -result "wrong # args: should be \"string reverse string\""
test string-24.3 {string reverse command - shared string} {
    set x abcde
    string reverse $x
} edcba
test string-24.4 {string reverse command - unshared string} {
    set x abc
    set y de
    string reverse $x$y
} edcba
test string-24.5 {string reverse command - shared unicode string} {
    set x abcde\udead
    string reverse $x
} \udeadedcba
test string-24.6 {string reverse command - unshared string} {
    set x abc
    set y de\udead
    string reverse $x$y
} \udeadedcba
test string-24.7 {string reverse command - simple case} {
    string reverse a
} a
test string-24.8 {string reverse command - simple case} {
    string reverse \udead
} \udead
test string-24.9 {string reverse command - simple case} {
    string reverse {}
} {}
test string-24.10 {string reverse command - corner case} {
    set x \ubeef\udead
    string reverse $x
} \udead\ubeef
test string-24.11 {string reverse command - corner case} {
    set x \ubeef
    set y \udead
    string reverse $x$y
} \udead\ubeef

test string-25.1 {string is list} {
    string is list {a b c}
} 1
test string-25.2 {string is list} {
    string is list "a \{b c"
} 0
test string-25.3 {string is list} {
    string is list {a {b c}d e}
} 0
test string-25.4 {string is list} {
    string is list {}
} 1
test string-25.5 {string is list} {
    string is list -strict {a b c}
} 1
test string-25.6 {string is list} {
    string is list -strict "a \{b c"
} 0
test string-25.7 {string is list} {
    string is list -strict {a {b c}d e}
} 0
test string-25.8 {string is list} {
    string is list -strict {}
} 1
test string-25.9 {string is list} {
    set x {}
    list [string is list -failindex x {a b c}] $x
} {1 {}}
test string-25.10 {string is list} {
    set x {}
    list [string is list -failindex x "a \{b c"] $x
} {0 2}
test string-25.11 {string is list} {
    set x {}
    list [string is list -failindex x {a b {b c}d e}] $x
} {0 4}
test string-25.12 {string is list} {
    set x {}
    list [string is list -failindex x {}] $x
} {1 {}}
test string-25.13 {string is list} {
    set x {}
    list [string is list -failindex x {  {b c}d e}] $x
} {0 2}
test string-25.14 {string is list} {
    set x {}
    list [string is list -failindex x "\uabcd {b c}d e"] $x
} {0 2}

# cleanup
::tcltest::cleanupTests
return

# Local Variables:
# mode: tcl
# End:
= PyBytes_FromFormatV(format, vargs); va_end(vargs); return ret; } static void bytes_dealloc(PyObject *op) { Py_TYPE(op)->tp_free(op); } /* Unescape a backslash-escaped string. If unicode is non-zero, the string is a u-literal. If recode_encoding is non-zero, the string is UTF-8 encoded and should be re-encoded in the specified encoding. */ PyObject *PyBytes_DecodeEscape(const char *s, Py_ssize_t len, const char *errors, Py_ssize_t unicode, const char *recode_encoding) { int c; char *p, *buf; const char *end; PyObject *v; Py_ssize_t newlen = recode_encoding ? 4*len:len; v = PyBytes_FromStringAndSize((char *)NULL, newlen); if (v == NULL) return NULL; p = buf = PyBytes_AsString(v); end = s + len; while (s < end) { if (*s != '\\') { non_esc: if (recode_encoding && (*s & 0x80)) { PyObject *u, *w; char *r; const char* t; Py_ssize_t rn; t = s; /* Decode non-ASCII bytes as UTF-8. */ while (t < end && (*t & 0x80)) t++; u = PyUnicode_DecodeUTF8(s, t - s, errors); if(!u) goto failed; /* Recode them in target encoding. */ w = PyUnicode_AsEncodedString( u, recode_encoding, errors); Py_DECREF(u); if (!w) goto failed; /* Append bytes to output buffer. */ assert(PyBytes_Check(w)); r = PyBytes_AS_STRING(w); rn = PyBytes_GET_SIZE(w); Py_MEMCPY(p, r, rn); p += rn; Py_DECREF(w); s = t; } else { *p++ = *s++; } continue; } s++; if (s==end) { PyErr_SetString(PyExc_ValueError, "Trailing \\ in string"); goto failed; } switch (*s++) { /* XXX This assumes ASCII! */ case '\n': break; case '\\': *p++ = '\\'; break; case '\'': *p++ = '\''; break; case '\"': *p++ = '\"'; break; case 'b': *p++ = '\b'; break; case 'f': *p++ = '\014'; break; /* FF */ case 't': *p++ = '\t'; break; case 'n': *p++ = '\n'; break; case 'r': *p++ = '\r'; break; case 'v': *p++ = '\013'; break; /* VT */ case 'a': *p++ = '\007'; break; /* BEL, not classic C */ case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': c = s[-1] - '0'; if (s < end && '0' <= *s && *s <= '7') { c = (c<<3) + *s++ - '0'; if (s < end && '0' <= *s && *s <= '7') c = (c<<3) + *s++ - '0'; } *p++ = c; break; case 'x': if (s+1 < end && Py_ISXDIGIT(s[0]) && Py_ISXDIGIT(s[1])) { unsigned int x = 0; c = Py_CHARMASK(*s); s++; if (Py_ISDIGIT(c)) x = c - '0'; else if (Py_ISLOWER(c)) x = 10 + c - 'a'; else x = 10 + c - 'A'; x = x << 4; c = Py_CHARMASK(*s); s++; if (Py_ISDIGIT(c)) x += c - '0'; else if (Py_ISLOWER(c)) x += 10 + c - 'a'; else x += 10 + c - 'A'; *p++ = x; break; } if (!errors || strcmp(errors, "strict") == 0) { PyErr_SetString(PyExc_ValueError, "invalid \\x escape"); goto failed; } if (strcmp(errors, "replace") == 0) { *p++ = '?'; } else if (strcmp(errors, "ignore") == 0) /* do nothing */; else { PyErr_Format(PyExc_ValueError, "decoding error; unknown " "error handling code: %.400s", errors); goto failed; } default: *p++ = '\\'; s--; goto non_esc; /* an arbitrary number of unescaped UTF-8 bytes may follow. */ } } if (p-buf < newlen) _PyBytes_Resize(&v, p - buf); return v; failed: Py_DECREF(v); return NULL; } /* -------------------------------------------------------------------- */ /* object api */ Py_ssize_t PyBytes_Size(register PyObject *op) { if (!PyBytes_Check(op)) { PyErr_Format(PyExc_TypeError, "expected bytes, %.200s found", Py_TYPE(op)->tp_name); return -1; } return Py_SIZE(op); } char * PyBytes_AsString(register PyObject *op) { if (!PyBytes_Check(op)) { PyErr_Format(PyExc_TypeError, "expected bytes, %.200s found", Py_TYPE(op)->tp_name); return NULL; } return ((PyBytesObject *)op)->ob_sval; } int PyBytes_AsStringAndSize(register PyObject *obj, register char **s, register Py_ssize_t *len) { if (s == NULL) { PyErr_BadInternalCall(); return -1; } if (!PyBytes_Check(obj)) { PyErr_Format(PyExc_TypeError, "expected bytes, %.200s found", Py_TYPE(obj)->tp_name); return -1; } *s = PyBytes_AS_STRING(obj); if (len != NULL) *len = PyBytes_GET_SIZE(obj); else if (strlen(*s) != (size_t)PyBytes_GET_SIZE(obj)) { PyErr_SetString(PyExc_TypeError, "expected bytes with no null"); return -1; } return 0; } /* -------------------------------------------------------------------- */ /* Methods */ #include "stringlib/stringdefs.h" #include "stringlib/fastsearch.h" #include "stringlib/count.h" #include "stringlib/find.h" #include "stringlib/partition.h" #include "stringlib/split.h" #include "stringlib/ctype.h" #include "stringlib/transmogrify.h" PyObject * PyBytes_Repr(PyObject *obj, int smartquotes) { static const char *hexdigits = "0123456789abcdef"; register PyBytesObject* op = (PyBytesObject*) obj; Py_ssize_t length = Py_SIZE(op); size_t newsize; PyObject *v; if (length > (PY_SSIZE_T_MAX - 3) / 4) { PyErr_SetString(PyExc_OverflowError, "bytes object is too large to make repr"); return NULL; } newsize = 3 + 4 * length; v = PyUnicode_FromUnicode(NULL, newsize); if (v == NULL) { return NULL; } else { register Py_ssize_t i; register Py_UNICODE c; register Py_UNICODE *p = PyUnicode_AS_UNICODE(v); int quote; /* Figure out which quote to use; single is preferred */ quote = '\''; if (smartquotes) { char *test, *start; start = PyBytes_AS_STRING(op); for (test = start; test < start+length; ++test) { if (*test == '"') { quote = '\''; /* back to single */ goto decided; } else if (*test == '\'') quote = '"'; } decided: ; } *p++ = 'b', *p++ = quote; for (i = 0; i < length; i++) { /* There's at least enough room for a hex escape and a closing quote. */ assert(newsize - (p - PyUnicode_AS_UNICODE(v)) >= 5); c = op->ob_sval[i]; if (c == quote || c == '\\') *p++ = '\\', *p++ = c; else if (c == '\t') *p++ = '\\', *p++ = 't'; else if (c == '\n') *p++ = '\\', *p++ = 'n'; else if (c == '\r') *p++ = '\\', *p++ = 'r'; else if (c < ' ' || c >= 0x7f) { *p++ = '\\'; *p++ = 'x'; *p++ = hexdigits[(c & 0xf0) >> 4]; *p++ = hexdigits[c & 0xf]; } else *p++ = c; } assert(newsize - (p - PyUnicode_AS_UNICODE(v)) >= 1); *p++ = quote; *p = '\0'; if (PyUnicode_Resize(&v, (p - PyUnicode_AS_UNICODE(v)))) { Py_DECREF(v); return NULL; } return v; } } static PyObject * bytes_repr(PyObject *op) { return PyBytes_Repr(op, 1); } static PyObject * bytes_str(PyObject *op) { if (Py_BytesWarningFlag) { if (PyErr_WarnEx(PyExc_BytesWarning, "str() on a bytes instance", 1)) return NULL; } return bytes_repr(op); } static Py_ssize_t bytes_length(PyBytesObject *a) { return Py_SIZE(a); } /* This is also used by PyBytes_Concat() */ static PyObject * bytes_concat(PyObject *a, PyObject *b) { Py_ssize_t size; Py_buffer va, vb; PyObject *result = NULL; va.len = -1; vb.len = -1; if (_getbuffer(a, &va) < 0 || _getbuffer(b, &vb) < 0) { PyErr_Format(PyExc_TypeError, "can't concat %.100s to %.100s", Py_TYPE(a)->tp_name, Py_TYPE(b)->tp_name); goto done; } /* Optimize end cases */ if (va.len == 0 && PyBytes_CheckExact(b)) { result = b; Py_INCREF(result); goto done; } if (vb.len == 0 && PyBytes_CheckExact(a)) { result = a; Py_INCREF(result); goto done; } size = va.len + vb.len; if (size < 0) { PyErr_NoMemory(); goto done; } result = PyBytes_FromStringAndSize(NULL, size); if (result != NULL) { memcpy(PyBytes_AS_STRING(result), va.buf, va.len); memcpy(PyBytes_AS_STRING(result) + va.len, vb.buf, vb.len); } done: if (va.len != -1) PyBuffer_Release(&va); if (vb.len != -1) PyBuffer_Release(&vb); return result; } static PyObject * bytes_repeat(register PyBytesObject *a, register Py_ssize_t n) { register Py_ssize_t i; register Py_ssize_t j; register Py_ssize_t size; register PyBytesObject *op; size_t nbytes; if (n < 0) n = 0; /* watch out for overflows: the size can overflow int, * and the # of bytes needed can overflow size_t */ if (n > 0 && Py_SIZE(a) > PY_SSIZE_T_MAX / n) { PyErr_SetString(PyExc_OverflowError, "repeated bytes are too long"); return NULL; } size = Py_SIZE(a) * n; if (size == Py_SIZE(a) && PyBytes_CheckExact(a)) { Py_INCREF(a); return (PyObject *)a; } nbytes = (size_t)size; if (nbytes + PyBytesObject_SIZE <= nbytes) { PyErr_SetString(PyExc_OverflowError, "repeated bytes are too long"); return NULL; } op = (PyBytesObject *)PyObject_MALLOC(PyBytesObject_SIZE + nbytes); if (op == NULL) return PyErr_NoMemory(); PyObject_INIT_VAR(op, &PyBytes_Type, size); op->ob_shash = -1; op->ob_sval[size] = '\0'; if (Py_SIZE(a) == 1 && n > 0) { memset(op->ob_sval, a->ob_sval[0] , n); return (PyObject *) op; } i = 0; if (i < size) { Py_MEMCPY(op->ob_sval, a->ob_sval, Py_SIZE(a)); i = Py_SIZE(a); } while (i < size) { j = (i <= size-i) ? i : size-i; Py_MEMCPY(op->ob_sval+i, op->ob_sval, j); i += j; } return (PyObject *) op; } static int bytes_contains(PyObject *self, PyObject *arg) { Py_ssize_t ival = PyNumber_AsSsize_t(arg, PyExc_ValueError); if (ival == -1 && PyErr_Occurred()) { Py_buffer varg; Py_ssize_t pos; PyErr_Clear(); if (_getbuffer(arg, &varg) < 0) return -1; pos = stringlib_find(PyBytes_AS_STRING(self), Py_SIZE(self), varg.buf, varg.len, 0); PyBuffer_Release(&varg); return pos >= 0; } if (ival < 0 || ival >= 256) { PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)"); return -1; } return memchr(PyBytes_AS_STRING(self), (int) ival, Py_SIZE(self)) != NULL; } static PyObject * bytes_item(PyBytesObject *a, register Py_ssize_t i) { if (i < 0 || i >= Py_SIZE(a)) { PyErr_SetString(PyExc_IndexError, "index out of range"); return NULL; } return PyLong_FromLong((unsigned char)a->ob_sval[i]); } static PyObject* bytes_richcompare(PyBytesObject *a, PyBytesObject *b, int op) { int c; Py_ssize_t len_a, len_b; Py_ssize_t min_len; PyObject *result; /* Make sure both arguments are strings. */ if (!(PyBytes_Check(a) && PyBytes_Check(b))) { if (Py_BytesWarningFlag && (op == Py_EQ || op == Py_NE) && (PyObject_IsInstance((PyObject*)a, (PyObject*)&PyUnicode_Type) || PyObject_IsInstance((PyObject*)b, (PyObject*)&PyUnicode_Type))) { if (PyErr_WarnEx(PyExc_BytesWarning, "Comparison between bytes and string", 1)) return NULL; } result = Py_NotImplemented; goto out; } if (a == b) { switch (op) { case Py_EQ:case Py_LE:case Py_GE: result = Py_True; goto out; case Py_NE:case Py_LT:case Py_GT: result = Py_False; goto out; } } if (op == Py_EQ) { /* Supporting Py_NE here as well does not save much time, since Py_NE is rarely used. */ if (Py_SIZE(a) == Py_SIZE(b) && (a->ob_sval[0] == b->ob_sval[0] && memcmp(a->ob_sval, b->ob_sval, Py_SIZE(a)) == 0)) { result = Py_True; } else { result = Py_False; } goto out; } len_a = Py_SIZE(a); len_b = Py_SIZE(b); min_len = (len_a < len_b) ? len_a : len_b; if (min_len > 0) { c = Py_CHARMASK(*a->ob_sval) - Py_CHARMASK(*b->ob_sval); if (c==0) c = memcmp(a->ob_sval, b->ob_sval, min_len); } else c = 0; if (c == 0) c = (len_a < len_b) ? -1 : (len_a > len_b) ? 1 : 0; switch (op) { case Py_LT: c = c < 0; break; case Py_LE: c = c <= 0; break; case Py_EQ: assert(0); break; /* unreachable */ case Py_NE: c = c != 0; break; case Py_GT: c = c > 0; break; case Py_GE: c = c >= 0; break; default: result = Py_NotImplemented; goto out; } result = c ? Py_True : Py_False; out: Py_INCREF(result); return result; } static Py_hash_t bytes_hash(PyBytesObject *a) { register Py_ssize_t len; register unsigned char *p; register Py_uhash_t x; /* Unsigned for defined overflow behavior. */ #ifdef Py_DEBUG assert(_Py_HashSecret_Initialized); #endif if (a->ob_shash != -1) return a->ob_shash; len = Py_SIZE(a); /* We make the hash of the empty string be 0, rather than using (prefix ^ suffix), since this slightly obfuscates the hash secret */ if (len == 0) { a->ob_shash = 0; return 0; } p = (unsigned char *) a->ob_sval; x = _Py_HashSecret.prefix; x ^= *p << 7; while (--len >= 0) x = (_PyHASH_MULTIPLIER*x) ^ *p++; x ^= Py_SIZE(a); x ^= _Py_HashSecret.suffix; if (x == -1) x = -2; a->ob_shash = x; return x; } static PyObject* bytes_subscript(PyBytesObject* self, PyObject* item) { if (PyIndex_Check(item)) { Py_ssize_t i = PyNumber_AsSsize_t(item, PyExc_IndexError); if (i == -1 && PyErr_Occurred()) return NULL; if (i < 0) i += PyBytes_GET_SIZE(self); if (i < 0 || i >= PyBytes_GET_SIZE(self)) { PyErr_SetString(PyExc_IndexError, "index out of range"); return NULL; } return PyLong_FromLong((unsigned char)self->ob_sval[i]); } else if (PySlice_Check(item)) { Py_ssize_t start, stop, step, slicelength, cur, i; char* source_buf; char* result_buf; PyObject* result; if (PySlice_GetIndicesEx(item, PyBytes_GET_SIZE(self), &start, &stop, &step, &slicelength) < 0) { return NULL; } if (slicelength <= 0) { return PyBytes_FromStringAndSize("", 0); } else if (start == 0 && step == 1 && slicelength == PyBytes_GET_SIZE(self) && PyBytes_CheckExact(self)) { Py_INCREF(self); return (PyObject *)self; } else if (step == 1) { return PyBytes_FromStringAndSize( PyBytes_AS_STRING(self) + start, slicelength); } else { source_buf = PyBytes_AS_STRING(self); result = PyBytes_FromStringAndSize(NULL, slicelength); if (result == NULL) return NULL; result_buf = PyBytes_AS_STRING(result); for (cur = start, i = 0; i < slicelength; cur += step, i++) { result_buf[i] = source_buf[cur]; } return result; } } else { PyErr_Format(PyExc_TypeError, "byte indices must be integers, not %.200s", Py_TYPE(item)->tp_name); return NULL; } } static int bytes_buffer_getbuffer(PyBytesObject *self, Py_buffer *view, int flags) { return PyBuffer_FillInfo(view, (PyObject*)self, (void *)self->ob_sval, Py_SIZE(self), 1, flags); } static PySequenceMethods bytes_as_sequence = { (lenfunc)bytes_length, /*sq_length*/ (binaryfunc)bytes_concat, /*sq_concat*/ (ssizeargfunc)bytes_repeat, /*sq_repeat*/ (ssizeargfunc)bytes_item, /*sq_item*/ 0, /*sq_slice*/ 0, /*sq_ass_item*/ 0, /*sq_ass_slice*/ (objobjproc)bytes_contains /*sq_contains*/ }; static PyMappingMethods bytes_as_mapping = { (lenfunc)bytes_length, (binaryfunc)bytes_subscript, 0, }; static PyBufferProcs bytes_as_buffer = { (getbufferproc)bytes_buffer_getbuffer, NULL, }; #define LEFTSTRIP 0 #define RIGHTSTRIP 1 #define BOTHSTRIP 2 /* Arrays indexed by above */ static const char *stripformat[] = {"|O:lstrip", "|O:rstrip", "|O:strip"}; #define STRIPNAME(i) (stripformat[i]+3) PyDoc_STRVAR(split__doc__, "B.split([sep[, maxsplit]]) -> list of bytes\n\ \n\ Return a list of the sections in B, using sep as the delimiter.\n\ If sep is not specified or is None, B is split on ASCII whitespace\n\ characters (space, tab, return, newline, formfeed, vertical tab).