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)
37 } Emchar_to_byte_table;
40 get_byte_from_character_table (Emchar ch, Emchar_to_byte_table* table);
43 extern Lisp_Object Vcharset_ucs_bmp;
45 extern Lisp_Object Vcharset_latin_jisx0201;
46 extern Emchar latin_jisx0201_to_ucs[94];
47 extern Emchar_to_byte_table* ucs_to_latin_jisx0201;
49 extern Lisp_Object Vcharset_latin_iso8859_2;
50 extern Emchar latin_iso8859_2_to_ucs[96];
51 extern Emchar_to_byte_table* ucs_to_latin_iso8859_2;
53 extern Lisp_Object Vcharset_latin_iso8859_3;
54 extern Emchar latin_iso8859_3_to_ucs[96];
55 extern Emchar_to_byte_table* ucs_to_latin_iso8859_3;
57 extern Lisp_Object Vcharset_latin_iso8859_4;
58 extern Emchar latin_iso8859_4_to_ucs[96];
59 extern Emchar_to_byte_table* ucs_to_latin_iso8859_4;
61 extern Lisp_Object Vcharset_latin_iso8859_9;
62 extern Emchar latin_iso8859_9_to_ucs[96];
63 extern Emchar_to_byte_table* ucs_to_latin_iso8859_9;
65 extern Lisp_Object Vcharset_latin_viscii_lower;
66 extern Emchar latin_viscii_lower_to_ucs[96];
67 extern Emchar_to_byte_table* ucs_to_latin_viscii_lower;
69 extern Lisp_Object Vcharset_latin_viscii_upper;
70 extern Emchar latin_viscii_upper_to_ucs[96];
71 extern Emchar_to_byte_table* ucs_to_latin_viscii_upper;
74 /************************************************************************/
75 /* Definition of leading bytes */
76 /************************************************************************/
78 typedef int Charset_ID;
80 #define MIN_LEADING_BYTE 0x80
82 #define LEADING_BYTE_UCS_BMP 0x80
83 #define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */
86 #define CHARSET_ID_OFFSET_94 0x55
88 #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0')
89 #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?')
92 #define LEADING_BYTE_ASCII (CHARSET_ID_OFFSET_94 + 'B')
94 /* Right half of JIS X0201-1976 */
95 #define LEADING_BYTE_KATAKANA_JISX0201 (CHARSET_ID_OFFSET_94 + 'I')
97 /* Left half of JIS X0201-1976 */
98 #define LEADING_BYTE_LATIN_JISX0201 (CHARSET_ID_OFFSET_94 + 'J')
101 #define CHARSET_ID_OFFSET_96 0x70
103 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET_96 + '1')
104 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET_96 + '2')
106 /* Right half of ISO 8859-1 */
107 #define LEADING_BYTE_LATIN_ISO8859_1 (CHARSET_ID_OFFSET_96 + 'A')
109 /* Right half of ISO 8859-2 */
110 #define LEADING_BYTE_LATIN_ISO8859_2 (CHARSET_ID_OFFSET_96 + 'B')
112 /* Right half of ISO 8859-3 */
113 #define LEADING_BYTE_LATIN_ISO8859_3 (CHARSET_ID_OFFSET_96 + 'C')
115 /* Right half of ISO 8859-4 */
116 #define LEADING_BYTE_LATIN_ISO8859_4 (CHARSET_ID_OFFSET_96 + 'D')
118 /* Right half of ISO 8859-7 */
119 #define LEADING_BYTE_GREEK_ISO8859_7 (CHARSET_ID_OFFSET_96 + 'F')
121 /* Right half of ISO 8859-6 */
122 #define LEADING_BYTE_ARABIC_ISO8859_6 (CHARSET_ID_OFFSET_96 + 'G')
124 /* Right half of ISO 8859-8 */
125 #define LEADING_BYTE_HEBREW_ISO8859_8 (CHARSET_ID_OFFSET_96 + 'H')
127 /* Right half of ISO 8859-5 */
128 #define LEADING_BYTE_CYRILLIC_ISO8859_5 (CHARSET_ID_OFFSET_96 + 'L')
130 /* Right half of ISO 8859-9 */
131 #define LEADING_BYTE_LATIN_ISO8859_9 (CHARSET_ID_OFFSET_96 + 'M')
134 #define LEADING_BYTE_THAI_TIS620 (CHARSET_ID_OFFSET_96 + 'T')
137 #define MIN_LEADING_BYTE_PRIVATE_1 0xD0
138 #define MAX_LEADING_BYTE_PRIVATE_1 0xDF
141 #define CHARSET_ID_OFFSET_94x94 0xB0
144 #define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94)
147 #define LEADING_BYTE_CHINESE_BIG5_2 ('1' + CHARSET_ID_OFFSET_94x94)
149 #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94)
150 #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94)
152 /* Japanese JIS X0208-1978 */
153 #define LEADING_BYTE_JAPANESE_JISX0208_1978 \
154 ('@' + CHARSET_ID_OFFSET_94x94)
