-
Notifications
You must be signed in to change notification settings - Fork 33
/
encGlue.c
1045 lines (946 loc) · 21.6 KB
/
encGlue.c
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
/*
Copyright (c) 2000-2004 Nick Ing-Simmons. All rights reserved.
This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
*/
#define PERL_NO_GET_CONTEXT
#include <EXTERN.h>
#include <perl.h>
#include <XSUB.h>
#ifdef HAS_NL_LANGINFO
#include <langinfo.h>
#endif
#define NEED_utf8_to_uvchr_buf
#define NEED_my_strnlen
#include "ppport.h"
#define U8 U8
#include "tkGlue.def"
#include "pTk/tkPort.h"
#include "pTk/tkInt.h"
#include "tkGlue.h"
#ifdef WIN32
#include "pTk/tkWinInt.h"
#endif
#ifdef SvUTF8
/* Workaround for immediate crash with perl 5.19.9+ and without XFT
* See https://rt.cpan.org/Ticket/Display.html?id=96543 and
* https://rt.perl.org/Ticket/Display.html?id=120626
*/
#if !defined(USE_XFT_FONTS) && PERL_VERSION > 19 || (PERL_VERSION == 19 && PERL_SUBVERSION >= 9)
#define NEED_PUSHSTACK_HACK
#endif
#undef MAX
#define MAX(a,b) ((a)>(b)?(a):(b))
/* -------------------------------------------------------------------------- */
/* UTF8-ness routines
/* -------------------------------------------------------------------------- */
int
Tcl_UtfCharComplete(str, len)
CONST char *str; /* String to check if first few bytes
* contain a complete UTF-8 character. */
int len; /* Length of above string in bytes. */
{
return len >= UTF8SKIP((U8 *) str);
}
Tcl_UniChar
Tcl_UniCharToUpper(int ch)
{
dTHX;
U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
STRLEN len;
return toUPPER_uvchr(ch, tmpbuf, &len);
}
Tcl_UniChar
Tcl_UniCharToLower(int ch)
{
dTHX;
U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
STRLEN len;
return toLOWER_uvchr(ch, tmpbuf, &len);
}
int
Tcl_UniCharIsAlpha(int ch)
{
dTHX;
return isALPHA_uvchr(ch);
}
int
Tcl_UniCharIsWordChar(int ch)
{
dTHX;
return isWORDCHAR_uvchr(ch);
}
int
Tcl_UniCharIsSpace(int ch)
{
dTHX;
return isSPACE_uvchr(ch);
}
int
Tcl_UniCharIsUpper(int ch)
{
dTHX;
return isUPPER_uvchr(ch);
}
int
Tcl_NumUtfChars(CONST char * src, int len)
{
U8 *s = (U8 *) src;
U8 *send;
if (len < 0)
len = strlen(src);
send = s + len;
len = 0;
while (s < send)
{
s += UTF8SKIP(s);
len++;
}
return len;
}
CONST char *
Tcl_UtfNext (CONST char * src)
{
CONST U8 *s = (CONST U8 *) src;
if (*s)
src += UTF8SKIP(s);
return src;
}
CONST char *
Tcl_UtfPrev (CONST char * src,CONST char * start)
{
dTHX;
U8 *s = (U8 *) src;
if (src > start)
return (CONST char *) utf8_hop(s,-1);
else
return (CONST char *) s;
}
CONST char *
Tcl_UtfAtIndex (CONST char * src, int index)
{
dTHX;
U8 *s = (U8 *) src;
return (CONST char*)utf8_hop(s,index);
}
int
Tcl_UtfToUniChar (CONST char * src,Tcl_UniChar * chPtr)
{
dTHX;
STRLEN len;
*chPtr = utf8_to_uvchr_buf((U8 *)src, src + UTF8_CHK_SKIP(src), &len);
return len;
}
int
Tcl_UniCharToUtf(int ch, char * buf)
{
dTHX;
/* We "allow any" as the page cache algorithm hits at least U+FFFE */
#ifdef UNICODE_ALLOW_ANY
U8 *p = uvchr_to_utf8_flags((U8 *) buf,ch, UNICODE_ALLOW_ANY);
#else
U8 *p = Perl_uv_to_utf8(aTHX_ (U8 *) buf,ch);
#endif
return p - (U8 *) buf;
}
char *
Tcl_UniCharToUtfDString(wString, numChars, dsPtr)
CONST Tcl_UniChar *wString; /* Unicode string to convert to UTF-8. */
int numChars; /* Length of Unicode string in Tcl_UniChars
* (must be >= 0). */
Tcl_DString *dsPtr; /* UTF-8 representation of string is
* appended to this previously initialized
* DString. */
{
CONST Tcl_UniChar *w, *wEnd;
char *p, *string;
int oldLength;
/*
* UTF-8 string length in bytes will be <= Unicode string length *
* TCL_UTF_MAX.
