-
Notifications
You must be signed in to change notification settings - Fork 0
/
regcomp.c
3958 lines (3602 loc) · 111 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
/* Extended regular expression matching and search library.
Copyright (C) 2002-2015 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <[email protected]>.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
#ifdef HAVE_STDINT_H
#include <stdint.h>
#endif
#ifdef _LIBC
# include <locale/weight.h>
#endif
static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern,
size_t length, reg_syntax_t syntax);
static void re_compile_fastmap_iter (regex_t *bufp,
const re_dfastate_t *init_state,
char *fastmap);
static reg_errcode_t init_dfa (re_dfa_t *dfa, size_t pat_len);
#ifdef RE_ENABLE_I18N
static void free_charset (re_charset_t *cset);
#endif /* RE_ENABLE_I18N */
static void free_workarea_compile (regex_t *preg);
static reg_errcode_t create_initial_state (re_dfa_t *dfa);
#ifdef RE_ENABLE_I18N
static void optimize_utf8 (re_dfa_t *dfa);
#endif
static reg_errcode_t analyze (regex_t *preg);
static reg_errcode_t preorder (bin_tree_t *root,
reg_errcode_t (fn (void *, bin_tree_t *)),
void *extra);
static reg_errcode_t postorder (bin_tree_t *root,
reg_errcode_t (fn (void *, bin_tree_t *)),
void *extra);
static reg_errcode_t optimize_subexps (void *extra, bin_tree_t *node);
static reg_errcode_t lower_subexps (void *extra, bin_tree_t *node);
static bin_tree_t *lower_subexp (reg_errcode_t *err, regex_t *preg,
bin_tree_t *node);
static reg_errcode_t calc_first (void *extra, bin_tree_t *node);
static reg_errcode_t calc_next (void *extra, bin_tree_t *node);
static reg_errcode_t link_nfa_nodes (void *extra, bin_tree_t *node);
static int duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint);
static int search_duplicated_node (const re_dfa_t *dfa, int org_node,
unsigned int constraint);
static reg_errcode_t calc_eclosure (re_dfa_t *dfa);
static reg_errcode_t calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa,
int node, int root);
static reg_errcode_t calc_inveclosure (re_dfa_t *dfa);
static int fetch_number (re_string_t *input, re_token_t *token,
reg_syntax_t syntax);
static int peek_token (re_token_t *token, re_string_t *input,
reg_syntax_t syntax) internal_function;
static bin_tree_t *parse (re_string_t *regexp, regex_t *preg,
reg_syntax_t syntax, reg_errcode_t *err);
static bin_tree_t *parse_reg_exp (re_string_t *regexp, regex_t *preg,
re_token_t *token, reg_syntax_t syntax,
int nest, reg_errcode_t *err);
static bin_tree_t *parse_branch (re_string_t *regexp, regex_t *preg,
re_token_t *token, reg_syntax_t syntax,
int nest, reg_errcode_t *err);
static bin_tree_t *parse_expression (re_string_t *regexp, regex_t *preg,
re_token_t *token, reg_syntax_t syntax,
int nest, reg_errcode_t *err);
static bin_tree_t *parse_sub_exp (re_string_t *regexp, regex_t *preg,
re_token_t *token, reg_syntax_t syntax,
int nest, reg_errcode_t *err);
static bin_tree_t *parse_dup_op (bin_tree_t *dup_elem, re_string_t *regexp,
re_dfa_t *dfa, re_token_t *token,
reg_syntax_t syntax, reg_errcode_t *err);
static bin_tree_t *parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa,
re_token_t *token, reg_syntax_t syntax,
reg_errcode_t *err);
static reg_errcode_t parse_bracket_element (bracket_elem_t *elem,
re_string_t *regexp,
re_token_t *token, int token_len,
re_dfa_t *dfa,
reg_syntax_t syntax,
int accept_hyphen);
static reg_errcode_t parse_bracket_symbol (bracket_elem_t *elem,
re_string_t *regexp,
re_token_t *token);
#ifdef RE_ENABLE_I18N
static reg_errcode_t build_equiv_class (bitset_t sbcset,
re_charset_t *mbcset,
int *equiv_class_alloc,
const unsigned char *name);
static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans,
bitset_t sbcset,
re_charset_t *mbcset,
int *char_class_alloc,
const char *class_name,
reg_syntax_t syntax);
#else /* not RE_ENABLE_I18N */
static reg_errcode_t build_equiv_class (bitset_t sbcset,
const unsigned char *name);
static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans,
bitset_t sbcset,
const char *class_name,
reg_syntax_t syntax);
#endif /* not RE_ENABLE_I18N */
static bin_tree_t *build_charclass_op (re_dfa_t *dfa,
RE_TRANSLATE_TYPE trans,
const char *class_name,
const char *extra,
int non_match, reg_errcode_t *err);
static bin_tree_t *create_tree (re_dfa_t *dfa,
bin_tree_t *left, bin_tree_t *right,
re_token_type_t type);
static bin_tree_t *create_token_tree (re_dfa_t *dfa,
bin_tree_t *left, bin_tree_t *right,
const re_token_t *token);
static bin_tree_t *duplicate_tree (const bin_tree_t *src, re_dfa_t *dfa);
static void free_token (re_token_t *node);
static reg_errcode_t free_tree (void *extra, bin_tree_t *node);
static reg_errcode_t mark_opt_subexp (void *extra, bin_tree_t *node);
/* This table gives an error message for each of the error codes listed
in regex.h. Obviously the order here has to be same as there.
