-
Notifications
You must be signed in to change notification settings - Fork 1
/
regex.c
3464 lines (3007 loc) · 91.8 KB
/
regex.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
/* Copyright 2009-2024
* Kaz Kylheku <kaz@kylheku.com>
* Vancouver, Canada
* All rights reserved.
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT HOLDER 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.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>
#include <assert.h>
#include <limits.h>
#include <signal.h>
#include <stdarg.h>
#include "config.h"
#include "alloca.h"
#include "lib.h"
#include "parser.h"
#include "signal.h"
#include "unwind.h"
#include "stream.h"
#include "gc.h"
#include "eval.h"
#include "cadr.h"
#include "itypes.h"
#include "regex.h"
#include "txr.h"
#if WCHAR_MAX > 65535
#define FULL_UNICODE
#endif
typedef union nfa_state nfa_state_t;
typedef struct nfa {
nfa_state_t *start;
nfa_state_t *accept;
} nfa_t;
typedef enum { REGEX_NFA, REGEX_DV } regex_kind_t;
typedef struct regex {
regex_kind_t kind;
union {
struct nfa nfa;
val dv;
} r;
int nstates;
val source;
} regex_t;
/*
* Result from regex_machine_feed.
* These values have two meanings, based on whether
* the matching is still open (characters are being fed)
* or finalized.
*
* When feeding characters:
* REGM_INCOMPLETE: no match at this character, but matching can continue.
* REGM_FAIL: no more state transitions are possible.
* REGM_MATCH: match (accept state) for this character.
* REGM_MATCH_DONE: match (accept state) for this character, and no more
* moves are possible.
*
* When the end of the input is encountered, or a REGM_FAIL,
* then regex_machine_feed is called one more time with
* the null character. It then reports:
* REGM_INCOMPLETE: there was a partial match for the input.
* REGM_FAIL: none of the input matched.
* REGM_MATCH: the input was completely matched
* REGM_MATCH_DONE: not returned.
*
* Note that a REGM_FAIL (no transitions) during the character feeding phase
* can turn into REGM_INCOMPLETE (partial match) when the match is sealed with
* the null character signal!
*/
typedef enum regm_result {
REGM_INCOMPLETE,
REGM_FAIL,
REGM_MATCH,
REGM_MATCH_DONE
} regm_result_t;
typedef union regex_machine regex_machine_t;
typedef unsigned int bitcell_t;
#define CHAR_SET_SIZE (256 / (sizeof (bitcell_t) * CHAR_BIT))
#define BITCELL_BIT (sizeof (bitcell_t) * CHAR_BIT)
#define CHAR_SET_INDEX(CH) ((CH) / BITCELL_BIT)
#define CHAR_SET_BIT(CH) ((CH) % BITCELL_BIT)
#define CHAR_SET_L0(CH) ((CH) & 0xFF)
#define CHAR_SET_L1(CH) (((CH) >> 8) & 0xF)
#define CHAR_SET_L2(CH) (((CH) >> 12) & 0xF)
#ifdef FULL_UNICODE
#define CHAR_SET_L3(CH) (((CH) >> 16) & 0x1F)
#endif
#ifdef FULL_UNICODE
#define CHAR_SET_L2_LO(CH) ((CH) & ~convert(wchar_t, 0xFFFF))
#define CHAR_SET_L2_HI(CH) ((CH) | convert(wchar_t, 0xFFFF))
#endif
#define CHAR_SET_L1_LO(CH) ((CH) & ~convert(wchar_t, 0xFFF))
