Source

xemacs-beta / src / charset.h

Full commit
  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
/* Header for charsets.
   Copyright (C) 1992, 1995 Free Software Foundation, Inc.
   Copyright (C) 1995 Sun Microsystems, Inc.
   Copyright (C) 2001, 2002, 2010 Ben Wing.

This file is part of XEmacs.

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

XEmacs 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 General Public License
for more details.

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

/* Synched up with: Mule 2.3.  Not in FSF. */

/* Rewritten by Ben Wing <ben@xemacs.org>. */

#ifndef INCLUDED_charset_h_
#define INCLUDED_charset_h_



#ifndef MULE

/************************************************************************/
/*                            fake charset defs                         */
/************************************************************************/

/* used when MULE is not defined, so that Charset-type stuff can still
   be done */

#define Vcharset_ascii Qnil

#define ichar_charset(ch) Vcharset_ascii
#define ichar_leading_byte(ch) LEADING_BYTE_ASCII
#define ichar_len(ch) 1
#define ichar_len_fmt(ch, fmt) 1
#define LEADING_BYTE_ASCII 0x80
#define NUM_LEADING_BYTES 1
#define MIN_LEADING_BYTE 0x80
#define CHARSETP(cs) 1
#define charset_by_leading_byte(lb) Vcharset_ascii
#define XCHARSET_LEADING_BYTE(cs) LEADING_BYTE_ASCII
#define XCHARSET_GRAPHIC(cs) -1
#define XCHARSET_COLUMNS(cs) 1
#define XCHARSET_DIMENSION(cs) 1
#define BREAKUP_ICHAR(ch, charset, byte1, byte2) do {	\
  (charset) = Vcharset_ascii;				\
  (byte1) = (ch);					\
  (byte2) = 0;						\
} while (0)
#define XCHARSET_CCL_PROGRAM(cs) Qnil
#define XCHARSET_NAME(cs) Qascii
#define Fget_charset(cs) (cs)
#define Fcharset_list() list1 (Vcharset_ascii)

#else /* MULE */


/************************************************************************/
/*                    Definition of leading bytes                       */
/************************************************************************/

#define MIN_LEADING_BYTE		0x7F

/** The following are for 1-byte characters in an official charset. **/
enum LEADING_BYTE_OFFICIAL_1
{
  MIN_LEADING_BYTE_OFFICIAL_1 = 0x80,
  /* LEADING_BYTE_LATIN_ISO8859_1 *MUST* be equal to
     MIN_LEADING_BYTE_OFFICIAL_1. */
  LEADING_BYTE_LATIN_ISO8859_1 =  /* 0x80 Right half of ISO 8859-1 */
    MIN_LEADING_BYTE_OFFICIAL_1,
  LEADING_BYTE_LATIN_ISO8859_2,   /* 0x81 Right half of ISO 8859-2 */
  LEADING_BYTE_LATIN_ISO8859_3,   /* 0x82 Right half of ISO 8859-3 */
  LEADING_BYTE_LATIN_ISO8859_4,   /* 0x83 Right half of ISO 8859-4 */
  LEADING_BYTE_THAI_TIS620,       /* 0x84 TIS620-2533 */
  LEADING_BYTE_GREEK_ISO8859_7,   /* 0x85 Right half of ISO 8859-7 */
  LEADING_BYTE_ARABIC_ISO8859_6,  /* 0x86 Right half of ISO 8859-6 */
  LEADING_BYTE_HEBREW_ISO8859_8,  /* 0x87 Right half of ISO 8859-8 */
  LEADING_BYTE_KATAKANA_JISX0201, /* 0x88 Right half of JIS X0201-1976 */
  LEADING_BYTE_LATIN_JISX0201,    /* 0x89 Left  half of JIS X0201-1976 */
  LEADING_BYTE_CYRILLIC_ISO8859_5,/* 0x8A Right half of ISO 8859-5 */
  LEADING_BYTE_LATIN_ISO8859_9,   /* 0x8B Right half of ISO 8859-9 */
  LEADING_BYTE_LATIN_ISO8859_15,  /* 0x8C Right half of ISO 8859-15 */
#ifdef ENABLE_COMPOSITE_CHARS
  LEADING_BYTE_COMPOSITE,         /* 0x8D For a composite character */
  MAX_LEADING_BYTE_OFFICIAL_1 =
    LEADING_BYTE_COMPOSITE - 1,
#else
    /* Does not need to be the last entry, but simplifies things */
  LEADING_BYTE_COMPOSITE_REPLACEMENT, /* 0x8D Replaces ESC 0 - ESC 4 in a
                                         buffer */
  MAX_LEADING_BYTE_OFFICIAL_1 =
    LEADING_BYTE_COMPOSITE_REPLACEMENT,
#endif
                                  /* 0x8E Unused */
};

