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_CHARACTER_H
25 #define _XEMACS_CHARACTER_H
28 #include "mule-charset.h"
31 /************************************************************************/
32 /* Definition of leading bytes */
33 /************************************************************************/
35 typedef int Charset_ID;
37 #define MIN_LEADING_BYTE 0x80
39 #define LEADING_BYTE_UCS_BMP 0x80
40 #define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */
43 #define CHARSET_ID_OFFSET_94 0x60
45 #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0')
46 #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?')
49 #define LEADING_BYTE_ASCII (CHARSET_ID_OFFSET_94 + 'B')
51 /* Right half of JIS X0201-1976 */
52 #define LEADING_BYTE_KATAKANA_JISX0201 (CHARSET_ID_OFFSET_94 + 'I')
54 /* Left half of JIS X0201-1976 */
55 #define LEADING_BYTE_LATIN_JISX0201 (CHARSET_ID_OFFSET_94 + 'J')
58 #define CHARSET_ID_OFFSET_96 0x70
60 /* Right half of ISO 8859-1 */
61 #define LEADING_BYTE_LATIN_ISO8859_1 (CHARSET_ID_OFFSET_96 + 'A')
63 /* Right half of ISO 8859-2 */
64 #define LEADING_BYTE_LATIN_ISO8859_2 (CHARSET_ID_OFFSET_96 + 'B')
66 /* Right half of ISO 8859-3 */
67 #define LEADING_BYTE_LATIN_ISO8859_3 (CHARSET_ID_OFFSET_96 + 'C')
69 /* Right half of ISO 8859-4 */
70 #define LEADING_BYTE_LATIN_ISO8859_4 (CHARSET_ID_OFFSET_96 + 'D')
72 /* Right half of ISO 8859-7 */
73 #define LEADING_BYTE_GREEK_ISO8859_7 (CHARSET_ID_OFFSET_96 + 'F')
75 /* Right half of ISO 8859-6 */
76 #define LEADING_BYTE_ARABIC_ISO8859_6 (CHARSET_ID_OFFSET_96 + 'G')
78 /* Right half of ISO 8859-8 */
79 #define LEADING_BYTE_HEBREW_ISO8859_8 (CHARSET_ID_OFFSET_96 + 'H')
81 /* Right half of ISO 8859-5 */
82 #define LEADING_BYTE_CYRILLIC_ISO8859_5 (CHARSET_ID_OFFSET_96 + 'L')
84 /* Right half of ISO 8859-9 */
85 #define LEADING_BYTE_LATIN_ISO8859_9 (CHARSET_ID_OFFSET_96 + 'M')
88 #define LEADING_BYTE_THAI_TIS620 (CHARSET_ID_OFFSET_96 + 'T')
91 #define MIN_LEADING_BYTE_PRIVATE_1 0xD0
92 #define MAX_LEADING_BYTE_PRIVATE_1 0xDF
95 #define CHARSET_ID_OFFSET_94x94 0xB0
98 #define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94)
101 #define LEADING_BYTE_CHINESE_BIG5_2 ('1' + CHARSET_ID_OFFSET_94x94)
103 #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94)
104 #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94)
106 /* Japanese JIS X0208-1978 */
107 #define LEADING_BYTE_JAPANESE_JISX0208_1978 \
108 ('@' + CHARSET_ID_OFFSET_94x94)
110 /* Chinese Hanzi GB2312-1980 */
111 #define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94)
113 /* Japanese JIS X0208-1983 */
114 #define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94)
116 /* Hangul KS C5601-1987 */
117 #define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94)
119 /* Japanese JIS X0212-1990 */
120 #define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94)
122 /* CCITT Extended GB */
123 #define LEADING_BYTE_CHINESE_CCITT_GB ('E' + CHARSET_ID_OFFSET_94x94)
125 /* Chinese CNS11643 Set 1 */
126 #define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + CHARSET_ID_OFFSET_94x94)
128 /* Chinese CNS11643 Set 2 */
129 #define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + CHARSET_ID_OFFSET_94x94)
131 /* Chinese CNS11643 Set 3 */
132 #define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + CHARSET_ID_OFFSET_94x94)
134 /* Chinese CNS11643 Set 4 */
135 #define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + CHARSET_ID_OFFSET_94x94)
137 /* Chinese CNS11643 Set 5 */
138 #define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + CHARSET_ID_OFFSET_94x94)
140 /* Chinese CNS11643 Set 6 */
141 #define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + CHARSET_ID_OFFSET_94x94)
143 /* Chinese CNS11643 Set 7 */
144 #define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + CHARSET_ID_OFFSET_94x94)
146 /* DPRK Hangul KPS 9566-1997 */
147 #define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94)
149 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
150 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566
152 #define NUM_LEADING_BYTES 256
155 /************************************************************************/
156 /* Operations on individual bytes */
158 /************************************************************************/
160 /* Argument `c' should be (unsigned int) or (unsigned char). */
161 /* Note that SP and DEL are not included. */
163 #define BYTE_ASCII_P(c) ((c) < 0x80)
164 #define BYTE_C0_P(c) ((c) < 0x20)
165 /* Do some forced casting just to make *sure* things are gotten right. */
166 #define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20)
169 /************************************************************************/
