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;
44 extern Lisp_Object Vcharset_latin_jisx0201;
45 extern Lisp_Object Vcharset_latin_iso8859_2;
46 extern Lisp_Object Vcharset_latin_iso8859_3;
47 extern Lisp_Object Vcharset_latin_iso8859_4;
48 extern Lisp_Object Vcharset_latin_iso8859_9;
49 extern Lisp_Object Vcharset_latin_viscii_lower;
50 extern Lisp_Object Vcharset_latin_viscii_upper;
53 /************************************************************************/
54 /* Definition of leading bytes */
55 /************************************************************************/
57 typedef int Charset_ID;
59 #define MIN_LEADING_BYTE 0x80
61 #define LEADING_BYTE_UCS_BMP 0x80
62 #define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */
65 #define CHARSET_ID_OFFSET_94 0x55
67 #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0')
68 #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?')
71 #define LEADING_BYTE_ASCII (CHARSET_ID_OFFSET_94 + 'B')
73 /* Right half of JIS X0201-1976 */
74 #define LEADING_BYTE_KATAKANA_JISX0201 (CHARSET_ID_OFFSET_94 + 'I')
76 /* Left half of JIS X0201-1976 */
77 #define LEADING_BYTE_LATIN_JISX0201 (CHARSET_ID_OFFSET_94 + 'J')
80 #define CHARSET_ID_OFFSET_96 0x70
82 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET_96 + '1')
83 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET_96 + '2')
85 /* Right half of ISO 8859-1 */
86 #define LEADING_BYTE_LATIN_ISO8859_1 (CHARSET_ID_OFFSET_96 + 'A')
88 /* Right half of ISO 8859-2 */
89 #define LEADING_BYTE_LATIN_ISO8859_2 (CHARSET_ID_OFFSET_96 + 'B')
91 /* Right half of ISO 8859-3 */
92 #define LEADING_BYTE_LATIN_ISO8859_3 (CHARSET_ID_OFFSET_96 + 'C')
94 /* Right half of ISO 8859-4 */
95 #define LEADING_BYTE_LATIN_ISO8859_4 (CHARSET_ID_OFFSET_96 + 'D')
97 /* Right half of ISO 8859-7 */
98 #define LEADING_BYTE_GREEK_ISO8859_7 (CHARSET_ID_OFFSET_96 + 'F')
100 /* Right half of ISO 8859-6 */
101 #define LEADING_BYTE_ARABIC_ISO8859_6 (CHARSET_ID_OFFSET_96 + 'G')
103 /* Right half of ISO 8859-8 */
104 #define LEADING_BYTE_HEBREW_ISO8859_8 (CHARSET_ID_OFFSET_96 + 'H')
106 /* Right half of ISO 8859-5 */
107 #define LEADING_BYTE_CYRILLIC_ISO8859_5 (CHARSET_ID_OFFSET_96 + 'L')
109 /* Right half of ISO 8859-9 */
110 #define LEADING_BYTE_LATIN_ISO8859_9 (CHARSET_ID_OFFSET_96 + 'M')
113 #define LEADING_BYTE_THAI_TIS620 (CHARSET_ID_OFFSET_96 + 'T')
116 #define MIN_LEADING_BYTE_PRIVATE_1 0xD0
117 #define MAX_LEADING_BYTE_PRIVATE_1 0xDF
120 #define CHARSET_ID_OFFSET_94x94 0xB0
123 #define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94)
126 #define LEADING_BYTE_CHINESE_BIG5_2 ('1' + CHARSET_ID_OFFSET_94x94)
128 #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94)
129 #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94)
131 /* Japanese JIS X0208-1978 */
132 #define LEADING_BYTE_JAPANESE_JISX0208_1978 \
133 ('@' + CHARSET_ID_OFFSET_94x94)
135 /* Chinese Hanzi GB2312-1980 */
136 #define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94)
138 /* Japanese JIS X0208-1983 */
139 #define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94)
141 /* Hangul KS C5601-1987 */
142 #define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94)
144 /* Japanese JIS X0212-1990 */
145 #define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94)
147 /* CCITT Extended GB */
148 #define LEADING_BYTE_CHINESE_CCITT_GB ('E' + CHARSET_ID_OFFSET_94x94)
150 /* Chinese CNS11643 Set 1 */
151 #define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + CHARSET_ID_OFFSET_94x94)
153 /* Chinese CNS11643 Set 2 */
154 #define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + CHARSET_ID_OFFSET_94x94)
156 /* Chinese CNS11643 Set 3 */
157 #define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + CHARSET_ID_OFFSET_94x94)
159 /* Chinese CNS11643 Set 4 */
160 #define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + CHARSET_ID_OFFSET_94x94)
162 /* Chinese CNS11643 Set 5 */
163 #define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + CHARSET_ID_OFFSET_94x94)
165 /* Chinese CNS11643 Set 6 */
166 #define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + CHARSET_ID_OFFSET_94x94)
168 /* Chinese CNS11643 Set 7 */
169 #define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + CHARSET_ID_OFFSET_94x94)
171 /* DPRK Hangul KPS 9566-1997 */
172 #define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94)
174 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
175 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566
177 #define NUM_LEADING_BYTES 256
180 /************************************************************************/
181 /* Information about a particular character set */
182 /************************************************************************/
