summaryrefslogtreecommitdiff
path: root/utf8.c
blob: 5e018260fa855b3cdf0ba54ac770f7718f6ccf2e (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
/*    utf8.c
 *
 *    Copyright (c) 1998-2000, Larry Wall
 *
 *    You may distribute under the terms of either the GNU General Public
 *    License or the Artistic License, as specified in the README file.
 *
 */

/*
 * 'What a fix!' said Sam. 'That's the one place in all the lands we've ever
 * heard of that we don't want to see any closer; and that's the one place
 * we're trying to get to!  And that's just where we can't get, nohow.'
 *
 * 'Well do I understand your speech,' he answered in the same language;
 * 'yet few strangers do so.  Why then do you not speak in the Common Tongue,
 * as is the custom in the West, if you wish to be answered?'
 *
 * ...the travellers perceived that the floor was paved with stones of many
 * hues; branching runes and strange devices intertwined beneath their feet.
 */

#include "EXTERN.h"
#define PERL_IN_UTF8_C
#include "perl.h"

/* Unicode support */

U8 *
Perl_uv_to_utf8(pTHX_ U8 *d, UV uv) /* the d must be UTF8_MAXLEN+1 deep */
{
    if (uv < 0x80) {
	*d++ = uv;
	*d   = 0;
	return d;
    }
    if (uv < 0x800) {
	*d++ = (( uv >>  6)         | 0xc0);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
    if (uv < 0x10000) {
	*d++ = (( uv >> 12)         | 0xe0);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
    if (uv < 0x200000) {
	*d++ = (( uv >> 18)         | 0xf0);
	*d++ = (((uv >> 12) & 0x3f) | 0x80);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
    if (uv < 0x4000000) {
	*d++ = (( uv >> 24)         | 0xf8);
	*d++ = (((uv >> 18) & 0x3f) | 0x80);
	*d++ = (((uv >> 12) & 0x3f) | 0x80);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
    if (uv < 0x80000000) {
	*d++ = (( uv >> 30)         | 0xfc);
	*d++ = (((uv >> 24) & 0x3f) | 0x80);
	*d++ = (((uv >> 18) & 0x3f) | 0x80);
	*d++ = (((uv >> 12) & 0x3f) | 0x80);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
#ifdef HAS_QUAD
    if (uv < UTF8_QUAD_MAX)
#endif
    {
	*d++ =                        0xfe;	/* Can't match U+FEFF! */
	*d++ = (((uv >> 30) & 0x3f) | 0x80);
	*d++ = (((uv >> 24) & 0x3f) | 0x80);
	*d++ = (((uv >> 18) & 0x3f) | 0x80);
	*d++ = (((uv >> 12) & 0x3f) | 0x80);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
#ifdef HAS_QUAD
    {
	*d++ =                        0xff;	/* Can't match U+FFFE! */
	*d++ =                        0x80;	/* 6 Reserved bits */
	*d++ = (((uv >> 60) & 0x0f) | 0x80);	/* 2 Reserved bits */
	*d++ = (((uv >> 54) & 0x3f) | 0x80);
	*d++ = (((uv >> 48) & 0x3f) | 0x80);
	*d++ = (((uv >> 42) & 0x3f) | 0x80);
	*d++ = (((uv >> 36) & 0x3f) | 0x80);
	*d++ = (((uv >> 30) & 0x3f) | 0x80);
	*d++ = (((uv >> 24) & 0x3f) | 0x80);
	*d++ = (((uv >> 18) & 0x3f) | 0x80);
	*d++ = (((uv >> 12) & 0x3f) | 0x80);
	*d++ = (((uv >>  6) & 0x3f) | 0x80);
	*d++ = (( uv        & 0x3f) | 0x80);
	*d   = 0;
	return d;
    }
#endif
}

/* Tests if some arbitrary number of bytes begins in a valid UTF-8 character.
 * The actual number of bytes in the UTF-8 character will be returned if it
 * is valid, otherwise 0. */
STRLEN
Perl_is_utf8_char(pTHX_ U8 *s)
{
    U8 u = *s;
    STRLEN slen, len;
    UV uv, ouv;

    if (u <= 0x7f)
	return 1;

    if (u >= 0x80 && u <= 0xbf)
	return 0;

    len = UTF8SKIP(s);

    if (len < 2 || (u >= 0xc0 && u <= 0xfd && s[1] < 0x80))
	return 0;

    slen = len - 1;
    s++;
    uv = u;
    ouv = uv;
    while (slen--) {
	if ((*s & 0xc0) != 0x80)
	    return 0;
	uv = (uv << 6) | (*s & 0x3f);
	if (uv < ouv)
	    return 0;
	ouv = uv;
	s++;
    }

    if (UNISKIP(uv) < len)
	return 0;

    return len;
}

/*
=for apidoc Am|is_utf8_string|U8 *s|STRLEN len

Returns true if first C<len> bytes of the given string form valid a UTF8
string, false otherwise.