\n\ If maxsplit is given, at most maxsplit splits are done."); static PyObject * bytes_split(PyBytesObject *self, PyObject *args) { Py_ssize_t len = PyBytes_GET_SIZE(self), n; Py_ssize_t maxsplit = -1; const char *s = PyBytes_AS_STRING(self), *sub; Py_buffer vsub; PyObject *list, *subobj = Py_None; if (!PyArg_ParseTuple(args, "|On:split", &subobj, &maxsplit)) return NULL; if (maxsplit < 0) maxsplit = PY_SSIZE_T_MAX; if (subobj == Py_None) return stringlib_split_whitespace((PyObject*) self, s, len, maxsplit); if (_getbuffer(subobj, &vsub) < 0) return NULL; sub = vsub.buf; n = vsub.len; list = stringlib_split((PyObject*) self, s, len, sub, n, maxsplit); PyBuffer_Release(&vsub); return list; } PyDoc_STRVAR(partition__doc__, "B.partition(sep) -> (head, sep, tail)\n\ \n\ Search for the separator sep in B, and return the part before it,\n\ the separator itself, and the part after it. If the separator is not\n\ found, returns B and two empty bytes objects."); static PyObject * bytes_partition(PyBytesObject *self, PyObject *sep_obj) { const char *sep; Py_ssize_t sep_len; if (PyBytes_Check(sep_obj)) { sep = PyBytes_AS_STRING(sep_obj); sep_len = PyBytes_GET_SIZE(sep_obj); } else if (PyObject_AsCharBuffer(sep_obj, &sep, &sep_len)) return NULL; return stringlib_partition( (PyObject*) self, PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), sep_obj, sep, sep_len ); } PyDoc_STRVAR(rpartition__doc__, "B.rpartition(sep) -> (head, sep, tail)\n\ \n\ Search for the separator sep in B, starting at the end of B,\n\ and return the part before it, the separator itself, and the\n\ part after it. If the separator is not found, returns two empty\n\ bytes objects and B."); static PyObject * bytes_rpartition(PyBytesObject *self, PyObject *sep_obj) { const char *sep; Py_ssize_t sep_len; if (PyBytes_Check(sep_obj)) { sep = PyBytes_AS_STRING(sep_obj); sep_len = PyBytes_GET_SIZE(sep_obj); } else if (PyObject_AsCharBuffer(sep_obj, &sep, &sep_len)) return NULL; return stringlib_rpartition( (PyObject*) self, PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), sep_obj, sep, sep_len ); } PyDoc_STRVAR(rsplit__doc__, "B.rsplit([sep[, maxsplit]]) -> list of bytes\n\ \n\ Return a list of the sections in B, using sep as the delimiter,\n\ starting at the end of B and working to the front.\n\ If sep is not given, B is split on ASCII whitespace characters\n\ (space, tab, return, newline, formfeed, vertical tab).\n\ If maxsplit is given, at most maxsplit splits are done."); static PyObject * bytes_rsplit(PyBytesObject *self, PyObject *args) { Py_ssize_t len = PyBytes_GET_SIZE(self), n; Py_ssize_t maxsplit = -1; const char *s = PyBytes_AS_STRING(self), *sub; Py_buffer vsub; PyObject *list, *subobj = Py_None; if (!PyArg_ParseTuple(args, "|On:rsplit", &subobj, &maxsplit)) return NULL; if (maxsplit < 0) maxsplit = PY_SSIZE_T_MAX; if (subobj == Py_None) return stringlib_rsplit_whitespace((PyObject*) self, s, len, maxsplit); if (_getbuffer(subobj, &vsub) < 0) return NULL; sub = vsub.buf; n = vsub.len; list = stringlib_rsplit((PyObject*) self, s, len, sub, n, maxsplit); PyBuffer_Release(&vsub); return list; } PyDoc_STRVAR(join__doc__, "B.join(iterable_of_bytes) -> bytes\n\ \n\ Concatenate any number of bytes objects, with B in between each pair.\n\ Example: b'.'.join([b'ab', b'pq', b'rs']) -> b'ab.pq.rs'."); static PyObject * bytes_join(PyObject *self, PyObject *orig) { char *sep = PyBytes_AS_STRING(self); const Py_ssize_t seplen = PyBytes_GET_SIZE(self); PyObject *res = NULL; char *p; Py_ssize_t seqlen = 0; size_t sz = 0; Py_ssize_t i; PyObject *seq, *item; seq = PySequence_Fast(orig, ""); if (seq == NULL) { return NULL; } seqlen = PySequence_Size(seq); if (seqlen == 0) { Py_DECREF(seq); return PyBytes_FromString(""); } if (seqlen == 1) { item = PySequence_Fast_GET_ITEM(seq, 0); if (PyBytes_CheckExact(item)) { Py_INCREF(item); Py_DECREF(seq); return item; } } /* There are at least two things to join, or else we have a subclass * of the builtin types in the sequence. * Do a pre-pass to figure out the total amount of space we'll * need (sz), and see whether all argument are bytes. */ /* XXX Shouldn't we use _getbuffer() on these items instead? */ for (i = 0; i < seqlen; i++) { const size_t old_sz = sz; item = PySequence_Fast_GET_ITEM(seq, i); if (!PyBytes_Check(item) && !PyByteArray_Check(item)) { PyErr_Format(PyExc_TypeError, "sequence item %zd: expected bytes," " %.80s found", i, Py_TYPE(item)->tp_name); Py_DECREF(seq); return NULL; } sz += Py_SIZE(item); if (i != 0) sz += seplen; if (sz < old_sz || sz > PY_SSIZE_T_MAX) { PyErr_SetString(PyExc_OverflowError, "join() result is too long for bytes"); Py_DECREF(seq); return NULL; } } /* Allocate result space. */ res = PyBytes_FromStringAndSize((char*)NULL, sz); if (res == NULL) { Py_DECREF(seq); return NULL; } /* Catenate everything. */ /* I'm not worried about a PyByteArray item growing because there's nowhere in this function where we release the GIL. */ p = PyBytes_AS_STRING(res); for (i = 0; i < seqlen; ++i) { size_t n; char *q; if (i) { Py_MEMCPY(p, sep, seplen); p += seplen; } item = PySequence_Fast_GET_ITEM(seq, i); n = Py_SIZE(item); if (PyBytes_Check(item)) q = PyBytes_AS_STRING(item); else q = PyByteArray_AS_STRING(item); Py_MEMCPY(p, q, n); p += n; } Py_DECREF(seq); return res; } PyObject * _PyBytes_Join(PyObject *sep, PyObject *x) { assert(sep != NULL && PyBytes_Check(sep)); assert(x != NULL); return bytes_join(sep, x); } /* helper macro to fixup start/end slice values */ #define ADJUST_INDICES(start, end, len) \ if (end > len) \ end = len; \ else if (end < 0) { \ end += len; \ if (end < 0) \ end = 0; \ } \ if (start < 0) { \ start += len; \ if (start < 0) \ start = 0; \ } Py_LOCAL_INLINE(Py_ssize_t) bytes_find_internal(PyBytesObject *self, PyObject *args, int dir) { PyObject *subobj; const char *sub; Py_ssize_t sub_len; Py_ssize_t start=0, end=PY_SSIZE_T_MAX; if (!stringlib_parse_args_finds("find/rfind/index/rindex", args, &subobj, &start, &end)) return -2; if (PyBytes_Check(subobj)) { sub = PyBytes_AS_STRING(subobj); sub_len = PyBytes_GET_SIZE(subobj); } else if (PyObject_AsCharBuffer(subobj, &sub, &sub_len)) /* XXX - the "expected a character buffer object" is pretty confusing for a non-expert. remap to something else ? */ return -2; if (dir > 0) return stringlib_find_slice( PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), sub, sub_len, start, end); else return stringlib_rfind_slice( PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), sub, sub_len, start, end); } PyDoc_STRVAR(find__doc__, "B.find(sub[, start[, end]]) -> int\n\ \n\ Return the lowest index in B where substring sub is found,\n\ such that sub is contained within B[start:end]. Optional\n\ arguments start and end are interpreted as in slice notation.\n\ \n\ Return -1 on failure."); static PyObject * bytes_find(PyBytesObject *self, PyObject *args) { Py_ssize_t result = bytes_find_internal(self, args, +1); if (result == -2) return NULL; return PyLong_FromSsize_t(result); } PyDoc_STRVAR(index__doc__, "B.index(sub[, start[, end]]) -> int\n\ \n\ Like B.find() but raise ValueError when the substring is not found."); static PyObject * bytes_index(PyBytesObject *self, PyObject *args) { Py_ssize_t result = bytes_find_internal(self, args, +1); if (result == -2) return NULL; if (result == -1) { PyErr_SetString(PyExc_ValueError, "substring not found"); return NULL; } return PyLong_FromSsize_t(result); } PyDoc_STRVAR(rfind__doc__, "B.rfind(sub[, start[, end]]) -> int\n\ \n\ Return the highest index in B where substring sub is found,\n\ such that sub is contained within B[start:end]. Optional\n\ arguments start and end are interpreted as in slice notation.\n\ \n\ Return -1 on failure."); static PyObject * bytes_rfind(PyBytesObject *self, PyObject *args) { Py_ssize_t result = bytes_find_internal(self, args, -1); if (result == -2) return NULL; return PyLong_FromSsize_t(result); } PyDoc_STRVAR(rindex__doc__, "B.rindex(sub[, start[, end]]) -> int\n\ \n\ Like B.rfind() but raise ValueError when the substring is not found."); static PyObject * bytes_rindex(PyBytesObject *self, PyObject *args) { Py_ssize_t result = bytes_find_internal(self, args, -1); if (result == -2) return NULL; if (result == -1) { PyErr_SetString(PyExc_ValueError, "substring not found"); return NULL; } return PyLong_FromSsize_t(result); } Py_LOCAL_INLINE(PyObject *) do_xstrip(PyBytesObject *self, int striptype, PyObject *sepobj) { Py_buffer vsep; char *s = PyBytes_AS_STRING(self); Py_ssize_t len = PyBytes_GET_SIZE(self); char *sep; Py_ssize_t seplen; Py_ssize_t i, j; if (_getbuffer(sepobj, &vsep) < 0) return NULL; sep = vsep.buf; seplen = vsep.len; i = 0; if (striptype != RIGHTSTRIP) { while (i < len && memchr(sep, Py_CHARMASK(s[i]), seplen)) { i++; } } j = len; if (striptype != LEFTSTRIP) { do { j--; } while (j >= i && memchr(sep, Py_CHARMASK(s[j]), seplen)); j++; } PyBuffer_Release(&vsep); if (i == 0 && j == len && PyBytes_CheckExact(self)) { Py_INCREF(self); return (PyObject*)self; } else return PyBytes_FromStringAndSize(s+i, j-i); } Py_LOCAL_INLINE(PyObject *) do_strip(PyBytesObject *self, int striptype) { char *s = PyBytes_AS_STRING(self); Py_ssize_t len = PyBytes_GET_SIZE(self), i, j; i = 0; if (striptype != RIGHTSTRIP) { while (i < len && Py_ISSPACE(s[i])) { i++; } } j = len; if (striptype != LEFTSTRIP) { do { j--; } while (j >= i && Py_ISSPACE(s[j])); j++; } if (i == 0 && j == len && PyBytes_CheckExact(self)) { Py_INCREF(self); return (PyObject*)self; } else return PyBytes_FromStringAndSize(s+i, j-i); } Py_LOCAL_INLINE(PyObject *) do_argstrip(PyBytesObject *self, int striptype, PyObject *args) { PyObject *sep = NULL; if (!PyArg_ParseTuple(args, (char *)stripformat[striptype], &sep)) return NULL; if (sep != NULL && sep != Py_None) { return do_xstrip(self, striptype, sep); } return do_strip(self, striptype); } PyDoc_STRVAR(strip__doc__, "B.strip([bytes]) -> bytes\n\ \n\ Strip leading and trailing bytes contained in the argument.