summaryrefslogtreecommitdiff
path: root/Build/source/libs/gd/gdkanji.c
blob: 7319337752d352cd51bd011e128423a879513e8c (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
/* gdkanji.c (Kanji code converter)                            */
/*                 written by Masahito Yamaga (ma@yama-ga.com) */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "gd.h"
#include "gdhelpers.h"

#ifdef HAVE_ERRNO_H
#include <errno.h>
#endif

#include <stdarg.h>
#if defined(HAVE_ICONV_H)
#include <iconv.h>
#endif

#ifndef HAVE_ICONV_T_DEF
typedef void *iconv_t;
#endif

#ifndef HAVE_ICONV
#define ICONV_CONST /**/
  iconv_t iconv_open (const char *, const char *);
size_t iconv (iconv_t, ICONV_CONST char **, size_t *, char **, size_t *);
int iconv_close (iconv_t);

iconv_t
iconv_open (const char *tocode, const char *fromcode)
{
  return (iconv_t) (-1);
}

size_t
iconv (iconv_t cd, ICONV_CONST char **inbuf, size_t * inbytesleft,
       char **outbuf, size_t * outbytesleft)
{
  return 0;
}

int
iconv_close (iconv_t cd)
{
  return 0;
}

#endif /* !HAVE_ICONV */

#define LIBNAME "any2eucjp()"

#if defined(__MSC__) || defined(__BORLANDC__) || defined(__TURBOC__) || defined(_Windows) || defined(MSDOS)
#ifndef SJISPRE
#define SJISPRE 1
#endif
#endif

#ifdef TRUE
#undef TRUE
#endif
#ifdef FALSE
#undef FALSE
#endif

#define TRUE  1
#define FALSE 0

#define NEW 1
#define OLD 2
#define ESCI 3
#define NEC 4
#define EUC 5
#define SJIS 6
#define EUCORSJIS 7
#define ASCII 8

#define NEWJISSTR "JIS7"
#define OLDJISSTR "jis"
#define EUCSTR    "eucJP"
#define SJISSTR   "SJIS"

#define ESC 27
#define SS2 142

static void
debug (const char *format, ...)
{
#ifdef DEBUG
  va_list args;

  va_start (args, format);
  fprintf (stdout, "%s: ", LIBNAME);
  vfprintf (stdout, format, args);
  fprintf (stdout, "\n");
  va_end (args);
#endif
}

static void
error (const char *format, ...)
{
  va_list args;

  va_start (args, format);
  fprintf (stderr, "%s: ", LIBNAME);
  vfprintf (stderr, format, args);
  fprintf (stderr, "\n");
  va_end (args);
}

/* DetectKanjiCode() derived from DetectCodeType() by Ken Lunde. */

static int
DetectKanjiCode (unsigned char *str)
{
  static int whatcode = ASCII;
  int oldcode = ASCII;
  int c, i;
  char *lang = NULL;

  c = '\1';
  i = 0;

  if (whatcode != EUCORSJIS && whatcode != ASCII)
    {
      oldcode = whatcode;
      whatcode = ASCII;
    }

  while ((whatcode == EUCORSJIS || whatcode == ASCII) && c != '\0')
    {
      if ((c = str[i++]) != '\0')
	{
	  if (c == ESC)
	    {
	      c = str[i++];
	      if (c == '$')
		{
		  c = str[i++];
		  if (c == 'B')
		    whatcode = NEW;
		  else if (c == '@')
		    whatcode = OLD;
		}
	      else if (c == '(')
		{
		  c = str[i++];
		  if (c == 'I')
		    whatcode = ESCI;
		}
	      else if (c == 'K')
		whatcode = NEC;
	    }
	  else if ((c >= 129 && c <= 141) || (c >= 143 && c <= 159))
	    whatcode = SJIS;
	  else if (c == SS2)
	    {
	      c = str[i++];
	      if ((c >= 64 && c <= 126) || (c >= 128 && c <= 160)
		  || (c >= 224 && c <= 252))
		whatcode = SJIS;
	      else if (c >= 161 && c <= 223)
		whatcode = EUCORSJIS;
	    }
	  else if (c >= 161 && c <= 223)
	    {
	      c = str[i++];
	      if (c >= 240 && c <= 254)
		whatcode = EUC;
	      else if (c >= 161 && c <= 223)
		whatcode = EUCORSJIS;
	      else if (c >= 224 && c <= 239)
		{
		  whatcode = EUCORSJIS;
		  while (c >= 64 && c != '\0' && whatcode == EUCORSJIS)
		    {
		      if (c >= 129)
			{
			  if (c <= 141 || (c >= 143 && c <= 159))
			    whatcode = SJIS;
			  else if (c >= 253 && c <= 254)
			    whatcode = EUC;
			}
		      c = str[i++];
		    }
		}
	      else if (c <= 159)
		whatcode = SJIS;
	    }
	  else if (c >= 240 && c <= 254)
	    whatcode = EUC;
	  else if (c >= 224 && c <= 239)
	    {
	      c = str[i++];
	      if ((c >= 64 && c <= 126) || (c >= 128 && c <= 160))
		whatcode = SJIS;
	      else if (c >= 253 && c <= 254)
		whatcode = EUC;
	      else if (c >= 161 && c <= 252)
		whatcode = EUCORSJIS;
	    }
	}
    }

