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 #define MIN_LEADING_BYTE 0x80
36 /* These need special treatment in a string and/or character */
37 #define LEADING_BYTE_ASCII 0x8E /* Omitted in a buffer */
38 #define LEADING_BYTE_CONTROL_1 0x8F /* represent normal 80-9F */
40 /** The following are for 1-byte characters in an official charset. **/
44 #define LEADING_BYTE_LATIN_ISO8859_1 0x81 /* Right half of ISO 8859-1 */
45 #define LEADING_BYTE_LATIN_ISO8859_2 0x82 /* Right half of ISO 8859-2 */
46 #define LEADING_BYTE_LATIN_ISO8859_3 0x83 /* Right half of ISO 8859-3 */
47 #define LEADING_BYTE_LATIN_ISO8859_4 0x84 /* Right half of ISO 8859-4 */
48 #define LEADING_BYTE_THAI_TIS620 0x85 /* TIS620-2533 */
49 #define LEADING_BYTE_GREEK_ISO8859_7 0x86 /* Right half of ISO 8859-7 */
50 #define LEADING_BYTE_ARABIC_ISO8859_6 0x87 /* Right half of ISO 8859-6 */
51 #define LEADING_BYTE_HEBREW_ISO8859_8 0x88 /* Right half of ISO 8859-8 */
52 #define LEADING_BYTE_KATAKANA_JISX0201 0x89 /* Right half of JIS X0201-1976 */
53 #define LEADING_BYTE_LATIN_JISX0201 0x8A /* Left half of JIS X0201-1976 */
54 #define LEADING_BYTE_CYRILLIC_ISO8859_5 0x8C /* Right half of ISO 8859-5 */
55 #define LEADING_BYTE_LATIN_ISO8859_9 0x8D /* Right half of ISO 8859-9 */
57 #define MIN_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_1
58 #define MAX_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_9
60 #define LEADING_BYTE_CHINESE_BIG5_1 0xB0 /* Big5 Level 1 */
61 #define LEADING_BYTE_CHINESE_BIG5_2 0xB1 /* Big5 Level 2 */
62 #define MIN_LEADING_BYTE_PRIVATE_2 0xB0
63 #define MAX_LEADING_BYTE_PRIVATE_2 0xBF
65 /** The following are for 2-byte characters in an official charset. **/
67 #define LEADING_BYTE_JAPANESE_JISX0208_1978 0xC0/* Japanese JIS X0208-1978 */
68 #define LEADING_BYTE_CHINESE_GB2312 0xC1 /* Chinese Hanzi GB2312-1980 */
69 #define LEADING_BYTE_JAPANESE_JISX0208 0xC2 /* Japanese JIS X0208-1983 */
70 #define LEADING_BYTE_KOREAN_KSC5601 0xC3 /* Hangul KS C5601-1987 */
71 #define LEADING_BYTE_JAPANESE_JISX0212 0xC4 /* Japanese JIS X0212-1990 */
72 #define LEADING_BYTE_CHINESE_CCITT_GB 0xC5 /* CCITT Extended GB */
73 #define LEADING_BYTE_CHINESE_CNS11643_1 0xC7 /* Chinese CNS11643 Set 1 */
74 #define LEADING_BYTE_CHINESE_CNS11643_2 0xC8 /* Chinese CNS11643 Set 2 */
75 #define LEADING_BYTE_CHINESE_CNS11643_3 0xC9 /* Chinese CNS11643 Set 3 */
76 #define LEADING_BYTE_CHINESE_CNS11643_4 0xCA /* Chinese CNS11643 Set 4 */
77 #define LEADING_BYTE_CHINESE_CNS11643_5 0xCB /* Chinese CNS11643 Set 5 */
78 #define LEADING_BYTE_CHINESE_CNS11643_6 0xCC /* Chinese CNS11643 Set 6 */
79 #define LEADING_BYTE_CHINESE_CNS11643_7 0xCD /* Chinese CNS11643 Set 7 */
80 #define LEADING_BYTE_KOREAN_KPS9566 0xCE /* DPRK Hangul KPS 9566-1997 */
82 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
83 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566
85 /** The following are for 1- and 2-byte characters in a private charset. **/
87 #define PRE_LEADING_BYTE_PRIVATE_1 0x120 /* 1-byte char-set */
88 #define PRE_LEADING_BYTE_PRIVATE_2 0x121 /* 2-byte char-set */
90 #define MIN_LEADING_BYTE_PRIVATE_1 0x0D0
91 #define MAX_LEADING_BYTE_PRIVATE_1 0x11f
95 #define LEADING_BYTE_LATIN_ISO8859_1 0x81 /* Right half of ISO 8859-1 */
96 #define LEADING_BYTE_LATIN_ISO8859_2 0x82 /* Right half of ISO 8859-2 */
97 #define LEADING_BYTE_LATIN_ISO8859_3 0x83 /* Right half of ISO 8859-3 */
98 #define LEADING_BYTE_LATIN_ISO8859_4 0x84 /* Right half of ISO 8859-4 */
99 #define LEADING_BYTE_THAI_TIS620 0x85 /* TIS620-2533 */
100 #define LEADING_BYTE_GREEK_ISO8859_7 0x86 /* Right half of ISO 8859-7 */
101 #define LEADING_BYTE_ARABIC_ISO8859_6 0x87 /* Right half of ISO 8859-6 */
102 #define LEADING_BYTE_HEBREW_ISO8859_8 0x88 /* Right half of ISO 8859-8 */
103 #define LEADING_BYTE_KATAKANA_JISX0201 0x89 /* Right half of JIS X0201-1976 */
104 #define LEADING_BYTE_LATIN_JISX0201 0x8A /* Left half of JIS X0201-1976 */
105 #define LEADING_BYTE_CYRILLIC_ISO8859_5 0x8C /* Right half of ISO 8859-5 */
106 #define LEADING_BYTE_LATIN_ISO8859_9 0x8D /* Right half of ISO 8859-9 */
108 #define MIN_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_1
