/
handy.h
2219 lines (1900 loc) · 101 KB
/
handy.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
/* handy.h
*
* Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1999, 2000,
* 2001, 2002, 2004, 2005, 2006, 2007, 2008, 2012 by Larry Wall and others
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
*
*/
/* IMPORTANT NOTE: Everything whose name begins with an underscore is for
* internal core Perl use only. */
#ifndef HANDY_H /* Guard against nested #inclusion */
#define HANDY_H
#if !defined(__STDC__)
#ifdef NULL
#undef NULL
#endif
# define NULL 0
#endif
#ifndef PERL_CORE
# define Null(type) ((type)NULL)
/*
=head1 Handy Values
=for apidoc AmU||Nullch
Null character pointer. (No longer available when C<PERL_CORE> is
defined.)
=for apidoc AmU||Nullsv
Null SV pointer. (No longer available when C<PERL_CORE> is defined.)
=cut
*/
# define Nullch Null(char*)
# define Nullfp Null(PerlIO*)
# define Nullsv Null(SV*)
#endif
#ifdef TRUE
#undef TRUE
#endif
#ifdef FALSE
#undef FALSE
#endif
#define TRUE (1)
#define FALSE (0)
/* The MUTABLE_*() macros cast pointers to the types shown, in such a way
* (compiler permitting) that casting away const-ness will give a warning;
* e.g.:
*
* const SV *sv = ...;
* AV *av1 = (AV*)sv; <== BAD: the const has been silently cast away
* AV *av2 = MUTABLE_AV(sv); <== GOOD: it may warn
*/
#if defined(__GNUC__) && !defined(PERL_GCC_BRACE_GROUPS_FORBIDDEN)
# define MUTABLE_PTR(p) ({ void *_p = (p); _p; })
#else
# define MUTABLE_PTR(p) ((void *) (p))
#endif
#define MUTABLE_AV(p) ((AV *)MUTABLE_PTR(p))
#define MUTABLE_CV(p) ((CV *)MUTABLE_PTR(p))
#define MUTABLE_GV(p) ((GV *)MUTABLE_PTR(p))
#define MUTABLE_HV(p) ((HV *)MUTABLE_PTR(p))
#define MUTABLE_IO(p) ((IO *)MUTABLE_PTR(p))
#define MUTABLE_SV(p) ((SV *)MUTABLE_PTR(p))
#if defined(I_STDBOOL) && !defined(PERL_BOOL_AS_CHAR)
# include <stdbool.h>
# ifndef HAS_BOOL
# define HAS_BOOL 1
# endif
#endif
/* bool is built-in for g++-2.6.3 and later, which might be used
for extensions. <_G_config.h> defines _G_HAVE_BOOL, but we can't
be sure _G_config.h will be included before this file. _G_config.h
also defines _G_HAVE_BOOL for both gcc and g++, but only g++
actually has bool. Hence, _G_HAVE_BOOL is pretty useless for us.
g++ can be identified by __GNUG__.
Andy Dougherty February 2000
*/
#ifdef __GNUG__ /* GNU g++ has bool built-in */
# ifndef PERL_BOOL_AS_CHAR
# ifndef HAS_BOOL
# define HAS_BOOL 1
# endif
# endif
#endif
#ifndef HAS_BOOL
# ifdef bool
# undef bool
# endif
# define bool char
# define HAS_BOOL 1
#endif
/* cast-to-bool. A simple (bool) cast may not do the right thing: if bool is
* defined as char for example, then the cast from int is
* implementation-defined (bool)!!(cbool) in a ternary triggers a bug in xlc on
* AIX */
#define cBOOL(cbool) ((cbool) ? (bool)1 : (bool)0)
/* Try to figure out __func__ or __FUNCTION__ equivalent, if any.
* XXX Should really be a Configure probe, with HAS__FUNCTION__
* and FUNCTION__ as results.
* XXX Similarly, a Configure probe for __FILE__ and __LINE__ is needed. */
#if (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L) || (defined(__SUNPRO_C)) /* C99 or close enough. */
# define FUNCTION__ __func__
#else
# if (defined(USING_MSVC6)) || /* MSVC6 has neither __func__ nor __FUNCTION and no good workarounds, either. */ \
(defined(__DECC_VER)) /* Tru64 or VMS, and strict C89 being used, but not modern enough cc (in Tur64, -c99 not known, only -std1). */
# define FUNCTION__ ""
# else
# define FUNCTION__ __FUNCTION__ /* Common extension. */
# endif
#endif
/* XXX A note on the perl source internal type system. The
original intent was that I32 be *exactly* 32 bits.
Currently, we only guarantee that I32 is *at least* 32 bits.
