forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathregcomp.c
1574 lines (1437 loc) · 36.2 KB
/
regcomp.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
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)regcomp.c 8.5 (Berkeley) 3/20/94
*/
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>
#include <stdlib.h>
#include "regex_impl.h"
#include "regutils.h"
#include "regex2.h"
#include "regcclass.h"
#include "regcname.h"
#include "llvm/Config/config.h"
#if HAVE_STDINT_H
#include <stdint.h>
#else
/* Pessimistically bound memory use */
#define SIZE_MAX UINT_MAX
#endif
/*
* parse structure, passed up and down to avoid global variables and
* other clumsinesses
*/
struct parse {
char *next; /* next character in RE */
char *end; /* end of string (-> NUL normally) */
int error; /* has an error been seen? */
sop *strip; /* malloced strip */
sopno ssize; /* malloced strip size (allocated) */
sopno slen; /* malloced strip length (used) */
int ncsalloc; /* number of csets allocated */
struct re_guts *g;
# define NPAREN 10 /* we need to remember () 1-9 for back refs */
sopno pbegin[NPAREN]; /* -> ( ([0] unused) */
sopno pend[NPAREN]; /* -> ) ([0] unused) */
};
static void p_ere(struct parse *, int);
static void p_ere_exp(struct parse *);
static void p_str(struct parse *);
static void p_bre(struct parse *, int, int);
static int p_simp_re(struct parse *, int);
static int p_count(struct parse *);
static void p_bracket(struct parse *);
static void p_b_term(struct parse *, cset *);
static void p_b_cclass(struct parse *, cset *);
static void p_b_eclass(struct parse *, cset *);
static char p_b_symbol(struct parse *);
static char p_b_coll_elem(struct parse *, int);
static char othercase(int);
static void bothcases(struct parse *, int);
static void ordinary(struct parse *, int);
static void nonnewline(struct parse *);
static void repeat(struct parse *, sopno, int, int);
static int seterr(struct parse *, int);
static cset *allocset(struct parse *);
static void freeset(struct parse *, cset *);
static int freezeset(struct parse *, cset *);
static int firstch(struct parse *, cset *);
static int nch(struct parse *, cset *);
static void mcadd(struct parse *, cset *, const char *);
static void mcinvert(struct parse *, cset *);
static void mccase(struct parse *, cset *);
static int isinsets(struct re_guts *, int);
static int samesets(struct re_guts *, int, int);
static void categorize(struct parse *, struct re_guts *);
static sopno dupl(struct parse *, sopno, sopno);
static void doemit(struct parse *, sop, size_t);
static void doinsert(struct parse *, sop, size_t, sopno);
static void dofwd(struct parse *, sopno, sop);
static void enlarge(struct parse *, sopno);
static void stripsnug(struct parse *, struct re_guts *);
static void findmust(struct parse *, struct re_guts *);
static sopno pluscount(struct parse *, struct re_guts *);
static char nuls[10]; /* place to point scanner in event of error */
/*
* macros for use with parse structure
* BEWARE: these know that the parse structure is named `p' !!!