\n\ If the argument is omitted, strip leading and trailing ASCII whitespace."); static PyObject * bytes_strip(PyBytesObject *self, PyObject *args) { if (PyTuple_GET_SIZE(args) == 0) return do_strip(self, BOTHSTRIP); /* Common case */ else return do_argstrip(self, BOTHSTRIP, args); } PyDoc_STRVAR(lstrip__doc__, "B.lstrip([bytes]) -> bytes\n\ \n\ Strip leading bytes contained in the argument.\n\ If the argument is omitted, strip leading ASCII whitespace."); static PyObject * bytes_lstrip(PyBytesObject *self, PyObject *args) { if (PyTuple_GET_SIZE(args) == 0) return do_strip(self, LEFTSTRIP); /* Common case */ else return do_argstrip(self, LEFTSTRIP, args); } PyDoc_STRVAR(rstrip__doc__, "B.rstrip([bytes]) -> bytes\n\ \n\ Strip trailing bytes contained in the argument.\n\ If the argument is omitted, strip trailing ASCII whitespace."); static PyObject * bytes_rstrip(PyBytesObject *self, PyObject *args) { if (PyTuple_GET_SIZE(args) == 0) return do_strip(self, RIGHTSTRIP); /* Common case */ else return do_argstrip(self, RIGHTSTRIP, args); } PyDoc_STRVAR(count__doc__, "B.count(sub[, start[, end]]) -> int\n\ \n\ Return the number of non-overlapping occurrences of substring sub in\n\ string B[start:end]. Optional arguments start and end are interpreted\n\ as in slice notation."); static PyObject * bytes_count(PyBytesObject *self, PyObject *args) { PyObject *sub_obj; const char *str = PyBytes_AS_STRING(self), *sub; Py_ssize_t sub_len; Py_ssize_t start = 0, end = PY_SSIZE_T_MAX; if (!stringlib_parse_args_finds("count", args, &sub_obj, &start, &end)) return NULL; if (PyBytes_Check(sub_obj)) { sub = PyBytes_AS_STRING(sub_obj); sub_len = PyBytes_GET_SIZE(sub_obj); } else if (PyObject_AsCharBuffer(sub_obj, &sub, &sub_len)) return NULL; ADJUST_INDICES(start, end, PyBytes_GET_SIZE(self)); return PyLong_FromSsize_t( stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX) ); } PyDoc_STRVAR(translate__doc__, "B.translate(table[, deletechars]) -> bytes\n\ \n\ Return a copy of B, where all characters occurring in the\n\ optional argument deletechars are removed, and the remaining\n\ characters have been mapped through the given translation\n\ table, which must be a bytes object of length 256."); static PyObject * bytes_translate(PyBytesObject *self, PyObject *args) { register char *input, *output; const char *table; register Py_ssize_t i, c, changed = 0; PyObject *input_obj = (PyObject*)self; const char *output_start, *del_table=NULL; Py_ssize_t inlen, tablen, dellen = 0; PyObject *result; int trans_table[256]; PyObject *tableobj, *delobj = NULL; if (!PyArg_UnpackTuple(args, "translate", 1, 2, &tableobj, &delobj)) return NULL; if (PyBytes_Check(tableobj)) { table = PyBytes_AS_STRING(tableobj); tablen = PyBytes_GET_SIZE(tableobj); } else if (tableobj == Py_None) { table = NULL; tablen = 256; } else if (PyObject_AsCharBuffer(tableobj, &table, &tablen)) return NULL; if (tablen != 256) { PyErr_SetString(PyExc_ValueError, "translation table must be 256 characters long"); return NULL; } if (delobj != NULL) { if (PyBytes_Check(delobj)) { del_table = PyBytes_AS_STRING(delobj); dellen = PyBytes_GET_SIZE(delobj); } else if (PyObject_AsCharBuffer(delobj, &del_table, &dellen)) return NULL; } else { del_table = NULL; dellen = 0; } inlen = PyBytes_GET_SIZE(input_obj); result = PyBytes_FromStringAndSize((char *)NULL, inlen); if (result == NULL) return NULL; output_start = output = PyBytes_AsString(result); input = PyBytes_AS_STRING(input_obj); if (dellen == 0 && table != NULL) { /* If no deletions are required, use faster code */ for (i = inlen; --i >= 0; ) { c = Py_CHARMASK(*input++); if (Py_CHARMASK((*output++ = table[c])) != c) changed = 1; } if (changed || !PyBytes_CheckExact(input_obj)) return result; Py_DECREF(result); Py_INCREF(input_obj); return input_obj; } if (table == NULL) { for (i = 0; i < 256; i++) trans_table[i] = Py_CHARMASK(i); } else { for (i = 0; i < 256; i++) trans_table[i] = Py_CHARMASK(table[i]); } for (i = 0; i < dellen; i++) trans_table[(int) Py_CHARMASK(del_table[i])] = -1; for (i = inlen; --i >= 0; ) { c = Py_CHARMASK(*input++); if (trans_table[c] != -1) if (Py_CHARMASK(*output++ = (char)trans_table[c]) == c) continue; changed = 1; } if (!changed && PyBytes_CheckExact(input_obj)) { Py_DECREF(result); Py_INCREF(input_obj); return input_obj; } /* Fix the size of the resulting string */ if (inlen > 0) _PyBytes_Resize(&result, output - output_start); return result; } static PyObject * bytes_maketrans(PyObject *null, PyObject *args) { return _Py_bytes_maketrans(args); } /* find and count characters and substrings */ #define findchar(target, target_len, c) \ ((char *)memchr((const void *)(target), c, target_len)) /* String ops must return a string. */ /* If the object is subclass of string, create a copy */ Py_LOCAL(PyBytesObject *) return_self(PyBytesObject *self) { if (PyBytes_CheckExact(self)) { Py_INCREF(self); return self; } return (PyBytesObject *)PyBytes_FromStringAndSize( PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self)); } Py_LOCAL_INLINE(Py_ssize_t) countchar(const char *target, Py_ssize_t target_len, char c, Py_ssize_t maxcount) { Py_ssize_t count=0; const char *start=target; const char *end=target+target_len; while ( (start=findchar(start, end-start, c)) != NULL ) { count++; if (count >= maxcount) break; start += 1; } return count; } /* Algorithms for different cases of string replacement */ /* len(self)>=1, from="", len(to)>=1, maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_interleave(PyBytesObject *self, const char *to_s, Py_ssize_t to_len, Py_ssize_t maxcount) { char *self_s, *result_s; Py_ssize_t self_len, result_len; Py_ssize_t count, i; PyBytesObject *result; self_len = PyBytes_GET_SIZE(self); /* 1 at the end plus 1 after every character; count = min(maxcount, self_len + 1) */ if (maxcount <= self_len) count = maxcount; else /* Can't overflow: self_len + 1 <= maxcount <= PY_SSIZE_T_MAX. */ count = self_len + 1; /* Check for overflow */ /* result_len = count * to_len + self_len; */ assert(count > 0); if (to_len > (PY_SSIZE_T_MAX - self_len) / count) { PyErr_SetString(PyExc_OverflowError, "replacement bytes are too long"); return NULL; } result_len = count * to_len + self_len; if (! (result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, result_len)) ) return NULL; self_s = PyBytes_AS_STRING(self); result_s = PyBytes_AS_STRING(result); /* TODO: special case single character, which doesn't need memcpy */ /* Lay the first one down (guaranteed this will occur) */ Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; count -= 1; for (i=0; i<count; i++) { *result_s++ = *self_s++; Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; } /* Copy the rest of the original string */ Py_MEMCPY(result_s, self_s, self_len-i); return result; } /* Special case for deleting a single character */ /* len(self)>=1, len(from)==1, to="", maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_delete_single_character(PyBytesObject *self, char from_c, Py_ssize_t maxcount) { char *self_s, *result_s; char *start, *next, *end; Py_ssize_t self_len, result_len; Py_ssize_t count; PyBytesObject *result; self_len = PyBytes_GET_SIZE(self); self_s = PyBytes_AS_STRING(self); count = countchar(self_s, self_len, from_c, maxcount); if (count == 0) { return return_self(self); } result_len = self_len - count; /* from_len == 1 */ assert(result_len>=0); if ( (result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, result_len)) == NULL) return NULL; result_s = PyBytes_AS_STRING(result); start = self_s; end = self_s + self_len; while (count-- > 0) { next = findchar(start, end-start, from_c); if (next == NULL) break; Py_MEMCPY(result_s, start, next-start); result_s += (next-start); start = next+1; } Py_MEMCPY(result_s, start, end-start); return result; } /* len(self)>=1, len(from)>=2, to="", maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_delete_substring(PyBytesObject *self, const char *from_s, Py_ssize_t from_len, Py_ssize_t maxcount) { char *self_s, *result_s; char *start, *next, *end; Py_ssize_t self_len, result_len; Py_ssize_t count, offset; PyBytesObject *result; self_len = PyBytes_GET_SIZE(self); self_s = PyBytes_AS_STRING(self); count = stringlib_count(self_s, self_len, from_s, from_len, maxcount); if (count == 0) { /* no matches */ return return_self(self); } result_len = self_len - (count * from_len); assert (result_len>=0); if ( (result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, result_len)) == NULL ) return NULL; result_s = PyBytes_AS_STRING(result); start = self_s; end = self_s + self_len; while (count-- > 0) { offset = stringlib_find(start, end-start, from_s, from_len, 0); if (offset == -1) break; next = start + offset; Py_MEMCPY(result_s, start, next-start); result_s += (next-start); start = next+from_len; } Py_MEMCPY(result_s, start, end-start); return result; } /* len(self)>=1, len(from)==len(to)==1, maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_single_character_in_place(PyBytesObject *self, char from_c, char to_c, Py_ssize_t maxcount) { char *self_s, *result_s, *start, *end, *next; Py_ssize_t self_len; PyBytesObject *result; /* The result string will be the same size */ self_s = PyBytes_AS_STRING(self); self_len = PyBytes_GET_SIZE(self); next = findchar(self_s, self_len, from_c); if (next == NULL) { /* No matches; return the original string */ return return_self(self); } /* Need to make a new string */ result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, self_len); if (result == NULL) return NULL; result_s = PyBytes_AS_STRING(result); Py_MEMCPY(result_s, self_s, self_len); /* change everything in-place, starting with this one */ start = result_s + (next-self_s); *start = to_c; start++; end = result_s + self_len; while (--maxcount > 0) { next = findchar(start, end-start, from_c); if (next == NULL) break; *next = to_c; start = next+1; } return result; } /* len(self)>=1, len(from)==len(to)>=2, maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_substring_in_place(PyBytesObject *self, const char *from_s, Py_ssize_t from_len, const char *to_s, Py_ssize_t to_len, Py_ssize_t maxcount) { char *result_s, *start, *end; char *self_s; Py_ssize_t self_len, offset; PyBytesObject *result; /* The result string will be the same size */ self_s = PyBytes_AS_STRING(self); self_len = PyBytes_GET_SIZE(self); offset = stringlib_find(self_s, self_len, from_s, from_len, 0); if (offset == -1) { /* No matches; return the original string */ return return_self(self); } /* Need to make a new string */ result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, self_len); if (result == NULL) return NULL; result_s = PyBytes_AS_STRING(result); Py_MEMCPY(result_s, self_s, self_len); /* change everything in-place, starting with this one */ start = result_s + offset; Py_MEMCPY(start, to_s, from_len); start += from_len; end = result_s + self_len; while ( --maxcount > 0) { offset = stringlib_find(start, end-start, from_s, from_len, 0); if (offset==-1) break; Py_MEMCPY(start+offset, to_s, from_len); start += offset+from_len; } return result; } /* len(self)>=1, len(from)==1, len(to)>=2, maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_single_character(PyBytesObject *self, char from_c, const char *to_s, Py_ssize_t to_len, Py_ssize_t maxcount) { char *self_s, *result_s; char *start, *next, *end; Py_ssize_t self_len, result_len; Py_ssize_t count; PyBytesObject *result; self_s = PyBytes_AS_STRING(self); self_len = PyBytes_GET_SIZE(self); count = countchar(self_s, self_len, from_c, maxcount); if (count == 0) { /* no matches, return unchanged */ return return_self(self); } /* use the difference between current and new, hence the "-1" */ /* result_len = self_len + count * (to_len-1) */ assert(count > 0); if (to_len - 1 > (PY_SSIZE_T_MAX - self_len) / count) { PyErr_SetString(PyExc_OverflowError, "replacement bytes are too long"); return NULL; } result_len = self_len + count * (to_len - 1); if ( (result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, result_len)) == NULL) return NULL; result_s = PyBytes_AS_STRING(result); start = self_s; end = self_s + self_len; while (count-- > 0) { next = findchar(start, end-start, from_c); if (next == NULL) break; if (next == start) { /* replace with the 'to' */ Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; start += 1; } else { /* copy the unchanged old then the 'to' */ Py_MEMCPY(result_s, start, next-start); result_s += (next-start); Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; start = next+1; } } /* Copy the remainder of the remaining string */ Py_MEMCPY(result_s, start, end-start); return result; } /* len(self)>=1, len(from)>=2, len(to)>=2, maxcount>=1 */ Py_LOCAL(PyBytesObject *) replace_substring(PyBytesObject *self, const char *from_s, Py_ssize_t from_len, const char *to_s, Py_ssize_t to_len, Py_ssize_t maxcount) { char *self_s, *result_s; char *start, *next, *end; Py_ssize_t self_len, result_len; Py_ssize_t count, offset; PyBytesObject *result; self_s = PyBytes_AS_STRING(self); self_len = PyBytes_GET_SIZE(self); count = stringlib_count(self_s, self_len, from_s, from_len, maxcount); if (count == 0) { /* no matches, return unchanged */ return return_self(self); } /* Check for overflow */ /* result_len = self_len + count * (to_len-from_len) */ assert(count > 0); if (to_len - from_len > (PY_SSIZE_T_MAX - self_len) / count) { PyErr_SetString(PyExc_OverflowError, "replacement bytes are too long"); return NULL; } result_len = self_len + count * (to_len-from_len); if ( (result = (PyBytesObject *) PyBytes_FromStringAndSize(NULL, result_len)) == NULL) return NULL; result_s = PyBytes_AS_STRING(result); start = self_s; end = self_s + self_len; while (count-- > 0) { offset = stringlib_find(start, end-start, from_s, from_len, 0); if (offset == -1) break; next = start+offset; if (next == start) { /* replace with the 'to' */ Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; start += from_len; } else { /* copy the unchanged old then the 'to' */ Py_MEMCPY(result_s, start, next-start); result_s += (next-start); Py_MEMCPY(result_s, to_s, to_len); result_s += to_len; start = next+from_len; } } /* Copy the remainder of the remaining string */ Py_MEMCPY(result_s, start, end-start); return result; } Py_LOCAL(PyBytesObject *) replace(PyBytesObject *self, const char *from_s, Py_ssize_t from_len, const char *to_s, Py_ssize_t to_len, Py_ssize_t maxcount) { if (maxcount < 0) { maxcount = PY_SSIZE_T_MAX; } else if (maxcount == 0 || PyBytes_GET_SIZE(self) == 0) { /* nothing to do; return the original string */ return return_self(self); } if (maxcount == 0 || (from_len == 0 && to_len == 0)) { /* nothing to do; return the original string */ return return_self(self); } /* Handle zero-length special cases */ if (from_len == 0) { /* insert the 'to' string everywhere. */ /* >>> "Python".replace("", ".") */ /* '.P.y.t.h.o.n.' */ return replace_interleave(self, to_s, to_len, maxcount); } /* Except for "".replace("", "A") == "A" there is no way beyond this */ /* point for an empty self string to generate a non-empty string */ /* Special case so the remaining code always gets a non-empty string */ if (PyBytes_GET_SIZE(self) == 0) { return return_self(self); } if (to_len == 0) { /* delete all occurrences of 'from' string */ if (from_len == 1) { return replace_delete_single_character( self, from_s[0], maxcount); } else { return replace_delete_substring(self, from_s, from_len, maxcount); } } /* Handle special case where both strings have the same length */ if (from_len == to_len) { if (from_len == 1) { return replace_single_character_in_place( self, from_s[0], to_s[0], maxcount); } else { return replace_substring_in_place( self, from_s, from_len, to_s, to_len, maxcount); } } /* Otherwise use the more generic algorithms */ if (from_len == 1) { return