POSIX doesn't require that we do anything for REG_NOERROR,
but why not be nice? */
const char __re_error_msgid[] attribute_hidden =
{
#define REG_NOERROR_IDX 0
gettext_noop ("Success") /* REG_NOERROR */
"\0"
#define REG_NOMATCH_IDX (REG_NOERROR_IDX + sizeof "Success")
gettext_noop ("No match") /* REG_NOMATCH */
"\0"
#define REG_BADPAT_IDX (REG_NOMATCH_IDX + sizeof "No match")
gettext_noop ("Invalid regular expression") /* REG_BADPAT */
"\0"
#define REG_ECOLLATE_IDX (REG_BADPAT_IDX + sizeof "Invalid regular expression")
gettext_noop ("Invalid collation character") /* REG_ECOLLATE */
"\0"
#define REG_ECTYPE_IDX (REG_ECOLLATE_IDX + sizeof "Invalid collation character")
gettext_noop ("Invalid character class name") /* REG_ECTYPE */
"\0"
#define REG_EESCAPE_IDX (REG_ECTYPE_IDX + sizeof "Invalid character class name")
gettext_noop ("Trailing backslash") /* REG_EESCAPE */
"\0"
#define REG_ESUBREG_IDX (REG_EESCAPE_IDX + sizeof "Trailing backslash")
gettext_noop ("Invalid back reference") /* REG_ESUBREG */
"\0"
#define REG_EBRACK_IDX (REG_ESUBREG_IDX + sizeof "Invalid back reference")
gettext_noop ("Unmatched [, [^, [:, [., or [=") /* REG_EBRACK */
"\0"
#define REG_EPAREN_IDX (REG_EBRACK_IDX + sizeof "Unmatched [ or [^")
gettext_noop ("Unmatched ( or \\(") /* REG_EPAREN */
"\0"
#define REG_EBRACE_IDX (REG_EPAREN_IDX + sizeof "Unmatched ( or \\(")
gettext_noop ("Unmatched \\{") /* REG_EBRACE */
"\0"
#define REG_BADBR_IDX (REG_EBRACE_IDX + sizeof "Unmatched \\{")
gettext_noop ("Invalid content of \\{\\}") /* REG_BADBR */
"\0"
#define REG_ERANGE_IDX (REG_BADBR_IDX + sizeof "Invalid content of \\{\\}")
gettext_noop ("Invalid range end") /* REG_ERANGE */
"\0"
#define REG_ESPACE_IDX (REG_ERANGE_IDX + sizeof "Invalid range end")
gettext_noop ("Memory exhausted") /* REG_ESPACE */
"\0"
#define REG_BADRPT_IDX (REG_ESPACE_IDX + sizeof "Memory exhausted")
gettext_noop ("Invalid preceding regular expression") /* REG_BADRPT */
"\0"
#define REG_EEND_IDX (REG_BADRPT_IDX + sizeof "Invalid preceding regular expression")
gettext_noop ("Premature end of regular expression") /* REG_EEND */
"\0"
#define REG_ESIZE_IDX (REG_EEND_IDX + sizeof "Premature end of regular expression")
gettext_noop ("Regular expression too big") /* REG_ESIZE */
"\0"
#define REG_ERPAREN_IDX (REG_ESIZE_IDX + sizeof "Regular expression too big")
gettext_noop ("Unmatched ) or \\)") /* REG_ERPAREN */
};
const size_t __re_error_msgid_idx[] attribute_hidden =
{
REG_NOERROR_IDX,
REG_NOMATCH_IDX,
REG_BADPAT_IDX,
REG_ECOLLATE_IDX,
REG_ECTYPE_IDX,
REG_EESCAPE_IDX,
REG_ESUBREG_IDX,
REG_EBRACK_IDX,
REG_EPAREN_IDX,
REG_EBRACE_IDX,
REG_BADBR_IDX,
REG_ERANGE_IDX,
REG_ESPACE_IDX,
REG_BADRPT_IDX,
REG_EEND_IDX,
REG_ESIZE_IDX,
REG_ERPAREN_IDX
};
/* Entry points for GNU code. */
#ifdef ZOS_USS
/* For ZOS USS we must define btowc */
wchar_t
btowc (int c)
