forked from Floorp-Projects/Floorp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnsJapaneseToUnicode.cpp
911 lines (865 loc) · 30.7 KB
/
nsJapaneseToUnicode.cpp
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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
#include "nsJapaneseToUnicode.h"
#include "nsUCSupport.h"
#include "japanese.map"
#include "nsICharsetConverterManager.h"
#include "nsIServiceManager.h"
#include "mozilla/Assertions.h"
static NS_DEFINE_CID(kCharsetConverterManagerCID, NS_ICHARSETCONVERTERMANAGER_CID);
#ifdef XP_OS2
// HTML5-incompliant behavior for OS/2, see bug 108136
// This is bogus. The right fix would be working around the font problems
// in OS/2 gfx, since this "fix" introduces script-visible DOM differences
// between the platforms.
#define SJIS_INDEX gIBM943Index[0]
#define JIS0208_INDEX gIBM943Index[1]
#else
// HTML5 says to use Windows-31J instead of the real Shift_JIS for decoding
#define SJIS_INDEX gCP932Index[0]
#define JIS0208_INDEX gCP932Index[1]
#endif
#define JIS0212_INDEX gJIS0212Index
#define SJIS_UNMAPPED 0x30fb
#define UNICODE_REPLACEMENT_CHARACTER 0xfffd
#define IN_GR_RANGE(b) \
((uint8_t(0xa1) <= uint8_t(b)) && (uint8_t(b) <= uint8_t(0xfe)))
NS_IMETHODIMP nsShiftJISToUnicode::Convert(
const char * aSrc, int32_t * aSrcLen,
PRUnichar * aDest, int32_t * aDestLen)
{
static const uint8_t sbIdx[256] =
{
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x00 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x08 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x10 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x18 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x20 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x28 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x30 */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, /* 0x38 */
0, 1, 2, 3, 4, 5, 6, 7, /* 0x40 */
8, 9, 10, 11, 12, 13, 14, 15, /* 0x48 */
16, 17, 18, 19, 20, 21, 22, 23, /* 0x50 */
24, 25, 26, 27, 28, 29, 30, 31, /* 0x58 */
32, 33, 34, 35, 36, 37, 38, 39, /* 0x60 */
40, 41, 42, 43, 44, 45, 46, 47, /* 0x68 */
48, 49, 50, 51, 52, 53, 54, 55, /* 0x70 */
56, 57, 58, 59, 60, 61, 62, 0xFF, /* 0x78 */
63, 64, 65, 66, 67, 68, 69, 70, /* 0x80 */
71, 72, 73, 74, 75, 76, 77, 78, /* 0x88 */
79, 80, 81, 82, 83, 84, 85, 86, /* 0x90 */
87, 88, 89, 90, 91, 92, 93, 94, /* 0x98 */
95, 96, 97, 98, 99, 100, 101, 102, /* 0xa0 */
103, 104, 105, 106, 107, 108, 109, 110, /* 0xa8 */
111, 112, 113, 114, 115, 116, 117, 118, /* 0xb0 */
119, 120, 121, 122, 123, 124, 125, 126, /* 0xb8 */
127, 128, 129, 130, 131, 132, 133, 134, /* 0xc0 */
135, 136, 137, 138, 139, 140, 141, 142, /* 0xc8 */
143, 144, 145, 146, 147, 148, 149, 150, /* 0xd0 */
151, 152, 153, 154, 155, 156, 157, 158, /* 0xd8 */
159, 160, 161, 162, 163, 164, 165, 166, /* 0xe0 */
167, 168, 169, 170, 171, 172, 173, 174, /* 0xe8 */
175, 176, 177, 178, 179, 180, 181, 182, /* 0xf0 */
183, 184, 185, 186, 187, 0xFF, 0xFF, 0xFF, /* 0xf8 */
};
const unsigned char* srcEnd = (unsigned char*)aSrc + *aSrcLen;
const unsigned char* src =(unsigned char*) aSrc;
PRUnichar* destEnd = aDest + *aDestLen;
PRUnichar* dest = aDest;
while (src < srcEnd) {
switch (mState) {
case 0:
if (*src <= 0x80) {
// ASCII
*dest++ = (PRUnichar) *src;
if (dest >= destEnd) {
goto error1;
}
} else {
mData = SJIS_INDEX[*src & 0x7F];
if (mData < 0xE000) {
mState = 1; // two bytes
} else if (mData < 0xF000) {
mState = 2; // EUDC
} else {
*dest++ = mData; // JIS 0201
if (dest >= destEnd) {
goto error1;
}
}
}
break;
case 1: // Index to table
{
MOZ_ASSERT(mData < 0xE000);
uint8_t off = sbIdx[*src];
// Error handling: in the case where the second octet is not in the
// valid ranges 0x40-0x7E 0x80-0xFC, unconsume the invalid octet and
// interpret it as the ASCII value. In the case where the second
// octet is in the valid range but there is no mapping for the
// 2-octet sequence, do not unconsume.
