1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999,2000,2001,2002,2003 MORIOKA Tomohiko
4 This file is part of XEmacs.
6 XEmacs is free software; you can redistribute it and/or modify it
7 under the terms of the GNU General Public License as published by the
8 Free Software Foundation; either version 2, or (at your option) any
11 XEmacs is distributed in the hope that it will be useful, but WITHOUT
12 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
16 You should have received a copy of the GNU General Public License
17 along with XEmacs; see the file COPYING. If not, write to
18 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 Boston, MA 02111-1307, USA. */
21 #ifndef INCLUDED_char_ucs_h_
22 #define INCLUDED_char_ucs_h_
27 EXFUN (Fmake_directory_internal, 1);
29 extern Lisp_Object Vchar_attribute_hash_table;
31 #define valid_char_p(ch) 1
33 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
36 /************************************************************************/
37 /* Exported functions */
38 /************************************************************************/
40 extern Lisp_Object Vcharset_ucs;
41 extern Lisp_Object Vcharset_latin_jisx0201;
42 extern Lisp_Object Vcharset_chinese_big5;
43 extern Lisp_Object Vcharset_chinese_big5_1;
44 extern Lisp_Object Vcharset_chinese_big5_2;
45 extern Lisp_Object Vcharset_japanese_jisx0208;
46 extern Lisp_Object Vcharset_japanese_jisx0208_1990;
47 extern Lisp_Object Vcharset_japanese_jisx0212;
49 EXFUN (Fget_charset, 1);
51 extern Lisp_Object Qucs;
53 Lisp_Object put_char_ccs_code_point (Lisp_Object character,
54 Lisp_Object ccs, Lisp_Object value);
55 Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
58 /************************************************************************/
59 /* Definition of leading bytes */
60 /************************************************************************/
62 typedef short Charset_ID;
64 #define MIN_LEADING_BYTE -0x200
67 #define LEADING_BYTE_UCS (MIN_LEADING_BYTE + 1)
69 /* represent normal 80-9F */
70 #define LEADING_BYTE_CONTROL_1 (MIN_LEADING_BYTE + 2)
72 /* ISO/IEC 10646 BMP */
73 #define LEADING_BYTE_UCS_BMP (MIN_LEADING_BYTE + 3)
75 /* ISO/IEC 10646 SMP */
76 #define LEADING_BYTE_UCS_SMP (MIN_LEADING_BYTE + 4)
78 /* ISO/IEC 10646 SIP */
79 #define LEADING_BYTE_UCS_SIP (MIN_LEADING_BYTE + 5)
81 /* ISO/IEC 10646 for GB */
82 #define LEADING_BYTE_UCS_GB (MIN_LEADING_BYTE + 6)
84 /* ISO/IEC 10646 for CNS */
85 #define LEADING_BYTE_UCS_CNS (MIN_LEADING_BYTE + 7)
87 /* ISO/IEC 10646 for JIS */
88 #define LEADING_BYTE_UCS_JIS (MIN_LEADING_BYTE + 8)
90 /* ISO/IEC 10646 for KS */
91 #define LEADING_BYTE_UCS_KS (MIN_LEADING_BYTE + 9)
93 /* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
94 #define LEADING_BYTE_JIS_X0208 (MIN_LEADING_BYTE + 11)
96 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
97 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (MIN_LEADING_BYTE + 12)
99 /* Chinese GB 12345-1990 */
100 #define LEADING_BYTE_CHINESE_GB12345 (MIN_LEADING_BYTE + 13)
102 #define LEADING_BYTE_CHINESE_BIG5 (MIN_LEADING_BYTE + 20)
104 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
105 #define LEADING_BYTE_CHINESE_BIG5_1 (MIN_LEADING_BYTE + 21)
107 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
108 #define LEADING_BYTE_CHINESE_BIG5_2 (MIN_LEADING_BYTE + 22)
111 #define LEADING_BYTE_LATIN_VISCII (MIN_LEADING_BYTE + 24)
113 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
114 #define LEADING_BYTE_LATIN_VISCII_LOWER (MIN_LEADING_BYTE + 25)
116 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
117 #define LEADING_BYTE_LATIN_VISCII_UPPER (MIN_LEADING_BYTE + 26)
119 #define LEADING_BYTE_ETHIOPIC_UCS (MIN_LEADING_BYTE + 27)
121 #define MIN_LEADING_BYTE_PRIVATE (MIN_LEADING_BYTE + 97)
122 #define MAX_LEADING_BYTE_PRIVATE -1
126 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
128 /* Right half of JIS X0201-1976 */
129 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
131 /* Left half of JIS X0201-1976 */
132 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
135 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
137 /* Right half of ISO 8859-1 */
138 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
140 /* Right half of ISO 8859-2 */
141 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
143 /* Right half of ISO 8859-3 */
144 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
146 /* Right half of ISO 8859-4 */
147 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
149 /* Right half of ISO 8859-7 */
150 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
152 /* Right half of ISO 8859-6 */
153 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