{
wchar_t wtmp[2];
char tmp[2];
mbstate_t mbs;
memset(& mbs, 0, sizeof(mbs));
tmp[0] = c;
tmp[1] = 0;
mbrtowc (wtmp, tmp, 1, & mbs);
return wtmp[0];
}
#endif
/* re_compile_pattern is the GNU regular expression compiler: it
compiles PATTERN (of length LENGTH) and puts the result in BUFP.
Returns 0 if the pattern was valid, otherwise an error string.
Assumes the `allocated' (and perhaps `buffer') and `translate' fields
are set in BUFP on entry. */
const char *
re_compile_pattern (pattern, length, bufp)
const char *pattern;
size_t length;
struct re_pattern_buffer *bufp;
{
reg_errcode_t ret;
/* And GNU code determines whether or not to get register information
by passing null for the REGS argument to re_match, etc., not by
setting no_sub, unless RE_NO_SUB is set. */
bufp->no_sub = !!(re_syntax_options & RE_NO_SUB);
/* Match anchors at newline. */
bufp->newline_anchor = 1;
ret = re_compile_internal (bufp, pattern, length, re_syntax_options);
if (!ret)
return NULL;
return gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]);
}
#ifdef _LIBC
weak_alias (__re_compile_pattern, re_compile_pattern)
#endif
/* Set by `re_set_syntax' to the current regexp syntax to recognize. Can
also be assigned to arbitrarily: each pattern buffer stores its own
syntax, so it can be changed between regex compilations. */
/* This has no initializer because initialized variables in Emacs
become read-only after dumping. */
reg_syntax_t re_syntax_options;
/* Specify the precise syntax of regexps for compilation. This provides
for compatibility for various utilities which historically have
different, incompatible syntaxes.
The argument SYNTAX is a bit mask comprised of the various bits
defined in regex.h. We return the old syntax. */
reg_syntax_t
re_set_syntax (syntax)
reg_syntax_t syntax;
{
reg_syntax_t ret = re_syntax_options;
re_syntax_options = syntax;
return ret;
}
#ifdef _LIBC
weak_alias (__re_set_syntax, re_set_syntax)
#endif
int
re_compile_fastmap (bufp)
struct re_pattern_buffer *bufp;
{
re_dfa_t *dfa = (re_dfa_t *) bufp->buffer;
char *fastmap = bufp->fastmap;
memset (fastmap, '\0', sizeof (char) * SBC_MAX);
re_compile_fastmap_iter (bufp, dfa->init_state, fastmap);
if (dfa->init_state != dfa->init_state_word)
re_compile_fastmap_iter (bufp, dfa->init_state_word, fastmap);
if (dfa->init_state != dfa->init_state_nl)
re_compile_fastmap_iter (bufp, dfa->init_state_nl, fastmap);
if (dfa->init_state != dfa->init_state_begbuf)
re_compile_fastmap_iter (bufp, dfa->init_state_begbuf, fastmap);
bufp->fastmap_accurate = 1;
return 0;
}
#ifdef _LIBC
weak_alias (__re_compile_fastmap, re_compile_fastmap)
#endif
static inline void
__attribute ((always_inline))
re_set_fastmap (char *fastmap, int icase, int ch)
{
fastmap[ch] = 1;
if (icase)
fastmap[tolower (ch)] = 1;
}
/* Helper function for re_compile_fastmap.
