1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
5 This file is part of XEmacs.
7 XEmacs is free software; you can redistribute it and/or modify it
8 under the terms of the GNU General Public License as published by the
9 Free Software Foundation; either version 2, or (at your option) any
12 XEmacs is distributed in the hope that it will be useful, but WITHOUT
13 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
14 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
17 You should have received a copy of the GNU General Public License
18 along with XEmacs; see the file COPYING. If not, write to
19 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
20 Boston, MA 02111-1307, USA. */
22 /* Rewritten by MORIOKA Tomohiko <tomo@m17n.org>. */
24 #ifndef _XEMACS_CHAR_UCS_H
25 #define _XEMACS_CHAR_UCS_H
27 #define valid_char_p(ch) 1
29 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
32 DECLARE_LRECORD (char_byte_table, struct Lisp_Char_Byte_Table);
33 #define XCHAR_BYTE_TABLE(x) \
34 XRECORD (x, char_byte_table, struct Lisp_Char_Byte_Table)
35 #define XSETCHAR_BYTE_TABLE(x, p) XSETRECORD (x, p, char_byte_table)
36 #define CHAR_BYTE_TABLE_P(x) RECORDP (x, char_byte_table)
37 #define GC_CHAR_BYTE_TABLE_P(x) GC_RECORDP (x, char_byte_table)
38 /* #define CHECK_CHAR_BYTE_TABLE(x) CHECK_RECORD (x, char_byte_table)
39 char table entries should never escape to Lisp */
41 struct Lisp_Char_Byte_Table
43 struct lcrecord_header header;
45 Lisp_Object property[256];
49 DECLARE_LRECORD (char_code_table, struct Lisp_Char_Code_Table);
50 #define XCHAR_CODE_TABLE(x) \
51 XRECORD (x, char_code_table, struct Lisp_Char_Code_Table)
52 #define XSETCHAR_CODE_TABLE(x, p) XSETRECORD (x, p, char_code_table)
53 #define CHAR_CODE_TABLE_P(x) RECORDP (x, char_code_table)
54 #define GC_CHAR_CODE_TABLE_P(x) GC_RECORDP (x, char_code_table)
55 /* #define CHECK_CHAR_CODE_TABLE(x) CHECK_RECORD (x, char_code_table)
56 char table entries should never escape to Lisp */
58 struct Lisp_Char_Code_Table
60 struct lcrecord_header header;
65 Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table);
68 extern Lisp_Object Vcharset_ucs_bmp;
69 extern Lisp_Object Vcharset_latin_jisx0201;
70 extern Lisp_Object Vcharset_latin_iso8859_2;
71 extern Lisp_Object Vcharset_latin_iso8859_3;
72 extern Lisp_Object Vcharset_latin_iso8859_4;
73 extern Lisp_Object Vcharset_latin_iso8859_9;
74 extern Lisp_Object Vcharset_latin_viscii_lower;
75 extern Lisp_Object Vcharset_latin_viscii_upper;
78 /************************************************************************/
79 /* Definition of leading bytes */
80 /************************************************************************/
82 typedef int Charset_ID;
84 #define MIN_LEADING_BYTE -0x40
85 #define CHARSET_ID_OFFSET 0x00
87 /* represent normal 80-9F */
88 #define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 1)
90 /* ISO/IEC 10646 BMP */
91 #define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 2)
94 #define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 3)
96 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
97 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 4)
99 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
100 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 5)
102 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
103 #define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 6)
105 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
106 #define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 7)
108 #define LEADING_BYTE_HIRAGANA_JISX0208 (CHARSET_ID_OFFSET - 8)
109 #define LEADING_BYTE_KATAKANA_JISX0208 (CHARSET_ID_OFFSET - 9)
111 #define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
112 #define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 10)
115 /* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
117 /* #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') */
118 /* #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') */
121 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
123 /* Right half of JIS X0201-1976 */
124 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
126 /* Left half of JIS X0201-1976 */
127 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
130 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
132 /* Right half of ISO 8859-1 */
133 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
135 /* Right half of ISO 8859-2 */
136 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
138 /* Right half of ISO 8859-3 */
139 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
141 /* Right half of ISO 8859-4 */
142 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
144 /* Right half of ISO 8859-7 */
145 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
147 /* Right half of ISO 8859-6 */
148 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
150 /* Right half of ISO 8859-8 */
151 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
153 /* Right half of ISO 8859-5 */
154 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
156 /* Right half of ISO 8859-9 */
157 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
160 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
163 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
166 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
167 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
169 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
170 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
172 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
173 #define LEADING_BYTE_CHINESE_GB2312 58
175 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
176 #define LEADING_BYTE_JAPANESE_JISX0208 87
178 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
179 #define LEADING_BYTE_KOREAN_KSC5601 149
181 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
182 #define LEADING_BYTE_JAPANESE_JISX0212 159
184 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
