forked from php/php-src
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpcre_internal.h
1869 lines (1593 loc) · 76.6 KB
/
pcre_internal.h
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) 1997-2010 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 header contains definitions that are shared between the different
modules, but which are not relevant to the exported API. This includes some
functions whose names all begin with "_pcre_". */
#ifndef PCRE_INTERNAL_H
#define PCRE_INTERNAL_H
/* Define PCRE_DEBUG to get debugging output on stdout. */
#if 0
#define PCRE_DEBUG
#endif
/* We do not support both EBCDIC and UTF-8 at the same time. The "configure"
script prevents both being selected, but not everybody uses "configure". */
#if defined EBCDIC && defined SUPPORT_UTF8
#error The use of both EBCDIC and SUPPORT_UTF8 is not supported.
#endif
/* If SUPPORT_UCP is defined, SUPPORT_UTF8 must also be defined. The
"configure" script ensures this, but not everybody uses "configure". */
#if defined SUPPORT_UCP && !defined SUPPORT_UTF8
#define SUPPORT_UTF8 1
#endif
/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef
inline, and there are *still* stupid compilers about that don't like indented
pre-processor statements, or at least there were when I first wrote this. After
all, it had only been about 10 years then...
It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so
be absolutely sure we get our version. */
#undef DPRINTF
#ifdef PCRE_DEBUG
#define DPRINTF(p) printf p
#else
#define DPRINTF(p) /* Nothing */
#endif
/* Standard C headers plus the external interface definition. The only time
setjmp and stdarg are used is when NO_RECURSE is set. */
#include <ctype.h>
#include <limits.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/* When compiling a DLL for Windows, the exported symbols have to be declared
using some MS magic. I found some useful information on this web page:
http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the
information there, using __declspec(dllexport) without "extern" we have a
definition; with "extern" we have a declaration. The settings here override the
setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL,
which is all that is needed for applications (they just import the symbols). We
use:
PCRE_EXP_DECL for declarations
PCRE_EXP_DEFN for definitions of exported functions
PCRE_EXP_DATA_DEFN for definitions of exported variables
The reason for the two DEFN macros is that in non-Windows environments, one
does not want to have "extern" before variable definitions because it leads to
compiler warnings. So we distinguish between functions and variables. In
Windows, the two should always be the same.
The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest,
which is an application, but needs to import this file in order to "peek" at
internals, can #include pcre.h first to get an application's-eye view.
In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon,
special-purpose environments) might want to stick other stuff in front of
exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and
PCRE_EXP_DATA_DEFN only if they are not already set. */
#ifndef PCRE_EXP_DECL
# ifdef _WIN32
# ifndef PCRE_STATIC
# define PCRE_EXP_DECL extern __declspec(dllexport)
# define PCRE_EXP_DEFN __declspec(dllexport)
# define PCRE_EXP_DATA_DEFN __declspec(dllexport)
# else
# define PCRE_EXP_DECL extern
# define PCRE_EXP_DEFN
# define PCRE_EXP_DATA_DEFN
# endif
# else
# ifdef __cplusplus
# define PCRE_EXP_DECL extern "C"
# else
# define PCRE_EXP_DECL extern
# endif
# ifndef PCRE_EXP_DEFN
# define PCRE_EXP_DEFN PCRE_EXP_DECL
# endif
# ifndef PCRE_EXP_DATA_DEFN
# define PCRE_EXP_DATA_DEFN
# endif
# endif
#endif
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE_CALL_CONVENTION
#define PCRE_CALL_CONVENTION
#endif
/* We need to have types that specify unsigned 16-bit and 32-bit integers. We
cannot determine these outside the compilation (e.g. by running a program as
part of "configure") because PCRE is often cross-compiled for use on other
systems. Instead we make use of the maximum sizes that are available at
preprocessor time in standard C environments. */
#if USHRT_MAX == 65535
typedef unsigned short pcre_uint16;
typedef short pcre_int16;
#elif UINT_MAX == 65535
typedef unsigned int pcre_uint16;
typedef int pcre_int16;
#else
#error Cannot determine a type for 16-bit unsigned integers
#endif
#if UINT_MAX == 4294967295
typedef unsigned int pcre_uint32;
typedef int pcre_int32;
#elif ULONG_MAX == 4294967295
typedef unsigned long int pcre_uint32;
typedef long int pcre_int32;
#else
#error Cannot determine a type for 32-bit unsigned integers
#endif
/* When checking for integer overflow in pcre_compile(), we need to handle
large integers. If a 64-bit integer type is available, we can use that.
