-
Notifications
You must be signed in to change notification settings - Fork 89
/
pcre_compile.cpp
6542 lines (5442 loc) · 199 KB
/
pcre_compile.cpp
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
#include "avmplus.h"
/*************************************************
* 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) 1997-2007 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. */
#include "config.h"
#define NLBLOCK cd /* Block containing newline information */
#define PSSTART start_pattern /* Field containing processed string start */
#define PSEND end_pattern /* Field containing processed string end */
#include "pcre_internal.h"
/* When DEBUG is defined, we need the pcre_printint() function, which is also
used by pcretest. DEBUG is not defined when building a production library. */
#ifdef PCRE_DEBUG
#include "pcre_printint.src"
#endif
/* Macro for setting individual bits in class bitmaps. */
#define SETBIT(a,b) a[b/8] |= (1 << (b%8))
/* 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)
/*************************************************
* 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. */
//#define COMPILE_WORK_SIZE (4096)
#define COMPILE_WORK_SIZE (2048) //tierney: smaller size to avoid stack overflow when compiling patterns with many nested ()'s
/* 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 */
static const short int escapes[] = {
0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */
0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */
'@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */
-ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */
-ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */
-ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */
'`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */
-ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */
-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */
0, 0, -ESC_z /* x - z */
};
#else /* This is the "abnormal" table for EBCDIC systems */
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, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0,
/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0,
/* 90 */ 0, 0, -ESC_k, 'l', 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, 0, 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
};
#endif
/* Table of special "verbs" like (*PRUNE) */
typedef struct verbitem {
const char *name;
int len;
int op;
} verbitem;
static verbitem verbs[] = {
{ "ACCEPT", 6, OP_ACCEPT },
{ "COMMIT", 6, OP_COMMIT },
{ "F", 1, OP_FAIL },
{ "FAIL", 4, OP_FAIL },
{ "PRUNE", 5, OP_PRUNE },
{ "SKIP", 4, OP_SKIP },
{ "THEN", 4, OP_THEN }
};
static int verbcount = sizeof(verbs)/sizeof(verbitem);
/* Tables of names of POSIX character classes and their lengths. The list is
terminated by a zero length entry. The first three must be alpha, lower, upper,
as this is assumed for handling case independence. */
static const char *const posix_names[] = {
"alpha", "lower", "upper",
"alnum", "ascii", "blank", "cntrl", "digit", "graph",
"print", "punct", "space", "word", "xdigit" };
static const uschar posix_name_lengths[] = {
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
/* 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 */
};
#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. */
static const char *error_texts[] = {
#ifdef AVMPLUS_PCRE
"",
"",
"",
"",
"",
/* 5 */
"",
"",
"",
"",
"",
/* 10 */
"",
"",
"",
"",
"",
/* 15 */
"",
"",
"",
"",
"",
/* 20 */
"",
"",
"",
"",
"",
/* 25 */
"",
"",
"",
"",
"",
/* 30 */
"",
"",
"",
"",
"",
/* 35 */
"",
"",
"",
"",
"",
/* 40 */
"",
"",
"",
"",
"",
/* 45 */
"",
"",
"",
"",
"",
/* 50 */
"", /** DEAD **/
"",
"",
"",
"",
/* 55 */
"",
"",
"",
"",
"",
/* 60 */
"",
""
#else // AVMPLUS_PCRE
"no error",
"\\ at end of pattern",
"\\c at end of pattern",
"unrecognized character follows \\",
"numbers out of order in {} quantifier",
/* 5 */
"number too big in {} quantifier",
"missing terminating ] for character class",
"invalid escape sequence in character class",
"range out of order in character class",
"nothing to repeat",
/* 10 */
"operand of unlimited repeat could match the empty string", /** DEAD **/
"internal error: unexpected repeat",
"unrecognized character after (?",
"POSIX named classes are supported only within a class",
"missing )",
/* 15 */
"reference to non-existent subpattern",
"erroffset passed as NULL",
