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 #ifdef ENABLE_COMPOSITE_CHARS
40 #define LEADING_BYTE_COMPOSITE 0x80 /* for a composite character */
41 #define LEADING_BYTE_CONTROL_1 0x8F /* represent normal 80-9F */
43 /** The following are for 1-byte characters in an official charset. **/
45 #define LEADING_BYTE_LATIN_ISO8859_1 0x81 /* Right half of ISO 8859-1 */
46 #define LEADING_BYTE_LATIN_ISO8859_2 0x82 /* Right half of ISO 8859-2 */
47 #define LEADING_BYTE_LATIN_ISO8859_3 0x83 /* Right half of ISO 8859-3 */
48 #define LEADING_BYTE_LATIN_ISO8859_4 0x84 /* Right half of ISO 8859-4 */
49 #define LEADING_BYTE_THAI_TIS620 0x85 /* TIS620-2533 */
50 #define LEADING_BYTE_GREEK_ISO8859_7 0x86 /* Right half of ISO 8859-7 */
51 #define LEADING_BYTE_ARABIC_ISO8859_6 0x87 /* Right half of ISO 8859-6 */
52 #define LEADING_BYTE_HEBREW_ISO8859_8 0x88 /* Right half of ISO 8859-8 */
53 #define LEADING_BYTE_KATAKANA_JISX0201 0x89 /* Right half of JIS X0201-1976 */
54 #define LEADING_BYTE_LATIN_JISX0201 0x8A /* Left half of JIS X0201-1976 */
55 #define LEADING_BYTE_CYRILLIC_ISO8859_5 0x8C /* Right half of ISO 8859-5 */
56 #define LEADING_BYTE_LATIN_ISO8859_9 0x8D /* Right half of ISO 8859-9 */
58 #define MIN_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_1
59 #define MAX_LEADING_BYTE_OFFICIAL_1 LEADING_BYTE_LATIN_ISO8859_9
61 /** The following are for 2-byte characters in an official charset. **/
63 #define LEADING_BYTE_JAPANESE_JISX0208_1978 0x90/* Japanese JIS X0208-1978 */
64 #define LEADING_BYTE_CHINESE_GB2312 0x91 /* Chinese Hanzi GB2312-1980 */
65 #define LEADING_BYTE_JAPANESE_JISX0208 0x92 /* Japanese JIS X0208-1983 */
66 #define LEADING_BYTE_KOREAN_KSC5601 0x93 /* Hangul KS C5601-1987 */
67 #define LEADING_BYTE_JAPANESE_JISX0212 0x94 /* Japanese JIS X0212-1990 */
68 #define LEADING_BYTE_CHINESE_CCITT_GB 0x95 /* CCITT Extended GB */
69 #define LEADING_BYTE_CHINESE_BIG5_1 0x96 /* Big5 Level 1 */
70 #define LEADING_BYTE_CHINESE_CNS11643_1 0x97 /* Chinese CNS11643 Set 1 */
71 #define LEADING_BYTE_CHINESE_CNS11643_2 0x98 /* Chinese CNS11643 Set 2 */
72 #define LEADING_BYTE_CHINESE_CNS11643_3 0x99 /* Chinese CNS11643 Set 3 */
73 #define LEADING_BYTE_CHINESE_CNS11643_4 0x9A /* Chinese CNS11643 Set 4 */
74 #define LEADING_BYTE_CHINESE_CNS11643_5 0x9B /* Chinese CNS11643 Set 5 */
75 #define LEADING_BYTE_CHINESE_CNS11643_6 0x9C /* Chinese CNS11643 Set 6 */
76 #define LEADING_BYTE_CHINESE_CNS11643_7 0x9D /* Chinese CNS11643 Set 7 */
77 #define LEADING_BYTE_CHINESE_BIG5_2 0x9D /* Big5 Level 2 */
78 #define LEADING_BYTE_KOREAN_KPS9566 0x9E /* DPRK Hangul KPS 9566-1997 */
80 #define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978
81 #define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_CHINESE_BIG5_2
83 /** The following are for 1- and 2-byte characters in a private charset. **/
85 #define PRE_LEADING_BYTE_PRIVATE_1 0x9E /* 1-byte char-set */
86 #define PRE_LEADING_BYTE_PRIVATE_2 0x9F /* 2-byte char-set */
88 #define MIN_LEADING_BYTE_PRIVATE_1 0xA0
89 #define MAX_LEADING_BYTE_PRIVATE_1 0xEF
90 #define MIN_LEADING_BYTE_PRIVATE_2 0xF0
91 #define MAX_LEADING_BYTE_PRIVATE_2 0xFF
93 #define NUM_LEADING_BYTES 128
96 /************************************************************************/
97 /* Operations on leading bytes */
98 /************************************************************************/
100 /* Is this leading byte for a private charset? */
102 #define LEADING_BYTE_PRIVATE_P(lb) ((lb) >= MIN_LEADING_BYTE_PRIVATE_1)
104 /* Is this a prefix for a private leading byte? */
106 INLINE int LEADING_BYTE_PREFIX_P (unsigned char lb);
108 LEADING_BYTE_PREFIX_P (unsigned char lb)
110 return (lb == PRE_LEADING_BYTE_PRIVATE_1 ||
111 lb == PRE_LEADING_BYTE_PRIVATE_2);
114 /* Given a private leading byte, return the leading byte prefix stored
117 #define PRIVATE_LEADING_BYTE_PREFIX(lb) \
118 ((lb) < MIN_LEADING_BYTE_PRIVATE_2 ? \
119 PRE_LEADING_BYTE_PRIVATE_1 : \
120 PRE_LEADING_BYTE_PRIVATE_2)
123 /************************************************************************/