if(0xFF == off) {
src--;
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = UNICODE_REPLACEMENT_CHARACTER;
} else {
PRUnichar ch = gJapaneseMap[mData+off];
if(ch == 0xfffd) {
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
ch = SJIS_UNMAPPED;
}
*dest++ = ch;
}
mState = 0;
if(dest >= destEnd)
goto error1;
}
break;
case 2: // EUDC
{
MOZ_ASSERT(0xE000 <= mData && mData < 0xF000);
uint8_t off = sbIdx[*src];
// Error handling as in case 1
if(0xFF == off) {
src--;
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = UNICODE_REPLACEMENT_CHARACTER;
} else {
*dest++ = mData + off;
}
mState = 0;
if(dest >= destEnd)
goto error1;
}
break;
}
src++;
}
*aDestLen = dest - aDest;
return NS_OK;
error_invalidchar:
*aDestLen = dest - aDest;
*aSrcLen = src - (const unsigned char*)aSrc;
return NS_ERROR_ILLEGAL_INPUT;
error1:
*aDestLen = dest - aDest;
src++;
if ((mState == 0) && (src == srcEnd)) {
return NS_OK;
}
*aSrcLen = src - (const unsigned char*)aSrc;
return NS_OK_UDEC_MOREOUTPUT;
}
PRUnichar
nsShiftJISToUnicode::GetCharacterForUnMapped()
{
return PRUnichar(SJIS_UNMAPPED);
}
NS_IMETHODIMP nsEUCJPToUnicodeV2::Convert(
const char * aSrc, int32_t * aSrcLen,
PRUnichar * aDest, int32_t * aDestLen)
{
static const uint8_t sbIdx[256] =
{
/* 0x0X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x1X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x2X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x3X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x4X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x5X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x6X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x7X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x8X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x9X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xAX */
0xFF, 0, 1, 2, 3, 4, 5, 6,
7, 8 , 9, 10, 11, 12, 13, 14,
/* 0xBX */
15, 16, 17, 18, 19, 20, 21, 22,
23, 24, 25, 26, 27, 28, 29, 30,
/* 0xCX */
31, 32, 33, 34, 35, 36, 37, 38,
39, 40, 41, 42, 43, 44, 45, 46,
/* 0xDX */
47, 48, 49, 50, 51, 52, 53, 54,
55, 56, 57, 58, 59, 60, 61, 62,
/* 0xEX */
63, 64, 65, 66, 67, 68, 69, 70,
71, 72, 73, 74, 75, 76, 77, 78,
/* 0xFX */
79, 80, 81, 82, 83, 84, 85, 86,
87, 88, 89, 90, 91, 92, 93, 0xFF,
};
const unsigned char* srcEnd = (unsigned char*)aSrc + *aSrcLen;
const unsigned char* src =(unsigned char*) aSrc;
PRUnichar* destEnd = aDest + *aDestLen;
PRUnichar* dest = aDest;
while((src < srcEnd))
{
switch(mState)
{
case 0:
if(*src & 0x80 && *src != (unsigned char)0xa0)
{
mData = JIS0208_INDEX[*src & 0x7F];
if(mData != 0xFFFD )
{
mState = 1; // two byte JIS0208
} else {
if( 0x8e == *src) {
// JIS 0201
mState = 2; // JIS0201
} else if(0x8f == *src) {
// JIS 0212
mState = 3; // JIS0212
} else {
// others
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = 0xFFFD;
if(dest >= destEnd)
goto error1;
}
}
} else {
// ASCII
*dest++ = (PRUnichar) *src;
if(dest >= destEnd)
goto error1;
}
break;
case 1: // Index to table
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = 0xFFFD;
// if the first byte is valid for EUC-JP but the second
// is not while being a valid US-ASCII, save it
// instead of eating it up !
