-
Notifications
You must be signed in to change notification settings - Fork 13
/
pcre_compile.c
9820 lines (8255 loc) · 316 KB
/
pcre_compile.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
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2021 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* 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.
* Neither the name of the University of Cambridge 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 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 OWNER 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.
-----------------------------------------------------------------------------
*/
/* This module contains the external function pcre_compile(), along with
supporting internal functions that are not used by other modules. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#define NLBLOCK cd /* Block containing newline information */
#define PSSTART start_pattern /* Field containing pattern start */
#define PSEND end_pattern /* Field containing pattern end */
#include "pcre_internal.h"
/* When PCRE_DEBUG is defined, we need the pcre(16|32)_printint() function, which
is also used by pcretest. PCRE_DEBUG is not defined when building a production
library. We do not need to select pcre16_printint.c specially, because the
COMPILE_PCREx macro will already be appropriately set. */
#ifdef PCRE_DEBUG
/* pcre_printint.c should not include any headers */
#define PCRE_INCLUDED
#include "pcre_printint.c"
#undef PCRE_INCLUDED
#endif
/* Macro for setting individual bits in class bitmaps. */
#define SETBIT(a,b) a[(b)/8] |= (1U << ((b)&7))
/* Maximum length value to check against when making sure that the integer that
holds the compiled pattern length does not overflow. We make it a bit less than
INT_MAX to allow for adding in group terminating bytes, so that we don't have
to check them every time. */
#define OFLOW_MAX (INT_MAX - 20)
/* Definitions to allow mutual recursion */
static int
add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *,
const pcre_uint32 *, unsigned int);
static BOOL
compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int,
pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *,
compile_data *, int *);
/*************************************************
* Code parameters and static tables *
*************************************************/
/* This value specifies the size of stack workspace that is used during the
first pre-compile phase that determines how much memory is required. The regex
is partly compiled into this space, but the compiled parts are discarded as
soon as they can be, so that hopefully there will never be an overrun. The code
does, however, check for an overrun. The largest amount I've seen used is 218,
so this number is very generous.
The same workspace is used during the second, actual compile phase for
remembering forward references to groups so that they can be filled in at the
end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE
is 4 there is plenty of room for most patterns. However, the memory can get
filled up by repetitions of forward references, for example patterns like
/(?1){0,1999}(b)/, and one user did hit the limit. The code has been changed so
that the workspace is expanded using malloc() in this situation. The value
below is therefore a minimum, and we put a maximum on it for safety. The
minimum is now also defined in terms of LINK_SIZE so that the use of malloc()
kicks in at the same number of forward references in all cases. */
#define COMPILE_WORK_SIZE (2048*LINK_SIZE)
#define COMPILE_WORK_SIZE_MAX (100*COMPILE_WORK_SIZE)
/* This value determines the size of the initial vector that is used for
remembering named groups during the pre-compile. It is allocated on the stack,
but if it is too small, it is expanded using malloc(), in a similar way to the
workspace. The value is the number of slots in the list. */
#define NAMED_GROUP_LIST_SIZE 20
/* The overrun tests check for a slightly smaller size so that they detect the
overrun before it actually does run off the end of the data block. */
#define WORK_SIZE_SAFETY_MARGIN (100)
/* Private flags added to firstchar and reqchar. */
#define REQ_CASELESS (1U << 0) /* Indicates caselessness */
#define REQ_VARY (1U << 1) /* Reqchar followed non-literal item */
/* Negative values for the firstchar and reqchar flags */
#define REQ_UNSET (-2)
#define REQ_NONE (-1)
/* Repeated character flags. */
#define UTF_LENGTH 0x10000000l /* The char contains its length. */
/* Table for handling escaped characters in the range '0'-'z'. Positive returns
are simple data values; negative values are for special things like \d and so
