aboutsummaryrefslogtreecommitdiff
path: root/lib/libopenbsd/regex/regcomp.c
blob: 19c86cc4c39da6b0c136f647d522f535489bde38 (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
/*	$OpenBSD: regcomp.c,v 1.32 2017/10/30 06:48:20 otto Exp $ */
/*-
 * 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.h>

#include "utils.h"
#include "regex2.h"

#include "cclass.h"
#include "cname.h"

/*
 * 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 backslash(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 *, 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 int 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	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))

#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

/*
 - regcomp - interface for parser and compilation
 */
int				/* 0 success, otherwise REG_something */
regcomp(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&REG_EXTENDED) && (cflags&REG_NOSPEC))
		return(REG_INVARG);

	if (cflags&REG_PEND) {
		if (preg->re_endp < pattern)
			return(REG_INVARG);
		len = preg->re_endp - pattern;
	} else
		len = strlen((char *)pattern);

	/* do the mallocs early so failure handling is easy */
	g = malloc(sizeof(struct re_guts));
	if (g == NULL)
		return(REG_ESPACE);
	p->ssize = len/(size_t)2*(size_t)3 + (size_t)1;	/* ugh */
	p->strip = reallocarray(NULL, p->ssize, sizeof(sop));
	p->slen = 0;
	if (p->strip == NULL) {
		free(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)];
	memset(g->catspace, 0, sizeof(g->catspace));
	g->backrefs = 0;

	/* do it */
	EMIT(OEND, 0);
	g->firststate = THERE();
	if (cflags&REG_EXTENDED)
		p_ere(p, OUT);
	else if (cflags&REG_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 regexec() */
	if (g->iflags&BAD)
		SETERROR(REG_ASSERT);
#endif

	/* win or lose, we're done */
	if (p->error != 0)	/* lose */
		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;
	sopno prevfwd;
	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;
	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);
		REQUIRE(MORE() && GETNEXT() == ')', REG_EPAREN);
		break;
	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&REG_NEWLINE)
			nonnewline(p);
		else
			EMIT(OANY, 0);
		break;
	case '[':
		p_bracket(p);
		break;
	case '\\':
		REQUIRE(MORE(), REG_EESCAPE);
		c = GETNEXT();
		backslash(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();		/* repetion 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&REG_NEWLINE)
			nonnewline(p);
		else
			EMIT(OANY, 0);
		break;
	case '[':
		p_bracket(p);
		break;
	case BACKSL|'<':
		EMIT(OBOW, 0);
		break;
	case BACKSL|'>':
		EMIT(OEOW, 0);
		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, '-');
	REQUIRE(MORE() && GETNEXT() == ']', REG_EBRACK);

	if (p->error != 0) {	/* don't mess things up further */
		freeset(p, cs);
		return;
	}

	if (p->g->cflags&REG_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&REG_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;
	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;
	size_t 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 && strlen(cp->name) == len)
			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&REG_ICASE) && isalpha((uch)ch) && othercase(ch) != ch)
		bothcases(p, ch);
	else {
		EMIT(OCHAR, (uch)ch);
		if (cap[ch] == 0)
			cap[ch] = p->g->ncategories++;
	}
}

/*
 * do something magic with this character, but only if it's extra magic
 */
static void
backslash(struct parse *p, int ch)
{
	switch (ch) {
	case '<':
		EMIT(OBOW, 0);
		break;
	case '>':
		EMIT(OEOW, 0);
		break;
	default:
		ordinary(p, ch);
		break;
	}
}

/*
 - 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))) {
	case REP(0, 0):			/* must be user doing this */
		DROP(finish-start);	/* drop the operand */
		break;
	case REP(0, 1):			/* as x{1,1}? */
	case REP(0, N):			/* as x{1,n}? */
	case REP(0, INF):		/* as x{1,}? */
		/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
		INSERT(OCH_, start);		/* offset is wrong... */
		repeat(p, start+1, 1, to);
		ASTERN(OOR1, start);
		AHEAD(start);			/* ... fix it */
		EMIT(OOR2, 0);
		AHEAD(THERE());
		ASTERN(O_CH, THERETHERE());
		break;
	case REP(1, 1):			/* trivial case */
		/* done */
		break;
	case REP(1, N):			/* as x?x{1,n-1} */
		/* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
		INSERT(OCH_, start);
		ASTERN(OOR1, start);
		AHEAD(start);
		EMIT(OOR2, 0);			/* offset very wrong... */
		AHEAD(THERE());			/* ...so fix it */
		ASTERN(O_CH, THERETHERE());
		copy = dupl(p, start+1, finish+1);
		assert(copy == finish+4);
		repeat(p, copy, 1, to-1);
		break;
	case REP(1, INF):		/* as x+ */
		INSERT(OPLUS_, start);
		ASTERN(O_PLUS, start);
		break;
	case REP(N, N):			/* as xx{m-1,n-1} */
		copy = dupl(p, start, finish);
		repeat(p, copy, from-1, to-1);
		break;
	case REP(N, INF):		/* as xx{n-1,INF} */
		copy = dupl(p, start, finish);
		repeat(p, copy, from-1, to);
		break;
	default:			/* "can't happen" */
		SETERROR(REG_ASSERT);	/* just in case */
		break;
	}
}