*/
oldLength = Tcl_DStringLength(dsPtr);
Tcl_DStringSetLength(dsPtr, (oldLength + numChars + 1) * UTF8_MAXBYTES_CASE);
string = Tcl_DStringValue(dsPtr) + oldLength;
p = string;
wEnd = wString + numChars;
for (w = wString; w < wEnd; ) {
p += Tcl_UniCharToUtf(*w, p);
w++;
}
Tcl_DStringSetLength(dsPtr, oldLength + (p - string));
return string;
}
Tcl_UniChar *
Tcl_UtfToUniCharDString(string, length, dsPtr)
CONST char *string; /* UTF-8 string to convert to Unicode. */
int length; /* Length of UTF-8 string in bytes, or -1
* for strlen(). */
Tcl_DString *dsPtr; /* Unicode representation of string is
* appended to this previously initialized
* DString. */
{
Tcl_UniChar *w, *wString;
CONST char *p, *end;
int oldLength;
if (length < 0) {
length = strlen(string);
}
/*
* Unicode string length in Tcl_UniChars will be <= UTF-8 string length
* in bytes.
*/
oldLength = Tcl_DStringLength(dsPtr);
Tcl_DStringSetLength(dsPtr,
(int) ((oldLength + length + 1) * sizeof(Tcl_UniChar)));
wString = (Tcl_UniChar *) (Tcl_DStringValue(dsPtr) + oldLength);
w = wString;
end = string + length;
for (p = string; p < end; ) {
p += Tcl_UtfToUniChar(p, w);
w++;
}
*w = '\0';
Tcl_DStringSetLength(dsPtr,
(oldLength + ((char *) w - (char *) wString)));
return wString;
}
int
Tcl_UniCharLen(str)
CONST Tcl_UniChar *str; /* Unicode string to find length of. */
{
int len = 0;
while (*str != '\0') {
len++;
str++;
}
return len;
}
/* Doing these in-place seems risky ... */
int
Tcl_UtfToLower (char * src)
{
dTHX;
U8 *s = (U8 *)src;
U8 *d = s;
while (*s)
{
STRLEN len;
toLOWER_utf8_safe(s, s + UTF8_CHK_SKIP(s), d, &len );
d += len;
s += len;
}
*d = '\0';
return (d-(U8 *)src);
}
int
Tcl_UtfToUpper(char * src)
{
dTHX;
U8 *s = (U8 *)src;
U8 *d = s;
while (*s)
{
STRLEN len;
toUPPER_utf8_safe(s, s + UTF8_CHK_SKIP(s), d, &len );
d += len;
s += len;
}
*d = '\0';
return (d-(U8 *)src);
}
#else
/* -------------------------------------------------------------------------- */
/* Dummy UTF8-ness routines
/* -------------------------------------------------------------------------- */
Tcl_UniChar
Tcl_UniCharToUpper(int ch)
{
/* Only the ASCII characters and those in E0..FE have upper case
* values that are still in range */
return ((isLOWER_L1(ch) && (isASCII(ch) || (ch >= 0xE0 && ch <= 0xFE)))
? ch - 0x20
: ch);
}
Tcl_UniChar
Tcl_UniCharToLower(int ch)
{
return ((! isUPPER_L1(ch)) ? ch : ch + 0x20)
}
int
Tcl_UniCharIsAlpha(int ch)
{
return isALPHA_L1(ch);
}
int
Tcl_UniCharIsUpper(int ch)
{
return isUPPER_L1(ch);
}
int
Tcl_NumUtfChars(CONST char * src, int len)
{
if (len < 0)
return strlen(src);
return len;
}
int
Tcl_UtfToLower (char * src)
{
char *s = src;
int n = 0;
while (*s)
{
*s = Tcl_UniCharToLower(UCHAR(*s));
s++;
}
*s = '\0';
return (s-src);
}
int
Tcl_UtfToUpper(char * src)
{
char *s = src;
int n = 0;
while (*s)
{
*s = Tcl_UniCharToUpper(UCHAR(*s));
s++;
}
*s = '\0';
return (s-src);
}
CONST char *
Tcl_UtfNext (CONST char * src)
{
return src+1;
}
char *
Tcl_UtfPrev (CONST char * src,CONST char * start)
{
if (src > start)
src--;
return (char *)src;
}
char *
Tcl_UtfAtIndex (CONST char * src, int index)
{
return (char*)src+index;
}
int
Tcl_UtfToUniChar (CONST char * src,Tcl_UniChar * chPtr)
{
*chPtr = *src;
return 1;
}
int
Tcl_UniCharToUtf(int ch, char * buf)
{
*buf = ch;
return 1;
}
#endif /* SvUTF8 */
/*
*----------------------------------------------------------------------
*
* Tcl_StringMatch --
*
* See if a particular string matches a particular pattern.