Otherwise we have to cast to double, which of course requires floating point
arithmetic. Handle this by defining a macro for the appropriate type. If
stdint.h is available, include it; it may define INT64_MAX. Systems that do not
have stdint.h (e.g. Solaris) may have inttypes.h. The macro int64_t may be set
by "configure". */
#ifdef PHP_WIN32
#include "win32/php_stdint.h"
#elif HAVE_STDINT_H
#include <stdint.h>
#elif HAVE_INTTYPES_H
#include <inttypes.h>
#endif
#if defined INT64_MAX || defined int64_t
#define INT64_OR_DOUBLE int64_t
#else
#define INT64_OR_DOUBLE double
#endif
/* All character handling must be done as unsigned characters. Otherwise there
are problems with top-bit-set characters and functions such as isspace().
However, we leave the interface to the outside world as char *, because that
should make things easier for callers. We define a short type for unsigned char
to save lots of typing. I tried "uchar", but it causes problems on Digital
Unix, where it is defined in sys/types, so use "uschar" instead. */
typedef unsigned char uschar;
/* This is an unsigned int value that no character can ever have. UTF-8
characters only go up to 0x7fffffff (though Unicode doesn't go beyond
0x0010ffff). */
#define NOTACHAR 0xffffffff
/* PCRE is able to support several different kinds of newline (CR, LF, CRLF,
"any" and "anycrlf" at present). The following macros are used to package up
testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various
modules to indicate in which datablock the parameters exist, and what the
start/end of string field names are. */
#define NLTYPE_FIXED 0 /* Newline is a fixed length string */
#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */
#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */
/* This macro checks for a newline at the given position */
#define IS_NEWLINE(p) \
((NLBLOCK->nltype != NLTYPE_FIXED)? \
((p) < NLBLOCK->PSEND && \
_pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\
utf8)) \
: \
((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \
(p)[0] == NLBLOCK->nl[0] && \
(NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \
) \
)
/* This macro checks for a newline immediately preceding the given position */
#define WAS_NEWLINE(p) \
((NLBLOCK->nltype != NLTYPE_FIXED)? \
((p) > NLBLOCK->PSSTART && \
_pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \
&(NLBLOCK->nllen), utf8)) \
: \
((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \
(p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \
(NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \
) \
)
/* When PCRE is compiled as a C++ library, the subject pointer can be replaced
with a custom type. This makes it possible, for example, to allow pcre_exec()
to process subject strings that are discontinuous by using a smart pointer
class. It must always be possible to inspect all of the subject string in
pcre_exec() because of the way it backtracks. Two macros are required in the
normal case, for sign-unspecified and unsigned char pointers. The former is
used for the external interface and appears in pcre.h, which is why its name
must begin with PCRE_. */
#ifdef CUSTOM_SUBJECT_PTR
#define PCRE_SPTR CUSTOM_SUBJECT_PTR
#define USPTR CUSTOM_SUBJECT_PTR
#else
#define PCRE_SPTR const char *
#define USPTR const unsigned char *
#endif
/* Include the public PCRE header and the definitions of UCP character property
values. */
#include "pcre.h"
#include "ucp.h"
/* When compiling for use with the Virtual Pascal compiler, these functions
need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
option on the command line. */
#ifdef VPCOMPAT
#define strlen(s) _strlen(s)
#define strncmp(s1,s2,m) _strncmp(s1,s2,m)
#define memcmp(s,c,n) _memcmp(s,c,n)
#define memcpy(d,s,n) _memcpy(d,s,n)
#define memmove(d,s,n) _memmove(d,s,n)
#define memset(s,c,n) _memset(s,c,n)
#else /* VPCOMPAT */
/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
is set. Otherwise, include an emulating function for those systems that have
neither (there some non-Unix environments where this is the case). */
#ifndef HAVE_MEMMOVE
#undef memmove /* some systems may have a macro */
#ifdef HAVE_BCOPY
#define memmove(a, b, c) bcopy(b, a, c)
#else /* HAVE_BCOPY */
static void *
pcre_memmove(void *d, const void *s, size_t n)
{
size_t i;
unsigned char *dest = (unsigned char *)d;
const unsigned char *src = (const unsigned char *)s;
if (dest > src)
{
dest += n;
src += n;
for (i = 0; i < n; ++i) *(--dest) = *(--src);
return (void *)dest;
}
else
{
for (i = 0; i < n; ++i) *dest++ = *src++;
return (void *)(dest - n);
}
}
#define memmove(a, b, c) pcre_memmove(a, b, c)
#endif /* not HAVE_BCOPY */
#endif /* not HAVE_MEMMOVE */
#endif /* not VPCOMPAT */
/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored
in big-endian order) by default. These are used, for example, to link from the
start of a subpattern to its alternatives and its end. The use of 2 bytes per
offset limits the size of the compiled regex to around 64K, which is big enough
for almost everybody. However, I received a request for an even bigger limit.