Specifically, if int is 64 bits, then so is I32. (This is the case
for the Cray.) This has the advantage of meshing nicely with
standard library calls (where we pass an I32 and the library is
expecting an int), but the disadvantage that an I32 is not 32 bits.
Andy Dougherty August 1996
There is no guarantee that there is *any* integral type with
exactly 32 bits. It is perfectly legal for a system to have
sizeof(short) == sizeof(int) == sizeof(long) == 8.
Similarly, there is no guarantee that I16 and U16 have exactly 16
bits.
For dealing with issues that may arise from various 32/64-bit
systems, we will ask Configure to check out
SHORTSIZE == sizeof(short)
INTSIZE == sizeof(int)
LONGSIZE == sizeof(long)
LONGLONGSIZE == sizeof(long long) (if HAS_LONG_LONG)
PTRSIZE == sizeof(void *)
DOUBLESIZE == sizeof(double)
LONG_DOUBLESIZE == sizeof(long double) (if HAS_LONG_DOUBLE).
*/
#ifdef I_INTTYPES /* e.g. Linux has int64_t without <inttypes.h> */
# include <inttypes.h>
# ifdef INT32_MIN_BROKEN
# undef INT32_MIN
# define INT32_MIN (-2147483647-1)
# endif
# ifdef INT64_MIN_BROKEN
# undef INT64_MIN
# define INT64_MIN (-9223372036854775807LL-1)
# endif
#endif
typedef I8TYPE I8;
typedef U8TYPE U8;
typedef I16TYPE I16;
typedef U16TYPE U16;
typedef I32TYPE I32;
typedef U32TYPE U32;
#ifdef HAS_QUAD
typedef I64TYPE I64;
typedef U64TYPE U64;
#endif
/* INT64_C/UINT64_C are C99 from <stdint.h> (so they will not be
* available in strict C89 mode), but they are nice, so let's define
* them if necessary. */
#if defined(HAS_QUAD)
# undef PeRl_INT64_C
# undef PeRl_UINT64_C
/* Prefer the native integer types (int and long) over long long
* (which is not C89) and Win32-specific __int64. */
# if QUADKIND == QUAD_IS_INT && INTSIZE == 8
# define PeRl_INT64_C(c) (c)
# define PeRl_UINT64_C(c) CAT2(c,U)
# endif
# if QUADKIND == QUAD_IS_LONG && LONGSIZE == 8
# define PeRl_INT64_C(c) CAT2(c,L)
# define PeRl_UINT64_C(c) CAT2(c,UL)
# endif
# if QUADKIND == QUAD_IS_LONG_LONG && defined(HAS_LONG_LONG)
# define PeRl_INT64_C(c) CAT2(c,LL)
# define PeRl_UINT64_C(c) CAT2(c,ULL)
# endif
# if QUADKIND == QUAD_IS___INT64
# define PeRl_INT64_C(c) CAT2(c,I64)
# define PeRl_UINT64_C(c) CAT2(c,UI64)
# endif
# ifndef PeRl_INT64_C
# define PeRl_INT64_C(c) ((I64)(c)) /* last resort */
# define PeRl_UINT64_C(c) ((U64)(c))
# endif
/* In OS X the INT64_C/UINT64_C are defined with LL/ULL, which will
* not fly with C89-pedantic gcc, so let's undefine them first so that
* we can redefine them with our native integer preferring versions. */
# if defined(PERL_DARWIN) && defined(PERL_GCC_PEDANTIC)
# undef INT64_C
# undef UINT64_C
# endif
# ifndef INT64_C
# define INT64_C(c) PeRl_INT64_C(c)
# endif
# ifndef UINT64_C
# define UINT64_C(c) PeRl_UINT64_C(c)
# endif
#endif
#if defined(UINT8_MAX) && defined(INT16_MAX) && defined(INT32_MAX)
/* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type.
Please search CHAR_MAX in perl.h for further details. */
#define U8_MAX UINT8_MAX
#define U8_MIN UINT8_MIN
#define I16_MAX INT16_MAX
#define I16_MIN INT16_MIN
#define U16_MAX UINT16_MAX
#define U16_MIN UINT16_MIN
#define I32_MAX INT32_MAX
#define I32_MIN INT32_MIN
#ifndef UINT32_MAX_BROKEN /* e.g. HP-UX with gcc messes this up */
# define U32_MAX UINT32_MAX
#else
# define U32_MAX 4294967295U
#endif
#define U32_MIN UINT32_MIN
#else
/* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type.