on. Zero means further processing is needed (for things like \x), or the escape
is invalid. */
#ifndef EBCDIC
/* This is the "normal" table for ASCII systems or for EBCDIC systems running
in UTF-8 mode. */
static const short int escapes[] = {
0, 0,
0, 0,
0, 0,
0, 0,
0, 0,
CHAR_COLON, CHAR_SEMICOLON,
CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN,
CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK,
CHAR_COMMERCIAL_AT, -ESC_A,
-ESC_B, -ESC_C,
-ESC_D, -ESC_E,
0, -ESC_G,
-ESC_H, 0,
0, -ESC_K,
0, 0,
-ESC_N, 0,
-ESC_P, -ESC_Q,
-ESC_R, -ESC_S,
0, 0,
-ESC_V, -ESC_W,
-ESC_X, 0,
-ESC_Z, CHAR_LEFT_SQUARE_BRACKET,
CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET,
CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE,
CHAR_GRAVE_ACCENT, ESC_a,
-ESC_b, 0,
-ESC_d, ESC_e,
ESC_f, 0,
-ESC_h, 0,
0, -ESC_k,
0, 0,
ESC_n, 0,
-ESC_p, 0,
ESC_r, -ESC_s,
ESC_tee, 0,
-ESC_v, -ESC_w,
0, 0,
-ESC_z
};
#else
/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */
static const short int escapes[] = {
/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|',
/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0,
/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~',
/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0,
/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?',
/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"',
/* 80 */ 0, ESC_a, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0,
/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0,
/* 90 */ 0, 0, -ESC_k, 0, 0, ESC_n, 0, -ESC_p,
/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0,
/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0,
/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0,
/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-',
/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G,
/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0,
/* D0 */ '}', 0, -ESC_K, 0, 0,-ESC_N, 0, -ESC_P,
/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0,
/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X,
/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0,
/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0,
/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0
};
/* We also need a table of characters that may follow \c in an EBCDIC
environment for characters 0-31. */
static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
#endif
/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
searched linearly. Put all the names into a single string, in order to reduce
the number of relocations when a shared library is dynamically linked. The
string is built from string macros so that it works in UTF-8 mode on EBCDIC
platforms. */
typedef struct verbitem {
int len; /* Length of verb name */
int op; /* Op when no arg, or -1 if arg mandatory */
int op_arg; /* Op when arg present, or -1 if not allowed */
} verbitem;
static const char verbnames[] =
"\0" /* Empty name is a shorthand for MARK */
STRING_MARK0
STRING_ACCEPT0
STRING_COMMIT0
STRING_F0
STRING_FAIL0
STRING_PRUNE0
STRING_SKIP0
STRING_THEN;
static const verbitem verbs[] = {
{ 0, -1, OP_MARK },
{ 4, -1, OP_MARK },
{ 6, OP_ACCEPT, -1 },
{ 6, OP_COMMIT, -1 },
{ 1, OP_FAIL, -1 },
{ 4, OP_FAIL, -1 },
{ 5, OP_PRUNE, OP_PRUNE_ARG },
{ 4, OP_SKIP, OP_SKIP_ARG },
{ 4, OP_THEN, OP_THEN_ARG }
};
static const int verbcount = sizeof(verbs)/sizeof(verbitem);
/* Substitutes for [[:<:]] and [[:>:]], which mean start and end of word in
another regex library. */
static const pcre_uchar sub_start_of_word[] = {
CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK,
CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, CHAR_RIGHT_PARENTHESIS, '\0' };
static const pcre_uchar sub_end_of_word[] = {
CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK,
CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w,
CHAR_RIGHT_PARENTHESIS, '\0' };
/* Tables of names of POSIX character classes and their lengths. The names are
now all in a single string, to reduce the number of relocations when a shared
library is dynamically loaded. The list of lengths is terminated by a zero
length entry. The first three must be alpha, lower, upper, as this is assumed
for handling case independence. The indices for graph, print, and punct are
needed, so identify them. */
static const char posix_names[] =
STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0
STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0
STRING_graph0 STRING_print0 STRING_punct0 STRING_space0
STRING_word0 STRING_xdigit;
static const pcre_uint8 posix_name_lengths[] = {
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
#define PC_GRAPH 8
#define PC_PRINT 9
#define PC_PUNCT 10
