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 extern Lisp_Object Vchar_attribute_hash_table;
29 #define valid_char_p(ch) 1
31 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
34 /************************************************************************/
35 /* Exported functions */
36 /************************************************************************/
38 extern Lisp_Object Vcharset_ucs;
39 extern Lisp_Object Vcharset_latin_jisx0201;
40 extern Lisp_Object Vcharset_chinese_big5;
41 extern Lisp_Object Vcharset_chinese_big5_1;
42 extern Lisp_Object Vcharset_chinese_big5_2;
43 extern Lisp_Object Vcharset_japanese_jisx0208;
44 extern Lisp_Object Vcharset_japanese_jisx0208_1990;
45 extern Lisp_Object Vcharset_japanese_jisx0212;
47 EXFUN (Fget_charset, 1);
49 extern Lisp_Object Qmap_ucs, Qucs;
51 Lisp_Object put_char_ccs_code_point (Lisp_Object character,
52 Lisp_Object ccs, Lisp_Object value);
53 Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
56 /************************************************************************/
57 /* Definition of leading bytes */
58 /************************************************************************/
60 typedef short Charset_ID;
63 #define LEADING_BYTE_UCS -177
65 /* represent normal 80-9F */
66 #define LEADING_BYTE_CONTROL_1 -77
68 /* ISO/IEC 10646 BMP */
69 #define LEADING_BYTE_UCS_BMP -176
71 /* ISO/IEC 10646 SMP */
72 #define LEADING_BYTE_UCS_SMP 1
74 /* ISO/IEC 10646 SIP */
75 #define LEADING_BYTE_UCS_SIP 2
77 /* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
78 #define LEADING_BYTE_JIS_X0208 3
80 /* Chinese GB 12345-1990 */
81 #define LEADING_BYTE_CHINESE_GB12345 4
83 #define LEADING_BYTE_CHINESE_BIG5 5
85 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
86 #define LEADING_BYTE_CHINESE_BIG5_1 6
88 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
89 #define LEADING_BYTE_CHINESE_BIG5_2 7
92 #define LEADING_BYTE_LATIN_VISCII 8
94 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
95 #define LEADING_BYTE_LATIN_VISCII_LOWER 9
97 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
98 #define LEADING_BYTE_LATIN_VISCII_UPPER 10
100 #define LEADING_BYTE_ETHIOPIC_UCS 11
102 #define MIN_LEADING_BYTE_PRIVATE 12
103 #define MAX_LEADING_BYTE_PRIVATE 512
107 #define LEADING_BYTE_ASCII -6 /* (CHARSET_ID_OFFSET_94 + 'B') */
109 /* Right half of JIS X0201-1976 */
110 #define LEADING_BYTE_KATAKANA_JISX0201 -13 /* (CHARSET_ID_OFFSET_94 + 'I') */
112 /* Left half of JIS X0201-1976 */
113 #define LEADING_BYTE_LATIN_JISX0201 -14 /* (CHARSET_ID_OFFSET_94 + 'J') */
116 /* Right half of ISO 8859-1 */
117 #define LEADING_BYTE_LATIN_ISO8859_1 -100 /* (CHARSET_ID_OFFSET_96 + 'A') */
119 /* Right half of ISO 8859-2 */
120 #define LEADING_BYTE_LATIN_ISO8859_2 -101 /* (CHARSET_ID_OFFSET_96 + 'B') */
122 /* Right half of ISO 8859-3 */
123 #define LEADING_BYTE_LATIN_ISO8859_3 -109 /* (CHARSET_ID_OFFSET_96 + 'C') */
125 /* Right half of ISO 8859-4 */
126 #define LEADING_BYTE_LATIN_ISO8859_4 -110 /* (CHARSET_ID_OFFSET_96 + 'D') */
128 /* Right half of ISO 8859-7 */
129 #define LEADING_BYTE_GREEK_ISO8859_7 -126 /* (CHARSET_ID_OFFSET_96 + 'F') */
131 /* Right half of ISO 8859-6 */
132 #define LEADING_BYTE_ARABIC_ISO8859_6 -127 /* (CHARSET_ID_OFFSET_96 + 'G') */
134 /* Right half of ISO 8859-8 */
135 #define LEADING_BYTE_HEBREW_ISO8859_8 -138 /* (CHARSET_ID_OFFSET_96 + 'H') */
137 /* Right half of ISO 8859-5 */
138 #define LEADING_BYTE_CYRILLIC_ISO8859_5 -144 /* (CHARSET_ID_OFFSET_96 + 'L') */
140 /* Right half of ISO 8859-9 */
141 #define LEADING_BYTE_LATIN_ISO8859_9 -148 /* (CHARSET_ID_OFFSET_96 + 'M') */
144 #define LEADING_BYTE_THAI_TIS620 -166 /* (CHARSET_ID_OFFSET_96 + 'T') */
146 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
147 #define LEADING_BYTE_LATIN_TCVN5712 -180 /* F = 5/10 0x5A `Z' */
150 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
151 #define LEADING_BYTE_JAPANESE_JISX0208_1978 -42
153 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
154 #define LEADING_BYTE_CHINESE_GB2312 -58
156 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
157 #define LEADING_BYTE_JAPANESE_JISX0208 -87
159 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
160 #define LEADING_BYTE_JAPANESE_JISX0208_1990 -168
162 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
163 #define LEADING_BYTE_KOREAN_KSC5601 -149
165 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
166 #define LEADING_BYTE_JAPANESE_JISX0212 -159
168 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
169 #define LEADING_BYTE_CHINESE_CCITT_GB -165
171 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
172 #define LEADING_BYTE_CHINESE_CNS11643_1 -171
174 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
175 #define LEADING_BYTE_CHINESE_CNS11643_2 -172
177 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
178 #define LEADING_BYTE_CHINESE_CNS11643_3 -183
180 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
181 #define LEADING_BYTE_CHINESE_CNS11643_4 -184
183 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
184 #define LEADING_BYTE_CHINESE_CNS11643_5 -185
186 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
187 #define LEADING_BYTE_CHINESE_CNS11643_6 -186
189 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
190 #define LEADING_BYTE_CHINESE_CNS11643_7 -187