155 /* Right half of ISO 8859-8 */
156 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
158 /* Right half of ISO 8859-5 */
159 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
161 /* Right half of ISO 8859-9 */
162 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
165 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
167 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
168 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
171 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
173 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
174 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
176 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
177 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
179 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
180 #define LEADING_BYTE_CHINESE_GB2312 58
182 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
183 #define LEADING_BYTE_JAPANESE_JISX0208 87
185 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
186 #define LEADING_BYTE_KOREAN_KSC5601 149
188 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
189 #define LEADING_BYTE_JAPANESE_JISX0212 159
191 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
192 #define LEADING_BYTE_CHINESE_CCITT_GB 165
194 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
195 #define LEADING_BYTE_CHINESE_CNS11643_1 171
197 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
198 #define LEADING_BYTE_CHINESE_CNS11643_2 172
200 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
201 #define LEADING_BYTE_CHINESE_CNS11643_3 183
203 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
204 #define LEADING_BYTE_CHINESE_CNS11643_4 184
206 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
207 #define LEADING_BYTE_CHINESE_CNS11643_5 185
209 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
210 #define LEADING_BYTE_CHINESE_CNS11643_6 186
212 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
213 #define LEADING_BYTE_CHINESE_CNS11643_7 187
215 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
216 #define LEADING_BYTE_KOREAN_KPS9566 202
219 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
222 /************************************************************************/
223 /* Information about a particular character set */
224 /************************************************************************/
228 struct lcrecord_header header;
232 Lisp_Object doc_string;
233 Lisp_Object registry;
234 Lisp_Object short_name;
235 Lisp_Object long_name;
237 Lisp_Object reverse_direction_charset;
239 Lisp_Object ccl_program;
241 /* Final byte of this character set in ISO2022 designating escape sequence */
244 /* Number of columns a character in this charset takes up, on TTY
245 devices. Not used for X devices. */
246 unsigned int columns;
248 /* Direction of this character set */
249 unsigned int direction;
251 /* Number of bytes used in encoding of this character set (1 .. 4) */
252 unsigned short dimension;
254 /* Number of chars in each dimension (94, 96, 128, 256) */
255 unsigned short chars;
257 /* Which half of font to be used to display this character set */
258 unsigned int graphic;
260 /* Code-point->character mapping table */
261 Lisp_Object decoding_table;
266 /* Range of character code */
267 int min_code, max_code;
269 /* Offset for external code */
272 /* Type of conversion from mother CCS */
273 unsigned char conversion;
275 /* Offset for each byte */
278 typedef struct Lisp_Charset Lisp_Charset;
280 DECLARE_LRECORD (charset, Lisp_Charset);
281 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
282 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
283 #define CHARSETP(x) RECORDP (x, charset)
284 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
285 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
287 #define CHARSET_LEFT_TO_RIGHT 0
288 #define CHARSET_RIGHT_TO_LEFT 1
290 /* Leading byte and id have been regrouped. -- OG */
291 #define CHARSET_ID(cs) ((cs)->id)
292 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
293 #define CHARSET_NAME(cs) ((cs)->name)
294 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
295 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
296 #define CHARSET_COLUMNS(cs) ((cs)->columns)
297 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
298 #define CHARSET_DIRECTION(cs) ((cs)->direction)
299 #define CHARSET_FINAL(cs) ((cs)->final)
300 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
301 #define CHARSET_REGISTRY(cs) ((cs)->registry)
302 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
303 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
304 #define CHARSET_CHARS(cs) ((cs)->chars)
305 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