For this reason, and also to make the code easier to maintain, the storing and
loading of offsets from the byte string is now handled by the macros that are
defined here.
The macros are controlled by the value of LINK_SIZE. This defaults to 2 in
the config.h file, but can be overridden by using -D on the command line. This
is automated on Unix systems via the "configure" command. */
#if LINK_SIZE == 2
#define PUT(a,n,d) \
(a[n] = (d) >> 8), \
(a[(n)+1] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 8) | (a)[(n)+1])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3
#define PUT(a,n,d) \
(a[n] = (d) >> 16), \
(a[(n)+1] = (d) >> 8), \
(a[(n)+2] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
#define MAX_PATTERN_SIZE (1 << 24)
#elif LINK_SIZE == 4
#define PUT(a,n,d) \
(a[n] = (d) >> 24), \
(a[(n)+1] = (d) >> 16), \
(a[(n)+2] = (d) >> 8), \
(a[(n)+3] = (d) & 255)
#define GET(a,n) \
(((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */
#else
#error LINK_SIZE must be either 2, 3, or 4
#endif
/* Convenience macro defined in terms of the others */
#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE
/* PCRE uses some other 2-byte quantities that do not change when the size of
offsets changes. There are used for repeat counts and for other things such as
capturing parenthesis numbers in back references. */
#define PUT2(a,n,d) \
a[n] = (d) >> 8; \
a[(n)+1] = (d) & 255
#define GET2(a,n) \
(((a)[n] << 8) | (a)[(n)+1])
#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2
/* When UTF-8 encoding is being used, a character is no longer just a single
byte. The macros for character handling generate simple sequences when used in
byte-mode, and more complicated ones for UTF-8 characters. GETCHARLENTEST is
not used when UTF-8 is not supported, so it is not defined, and BACKCHAR should
never be called in byte mode. To make sure they can never even appear when
UTF-8 support is omitted, we don't even define them. */
#ifndef SUPPORT_UTF8
#define GETCHAR(c, eptr) c = *eptr;
#define GETCHARTEST(c, eptr) c = *eptr;
#define GETCHARINC(c, eptr) c = *eptr++;
#define GETCHARINCTEST(c, eptr) c = *eptr++;
#define GETCHARLEN(c, eptr, len) c = *eptr;
/* #define GETCHARLENTEST(c, eptr, len) */
/* #define BACKCHAR(eptr) */
#else /* SUPPORT_UTF8 */
/* These macros were originally written in the form of loops that used data
from the tables whose names start with _pcre_utf8_table. They were rewritten by
a user so as not to use loops, because in some environments this gives a
significant performance advantage, and it seems never to do any harm. */
/* Base macro to pick up the remaining bytes of a UTF-8 character, not
advancing the pointer. */
#define GETUTF8(c, eptr) \
{ \
if ((c & 0x20) == 0) \
c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
else if ((c & 0x10) == 0) \
c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
else if ((c & 0x08) == 0) \
c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
else if ((c & 0x04) == 0) \
c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
(eptr[4] & 0x3f); \
else \
c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
}
/* Get the next UTF-8 character, not advancing the pointer. This is called when
we know we are in UTF-8 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if (c >= 0xc0) GETUTF8(c, eptr);
/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf8 && c >= 0xc0) GETUTF8(c, eptr);
/* Base macro to pick up the remaining bytes of a UTF-8 character, advancing
the pointer. */
#define GETUTF8INC(c, eptr) \
{ \
if ((c & 0x20) == 0) \
c = ((c & 0x1f) << 6) | (*eptr++ & 0x3f); \
else if ((c & 0x10) == 0) \
{ \
c = ((c & 0x0f) << 12) | ((*eptr & 0x3f) << 6) | (eptr[1] & 0x3f); \
eptr += 2; \
} \
else if ((c & 0x08) == 0) \
{ \
c = ((c & 0x07) << 18) | ((*eptr & 0x3f) << 12) | \
((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
eptr += 3; \
} \
else if ((c & 0x04) == 0) \
{ \
c = ((c & 0x03) << 24) | ((*eptr & 0x3f) << 18) | \
((eptr[1] & 0x3f) << 12) | ((eptr[2] & 0x3f) << 6) | \
(eptr[3] & 0x3f); \
eptr += 4; \
} \
else \
{ \
c = ((c & 0x01) << 30) | ((*eptr & 0x3f) << 24) | \
((eptr[1] & 0x3f) << 18) | ((eptr[2] & 0x3f) << 12) | \
((eptr[3] & 0x3f) << 6) | (eptr[4] & 0x3f); \
eptr += 5; \
} \
}
/* Get the next UTF-8 character, advancing the pointer. This is called when we
know we are in UTF-8 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if (c >= 0xc0) GETUTF8INC(c, eptr);
/* Get the next character, testing for UTF-8 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-8 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf8 && c >= 0xc0) GETUTF8INC(c, eptr);
/* Base macro to pick up the remaining bytes of a UTF-8 character, not