if ( (uint8_t)*src < (uint8_t)0x7f )
--src;
} else {
*dest++ = gJapaneseMap[mData+off];
}
mState = 0;
if(dest >= destEnd)
goto error1;
}
break;
case 2: // JIS 0201
{
if((0xA1 <= *src) && (*src <= 0xDF)) {
*dest++ = (0xFF61-0x00A1) + *src;
} else {
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = 0xFFFD;
// if 0x8e is not followed by a valid JIS X 0201 byte
// but by a valid US-ASCII, save it instead of eating it up.
if ( (uint8_t)*src < (uint8_t)0x7f )
--src;
}
mState = 0;
if(dest >= destEnd)
goto error1;
}
break;
case 3: // JIS 0212
{
if (IN_GR_RANGE(*src))
{
mData = JIS0212_INDEX[*src & 0x7F];
if(mData != 0xFFFD )
{
mState = 4;
} else {
mState = 5; // error
}
} else {
// First "JIS 0212" byte is not in the valid GR range: save it
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = 0xFFFD;
--src;
mState = 0;
if(dest >= destEnd)
goto error1;
}
}
break;
case 4:
{
uint8_t off = sbIdx[*src];
if(0xFF != off) {
*dest++ = gJapaneseMap[mData+off];
mState = 0;
if(dest >= destEnd)
goto error1;
break;
}
// else fall through to error handler
}
case 5: // two bytes undefined
{
if (mErrBehavior == kOnError_Signal)
goto error_invalidchar;
*dest++ = 0xFFFD;
// Undefined JIS 0212 two byte sequence. If the second byte is in
// the valid range for a two byte sequence (0xa1 - 0xfe) consume
// both bytes. Otherwise resynchronize on the second byte.
if (!IN_GR_RANGE(*src))
--src;
mState = 0;
if(dest >= destEnd)
goto error1;
}
break;
}
src++;
}
*aDestLen = dest - aDest;
return NS_OK;
error_invalidchar:
*aDestLen = dest - aDest;
*aSrcLen = src - (const unsigned char*)aSrc;
return NS_ERROR_ILLEGAL_INPUT;
error1:
*aDestLen = dest - aDest;
src++;
if ((mState == 0) && (src == srcEnd)) {
return NS_OK;
}
*aSrcLen = src - (const unsigned char*)aSrc;
return NS_OK_UDEC_MOREOUTPUT;
}
NS_IMETHODIMP nsISO2022JPToUnicodeV2::Convert(
const char * aSrc, int32_t * aSrcLen,
PRUnichar * aDest, int32_t * aDestLen)
{
static const uint16_t fbIdx[128] =
{
/* 0x8X */
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
/* 0x9X */
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD,
/* 0xAX */
0xFFFD, 0, 94, 94* 2, 94* 3, 94* 4, 94* 5, 94* 6,
94* 7, 94* 8 , 94* 9, 94*10, 94*11, 94*12, 94*13, 94*14,
/* 0xBX */
94*15, 94*16, 94*17, 94*18, 94*19, 94*20, 94*21, 94*22,
94*23, 94*24, 94*25, 94*26, 94*27, 94*28, 94*29, 94*30,
/* 0xCX */
94*31, 94*32, 94*33, 94*34, 94*35, 94*36, 94*37, 94*38,
94*39, 94*40, 94*41, 94*42, 94*43, 94*44, 94*45, 94*46,
/* 0xDX */
94*47, 94*48, 94*49, 94*50, 94*51, 94*52, 94*53, 94*54,
94*55, 94*56, 94*57, 94*58, 94*59, 94*60, 94*61, 94*62,
/* 0xEX */
94*63, 94*64, 94*65, 94*66, 94*67, 94*68, 94*69, 94*70,
94*71, 94*72, 94*73, 94*74, 94*75, 94*76, 94*77, 94*78,
/* 0xFX */
94*79, 94*80, 94*81, 94*82, 94*83, 94*84, 94*85, 94*86,
94*87, 94*88, 94*89, 94*90, 94*91, 94*92, 94*93, 0xFFFD,
};
static const uint8_t sbIdx[256] =
{
/* 0x0X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x1X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x2X */
0xFF, 0, 1, 2, 3, 4, 5, 6,
7, 8 , 9, 10, 11, 12, 13, 14,
/* 0x3X */
15, 16, 17, 18, 19, 20, 21, 22,