"unknown option bit(s) set",
"missing ) after comment",
"parentheses nested too deeply", /** DEAD **/
/* 20 */
"regular expression is too large",
"failed to get memory",
"unmatched parentheses",
"internal error: code overflow",
"unrecognized character after (?<",
/* 25 */
"lookbehind assertion is not fixed length",
"malformed number or name after (?(",
"conditional group contains more than two branches",
"assertion expected after (?(",
"(?R or (?[+-]digits must be followed by )",
/* 30 */
"unknown POSIX class name",
"POSIX collating elements are not supported",
"this version of PCRE is not compiled with PCRE_UTF8 support",
"spare error", /** DEAD **/
"character value in \\x{...} sequence is too large",
/* 35 */
"invalid condition (?(0)",
"\\C not allowed in lookbehind assertion",
"PCRE does not support \\L, \\l, \\N, \\U, or \\u",
"number after (?C is > 255",
"closing ) for (?C expected",
/* 40 */
"recursive call could loop indefinitely",
"unrecognized character after (?P",
"syntax error in subpattern name (missing terminator)",
"two named subpatterns have the same name",
"invalid UTF-8 string",
/* 45 */
"support for \\P, \\p, and \\X has not been compiled",
"malformed \\P or \\p sequence",
"unknown property name after \\P or \\p",
"subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)",
"too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")",
/* 50 */
"repeated subpattern is too long", /** DEAD **/
"octal value is greater than \\377 (not in UTF-8 mode)",
"internal error: overran compiling workspace",
"internal error: previously-checked referenced subpattern not found",
"DEFINE group contains more than one branch",
/* 55 */
"repeating a DEFINE group is not allowed",
"inconsistent NEWLINE options",
"\\g is not followed by a braced name or an optionally braced non-zero number",
"(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number",
"(*VERB) with an argument is not supported",
/* 60 */
"(*VERB) not recognized",
"number is too big"
#endif // AVMPLUS_PCRE
};
/* 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. */
#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */
static const unsigned char 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 */
static const unsigned char 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 unsigned char 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
/* Definition to allow mutual recursion */
static BOOL
compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int,
int *, int *, branch_chain *, compile_data *, int *);
/*************************************************
* 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 a negative value which
encodes one of the more complicated things such as \d. A backreference to group
n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When
UTF-8 is enabled, a positive value greater than 255 may be returned. 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
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 or positive => a data character
negative => a special escape sequence
on error, errorcodeptr is set
*/
static int
check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount,
int options, BOOL isclass)
{
BOOL utf8 = (options & PCRE_UTF8) != 0;
const uschar *ptr = *ptrptr + 1;
int c, i;
GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
ptr--; /* Set pointer back to the last byte */
/* If backslash is at the end of the pattern, it's an error. */
if (c == 0) *errorcodeptr = ERR1;
/* Non-alphamerics are literals. For digits or letters, do an initial lookup in
a table. A non-zero result is something that can be returned immediately.
Otherwise further processing may be required. */
#ifndef EBCDIC /* ASCII coding */
else if (c < '0' || c > 'z') {} /* Not alphameric */
else if ((i = escapes[c - '0']) != 0) c = i;
#else /* EBCDIC coding */
else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */
else if ((i = escapes[c - 0x48]) != 0) c = i;
#endif
/* Escapes that need further processing, or are illegal. */
else
{
const uschar *oldptr;
BOOL braced, negated;
switch (c)
{
/* A number of Perl escapes are not handled by PCRE. We give an explicit
error. */
case 'l':
case 'L':
case 'N':
case 'u':
case 'U':
*errorcodeptr = ERR37;
break;
/* \g must be followed by a number, either plain or braced. If positive, it
is an absolute backreference. If negative, it is a relative backreference.