Please search CHAR_MAX in perl.h for further details. */
#define U8_MAX PERL_UCHAR_MAX
#define U8_MIN PERL_UCHAR_MIN
#define I16_MAX PERL_SHORT_MAX
#define I16_MIN PERL_SHORT_MIN
#define U16_MAX PERL_USHORT_MAX
#define U16_MIN PERL_USHORT_MIN
#if LONGSIZE > 4
# define I32_MAX PERL_INT_MAX
# define I32_MIN PERL_INT_MIN
# define U32_MAX PERL_UINT_MAX
# define U32_MIN PERL_UINT_MIN
#else
# define I32_MAX PERL_LONG_MAX
# define I32_MIN PERL_LONG_MIN
# define U32_MAX PERL_ULONG_MAX
# define U32_MIN PERL_ULONG_MIN
#endif
#endif
/* log(2) is pretty close to 0.30103, just in case anyone is grepping for it */
#define BIT_DIGITS(N) (((N)*146)/485 + 1) /* log2(10) =~ 146/485 */
#define TYPE_DIGITS(T) BIT_DIGITS(sizeof(T) * 8)
#define TYPE_CHARS(T) (TYPE_DIGITS(T) + 2) /* sign, NUL */
/* Unused by core; should be deprecated */
#define Ctl(ch) ((ch) & 037)
/* This is a helper macro to avoid preprocessor issues, replaced by nothing
* unless under DEBUGGING, where it expands to an assert of its argument,
* followed by a comma (hence the comma operator). If we just used a straight
* assert(), we would get a comma with nothing before it when not DEBUGGING.
*
* We also use empty definition under Coverity since the __ASSERT__
* checks often check for things that Really Cannot Happen, and Coverity
* detects that and gets all excited. */
#if defined(DEBUGGING) && !defined(__COVERITY__)
# define __ASSERT_(statement) assert(statement),
#else
# define __ASSERT_(statement)
#endif
/*
=head1 SV-Body Allocation
=for apidoc Ama|SV*|newSVpvs|const char* s
Like C<newSVpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|SV*|newSVpvs_flags|const char* s|U32 flags
Like C<newSVpvn_flags>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=for apidoc Ama|SV*|newSVpvs_share|const char* s
Like C<newSVpvn_share>, but takes a C<NUL>-terminated literal string instead of
a string/length pair and omits the hash parameter.
=for apidoc Am|void|sv_catpvs_flags|SV* sv|const char* s|I32 flags
Like C<sv_catpvn_flags>, but takes a C<NUL>-terminated literal string instead
of a string/length pair.
=for apidoc Am|void|sv_catpvs_nomg|SV* sv|const char* s
Like C<sv_catpvn_nomg>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=for apidoc Am|void|sv_catpvs|SV* sv|const char* s
Like C<sv_catpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|void|sv_catpvs_mg|SV* sv|const char* s
Like C<sv_catpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|void|sv_setpvs|SV* sv|const char* s
Like C<sv_setpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|void|sv_setpvs_mg|SV* sv|const char* s
Like C<sv_setpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|SV *|sv_setref_pvs|const char* s
Like C<sv_setref_pvn>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=head1 Memory Management
=for apidoc Ama|char*|savepvs|const char* s
Like C<savepvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|char*|savesharedpvs|const char* s
A version of C<savepvs()> which allocates the duplicate string in memory
which is shared between threads.
=head1 GV Functions
=for apidoc Am|HV*|gv_stashpvs|const char* name|I32 create
Like C<gv_stashpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=head1 Hash Manipulation Functions
=for apidoc Am|SV**|hv_fetchs|HV* tb|const char* key|I32 lval
Like C<hv_fetch>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|SV**|hv_stores|HV* tb|const char* key|NULLOK SV* val
Like C<hv_store>, but takes a C<NUL>-terminated literal string instead of a
string/length pair
and omits the hash parameter.
=head1 Lexer interface
=for apidoc Amx|void|lex_stuff_pvs|const char *pv|U32 flags
Like L</lex_stuff_pvn>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=cut
*/
/* concatenating with "" ensures that only literal strings are accepted as
* argument */
#define STR_WITH_LEN(s) ("" s ""), (sizeof(s)-1)
/* note that STR_WITH_LEN() can't be used as argument to macros or functions
* that under some configurations might be macros, which means that it requires
* the full Perl_xxx(aTHX_ ...) form for any API calls where it's used.