23, 24, 25, 26, 27, 28, 29, 30,
/* 0x4X */
31, 32, 33, 34, 35, 36, 37, 38,
39, 40, 41, 42, 43, 44, 45, 46,
/* 0x5X */
47, 48, 49, 50, 51, 52, 53, 54,
55, 56, 57, 58, 59, 60, 61, 62,
/* 0x6X */
63, 64, 65, 66, 67, 68, 69, 70,
71, 72, 73, 74, 75, 76, 77, 78,
/* 0x7X */
79, 80, 81, 82, 83, 84, 85, 86,
87, 88, 89, 90, 91, 92, 93, 0xFF,
/* 0x8X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0x9X */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xAX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xBX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xCX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xDX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xEX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
/* 0xFX */
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
};
const unsigned char* srcEnd = (unsigned char*)aSrc + *aSrcLen;
const unsigned char* src =(unsigned char*) aSrc;
PRUnichar* destEnd = aDest + *aDestLen;
PRUnichar* dest = aDest;
while((src < srcEnd))
{
switch(mState)
{
case mState_ASCII:
if(0x1b == *src)
{
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = (PRUnichar) *src;
}
break;
case mState_ESC:
if( '(' == *src) {
mState = mState_ESC_28;
} else if ('$' == *src) {
mState = mState_ESC_24;
} else if ('.' == *src) { // for ISO-2022-JP-2
mState = mState_ESC_2e;
} else if ('N' == *src) { // for ISO-2022-JP-2
mState = mState_ESC_4e;
} else {
if (CHECK_OVERRUN(dest, destEnd, 2))
goto error1;
*dest++ = (PRUnichar) 0x1b;
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
mState = mLastLegalState;
}
break;
case mState_ESC_28: // ESC (
if( 'B' == *src) {
mState = mState_ASCII;
if (mRunLength == 0) {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = 0xFFFD;
}
mRunLength = 0;
} else if ('J' == *src) {
mState = mState_JISX0201_1976Roman;
if (mRunLength == 0 && mLastLegalState != mState_ASCII) {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
if (mErrBehavior == kOnError_Signal)
goto error2;
*dest++ = 0xFFFD;
}
mRunLength = 0;
} else if ('I' == *src) {
mState = mState_JISX0201_1976Kana;
mRunLength = 0;
} else {
if (CHECK_OVERRUN(dest, destEnd, 3))
goto error1;
*dest++ = (PRUnichar) 0x1b;
*dest++ = (PRUnichar) '(';
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
mState = mLastLegalState;
}
break;
case mState_ESC_24: // ESC $
if( '@' == *src) {
mState = mState_JISX0208_1978;
mRunLength = 0;
} else if ('A' == *src) {
mState = mState_GB2312_1980;
mRunLength = 0;
} else if ('B' == *src) {
mState = mState_JISX0208_1983;
mRunLength = 0;
} else if ('(' == *src) {
mState = mState_ESC_24_28;
} else {
if (CHECK_OVERRUN(dest, destEnd, 3))
goto error1;
*dest++ = (PRUnichar) 0x1b;
*dest++ = (PRUnichar) '$';
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
mState = mLastLegalState;
}
break;
case mState_ESC_24_28: // ESC $ (
if( 'C' == *src) {
mState = mState_KSC5601_1987;
mRunLength = 0;
} else if ('D' == *src) {
mState = mState_JISX0212_1990;
mRunLength = 0;
} else {
if (CHECK_OVERRUN(dest, destEnd, 4))
goto error1;
*dest++ = (PRUnichar) 0x1b;
*dest++ = (PRUnichar) '$';
*dest++ = (PRUnichar) '(';
