1 /* Header for UCS-4 character representation.
2 Copyright (C) 1999,2000 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_Byte_Table
31 struct lcrecord_header header;
33 Lisp_Object property[256];
35 typedef struct Lisp_Byte_Table Lisp_Byte_Table;
37 DECLARE_LRECORD (byte_table, Lisp_Byte_Table);
38 #define XBYTE_TABLE(x) XRECORD (x, byte_table, Lisp_Byte_Table)
39 #define XSETBYTE_TABLE(x, p) XSETRECORD (x, p, byte_table)
40 #define BYTE_TABLE_P(x) RECORDP (x, byte_table)
41 #define GC_BYTE_TABLE_P(x) GC_RECORDP (x, byte_table)
42 /* #define CHECK_BYTE_TABLE(x) CHECK_RECORD (x, byte_table)
43 char table entries should never escape to Lisp */
46 struct Lisp_Char_ID_Table
48 struct lcrecord_header header;
52 typedef struct Lisp_Char_ID_Table Lisp_Char_ID_Table;
54 DECLARE_LRECORD (char_id_table, Lisp_Char_ID_Table);
55 #define XCHAR_ID_TABLE(x) XRECORD (x, char_id_table, Lisp_Char_ID_Table)
56 #define XSETCHAR_ID_TABLE(x, p) XSETRECORD (x, p, char_id_table)
57 #define CHAR_ID_TABLE_P(x) RECORDP (x, char_id_table)
58 #define GC_CHAR_ID_TABLE_P(x) GC_RECORDP (x, char_id_table)
59 /* #define CHECK_CHAR_ID_TABLE(x) CHECK_RECORD (x, char_id_table)
60 char table entries should never escape to Lisp */
63 Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table);
66 extern Lisp_Object Vcharset_mojikyo;
67 extern Lisp_Object Vcharset_latin_jisx0201;
70 /************************************************************************/
71 /* Definition of leading bytes */
72 /************************************************************************/
74 typedef short Charset_ID;
76 #define MIN_LEADING_BYTE -0x60
77 #define CHARSET_ID_OFFSET 0x00
80 #define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1)
82 /* represent normal 80-9F */
83 #define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2)
85 /* ISO/IEC 10646 BMP */
86 #define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
89 #define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 4)
91 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
92 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 5)
94 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
95 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 6)
97 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
98 #define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 7)
100 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
101 #define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 8)
103 #define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 9)
105 #define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 10)
106 #define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 11)
107 #define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 12)
109 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
110 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 13)
112 /* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */
113 #define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 14)
114 #define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 15)
115 #define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 16)
116 #define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 17)
117 #define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 18)
118 #define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 19)
119 #define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 20)
120 #define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 21)
121 #define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 22)
122 #define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 23)
123 #define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 24)
124 #define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 25)
125 #define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 26)
126 #define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 27)
127 #define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 28)
128 #define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 29)
129 #define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 30)
130 #define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 31)
131 #define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 32)
132 #define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 33)
133 #define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 34)
135 #define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
136 #define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 35)
139 /* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
141 /* #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') */
142 /* #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') */
145 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
147 /* Right half of JIS X0201-1976 */
148 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
150 /* Left half of JIS X0201-1976 */
151 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
154 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
156 /* Right half of ISO 8859-1 */
157 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
159 /* Right half of ISO 8859-2 */
160 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
162 /* Right half of ISO 8859-3 */
163 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
165 /* Right half of ISO 8859-4 */
166 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
168 /* Right half of ISO 8859-7 */
169 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
171 /* Right half of ISO 8859-6 */
172 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
174 /* Right half of ISO 8859-8 */
175 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
177 /* Right half of ISO 8859-5 */
178 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
180 /* Right half of ISO 8859-9 */
181 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
184 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
186 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
187 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
190 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
192 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
193 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
195 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
196 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
198 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
199 #define LEADING_BYTE_CHINESE_GB2312 58
201 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
202 #define LEADING_BYTE_JAPANESE_JISX0208 87