*
* Results:
* The return value is 1 if string matches pattern, and
* 0 otherwise. The matching operation permits the following
* special characters in the pattern: *?\[] (see the manual
* entry for details on what these mean).
*
* Side effects:
* None.
*
*----------------------------------------------------------------------
*/
int
Tcl_StringMatch(string, pattern)
CONST char *string; /* String. */
CONST char *pattern; /* Pattern, which may contain special
* characters. */
{
int p, s;
CONST char *pstart = pattern;
while (1) {
p = *pattern;
s = *string;
/*
* See if we're at the end of both the pattern and the string. If
* so, we succeeded. If we're at the end of the pattern but not at
* the end of the string, we failed.
*/
if (p == '\0') {
if (s == '\0') {
return 1;
} else {
return 0;
}
}
if ((s == '\0') && (p != '*')) {
return 0;
}
/* Check for a "*" as the next pattern character. It matches
* any substring. We handle this by calling ourselves
* recursively for each postfix of string, until either we
* match or we reach the end of the string.
*/
if (p == '*') {
pattern++;
if (*pattern == '\0') {
return 1;
}
while (1) {
if (Tcl_StringMatch(string, pattern)) {
return 1;
}
if (*string == '\0') {
return 0;
}
string++;
}
}
/* Check for a "?" as the next pattern character. It matches
* any single character.
*/
if (p == '?') {
Tcl_UniChar ch;
pattern++;
string += Tcl_UtfToUniChar(string, &ch);
continue;
}
/* Check for a "[" as the next pattern character. It is followed
* by a list of characters that are acceptable, or by a range
* (two characters separated by "-").
*/
if (p == '[') {
Tcl_UniChar ch, startChar, endChar;
pattern++;
string += Tcl_UtfToUniChar(string, &ch);
while (1) {
if ((*pattern == ']') || (*pattern == '\0')) {
return 0;
}
pattern += Tcl_UtfToUniChar(pattern, &startChar);
if (*pattern == '-') {
pattern++;
if (*pattern == '\0') {
return 0;
}
pattern += Tcl_UtfToUniChar(pattern, &endChar);
if (((startChar <= ch) && (ch <= endChar))
|| ((endChar <= ch) && (ch <= startChar))) {
/*
* Matches ranges of form [a-z] or [z-a].
*/
break;
}
} else if (startChar == ch) {
break;
}
}
while (*pattern != ']') {
if (*pattern == '\0') {
pattern = Tcl_UtfPrev(pattern, pstart);
break;
}
pattern++;
}
pattern++;
continue;
}
/* If the next pattern character is '\', just strip off the '\'
* so we do exact matching on the character that follows.
*/
if (p == '\\') {
pattern++;
p = *pattern;
if (p == '\0') {
return 0;
}
}
/* There's no special character. Just make sure that the next
* bytes of each string match.