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
mState = mLastLegalState;
}
break;
case mState_JISX0201_1976Roman:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
goto error2;
} else {
// XXX We need to decide how to handle \ and ~ here
// we may need a if statement here for '\' and '~'
// to map them to Yen and Overbar
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = (PRUnichar) *src;
++mRunLength;
}
break;
case mState_JISX0201_1976Kana:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else {
if((0x21 <= *src) && (*src <= 0x5F)) {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = (0xFF61-0x0021) + *src;
++mRunLength;
} else {
goto error2;
}
}
break;
case mState_JISX0208_1978:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
mLastLegalState = mState;
mState = mState_ERROR;
} else {
mData = JIS0208_INDEX[*src & 0x7F];
if(0xFFFD == mData)
goto error2;
mState = mState_JISX0208_1978_2ndbyte;
}
break;
case mState_GB2312_1980:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
mLastLegalState = mState;
mState = mState_ERROR;
} else {
mData = fbIdx[*src & 0x7F];
if(0xFFFD == mData)
goto error2;
mState = mState_GB2312_1980_2ndbyte;
}
break;
case mState_JISX0208_1983:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
mLastLegalState = mState;
mState = mState_ERROR;
} else {
mData = JIS0208_INDEX[*src & 0x7F];
if(0xFFFD == mData)
goto error2;
mState = mState_JISX0208_1983_2ndbyte;
}
break;
case mState_KSC5601_1987:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
mLastLegalState = mState;
mState = mState_ERROR;
} else {
mData = fbIdx[*src & 0x7F];
if(0xFFFD == mData)
goto error2;
mState = mState_KSC5601_1987_2ndbyte;
}
break;
case mState_JISX0212_1990:
if(0x1b == *src) {
mLastLegalState = mState;
mState = mState_ESC;
} else if(*src & 0x80) {
mLastLegalState = mState;
mState = mState_ERROR;
} else {
mData = JIS0212_INDEX[*src & 0x7F];
if(0xFFFD == mData)
goto error2;
mState = mState_JISX0212_1990_2ndbyte;
}
break;
case mState_JISX0208_1978_2ndbyte:
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
goto error2;
} else {
// XXX We need to map from JIS X 0208 1983 to 1987
// in the next line before pass to *dest++
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = gJapaneseMap[mData+off];
++mRunLength;
}
mState = mState_JISX0208_1978;
}
break;
case mState_GB2312_1980_2ndbyte:
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
goto error2;
} else {
if (!mGB2312Decoder) {
// creating a delegate converter (GB2312)
nsresult rv;
nsCOMPtr<nsICharsetConverterManager> ccm =
do_GetService(kCharsetConverterManagerCID, &rv);
if (NS_SUCCEEDED(rv)) {
rv = ccm->GetUnicodeDecoderRaw("GB2312", &mGB2312Decoder);
}
}
if (!mGB2312Decoder) {// failed creating a delegate converter
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
unsigned char gb[2];
PRUnichar uni;
int32_t gbLen = 2, uniLen = 1;
// ((mData/94)+0x21) is the original 1st byte.
// *src is the present 2nd byte.
// Put 2 bytes (one character) to gb[] with GB2312 encoding.
gb[0] = ((mData / 94) + 0x21) | 0x80;
gb[1] = *src | 0x80;
// Convert GB2312 to unicode.
