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 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;
62 #define MIN_LEADING_BYTE -0x200
65 #define LEADING_BYTE_UCS (MIN_LEADING_BYTE + 1)
67 /* represent normal 80-9F */
68 #define LEADING_BYTE_CONTROL_1 (MIN_LEADING_BYTE + 2)
70 /* ISO/IEC 10646 BMP */
71 #define LEADING_BYTE_UCS_BMP (MIN_LEADING_BYTE + 3)
73 /* ISO/IEC 10646 SMP */
74 #define LEADING_BYTE_UCS_SMP (MIN_LEADING_BYTE + 4)
76 /* ISO/IEC 10646 SIP */
77 #define LEADING_BYTE_UCS_SIP (MIN_LEADING_BYTE + 5)
79 /* ISO/IEC 10646 for GB */
80 #define LEADING_BYTE_UCS_GB (MIN_LEADING_BYTE + 6)
82 /* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
83 #define LEADING_BYTE_JIS_X0208 (MIN_LEADING_BYTE + 11)
85 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
86 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (MIN_LEADING_BYTE + 12)
88 /* Chinese GB 12345-1990 */
89 #define LEADING_BYTE_CHINESE_GB12345 (MIN_LEADING_BYTE + 13)
91 #define LEADING_BYTE_CHINESE_BIG5 (MIN_LEADING_BYTE + 20)
93 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
94 #define LEADING_BYTE_CHINESE_BIG5_1 (MIN_LEADING_BYTE + 21)
96 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
97 #define LEADING_BYTE_CHINESE_BIG5_2 (MIN_LEADING_BYTE + 22)
100 #define LEADING_BYTE_LATIN_VISCII (MIN_LEADING_BYTE + 24)
102 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
103 #define LEADING_BYTE_LATIN_VISCII_LOWER (MIN_LEADING_BYTE + 25)
105 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
106 #define LEADING_BYTE_LATIN_VISCII_UPPER (MIN_LEADING_BYTE + 26)
108 #define LEADING_BYTE_ETHIOPIC_UCS (MIN_LEADING_BYTE + 27)
110 #define MIN_LEADING_BYTE_PRIVATE (MIN_LEADING_BYTE + 97)
111 #define MAX_LEADING_BYTE_PRIVATE -1
115 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
117 /* Right half of JIS X0201-1976 */
118 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
120 /* Left half of JIS X0201-1976 */
121 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
124 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
126 /* Right half of ISO 8859-1 */
127 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
129 /* Right half of ISO 8859-2 */
130 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
132 /* Right half of ISO 8859-3 */
133 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
135 /* Right half of ISO 8859-4 */
136 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
138 /* Right half of ISO 8859-7 */
139 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
141 /* Right half of ISO 8859-6 */
142 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
144 /* Right half of ISO 8859-8 */
145 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
147 /* Right half of ISO 8859-5 */
148 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
150 /* Right half of ISO 8859-9 */
151 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
154 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
156 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
157 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
160 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
162 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
163 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
165 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
166 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
168 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
169 #define LEADING_BYTE_CHINESE_GB2312 58
171 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
172 #define LEADING_BYTE_JAPANESE_JISX0208 87
174 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
175 #define LEADING_BYTE_KOREAN_KSC5601 149
177 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
178 #define LEADING_BYTE_JAPANESE_JISX0212 159
180 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
181 #define LEADING_BYTE_CHINESE_CCITT_GB 165
183 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
184 #define LEADING_BYTE_CHINESE_CNS11643_1 171
186 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
187 #define LEADING_BYTE_CHINESE_CNS11643_2 172
189 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
190 #define LEADING_BYTE_CHINESE_CNS11643_3 183
192 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
193 #define LEADING_BYTE_CHINESE_CNS11643_4 184
195 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
196 #define LEADING_BYTE_CHINESE_CNS11643_5 185
198 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
199 #define LEADING_BYTE_CHINESE_CNS11643_6 186
201 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
202 #define LEADING_BYTE_CHINESE_CNS11643_7 187
204 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
205 #define LEADING_BYTE_KOREAN_KPS9566 202
208 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
211 /************************************************************************/
212 /* Information about a particular character set */
213 /************************************************************************/
217 struct lcrecord_header header;
221 Lisp_Object doc_string;
222 Lisp_Object registry;
223 Lisp_Object short_name;
224 Lisp_Object long_name;
226 Lisp_Object reverse_direction_charset;
228 Lisp_Object ccl_program;
230 /* Final byte of this character set in ISO2022 designating escape sequence */