Compile fastmap for the initial_state INIT_STATE. */
static void
re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
char *fastmap)
{
re_dfa_t *dfa = (re_dfa_t *) bufp->buffer;
int node_cnt;
int icase = (dfa->mb_cur_max == 1 && (bufp->syntax & RE_ICASE));
for (node_cnt = 0; node_cnt < init_state->nodes.nelem; ++node_cnt)
{
int node = init_state->nodes.elems[node_cnt];
re_token_type_t type = dfa->nodes[node].type;
if (type == CHARACTER)
{
re_set_fastmap (fastmap, icase, dfa->nodes[node].opr.c);
#ifdef RE_ENABLE_I18N
if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1)
{
unsigned char *buf = re_malloc (unsigned char, dfa->mb_cur_max), *p;
wchar_t wc;
mbstate_t state;
p = buf;
*p++ = dfa->nodes[node].opr.c;
while (++node < dfa->nodes_len
&& dfa->nodes[node].type == CHARACTER
&& dfa->nodes[node].mb_partial)
*p++ = dfa->nodes[node].opr.c;
memset (&state, '\0', sizeof (state));
if (__mbrtowc (&wc, (const char *) buf, p - buf,
&state) == p - buf
&& (__wcrtomb ((char *) buf, towlower (wc), &state)
!= (size_t) -1))
re_set_fastmap (fastmap, 0, buf[0]);
re_free (buf);
}
#endif
}
else if (type == SIMPLE_BRACKET)
{
int i, ch;
for (i = 0, ch = 0; i < BITSET_WORDS; ++i)
{
int j;
bitset_word_t w = dfa->nodes[node].opr.sbcset[i];
for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch)
if (w & ((bitset_word_t) 1 << j))
re_set_fastmap (fastmap, icase, ch);
}
}
#ifdef RE_ENABLE_I18N
else if (type == COMPLEX_BRACKET)
{
re_charset_t *cset = dfa->nodes[node].opr.mbcset;
int i;
# ifdef _LIBC
/* See if we have to try all bytes which start multiple collation
elements.
e.g. In da_DK, we want to catch 'a' since "aa" is a valid
collation element, and don't catch 'b' since 'b' is
the only collation element which starts from 'b' (and
it is caught by SIMPLE_BRACKET). */
if (_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES) != 0
&& (cset->ncoll_syms || cset->nranges))
{
const int32_t *table = (const int32_t *)
_NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB);
for (i = 0; i < SBC_MAX; ++i)
if (table[i] < 0)
re_set_fastmap (fastmap, icase, i);
}
# endif /* _LIBC */
/* See if we have to start the match at all multibyte characters,
i.e. where we would not find an invalid sequence. This only
applies to multibyte character sets; for single byte character
sets, the SIMPLE_BRACKET again suffices. */
if (dfa->mb_cur_max > 1
&& (cset->nchar_classes || cset->non_match || cset->nranges
# ifdef _LIBC
|| cset->nequiv_classes
# endif /* _LIBC */
))
{
unsigned char c = 0;
do
{
mbstate_t mbs;
memset (&mbs, 0, sizeof (mbs));
if (__mbrtowc (NULL, (char *) &c, 1, &mbs) == (size_t) -2)
re_set_fastmap (fastmap, false, (int) c);
}
while (++c != 0);
}
else
{
/* ... Else catch all bytes which can start the mbchars. */
for (i = 0; i < cset->nmbchars; ++i)
{
char buf[256];
mbstate_t state;
memset (&state, '\0', sizeof (state));
if (__wcrtomb (buf, cset->mbchars[i], &state) != (size_t) -1)
re_set_fastmap (fastmap, icase, *(unsigned char *) buf);
if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1)
{
if (__wcrtomb (buf, towlower (cset->mbchars[i]), &state)
!= (size_t) -1)
re_set_fastmap (fastmap, false, *(unsigned char *) buf);
}
}
}
}
#endif /* RE_ENABLE_I18N */
else if (type == OP_PERIOD
#ifdef RE_ENABLE_I18N
|| type == OP_UTF8_PERIOD
#endif /* RE_ENABLE_I18N */
|| type == END_OF_RE)
{
memset (fastmap, '\1', sizeof (char) * SBC_MAX);
if (type == END_OF_RE)
bufp->can_be_null = 1;
return;
}
}
}
/* Entry point for POSIX code. */
/* regcomp takes a regular expression as a string and compiles it.
