1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999,2000,2001 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_
24 #define valid_char_p(ch) 1
26 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
29 struct Lisp_Uint8_Byte_Table
31 struct lcrecord_header header;
33 unsigned char property[256];
35 typedef struct Lisp_Uint8_Byte_Table Lisp_Uint8_Byte_Table;
37 DECLARE_LRECORD (uint8_byte_table, Lisp_Uint8_Byte_Table);
38 #define XUINT8_BYTE_TABLE(x) \
39 XRECORD (x, uint8_byte_table, Lisp_Uint8_Byte_Table)
40 #define XSETUINT8_BYTE_TABLE(x, p) XSETRECORD (x, p, uint8_byte_table)
41 #define UINT8_BYTE_TABLE_P(x) RECORDP (x, uint8_byte_table)
42 #define GC_UINT8_BYTE_TABLE_P(x) GC_RECORDP (x, uint8_byte_table)
43 /* #define CHECK_UINT8_BYTE_TABLE(x) CHECK_RECORD (x, uint8_byte_table)
44 char table entries should never escape to Lisp */
47 struct Lisp_Uint16_Byte_Table
49 struct lcrecord_header header;
51 unsigned short property[256];
53 typedef struct Lisp_Uint16_Byte_Table Lisp_Uint16_Byte_Table;
55 DECLARE_LRECORD (uint16_byte_table, Lisp_Uint16_Byte_Table);
56 #define XUINT16_BYTE_TABLE(x) \
57 XRECORD (x, uint16_byte_table, Lisp_Uint16_Byte_Table)
58 #define XSETUINT16_BYTE_TABLE(x, p) XSETRECORD (x, p, uint16_byte_table)
59 #define UINT16_BYTE_TABLE_P(x) RECORDP (x, uint16_byte_table)
60 #define GC_UINT16_BYTE_TABLE_P(x) GC_RECORDP (x, uint16_byte_table)
61 /* #define CHECK_UINT16_BYTE_TABLE(x) CHECK_RECORD (x, uint16_byte_table)
62 char table entries should never escape to Lisp */
65 struct Lisp_Byte_Table
67 struct lcrecord_header header;
69 Lisp_Object property[256];
71 typedef struct Lisp_Byte_Table Lisp_Byte_Table;
73 DECLARE_LRECORD (byte_table, Lisp_Byte_Table);
74 #define XBYTE_TABLE(x) XRECORD (x, byte_table, Lisp_Byte_Table)
75 #define XSETBYTE_TABLE(x, p) XSETRECORD (x, p, byte_table)
76 #define BYTE_TABLE_P(x) RECORDP (x, byte_table)
77 #define GC_BYTE_TABLE_P(x) GC_RECORDP (x, byte_table)
78 /* #define CHECK_BYTE_TABLE(x) CHECK_RECORD (x, byte_table)
79 char table entries should never escape to Lisp */
82 struct Lisp_Char_ID_Table
84 struct lcrecord_header header;
88 typedef struct Lisp_Char_ID_Table Lisp_Char_ID_Table;
90 DECLARE_LRECORD (char_id_table, Lisp_Char_ID_Table);
91 #define XCHAR_ID_TABLE(x) XRECORD (x, char_id_table, Lisp_Char_ID_Table)
92 #define XSETCHAR_ID_TABLE(x, p) XSETRECORD (x, p, char_id_table)
93 #define CHAR_ID_TABLE_P(x) RECORDP (x, char_id_table)
94 #define GC_CHAR_ID_TABLE_P(x) GC_RECORDP (x, char_id_table)
95 /* #define CHECK_CHAR_ID_TABLE(x) CHECK_RECORD (x, char_id_table)
96 char table entries should never escape to Lisp */
99 Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table);
102 extern Lisp_Object Vcharset_mojikyo;
103 extern Lisp_Object Vcharset_mojikyo_2022_1;
104 extern Lisp_Object Vcharset_latin_jisx0201;
107 /************************************************************************/
108 /* Definition of leading bytes */
109 /************************************************************************/
111 typedef short Charset_ID;
113 #define MIN_LEADING_BYTE -0x70
114 #define CHARSET_ID_OFFSET 0x00
117 #define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1)
119 /* represent normal 80-9F */
120 #define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2)
122 /* ISO/IEC 10646 BMP */
123 #define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
125 /* ISO/IEC 10646 for CNS */
126 #define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 5)
128 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
129 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 10)
131 /* Chinese GB 12345-1990 */
132 #define LEADING_BYTE_CHINESE_GB12345 (CHARSET_ID_OFFSET - 11)
134 #define LEADING_BYTE_CHINESE_BIG5 (CHARSET_ID_OFFSET - 20)
136 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
137 #define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 21)
139 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
140 #define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 22)
143 #define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 23)
145 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
146 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 24)
148 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
149 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 25)
151 #define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 26)
153 #define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 27)
154 #define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 28)
156 #define LEADING_BYTE_GT (CHARSET_ID_OFFSET - 29)
157 #define LEADING_BYTE_GT_PJ_1 (CHARSET_ID_OFFSET - 31)
158 #define LEADING_BYTE_GT_PJ_2 (CHARSET_ID_OFFSET - 32)
159 #define LEADING_BYTE_GT_PJ_3 (CHARSET_ID_OFFSET - 33)
160 #define LEADING_BYTE_GT_PJ_4 (CHARSET_ID_OFFSET - 34)
161 #define LEADING_BYTE_GT_PJ_5 (CHARSET_ID_OFFSET - 35)
162 #define LEADING_BYTE_GT_PJ_6 (CHARSET_ID_OFFSET - 36)
163 #define LEADING_BYTE_GT_PJ_7 (CHARSET_ID_OFFSET - 37)