*/
#define PEEK() (*p->next)
#define PEEK2() (*(p->next+1))
#define MORE() (p->next < p->end)
#define MORE2() (p->next+1 < p->end)
#define SEE(c) (MORE() && PEEK() == (c))
#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b))
#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0)
#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0)
#define NEXT() (p->next++)
#define NEXT2() (p->next += 2)
#define NEXTn(n) (p->next += (n))
#define GETNEXT() (*p->next++)
#define SETERROR(e) seterr(p, (e))
#define REQUIRE(co, e) (void)((co) || SETERROR(e))
#define MUSTSEE(c, e) (REQUIRE(MORE() && PEEK() == (c), e))
#define MUSTEAT(c, e) (REQUIRE(MORE() && GETNEXT() == (c), e))
#define MUSTNOTSEE(c, e) (REQUIRE(!MORE() || PEEK() != (c), e))
#define EMIT(op, sopnd) doemit(p, (sop)(op), (size_t)(sopnd))
#define INSERT(op, pos) doinsert(p, (sop)(op), HERE()-(pos)+1, pos)
#define AHEAD(pos) dofwd(p, pos, HERE()-(pos))
#define ASTERN(sop, pos) EMIT(sop, HERE()-pos)
#define HERE() (p->slen)
#define THERE() (p->slen - 1)
#define THERETHERE() (p->slen - 2)
#define DROP(n) (p->slen -= (n))
#ifdef _POSIX2_RE_DUP_MAX
#define DUPMAX _POSIX2_RE_DUP_MAX
#else
#define DUPMAX 255
#endif
#define INFINITY (DUPMAX + 1)
#ifndef NDEBUG
static int never = 0; /* for use in asserts; shuts lint up */
#else
#define never 0 /* some <assert.h>s have bugs too */
#endif
/*
- llvm_regcomp - interface for parser and compilation
*/
int /* 0 success, otherwise REG_something */
llvm_regcomp(llvm_regex_t *preg, const char *pattern, int cflags)
{
struct parse pa;
struct re_guts *g;
struct parse *p = &pa;
int i;
size_t len;
#ifdef REDEBUG
# define GOODFLAGS(f) (f)
#else
# define GOODFLAGS(f) ((f)&~REG_DUMP)
#endif
cflags = GOODFLAGS(cflags);
if ((cflags®_EXTENDED) && (cflags®_NOSPEC))
return(REG_INVARG);
if (cflags®_PEND) {
if (preg->re_endp < pattern)
return(REG_INVARG);
len = preg->re_endp - pattern;
} else
len = strlen((const char *)pattern);
/* do the mallocs early so failure handling is easy */
g = (struct re_guts *)malloc(sizeof(struct re_guts) +
(NC-1)*sizeof(cat_t));
if (g == NULL)
return(REG_ESPACE);
p->ssize = len/(size_t)2*(size_t)3 + (size_t)1; /* ugh */
p->strip = (sop *)calloc(p->ssize, sizeof(sop));
p->slen = 0;
if (p->strip == NULL) {
free((char *)g);
return(REG_ESPACE);
}
/* set things up */
p->g = g;
p->next = (char *)pattern; /* convenience; we do not modify it */
p->end = p->next + len;
p->error = 0;
p->ncsalloc = 0;
for (i = 0; i < NPAREN; i++) {
p->pbegin[i] = 0;
p->pend[i] = 0;
}
g->csetsize = NC;
g->sets = NULL;
g->setbits = NULL;
g->ncsets = 0;
g->cflags = cflags;
g->iflags = 0;
g->nbol = 0;
g->neol = 0;
g->must = NULL;
g->mlen = 0;
g->nsub = 0;
g->ncategories = 1; /* category 0 is "everything else" */
g->categories = &g->catspace[-(CHAR_MIN)];
(void) memset((char *)g->catspace, 0, NC*sizeof(cat_t));
g->backrefs = 0;
/* do it */
EMIT(OEND, 0);
g->firststate = THERE();
if (cflags®_EXTENDED)
p_ere(p, OUT);
else if (cflags®_NOSPEC)
p_str(p);
else
p_bre(p, OUT, OUT);
EMIT(OEND, 0);
g->laststate = THERE();
/* tidy up loose ends and fill things in */
categorize(p, g);
stripsnug(p, g);
findmust(p, g);
g->nplus = pluscount(p, g);
g->magic = MAGIC2;
preg->re_nsub = g->nsub;
preg->re_g = g;
preg->re_magic = MAGIC1;
#ifndef REDEBUG
/* not debugging, so can't rely on the assert() in llvm_regexec() */