/* These next 2 + LEADING_BYTE_COMPOSITE need special treatment in a string
   and/or character */

#define LEADING_BYTE_ASCII		0x7F /* Not used except in arrays
						indexed by leading byte */
#define LEADING_BYTE_CONTROL_1          0x8F /* represent normal 80-9F */

/** The following are for 2-byte characters in an official charset. **/
enum LEADING_BYTE_OFFICIAL_2
{
  MIN_LEADING_BYTE_OFFICIAL_2 = 0x90,
  LEADING_BYTE_JAPANESE_JISX0208_1978 =
    MIN_LEADING_BYTE_OFFICIAL_2,       /* 0x90 Japanese JIS X0208-1978 */
  LEADING_BYTE_CHINESE_GB2312,         /* 0x91 Chinese Hanzi GB2312-1980 */
  LEADING_BYTE_JAPANESE_JISX0208,      /* 0x92 Japanese JIS X0208-1983 */
  LEADING_BYTE_KOREAN_KSC5601,         /* 0x93 Hangul KS C5601-1987 */
  LEADING_BYTE_JAPANESE_JISX0212,      /* 0x94 Japanese JIS X0212-1990 */
  LEADING_BYTE_CHINESE_CNS11643_1,     /* 0x95 Chinese CNS11643 Set 1 */
  LEADING_BYTE_CHINESE_CNS11643_2,     /* 0x96 Chinese CNS11643 Set 2 */
  LEADING_BYTE_CHINESE_BIG5_1,         /* 0x97 Big5 Level 1 */
  LEADING_BYTE_CHINESE_BIG5_2,         /* 0x98 Big5 Level 2 */
  MAX_LEADING_BYTE_OFFICIAL_2 =
    LEADING_BYTE_CHINESE_BIG5_2,

                                       /* 0x99 unused */
                                       /* 0x9A unused */
                                       /* 0x9B unused */
                                       /* 0x9C unused */
                                       /* 0x9D unused */
};


/** The following are for 1- and 2-byte characters in a private charset. **/

#define PRE_LEADING_BYTE_PRIVATE_1	0x9E	/* 1-byte char-set */
#define PRE_LEADING_BYTE_PRIVATE_2	0x9F	/* 2-byte char-set */

#define MIN_LEADING_BYTE_PRIVATE_1	0xA0
#define MAX_LEADING_BYTE_PRIVATE_1	0xC0
#define MIN_LEADING_BYTE_PRIVATE_2	0xC1
#define MAX_LEADING_BYTE_PRIVATE_2	0xFF

#define NUM_LEADING_BYTES 129


/************************************************************************/
/*                    Operations on leading bytes                       */
/************************************************************************/

/* Is this leading byte for a private charset? */

#define leading_byte_private_p(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1)

/* Is this a prefix for a private leading byte? */

DECLARE_INLINE_HEADER (
int
leading_byte_prefix_p (Ibyte lb)
)
{
  return (lb == PRE_LEADING_BYTE_PRIVATE_1 ||
	  lb == PRE_LEADING_BYTE_PRIVATE_2);
}

/* Given a private leading byte, return the leading byte prefix stored
   in a string. */

#define private_leading_byte_prefix(lb)			\
  ((unsigned int) (lb) < MIN_LEADING_BYTE_PRIVATE_2 ?	\
   PRE_LEADING_BYTE_PRIVATE_1 :				\
   PRE_LEADING_BYTE_PRIVATE_2)


/************************************************************************/
/*            Information about a particular character set              */
/************************************************************************/

struct Lisp_Charset
{
  NORMAL_LISP_OBJECT_HEADER header;

  int id;
  Lisp_Object name;
  Lisp_Object doc_string;
  Lisp_Object registries;
  Lisp_Object short_name;
  Lisp_Object long_name;

  Lisp_Object reverse_direction_charset;

  Lisp_Object ccl_program;