164 #define LEADING_BYTE_GT_PJ_8 (CHARSET_ID_OFFSET - 38)
165 #define LEADING_BYTE_GT_PJ_9 (CHARSET_ID_OFFSET - 39)
166 #define LEADING_BYTE_GT_PJ_10 (CHARSET_ID_OFFSET - 40)
167 #define LEADING_BYTE_GT_PJ_11 (CHARSET_ID_OFFSET - 41)
169 #define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 48)
170 #define LEADING_BYTE_MOJIKYO_2022_1 (CHARSET_ID_OFFSET - 49)
171 #define LEADING_BYTE_MOJIKYO_2022_2 (CHARSET_ID_OFFSET - 50)
173 /* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */
174 #define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 51)
175 #define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 52)
176 #define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 53)
177 #define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 54)
178 #define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 55)
179 #define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 56)
180 #define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 57)
181 #define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 58)
182 #define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 59)
183 #define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 60)
184 #define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 61)
185 #define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 62)
186 #define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 63)
187 #define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 64)
188 #define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 65)
189 #define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 66)
190 #define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 67)
191 #define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 68)
192 #define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 69)
193 #define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 70)
194 #define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 71)
196 #define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
197 #define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 72)
200 /* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
202 /* #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') */
203 /* #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') */
206 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
208 /* Right half of JIS X0201-1976 */
209 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
211 /* Left half of JIS X0201-1976 */
212 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
215 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
217 /* Right half of ISO 8859-1 */
218 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
220 /* Right half of ISO 8859-2 */
221 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
223 /* Right half of ISO 8859-3 */
224 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
226 /* Right half of ISO 8859-4 */
227 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
229 /* Right half of ISO 8859-7 */
230 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
232 /* Right half of ISO 8859-6 */
233 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
235 /* Right half of ISO 8859-8 */
236 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
238 /* Right half of ISO 8859-5 */
239 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
241 /* Right half of ISO 8859-9 */
242 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
245 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
247 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
248 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
251 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
253 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
254 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
256 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
257 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
259 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
260 #define LEADING_BYTE_CHINESE_GB2312 58
262 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
263 #define LEADING_BYTE_JAPANESE_JISX0208 87
265 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
266 #define LEADING_BYTE_KOREAN_KSC5601 149
268 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
269 #define LEADING_BYTE_JAPANESE_JISX0212 159
271 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
272 #define LEADING_BYTE_CHINESE_CCITT_GB 165
274 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
275 #define LEADING_BYTE_CHINESE_CNS11643_1 171
277 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
278 #define LEADING_BYTE_CHINESE_CNS11643_2 172
280 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
281 #define LEADING_BYTE_CHINESE_CNS11643_3 183
283 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
284 #define LEADING_BYTE_CHINESE_CNS11643_4 184
286 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
287 #define LEADING_BYTE_CHINESE_CNS11643_5 185
289 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