185 #define LEADING_BYTE_CHINESE_CCITT_GB 165
187 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
188 #define LEADING_BYTE_CHINESE_CNS11643_1 171
190 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
191 #define LEADING_BYTE_CHINESE_CNS11643_2 172
193 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
194 #define LEADING_BYTE_CHINESE_CNS11643_3 183
196 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
197 #define LEADING_BYTE_CHINESE_CNS11643_4 184
199 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
200 #define LEADING_BYTE_CHINESE_CNS11643_5 185
202 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
203 #define LEADING_BYTE_CHINESE_CNS11643_6 186
205 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
206 #define LEADING_BYTE_CHINESE_CNS11643_7 187
208 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
209 #define LEADING_BYTE_KOREAN_KPS9566 202
212 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
215 /************************************************************************/
216 /* Information about a particular character set */
217 /************************************************************************/
221 struct lcrecord_header header;
225 Lisp_Object doc_string, registry, short_name, long_name;
227 Lisp_Object reverse_direction_charset;
229 Lisp_Object ccl_program;
231 /* Final byte of this character set in ISO2022 designating escape sequence */
234 /* Number of columns a character in this charset takes up, on TTY
235 devices. Not used for X devices. */
236 unsigned int columns;
238 /* Direction of this character set */
239 unsigned int direction;
241 /* Type of this character set (94, 96, 94x94, 96x96) */
244 /* Number of bytes used in encoding of this character set (1 or 2) */
245 unsigned int dimension;
247 /* Number of chars in each dimension (usually 94 or 96) */
250 /* Which half of font to be used to display this character set */
251 unsigned int graphic;
253 /* Byte->character mapping table */
254 Lisp_Object decoding_table;
256 /* Range of character code */
257 Emchar ucs_min, ucs_max;
259 /* Offset for external code */
262 /* Offset for each byte */
266 DECLARE_LRECORD (charset, struct Lisp_Charset);
267 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
268 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
269 #define CHARSETP(x) RECORDP (x, charset)
270 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
271 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
272 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
274 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
275 #define CHARSET_TYPE_94X94 1 /* This charset includes 94x94 characters. */
276 #define CHARSET_TYPE_96 2 /* This charset includes 96 characters. */
277 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
278 #define CHARSET_TYPE_128 4 /* This charset includes 128 characters. */
279 #define CHARSET_TYPE_128X128 5 /* This charset includes 128x128 characters. */
280 #define CHARSET_TYPE_256 6 /* This charset includes 256 characters. */
281 #define CHARSET_TYPE_256X256 7 /* This charset includes 256x256 characters. */
283 #define CHARSET_LEFT_TO_RIGHT 0
284 #define CHARSET_RIGHT_TO_LEFT 1
286 /* Leading byte and id have been regrouped. -- OG */
287 #define CHARSET_ID(cs) ((cs)->id)
288 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
289 #define CHARSET_NAME(cs) ((cs)->name)
290 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
291 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
292 #define CHARSET_COLUMNS(cs) ((cs)->columns)
293 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
294 #define CHARSET_TYPE(cs) ((cs)->type)
295 #define CHARSET_DIRECTION(cs) ((cs)->direction)
296 #define CHARSET_FINAL(cs) ((cs)->final)
297 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
298 #define CHARSET_REGISTRY(cs) ((cs)->registry)
299 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
300 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
301 #define CHARSET_CHARS(cs) ((cs)->chars)
302 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
303 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
304 #define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
305 #define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
306 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
307 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
310 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
311 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
312 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
313 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
314 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
315 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
316 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
317 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
318 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
319 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
320 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
321 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
322 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
323 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
324 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
325 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
326 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
327 #define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs))
328 #define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs))
329 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
330 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
332 /* Table of charsets indexed by (leading byte - 128). */
333 extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
335 /* Table of charsets indexed by type/final-byte. */
336 extern Lisp_Object charset_by_attributes[4][128];
338 #ifdef ERROR_CHECK_TYPECHECK
339 /* int not Bufbyte even though that is the actual type of a leading byte.
