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 /* Rewritten by MORIOKA Tomohiko <tomo@m17n.org>. */
23 #ifndef INCLUDED_char_ucs_h_
24 #define INCLUDED_char_ucs_h_
26 #define valid_char_p(ch) 1
28 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
31 struct Lisp_Byte_Table
33 struct lcrecord_header header;
35 Lisp_Object property[256];
37 typedef struct Lisp_Byte_Table Lisp_Byte_Table;
39 DECLARE_LRECORD (byte_table, Lisp_Byte_Table);
40 #define XBYTE_TABLE(x) XRECORD (x, byte_table, Lisp_Byte_Table)
41 #define XSETBYTE_TABLE(x, p) XSETRECORD (x, p, byte_table)
42 #define BYTE_TABLE_P(x) RECORDP (x, byte_table)
43 #define GC_BYTE_TABLE_P(x) GC_RECORDP (x, byte_table)
44 /* #define CHECK_BYTE_TABLE(x) CHECK_RECORD (x, byte_table)
45 char table entries should never escape to Lisp */
48 struct Lisp_Char_ID_Table
50 struct lcrecord_header header;
54 typedef struct Lisp_Char_ID_Table Lisp_Char_ID_Table;
56 DECLARE_LRECORD (char_id_table, Lisp_Char_ID_Table);
57 #define XCHAR_ID_TABLE(x) XRECORD (x, char_id_table, Lisp_Char_ID_Table)
58 #define XSETCHAR_ID_TABLE(x, p) XSETRECORD (x, p, char_id_table)
59 #define CHAR_ID_TABLE_P(x) RECORDP (x, char_id_table)
60 #define GC_CHAR_ID_TABLE_P(x) GC_RECORDP (x, char_id_table)
61 /* #define CHECK_CHAR_ID_TABLE(x) CHECK_RECORD (x, char_id_table)
62 char table entries should never escape to Lisp */
65 Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table);
68 extern Lisp_Object Vcharset_mojikyo;
69 extern Lisp_Object Vcharset_latin_jisx0201;
72 /************************************************************************/
73 /* Definition of leading bytes */
74 /************************************************************************/
76 typedef short Charset_ID;
78 #define MIN_LEADING_BYTE -0x60
79 #define CHARSET_ID_OFFSET 0x00
82 #define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1)
84 /* represent normal 80-9F */
85 #define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2)
87 /* ISO/IEC 10646 BMP */
88 #define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
91 #define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 4)
93 /* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
94 #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 5)
96 /* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
97 #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 6)
99 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
100 #define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 7)
102 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
103 #define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 8)
105 #define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 9)
107 #define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 10)
108 #define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 11)
109 #define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 12)
111 /* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
112 #define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 13)
114 /* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */
115 #define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 14)
116 #define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 15)
117 #define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 16)
118 #define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 17)
119 #define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 18)
120 #define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 19)
121 #define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 20)
122 #define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 21)
123 #define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 22)
124 #define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 23)
125 #define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 24)
126 #define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 25)
127 #define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 26)
128 #define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 27)
129 #define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 28)
130 #define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 29)
131 #define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 30)
132 #define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 31)
133 #define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 32)
134 #define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 33)
135 #define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 34)
137 #define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
138 #define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 35)
141 /* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
143 /* #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') */
144 /* #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') */
147 #define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */
149 /* Right half of JIS X0201-1976 */