204 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
205 #define LEADING_BYTE_KOREAN_KSC5601 149
207 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
208 #define LEADING_BYTE_JAPANESE_JISX0212 159
210 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
211 #define LEADING_BYTE_CHINESE_CCITT_GB 165
213 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
214 #define LEADING_BYTE_CHINESE_CNS11643_1 171
216 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
217 #define LEADING_BYTE_CHINESE_CNS11643_2 172
219 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
220 #define LEADING_BYTE_CHINESE_CNS11643_3 183
222 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
223 #define LEADING_BYTE_CHINESE_CNS11643_4 184
225 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
226 #define LEADING_BYTE_CHINESE_CNS11643_5 185
228 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
229 #define LEADING_BYTE_CHINESE_CNS11643_6 186
231 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
232 #define LEADING_BYTE_CHINESE_CNS11643_7 187
234 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
235 #define LEADING_BYTE_KOREAN_KPS9566 202
238 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
241 /************************************************************************/
242 /* Information about a particular character set */
243 /************************************************************************/
247 struct lcrecord_header header;
251 Lisp_Object doc_string;
252 Lisp_Object registry;
253 Lisp_Object short_name;
254 Lisp_Object long_name;
256 Lisp_Object reverse_direction_charset;
258 Lisp_Object ccl_program;
260 /* Final byte of this character set in ISO2022 designating escape sequence */
263 /* Number of columns a character in this charset takes up, on TTY
264 devices. Not used for X devices. */
265 unsigned int columns;
267 /* Direction of this character set */
268 unsigned int direction;
270 /* Number of bytes used in encoding of this character set (1 .. 4) */
271 unsigned short dimension;
273 /* Number of chars in each dimension (94, 96, 128, 256) */
274 unsigned short chars;
276 /* Which half of font to be used to display this character set */
277 unsigned int graphic;
279 /* Code-point->character mapping table */
280 Lisp_Object decoding_table;
282 /* Character->code-point mapping table */
283 Lisp_Object encoding_table;
285 /* Range of character code */
286 Emchar ucs_min, ucs_max;
288 /* Offset for external code */
291 /* Offset for each byte */
294 typedef struct Lisp_Charset Lisp_Charset;
296 DECLARE_LRECORD (charset, Lisp_Charset);
297 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
298 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
299 #define CHARSETP(x) RECORDP (x, charset)
300 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
301 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
302 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
304 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
305 #define CHARSET_TYPE_94X94 1 /* This charset includes 94x94 characters. */
306 #define CHARSET_TYPE_96 2 /* This charset includes 96 characters. */
307 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
308 #define CHARSET_TYPE_128 4 /* This charset includes 128 characters. */
309 #define CHARSET_TYPE_128X128 5 /* This charset includes 128x128 characters. */
310 #define CHARSET_TYPE_256 6 /* This charset includes 256 characters. */
311 #define CHARSET_TYPE_256X256 7 /* This charset includes 256x256 characters. */
313 #define CHARSET_LEFT_TO_RIGHT 0
314 #define CHARSET_RIGHT_TO_LEFT 1
316 /* Leading byte and id have been regrouped. -- OG */
317 #define CHARSET_ID(cs) ((cs)->id)
318 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
319 #define CHARSET_NAME(cs) ((cs)->name)
320 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
321 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
322 #define CHARSET_COLUMNS(cs) ((cs)->columns)
323 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
324 #define CHARSET_DIRECTION(cs) ((cs)->direction)
325 #define CHARSET_FINAL(cs) ((cs)->final)
326 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
327 #define CHARSET_REGISTRY(cs) ((cs)->registry)
328 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
329 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
330 #define CHARSET_CHARS(cs) ((cs)->chars)
331 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
332 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
333 #define CHARSET_ENCODING_TABLE(cs) ((cs)->encoding_table)
334 #define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
335 #define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
336 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
337 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
340 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
341 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
342 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
343 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
344 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
345 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
346 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
347 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
348 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
349 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
350 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
351 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
352 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
353 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
354 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
355 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
356 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
357 #define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs))
358 #define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs))
359 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
360 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
362 struct charset_lookup {
363 /* Table of charsets indexed by (leading byte - 128). */
364 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
366 /* Table of charsets indexed by type/final-byte/direction. */
367 Lisp_Object charset_by_attributes[4][128];
369 Charset_ID next_allocated_leading_byte;
372 extern struct charset_lookup *chlook;
374 #ifdef ERROR_CHECK_TYPECHECK
375 /* int not Bufbyte even though that is the actual type of a leading byte.