/*
 - seterr - set an error condition
 */
static int			/* useless but makes type checking happy */
seterr(struct parse *p, int e)
{
	if (p->error == 0)	/* keep earliest error condition */
		p->error = e;
	p->next = nuls;		/* try to bring things to a halt */
	p->end = nuls;
	return(0);		/* make the return value well-defined */
}

/*
 - allocset - allocate a set of characters for []
 */
static cset *
allocset(struct parse *p)
{
	int no = p->g->ncsets++;
	size_t nc;
	size_t nbytes;
	cset *cs;
	size_t css = (size_t)p->g->csetsize;
	int i;

	if (no >= p->ncsalloc) {	/* need another column of space */
		void *ptr;

		p->ncsalloc += CHAR_BIT;
		nc = p->ncsalloc;
		assert(nc % CHAR_BIT == 0);

		ptr = reallocarray(p->g->sets, nc, sizeof(cset));
		if (ptr == NULL)
			goto nomem;
		p->g->sets = ptr;

		ptr = reallocarray(p->g->setbits, nc / CHAR_BIT, css);
		if (ptr == NULL)
			goto nomem;
		nbytes = (nc / CHAR_BIT) * css;
		p->g->setbits = ptr;

		for (i = 0; i < no; i++)
			p->g->sets[i].ptr = p->g->setbits + css*(i/CHAR_BIT);

		(void) memset((char *)p->g->setbits + (nbytes - css), 0, css);
	}
	/* XXX should not happen */
	if (p->g->sets == NULL || p->g->setbits == NULL)
		goto nomem;

	cs = &p->g->sets[no];
	cs->ptr = p->g->setbits + css*((no)/CHAR_BIT);
	cs->mask = 1 << ((no) % CHAR_BIT);
	cs->hash = 0;
	cs->smultis = 0;
	cs->multis = NULL;

	return(cs);
nomem:
	free(p->g->sets);
	p->g->sets = NULL;
	free(p->g->setbits);
	p->g->setbits = NULL;

	SETERROR(REG_ESPACE);
	/* caller's responsibility not to do set ops */
	return(NULL);
}

/*
 - freeset - free a now-unused set
 */
static void
freeset(struct parse *p, cset *cs)
{
	int i;
	cset *top = &p->g->sets[p->g->ncsets];
	size_t css = (size_t)p->g->csetsize;

	for (i = 0; i < css; i++)
		CHsub(cs, i);
	if (cs == top-1)	/* recover only the easy case */
		p->g->ncsets--;
}

/*
 - freezeset - final processing on a set of characters
 *
 * The main task here is merging identical sets.  This is usually a waste
 * of time (although the hash code minimizes the overhead), but can win
 * big if REG_ICASE is being used.  REG_ICASE, by the way, is why the hash
 * is done using addition rather than xor -- all ASCII [aA] sets xor to
 * the same value!
 */
static int			/* set number */
freezeset(struct parse *p, cset *cs)
{
	uch h = cs->hash;
	int i;
	cset *top = &p->g->sets[p->g->ncsets];
	cset *cs2;
	size_t css = (size_t)p->g->csetsize;

	/* look for an earlier one which is the same */
	for (cs2 = &p->g->sets[0]; cs2 < top; cs2++)
		if (cs2->hash == h && cs2 != cs) {
			/* maybe */
			for (i = 0; i < css; i++)
				if (!!CHIN(cs2, i) != !!CHIN(cs, i))
					break;		/* no */
			if (i == css)
				break;			/* yes */
		}

	if (cs2 < top) {	/* found one */
		freeset(p, cs);
		cs = cs2;
	}

	return((int)(cs - p->g->sets));
}

/*
 - firstch - return first character in a set (which must have at least one)
 */
static int			/* character; there is no "none" value */
firstch(struct parse *p, cset *cs)
{
	int i;
	size_t css = (size_t)p->g->csetsize;

	for (i = 0; i < css; i++)
		if (CHIN(cs, i))
			return((char)i);
	assert(never);
	return(0);		/* arbitrary */
}