192 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
193 #define LEADING_BYTE_KOREAN_KPS9566 -202
196 #define MIN_LEADING_BYTE (- 80 * 3)
198 #define NUM_LEADING_BYTES (MAX_LEADING_BYTE_PRIVATE - MIN_LEADING_BYTE)
201 /************************************************************************/
202 /* Information about a particular character set */
203 /************************************************************************/
207 struct lcrecord_header header;
211 Lisp_Object doc_string;
212 Lisp_Object registry;
213 Lisp_Object short_name;
214 Lisp_Object long_name;
216 Lisp_Object reverse_direction_charset;
218 Lisp_Object ccl_program;
220 /* Final byte of this character set in ISO2022 designating escape sequence */
223 /* Number of columns a character in this charset takes up, on TTY
224 devices. Not used for X devices. */
225 unsigned int columns;
227 /* Direction of this character set */
228 unsigned int direction;
230 /* Number of bytes used in encoding of this character set (1 .. 4) */
231 unsigned short dimension;
233 /* Number of chars in each dimension (94, 96, 128, 256) */
234 unsigned short chars;
236 /* Which half of font to be used to display this character set */
237 unsigned int graphic;
239 /* Code-point->character mapping table */
240 Lisp_Object decoding_table;
245 /* Range of character code */
246 int min_code, max_code;
248 /* Offset for external code */
251 /* Type of conversion from mother CCS */
252 unsigned char conversion;
254 /* Offset for each byte */
257 typedef struct Lisp_Charset Lisp_Charset;
259 DECLARE_LRECORD (charset, Lisp_Charset);
260 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
261 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
262 #define CHARSETP(x) RECORDP (x, charset)
263 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
264 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
266 #define CHARSET_LEFT_TO_RIGHT 0
267 #define CHARSET_RIGHT_TO_LEFT 1
269 /* Leading byte and id have been regrouped. -- OG */
270 #define CHARSET_ID(cs) ((cs)->id)
271 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
272 #define CHARSET_NAME(cs) ((cs)->name)
273 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
274 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
275 #define CHARSET_COLUMNS(cs) ((cs)->columns)
276 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
277 #define CHARSET_DIRECTION(cs) ((cs)->direction)
278 #define CHARSET_FINAL(cs) ((cs)->final)
279 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
280 #define CHARSET_REGISTRY(cs) ((cs)->registry)
281 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
282 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
283 #define CHARSET_CHARS(cs) ((cs)->chars)
284 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
285 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
286 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
287 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
288 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
289 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
290 #define CHARSET_MOTHER(cs) ((cs)->mother)
291 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
293 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
295 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
297 /* ad-hoc method for `ascii' */
298 if ((CHARSET_CHARS (cs) == 94) &&
299 (CHARSET_BYTE_OFFSET (cs) != 33))
300 return 128 - CHARSET_BYTE_OFFSET (cs);
302 return CHARSET_CHARS (cs);
305 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
306 INLINE_HEADER Lisp_Object
307 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
309 return Fgethash (CHARSET_NAME(cs),
310 Vchar_attribute_hash_table,
314 #define CONVERSION_IDENTICAL 0
315 #define CONVERSION_94 1
316 #define CONVERSION_96 2
317 #define CONVERSION_94x60 3
318 #define CONVERSION_94x94 4
319 #define CONVERSION_96x96 5
320 #define CONVERSION_94x94x60 6
321 #define CONVERSION_94x94x94 7
322 #define CONVERSION_96x96x96 8
323 #define CONVERSION_94x94x94x60 9
324 #define CONVERSION_94x94x94x94 10
325 #define CONVERSION_96x96x96x96 11
327 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
328 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
329 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
330 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
331 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
332 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
333 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
334 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
335 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
336 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
337 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
338 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
339 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
340 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
341 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
342 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
343 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
344 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
345 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
346 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