*/
/* STR_WITH_LEN() shortcuts */
#define newSVpvs(str) Perl_newSVpvn(aTHX_ STR_WITH_LEN(str))
#define newSVpvs_flags(str,flags) \
Perl_newSVpvn_flags(aTHX_ STR_WITH_LEN(str), flags)
#define newSVpvs_share(str) Perl_newSVpvn_share(aTHX_ STR_WITH_LEN(str), 0)
#define sv_catpvs_flags(sv, str, flags) \
Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), flags)
#define sv_catpvs_nomg(sv, str) \
Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), 0)
#define sv_catpvs(sv, str) \
Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), SV_GMAGIC)
#define sv_catpvs_mg(sv, str) \
Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), SV_GMAGIC|SV_SMAGIC)
#define sv_setpvs(sv, str) Perl_sv_setpvn(aTHX_ sv, STR_WITH_LEN(str))
#define sv_setpvs_mg(sv, str) Perl_sv_setpvn_mg(aTHX_ sv, STR_WITH_LEN(str))
#define sv_setref_pvs(rv, classname, str) \
Perl_sv_setref_pvn(aTHX_ rv, classname, STR_WITH_LEN(str))
#define savepvs(str) Perl_savepvn(aTHX_ STR_WITH_LEN(str))
#define savesharedpvs(str) Perl_savesharedpvn(aTHX_ STR_WITH_LEN(str))
#define gv_stashpvs(str, create) \
Perl_gv_stashpvn(aTHX_ STR_WITH_LEN(str), create)
#define gv_fetchpvs(namebeg, add, sv_type) \
Perl_gv_fetchpvn_flags(aTHX_ STR_WITH_LEN(namebeg), add, sv_type)
#define gv_fetchpvn(namebeg, len, add, sv_type) \
Perl_gv_fetchpvn_flags(aTHX_ namebeg, len, add, sv_type)
#define sv_catxmlpvs(dsv, str, utf8) \
Perl_sv_catxmlpvn(aTHX_ dsv, STR_WITH_LEN(str), utf8)
#define hv_fetchs(hv,key,lval) \
((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
(lval) ? (HV_FETCH_JUST_SV | HV_FETCH_LVALUE) \
: HV_FETCH_JUST_SV, NULL, 0))
#define hv_stores(hv,key,val) \
((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
(HV_FETCH_ISSTORE|HV_FETCH_JUST_SV), (val), 0))
#define lex_stuff_pvs(pv,flags) Perl_lex_stuff_pvn(aTHX_ STR_WITH_LEN(pv), flags)
#define get_cvs(str, flags) \
Perl_get_cvn_flags(aTHX_ STR_WITH_LEN(str), (flags))
/*
=head1 Miscellaneous Functions
=for apidoc Am|bool|strNE|char* s1|char* s2
Test two C<NUL>-terminated strings to see if they are different. Returns true
or false.
=for apidoc Am|bool|strEQ|char* s1|char* s2
Test two C<NUL>-terminated strings to see if they are equal. Returns true or
false.
=for apidoc Am|bool|strLT|char* s1|char* s2
Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than the
second, C<s2>. Returns true or false.
=for apidoc Am|bool|strLE|char* s1|char* s2
Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than or
equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGT|char* s1|char* s2
Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGE|char* s1|char* s2
Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
or equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strnNE|char* s1|char* s2|STRLEN len
Test two C<NUL>-terminated strings to see if they are different. The C<len>
parameter indicates the number of bytes to compare. Returns true or false. (A
wrapper for C<strncmp>).
=for apidoc Am|bool|strnEQ|char* s1|char* s2|STRLEN len
Test two C<NUL>-terminated strings to see if they are equal. The C<len>
parameter indicates the number of bytes to compare. Returns true or false. (A
wrapper for C<strncmp>).
=for apidoc Am|bool|memEQ|char* s1|char* s2|STRLEN len
Test two buffers (which may contain embedded C<NUL> characters, to see if they
are equal. The C<len> parameter indicates the number of bytes to compare.
Returns zero if equal, or non-zero if non-equal.
=for apidoc Am|bool|memNE|char* s1|char* s2|STRLEN len
Test two buffers (which may contain embedded C<NUL> characters, to see if they
are not equal. The C<len> parameter indicates the number of bytes to compare.
Returns zero if non-equal, or non-zero if equal.
=cut
*/
#define strNE(s1,s2) (strcmp(s1,s2))
#define strEQ(s1,s2) (!strcmp(s1,s2))
#define strLT(s1,s2) (strcmp(s1,s2) < 0)
#define strLE(s1,s2) (strcmp(s1,s2) <= 0)
#define strGT(s1,s2) (strcmp(s1,s2) > 0)
#define strGE(s1,s2) (strcmp(s1,s2) >= 0)
#define strnNE(s1,s2,l) (strncmp(s1,s2,l))
#define strnEQ(s1,s2,l) (!strncmp(s1,s2,l))
#ifdef HAS_MEMCMP
# define memNE(s1,s2,l) (memcmp(s1,s2,l))
# define memEQ(s1,s2,l) (!memcmp(s1,s2,l))
#else
# define memNE(s1,s2,l) (bcmp(s1,s2,l))
# define memEQ(s1,s2,l) (!bcmp(s1,s2,l))
#endif
#define memEQs(s1, l, s2) \
(sizeof(s2)-1 == l && memEQ(s1, ("" s2 ""), (sizeof(s2)-1)))
#define memNEs(s1, l, s2) !memEQs(s1, l, s2)
/*
* Character classes.
