1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999,2000,2001,2002 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)
35 extern Lisp_Object Vcharset_latin_jisx0201;
38 /************************************************************************/
39 /* Definition of leading bytes */
40 /************************************************************************/
42 typedef short Charset_ID;
44 #define MIN_LEADING_BYTE -0x200
47 #define LEADING_BYTE_UCS (MIN_LEADING_BYTE + 1)
49 /* represent normal 80-9F */
50 #define LEADING_BYTE_CONTROL_1 (MIN_LEADING_BYTE + 2)
52 /* ISO/IEC 10646 BMP */
53 #define LEADING_BYTE_UCS_BMP (MIN_LEADING_BYTE + 3)
55 /* ISO/IEC 10646 SMP */
56 #define LEADING_BYTE_UCS_SMP (MIN_LEADING_BYTE + 4)
58 /* ISO/IEC 10646 SIP */
59 #define LEADING_BYTE_UCS_SIP (MIN_LEADING_BYTE + 5)
61 /* ISO/IEC 10646 for CNS */
62 #define LEADING_BYTE_UCS_CNS (MIN_LEADING_BYTE + 6)
64 /* ISO/IEC 10646 for JIS */
65 #define LEADING_BYTE_UCS_JIS (MIN_LEADING_BYTE + 7)
67 /* ISO/IEC 10646 for KS */
68 #define LEADING_BYTE_UCS_KS (MIN_LEADING_BYTE + 8)
70 /* ISO/IEC 10646 for Big5 */
71 #define LEADING_BYTE_UCS_BIG5 (MIN_LEADING_BYTE + 9)
73 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
74 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (MIN_LEADING_BYTE + 10)
76 /* Chinese GB 12345-1990 */
77 #define LEADING_BYTE_CHINESE_GB12345 (MIN_LEADING_BYTE + 11)
79 #define LEADING_BYTE_CHINESE_BIG5 (MIN_LEADING_BYTE + 20)
81 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
82 #define LEADING_BYTE_CHINESE_BIG5_1 (MIN_LEADING_BYTE + 21)
84 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
85 #define LEADING_BYTE_CHINESE_BIG5_2 (MIN_LEADING_BYTE + 22)
88 #define LEADING_BYTE_LATIN_VISCII (MIN_LEADING_BYTE + 24)
90 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
91 #define LEADING_BYTE_LATIN_VISCII_LOWER (MIN_LEADING_BYTE + 25)
93 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
94 #define LEADING_BYTE_LATIN_VISCII_UPPER (MIN_LEADING_BYTE + 26)
96 #define LEADING_BYTE_ETHIOPIC_UCS (MIN_LEADING_BYTE + 27)
98 #define LEADING_BYTE_DAIKANWA_0 (MIN_LEADING_BYTE + 28)
99 #define LEADING_BYTE_DAIKANWA_1 (MIN_LEADING_BYTE + 29)
100 #define LEADING_BYTE_DAIKANWA_2 (MIN_LEADING_BYTE + 30)
101 #define LEADING_BYTE_DAIKANWA_3 (MIN_LEADING_BYTE + 31)
103 #define LEADING_BYTE_GT (MIN_LEADING_BYTE + 40)
104 #define LEADING_BYTE_GT_PJ_1 (MIN_LEADING_BYTE + 41)
105 #define LEADING_BYTE_GT_PJ_2 (MIN_LEADING_BYTE + 42)
106 #define LEADING_BYTE_GT_PJ_3 (MIN_LEADING_BYTE + 43)
107 #define LEADING_BYTE_GT_PJ_4 (MIN_LEADING_BYTE + 44)
108 #define LEADING_BYTE_GT_PJ_5 (MIN_LEADING_BYTE + 45)
109 #define LEADING_BYTE_GT_PJ_6 (MIN_LEADING_BYTE + 46)
110 #define LEADING_BYTE_GT_PJ_7 (MIN_LEADING_BYTE + 47)
111 #define LEADING_BYTE_GT_PJ_8 (MIN_LEADING_BYTE + 48)
112 #define LEADING_BYTE_GT_PJ_9 (MIN_LEADING_BYTE + 49)
113 #define LEADING_BYTE_GT_PJ_10 (MIN_LEADING_BYTE + 50)
114 #define LEADING_BYTE_GT_PJ_11 (MIN_LEADING_BYTE + 51)
116 #define LEADING_BYTE_CHINA3_JEF (MIN_LEADING_BYTE + 82)
117 #define LEADING_BYTE_CBETA (MIN_LEADING_BYTE + 83)
118 /* #define LEADING_BYTE_CHINESE_BIG5_CDP (MIN_LEADING_BYTE + 84) */
119 #define LEADING_BYTE_HANZIKU_1 (MIN_LEADING_BYTE + 85)
120 #define LEADING_BYTE_HANZIKU_2 (MIN_LEADING_BYTE + 86)
121 #define LEADING_BYTE_HANZIKU_3 (MIN_LEADING_BYTE + 87)
122 #define LEADING_BYTE_HANZIKU_4 (MIN_LEADING_BYTE + 88)
123 #define LEADING_BYTE_HANZIKU_5 (MIN_LEADING_BYTE + 89)
124 #define LEADING_BYTE_HANZIKU_6 (MIN_LEADING_BYTE + 90)
125 #define LEADING_BYTE_HANZIKU_7 (MIN_LEADING_BYTE + 91)
126 #define LEADING_BYTE_HANZIKU_8 (MIN_LEADING_BYTE + 92)
127 #define LEADING_BYTE_HANZIKU_9 (MIN_LEADING_BYTE + 93)
128 #define LEADING_BYTE_HANZIKU_10 (MIN_LEADING_BYTE + 94)
129 #define LEADING_BYTE_HANZIKU_11 (MIN_LEADING_BYTE + 95)
130 #define LEADING_BYTE_HANZIKU_12 (MIN_LEADING_BYTE + 96)
132 #define MIN_LEADING_BYTE_PRIVATE (MIN_LEADING_BYTE + 97)
133 #define MAX_LEADING_BYTE_PRIVATE -1
137 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
139 /* Right half of JIS X0201-1976 */
140 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
142 /* Left half of JIS X0201-1976 */
143 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
146 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
148 /* Right half of ISO 8859-1 */
149 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
151 /* Right half of ISO 8859-2 */
152 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
154 /* Right half of ISO 8859-3 */
155 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
157 /* Right half of ISO 8859-4 */
158 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
160 /* Right half of ISO 8859-7 */
161 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
163 /* Right half of ISO 8859-6 */
164 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
