forked from php/php-src
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpcre_internal.h
2798 lines (2324 loc) · 111 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) 1997-2014 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_", "_pcre16_" or "_pcre32_"
depending on the PRIV macro. */
#ifndef PCRE_INTERNAL_H
#define PCRE_INTERNAL_H
/* Define PCRE_DEBUG to get debugging output on stdout. */
#if 0
#define PCRE_DEBUG
#endif
/* PCRE is compiled as an 8 bit library if it is not requested otherwise. */
#if !defined COMPILE_PCRE16 && !defined COMPILE_PCRE32
#define COMPILE_PCRE8
#endif
/* If SUPPORT_UCP is defined, SUPPORT_UTF must also be defined. The
"configure" script ensures this, but not everybody uses "configure". */
#if defined SUPPORT_UCP && !(defined SUPPORT_UTF)
#define SUPPORT_UTF 1
#endif
/* We define SUPPORT_UTF if SUPPORT_UTF8 is enabled for compatibility
reasons with existing code. */
#if defined SUPPORT_UTF8 && !(defined SUPPORT_UTF)
#define SUPPORT_UTF 1
#endif
/* Fixme: SUPPORT_UTF8 should be eventually disappear from the code.
Until then we define it if SUPPORT_UTF is defined. */
#if defined SUPPORT_UTF && !(defined SUPPORT_UTF8)
#define SUPPORT_UTF8 1
#endif
/* We do not support both EBCDIC and UTF-8/16/32 at the same time. The "configure"
script prevents both being selected, but not everybody uses "configure". */
#if defined EBCDIC && defined SUPPORT_UTF
#error The use of both EBCDIC and SUPPORT_UTF is not supported.
#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>
/* Valgrind (memcheck) support */
#ifdef SUPPORT_VALGRIND
#include <valgrind/memcheck.h>
#endif
/* 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 8, 16 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. */
typedef unsigned char pcre_uint8;
#if USHRT_MAX == 65535
typedef unsigned short pcre_uint16;
typedef short pcre_int16;
#define PCRE_UINT16_MAX USHRT_MAX
#define PCRE_INT16_MAX SHRT_MAX
#elif UINT_MAX == 65535
typedef unsigned int pcre_uint16;
typedef int pcre_int16;
#define PCRE_UINT16_MAX UINT_MAX
#define PCRE_INT16_MAX INT_MAX
#else
#error Cannot determine a type for 16-bit integers
#endif
#if UINT_MAX == 4294967295U
typedef unsigned int pcre_uint32;
typedef int pcre_int32;
#define PCRE_UINT32_MAX UINT_MAX
#define PCRE_INT32_MAX INT_MAX
#elif ULONG_MAX == 4294967295UL
typedef unsigned long int pcre_uint32;
typedef long int pcre_int32;
#define PCRE_UINT32_MAX ULONG_MAX
#define PCRE_INT32_MAX LONG_MAX
#else
#error Cannot determine a type for 32-bit 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". */
#if defined HAVE_STDINT_H
#include <stdint.h>
#elif defined 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 * or short *,
because that should make things easier for callers. This character type is
called pcre_uchar.
The IN_UCHARS macro multiply its argument with the byte size of the current
pcre_uchar type. Useful for memcpy and such operations, whose require the
byte size of their input/output buffers.
The MAX_255 macro checks whether its pcre_uchar input is less than 256.
The TABLE_GET macro is designed for accessing elements of tables whose contain
exactly 256 items. When the character is able to contain more than 256
items, some check is needed before accessing these tables.
*/
#if defined COMPILE_PCRE8
typedef unsigned char pcre_uchar;
#define IN_UCHARS(x) (x)
#define MAX_255(c) 1
#define TABLE_GET(c, table, default) ((table)[c])
#elif defined COMPILE_PCRE16
#if USHRT_MAX != 65535
/* This is a warning message. Change PCRE_UCHAR16 to a 16 bit data type in
pcre.h(.in) and disable (comment out) this message. */
#error Warning: PCRE_UCHAR16 is not a 16 bit data type.