#define CHAR_SET_L1_HI(CH) ((CH) | convert(wchar_t, 0xFFF))
#define CHAR_SET_L0_LO(CH) ((CH) & ~convert(wchar_t, 0xFF))
#define CHAR_SET_L0_HI(CH) ((CH) | convert(wchar_t, 0xFF))
typedef enum {
CHSET_SMALL, CHSET_DISPLACED, CHSET_LARGE,
#ifdef FULL_UNICODE
CHSET_XLARGE
#endif
} chset_type_t;
typedef bitcell_t cset_L0_t[CHAR_SET_SIZE];
typedef cset_L0_t *cset_L1_t[16];
typedef cset_L1_t *cset_L2_t[16];
#ifdef FULL_UNICODE
typedef cset_L2_t *cset_L3_t[17];
#endif
struct any_char_set {
unsigned type : 3;
unsigned comp : 1;
unsigned stat : 1;
};
struct small_char_set {
unsigned type : 3;
unsigned comp : 1;
unsigned stat : 1;
cset_L0_t bitcell;
};
struct displaced_char_set {
unsigned type : 3;
unsigned comp : 1;
unsigned stat : 1;
cset_L0_t bitcell;
wchar_t base;
};
struct large_char_set {
unsigned type : 3;
unsigned comp : 1;
unsigned stat : 1;
cset_L2_t dir;
};
#ifdef FULL_UNICODE
struct xlarge_char_set {
unsigned type : 3;
unsigned comp : 1;
unsigned stat : 1;
cset_L3_t dir;
};
#endif
typedef union char_set {
struct any_char_set any;
struct small_char_set s;
struct displaced_char_set d;
struct large_char_set l;
#ifdef FULL_UNICODE
struct xlarge_char_set xl;
#endif
} char_set_t;
typedef enum {
nfa_empty, nfa_accept, nfa_wild, nfa_single, nfa_set
} nfa_kind_t;
struct nfa_state_any {
nfa_kind_t kind;
unsigned visited;
};
struct nfa_state_empty {
nfa_kind_t kind;
unsigned visited;
nfa_state_t *trans0;
nfa_state_t *trans1;
};
struct nfa_state_single {
nfa_kind_t kind;
unsigned visited;
nfa_state_t *trans;
wchar_t ch;
};
struct nfa_state_set {
nfa_kind_t kind;
unsigned visited;
nfa_state_t *trans;
char_set_t *set;
};
union nfa_state {
struct nfa_state_any a;
struct nfa_state_empty e;
struct nfa_state_single o;
struct nfa_state_set s;
};
#define nfa_accept_state_p(s) ((s)->a.kind == nfa_accept)
#define nfa_empty_state_p(s) ((s)->a.kind == nfa_accept || \
(s)->a.kind == nfa_empty)
#define nfa_has_transitions(s) ((s)->a.kind != nfa_empty || \
(s)->e.trans0 || (s)->e.trans1)
struct nfa_machine {
int is_nfa; /* common member */
cnum last_accept_pos; /* common member */
cnum count; /* common member */
unsigned visited;
nfa_state_t **set, **stack;
int nclos;
nfa_t nfa;
int nstates;
};
struct dv_machine {
int is_nfa; /* common member */
cnum last_accept_pos; /* common member */
cnum count; /* common member */
val deriv;
val regex;
};
union regex_machine {
struct nfa_machine n;
struct dv_machine d;
};
int opt_derivative_regex = 0;
struct cobj_class *regex_cls;
static struct cobj_class *chset_cls;
wchar_t spaces[] = {
0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x0020, 0x00a0, 0x1680, 0x180e,
0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, 0x2006, 0x2007, 0x2008,
0x2009, 0x200a, 0x2028, 0x2029, 0x205f, 0x3000, 0
};
static int L0_full(cset_L0_t *L0)
{
int i;
for (i = 0; i < convert(int, CHAR_SET_SIZE); i++)
if ((*L0)[i] != convert(bitcell_t, -1))
return 0;
return 1;
}