*/
if (s != p) {
return 0;
}
pattern++;
string++;
}
}
static HV *encodings = NULL;
Tcl_Encoding system_encoding = NULL;
Tcl_Encoding
GetSystemEncoding(void)
{
if (!system_encoding)
{
char *codeset = NULL;
/* This assumes perl's Configure probe stuff is #include-d above */
#if defined(HAS_NL_LANGINFO) && defined(CODESET)
codeset = nl_langinfo(CODESET);
#endif
if (!codeset)
codeset = "iso8859-1";
system_encoding = Tcl_GetEncoding(NULL,codeset);
if (!system_encoding)
system_encoding = Tcl_GetEncoding(NULL,"iso8859-1");
}
return system_encoding;
}
#define PerlEncObj(enc) (HeVAL((HE *) (enc)))
SV *
Lang_SystemEncoding(void)
{
dTHX;
return SvREFCNT_inc(PerlEncObj(GetSystemEncoding()));
}
Tcl_Encoding
Tcl_GetEncoding (Tcl_Interp * interp, CONST char * name)
{
dTHX;
HE *he;
STRLEN len = strlen(name);
SV *sv = NULL;
SV *nmsv = newSVpv((char *)name,len);
if (!encodings)
{
encodings = newHV();
}
he = hv_fetch_ent(encodings,nmsv,0,0);
if (!he || !HeVAL(he))
{
dSP;
ENTER;
SAVETMPS;
#ifdef NEED_PUSHSTACK_HACK
PUSHSTACKi(PERLSI_REQUIRE);
#endif
PUSHMARK(sp);
XPUSHs(sv_2mortal(newSVpv("Tk",0)));
XPUSHs(nmsv);
PUTBACK;
perl_call_method("getEncoding",G_SCALAR);
SPAGAIN;
sv = POPs;
PUTBACK;
he = hv_store_ent(encodings,nmsv,newSVsv(sv),0);
if (0 && !SvOK(sv))
warn("Cannot find '%s'",name);
#ifdef NEED_PUSHSTACK_HACK
POPSTACK;
#endif
FREETMPS;
LEAVE;
}
SvREFCNT_dec(nmsv);
sv = HeVAL(he);
if (sv_isobject(sv))
{
SvREFCNT_inc(sv);
return (Tcl_Encoding) he;
}
else
{
if (SvOK(sv))
warn("Strange encoding %"SVf,sv);
}
return NULL;
}
Tcl_Encoding
Lang_CreateEncoding(CONST char *encodingName,
Tcl_EncodingConvertProc *toUtfProc,
Tcl_EncodingConvertProc *fromUtfProc,
Tcl_EncodingFreeProc *freeProc,
ClientData clientData,
int nullSize)
{
return Tcl_GetEncoding(NULL,encodingName);
}
void
Tcl_FreeEncoding (Tcl_Encoding t)
{
if (t)
{
dTHX;
HE *he = (HE *) t;
SV *sv = HeVAL(he);
SvREFCNT_dec(sv);
}
}
CONST char *
Tcl_GetEncodingName(Tcl_Encoding encoding)
{
dTHX;
HE *he;
STRLEN len;
if (!encoding)
encoding = GetSystemEncoding();
he = (HE *) encoding;
return HePV(he,len);
}
static int
CallEncode(Tcl_Interp * interp,
Tcl_Encoding encoding, CONST char * src,
int srcLen, int flags,
Tcl_EncodingState * statePtr, char * dst,
int dstLen, int * srcReadPtr,
int * dstWrotePtr, int * dstCharsPtr,
const char *method)
{
dTHX;
int srcRead;
int dstWrote;
int dstChars;
int code = TCL_OK;
U8 *s = (U8 *) src;
U8 *send;
U8 *d = (U8 *) dst;
U8 *dend;
int chars = 0;
dSP;
SV *quiet;
SV *stmp;
SV *dtmp;
char *td;
STRLEN dbytes;
if (flags & TCL_ENCODING_STOPONERROR)
quiet = get_sv("Tk::encodeStopOnError",0);
else
quiet = get_sv("Tk::encodeFallback",0);
if (!encoding)
encoding = GetSystemEncoding();
if (!sv_isobject(PerlEncObj(encoding)))
abort();
if (!srcReadPtr)
srcReadPtr = &srcRead;
if (!dstWrotePtr)
dstWrotePtr = &dstWrote;
if (!dstCharsPtr)
dstCharsPtr = &dstChars;
else
{
LangDebug("%s wants char count\n",method);
}
if (!src)
srcLen = 0;
if (srcLen < 0)
srcLen = strlen(src);
send = s+srcLen;
dstLen -= 2;
dend = d + dstLen;
stmp = newSV(srcLen);
while (s < send)
{
STRLEN len = srcLen;
if (*method == 'e')
{
#if 0
/* We used to do things one char at a time ... can't remember why
perhaps to handle partial chars ?