mGB2312Decoder->Convert((const char *)gb, &gbLen,
&uni, &uniLen);
*dest++ = uni;
++mRunLength;
}
}
mState = mState_GB2312_1980;
}
break;
case mState_JISX0208_1983_2ndbyte:
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = gJapaneseMap[mData+off];
++mRunLength;
}
mState = mState_JISX0208_1983;
}
break;
case mState_KSC5601_1987_2ndbyte:
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
goto error2;
} else {
if (!mEUCKRDecoder) {
// creating a delegate converter (EUC-KR)
nsresult rv;
nsCOMPtr<nsICharsetConverterManager> ccm =
do_GetService(kCharsetConverterManagerCID, &rv);
if (NS_SUCCEEDED(rv)) {
rv = ccm->GetUnicodeDecoderRaw("EUC-KR", &mEUCKRDecoder);
}
}
if (!mEUCKRDecoder) {// failed creating a delegate converter
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
unsigned char ksc[2];
PRUnichar uni;
int32_t kscLen = 2, uniLen = 1;
// ((mData/94)+0x21) is the original 1st byte.
// *src is the present 2nd byte.
// Put 2 bytes (one character) to ksc[] with EUC-KR encoding.
ksc[0] = ((mData / 94) + 0x21) | 0x80;
ksc[1] = *src | 0x80;
// Convert EUC-KR to unicode.
mEUCKRDecoder->Convert((const char *)ksc, &kscLen,
&uni, &uniLen);
*dest++ = uni;
++mRunLength;
}
}
mState = mState_KSC5601_1987;
}
break;
case mState_JISX0212_1990_2ndbyte:
{
uint8_t off = sbIdx[*src];
if(0xFF == off) {
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = gJapaneseMap[mData+off];
++mRunLength;
}
mState = mState_JISX0212_1990;
}
break;
case mState_ESC_2e: // ESC .
// "ESC ." will designate 96 character set to G2.
mState = mLastLegalState;
if( 'A' == *src) {
G2charset = G2_ISO88591;
} else if ('F' == *src) {
G2charset = G2_ISO88597;
} else {
if (CHECK_OVERRUN(dest, destEnd, 3))
goto error1;
*dest++ = (PRUnichar) 0x1b;
*dest++ = (PRUnichar) '.';
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
}
break;
case mState_ESC_4e: // ESC N
// "ESC N" is the SS2 sequence, that invoke a G2 designated
// character set. Since SS2 is effective only for next one
// character, mState should be returned to the last status.
mState = mLastLegalState;
if((0x20 <= *src) && (*src <= 0x7F)) {
if (G2_ISO88591 == G2charset) {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
*dest++ = *src | 0x80;
++mRunLength;
} else if (G2_ISO88597 == G2charset) {
if (!mISO88597Decoder) {
// creating a delegate converter (ISO-8859-7)
nsresult rv;
nsCOMPtr<nsICharsetConverterManager> ccm =
do_GetService(kCharsetConverterManagerCID, &rv);
if (NS_SUCCEEDED(rv)) {
rv = ccm->GetUnicodeDecoderRaw("ISO-8859-7", &mISO88597Decoder);
}
}
if (!mISO88597Decoder) {// failed creating a delegate converter
goto error2;
} else {
if (CHECK_OVERRUN(dest, destEnd, 1))
goto error1;
// Put one character with ISO-8859-7 encoding.
unsigned char gr = *src | 0x80;
PRUnichar uni;
int32_t grLen = 1, uniLen = 1;
// Convert ISO-8859-7 to unicode.
mISO88597Decoder->Convert((const char *)&gr, &grLen,
&uni, &uniLen);
*dest++ = uni;
++mRunLength;
}
} else {// G2charset is G2_unknown (not designated yet)
goto error2;
}
} else {
if (CHECK_OVERRUN(dest, destEnd, 3))
goto error1;
*dest++ = (PRUnichar) 0x1b;
*dest++ = (PRUnichar) 'N';
if(0x80 & *src)
goto error2;
*dest++ = (PRUnichar) *src;
}
break;
case mState_ERROR:
mState = mLastLegalState;
mRunLength = 0;
goto error2;
break;
} // switch
src++;
}
*aDestLen = dest - aDest;
return NS_OK;
error1:
*aDestLen = dest - aDest;
*aSrcLen = src - (const unsigned char*)aSrc;
return NS_OK_UDEC_MOREOUTPUT;
error2:
*aSrcLen = src - (const unsigned char*)aSrc;
*aDestLen = dest - aDest;
return NS_ERROR_UNEXPECTED;
}