static void L0_fill_range(cset_L0_t *L0, wchar_t ch0, wchar_t ch1)
{
int i;
int bt0 = CHAR_SET_BIT(ch0);
int bc0 = CHAR_SET_INDEX(ch0);
bitcell_t mask0 = ~((convert(bitcell_t, 1) << bt0) - 1);
int bt1 = CHAR_SET_BIT(ch1);
int bc1 = CHAR_SET_INDEX(ch1);
bitcell_t mask1 = (bt1 == (BITCELL_BIT - 1))
? convert(bitcell_t, -1)
: (convert(bitcell_t, 1) << (bt1 + 1)) - 1;
if (bc1 == bc0) {
(*L0)[bc0] |= (mask0 & mask1);
} else {
(*L0)[bc0] |= mask0;
(*L0)[bc1] |= mask1;
for (i = bc0 + 1; i < bc1; i++)
(*L0)[i] = convert(bitcell_t, -1);
}
}
static int L0_contains(cset_L0_t *L0, wchar_t ch)
{
return ((*L0)[CHAR_SET_INDEX(ch)] &
(convert(bitcell_t, 1) << CHAR_SET_BIT(ch))) != 0;
}
static int L1_full(cset_L1_t *L1)
{
int i;
for (i = 0; i < 16; i++)
if ((*L1)[i] != coerce(cset_L0_t *, -1))
return 0;
return 1;
}
static void L1_fill_range(cset_L1_t *L1, wchar_t ch0, wchar_t ch1)
{
int i1, i10, i11;
i10 = CHAR_SET_L1(ch0);
i11 = CHAR_SET_L1(ch1);
for (i1 = i10; i1 <= i11; i1++) {
wchar_t c0 = 0, c1 = 0;
cset_L0_t *L0;
if (i1 > i10 && i1 < i11) {
if ((*L1)[i1] != coerce(cset_L0_t *, -1)) {
free((*L1)[i1]);
(*L1)[i1] = coerce(cset_L0_t *, -1);
}
continue;
} else if (i10 == i11) {
c0 = ch0;
c1 = ch1;
} else if (i1 == i10) {
c0 = ch0;
c1 = CHAR_SET_L0_HI(ch0);
} else if (i1 == i11) {
c0 = CHAR_SET_L0_LO(ch1);
c1 = ch1;
}
if ((L0 = (*L1)[i1]) == coerce(cset_L0_t *, -1))
continue;
if (L0 == 0) {
static cset_L0_t blank;
L0 = (*L1)[i1] = coerce(cset_L0_t *, chk_malloc(sizeof *L0));
memcpy(L0, &blank, sizeof *L0);
}
L0_fill_range(L0, CHAR_SET_L0(c0), CHAR_SET_L0(c1));
if (L0_full(L0)) {
free(L0);
(*L1)[i1] = coerce(cset_L0_t *, -1);
}
}
}
static int L1_contains(cset_L1_t *L1, wchar_t ch)
{
int i1 = CHAR_SET_L1(ch);
cset_L0_t *L0 = (*L1)[i1];
if (L0 == 0)
return 0;
else if (L0 == coerce(cset_L0_t *, -1))
return 1;
else
return L0_contains(L0, CHAR_SET_L0(ch));
}
static void L1_free(cset_L1_t *L1)
{
int i1;
if (L1 == coerce(cset_L1_t *, -1))
return;
for (i1 = 0; i1 < 16; i1++)
if ((*L1)[i1] != coerce(cset_L0_t *, -1))
free((*L1)[i1]);
}
#ifdef FULL_UNICODE
static int L2_full(cset_L2_t *L2)
{
int i;
for (i = 0; i < 16; i++)
if ((*L2)[i] != coerce(cset_L1_t *, -1))
return 0;
return 1;
}
#endif
static void L2_fill_range(cset_L2_t *L2, wchar_t ch0, wchar_t ch1)
{
int i2, i20, i21;
i20 = CHAR_SET_L2(ch0);
i21 = CHAR_SET_L2(ch1);
for (i2 = i20; i2 <= i21; i2++) {
wchar_t c0 = 0, c1 = 0;
cset_L1_t *L1;
if (i2 > i20 && i2 < i21) {
if ((*L2)[i2] != coerce(cset_L1_t *, -1)) {
free((*L2)[i2]);
(*L2)[i2] = coerce(cset_L1_t *, -1);
}
continue;
} else if (i20 == i21) {
c0 = ch0;
c1 = ch1;
} else if (i2 == i20) {
c0 = ch0;
c1 = CHAR_SET_L1_HI(ch0);
} else if (i2 == i21) {
c0 = CHAR_SET_L1_LO(ch1);
c1 = ch1;
}
if ((L1 = (*L2)[i2]) == coerce(cset_L1_t *, -1))
continue;
if (L1 == 0) {
static cset_L1_t blank;
L1 = (*L2)[i2] = coerce(cset_L1_t *, chk_malloc(sizeof *L1));
memcpy(L1, &blank, sizeof *L1);
}
L1_fill_range(L1, c0, c1);