we got perl to tell us length of one char using call below
Only makes sense for encode when source is UTF-8, though
by luck it worked for "decode" of UTF-8 as well
provided we did not set SvUTF8_on which upset Encode.xs
*/
UV ch = utf8n_to_uvchr(s, send-s, &len, UTF8_ALLOW_ANY|UTF8_CHECK_ONLY);
#endif
sv_setpvn(stmp,s,len);
if (has_highbit(s,len))
SvUTF8_on(stmp);
}
else
{
sv_setpvn(stmp,s,len);
}
SPAGAIN;
PUSHMARK(sp);
XPUSHs(PerlEncObj(encoding));
XPUSHs(stmp);
XPUSHs(quiet);
PUTBACK;
perl_call_method(method,G_SCALAR|G_EVAL);
if (SvTRUE(ERRSV))
{
code = TCL_ERROR;
if (interp)
{
Tcl_SetResult(interp,SvPV_nolen(ERRSV),TCL_VOLATILE);
}
else
{
warn("%"SVf,ERRSV);
}
break;
}
SPAGAIN;
dtmp = POPs;
PUTBACK;
#if 0
/* XXX This code seems to be wrong since Encode 2.10, when LEAVE_SRC was
* default (is this true?).
* This would fix the "selection conversion left too many bytes unconverted"
* aborts.
*/
if (SvCUR(stmp))
{
/* This could also be TCL_CONVERT_MULTIBYTE - how do we tell ? */
code = TCL_CONVERT_UNKNOWN;
break;
}
#endif
td = SvPV(dtmp,dbytes);
if (!dbytes)
{
code = TCL_CONVERT_UNKNOWN;
break;
}
if (d+dbytes > dend)
{
code = TCL_CONVERT_NOSPACE;
dbytes = dend-d;
break;
}
memcpy(d,td,dbytes);
d += dbytes;
/* FIXME? : Char count is bogus unless we do one-at-atime - if
we find something that wants it we need to get it some
other way - e.g. UTF8_SKIP()ing over whichever of src/dst is UTF-8
*/
chars++;
s += len;
}
SvREFCNT_dec(stmp);
*srcReadPtr = (s - (U8 *)src);
*dstCharsPtr = chars;
dst[dstLen] = '\0';
dst[dstLen+1] = '\0';
/* If dest is wide single '\0' may not be enough */
Zero(d,dend-d,char);
*dstWrotePtr = (d- (U8 *)dst);
return code;
}
int
Tcl_ExternalToUtf (Tcl_Interp * interp,
Tcl_Encoding encoding, CONST char * src,
int srcLen, int flags,
Tcl_EncodingState * statePtr, char * dst,
int dstLen, int * srcReadPtr,
int * dstWrotePtr, int * dstCharsPtr)
{
return CallEncode(interp,encoding,src,srcLen,flags,statePtr,dst,dstLen,
srcReadPtr,dstWrotePtr,dstCharsPtr,"decode");
}
int
Tcl_UtfToExternal(Tcl_Interp * interp,
Tcl_Encoding encoding, CONST char * src,
int srcLen, int flags,
Tcl_EncodingState * statePtr, char * dst,
int dstLen, int * srcReadPtr,
int * dstWrotePtr, int * dstCharsPtr)
{
return CallEncode(interp,encoding,src,srcLen,flags,statePtr,dst,dstLen,
srcReadPtr,dstWrotePtr,dstCharsPtr,"encode");
}
char *
Tcl_UtfToExternalDString(Tcl_Encoding encoding, CONST char * src,
int srcLen, Tcl_DString * dsPtr)
{
dTHX;
dSP;
SV *sv;
char *s = "";
STRLEN len = 0;
SV *fallback = get_sv("Tk::encodeFallback",0);
Tcl_DStringInit(dsPtr);
if (!encoding)
encoding = GetSystemEncoding();
if (!src)
srcLen = 0;
if (srcLen < 0)
srcLen = strlen(src);
if (srcLen)
{
int count;
SPAGAIN;
ENTER;
SAVETMPS;
PUSHMARK(sp);
XPUSHs(PerlEncObj(encoding));
sv = newSV(srcLen);
sv_setpvn(sv,src,srcLen);
sv_maybe_utf8(sv);
XPUSHs(sv_2mortal(sv));
XPUSHs(fallback);
PUTBACK;
count = perl_call_method("encode",G_SCALAR);
SPAGAIN;
if (count > 0)
{
sv = POPs;
PUTBACK;
if (sv && SvPOK(sv))
s = SvPV(sv,len);
}
else
{
LangDebug("Encode did not return a value:%s\n",SvPV_nolen(ERRSV));
}
Tcl_DStringAppend(dsPtr,s,len);
FREETMPS;
LEAVE;
}
else
{