PREG is a regex_t *. We do not expect any fields to be initialized,
since POSIX says we shouldn't. Thus, we set
`buffer' to the compiled pattern;
`used' to the length of the compiled pattern;
`syntax' to RE_SYNTAX_POSIX_EXTENDED if the
REG_EXTENDED bit in CFLAGS is set; otherwise, to
RE_SYNTAX_POSIX_BASIC;
`newline_anchor' to REG_NEWLINE being set in CFLAGS;
`fastmap' to an allocated space for the fastmap;
`fastmap_accurate' to zero;
`re_nsub' to the number of subexpressions in PATTERN.
PATTERN is the address of the pattern string.
CFLAGS is a series of bits which affect compilation.
If REG_EXTENDED is set, we use POSIX extended syntax; otherwise, we
use POSIX basic syntax.
If REG_NEWLINE is set, then . and [^...] don't match newline.
Also, regexec will try a match beginning after every newline.
If REG_ICASE is set, then we considers upper- and lowercase
versions of letters to be equivalent when matching.
If REG_NOSUB is set, then when PREG is passed to regexec, that
routine will report only success or failure, and nothing about the
registers.
It returns 0 if it succeeds, nonzero if it doesn't. (See regex.h for
the return codes and their meanings.) */
int
regcomp (preg, pattern, cflags)
regex_t *__restrict preg;
const char *__restrict pattern;
int cflags;
{
reg_errcode_t ret;
reg_syntax_t syntax = ((cflags & REG_EXTENDED) ? RE_SYNTAX_POSIX_EXTENDED
: RE_SYNTAX_POSIX_BASIC);
preg->buffer = NULL;
preg->allocated = 0;
preg->used = 0;
/* Try to allocate space for the fastmap. */
preg->fastmap = re_malloc (char, SBC_MAX);
if (BE (preg->fastmap == NULL, 0))
return REG_ESPACE;
syntax |= (cflags & REG_ICASE) ? RE_ICASE : 0;
/* If REG_NEWLINE is set, newlines are treated differently. */
if (cflags & REG_NEWLINE)
{ /* REG_NEWLINE implies neither . nor [^...] match newline. */
syntax &= ~RE_DOT_NEWLINE;
syntax |= RE_HAT_LISTS_NOT_NEWLINE;
/* It also changes the matching behavior. */
preg->newline_anchor = 1;
}
else
preg->newline_anchor = 0;
preg->no_sub = !!(cflags & REG_NOSUB);
preg->translate = NULL;
ret = re_compile_internal (preg, pattern, strlen (pattern), syntax);
/* POSIX doesn't distinguish between an unmatched open-group and an
unmatched close-group: both are REG_EPAREN. */
if (ret == REG_ERPAREN)
ret = REG_EPAREN;
/* We have already checked preg->fastmap != NULL. */
if (BE (ret == REG_NOERROR, 1))
/* Compute the fastmap now, since regexec cannot modify the pattern
buffer. This function never fails in this implementation. */
(void) re_compile_fastmap (preg);
else
{
/* Some error occurred while compiling the expression. */
re_free (preg->fastmap);
preg->fastmap = NULL;
}
return (int) ret;
}
#ifdef _LIBC
weak_alias (__regcomp, regcomp)
#endif
/* Returns a message corresponding to an error code, ERRCODE, returned
from either regcomp or regexec. We don't use PREG here. */
size_t
regerror (errcode, preg, errbuf, errbuf_size)
int errcode;
const regex_t *__restrict preg;
char *__restrict errbuf;
size_t errbuf_size;
{
const char *msg;
size_t msg_size;
if (BE (errcode < 0
|| errcode >= (int) (sizeof (__re_error_msgid_idx)
/ sizeof (__re_error_msgid_idx[0])), 0))
/* Only error codes returned by the rest of the code should be passed
to this routine. If we are given anything else, or if other regex
code generates an invalid error code, then the program has a bug.