156 /* Chinese Hanzi GB2312-1980 */
157 #define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94)
159 /* Japanese JIS X0208-1983 */
160 #define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94)
162 /* Hangul KS C5601-1987 */
163 #define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94)
165 /* Japanese JIS X0212-1990 */
166 #define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94)
168 /* CCITT Extended GB */
169 #define LEADING_BYTE_CHINESE_CCITT_GB ('E' + CHARSET_ID_OFFSET_94x94)
171 /* Chinese CNS11643 Set 1 */
172 #define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + CHARSET_ID_OFFSET_94x94)
174 /* Chinese CNS11643 Set 2 */
175 #define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + CHARSET_ID_OFFSET_94x94)
177 /* Chinese CNS11643 Set 3 */
178 #define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + CHARSET_ID_OFFSET_94x94)
180 /* Chinese CNS11643 Set 4 */
181 #define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + CHARSET_ID_OFFSET_94x94)
183 /* Chinese CNS11643 Set 5 */
184 #define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + CHARSET_ID_OFFSET_94x94)
186 /* Chinese CNS11643 Set 6 */
187 #define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + CHARSET_ID_OFFSET_94x94)
189 /* Chinese CNS11643 Set 7 */
190 #define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + CHARSET_ID_OFFSET_94x94)
192 /* DPRK Hangul KPS 9566-1997 */
193 #define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94)
195 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
196 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566
198 #define NUM_LEADING_BYTES 256
201 /************************************************************************/
202 /* Information about a particular character set */
203 /************************************************************************/
207 struct lcrecord_header header;
211 Lisp_Object doc_string, registry, short_name, long_name;
213 Lisp_Object reverse_direction_charset;
215 Lisp_Object ccl_program;
217 /* Final byte of this character set in ISO2022 designating escape sequence */
220 /* Number of bytes (1 - 4) required in the internal representation
221 for characters in this character set. This is *not* the
222 same as the dimension of the character set). */
223 unsigned int rep_bytes;
225 /* Number of columns a character in this charset takes up, on TTY
226 devices. Not used for X devices. */
227 unsigned int columns;
229 /* Direction of this character set */
230 unsigned int direction;
232 /* Type of this character set (94, 96, 94x94, 96x96) */
235 /* Number of bytes used in encoding of this character set (1 or 2) */
236 unsigned int dimension;
238 /* Number of chars in each dimension (usually 94 or 96) */
241 /* Which half of font to be used to display this character set */
242 unsigned int graphic;
245 DECLARE_LRECORD (charset, struct Lisp_Charset);
246 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
247 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
248 #define CHARSETP(x) RECORDP (x, charset)
249 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
250 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
251 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
253 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
254 #define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */
255 #define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */
256 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
257 #define CHARSET_TYPE_128X128 4 /* This charset includes 128x128 characters. */
258 #define CHARSET_TYPE_256X256 5 /* This charset includes 256x256 characters. */
260 #define CHARSET_LEFT_TO_RIGHT 0
261 #define CHARSET_RIGHT_TO_LEFT 1