if (g->iflags®EX_BAD)
SETERROR(REG_ASSERT);
#endif
/* win or lose, we're done */
if (p->error != 0) /* lose */
llvm_regfree(preg);
return(p->error);
}
/*
- p_ere - ERE parser top level, concatenation and alternation
*/
static void
p_ere(struct parse *p, int stop) /* character this ERE should end at */
{
char c;
sopno prevback = 0;
sopno prevfwd = 0;
sopno conc;
int first = 1; /* is this the first alternative? */
for (;;) {
/* do a bunch of concatenated expressions */
conc = HERE();
while (MORE() && (c = PEEK()) != '|' && c != stop)
p_ere_exp(p);
REQUIRE(HERE() != conc, REG_EMPTY); /* require nonempty */
if (!EAT('|'))
break; /* NOTE BREAK OUT */
if (first) {
INSERT(OCH_, conc); /* offset is wrong */
prevfwd = conc;
prevback = conc;
first = 0;
}
ASTERN(OOR1, prevback);
prevback = THERE();
AHEAD(prevfwd); /* fix previous offset */
prevfwd = HERE();
EMIT(OOR2, 0); /* offset is very wrong */
}
if (!first) { /* tail-end fixups */
AHEAD(prevfwd);
ASTERN(O_CH, prevback);
}
assert(!MORE() || SEE(stop));
}
/*
- p_ere_exp - parse one subERE, an atom possibly followed by a repetition op
*/
static void
p_ere_exp(struct parse *p)
{
char c;
sopno pos;
int count;
int count2;
int backrefnum;
sopno subno;
int wascaret = 0;
assert(MORE()); /* caller should have ensured this */
c = GETNEXT();
pos = HERE();
switch (c) {
case '(':
REQUIRE(MORE(), REG_EPAREN);
p->g->nsub++;
subno = p->g->nsub;
if (subno < NPAREN)
p->pbegin[subno] = HERE();
EMIT(OLPAREN, subno);
if (!SEE(')'))
p_ere(p, ')');
if (subno < NPAREN) {
p->pend[subno] = HERE();
assert(p->pend[subno] != 0);
}
EMIT(ORPAREN, subno);
MUSTEAT(')', REG_EPAREN);
break;
#ifndef POSIX_MISTAKE
case ')': /* happens only if no current unmatched ( */
/*
* You may ask, why the ifndef? Because I didn't notice
* this until slightly too late for 1003.2, and none of the
* other 1003.2 regular-expression reviewers noticed it at
* all. So an unmatched ) is legal POSIX, at least until
* we can get it fixed.
*/
SETERROR(REG_EPAREN);
break;
#endif
case '^':
EMIT(OBOL, 0);
p->g->iflags |= USEBOL;
p->g->nbol++;
wascaret = 1;
break;
case '$':
EMIT(OEOL, 0);
p->g->iflags |= USEEOL;
p->g->neol++;
break;
case '|':
SETERROR(REG_EMPTY);
break;
case '*':
case '+':
case '?':
SETERROR(REG_BADRPT);
break;
case '.':
if (p->g->cflags®_NEWLINE)
nonnewline(p);
else
EMIT(OANY, 0);
break;
case '[':
p_bracket(p);
break;
case '\\':
REQUIRE(MORE(), REG_EESCAPE);
c = GETNEXT();
if (c >= '1' && c <= '9') {
/* \[0-9] is taken to be a back-reference to a previously specified
* matching group. backrefnum will hold the number. The matching
* group must exist (i.e. if \4 is found there must have been at
* least 4 matching groups specified in the pattern previously).
*/
backrefnum = c - '0';
if (p->pend[backrefnum] == 0) {
SETERROR(REG_ESUBREG);
break;
}
/* Make sure everything checks out and emit the sequence
* that marks a back-reference to the parse structure.
*/
assert(backrefnum <= p->g->nsub);
EMIT(OBACK_, backrefnum);
assert(p->pbegin[backrefnum] != 0);
assert(OP(p->strip[p->pbegin[backrefnum]]) != OLPAREN);
assert(OP(p->strip[p->pend[backrefnum]]) != ORPAREN);
(void) dupl(p, p->pbegin[backrefnum]+1, p->pend[backrefnum]);
EMIT(O_BACK, backrefnum);
p->g->backrefs = 1;
} else {
/* Other chars are simply themselves when escaped with a backslash.
