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 MIN_LEADING_BYTE_PRIVATE (MIN_LEADING_BYTE + 97)
120 #define MAX_LEADING_BYTE_PRIVATE -1
124 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
126 /* Right half of JIS X0201-1976 */
127 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
129 /* Left half of JIS X0201-1976 */
130 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
133 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
135 /* Right half of ISO 8859-1 */
136 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
138 /* Right half of ISO 8859-2 */
139 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
141 /* Right half of ISO 8859-3 */
142 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
144 /* Right half of ISO 8859-4 */
145 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
147 /* Right half of ISO 8859-7 */
148 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
150 /* Right half of ISO 8859-6 */
151 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
153 /* Right half of ISO 8859-8 */
154 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
156 /* Right half of ISO 8859-5 */
157 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
159 /* Right half of ISO 8859-9 */
160 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
163 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
165 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
166 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
169 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
171 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
172 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
174 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
175 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
177 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
178 #define LEADING_BYTE_CHINESE_GB2312 58
180 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
181 #define LEADING_BYTE_JAPANESE_JISX0208 87
183 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
184 #define LEADING_BYTE_KOREAN_KSC5601 149
186 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
187 #define LEADING_BYTE_JAPANESE_JISX0212 159
189 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
190 #define LEADING_BYTE_CHINESE_CCITT_GB 165
192 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
193 #define LEADING_BYTE_CHINESE_CNS11643_1 171
195 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
196 #define LEADING_BYTE_CHINESE_CNS11643_2 172
198 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
199 #define LEADING_BYTE_CHINESE_CNS11643_3 183
201 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
202 #define LEADING_BYTE_CHINESE_CNS11643_4 184
204 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
205 #define LEADING_BYTE_CHINESE_CNS11643_5 185
207 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
208 #define LEADING_BYTE_CHINESE_CNS11643_6 186
210 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
211 #define LEADING_BYTE_CHINESE_CNS11643_7 187
213 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
214 #define LEADING_BYTE_KOREAN_KPS9566 202
217 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
220 /************************************************************************/
221 /* Information about a particular character set */
222 /************************************************************************/
226 struct lcrecord_header header;
230 Lisp_Object doc_string;
231 Lisp_Object registry;
232 Lisp_Object short_name;
233 Lisp_Object long_name;
235 Lisp_Object reverse_direction_charset;
237 Lisp_Object ccl_program;
239 /* Final byte of this character set in ISO2022 designating escape sequence */
242 /* Number of columns a character in this charset takes up, on TTY
243 devices. Not used for X devices. */
244 unsigned int columns;
246 /* Direction of this character set */
247 unsigned int direction;
249 /* Number of bytes used in encoding of this character set (1 .. 4) */
250 unsigned short dimension;
252 /* Number of chars in each dimension (94, 96, 128, 256) */
253 unsigned short chars;
255 /* Which half of font to be used to display this character set */
256 unsigned int graphic;
258 /* Code-point->character mapping table */
259 Lisp_Object decoding_table;
264 /* Range of character code */
265 int min_code, max_code;
267 /* Offset for external code */
270 /* Type of conversion from mother CCS */
271 unsigned char conversion;
273 /* Offset for each byte */
276 typedef struct Lisp_Charset Lisp_Charset;
278 DECLARE_LRECORD (charset, Lisp_Charset);
279 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
280 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
281 #define CHARSETP(x) RECORDP (x, charset)
282 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
283 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
285 #define CHARSET_LEFT_TO_RIGHT 0
286 #define CHARSET_RIGHT_TO_LEFT 1
288 /* Leading byte and id have been regrouped. -- OG */
289 #define CHARSET_ID(cs) ((cs)->id)
290 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
291 #define CHARSET_NAME(cs) ((cs)->name)
292 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
293 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
294 #define CHARSET_COLUMNS(cs) ((cs)->columns)
295 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
296 #define CHARSET_DIRECTION(cs) ((cs)->direction)
297 #define CHARSET_FINAL(cs) ((cs)->final)
298 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
299 #define CHARSET_REGISTRY(cs) ((cs)->registry)
300 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
301 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
302 #define CHARSET_CHARS(cs) ((cs)->chars)
303 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
304 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
305 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
306 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
307 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
308 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
309 #define CHARSET_MOTHER(cs) ((cs)->mother)
310 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
312 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
314 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
316 /* ad-hoc method for `ascii' */