340 This way, out-ot-range values will get caught rather than automatically
342 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
344 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
346 assert (lb >= MIN_LEADING_BYTE &&
347 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
348 return charset_by_leading_byte[lb - MIN_LEADING_BYTE];
353 #define CHARSET_BY_LEADING_BYTE(lb) \
354 (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
358 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
359 (charset_by_attributes[type][final])
362 /************************************************************************/
363 /* Dealing with characters */
364 /************************************************************************/
366 #define MAX_CHAR_BASIC_LATIN 0x007F
368 #define MIN_CHAR_GREEK 0x0370
369 #define MAX_CHAR_GREEK 0x03CF
371 #define MIN_CHAR_CYRILLIC 0x0400
372 #define MAX_CHAR_CYRILLIC 0x045F
374 #define MIN_CHAR_HEBREW 0x0590
375 #define MAX_CHAR_HEBREW 0x05EF
377 #define MIN_CHAR_THAI 0x0E00
378 #define MAX_CHAR_THAI 0x0E5F
380 #define MIN_CHAR_HIRAGANA 0x3041
381 #define MAX_CHAR_HIRAGANA 0x3093
383 #define MIN_CHAR_KATAKANA 0x30A1
384 #define MAX_CHAR_KATAKANA 0x30F6
386 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
387 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
389 #define MIN_CHAR_OBS_94x94 0xE00000
390 #define MAX_CHAR_OBS_94x94 (0xE00000 + 94 * 94 * 14 - 1)
392 #define MIN_CHAR_94 0xE90940
393 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
394 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
395 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
397 #define MIN_CHAR_94x94 0xE9F6C0
398 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
399 #define MIN_CHAR_96x96 0xF4C000
400 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
403 /* Return a character whose charset is CHARSET and position-codes
404 are C1 and C2. TYPE9N character ignores C2. */
406 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
408 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
410 Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
414 if (!EQ (decoding_table, Qnil)
415 && (0 <= (idx = c1 - XCHARSET_BYTE_OFFSET (charset)))
416 && (idx < XVECTOR_LENGTH (decoding_table))
417 && !EQ (ch = XVECTOR_DATA(decoding_table)[idx], Qnil))
421 if ((0 <= (idx = c2 - XCHARSET_BYTE_OFFSET (charset)))
422 && (idx < XVECTOR_LENGTH (ch))
423 && !EQ (ch = XVECTOR_DATA(ch)[idx], Qnil))
429 if (EQ (charset, Vcharset_katakana_jisx0201))
431 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 33;
433 /* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */
435 else if (XCHARSET_UCS_MAX (charset))
438 = (XCHARSET_DIMENSION (charset) == 1
440 c1 - XCHARSET_BYTE_OFFSET (charset)
442 (c1 - XCHARSET_BYTE_OFFSET (charset)) * XCHARSET_CHARS (charset)
443 + c2 - XCHARSET_BYTE_OFFSET (charset))
444 - XCHARSET_CODE_OFFSET (charset) + XCHARSET_UCS_MIN (charset);
445 if ((code < XCHARSET_UCS_MIN (charset))
446 || (XCHARSET_UCS_MAX (charset) < code))
447 signal_simple_error ("Arguments makes invalid character",
451 else if (XCHARSET_DIMENSION (charset) == 1)
453 switch (XCHARSET_CHARS (charset))
457 + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
460 + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
467 switch (XCHARSET_CHARS (charset))
470 return MIN_CHAR_94x94
471 + (XCHARSET_FINAL (charset) - '0') * 94 * 94
472 + (c1 - 33) * 94 + (c2 - 33);
474 return MIN_CHAR_96x96
475 + (XCHARSET_FINAL (charset) - '0') * 96 * 96
476 + (c1 - 32) * 96 + (c2 - 32);
483 extern Lisp_Object Vcharacter_attribute_table;
485 Lisp_Object range_charset_code_point (Lisp_Object charset, Emchar ch);
486 Lisp_Object charset_code_point (Lisp_Object charset, Emchar ch);
488 extern Lisp_Object Vdefault_coded_charset_priority_list;
489 EXFUN (Ffind_charset, 1);
491 INLINE Lisp_Object SPLIT_CHAR (Emchar c);
493 SPLIT_CHAR (Emchar c)