166 /* Right half of ISO 8859-8 */
167 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
169 /* Right half of ISO 8859-5 */
170 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
172 /* Right half of ISO 8859-9 */
173 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
176 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
178 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
179 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
182 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
184 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
185 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
187 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
188 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
190 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
191 #define LEADING_BYTE_CHINESE_GB2312 58
193 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
194 #define LEADING_BYTE_JAPANESE_JISX0208 87
196 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
197 #define LEADING_BYTE_KOREAN_KSC5601 149
199 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
200 #define LEADING_BYTE_JAPANESE_JISX0212 159
202 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
203 #define LEADING_BYTE_CHINESE_CCITT_GB 165
205 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
206 #define LEADING_BYTE_CHINESE_CNS11643_1 171
208 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
209 #define LEADING_BYTE_CHINESE_CNS11643_2 172
211 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
212 #define LEADING_BYTE_CHINESE_CNS11643_3 183
214 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
215 #define LEADING_BYTE_CHINESE_CNS11643_4 184
217 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
218 #define LEADING_BYTE_CHINESE_CNS11643_5 185
220 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
221 #define LEADING_BYTE_CHINESE_CNS11643_6 186
223 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
224 #define LEADING_BYTE_CHINESE_CNS11643_7 187
226 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
227 #define LEADING_BYTE_KOREAN_KPS9566 202
230 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
233 /************************************************************************/
234 /* Information about a particular character set */
235 /************************************************************************/
239 struct lcrecord_header header;
243 Lisp_Object doc_string;
244 Lisp_Object registry;
245 Lisp_Object short_name;
246 Lisp_Object long_name;
248 Lisp_Object reverse_direction_charset;
250 Lisp_Object ccl_program;
252 /* Final byte of this character set in ISO2022 designating escape sequence */
255 /* Number of columns a character in this charset takes up, on TTY
256 devices. Not used for X devices. */
257 unsigned int columns;
259 /* Direction of this character set */
260 unsigned int direction;
262 /* Number of bytes used in encoding of this character set (1 .. 4) */
263 unsigned short dimension;
265 /* Number of chars in each dimension (94, 96, 128, 256) */
266 unsigned short chars;
268 /* Which half of font to be used to display this character set */
269 unsigned int graphic;
271 /* Code-point->character mapping table */
272 Lisp_Object decoding_table;
277 /* Range of character code */
278 int min_code, max_code;
280 /* Offset for external code */
283 /* Type of conversion from mother CCS */
284 unsigned char conversion;
286 /* Offset for each byte */
289 typedef struct Lisp_Charset Lisp_Charset;
291 DECLARE_LRECORD (charset, Lisp_Charset);
292 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
293 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
294 #define CHARSETP(x) RECORDP (x, charset)
295 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
296 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
297 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
299 #define CHARSET_LEFT_TO_RIGHT 0
300 #define CHARSET_RIGHT_TO_LEFT 1
302 /* Leading byte and id have been regrouped. -- OG */
303 #define CHARSET_ID(cs) ((cs)->id)
304 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
305 #define CHARSET_NAME(cs) ((cs)->name)
306 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
307 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
308 #define CHARSET_COLUMNS(cs) ((cs)->columns)
309 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
310 #define CHARSET_DIRECTION(cs) ((cs)->direction)
311 #define CHARSET_FINAL(cs) ((cs)->final)
312 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
313 #define CHARSET_REGISTRY(cs) ((cs)->registry)
314 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
315 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
316 #define CHARSET_CHARS(cs) ((cs)->chars)
317 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
318 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
