1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999,2000,2001,2002,2003 MORIOKA Tomohiko
4 This file is part of XEmacs.
6 XEmacs is free software; you can redistribute it and/or modify it
7 under the terms of the GNU General Public License as published by the
8 Free Software Foundation; either version 2, or (at your option) any
11 XEmacs is distributed in the hope that it will be useful, but WITHOUT
12 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
16 You should have received a copy of the GNU General Public License
17 along with XEmacs; see the file COPYING. If not, write to
18 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 Boston, MA 02111-1307, USA. */
21 #ifndef INCLUDED_char_ucs_h_
22 #define INCLUDED_char_ucs_h_
27 EXFUN (Fmake_directory_internal, 1);
29 extern Lisp_Object Vchar_attribute_hash_table;
31 #define valid_char_p(ch) 1
33 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
36 /************************************************************************/
37 /* Exported functions */
38 /************************************************************************/
40 extern Lisp_Object Vcharset_ucs;
41 extern Lisp_Object Vcharset_latin_jisx0201;
42 extern Lisp_Object Vcharset_chinese_big5;
43 extern Lisp_Object Vcharset_chinese_big5_1;
44 extern Lisp_Object Vcharset_chinese_big5_2;
45 extern Lisp_Object Vcharset_japanese_jisx0208;
46 extern Lisp_Object Vcharset_japanese_jisx0208_1990;
47 extern Lisp_Object Vcharset_japanese_jisx0212;
49 EXFUN (Fget_charset, 1);
51 extern Lisp_Object Qmap_ucs, Qucs;
53 Lisp_Object put_char_ccs_code_point (Lisp_Object character,
54 Lisp_Object ccs, Lisp_Object value);
55 Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
58 /************************************************************************/
59 /* Definition of leading bytes */
60 /************************************************************************/
62 typedef short Charset_ID;
65 #define LEADING_BYTE_UCS -177
67 /* represent normal 80-9F */
68 #define LEADING_BYTE_CONTROL_1 -77
70 /* ISO/IEC 10646 BMP */
71 #define LEADING_BYTE_UCS_BMP -176
73 /* ISO/IEC 10646 SMP */
74 #define LEADING_BYTE_UCS_SMP 1
76 /* ISO/IEC 10646 SIP */
77 #define LEADING_BYTE_UCS_SIP 2
79 /* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
80 #define LEADING_BYTE_JIS_X0208 3
82 /* Chinese GB 12345-1990 */
83 #define LEADING_BYTE_CHINESE_GB12345 4
85 #define LEADING_BYTE_CHINESE_BIG5 5
87 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
88 #define LEADING_BYTE_CHINESE_BIG5_1 6
90 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
91 #define LEADING_BYTE_CHINESE_BIG5_2 7
94 #define LEADING_BYTE_LATIN_VISCII 8
96 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
97 #define LEADING_BYTE_LATIN_VISCII_LOWER 9
99 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
100 #define LEADING_BYTE_LATIN_VISCII_UPPER 10
102 #define LEADING_BYTE_ETHIOPIC_UCS 11
104 #define MIN_LEADING_BYTE_PRIVATE 12
105 #define MAX_LEADING_BYTE_PRIVATE 512
109 #define LEADING_BYTE_ASCII -6 /* (CHARSET_ID_OFFSET_94 + 'B') */
111 /* Right half of JIS X0201-1976 */
112 #define LEADING_BYTE_KATAKANA_JISX0201 -13 /* (CHARSET_ID_OFFSET_94 + 'I') */
114 /* Left half of JIS X0201-1976 */
115 #define LEADING_BYTE_LATIN_JISX0201 -14 /* (CHARSET_ID_OFFSET_94 + 'J') */
118 /* Right half of ISO 8859-1 */
119 #define LEADING_BYTE_LATIN_ISO8859_1 -100 /* (CHARSET_ID_OFFSET_96 + 'A') */
121 /* Right half of ISO 8859-2 */
122 #define LEADING_BYTE_LATIN_ISO8859_2 -101 /* (CHARSET_ID_OFFSET_96 + 'B') */
124 /* Right half of ISO 8859-3 */
125 #define LEADING_BYTE_LATIN_ISO8859_3 -109 /* (CHARSET_ID_OFFSET_96 + 'C') */
127 /* Right half of ISO 8859-4 */
128 #define LEADING_BYTE_LATIN_ISO8859_4 -110 /* (CHARSET_ID_OFFSET_96 + 'D') */
130 /* Right half of ISO 8859-7 */
131 #define LEADING_BYTE_GREEK_ISO8859_7 -126 /* (CHARSET_ID_OFFSET_96 + 'F') */
133 /* Right half of ISO 8859-6 */
134 #define LEADING_BYTE_ARABIC_ISO8859_6 -127 /* (CHARSET_ID_OFFSET_96 + 'G') */
136 /* Right half of ISO 8859-8 */
137 #define LEADING_BYTE_HEBREW_ISO8859_8 -138 /* (CHARSET_ID_OFFSET_96 + 'H') */
139 /* Right half of ISO 8859-5 */
140 #define LEADING_BYTE_CYRILLIC_ISO8859_5 -144 /* (CHARSET_ID_OFFSET_96 + 'L') */
142 /* Right half of ISO 8859-9 */
143 #define LEADING_BYTE_LATIN_ISO8859_9 -148 /* (CHARSET_ID_OFFSET_96 + 'M') */
146 #define LEADING_BYTE_THAI_TIS620 -166 /* (CHARSET_ID_OFFSET_96 + 'T') */
148 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
149 #define LEADING_BYTE_LATIN_TCVN5712 -180 /* F = 5/10 0x5A `Z' */
152 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
153 #define LEADING_BYTE_JAPANESE_JISX0208_1978 -42
155 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
156 #define LEADING_BYTE_CHINESE_GB2312 -58
158 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
159 #define LEADING_BYTE_JAPANESE_JISX0208 -87
161 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
162 #define LEADING_BYTE_JAPANESE_JISX0208_1990 -168
164 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
165 #define LEADING_BYTE_KOREAN_KSC5601 -149
167 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
168 #define LEADING_BYTE_JAPANESE_JISX0212 -159
170 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
171 #define LEADING_BYTE_CHINESE_CCITT_GB -165
173 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
174 #define LEADING_BYTE_CHINESE_CNS11643_1 -171