495 Lisp_Object cdef = get_char_code_table (c, Vcharacter_attribute_table);
497 if (!EQ (cdef, Qnil))
499 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
502 while (!EQ (charsets, Qnil))
504 Lisp_Object charset = Ffind_charset (Fcar (charsets));
506 if (!EQ (charset, Qnil))
508 if (!NILP (field = Fassq (charset, cdef)))
510 else if (!NILP (field = range_charset_code_point (charset, c)))
511 return Fcons (charset, field);
513 charsets = Fcdr (charsets);
517 /* otherwise --- maybe for bootstrap */
518 if (c < MIN_CHAR_OBS_94x94)
520 if (c <= MAX_CHAR_BASIC_LATIN)
522 return list2 (Vcharset_ascii, make_int (c));
526 return list2 (Vcharset_control_1, make_int (c & 0x7F));
530 return list2 (Vcharset_latin_iso8859_1, make_int (c & 0x7F));
532 else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
534 return list2 (Vcharset_greek_iso8859_7,
535 make_int (c - MIN_CHAR_GREEK + 0x20));
537 else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
539 return list2 (Vcharset_cyrillic_iso8859_5,
540 make_int (c - MIN_CHAR_CYRILLIC + 0x20));
542 else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
544 return list2 (Vcharset_hebrew_iso8859_8,
545 make_int (c - MIN_CHAR_HEBREW + 0x20));
547 else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
549 return list2 (Vcharset_thai_tis620,
550 make_int (c - MIN_CHAR_THAI + 0x20));
552 else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
553 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
555 return list2 (Vcharset_katakana_jisx0201,
556 make_int (c - MIN_CHAR_HALFWIDTH_KATAKANA + 33));
560 return list3 (Vcharset_ucs_bmp,
561 make_int (c >> 8), make_int (c & 0xff));
564 else if (c <= MAX_CHAR_OBS_94x94)
566 return list3 (CHARSET_BY_ATTRIBUTES
568 ((c - MIN_CHAR_OBS_94x94) / (94 * 94)) + '@',
569 CHARSET_LEFT_TO_RIGHT),
570 make_int ((((c - MIN_CHAR_OBS_94x94) / 94) % 94) + 33),
571 make_int (((c - MIN_CHAR_OBS_94x94) % 94) + 33));
573 else if (c <= MAX_CHAR_94)
575 return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
576 ((c - MIN_CHAR_94) / 94) + '0',
577 CHARSET_LEFT_TO_RIGHT),
578 make_int (((c - MIN_CHAR_94) % 94) + 33));
580 else if (c <= MAX_CHAR_96)
582 return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
583 ((c - MIN_CHAR_96) / 96) + '0',
584 CHARSET_LEFT_TO_RIGHT),
585 make_int (((c - MIN_CHAR_96) % 96) + 32));
587 else if (c <= MAX_CHAR_94x94)
589 return list3 (CHARSET_BY_ATTRIBUTES
591 ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
592 CHARSET_LEFT_TO_RIGHT),
593 make_int ((((c - MIN_CHAR_94x94) / 94) % 94) + 33),
594 make_int (((c - MIN_CHAR_94x94) % 94) + 33));
596 else if (c <= MAX_CHAR_96x96)
598 return list3 (CHARSET_BY_ATTRIBUTES
600 ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
601 CHARSET_LEFT_TO_RIGHT),
602 make_int ((((c - MIN_CHAR_96x96) / 96) % 96) + 32),
603 make_int (((c - MIN_CHAR_96x96) % 96) + 32));
611 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
613 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
615 Lisp_Object ret = SPLIT_CHAR (c);
617 *charset = Fcar (ret);
619 if (INTP (Fcar (ret)))
621 *c1 = XINT (Fcar (ret));
623 if (INTP (Fcar (ret)))
624 *c2 = XINT (Fcar (ret));
634 #define BREAKUP_CHAR(ch, charset, b1, b2) \
635 breakup_char_1 (ch, &(charset), &(b1), &(b2))
637 INLINE Lisp_Object CHAR_CHARSET (Emchar ch);
639 CHAR_CHARSET (Emchar ch)
644 BREAKUP_CHAR(ch, charset, b1, b2);
648 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
649 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
652 /************************************************************************/
653 /* Exported functions */
654 /************************************************************************/
656 EXFUN (Fget_charset, 1);
658 extern Lisp_Object Vcharset_chinese_big5_1;
659 extern Lisp_Object Vcharset_chinese_big5_2;
660 extern Lisp_Object Vcharset_japanese_jisx0208;
661 extern Lisp_Object Vcharset_japanese_jisx0212;
663 #endif /* _XEMACS_CHAR_UCS_H */