290 #define LEADING_BYTE_CHINESE_CNS11643_6 186
292 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
293 #define LEADING_BYTE_CHINESE_CNS11643_7 187
295 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
296 #define LEADING_BYTE_KOREAN_KPS9566 202
299 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
302 /************************************************************************/
303 /* Information about a particular character set */
304 /************************************************************************/
308 struct lcrecord_header header;
312 Lisp_Object doc_string;
313 Lisp_Object registry;
314 Lisp_Object short_name;
315 Lisp_Object long_name;
317 Lisp_Object reverse_direction_charset;
319 Lisp_Object ccl_program;
321 /* Final byte of this character set in ISO2022 designating escape sequence */
324 /* Number of columns a character in this charset takes up, on TTY
325 devices. Not used for X devices. */
326 unsigned int columns;
328 /* Direction of this character set */
329 unsigned int direction;
331 /* Number of bytes used in encoding of this character set (1 .. 4) */
332 unsigned short dimension;
334 /* Number of chars in each dimension (94, 96, 128, 256) */
335 unsigned short chars;
337 /* Which half of font to be used to display this character set */
338 unsigned int graphic;
340 /* Code-point->character mapping table */
341 Lisp_Object decoding_table;
343 /* Character->code-point mapping table */
344 Lisp_Object encoding_table;
346 /* Range of character code */
347 Emchar ucs_min, ucs_max;
349 /* Offset for external code */
352 /* Offset for each byte */
355 typedef struct Lisp_Charset Lisp_Charset;
357 DECLARE_LRECORD (charset, Lisp_Charset);
358 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
359 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
360 #define CHARSETP(x) RECORDP (x, charset)
361 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
362 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
363 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
365 #define CHARSET_LEFT_TO_RIGHT 0
366 #define CHARSET_RIGHT_TO_LEFT 1
368 /* Leading byte and id have been regrouped. -- OG */
369 #define CHARSET_ID(cs) ((cs)->id)
370 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
371 #define CHARSET_NAME(cs) ((cs)->name)
372 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
373 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
374 #define CHARSET_COLUMNS(cs) ((cs)->columns)
375 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
376 #define CHARSET_DIRECTION(cs) ((cs)->direction)
377 #define CHARSET_FINAL(cs) ((cs)->final)
378 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
379 #define CHARSET_REGISTRY(cs) ((cs)->registry)
380 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
381 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
382 #define CHARSET_CHARS(cs) ((cs)->chars)
383 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
384 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
385 #define CHARSET_ENCODING_TABLE(cs) ((cs)->encoding_table)
386 #define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
387 #define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
388 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
389 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
392 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
393 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
394 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
395 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
396 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
397 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
398 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
399 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
400 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
401 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
402 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
403 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
404 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
405 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
406 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
407 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
408 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
409 #define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs))
410 #define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs))
411 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
412 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
414 struct charset_lookup {
415 /* Table of charsets indexed by (leading byte - 128). */
416 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
418 /* Table of charsets indexed by type/final-byte/direction. */
419 Lisp_Object charset_by_attributes[4][128];
421 Charset_ID next_allocated_leading_byte;
424 extern struct charset_lookup *chlook;
426 #ifdef ERROR_CHECK_TYPECHECK
427 /* int not Bufbyte even though that is the actual type of a leading byte.