109 #define MAX_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_9
111 /** The following are for 2-byte characters in an official charset. **/
113 #define LEADING_BYTE_JAPANESE_JISX0208_1978 0x90/* Japanese JIS X0208-1978 */
114 #define LEADING_BYTE_CHINESE_GB2312 0x91 /* Chinese Hanzi GB2312-1980 */
115 #define LEADING_BYTE_JAPANESE_JISX0208 0x92 /* Japanese JIS X0208-1983 */
116 #define LEADING_BYTE_KOREAN_KSC5601 0x93 /* Hangul KS C5601-1987 */
117 #define LEADING_BYTE_JAPANESE_JISX0212 0x94 /* Japanese JIS X0212-1990 */
118 #define LEADING_BYTE_CHINESE_CCITT_GB 0x95 /* CCITT Extended GB */
119 #define LEADING_BYTE_CHINESE_BIG5_1 0x96 /* Big5 Level 1 */
120 #define LEADING_BYTE_CHINESE_CNS11643_1 0x97 /* Chinese CNS11643 Set 1 */
121 #define LEADING_BYTE_CHINESE_CNS11643_2 0x98 /* Chinese CNS11643 Set 2 */
122 #define LEADING_BYTE_CHINESE_CNS11643_3 0x99 /* Chinese CNS11643 Set 3 */
123 #define LEADING_BYTE_CHINESE_CNS11643_4 0x9A /* Chinese CNS11643 Set 4 */
124 #define LEADING_BYTE_CHINESE_CNS11643_5 0x9B /* Chinese CNS11643 Set 5 */
125 #define LEADING_BYTE_CHINESE_CNS11643_6 0x9C /* Chinese CNS11643 Set 6 */
126 #define LEADING_BYTE_CHINESE_CNS11643_7 0x9D /* Chinese CNS11643 Set 7 */
127 #define LEADING_BYTE_CHINESE_BIG5_2 0x9D /* Big5 Level 2 */
128 #define LEADING_BYTE_KOREAN_KPS9566 0x9E /* DPRK Hangul KPS 9566-1997 */
130 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
131 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_CHINESE_BIG5_2
133 /** The following are for 1- and 2-byte characters in a private charset. **/
135 #define PRE_LEADING_BYTE_PRIVATE_1 0x9E /* 1-byte char-set */
136 #define PRE_LEADING_BYTE_PRIVATE_2 0x9F /* 2-byte char-set */
138 #define MIN_LEADING_BYTE_PRIVATE_1 0xA0
139 #define MAX_LEADING_BYTE_PRIVATE_1 0xEF
140 #define MIN_LEADING_BYTE_PRIVATE_2 0xF0
141 #define MAX_LEADING_BYTE_PRIVATE_2 0xFF
145 #define NUM_LEADING_BYTES 256
148 /************************************************************************/
149 /* Operations on leading bytes */
150 /************************************************************************/
152 /* Is this leading byte for a private charset? */
155 #define LEADING_BYTE_PRIVATE_P(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1)
158 /* Is this a prefix for a private leading byte? */
160 INLINE int LEADING_BYTE_PREFIX_P (unsigned char lb);
162 LEADING_BYTE_PREFIX_P (unsigned char lb)
164 return (lb == PRE_LEADING_BYTE_PRIVATE_1 ||
165 lb == PRE_LEADING_BYTE_PRIVATE_2);
168 /* Given a private leading byte, return the leading byte prefix stored
171 #define PRIVATE_LEADING_BYTE_PREFIX(lb) \
172 ((lb) < MIN_LEADING_BYTE_PRIVATE_2 ? \
173 PRE_LEADING_BYTE_PRIVATE_1 : \
174 PRE_LEADING_BYTE_PRIVATE_2)
177 /************************************************************************/
178 /* Operations on individual bytes */
180 /************************************************************************/
182 /* Argument `c' should be (unsigned int) or (unsigned char). */
183 /* Note that SP and DEL are not included. */
185 #define BYTE_ASCII_P(c) ((c) < 0x80)
186 #define BYTE_C0_P(c) ((c) < 0x20)
187 /* Do some forced casting just to make *sure* things are gotten right. */
188 #define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20)
191 /************************************************************************/
192 /* Operations on individual bytes */
193 /* in a Mule-formatted string */
194 /************************************************************************/
196 /* Does this byte represent the first byte of a character? */
200 BUFBYTE_FIRST_BYTE_P(Bufbyte c)
202 return (c <= 0x7f) || (0xc0 <= c);
205 #define BUFBYTE_FIRST_BYTE_P(c) ((c) < 0xA0)
208 /* Does this byte represent the first byte of a multi-byte character? */
210 #define BUFBYTE_LEADING_BYTE_P(c) BYTE_C1_P (c)
213 /************************************************************************/
214 /* Information about a particular character set */
215 /************************************************************************/
219 struct lcrecord_header header;
223 Lisp_Object doc_string, registry, short_name, long_name;
225 Lisp_Object reverse_direction_charset;