replace_single_character(self, from_s[0], to_s, to_len, maxcount); } else { /* len('from')>=2, len('to')>=1 */ return replace_substring(self, from_s, from_len, to_s, to_len, maxcount); } } PyDoc_STRVAR(replace__doc__, "B.replace(old, new[, count]) -> bytes\n\ \n\ Return a copy of B with all occurrences of subsection\n\ old replaced by new. If the optional argument count is\n\ given, only first count occurances are replaced."); static PyObject * bytes_replace(PyBytesObject *self, PyObject *args) { Py_ssize_t count = -1; PyObject *from, *to; const char *from_s, *to_s; Py_ssize_t from_len, to_len; if (!PyArg_ParseTuple(args, "OO|n:replace", &from, &to, &count)) return NULL; if (PyBytes_Check(from)) { from_s = PyBytes_AS_STRING(from); from_len = PyBytes_GET_SIZE(from); } else if (PyObject_AsCharBuffer(from, &from_s, &from_len)) return NULL; if (PyBytes_Check(to)) { to_s = PyBytes_AS_STRING(to); to_len = PyBytes_GET_SIZE(to); } else if (PyObject_AsCharBuffer(to, &to_s, &to_len)) return NULL; return (PyObject *)replace((PyBytesObject *) self, from_s, from_len, to_s, to_len, count); } /** End DALKE **/ /* Matches the end (direction >= 0) or start (direction < 0) of self * against substr, using the start and end arguments. Returns * -1 on error, 0 if not found and 1 if found. */ Py_LOCAL(int) _bytes_tailmatch(PyBytesObject *self, PyObject *substr, Py_ssize_t start, Py_ssize_t end, int direction) { Py_ssize_t len = PyBytes_GET_SIZE(self); Py_ssize_t slen; const char* sub; const char* str; if (PyBytes_Check(substr)) { sub = PyBytes_AS_STRING(substr); slen = PyBytes_GET_SIZE(substr); } else if (PyObject_AsCharBuffer(substr, &sub, &slen)) return -1; str = PyBytes_AS_STRING(self); ADJUST_INDICES(start, end, len); if (direction < 0) { /* startswith */ if (start+slen > len) return 0; } else { /* endswith */ if (end-start < slen || start > len) return 0; if (end-slen > start) start = end - slen; } if (end-start >= slen) return ! memcmp(str+start, sub, slen); return 0; } PyDoc_STRVAR(startswith__doc__, "B.startswith(prefix[, start[, end]]) -> bool\n\ \n\ Return True if B starts with the specified prefix, False otherwise.\n\ With optional start, test B beginning at that position.\n\ With optional end, stop comparing B at that position.\n\ prefix can also be a tuple of bytes to try."); static PyObject * bytes_startswith(PyBytesObject *self, PyObject *args) { Py_ssize_t start = 0; Py_ssize_t end = PY_SSIZE_T_MAX; PyObject *subobj; int result; if (!stringlib_parse_args_finds("startswith", args, &subobj, &start, &end)) return NULL; if (PyTuple_Check(subobj)) { Py_ssize_t i; for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) { result = _bytes_tailmatch(self, PyTuple_GET_ITEM(subobj, i), start, end, -1); if (result == -1) return NULL; else if (result) { Py_RETURN_TRUE; } } Py_RETURN_FALSE; } result = _bytes_tailmatch(self, subobj, start, end, -1); if (result == -1) { if (PyErr_ExceptionMatches(PyExc_TypeError)) PyErr_Format(PyExc_TypeError, "startswith first arg must be bytes " "or a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name); return NULL; } else return PyBool_FromLong(result); } PyDoc_STRVAR(endswith__doc__, "B.endswith(suffix[, start[, end]]) -> bool\n\ \n\ Return True if B ends with the specified suffix, False otherwise.\n\ With optional start, test B beginning at that position.\n\ With optional end, stop comparing B at that position.\n\ suffix can also be a tuple of bytes to try."); static PyObject * bytes_endswith(PyBytesObject *self, PyObject *args) { Py_ssize_t start = 0; Py_ssize_t end = PY_SSIZE_T_MAX; PyObject *subobj; int result; if (!stringlib_parse_args_finds("endswith", args, &subobj, &start, &end)) return NULL; if (PyTuple_Check(subobj)) { Py_ssize_t i; for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) { result = _bytes_tailmatch(self, PyTuple_GET_ITEM(subobj, i), start, end, +1); if (result == -1) return NULL; else if (result) { Py_RETURN_TRUE; } } Py_RETURN_FALSE; } result = _bytes_tailmatch(self, subobj, start, end, +1); if (result == -1) { if (PyErr_ExceptionMatches(PyExc_TypeError)) PyErr_Format(PyExc_TypeError, "endswith first arg must be bytes or " "a tuple of bytes, not %s", Py_TYPE(subobj)->tp_name); return NULL; } else return PyBool_FromLong(result); } PyDoc_STRVAR(decode__doc__, "B.decode(encoding='utf-8', errors='strict') -> str\n\ \n\ Decode B using the codec registered for encoding. Default encoding\n\ is 'utf-8'. errors may be given to set a different error\n\ handling scheme. Default is 'strict' meaning that encoding errors raise\n\ a UnicodeDecodeError. Other possible values are 'ignore' and 'replace'\n\ as well as any other name registerd with codecs.register_error that is\n\ able to handle UnicodeDecodeErrors."); static PyObject * bytes_decode(PyObject *self, PyObject *args, PyObject *kwargs) { const char *encoding = NULL; const char *errors = NULL; static char *kwlist[] = {"encoding", "errors", 0}; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss:decode", kwlist, &encoding, &errors)) return NULL; if (encoding == NULL) encoding = PyUnicode_GetDefaultEncoding(); return PyUnicode_FromEncodedObject(self, encoding, errors); } PyDoc_STRVAR(splitlines__doc__, "B.splitlines([keepends]) -> list of lines\n\ \n\ Return a list of the lines in B, breaking at line boundaries.\n\ Line breaks are not included in the resulting list unless keepends\n\ is given and true."); static PyObject* bytes_splitlines(PyObject *self, PyObject *args) { int keepends = 0; if (!PyArg_ParseTuple(args, "|i:splitlines", &keepends)) return NULL; return stringlib_splitlines( (PyObject*) self, PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self), keepends ); } PyDoc_STRVAR(fromhex_doc, "bytes.fromhex(string) -> bytes\n\ \n\ Create a bytes object from a string of hexadecimal numbers.\n\ Spaces between two numbers are accepted.\n\ Example: bytes.fromhex('B9 01EF') -> b'\\xb9\\x01\\xef'."); static int hex_digit_to_int(Py_UNICODE c) { if (c >= 128) return -1; if (Py_ISDIGIT(c)) return c - '0'; else { if (Py_ISUPPER(c)) c = Py_TOLOWER(c); if (c >= 'a' && c <= 'f') return c - 'a' + 10; } return -1; } static PyObject * bytes_fromhex(PyObject *cls, PyObject *args) { PyObject *newstring, *hexobj; char *buf; Py_UNICODE *hex; Py_ssize_t hexlen, byteslen, i, j; int top, bot; if (!PyArg_ParseTuple(args, "U:fromhex", &hexobj)) return NULL; assert(PyUnicode_Check(hexobj)); hexlen = PyUnicode_GET_SIZE(hexobj); hex = PyUnicode_AS_UNICODE(hexobj); byteslen = hexlen/2; /* This overestimates if there are spaces */ newstring = PyBytes_FromStringAndSize(NULL, byteslen); if (!newstring) return NULL; buf = PyBytes_AS_STRING(newstring); for (i = j = 0; i < hexlen; i += 2) { /* skip over spaces in the input */ while (hex[i] == ' ') i++; if (i >= hexlen) break; top = hex_digit_to_int(hex[i]); bot = hex_digit_to_int(hex[i+1]); if (top == -1 || bot == -1) { PyErr_Format(PyExc_ValueError, "non-hexadecimal number found in " "fromhex() arg at position %zd", i); goto error; } buf[j++] = (top << 4) + bot; } if (j != byteslen && _PyBytes_Resize(&newstring, j) < 0) goto error; return newstring; error: Py_XDECREF(newstring); return NULL; } PyDoc_STRVAR(sizeof__doc__, "B.