347 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
348 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
349 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
350 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
352 struct charset_lookup {
353 /* Table of charsets indexed by (leading byte - 128). */
354 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
356 /* Table of charsets indexed by type/final-byte/direction. */
357 Lisp_Object charset_by_attributes[4][128];
359 Charset_ID next_allocated_leading_byte;
362 extern struct charset_lookup *chlook;
364 #ifdef ERROR_CHECK_TYPECHECK
365 /* int not Bufbyte even though that is the actual type of a leading byte.
366 This way, out-ot-range values will get caught rather than automatically
368 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
369 INLINE_HEADER Lisp_Object
370 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
372 assert (lb >= MIN_LEADING_BYTE &&
373 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
374 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
379 #define CHARSET_BY_LEADING_BYTE(lb) \
380 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
384 INLINE_HEADER Lisp_Object
385 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
386 INLINE_HEADER Lisp_Object
387 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
393 else if (chars == 96)
397 type += dimension == 1 ? 0 : 2;
398 return chlook->charset_by_attributes[type][final];
402 /************************************************************************/
403 /* Dealing with characters */
404 /************************************************************************/
406 #define MAX_CHAR_BASIC_LATIN 0x007F
409 #define MIN_CHAR_HEBREW 0x0590
410 #define MAX_CHAR_HEBREW 0x05EF
413 #define MIN_CHAR_THAI 0x0E00
414 #define MAX_CHAR_THAI 0x0E5F
417 #define MIN_CHAR_HIRAGANA 0x3041
418 #define MAX_CHAR_HIRAGANA 0x3093
420 #define MIN_CHAR_KATAKANA 0x30A1
421 #define MAX_CHAR_KATAKANA 0x30F6
424 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
425 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
427 #define MAX_CHAR_BMP 0x00FFFF
429 #define MIN_CHAR_SMP 0x010000
430 #define MAX_CHAR_SMP 0x01FFFF
432 #define MIN_CHAR_SIP 0x020000
433 #define MAX_CHAR_SIP 0x02FFFF
436 #define MIN_CHAR_DAIKANWA 0x00E00000
437 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
439 #define MIN_CHAR_CBETA 0x00E20000
440 #define MAX_CHAR_CBETA 0x00E2FFFF
442 #define MIN_CHAR_CHINA3_JEF 0x00E80000
443 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
446 #define MIN_CHAR_94 0x00E90940
447 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
448 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
449 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
451 #define MIN_CHAR_94x94 0xE9F6C0
452 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
453 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
454 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
455 #define MIN_CHAR_96x96 0xF4C000
456 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
459 #define MIN_CHAR_GT 0x61000000
460 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
462 #define MIN_CHAR_BIG5_CDP 0x62000000
463 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
465 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
466 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
467 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
468 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
469 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
470 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
471 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
472 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
473 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
474 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
475 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
476 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
477 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
478 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
479 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
480 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
481 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
482 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
483 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
484 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
485 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
486 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
487 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
488 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
491 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
493 INLINE_HEADER Lisp_Object
494 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
495 INLINE_HEADER Lisp_Object
496 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
498 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
502 int idx = code - byte_offset;
504 if (idx < XVECTOR_LENGTH(table))
505 return XVECTOR_DATA(table)[idx];
513 INLINE_HEADER Lisp_Object
514 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
516 INLINE_HEADER Lisp_Object
517 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
520 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
521 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
