forked from kokke/tiny-regex-c
-
Notifications
You must be signed in to change notification settings - Fork 2
/
re.c
1145 lines (1042 loc) · 30.4 KB
/
re.c
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
/*
*
* Mini regex-module inspired by Rob Pike's regex code described in:
*
* http://www.cs.princeton.edu/courses/archive/spr09/cos333/beautiful.html
*
*
*
* Supports:
* ---------
* '.' Dot, matches any character
* '^' Start anchor, matches beginning of string
* '$' End anchor, matches end of string
* '*' Asterisk, match zero or more (greedy)
* '+' Plus, match one or more (greedy)
* '?' Question, match zero or one (non-greedy)
* '[abc]' Character class, match if one of {'a', 'b', 'c'}
* '[^abc]' Inverted class, match if NOT one of {'a', 'b', 'c'}
* '[a-zA-Z]' Character ranges, the character set of the ranges { a-z | A-Z }
* '\s' Whitespace, \t \f \r \n \v and spaces
* '\S' Non-whitespace
* '\w' Alphanumeric, [a-zA-Z0-9_]
* '\W' Non-alphanumeric
* '\d' Digits, [0-9]
* '\D' Non-digits
* '\xXX' Hex-encoded byte
* '|' Branch Or, e.g. a|A, \w|\s
* '{n}' Match n times
* '{n,}' Match n or more times
* '{,m}' Match m or less times
* '{n,m}' Match n to m times
* FIXME:
* '(...)' Group
*
* TODO:
* - multibyte support (mbtowc, esp. UTF-8. maybe hardcode UTF-8 without libc locale insanity)
* - \b word boundary support
*/
#include "re.h"
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#ifdef _UNICODE
# include <stdlib.h>
# include <locale.h>
#endif
/* Definitions: */
#define MAX_CHAR_CLASS_LEN 40 /* Max length of character-class buffer in. */
#ifndef CPROVER
#define MAX_REGEXP_OBJECTS 30 /* Max number of regex symbols in expression. */
#else
#define MAX_REGEXP_OBJECTS 8 /* faster formal proofs */
#endif
#define MAX_REGEXP_LEN 70
#ifdef DEBUG
#define DEBUG_P(...) fprintf(stderr, __VA_ARGS__)
#else
#define DEBUG_P(...)
#endif
enum regex_type_e { UNUSED, DOT, BEGIN, END, QUESTIONMARK, STAR, PLUS, CHAR,
CHAR_CLASS, INV_CHAR_CLASS, DIGIT, NOT_DIGIT, ALPHA,
NOT_ALPHA, WHITESPACE, NOT_WHITESPACE, BRANCH, GROUP, GROUPEND,
TIMES, TIMES_N, TIMES_M, TIMES_NM };
typedef struct regex_t
{
unsigned short type; /* CHAR, STAR, etc. */
union
{
struct {
char ch; /* the character itself */
char data[];
};
unsigned char group_size; /* OR the number of group patterns. */
unsigned char group_start; /* OR for GROUPEND, the start index of the group. */
struct {
unsigned short n; /* match n times */
unsigned short m; /* match n to m times */
};
} u;
} regex_t;
static unsigned getsize(regex_t* pattern)
{
unsigned size = sizeof(unsigned short);
switch(pattern->type) {
case GROUP:
case GROUPEND:
size += sizeof(unsigned short) * 2;
break;
case TIMES:
case TIMES_N:
case TIMES_M:
case TIMES_NM:
size += sizeof(unsigned short) * 2;
break;
case CHAR:
size += sizeof(unsigned short) * 2;
break;
case CHAR_CLASS:
case INV_CHAR_CLASS:
size += sizeof(unsigned short) + strlen(&pattern->u.data[-1]);
default:
break;
}
if(size % 2)
++size;
return size;
}
static re_t getnext(regex_t* pattern)
{
return (re_t)(((unsigned char*)pattern) + getsize(pattern));
}