124 /* Operations on individual bytes */
126 /************************************************************************/
128 /* Argument `c' should be (unsigned int) or (unsigned char). */
129 /* Note that SP and DEL are not included. */
131 #define BYTE_ASCII_P(c) ((c) < 0x80)
132 #define BYTE_C0_P(c) ((c) < 0x20)
133 /* Do some forced casting just to make *sure* things are gotten right. */
134 #define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20)
137 /************************************************************************/
138 /* Operations on individual bytes */
139 /* in a Mule-formatted string */
140 /************************************************************************/
142 /* Does this byte represent the first byte of a character? */
146 BUFBYTE_FIRST_BYTE_P(Bufbyte c)
148 return (c <= 0x7f) || (0xc0 <= c);
151 #define BUFBYTE_FIRST_BYTE_P(c) ((c) < 0xA0)
154 /* Does this byte represent the first byte of a multi-byte character? */
156 #define BUFBYTE_LEADING_BYTE_P(c) BYTE_C1_P (c)
159 /************************************************************************/
160 /* Information about a particular character set */
161 /************************************************************************/
165 struct lcrecord_header header;
169 Lisp_Object doc_string, registry, short_name, long_name;
171 Lisp_Object reverse_direction_charset;
173 Lisp_Object ccl_program;
175 /* Final byte of this character set in ISO2022 designating escape sequence */
178 /* Number of bytes (1 - 4) required in the internal representation
179 for characters in this character set. This is *not* the
180 same as the dimension of the character set). */
181 unsigned int rep_bytes;
183 /* Number of columns a character in this charset takes up, on TTY
184 devices. Not used for X devices. */
185 unsigned int columns;
187 /* Direction of this character set */
188 unsigned int direction;
190 /* Type of this character set (94, 96, 94x94, 96x96) */
193 /* Number of bytes used in encoding of this character set (1 or 2) */
194 unsigned int dimension;
196 /* Number of chars in each dimension (usually 94 or 96) */
199 /* Which half of font to be used to display this character set */
200 unsigned int graphic;
203 DECLARE_LRECORD (charset, struct Lisp_Charset);
204 #define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
205 #define XSETCHARSET(x, p) XSETRECORD (x, p, charset)
206 #define CHARSETP(x) RECORDP (x, charset)
207 #define GC_CHARSETP(x) GC_RECORDP (x, charset)
208 #define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
209 #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset)
211 #define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */
212 #define CHARSET_TYPE_96 1 /* This charset includes 96 characters. */
213 #define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */
214 #define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */
216 #define CHARSET_LEFT_TO_RIGHT 0
217 #define CHARSET_RIGHT_TO_LEFT 1
219 /* Leading byte and id have been regrouped. -- OG */
220 #define CHARSET_ID(cs) ((cs)->id)
221 #define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs)))
222 #define CHARSET_NAME(cs) ((cs)->name)
223 #define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
224 #define CHARSET_LONG_NAME(cs) ((cs)->long_name)
225 #define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes)
226 #define CHARSET_COLUMNS(cs) ((cs)->columns)
227 #define CHARSET_GRAPHIC(cs) ((cs)->graphic)
228 #define CHARSET_TYPE(cs) ((cs)->type)
229 #define CHARSET_DIRECTION(cs) ((cs)->direction)
230 #define CHARSET_FINAL(cs) ((cs)->final)
231 #define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
232 #define CHARSET_REGISTRY(cs) ((cs)->registry)
233 #define CHARSET_CCL_PROGRAM(cs) ((cs)->ccl_program)
234 #define CHARSET_DIMENSION(cs) ((cs)->dimension)
235 #define CHARSET_CHARS(cs) ((cs)->chars)
236 #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset)
239 #define CHARSET_PRIVATE_P(cs) LEADING_BYTE_PRIVATE_P (CHARSET_LEADING_BYTE (cs))