317 if ((CHARSET_CHARS (cs) == 94) &&
318 (CHARSET_BYTE_OFFSET (cs) != 33))
319 return 128 - CHARSET_BYTE_OFFSET (cs);
321 return CHARSET_CHARS (cs);
324 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
325 INLINE_HEADER Lisp_Object
326 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
328 return Fgethash (CHARSET_NAME(cs),
329 Vchar_attribute_hash_table,
333 #define CONVERSION_IDENTICAL 0
334 #define CONVERSION_94 1
335 #define CONVERSION_96 2
336 #define CONVERSION_94x60 3
337 #define CONVERSION_94x94 4
338 #define CONVERSION_96x96 5
339 #define CONVERSION_94x94x60 6
340 #define CONVERSION_94x94x94 7
341 #define CONVERSION_96x96x96 8
342 #define CONVERSION_94x94x94x60 9
343 #define CONVERSION_94x94x94x94 10
344 #define CONVERSION_96x96x96x96 11
346 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
347 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
348 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
349 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
350 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
351 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
352 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
353 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
354 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
355 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
356 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
357 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
358 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
359 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
360 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
361 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
362 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
363 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
364 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
365 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
366 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
367 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
368 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
369 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
371 struct charset_lookup {
372 /* Table of charsets indexed by (leading byte - 128). */
373 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
375 /* Table of charsets indexed by type/final-byte/direction. */
376 Lisp_Object charset_by_attributes[4][128];
378 Charset_ID next_allocated_leading_byte;
381 extern struct charset_lookup *chlook;
383 #ifdef ERROR_CHECK_TYPECHECK
384 /* int not Bufbyte even though that is the actual type of a leading byte.
385 This way, out-ot-range values will get caught rather than automatically
387 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
388 INLINE_HEADER Lisp_Object
389 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
391 assert (lb >= MIN_LEADING_BYTE &&
392 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
393 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
398 #define CHARSET_BY_LEADING_BYTE(lb) \
399 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
403 INLINE_HEADER Lisp_Object
404 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
405 INLINE_HEADER Lisp_Object
406 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
412 else if (chars == 96)
416 type += dimension == 1 ? 0 : 2;
417 return chlook->charset_by_attributes[type][final];
421 /************************************************************************/
422 /* Dealing with characters */
423 /************************************************************************/
425 #define MAX_CHAR_BASIC_LATIN 0x007F
428 #define MIN_CHAR_HEBREW 0x0590
429 #define MAX_CHAR_HEBREW 0x05EF
432 #define MIN_CHAR_THAI 0x0E00
433 #define MAX_CHAR_THAI 0x0E5F
436 #define MIN_CHAR_HIRAGANA 0x3041
437 #define MAX_CHAR_HIRAGANA 0x3093
439 #define MIN_CHAR_KATAKANA 0x30A1
440 #define MAX_CHAR_KATAKANA 0x30F6
443 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
444 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
446 #define MAX_CHAR_BMP 0x00FFFF
448 #define MIN_CHAR_SMP 0x010000
449 #define MAX_CHAR_SMP 0x01FFFF
451 #define MIN_CHAR_SIP 0x020000
452 #define MAX_CHAR_SIP 0x02FFFF
455 #define MIN_CHAR_DAIKANWA 0x00E00000
456 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
458 #define MIN_CHAR_CBETA 0x00E20000
459 #define MAX_CHAR_CBETA 0x00E2FFFF
461 #define MIN_CHAR_CHINA3_JEF 0x00E80000
462 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
465 #define MIN_CHAR_94 0x00E90940
466 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
467 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
468 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
470 #define MIN_CHAR_94x94 0xE9F6C0
471 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
472 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
473 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
474 #define MIN_CHAR_96x96 0xF4C000
475 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
478 #define MIN_CHAR_GT 0x61000000
479 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
481 #define MIN_CHAR_BIG5_CDP 0x62000000
482 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
484 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
485 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
486 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
487 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
488 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
489 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
490 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
491 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
492 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
493 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
494 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
495 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
496 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
497 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
498 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
499 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
500 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
501 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
502 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