#endif
typedef pcre_uint16 pcre_uchar;
#define UCHAR_SHIFT (1)
#define IN_UCHARS(x) ((x) << UCHAR_SHIFT)
#define MAX_255(c) ((c) <= 255u)
#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default))
#elif defined COMPILE_PCRE32
typedef pcre_uint32 pcre_uchar;
#define UCHAR_SHIFT (2)
#define IN_UCHARS(x) ((x) << UCHAR_SHIFT)
#define MAX_255(c) ((c) <= 255u)
#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default))
#else
#error Unsupported compiling mode
#endif /* COMPILE_PCRE[8|16|32] */
/* 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 && \
PRIV(is_newline)((p), NLBLOCK->nltype, NLBLOCK->PSEND, \
&(NLBLOCK->nllen), utf)) \
: \
((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \
UCHAR21TEST(p) == NLBLOCK->nl[0] && \
(NLBLOCK->nllen == 1 || UCHAR21TEST(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 && \
PRIV(was_newline)((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \
&(NLBLOCK->nllen), utf)) \
: \
((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \
UCHAR21TEST(p - NLBLOCK->nllen) == NLBLOCK->nl[0] && \
(NLBLOCK->nllen == 1 || UCHAR21TEST(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_PUCHAR CUSTOM_SUBJECT_PTR
#else
#define PCRE_PUCHAR const pcre_uchar *
#endif
/* Include the public PCRE header and the definitions of UCP character property
values. */
#include "pcre.h"
#include "ucp.h"
#ifdef COMPILE_PCRE32
/* Assert that the public PCRE_UCHAR32 is a 32-bit type */
typedef int __assert_pcre_uchar32_size[sizeof(PCRE_UCHAR32) == 4 ? 1 : -1];
#endif
/* 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 defined COMPILE_PCRE8
#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])
/* Keep it positive */
#define MAX_PATTERN_SIZE (1 << 30)
#else
#error LINK_SIZE must be either 2, 3, or 4
#endif
#elif defined COMPILE_PCRE16
#if LINK_SIZE == 2
/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (d))
#define GET(a,n) \
(a[n])
#define MAX_PATTERN_SIZE (1 << 16)
#elif LINK_SIZE == 3 || LINK_SIZE == 4
/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */
#undef LINK_SIZE
#define LINK_SIZE 2
#define PUT(a,n,d) \
(a[n] = (d) >> 16), \
(a[(n)+1] = (d) & 65535)
#define GET(a,n) \
(((a)[n] << 16) | (a)[(n)+1])
/* Keep it positive */
#define MAX_PATTERN_SIZE (1 << 30)
#else
#error LINK_SIZE must be either 2, 3, or 4
#endif
#elif defined COMPILE_PCRE32
/* Only supported LINK_SIZE is 4 */
/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */
#undef LINK_SIZE
#define LINK_SIZE 1
#define PUT(a,n,d) \
(a[n] = (d))
#define GET(a,n) \
(a[n])
/* Keep it positive */
#define MAX_PATTERN_SIZE (1 << 30)
#else
#error Unsupported compiling mode
#endif /* COMPILE_PCRE[8|16|32] */
/* 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. */
#if defined COMPILE_PCRE8
#define IMM2_SIZE 2
#define PUT2(a,n,d) \
a[n] = (d) >> 8; \
a[(n)+1] = (d) & 255
/* For reasons that I do not understand, the expression in this GET2 macro is
treated by gcc as a signed expression, even when a is declared as unsigned. It
seems that any kind of arithmetic results in a signed value. */
#define GET2(a,n) \
(unsigned int)(((a)[n] << 8) | (a)[(n)+1])
#elif defined COMPILE_PCRE16
#define IMM2_SIZE 1
#define PUT2(a,n,d) \
a[n] = d
#define GET2(a,n) \
a[n]
#elif defined COMPILE_PCRE32
#define IMM2_SIZE 1
#define PUT2(a,n,d) \
a[n] = d
#define GET2(a,n) \
a[n]
#else
#error Unsupported compiling mode
#endif /* COMPILE_PCRE[8|16|32] */
#define PUT2INC(a,n,d) PUT2(a,n,d), a += IMM2_SIZE
/* The maximum length of a MARK name is currently one data unit; it may be
changed in future to be a fixed number of bytes or to depend on LINK_SIZE. */
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
#define MAX_MARK ((1u << 16) - 1)
#else
#define MAX_MARK ((1u << 8) - 1)
#endif
/* There is a proposed future special "UTF-21" mode, in which only the lowest
21 bits of a 32-bit character are interpreted as UTF, with the remaining 11
high-order bits available to the application for other uses. In preparation for
the future implementation of this mode, there are macros that load a data item
and, if in this special mode, mask it to 21 bits. These macros all have names
starting with UCHAR21. In all other modes, including the normal 32-bit
library, the macros all have the same simple definitions. When the new mode is