170 /* Operations on individual bytes */
171 /* in a Mule-formatted string */
172 /************************************************************************/
174 /* Does this byte represent the first byte of a character? */
177 BUFBYTE_FIRST_BYTE_P(Bufbyte c)
179 return (c <= 0x7f) || (0xc0 <= c);
183 /************************************************************************/
184 /* Information about a particular character set */
185 /************************************************************************/
189 struct lcrecord_header header;
193 Lisp_Object doc_string, registry, short_name, long_name;
195 Lisp_Object reverse_direction_charset;
197 Lisp_Object ccl_program;
199 /* Final byte of this character set in ISO2022 designating escape sequence */
202 /* Number of bytes (1 - 4) required in the internal representation
203 for characters in this character set. This is *not* the
204 same as the dimension of the character set). */
205 unsigned int rep_bytes;
207 /* Number of columns a character in this charset takes up, on TTY
208 devices. Not used for X devices. */
209 unsigned int columns;
211 /* Direction of this character set */
212 unsigned int direction;
214 /* Type of this character set (94, 96, 94x94, 96x96) */
217 /* Number of bytes used in encoding of this character set (1 or 2) */
218 unsigned int dimension;
220 /* Number of chars in each dimension (usually 94 or 96) */
223 /* Which half of font to be used to display this character set */
224 unsigned int graphic;
227 DECLARE_LRECORD (charset, struct Lisp_Charset);
228 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
229 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
230 #define CHARSETP(x) RECORDP (x, charset)
231 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
232 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
233 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
235 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
236 #define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */
237 #define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */
238 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
239 #define CHARSET_TYPE_128X128 4 /* This charset includes 128x128 characters. */
240 #define CHARSET_TYPE_256X256 5 /* This charset includes 256x256 characters. */
242 #define CHARSET_LEFT_TO_RIGHT 0
243 #define CHARSET_RIGHT_TO_LEFT 1
245 /* Leading byte and id have been regrouped. -- OG */
246 #define CHARSET_ID(cs) ((cs)->id)
247 #define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs)))
248 #define CHARSET_NAME(cs) ((cs)->name)
249 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
250 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
251 #define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes)
252 #define CHARSET_COLUMNS(cs) ((cs)->columns)
253 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
254 #define CHARSET_TYPE(cs) ((cs)->type)
255 #define CHARSET_DIRECTION(cs) ((cs)->direction)
256 #define CHARSET_FINAL(cs) ((cs)->final)
257 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
258 #define CHARSET_REGISTRY(cs) ((cs)->registry)
259 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
260 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
261 #define CHARSET_CHARS(cs) ((cs)->chars)
262 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
265 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
266 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
267 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
268 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
269 #define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs))
270 #define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs))
271 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
272 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
273 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
274 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
275 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
276 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
277 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
278 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
279 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
280 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
281 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
282 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
284 /* Table of charsets indexed by (leading byte - 128). */
285 extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
287 /* Table of charsets indexed by type/final-byte. */
288 extern Lisp_Object charset_by_attributes[4][128];
290 #ifdef ERROR_CHECK_TYPECHECK
291 /* int not Bufbyte even though that is the actual type of a leading byte.