/*
 - nch - number of characters in a set
 */
static int
nch(struct parse *p, cset *cs)
{
	int i;
	size_t css = (size_t)p->g->csetsize;
	int n = 0;

	for (i = 0; i < css; i++)
		if (CHIN(cs, i))
			n++;
	return(n);
}

/*
 - mcadd - add a collating element to a cset
 */
static void
mcadd( struct parse *p, cset *cs, char *cp)
{
	size_t oldend = cs->smultis;
	void *np;

	cs->smultis += strlen(cp) + 1;
	np = realloc(cs->multis, cs->smultis);
	if (np == NULL) {
		free(cs->multis);
		cs->multis = NULL;
		SETERROR(REG_ESPACE);
		return;
	}
	cs->multis = np;

	strlcpy(cs->multis + oldend - 1, cp, cs->smultis - oldend + 1);
}

/*
 - mcinvert - invert the list of collating elements in a cset
 *
 * This would have to know the set of possibilities.  Implementation
 * is deferred.
 */
static void
mcinvert(struct parse *p, cset *cs)
{
	assert(cs->multis == NULL);	/* xxx */
}

/*
 - mccase - add case counterparts of the list of collating elements in a cset
 *
 * This would have to know the set of possibilities.  Implementation
 * is deferred.
 */
static void
mccase(struct parse *p, cset *cs)
{
	assert(cs->multis == NULL);	/* xxx */
}

/*
 - isinsets - is this character in any sets?
 */
static int			/* predicate */
isinsets(struct re_guts *g, int c)
{
	uch *col;
	int i;
	int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
	unsigned uc = (uch)c;

	for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
		if (col[uc] != 0)
			return(1);
	return(0);
}

/*
 - samesets - are these two characters in exactly the same sets?
 */
static int			/* predicate */
samesets(struct re_guts *g, int c1, int c2)
{
	uch *col;
	int i;
	int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
	unsigned uc1 = (uch)c1;
	unsigned uc2 = (uch)c2;

	for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
		if (col[uc1] != col[uc2])
			return(0);
	return(1);
}

/*
 - categorize - sort out character categories
 */
static void
categorize(struct parse *p, struct re_guts *g)
{
	cat_t *cats = g->categories;
	int c;
	int c2;
	cat_t cat;

	/* avoid making error situations worse */
	if (p->error != 0)
		return;

	for (c = CHAR_MIN; c <= CHAR_MAX; c++)
		if (cats[c] == 0 && isinsets(g, c)) {
			cat = g->ncategories++;
			cats[c] = cat;
			for (c2 = c+1; c2 <= CHAR_MAX; c2++)
				if (cats[c2] == 0 && samesets(g, c, c2))
					cats[c2] = cat;
		}
}

/*
 - dupl - emit a duplicate of a bunch of sops
 */
static sopno			/* start of duplicate */
dupl(struct parse *p,
    sopno start,		/* from here */
    sopno finish)		/* to this less one */
{
	sopno ret = HERE();
	sopno len = finish - start;

	assert(finish >= start);
	if (len == 0)
		return(ret);
	if (!enlarge(p, p->ssize + len)) /* this many unexpected additions */
		return(ret);
	(void) memcpy(p->strip + p->slen, p->strip + start, len * sizeof(sop));
	p->slen += len;
	return(ret);
}

/*
 - doemit - emit a strip operator
 *
 * It might seem better to implement this as a macro with a function as
 * hard-case backup, but it's just too big and messy unless there are
 * some changes to the data structures.  Maybe later.
 */
static void
doemit(struct parse *p, sop op, size_t opnd)
{
	/* avoid making error situations worse */
	if (p->error != 0)
		return;

	/* deal with oversize operands ("can't happen", more or less) */
	assert(opnd < 1<<OPSHIFT);

	/* deal with undersized strip */
	if (p->slen >= p->ssize)
		if (!enlarge(p, (p->ssize+1) / 2 * 3))	/* +50% */
			return;

	/* finally, it's all reduced to the easy case */
	p->strip[p->slen++] = SOP(op, opnd);
}

/*
 - doinsert - insert a sop into the strip
 */
static void
doinsert(struct parse *p, sop op, size_t opnd, sopno pos)
{
	sopno sn;
	sop s;
	int i;

	/* avoid making error situations worse */
	if (p->error != 0)
		return;

	sn = HERE();
	EMIT(op, opnd);		/* do checks, ensure space */
	assert(HERE() == sn+1);
	s = p->strip[sn];