227 Lisp_Object ccl_program;
229 /* Final byte of this character set in ISO2022 designating escape sequence */
232 /* Number of bytes (1 - 4) required in the internal representation
233 for characters in this character set. This is *not* the
234 same as the dimension of the character set). */
235 unsigned int rep_bytes;
237 /* Number of columns a character in this charset takes up, on TTY
238 devices. Not used for X devices. */
239 unsigned int columns;
241 /* Direction of this character set */
242 unsigned int direction;
244 /* Type of this character set (94, 96, 94x94, 96x96) */
247 /* Number of bytes used in encoding of this character set (1 or 2) */
248 unsigned int dimension;
250 /* Number of chars in each dimension (usually 94 or 96) */
253 /* Which half of font to be used to display this character set */
254 unsigned int graphic;
257 DECLARE_LRECORD (charset, struct Lisp_Charset);
258 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
259 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
260 #define CHARSETP(x) RECORDP (x, charset)
261 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
262 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
263 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
265 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
266 #define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */
267 #define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */
268 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
270 #define CHARSET_LEFT_TO_RIGHT 0
271 #define CHARSET_RIGHT_TO_LEFT 1
273 /* Leading byte and id have been regrouped. -- OG */
274 #define CHARSET_ID(cs) ((cs)->id)
275 #define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs)))
276 #define CHARSET_NAME(cs) ((cs)->name)
277 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
278 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
279 #define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes)
280 #define CHARSET_COLUMNS(cs) ((cs)->columns)
281 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
282 #define CHARSET_TYPE(cs) ((cs)->type)
283 #define CHARSET_DIRECTION(cs) ((cs)->direction)
284 #define CHARSET_FINAL(cs) ((cs)->final)
285 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
286 #define CHARSET_REGISTRY(cs) ((cs)->registry)
287 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
288 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
289 #define CHARSET_CHARS(cs) ((cs)->chars)
290 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
293 #ifdef LEADING_BYTE_PRIVATE_P
294 #define CHARSET_PRIVATE_P(cs) LEADING_BYTE_PRIVATE_P (CHARSET_LEADING_BYTE (cs))
297 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
298 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
299 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
300 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
301 #define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs))
302 #define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs))
303 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
304 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
305 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
306 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
307 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
308 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
309 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
310 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
311 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
312 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
313 #ifdef CHARSET_PRIVATE_P
314 #define XCHARSET_PRIVATE_P(cs) CHARSET_PRIVATE_P (XCHARSET (cs))
316 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
317 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
319 /* Table of charsets indexed by (leading byte - 128). */
320 extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
322 /* Table of charsets indexed by type/final-byte/direction. */
323 extern Lisp_Object charset_by_attributes[4][128][2];
326 /* Table of number of bytes in the string representation of a character
327 indexed by the first byte of that representation.