176 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
177 #define LEADING_BYTE_CHINESE_CNS11643_2 -172
179 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
180 #define LEADING_BYTE_CHINESE_CNS11643_3 -183
182 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
183 #define LEADING_BYTE_CHINESE_CNS11643_4 -184
185 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
186 #define LEADING_BYTE_CHINESE_CNS11643_5 -185
188 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
189 #define LEADING_BYTE_CHINESE_CNS11643_6 -186
191 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
192 #define LEADING_BYTE_CHINESE_CNS11643_7 -187
194 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
195 #define LEADING_BYTE_KOREAN_KPS9566 -202
198 #define MIN_LEADING_BYTE (- 80 * 3)
200 #define NUM_LEADING_BYTES (MAX_LEADING_BYTE_PRIVATE - MIN_LEADING_BYTE)
203 /************************************************************************/
204 /* Information about a particular character set */
205 /************************************************************************/
209 struct lcrecord_header header;
213 Lisp_Object doc_string;
214 Lisp_Object registry;
215 Lisp_Object short_name;
216 Lisp_Object long_name;
218 Lisp_Object reverse_direction_charset;
220 Lisp_Object ccl_program;
222 /* Final byte of this character set in ISO2022 designating escape sequence */
225 /* Number of columns a character in this charset takes up, on TTY
226 devices. Not used for X devices. */
227 unsigned int columns;
229 /* Direction of this character set */
230 unsigned int direction;
232 /* Number of bytes used in encoding of this character set (1 .. 4) */
233 unsigned short dimension;
235 /* Number of chars in each dimension (94, 96, 128, 256) */
236 unsigned short chars;
238 /* Which half of font to be used to display this character set */
239 unsigned int graphic;
241 /* Code-point->character mapping table */
242 Lisp_Object decoding_table;
247 /* Range of character code */
248 int min_code, max_code;
250 /* Offset for external code */
253 /* Type of conversion from mother CCS */
254 unsigned char conversion;
256 /* Offset for each byte */
259 typedef struct Lisp_Charset Lisp_Charset;
261 DECLARE_LRECORD (charset, Lisp_Charset);
262 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
263 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
264 #define CHARSETP(x) RECORDP (x, charset)
265 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
266 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
268 #define CHARSET_LEFT_TO_RIGHT 0
269 #define CHARSET_RIGHT_TO_LEFT 1
271 /* Leading byte and id have been regrouped. -- OG */
272 #define CHARSET_ID(cs) ((cs)->id)
273 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
274 #define CHARSET_NAME(cs) ((cs)->name)
275 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
276 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
277 #define CHARSET_COLUMNS(cs) ((cs)->columns)
278 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
279 #define CHARSET_DIRECTION(cs) ((cs)->direction)
280 #define CHARSET_FINAL(cs) ((cs)->final)
281 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
282 #define CHARSET_REGISTRY(cs) ((cs)->registry)
283 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
284 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
285 #define CHARSET_CHARS(cs) ((cs)->chars)
286 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
287 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
288 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
289 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
290 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
291 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
292 #define CHARSET_MOTHER(cs) ((cs)->mother)
293 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
295 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
297 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
299 /* ad-hoc method for `ascii' */
300 if ((CHARSET_CHARS (cs) == 94) &&
301 (CHARSET_BYTE_OFFSET (cs) != 33))
302 return 128 - CHARSET_BYTE_OFFSET (cs);
304 return CHARSET_CHARS (cs);
307 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
308 INLINE_HEADER Lisp_Object
309 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
311 return Fgethash (CHARSET_NAME(cs),
312 Vchar_attribute_hash_table,
316 #define CONVERSION_IDENTICAL 0
317 #define CONVERSION_94 1
318 #define CONVERSION_96 2
319 #define CONVERSION_94x94 3
320 #define CONVERSION_96x96 4
321 #define CONVERSION_94x94x94 5
322 #define CONVERSION_96x96x96 6
323 #define CONVERSION_94x94x94x94 7
324 #define CONVERSION_96x96x96x96 8
325 #define CONVERSION_94x60 9
326 #define CONVERSION_94x94x60 10
327 #define CONVERSION_94x94x94x60 11
328 #define CONVERSION_BIG5_1 12
329 #define CONVERSION_BIG5_2 13
331 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
332 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
333 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
334 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
335 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
336 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
337 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
338 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
339 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
340 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
