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 /* ISO/IEC 10646 for CNS */
83 #define LEADING_BYTE_UCS_CNS (MIN_LEADING_BYTE + 7)
85 /* ISO/IEC 10646 for JIS */
86 #define LEADING_BYTE_UCS_JIS (MIN_LEADING_BYTE + 8)
88 /* ISO/IEC 10646 for KS */
89 #define LEADING_BYTE_UCS_KS (MIN_LEADING_BYTE + 9)
91 /* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
92 #define LEADING_BYTE_JIS_X0208 (MIN_LEADING_BYTE + 11)
94 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
95 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (MIN_LEADING_BYTE + 12)
97 /* Chinese GB 12345-1990 */
98 #define LEADING_BYTE_CHINESE_GB12345 (MIN_LEADING_BYTE + 13)
100 #define LEADING_BYTE_CHINESE_BIG5 (MIN_LEADING_BYTE + 20)
102 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
103 #define LEADING_BYTE_CHINESE_BIG5_1 (MIN_LEADING_BYTE + 21)
105 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
106 #define LEADING_BYTE_CHINESE_BIG5_2 (MIN_LEADING_BYTE + 22)
109 #define LEADING_BYTE_LATIN_VISCII (MIN_LEADING_BYTE + 24)
111 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
112 #define LEADING_BYTE_LATIN_VISCII_LOWER (MIN_LEADING_BYTE + 25)
114 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
115 #define LEADING_BYTE_LATIN_VISCII_UPPER (MIN_LEADING_BYTE + 26)
117 #define LEADING_BYTE_ETHIOPIC_UCS (MIN_LEADING_BYTE + 27)
119 #define LEADING_BYTE_DAIKANWA_0 (MIN_LEADING_BYTE + 28)
120 #define LEADING_BYTE_DAIKANWA_1 (MIN_LEADING_BYTE + 29)
121 #define LEADING_BYTE_DAIKANWA_2 (MIN_LEADING_BYTE + 30)
123 #define MIN_LEADING_BYTE_PRIVATE (MIN_LEADING_BYTE + 97)
124 #define MAX_LEADING_BYTE_PRIVATE -1
128 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
130 /* Right half of JIS X0201-1976 */
131 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
133 /* Left half of JIS X0201-1976 */
134 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
137 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
139 /* Right half of ISO 8859-1 */
140 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
142 /* Right half of ISO 8859-2 */
143 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
145 /* Right half of ISO 8859-3 */
146 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
148 /* Right half of ISO 8859-4 */
149 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
151 /* Right half of ISO 8859-7 */
152 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
154 /* Right half of ISO 8859-6 */
155 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
157 /* Right half of ISO 8859-8 */
158 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
160 /* Right half of ISO 8859-5 */
161 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
163 /* Right half of ISO 8859-9 */
164 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
167 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
169 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
170 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
173 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
175 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
176 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
178 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
179 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
181 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
182 #define LEADING_BYTE_CHINESE_GB2312 58
184 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
185 #define LEADING_BYTE_JAPANESE_JISX0208 87
187 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
188 #define LEADING_BYTE_KOREAN_KSC5601 149
190 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
191 #define LEADING_BYTE_JAPANESE_JISX0212 159
193 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
194 #define LEADING_BYTE_CHINESE_CCITT_GB 165
196 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
197 #define LEADING_BYTE_CHINESE_CNS11643_1 171
199 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
200 #define LEADING_BYTE_CHINESE_CNS11643_2 172
202 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
203 #define LEADING_BYTE_CHINESE_CNS11643_3 183
205 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
206 #define LEADING_BYTE_CHINESE_CNS11643_4 184
208 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
209 #define LEADING_BYTE_CHINESE_CNS11643_5 185
211 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
212 #define LEADING_BYTE_CHINESE_CNS11643_6 186
214 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
215 #define LEADING_BYTE_CHINESE_CNS11643_7 187
217 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
218 #define LEADING_BYTE_KOREAN_KPS9566 202
221 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
224 /************************************************************************/
225 /* Information about a particular character set */
226 /************************************************************************/
230 struct lcrecord_header header;
234 Lisp_Object doc_string;
235 Lisp_Object registry;
236 Lisp_Object short_name;
237 Lisp_Object long_name;
239 Lisp_Object reverse_direction_charset;
241 Lisp_Object ccl_program;
243 /* Final byte of this character set in ISO2022 designating escape sequence */
