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
|
/***********************************************************
Copyright 1991-1995 by Stichting Mathematisch Centrum, Amsterdam,
The Netherlands.
All Rights Reserved
Permission to use, copy, modify, and distribute this software and its
documentation for any purpose and without fee is hereby granted,
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in
supporting documentation, and that the names of Stichting Mathematisch
Centrum or CWI or Corporation for National Research Initiatives or
CNRI not be used in advertising or publicity pertaining to
distribution of the software without specific, written prior
permission.
While CWI is the initial source for this software, a modified version
is made available by the Corporation for National Research Initiatives
(CNRI) at the Internet address ftp://ftp.python.org.
STICHTING MATHEMATISCH CENTRUM AND CNRI DISCLAIM ALL WARRANTIES WITH
REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH
CENTRUM OR CNRI BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL
DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
******************************************************************/
/* strop module */
static char strop_module__doc__[] =
"Common string manipulations, optimized for speed.\n\
\n\
Always use \"import string\" rather than referencing\n\
this module directly.";
#include "Python.h"
#ifdef HAVE_LIMITS_H
#include <limits.h>
#else
#define INT_MAX 2147483647
#endif
#include <ctype.h>
/* XXX This file assumes that the <ctype.h> is*() functions
XXX are defined for all 8-bit characters! */
/* The lstrip(), rstrip() and strip() functions are implemented
in do_strip(), which uses an additional parameter to indicate what
type of strip should occur. */
#define LEFTSTRIP 0
#define RIGHTSTRIP 1
#define BOTHSTRIP 2
static PyObject *
split_whitespace(s, len, maxsplit)
char *s;
int len;
int maxsplit;
{
int i = 0, j, err;
int countsplit = 0;
PyObject* item;
PyObject *list = PyList_New(0);
if (list == NULL)
return NULL;
while (i < len) {
while (i < len && isspace(Py_CHARMASK(s[i]))) {
i = i+1;
}
j = i;
while (i < len && !isspace(Py_CHARMASK(s[i]))) {
i = i+1;
}
if (j < i) {
item = PyString_FromStringAndSize(s+j, (int)(i-j));
if (item == NULL)
goto finally;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto finally;
countsplit++;
while (i < len && isspace(Py_CHARMASK(s[i]))) {
i = i+1;
}
if (maxsplit && (countsplit >= maxsplit) && i < len) {
item = PyString_FromStringAndSize(
s+i, (int)(len - i));
if (item == NULL)
goto finally;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto finally;
i = len;
}
}
}
return list;
finally:
Py_DECREF(list);
return NULL;
}
static char splitfields__doc__[] =
"split(str [,sep [,maxsplit]]) -> list of strings\n\
splitfields(str [,sep [,maxsplit]]) -> list of strings\n\
\n\
Return a list of the words in the string s, using sep as the\n\
delimiter string. If maxsplit is nonzero, splits into at most\n\
maxsplit words If sep is not specified, any whitespace string\n\
is a separator. Maxsplit defaults to 0.\n\
\n\
(split and splitfields are synonymous)";
static PyObject *
strop_splitfields(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
int len, n, i, j, err;
int splitcount, maxsplit;
char *s, *sub;
PyObject *list, *item;
sub = NULL;
n = 0;
splitcount = 0;
maxsplit = 0;
if (!PyArg_ParseTuple(args, "s#|z#i", &s, &len, &sub, &n, &maxsplit))
return NULL;
if (sub == NULL)
return split_whitespace(s, len, maxsplit);
if (n == 0) {
PyErr_SetString(PyExc_ValueError, "empty separator");
return NULL;
}
list = PyList_New(0);
if (list == NULL)
return NULL;
i = j = 0;
while (i+n <= len) {