150 #define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */
152 /* Left half of JIS X0201-1976 */
153 #define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */
156 /* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */
158 /* Right half of ISO 8859-1 */
159 #define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */
161 /* Right half of ISO 8859-2 */
162 #define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */
164 /* Right half of ISO 8859-3 */
165 #define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */
167 /* Right half of ISO 8859-4 */
168 #define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */
170 /* Right half of ISO 8859-7 */
171 #define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */
173 /* Right half of ISO 8859-6 */
174 #define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */
176 /* Right half of ISO 8859-8 */
177 #define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */
179 /* Right half of ISO 8859-5 */
180 #define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */
182 /* Right half of ISO 8859-9 */
183 #define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
186 #define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
188 /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
189 #define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
192 /* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
194 /* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */
195 /* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */
197 /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
198 #define LEADING_BYTE_JAPANESE_JISX0208_1978 42
200 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
201 #define LEADING_BYTE_CHINESE_GB2312 58
203 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
204 #define LEADING_BYTE_JAPANESE_JISX0208 87
206 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
207 #define LEADING_BYTE_KOREAN_KSC5601 149
209 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
210 #define LEADING_BYTE_JAPANESE_JISX0212 159
212 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
213 #define LEADING_BYTE_CHINESE_CCITT_GB 165
215 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
216 #define LEADING_BYTE_CHINESE_CNS11643_1 171
218 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
219 #define LEADING_BYTE_CHINESE_CNS11643_2 172
221 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
222 #define LEADING_BYTE_CHINESE_CNS11643_3 183
224 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
225 #define LEADING_BYTE_CHINESE_CNS11643_4 184
227 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
228 #define LEADING_BYTE_CHINESE_CNS11643_5 185
230 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
231 #define LEADING_BYTE_CHINESE_CNS11643_6 186
233 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
234 #define LEADING_BYTE_CHINESE_CNS11643_7 187
236 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
237 #define LEADING_BYTE_KOREAN_KPS9566 202
240 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
243 /************************************************************************/
244 /* Information about a particular character set */
245 /************************************************************************/
249 struct lcrecord_header header;
253 Lisp_Object doc_string;
254 Lisp_Object registry;
255 Lisp_Object short_name;
256 Lisp_Object long_name;
258 Lisp_Object reverse_direction_charset;
260 Lisp_Object ccl_program;
262 /* Final byte of this character set in ISO2022 designating escape sequence */
265 /* Number of columns a character in this charset takes up, on TTY
266 devices. Not used for X devices. */
267 unsigned int columns;
269 /* Direction of this character set */
270 unsigned int direction;
272 /* Number of bytes used in encoding of this character set (1 .. 4) */
273 unsigned short dimension;
275 /* Number of chars in each dimension (94, 96, 128, 256) */
276 unsigned short chars;
278 /* Which half of font to be used to display this character set */
279 unsigned int graphic;
281 /* Code-point->character mapping table */
282 Lisp_Object decoding_table;
284 /* Character->code-point mapping table */
285 Lisp_Object encoding_table;
287 /* Range of character code */
288 Emchar ucs_min, ucs_max;
290 /* Offset for external code */
293 /* Offset for each byte */
296 typedef struct Lisp_Charset Lisp_Charset;
298 DECLARE_LRECORD (charset, Lisp_Charset);
299 #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset)
300 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
301 #define CHARSETP(x) RECORDP (x, charset)
302 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
303 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
304 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
306 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
307 #define CHARSET_TYPE_94X94 1 /* This charset includes 94x94 characters. */