advancing the pointer, incrementing the length. */
#define GETUTF8LEN(c, eptr, len) \
{ \
if ((c & 0x20) == 0) \
{ \
c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
len++; \
} \
else if ((c & 0x10) == 0) \
{ \
c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
len += 2; \
} \
else if ((c & 0x08) == 0) \
{\
c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
len += 3; \
} \
else if ((c & 0x04) == 0) \
{ \
c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
(eptr[4] & 0x3f); \
len += 4; \
} \
else \
{\
c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
len += 5; \
} \
}
/* Get the next UTF-8 character, not advancing the pointer, incrementing length
if there are extra bytes. This is called when we know we are in UTF-8 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if (c >= 0xc0) GETUTF8LEN(c, eptr, len);
/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
pointer, incrementing length if there are extra bytes. This is called when we
do not know if we are in UTF-8 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf8 && c >= 0xc0) GETUTF8LEN(c, eptr, len);
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-8 mode - we don't put a test within the macro
because almost all calls are already within a block of UTF-8 only code. */
#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--
#endif /* SUPPORT_UTF8 */
/* In case there is no definition of offsetof() provided - though any proper
Standard C system should have one. */
#ifndef offsetof
#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
#endif
/* These are the public options that can change during matching. */
#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL)
/* Private flags containing information about the compiled regex. They used to
live at the top end of the options word, but that got almost full, so now they
are in a 16-bit flags word. From release 8.00, PCRE_NOPARTIAL is unused, as
the restrictions on partial matching have been lifted. It remains for backwards
compatibility. */
#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */
#define PCRE_FIRSTSET 0x0002 /* first_byte is set */
#define PCRE_REQCHSET 0x0004 /* req_byte is set */
#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */
#define PCRE_JCHANGED 0x0010 /* j option used in regex */
#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */
/* Options for the "extra" block produced by pcre_study(). */
#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */
#define PCRE_STUDY_MINLEN 0x02 /* a minimum length field exists */
/* Masks for identifying the public options that are permitted at compile
time, run time, or study time, respectively. */
#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \
PCRE_NEWLINE_ANYCRLF)
#define PUBLIC_COMPILE_OPTIONS \
(PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
PCRE_JAVASCRIPT_COMPAT|PCRE_UCP|PCRE_NO_START_OPTIMIZE)
#define PUBLIC_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_NEWLINE_BITS| \
PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE)
#define PUBLIC_DFA_EXEC_OPTIONS \
(PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_DFA_SHORTEST| \
PCRE_DFA_RESTART|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
PCRE_NO_START_OPTIMIZE)
#define PUBLIC_STUDY_OPTIONS 0 /* None defined */
/* Magic number to provide a small check against being handed junk. Also used
to detect whether a pattern was compiled on a host of different endianness. */
#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */
/* Negative values for the firstchar and reqchar variables */
#define REQ_UNSET (-2)
#define REQ_NONE (-1)
/* The maximum remaining length of subject we are prepared to search for a
req_byte match. */
#define REQ_BYTE_MAX 1000
/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a
variable-length repeat, or a anything other than literal characters. */
#define REQ_CASELESS 0x0100 /* indicates caselessness */
#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */
/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in
environments where these macros are defined elsewhere. Unfortunately, there
is no way to do the same for the typedef. */
typedef int BOOL;
#ifndef FALSE
#define FALSE 0
#define TRUE 1
#endif
/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal
character constants like '*' because the compiler would emit their EBCDIC code,
which is different from their ASCII/UTF-8 code. Instead we define macros for
the characters so that they always use the ASCII/UTF-8 code when UTF-8 support
is enabled. When UTF-8 support is not enabled, the definitions use character
literals. Both character and string versions of each character are needed, and
there are some longer strings as well.