341 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
342 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
343 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
344 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
345 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
346 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
347 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
348 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
349 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
350 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
351 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
352 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
353 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
354 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
356 struct charset_lookup {
357 /* Table of charsets indexed by (leading byte - 128). */
358 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
360 /* Table of charsets indexed by type/final-byte/direction. */
361 Lisp_Object charset_by_attributes[4][128];
363 Charset_ID next_allocated_leading_byte;
366 extern struct charset_lookup *chlook;
368 #ifdef ERROR_CHECK_TYPECHECK
369 /* int not Bufbyte even though that is the actual type of a leading byte.
370 This way, out-ot-range values will get caught rather than automatically
372 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
373 INLINE_HEADER Lisp_Object
374 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
376 assert (lb >= MIN_LEADING_BYTE &&
377 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
378 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
383 #define CHARSET_BY_LEADING_BYTE(lb) \
384 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
388 INLINE_HEADER Lisp_Object
389 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
390 INLINE_HEADER Lisp_Object
391 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
397 else if (chars == 96)
401 type += dimension == 1 ? 0 : 2;
402 return chlook->charset_by_attributes[type][final];
406 /************************************************************************/
407 /* Dealing with characters */
408 /************************************************************************/
410 #define MAX_CHAR_BASIC_LATIN 0x007F
413 #define MIN_CHAR_HEBREW 0x0590
414 #define MAX_CHAR_HEBREW 0x05EF
417 #define MIN_CHAR_THAI 0x0E00
418 #define MAX_CHAR_THAI 0x0E5F
421 #define MIN_CHAR_HIRAGANA 0x3041
422 #define MAX_CHAR_HIRAGANA 0x3093
424 #define MIN_CHAR_KATAKANA 0x30A1
425 #define MAX_CHAR_KATAKANA 0x30F6
428 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
429 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
431 #define MAX_CHAR_BMP 0x00FFFF
433 #define MIN_CHAR_SMP 0x010000
434 #define MAX_CHAR_SMP 0x01FFFF
436 #define MIN_CHAR_SIP 0x020000
437 #define MAX_CHAR_SIP 0x02FFFF
440 #define MIN_CHAR_DAIKANWA 0x00E00000
441 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
443 #define MIN_CHAR_CBETA 0x00E20000
444 #define MAX_CHAR_CBETA 0x00E2FFFF
446 #define MIN_CHAR_CHINA3_JEF 0x00E80000
447 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
450 #define MIN_CHAR_94 0x00E90940
451 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
452 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
453 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
455 #define MIN_CHAR_94x94 0xE9F6C0
456 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
457 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
458 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
459 #define MIN_CHAR_96x96 0xF4C000
460 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
463 #define MIN_CHAR_GT 0x61000000
464 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
466 #define MIN_CHAR_BIG5_CDP 0x62000000
467 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
469 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
470 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
471 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
472 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
473 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
474 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
475 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
476 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
477 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
478 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
479 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
480 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
481 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
482 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
483 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
484 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
485 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
486 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
487 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
488 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
489 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
490 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
491 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
492 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
495 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
497 INLINE_HEADER Lisp_Object
498 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
499 INLINE_HEADER Lisp_Object