233 /* Number of columns a character in this charset takes up, on TTY
234 devices. Not used for X devices. */
235 unsigned int columns;
237 /* Direction of this character set */
238 unsigned int direction;
240 /* Number of bytes used in encoding of this character set (1 .. 4) */
241 unsigned short dimension;
243 /* Number of chars in each dimension (94, 96, 128, 256) */
244 unsigned short chars;
246 /* Which half of font to be used to display this character set */
247 unsigned int graphic;
249 /* Code-point->character mapping table */
250 Lisp_Object decoding_table;
255 /* Range of character code */
256 int min_code, max_code;
258 /* Offset for external code */
261 /* Type of conversion from mother CCS */
262 unsigned char conversion;
264 /* Offset for each byte */
267 typedef struct Lisp_Charset Lisp_Charset;
269 DECLARE_LRECORD (charset, Lisp_Charset);
270 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
271 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
272 #define CHARSETP(x) RECORDP (x, charset)
273 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
274 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
276 #define CHARSET_LEFT_TO_RIGHT 0
277 #define CHARSET_RIGHT_TO_LEFT 1
279 /* Leading byte and id have been regrouped. -- OG */
280 #define CHARSET_ID(cs) ((cs)->id)
281 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
282 #define CHARSET_NAME(cs) ((cs)->name)
283 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
284 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
285 #define CHARSET_COLUMNS(cs) ((cs)->columns)
286 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
287 #define CHARSET_DIRECTION(cs) ((cs)->direction)
288 #define CHARSET_FINAL(cs) ((cs)->final)
289 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
290 #define CHARSET_REGISTRY(cs) ((cs)->registry)
291 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
292 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
293 #define CHARSET_CHARS(cs) ((cs)->chars)
294 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
295 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
296 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
297 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
298 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
299 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
300 #define CHARSET_MOTHER(cs) ((cs)->mother)
301 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
303 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
305 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
307 /* ad-hoc method for `ascii' */
308 if ((CHARSET_CHARS (cs) == 94) &&
309 (CHARSET_BYTE_OFFSET (cs) != 33))
310 return 128 - CHARSET_BYTE_OFFSET (cs);
312 return CHARSET_CHARS (cs);
315 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
316 INLINE_HEADER Lisp_Object
317 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
319 return Fgethash (CHARSET_NAME(cs),
320 Vchar_attribute_hash_table,
324 #define CONVERSION_IDENTICAL 0
325 #define CONVERSION_94 1
326 #define CONVERSION_96 2
327 #define CONVERSION_94x60 3
328 #define CONVERSION_94x94 4
329 #define CONVERSION_96x96 5
330 #define CONVERSION_94x94x60 6
331 #define CONVERSION_94x94x94 7
332 #define CONVERSION_96x96x96 8
333 #define CONVERSION_94x94x94x60 9
334 #define CONVERSION_94x94x94x94 10
335 #define CONVERSION_96x96x96x96 11
337 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
338 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
339 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
340 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
341 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
342 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
343 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
344 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
345 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
346 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
347 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
348 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
349 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
350 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
351 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
352 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
353 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
354 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
355 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
356 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
357 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
358 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
359 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
360 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
362 struct charset_lookup {
363 /* Table of charsets indexed by (leading byte - 128). */
364 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
366 /* Table of charsets indexed by type/final-byte/direction. */
367 Lisp_Object charset_by_attributes[4][128];
369 Charset_ID next_allocated_leading_byte;
372 extern struct charset_lookup *chlook;
374 #ifdef ERROR_CHECK_TYPECHECK
375 /* int not Bufbyte even though that is the actual type of a leading byte.