if (s[i] == sub[0] && (n == 1 || memcmp(s+i, sub, n) == 0)) {
item = PyString_FromStringAndSize(s+j, (int)(i-j));
if (item == NULL)
goto fail;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto fail;
i = j = i + n;
splitcount++;
if (maxsplit && (splitcount >= maxsplit))
break;
}
else
i++;
}
item = PyString_FromStringAndSize(s+j, (int)(len-j));
if (item == NULL)
goto fail;
err = PyList_Append(list, item);
Py_DECREF(item);
if (err < 0)
goto fail;
return list;
fail:
Py_DECREF(list);
return NULL;
}
static char joinfields__doc__[] =
"join(list [,sep]) -> string\n\
joinfields(list [,sep]) -> string\n\
\n\
Return a string composed of the words in list, with\n\
intervening occurences of sep. Sep defaults to a single\n\
space.\n\
\n\
(join and joinfields are synonymous)";
static PyObject *
strop_joinfields(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
PyObject *seq;
char *sep = NULL;
int seqlen, seplen = 0;
int i, reslen = 0, slen = 0, sz = 100;
PyObject *res = NULL;
char* p = NULL;
intargfunc getitemfunc;
if (!PyArg_ParseTuple(args, "O|s#", &seq, &sep, &seplen))
return NULL;
if (sep == NULL) {
sep = " ";
seplen = 1;
}
seqlen = PySequence_Length(seq);
if (seqlen < 0 && PyErr_Occurred())
return NULL;
if (seqlen == 1) {
/* Optimization if there's only one item */
PyObject *item = PySequence_GetItem(seq, 0);
if (item && !PyString_Check(item)) {
PyErr_SetString(PyExc_TypeError,
"first argument must be sequence of strings");
return NULL;
}
return item;
}
if (!(res = PyString_FromStringAndSize((char*)NULL, sz)))
return NULL;
p = PyString_AsString(res);
/* optimize for lists, since it's the most common case. all others
* (tuples and arbitrary sequences) just use the sequence abstract
* interface.
*/
if (PyList_Check(seq)) {
for (i = 0; i < seqlen; i++) {
PyObject *item = PyList_GET_ITEM(seq, i);
if (!PyString_Check(item)) {
PyErr_SetString(PyExc_TypeError,
"first argument must be sequence of strings");
Py_DECREF(res);
return NULL;
}
slen = PyString_GET_SIZE(item);
while (reslen + slen + seplen >= sz) {
if (_PyString_Resize(&res, sz * 2)) {
Py_DECREF(res);
return NULL;
}
sz *= 2;
p = PyString_AsString(res) + reslen;
}
if (i > 0) {
memcpy(p, sep, seplen);
p += seplen;
reslen += seplen;
}
memcpy(p, PyString_AS_STRING(item), slen);
p += slen;
reslen += slen;
}
if (_PyString_Resize(&res, reslen)) {
Py_DECREF(res);
res = NULL;
}
return res;
}
if (seq->ob_type->tp_as_sequence == NULL ||
(getitemfunc = seq->ob_type->tp_as_sequence->sq_item) == NULL)
{
PyErr_SetString(PyExc_TypeError,
"first argument must be a sequence");
return NULL;
}
/* This is now type safe */
for (i = 0; i < seqlen; i++) {
PyObject *item = getitemfunc(seq, i);
if (!item || !PyString_Check(item)) {
PyErr_SetString(PyExc_TypeError,
"first argument must be sequence of strings");
Py_DECREF(res);
Py_XDECREF(item);
return NULL;
}
slen = PyString_GET_SIZE(item);
while (reslen + slen + seplen >= sz) {
if (_PyString_Resize(&res, sz * 2)) {
Py_DECREF(res);
Py_DECREF(item);
return NULL;
}
sz *= 2;
p = PyString_AsString(res) + reslen;
}
if (i > 0) {
memcpy(p, sep, seplen);
p += seplen;
reslen += seplen;
}
memcpy(p, PyString_AS_STRING(item), slen);
p += slen;
reslen += slen;
Py_DECREF(item);
}
if (_PyString_Resize(&res, reslen)) {
Py_DECREF(res);
res = NULL;
}
return res;
}
static char find__doc__[] =
"find(s, sub [,start [,end]]) -> in\n\
\n\
Return the lowest index in s where substring sub is found,\n\
such that sub is contained within s[start,end]. Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.";
static PyObject *
strop_find(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *sub;
int len, n, i = 0, last = INT_MAX;
if (!PyArg_ParseTuple(args, "s#s#|ii", &s, &len, &sub, &n, &i, &last))