This means that, on EBCDIC platforms, the PCRE library can handle either
EBCDIC, or UTF-8, but not both. To support both in the same compiled library
would need different lookups depending on whether PCRE_UTF8 was set or not.
This would make it impossible to use characters in switch/case statements,
which would reduce performance. For a theoretical use (which nobody has asked
for) in a minority area (EBCDIC platforms), this is not sensible. Any
application that did need both could compile two versions of the library, using
macros to give the functions distinct names. */
#ifndef SUPPORT_UTF8
/* UTF-8 support is not enabled; use the platform-dependent character literals
so that PCRE works on both ASCII and EBCDIC platforms, in non-UTF-mode only. */
#define CHAR_HT '\t'
#define CHAR_VT '\v'
#define CHAR_FF '\f'
#define CHAR_CR '\r'
#define CHAR_NL '\n'
#define CHAR_BS '\b'
#define CHAR_BEL '\a'
#ifdef EBCDIC
#define CHAR_ESC '\047'
#define CHAR_DEL '\007'
#else
#define CHAR_ESC '\033'
#define CHAR_DEL '\177'
#endif
#define CHAR_SPACE ' '
#define CHAR_EXCLAMATION_MARK '!'
#define CHAR_QUOTATION_MARK '"'
#define CHAR_NUMBER_SIGN '#'
#define CHAR_DOLLAR_SIGN '$'
#define CHAR_PERCENT_SIGN '%'
#define CHAR_AMPERSAND '&'
#define CHAR_APOSTROPHE '\''
#define CHAR_LEFT_PARENTHESIS '('
#define CHAR_RIGHT_PARENTHESIS ')'
#define CHAR_ASTERISK '*'
#define CHAR_PLUS '+'
#define CHAR_COMMA ','
#define CHAR_MINUS '-'
#define CHAR_DOT '.'
#define CHAR_SLASH '/'
#define CHAR_0 '0'
#define CHAR_1 '1'
#define CHAR_2 '2'
#define CHAR_3 '3'
#define CHAR_4 '4'
#define CHAR_5 '5'
#define CHAR_6 '6'
#define CHAR_7 '7'
#define CHAR_8 '8'
#define CHAR_9 '9'
#define CHAR_COLON ':'
#define CHAR_SEMICOLON ';'
#define CHAR_LESS_THAN_SIGN '<'
#define CHAR_EQUALS_SIGN '='
#define CHAR_GREATER_THAN_SIGN '>'
#define CHAR_QUESTION_MARK '?'