=cut
*/

bool
Perl_is_utf8_string(pTHX_ U8 *s, STRLEN len)
{
    U8* x = s;
    U8* send = s + len;
    STRLEN c;

    while (x < send) {
        c = is_utf8_char(x);
	if (!c)
	    return FALSE;
        x += c;
        if (x > send)
            return FALSE;
    }

    return TRUE;
}

/*
=for apidoc Am|U8* s|utf8_to_uv|STRLEN curlen|STRLEN *retlen|U32 flags

Returns the character value of the first character in the string C<s>
which is assumed to be in UTF8 encoding and no longer than C<curlen>;
C<retlen> will be set to the length, in bytes, of that character,
and the pointer C<s> will be advanced to the end of the character.

If C<s> does not point to a well-formed UTF8 character, the behaviour
is dependent on the value of C<flags>: if it contains UTF8_CHECK_ONLY,
it is assumed that the caller will raise a warning, and this function
will set C<retlen> to C<-1> and return.  The C<flags> can also contain
various flags to allow deviations from the strict UTF-8 encoding 
(see F<utf8.h>).

=cut */

UV
Perl_utf8_to_uv(pTHX_ U8* s, STRLEN curlen, STRLEN* retlen, U32 flags)
{
    UV uv = *s, ouv;
    STRLEN len = 1;
#ifdef EBCDIC
    bool dowarn = 0;
#else
    bool dowarn = ckWARN_d(WARN_UTF8);
#endif
    STRLEN expectlen = 0;
    
    if (curlen == 0) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (an empty string)");
	goto malformed;
    }

    if (uv <= 0x7f) { /* Pure ASCII. */
	if (retlen)
	    *retlen = 1;
	return *s;
    }

    if ((uv >= 0x80 && uv <= 0xbf) &&
	!(flags & UTF8_ALLOW_CONTINUATION)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (unexpected continuation byte 0x%02"UVxf")",
			uv);
	goto malformed;
    }

    if ((uv >= 0xc0 && uv <= 0xfd && curlen > 1 && s[1] < 0x80) &&
	!(flags & UTF8_ALLOW_NON_CONTINUATION)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (unexpected non-continuation byte 0x%02"UVxf" after byte 0x%02"UVxf")",
			(UV)s[1], uv);
	goto malformed;
    }
    
    if ((uv == 0xfe || uv == 0xff) &&
	!(flags & UTF8_ALLOW_FE_FF)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (byte 0x%02"UVxf")",
			uv);
	goto malformed;
    }
	
    if      (!(uv & 0x20))	{ len =  2; uv &= 0x1f; }
    else if (!(uv & 0x10))	{ len =  3; uv &= 0x0f; }
    else if (!(uv & 0x08))	{ len =  4; uv &= 0x07; }
    else if (!(uv & 0x04))	{ len =  5; uv &= 0x03; }
    else if (!(uv & 0x02))	{ len =  6; uv &= 0x01; }
    else if (!(uv & 0x01))	{ len =  7; uv = 0; }
    else 			{ len = 13; uv = 0; } /* whoa! */
	
    if (retlen)
	*retlen = len;
    
    expectlen = len;

    if ((curlen < expectlen) &&
	!(flags & UTF8_ALLOW_SHORT)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (%d byte%s, need %d)",
			curlen, curlen == 1 ? "" : "s", expectlen);
	goto malformed;
    }

    len--;
    s++;
    ouv = uv;