263 /* Leading byte and id have been regrouped. -- OG */
264 #define CHARSET_ID(cs) ((cs)->id)
265 #define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs)))
266 #define CHARSET_NAME(cs) ((cs)->name)
267 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
268 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
269 #define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes)
270 #define CHARSET_COLUMNS(cs) ((cs)->columns)
271 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
272 #define CHARSET_TYPE(cs) ((cs)->type)
273 #define CHARSET_DIRECTION(cs) ((cs)->direction)
274 #define CHARSET_FINAL(cs) ((cs)->final)
275 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
276 #define CHARSET_REGISTRY(cs) ((cs)->registry)
277 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
278 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
279 #define CHARSET_CHARS(cs) ((cs)->chars)
280 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
283 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
284 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
285 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
286 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
287 #define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs))
288 #define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs))
289 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
290 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
291 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
292 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
293 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
294 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
295 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
296 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
297 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
298 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
299 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
300 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
302 /* Table of charsets indexed by (leading byte - 128). */
303 extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
305 /* Table of charsets indexed by type/final-byte. */
306 extern Lisp_Object charset_by_attributes[4][128];
308 #ifdef ERROR_CHECK_TYPECHECK
309 /* int not Bufbyte even though that is the actual type of a leading byte.
310 This way, out-ot-range values will get caught rather than automatically
312 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
314 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
316 assert (lb >= MIN_LEADING_BYTE &&
317 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
318 return charset_by_leading_byte[lb - MIN_LEADING_BYTE];
323 #define CHARSET_BY_LEADING_BYTE(lb) \
324 (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
328 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
329 (charset_by_attributes[type][final])
332 /************************************************************************/
333 /* Dealing with characters */
334 /************************************************************************/
336 #define MAX_CHAR_BASIC_LATIN 0x007F
338 #define MIN_CHAR_GREEK 0x0370
339 #define MAX_CHAR_GREEK 0x03CF
341 #define MIN_CHAR_CYRILLIC 0x0400
342 #define MAX_CHAR_CYRILLIC 0x045F
344 #define MIN_CHAR_HEBREW 0x0590
345 #define MAX_CHAR_HEBREW 0x05EF
347 #define MIN_CHAR_THAI 0x0E00
348 #define MAX_CHAR_THAI 0x0E5F
350 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
351 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
353 #define MIN_CHAR_94 0xE90940
354 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
355 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
356 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