Dump core so we can fix it. */
abort ();
msg = gettext (__re_error_msgid + __re_error_msgid_idx[errcode]);
msg_size = strlen (msg) + 1; /* Includes the null. */
if (BE (errbuf_size != 0, 1))
{
if (BE (msg_size > errbuf_size, 0))
{
#if defined HAVE_MEMPCPY || defined _LIBC
*((char *) __mempcpy (errbuf, msg, errbuf_size - 1)) = '\0';
#else
memcpy (errbuf, msg, errbuf_size - 1);
errbuf[errbuf_size - 1] = 0;
#endif
}
else
memcpy (errbuf, msg, msg_size);
}
return msg_size;
}
#ifdef _LIBC
weak_alias (__regerror, regerror)
#endif
#ifdef RE_ENABLE_I18N
/* This static array is used for the map to single-byte characters when
UTF-8 is used. Otherwise we would allocate memory just to initialize
it the same all the time. UTF-8 is the preferred encoding so this is
a worthwhile optimization. */
#if __GNUC__ >= 3
static const bitset_t utf8_sb_map = {
/* Set the first 128 bits. */
[0 ... 0x80 / BITSET_WORD_BITS - 1] = BITSET_WORD_MAX
};
#else /* ! (__GNUC__ >= 3) */
static bitset_t utf8_sb_map;
#endif /* __GNUC__ >= 3 */
#endif /* RE_ENABLE_I18N */
static void
free_dfa_content (re_dfa_t *dfa)
{
int i, j;
if (dfa->nodes)
for (i = 0; i < dfa->nodes_len; ++i)
free_token (dfa->nodes + i);
re_free (dfa->nexts);
for (i = 0; i < dfa->nodes_len; ++i)
{
if (dfa->eclosures != NULL)
re_node_set_free (dfa->eclosures + i);
if (dfa->inveclosures != NULL)
re_node_set_free (dfa->inveclosures + i);
if (dfa->edests != NULL)
re_node_set_free (dfa->edests + i);
}
re_free (dfa->edests);
re_free (dfa->eclosures);
re_free (dfa->inveclosures);
re_free (dfa->nodes);
if (dfa->state_table)
for (i = 0; i <= dfa->state_hash_mask; ++i)
{
struct re_state_table_entry *entry = dfa->state_table + i;
for (j = 0; j < entry->num; ++j)
{
re_dfastate_t *state = entry->array[j];
free_state (state);
}
re_free (entry->array);
}
re_free (dfa->state_table);
#ifdef RE_ENABLE_I18N
if (dfa->sb_char != utf8_sb_map)
re_free (dfa->sb_char);
#endif
re_free (dfa->subexp_map);
#ifdef DEBUG
re_free (dfa->re_str);
#endif
re_free (dfa);
}
/* Free dynamically allocated space used by PREG. */
void
regfree (preg)
regex_t *preg;
{
re_dfa_t *dfa = (re_dfa_t *) preg->buffer;
if (BE (dfa != NULL, 1))
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
re_free (preg->fastmap);
preg->fastmap = NULL;
re_free (preg->translate);
preg->translate = NULL;
}
#ifdef _LIBC
weak_alias (__regfree, regfree)
#endif
/* Entry points compatible with 4.2 BSD regex library. We don't define
them unless specifically requested. */
#if defined _REGEX_RE_COMP || defined _LIBC
/* BSD has one and only one pattern buffer. */
static struct re_pattern_buffer re_comp_buf;
char *
# ifdef _LIBC
/* Make these definitions weak in libc, so POSIX programs can redefine
these names if they don't use our functions, and still use
regcomp/regexec above without link errors. */
weak_function
# endif
re_comp (s)
const char *s;
{
reg_errcode_t ret;
char *fastmap;
if (!s)
{
if (!re_comp_buf.buffer)
return gettext ("No previous regular expression");
return 0;
}
if (re_comp_buf.buffer)
{
fastmap = re_comp_buf.fastmap;
re_comp_buf.fastmap = NULL;
__regfree (&re_comp_buf);
memset (&re_comp_buf, '\0', sizeof (re_comp_buf));
re_comp_buf.fastmap = fastmap;
}
if (re_comp_buf.fastmap == NULL)
{
re_comp_buf.fastmap = (char *) malloc (SBC_MAX);
if (re_comp_buf.fastmap == NULL)
return (char *) gettext (__re_error_msgid
+ __re_error_msgid_idx[(int) REG_ESPACE]);
}
/* Since `re_exec' always passes NULL for the `regs' argument, we
don't need to initialize the pattern buffer fields which affect it. */
/* Match anchors at newlines. */
re_comp_buf.newline_anchor = 1;
ret = re_compile_internal (&re_comp_buf, s, strlen (s), re_syntax_options);
if (!ret)
return NULL;
/* Yes, we're discarding `const' here if !HAVE_LIBINTL. */
return (char *) gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]);
}
#ifdef _LIBC
libc_freeres_fn (free_mem)
{
__regfree (&re_comp_buf);
}
#endif
#endif /* _REGEX_RE_COMP */
/* Internal entry point.