*
* Unfortunately, the introduction of locales means that we
* can't trust isupper(), etc. to tell the truth. And when
* it comes to /\w+/ with tainting enabled, we *must* be able
* to trust our character classes.
*
* Therefore, the default tests in the text of Perl will be
* independent of locale. Any code that wants to depend on
* the current locale will use the tests that begin with "lc".
*/
#ifdef HAS_SETLOCALE /* XXX Is there a better test for this? */
# ifndef CTYPE256
# define CTYPE256
# endif
#endif
/*
=head1 Character classification
This section is about functions (really macros) that classify characters
into types, such as punctuation versus alphabetic, etc. Most of these are
analogous to regular expression character classes. (See
L<perlrecharclass/POSIX Character Classes>.) There are several variants for
each class. (Not all macros have all variants; each item below lists the
ones valid for it.) None are affected by C<use bytes>, and only the ones
with C<LC> in the name are affected by the current locale.
The base function, e.g., C<isALPHA()>, takes an octet (either a C<char> or a
C<U8>) as input and returns a boolean as to whether or not the character
represented by that octet is (or on non-ASCII platforms, corresponds to) an
ASCII character in the named class based on platform, Unicode, and Perl rules.
If the input is a number that doesn't fit in an octet, FALSE is returned.
Variant C<isFOO_A> (e.g., C<isALPHA_A()>) is identical to the base function
with no suffix C<"_A">.
Variant C<isFOO_L1> imposes the Latin-1 (or EBCDIC equivlalent) character set
onto the platform. That is, the code points that are ASCII are unaffected,
since ASCII is a subset of Latin-1. But the non-ASCII code points are treated
as if they are Latin-1 characters. For example, C<isWORDCHAR_L1()> will return
true when called with the code point 0xDF, which is a word character in both
ASCII and EBCDIC (though it represents different characters in each).
Variant C<isFOO_uvchr> is like the C<isFOO_L1> variant, but accepts any UV code
point as input. If the code point is larger than 255, Unicode rules are used
to determine if it is in the character class. For example,
C<isWORDCHAR_uvchr(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
WITH MACRON in Unicode, and is a word character.
Variant C<isFOO_utf8> is like C<isFOO_uvchr>, but the input is a pointer to a
(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
possibly containing embedded C<NUL> characters). The classification of just
the first (possibly multi-byte) character in the string is tested.
Variant C<isFOO_LC> is like the C<isFOO_A> and C<isFOO_L1> variants, but the
result is based on the current locale, which is what C<LC> in the name stands
for. If Perl can determine that the current locale is a UTF-8 locale, it uses
the published Unicode rules; otherwise, it uses the C library function that
gives the named classification. For example, C<isDIGIT_LC()> when not in a
UTF-8 locale returns the result of calling C<isdigit()>. FALSE is always
returned if the input won't fit into an octet. On some platforms where the C
library function is known to be defective, Perl changes its result to follow
the POSIX standard's rules.
Variant C<isFOO_LC_uvchr> is like C<isFOO_LC>, but is defined on any UV. It
returns the same as C<isFOO_LC> for input code points less than 256, and
returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer
to a (known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
possibly containing embedded C<NUL> characters). The classification of just
the first (possibly multi-byte) character in the string is tested.
=for apidoc Am|bool|isALPHA|char ch
Returns a boolean indicating whether the specified character is an
alphabetic character, analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8>, C<isALPHA_LC>,
C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8>.
=for apidoc Am|bool|isALPHANUMERIC|char ch
Returns a boolean indicating whether the specified character is a either an
alphabetic character or decimal digit, analogous to C<m/[[:alnum:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uvchr>,
C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>, and
C<isALPHANUMERIC_LC_utf8>.
=for apidoc Am|bool|isASCII|char ch
Returns a boolean indicating whether the specified character is one of the 128
characters in the ASCII character set, analogous to C<m/[[:ascii:]]/>.
On non-ASCII platforms, it returns TRUE iff this
character corresponds to an ASCII character. Variants C<isASCII_A()> and
C<isASCII_L1()> are identical to C<isASCII()>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isASCII_uvchr>, C<isASCII_utf8>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
C<isASCII_LC_utf8>. Note, however, that some platforms do not have the C
library routine C<isascii()>. In these cases, the variants whose names contain
C<LC> are the same as the corresponding ones without.