/* Table of class bit maps for each POSIX class. Each class is formed from a
base map, with an optional addition or removal of another map. Then, for some
classes, there is some additional tweaking: for [:blank:] the vertical space
characters are removed, and for [:alpha:] and [:alnum:] the underscore
character is removed. The triples in the table consist of the base map offset,
second map offset or -1 if no second map, and a non-negative value for map
addition or a negative value for map subtraction (if there are two maps). The
absolute value of the third field has these meanings: 0 => no tweaking, 1 =>
remove vertical space characters, 2 => remove underscore. */
static const int posix_class_maps[] = {
cbit_word, cbit_digit, -2, /* alpha */
cbit_lower, -1, 0, /* lower */
cbit_upper, -1, 0, /* upper */
cbit_word, -1, 2, /* alnum - word without underscore */
cbit_print, cbit_cntrl, 0, /* ascii */
cbit_space, -1, 1, /* blank - a GNU extension */
cbit_cntrl, -1, 0, /* cntrl */
cbit_digit, -1, 0, /* digit */
cbit_graph, -1, 0, /* graph */
cbit_print, -1, 0, /* print */
cbit_punct, -1, 0, /* punct */
cbit_space, -1, 0, /* space */
cbit_word, -1, 0, /* word - a Perl extension */
cbit_xdigit,-1, 0 /* xdigit */
};
/* Table of substitutes for \d etc when PCRE_UCP is set. They are replaced by
Unicode property escapes. */
#ifdef SUPPORT_UCP
static const pcre_uchar string_PNd[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pNd[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PXsp[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pXsp[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PXwd[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pXwd[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar *substitutes[] = {
string_PNd, /* \D */
string_pNd, /* \d */
string_PXsp, /* \S */ /* Xsp is Perl space, but from 8.34, Perl */
string_pXsp, /* \s */ /* space and POSIX space are the same. */
string_PXwd, /* \W */
string_pXwd /* \w */
};
/* The POSIX class substitutes must be in the order of the POSIX class names,
defined above, and there are both positive and negative cases. NULL means no
general substitute of a Unicode property escape (\p or \P). However, for some
POSIX classes (e.g. graph, print, punct) a special property code is compiled
directly. */
static const pcre_uchar string_pL[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pLl[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pLu[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_pXan[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_h[] = {
CHAR_BACKSLASH, CHAR_h, '\0' };
static const pcre_uchar string_pXps[] = {
CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PL[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PLl[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PLu[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_PXan[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar string_H[] = {
CHAR_BACKSLASH, CHAR_H, '\0' };
static const pcre_uchar string_PXps[] = {
CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
static const pcre_uchar *posix_substitutes[] = {
string_pL, /* alpha */
string_pLl, /* lower */
string_pLu, /* upper */
string_pXan, /* alnum */
NULL, /* ascii */
string_h, /* blank */
NULL, /* cntrl */
string_pNd, /* digit */
NULL, /* graph */
NULL, /* print */
NULL, /* punct */
string_pXps, /* space */ /* Xps is POSIX space, but from 8.34 */
string_pXwd, /* word */ /* Perl and POSIX space are the same */
NULL, /* xdigit */
/* Negated cases */
string_PL, /* ^alpha */
string_PLl, /* ^lower */
string_PLu, /* ^upper */
string_PXan, /* ^alnum */
NULL, /* ^ascii */
string_H, /* ^blank */
NULL, /* ^cntrl */
string_PNd, /* ^digit */
NULL, /* ^graph */
NULL, /* ^print */
NULL, /* ^punct */
string_PXps, /* ^space */ /* Xps is POSIX space, but from 8.34 */
string_PXwd, /* ^word */ /* Perl and POSIX space are the same */
NULL /* ^xdigit */
};
#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *))
#endif
#define STRING(a) # a
#define XSTRING(s) STRING(s)
/* The texts of compile-time error messages. These are "char *" because they
are passed to the outside world. Do not ever re-use any error number, because
they are documented. Always add a new error instead. Messages marked DEAD below
are no longer used. This used to be a table of strings, but in order to reduce
the number of relocations needed when a shared library is loaded dynamically,
it is now one long string. We cannot use a table of offsets, because the
lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we
simply count through to the one we want - this isn't a performance issue
because these strings are used only when there is a compilation error.