implemented, it is expected that these definitions will be varied appropriately
using #ifdef when compiling the library that supports the special mode. */
#define UCHAR21(eptr) (*(eptr))
#define UCHAR21TEST(eptr) (*(eptr))
#define UCHAR21INC(eptr) (*(eptr)++)
#define UCHAR21INCTEST(eptr) (*(eptr)++)
/* When UTF encoding is being used, a character is no longer just a single
byte in 8-bit mode or a single short in 16-bit mode. The macros for character
handling generate simple sequences when used in the basic mode, and more
complicated ones for UTF characters. GETCHARLENTEST and other macros are not
used when UTF is not supported. To make sure they can never even appear when
UTF support is omitted, we don't even define them. */
#ifndef SUPPORT_UTF
/* #define MAX_VALUE_FOR_SINGLE_CHAR */
/* #define HAS_EXTRALEN(c) */
/* #define GET_EXTRALEN(c) */
/* #define NOT_FIRSTCHAR(c) */
#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) */
/* #define FORWARDCHAR(eptr) */
/* #define ACROSSCHAR(condition, eptr, action) */
#else /* SUPPORT_UTF */
/* Tests whether the code point needs extra characters to decode. */
#define HASUTF8EXTRALEN(c) ((c) >= 0xc0)
/* 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); \
}
/* 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; \
} \
}
#if defined COMPILE_PCRE8
/* These macros were originally written in the form of loops that used data
from the tables whose names start with PRIV(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. */
/* Tells the biggest code point which can be encoded as a single character. */
#define MAX_VALUE_FOR_SINGLE_CHAR 127
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) ((c) >= 0xc0)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3f])
/* Returns TRUE, if the given character is not the first character
of a UTF sequence. */
#define NOT_FIRSTCHAR(c) (((c) & 0xc0) == 0x80)
/* 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 (utf && c >= 0xc0) GETUTF8(c, eptr);
/* 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 (utf && 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 (utf && 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--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
while((condition) && ((eptr) & 0xc0) == 0x80) action
#elif defined COMPILE_PCRE16
/* Tells the biggest code point which can be encoded as a single character. */
#define MAX_VALUE_FOR_SINGLE_CHAR 65535
/* Tests whether the code point needs extra characters to decode. */
#define HAS_EXTRALEN(c) (((c) & 0xfc00) == 0xd800)
/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
Otherwise it has an undefined behaviour. */
#define GET_EXTRALEN(c) 1
/* Returns TRUE, if the given character is not the first character
of a UTF sequence. */
#define NOT_FIRSTCHAR(c) (((c) & 0xfc00) == 0xdc00)
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer. */
#define GETUTF16(c, eptr) \
{ c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; }
/* Get the next UTF-16 character, not advancing the pointer. This is called when
we know we are in UTF-16 mode. */
#define GETCHAR(c, eptr) \
c = *eptr; \
if ((c & 0xfc00) == 0xd800) GETUTF16(c, eptr);
/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *eptr; \
if (utf && (c & 0xfc00) == 0xd800) GETUTF16(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, advancing
the pointer. */
#define GETUTF16INC(c, eptr) \
{ c = (((c & 0x3ff) << 10) | (*eptr++ & 0x3ff)) + 0x10000; }
/* Get the next UTF-16 character, advancing the pointer. This is called when we
know we are in UTF-16 mode. */
#define GETCHARINC(c, eptr) \
c = *eptr++; \
if ((c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr);
/* Get the next character, testing for UTF-16 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-16 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *eptr++; \
if (utf && (c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr);
/* Base macro to pick up the low surrogate of a UTF-16 character, not
advancing the pointer, incrementing the length. */
#define GETUTF16LEN(c, eptr, len) \
{ c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; len++; }
/* Get the next UTF-16 character, not advancing the pointer, incrementing
length if there is a low surrogate. This is called when we know we are in