376 This way, out-ot-range values will get caught rather than automatically
378 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
379 INLINE_HEADER Lisp_Object
380 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
382 assert (lb >= MIN_LEADING_BYTE &&
383 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
384 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
389 #define CHARSET_BY_LEADING_BYTE(lb) \
390 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
394 INLINE_HEADER Lisp_Object
395 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
396 INLINE_HEADER Lisp_Object
397 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
403 else if (chars == 96)
407 type += dimension == 1 ? 0 : 2;
408 return chlook->charset_by_attributes[type][final];
412 /************************************************************************/
413 /* Dealing with characters */
414 /************************************************************************/
416 #define MAX_CHAR_BASIC_LATIN 0x007F
419 #define MIN_CHAR_HEBREW 0x0590
420 #define MAX_CHAR_HEBREW 0x05EF
423 #define MIN_CHAR_THAI 0x0E00
424 #define MAX_CHAR_THAI 0x0E5F
427 #define MIN_CHAR_HIRAGANA 0x3041
428 #define MAX_CHAR_HIRAGANA 0x3093
430 #define MIN_CHAR_KATAKANA 0x30A1
431 #define MAX_CHAR_KATAKANA 0x30F6
434 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
435 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
437 #define MAX_CHAR_BMP 0x00FFFF
439 #define MIN_CHAR_SMP 0x010000
440 #define MAX_CHAR_SMP 0x01FFFF
442 #define MIN_CHAR_SIP 0x020000
443 #define MAX_CHAR_SIP 0x02FFFF
446 #define MIN_CHAR_DAIKANWA 0x00E00000
447 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
449 #define MIN_CHAR_CBETA 0x00E20000
450 #define MAX_CHAR_CBETA 0x00E2FFFF
452 #define MIN_CHAR_CHINA3_JEF 0x00E80000
453 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
456 #define MIN_CHAR_94 0x00E90940
457 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
458 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
459 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
461 #define MIN_CHAR_94x94 0xE9F6C0
462 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
463 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
464 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
465 #define MIN_CHAR_96x96 0xF4C000
466 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
469 #define MIN_CHAR_GT 0x61000000
470 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
472 #define MIN_CHAR_BIG5_CDP 0x62000000
473 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
475 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
476 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
477 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
478 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
479 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
480 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
481 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
482 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
483 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
484 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
485 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
486 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
487 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
488 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
489 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
490 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
491 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
492 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
493 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
494 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
495 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
496 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
497 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
498 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
501 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
503 INLINE_HEADER Lisp_Object
504 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
505 INLINE_HEADER Lisp_Object
506 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
508 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
512 int idx = code - byte_offset;
514 if (idx < XVECTOR_LENGTH(table))
515 return XVECTOR_DATA(table)[idx];
523 INLINE_HEADER Lisp_Object
524 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
526 INLINE_HEADER Lisp_Object
527 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
530 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
531 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
535 XVECTOR_DATA(table)[code - byte_offset] = value;
538 else if (EQ (table, value))
542 table = make_vector (ccs_len, table);
543 XVECTOR_DATA(table)[code - byte_offset] = value;
549 decoding_table_put_char (Lisp_Object ccs,
550 int code_point, Lisp_Object character);
552 decoding_table_put_char (Lisp_Object ccs,