319 #define CHARSET_MIN_CODE(cs) ((cs)->min_code)
320 #define CHARSET_MAX_CODE(cs) ((cs)->max_code)
321 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
322 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
323 #define CHARSET_MOTHER(cs) ((cs)->mother)
324 #define CHARSET_CONVERSION(cs) ((cs)->conversion)
326 INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
328 CHARSET_BYTE_SIZE (Lisp_Charset* cs)
330 /* ad-hoc method for `ascii' */
331 if ((CHARSET_CHARS (cs) == 94) &&
332 (CHARSET_BYTE_OFFSET (cs) != 33))
333 return 128 - CHARSET_BYTE_OFFSET (cs);
335 return CHARSET_CHARS (cs);
338 INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
339 INLINE_HEADER Lisp_Object
340 CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
342 return Fgethash (CHARSET_NAME(cs),
343 Vchar_attribute_hash_table,
347 #define CONVERSION_IDENTICAL 0
348 #define CONVERSION_94x60 1
349 #define CONVERSION_94x94x60 2
351 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
352 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
353 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
354 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
355 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
356 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
357 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
358 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
359 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
360 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
361 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
362 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
363 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
364 #define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs))
365 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
366 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
367 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
368 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
369 #define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
370 #define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
371 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
372 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
373 #define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
374 #define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
376 struct charset_lookup {
377 /* Table of charsets indexed by (leading byte - 128). */
378 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
380 /* Table of charsets indexed by type/final-byte/direction. */
381 Lisp_Object charset_by_attributes[4][128];
383 Charset_ID next_allocated_leading_byte;
386 extern struct charset_lookup *chlook;
388 #ifdef ERROR_CHECK_TYPECHECK
389 /* int not Bufbyte even though that is the actual type of a leading byte.
390 This way, out-ot-range values will get caught rather than automatically
392 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
393 INLINE_HEADER Lisp_Object
394 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
396 assert (lb >= MIN_LEADING_BYTE &&
397 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
398 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
403 #define CHARSET_BY_LEADING_BYTE(lb) \
404 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
408 INLINE_HEADER Lisp_Object
409 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
410 INLINE_HEADER Lisp_Object
411 CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
417 else if (chars == 96)
421 type += dimension == 1 ? 0 : 2;
422 return chlook->charset_by_attributes[type][final];
426 /************************************************************************/
427 /* Dealing with characters */
428 /************************************************************************/
430 #define MAX_CHAR_BASIC_LATIN 0x007F
433 #define MIN_CHAR_HEBREW 0x0590
434 #define MAX_CHAR_HEBREW 0x05EF
437 #define MIN_CHAR_THAI 0x0E00
438 #define MAX_CHAR_THAI 0x0E5F
441 #define MIN_CHAR_HIRAGANA 0x3041
442 #define MAX_CHAR_HIRAGANA 0x3093
444 #define MIN_CHAR_KATAKANA 0x30A1
445 #define MAX_CHAR_KATAKANA 0x30F6
448 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
449 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
451 #define MAX_CHAR_BMP 0x00FFFF
453 #define MIN_CHAR_SMP 0x010000
454 #define MAX_CHAR_SMP 0x01FFFF
456 #define MIN_CHAR_SIP 0x020000
457 #define MAX_CHAR_SIP 0x02FFFF
459 #define MIN_CHAR_DAIKANWA 0x00E00000
460 #define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
461 #define MIN_CHAR_CBETA 0x00E20000
462 #define MAX_CHAR_CBETA 0x00E2FFFF
463 #define MIN_CHAR_CHINA3_JEF 0x00E80000
464 #define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
466 #define MIN_CHAR_94 0x00E90940
467 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
468 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