static re_t getindex(regex_t* pattern, int index)
{
for(int i = 1; i <= index; ++i)
pattern = getnext(pattern);
return pattern;
}
/* Private function declarations: */
static int matchpattern(regex_t* pattern, const char* text, int* matchlength, int *num_patterns);
static int matchcharclass(char c, const char* str);
static int matchstar(regex_t* p, regex_t* pattern, const char* text, int* matchlength);
static int matchplus(regex_t* p, regex_t* pattern, const char* text, int* matchlength);
static int matchquestion(regex_t* p, regex_t* pattern, const char* text, int* matchlength);
static int matchbranch(regex_t* p, regex_t* pattern, const char* text, int* matchlength);
static int matchtimes(regex_t* p, unsigned short n, const char* text, int* matchlength);
static int matchtimes_n(regex_t* p, unsigned short n, const char* text, int* matchlength);
static int matchtimes_m(regex_t* p, unsigned short m, const char* text, int* matchlength);
static int matchtimes_nm(regex_t* p, unsigned short n, unsigned short m,
const char* text, int* matchlength);
static int matchgroup(regex_t* p, const char* text, int* matchlength);
static int matchone(regex_t* p, char c);
static int matchdigit(char c);
static int matchalpha(char c);
static int matchwhitespace(char c);
static int matchmetachar(char c, const char* str);
static int matchrange(char c, const char* str);
static int matchdot(char c);
static int ismetachar(char c);
static int hex (char c);
/* Public functions: */
int re_match(const char* pattern, const char* text, int* matchlength)
{
return re_matchp(re_compile(pattern), text, matchlength);
}
int re_matchp(re_t pattern, const char* text, int* matchlength)
{
int num_patterns = 0;
*matchlength = 0;
if (pattern != 0)
{
if (pattern->type == BEGIN)
{
return ((matchpattern(getnext(pattern), text, matchlength, &num_patterns)) ? 0 : -1);
}
else
{
int idx = -1;
do
{
idx += 1;
if (matchpattern(pattern, text, matchlength, &num_patterns))
{
// empty branch matches null (i.e. ok, but *matchlength == 0)
if (*matchlength && text[0] == '\0')
return -1;
return idx;
}
// Reset match length for the next starting point
*matchlength = 0;
}
while (*text++ != '\0');
}
}
return -1;
}
re_t re_compile_to(const char* pattern, unsigned char* re_data, unsigned* size)
{
memset(re_data, 0, *size);
char c; /* current char in pattern */
int i = 0; /* index into pattern */
int j = 0; /* index into re_data */
unsigned bytes = *size;
*size = 0;
regex_t *re_compiled = (regex_t*)(re_data);
while (pattern[i] != '\0' && ((char*)re_compiled < (char*)re_data + bytes - sizeof(re_compiled)))
{
c = pattern[i];
switch (c)
{
/* Meta-characters: */
case '^': { re_compiled->type = BEGIN; } break;
case '$': { re_compiled->type = END; } break;
case '.': { re_compiled->type = DOT; } break;
case '|': { re_compiled->type = BRANCH; } break;
case '*':
{
if (j > 0)
re_compiled->type = STAR;
else // nothing to repeat at position 0
return 0;
} break;
case '+':
{
if (j > 0)
re_compiled->type = PLUS;
else // nothing to repeat at position 0
return 0;
} break;
case '?':
{
if (j > 0)
re_compiled->type = QUESTIONMARK;