241 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
242 #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
243 #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
244 #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
245 #define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs))
246 #define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (XCHARSET (cs))
247 #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
248 #define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
249 #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
250 #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
251 #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs))
252 #define XCHARSET_REGISTRY(cs) CHARSET_REGISTRY (XCHARSET (cs))
253 #define XCHARSET_LEADING_BYTE(cs) CHARSET_LEADING_BYTE (XCHARSET (cs))
254 #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
255 #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
256 #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
257 #define XCHARSET_PRIVATE_P(cs) CHARSET_PRIVATE_P (XCHARSET (cs))
258 #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \
259 CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
261 /* Table of charsets indexed by (leading byte - 128). */
262 extern Lisp_Object charset_by_leading_byte[128];
264 /* Table of charsets indexed by type/final-byte/direction. */
265 extern Lisp_Object charset_by_attributes[4][128][2];
267 /* Table of number of bytes in the string representation of a character
268 indexed by the first byte of that representation.
270 This value can be derived other ways -- e.g. something like
272 (BYTE_ASCII_P (first_byte) ? 1 :
273 XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte)))
275 but it's faster this way. */
276 extern Bytecount rep_bytes_by_first_byte[0xA0];
278 #ifdef ERROR_CHECK_TYPECHECK
279 /* int not Bufbyte even though that is the actual type of a leading byte.
280 This way, out-ot-range values will get caught rather than automatically
282 INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (int lb);
284 CHARSET_BY_LEADING_BYTE (int lb)
286 assert (lb >= 0x80 && lb <= 0xFF);
287 return charset_by_leading_byte[lb - 128];
292 #define CHARSET_BY_LEADING_BYTE(lb) (charset_by_leading_byte[(lb) - 128])
296 #define CHARSET_BY_ATTRIBUTES(type, final, dir) \
297 (charset_by_attributes[type][final][dir])
300 INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
302 REP_BYTES_BY_FIRST_BYTE (int fb)
306 else if ( fb >= 0xf8 )
308 else if ( fb >= 0xf0 )
310 else if ( fb >= 0xe0 )
312 else if ( fb >= 0xc0 )
318 #ifdef ERROR_CHECK_TYPECHECK
320 /* Number of bytes in the string representation of a character */
321 INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
323 REP_BYTES_BY_FIRST_BYTE (int fb)
325 assert (fb >= 0 && fb < 0xA0);
326 return rep_bytes_by_first_byte[fb];
330 #define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb])
332 #endif /* end MULE */
335 /************************************************************************/
336 /* Dealing with characters */
337 /************************************************************************/
339 /* Is this character represented by more than one byte in a string? */
341 #define CHAR_MULTIBYTE_P(c) ((c) >= 0x80)
343 #define CHAR_ASCII_P(c) (!CHAR_MULTIBYTE_P (c))
345 /* The bit fields of character are divided into 3 parts:
346 FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */
348 #define CHAR_FIELD1_MASK (0x7F << 14)
349 #define CHAR_FIELD2_MASK (0x7F << 7)
350 #define CHAR_FIELD3_MASK 0x7F
352 #define MIN_CHAR_GREEK 0x0370
353 #define MAX_CHAR_GREEK 0x03CF
355 #define MIN_CHAR_CYRILLIC 0x0400
356 #define MAX_CHAR_CYRILLIC 0x045F
358 #define MIN_CHAR_HEBREW 0x0590
359 #define MAX_CHAR_HEBREW 0x05EF
361 #define MIN_CHAR_THAI 0x0E00
362 #define MAX_CHAR_THAI 0x0E5F
364 #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
365 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
367 /* Macros to access each field of a character code of C. */