	/* adjust paren pointers */
	assert(pos > 0);
	for (i = 1; i < NPAREN; i++) {
		if (p->pbegin[i] >= pos) {
			p->pbegin[i]++;
		}
		if (p->pend[i] >= pos) {
			p->pend[i]++;
		}
	}

	memmove((char *)&p->strip[pos+1], (char *)&p->strip[pos],
						(HERE()-pos-1)*sizeof(sop));
	p->strip[pos] = s;
}

/*
 - dofwd - complete a forward reference
 */
static void
dofwd(struct parse *p, sopno pos, sop value)
{
	/* avoid making error situations worse */
	if (p->error != 0)
		return;

	assert(value < 1<<OPSHIFT);
	p->strip[pos] = OP(p->strip[pos]) | value;
}

/*
 - enlarge - enlarge the strip
 */
static int
enlarge(struct parse *p, sopno size)
{
	sop *sp;

	if (p->ssize >= size)
		return 1;

	sp = reallocarray(p->strip, size, sizeof(sop));
	if (sp == NULL) {
		SETERROR(REG_ESPACE);
		return 0;
	}
	p->strip = sp;
	p->ssize = size;
	return 1;
}

/*
 - stripsnug - compact the strip
 */
static void
stripsnug(struct parse *p, struct re_guts *g)
{
	g->nstates = p->slen;
	g->strip = reallocarray(p->strip, p->slen, sizeof(sop));
	if (g->strip == NULL) {
		SETERROR(REG_ESPACE);
		g->strip = p->strip;
	}
}

/*
 - findmust - fill in must and mlen with longest mandatory literal string
 *
 * This algorithm could do fancy things like analyzing the operands of |
 * for common subsequences.  Someday.  This code is simple and finds most
 * of the interesting cases.
 *
 * Note that must and mlen got initialized during setup.
 */
static void
findmust(struct parse *p, struct re_guts *g)
{
	sop *scan;
	sop *start;    /* start initialized in the default case, after that */
	sop *newstart; /* newstart was initialized in the OCHAR case */
	sopno newlen;
	sop s;
	char *cp;
	sopno i;

	/* avoid making error situations worse */
	if (p->error != 0)
		return;

	/* find the longest OCHAR sequence in strip */
	newlen = 0;
	scan = g->strip + 1;
	do {
		s = *scan++;
		switch (OP(s)) {
		case OCHAR:		/* sequence member */
			if (newlen == 0)		/* new sequence */
				newstart = scan - 1;
			newlen++;
			break;
		case OPLUS_:		/* things that don't break one */
		case OLPAREN:
		case ORPAREN:
			break;
		case OQUEST_:		/* things that must be skipped */
		case OCH_:
			scan--;
			do {
				scan += OPND(s);
				s = *scan;
				/* assert() interferes w debug printouts */
				if (OP(s) != O_QUEST && OP(s) != O_CH &&
							OP(s) != OOR2) {
					g->iflags |= BAD;
					return;
				}
			} while (OP(s) != O_QUEST && OP(s) != O_CH);
			/* fallthrough */
		default:		/* things that break a sequence */
			if (newlen > g->mlen) {		/* ends one */
				start = newstart;
				g->mlen = newlen;
			}
			newlen = 0;
			break;
		}
	} while (OP(s) != OEND);

	if (g->mlen == 0)		/* there isn't one */
		return;

	/* turn it into a character string */
	g->must = malloc((size_t)g->mlen + 1);
	if (g->must == NULL) {		/* argh; just forget it */
		g->mlen = 0;
		return;
	}
	cp = g->must;
	scan = start;
	for (i = g->mlen; i > 0; i--) {
		while (OP(s = *scan++) != OCHAR)
			continue;
		assert(cp < g->must + g->mlen);
		*cp++ = (char)OPND(s);
	}
	assert(cp == g->must + g->mlen);
	*cp++ = '\0';		/* just on general principles */
}

/*
 - pluscount - count + nesting
 */
static sopno			/* nesting depth */
pluscount(struct parse *p, struct re_guts *g)
{
	sop *scan;
	sop s;
	sopno plusnest = 0;
	sopno maxnest = 0;

	if (p->error != 0)
		return(0);	/* there may not be an OEND */

	scan = g->strip + 1;
	do {
		s = *scan++;
		switch (OP(s)) {
		case OPLUS_:
			plusnest++;
			break;
		case O_PLUS:
			if (plusnest > maxnest)
				maxnest = plusnest;
			plusnest--;
			break;
		}
	} while (OP(s) != OEND);
	if (plusnest != 0)
		g->iflags |= BAD;
	return(maxnest);
}