return NULL;
if (last > len)
last = len;
if (last < 0)
last += len;
if (last < 0)
last = 0;
if (i < 0)
i += len;
if (i < 0)
i = 0;
if (n == 0 && i <= last)
return PyInt_FromLong((long)i);
last -= n;
for (; i <= last; ++i)
if (s[i] == sub[0] &&
(n == 1 || memcmp(&s[i+1], &sub[1], n-1) == 0))
return PyInt_FromLong((long)i);
return PyInt_FromLong(-1L);
}
static char rfind__doc__[] =
"rfind(s, sub [,start [,end]]) -> int\n\
\n\
Return the highest index in s where substring sub is found,\n\
such that sub is contained within s[start,end]. Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.";
static PyObject *
strop_rfind(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *sub;
int len, n, j;
int i = 0, last = INT_MAX;
if (!PyArg_ParseTuple(args, "s#s#|ii", &s, &len, &sub, &n, &i, &last))
return NULL;
if (last > len)
last = len;
if (last < 0)
last += len;
if (last < 0)
last = 0;
if (i < 0)
i += len;
if (i < 0)
i = 0;
if (n == 0 && i <= last)
return PyInt_FromLong((long)last);
for (j = last-n; j >= i; --j)
if (s[j] == sub[0] &&
(n == 1 || memcmp(&s[j+1], &sub[1], n-1) == 0))
return PyInt_FromLong((long)j);
return PyInt_FromLong(-1L);
}
static PyObject *
do_strip(args, striptype)
PyObject *args;
int striptype;
{
char *s;
int len, i, j;
if (!PyArg_Parse(args, "s#", &s, &len))
return NULL;
i = 0;
if (striptype != RIGHTSTRIP) {
while (i < len && isspace(Py_CHARMASK(s[i]))) {
i++;
}
}
j = len;
if (striptype != LEFTSTRIP) {
do {
j--;
} while (j >= i && isspace(Py_CHARMASK(s[j])));
j++;
}
if (i == 0 && j == len) {
Py_INCREF(args);
return args;
}
else
return PyString_FromStringAndSize(s+i, j-i);
}
static char strip__doc__[] =
"strip(s) -> string\n\
\n\
Return a copy of the string s with leading and trailing\n\
whitespace removed.";
static PyObject *
strop_strip(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
return do_strip(args, BOTHSTRIP);
}
static char lstrip__doc__[] =
"lstrip(s) -> string\n\
\n\
Return a copy of the string s with leading whitespace removed.";
static PyObject *
strop_lstrip(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
return do_strip(args, LEFTSTRIP);
}
static char rstrip__doc__[] =
"rstrip(s) -> string\n\
\n\
Return a copy of the string s with trailing whitespace removed.";
static PyObject *
strop_rstrip(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
return do_strip(args, RIGHTSTRIP);
}
static char lower__doc__[] =
"lower(s) -> string\n\
\n\
Return a copy of the string s converted to lowercase.";
static PyObject *
strop_lower(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *s_new;
int i, n;
PyObject *new;
int changed;
if (!PyArg_Parse(args, "s#", &s, &n))
return NULL;
new = PyString_FromStringAndSize(NULL, n);
if (new == NULL)
return NULL;
s_new = PyString_AsString(new);
changed = 0;
for (i = 0; i < n; i++) {
int c = Py_CHARMASK(*s++);
if (isupper(c)) {
changed = 1;
*s_new = tolower(c);
} else
*s_new = c;
s_new++;
}
if (!changed) {
Py_DECREF(new);
Py_INCREF(args);
return args;
}
return new;
}
static char upper__doc__[] =
"upper(s) -> string\n\
\n\
Return a copy of the string s converted to uppercase.";
static PyObject *
strop_upper(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *s_new;
int i, n;
PyObject *new;
int changed;
if (!PyArg_Parse(args, "s#", &s, &n))
return NULL;
new = PyString_FromStringAndSize(NULL, n);
if (new == NULL)
return NULL;
s_new = PyString_AsString(new);
changed = 0;
for (i = 0; i < n; i++) {
int c = Py_CHARMASK(*s++);
if (islower(c)) {
changed = 1;
*s_new = toupper(c);
} else
*s_new = c;
s_new++;
}
if (!changed) {
Py_DECREF(new);
Py_INCREF(args);
return args;
}
return new;
}
static char capitalize__doc__[] =
"capitalize(s) -> string\n\
\n\