525 XVECTOR_DATA(table)[code - byte_offset] = value;
528 else if (EQ (table, value))
532 table = make_vector (ccs_len, table);
533 XVECTOR_DATA(table)[code - byte_offset] = value;
539 decoding_table_put_char (Lisp_Object ccs,
540 int code_point, Lisp_Object character);
542 decoding_table_put_char (Lisp_Object ccs,
543 int code_point, Lisp_Object character)
545 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
546 int dim = XCHARSET_DIMENSION (ccs);
549 XCHARSET_DECODING_TABLE (ccs)
550 = put_ccs_octet_table (table1, ccs, code_point, character);
554 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
556 table2 = put_ccs_octet_table (table2, ccs,
557 (unsigned char)code_point, character);
558 XCHARSET_DECODING_TABLE (ccs)
559 = put_ccs_octet_table (table1, ccs,
560 (unsigned char)(code_point >> 8), table2);
565 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
567 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
569 table3 = put_ccs_octet_table (table3, ccs,
570 (unsigned char)code_point, character);
571 table2 = put_ccs_octet_table (table2, ccs,
572 (unsigned char)(code_point >> 8), table3);
573 XCHARSET_DECODING_TABLE (ccs)
574 = put_ccs_octet_table (table1, ccs,
575 (unsigned char)(code_point >> 16), table2);
577 else /* if (dim == 4) */
580 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
582 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
584 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
586 table4 = put_ccs_octet_table (table4, ccs,
587 (unsigned char)code_point, character);
588 table3 = put_ccs_octet_table (table3, ccs,
589 (unsigned char)(code_point >> 8), table4);
590 table2 = put_ccs_octet_table (table2, ccs,
591 (unsigned char)(code_point >> 16), table3);
592 XCHARSET_DECODING_TABLE (ccs)
593 = put_ccs_octet_table (table1, ccs,
594 (unsigned char)(code_point >> 24), table2);
599 decoding_table_remove_char (Lisp_Object ccs, int code_point);
601 decoding_table_remove_char (Lisp_Object ccs, int code_point)
603 decoding_table_put_char (ccs, code_point, Qunbound);
606 Emchar decode_defined_char (Lisp_Object charset, int code_point);
608 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
610 DECODE_CHAR (Lisp_Object charset, int code_point)
612 Emchar char_id = decode_defined_char (charset, code_point);
616 else if (XCHARSET_DIMENSION (charset) == 1)
617 return decode_builtin_char (charset, code_point);
618 else if (EQ (charset, Vcharset_chinese_big5_1))
621 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
622 + ((code_point & 0xFF) - 33);
623 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
624 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
626 b2 += b2 < 0x3F ? 0x40 : 0x62;
627 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
629 else if (EQ (charset, Vcharset_chinese_big5_2))
632 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
633 + ((code_point & 0xFF) - 33);
634 unsigned char b1, b2;
636 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
637 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
638 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
639 b2 += b2 < 0x3F ? 0x40 : 0x62;
640 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
642 return decode_builtin_char (charset, code_point);
645 /* Return a character whose charset is CHARSET and position-codes
646 are C1 and C2. TYPE9N character ignores C2. */
648 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
650 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
652 if (XCHARSET_DIMENSION (charset) == 1)
653 return DECODE_CHAR (charset, c1);
655 return DECODE_CHAR (charset, (c1 << 8) | c2);
658 extern Lisp_Object Vcharacter_attribute_table;
660 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
661 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
662 int range_charset_code_point (Lisp_Object charset, Emchar ch);
664 extern Lisp_Object Vdefault_coded_charset_priority_list;
665 EXFUN (Ffind_charset, 1);
667 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
669 encode_char_1 (Emchar ch, Lisp_Object* charset)
671 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
673 while (!NILP (charsets))
675 *charset = Ffind_charset (Fcar (charsets));
676 if (!NILP (*charset))
678 int code_point = charset_code_point (*charset, ch, 0);
683 charsets = Fcdr (charsets);
686 /* otherwise --- maybe for bootstrap */
687 return encode_builtin_char_1 (ch, charset);
690 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
693 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
695 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
697 int code_point = encode_char_1 (c, charset);
701 int dim = XCHARSET_DIMENSION (*charset);
708 else /* if (dim == 2) */
710 *c1 = code_point >> 8;
711 *c2 = code_point & 255;
719 #define BREAKUP_CHAR(ch, charset, b1, b2) \
720 breakup_char_1 (ch, &(charset), &(b1), &(b2))
722 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
723 INLINE_HEADER Lisp_Object
724 CHAR_CHARSET (Emchar ch)
728 ENCODE_CHAR (ch, charset);
732 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
733 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
742 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
744 CHAR_TO_CHARC (Emchar ch)
748 cc.code_point = encode_char_1 (ch, &cc.charset);
752 #endif /* INCLUDED_char_ucs_h_ */