Each substring ends with \0 to insert a null character. This includes the final
substring, so that the whole string ends with \0\0, which can be detected when
counting through. */
static const char error_texts[] =
"no error\0"
"\\ at end of pattern\0"
"\\c at end of pattern\0"
"unrecognized character follows \\\0"
"numbers out of order in {} quantifier\0"
/* 5 */
"number too big in {} quantifier\0"
"missing terminating ] for character class\0"
"invalid escape sequence in character class\0"
"range out of order in character class\0"
"nothing to repeat\0"
/* 10 */
"internal error: invalid forward reference offset\0"
"internal error: unexpected repeat\0"
"unrecognized character after (? or (?-\0"
"POSIX named classes are supported only within a class\0"
"missing )\0"
/* 15 */
"reference to non-existent subpattern\0"
"erroffset passed as NULL\0"
"unknown option bit(s) set\0"
"missing ) after comment\0"
"parentheses nested too deeply\0" /** DEAD **/
/* 20 */
"regular expression is too large\0"
"failed to get memory\0"
"unmatched parentheses\0"
"internal error: code overflow\0"
"unrecognized character after (?<\0"
/* 25 */
"lookbehind assertion is not fixed length\0"
"malformed number or name after (?(\0"
"conditional group contains more than two branches\0"
"assertion expected after (?( or (?(?C)\0"
"(?R or (?[+-]digits must be followed by )\0"
/* 30 */
"unknown POSIX class name\0"
"POSIX collating elements are not supported\0"
"this version of PCRE is compiled without UTF support\0"
"spare error\0" /** DEAD **/
"character value in \\x{} or \\o{} is too large\0"
/* 35 */
"invalid condition (?(0)\0"
"\\C not allowed in lookbehind assertion\0"
"PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0"
"number after (?C is > 255\0"
"closing ) for (?C expected\0"
/* 40 */
"recursive call could loop indefinitely\0"
"unrecognized character after (?P\0"
"syntax error in subpattern name (missing terminator)\0"
"two named subpatterns have the same name\0"
"invalid UTF-8 string\0"
/* 45 */
"support for \\P, \\p, and \\X has not been compiled\0"
"malformed \\P or \\p sequence\0"
"unknown property name after \\P or \\p\0"
"subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0"
"too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
/* 50 */
"repeated subpattern is too long\0" /** DEAD **/
"octal value is greater than \\377 in 8-bit non-UTF-8 mode\0"
"internal error: overran compiling workspace\0"
"internal error: previously-checked referenced subpattern not found\0"
"DEFINE group contains more than one branch\0"
/* 55 */
"repeating a DEFINE group is not allowed\0" /** DEAD **/
"inconsistent NEWLINE options\0"
"\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0"
"a numbered reference must not be zero\0"
"an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0"
/* 60 */
"(*VERB) not recognized or malformed\0"
"number is too big\0"
"subpattern name expected\0"
"digit expected after (?+\0"
"] is an invalid data character in JavaScript compatibility mode\0"
/* 65 */
"different names for subpatterns of the same number are not allowed\0"
"(*MARK) must have an argument\0"
"this version of PCRE is not compiled with Unicode property support\0"
#ifndef EBCDIC
"\\c must be followed by an ASCII character\0"
#else
"\\c must be followed by a letter or one of [\\]^_?\0"
#endif
"\\k is not followed by a braced, angle-bracketed, or quoted name\0"
/* 70 */
"internal error: unknown opcode in find_fixedlength()\0"
"\\N is not supported in a class\0"
"too many forward references\0"
"disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
"invalid UTF-16 string\0"
/* 75 */
"name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0"
"character value in \\u.... sequence is too large\0"
"invalid UTF-32 string\0"
"setting UTF is disabled by the application\0"
"non-hex character in \\x{} (closing brace missing?)\0"
/* 80 */
"non-octal character in \\o{} (closing brace missing?)\0"
"missing opening brace after \\o\0"
"parentheses are too deeply nested\0"
"invalid range in character class\0"
"group name must start with a non-digit\0"
/* 85 */
"parentheses are too deeply nested (stack check)\0"
"digits missing in \\x{} or \\o{}\0"
"regular expression is too complicated\0"
;
/* Table to identify digits and hex digits. This is used when compiling
patterns. Note that the tables in chartables are dependent on the locale, and
may mark arbitrary characters as digits - but the PCRE compiling code expects
to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have
a private table here. It costs 256 bytes, but it is a lot faster than doing
character value tests (at least in some simple cases I timed), and in some
applications one wants PCRE to compile efficiently as well as match
efficiently.
For convenience, we use the same bit definitions as in chartables:
0x04 decimal digit
0x08 hexadecimal digit
Then we can use ctype_digit and ctype_xdigit in the code. */
/* Using a simple comparison for decimal numbers rather than a memory read
is much faster, and the resulting code is simpler (the compiler turns it
into a subtraction and unsigned comparison). */
#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9)
#ifndef EBCDIC
/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in
UTF-8 mode. */
static const pcre_uint8 digitab[] =
{
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */
0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */
0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */
0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */
0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
#else
/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */
static const pcre_uint8 digitab[] =
{
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */
0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */
0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */
0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */
static const pcre_uint8 ebcdic_chartab[] = { /* chartable partial dup */
0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */
0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */
0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */
0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */
0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */
0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */
0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */
0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */
0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */
0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */
0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */
0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */
0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */
0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */
0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */
0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */
0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */
0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */
0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */
#endif
/* This table is used to check whether auto-possessification is possible
between adjacent character-type opcodes. The left-hand (repeated) opcode is
used to select the row, and the right-hand opcode is use to select the column.