Compile the regular expression PATTERN, whose length is LENGTH.
SYNTAX indicate regular expression's syntax. */
static reg_errcode_t
re_compile_internal (regex_t *preg, const char * pattern, size_t length,
reg_syntax_t syntax)
{
reg_errcode_t err = REG_NOERROR;
re_dfa_t *dfa;
re_string_t regexp;
/* Initialize the pattern buffer. */
preg->fastmap_accurate = 0;
preg->syntax = syntax;
preg->not_bol = preg->not_eol = 0;
preg->used = 0;
preg->re_nsub = 0;
preg->can_be_null = 0;
preg->regs_allocated = REGS_UNALLOCATED;
/* Initialize the dfa. */
dfa = (re_dfa_t *) preg->buffer;
if (BE (preg->allocated < sizeof (re_dfa_t), 0))
{
/* If zero allocated, but buffer is non-null, try to realloc
enough space. This loses if buffer's address is bogus, but
that is the user's responsibility. If ->buffer is NULL this
is a simple allocation. */
dfa = re_realloc (preg->buffer, re_dfa_t, 1);
if (dfa == NULL)
return REG_ESPACE;
preg->allocated = sizeof (re_dfa_t);
preg->buffer = (unsigned char *) dfa;
}
preg->used = sizeof (re_dfa_t);
err = init_dfa (dfa, length);
if (BE (err != REG_NOERROR, 0))
{
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
return err;
}
#ifdef DEBUG
/* Note: length+1 will not overflow since it is checked in init_dfa. */
dfa->re_str = re_malloc (char, length + 1);
strncpy (dfa->re_str, pattern, length + 1);
#endif
__libc_lock_init (dfa->lock);
err = re_string_construct (®exp, pattern, length, preg->translate,
syntax & RE_ICASE, dfa);
if (BE (err != REG_NOERROR, 0))
{
re_compile_internal_free_return:
free_workarea_compile (preg);
re_string_destruct (®exp);
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
return err;
}
/* Parse the regular expression, and build a structure tree. */
preg->re_nsub = 0;
dfa->str_tree = parse (®exp, preg, syntax, &err);
if (BE (dfa->str_tree == NULL, 0))
goto re_compile_internal_free_return;
/* Analyze the tree and create the nfa. */
err = analyze (preg);
if (BE (err != REG_NOERROR, 0))
goto re_compile_internal_free_return;
#ifdef RE_ENABLE_I18N
/* If possible, do searching in single byte encoding to speed things up. */
if (dfa->is_utf8 && !(syntax & RE_ICASE) && preg->translate == NULL)
optimize_utf8 (dfa);
#endif
/* Then create the initial state of the dfa. */
err = create_initial_state (dfa);
/* Release work areas. */
free_workarea_compile (preg);
re_string_destruct (®exp);
if (BE (err != REG_NOERROR, 0))
{
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
}
return err;
}
/* Initialize DFA. We use the length of the regular expression PAT_LEN
as the initial length of some arrays. */
static reg_errcode_t
init_dfa (re_dfa_t *dfa, size_t pat_len)
{
unsigned int table_size;
#ifndef _LIBC
char *codeset_name;
#endif
#if defined(GAWK) && defined(LIBC_IS_BORKED)
/* Needed for brain damaged systems */
extern int gawk_mb_cur_max;
#endif
memset (dfa, '\0', sizeof (re_dfa_t));
/* Force allocation of str_tree_storage the first time. */
dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE;
/* Avoid overflows. */
if (pat_len == SIZE_MAX)
return REG_ESPACE;