Also note, that because all ASCII characters are UTF-8 invariant (meaning they
have the exact same representation (always a single byte) whether encoded in
UTF-8 or not), C<isASCII> will give the correct results when called with any
byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8> will
work properly on any string encoded or not in UTF-8.
=for apidoc Am|bool|isBLANK|char ch
Returns a boolean indicating whether the specified character is a
character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8>, C<isBLANK_LC>,
C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8>. Note, however, that some
platforms do not have the C library routine C<isblank()>. In these cases, the
variants whose names contain C<LC> are the same as the corresponding ones
without.
=for apidoc Am|bool|isCNTRL|char ch
Returns a boolean indicating whether the specified character is a
control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8>, C<isCNTRL_LC>,
C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8>
On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
=for apidoc Am|bool|isDIGIT|char ch
Returns a boolean indicating whether the specified character is a
digit, analogous to C<m/[[:digit:]]/>.
Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isDIGIT_uvchr>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
C<isDIGIT_LC_utf8>.
=for apidoc Am|bool|isGRAPH|char ch
Returns a boolean indicating whether the specified character is a
graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8>.
=for apidoc Am|bool|isLOWER|char ch
Returns a boolean indicating whether the specified character is a
lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8>, C<isLOWER_LC>,
C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
=for apidoc Am|bool|isOCTAL|char ch
Returns a boolean indicating whether the specified character is an
octal digit, [0-7].
The only two variants are C<isOCTAL_A> and C<isOCTAL_L1>; each is identical to
C<isOCTAL>.
=for apidoc Am|bool|isPUNCT|char ch
Returns a boolean indicating whether the specified character is a
punctuation character, analogous to C<m/[[:punct:]]/>.
Note that the definition of what is punctuation isn't as
straightforward as one might desire. See L<perlrecharclass/POSIX Character
Classes> for details.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
=for apidoc Am|bool|isSPACE|char ch
Returns a boolean indicating whether the specified character is a
whitespace character. This is analogous
to what C<m/\s/> matches in a regular expression. Starting in Perl 5.18
this also matches what C<m/[[:space:]]/> does. Prior to 5.18, only the
locale forms of this macro (the ones with C<LC> in their names) matched
precisely what C<m/[[:space:]]/> does. In those releases, the only difference,
in the non-locale variants, was that C<isSPACE()> did not match a vertical tab.
(See L</isPSXSPC> for a macro that matches a vertical tab in all releases.)
See the L<top of this section|/Character classification> for an explanation of
variants
C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8>, C<isSPACE_LC>,
C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
=for apidoc Am|bool|isPSXSPC|char ch
(short for Posix Space)
Starting in 5.18, this is identical in all its forms to the
corresponding C<isSPACE()> macros.
The locale forms of this macro are identical to their corresponding
C<isSPACE()> forms in all Perl releases. In releases prior to 5.18, the
non-locale forms differ from their C<isSPACE()> forms only in that the
C<isSPACE()> forms don't match a Vertical Tab, and the C<isPSXSPC()> forms do.
Otherwise they are identical. Thus this macro is analogous to what
C<m/[[:space:]]/> matches in a regular expression.
See the L<top of this section|/Character classification> for an explanation of
variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8>,
C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
=for apidoc Am|bool|isUPPER|char ch
Returns a boolean indicating whether the specified character is an
uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8>, C<isUPPER_LC>,
C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8>.
=for apidoc Am|bool|isPRINT|char ch
Returns a boolean indicating whether the specified character is a
printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8>, C<isPRINT_LC>,
C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
=for apidoc Am|bool|isWORDCHAR|char ch
Returns a boolean indicating whether the specified character is a character
that is a word character, analogous to what C<m/\w/> and C<m/[[:word:]]/> match
in a regular expression. A word character is an alphabetic character, a
decimal digit, a connecting punctuation character (such as an underscore), or
a "mark" character that attaches to one of those (like some sort of accent).
C<isALNUM()> is a synonym provided for backward compatibility, even though a
word character includes more than the standard C language meaning of
alphanumeric.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and C<isWORDCHAR_utf8>.
C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and C<isWORDCHAR_LC_utf8> are also as
described there, but additionally include the platform's native underscore.
=for apidoc Am|bool|isXDIGIT|char ch
Returns a boolean indicating whether the specified character is a hexadecimal
digit. In the ASCII range these are C<[0-9A-Fa-f]>. Variants C<isXDIGIT_A()>
and C<isXDIGIT_L1()> are identical to C<isXDIGIT()>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isXDIGIT_uvchr>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
C<isXDIGIT_LC_utf8>.
=for apidoc Am|bool|isIDFIRST|char ch
Returns a boolean indicating whether the specified character can be the first
character of an identifier. This is very close to, but not quite the same as
the official Unicode property C<XID_Start>. The difference is that this
returns true only if the input character also matches L</isWORDCHAR>.