376 This way, out-ot-range values will get caught rather than automatically
378 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
379 INLINE_HEADER Lisp_Object
380 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
382 assert (lb >= MIN_LEADING_BYTE &&
383 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
384 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
389 #define CHARSET_BY_LEADING_BYTE(lb) \
390 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
394 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
395 (chlook->charset_by_attributes[type][final])
398 /************************************************************************/
399 /* Dealing with characters */
400 /************************************************************************/
402 #define MAX_CHAR_BASIC_LATIN 0x007F
405 #define MIN_CHAR_GREEK 0x0370
406 #define MAX_CHAR_GREEK 0x03CF
408 #define MIN_CHAR_CYRILLIC 0x0400
409 #define MAX_CHAR_CYRILLIC 0x045F
412 #define MIN_CHAR_HEBREW 0x0590
413 #define MAX_CHAR_HEBREW 0x05EF
415 #define MIN_CHAR_THAI 0x0E00
416 #define MAX_CHAR_THAI 0x0E5F
419 #define MIN_CHAR_HIRAGANA 0x3041
420 #define MAX_CHAR_HIRAGANA 0x3093
422 #define MIN_CHAR_KATAKANA 0x30A1
423 #define MAX_CHAR_KATAKANA 0x30F6
426 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
427 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
429 #define MAX_CHAR_BMP 0x00FFFF
431 #define MIN_CHAR_MOJIKYO 0xE00000
432 #define MIN_CHAR_DAIKANWA MIN_CHAR_MOJIKYO
433 #define MAX_CHAR_DAIKANWA (MIN_CHAR_MOJIKYO + 50100) /* 0xE0FFFF */
434 /* #define MAX_CHAR_MOJIKYO 0xE9093F */
435 #define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
437 #define MIN_CHAR_94 0xE90940
438 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
439 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
440 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
442 #define MIN_CHAR_94x94 0xE9F6C0
443 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
444 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
445 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
446 #define MIN_CHAR_96x96 0xF4C000
447 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
450 Emchar make_builtin_char (Lisp_Object charset, int c1, int c2);
452 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
454 DECODE_CHAR (Lisp_Object charset, int code_point)
456 int dim = XCHARSET_DIMENSION (charset);
457 Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
464 if ( VECTORP (decoding_table)
465 && ( 0 <= (idx = ((code_point >> (dim * 8))
466 & 255) - XCHARSET_BYTE_OFFSET (charset)) )
467 && ( idx < XVECTOR_LENGTH (decoding_table) )
468 && !NILP (ch = XVECTOR_DATA(decoding_table)[idx]) )
478 if (XCHARSET_DIMENSION (charset) == 1)
479 return make_builtin_char (charset, code_point, 0);
482 int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset);
484 if ( (0 <= plane) && (plane <= 21) )
486 int c1 = code_point >> 8;
487 int c2 = code_point & 255;
491 else if (c1 < 16 + 32 + 30)
492 return DECODE_CHAR (Vcharset_mojikyo,
494 + (c1 - (16 + 32)) * 94
497 else if (c1 < 18 + 32 + 30)
499 else if (c1 < 18 + 32 + 60)
500 return DECODE_CHAR (Vcharset_mojikyo,
502 + (c1 - (18 + 32)) * 94
509 return make_builtin_char (charset, code_point >> 8, code_point & 255);
513 /* Return a character whose charset is CHARSET and position-codes
514 are C1 and C2. TYPE9N character ignores C2. */
516 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
518 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
520 if (XCHARSET_DIMENSION (charset) == 1)
521 return DECODE_CHAR (charset, c1);
523 return DECODE_CHAR (charset, (c1 << 8) | c2);
526 extern Lisp_Object Vcharacter_attribute_table;
528 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
529 int range_charset_code_point (Lisp_Object charset, Emchar ch);
531 INLINE_HEADER int charset_code_point (Lisp_Object charset, Emchar ch);
533 charset_code_point (Lisp_Object charset, Emchar ch)
535 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset);
538 if ( CHAR_ID_TABLE_P (encoding_table)
539 && INTP (ret = get_char_id_table (ch, encoding_table)) )
542 return range_charset_code_point (charset, ch);
545 extern Lisp_Object Vdefault_coded_charset_priority_list;
546 EXFUN (Ffind_charset, 1);
548 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
550 encode_char_1 (Emchar ch, Lisp_Object* charset)
552 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
554 while (!NILP (charsets))
556 *charset = Ffind_charset (Fcar (charsets));
557 if (!NILP (*charset))
559 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset);
562 if ( CHAR_ID_TABLE_P (encoding_table)
563 && INTP (ret = get_char_id_table (ch, encoding_table)) )
570 = range_charset_code_point (*charset, ch)) >= 0)
574 charsets = Fcdr (charsets);
577 /* otherwise --- maybe for bootstrap */
578 return encode_builtin_char_1 (ch, charset);
581 #define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
584 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
586 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
588 int code_point = encode_char_1 (c, charset);
592 int dim = XCHARSET_DIMENSION (*charset);
599 else /* if (dim == 2) */
601 *c1 = code_point >> 8;
602 *c2 = code_point & 255;
610 #define BREAKUP_CHAR(ch, charset, b1, b2) \
611 breakup_char_1 (ch, &(charset), &(b1), &(b2))
613 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
614 INLINE_HEADER Lisp_Object
615 CHAR_CHARSET (Emchar ch)
619 ENCODE_CHAR (ch, charset);
623 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
624 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
633 INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
635 CHAR_TO_CHARC (Emchar ch)
639 cc.code_point = encode_char_1 (ch, &cc.charset);
640 if (EQ (cc.charset, Vcharset_mojikyo))
642 int plane, byte1, byte2;
645 plane = cc.code_point / (94 * 60);
646 byte1 = (cc.code_point % (94 * 60)) / 94;
651 byte2 = cc.code_point % 94 + 33;
653 = CHARSET_BY_LEADING_BYTE (LEADING_BYTE_MOJIKYO_PJ_1 - plane);
654 cc.code_point = (byte1 << 8) | byte2;
660 /************************************************************************/
661 /* Exported functions */
662 /************************************************************************/
664 EXFUN (Fget_charset, 1);
666 extern Lisp_Object Vcharset_chinese_big5_1;
667 extern Lisp_Object Vcharset_chinese_big5_2;
668 extern Lisp_Object Vcharset_japanese_jisx0208;
669 extern Lisp_Object Vcharset_japanese_jisx0212;
671 #endif /* INCLUDED_char_ucs_h_ */