292 This way, out-ot-range values will get caught rather than automatically
294 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
296 CHARSET_BY_LEADING_BYTE (Charset_ID lb)
298 assert (lb >= MIN_LEADING_BYTE &&
299 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
300 return charset_by_leading_byte[lb - MIN_LEADING_BYTE];
305 #define CHARSET_BY_LEADING_BYTE(lb) \
306 (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
310 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
311 (charset_by_attributes[type][final])
313 INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
315 REP_BYTES_BY_FIRST_BYTE (int fb)
319 else if ( fb < 0xe0 )
321 else if ( fb < 0xf0 )
323 else if ( fb < 0xf8 )
325 else if ( fb < 0xfc )
332 /************************************************************************/
333 /* Dealing with characters */
334 /************************************************************************/
336 /* Is this character represented by more than one byte in a string? */
338 #define CHAR_MULTIBYTE_P(c) ((c) >= 0x80)
340 #define CHAR_ASCII_P(c) (!CHAR_MULTIBYTE_P (c))
342 /* The bit fields of character are divided into 3 parts:
343 FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */
345 #define CHAR_FIELD1_MASK (0x7F << 14)
346 #define CHAR_FIELD2_MASK (0x7F << 7)
347 #define CHAR_FIELD3_MASK 0x7F
349 #define MIN_CHAR_GREEK 0x0370
350 #define MAX_CHAR_GREEK 0x03CF
352 #define MIN_CHAR_CYRILLIC 0x0400
353 #define MAX_CHAR_CYRILLIC 0x045F
355 #define MIN_CHAR_HEBREW 0x0590
356 #define MAX_CHAR_HEBREW 0x05EF
358 #define MIN_CHAR_THAI 0x0E00
359 #define MAX_CHAR_THAI 0x0E5F
361 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
362 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
364 #define MIN_CHAR_94 0xE90940
365 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
366 #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80)
367 #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1)
369 #define MIN_CHAR_94x94 0xE9F6C0
370 #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1)
371 #define MIN_CHAR_96x96 0xF4C000
372 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
374 /* Macros to access each field of a character code of C. */
376 #define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14)
377 #define CHAR_FIELD2_INTERNAL(c) (((c) & CHAR_FIELD2_MASK) >> 7)
378 #define CHAR_FIELD3_INTERNAL(c) ((c) & CHAR_FIELD3_MASK)
380 /* Field 1, if non-zero, usually holds a leading byte for a
381 dimension-2 charset. Field 2, if non-zero, usually holds a leading
382 byte for a dimension-1 charset. */
384 /* Converting between field values and leading bytes. */
386 #define FIELD1_TO_PRIVATE_LEADING_BYTE CHARSET_ID_OFFSET_94x94
387 #define FIELD1_TO_OFFICIAL_LEADING_BYTE CHARSET_ID_OFFSET_94x94
388 #define FIELD2_TO_PRIVATE_LEADING_BYTE (MIN_LEADING_BYTE_PRIVATE_1 - 32)
389 #define FIELD2_TO_OFFICIAL_LEADING_BYTE LEADING_BYTE_ASCII
391 /* Minimum and maximum allowed values for the fields. */
393 #define MIN_CHAR_FIELD1_OFFICIAL \
394 (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
395 #define MAX_CHAR_FIELD1_OFFICIAL \
396 (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
398 #define MIN_CHAR_FIELD2_PRIVATE \
399 (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
400 #define MAX_CHAR_FIELD2_PRIVATE \
401 (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
403 #define MIN_CHAR_FIELD1_PRIVATE \
404 (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
405 #define MAX_CHAR_FIELD1_PRIVATE \
406 (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
408 /* Minimum character code of each <type> character. */
410 #define MULE_CHAR_PRIVATE_OFFSET (0xe0 << 16)
412 #define MIN_CHAR_PRIVATE_TYPE9N \
413 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_PRIVATE << 7))
414 #define MAX_CHAR_PRIVATE_TYPE9N \
415 (MULE_CHAR_PRIVATE_OFFSET | (MAX_CHAR_FIELD2_PRIVATE << 7) | 0x7f)
416 #define MIN_CHAR_PRIVATE_TYPE9NX9N \
417 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_PRIVATE << 14))
418 #define MIN_CHAR_OFFICIAL_TYPE9NX9N \
419 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_OFFICIAL << 14))
420 #define MIN_CHAR_COMPOSITION \
421 (MULE_CHAR_PRIVATE_OFFSET | (0x7f << 14))
423 /* Return a character whose charset is CHARSET and position-codes
424 are C1 and C2. TYPE9N character ignores C2.