if (L1_full(L1)) {
free(L1);
(*L2)[i2] = coerce(cset_L1_t *, -1);
}
}
}
static int L2_contains(cset_L2_t *L2, wchar_t ch)
{
int i2 = CHAR_SET_L2(ch);
cset_L1_t *L1 = (*L2)[i2];
if (L1 == 0)
return 0;
else if (L1 == coerce(cset_L1_t *, -1))
return 1;
else
return L1_contains(L1, ch);
}
static void L2_free(cset_L2_t *L2)
{
int i2;
for (i2 = 0; i2 < 16; i2++) {
cset_L1_t *L1 = (*L2)[i2];
if (L1 != 0 && L1 != coerce(cset_L1_t *, -1)) {
L1_free((*L2)[i2]);
free((*L2)[i2]);
}
}
}
#ifdef FULL_UNICODE
static void L3_fill_range(cset_L3_t *L3, wchar_t ch0, wchar_t ch1)
{
int i3, i30, i31;
i30 = CHAR_SET_L3(ch0);
i31 = CHAR_SET_L3(ch1);
for (i3 = i30; i3 <= i31; i3++) {
wchar_t c0 = 0, c1 = 0;
cset_L2_t *L2;
if (i3 > i30 && i3 < i31) {
if ((*L3)[i3] != coerce(cset_L2_t *, -1)) {
free((*L3)[i3]);
(*L3)[i3] = coerce(cset_L2_t *, -1);
}
continue;
} else if (i30 == i31) {
c0 = ch0;
c1 = ch1;
} else if (i3 == i30) {
c0 = ch0;
c1 = CHAR_SET_L2_HI(ch0);
} else if (i3 == i31) {
c0 = CHAR_SET_L2_LO(ch1);
c1 = ch1;
}
if ((L2 = (*L3)[i3]) == coerce(cset_L2_t *, -1))
continue;
if (L2 == 0) {
static cset_L2_t blank;
L2 = (*L3)[i3] = coerce(cset_L2_t *, chk_malloc(sizeof *L2));
memcpy(L2, &blank, sizeof *L2);
}
L2_fill_range(L2, c0, c1);
if (L2_full(L2)) {
free(L2);
(*L3)[i3] = coerce(cset_L2_t *, -1);
}
}
}
static int L3_contains(cset_L3_t *L3, wchar_t ch)
{
int i3 = CHAR_SET_L3(ch);
cset_L2_t *L2 = (*L3)[i3];
if (L2 == 0)
return 0;
else if (L2 == coerce(cset_L2_t *, -1))
return 1;
else
return L2_contains(L2, ch);
}
static void L3_free(cset_L3_t *L3)
{
int i3;
for (i3 = 0; i3 < 17; i3++) {
cset_L2_t *L2 = (*L3)[i3];
if (L2 != 0 && L2 != coerce(cset_L2_t *, -1)) {
L2_free((*L3)[i3]);
free((*L3)[i3]);
}
}
}
#endif
static char_set_t *char_set_create(chset_type_t type, wchar_t base, unsigned st)
{
static char_set_t blank;
char_set_t *cs = coerce(char_set_t *, chk_malloc(sizeof *cs));
*cs = blank;
cs->any.type = type;
cs->any.stat = st;
if (type == CHSET_DISPLACED)
cs->d.base = base;
return cs;
}
static void char_set_destroy(char_set_t *set, int force)
{
if (!set)
return;
if (set->any.stat && !force)
return;
switch (set->any.type) {
case CHSET_DISPLACED:
case CHSET_SMALL:
free(set);
break;
case CHSET_LARGE:
L2_free(&set->l.dir);
free(set);
break;
#ifdef FULL_UNICODE
case CHSET_XLARGE:
L3_free(&set->xl.dir);
free(set);
break;
#endif
}
}
static void char_set_compl(char_set_t *set)
{
set->any.comp = 1;
}
static void char_set_add(char_set_t *set, wchar_t ch)
{
switch (set->any.type) {
case CHSET_DISPLACED:
assert (ch >= set->d.base && ch < set->d.base + 256);
ch -= set->d.base;
/* fallthrough */
case CHSET_SMALL:
assert (ch < 256);
set->s.bitcell[CHAR_SET_INDEX(ch)] |= (convert(bitcell_t, 1)
<< CHAR_SET_BIT(ch));
break;
case CHSET_LARGE:
assert (ch < 0x10000);
L2_fill_range(&set->l.dir, ch, ch);
break;
#ifdef FULL_UNICODE
case CHSET_XLARGE:
assert (ch < 0x110000);
L3_fill_range(&set->xl.dir, ch, ch);