428 This way, out-ot-range values will get caught rather than automatically
430 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
431 INLINE_HEADER Lisp_Object
432 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
434 assert (lb >= MIN_LEADING_BYTE &&
435 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
436 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
441 #define CHARSET_BY_LEADING_BYTE(lb) \
442 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
446 INLINE_HEADER Lisp_Object
447 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
448 INLINE_HEADER Lisp_Object
449 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
455 else if (chars == 96)
459 type += dimension == 1 ? 0 : 2;
460 return chlook->charset_by_attributes[type][final];
464 /************************************************************************/
465 /* Dealing with characters */
466 /************************************************************************/
468 #define MAX_CHAR_BASIC_LATIN 0x007F
471 #define MIN_CHAR_GREEK 0x0370
472 #define MAX_CHAR_GREEK 0x03CF
474 #define MIN_CHAR_CYRILLIC 0x0400
475 #define MAX_CHAR_CYRILLIC 0x045F
478 #define MIN_CHAR_HEBREW 0x0590
479 #define MAX_CHAR_HEBREW 0x05EF
481 #define MIN_CHAR_THAI 0x0E00
482 #define MAX_CHAR_THAI 0x0E5F
485 #define MIN_CHAR_HIRAGANA 0x3041
486 #define MAX_CHAR_HIRAGANA 0x3093
488 #define MIN_CHAR_KATAKANA 0x30A1
489 #define MAX_CHAR_KATAKANA 0x30F6
492 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
493 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
495 #define MAX_CHAR_BMP 0x00FFFF
497 #define MIN_CHAR_DAIKANWA 0x00E00000
498 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
499 #define MIN_CHAR_MOJIKYO_0 MIN_CHAR_DAIKANWA
500 #define MAX_CHAR_MOJIKYO_0 (MIN_CHAR_MOJIKYO_0 + 94 * 60 * 22)
502 #define MIN_CHAR_94 0xE90940
503 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
504 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
505 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
507 #define MIN_CHAR_94x94 0xE9F6C0
508 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
509 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
510 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
511 #define MIN_CHAR_96x96 0xF4C000
512 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
514 #define MIN_CHAR_MOJIKYO 0x60000000
515 #define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
516 #define MIN_CHAR_GT 0x61000000
517 #define MAX_CHAR_GT (MIN_CHAR_GT + 66773)
519 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
522 DECODE_MOJIKYO_2022 (unsigned char b1, unsigned char b2, unsigned char b3);
524 DECODE_MOJIKYO_2022 (unsigned char b1, unsigned char b2, unsigned char b3)
528 else if (b2 < 16 + 32 + 30)
530 (b1 - 33) * (94 * 60)
531 + (b2 - (16 + 32)) * 94
534 else if (b2 < 18 + 32 + 30)
536 else if (b2 < 18 + 32 + 60)
538 (b1 - 33) * (94 * 60)
539 + (b2 - (18 + 32)) * 94
546 extern Lisp_Object Vcharset_chinese_big5;
547 extern Lisp_Object Vcharset_chinese_big5_1;
548 extern Lisp_Object Vcharset_chinese_big5_2;
550 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
552 DECODE_CHAR (Lisp_Object charset, int code_point)
554 int dim = XCHARSET_DIMENSION (charset);
555 Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
562 if ( VECTORP (decoding_table)
563 && ( 0 <= (idx = ((code_point >> (dim * 8))
564 & 255) - XCHARSET_BYTE_OFFSET (charset)) )
565 && ( idx < XVECTOR_LENGTH (decoding_table) )
566 && !NILP (ch = XVECTOR_DATA(decoding_table)[idx]) )
576 if (XCHARSET_DIMENSION (charset) == 1)
577 return decode_builtin_char (charset, code_point);
578 else if (EQ (charset, Vcharset_chinese_big5_1))
581 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
582 + ((code_point & 0xFF) - 33);
583 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
584 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
586 b2 += b2 < 0x3F ? 0x40 : 0x62;
587 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
589 else if (EQ (charset, Vcharset_chinese_big5_2))