    while (len--) {
	if ((*s & 0xc0) != 0x80) {
	    if (dowarn)
		Perl_warner(aTHX_ WARN_UTF8,
			    "Malformed UTF-8 character (unexpected continuation byte 0x%02x)",
			    *s);
	    goto malformed;
	}
	else
	    uv = (uv << 6) | (*s & 0x3f);
	if (uv < ouv) {
	    /* This cannot be allowed. */
	    if (dowarn)
		Perl_warner(aTHX_ WARN_UTF8,
			    "Malformed UTF-8 character (overflow at 0x%"UVxf", byte 0x%02x)",
			    ouv, *s);
	    goto malformed;
	}
	s++;
	ouv = uv;
    }

    if ((uv >= 0xd800 && uv <= 0xdfff) &&
	!(flags & UTF8_ALLOW_SURROGATE)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (UTF-16 surrogate 0x%04"UVxf")",
			uv);
	goto malformed;
    } else if ((uv == 0xfffe) &&
	       !(flags & UTF8_ALLOW_BOM)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (byte order mark 0x%04"UVxf")",
			uv);
	goto malformed;
    } else if ((uv == 0xffff) &&
	       !(flags & UTF8_ALLOW_FFFF)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (character 0x%04"UVxf")",
			uv);
	goto malformed;
    } else if ((expectlen > UNISKIP(uv)) &&
	       !(flags & UTF8_ALLOW_LONG)) {
	if (dowarn)
	    Perl_warner(aTHX_ WARN_UTF8,
			"Malformed UTF-8 character (%d byte%s, need %d)",
			expectlen, expectlen == 1 ? "": "s", UNISKIP(uv));
	goto malformed;
    }

    return uv;

malformed:

    if (flags & UTF8_CHECK_ONLY) {
	if (retlen)
	    *retlen = -1;
	return 0;
    }

    if (retlen)
	*retlen = expectlen ? expectlen : len;

    return UNICODE_REPLACEMENT_CHARACTER;
}

/*
=for apidoc Am|U8* s|utf8_to_uv_simple|STRLEN *retlen

Returns the character value of the first character in the string C<s>
which is assumed to be in UTF8 encoding; C<retlen> will be set to the
length, in bytes, of that character, and the pointer C<s> will be
advanced to the end of the character.

If C<s> does not point to a well-formed UTF8 character, zero is
returned and retlen is set, if possible, to -1.

=cut
*/

UV
Perl_utf8_to_uv_simple(pTHX_ U8* s, STRLEN* retlen)
{
    return Perl_utf8_to_uv(aTHX_ s, UTF8_MAXLEN, retlen, 0);
}

/*
=for apidoc|utf8_length|U8 *s|U8 *e

Return the length of the UTF-8 char encoded string C<s> in characters.
Stops at C<e> (inclusive).  If C<e E<lt> s> or if the scan would end
up past C<e>, croaks.

=cut
*/

STRLEN
Perl_utf8_length(pTHX_ U8* s, U8* e)
{
    STRLEN len = 0;

    if (e < s)
	Perl_croak(aTHX_ "panic: utf8_length: unexpected end");
    while (s < e) {
	U8 t = UTF8SKIP(s);

	if (e - s < t)
	    Perl_croak(aTHX_ "panic: utf8_length: unaligned end");
	s += t;
	len++;
    }

    return len;
}

/* utf8_distance(a,b) returns the number of UTF8 characters between
   the pointers a and b							*/

IV
Perl_utf8_distance(pTHX_ U8 *a, U8 *b)
{
    IV off = 0;

    if (a < b) {
	while (a < b) {
	    U8 c = UTF8SKIP(a);

	    if (b - a < c)
		Perl_croak(aTHX_ "panic: utf8_distance: unaligned end");
	    a += c;
	    off--;
	}
    }
    else {
	while (b < a) {
	    U8 c = UTF8SKIP(b);

	    if (a - b < c)
		Perl_croak(aTHX_ "panic: utf8_distance: unaligned end");
	    b += c;
	    off++;
	}
    }

    return off;
}

/* WARNING: do not use the following unless you *know* off is within bounds */

U8 *
Perl_utf8_hop(pTHX_ U8 *s, I32 off)
{
    if (off >= 0) {
	while (off--)
	    s += UTF8SKIP(s);
    }
    else {
	while (off++) {
	    s--;
	    if (*s & 0x80) {
		while ((*s & 0xc0) == 0x80)
		    s--;
	    }
	}
    }
    return s;
}

/*
=for apidoc Am|U8 *|utf8_to_bytes|U8 *s|STRLEN *len

Converts a string C<s> of length C<len> from UTF8 into byte encoding.
Unlike C<bytes_to_utf8>, this over-writes the original string, and
updates len to contain the new length.
Returns zero on failure, setting C<len> to -1.