break;
#endif
}
}
static void char_set_add_range(char_set_t *set, wchar_t ch0, wchar_t ch1)
{
if (ch0 >= ch1)
return;
switch (set->any.type) {
case CHSET_DISPLACED:
assert (ch0 >= set->d.base && ch1 < set->d.base + 256);
ch0 -= set->d.base;
ch1 -= set->d.base;
/* fallthrough */
case CHSET_SMALL:
assert (ch1 < 256);
L0_fill_range(&set->s.bitcell, ch0, ch1);
break;
case CHSET_LARGE:
assert (ch1 < 0x10000);
L2_fill_range(&set->l.dir, ch0, ch1);
break;
#ifdef FULL_UNICODE
case CHSET_XLARGE:
assert (ch1 < 0x110000);
L3_fill_range(&set->xl.dir, ch0, ch1);
break;
#endif
}
}
static void char_set_add_str(char_set_t *set, wchar_t *str)
{
while (*str != 0)
char_set_add(set, *str++);
}
static int char_set_contains(char_set_t *set, wchar_t ch)
{
int result = 0;
switch (set->any.type) {
case CHSET_DISPLACED:
if (ch < set->d.base)
break;
ch -= set->d.base;
/* fallthrough */
case CHSET_SMALL:
if (ch >= 256)
break;
result = L0_contains(&set->s.bitcell, ch);
break;
case CHSET_LARGE:
if (ch >= 0x10000)
break;
result = L2_contains(&set->l.dir, ch);
break;
#ifdef FULL_UNICODE
case CHSET_XLARGE:
if (ch >= 0x110000)
break;
result = L3_contains(&set->xl.dir, ch);
break;
#endif
}
return set->any.comp ? !result : result;
}
static char_set_t *char_set_compile(val args, val comp)
{
val iter;
wchar_t min = WCHAR_MAX;
wchar_t max = 0;
chset_type_t cst;
for (iter = args; iter; iter = rest(iter)) {
val item = first(iter);
if (consp(item)) {
val from = car(item);
val to = cdr(item);
assert (is_chr(from) && is_chr(to));
if (c_chr(from) < min)
min = c_chr(from);
if (c_chr(from) > max)
max = c_chr(from);
if (c_chr(to) < min)
min = c_chr(to);
if (c_chr(to) > max)
max = c_chr(to);
} else if (is_chr(item)) {
if (c_chr(item) < min)
min = c_chr(item);
if (c_chr(item) > max)
max = c_chr(item);
} else if (item == space_k) {
if (max < 0x3000)
max = 0x3000;
if (min > 0x9)
min = 0x9;
} else if (item == digit_k) {
if (max < '9')
max = 9;
if (min > '0')
min = 0;
} else if (item == word_char_k) {
if (min > 'A')
min = 'A';
if (max < 'z')
max = 'z';
} else if (item == cspace_k || item == cdigit_k || item == cword_char_k) {
uw_throwf(error_s, lit("bad object in character class syntax: ~s"),
item, nao);
} else {
assert(0 && "bad regex set");
}
}
if (max < 0x100)
cst = CHSET_SMALL;
else if (max - min < 0x100)
cst = CHSET_DISPLACED;
else if (max < 0x10000)
cst = CHSET_LARGE;
else
#ifdef FULL_UNICODE
cst = CHSET_XLARGE;
#else
cst = CHSET_LARGE;
#endif
{
char_set_t *set = char_set_create(cst, min, 0);
for (iter = args; iter; iter = rest(iter)) {
val item = first(iter);
if (consp(item)) {
val from = car(item);
val to = cdr(item);
assert (is_chr(from) && is_chr(to));
char_set_add_range(set, c_chr(from), c_chr(to));
} else if (is_chr(item)) {
char_set_add(set, c_chr(item));
} else if (item == space_k) {
char_set_add_str(set, spaces);
} else if (item == digit_k) {
char_set_add_range(set, '0', '9');
} else if (item == word_char_k) {