  /* Unicode translation tables.  See unicode.c for the format of these
     tables, and discussion of how they are initialized.
  */
  void *to_unicode_table;
  void *from_unicode_table;
  int from_unicode_levels;

  /* Final byte of this character set in ISO2022 designating escape
     sequence */
  Ibyte final;

  /* Number of bytes (1 - 4) required in the internal representation
     for characters in this character set.  This is *not* the
     same as the dimension of the character set). */
  int rep_bytes;

  /* Number of columns a character in this charset takes up, on TTY
     devices.  Not used for X devices. */
  int columns;

  /* Direction of this character set */
  int direction;

  /* Type of this character set (94, 96, 94x94, 96x96) */
  int type;

  /* Number of bytes used in encoding of this character set (1 or 2) */
  int dimension;

  /* Number of chars in each dimension (usually 94 or 96) */
  int chars;

  /* Which half of font to be used to display this character set */
  int graphic;

  /* If set, this charset should be written out in ISO-2022-based coding
     systems using the escape sequence for UTF-8, not using our internal
     representation and the associated real ISO 2022 designation. */
  unsigned int encode_as_utf_8 :1;

  /* If set, this is a "temporary" charset created when we encounter
     an unknown final.  This is so that we can successfully compile
     and load such files.  We allow a real charset to be created on top
     of this temporary charset. */
  unsigned int temporary :1;
};
typedef struct Lisp_Charset Lisp_Charset;

DECLARE_LISP_OBJECT (charset, Lisp_Charset);
#define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
#define wrap_charset(p) wrap_record (p, charset)
#define CHARSETP(x) RECORDP (x, charset)
#define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
#define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)

#define CHARSET_TYPE_94    0	/* This charset includes 94    characters. */
#define CHARSET_TYPE_96    1	/* This charset includes 96    characters. */
#define CHARSET_TYPE_94X94 2	/* This charset includes 94x94 characters. */
#define CHARSET_TYPE_96X96 3	/* This charset includes 96x96 characters. */

#define CHARSET_LEFT_TO_RIGHT	0
#define CHARSET_RIGHT_TO_LEFT	1

/* Leading byte and id have been regrouped. -- OG */
#define CHARSET_ID(cs)		 ((cs)->id)
#define CHARSET_LEADING_BYTE(cs) ((Ibyte) CHARSET_ID (cs))
#define CHARSET_NAME(cs)	 ((cs)->name)
#define CHARSET_SHORT_NAME(cs)	 ((cs)->short_name)
#define CHARSET_LONG_NAME(cs)	 ((cs)->long_name)
#define CHARSET_REP_BYTES(cs)	 ((cs)->rep_bytes)
#define CHARSET_COLUMNS(cs)	 ((cs)->columns)
#define CHARSET_GRAPHIC(cs)	 ((cs)->graphic)
#define CHARSET_ENCODE_AS_UTF_8(cs)	 ((cs)->encode_as_utf_8)
#define CHARSET_TYPE(cs)	 ((cs)->type)
#define CHARSET_DIRECTION(cs)	 ((cs)->direction)
#define CHARSET_FINAL(cs)	 ((cs)->final)
#define CHARSET_DOC_STRING(cs)	 ((cs)->doc_string)
#define CHARSET_REGISTRIES(cs)	 ((cs)->registries)
#define CHARSET_CCL_PROGRAM(cs)  ((cs)->ccl_program)
#define CHARSET_DIMENSION(cs)	 ((cs)->dimension)
#define CHARSET_CHARS(cs)	 ((cs)->chars)
#define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
#define CHARSET_TO_UNICODE_TABLE(cs) ((cs)->to_unicode_table)
#define CHARSET_FROM_UNICODE_TABLE(cs) ((cs)->from_unicode_table)
#define CHARSET_FROM_UNICODE_LEVELS(cs) ((cs)->from_unicode_levels)

#define CHARSET_PRIVATE_P(cs) leading_byte_private_p (CHARSET_LEADING_BYTE (cs))