=cut
*/

U8 *
Perl_utf8_to_bytes(pTHX_ U8* s, STRLEN *len)
{
    U8 *send;
    U8 *d;
    U8 *save = s;

    /* ensure valid UTF8 and chars < 256 before updating string */
    for (send = s + *len; s < send; ) {
        U8 c = *s++;

        if (c >= 0x80 &&
            ((s >= send) ||
	     ((*s++ & 0xc0) != 0x80) || ((c & 0xfe) != 0xc2))) {
            *len = -1;
            return 0;
        }
    }

    d = s = save;
    while (s < send) {
        if (*s < 0x80) {
	    *d++ = *s++;
	}
        else {
            STRLEN ulen;
            *d++ = (U8)utf8_to_uv_simple(s, &ulen);
            s += ulen;
        }
    }
    *d = '\0';
    *len = d - save;
    return save;
}

/*
=for apidoc Am|U8 *|bytes_to_utf8|U8 *s|STRLEN *len

Converts a string C<s> of length C<len> from ASCII into UTF8 encoding.
Returns a pointer to the newly-created string, and sets C<len> to
reflect the new length.

=cut
*/

U8*
Perl_bytes_to_utf8(pTHX_ U8* s, STRLEN *len)
{
    U8 *send;
    U8 *d;
    U8 *dst;
    send = s + (*len);

    Newz(801, d, (*len) * 2 + 1, U8);
    dst = d;

    while (s < send) {
        if (*s < 0x80)
            *d++ = *s++;
        else {
            UV uv = *s++;
            *d++ = (( uv >>  6)         | 0xc0);
            *d++ = (( uv        & 0x3f) | 0x80);
        }
    }
    *d = '\0';
    *len = d-dst;
    return dst;
}

/*
 * Convert native (big-endian) or reversed (little-endian) UTF-16 to UTF-8.
 *
 * Destination must be pre-extended to 3/2 source.  Do not use in-place.
 * We optimize for native, for obvious reasons. */

U8*
Perl_utf16_to_utf8(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
{
    U8* pend;
    U8* dstart = d;

    if (bytelen & 1)
	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen");

    pend = p + bytelen;

    while (p < pend) {
	UV uv = (p[0] << 8) + p[1]; /* UTF-16BE */
	p += 2;
	if (uv < 0x80) {
	    *d++ = uv;
	    continue;
	}
	if (uv < 0x800) {
	    *d++ = (( uv >>  6)         | 0xc0);
	    *d++ = (( uv        & 0x3f) | 0x80);
	    continue;
	}
	if (uv >= 0xd800 && uv < 0xdbff) {	/* surrogates */
	    UV low = *p++;
	    if (low < 0xdc00 || low >= 0xdfff)
		Perl_croak(aTHX_ "Malformed UTF-16 surrogate");
	    uv = ((uv - 0xd800) << 10) + (low - 0xdc00) + 0x10000;
	}
	if (uv < 0x10000) {
	    *d++ = (( uv >> 12)         | 0xe0);
	    *d++ = (((uv >>  6) & 0x3f) | 0x80);
	    *d++ = (( uv        & 0x3f) | 0x80);
	    continue;
	}
	else {
	    *d++ = (( uv >> 18)         | 0xf0);
	    *d++ = (((uv >> 12) & 0x3f) | 0x80);
	    *d++ = (((uv >>  6) & 0x3f) | 0x80);
	    *d++ = (( uv        & 0x3f) | 0x80);
	    continue;
	}
    }
    *newlen = d - dstart;
    return d;
}

/* Note: this one is slightly destructive of the source. */

U8*
Perl_utf16_to_utf8_reversed(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
{
    U8* s = (U8*)p;
    U8* send = s + bytelen;
    while (s < send) {
	U8 tmp = s[0];
	s[0] = s[1];
	s[1] = tmp;
	s += 2;
    }
    return utf16_to_utf8(p, d, bytelen, newlen);
}