This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a
reference to a named group. This is part of Perl's movement towards a
unified syntax for back references. As this is synonymous with \k{name}, we
fudge it up by pretending it really was \k. */
case 'g':
if (ptr[1] == '{')
{
const uschar *p;
for (p = ptr+2; *p != 0 && *p != '}'; p++)
if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break;
if (*p != 0 && *p != '}')
{
c = -ESC_k;
break;
}
braced = TRUE;
ptr++;
}
else braced = FALSE;
if (ptr[1] == '-')
{
negated = TRUE;
ptr++;
}
else negated = FALSE;
c = 0;
while ((digitab[ptr[1]] & ctype_digit) != 0)
c = c * 10 + *(++ptr) - '0';
if (c < 0)
{
*errorcodeptr = ERR61;
break;
}
if (c == 0 || (braced && *(++ptr) != '}'))
{
*errorcodeptr = ERR57;
break;
}
if (negated)
{
if (c > bracount)
{
*errorcodeptr = ERR15;
break;
}
c = bracount - (c - 1);
}
c = -(ESC_REF + c);
break;
/* The handling of escape sequences consisting of a string of digits
starting with one that is not zero is not straightforward. By experiment,
the way Perl works seems to be as follows:
Outside a character class, the digits are read as a decimal number. If the
number is less than 10, or if there are that many previous extracting
left brackets, then it is a back reference. Otherwise, up to three octal
digits are read to form an escaped byte. Thus \123 is likely to be octal
123 (cf \0123, which is octal 012 followed by the literal 3). If the octal
value is greater than 377, the least significant 8 bits are taken. Inside a
character class, \ followed by a digit is always an octal number. */
case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
if (!isclass)
{
oldptr = ptr;
c -= '0';
while ((digitab[ptr[1]] & ctype_digit) != 0)
c = c * 10 + *(++ptr) - '0';
if (c < 0)
{
*errorcodeptr = ERR61;
break;
}
if (c < 10 || c <= bracount)
{
c = -(ESC_REF + c);
break;
}
ptr = oldptr; /* Put the pointer back and fall through */
}
/* Handle an octal number following \. If the first digit is 8 or 9, Perl
generates a binary zero byte and treats the digit as a following literal.
Thus we have to pull back the pointer by one. */
if ((c = *ptr) >= '8')
{
ptr--;
c = 0;
break;
}
/* \0 always starts an octal number, but we may drop through to here with a
larger first octal digit. The original code used just to take the least
significant 8 bits of octal numbers (I think this is what early Perls used
to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more
than 3 octal digits. */
case '0':
c -= '0';
while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7')
c = c * 8 + *(++ptr) - '0';
if (!utf8 && c > 255) *errorcodeptr = ERR51;
break;
/* \x is complicated. \x{ddd} is a character number which can be greater
than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is
treated as a data character. */
case 'x':
if (ptr[1] == '{')
{
const uschar *pt = ptr + 2;
int count = 0;
c = 0;
while ((digitab[*pt] & ctype_xdigit) != 0)
{
register int cc = *pt++;
if (c == 0 && cc == '0') continue; /* Leading zeroes */
count++;
#ifndef EBCDIC /* ASCII coding */
if (cc >= 'a') cc -= 32; /* Convert to upper case */
c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10));
#else /* EBCDIC coding */
if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */
c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
}
if (*pt == '}')
{
if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34;
ptr = pt;
break;
}
/* If the sequence of hex digits does not end with '}', then we don't
recognize this construct; fall through to the normal \x handling. */
}
/* Read just a single-byte hex-defined char */
c = 0;
while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0)
{
int cc; /* Some compilers don't like ++ */
cc = *(++ptr); /* in initializers */
#ifndef EBCDIC /* ASCII coding */
if (cc >= 'a') cc -= 32; /* Convert to upper case */
c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10));
#else /* EBCDIC coding */
if (cc <= 'z') cc += 64; /* Convert to upper case */
c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
}
break;
/* For \c, a following letter is upper-cased; then the 0x40 bit is flipped.
This coding is ASCII-specific, but then the whole concept of \cx is
ASCII-specific. (However, an EBCDIC equivalent has now been added.) */
case 'c':
c = *(++ptr);
if (c == 0)
{
*errorcodeptr = ERR2;
break;
}
#ifndef EBCDIC /* ASCII coding */
if (c >= 'a' && c <= 'z') c -= 32;
c ^= 0x40;
#else /* EBCDIC coding */
if (c >= 'a' && c <= 'z') c += 64;
c ^= 0xC0;
#endif
break;
/* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any
other alphameric following \ is an error if PCRE_EXTRA was set; otherwise,
for Perl compatibility, it is a literal. This code looks a bit odd, but
there used to be some cases other than the default, and there may be again
in future, so I haven't "optimized" it. */
default:
#ifdef AVMPLUS_PCRE
if ((options & PCRE_EXTRA) != 0)
{
*errorcodeptr = ERR3;
}
#else
if ((options & PCRE_EXTRA) != 0) switch(c)
{
default:
*errorcodeptr = ERR3;
break;
}
#endif
break;
}
}
*ptrptr = ptr;
return c;
}
#ifdef SUPPORT_UCP
/*************************************************
* Handle \P and \p *
*************************************************/
/* This function is called after \P or \p has been encountered, provided that
PCRE is compiled with support for Unicode properties. On entry, ptrptr is
pointing at the P or p. On exit, it is pointing at the final character of the
escape sequence.