Return a copy of the string s with only its first character\n\
capitalized.";
static PyObject *
strop_capitalize(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *s_new;
int i, n;
PyObject *new;
int changed;
if (!PyArg_Parse(args, "s#", &s, &n))
return NULL;
new = PyString_FromStringAndSize(NULL, n);
if (new == NULL)
return NULL;
s_new = PyString_AsString(new);
changed = 0;
if (0 < n) {
int c = Py_CHARMASK(*s++);
if (islower(c)) {
changed = 1;
*s_new = toupper(c);
} else
*s_new = c;
s_new++;
}
for (i = 1; i < n; i++) {
int c = Py_CHARMASK(*s++);
if (isupper(c)) {
changed = 1;
*s_new = tolower(c);
} else
*s_new = c;
s_new++;
}
if (!changed) {
Py_DECREF(new);
Py_INCREF(args);
return args;
}
return new;
}
static char swapcase__doc__[] =
"swapcase(s) -> string\n\
\n\
Return a copy of the string s with upper case characters\n\
converted to lowercase and vice versa.";
static PyObject *
strop_swapcase(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *s_new;
int i, n;
PyObject *new;
int changed;
if (!PyArg_Parse(args, "s#", &s, &n))
return NULL;
new = PyString_FromStringAndSize(NULL, n);
if (new == NULL)
return NULL;
s_new = PyString_AsString(new);
changed = 0;
for (i = 0; i < n; i++) {
int c = Py_CHARMASK(*s++);
if (islower(c)) {
changed = 1;
*s_new = toupper(c);
}
else if (isupper(c)) {
changed = 1;
*s_new = tolower(c);
}
else
*s_new = c;
s_new++;
}
if (!changed) {
Py_DECREF(new);
Py_INCREF(args);
return args;
}
return new;
}
static char atoi__doc__[] =
"atoi(s [,base]) -> int\n\
\n\
Return the integer represented by the string s in the given\n\
base, which defaults to 10. The string s must consist of one\n\
or more digits, possibly preceded by a sign. If base is 0, it\n\
is chosen from the leading characters of s, 0 for octal, 0x or\n\
0X for hexadecimal. If base is 16, a preceding 0x or 0X is\n\
accepted.";
static PyObject *
strop_atoi(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
extern long PyOS_strtol Py_PROTO((const char *, char **, int));
extern unsigned long
PyOS_strtoul Py_PROTO((const char *, char **, int));
char *s, *end;
int base = 10;
long x;
char buffer[256]; /* For errors */
if (!PyArg_ParseTuple(args, "s|i", &s, &base))
return NULL;
if ((base != 0 && base < 2) || base > 36) {
PyErr_SetString(PyExc_ValueError, "invalid base for atoi()");
return NULL;
}
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "empty string for atoi()");
return NULL;
}
errno = 0;
if (base == 0 && s[0] == '0')
x = (long) PyOS_strtoul(s, &end, base);
else
x = PyOS_strtol(s, &end, base);
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
sprintf(buffer, "invalid literal for atoi(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "atoi() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
return PyInt_FromLong(x);
}
static char atol__doc__[] =
"atol(s [,base]) -> long\n\
\n\
Return the long integer represented by the string s in the\n\
given base, which defaults to 10. The string s must consist\n\
of one or more digits, possibly preceded by a sign. If base\n\
is 0, it is chosen from the leading characters of s, 0 for\n\
octal, 0x or 0X for hexadecimal. If base is 16, a preceding\n\
0x or 0X is accepted. A trailing L or l is not accepted,\n\
unless base is 0.";
static PyObject *
strop_atol(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *s, *end;
int base = 10;
PyObject *x;
char buffer[256]; /* For errors */
if (!PyArg_ParseTuple(args, "s|i", &s, &base))
return NULL;
if ((base != 0 && base < 2) || base > 36) {
PyErr_SetString(PyExc_ValueError, "invalid base for atol()");
return NULL;
}
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "empty string for atol()");
return NULL;
}
x = PyLong_FromString(s, &end, base);
if (x == NULL)