See the L<top of this section|/Character classification> for an explanation of
variants
C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8>,
C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8>.
=for apidoc Am|bool|isIDCONT|char ch
Returns a boolean indicating whether the specified character can be the
second or succeeding character of an identifier. This is very close to, but
not quite the same as the official Unicode property C<XID_Continue>. The
difference is that this returns true only if the input character also matches
L</isWORDCHAR>. See the L<top of this section|/Character classification> for
an
explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uvchr>,
C<isIDCONT_utf8>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
C<isIDCONT_LC_utf8>.
=head1 Miscellaneous Functions
=for apidoc Am|U8|READ_XDIGIT|char str*
Returns the value of an ASCII-range hex digit and advances the string pointer.
Behaviour is only well defined when isXDIGIT(*str) is true.
=head1 Character case changing
=for apidoc Am|U8|toUPPER|U8 ch
Converts the specified character to uppercase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
C<toUPPER_A> is equivalent.
=for apidoc Am|UV|toUPPER_uvchr|UV cp|U8* s|STRLEN* lenp
Converts the code point C<cp> to its uppercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
(but note, as explained just above, that there may be more.)
=for apidoc Am|UV|toUPPER_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its uppercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
(but note, as explained just above, that there may be more.)
The input character at C<p> is assumed to be well-formed.
=for apidoc Am|U8|toFOLD|U8 ch
Converts the specified character to foldcase. If the input is anything but an
ASCII uppercase character, that input character itself is returned. Variant
C<toFOLD_A> is equivalent. (There is no equivalent C<to_FOLD_L1> for the full
Latin1 range, as the full generality of L</toFOLD_uvchr> is needed there.)
=for apidoc Am|UV|toFOLD_uvchr|UV cp|U8* s|STRLEN* lenp
Converts the code point C<cp> to its foldcase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
(but note, as explained just above, that there may be more.)
=for apidoc Am|UV|toFOLD_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its foldcase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
(but note, as explained just above, that there may be more.)
The input character at C<p> is assumed to be well-formed.
=for apidoc Am|U8|toLOWER|U8 ch
Converts the specified character to lowercase. If the input is anything but an
ASCII uppercase character, that input character itself is returned. Variant
C<toLOWER_A> is equivalent.
=for apidoc Am|U8|toLOWER_L1|U8 ch
Converts the specified Latin1 character to lowercase. The results are
undefined if the input doesn't fit in a byte.
=for apidoc Am|U8|toLOWER_LC|U8 ch
Converts the specified character to lowercase using the current locale's rules,
if possible; otherwise returns the input character itself.
=for apidoc Am|UV|toLOWER_uvchr|UV cp|U8* s|STRLEN* lenp
Converts the code point C<cp> to its lowercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the lowercase version may be longer than the original character.
The first code point of the lowercased version is returned
(but note, as explained just above, that there may be more.)
=for apidoc Am|UV|toLOWER_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its lowercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the lowercase version may be longer than the original character.
The first code point of the lowercased version is returned
(but note, as explained just above, that there may be more.)
The input character at C<p> is assumed to be well-formed.
=for apidoc Am|U8|toTITLE|U8 ch
Converts the specified character to titlecase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1
range, as the full generality of L</toTITLE_uvchr> is needed there. Titlecase is
not a concept used in locale handling, so there is no functionality for that.)
=for apidoc Am|UV|toTITLE_uvchr|UV cp|U8* s|STRLEN* lenp
Converts the code point C<cp> to its titlecase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
(but note, as explained just above, that there may be more.)
=for apidoc Am|UV|toTITLE_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its titlecase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
(but note, as explained just above, that there may be more.)
The input character at C<p> is assumed to be well-formed.
=cut
XXX Still undocumented isVERTWS_uvchr and _utf8; it's unclear what their names
really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change.
Note that these macros are repeated in Devel::PPPort, so should also be
patched there. The file as of this writing is cpan/Devel-PPPort/parts/inc/misc
*/
/* Specify the widest unsigned type on the platform. Use U64TYPE because U64
* is known only in the perl core, and this macro can be called from outside
* that */
#ifdef HAS_QUAD
# define WIDEST_UTYPE U64TYPE
#else
# define WIDEST_UTYPE U32
#endif
/* FITS_IN_8_BITS(c) returns true if c doesn't have a bit set other than in
* the lower 8. It is designed to be hopefully bomb-proof, making sure that no
* bits of information are lost even on a 64-bit machine, but to get the
* compiler to optimize it out if possible. This is because Configure makes
* sure that the machine has an 8-bit byte, so if c is stored in a byte, the
* sizeof() guarantees that this evaluates to a constant true at compile time.