#define XCHARSET_ID(cs)		  CHARSET_ID           (XCHARSET (cs))
#define XCHARSET_NAME(cs)	  CHARSET_NAME         (XCHARSET (cs))
#define XCHARSET_SHORT_NAME(cs)	  CHARSET_SHORT_NAME   (XCHARSET (cs))
#define XCHARSET_LONG_NAME(cs)	  CHARSET_LONG_NAME    (XCHARSET (cs))
#define XCHARSET_REP_BYTES(cs)	  CHARSET_REP_BYTES    (XCHARSET (cs))
#define XCHARSET_COLUMNS(cs)	  CHARSET_COLUMNS      (XCHARSET (cs))
#define XCHARSET_GRAPHIC(cs)      CHARSET_GRAPHIC      (XCHARSET (cs))
#define XCHARSET_ENCODE_AS_UTF_8(cs) CHARSET_ENCODE_AS_UTF_8 (XCHARSET (cs))
#define XCHARSET_TYPE(cs)	  CHARSET_TYPE         (XCHARSET (cs))
#define XCHARSET_DIRECTION(cs)	  CHARSET_DIRECTION    (XCHARSET (cs))
#define XCHARSET_FINAL(cs)	  CHARSET_FINAL        (XCHARSET (cs))
#define XCHARSET_DOC_STRING(cs)	  CHARSET_DOC_STRING   (XCHARSET (cs))
#define XCHARSET_REGISTRIES(cs)	  CHARSET_REGISTRIES     (XCHARSET (cs))
#define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
#define XCHARSET_CCL_PROGRAM(cs)  CHARSET_CCL_PROGRAM  (XCHARSET (cs))
#define XCHARSET_DIMENSION(cs)	  CHARSET_DIMENSION    (XCHARSET (cs))
#define XCHARSET_CHARS(cs)	  CHARSET_CHARS        (XCHARSET (cs))

#define XCHARSET_PRIVATE_P(cs)	  CHARSET_PRIVATE_P    (XCHARSET (cs))
#define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
  CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
#define XCHARSET_TO_UNICODE_TABLE(cs) \
  CHARSET_TO_UNICODE_TABLE (XCHARSET (cs))
#define XCHARSET_FROM_UNICODE_TABLE(cs) \
  CHARSET_FROM_UNICODE_TABLE (XCHARSET (cs))
#define XCHARSET_FROM_UNICODE_LEVELS(cs) \
  CHARSET_FROM_UNICODE_LEVELS (XCHARSET (cs))

struct charset_lookup
{
  /* Table of charsets indexed by leading byte. */
  Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];

  /* Table of charsets indexed by type/final-byte/direction. */
  Lisp_Object charset_by_attributes[4][128][2];
  Ibyte next_allocated_1_byte_leading_byte;
  Ibyte next_allocated_2_byte_leading_byte;
};

extern struct charset_lookup *chlook;

DECLARE_INLINE_HEADER (
Lisp_Object
charset_by_leading_byte (int lb)
)
{
#ifdef ERROR_CHECK_TEXT
  /* When error-checking is on, x86 GCC 2.95.2 -O3 miscompiles the
     following unless we introduce `tem'. */
  int tem = lb;
  text_checking_assert (tem >= MIN_LEADING_BYTE && tem <= 0xFF);
#endif
  return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
}

DECLARE_INLINE_HEADER (
Lisp_Object
charset_by_attributes (int type, int final, int dir)
)
{
  type_checking_assert (type  < countof (chlook->charset_by_attributes) &&
			final < countof (chlook->charset_by_attributes[0]) &&
			dir   < countof (chlook->charset_by_attributes[0][0]));
  return chlook->charset_by_attributes[type][final][dir];
}


/************************************************************************/
/*                        Dealing with characters                       */
/************************************************************************/

/* The bit fields of character are divided into 3 parts:
   FIELD1(7bits):FIELD2(7bits):FIELD3(7bits) */

#define ICHAR_FIELD1_MASK (0x7F << 14)
#define ICHAR_FIELD2_MASK (0x7F << 7)
#define ICHAR_FIELD3_MASK 0x7F

/* Macros to access each field of a character code of C.  */

#define ichar_field1(c) (((c) & ICHAR_FIELD1_MASK) >> 14)
#define ichar_field2(c) (((c) & ICHAR_FIELD2_MASK) >> 7)
#define ichar_field3(c)  ((c) & ICHAR_FIELD3_MASK)

/* Field 1, if non-zero, usually holds a leading byte for a
   dimension-2 charset.  Field 2, if non-zero, usually holds a leading
   byte for a dimension-1 charset. */