/* for now these are all defined (inefficiently) in terms of the utf8 versions */

bool
Perl_is_uni_alnum(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_alnum(tmpbuf);
}

bool
Perl_is_uni_alnumc(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_alnumc(tmpbuf);
}

bool
Perl_is_uni_idfirst(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_idfirst(tmpbuf);
}

bool
Perl_is_uni_alpha(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_alpha(tmpbuf);
}

bool
Perl_is_uni_ascii(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_ascii(tmpbuf);
}

bool
Perl_is_uni_space(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_space(tmpbuf);
}

bool
Perl_is_uni_digit(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_digit(tmpbuf);
}

bool
Perl_is_uni_upper(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_upper(tmpbuf);
}

bool
Perl_is_uni_lower(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_lower(tmpbuf);
}

bool
Perl_is_uni_cntrl(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_cntrl(tmpbuf);
}

bool
Perl_is_uni_graph(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_graph(tmpbuf);
}

bool
Perl_is_uni_print(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_print(tmpbuf);
}

bool
Perl_is_uni_punct(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_punct(tmpbuf);
}

bool
Perl_is_uni_xdigit(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return is_utf8_xdigit(tmpbuf);
}

U32
Perl_to_uni_upper(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return to_utf8_upper(tmpbuf);
}

U32
Perl_to_uni_title(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return to_utf8_title(tmpbuf);
}

U32
Perl_to_uni_lower(pTHX_ U32 c)
{
    U8 tmpbuf[UTF8_MAXLEN+1];
    uv_to_utf8(tmpbuf, (UV)c);
    return to_utf8_lower(tmpbuf);
}

/* for now these all assume no locale info available for Unicode > 255 */

bool
Perl_is_uni_alnum_lc(pTHX_ U32 c)
{
    return is_uni_alnum(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_alnumc_lc(pTHX_ U32 c)
{
    return is_uni_alnumc(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_idfirst_lc(pTHX_ U32 c)
{
    return is_uni_idfirst(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_alpha_lc(pTHX_ U32 c)
{
    return is_uni_alpha(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_ascii_lc(pTHX_ U32 c)
{
    return is_uni_ascii(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_space_lc(pTHX_ U32 c)
{
    return is_uni_space(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_digit_lc(pTHX_ U32 c)
{
    return is_uni_digit(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_upper_lc(pTHX_ U32 c)
{
    return is_uni_upper(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_lower_lc(pTHX_ U32 c)
{
    return is_uni_lower(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_cntrl_lc(pTHX_ U32 c)
{
    return is_uni_cntrl(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_graph_lc(pTHX_ U32 c)
{
    return is_uni_graph(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_print_lc(pTHX_ U32 c)
{
    return is_uni_print(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_punct_lc(pTHX_ U32 c)
{
    return is_uni_punct(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_xdigit_lc(pTHX_ U32 c)
{
    return is_uni_xdigit(c);	/* XXX no locale support yet */
}

U32
Perl_to_uni_upper_lc(pTHX_ U32 c)
{
    return to_uni_upper(c);	/* XXX no locale support yet */
}

U32
Perl_to_uni_title_lc(pTHX_ U32 c)
{
    return to_uni_title(c);	/* XXX no locale support yet */
}

U32
Perl_to_uni_lower_lc(pTHX_ U32 c)
{
    return to_uni_lower(c);	/* XXX no locale support yet */
}

bool
Perl_is_utf8_alnum(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_alnum)
	/* NOTE: "IsWord", not "IsAlnum", since Alnum is a true
	 * descendant of isalnum(3), in other words, it doesn't
	 * contain the '_'. --jhi */
	PL_utf8_alnum = swash_init("utf8", "IsWord", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_alnum, p);
/*    return *p == '_' || is_utf8_alpha(p) || is_utf8_digit(p); */
#ifdef SURPRISINGLY_SLOWER  /* probably because alpha is usually true */
    if (!PL_utf8_alnum)
	PL_utf8_alnum = swash_init("utf8", "",
	    sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
    return swash_fetch(PL_utf8_alnum, p);
#endif
}

bool
Perl_is_utf8_alnumc(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_alnum)
	PL_utf8_alnum = swash_init("utf8", "IsAlnumC", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_alnum, p);
/*    return is_utf8_alpha(p) || is_utf8_digit(p); */
#ifdef SURPRISINGLY_SLOWER  /* probably because alpha is usually true */
    if (!PL_utf8_alnum)
	PL_utf8_alnum = swash_init("utf8", "",
	    sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
    return swash_fetch(PL_utf8_alnum, p);
#endif
}