469 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
471 #define MIN_CHAR_94x94 0xE9F6C0
472 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
473 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
474 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
475 #define MIN_CHAR_96x96 0xF4C000
476 #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 + 66773)
480 #define MIN_CHAR_BIG5_CDP 0x62000000
481 #define MAX_CHAR_BIG5_CDP 0x6200FFFF
482 #define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
483 #define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
484 #define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
485 #define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
486 #define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
487 #define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
488 #define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
489 #define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
490 #define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
491 #define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
492 #define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
493 #define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
494 #define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
495 #define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
496 #define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
497 #define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
498 #define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
499 #define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
500 #define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
501 #define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
502 #define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
503 #define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
504 #define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
505 #define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
507 Emchar decode_builtin_char (Lisp_Object charset, int code_point);
509 extern Lisp_Object Vcharset_chinese_big5;
510 extern Lisp_Object Vcharset_chinese_big5_1;
511 extern Lisp_Object Vcharset_chinese_big5_2;
513 INLINE_HEADER Lisp_Object
514 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
515 INLINE_HEADER Lisp_Object
516 get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
518 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
522 int idx = code - byte_offset;
524 if (idx < XVECTOR_LENGTH(table))
525 return XVECTOR_DATA(table)[idx];
533 INLINE_HEADER Lisp_Object
534 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
536 INLINE_HEADER Lisp_Object
537 put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
540 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
541 int ccs_len = XCHARSET_BYTE_SIZE (ccs);
545 XVECTOR_DATA(table)[code - byte_offset] = value;
548 else if (EQ (table, value))
552 table = make_vector (ccs_len, table);
553 XVECTOR_DATA(table)[code - byte_offset] = value;
559 decoding_table_put_char (Lisp_Object ccs,
560 int code_point, Lisp_Object character);
562 decoding_table_put_char (Lisp_Object ccs,
563 int code_point, Lisp_Object character)
566 Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
567 int dim = XCHARSET_DIMENSION (ccs);
570 XCHARSET_DECODING_TABLE (ccs)
571 = put_ccs_octet_table (table1, ccs, code_point, character);
575 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
577 table2 = put_ccs_octet_table (table2, ccs,
578 (unsigned char)code_point, character);
579 XCHARSET_DECODING_TABLE (ccs)
580 = put_ccs_octet_table (table1, ccs,
581 (unsigned char)(code_point >> 8), table2);
586 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
588 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
590 table3 = put_ccs_octet_table (table3, ccs,
591 (unsigned char)code_point, character);
592 table2 = put_ccs_octet_table (table2, ccs,
593 (unsigned char)(code_point >> 8), table3);
594 XCHARSET_DECODING_TABLE (ccs)
595 = put_ccs_octet_table (table1, ccs,
596 (unsigned char)(code_point >> 16), table2);
598 else /* if (dim == 4) */
601 = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
603 = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
605 = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
607 table4 = put_ccs_octet_table (table4, ccs,
608 (unsigned char)code_point, character);
609 table3 = put_ccs_octet_table (table3, ccs,
610 (unsigned char)(code_point >> 8), table4);
611 table2 = put_ccs_octet_table (table2, ccs,
612 (unsigned char)(code_point >> 16), table3);
613 XCHARSET_DECODING_TABLE (ccs)
614 = put_ccs_octet_table (table1, ccs,
615 (unsigned char)(code_point >> 24), table2);
618 Lisp_Object v = XCHARSET_DECODING_TABLE (ccs);
619 int dim = XCHARSET_DIMENSION (ccs);