return NULL;
if (base == 0 && (*end == 'l' || *end == 'L'))
end++;
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
sprintf(buffer, "invalid literal for atol(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
Py_DECREF(x);
return NULL;
}
return x;
}
static char atof__doc__[] =
"atof(s) -> float\n\
\n\
Return the floating point number represented by the string s.";
static PyObject *
strop_atof(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
extern double strtod Py_PROTO((const char *, char **));
char *s, *end;
double x;
char buffer[256]; /* For errors */
if (!PyArg_ParseTuple(args, "s", &s))
return NULL;
while (*s && isspace(Py_CHARMASK(*s)))
s++;
if (s[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "empty string for atof()");
return NULL;
}
errno = 0;
PyFPE_START_PROTECT("strop_atof", return 0)
x = strtod(s, &end);
PyFPE_END_PROTECT(x)
while (*end && isspace(Py_CHARMASK(*end)))
end++;
if (*end != '\0') {
sprintf(buffer, "invalid literal for atof(): %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
else if (errno != 0) {
sprintf(buffer, "atof() literal too large: %.200s", s);
PyErr_SetString(PyExc_ValueError, buffer);
return NULL;
}
return PyFloat_FromDouble(x);
}
static char maketrans__doc__[] =
"maketrans(frm, to) -> string\n\
\n\
Return a translation table (a string of 256 bytes long)\n\
suitable for use in string.translate. The strings frm and to\n\
must be of the same length.";
static PyObject *
strop_maketrans(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
unsigned char *c, *from=NULL, *to=NULL;
int i, fromlen=0, tolen=0;
PyObject *result;
if (!PyArg_ParseTuple(args, "s#s#", &from, &fromlen, &to, &tolen))
return NULL;
if (fromlen != tolen) {
PyErr_SetString(PyExc_ValueError,
"maketrans arguments must have same length");
return NULL;
}
result = PyString_FromStringAndSize((char *)NULL, 256);
if (result == NULL)
return NULL;
c = (unsigned char *) PyString_AS_STRING((PyStringObject *)result);
for (i = 0; i < 256; i++)
c[i]=(unsigned char)i;
for (i = 0; i < fromlen; i++)
c[from[i]]=to[i];
return result;
}
static char translate__doc__[] =
"translate(s,table [,deletechars]) -> string\n\
\n\
Return a copy of the string s, where all characters occurring\n\
in the optional argument deletechars are removed, and the\n\
remaining characters have been mapped through the given\n\
translation table, which must be a string of length 256.";
static PyObject *
strop_translate(self, args)
PyObject *self;
PyObject *args;
{
register char *input, *table, *output;
register int i, c, changed = 0;
PyObject *input_obj;
char *table1, *output_start, *del_table=NULL;
int inlen, tablen, dellen = 0;
PyObject *result;
int trans_table[256];
if (!PyArg_ParseTuple(args, "Ss#|s#", &input_obj,
&table1, &tablen, &del_table, &dellen))
return NULL;
if (tablen != 256) {
PyErr_SetString(PyExc_ValueError,
"translation table must be 256 characters long");
return NULL;
}
table = table1;
inlen = PyString_Size(input_obj);
result = PyString_FromStringAndSize((char *)NULL, inlen);
if (result == NULL)
return NULL;
output_start = output = PyString_AsString(result);
input = PyString_AsString(input_obj);
if (dellen == 0) {
/* 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)
return result;
Py_DECREF(result);
Py_INCREF(input_obj);
return input_obj;
}
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) {
Py_DECREF(result);
Py_INCREF(input_obj);
return input_obj;
}
/* Fix the size of the resulting string */
if (inlen > 0 &&_PyString_Resize(&result, output-output_start))
return NULL;
return result;
}
/* What follows is used for implementing replace(). Perry Stoll. */
/*
mymemfind
strstr replacement for arbitrary blocks of memory.