592 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
593 + ((code_point & 0xFF) - 33);
594 unsigned char b1, b2;
596 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
597 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
598 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
599 b2 += b2 < 0x3F ? 0x40 : 0x62;
600 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
602 else if (EQ (charset, Vcharset_mojikyo_2022_1))
606 ((unsigned char)(code_point >> 16),
607 (unsigned char)(code_point >> 8),
608 (unsigned char) code_point);
611 return DECODE_CHAR (Vcharset_mojikyo, m);
617 int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset);
619 if ( (0 <= plane) && (plane <= 21) )
621 int m = DECODE_MOJIKYO_2022 (plane + 33,
623 (unsigned char)code_point);
625 return DECODE_CHAR (Vcharset_mojikyo, m);
630 return decode_builtin_char (charset, code_point);
634 /* Return a character whose charset is CHARSET and position-codes
635 are C1 and C2. TYPE9N character ignores C2. */
637 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
639 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
641 if (XCHARSET_DIMENSION (charset) == 1)
642 return DECODE_CHAR (charset, c1);
644 return DECODE_CHAR (charset, (c1 << 8) | c2);
647 extern Lisp_Object Vcharacter_attribute_table;
649 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
650 int range_charset_code_point (Lisp_Object charset, Emchar ch);
652 INLINE_HEADER int charset_code_point (Lisp_Object charset, Emchar ch);
654 charset_code_point (Lisp_Object charset, Emchar ch)
656 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset);
659 if ( CHAR_ID_TABLE_P (encoding_table)
660 && INTP (ret = get_char_id_table (ch, encoding_table)) )
663 return range_charset_code_point (charset, ch);
666 extern Lisp_Object Vdefault_coded_charset_priority_list;
667 EXFUN (Ffind_charset, 1);
669 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
671 encode_char_1 (Emchar ch, Lisp_Object* charset)
673 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
675 while (!NILP (charsets))
677 *charset = Ffind_charset (Fcar (charsets));
678 if (!NILP (*charset))
680 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset);
683 if ( CHAR_ID_TABLE_P (encoding_table)
684 && INTP (ret = get_char_id_table (ch, encoding_table)) )
688 int code_point = range_charset_code_point (*charset, ch);
694 charsets = Fcdr (charsets);
697 /* otherwise --- maybe for bootstrap */
698 return encode_builtin_char_1 (ch, charset);
701 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
704 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
706 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
708 int code_point = encode_char_1 (c, charset);
712 int dim = XCHARSET_DIMENSION (*charset);
719 else /* if (dim == 2) */
721 *c1 = code_point >> 8;
722 *c2 = code_point & 255;
730 #define BREAKUP_CHAR(ch, charset, b1, b2) \
731 breakup_char_1 (ch, &(charset), &(b1), &(b2))
733 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
734 INLINE_HEADER Lisp_Object
735 CHAR_CHARSET (Emchar ch)
739 ENCODE_CHAR (ch, charset);
743 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
744 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
753 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
755 CHAR_TO_CHARC (Emchar ch)
759 cc.code_point = encode_char_1 (ch, &cc.charset);
760 if (EQ (cc.charset, Vcharset_mojikyo))
762 int plane, byte1, byte2;
765 plane = cc.code_point / (94 * 60);
766 byte1 = (cc.code_point % (94 * 60)) / 94;
771 byte2 = cc.code_point % 94 + 33;
773 = CHARSET_BY_LEADING_BYTE (LEADING_BYTE_MOJIKYO_PJ_1 - plane);
774 cc.code_point = (byte1 << 8) | byte2;
780 /************************************************************************/
781 /* Exported functions */
782 /************************************************************************/
784 EXFUN (Fget_charset, 1);
786 extern Lisp_Object Vcharset_japanese_jisx0208;
787 extern Lisp_Object Vcharset_japanese_jisx0208_1990;
788 extern Lisp_Object Vcharset_japanese_jisx0212;
790 #endif /* INCLUDED_char_ucs_h_ */