329 This value can be derived other ways -- e.g. something like
331 (BYTE_ASCII_P (first_byte) ? 1 :
332 XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte)))
334 but it's faster this way. */
335 extern Bytecount rep_bytes_by_first_byte[0xA0];
338 #ifdef ERROR_CHECK_TYPECHECK
339 /* int not Bufbyte even though that is the actual type of a leading byte.
340 This way, out-ot-range values will get caught rather than automatically
342 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (int lb);
344 CHARSET_BY_LEADING_BYTE (int lb)
346 assert (lb >= MIN_LEADING_BYTE &&
347 lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
348 return charset_by_leading_byte[lb - MIN_LEADING_BYTE];
353 #define CHARSET_BY_LEADING_BYTE(lb) \
354 (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
358 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
359 (charset_by_attributes[type][final][dir])
362 INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
364 REP_BYTES_BY_FIRST_BYTE (int fb)
368 else if ( fb < 0xe0 )
370 else if ( fb < 0xf0 )
372 else if ( fb < 0xf8 )
374 else if ( fb < 0xfc )
380 #ifdef ERROR_CHECK_TYPECHECK
382 /* Number of bytes in the string representation of a character */
383 INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
385 REP_BYTES_BY_FIRST_BYTE (int fb)
387 assert (fb >= 0 && fb < 0xA0);
388 return rep_bytes_by_first_byte[fb];
392 #define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb])
394 #endif /* end MULE */
397 /************************************************************************/
398 /* Dealing with characters */
399 /************************************************************************/
401 /* Is this character represented by more than one byte in a string? */
403 #define CHAR_MULTIBYTE_P(c) ((c) >= 0x80)
405 #define CHAR_ASCII_P(c) (!CHAR_MULTIBYTE_P (c))
407 /* The bit fields of character are divided into 3 parts:
408 FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */
410 #define CHAR_FIELD1_MASK (0x7F << 14)
411 #define CHAR_FIELD2_MASK (0x7F << 7)
412 #define CHAR_FIELD3_MASK 0x7F
414 #define MIN_CHAR_GREEK 0x0370
415 #define MAX_CHAR_GREEK 0x03CF
417 #define MIN_CHAR_CYRILLIC 0x0400
418 #define MAX_CHAR_CYRILLIC 0x045F
420 #define MIN_CHAR_HEBREW 0x0590
421 #define MAX_CHAR_HEBREW 0x05EF
423 #define MIN_CHAR_THAI 0x0E00
424 #define MAX_CHAR_THAI 0x0E5F
426 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
427 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
429 /* Macros to access each field of a character code of C. */
431 #define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14)
432 #define CHAR_FIELD2_INTERNAL(c) (((c) & CHAR_FIELD2_MASK) >> 7)
433 #define CHAR_FIELD3_INTERNAL(c) ((c) & CHAR_FIELD3_MASK)
435 /* Field 1, if non-zero, usually holds a leading byte for a
436 dimension-2 charset. Field 2, if non-zero, usually holds a leading
437 byte for a dimension-1 charset. */
439 /* Converting between field values and leading bytes. */
441 #define FIELD2_TO_OFFICIAL_LEADING_BYTE 0x80
445 #define FIELD1_TO_PRIVATE_LEADING_BYTE 0x80
446 #define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x80
447 #define FIELD2_TO_PRIVATE_LEADING_BYTE 0xb0
451 #define FIELD1_TO_PRIVATE_LEADING_BYTE 0xc0
452 #define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x50
453 #define FIELD2_TO_PRIVATE_LEADING_BYTE 0x80
458 CHAR_FIELD2 (Emchar c)
460 if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) )
461 return LEADING_BYTE_GREEK_ISO8859_7
462 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
463 else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) )
464 return LEADING_BYTE_CYRILLIC_ISO8859_5
465 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
466 else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) )
467 return LEADING_BYTE_HEBREW_ISO8859_8
468 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
469 else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) )
470 return LEADING_BYTE_THAI_TIS620