bool
Perl_is_utf8_idfirst(pTHX_ U8 *p)
{
    return *p == '_' || is_utf8_alpha(p);
}

bool
Perl_is_utf8_alpha(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_alpha)
	PL_utf8_alpha = swash_init("utf8", "IsAlpha", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_alpha, p);
}

bool
Perl_is_utf8_ascii(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_ascii)
	PL_utf8_ascii = swash_init("utf8", "IsAscii", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_ascii, p);
}

bool
Perl_is_utf8_space(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_space)
	PL_utf8_space = swash_init("utf8", "IsSpacePerl", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_space, p);
}

bool
Perl_is_utf8_digit(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_digit)
	PL_utf8_digit = swash_init("utf8", "IsDigit", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_digit, p);
}

bool
Perl_is_utf8_upper(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_upper)
	PL_utf8_upper = swash_init("utf8", "IsUpper", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_upper, p);
}

bool
Perl_is_utf8_lower(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_lower)
	PL_utf8_lower = swash_init("utf8", "IsLower", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_lower, p);
}

bool
Perl_is_utf8_cntrl(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_cntrl)
	PL_utf8_cntrl = swash_init("utf8", "IsCntrl", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_cntrl, p);
}

bool
Perl_is_utf8_graph(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_graph)
	PL_utf8_graph = swash_init("utf8", "IsGraph", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_graph, p);
}

bool
Perl_is_utf8_print(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_print)
	PL_utf8_print = swash_init("utf8", "IsPrint", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_print, p);
}

bool
Perl_is_utf8_punct(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_punct)
	PL_utf8_punct = swash_init("utf8", "IsPunct", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_punct, p);
}

bool
Perl_is_utf8_xdigit(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_xdigit)
	PL_utf8_xdigit = swash_init("utf8", "IsXDigit", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_xdigit, p);
}

bool
Perl_is_utf8_mark(pTHX_ U8 *p)
{
    if (!is_utf8_char(p))
	return FALSE;
    if (!PL_utf8_mark)
	PL_utf8_mark = swash_init("utf8", "IsM", &PL_sv_undef, 0, 0);
    return swash_fetch(PL_utf8_mark, p);
}

UV
Perl_to_utf8_upper(pTHX_ U8 *p)
{
    UV uv;

    if (!PL_utf8_toupper)
	PL_utf8_toupper = swash_init("utf8", "ToUpper", &PL_sv_undef, 4, 0);
    uv = swash_fetch(PL_utf8_toupper, p);
    return uv ? uv : utf8_to_uv(p,UTF8_MAXLEN,0,0);
}

UV
Perl_to_utf8_title(pTHX_ U8 *p)
{
    UV uv;

    if (!PL_utf8_totitle)
	PL_utf8_totitle = swash_init("utf8", "ToTitle", &PL_sv_undef, 4, 0);
    uv = swash_fetch(PL_utf8_totitle, p);
    return uv ? uv : utf8_to_uv(p,UTF8_MAXLEN,0,0);
}

UV
Perl_to_utf8_lower(pTHX_ U8 *p)
{
    UV uv;

    if (!PL_utf8_tolower)
	PL_utf8_tolower = swash_init("utf8", "ToLower", &PL_sv_undef, 4, 0);
    uv = swash_fetch(PL_utf8_tolower, p);
    return uv ? uv : utf8_to_uv(p,UTF8_MAXLEN,0,0);
}

/* a "swash" is a swatch hash */

SV*
Perl_swash_init(pTHX_ char* pkg, char* name, SV *listsv, I32 minbits, I32 none)
{
    SV* retval;
    char tmpbuf[256];
    dSP;