246 /* Number of columns a character in this charset takes up, on TTY
247 devices. Not used for X devices. */
248 unsigned int columns;
250 /* Direction of this character set */
251 unsigned int direction;
253 /* Number of bytes used in encoding of this character set (1 .. 4) */
254 unsigned short dimension;
256 /* Number of chars in each dimension (94, 96, 128, 256) */
257 unsigned short chars;
259 /* Which half of font to be used to display this character set */
260 unsigned int graphic;
262 /* Code-point->character mapping table */
263 Lisp_Object decoding_table;
268 /* Range of character code */
269 int min_code, max_code;
271 /* Offset for external code */
274 /* Type of conversion from mother CCS */
275 unsigned char conversion;
277 /* Offset for each byte */
280 typedef struct Lisp_Charset Lisp_Charset;
282 DECLARE_LRECORD (charset, Lisp_Charset);
283 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
284 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
285 #define CHARSETP(x) RECORDP (x, charset)
286 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
287 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
289 #define CHARSET_LEFT_TO_RIGHT 0
290 #define CHARSET_RIGHT_TO_LEFT 1
292 /* Leading byte and id have been regrouped. -- OG */
293 #define CHARSET_ID(cs) ((cs)->id)
294 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
295 #define CHARSET_NAME(cs) ((cs)->name)
296 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
297 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
298 #define CHARSET_COLUMNS(cs) ((cs)->columns)
299 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
300 #define CHARSET_DIRECTION(cs) ((cs)->direction)
301 #define CHARSET_FINAL(cs) ((cs)->final)
302 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
303 #define CHARSET_REGISTRY(cs) ((cs)->registry)
304 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
305 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
306 #define CHARSET_CHARS(cs) ((cs)->chars)
307 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
308 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
309 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
310 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
311 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
312 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
313 #define CHARSET_MOTHER(cs) ((cs)->mother)
314 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
316 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
318 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
320 /* ad-hoc method for `ascii' */
321 if ((CHARSET_CHARS (cs) == 94) &&
322 (CHARSET_BYTE_OFFSET (cs) != 33))
323 return 128 - CHARSET_BYTE_OFFSET (cs);
325 return CHARSET_CHARS (cs);
328 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
329 INLINE_HEADER Lisp_Object
330 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
332 return Fgethash (CHARSET_NAME(cs),
333 Vchar_attribute_hash_table,
337 #define CONVERSION_IDENTICAL 0
338 #define CONVERSION_94 1
339 #define CONVERSION_96 2
340 #define CONVERSION_94x60 3
341 #define CONVERSION_94x94 4
342 #define CONVERSION_96x96 5
343 #define CONVERSION_94x94x60 6
344 #define CONVERSION_94x94x94 7
345 #define CONVERSION_96x96x96 8
346 #define CONVERSION_94x94x94x60 9
347 #define CONVERSION_94x94x94x94 10
348 #define CONVERSION_96x96x96x96 11
350 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
351 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
352 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
353 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
354 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
355 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
356 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
357 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
358 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
359 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
360 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
361 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
362 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
363 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
364 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
365 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
366 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
367 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
368 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
369 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
370 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
371 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
372 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
373 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
375 struct charset_lookup {
376 /* Table of charsets indexed by (leading byte - 128). */
377 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
379 /* Table of charsets indexed by type/final-byte/direction. */
380 Lisp_Object charset_by_attributes[4][128];
382 Charset_ID next_allocated_leading_byte;
385 extern struct charset_lookup *chlook;
387 #ifdef ERROR_CHECK_TYPECHECK
388 /* int not Bufbyte even though that is the actual type of a leading byte.