553 int code_point, Lisp_Object character)
555 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
556 int dim = XCHARSET_DIMENSION (ccs);
559 XCHARSET_DECODING_TABLE (ccs)
560 = put_ccs_octet_table (table1, ccs, code_point, character);
564 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
566 table2 = put_ccs_octet_table (table2, ccs,
567 (unsigned char)code_point, character);
568 XCHARSET_DECODING_TABLE (ccs)
569 = put_ccs_octet_table (table1, ccs,
570 (unsigned char)(code_point >> 8), table2);
575 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
577 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
579 table3 = put_ccs_octet_table (table3, ccs,
580 (unsigned char)code_point, character);
581 table2 = put_ccs_octet_table (table2, ccs,
582 (unsigned char)(code_point >> 8), table3);
583 XCHARSET_DECODING_TABLE (ccs)
584 = put_ccs_octet_table (table1, ccs,
585 (unsigned char)(code_point >> 16), table2);
587 else /* if (dim == 4) */
590 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
592 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
594 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
596 table4 = put_ccs_octet_table (table4, ccs,
597 (unsigned char)code_point, character);
598 table3 = put_ccs_octet_table (table3, ccs,
599 (unsigned char)(code_point >> 8), table4);
600 table2 = put_ccs_octet_table (table2, ccs,
601 (unsigned char)(code_point >> 16), table3);
602 XCHARSET_DECODING_TABLE (ccs)
603 = put_ccs_octet_table (table1, ccs,
604 (unsigned char)(code_point >> 24), table2);
609 decoding_table_remove_char (Lisp_Object ccs, int code_point);
611 decoding_table_remove_char (Lisp_Object ccs, int code_point)
613 decoding_table_put_char (ccs, code_point, Qunbound);
616 Emchar decode_defined_char (Lisp_Object charset, int code_point);
618 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
620 DECODE_CHAR (Lisp_Object charset, int code_point)
622 Emchar char_id = decode_defined_char (charset, code_point);
626 else if (XCHARSET_DIMENSION (charset) == 1)
627 return decode_builtin_char (charset, code_point);
628 else if (EQ (charset, Vcharset_chinese_big5_1))
631 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
632 + ((code_point & 0xFF) - 33);
633 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
634 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
636 b2 += b2 < 0x3F ? 0x40 : 0x62;
637 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
639 else if (EQ (charset, Vcharset_chinese_big5_2))
642 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
643 + ((code_point & 0xFF) - 33);
644 unsigned char b1, b2;
646 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
647 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
648 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
649 b2 += b2 < 0x3F ? 0x40 : 0x62;
650 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
652 return decode_builtin_char (charset, code_point);
655 /* Return a character whose charset is CHARSET and position-codes
656 are C1 and C2. TYPE9N character ignores C2. */
658 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
660 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
662 if (XCHARSET_DIMENSION (charset) == 1)
663 return DECODE_CHAR (charset, c1);
665 return DECODE_CHAR (charset, (c1 << 8) | c2);
668 extern Lisp_Object Vcharacter_attribute_table;
670 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
671 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
672 int range_charset_code_point (Lisp_Object charset, Emchar ch);
674 extern Lisp_Object Vdefault_coded_charset_priority_list;
675 EXFUN (Ffind_charset, 1);
677 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
679 encode_char_1 (Emchar ch, Lisp_Object* charset)
681 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
683 while (!NILP (charsets))
685 *charset = Ffind_charset (Fcar (charsets));
686 if (!NILP (*charset))
688 int code_point = charset_code_point (*charset, ch, 0);
693 charsets = Fcdr (charsets);
696 /* otherwise --- maybe for bootstrap */
697 return encode_builtin_char_1 (ch, charset);
700 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
703 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
705 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
707 int code_point = encode_char_1 (c, charset);
711 int dim = XCHARSET_DIMENSION (*charset);
718 else /* if (dim == 2) */
720 *c1 = code_point >> 8;
721 *c2 = code_point & 255;
729 #define BREAKUP_CHAR(ch, charset, b1, b2) \
730 breakup_char_1 (ch, &(charset), &(b1), &(b2))
732 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
733 INLINE_HEADER Lisp_Object
734 CHAR_CHARSET (Emchar ch)
738 ENCODE_CHAR (ch, charset);
742 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
743 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
752 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
754 CHAR_TO_CHARC (Emchar ch)
758 cc.code_point = encode_char_1 (ch, &cc.charset);
762 #endif /* INCLUDED_char_ucs_h_ */