Locates the first occurance in the memory pointed to by MEM of the
contents of memory pointed to by PAT. Returns the index into MEM if
found, or -1 if not found. If len of PAT is greater than length of
MEM, the function returns -1.
*/
static int mymemfind(mem, len, pat, pat_len)
char *mem;
int len;
char *pat;
int pat_len;
{
register int ii;
/* pattern can not occur in the last pat_len-1 chars */
len -= pat_len;
for (ii = 0; ii <= len; ii++) {
if (mem[ii] == pat[0] &&
(pat_len == 1 ||
memcmp(&mem[ii+1], &pat[1], pat_len-1) == 0)) {
return ii;
}
}
return -1;
}
/*
mymemcnt
Return the number of distinct times PAT is found in MEM.
meaning mem=1111 and pat==11 returns 2.
mem=11111 and pat==11 also return 2.
*/
static int mymemcnt(mem, len, pat, pat_len)
char *mem;
int len;
char *pat;
int pat_len;
{
register int offset = 0;
int nfound = 0;
while (len >= 0) {
offset = mymemfind(mem, len, pat, pat_len);
if (offset == -1)
break;
mem += offset + pat_len;
len -= offset + pat_len;
nfound++;
}
return nfound;
}
/*
mymemreplace
Return a string in which all occurences of PAT in memory STR are
replaced with SUB.
If length of PAT is less than length of STR or there are no occurences
of PAT in STR, then the original string is returned. Otherwise, a new
string is allocated here and returned.
on return, out_len is:
the length of output string, or
-1 if the input string is returned, or
unchanged if an error occurs (no memory).
return value is:
the new string allocated locally, or
NULL if an error occurred.
*/
static char *mymemreplace(str, len, pat, pat_len, sub, sub_len, count, out_len)
char *str;
int len; /* input string */
char *pat;
int pat_len; /* pattern string to find */
char *sub;
int sub_len; /* substitution string */
int count; /* number of replacements, 0 == all */
int *out_len;
{
char *out_s;
char *new_s;
int nfound, offset, new_len;
if (len == 0 || pat_len > len)
goto return_same;
/* find length of output string */
nfound = mymemcnt(str, len, pat, pat_len);
if (count > 0)
nfound = nfound > count ? count : nfound;
if (nfound == 0)
goto return_same;
new_len = len + nfound*(sub_len - pat_len);
new_s = (char *)malloc(new_len);
if (new_s == NULL) return NULL;
*out_len = new_len;
out_s = new_s;
while (len > 0) {
/* find index of next instance of pattern */
offset = mymemfind(str, len, pat, pat_len);
/* if not found, break out of loop */
if (offset == -1) break;
/* copy non matching part of input string */
memcpy(new_s, str, offset); /* copy part of str before pat */
str += offset + pat_len; /* move str past pattern */
len -= offset + pat_len; /* reduce length of str remaining */
/* copy substitute into the output string */
new_s += offset; /* move new_s to dest for sub string */
memcpy(new_s, sub, sub_len); /* copy substring into new_s */
new_s += sub_len; /* offset new_s past sub string */
/* break when we've done count replacements */
if (--count == 0) break;
}
/* copy any remaining values into output string */
if (len > 0)