308 #define CHARSET_TYPE_96 2 /* This charset includes 96 characters. */
309 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
310 #define CHARSET_TYPE_128 4 /* This charset includes 128 characters. */
311 #define CHARSET_TYPE_128X128 5 /* This charset includes 128x128 characters. */
312 #define CHARSET_TYPE_256 6 /* This charset includes 256 characters. */
313 #define CHARSET_TYPE_256X256 7 /* This charset includes 256x256 characters. */
315 #define CHARSET_LEFT_TO_RIGHT 0
316 #define CHARSET_RIGHT_TO_LEFT 1
318 /* Leading byte and id have been regrouped. -- OG */
319 #define CHARSET_ID(cs) ((cs)->id)
320 #define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs))
321 #define CHARSET_NAME(cs) ((cs)->name)
322 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
323 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
324 #define CHARSET_COLUMNS(cs) ((cs)->columns)
325 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
326 #define CHARSET_DIRECTION(cs) ((cs)->direction)
327 #define CHARSET_FINAL(cs) ((cs)->final)
328 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
329 #define CHARSET_REGISTRY(cs) ((cs)->registry)
330 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
331 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
332 #define CHARSET_CHARS(cs) ((cs)->chars)
333 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
334 #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table)
335 #define CHARSET_ENCODING_TABLE(cs) ((cs)->encoding_table)
336 #define CHARSET_UCS_MIN(cs) ((cs)->ucs_min)
337 #define CHARSET_UCS_MAX(cs) ((cs)->ucs_max)
338 #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
339 #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
342 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
343 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
344 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
345 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
346 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
347 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
348 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
349 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
350 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
351 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
352 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
353 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
354 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
355 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
356 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
357 #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs))
358 #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs))
359 #define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs))
360 #define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs))
361 #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
362 #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
364 struct charset_lookup {
365 /* Table of charsets indexed by (leading byte - 128). */
366 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
368 /* Table of charsets indexed by type/final-byte/direction. */
369 Lisp_Object charset_by_attributes[4][128];
371 Charset_ID next_allocated_leading_byte;
374 extern struct charset_lookup *chlook;
376 #ifdef ERROR_CHECK_TYPECHECK
377 /* int not Bufbyte even though that is the actual type of a leading byte.
378 This way, out-ot-range values will get caught rather than automatically
380 INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
381 INLINE_HEADER Lisp_Object
382 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
384 assert (lb >= MIN_LEADING_BYTE &&
385 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
386 return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
391 #define CHARSET_BY_LEADING_BYTE(lb) \
392 (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
396 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
397 (chlook->charset_by_attributes[type][final])
400 /************************************************************************/
401 /* Dealing with characters */
402 /************************************************************************/
404 #define MAX_CHAR_BASIC_LATIN 0x007F
407 #define MIN_CHAR_GREEK 0x0370
408 #define MAX_CHAR_GREEK 0x03CF
410 #define MIN_CHAR_CYRILLIC 0x0400
411 #define MAX_CHAR_CYRILLIC 0x045F
414 #define MIN_CHAR_HEBREW 0x0590
415 #define MAX_CHAR_HEBREW 0x05EF
417 #define MIN_CHAR_THAI 0x0E00
418 #define MAX_CHAR_THAI 0x0E5F
421 #define MIN_CHAR_HIRAGANA 0x3041
422 #define MAX_CHAR_HIRAGANA 0x3093
424 #define MIN_CHAR_KATAKANA 0x30A1
425 #define MAX_CHAR_KATAKANA 0x30F6
428 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
429 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
431 #define MAX_CHAR_BMP 0x00FFFF
433 #define MIN_CHAR_MOJIKYO 0xE00000
434 #define MIN_CHAR_DAIKANWA MIN_CHAR_MOJIKYO
435 #define MAX_CHAR_DAIKANWA 0xE0FFFF
436 /* #define MAX_CHAR_MOJIKYO 0xE9093F */