char_set_add_range(set, 'A', 'Z');
char_set_add_range(set, 'a', 'z');
char_set_add(set, '_');
} else {
assert(0 && "bad regex set");
}
}
if (comp)
char_set_compl(set);
return set;
}
}
static char_set_t *space_cs, *digit_cs, *word_cs;
static char_set_t *cspace_cs, *cdigit_cs, *cword_cs;
static void init_special_char_sets(void)
{
space_cs = char_set_create(CHSET_LARGE, 0, 1);
cspace_cs = char_set_create(CHSET_LARGE, 0, 1);
digit_cs = char_set_create(CHSET_SMALL, 0, 1);
cdigit_cs = char_set_create(CHSET_SMALL, 0, 1);
word_cs = char_set_create(CHSET_SMALL, 0, 1);
cword_cs = char_set_create(CHSET_SMALL, 0, 1);
char_set_compl(cspace_cs);
char_set_compl(cdigit_cs);
char_set_compl(cword_cs);
char_set_add_str(space_cs, spaces);
char_set_add_str(cspace_cs, spaces);
char_set_add_range(digit_cs, '0', '9');
char_set_add_range(cdigit_cs, '0', '9');
char_set_add_range(word_cs, 'A', 'Z');
char_set_add_range(cword_cs, 'A', 'Z');
char_set_add_range(word_cs, 'a', 'z');
char_set_add_range(cword_cs, 'a', 'z');
char_set_add(word_cs, '_');
char_set_add(cword_cs, '_');
}
static void char_set_cobj_destroy(val chset)
{
char_set_t *set = coerce(char_set_t *, chset->co.handle);
char_set_destroy(set, 0);
chset->co.handle = 0;
}
static struct cobj_ops char_set_obj_ops = cobj_ops_init(eq,
cobj_print_op,
char_set_cobj_destroy,
cobj_mark_op,
cobj_eq_hash_op,
0);
static nfa_state_t *nfa_state_accept(void)
{
nfa_state_t *st = coerce(nfa_state_t *, chk_malloc(sizeof *st));
st->e.kind = nfa_accept;
st->e.visited = 0;
st->e.trans0 = st->e.trans1 = 0;
return st;
}
static nfa_state_t *nfa_state_empty(nfa_state_t *t0, nfa_state_t *t1)
{
nfa_state_t *st = coerce(nfa_state_t *, chk_malloc(sizeof *st));
st->e.kind = nfa_empty;
st->e.visited = 0;
st->e.trans0 = t0;
st->e.trans1 = t1;
return st;
}
static nfa_state_t *nfa_state_single(nfa_state_t *t, wchar_t ch)
{
nfa_state_t *st = coerce(nfa_state_t *, chk_malloc(sizeof *st));
st->o.kind = nfa_single;
st->o.visited = 0;
st->o.trans = t;
st->o.ch = ch;
return st;
}
static nfa_state_t *nfa_state_wild(nfa_state_t *t)
{
nfa_state_t *st = coerce(nfa_state_t *, chk_malloc(sizeof *st));
st->o.kind = nfa_wild;
st->o.visited = 0;
st->o.trans = t;
st->o.ch = 0;
return st;
}
static void nfa_state_free(nfa_state_t *st)
{
if (st->a.kind == nfa_set)
char_set_destroy(st->s.set, 0);
free(st);
}
static void nfa_state_shallow_free(nfa_state_t *st)
{
free(st);
}
static nfa_state_t *nfa_state_set(nfa_state_t *t, char_set_t *cs)
{
nfa_state_t *st = coerce(nfa_state_t *, chk_malloc(sizeof *st));
st->s.kind = nfa_set;
st->s.visited = 0;
st->s.trans = t;
st->s.set = cs;
return st;
}
/*
* An acceptance state is converted to an empty transition
* state with specified transitions. It thereby loses
* its acceptance state status. This is used during
* compilation to hook new output paths into an inner NFA,
* either back to itself, or to a new state in the
* surrounding new NFA.