else // nothing to repeat at position 0
return 0;
} break;
case '(':
{
char *p = strrchr(&pattern[i], ')');
if (p && *(p - 1) != '\\')
{
re_compiled->type = GROUP;
re_compiled->u.group_size = 0;
}
/* '(' without matching ')' */
else
return 0;
break;
}
case ')':
{
int nestlevel = 0;
int k = j - 1;
/* search back to next innermost groupstart */
for (; k >= 0; k--)
{
regex_t* cur = getindex((regex_t*)re_data, k);
if (k < j && cur->type == GROUPEND)
nestlevel++;
else if (cur->type == GROUP)
{
if (nestlevel == 0)
{
cur->u.group_size = j - k - 1;
re_compiled->type = GROUPEND;
re_compiled->u.group_start = k; // index of group
break;
}
nestlevel--;
}
}
/* ')' without matching '(' */
if (k < 0)
return 0;
break;
}
case '{':
{
unsigned short n, m;
char *p = strchr (&pattern[i+1], '}');
re_compiled->type = CHAR;
re_compiled->u.ch = c;
//re_compiled->u.data_len = 1;
if (!p || j == 0) // those invalid quantifiers are compiled as is
{ // (in python and perl)
re_compiled->type = CHAR;
re_compiled->u.ch = c;
//re_compiled->u.data_len = 1;
}
else if (2 != sscanf (&pattern[i], "{%hd,%hd}", &n, &m))
{
int o;
if (!(2 == sscanf (&pattern[i], "{%hd,}%n", &n, &o) && pattern[o] == '\0') ||
n == 0 || n > 32767)
{
if (1 != sscanf (&pattern[i], "{,%hd}", &m) ||
*(p-1) == ',' || m == 0 || m > 32767)
{
if (1 == sscanf (&pattern[i], "{%hd}", &n) &&
n > 0 && n <= 32767)
{
re_compiled->type = TIMES;
re_compiled->u.n = n;
}
}
else
{
re_compiled->type = TIMES_M;
re_compiled->u.m = m;
}
}
else
{
re_compiled->type = TIMES_N;
re_compiled->u.n = n;
}
}
else
{
// m must be greater than n, and none of them may be 0 or negative.
if (!(n == 0 || m == 0 || n > 32767 || m > 32767 || m <= n || *(p-1) == ','))
{
re_compiled->type = TIMES_NM;
re_compiled->u.n = n;
re_compiled->u.m = m;
}
}
if (re_compiled->type != CHAR)
i += (p - &pattern[i]);
break;
}
/* Escaped character-classes (\s \S \w \W \d \D \*): */
case '\\':
{
if (pattern[i+1] != '\0')
{
/* Skip the escape-char '\\' */
i += 1;
/* ... and check the next */
switch (pattern[i])
{
/* Meta-characters: */
case 'd': { re_compiled->type = DIGIT; } break;
case 'D': { re_compiled->type = NOT_DIGIT; } break;
case 'w': { re_compiled->type = ALPHA; } break;
case 'W': { re_compiled->type = NOT_ALPHA; } break;
case 's': { re_compiled->type = WHITESPACE; } break;
case 'S': { re_compiled->type = NOT_WHITESPACE; } break;
case 'x': {
/* \xXX */
re_compiled->type = CHAR;
i++;
int h = hex(pattern[i]);
if (h == -1)
{
re_compiled->u.ch = '\\';
re_compiled->type = CHAR;
re_compiled = getnext(re_compiled);
re_compiled->u.ch = 'x';
re_compiled->type = CHAR;
re_compiled = getnext(re_compiled);
re_compiled->u.ch = pattern[i];
re_compiled->type = CHAR;
break;
}
re_compiled->u.ch = h << 4;
h = hex(pattern[++i]);
if (h != -1)
re_compiled->u.ch += h;
else
{
re_compiled->u.ch = '\\';
re_compiled->type = CHAR;
re_compiled = getnext(re_compiled);
re_compiled->u.ch = 'x';
re_compiled->type = CHAR;
re_compiled = getnext(re_compiled);
re_compiled->u.ch = pattern[i-1];
re_compiled->type = CHAR;
if (pattern[i])
{
re_compiled = getnext(re_compiled);
re_compiled->u.ch = pattern[i];