#ifdef DEBUG
  if (whatcode == ASCII)
    debug ("Kanji code not included.");
  else if (whatcode == EUCORSJIS)
    debug ("Kanji code not detected.");
  else
    debug ("Kanji code detected at %d byte.", i);
#endif

  if (whatcode == EUCORSJIS && oldcode != ASCII)
    whatcode = oldcode;

  if (whatcode == EUCORSJIS)
    {
      if (getenv ("LC_ALL"))
	lang = getenv ("LC_ALL");
      else if (getenv ("LC_CTYPE"))
	lang = getenv ("LC_CTYPE");
      else if (getenv ("LANG"))
	lang = getenv ("LANG");

      if (lang)
	{
	  if (strcmp (lang, "ja_JP.SJIS") == 0 ||
#ifdef hpux
	      strcmp (lang, "japanese") == 0 ||
#endif
	      strcmp (lang, "ja_JP.mscode") == 0 ||
	      strcmp (lang, "ja_JP.PCK") == 0)
	    whatcode = SJIS;
	  else if (strncmp (lang, "ja", 2) == 0)
#ifdef SJISPRE
	    whatcode = SJIS;
#else
	    whatcode = EUC;
#endif
	}
    }

  if (whatcode == EUCORSJIS)
#ifdef SJISPRE
    whatcode = SJIS;
#else
    whatcode = EUC;
#endif

  return whatcode;
}

/* SJIStoJIS() is sjis2jis() by Ken Lunde. */

static void
SJIStoJIS (int *p1, int *p2)
{
  register unsigned char c1 = *p1;
  register unsigned char c2 = *p2;
  register int adjust = c2 < 159;
  register int rowOffset = c1 < 160 ? 112 : 176;
  register int cellOffset = adjust ? (31 + (c2 > 127)) : 126;

  *p1 = ((c1 - rowOffset) << 1) - adjust;
  *p2 -= cellOffset;
}

/* han2zen() was derived from han2zen() written by Ken Lunde. */

#define IS_DAKU(c) ((c >= 182 && c <= 196) || (c >= 202 && c <= 206) || (c == 179))
#define IS_HANDAKU(c) (c >= 202 && c <= 206)

static void
han2zen (int *p1, int *p2)
{
  int c = *p1;
  int daku = FALSE;
  int handaku = FALSE;
  int mtable[][2] = {
    {129, 66},
    {129, 117},
    {129, 118},
    {129, 65},
    {129, 69},
    {131, 146},
    {131, 64},
    {131, 66},
    {131, 68},
    {131, 70},
    {131, 72},
    {131, 131},
    {131, 133},
    {131, 135},
    {131, 98},
    {129, 91},
    {131, 65},
    {131, 67},
    {131, 69},
    {131, 71},
    {131, 73},
    {131, 74},
    {131, 76},
    {131, 78},
    {131, 80},
    {131, 82},
    {131, 84},
    {131, 86},
    {131, 88},
    {131, 90},
    {131, 92},
    {131, 94},
    {131, 96},
    {131, 99},
    {131, 101},
    {131, 103},
    {131, 105},
    {131, 106},
    {131, 107},
    {131, 108},
    {131, 109},
    {131, 110},
    {131, 113},
    {131, 116},
    {131, 119},
    {131, 122},
    {131, 125},
    {131, 126},
    {131, 128},
    {131, 129},
    {131, 130},
    {131, 132},
    {131, 134},
    {131, 136},
    {131, 137},
    {131, 138},
    {131, 139},
    {131, 140},
    {131, 141},
    {131, 143},
    {131, 147},
    {129, 74},
    {129, 75}
  };

  if (*p2 == 222 && IS_DAKU (*p1))
    daku = TRUE;		/* Daku-ten */
  else if (*p2 == 223 && IS_HANDAKU (*p1))
    handaku = TRUE;		/* Han-daku-ten */