memcpy(new_s, str, len);
return out_s;
return_same:
*out_len = -1;
return str;
}
static char replace__doc__[] =
"replace (str, old, new[, maxsplit]) -> string\n\
\n\
Return a copy of string str with all occurrences of substring\n\
old replaced by new. If the optional argument maxsplit is\n\
given, only the first maxsplit occurrences are replaced.";
static PyObject *
strop_replace(self, args)
PyObject *self; /* Not used */
PyObject *args;
{
char *str, *pat,*sub,*new_s;
int len,pat_len,sub_len,out_len;
int count = 0;
PyObject *new;
if (!PyArg_ParseTuple(args, "s#s#s#|i",
&str, &len, &pat, &pat_len, &sub, &sub_len,
&count))
return NULL;
if (pat_len <= 0) {
PyErr_SetString(PyExc_ValueError, "empty pattern string");
return NULL;
}
new_s = mymemreplace(str,len,pat,pat_len,sub,sub_len,count,&out_len);
if (new_s == NULL) {
PyErr_NoMemory();
return NULL;
}
if (out_len == -1) {
/* we're returning another reference to the input string */
new = PyTuple_GetItem(args, 0);
Py_XINCREF(new);
}
else {
new = PyString_FromStringAndSize(new_s, out_len);
free(new_s);
}
return new;
}
/* List of functions defined in the module */
static PyMethodDef
strop_methods[] = {
{"atof", strop_atof, 1, atof__doc__},
{"atoi", strop_atoi, 1, atoi__doc__},
{"atol", strop_atol, 1, atol__doc__},
{"capitalize", strop_capitalize, 0, capitalize__doc__},
{"find", strop_find, 1, find__doc__},
{"join", strop_joinfields, 1, joinfields__doc__},
{"joinfields", strop_joinfields, 1, joinfields__doc__},
{"lstrip", strop_lstrip, 0, lstrip__doc__},
{"lower", strop_lower, 0, lower__doc__},
{"maketrans", strop_maketrans, 1, maketrans__doc__},
{"replace", strop_replace, 1, replace__doc__},
{"rfind", strop_rfind, 1, rfind__doc__},
{"rstrip", strop_rstrip, 0, rstrip__doc__},
{"split", strop_splitfields, 1, splitfields__doc__},
{"splitfields", strop_splitfields, 1, splitfields__doc__},
{"strip", strop_strip, 0, strip__doc__},
{"swapcase", strop_swapcase, 0, swapcase__doc__},
{"translate", strop_translate, 1, translate__doc__},
{"upper", strop_upper, 0, upper__doc__},
{NULL, NULL} /* sentinel */
};
void
initstrop()
{
PyObject *m, *d, *s;
char buf[256];
int c, n;
m = Py_InitModule4("strop", strop_methods, strop_module__doc__,
(PyObject*)NULL, PYTHON_API_VERSION);
d = PyModule_GetDict(m);
/* Create 'whitespace' object */
n = 0;
for (c = 0; c < 256; c++) {
if (isspace(c))
buf[n++] = c;
}
s = PyString_FromStringAndSize(buf, n);
if (s) {
PyDict_SetItemString(d, "whitespace", s);
Py_DECREF(s);
}
/* Create 'lowercase' object */
n = 0;
for (c = 0; c < 256; c++) {
if (islower(c))
buf[n++] = c;
}
s = PyString_FromStringAndSize(buf, n);
if (s) {
PyDict_SetItemString(d, "lowercase", s);
Py_DECREF(s);
}
/* Create 'uppercase' object */
n = 0;
for (c = 0; c < 256; c++) {
if (isupper(c))
buf[n++] = c;
}
s = PyString_FromStringAndSize(buf, n);
if (s) {
PyDict_SetItemString(d, "uppercase", s);
Py_DECREF(s);
}
if (PyErr_Occurred())
Py_FatalError("can't initialize module strop");
}
|