summary refs log tree commit diff
path: root/iconvdata/johab.c
blob: 6a582c0b707fa3ec7a3bb80319cb89e13ee12a6c (plain) (blame)
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
/* Mapping tables for JOHAB handling.
   Copyright (C) 1998 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Jungshik Shin <jshin@pantheon.yale.edu>
   and Ulrich Drepper <drepper@cygnus.com>, 1998.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 of the
   License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public
   License along with the GNU C Library; see the file COPYING.LIB.  If not,
   write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.  */

#include <stdint.h>
#include <ksc5601.h>

/* The table for Bit pattern to Hangul Jamo
   5 bits each are used to encode
   leading consonants(19 + 1 filler), medial vowels(21 + 1 filler)
   and trailing consonants(27 + 1 filler).

   KS C 5601-1992 Annex 3 Table 2
   0 : Filler, -1: invalid, >= 1 : valid

 */
static const int init[32] =
{
  -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,
  19, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
static const int mid[32] =
{
  -1, -1, 0, 1, 2, 3, 4, 5,
  -1, -1, 6, 7, 8, 9, 10, 11,
  -1, -1, 12, 13, 14, 15, 16, 17,
  -1, -1, 18, 19, 20, 21, -1, -1
};
static const int final[32] =
{
  -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
  -1, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, -1, -1
};

/*
   Hangul Jamo in Johab to Unicode 2.0 : Unicode 2.0
   defines 51 Hangul Compatibility Jamos in the block [0x3131,0x314e]

   It's to be considered later which Jamo block to use, Compatibility
   block [0x3131,0x314e] or Hangul Conjoining Jamo block, [0x1100,0x11ff]

 */
static const uint32_t init_to_ucs[19] =
{
  0x3131, 0x3132, 0x3134, 0x3137, 0x3138, 0x3139, 0x3141, 0x3142,
  0x3143, 0x3145, 0x3146, 0x3147, 0x3148, 0x3149, 0x314a, 0x314b,
  0x314c, 0x314d, 0x314e
};

static const uint32_t final_to_ucs[27] =
{
  L'\0', L'\0', 0x3133, L'\0', 0x3135, 0x3136, L'\0', L'\0',
  0x313a, 0x313b, 0x314c, 0x313d, 0x313e, 0x313f,
  0x3140, L'\0', L'\0', 0x3144, L'\0', L'\0', L'\0',
  L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'
};

/* The following three arrays are used to convert
   precomposed Hangul syllables in [0xac00,0xd???]
   to Jamo bit patterns for Johab encoding

   cf. : KS C 5601-1992, Annex3 Table 2

   Arrays are used to speed up things although it's possible
   to get the same result arithmetically.

 */
static const int init_to_bit[19] =
{
  0x8800, 0x8c00, 0x9000, 0x9400, 0x9800, 0x9c00,
  0xa000, 0xa400, 0xa800, 0xac00, 0xb000, 0xb400,
  0xb800, 0xbc00, 0xc000, 0xc400, 0xc800, 0xcc00,
  0xd000
};

static const int mid_to_bit[21] =
{
          0x0060, 0x0080, 0x00a0, 0x00c0, 0x00e0,
  0x0140, 0x0160, 0x0180, 0x01a0, 0x01c0, 0x1e0,
  0x0240, 0x0260, 0x0280, 0x02a0, 0x02c0, 0x02e0,
  0x0340, 0x0360, 0x0380, 0x03a0
};

static const int final_to_bit[28] =
{
  1, 2, 3, 4, 5, 6, 7, 8, 9, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 0x10, 0x11,
  0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d
};

/* The conversion table from
   UCS4 Hangul Compatibility Jamo in [0x3131,0x3163]
   to Johab

   cf. 1. KS C 5601-1992 Annex 3 Table 2
   2. Unicode 2.0 manual

 */
static const uint16_t jamo_from_ucs_table[51] =
{
  0x8841, 0x8c41,
  0x8444,
  0x9041,
  0x8446, 0x8447,
  0x9441, 0x9841, 0x9c41,
  0x844a, 0x844b, 0x844c, 0x844d, 0x884e, 0x884f, 0x8450,
  0xa041, 0xa441, 0xa841,
  0x8454,
  0xac41, 0xb041, 0xb441, 0xb841, 0xbc41,
  0xc041, 0xc441, 0xc841, 0xca41, 0xd041,
  0x8461, 0x8481, 0x84a1, 0x84c1, 0x84e1,
  0x8541, 0x8561, 0x8581, 0x85a1, 0x85c1, 0x85e1,
  0x8641, 0x8661, 0x8681, 0x86a1, 0x86c1, 0x86e1,
  0x8741, 0x8761, 0x8781, 0x87a1
};