  *p1 = mtable[c - 161][0];
  *p2 = mtable[c - 161][1];

  if (daku)
    {
      if ((*p2 >= 74 && *p2 <= 103) || (*p2 >= 110 && *p2 <= 122))
	(*p2)++;
      else if (*p2 == 131 && *p2 == 69)
	*p2 = 148;
    }
  else if (handaku && *p2 >= 110 && *p2 <= 122)
    (*p2) += 2;
}

/* Recast strcpy to handle unsigned chars used below. */
#define ustrcpy(A,B) (strcpy((char*)(A),(const char*)(B)))

static void
do_convert (unsigned char **to_p, unsigned char **from_p, const char *code)
{
unsigned char *to = *to_p;
unsigned char *from = *from_p;
#ifdef HAVE_ICONV
  iconv_t cd;
  size_t from_len, to_len;

  if ((cd = iconv_open (EUCSTR, code)) == (iconv_t) - 1)
    {
      error ("iconv_open() error");
#ifdef HAVE_ERRNO_H
      if (errno == EINVAL)
	error ("invalid code specification: \"%s\" or \"%s\"", EUCSTR, code);
#endif
      ustrcpy (to, from);
      return;
    }

  from_len = strlen ((const char *)from) + 1;
  to_len = BUFSIZ;

  if ((int) (iconv (cd, (char **)from_p, &from_len, (char **)to_p, &to_len))
      == -1)
    {
#ifdef HAVE_ERRNO_H
      if (errno == EINVAL)
	error ("invalid end of input string");
      else if (errno == EILSEQ)
	error ("invalid code in input string");
      else if (errno == E2BIG)
	error ("output buffer overflow at do_convert()");
      else
#endif
	error ("something happen");
      ustrcpy (to, from);
      return;
    }

  if (iconv_close (cd) != 0)
    {
      error ("iconv_close() error");
    }
#else
  int p1, p2, i, j;
  int jisx0208 = FALSE;
  int hankaku = FALSE;

  j = 0;
  if (strcmp (code, NEWJISSTR) == 0 || strcmp (code, OLDJISSTR) == 0)
    {
      for (i = 0; from[i] != '\0' && j < BUFSIZ; i++)
	{
	  if (from[i] == ESC)
	    {
	      i++;
	      if (from[i] == '$')
		{
		  jisx0208 = TRUE;
		  hankaku = FALSE;
		  i++;
		}
	      else if (from[i] == '(')
		{
		  jisx0208 = FALSE;
		  i++;
		  if (from[i] == 'I')	/* Hankaku Kana */
		    hankaku = TRUE;
		  else
		    hankaku = FALSE;
		}
	    }
	  else
	    {
	      if (jisx0208)
		to[j++] = from[i] + 128;
	      else if (hankaku)
		{
		  to[j++] = SS2;
		  to[j++] = from[i] + 128;
		}
	      else
		to[j++] = from[i];
	    }
	}
    }
  else if (strcmp (code, SJISSTR) == 0)
    {
      for (i = 0; from[i] != '\0' && j < BUFSIZ; i++)
	{
	  p1 = from[i];
	  if (p1 < 127)
	    to[j++] = p1;
	  else if ((p1 >= 161) && (p1 <= 223))
	    {			/* Hankaku Kana */
	      to[j++] = SS2;
	      to[j++] = p1;
	    }
	  else
	    {
	      p2 = from[++i];
	      SJIStoJIS (&p1, &p2);
	      to[j++] = p1 + 128;
	      to[j++] = p2 + 128;
	    }
	}
    }
  else
    {
      error ("invalid code specification: \"%s\"", code);
      return;
    }

  if (j >= BUFSIZ)
    {
      error ("output buffer overflow at do_convert()");
      ustrcpy (to, from);
    }
  else
    to[j] = '\0';
#endif /* HAVE_ICONV */
}