    if (!gv_stashpv(pkg, 0)) {	/* demand load utf8 */
	ENTER;
	Perl_load_module(aTHX_ PERL_LOADMOD_NOIMPORT, newSVpv(pkg,0), Nullsv);
	LEAVE;
    }
    SPAGAIN;
    PUSHSTACKi(PERLSI_MAGIC);
    PUSHMARK(SP);
    EXTEND(SP,5);
    PUSHs(sv_2mortal(newSVpvn(pkg, strlen(pkg))));
    PUSHs(sv_2mortal(newSVpvn(name, strlen(name))));
    PUSHs(listsv);
    PUSHs(sv_2mortal(newSViv(minbits)));
    PUSHs(sv_2mortal(newSViv(none)));
    PUTBACK;
    ENTER;
    SAVEI32(PL_hints);
    PL_hints = 0;
    save_re_context();
    if (PL_curcop == &PL_compiling)	/* XXX ought to be handled by lex_start */
	strncpy(tmpbuf, PL_tokenbuf, sizeof tmpbuf);
    if (call_method("SWASHNEW", G_SCALAR))
	retval = newSVsv(*PL_stack_sp--);
    else
	retval = &PL_sv_undef;
    LEAVE;
    POPSTACK;
    if (PL_curcop == &PL_compiling) {
	strncpy(PL_tokenbuf, tmpbuf, sizeof tmpbuf);
	PL_curcop->op_private = PL_hints;
    }
    if (!SvROK(retval) || SvTYPE(SvRV(retval)) != SVt_PVHV)
	Perl_croak(aTHX_ "SWASHNEW didn't return an HV ref");
    return retval;
}

UV
Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr)
{
    HV* hv = (HV*)SvRV(sv);
    U32 klen = UTF8SKIP(ptr) - 1;
    U32 off = ptr[klen] & 127;  /* NB: 64 bit always 0 when len > 1 */
    STRLEN slen;
    STRLEN needents = (klen ? 64 : 128);
    U8 *tmps;
    U32 bit;
    SV *retval;

    /*
     * This single-entry cache saves about 1/3 of the utf8 overhead in test
     * suite.  (That is, only 7-8% overall over just a hash cache.  Still,
     * it's nothing to sniff at.)  Pity we usually come through at least
     * two function calls to get here...
     *
     * NB: this code assumes that swatches are never modified, once generated!
     */

    if (hv == PL_last_swash_hv &&
	klen == PL_last_swash_klen &&
	(!klen || memEQ((char *)ptr,(char *)PL_last_swash_key,klen)) )
    {
	tmps = PL_last_swash_tmps;
	slen = PL_last_swash_slen;
    }
    else {
	/* Try our second-level swatch cache, kept in a hash. */
	SV** svp = hv_fetch(hv, (char*)ptr, klen, FALSE);

	/* If not cached, generate it via utf8::SWASHGET */
	if (!svp || !SvPOK(*svp) || !(tmps = (U8*)SvPV(*svp, slen))) {
	    dSP;
	    ENTER;
	    SAVETMPS;
	    save_re_context();
	    PUSHSTACKi(PERLSI_MAGIC);
	    PUSHMARK(SP);
	    EXTEND(SP,3);
	    PUSHs((SV*)sv);
	    PUSHs(sv_2mortal(newSViv(utf8_to_uv(ptr, UTF8_MAXLEN, 0, 0) & ~(needents - 1))));
	    PUSHs(sv_2mortal(newSViv(needents)));
	    PUTBACK;
	    if (call_method("SWASHGET", G_SCALAR))
		retval = newSVsv(*PL_stack_sp--);
	    else
		retval = &PL_sv_undef;
	    POPSTACK;
	    FREETMPS;
	    LEAVE;
	    if (PL_curcop == &PL_compiling)
		PL_curcop->op_private = PL_hints;

	    svp = hv_store(hv, (char*)ptr, klen, retval, 0);

	    if (!svp || !(tmps = (U8*)SvPV(*svp, slen)) || slen < 8)
		Perl_croak(aTHX_ "SWASHGET didn't return result of proper length");
	}

	PL_last_swash_hv = hv;
	PL_last_swash_klen = klen;
	PL_last_swash_tmps = tmps;
	PL_last_swash_slen = slen;
	if (klen)
	    Copy(ptr, PL_last_swash_key, klen, U8);
    }

    switch ((int)((slen << 3) / needents)) {
    case 1:
	bit = 1 << (off & 7);
	off >>= 3;
	return (tmps[off] & bit) != 0;
    case 8:
	return tmps[off];
    case 16:
	off <<= 1;
	return (tmps[off] << 8) + tmps[off + 1] ;
    case 32:
	off <<= 2;
	return (tmps[off] << 24) + (tmps[off+1] << 16) + (tmps[off+2] << 8) + tmps[off + 3] ;
    }
    Perl_croak(aTHX_ "panic: swash_fetch");
    return 0;
}