re_compiled->type = CHAR;
}
}
} break;
/* Escaped character, e.g. '.', '$' or '\\' */
default:
{
re_compiled->type = CHAR;
re_compiled->u.ch = pattern[i];
} break;
}
}
/* '\\' as last char without previous \\ -> invalid regular expression. */
else
return 0;
} break;
/* Character class: */
case '[':
{
int charIdx = -1;
/* Look-ahead to determine if negated */
if (pattern[i+1] == '^')
{
re_compiled->type = INV_CHAR_CLASS;
i += 1; /* Increment i to avoid including '^' in the char-buffer */
if (pattern[i+1] == 0) /* incomplete pattern, missing non-zero char after '^' */
{
return 0;
}
}
else
{
re_compiled->type = CHAR_CLASS;
}
/* Copy characters inside [..] to buffer */
while ( (pattern[++i] != ']')
&& (pattern[i] != '\0')) /* Missing ] */
{
if (pattern[i] == '\\')
{
if (&re_compiled->u.data[charIdx] >= (char*)re_data + bytes)
{
//fputs("exceeded internal buffer!\n", stderr);
return 0;
}
if (pattern[i+1] == 0) /* incomplete pattern, missing non-zero char after '\\' */
{
return 0;
}
re_compiled->u.data[charIdx++] = pattern[i++];
}
else if (&re_compiled->u.data[charIdx] >= (char*)re_data + bytes)
{
//fputs("exceeded internal buffer!\n", stderr);
return 0;
}
re_compiled->u.data[charIdx++] = pattern[i];
}
if (&re_compiled->u.data[charIdx] >= (char*)re_data + bytes)
{
/* Catches cases such as [00000000000000000000000000000000000000][ */
//fputs("exceeded internal buffer!\n", stderr);
return 0;
}
/* Null-terminate string end */
re_compiled->u.data[charIdx++] = '\0';
} break;
case '\0': // EOL (dead-code)
return 0;
/* Other characters: */
default:
{
re_compiled->type = CHAR;
// cbmc: arithmetic overflow on signed to unsigned type conversion in c
re_compiled->u.ch = c;
} break;
}
i += 1;
j += 1;
re_compiled = getnext(re_compiled);
}
/* 'UNUSED' is a sentinel used to indicate end-of-pattern */
re_compiled->type = UNUSED;
/* Calculate final, compressed actual size. */
*size = (unsigned char*)getnext(re_compiled) - re_data;
return (re_t) re_data;
}
re_t re_compile(const char* pattern)
{
static unsigned char buffer[MAX_REGEXP_OBJECTS * sizeof(regex_t)];
unsigned size = sizeof(buffer);
return re_compile_to(pattern, buffer, &size);
}
unsigned re_size(re_t pattern)
{
unsigned bytes = 0;
while(pattern)
{
bytes += getsize(pattern);
if(pattern->type == UNUSED)
break;
pattern = getnext(pattern);
}
return bytes;
}
int re_compare(re_t pattern1, re_t pattern2) {
int result = 0;
const unsigned totalSize1 = re_size(pattern1);
const unsigned totalSize2 = re_size(pattern2);
if(totalSize1 > totalSize2)
return 1;
else if(totalSize2 > totalSize1)
return -1;
while(pattern1 && pattern2) {
unsigned size1 = getsize(pattern1);
unsigned size2 = getsize(pattern2);
if(size1 > size2)
return 1;
else if(size2 > size1)
return -1;
result = memcmp(pattern1, pattern2, size1);
if(result != 0)
return result;
if(pattern1->type == UNUSED)
break;
pattern1 = getnext(pattern1);
pattern2 = getnext(pattern2);
}
return result;
}
#define re_string_cat_fmt_(buff, ...) \
do { \
sprintf(tmp_buff, __VA_ARGS__); \
strncat(buff, tmp_buff, count - *size - 1); \
*size = strlen(buff); \