620 int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
623 int ccs_len = XVECTOR_LENGTH (v);
628 i = ((code_point >> (8 * dim)) & 255) - byte_offset;
629 nv = XVECTOR_DATA(v)[i];
634 if (EQ (nv, character))
637 nv = (XVECTOR_DATA(v)[i] = make_vector (ccs_len, Qnil));
644 XVECTOR_DATA(v)[i] = character;
649 decoding_table_remove_char (Lisp_Object ccs, int code_point);
651 decoding_table_remove_char (Lisp_Object ccs, int code_point)
653 decoding_table_put_char (ccs, code_point, Qunbound);
657 Emchar load_char_decoding_entry_maybe (Lisp_Object ccs, int code_point);
661 DECODE_DEFINED_CHAR (Lisp_Object charset, int code_point);
663 DECODE_DEFINED_CHAR (Lisp_Object ccs, int code_point)
665 int dim = XCHARSET_DIMENSION (ccs);
666 Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (ccs);
672 = get_ccs_octet_table (decoding_table, ccs,
673 (code_point >> (dim * 8)) & 255);
675 if (CHARP (decoding_table))
676 return XCHAR (decoding_table);
678 if (EQ (decoding_table, Qunloaded) ||
679 EQ (decoding_table, Qunbound) ||
680 NILP (decoding_table) )
682 return load_char_decoding_entry_maybe (ccs, code_point);
689 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
691 DECODE_CHAR (Lisp_Object charset, int code_point)
693 Emchar char_id = DECODE_DEFINED_CHAR (charset, code_point);
697 else if (XCHARSET_DIMENSION (charset) == 1)
698 return decode_builtin_char (charset, code_point);
699 else if (EQ (charset, Vcharset_chinese_big5_1))
702 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
703 + ((code_point & 0xFF) - 33);
704 unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
705 unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
707 b2 += b2 < 0x3F ? 0x40 : 0x62;
708 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
710 else if (EQ (charset, Vcharset_chinese_big5_2))
713 = ((code_point >> 8) - 33) * (0xFF - 0xA1)
714 + ((code_point & 0xFF) - 33);
715 unsigned char b1, b2;
717 I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
718 b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
719 b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
720 b2 += b2 < 0x3F ? 0x40 : 0x62;
721 return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
723 return decode_builtin_char (charset, code_point);
726 /* Return a character whose charset is CHARSET and position-codes
727 are C1 and C2. TYPE9N character ignores C2. */
729 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
731 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
733 if (XCHARSET_DIMENSION (charset) == 1)
734 return DECODE_CHAR (charset, c1);
736 return DECODE_CHAR (charset, (c1 << 8) | c2);
739 extern Lisp_Object Vcharacter_attribute_table;
741 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
742 int charset_code_point (Lisp_Object charset, Emchar ch);
743 int range_charset_code_point (Lisp_Object charset, Emchar ch);
745 extern Lisp_Object Vdefault_coded_charset_priority_list;
746 EXFUN (Ffind_charset, 1);
748 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
750 encode_char_1 (Emchar ch, Lisp_Object* charset)
752 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
754 while (!NILP (charsets))
756 *charset = Ffind_charset (Fcar (charsets));
757 if (!NILP (*charset))
759 int code_point = charset_code_point (*charset, ch);
764 charsets = Fcdr (charsets);
767 /* otherwise --- maybe for bootstrap */
768 return encode_builtin_char_1 (ch, charset);
771 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
774 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
776 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
778 int code_point = encode_char_1 (c, charset);
782 int dim = XCHARSET_DIMENSION (*charset);
789 else /* if (dim == 2) */
791 *c1 = code_point >> 8;
792 *c2 = code_point & 255;
800 #define BREAKUP_CHAR(ch, charset, b1, b2) \
801 breakup_char_1 (ch, &(charset), &(b1), &(b2))
803 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
804 INLINE_HEADER Lisp_Object
805 CHAR_CHARSET (Emchar ch)
809 ENCODE_CHAR (ch, charset);
813 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
814 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
823 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
825 CHAR_TO_CHARC (Emchar ch)
829 cc.code_point = encode_char_1 (ch, &cc.charset);
834 /************************************************************************/
835 /* Exported functions */
836 /************************************************************************/
838 EXFUN (Fget_charset, 1);
840 extern Lisp_Object Qucs;
842 extern Lisp_Object Vcharset_japanese_jisx0208;
843 extern Lisp_Object Vcharset_japanese_jisx0208_1990;
844 extern Lisp_Object Vcharset_japanese_jisx0212;
846 Lisp_Object put_char_ccs_code_point (Lisp_Object character,
847 Lisp_Object ccs, Lisp_Object value);
848 Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
850 #endif /* INCLUDED_char_ucs_h_ */