UTF-16 mode. */
#define GETCHARLEN(c, eptr, len) \
c = *eptr; \
if ((c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len);
/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
pointer, incrementing length if there is a low surrogate. This is called when
we do not know if we are in UTF-16 mode. */
#define GETCHARLENTEST(c, eptr, len) \
c = *eptr; \
if (utf && (c & 0xfc00) == 0xd800) GETUTF16LEN(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-16 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-16 only
code. */
#define BACKCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr--
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr++
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) \
if ((condition) && ((eptr) & 0xfc00) == 0xdc00) action
#elif defined COMPILE_PCRE32
/* These are trivial for the 32-bit library, since all UTF-32 characters fit
into one pcre_uchar unit. */
#define MAX_VALUE_FOR_SINGLE_CHAR (0x10ffffu)
#define HAS_EXTRALEN(c) (0)
#define GET_EXTRALEN(c) (0)
#define NOT_FIRSTCHAR(c) (0)
/* Get the next UTF-32 character, not advancing the pointer. This is called when
we know we are in UTF-32 mode. */
#define GETCHAR(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the
pointer. */
#define GETCHARTEST(c, eptr) \
c = *(eptr);
/* Get the next UTF-32 character, advancing the pointer. This is called when we
know we are in UTF-32 mode. */
#define GETCHARINC(c, eptr) \
c = *((eptr)++);
/* Get the next character, testing for UTF-32 mode, and advancing the pointer.
This is called when we don't know if we are in UTF-32 mode. */
#define GETCHARINCTEST(c, eptr) \
c = *((eptr)++);
/* Get the next UTF-32 character, not advancing the pointer, not incrementing
length (since all UTF-32 is of length 1). This is called when we know we are in
UTF-32 mode. */
#define GETCHARLEN(c, eptr, len) \
GETCHAR(c, eptr)
/* Get the next UTF-32character, testing for UTF-32 mode, not advancing the
pointer, not incrementing the length (since all UTF-32 is of length 1).
This is called when we do not know if we are in UTF-32 mode. */
#define GETCHARLENTEST(c, eptr, len) \
GETCHARTEST(c, eptr)
/* If the pointer is not at the start of a character, move it back until
it is. This is called only in UTF-32 mode - we don't put a test within the
macro because almost all calls are already within a block of UTF-32 only
code.
These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */
#define BACKCHAR(eptr) do { } while (0)
/* Same as above, just in the other direction. */
#define FORWARDCHAR(eptr) do { } while (0)
/* Same as above, but it allows a fully customizable form. */
#define ACROSSCHAR(condition, eptr, action) do { } while (0)
#else
#error Unsupported compiling mode
#endif /* COMPILE_PCRE[8|16|32] */
#endif /* SUPPORT_UTF */
/* Tests for Unicode horizontal and vertical whitespace characters must check a
number of different values. Using a switch statement for this generates the
fastest code (no loop, no memory access), and there are several places in the
interpreter code where this happens. In order to ensure that all the case lists
remain in step, we use macros so that there is only one place where the lists
are defined.
These values are also required as lists in pcre_compile.c when processing \h,
\H, \v and \V in a character class. The lists are defined in pcre_tables.c, but
macros that define the values are here so that all the definitions are
together. The lists must be in ascending character order, terminated by
NOTACHAR (which is 0xffffffff).
Any changes should ensure that the various macros are kept in step with each
other. NOTE: The values also appear in pcre_jit_compile.c. */
/* ------ ASCII/Unicode environments ------ */
#ifndef EBCDIC
#define HSPACE_LIST \
CHAR_HT, CHAR_SPACE, CHAR_NBSP, \
0x1680, 0x180e, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, \
0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x202f, 0x205f, 0x3000, \
NOTACHAR
#define HSPACE_MULTIBYTE_CASES \
case 0x1680: /* OGHAM SPACE MARK */ \
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ \
case 0x2000: /* EN QUAD */ \
case 0x2001: /* EM QUAD */ \
case 0x2002: /* EN SPACE */ \
case 0x2003: /* EM SPACE */ \
case 0x2004: /* THREE-PER-EM SPACE */ \
case 0x2005: /* FOUR-PER-EM SPACE */ \