503 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
504 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
505 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
506 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
507 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
510 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
512 INLINE_HEADER Lisp_Object
513 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
514 INLINE_HEADER Lisp_Object
515 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
517 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
521 int idx = code - byte_offset;
523 if (idx < XVECTOR_LENGTH(table))
524 return XVECTOR_DATA(table)[idx];
532 INLINE_HEADER Lisp_Object
533 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
535 INLINE_HEADER Lisp_Object
536 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
539 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
540 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
544 XVECTOR_DATA(table)[code - byte_offset] = value;
547 else if (EQ (table, value))
551 table = make_vector (ccs_len, table);
552 XVECTOR_DATA(table)[code - byte_offset] = value;
558 decoding_table_put_char (Lisp_Object ccs,
559 int code_point, Lisp_Object character);
561 decoding_table_put_char (Lisp_Object ccs,
562 int code_point, Lisp_Object character)
564 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
565 int dim = XCHARSET_DIMENSION (ccs);
568 XCHARSET_DECODING_TABLE (ccs)
569 = put_ccs_octet_table (table1, ccs, code_point, character);
573 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
575 table2 = put_ccs_octet_table (table2, ccs,
576 (unsigned char)code_point, character);
577 XCHARSET_DECODING_TABLE (ccs)
578 = put_ccs_octet_table (table1, ccs,
579 (unsigned char)(code_point >> 8), table2);
584 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
586 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
588 table3 = put_ccs_octet_table (table3, ccs,
589 (unsigned char)code_point, character);
590 table2 = put_ccs_octet_table (table2, ccs,
591 (unsigned char)(code_point >> 8), table3);
592 XCHARSET_DECODING_TABLE (ccs)
593 = put_ccs_octet_table (table1, ccs,
594 (unsigned char)(code_point >> 16), table2);
596 else /* if (dim == 4) */
599 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
601 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
603 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
605 table4 = put_ccs_octet_table (table4, ccs,
606 (unsigned char)code_point, character);
607 table3 = put_ccs_octet_table (table3, ccs,
608 (unsigned char)(code_point >> 8), table4);
609 table2 = put_ccs_octet_table (table2, ccs,
610 (unsigned char)(code_point >> 16), table3);
611 XCHARSET_DECODING_TABLE (ccs)
612 = put_ccs_octet_table (table1, ccs,
613 (unsigned char)(code_point >> 24), table2);
618 decoding_table_remove_char (Lisp_Object ccs, int code_point);
620 decoding_table_remove_char (Lisp_Object ccs, int code_point)
622 decoding_table_put_char (ccs, code_point, Qunbound);
625 Emchar decode_defined_char (Lisp_Object charset, int code_point);
627 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
629 DECODE_CHAR (Lisp_Object charset, int code_point)
631 Emchar char_id = decode_defined_char (charset, code_point);
635 else if (XCHARSET_DIMENSION (charset) == 1)
636 return decode_builtin_char (charset, code_point);
637 else if (EQ (charset, Vcharset_chinese_big5_1))
640 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
641 + ((code_point & 0xFF) - 33);
642 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
643 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
645 b2 += b2 < 0x3F ? 0x40 : 0x62;
646 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
648 else if (EQ (charset, Vcharset_chinese_big5_2))
651 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
652 + ((code_point & 0xFF) - 33);
653 unsigned char b1, b2;
655 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
656 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
657 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
658 b2 += b2 < 0x3F ? 0x40 : 0x62;
659 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
661 return decode_builtin_char (charset, code_point);
664 /* Return a character whose charset is CHARSET and position-codes
665 are C1 and C2. TYPE9N character ignores C2. */
667 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
669 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
671 if (XCHARSET_DIMENSION (charset) == 1)
672 return DECODE_CHAR (charset, c1);
674 return DECODE_CHAR (charset, (c1 << 8) | c2);
677 extern Lisp_Object Vcharacter_attribute_table;
679 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
680 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
681 int range_charset_code_point (Lisp_Object charset, Emchar ch);
683 extern Lisp_Object Vdefault_coded_charset_priority_list;
684 EXFUN (Ffind_charset, 1);
686 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
688 encode_char_1 (Emchar ch, Lisp_Object* charset)
690 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
692 while (!NILP (charsets))
694 *charset = Ffind_charset (Fcar (charsets));
695 if (!NILP (*charset))
697 int code_point = charset_code_point (*charset, ch, 0);
702 charsets = Fcdr (charsets);
705 /* otherwise --- maybe for bootstrap */
706 return encode_builtin_char_1 (ch, charset);
709 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
712 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
714 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
716 int code_point = encode_char_1 (c, charset);
720 int dim = XCHARSET_DIMENSION (*charset);
727 else /* if (dim == 2) */
729 *c1 = code_point >> 8;
730 *c2 = code_point & 255;
738 #define BREAKUP_CHAR(ch, charset, b1, b2) \
739 breakup_char_1 (ch, &(charset), &(b1), &(b2))
741 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
742 INLINE_HEADER Lisp_Object
743 CHAR_CHARSET (Emchar ch)
747 ENCODE_CHAR (ch, charset);
751 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
752 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
761 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
763 CHAR_TO_CHARC (Emchar ch)
767 cc.code_point = encode_char_1 (ch, &cc.charset);
771 #endif /* INCLUDED_char_ucs_h_ */