500 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
502 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
506 int idx = code - byte_offset;
508 if (idx < XVECTOR_LENGTH(table))
509 return XVECTOR_DATA(table)[idx];
517 INLINE_HEADER Lisp_Object
518 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
520 INLINE_HEADER Lisp_Object
521 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
524 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
525 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
529 XVECTOR_DATA(table)[code - byte_offset] = value;
532 else if (EQ (table, value))
536 table = make_vector (ccs_len, table);
537 XVECTOR_DATA(table)[code - byte_offset] = value;
543 decoding_table_put_char (Lisp_Object ccs,
544 int code_point, Lisp_Object character);
546 decoding_table_put_char (Lisp_Object ccs,
547 int code_point, Lisp_Object character)
550 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
551 int dim = XCHARSET_DIMENSION (ccs);
554 XCHARSET_DECODING_TABLE (ccs)
555 = put_ccs_octet_table (table1, ccs, code_point, character);
559 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
561 table2 = put_ccs_octet_table (table2, ccs,
562 (unsigned char)code_point, character);
563 XCHARSET_DECODING_TABLE (ccs)
564 = put_ccs_octet_table (table1, ccs,
565 (unsigned char)(code_point >> 8), table2);
570 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
572 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
574 table3 = put_ccs_octet_table (table3, ccs,
575 (unsigned char)code_point, character);
576 table2 = put_ccs_octet_table (table2, ccs,
577 (unsigned char)(code_point >> 8), table3);
578 XCHARSET_DECODING_TABLE (ccs)
579 = put_ccs_octet_table (table1, ccs,
580 (unsigned char)(code_point >> 16), table2);
582 else /* if (dim == 4) */
585 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
587 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
589 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
591 table4 = put_ccs_octet_table (table4, ccs,
592 (unsigned char)code_point, character);
593 table3 = put_ccs_octet_table (table3, ccs,
594 (unsigned char)(code_point >> 8), table4);
595 table2 = put_ccs_octet_table (table2, ccs,
596 (unsigned char)(code_point >> 16), table3);
597 XCHARSET_DECODING_TABLE (ccs)
598 = put_ccs_octet_table (table1, ccs,
599 (unsigned char)(code_point >> 24), table2);
602 Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
603 int dim = XCHARSET_DIMENSION (ccs);
604 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
607 int ccs_len = XVECTOR_LENGTH (v);
612 i = ((code_point >> (8 * dim)) & 255) - byte_offset;
613 nv = XVECTOR_DATA(v)[i];
618 if (EQ (nv, character))
621 nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
628 XVECTOR_DATA(v)[i] = character;
633 decoding_table_remove_char (Lisp_Object ccs, int code_point);
635 decoding_table_remove_char (Lisp_Object ccs, int code_point)
637 decoding_table_put_char (ccs, code_point, Qunbound);
641 Emchar load_char_decoding_entry_maybe (Lisp_Object ccs, int code_point);
644 Emchar decode_defined_char (Lisp_Object charset, int code_point);
646 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
648 DECODE_CHAR (Lisp_Object charset, int code_point)
650 Emchar char_id = decode_defined_char (charset, code_point);
655 return decode_builtin_char (charset, code_point);
658 /* Return a character whose charset is CHARSET and position-codes
659 are C1 and C2. TYPE9N character ignores C2. */
661 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
663 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
665 if (XCHARSET_DIMENSION (charset) == 1)
666 return DECODE_CHAR (charset, c1);
668 return DECODE_CHAR (charset, (c1 << 8) | c2);
671 extern Lisp_Object Vcharacter_attribute_table;
673 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
674 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
675 int range_charset_code_point (Lisp_Object charset, Emchar ch);
677 extern Lisp_Object Vdefault_coded_charset_priority_list;
678 EXFUN (Ffind_charset, 1);
680 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
682 encode_char_1 (Emchar ch, Lisp_Object* charset)
684 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
686 while (!NILP (charsets))
688 *charset = Ffind_charset (Fcar (charsets));
689 if (!NILP (*charset))
691 int code_point = charset_code_point (*charset, ch, 0);
696 charsets = Fcdr (charsets);
699 /* otherwise --- maybe for bootstrap */
700 return encode_builtin_char_1 (ch, charset);
703 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
706 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
708 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
710 int code_point = encode_char_1 (c, charset);
714 int dim = XCHARSET_DIMENSION (*charset);
721 else /* if (dim == 2) */
723 *c1 = code_point >> 8;
724 *c2 = code_point & 255;
732 #define BREAKUP_CHAR(ch, charset, b1, b2) \
733 breakup_char_1 (ch, &(charset), &(b1), &(b2))
735 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
736 INLINE_HEADER Lisp_Object
737 CHAR_CHARSET (Emchar ch)
741 ENCODE_CHAR (ch, charset);
745 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
746 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
755 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
757 CHAR_TO_CHARC (Emchar ch)
761 cc.code_point = encode_char_1 (ch, &cc.charset);
765 #endif /* INCLUDED_char_ucs_h_ */