*/
ordinary(p, c);
}
break;
case '{': /* okay as ordinary except if digit follows */
REQUIRE(!MORE() || !isdigit((uch)PEEK()), REG_BADRPT);
/* FALLTHROUGH */
default:
ordinary(p, c);
break;
}
if (!MORE())
return;
c = PEEK();
/* we call { a repetition if followed by a digit */
if (!( c == '*' || c == '+' || c == '?' ||
(c == '{' && MORE2() && isdigit((uch)PEEK2())) ))
return; /* no repetition, we're done */
NEXT();
REQUIRE(!wascaret, REG_BADRPT);
switch (c) {
case '*': /* implemented as +? */
/* this case does not require the (y|) trick, noKLUDGE */
INSERT(OPLUS_, pos);
ASTERN(O_PLUS, pos);
INSERT(OQUEST_, pos);
ASTERN(O_QUEST, pos);
break;
case '+':
INSERT(OPLUS_, pos);
ASTERN(O_PLUS, pos);
break;
case '?':
/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
INSERT(OCH_, pos); /* offset slightly wrong */
ASTERN(OOR1, pos); /* this one's right */
AHEAD(pos); /* fix the OCH_ */
EMIT(OOR2, 0); /* offset very wrong... */
AHEAD(THERE()); /* ...so fix it */
ASTERN(O_CH, THERETHERE());
break;
case '{':
count = p_count(p);
if (EAT(',')) {
if (isdigit((uch)PEEK())) {
count2 = p_count(p);
REQUIRE(count <= count2, REG_BADBR);
} else /* single number with comma */
count2 = INFINITY;
} else /* just a single number */
count2 = count;
repeat(p, pos, count, count2);
if (!EAT('}')) { /* error heuristics */
while (MORE() && PEEK() != '}')
NEXT();
REQUIRE(MORE(), REG_EBRACE);
SETERROR(REG_BADBR);
}
break;
}
if (!MORE())
return;
c = PEEK();
if (!( c == '*' || c == '+' || c == '?' ||
(c == '{' && MORE2() && isdigit((uch)PEEK2())) ) )
return;
SETERROR(REG_BADRPT);
}
/*
- p_str - string (no metacharacters) "parser"
*/
static void
p_str(struct parse *p)
{
REQUIRE(MORE(), REG_EMPTY);
while (MORE())
ordinary(p, GETNEXT());
}
/*
- p_bre - BRE parser top level, anchoring and concatenation
* Giving end1 as OUT essentially eliminates the end1/end2 check.
*
* This implementation is a bit of a kludge, in that a trailing $ is first
* taken as an ordinary character and then revised to be an anchor. The
* only undesirable side effect is that '$' gets included as a character
* category in such cases. This is fairly harmless; not worth fixing.
* The amount of lookahead needed to avoid this kludge is excessive.