Tcl_DStringAppend(dsPtr,"\0",1);
}
/* Perl has appended a \0 for us, but that may not be enough
if encoding is "wide"
*/
Tcl_DStringAppend(dsPtr,"\0\0\0",3);
Tcl_DStringSetLength(dsPtr,len);
return Tcl_DStringValue(dsPtr);
}
char *
Tcl_ExternalToUtfDString(Tcl_Encoding encoding, CONST char * src,
int srcLen, Tcl_DString * dsPtr)
{
dTHX;
dSP;
SV *sv;
char *s;
STRLEN len;
if (!encoding)
encoding = GetSystemEncoding();
SPAGAIN;
ENTER;
SAVETMPS;
if (!src)
srcLen = 0;
if (srcLen < 0) {
/* FIXME - this is supposed to be based on size of encoding's thingies ! */
#ifdef WIN32
if (encoding == TkWinGetUnicodeEncoding())
{
srcLen = sizeof(Tcl_UniChar)*Tcl_UniCharLen((Tcl_UniChar *) src);
}
else
#endif
srcLen = strlen(src);
}
SPAGAIN;
PUSHMARK(sp);
XPUSHs(PerlEncObj(encoding));
sv = newSV(srcLen);
sv_setpvn(sv,src,srcLen);
XPUSHs(sv_2mortal(sv));
PUTBACK;
perl_call_method("decode",G_SCALAR);
SPAGAIN;
sv = POPs;
PUTBACK;
s = SvPV(sv,len);
Tcl_DStringInit(dsPtr);
Tcl_DStringAppend(dsPtr,s,len);
FREETMPS;
LEAVE;
return Tcl_DStringValue(dsPtr);
}
#if defined(WIN32) || (defined(__WIN32__) && defined(__CYGWIN__))
/*
*---------------------------------------------------------------------------
*
* Tcl_WinUtfToTChar, Tcl_WinTCharToUtf --
*
* Convert between UTF-8 and Unicode when running Windows NT or
* the current ANSI code page when running Windows 95.
*
* On Mac, Unix, and Windows 95, all strings exchanged between Tcl
* and the OS are "char" oriented. We need only one Tcl_Encoding to
* convert between UTF-8 and the system's native encoding. We use
* NULL to represent that encoding.
*
* On NT, some strings exchanged between Tcl and the OS are "char"
* oriented, while others are in Unicode. We need two Tcl_Encoding
* APIs depending on whether we are targeting a "char" or Unicode
* interface.
*
* Calling Tcl_UtfToExternal() or Tcl_ExternalToUtf() with an
* encoding of NULL should always used to convert between UTF-8
* and the system's "char" oriented encoding. The following two
* functions are used in Windows-specific code to convert between
* UTF-8 and Unicode strings (NT) or "char" strings(95). This saves
* you the trouble of writing the following type of fragment over and
* over:
*
* if (running NT) {
* encoding <- Tcl_GetEncoding("unicode");
* nativeBuffer <- UtfToExternal(encoding, utfBuffer);
* Tcl_FreeEncoding(encoding);
* } else {
* nativeBuffer <- UtfToExternal(NULL, utfBuffer);
* }
*
* By convention, in Windows a TCHAR is a character in the ANSI code
* page on Windows 95, a Unicode character on Windows NT. If you
* plan on targeting a Unicode interfaces when running on NT and a
* "char" oriented interface while running on 95, these functions
* should be used. If you plan on targetting the same "char"
* oriented function on both 95 and NT, use Tcl_UtfToExternal()
* with an encoding of NULL.
*
* Results:
* The result is a pointer to the string in the desired target
* encoding. Storage for the result string is allocated in
* dsPtr; the caller must call Tcl_DStringFree() when the result
* is no longer needed.
*
* Side effects:
* None.
*
*---------------------------------------------------------------------------
*/