306 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
307 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
308 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
309 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
310 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
311 #define CHARSET_MOTHER(cs) ((cs)->mother)
312 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
314 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
316 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
318 /* ad-hoc method for `ascii' */
319 if ((CHARSET_CHARS (cs) == 94) &&
320 (CHARSET_BYTE_OFFSET (cs) != 33))
321 return 128 - CHARSET_BYTE_OFFSET (cs);
323 return CHARSET_CHARS (cs);
326 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
327 INLINE_HEADER Lisp_Object
328 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
330 return Fgethash (CHARSET_NAME(cs),
331 Vchar_attribute_hash_table,
335 #define CONVERSION_IDENTICAL 0
336 #define CONVERSION_94 1
337 #define CONVERSION_96 2
338 #define CONVERSION_94x94 3
339 #define CONVERSION_96x96 4
340 #define CONVERSION_94x94x94 5
341 #define CONVERSION_96x96x96 6
342 #define CONVERSION_94x94x94x94 7
343 #define CONVERSION_96x96x96x96 8
344 #define CONVERSION_94x60 9
345 #define CONVERSION_94x94x60 10
346 #define CONVERSION_94x94x94x60 11
347 #define CONVERSION_BIG5_1 12
348 #define CONVERSION_BIG5_2 13
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
459 #define MIN_CHAR_DAIKANWA 0x00E00000
460 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
462 #define MIN_CHAR_CBETA 0x00E20000
463 #define MAX_CHAR_CBETA 0x00E2FFFF
465 #define MIN_CHAR_CHINA3_JEF 0x00E80000
466 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
469 #define MIN_CHAR_94 0x00E90940
470 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
471 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
472 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
474 #define MIN_CHAR_94x94 0xE9F6C0
475 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
476 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
477 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
478 #define MIN_CHAR_96x96 0xF4C000
479 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
482 #define MIN_CHAR_GT 0x61000000
483 #define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
485 #define MIN_CHAR_BIG5_CDP 0x62000000
486 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
488 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
489 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
490 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
491 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
492 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
493 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
494 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
495 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
496 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
497 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
498 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
499 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
500 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
501 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
502 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
503 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
504 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
505 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
506 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
507 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
508 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
509 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
510 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
511 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
514 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
516 INLINE_HEADER Lisp_Object
517 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
518 INLINE_HEADER Lisp_Object
519 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
521 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
525 int idx = code - byte_offset;
527 if (idx < XVECTOR_LENGTH(table))
528 return XVECTOR_DATA(table)[idx];
536 INLINE_HEADER Lisp_Object
537 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
539 INLINE_HEADER Lisp_Object
540 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
543 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
544 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
548 XVECTOR_DATA(table)[code - byte_offset] = value;
551 else if (EQ (table, value))
555 table = make_vector (ccs_len, table);
556 XVECTOR_DATA(table)[code - byte_offset] = value;