if(*size >= count) \
return; \
} while(0)
void re_string(regex_t* pattern, char* buffer, unsigned* size)
{
#if 0
const char *const types[] = { "UNUSED", "DOT", "BEGIN", "END", "QUESTIONMARK", "STAR", "PLUS", "CHAR", "CHAR_CLASS", "INV_CHAR_CLASS", "DIGIT", "NOT_DIGIT", "ALPHA", "NOT_ALPHA", "WHITESPACE", "NOT_WHITESPACE", "BRANCH", "GROUP", "GROUPEND", "TIMES", "TIMES_N", "TIMES_M", "TIMES_NM" };
#endif
unsigned count = *size;
unsigned char i = 0;
int j;
unsigned char group_end = 0;
char c;
char tmp_buff[128];
*size = 0;
buffer[0] = '\0';
if (!pattern)
return;
while(*size < count)
{
if (pattern->type == UNUSED)
{
break;
}
//if (group_end && i == group_end)
// printf(" )\n");
#if 0
if (pattern->type <= TIMES_NM)
re_string_cat_fmt_(buffer, "type: %s", types[pattern->type]);
else
re_string_cat_fmt_(buffer, "invalid type: %d", pattern->type);
#endif
if (pattern->type == CHAR_CLASS || pattern->type == INV_CHAR_CLASS)
{
re_string_cat_fmt_(buffer, "[");
if (pattern->type == INV_CHAR_CLASS)
re_string_cat_fmt_(buffer, "^");
j = -1;
while((c = pattern->u.data[j]))
{
if (c == ']')
{
break;
}
re_string_cat_fmt_(buffer, "%c", c);
++j;
}
re_string_cat_fmt_(buffer, "]");
}
else if (pattern->type == CHAR)
{
re_string_cat_fmt_(buffer, "%c", pattern->u.ch);
}
else if (pattern->type == TIMES)
{
re_string_cat_fmt_(buffer, "{%hu}", pattern->u.n);
}
else if (pattern->type == TIMES_N)
{
re_string_cat_fmt_(buffer, "{%hu,}", pattern->u.n);
}
else if (pattern->type == TIMES_M)
{
re_string_cat_fmt_(buffer, "{,%hu}", pattern->u.m);
}
else if (pattern->type == TIMES_NM)
{
re_string_cat_fmt_(buffer, "{%hu,%hu}", pattern->u.n, pattern->u.m);
}
else if (pattern->type == GROUP)
{
group_end = i + pattern->u.group_size;
if (group_end >= MAX_REGEXP_OBJECTS)
return;
re_string_cat_fmt_(buffer, " (");
}
else if (pattern->type == GROUPEND)
{
re_string_cat_fmt_(buffer, " )");
}
else if(pattern->type == BEGIN)
{
re_string_cat_fmt_(buffer, "^");
}
else if(pattern->type == END)
{
re_string_cat_fmt_(buffer, "$");
}
else if(pattern->type == QUESTIONMARK)
{
re_string_cat_fmt_(buffer, "?");
}
else if(pattern->type == DIGIT)
{
re_string_cat_fmt_(buffer, "\\d");
}
//re_string_cat_fmt_(buffer, "\n");
++i;
pattern = getnext(pattern);
}
}
static int hex (char c)
{
if (c >= 'a' && c <= 'f')
return c - 'a' + 10;
else if (c >= 'A' && c <= 'F')
return c - 'A' + 10;
else if (c >= '0' && c <= '9')
return c - '0';
else
return -1;
}
/* Private functions: */
static int matchdigit(char c)
{
return isdigit((unsigned char)c);
}
static int matchalpha(char c)
{
return isalpha((unsigned char)c);
}
static int matchwhitespace(char c)
{
return isspace((unsigned char)c);
}
static int matchalphanum(char c)
{
return ((c == '_') || matchalpha(c) || matchdigit(c));
}
static int matchrange(char c, const char* str)
{
return ( (c != '-')
&& (str[0] != '\0')
&& (str[0] != '-')
&& (str[1] == '-')
&& (str[2] != '\0')
&& ( (c >= str[0])
&& (c <= str[2])));
}
static int matchdot(char c)
{
#if defined(RE_DOT_MATCHES_NEWLINE) && (RE_DOT_MATCHES_NEWLINE == 1)
(void)c;
return 1;
#else
return c != '\n' && c != '\r';