*/
static void nfa_state_empty_convert(nfa_state_t *acc, nfa_state_t *t0,
nfa_state_t *t1)
{
assert (nfa_accept_state_p(acc));
acc->e.kind = nfa_empty;
acc->e.trans0 = t0;
acc->e.trans1 = t1;
}
/*
* Acceptance state takes on the kind of st, and all associated
* data. I.e. we merge the identity of accept,
* with the contents of st, such that the new state has
* all of the outgoing arrows of st, and
* all of the incoming arrows of acc.
* This is easily done with an assignment, provided
* that st doesn't have any incoming arrows.
* We ensure that start states don't have any incoming
* arrows in the compiler, by ensuring that repetition
* operators terminate their backwards arrows on an
* existing start state, and allocate a new start
* state in front of it.
*/
static void nfa_state_merge(nfa_state_t *acc, nfa_state_t *st)
{
assert (nfa_accept_state_p(acc));
*acc = *st;
}
static nfa_t nfa_make(nfa_state_t *s, nfa_state_t *acc)
{
nfa_t ret;
ret.start = s;
ret.accept = acc;
return ret;
}
/*
* Combine two NFA's representing regexps that are catenated.
* The acceptance state of the predecessor is merged with the start state of
* the successor.
*/
static nfa_t nfa_combine(nfa_t pred, nfa_t succ)
{
nfa_t ret;
ret.start = pred.start;
ret.accept = succ.accept;
nfa_state_merge(pred.accept, succ.start);
nfa_state_shallow_free(succ.start); /* No longer needed. */
return ret;
}
static nfa_t nfa_compile_set(val args, val comp)
{
char_set_t *set = char_set_compile(args, comp);
nfa_state_t *acc = nfa_state_accept();
nfa_state_t *s = nfa_state_set(acc, set);
return nfa_make(s, acc);
}
static nfa_t nfa_compile_given_set(char_set_t *set)
{
nfa_state_t *acc = nfa_state_accept();
nfa_state_t *s = nfa_state_set(acc, set);
return nfa_make(s, acc);
}
static nfa_t nfa_compile_regex(val regex);
/*
* Helper to nfa_compile_regex for compiling the argument list of
* a compound regex.
*/
static nfa_t nfa_compile_list(val exp_list)
{
nfa_t nfa_first = nfa_compile_regex(first(exp_list));
if (rest(exp_list)) {
nfa_t nfa_rest = nfa_compile_list(rest(exp_list));
return nfa_combine(nfa_first, nfa_rest);
} else {
return nfa_first;
}
}
/*
* Input is the items from a regex form,
* not including the regex symbol.
* I.e. (rest '(regex ...)) not '(regex ...).
*/
static nfa_t nfa_compile_regex(val exp)
{
if (nilp(exp)) {
nfa_state_t *acc = nfa_state_accept();
nfa_state_t *s = nfa_state_empty(acc, 0);
return nfa_make(s, acc);
} else if (chrp(exp)) {