186 struct lcrecord_header header;
190 Lisp_Object doc_string, registry, short_name, long_name;
192 Lisp_Object reverse_direction_charset;
194 Lisp_Object ccl_program;
196 /* Final byte of this character set in ISO2022 designating escape sequence */
199 /* Number of columns a character in this charset takes up, on TTY
200 devices. Not used for X devices. */
201 unsigned int columns;
203 /* Direction of this character set */
204 unsigned int direction;
206 /* Type of this character set (94, 96, 94x94, 96x96) */
209 /* Number of bytes used in encoding of this character set (1 or 2) */
210 unsigned int dimension;
212 /* Number of chars in each dimension (usually 94 or 96) */
215 /* Which half of font to be used to display this character set */
216 unsigned int graphic;
218 /* Byte->character mapping table */
219 Emchar* decoding_table;
221 /* Character->byte mapping table */
222 Emchar_to_byte_table* to_byte1_table;
223 Emchar_to_byte_table* to_byte2_table;
225 /* Range of character code */
226 Emchar ucs_min, ucs_max;
228 /* Offset for external representation */
232 DECLARE_LRECORD (charset, struct Lisp_Charset);
233 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
234 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
235 #define CHARSETP(x) RECORDP (x, charset)
236 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
237 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
238 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
240 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
241 #define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */
242 #define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */
243 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
244 #define CHARSET_TYPE_128X128 4 /* This charset includes 128x128 characters. */
245 #define CHARSET_TYPE_256X256 5 /* This charset includes 256x256 characters. */
247 #define CHARSET_LEFT_TO_RIGHT 0
248 #define CHARSET_RIGHT_TO_LEFT 1
250 /* Leading byte and id have been regrouped. -- OG */
251 #define CHARSET_ID(cs) ((cs)->id)
252 #define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs)))
253 #define CHARSET_NAME(cs) ((cs)->name)
254 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
255 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
256 #define CHARSET_COLUMNS(cs) ((cs)->columns)
257 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
258 #define CHARSET_TYPE(cs) ((cs)->type)
259 #define CHARSET_DIRECTION(cs) ((cs)->direction)
260 #define CHARSET_FINAL(cs) ((cs)->final)
261 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
262 #define CHARSET_REGISTRY(cs) ((cs)->registry)
263 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
264 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
265 #define CHARSET_CHARS(cs) ((cs)->chars)
266 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
267 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
268 #define CHARSET_TO_BYTE1_TABLE(cs) ((cs)->to_byte1_table)
269 #define CHARSET_TO_BYTE2_TABLE(cs) ((cs)->to_byte2_table)
270 #define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
271 #define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
272 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
275 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
276 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
277 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
278 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
279 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
280 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
281 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
282 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
283 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
284 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
285 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
286 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
287 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
288 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
289 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
290 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
291 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
292 #define XCHARSET_TO_BYTE1_TABLE(cs) CHARSET_TO_BYTE1_TABLE(XCHARSET(cs))
293 #define XCHARSET_TO_BYTE2_TABLE(cs) CHARSET_TO_BYTE2_TABLE(XCHARSET(cs))
295 /* Table of charsets indexed by (leading byte - 128). */
296 extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
298 /* Table of charsets indexed by type/final-byte. */
299 extern Lisp_Object charset_by_attributes[4][128];
301 #ifdef ERROR_CHECK_TYPECHECK
302 /* int not Bufbyte even though that is the actual type of a leading byte.