/* Converting between field values and leading bytes.  */

#define FIELD2_TO_OFFICIAL_LEADING_BYTE (MIN_LEADING_BYTE_OFFICIAL_1 - 1)
#define FIELD2_TO_PRIVATE_LEADING_BYTE  0x80

#define FIELD1_TO_OFFICIAL_LEADING_BYTE (MIN_LEADING_BYTE_OFFICIAL_2 - 1)
#define FIELD1_TO_PRIVATE_LEADING_BYTE  0x80

/* Minimum and maximum allowed values for the fields. */

#define MIN_ICHAR_FIELD2_OFFICIAL \
  (MIN_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
#define MAX_ICHAR_FIELD2_OFFICIAL \
  (MAX_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)

#define MIN_ICHAR_FIELD1_OFFICIAL \
  (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
#define MAX_ICHAR_FIELD1_OFFICIAL \
  (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)

#define MIN_ICHAR_FIELD2_PRIVATE \
  (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
#define MAX_ICHAR_FIELD2_PRIVATE \
  (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)

#define MIN_ICHAR_FIELD1_PRIVATE \
  (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
#define MAX_ICHAR_FIELD1_PRIVATE \
  (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)

/* Minimum character code of each <type> character.  */

#define MIN_CHAR_OFFICIAL_TYPE9N    (MIN_ICHAR_FIELD2_OFFICIAL <<  7)
#define MIN_CHAR_PRIVATE_TYPE9N     (MIN_ICHAR_FIELD2_PRIVATE  <<  7)
#define MIN_CHAR_OFFICIAL_TYPE9NX9N (MIN_ICHAR_FIELD1_OFFICIAL << 14)
#define MIN_CHAR_PRIVATE_TYPE9NX9N  (MIN_ICHAR_FIELD1_PRIVATE  << 14)
#define MIN_CHAR_COMPOSITION        (0x7F << 14)

/* Leading byte of a character.

   NOTE: This takes advantage of the fact that
   FIELD2_TO_OFFICIAL_LEADING_BYTE and
   FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
   */

DECLARE_INLINE_HEADER (
Ibyte
ichar_leading_byte (Ichar c)
)
{
  if (ichar_ascii_p (c))
    return LEADING_BYTE_ASCII;
  else if (c < 0xA0)
    return LEADING_BYTE_CONTROL_1;
  else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
    return ichar_field2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE;
  else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
    return ichar_field1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE;
  else if (c < MIN_CHAR_COMPOSITION)
    return ichar_field1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE;
  else
    {
#ifdef ENABLE_COMPOSITE_CHARS
      return LEADING_BYTE_COMPOSITE;
#else
      ABORT();
      return 0;
#endif /* ENABLE_COMPOSITE_CHARS */
    }
}

DECLARE_INLINE_HEADER (
Bytecount
ichar_len (Ichar c)
)
{
  if (ichar_ascii_p (c))
    return 1;
  else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
    return 2;
  else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
    return 3; /* dimension-2 official or dimension-1 private */
  else if (c < MIN_CHAR_COMPOSITION)
    return 4;
  else
    {
#ifdef ENABLE_COMPOSITE_CHARS
#error Not yet implemented
#else
      ABORT();
      return 0;
#endif /* ENABLE_COMPOSITE_CHARS */
    }
}

DECLARE_INLINE_HEADER (
Bytecount
ichar_len_fmt (Ichar c, Internal_Format fmt)
)
{
  switch (fmt)
    {
    case FORMAT_DEFAULT:
      return ichar_len (c);
    case FORMAT_16_BIT_FIXED:
      return 2;
    case FORMAT_32_BIT_FIXED:
      return 4;
    default:
      text_checking_assert (fmt == FORMAT_8_BIT_FIXED);
      return 1;
    }
}

#define ichar_charset(c) charset_by_leading_byte (ichar_leading_byte (c))

/* Return a character whose charset is CHARSET and position-codes are C1
   and C2.  TYPE9N character ignores C2. (For typical charsets, i.e. not
   ASCII, Control-1 or Composite, C1 and C2 will be in the range of 32 to
   127 or 33 to 126.  See `make-char'.)