#define CHAR_COMMERCIAL_AT '@'
#define CHAR_A 'A'
#define CHAR_B 'B'
#define CHAR_C 'C'
#define CHAR_D 'D'
#define CHAR_E 'E'
#define CHAR_F 'F'
#define CHAR_G 'G'
#define CHAR_H 'H'
#define CHAR_I 'I'
#define CHAR_J 'J'
#define CHAR_K 'K'
#define CHAR_L 'L'
#define CHAR_M 'M'
#define CHAR_N 'N'
#define CHAR_O 'O'
#define CHAR_P 'P'
#define CHAR_Q 'Q'
#define CHAR_R 'R'
#define CHAR_S 'S'
#define CHAR_T 'T'
#define CHAR_U 'U'
#define CHAR_V 'V'
#define CHAR_W 'W'
#define CHAR_X 'X'
#define CHAR_Y 'Y'
#define CHAR_Z 'Z'
#define CHAR_LEFT_SQUARE_BRACKET '['
#define CHAR_BACKSLASH '\\'
#define CHAR_RIGHT_SQUARE_BRACKET ']'
#define CHAR_CIRCUMFLEX_ACCENT '^'
#define CHAR_UNDERSCORE '_'
#define CHAR_GRAVE_ACCENT '`'
#define CHAR_a 'a'
#define CHAR_b 'b'
#define CHAR_c 'c'
#define CHAR_d 'd'
#define CHAR_e 'e'
#define CHAR_f 'f'
#define CHAR_g 'g'
#define CHAR_h 'h'
#define CHAR_i 'i'
#define CHAR_j 'j'
#define CHAR_k 'k'
#define CHAR_l 'l'
#define CHAR_m 'm'
#define CHAR_n 'n'
#define CHAR_o 'o'
#define CHAR_p 'p'
#define CHAR_q 'q'
#define CHAR_r 'r'
#define CHAR_s 's'
#define CHAR_t 't'
#define CHAR_u 'u'
#define CHAR_v 'v'
#define CHAR_w 'w'
#define CHAR_x 'x'
#define CHAR_y 'y'
#define CHAR_z 'z'
#define CHAR_LEFT_CURLY_BRACKET '{'
#define CHAR_VERTICAL_LINE '|'
#define CHAR_RIGHT_CURLY_BRACKET '}'
#define CHAR_TILDE '~'
#define STR_HT "\t"
#define STR_VT "\v"
#define STR_FF "\f"
#define STR_CR "\r"
#define STR_NL "\n"
#define STR_BS "\b"
#define STR_BEL "\a"
#ifdef EBCDIC
#define STR_ESC "\047"
#define STR_DEL "\007"
#else
#define STR_ESC "\033"
#define STR_DEL "\177"
#endif
#define STR_SPACE " "
#define STR_EXCLAMATION_MARK "!"
#define STR_QUOTATION_MARK "\""
#define STR_NUMBER_SIGN "#"
#define STR_DOLLAR_SIGN "$"
#define STR_PERCENT_SIGN "%"
#define STR_AMPERSAND "&"
#define STR_APOSTROPHE "'"
#define STR_LEFT_PARENTHESIS "("
#define STR_RIGHT_PARENTHESIS ")"
#define STR_ASTERISK "*"
#define STR_PLUS "+"
#define STR_COMMA ","
#define STR_MINUS "-"
#define STR_DOT "."
#define STR_SLASH "/"
#define STR_0 "0"
#define STR_1 "1"
#define STR_2 "2"
#define STR_3 "3"
#define STR_4 "4"
#define STR_5 "5"
#define STR_6 "6"
#define STR_7 "7"
#define STR_8 "8"
#define STR_9 "9"
#define STR_COLON ":"
#define STR_SEMICOLON ";"
#define STR_LESS_THAN_SIGN "<"
#define STR_EQUALS_SIGN "="
#define STR_GREATER_THAN_SIGN ">"
#define STR_QUESTION_MARK "?"