426 NOTE: This takes advantage of the fact that
427 FIELD2_TO_OFFICIAL_LEADING_BYTE and
428 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
431 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
433 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
435 if (EQ (charset, Vcharset_ascii))
437 else if (EQ (charset, Vcharset_control_1))
439 else if (EQ (charset, Vcharset_latin_iso8859_1))
441 else if (EQ (charset, Vcharset_greek_iso8859_7))
442 return c1 + MIN_CHAR_GREEK - 0x20;
443 else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
444 return c1 + MIN_CHAR_CYRILLIC - 0x20;
445 else if (EQ (charset, Vcharset_hebrew_iso8859_8))
446 return c1 + MIN_CHAR_HEBREW - 0x20;
447 else if (EQ (charset, Vcharset_thai_tis620))
448 return c1 + MIN_CHAR_THAI - 0x20;
449 else if (EQ (charset, Vcharset_katakana_jisx0201))
451 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
454 else if (XCHARSET_DIMENSION (charset) == 1)
456 switch (XCHARSET_CHARS (charset))
460 + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
463 + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
470 switch (XCHARSET_CHARS (charset))
473 return MIN_CHAR_94x94
474 + (XCHARSET_FINAL (charset) - '0') * 94 * 94
475 + (c1 - 33) * 94 + (c2 - 33);
477 return MIN_CHAR_96x96
478 + (XCHARSET_FINAL (charset) - '0') * 96 * 96
479 + (c1 - 32) * 96 + (c2 - 32);
486 extern Charset_ID latin_a_char_to_charset[128];
487 extern unsigned char latin_a_char_to_byte1[128];
488 extern unsigned char latin_a_char_to_byte2[128];
490 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
492 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
494 if (CHAR_ASCII_P (c))
496 *charset = Vcharset_ascii;
502 *charset = Vcharset_control_1;
503 *c1 = CHAR_FIELD3_INTERNAL (c);
508 *charset = Vcharset_latin_iso8859_1;
509 *c1 = CHAR_FIELD3_INTERNAL (c);
515 = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]);
516 *c1 = latin_a_char_to_byte1[c - 0x100];
517 *c2 = latin_a_char_to_byte2[c - 0x100];
519 else if (c < MIN_CHAR_GREEK)
521 printf("not break up u+%x", c);
524 else if (c <= MAX_CHAR_GREEK)
526 *charset = Vcharset_greek_iso8859_7;
527 *c1 = c - MIN_CHAR_GREEK + 0x20;
530 else if (c < MIN_CHAR_CYRILLIC)
532 printf("not break up u+%x", c);
535 else if (c <= MAX_CHAR_CYRILLIC)
537 *charset = Vcharset_cyrillic_iso8859_5;
538 *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
541 else if (c < MIN_CHAR_HEBREW)
543 printf("not break up u+%x", c);
546 else if (c <= MAX_CHAR_HEBREW)
548 *charset = Vcharset_hebrew_iso8859_8;
549 *c1 = c - MIN_CHAR_HEBREW + 0x20;
552 else if (c < MIN_CHAR_THAI)
554 printf("not break up u+%x", c);
557 else if (c <= MAX_CHAR_THAI)
559 *charset = Vcharset_thai_tis620;
560 *c1 = c - MIN_CHAR_THAI + 0x20;
563 else if (c < MIN_CHAR_HALFWIDTH_KATAKANA)
565 printf("not break up u+%x", c);
568 else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
570 *charset = Vcharset_katakana_jisx0201;
571 *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
574 else if (c <= MAX_CHAR_94)
577 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
578 ((c - MIN_CHAR_94) / 94) + '0',
579 CHARSET_LEFT_TO_RIGHT);
580 *c1 = ((c - MIN_CHAR_94) % 94) + 33;
583 else if (c <= MAX_CHAR_96)
586 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
587 ((c - MIN_CHAR_96) / 96) + '0',
588 CHARSET_LEFT_TO_RIGHT);
589 *c1 = ((c - MIN_CHAR_96) % 96) + 32;
592 else if (c <= MAX_CHAR_94x94)
595 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94,
596 ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
597 CHARSET_LEFT_TO_RIGHT);
598 *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33;
599 *c2 = ((c - MIN_CHAR_94x94) % 94) + 33;
601 else if (c <= MAX_CHAR_96x96)
604 = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96,
605 ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
606 CHARSET_LEFT_TO_RIGHT);
607 *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32;
608 *c2 = ((c - MIN_CHAR_96x96) % 96) + 32;
617 #define BREAKUP_CHAR(c, charset, c1, c2) \
618 breakup_char_1 (c, &(charset), &(c1), &(c2))
620 INLINE Lisp_Object CHAR_CHARSET (Emchar c);
622 CHAR_CHARSET (Emchar c)
627 BREAKUP_CHAR(c, charset, c1, c2);
631 #define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c)))
634 #ifdef ENABLE_COMPOSITE_CHARS
635 /************************************************************************/
636 /* Composite characters */
637 /************************************************************************/
639 Emchar lookup_composite_char (Bufbyte *str, int len);
640 Lisp_Object composite_char_string (Emchar ch);
641 #endif /* ENABLE_COMPOSITE_CHARS */
644 /************************************************************************/
645 /* Exported functions */
646 /************************************************************************/
648 EXFUN (Ffind_charset, 1);
649 EXFUN (Fget_charset, 1);
651 extern Lisp_Object Vcharset_chinese_big5_1;
652 extern Lisp_Object Vcharset_chinese_big5_2;
653 extern Lisp_Object Vcharset_japanese_jisx0208;
654 extern Lisp_Object Vcharset_japanese_jisx0212;
656 Emchar Lstream_get_emchar_1 (Lstream *stream, int first_char);
657 int Lstream_fput_emchar (Lstream *stream, Emchar ch);
658 void Lstream_funget_emchar (Lstream *stream, Emchar ch);
660 int copy_internal_to_external (CONST Bufbyte *internal, Bytecount len,
661 unsigned char *external);
662 Bytecount copy_external_to_internal (CONST unsigned char *external,
663 int len, Bufbyte *internal);
665 #endif /* CHAR_IS_UCS4 */
666 #endif /* _XEMACS_CHARACTER_H */