562 decoding_table_put_char (Lisp_Object ccs,
563 int code_point, Lisp_Object character);
565 decoding_table_put_char (Lisp_Object ccs,
566 int code_point, Lisp_Object character)
569 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
570 int dim = XCHARSET_DIMENSION (ccs);
573 XCHARSET_DECODING_TABLE (ccs)
574 = put_ccs_octet_table (table1, ccs, code_point, character);
578 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
580 table2 = put_ccs_octet_table (table2, ccs,
581 (unsigned char)code_point, character);
582 XCHARSET_DECODING_TABLE (ccs)
583 = put_ccs_octet_table (table1, ccs,
584 (unsigned char)(code_point >> 8), table2);
589 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
591 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
593 table3 = put_ccs_octet_table (table3, ccs,
594 (unsigned char)code_point, character);
595 table2 = put_ccs_octet_table (table2, ccs,
596 (unsigned char)(code_point >> 8), table3);
597 XCHARSET_DECODING_TABLE (ccs)
598 = put_ccs_octet_table (table1, ccs,
599 (unsigned char)(code_point >> 16), table2);
601 else /* if (dim == 4) */
604 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
606 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
608 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
610 table4 = put_ccs_octet_table (table4, ccs,
611 (unsigned char)code_point, character);
612 table3 = put_ccs_octet_table (table3, ccs,
613 (unsigned char)(code_point >> 8), table4);
614 table2 = put_ccs_octet_table (table2, ccs,
615 (unsigned char)(code_point >> 16), table3);
616 XCHARSET_DECODING_TABLE (ccs)
617 = put_ccs_octet_table (table1, ccs,
618 (unsigned char)(code_point >> 24), table2);
621 Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
622 int dim = XCHARSET_DIMENSION (ccs);
623 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
626 int ccs_len = XVECTOR_LENGTH (v);
631 i = ((code_point >> (8 * dim)) & 255) - byte_offset;
632 nv = XVECTOR_DATA(v)[i];
637 if (EQ (nv, character))
640 nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
647 XVECTOR_DATA(v)[i] = character;
652 decoding_table_remove_char (Lisp_Object ccs, int code_point);
654 decoding_table_remove_char (Lisp_Object ccs, int code_point)
656 decoding_table_put_char (ccs, code_point, Qunbound);
659 #ifdef HAVE_CHISE_CLIENT
660 Emchar load_char_decoding_entry_maybe (Lisp_Object ccs, int code_point);
663 Emchar decode_defined_char (Lisp_Object charset, int code_point);
665 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
667 DECODE_CHAR (Lisp_Object charset, int code_point)
669 Emchar char_id = decode_defined_char (charset, code_point);
674 return decode_builtin_char (charset, code_point);
677 /* Return a character whose charset is CHARSET and position-codes
678 are C1 and C2. TYPE9N character ignores C2. */
680 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
682 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
684 if (XCHARSET_DIMENSION (charset) == 1)
685 return DECODE_CHAR (charset, c1);
687 return DECODE_CHAR (charset, (c1 << 8) | c2);
690 extern Lisp_Object Vcharacter_attribute_table;
692 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
693 int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
694 int range_charset_code_point (Lisp_Object charset, Emchar ch);
696 extern Lisp_Object Vdefault_coded_charset_priority_list;
697 EXFUN (Ffind_charset, 1);
699 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
701 encode_char_1 (Emchar ch, Lisp_Object* charset)
703 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
705 while (!NILP (charsets))
707 *charset = Ffind_charset (Fcar (charsets));
708 if (!NILP (*charset))
710 int code_point = charset_code_point (*charset, ch, 0);
715 charsets = Fcdr (charsets);
718 /* otherwise --- maybe for bootstrap */
719 return encode_builtin_char_1 (ch, charset);
722 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
725 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
727 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
729 int code_point = encode_char_1 (c, charset);
733 int dim = XCHARSET_DIMENSION (*charset);
740 else /* if (dim == 2) */
742 *c1 = code_point >> 8;
743 *c2 = code_point & 255;
751 #define BREAKUP_CHAR(ch, charset, b1, b2) \
752 breakup_char_1 (ch, &(charset), &(b1), &(b2))
754 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
755 INLINE_HEADER Lisp_Object
756 CHAR_CHARSET (Emchar ch)
760 ENCODE_CHAR (ch, charset);
764 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
765 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
774 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
776 CHAR_TO_CHARC (Emchar ch)
780 cc.code_point = encode_char_1 (ch, &cc.charset);
784 #endif /* INCLUDED_char_ucs_h_ */