#endif
}
static int ismetachar(char c)
{
return ((c == 's') || (c == 'S') || (c == 'w') || (c == 'W') || (c == 'd') || (c == 'D'));
}
static int matchmetachar(char c, const char* str)
{
switch (str[0])
{
case 'd': return matchdigit(c);
case 'D': return !matchdigit(c);
case 'w': return matchalphanum(c);
case 'W': return !matchalphanum(c);
case 's': return matchwhitespace(c);
case 'S': return !matchwhitespace(c);
default: return (c == str[0]);
}
}
static int matchcharclass(char c, const char* str)
{
do
{
if (matchrange(c, str))
{
DEBUG_P("%c matches %s\n", c, str);
return 1;
}
else if (str[0] == '\\')
{
/* Escape-char: increment str-ptr and match on next char */
str += 1;
if (matchmetachar(c, str))
{
return 1;
}
else if ((c == str[0]) && !ismetachar(c))
{
return 1;
}
}
else if (c == str[0])
{
if (c == '-')
{
if ((str[-1] == '\0') || (str[1] == '\0'))
return 1;
// else continue
}
else
{
return 1;
}
}
}
while (*str++ != '\0');
DEBUG_P("%c did not match prev. ccl\n", c);
return 0;
}
static int matchone(regex_t* p, char c)
{
DEBUG_P("ONE %d matches %c?\n", p->type, c);
switch (p->type)
{
case DOT: return matchdot(c);
case CHAR_CLASS: return matchcharclass(c, (const char*)&p->u.data[-1]);
case INV_CHAR_CLASS: return !matchcharclass(c, (const char*)&p->u.data[-1]);
case DIGIT: return matchdigit(c);
case NOT_DIGIT: return !matchdigit(c);
case ALPHA: return matchalphanum(c);
case NOT_ALPHA: return !matchalphanum(c);
case WHITESPACE: return matchwhitespace(c);
case NOT_WHITESPACE: return !matchwhitespace(c);
case GROUPEND: return 1;
case BEGIN: return 0;
default: return (p->u.ch == c);
}
}
static int matchstar(regex_t* p, regex_t* pattern, const char* text, int* matchlength)
{
int num_patterns = 0;
return matchplus(p, pattern, text, matchlength) ||
matchpattern(pattern, text, matchlength, &num_patterns);
}
static int matchplus(regex_t* p, regex_t* pattern, const char* text, int* matchlength)
{
int num_patterns = 0;
const char* prepoint = text;
while ((text[0] != '\0') && matchone(p, *text))
{
DEBUG_P("+ matches %s\n", text);
text++;
}
for (; text > prepoint; text--)
{
if (matchpattern(pattern, text, matchlength, &num_patterns))
{
*matchlength += text - prepoint;
return 1;
}
DEBUG_P("+ pattern does not match %s\n", &text[1]);
}
DEBUG_P("+ pattern did not match %s\n", prepoint);
return 0;
}
static int matchquestion(regex_t* p, regex_t* pattern, const char* text, int* matchlength)
{
int num_patterns = 0;
if (p->type == UNUSED)
return 1;
if (matchpattern(pattern, text, matchlength, &num_patterns))
{
#ifdef DEBUG
re_print(pattern);
DEBUG_P("? matched %s\n", text);
#endif
return 1;
}
if (*text && matchone(p, *text++))
{
if (matchpattern(pattern, text, matchlength, &num_patterns))
{
(*matchlength)++;
#ifdef DEBUG
re_print(pattern);
DEBUG_P("? matched %s\n", text);
#endif
return 1;
}
}
return 0;
}
static int matchtimes(regex_t* p, unsigned short n, const char* text, int* matchlength)
{
unsigned short i = 0;
int pre = *matchlength;
/* Match the pattern n times */
while (*text && matchone(p, *text++) && i < n)
{
(*matchlength)++;
i++;
}
if (i == n)