Argument:
ptrptr points to the pattern position pointer
negptr points to a boolean that is set TRUE for negation else FALSE
dptr points to an int that is set to the detailed property value
errorcodeptr points to the error code variable
Returns: type value from ucp_type_table, or -1 for an invalid type
*/
static int
get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr)
{
int c, i, bot, top;
const uschar *ptr = *ptrptr;
char name[32];
c = *(++ptr);
if (c == 0) goto ERROR_RETURN;
*negptr = FALSE;
/* \P or \p can be followed by a name in {}, optionally preceded by ^ for
negation. */
if (c == '{')
{
if (ptr[1] == '^')
{
*negptr = TRUE;
ptr++;
}
for (i = 0; i < (int)sizeof(name) - 1; i++)
{
c = *(++ptr);
if (c == 0) goto ERROR_RETURN;
if (c == '}') break;
name[i] = c;
}
if (c !='}') goto ERROR_RETURN;
name[i] = 0;
}
/* Otherwise there is just one following character */
else
{
name[0] = c;
name[1] = 0;
}
*ptrptr = ptr;
/* Search for a recognized property name using binary chop */
bot = 0;
top = _pcre_utt_size;
while (bot < top)
{
i = (bot + top) >> 1;
c = VMPI_strcmp(name, _pcre_utt[i].name);
if (c == 0)
{
*dptr = _pcre_utt[i].value;
return _pcre_utt[i].type;
}
if (c > 0) bot = i + 1; else top = i;
}
*errorcodeptr = ERR47;
*ptrptr = ptr;
return -1;
ERROR_RETURN:
*errorcodeptr = ERR46;
*ptrptr = ptr;
return -1;
}
#endif
/*************************************************
* 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 uschar *p)
{
if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
while ((digitab[*p] & ctype_digit) != 0) p++;
if (*p == '}') return TRUE;
if (*p++ != ',') return FALSE;
if (*p == '}') return TRUE;
if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
while ((digitab[*p] & ctype_digit) != 0) p++;
return (*p == '}');
}
/*************************************************
* Read repeat counts *
*************************************************/
/* Read an item of the form {n,m} and return the values. This is called only
after is_counted_repeat() has confirmed that a repeat-count quantifier exists,
so the syntax is guaranteed to be correct, but we need to check the values.
Arguments:
p pointer to first char after '{'
minp pointer to int for min
maxp pointer to int for max
returned as -1 if no max
errorcodeptr points to error code variable
Returns: pointer to '}' on success;
current ptr on error, with errorcodeptr set non-zero
*/
static const uschar *
read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr)
{
int min = 0;
int max = -1;
/* Read the minimum value and do a paranoid check: a negative value indicates
an integer overflow. */
while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0';
if (min < 0 || min > 65535)
{
*errorcodeptr = ERR5;
return p;
}
/* Read the maximum value if there is one, and again do a paranoid on its size.
Also, max must not be less than min. */
if (*p == '}') max = min; else
{
if (*(++p) != '}')
{
max = 0;
while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0';
if (max < 0 || max > 65535)
{
*errorcodeptr = ERR5;
return p;
}
if (max < min)
{
*errorcodeptr = ERR4;
return p;
}
}
}
/* Fill in the required variables, and pass back the pointer to the terminating
'}'. */
*minp = min;
*maxp = max;
return p;
}
/*************************************************
* Find forward referenced subpattern *
*************************************************/
/* This function scans along a pattern's text looking for capturing
subpatterns, and counting them. If it finds a named pattern that matches the
name it is given, it returns its number. Alternatively, if the name is NULL, it
returns when it reaches a given numbered subpattern. This is used for forward
references to subpatterns. We know that if (?P< is encountered, the name will
be terminated by '>' because that is checked in the first pass.
Arguments:
ptr current position in the pattern
count current count of capturing parens so far encountered