A value of 1 means that auto-possessification is OK. For example, the second
value in the first row means that \D+\d can be turned into \D++\d.
The Unicode property types (\P and \p) have to be present to fill out the table
because of what their opcode values are, but the table values should always be
zero because property types are handled separately in the code. The last four
columns apply to items that cannot be repeated, so there is no need to have
rows for them. Note that OP_DIGIT etc. are generated only when PCRE_UCP is
*not* set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */
#define APTROWS (LAST_AUTOTAB_LEFT_OP - FIRST_AUTOTAB_OP + 1)
#define APTCOLS (LAST_AUTOTAB_RIGHT_OP - FIRST_AUTOTAB_OP + 1)
static const pcre_uint8 autoposstab[APTROWS][APTCOLS] = {
/* \D \d \S \s \W \w . .+ \C \P \p \R \H \h \V \v \X \Z \z $ $M */
{ 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \D */
{ 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \d */
{ 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \S */
{ 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \s */
{ 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \W */
{ 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \w */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* . */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* .+ */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \C */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \P */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \p */
{ 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \R */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \H */
{ 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \h */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \V */
{ 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0 }, /* \v */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 } /* \X */
};
/* This table is used to check whether auto-possessification is possible
between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP). The
left-hand (repeated) opcode is used to select the row, and the right-hand
opcode is used to select the column. The values are as follows:
0 Always return FALSE (never auto-possessify)
1 Character groups are distinct (possessify if both are OP_PROP)
2 Check character categories in the same group (general or particular)
3 TRUE if the two opcodes are not the same (PROP vs NOTPROP)
4 Check left general category vs right particular category
5 Check right general category vs left particular category
6 Left alphanum vs right general category
7 Left space vs right general category
8 Left word vs right general category
9 Right alphanum vs left general category
10 Right space vs left general category
11 Right word vs left general category
12 Left alphanum vs right particular category
13 Left space vs right particular category
14 Left word vs right particular category
15 Right alphanum vs left particular category
16 Right space vs left particular category
17 Right word vs left particular category
*/
static const pcre_uint8 propposstab[PT_TABSIZE][PT_TABSIZE] = {
/* ANY LAMP GC PC SC ALNUM SPACE PXSPACE WORD CLIST UCNC */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_ANY */
{ 0, 3, 0, 0, 0, 3, 1, 1, 0, 0, 0 }, /* PT_LAMP */
{ 0, 0, 2, 4, 0, 9, 10, 10, 11, 0, 0 }, /* PT_GC */
{ 0, 0, 5, 2, 0, 15, 16, 16, 17, 0, 0 }, /* PT_PC */
{ 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0 }, /* PT_SC */
{ 0, 3, 6, 12, 0, 3, 1, 1, 0, 0, 0 }, /* PT_ALNUM */
{ 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_SPACE */
{ 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_PXSPACE */
{ 0, 0, 8, 14, 0, 0, 1, 1, 3, 0, 0 }, /* PT_WORD */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_CLIST */
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3 } /* PT_UCNC */
};
/* This table is used to check whether auto-possessification is possible
between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP) when one
specifies a general category and the other specifies a particular category. The
row is selected by the general category and the column by the particular
category. The value is 1 if the particular category is not part of the general
category. */
static const pcre_uint8 catposstab[7][30] = {
/* Cc Cf Cn Co Cs Ll Lm Lo Lt Lu Mc Me Mn Nd Nl No Pc Pd Pe Pf Pi Po Ps Sc Sk Sm So Zl Zp Zs */
{ 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* C */
{ 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* L */
{ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* M */
{ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* N */
{ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 }, /* P */
{ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1 }, /* S */
{ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0 } /* Z */
};
/* This table is used when checking ALNUM, (PX)SPACE, SPACE, and WORD against
a general or particular category. The properties in each row are those
that apply to the character set in question. Duplication means that a little
unnecessary work is done when checking, but this keeps things much simpler
because they can all use the same code. For more details see the comment where
this table is used.