static int
do_check_and_conv (unsigned char *to, unsigned char *from)
{
  static unsigned char tmp[BUFSIZ];
  unsigned char *tmp_p = &tmp[0];
  int p1, p2, i, j;
  int kanji = TRUE;

  switch (DetectKanjiCode (from))
    {
    case NEW:
      debug ("Kanji code is New JIS.");
      do_convert (&tmp_p, &from, NEWJISSTR);
      break;
    case OLD:
      debug ("Kanji code is Old JIS.");
      do_convert (&tmp_p, &from, OLDJISSTR);
      break;
    case ESCI:
      debug
	("This string includes Hankaku-Kana (jisx0201) escape sequence [ESC] + ( + I.");
      do_convert (&tmp_p, &from, NEWJISSTR);
      break;
    case NEC:
      debug ("Kanji code is NEC Kanji.");
      error ("cannot convert NEC Kanji.");
      ustrcpy (tmp, from);
      kanji = FALSE;
      break;
    case EUC:
      debug ("Kanji code is EUC.");
      ustrcpy (tmp, from);
      break;
    case SJIS:
      debug ("Kanji code is SJIS.");
      do_convert (&tmp_p, &from, SJISSTR);
      break;
    case EUCORSJIS:
      debug ("Kanji code is EUC or SJIS.");
      ustrcpy (tmp, from);
      kanji = FALSE;
      break;
    case ASCII:
      debug ("This is ASCII string.");
      ustrcpy (tmp, from);
      kanji = FALSE;
      break;
    default:
      debug ("This string includes unknown code.");
      ustrcpy (tmp, from);
      kanji = FALSE;
      break;
    }

  /* Hankaku Kana ---> Zenkaku Kana */
  if (kanji)
    {
      j = 0;
      for (i = 0; tmp[i] != '\0' && j < BUFSIZ; i++)
	{
	  if (tmp[i] == SS2)
	    {
	      p1 = tmp[++i];
	      if (tmp[i + 1] == SS2)
		{
		  p2 = tmp[i + 2];
		  if (p2 == 222 || p2 == 223)
		    i += 2;
		  else
		    p2 = 0;
		}
	      else
		p2 = 0;
	      han2zen (&p1, &p2);
	      SJIStoJIS (&p1, &p2);
	      to[j++] = p1 + 128;
	      to[j++] = p2 + 128;
	    }
	  else
	    to[j++] = tmp[i];
	}

      if (j >= BUFSIZ)
	{
	  error ("output buffer overflow at Hankaku --> Zenkaku");
	  ustrcpy (to, tmp);
	}
      else
	to[j] = '\0';
    }
  else
    ustrcpy (to, tmp);

  return kanji;
}

int
any2eucjp (unsigned char *dest, unsigned char *src, unsigned int dest_max)
{
  static unsigned char tmp_dest[BUFSIZ];
  int ret;

  if (strlen ((const char *) src) >= BUFSIZ)
    {
      error ("input string too large");
      return -1;
    }
  if (dest_max > BUFSIZ)
    {
      error
	("invalid maximum size of destination\nit should be less than %d.",
	 BUFSIZ);
      return -1;
    }
  ret = do_check_and_conv (tmp_dest, src);
  if (strlen ((const char *) tmp_dest) >= dest_max)
    {
      error ("output buffer overflow");
      ustrcpy (dest, src);
      return -1;
    }
  ustrcpy (dest, tmp_dest);
  return ret;
}

#if 0
unsigned int
strwidth (unsigned char *s)
{
  unsigned char *t;
  unsigned int i;

  t = (unsigned char *) gdMalloc (BUFSIZ);
  any2eucjp (t, s, BUFSIZ);
  i = strlen (t);
  gdFree (t);
  return i;
}

#ifdef DEBUG
int
main ()
{
  unsigned char input[BUFSIZ];
  unsigned char *output;
  unsigned char *str;
  int c, i = 0;

  while ((c = fgetc (stdin)) != '\n' && i < BUFSIZ)
    input[i++] = c;
  input[i] = '\0';

  printf ("input : %d bytes\n", strlen ((const char *) input));
  printf ("output: %d bytes\n", strwidth (input));

  output = (unsigned char *) gdMalloc (BUFSIZ);
  any2eucjp (output, input, BUFSIZ);
  str = output;
  while (*str != '\0')
    putchar (*(str++));
  putchar ('\n');
  gdFree (output);

  return 0;
}
#endif
#endif