return 1;
*matchlength = pre;
return 0;
}
static int matchtimes_n(regex_t* p, unsigned short n, const char* text, int* matchlength)
{
unsigned short i = 0;
int pre = *matchlength;
/* Match the pattern n or more times */
while (*text && matchone(p, *text++))
{
i++;
++(*matchlength);
}
if (i >= n)
return 1;
*matchlength = pre;
return 0;
}
static int matchtimes_m(regex_t* p, unsigned short m, const char* text, int* matchlength)
{
unsigned short i = 0;
/* Match the pattern max m times */
while (*text && matchone(p, *text++) && i < m)
{
(*matchlength)++;
i++;
}
return 1;
}
static int matchtimes_nm(regex_t* p, unsigned short n, unsigned short m, const char* text, int* matchlength)
{
unsigned short i = 0;
int pre = *matchlength;
/* Match the pattern n to m times */
while (*text && matchone(p, *text++) && i < m)
{
(*matchlength)++;
i++;
}
if (i >= n && i <= m)
return 1;
*matchlength = pre;
return 0;
}
static int matchbranch(regex_t* p, regex_t* pattern, const char* text, int* matchlength)
{
int num_patterns = 0;
const char* prepoint = text;
if (p->type == UNUSED)
return 1;
/* Match the current p (previous) */
if (*text && matchone(p, *text++))
{
(*matchlength)++;
return 1;
}
if (pattern->type == UNUSED)
// empty branch "0|" allows NULL text
return 1;
/* or the next branch */
if (matchpattern(pattern, prepoint, matchlength, &num_patterns))
return 1;
return 0;
}
static int matchgroup(regex_t* p, const char* text, int* matchlength)
{
int pre = *matchlength;
int num_patterns = 0, length = pre;
regex_t* groupstart = p;
const regex_t* groupend = getindex(p, p->u.group_size + 1);//&p[p->u.group_size + 1];
DEBUG_P("does GROUP (%u) match %s?\n", (unsigned)p->u.group_size, text);
p = getnext(p);
while (p < groupend)
{
if (p->type == UNUSED) // only with invalid external compiles
return 0;
if (!matchpattern(p, text, &length, &num_patterns))
{
DEBUG_P("GROUP did not match %.*s (len %d, patterns %d)\n", length, text-*matchlength, *matchlength, num_patterns);
*matchlength = pre;
return 0;
}
DEBUG_P("GROUP did match %.*s (len %d, patterns %d)\n", length, text-*matchlength, *matchlength, num_patterns);
int delta = length - *matchlength;
text += delta;
p = getindex(groupstart, num_patterns);
*matchlength += delta;
}
DEBUG_P("ENDGROUP did match %s (len %d, patterns %d)\n", text-*matchlength, *matchlength, num_patterns);
return 1;
}
static inline int ismultimatch(unsigned char type) {
switch(type) {
case TIMES:
case TIMES_N:
case TIMES_M:
case TIMES_NM:
return 1;
default:
return 0;
}
}
/* Iterative matching */
static int matchpattern(regex_t* pattern, const char* text, int* matchlength, int *num_patterns)
{
int pre = *matchlength;
while(1)
{
if(pattern->type == UNUSED)
{
return 1;
}
regex_t* next_pattern = getnext(pattern);
if (next_pattern->type == QUESTIONMARK)
{
return matchquestion(pattern, getnext(next_pattern), text, matchlength);
}
else if (next_pattern->type == STAR)
{
//int i = (pattern[1].type == GROUPEND) ? pattern[1].u.group_start : 0;
return matchstar(pattern, getnext(next_pattern), text, matchlength);
}
else if (next_pattern->type == PLUS)
{