Note: SPACE and PXSPACE used to be different because Perl excluded VT from
"space", but from Perl 5.18 it's included, so both categories are treated the
same here. */
static const pcre_uint8 posspropstab[3][4] = {
{ ucp_L, ucp_N, ucp_N, ucp_Nl }, /* ALNUM, 3rd and 4th values redundant */
{ ucp_Z, ucp_Z, ucp_C, ucp_Cc }, /* SPACE and PXSPACE, 2nd value redundant */
{ ucp_L, ucp_N, ucp_P, ucp_Po } /* WORD */
};
/* This table is used when converting repeating opcodes into possessified
versions as a result of an explicit possessive quantifier such as ++. A zero
value means there is no possessified version - in those cases the item in
question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT
because all relevant opcodes are less than that. */
static const pcre_uint8 opcode_possessify[] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */
0, /* NOTI */
OP_POSSTAR, 0, /* STAR, MINSTAR */
OP_POSPLUS, 0, /* PLUS, MINPLUS */
OP_POSQUERY, 0, /* QUERY, MINQUERY */
OP_POSUPTO, 0, /* UPTO, MINUPTO */
0, /* EXACT */
0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */
OP_POSSTARI, 0, /* STARI, MINSTARI */
OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */
OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */
OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */
0, /* EXACTI */
0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */
OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */
OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */
OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */
OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */
0, /* NOTEXACT */
0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */
OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */
OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */
OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */
OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */
0, /* NOTEXACTI */
0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */
OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */
OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */
OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */
OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */
0, /* TYPEEXACT */
0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */
OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */
OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */
OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */
OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */
0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */
0, 0, 0, /* CLASS, NCLASS, XCLASS */
0, 0, /* REF, REFI */
0, 0, /* DNREF, DNREFI */
0, 0 /* RECURSE, CALLOUT */
};
/*************************************************
* Find an error text *
*************************************************/
/* The error texts are now all in one long string, to save on relocations. As
some of the text is of unknown length, we can't use a table of offsets.
Instead, just count through the strings. This is not a performance issue
because it happens only when there has been a compilation error.
Argument: the error number
Returns: pointer to the error string
*/
static const char *
find_error_text(int n)
{
const char *s = error_texts;
for (; n > 0; n--)
{
while (*s++ != CHAR_NULL) {};
if (*s == CHAR_NULL) return "Error text not found (please report)";
}
return s;
}
/*************************************************
* Expand the workspace *
*************************************************/
/* This function is called during the second compiling phase, if the number of
forward references fills the existing workspace, which is originally a block on
the stack. A larger block is obtained from malloc() unless the ultimate limit
has been reached or the increase will be rather small.
Argument: pointer to the compile data block
Returns: 0 if all went well, else an error number
*/
static int
expand_workspace(compile_data *cd)
{
pcre_uchar *newspace;
int newsize = cd->workspace_size * 2;
if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX;
if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX ||
newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN)
return ERR72;
newspace = (PUBL(malloc))(IN_UCHARS(newsize));
if (newspace == NULL) return ERR21;
memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar));
cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace);
if (cd->workspace_size > COMPILE_WORK_SIZE)
(PUBL(free))((void *)cd->start_workspace);
cd->start_workspace = newspace;
cd->workspace_size = newsize;
return 0;
}
/*************************************************
* Check for counted repeat *
*************************************************/
/* This function is called when a '{' is encountered in a place where it might
start a quantifier. It looks ahead to see if it really is a quantifier or not.
It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd}
where the ddds are digits.
Arguments:
p pointer to the first char after '{'
Returns: TRUE or FALSE
*/
static BOOL
is_counted_repeat(const pcre_uchar *p)
{
if (!IS_DIGIT(*p)) return FALSE;
p++;
while (IS_DIGIT(*p)) p++;
if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE;
if (*p++ != CHAR_COMMA) return FALSE;
if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE;
if (!IS_DIGIT(*p)) return FALSE;
p++;
while (IS_DIGIT(*p)) p++;
return (*p == CHAR_RIGHT_CURLY_BRACKET);
}
/*************************************************
* Handle escapes *
*************************************************/
/* This function is called when a \ has been encountered. It either returns a
positive value for a simple escape such as \n, or 0 for a data character which
will be placed in chptr. A backreference to group n is returned as negative n.
When UTF-8 is enabled, a positive value greater than 255 may be returned in
chptr. On entry, ptr is pointing at the \. On exit, it is on the final
character of the escape sequence.
Arguments:
ptrptr points to the pattern position pointer
chptr points to a returned data character
errorcodeptr points to the errorcode variable
bracount number of previous extracting brackets
options the options bits
isclass TRUE if inside a character class
Returns: zero => a data character
positive => a special escape sequence