*/
static void
p_bre(struct parse *p,
int end1, /* first terminating character */
int end2) /* second terminating character */
{
sopno start = HERE();
int first = 1; /* first subexpression? */
int wasdollar = 0;
if (EAT('^')) {
EMIT(OBOL, 0);
p->g->iflags |= USEBOL;
p->g->nbol++;
}
while (MORE() && !SEETWO(end1, end2)) {
wasdollar = p_simp_re(p, first);
first = 0;
}
if (wasdollar) { /* oops, that was a trailing anchor */
DROP(1);
EMIT(OEOL, 0);
p->g->iflags |= USEEOL;
p->g->neol++;
}
REQUIRE(HERE() != start, REG_EMPTY); /* require nonempty */
}
/*
- p_simp_re - parse a simple RE, an atom possibly followed by a repetition
*/
static int /* was the simple RE an unbackslashed $? */
p_simp_re(struct parse *p,
int starordinary) /* is a leading * an ordinary character? */
{
int c;
int count;
int count2;
sopno pos;
int i;
sopno subno;
# define BACKSL (1<<CHAR_BIT)
pos = HERE(); /* repetition op, if any, covers from here */
assert(MORE()); /* caller should have ensured this */
c = GETNEXT();
if (c == '\\') {
REQUIRE(MORE(), REG_EESCAPE);
c = BACKSL | GETNEXT();
}
switch (c) {
case '.':
if (p->g->cflags®_NEWLINE)
nonnewline(p);
else
EMIT(OANY, 0);
break;
case '[':
p_bracket(p);
break;
case BACKSL|'{':
SETERROR(REG_BADRPT);
break;
case BACKSL|'(':
p->g->nsub++;
subno = p->g->nsub;
if (subno < NPAREN)
p->pbegin[subno] = HERE();
EMIT(OLPAREN, subno);
/* the MORE here is an error heuristic */
if (MORE() && !SEETWO('\\', ')'))
p_bre(p, '\\', ')');
if (subno < NPAREN) {
p->pend[subno] = HERE();
assert(p->pend[subno] != 0);
}
EMIT(ORPAREN, subno);
REQUIRE(EATTWO('\\', ')'), REG_EPAREN);
break;
case BACKSL|')': /* should not get here -- must be user */
case BACKSL|'}':
SETERROR(REG_EPAREN);
break;
case BACKSL|'1':
case BACKSL|'2':
case BACKSL|'3':
case BACKSL|'4':
case BACKSL|'5':
case BACKSL|'6':
case BACKSL|'7':
case BACKSL|'8':
case BACKSL|'9':
i = (c&~BACKSL) - '0';
assert(i < NPAREN);
if (p->pend[i] != 0) {
assert(i <= p->g->nsub);
EMIT(OBACK_, i);
assert(p->pbegin[i] != 0);
assert(OP(p->strip[p->pbegin[i]]) == OLPAREN);
assert(OP(p->strip[p->pend[i]]) == ORPAREN);
(void) dupl(p, p->pbegin[i]+1, p->pend[i]);
EMIT(O_BACK, i);
} else
SETERROR(REG_ESUBREG);
p->g->backrefs = 1;
break;
case '*':
REQUIRE(starordinary, REG_BADRPT);
/* FALLTHROUGH */
default:
ordinary(p, (char)c);
break;
}
if (EAT('*')) { /* implemented as +? */
/* this case does not require the (y|) trick, noKLUDGE */
INSERT(OPLUS_, pos);
ASTERN(O_PLUS, pos);
INSERT(OQUEST_, pos);
ASTERN(O_QUEST, pos);
} else if (EATTWO('\\', '{')) {
count = p_count(p);
if (EAT(',')) {
if (MORE() && isdigit((uch)PEEK())) {
count2 = p_count(p);
REQUIRE(count <= count2, REG_BADBR);
} else /* single number with comma */
count2 = INFINITY;
} else /* just a single number */
count2 = count;
repeat(p, pos, count, count2);
if (!EATTWO('\\', '}')) { /* error heuristics */
while (MORE() && !SEETWO('\\', '}'))
NEXT();
REQUIRE(MORE(), REG_EBRACE);
SETERROR(REG_BADBR);
}
} else if (c == '$') /* $ (but not \$) ends it */
return(1);
return(0);
}
/*
- p_count - parse a repetition count
*/
static int /* the value */
p_count(struct parse *p)
{
int count = 0;
int ndigits = 0;
while (MORE() && isdigit((uch)PEEK()) && count <= DUPMAX) {
count = count*10 + (GETNEXT() - '0');
ndigits++;
}
REQUIRE(ndigits > 0 && count <= DUPMAX, REG_BADBR);
return(count);
}
/*
- p_bracket - parse a bracketed character list
*
* Note a significant property of this code: if the allocset() did SETERROR,
* no set operations are done.