471 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
472 else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c)
473 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) )
474 return LEADING_BYTE_KATAKANA_JISX0201
475 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
477 return CHAR_FIELD2_INTERNAL(c);
481 CHAR_FIELD3 (Emchar c)
483 if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) )
484 return c - MIN_CHAR_GREEK + 0x20;
485 else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) )
486 return c - MIN_CHAR_CYRILLIC + 0x20;
487 else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) )
488 return c - MIN_CHAR_HEBREW + 0x20;
489 else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) )
490 return c - MIN_CHAR_THAI + 0x20;
491 else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c)
492 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) )
493 return c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
495 return CHAR_FIELD3_INTERNAL(c);
498 /* Minimum and maximum allowed values for the fields. */
500 #define MIN_CHAR_FIELD2_OFFICIAL \
501 (MIN_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
502 #define MAX_CHAR_FIELD2_OFFICIAL \
503 (MAX_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
505 #define MIN_CHAR_FIELD1_OFFICIAL \
506 (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
507 #define MAX_CHAR_FIELD1_OFFICIAL \
508 (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
510 #define MIN_CHAR_FIELD2_PRIVATE \
511 (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
512 #define MAX_CHAR_FIELD2_PRIVATE \
513 (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
515 #define MIN_CHAR_FIELD1_PRIVATE \
516 (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
517 #define MAX_CHAR_FIELD1_PRIVATE \
518 (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
520 /* Minimum character code of each <type> character. */
522 #define MULE_CHAR_PRIVATE_OFFSET (0xe0 << 16)
524 #define MIN_CHAR_OFFICIAL_TYPE9N \
525 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_OFFICIAL << 7))
526 #define MIN_CHAR_PRIVATE_TYPE9N \
527 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_PRIVATE << 7))
528 #define MIN_CHAR_PRIVATE_TYPE9NX9N \
529 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_PRIVATE << 14))
530 #define MIN_CHAR_OFFICIAL_TYPE9NX9N \
531 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_OFFICIAL << 14))
532 #define MIN_CHAR_COMPOSITION \
533 (MULE_CHAR_PRIVATE_OFFSET | (0x7f << 14))
535 /* Leading byte of a character.
537 NOTE: This takes advantage of the fact that
538 FIELD2_TO_OFFICIAL_LEADING_BYTE and
539 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
542 INLINE Bufbyte CHAR_LEADING_BYTE (Emchar c);
544 CHAR_LEADING_BYTE (Emchar c)
546 if (CHAR_ASCII_P (c))
547 return LEADING_BYTE_ASCII;
549 return LEADING_BYTE_CONTROL_1;
551 return LEADING_BYTE_LATIN_ISO8859_1;
552 else if (c <= MAX_CHAR_GREEK)
553 return LEADING_BYTE_GREEK_ISO8859_7;
554 else if (c <= MAX_CHAR_CYRILLIC)
555 return LEADING_BYTE_CYRILLIC_ISO8859_5;
556 else if (c <= MAX_CHAR_HEBREW)
557 return LEADING_BYTE_HEBREW_ISO8859_8;
558 else if (c <= MAX_CHAR_THAI)
559 return LEADING_BYTE_THAI_TIS620;
560 else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
561 return LEADING_BYTE_KATAKANA_JISX0201;
562 else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
563 return CHAR_FIELD2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE;
564 else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
565 return CHAR_FIELD1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE;
566 else if (c < MIN_CHAR_COMPOSITION)
567 return CHAR_FIELD1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE;
570 #ifdef ENABLE_COMPOSITE_CHARS
571 return LEADING_BYTE_COMPOSITE;
575 #endif /* ENABLE_COMPOSITE_CHARS */
579 #define CHAR_CHARSET(c) CHARSET_BY_LEADING_BYTE (CHAR_LEADING_BYTE (c))
581 /* Return a character whose charset is CHARSET and position-codes
582 are C1 and C2. TYPE9N character ignores C2.