   NOTE: This takes advantage of the fact that
   FIELD2_TO_OFFICIAL_LEADING_BYTE and
   FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
   */

DECLARE_INLINE_HEADER (
Ichar
make_ichar (Lisp_Object charset, int c1, int c2)
)
{
  Ichar retval;
  if (EQ (charset, Vcharset_ascii))
    retval = c1;
  else if (EQ (charset, Vcharset_control_1))
    retval = c1 | 0x80;
#ifdef ENABLE_COMPOSITE_CHARS
  else if (EQ (charset, Vcharset_composite))
    retval = (0x1F << 14) | ((c1) << 7) | (c2);
#endif
  else if (XCHARSET_DIMENSION (charset) == 1)
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1);
  else if (!XCHARSET_PRIVATE_P (charset))
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
  else
    retval = ((XCHARSET_LEADING_BYTE (charset) -
	       FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
  text_checking_assert (valid_ichar_p (retval));
  return retval;
}

/* BREAKUP_ICHAR_1_UNSAFE assumes that the charset has already been
   calculated, and just computes c1 and c2.

   BREAKUP_ICHAR also computes and stores the charset. */

#define BREAKUP_ICHAR_1_UNSAFE(c, charset, c1, c2)	\
  XCHARSET_DIMENSION (charset) == 1			\
  ? ((c1) = ichar_field3 (c), (c2) = 0)		\
  : ((c1) = ichar_field2 (c),				\
     (c2) = ichar_field3 (c))

DECLARE_INLINE_HEADER (
void
breakup_ichar_1 (Ichar c, Lisp_Object *charset, int *c1, int *c2)
)
{
  text_checking_assert (valid_ichar_p (c));
  *charset = ichar_charset (c);
  BREAKUP_ICHAR_1_UNSAFE (c, *charset, *c1, *c2);
}

/* BREAKUP_ICHAR separates an Ichar into its components.  The charset of
   character C is set to CHARSET, and the position-codes of C are set to C1
   and C2.  C2 of TYPE9N character is 0.  */

#define BREAKUP_ICHAR(c, charset, c1, c2) \
  breakup_ichar_1 (c, &(charset), &(c1), &(c2))

/* Forward compatibility from ben-unicode-internal: Convert a charset
   codepoint into a character in the internal string representation.
   Return number of bytes written out.  FAIL controls failure mode when
   charset conversion to Unicode is not possible (unused as of yet). */
DECLARE_INLINE_HEADER (
Bytecount
charset_codepoint_to_itext (Lisp_Object charset, int c1, int c2, Ibyte *ptr,
			    enum converr UNUSED (fail))
)
{
  Ichar ch;

  if (EQ (charset, Vcharset_ascii))
    {
      ptr[0] = (Ibyte) c2;
      return 1;
    }

  ch = make_ichar (charset, c1, c2);

  /* We can't rely on the converted character being non-ASCII.  For
     example, JISX0208 codepoint (33, 64) == Unicode 0x5C (ASCII
     backslash). */
  return set_itext_ichar (ptr, ch);
}

/* Forward compatibility from ben-unicode-internal */

DECLARE_INLINE_HEADER (
void
buffer_itext_to_charset_codepoint (const Ibyte *ptr,
				   struct buffer *UNUSED (buf),
				   Lisp_Object *charset, int *c1, int *c2,
				   enum converr UNUSED (fail))
)
{
  Ichar ch = itext_ichar (ptr);
  breakup_ichar_1 (ch, charset, c1, c2);
}

void get_charset_limits (Lisp_Object charset, int *low, int *high);
int ichar_to_unicode (Ichar chr);

EXFUN (Fcharset_name, 1);

#endif /* MULE */

/* ISO 10646 UTF-16, UCS-4, UTF-8, UTF-7, etc. */

enum unicode_type
{
  UNICODE_UTF_16,
  UNICODE_UTF_8,
  UNICODE_UTF_7,
  UNICODE_UCS_4,
  UNICODE_UTF_32
};

void encode_unicode_char (Lisp_Object USED_IF_MULE (charset), int h,
			  int USED_IF_MULE (l), unsigned_char_dynarr *dst,
			  enum unicode_type type, unsigned int little_endian,
                          int write_error_characters_as_such);

#define UNICODE_ERROR_OCTET_RANGE_START 0x200000

#define valid_utf_16_first_surrogate(ch) (((ch) & 0xFC00) == 0xD800)
#define valid_utf_16_last_surrogate(ch) (((ch) & 0xFC00) == 0xDC00)
#define valid_utf_16_surrogate(ch) (((ch) & 0xF800) == 0xD800)

void set_charset_registries(Lisp_Object charset, Lisp_Object registries);

EXFUN (Funicode_to_char, 2);
EXFUN (Fchar_to_unicode, 1); 

#endif /* INCLUDED_charset_h_ */