*/
static void
p_bracket(struct parse *p)
{
cset *cs;
int invert = 0;
/* Dept of Truly Sickening Special-Case Kludges */
if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) {
EMIT(OBOW, 0);
NEXTn(6);
return;
}
if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) {
EMIT(OEOW, 0);
NEXTn(6);
return;
}
if ((cs = allocset(p)) == NULL) {
/* allocset did set error status in p */
return;
}
if (EAT('^'))
invert++; /* make note to invert set at end */
if (EAT(']'))
CHadd(cs, ']');
else if (EAT('-'))
CHadd(cs, '-');
while (MORE() && PEEK() != ']' && !SEETWO('-', ']'))
p_b_term(p, cs);
if (EAT('-'))
CHadd(cs, '-');
MUSTEAT(']', REG_EBRACK);
if (p->error != 0) { /* don't mess things up further */
freeset(p, cs);
return;
}
if (p->g->cflags®_ICASE) {
int i;
int ci;
for (i = p->g->csetsize - 1; i >= 0; i--)
if (CHIN(cs, i) && isalpha(i)) {
ci = othercase(i);
if (ci != i)
CHadd(cs, ci);
}
if (cs->multis != NULL)
mccase(p, cs);
}
if (invert) {
int i;
for (i = p->g->csetsize - 1; i >= 0; i--)
if (CHIN(cs, i))
CHsub(cs, i);
else
CHadd(cs, i);
if (p->g->cflags®_NEWLINE)
CHsub(cs, '\n');
if (cs->multis != NULL)
mcinvert(p, cs);
}
assert(cs->multis == NULL); /* xxx */
if (nch(p, cs) == 1) { /* optimize singleton sets */
ordinary(p, firstch(p, cs));
freeset(p, cs);
} else
EMIT(OANYOF, freezeset(p, cs));
}
/*
- p_b_term - parse one term of a bracketed character list
*/
static void
p_b_term(struct parse *p, cset *cs)
{
char c;
char start, finish;
int i;
/* classify what we've got */
switch ((MORE()) ? PEEK() : '\0') {
case '[':
c = (MORE2()) ? PEEK2() : '\0';
break;
case '-':
SETERROR(REG_ERANGE);
return; /* NOTE RETURN */
break;
default:
c = '\0';
break;
}
switch (c) {
case ':': /* character class */
NEXT2();
REQUIRE(MORE(), REG_EBRACK);
c = PEEK();
REQUIRE(c != '-' && c != ']', REG_ECTYPE);
p_b_cclass(p, cs);
REQUIRE(MORE(), REG_EBRACK);
REQUIRE(EATTWO(':', ']'), REG_ECTYPE);
break;
case '=': /* equivalence class */
NEXT2();
REQUIRE(MORE(), REG_EBRACK);
c = PEEK();
REQUIRE(c != '-' && c != ']', REG_ECOLLATE);
p_b_eclass(p, cs);
REQUIRE(MORE(), REG_EBRACK);
REQUIRE(EATTWO('=', ']'), REG_ECOLLATE);
break;
default: /* symbol, ordinary character, or range */
/* xxx revision needed for multichar stuff */
start = p_b_symbol(p);
if (SEE('-') && MORE2() && PEEK2() != ']') {
/* range */
NEXT();
if (EAT('-'))
finish = '-';
else
finish = p_b_symbol(p);
} else
finish = start;
/* xxx what about signed chars here... */
REQUIRE(start <= finish, REG_ERANGE);
for (i = start; i <= finish; i++)
CHadd(cs, i);
break;
}
}
/*
- p_b_cclass - parse a character-class name and deal with it
*/
static void
p_b_cclass(struct parse *p, cset *cs)
{
char *sp = p->next;
struct cclass *cp;
size_t len;
const char *u;
char c;
while (MORE() && isalpha((uch)PEEK()))
NEXT();
len = p->next - sp;
for (cp = cclasses; cp->name != NULL; cp++)
if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
break;
if (cp->name == NULL) {
/* oops, didn't find it */
SETERROR(REG_ECTYPE);
return;
}
u = cp->chars;
while ((c = *u++) != '\0')
CHadd(cs, c);
for (u = cp->multis; *u != '\0'; u += strlen(u) + 1)
MCadd(p, cs, u);
}
/*
- p_b_eclass - parse an equivalence-class name and deal with it
*
* This implementation is incomplete. xxx
*/
static void
p_b_eclass(struct parse *p, cset *cs)
{
char c;
c = p_b_coll_elem(p, '=');
CHadd(cs, c);
}
/*
- p_b_symbol - parse a character or [..]ed multicharacter collating symbol
*/
static char /* value of symbol */
p_b_symbol(struct parse *p)
{
char value;
REQUIRE(MORE(), REG_EBRACK);
if (!EATTWO('[', '.'))