__sizeof__() -> size of B in memory, in bytes"); static PyObject * bytes_sizeof(PyBytesObject *v) { Py_ssize_t res; res = PyBytesObject_SIZE + Py_SIZE(v) * Py_TYPE(v)->tp_itemsize; return PyLong_FromSsize_t(res); } static PyObject * bytes_getnewargs(PyBytesObject *v) { return Py_BuildValue("(y#)", v->ob_sval, Py_SIZE(v)); } static PyMethodDef bytes_methods[] = { {"__getnewargs__", (PyCFunction)bytes_getnewargs, METH_NOARGS}, {"capitalize", (PyCFunction)stringlib_capitalize, METH_NOARGS, _Py_capitalize__doc__}, {"center", (PyCFunction)stringlib_center, METH_VARARGS, center__doc__}, {"count", (PyCFunction)bytes_count, METH_VARARGS, count__doc__}, {"decode", (PyCFunction)bytes_decode, METH_VARARGS | METH_KEYWORDS, decode__doc__}, {"endswith", (PyCFunction)bytes_endswith, METH_VARARGS, endswith__doc__}, {"expandtabs", (PyCFunction)stringlib_expandtabs, METH_VARARGS, expandtabs__doc__}, {"find", (PyCFunction)bytes_find, METH_VARARGS, find__doc__}, {"fromhex", (PyCFunction)bytes_fromhex, METH_VARARGS|METH_CLASS, fromhex_doc}, {"index", (PyCFunction)bytes_index, METH_VARARGS, index__doc__}, {"isalnum", (PyCFunction)stringlib_isalnum, METH_NOARGS, _Py_isalnum__doc__}, {"isalpha", (PyCFunction)stringlib_isalpha, METH_NOARGS, _Py_isalpha__doc__}, {"isdigit", (PyCFunction)stringlib_isdigit, METH_NOARGS, _Py_isdigit__doc__}, {"islower", (PyCFunction)stringlib_islower, METH_NOARGS, _Py_islower__doc__}, {"isspace", (PyCFunction)stringlib_isspace, METH_NOARGS, _Py_isspace__doc__}, {"istitle", (PyCFunction)stringlib_istitle, METH_NOARGS, _Py_istitle__doc__}, {"isupper", (PyCFunction)stringlib_isupper, METH_NOARGS, _Py_isupper__doc__}, {"join", (PyCFunction)bytes_join, METH_O, join__doc__}, {"ljust", (PyCFunction)stringlib_ljust, METH_VARARGS, ljust__doc__}, {"lower", (PyCFunction)stringlib_lower, METH_NOARGS, _Py_lower__doc__}, {"lstrip", (PyCFunction)bytes_lstrip, METH_VARARGS, lstrip__doc__}, {"maketrans", (PyCFunction)bytes_maketrans, METH_VARARGS|METH_STATIC, _Py_maketrans__doc__}, {"partition", (PyCFunction)bytes_partition, METH_O, partition__doc__}, {"replace", (PyCFunction)bytes_replace, METH_VARARGS, replace__doc__}, {"rfind", (PyCFunction)bytes_rfind, METH_VARARGS, rfind__doc__}, {"rindex", (PyCFunction)bytes_rindex, METH_VARARGS, rindex__doc__}, {"rjust", (PyCFunction)stringlib_rjust, METH_VARARGS, rjust__doc__}, {"rpartition", (PyCFunction)bytes_rpartition, METH_O, rpartition__doc__}, {"rsplit", (PyCFunction)bytes_rsplit, METH_VARARGS, rsplit__doc__}, {"rstrip", (PyCFunction)bytes_rstrip, METH_VARARGS, rstrip__doc__}, {"split", (PyCFunction)bytes_split, METH_VARARGS, split__doc__}, {"splitlines", (PyCFunction)bytes_splitlines, METH_VARARGS, splitlines__doc__}, {"startswith", (PyCFunction)bytes_startswith, METH_VARARGS, startswith__doc__}, {"strip", (PyCFunction)bytes_strip, METH_VARARGS, strip__doc__}, {"swapcase", (PyCFunction)stringlib_swapcase, METH_NOARGS, _Py_swapcase__doc__}, {"title", (PyCFunction)stringlib_title, METH_NOARGS, _Py_title__doc__}, {"translate", (PyCFunction)bytes_translate, METH_VARARGS, translate__doc__}, {"upper", (PyCFunction)stringlib_upper, METH_NOARGS, _Py_upper__doc__}, {"zfill", (PyCFunction)stringlib_zfill, METH_VARARGS, zfill__doc__}, {"__sizeof__", (PyCFunction)bytes_sizeof, METH_NOARGS, sizeof__doc__}, {NULL, NULL} /* sentinel */ }; static PyObject * str_subtype_new(PyTypeObject *type, PyObject *args, PyObject *kwds); static PyObject * bytes_new(PyTypeObject *type, PyObject *args, PyObject *kwds) { PyObject *x = NULL; const char *encoding = NULL; const char *errors = NULL; PyObject *new = NULL; Py_ssize_t size; static char *kwlist[] = {"source", "encoding", "errors", 0}; if (type != &PyBytes_Type) return str_subtype_new(type, args, kwds); if (!PyArg_ParseTupleAndKeywords(args, kwds, "|Oss:bytes", kwlist, &x, &encoding, &errors)) return NULL; if (x == NULL) { if (encoding != NULL || errors != NULL) { PyErr_SetString(PyExc_TypeError, "encoding or errors without sequence " "argument"); return NULL; } return PyBytes_FromString(""); } if (PyUnicode_Check(x)) { /* Encode via the codec registry */ if (encoding == NULL) { PyErr_SetString(PyExc_TypeError, "string argument without an encoding"); return NULL; } new = PyUnicode_AsEncodedString(x, encoding, errors); if (new == NULL) return NULL; assert(PyBytes_Check(new)); return new; } /* Is it an integer? */ size = PyNumber_AsSsize_t(x, PyExc_OverflowError); if (size == -1 && PyErr_Occurred()) { if (PyErr_ExceptionMatches(PyExc_OverflowError)) return NULL; PyErr_Clear(); } else if (size < 0) { PyErr_SetString(PyExc_ValueError, "negative count"); return NULL; } else { new = PyBytes_FromStringAndSize(NULL, size); if (new == NULL) { return NULL; } if (size > 0) { memset(((PyBytesObject*)new)->ob_sval, 0, size); } return new; } /* If it's not unicode, there can't be encoding or errors */ if (encoding != NULL || errors != NULL) { PyErr_SetString(PyExc_TypeError, "encoding or errors without a string argument"); return NULL; } return PyObject_Bytes(x); } PyObject * PyBytes_FromObject(PyObject *x) { PyObject *new, *it; Py_ssize_t i, size; if (x == NULL) { PyErr_BadInternalCall(); return NULL; } /* Use the modern buffer interface */ if (PyObject_CheckBuffer(x)) { Py_buffer view; if (PyObject_GetBuffer(x, &view, PyBUF_FULL_RO) < 0) return NULL; new = PyBytes_FromStringAndSize(NULL, view.len); if (!new) goto fail; /* XXX(brett.cannon): Better way to get to internal buffer? */ if (PyBuffer_ToContiguous(((PyBytesObject *)new)->ob_sval, &view, view.len, 'C') < 0) goto fail; PyBuffer_Release(&view); return new; fail: Py_XDECREF(new); PyBuffer_Release(&view); return NULL; } if (PyUnicode_Check(x)) { PyErr_SetString(PyExc_TypeError, "cannot convert unicode object to bytes"); return NULL; } if (PyList_CheckExact(x)) { new = PyBytes_FromStringAndSize(NULL, Py_SIZE(x)); if (new == NULL) return NULL; for (i = 0; i < Py_SIZE(x); i++) { Py_ssize_t value = PyNumber_AsSsize_t( PyList_GET_ITEM(x, i), PyExc_ValueError); if (value == -1 && PyErr_Occurred()) { Py_DECREF(new); return NULL; } if (value < 0 || value >= 256) { PyErr_SetString(PyExc_ValueError, "bytes must be in range(0, 256)"); Py_DECREF(new); return NULL; } ((PyBytesObject *)new)->ob_sval[i] = (char) value; } return new; } if (PyTuple_CheckExact(x)) { new = PyBytes_FromStringAndSize(NULL, Py_SIZE(x)); if (new == NULL) return NULL; for (i = 0; i < Py_SIZE(x); i++) { Py_ssize_t value = PyNumber_AsSsize_t( PyTuple_GET_ITEM(x, i), PyExc_ValueError); if (value == -1 && PyErr_Occurred()) { Py_DECREF(new); return NULL; } if (value < 0 || value >= 256) { PyErr_SetString(PyExc_ValueError, "bytes must be in range(0, 256)"); Py_DECREF(new); return NULL; } ((PyBytesObject *)new)->ob_sval[i] = (char) value; } return new; } /* For iterator version, create a string object and resize as needed */ size = _PyObject_LengthHint(x, 64); if (size == -1 && PyErr_Occurred()) return NULL; /* Allocate an extra byte to prevent PyBytes_FromStringAndSize() from returning a shared empty bytes string. This required because we want to call _PyBytes_Resize() the returned object, which we can only do on bytes objects with refcount == 1. */ size += 1; new = PyBytes_FromStringAndSize(NULL, size); if (new == NULL) return NULL; /* Get the iterator */ it = PyObject_GetIter(x); if (it == NULL) goto error; /* Run the iterator to exhaustion */ for (i = 0; ; i++) { PyObject *item; Py_ssize_t value; /* Get the next item */ item = PyIter_Next(it); if (item == NULL) { if (PyErr_Occurred()) goto error; break; } /* Interpret it as an int (__index__) */ value = PyNumber_AsSsize_t(item, PyExc_ValueError); Py_DECREF(item); if (value == -1 && PyErr_Occurred()) goto error; /* Range check */ if (value < 0 || value >= 256) { PyErr_SetString(PyExc_ValueError, "bytes must be in range(0, 256)"); goto error; } /* Append the byte */ if (i >= size) { size = 2 * size + 1; if (_PyBytes_Resize(&new, size) < 0) goto error; } ((PyBytesObject *)new)->ob_sval[i] = (char) value; } _PyBytes_Resize(&new, i); /* Clean up and return success */ Py_DECREF(it); return new; error: /* Error handling when new != NULL */ Py_XDECREF(it); Py_DECREF(new); return NULL; } static PyObject * str_subtype_new(PyTypeObject *type, PyObject *args, PyObject *kwds) { PyObject *tmp, *pnew; Py_ssize_t n; assert(PyType_IsSubtype(type, &PyBytes_Type)); tmp = bytes_new(&PyBytes_Type, args, kwds); if (tmp == NULL) return NULL; assert(PyBytes_CheckExact(tmp)); n = PyBytes_GET_SIZE(tmp); pnew = type->tp_alloc(type, n); if (pnew != NULL) { Py_MEMCPY(PyBytes_AS_STRING(pnew), PyBytes_AS_STRING(tmp), n+1); ((PyBytesObject *)pnew)->ob_shash = ((PyBytesObject *)tmp)->ob_shash; } Py_DECREF(tmp); return pnew; } PyDoc_STRVAR(bytes_doc, "bytes(iterable_of_ints) -> bytes\n\ bytes(string, encoding[, errors]) -> bytes\n\ bytes(bytes_or_buffer) -> immutable copy of bytes_or_buffer\n\ bytes(int) -> bytes object of size given by the parameter initialized with null bytes\n\ bytes() -> empty bytes object\n\ \n\ Construct an immutable array of bytes from:\n\ - an iterable yielding integers in range(256)\n\ - a text string encoded using the specified encoding\n\ - any object implementing the buffer API.