389 This way, out-ot-range values will get caught rather than automatically
391 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
392 INLINE_HEADER Lisp_Object
393 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
395 assert (lb >= MIN_LEADING_BYTE &&
396 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
397 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
402 #define CHARSET_BY_LEADING_BYTE(lb) \
403 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
407 INLINE_HEADER Lisp_Object
408 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
409 INLINE_HEADER Lisp_Object
410 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
416 else if (chars == 96)
420 type += dimension == 1 ? 0 : 2;
421 return chlook->charset_by_attributes[type][final];
425 /************************************************************************/
426 /* Dealing with characters */
427 /************************************************************************/
429 #define MAX_CHAR_BASIC_LATIN 0x007F
432 #define MIN_CHAR_HEBREW 0x0590
433 #define MAX_CHAR_HEBREW 0x05EF
436 #define MIN_CHAR_THAI 0x0E00
437 #define MAX_CHAR_THAI 0x0E5F
440 #define MIN_CHAR_HIRAGANA 0x3041
441 #define MAX_CHAR_HIRAGANA 0x3093
443 #define MIN_CHAR_KATAKANA 0x30A1
444 #define MAX_CHAR_KATAKANA 0x30F6
447 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
448 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
450 #define MAX_CHAR_BMP 0x00FFFF
452 #define MIN_CHAR_SMP 0x010000
453 #define MAX_CHAR_SMP 0x01FFFF
455 #define MIN_CHAR_SIP 0x020000
456 #define MAX_CHAR_SIP 0x02FFFF
458 #define MIN_CHAR_DAIKANWA 0x00E00000
459 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
461 #define MIN_CHAR_CBETA 0x00E20000
462 #define MAX_CHAR_CBETA 0x00E2FFFF
464 #define MIN_CHAR_CHINA3_JEF 0x00E80000
465 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
468 #define MIN_CHAR_94 0x00E90940
469 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
470 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
471 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
473 #define MIN_CHAR_94x94 0xE9F6C0
474 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
475 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
476 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
477 #define MIN_CHAR_96x96 0xF4C000
478 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
481 #define MIN_CHAR_GT 0x61000000
482 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
484 #define MIN_CHAR_BIG5_CDP 0x62000000
485 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
487 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
488 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
489 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
490 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
491 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
492 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
493 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
494 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
495 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
496 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
497 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
498 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
499 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
500 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
501 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
502 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
503 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
504 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
505 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
506 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
507 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
508 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
509 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
510 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
513 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
515 INLINE_HEADER Lisp_Object
516 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
517 INLINE_HEADER Lisp_Object
518 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
520 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
524 int idx = code - byte_offset;
526 if (idx < XVECTOR_LENGTH(table))
527 return XVECTOR_DATA(table)[idx];
535 INLINE_HEADER Lisp_Object
536 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
538 INLINE_HEADER Lisp_Object
539 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
542 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
543 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
547 XVECTOR_DATA(table)[code - byte_offset] = value;
550 else if (EQ (table, value))
554 table = make_vector (ccs_len, table);
555 XVECTOR_DATA(table)[code - byte_offset] = value;
561 decoding_table_put_char (Lisp_Object ccs,
562 int code_point, Lisp_Object character);
564 decoding_table_put_char (Lisp_Object ccs,