return(GETNEXT());
/* collating symbol */
value = p_b_coll_elem(p, '.');
REQUIRE(EATTWO('.', ']'), REG_ECOLLATE);
return(value);
}
/*
- p_b_coll_elem - parse a collating-element name and look it up
*/
static char /* value of collating element */
p_b_coll_elem(struct parse *p,
int endc) /* name ended by endc,']' */
{
char *sp = p->next;
struct cname *cp;
int len;
while (MORE() && !SEETWO(endc, ']'))
NEXT();
if (!MORE()) {
SETERROR(REG_EBRACK);
return(0);
}
len = p->next - sp;
for (cp = cnames; cp->name != NULL; cp++)
if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
return(cp->code); /* known name */
if (len == 1)
return(*sp); /* single character */
SETERROR(REG_ECOLLATE); /* neither */
return(0);
}
/*
- othercase - return the case counterpart of an alphabetic
*/
static char /* if no counterpart, return ch */
othercase(int ch)
{
ch = (uch)ch;
assert(isalpha(ch));
if (isupper(ch))
return ((uch)tolower(ch));
else if (islower(ch))
return ((uch)toupper(ch));
else /* peculiar, but could happen */
return(ch);
}
/*
- bothcases - emit a dualcase version of a two-case character
*
* Boy, is this implementation ever a kludge...
*/
static void
bothcases(struct parse *p, int ch)
{
char *oldnext = p->next;
char *oldend = p->end;
char bracket[3];
ch = (uch)ch;
assert(othercase(ch) != ch); /* p_bracket() would recurse */
p->next = bracket;
p->end = bracket+2;
bracket[0] = ch;
bracket[1] = ']';
bracket[2] = '\0';
p_bracket(p);
assert(p->next == bracket+2);
p->next = oldnext;
p->end = oldend;
}
/*
- ordinary - emit an ordinary character
*/
static void
ordinary(struct parse *p, int ch)
{
cat_t *cap = p->g->categories;
if ((p->g->cflags®_ICASE) && isalpha((uch)ch) && othercase(ch) != ch)
bothcases(p, ch);
else {
EMIT(OCHAR, (uch)ch);
if (cap[ch] == 0)
cap[ch] = p->g->ncategories++;
}
}
/*
- nonnewline - emit REG_NEWLINE version of OANY
*
* Boy, is this implementation ever a kludge...
*/
static void
nonnewline(struct parse *p)
{
char *oldnext = p->next;
char *oldend = p->end;
char bracket[4];
p->next = bracket;
p->end = bracket+3;
bracket[0] = '^';
bracket[1] = '\n';
bracket[2] = ']';
bracket[3] = '\0';
p_bracket(p);
assert(p->next == bracket+3);
p->next = oldnext;
p->end = oldend;
}
/*
- repeat - generate code for a bounded repetition, recursively if needed
*/
static void
repeat(struct parse *p,
sopno start, /* operand from here to end of strip */
int from, /* repeated from this number */
int to) /* to this number of times (maybe INFINITY) */
{
sopno finish = HERE();
# define N 2
# define INF 3
# define REP(f, t) ((f)*8 + (t))
# define MAP(n) (((n) <= 1) ? (n) : ((n) == INFINITY) ? INF : N)
sopno copy;
if (p->error != 0) /* head off possible runaway recursion */
return;
assert(from <= to);
switch (REP(MAP(from), MAP(to))) {