\n\ - an integer"); static PyObject *bytes_iter(PyObject *seq); PyTypeObject PyBytes_Type = { PyVarObject_HEAD_INIT(&PyType_Type, 0) "bytes", PyBytesObject_SIZE, sizeof(char), bytes_dealloc, /* tp_dealloc */ 0, /* tp_print */ 0, /* tp_getattr */ 0, /* tp_setattr */ 0, /* tp_reserved */ (reprfunc)bytes_repr, /* tp_repr */ 0, /* tp_as_number */ &bytes_as_sequence, /* tp_as_sequence */ &bytes_as_mapping, /* tp_as_mapping */ (hashfunc)bytes_hash, /* tp_hash */ 0, /* tp_call */ bytes_str, /* tp_str */ PyObject_GenericGetAttr, /* tp_getattro */ 0, /* tp_setattro */ &bytes_as_buffer, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_BYTES_SUBCLASS, /* tp_flags */ bytes_doc, /* tp_doc */ 0, /* tp_traverse */ 0, /* tp_clear */ (richcmpfunc)bytes_richcompare, /* tp_richcompare */ 0, /* tp_weaklistoffset */ bytes_iter, /* tp_iter */ 0, /* tp_iternext */ bytes_methods, /* tp_methods */ 0, /* tp_members */ 0, /* tp_getset */ &PyBaseObject_Type, /* tp_base */ 0, /* tp_dict */ 0, /* tp_descr_get */ 0, /* tp_descr_set */ 0, /* tp_dictoffset */ 0, /* tp_init */ 0, /* tp_alloc */ bytes_new, /* tp_new */ PyObject_Del, /* tp_free */ }; void PyBytes_Concat(register PyObject **pv, register PyObject *w) { register PyObject *v; assert(pv != NULL); if (*pv == NULL) return; if (w == NULL) { Py_DECREF(*pv); *pv = NULL; return; } v = bytes_concat(*pv, w); Py_DECREF(*pv); *pv = v; } void PyBytes_ConcatAndDel(register PyObject **pv, register PyObject *w) { PyBytes_Concat(pv, w); Py_XDECREF(w); } /* The following function breaks the notion that strings are immutable: it changes the size of a string. We get away with this only if there is only one module referencing the object. You can also think of it as creating a new string object and destroying the old one, only more efficiently. In any case, don't use this if the string may already be known to some other part of the code... Note that if there's not enough memory to resize the string, the original string object at *pv is deallocated, *pv is set to NULL, an "out of memory" exception is set, and -1 is returned. Else (on success) 0 is returned, and the value in *pv may or may not be the same as on input. As always, an extra byte is allocated for a trailing \0 byte (newsize does *not* include that), and a trailing \0 byte is stored. */ int _PyBytes_Resize(PyObject **pv, Py_ssize_t newsize) { register PyObject *v; register PyBytesObject *sv; v = *pv; if (!PyBytes_Check(v) || Py_REFCNT(v) != 1 || newsize < 0) { *pv = 0; Py_DECREF(v); PyErr_BadInternalCall(); return -1; } /* XXX UNREF/NEWREF interface should be more symmetrical */ _Py_DEC_REFTOTAL; _Py_ForgetReference(v); *pv = (PyObject *) PyObject_REALLOC((char *)v, PyBytesObject_SIZE + newsize); if (*pv == NULL) { PyObject_Del(v); PyErr_NoMemory(); return -1; } _Py_NewReference(*pv); sv = (PyBytesObject *) *pv; Py_SIZE(sv) = newsize; sv->ob_sval[newsize] = '\0'; sv->ob_shash = -1; /* invalidate cached hash value */ return 0; } /* _PyBytes_FormatLong emulates the format codes d, u, o, x and X, and * the F_ALT flag, for Python's long (unbounded) ints. It's not used for * Python's regular ints. * Return value: a new PyBytes*, or NULL if error. * . *pbuf is set to point into it, * *plen set to the # of chars following that. * Caller must decref it when done using pbuf. * The string starting at *pbuf is of the form * "-"? ("0x" | "0X")? digit+ * "0x"/"0X" are present only for x and X conversions, with F_ALT * set in flags. The case of hex digits will be correct, * There will be at least prec digits, zero-filled on the left if * necessary to get that many. * val object to be converted * flags bitmask of format flags; only F_ALT is looked at * prec minimum number of digits; 0-fill on left if needed * type a character in [duoxX]; u acts the same as d * * CAUTION: o, x and X conversions on regular ints can never * produce a '-' sign, but can for Python's unbounded ints. */ PyObject* _PyBytes_FormatLong(PyObject *val, int flags, int prec, int type, char **pbuf, int *plen) { PyObject *result = NULL; char *buf; Py_ssize_t i; int sign; /* 1 if '-', else 0 */ int len; /* number of characters */ Py_ssize_t llen; int numdigits; /* len == numnondigits + numdigits */ int numnondigits = 0; /* Avoid exceeding SSIZE_T_MAX */ if (prec > INT_MAX-3) { PyErr_SetString(PyExc_OverflowError, "precision too large"); return NULL; } switch (type) { case 'd': case 'u': /* Special-case boolean: we want 0/1 */ if (PyBool_Check(val)) result = PyNumber_ToBase(val, 10); else result = Py_TYPE(val)->tp_str(val); break; case 'o': numnondigits = 2; result = PyNumber_ToBase(val, 8); break; case 'x': case 'X': numnondigits = 2; result = PyNumber_ToBase(val, 16); break; default: assert(!"'type' not in [duoxX]"); } if (!result) return NULL; buf = _PyUnicode_AsString(result); if (!buf) { Py_DECREF(result); return NULL; } /* To modify the string in-place, there can only be one reference. */ if (Py_REFCNT(result) != 1) { PyErr_BadInternalCall(); return NULL; } llen = PyUnicode_GetSize(result); if (llen > INT_MAX) { PyErr_SetString(PyExc_ValueError, "string too large in _PyBytes_FormatLong"); return NULL; } len = (int)llen; if (buf[len-1] == 'L') { --len; buf[len] = '\0'; } sign = buf[0] == '-'; numnondigits += sign; numdigits = len - numnondigits; assert(numdigits > 0); /* Get rid of base marker unless F_ALT */ if (((flags & F_ALT) == 0 && (type == 'o' || type == 'x' || type == 'X'))) { assert(buf[sign] == '0'); assert(buf[sign+1] == 'x' || buf[sign+1] == 'X' || buf[sign+1] == 'o'); numnondigits -= 2; buf += 2; len -= 2; if (sign) buf[0] = '-'; assert(len == numnondigits + numdigits); assert(numdigits > 0); } /* Fill with leading zeroes to meet minimum width. */ if (prec > numdigits) { PyObject *r1 = PyBytes_FromStringAndSize(NULL, numnondigits + prec); char *b1; if (!r1) { Py_DECREF(result); return NULL; } b1 = PyBytes_AS_STRING(r1); for (i = 0; i < numnondigits; ++i) *b1++ = *buf++; for (i = 0; i < prec - numdigits; i++) *b1++ = '0'; for (i = 0; i < numdigits; i++) *b1++ = *buf++; *b1 = '\0'; Py_DECREF(result); result = r1; buf = PyBytes_AS_STRING(result); len = numnondigits + prec; } /* Fix up case for hex conversions. */ if (type == 'X') { /* Need to convert all lower case letters to upper case. and need to convert 0x to 0X (and -0x to -0X). */ for (i = 0; i < len; i++) if (buf[i] >= 'a' && buf[i] <= 'x') buf[i] -= 'a'-'A'; } *pbuf = buf; *plen = len; return result; } void PyBytes_Fini(void) { int i; for (i = 0; i < UCHAR_MAX + 1; i++) { Py_XDECREF(characters[i]); characters[i] = NULL; } Py_XDECREF(nullstring); nullstring = NULL; } /*********************** Bytes Iterator ****************************/ typedef struct { PyObject_HEAD Py_ssize_t it_index; PyBytesObject *it_seq; /* Set to NULL when iterator is exhausted */ } striterobject; static void striter_dealloc(striterobject *it) { _PyObject_GC_UNTRACK(it); Py_XDECREF(it->it_seq); PyObject_GC_Del(it); } static int striter_traverse(striterobject *it, visitproc visit, void *arg) { Py_VISIT(it->it_seq); return 0; } static PyObject * striter_next(striterobject *it) { PyBytesObject *seq; PyObject *item; assert(it != NULL); seq = it->it_seq; if (seq == NULL) return NULL; assert(PyBytes_Check(seq)); if (it->it_index < PyBytes_GET_SIZE(seq)) { item = PyLong_FromLong( (unsigned char)seq->ob_sval[it->it_index]); if (item != NULL) ++it->it_index; return item; } Py_DECREF(seq); it->it_seq = NULL; return NULL; } static PyObject * striter_len(striterobject *it) { Py_ssize_t len = 0; if (it->it_seq) len = PyBytes_GET_SIZE(it->it_seq) - it->it_index; return PyLong_FromSsize_t(len); } PyDoc_STRVAR(length_hint_doc, "Private method returning an estimate of len(list(it))."); static PyMethodDef striter_methods[] = { {"__length_hint__", (PyCFunction)striter_len, METH_NOARGS, length_hint_doc}, {NULL, NULL} /* sentinel */ }; PyTypeObject PyBytesIter_Type = { PyVarObject_HEAD_INIT(&PyType_Type, 0) "bytes_iterator", /* tp_name */ sizeof(striterobject), /* tp_basicsize */ 0, /* tp_itemsize */ /* methods */ (destructor)striter_dealloc, /* tp_dealloc */ 0, /* tp_print */ 0, /* tp_getattr */ 0, /* tp_setattr */ 0, /* tp_reserved */ 0, /* tp_repr */ 0, /* tp_as_number */ 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ 0, /* tp_hash */ 0, /* tp_call */ 0, /* tp_str */ PyObject_GenericGetAttr, /* tp_getattro */ 0, /* tp_setattro */ 0, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC,/* tp_flags */ 0, /* tp_doc */ (traverseproc)striter_traverse, /* tp_traverse */ 0, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ PyObject_SelfIter, /* tp_iter */ (iternextfunc)striter_next, /* tp_iternext */ striter_methods, /* tp_methods */ 0, }; static PyObject * bytes_iter(PyObject *seq) { striterobject *it; if (!PyBytes_Check(seq)) { PyErr_BadInternalCall(); return NULL; } it = PyObject_GC_New(striterobject, &PyBytesIter_Type); if (it == NULL) return NULL; it->it_index = 0; Py_INCREF(seq); it->it_seq = (PyBytesObject *)seq; _PyObject_GC_TRACK(it); return (PyObject *)it; }