565 int code_point, Lisp_Object character)
567 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
568 int dim = XCHARSET_DIMENSION (ccs);
571 XCHARSET_DECODING_TABLE (ccs)
572 = put_ccs_octet_table (table1, ccs, code_point, character);
576 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
578 table2 = put_ccs_octet_table (table2, ccs,
579 (unsigned char)code_point, character);
580 XCHARSET_DECODING_TABLE (ccs)
581 = put_ccs_octet_table (table1, ccs,
582 (unsigned char)(code_point >> 8), table2);
587 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
589 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
591 table3 = put_ccs_octet_table (table3, ccs,
592 (unsigned char)code_point, character);
593 table2 = put_ccs_octet_table (table2, ccs,
594 (unsigned char)(code_point >> 8), table3);
595 XCHARSET_DECODING_TABLE (ccs)
596 = put_ccs_octet_table (table1, ccs,
597 (unsigned char)(code_point >> 16), table2);
599 else /* if (dim == 4) */
602 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
604 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
606 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
608 table4 = put_ccs_octet_table (table4, ccs,
609 (unsigned char)code_point, character);
610 table3 = put_ccs_octet_table (table3, ccs,
611 (unsigned char)(code_point >> 8), table4);
612 table2 = put_ccs_octet_table (table2, ccs,
613 (unsigned char)(code_point >> 16), table3);
614 XCHARSET_DECODING_TABLE (ccs)
615 = put_ccs_octet_table (table1, ccs,
616 (unsigned char)(code_point >> 24), table2);
621 decoding_table_remove_char (Lisp_Object ccs, int code_point);
623 decoding_table_remove_char (Lisp_Object ccs, int code_point)
625 decoding_table_put_char (ccs, code_point, Qunbound);
628 Emchar decode_defined_char (Lisp_Object charset, int code_point);
630 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
632 DECODE_CHAR (Lisp_Object charset, int code_point)
634 Emchar char_id = decode_defined_char (charset, code_point);
638 else if (XCHARSET_DIMENSION (charset) == 1)
639 return decode_builtin_char (charset, code_point);
640 else if (EQ (charset, Vcharset_chinese_big5_1))
643 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
644 + ((code_point & 0xFF) - 33);
645 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
646 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
648 b2 += b2 < 0x3F ? 0x40 : 0x62;
649 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
651 else if (EQ (charset, Vcharset_chinese_big5_2))
654 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
655 + ((code_point & 0xFF) - 33);
656 unsigned char b1, b2;
658 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
659 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
660 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
661 b2 += b2 < 0x3F ? 0x40 : 0x62;
662 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
664 return decode_builtin_char (charset, code_point);
667 /* Return a character whose charset is CHARSET and position-codes
668 are C1 and C2. TYPE9N character ignores C2. */
670 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
672 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
674 if (XCHARSET_DIMENSION (charset) == 1)
675 return DECODE_CHAR (charset, c1);
677 return DECODE_CHAR (charset, (c1 << 8) | c2);
680 extern Lisp_Object Vcharacter_attribute_table;
682 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
683 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
684 int range_charset_code_point (Lisp_Object charset, Emchar ch);
686 extern Lisp_Object Vdefault_coded_charset_priority_list;
687 EXFUN (Ffind_charset, 1);
689 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
691 encode_char_1 (Emchar ch, Lisp_Object* charset)
693 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
695 while (!NILP (charsets))
697 *charset = Ffind_charset (Fcar (charsets));
698 if (!NILP (*charset))
700 int code_point = charset_code_point (*charset, ch, 0);
705 charsets = Fcdr (charsets);
708 /* otherwise --- maybe for bootstrap */
709 return encode_builtin_char_1 (ch, charset);
712 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
715 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
717 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
719 int code_point = encode_char_1 (c, charset);
723 int dim = XCHARSET_DIMENSION (*charset);
730 else /* if (dim == 2) */
732 *c1 = code_point >> 8;
733 *c2 = code_point & 255;
741 #define BREAKUP_CHAR(ch, charset, b1, b2) \
742 breakup_char_1 (ch, &(charset), &(b1), &(b2))
744 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
745 INLINE_HEADER Lisp_Object
746 CHAR_CHARSET (Emchar ch)
750 ENCODE_CHAR (ch, charset);
754 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
755 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
764 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
766 CHAR_TO_CHARC (Emchar ch)
770 cc.code_point = encode_char_1 (ch, &cc.charset);
774 #endif /* INCLUDED_char_ucs_h_ */