static inline uint32_t
johab_sym_hanja_to_ucs (uint_fast32_t idx, uint_fast32_t c1, uint_fast32_t c2)
{
  if (idx <= 0xdefe)
    return (uint32_t) __ksc5601_sym_to_ucs[(c1 - 0xd9) * 188 + c2
					   - (c2 > 0x90 ? 0x43 : 0x31)];
  else
    return (uint32_t) __ksc5601_hanja_to_ucs[(c1 - 0xe0) * 188 + c2
					     - (c2 > 0x90 ? 0x43 : 0x31)];
}

static uint16_t
johab_hanja_from_ucs (uint32_t ch)
{
  uint16_t idx;
  if (ucs4_to_ksc5601_hanja (ch, &idx))
    {
      int idx1, idx2;
      /* Hanja begins at the 42th row. 42=0x2a : 0x2a + 0x20 = 0x4a.  */
      idx1 = idx / 256 - 0x4a;
      idx2 = idx % 256 + 0x80;

      return ((idx1 / 2) * 256 + 0xe000 + idx2
	      + (idx1 % 2 ? 0 :  (idx2 > 0xee ? 0x43 : 0x31) - 0xa1));
    }
  else
    return 0;
}

static uint16_t
johab_sym_from_ucs (uint32_t ch)
{
  uint16_t idx;
  if (ucs4_to_ksc5601_sym (ch, &idx))
    {
      int idx1, idx2;

      idx1 = idx / 256 - 0x21;
      idx2 = idx % 256 + 0x80;

      return ((idx1 / 2) * 256 + 0xd900 + idx2
	      + (idx1 % 2 ? 0 : (idx2 > 0xee ? 0x43 : 0x31) - 0xa1));
    }
  else
    return 0;
}


static inline void
johab_from_ucs4 (uint32_t ch, unsigned char *cp)
{
  if (ch >= 0x7f)
    {
      int idx;

      if (ch >= 0xac00 && ch <= 0xd7a3)
	{
	  ch -= 0xac00;
	  idx = init_to_bit[ch / 588];  /* 21*28 = 588 */
	  idx += mid_to_bit[(ch / 28) % 21];  /* (ch % (21 * 28)) / 28 */
	  idx += final_to_bit[ch %  28]; /* (ch % (21 * 28)) % 28 */
	}
      /* KS C 5601-1992 Annex 3 regards  0xA4DA(Hangul Filler : U3164)
         as symbol */
      else if (ch >= 0x3131 && ch <= 0x3163)
	idx = jamo_from_ucs_table[ch - 0x3131];
      else if (ch >= 0x4e00 && ch <= 0x9fa5
	       || ch >= 0xf900 && ch <= 0xfa0b)
	idx = johab_hanja_from_ucs (ch);
      /*       Half-width Korean Currency Won Sign
	       else if ( ch == 0x20a9 )
	       idx = 0x5c00;
      */
      else
	idx = johab_sym_from_ucs (ch);

      cp[0] = (unsigned char) (idx / 256);
      cp[1] = (unsigned char) (idx & 0xff);

    }
  else
    {
      cp[0] = (unsigned char) ch;
      cp[1] = 0;
    }
}


/* Definitions used in the body of the `gconv' function.  */
#define CHARSET_NAME		"JOHAB"
#define FROM_LOOP		from_johab
#define TO_LOOP			to_johab
#define DEFINE_INIT		1
#define DEFINE_FINI		1
#define MIN_NEEDED_FROM		1
#define MAX_NEEDED_FROM		2
#define MIN_NEEDED_TO		4