584 NOTE: This takes advantage of the fact that
585 FIELD2_TO_OFFICIAL_LEADING_BYTE and
586 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
589 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
591 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
593 if (EQ (charset, Vcharset_ascii))
595 else if (EQ (charset, Vcharset_control_1))
597 else if (EQ (charset, Vcharset_latin_iso8859_1))
599 else if (EQ (charset, Vcharset_greek_iso8859_7))
600 return c1 + MIN_CHAR_GREEK - 0x20;
601 else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
602 return c1 + MIN_CHAR_CYRILLIC - 0x20;
603 else if (EQ (charset, Vcharset_hebrew_iso8859_8))
604 return c1 + MIN_CHAR_HEBREW - 0x20;
605 else if (EQ (charset, Vcharset_thai_tis620))
606 return c1 + MIN_CHAR_THAI - 0x20;
607 else if (EQ (charset, Vcharset_katakana_jisx0201))
609 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
612 #ifdef ENABLE_COMPOSITE_CHARS
613 else if (EQ (charset, Vcharset_composite))
614 return (0x1F << 14) | ((c1) << 7) | (c2);
616 else if (XCHARSET_DIMENSION (charset) == 1)
617 return MULE_CHAR_PRIVATE_OFFSET
618 | ((XCHARSET_LEADING_BYTE (charset) -
619 FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1);
622 return MULE_CHAR_PRIVATE_OFFSET
623 | ((XCHARSET_LEADING_BYTE (charset) -
624 FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
626 else if (!XCHARSET_PRIVATE_P (charset))
627 return MULE_CHAR_PRIVATE_OFFSET
628 | ((XCHARSET_LEADING_BYTE (charset) -
629 FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
631 return MULE_CHAR_PRIVATE_OFFSET
632 | ((XCHARSET_LEADING_BYTE (charset) -
633 FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
637 /* The charset of character C is set to CHARSET, and the
638 position-codes of C are set to C1 and C2. C2 of TYPE9N character
641 /* BREAKUP_CHAR_1_UNSAFE assumes that the charset has already been
642 calculated, and just computes c1 and c2.
644 BREAKUP_CHAR also computes and stores the charset. */
646 #define BREAKUP_CHAR_1_UNSAFE(c, charset, c1, c2) \
647 XCHARSET_DIMENSION (charset) == 1 \
648 ? ((c1) = CHAR_FIELD3 (c), (c2) = 0) \
649 : ((c1) = CHAR_FIELD2 (c), \
650 (c2) = CHAR_FIELD3 (c))
652 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
654 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
656 *charset = CHAR_CHARSET (c);
657 BREAKUP_CHAR_1_UNSAFE (c, *charset, *c1, *c2);
660 #define BREAKUP_CHAR(c, charset, c1, c2) \
661 breakup_char_1 (c, &(charset), &(c1), &(c2))
665 #ifdef ENABLE_COMPOSITE_CHARS
666 /************************************************************************/
667 /* Composite characters */
668 /************************************************************************/
670 Emchar lookup_composite_char (Bufbyte *str, int len);
671 Lisp_Object composite_char_string (Emchar ch);
672 #endif /* ENABLE_COMPOSITE_CHARS */
675 /************************************************************************/
676 /* Exported functions */
677 /************************************************************************/
679 EXFUN (Ffind_charset, 1);
680 EXFUN (Fget_charset, 1);
682 extern Lisp_Object Vcharset_chinese_big5_1;
683 extern Lisp_Object Vcharset_chinese_big5_2;
684 extern Lisp_Object Vcharset_japanese_jisx0208;
686 Emchar Lstream_get_emchar_1 (Lstream *stream, int first_char);
687 int Lstream_fput_emchar (Lstream *stream, Emchar ch);
688 void Lstream_funget_emchar (Lstream *stream, Emchar ch);
690 int copy_internal_to_external (CONST Bufbyte *internal, Bytecount len,
691 unsigned char *external);
692 Bytecount copy_external_to_internal (CONST unsigned char *external,
693 int len, Bufbyte *internal);
695 #endif /* CHAR_IS_UCS4 */
696 #endif /* _XEMACS_CHARACTER_H */