358 #define MIN_CHAR_94x94 0xE9F6C0
359 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
360 #define MIN_CHAR_96x96 0xF4C000
361 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
364 /* Return a character whose charset is CHARSET and position-codes
365 are C1 and C2. TYPE9N character ignores C2. */
367 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
369 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
371 if (EQ (charset, Vcharset_ascii))
373 else if (EQ (charset, Vcharset_control_1))
375 else if (EQ (charset, Vcharset_ucs_bmp))
376 return (c1 << 8) | c2;
377 else if (EQ (charset, Vcharset_latin_iso8859_1))
379 else if (EQ (charset, Vcharset_latin_iso8859_2))
380 return latin_iso8859_2_to_ucs[c1 - 32];
381 else if (EQ (charset, Vcharset_latin_iso8859_3))
382 return latin_iso8859_3_to_ucs[c1 - 32];
383 else if (EQ (charset, Vcharset_latin_iso8859_4))
384 return latin_iso8859_4_to_ucs[c1 - 32];
385 else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
386 return c1 + MIN_CHAR_CYRILLIC - 0x20;
387 else if (EQ (charset, Vcharset_greek_iso8859_7))
388 return c1 + MIN_CHAR_GREEK - 0x20;
389 else if (EQ (charset, Vcharset_hebrew_iso8859_8))
390 return c1 + MIN_CHAR_HEBREW - 0x20;
391 else if (EQ (charset, Vcharset_latin_iso8859_9))
392 return latin_iso8859_9_to_ucs[c1 - 32];
393 else if (EQ (charset, Vcharset_thai_tis620))
394 return c1 + MIN_CHAR_THAI - 0x20;
395 else if (EQ (charset, Vcharset_katakana_jisx0201))
397 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
400 else if (EQ (charset, Vcharset_latin_jisx0201))
401 return latin_jisx0201_to_ucs[c1 - 33];
402 else if (EQ (charset, Vcharset_latin_viscii_lower))
403 return latin_viscii_lower_to_ucs[c1 - 32];
404 else if (EQ (charset, Vcharset_latin_viscii_upper))
405 return latin_viscii_upper_to_ucs[c1 - 32];
406 else if (XCHARSET_DIMENSION (charset) == 1)
408 switch (XCHARSET_CHARS (charset))
412 + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
415 + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
422 switch (XCHARSET_CHARS (charset))
425 return MIN_CHAR_94x94
426 + (XCHARSET_FINAL (charset) - '0') * 94 * 94
427 + (c1 - 33) * 94 + (c2 - 33);
429 return MIN_CHAR_96x96
430 + (XCHARSET_FINAL (charset) - '0') * 96 * 96
431 + (c1 - 32) * 96 + (c2 - 32);
438 extern Charset_ID latin_a_char_to_charset[128];
439 extern unsigned char latin_a_char_to_byte1[128];
440 extern unsigned char latin_a_char_to_byte2[128];
442 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
444 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
446 if (c <= MAX_CHAR_BASIC_LATIN)
448 *charset = Vcharset_ascii;
454 *charset = Vcharset_control_1;
460 *charset = Vcharset_latin_iso8859_1;
467 = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]);
469 if (EQ (*charset, Vcharset_latin_iso8859_2))
471 *c1 = get_byte_from_character_table (c, ucs_to_latin_iso8859_2);
474 else if (EQ (*charset, Vcharset_latin_iso8859_3))
476 *c1 = get_byte_from_character_table (c, ucs_to_latin_iso8859_3);
479 else if (EQ (*charset, Vcharset_latin_iso8859_4))
481 *c1 = get_byte_from_character_table (c, ucs_to_latin_iso8859_4);
484 else if (EQ (*charset, Vcharset_latin_iso8859_9))
486 *c1 = get_byte_from_character_table (c, ucs_to_latin_iso8859_9);
491 *c1 = latin_a_char_to_byte1[c - 0x100];
492 *c2 = latin_a_char_to_byte2[c - 0x100];
495 else if (c < MIN_CHAR_GREEK)
497 if ( (*c1 = get_byte_from_character_table (c, ucs_to_latin_iso8859_2)) )
499 *charset = Vcharset_latin_iso8859_2;
503 get_byte_from_character_table (c, ucs_to_latin_iso8859_3)) )
505 *charset = Vcharset_latin_iso8859_3;
509 get_byte_from_character_table (c, ucs_to_latin_iso8859_4)) )
511 *charset = Vcharset_latin_iso8859_4;
515 get_byte_from_character_table (c, ucs_to_latin_iso8859_9)) )