/* First define the conversion function from JOHAB to UCS4.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
#define LOOPFCT			FROM_LOOP
#define BODY \
  {									      \
    uint32_t ch = *inptr;						      \
									      \
    /* half-width Korean Currency WON sign				      \
       if (ch == 0x5c)							      \
	 ch =  0x20a9;							      \
       else if (ch < 0x7f)						      \
	 ch = (wchar_t) ch;						      \
    */									      \
    if (ch < 0x7f)							      \
      /* Plain ASCII.  */						      \
      ++inptr;								      \
    /* Johab : 1. Hangul						      \
       1st byte : 0x84-0xd3						      \
       2nd byte : 0x41-0x7e, 0x81-0xfe					      \
       2. Hanja & Symbol  :						      \
       1st byte : 0xd8-0xde, 0xe0-0xf9					      \
       2nd byte : 0x31-0x7e, 0x91-0xfe					      \
       0xd831-0xd87e and 0xd891-0xd8fe are user-defined area */		      \
    else								      \
      {									      \
	if (ch > 0xf9 || ch == 0xdf || (ch > 0x7e && ch < 0x84)		      \
	    || (ch > 0xd3 && ch < 0xd9))				      \
	  {								      \
	    /* These are illegal.  */					      \
	    result = GCONV_ILLEGAL_INPUT;				      \
	    break;							      \
	  }								      \
	else								      \
	  {								      \
	    /* Two-byte character.  First test whether the next		      \
	       character is also available.  */				      \
	    uint32_t ch2;						      \
	    uint_fast32_t idx;						      \
									      \
	    if (NEED_LENGTH_TEST && inptr + 1 >= inend)			      \
	      {								      \
		/* The second character is not available.  Store the	      \
		   intermediate result.  */				      \
		result = GCONV_INCOMPLETE_INPUT;			      \
		break;							      \
	      }								      \
									      \
	    ch2 = inptr[1];						      \
	    idx = ch * 256 + ch2;					      \
	    if (ch <= 0xd3)						      \
	      {								      \
		/* Hangul */						      \
		uint_fast32_t i, m, f;					      \
									      \
		i = init[(idx & 0x7c00) >> 10];				      \
		m = mid[(idx & 0x03e0) >> 5];				      \
		f = final[idx & 0x001f];				      \
									      \
		if (i == -1 || m == -1 || f == -1)			      \
		  {							      \
		    /* This is illegal.  */				      \
		    result = GCONV_ILLEGAL_INPUT;			      \
		    break;						      \
		  }							      \
		else if (i > 0 && m > 0)				      \
		  ch = ((i - 1) * 21 + (m - 1)) * 28 + f + 0xac00;	      \
		else if (i > 0 && m == 0 & f == 0)			      \
		  ch = init_to_ucs[i - 1];				      \
		else if (i == 0 && m > 0 & f == 0)			      \
		  ch = 0x314e + m;	/* 0x314f + m - 1 */		      \
		else if (i == 0 && m == 0 & f > 0)			      \
		  ch = final_to_ucs[f - 1];	/* round trip?? */	      \
		else							      \
		  {							      \
		    /* This is illegal.  */				      \
		    result = GCONV_ILLEGAL_INPUT;			      \
		    break;						      \
		  }							      \
	      }								      \
	    else							      \
	      {								      \
		if (ch2 < 0x31 || (ch2 > 0x7e && ch2 < 0x91) || ch2 == 0xff)  \
		  {							      \
		    /* This is illegal.  */				      \
		    result = GCONV_ILLEGAL_INPUT;			      \
		    break;						      \
		  }							      \
		else if (ch == 0xda && ch2 > 0xa0 && ch2 < 0xd4)	      \
		  {							      \
		    /* This is illegal.  Modern Hangul Jaso is defined	      \
		       elsewhere in Johab */				      \
		    result = GCONV_ILLEGAL_INPUT;			      \
		    break;						      \
		  }							      \
		else							      \
		  {							      \
		    ch = johab_sym_hanja_to_ucs (idx, ch, ch2);		      \
		    /* if (idx <= 0xdefe)				      \
			 ch = __ksc5601_sym_to_ucs[(ch - 0xd9) * 192	      \
						   + ch2 - (ch2 > 0x90	      \
							    ? 0x43 : 0x31)];  \
		       else						      \
		         ch = __ksc5601_hanja_to_ucs[(ch - 0xe0) *192	      \
						     + ch2 -  (ch2 > 0x90     \
							       ?0x43 : 0x31)];\
		    */							      \
		  }							      \
	      }								      \
	  }								      \
									      \
	if (ch == 0)							      \
	  {								      \
	    /* This is an illegal character.  */			      \
	    result = GCONV_ILLEGAL_INPUT;				      \
	    break;							      \
	  }								      \
									      \
	inptr += 2;							      \
      }									      \
									      \
    *((uint32_t *) outptr)++ = ch;					      \
  }
#include <iconv/loop.c>


/* Next, define the other direction.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_TO
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
#define LOOPFCT			TO_LOOP
#define BODY \
  {									      \
    uint32_t ch = *((uint32_t *) inptr);				      \
    unsigned char cp[2];						      \
    /*									      \
       if (ch >= (sizeof (from_ucs4_lat1) / sizeof (from_ucs4_lat1[0])))      \
	 {								      \
	   if (ch >= 0x0391 && ch <= 0x0451)				      \
	     cp = from_ucs4_greek[ch - 0x391];				      \
	   else if (ch >= 0x2010 && ch <= 0x9fa0)			      \
	     cp = from_ucs4_cjk[ch - 0x02010];				      \
	   else								      \
	     break;							      \
	 }								      \
       else								      \
	 cp = from_ucs4_lat1[ch];					      \
    */									      \
    johab_from_ucs4 (ch, cp);						      \
									      \
    if (cp[0] == '\0' && ch != 0)					      \
      {									      \
	/* Illegal character.  */					      \
	result = GCONV_ILLEGAL_INPUT;					      \
	break;								      \
      }									      \
									      \
    *outptr++ = cp[0];							      \
    /* Now test for a possible second byte and write this if possible.  */    \
    if (cp[1] != '\0')							      \
      {									      \
	if (NEED_LENGTH_TEST && outptr >= outend)			      \
	  {								      \
	    /* The result does not fit into the buffer.  */		      \
	    --outptr;							      \
	    result = GCONV_FULL_OUTPUT;					      \
	    break;							      \
	  }								      \
	*outptr++ = cp[1];						      \
      }									      \
									      \
    inptr += 4;								      \
  }
#include <iconv/loop.c>


/* Now define the toplevel functions.  */
#include <iconv/skeleton.c>