dfa->nodes_alloc = pat_len + 1;
dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc);
/* table_size = 2 ^ ceil(log pat_len) */
for (table_size = 1; ; table_size <<= 1)
if (table_size > pat_len)
break;
dfa->state_table = calloc (sizeof (struct re_state_table_entry), table_size);
dfa->state_hash_mask = table_size - 1;
#if defined(GAWK) && defined(LIBC_IS_BORKED)
dfa->mb_cur_max = gawk_mb_cur_max;
#else
dfa->mb_cur_max = MB_CUR_MAX;
#endif
#ifdef _LIBC
if (dfa->mb_cur_max == 6
&& strcmp (_NL_CURRENT (LC_CTYPE, _NL_CTYPE_CODESET_NAME), "UTF-8") == 0)
dfa->is_utf8 = 1;
dfa->map_notascii = (_NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_MAP_TO_NONASCII)
!= 0);
#else
# ifdef HAVE_LANGINFO_CODESET
codeset_name = nl_langinfo (CODESET);
# else
codeset_name = getenv ("LC_ALL");
if (codeset_name == NULL || codeset_name[0] == '\0')
codeset_name = getenv ("LC_CTYPE");
if (codeset_name == NULL || codeset_name[0] == '\0')
codeset_name = getenv ("LANG");
if (codeset_name == NULL)
codeset_name = "";
else if (strchr (codeset_name, '.') != NULL)
codeset_name = strchr (codeset_name, '.') + 1;
# endif
if (strcasecmp (codeset_name, "UTF-8") == 0
|| strcasecmp (codeset_name, "UTF8") == 0)
dfa->is_utf8 = 1;
#if defined(GAWK) && defined(LIBC_IS_BORKED)
if (gawk_mb_cur_max == 1)
dfa->is_utf8 = 0;
#endif /* defined(GAWK) && defined(LIBC_IS_BORKED) */
/* We check exhaustively in the loop below if this charset is a
superset of ASCII. */
dfa->map_notascii = 0;
#endif
#ifdef RE_ENABLE_I18N
if (dfa->mb_cur_max > 1)
{
if (dfa->is_utf8)
{
#if !defined(__GNUC__) || __GNUC__ < 3
static short utf8_sb_map_inited = 0;
if (! utf8_sb_map_inited)
{
int i;
utf8_sb_map_inited = 0;
for (i = 0; i <= 0x80 / BITSET_WORD_BITS - 1; i++)
utf8_sb_map[i] = BITSET_WORD_MAX;
}
#endif
dfa->sb_char = (re_bitset_ptr_t) utf8_sb_map;
}
else
{
int i, j, ch;
dfa->sb_char = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1);
if (BE (dfa->sb_char == NULL, 0))
return REG_ESPACE;
/* Set the bits corresponding to single byte chars. */
for (i = 0, ch = 0; i < BITSET_WORDS; ++i)
for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch)
{
wint_t wch = __btowc (ch);
if (wch != WEOF)
dfa->sb_char[i] |= (bitset_word_t) 1 << j;
# ifndef _LIBC
if (isascii (ch) && wch != ch)
dfa->map_notascii = 1;
# endif
}
}
}
#endif
if (BE (dfa->nodes == NULL || dfa->state_table == NULL, 0))
return REG_ESPACE;
return REG_NOERROR;
}
/* Initialize WORD_CHAR table, which indicate which character is
"word". In this case "word" means that it is the word construction
character used by some operators like "\<", "\>", etc. */
static void
internal_function
init_word_char (re_dfa_t *dfa)
{
int i, j, ch;
dfa->word_ops_used = 1;
#ifndef GAWK
if (BE (dfa->map_notascii == 0, 1))
{
if (sizeof (dfa->word_char[0]) == 8)
{
/* The extra temporaries here avoid "implicitly truncated"
warnings in the case when this is dead code, i.e. 32-bit. */
const uint64_t wc0 = UINT64_C (0x03ff000000000000);
const uint64_t wc1 = UINT64_C (0x07fffffe87fffffe);
dfa->word_char[0] = wc0;
dfa->word_char[1] = wc1;
i = 2;