517 *charset = Vcharset_latin_iso8859_9;
521 get_byte_from_character_table (c,
522 ucs_to_latin_viscii_lower)) )
524 *charset = Vcharset_latin_viscii_lower;
528 get_byte_from_character_table (c,
529 ucs_to_latin_viscii_upper)) )
531 *charset = Vcharset_latin_viscii_upper;
536 *charset = Vcharset_ucs_bmp;
541 else if (c <= MAX_CHAR_GREEK)
543 *charset = Vcharset_greek_iso8859_7;
544 *c1 = c - MIN_CHAR_GREEK + 0x20;
547 else if (c < MIN_CHAR_CYRILLIC)
549 *charset = Vcharset_ucs_bmp;
553 else if (c <= MAX_CHAR_CYRILLIC)
555 *charset = Vcharset_cyrillic_iso8859_5;
556 *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
559 else if (c < MIN_CHAR_HEBREW)
561 *charset = Vcharset_ucs_bmp;
565 else if (c <= MAX_CHAR_HEBREW)
567 *charset = Vcharset_hebrew_iso8859_8;
568 *c1 = c - MIN_CHAR_HEBREW + 0x20;
571 else if (c < MIN_CHAR_THAI)
573 *charset = Vcharset_ucs_bmp;
577 else if (c <= MAX_CHAR_THAI)
579 *charset = Vcharset_thai_tis620;
580 *c1 = c - MIN_CHAR_THAI + 0x20;
583 else if (c < MIN_CHAR_HALFWIDTH_KATAKANA)
585 if ( (*c1 = get_byte_from_character_table (c, ucs_to_latin_jisx0201)) )
587 *charset = Vcharset_latin_jisx0201;
590 else if ( (*c1 = get_byte_from_character_table
591 (c, ucs_to_latin_viscii_lower)) )
593 *charset = Vcharset_latin_viscii_lower;
596 else if ( (*c1 = get_byte_from_character_table
597 (c, ucs_to_latin_viscii_upper)) )
599 *charset = Vcharset_latin_viscii_upper;
604 *charset = Vcharset_ucs_bmp;
609 else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
611 *charset = Vcharset_katakana_jisx0201;
612 *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
615 else if (c <= MAX_CHAR_94)
618 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
619 ((c - MIN_CHAR_94) / 94) + '0',
620 CHARSET_LEFT_TO_RIGHT);
621 *c1 = ((c - MIN_CHAR_94) % 94) + 33;
624 else if (c <= MAX_CHAR_96)
627 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
628 ((c - MIN_CHAR_96) / 96) + '0',
629 CHARSET_LEFT_TO_RIGHT);
630 *c1 = ((c - MIN_CHAR_96) % 96) + 32;
633 else if (c <= MAX_CHAR_94x94)
636 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94,
637 ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
638 CHARSET_LEFT_TO_RIGHT);
639 *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33;
640 *c2 = ((c - MIN_CHAR_94x94) % 94) + 33;
642 else if (c <= MAX_CHAR_96x96)
645 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96,
646 ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
647 CHARSET_LEFT_TO_RIGHT);
648 *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32;
649 *c2 = ((c - MIN_CHAR_96x96) % 96) + 32;
658 #define BREAKUP_CHAR(ch, charset, b1, b2) \
659 breakup_char_1 (ch, &(charset), &(b1), &(b2))
661 INLINE Lisp_Object CHAR_CHARSET (Emchar ch);
663 CHAR_CHARSET (Emchar ch)
668 BREAKUP_CHAR(ch, charset, b1, b2);
672 #define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c)))
675 #ifdef ENABLE_COMPOSITE_CHARS
676 /************************************************************************/
677 /* Composite characters */
678 /************************************************************************/
680 Emchar lookup_composite_char (Bufbyte *str, int len);
681 Lisp_Object composite_char_string (Emchar ch);
682 #endif /* ENABLE_COMPOSITE_CHARS */
685 /************************************************************************/
686 /* Exported functions */
687 /************************************************************************/
689 EXFUN (Ffind_charset, 1);
690 EXFUN (Fget_charset, 1);
692 extern Lisp_Object Vcharset_chinese_big5_1;
693 extern Lisp_Object Vcharset_chinese_big5_2;
694 extern Lisp_Object Vcharset_japanese_jisx0208;
695 extern Lisp_Object Vcharset_japanese_jisx0212;
697 #endif /* _XEMACS_CHAR_UCS_H */