303 This way, out-ot-range values will get caught rather than automatically
305 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
307 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
309 assert (lb >= MIN_LEADING_BYTE &&
310 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
311 return charset_by_leading_byte[lb - MIN_LEADING_BYTE];
316 #define CHARSET_BY_LEADING_BYTE(lb) \
317 (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
321 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
322 (charset_by_attributes[type][final])
325 /************************************************************************/
326 /* Dealing with characters */
327 /************************************************************************/
329 #define MAX_CHAR_BASIC_LATIN 0x007F
331 #define MIN_CHAR_GREEK 0x0370
332 #define MAX_CHAR_GREEK 0x03CF
334 #define MIN_CHAR_CYRILLIC 0x0400
335 #define MAX_CHAR_CYRILLIC 0x045F
337 #define MIN_CHAR_HEBREW 0x0590
338 #define MAX_CHAR_HEBREW 0x05EF
340 #define MIN_CHAR_THAI 0x0E00
341 #define MAX_CHAR_THAI 0x0E5F
343 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
344 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
346 #define MIN_CHAR_94 0xE90940
347 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
348 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
349 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
351 #define MIN_CHAR_94x94 0xE9F6C0
352 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
353 #define MIN_CHAR_96x96 0xF4C000
354 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
357 /* Return a character whose charset is CHARSET and position-codes
358 are C1 and C2. TYPE9N character ignores C2. */
360 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
362 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
364 Emchar* decoding_table;
366 if ((decoding_table = XCHARSET_DECODING_TABLE (charset)) != NULL)
367 return decoding_table[c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32)];
368 else if (EQ (charset, Vcharset_katakana_jisx0201))
370 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
372 /* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */
374 else if (CHARSET_UCS_MAX (XCHARSET (charset)))
375 return (XCHARSET_DIMENSION (charset) == 1
377 c1 - CHARSET_CODE_OFFSET (XCHARSET (charset))
379 (c1 - CHARSET_CODE_OFFSET (XCHARSET (charset)))
380 * XCHARSET_CHARS (charset)
381 + c2 - CHARSET_CODE_OFFSET (XCHARSET (charset)))
382 + CHARSET_UCS_MIN (XCHARSET (charset));
383 else if (XCHARSET_DIMENSION (charset) == 1)
385 switch (XCHARSET_CHARS (charset))
389 + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
392 + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
399 switch (XCHARSET_CHARS (charset))
402 return MIN_CHAR_94x94
403 + (XCHARSET_FINAL (charset) - '0') * 94 * 94
404 + (c1 - 33) * 94 + (c2 - 33);
406 return MIN_CHAR_96x96
407 + (XCHARSET_FINAL (charset) - '0') * 96 * 96
408 + (c1 - 32) * 96 + (c2 - 32);
415 unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch);
416 unsigned char charset_get_byte2 (Lisp_Object charset, Emchar ch);
418 extern Lisp_Object Vdefault_coded_charset_priority_list;
419 EXFUN (Ffind_charset, 1);
421 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
423 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
427 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
428 while (!EQ (charsets, Qnil))
430 *charset = Ffind_charset (Fcar (charsets));
431 if (!EQ (*charset, Qnil)
432 && (*c1 = charset_get_byte1 (*charset, c)) )
434 *c2 = charset_get_byte2 (*charset, c);
437 charsets = Fcdr (charsets);
439 /* otherwise --- maybe for bootstrap */
440 if (c <= MAX_CHAR_BASIC_LATIN)
442 *charset = Vcharset_ascii;
443 *c1 = charset_get_byte1 (*charset, c);
444 *c2 = charset_get_byte2 (*charset, c);
448 *charset = Vcharset_control_1;
449 *c1 = charset_get_byte1 (*charset, c);
450 *c2 = charset_get_byte2 (*charset, c);
454 *charset = Vcharset_latin_iso8859_1;
455 *c1 = charset_get_byte1 (*charset, c);
456 *c2 = charset_get_byte2 (*charset, c);
458 else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
460 *charset = Vcharset_greek_iso8859_7;
461 *c1 = c - MIN_CHAR_GREEK + 0x20;
464 else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
466 *charset = Vcharset_cyrillic_iso8859_5;
467 *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
470 else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
472 *charset = Vcharset_hebrew_iso8859_8;
473 *c1 = c - MIN_CHAR_HEBREW + 0x20;
476 else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
478 *charset = Vcharset_thai_tis620;
479 *c1 = c - MIN_CHAR_THAI + 0x20;
482 else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
483 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
485 *charset = Vcharset_katakana_jisx0201;
486 *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
491 *charset = Vcharset_ucs_bmp;
496 else if (c <= MAX_CHAR_94)
499 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
500 ((c - MIN_CHAR_94) / 94) + '0',
501 CHARSET_LEFT_TO_RIGHT);
502 *c1 = ((c - MIN_CHAR_94) % 94) + 33;
505 else if (c <= MAX_CHAR_96)
508 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
509 ((c - MIN_CHAR_96) / 96) + '0',
510 CHARSET_LEFT_TO_RIGHT);
511 *c1 = ((c - MIN_CHAR_96) % 96) + 32;
514 else if (c <= MAX_CHAR_94x94)
517 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94,
518 ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
519 CHARSET_LEFT_TO_RIGHT);
520 *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33;
521 *c2 = ((c - MIN_CHAR_94x94) % 94) + 33;
523 else if (c <= MAX_CHAR_96x96)
526 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96,
527 ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
528 CHARSET_LEFT_TO_RIGHT);
529 *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32;
530 *c2 = ((c - MIN_CHAR_96x96) % 96) + 32;
539 #define BREAKUP_CHAR(ch, charset, b1, b2) \
540 breakup_char_1 (ch, &(charset), &(b1), &(b2))
542 INLINE Lisp_Object CHAR_CHARSET (Emchar ch);
544 CHAR_CHARSET (Emchar ch)
549 BREAKUP_CHAR(ch, charset, b1, b2);
553 #define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c)))
555 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
558 /************************************************************************/
559 /* Exported functions */
560 /************************************************************************/
562 EXFUN (Fget_charset, 1);
564 extern Lisp_Object Vcharset_chinese_big5_1;
565 extern Lisp_Object Vcharset_chinese_big5_2;
566 extern Lisp_Object Vcharset_japanese_jisx0208;
567 extern Lisp_Object Vcharset_japanese_jisx0212;
569 #endif /* _XEMACS_CHAR_UCS_H */