437 #define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
439 #define MIN_CHAR_94 0xE90940
440 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
441 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
442 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
444 #define MIN_CHAR_94x94 0xE9F6C0
445 #define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79)
446 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
447 #define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94
448 #define MIN_CHAR_96x96 0xF4C000
449 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
452 Emchar make_builtin_char (Lisp_Object charset, int c1, int c2);
454 INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
456 DECODE_CHAR (Lisp_Object charset, int code_point)
458 int dim = XCHARSET_DIMENSION (charset);
459 Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
466 if ( VECTORP (decoding_table)
467 && ( 0 <= (idx = ((code_point >> (dim * 8))
468 & 255) - XCHARSET_BYTE_OFFSET (charset)) )
469 && ( idx < XVECTOR_LENGTH (decoding_table) )
470 && !NILP (ch = XVECTOR_DATA(decoding_table)[idx]) )
480 if (XCHARSET_DIMENSION (charset) == 1)
481 return make_builtin_char (charset, code_point, 0);
484 int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset);
486 if ( (0 <= plane) && (plane <= 21) )
488 int c1 = code_point >> 8;
489 int c2 = code_point & 255;
493 else if (c1 < 16 + 32 + 30)
494 return DECODE_CHAR (Vcharset_mojikyo,
496 + (c1 - (16 + 32)) * 94
499 else if (c1 < 18 + 32 + 30)
501 else if (c1 < 18 + 32 + 60)
502 return DECODE_CHAR (Vcharset_mojikyo,
504 + (c1 - (18 + 32)) * 94
511 return make_builtin_char (charset, code_point >> 8, code_point & 255);
515 /* Return a character whose charset is CHARSET and position-codes
516 are C1 and C2. TYPE9N character ignores C2. */
518 INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
520 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
522 if (XCHARSET_DIMENSION (charset) == 1)
523 return DECODE_CHAR (charset, c1);
525 return DECODE_CHAR (charset, (c1 << 8) | c2);
528 extern Lisp_Object Vcharacter_attribute_table;
530 int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
531 int range_charset_code_point (Lisp_Object charset, Emchar ch);
533 INLINE_HEADER int charset_code_point (Lisp_Object charset, Emchar ch);
535 charset_code_point (Lisp_Object charset, Emchar ch)
537 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset);
540 if ( CHAR_ID_TABLE_P (encoding_table)
541 && INTP (ret = get_char_id_table (ch, encoding_table)) )
544 return range_charset_code_point (charset, ch);
547 extern Lisp_Object Vdefault_coded_charset_priority_list;
548 EXFUN (Ffind_charset, 1);
550 INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
552 encode_char_1 (Emchar ch, Lisp_Object* charset)
554 Lisp_Object charsets = Vdefault_coded_charset_priority_list;
556 while (!NILP (charsets))
558 *charset = Ffind_charset (Fcar (charsets));
559 if (!NILP (*charset))
561 Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset);
564 if ( CHAR_ID_TABLE_P (encoding_table)
565 && INTP (ret = get_char_id_table (ch, encoding_table)) )
572 = range_charset_code_point (*charset, ch)) >= 0)
576 charsets = Fcdr (charsets);
579 /* otherwise --- maybe for bootstrap */
580 return encode_builtin_char_1 (ch, charset);
583 INLINE_HEADER int encode_char_2 (Emchar ch, Lisp_Object* charset);
585 encode_char_2 (Emchar ch, Lisp_Object* charset)
587 int code_point = encode_char_1 (ch, charset);
589 if (EQ (*charset, Vcharset_mojikyo))
591 int plane, byte1, byte2;
594 plane = code_point / (94 * 60);
595 byte1 = (code_point % (94 * 60)) / 94;
600 byte2 = code_point % 94 + 33;
602 = CHARSET_BY_LEADING_BYTE (LEADING_BYTE_MOJIKYO_PJ_1 - plane);
603 return (byte1 << 8) | byte2;
609 #define ENCODE_CHAR(ch, charset) encode_char_2 (ch, &(charset))
612 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
614 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
616 int code_point = encode_char_2 (c, charset);
620 int dim = XCHARSET_DIMENSION (*charset);
627 else /* if (dim == 2) */
629 *c1 = code_point >> 8;
630 *c2 = code_point & 255;
638 #define BREAKUP_CHAR(ch, charset, b1, b2) \
639 breakup_char_1 (ch, &(charset), &(b1), &(b2))
641 INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
642 INLINE_HEADER Lisp_Object
643 CHAR_CHARSET (Emchar ch)
647 ENCODE_CHAR (ch, charset);
651 #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
652 #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
655 /************************************************************************/
656 /* Exported functions */
657 /************************************************************************/
659 EXFUN (Fget_charset, 1);
661 extern Lisp_Object Vcharset_chinese_big5_1;
662 extern Lisp_Object Vcharset_chinese_big5_2;
663 extern Lisp_Object Vcharset_japanese_jisx0208;
664 extern Lisp_Object Vcharset_japanese_jisx0212;
666 #endif /* INCLUDED_char_ucs_h_ */