#define STR_COMMERCIAL_AT "@"
#define STR_A "A"
#define STR_B "B"
#define STR_C "C"
#define STR_D "D"
#define STR_E "E"
#define STR_F "F"
#define STR_G "G"
#define STR_H "H"
#define STR_I "I"
#define STR_J "J"
#define STR_K "K"
#define STR_L "L"
#define STR_M "M"
#define STR_N "N"
#define STR_O "O"
#define STR_P "P"
#define STR_Q "Q"
#define STR_R "R"
#define STR_S "S"
#define STR_T "T"
#define STR_U "U"
#define STR_V "V"
#define STR_W "W"
#define STR_X "X"
#define STR_Y "Y"
#define STR_Z "Z"
#define STR_LEFT_SQUARE_BRACKET "["
#define STR_BACKSLASH "\\"
#define STR_RIGHT_SQUARE_BRACKET "]"
#define STR_CIRCUMFLEX_ACCENT "^"
#define STR_UNDERSCORE "_"
#define STR_GRAVE_ACCENT "`"
#define STR_a "a"
#define STR_b "b"
#define STR_c "c"
#define STR_d "d"
#define STR_e "e"
#define STR_f "f"
#define STR_g "g"
#define STR_h "h"
#define STR_i "i"
#define STR_j "j"
#define STR_k "k"
#define STR_l "l"
#define STR_m "m"
#define STR_n "n"
#define STR_o "o"
#define STR_p "p"
#define STR_q "q"
#define STR_r "r"
#define STR_s "s"
#define STR_t "t"
#define STR_u "u"
#define STR_v "v"
#define STR_w "w"
#define STR_x "x"
#define STR_y "y"
#define STR_z "z"
#define STR_LEFT_CURLY_BRACKET "{"
#define STR_VERTICAL_LINE "|"
#define STR_RIGHT_CURLY_BRACKET "}"
#define STR_TILDE "~"
#define STRING_ACCEPT0 "ACCEPT\0"
#define STRING_COMMIT0 "COMMIT\0"
#define STRING_F0 "F\0"
#define STRING_FAIL0 "FAIL\0"
#define STRING_MARK0 "MARK\0"
#define STRING_PRUNE0 "PRUNE\0"
#define STRING_SKIP0 "SKIP\0"
#define STRING_THEN "THEN"
#define STRING_alpha0 "alpha\0"
#define STRING_lower0 "lower\0"
#define STRING_upper0 "upper\0"
#define STRING_alnum0 "alnum\0"
#define STRING_ascii0 "ascii\0"
#define STRING_blank0 "blank\0"
#define STRING_cntrl0 "cntrl\0"
#define STRING_digit0 "digit\0"
#define STRING_graph0 "graph\0"
#define STRING_print0 "print\0"
#define STRING_punct0 "punct\0"
#define STRING_space0 "space\0"
#define STRING_word0 "word\0"
#define STRING_xdigit "xdigit"
#define STRING_DEFINE "DEFINE"
#define STRING_CR_RIGHTPAR "CR)"
#define STRING_LF_RIGHTPAR "LF)"
#define STRING_CRLF_RIGHTPAR "CRLF)"
#define STRING_ANY_RIGHTPAR "ANY)"
#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)"
#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)"
#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)"
#define STRING_UTF8_RIGHTPAR "UTF8)"
#define STRING_UCP_RIGHTPAR "UCP)"
#define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)"
#else /* SUPPORT_UTF8 */
/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This
works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode
only. */
#define CHAR_HT '\011'
#define CHAR_VT '\013'
#define CHAR_FF '\014'
#define CHAR_CR '\015'
#define CHAR_NL '\012'
#define CHAR_BS '\010'
#define CHAR_BEL '\007'
#define CHAR_ESC '\033'
#define CHAR_DEL '\177'
#define CHAR_SPACE '\040'
#define CHAR_EXCLAMATION_MARK '\041'
#define CHAR_QUOTATION_MARK '\042'
#define CHAR_NUMBER_SIGN '\043'
#define CHAR_DOLLAR_SIGN '\044'
#define CHAR_PERCENT_SIGN '\045'
#define CHAR_AMPERSAND '\046'
#define CHAR_APOSTROPHE '\047'
#define CHAR_LEFT_PARENTHESIS '\050'
#define CHAR_RIGHT_PARENTHESIS '\051'
#define CHAR_ASTERISK '\052'
#define CHAR_PLUS '\053'
#define CHAR_COMMA '\054'
#define CHAR_MINUS '\055'
#define CHAR_DOT '\056'
#define CHAR_SLASH '\057'
#define CHAR_0 '\060'
#define CHAR_1 '\061'
#define CHAR_2 '\062'
#define CHAR_3 '\063'
#define CHAR_4 '\064'
#define CHAR_5 '\065'
#define CHAR_6 '\066'
#define CHAR_7 '\067'
#define CHAR_8 '\070'
#define CHAR_9 '\071'
#define CHAR_COLON '\072'
#define CHAR_SEMICOLON '\073'
#define CHAR_LESS_THAN_SIGN '\074'
#define CHAR_EQUALS_SIGN '\075'
#define CHAR_GREATER_THAN_SIGN '\076'
#define CHAR_QUESTION_MARK '\077'
#define CHAR_COMMERCIAL_AT '\100'
#define CHAR_A '\101'
#define CHAR_B '\102'
#define CHAR_C '\103'
#define CHAR_D '\104'