*
* For Coverity, be always true, because otherwise Coverity thinks
* it finds several expressions that are always true, independent
* of operands. Well, they are, but that is kind of the point.
*/
#ifndef __COVERITY__
#define FITS_IN_8_BITS(c) ((sizeof(c) == 1) || !(((WIDEST_UTYPE)(c)) & ~0xFF))
#else
#define FITS_IN_8_BITS(c) (1)
#endif
#ifdef EBCDIC
# ifndef _ALL_SOURCE
/* The native libc isascii() et.al. functions return the wrong results
* on at least z/OS unless this is defined. */
# error _ALL_SOURCE should probably be defined
# endif
#else
/* There is a simple definition of ASCII for ASCII platforms. But the
* EBCDIC one isn't so simple, so is defined using table look-up like the
* other macros below.
* The '| 0' part ensures that c is an integer (and not e.g. a pointer) */
# define isASCII(c) ((WIDEST_UTYPE)((c) | 0) < 128)
#endif
/* The lower 3 bits in both the ASCII and EBCDIC representations of '0' are 0,
* and the 8 possible permutations of those bits exactly comprise the 8 octal
* digits */
#define isOCTAL_A(c) cBOOL(FITS_IN_8_BITS(c) && (0xF8 & (c)) == '0')
#ifdef H_PERL /* If have access to perl.h, lookup in its table */
/* Character class numbers. For internal core Perl use only. The ones less
* than 32 are used in PL_charclass[] and the ones up through the one that
* corresponds to <_HIGHEST_REGCOMP_DOT_H_SYNC> are used by regcomp.h and
* related files. PL_charclass ones use names used in l1_char_class_tab.h but
* their actual definitions are here. If that file has a name not used here,
* it won't compile.
*
* The first group of these is ordered in what I (khw) estimate to be the
* frequency of their use. This gives a slight edge to exiting a loop earlier
* (in reginclass() in regexec.c) */
# define _CC_WORDCHAR 0 /* \w and [:word:] */
# define _CC_DIGIT 1 /* \d and [:digit:] */
# define _CC_ALPHA 2 /* [:alpha:] */
# define _CC_LOWER 3 /* [:lower:] */
# define _CC_UPPER 4 /* [:upper:] */
# define _CC_PUNCT 5 /* [:punct:] */
# define _CC_PRINT 6 /* [:print:] */
# define _CC_ALPHANUMERIC 7 /* [:alnum:] */
# define _CC_GRAPH 8 /* [:graph:] */
# define _CC_CASED 9 /* [:lower:] and [:upper:] under /i */
#define _FIRST_NON_SWASH_CC 10
/* The character classes above are implemented with swashes. The second group
* (just below) contains the ones implemented without. These are also sorted
* in rough order of the frequency of their use, except that \v should be last,
* as it isn't a real Posix character class, and some (small) inefficiencies in
* regular expression handling would be introduced by putting it in the middle
* of those that are. Also, cntrl and ascii come after the others as it may be
* useful to group these which have no members that match above Latin1, (or
* above ASCII in the latter case) */
# define _CC_SPACE 10 /* \s, [:space:] */
# define _CC_BLANK 11 /* [:blank:] */
# define _CC_XDIGIT 12 /* [:xdigit:] */
# define _CC_CNTRL 13 /* [:cntrl:] */
# define _CC_ASCII 14 /* [:ascii:] */
# define _CC_VERTSPACE 15 /* \v */
# define _HIGHEST_REGCOMP_DOT_H_SYNC _CC_VERTSPACE
/* The members of the third group below do not need to be coordinated with data
* structures in regcomp.[ch] and regexec.c. */
# define _CC_IDFIRST 16
# define _CC_CHARNAME_CONT 17
# define _CC_NONLATIN1_FOLD 18
# define _CC_NONLATIN1_SIMPLE_FOLD 19
# define _CC_QUOTEMETA 20
# define _CC_NON_FINAL_FOLD 21
# define _CC_IS_IN_SOME_FOLD 22
# define _CC_MNEMONIC_CNTRL 23
/* This next group is only used on EBCDIC platforms, so theoretically could be
* shared with something entirely different that's only on ASCII platforms */
# define _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE 28
# define _CC_UTF8_IS_START 29
# define _CC_UTF8_IS_DOWNGRADEABLE_START 30
# define _CC_UTF8_IS_CONTINUATION 31
/* Unused: 24-27
* If more bits are needed, one could add a second word for non-64bit
* QUAD_IS_INT systems, using some #ifdefs to distinguish between having a 2nd
* word or not. The IS_IN_SOME_FOLD bit is the most easily expendable, as it
* is used only for optimization (as of this writing), and differs in the