369 #define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14)
370 #define CHAR_FIELD2_INTERNAL(c) (((c) & CHAR_FIELD2_MASK) >> 7)
371 #define CHAR_FIELD3_INTERNAL(c) ((c) & CHAR_FIELD3_MASK)
373 /* Field 1, if non-zero, usually holds a leading byte for a
374 dimension-2 charset. Field 2, if non-zero, usually holds a leading
375 byte for a dimension-1 charset. */
377 /* Converting between field values and leading bytes. */
379 #define FIELD2_TO_OFFICIAL_LEADING_BYTE 0x80
380 #define FIELD2_TO_PRIVATE_LEADING_BYTE 0x80
382 #define FIELD1_TO_PRIVATE_LEADING_BYTE 0xc0
383 #define FIELD1_TO_OFFICIAL_LEADING_BYTE 0x50
386 CHAR_FIELD2 (Emchar c)
388 if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) )
389 return LEADING_BYTE_GREEK_ISO8859_7
390 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
391 else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) )
392 return LEADING_BYTE_CYRILLIC_ISO8859_5
393 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
394 else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) )
395 return LEADING_BYTE_HEBREW_ISO8859_8
396 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
397 else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) )
398 return LEADING_BYTE_THAI_TIS620
399 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
400 else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c)
401 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) )
402 return LEADING_BYTE_KATAKANA_JISX0201
403 - FIELD2_TO_OFFICIAL_LEADING_BYTE;
405 return CHAR_FIELD2_INTERNAL(c);
409 CHAR_FIELD3 (Emchar c)
411 if( (MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK) )
412 return c - MIN_CHAR_GREEK + 0x20;
413 else if( (MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC) )
414 return c - MIN_CHAR_CYRILLIC + 0x20;
415 else if( (MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW) )
416 return c - MIN_CHAR_HEBREW + 0x20;
417 else if( (MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI) )
418 return c - MIN_CHAR_THAI + 0x20;
419 else if( (MIN_CHAR_HALFWIDTH_KATAKANA <= c)
420 && (c <= MAX_CHAR_HALFWIDTH_KATAKANA) )
421 return c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
423 return CHAR_FIELD3_INTERNAL(c);
426 /* Minimum and maximum allowed values for the fields. */
428 #define MIN_CHAR_FIELD2_OFFICIAL \
429 (MIN_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
430 #define MAX_CHAR_FIELD2_OFFICIAL \
431 (MAX_LEADING_BYTE_OFFICIAL_1 - FIELD2_TO_OFFICIAL_LEADING_BYTE)
433 #define MIN_CHAR_FIELD1_OFFICIAL \
434 (MIN_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
435 #define MAX_CHAR_FIELD1_OFFICIAL \
436 (MAX_LEADING_BYTE_OFFICIAL_2 - FIELD1_TO_OFFICIAL_LEADING_BYTE)
438 #define MIN_CHAR_FIELD2_PRIVATE \
439 (MIN_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
440 #define MAX_CHAR_FIELD2_PRIVATE \
441 (MAX_LEADING_BYTE_PRIVATE_1 - FIELD2_TO_PRIVATE_LEADING_BYTE)
443 #define MIN_CHAR_FIELD1_PRIVATE \
444 (MIN_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
445 #define MAX_CHAR_FIELD1_PRIVATE \
446 (MAX_LEADING_BYTE_PRIVATE_2 - FIELD1_TO_PRIVATE_LEADING_BYTE)
448 /* Minimum character code of each <type> character. */
450 #define MULE_CHAR_PRIVATE_OFFSET (0xe0 << 16)
452 #define MIN_CHAR_OFFICIAL_TYPE9N \
453 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_OFFICIAL << 7))
454 #define MIN_CHAR_PRIVATE_TYPE9N \
455 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD2_PRIVATE << 7))
456 #define MIN_CHAR_PRIVATE_TYPE9NX9N \
457 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_PRIVATE << 14))
458 #define MIN_CHAR_OFFICIAL_TYPE9NX9N \
459 (MULE_CHAR_PRIVATE_OFFSET | (MIN_CHAR_FIELD1_OFFICIAL << 14))
460 #define MIN_CHAR_COMPOSITION \
461 (MULE_CHAR_PRIVATE_OFFSET | (0x7f << 14))
463 /* Leading byte of a character.
465 NOTE: This takes advantage of the fact that
466 FIELD2_TO_OFFICIAL_LEADING_BYTE and
467 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
470 INLINE Bufbyte CHAR_LEADING_BYTE (Emchar c);
472 CHAR_LEADING_BYTE (Emchar c)
474 if (CHAR_ASCII_P (c))
475 return LEADING_BYTE_ASCII;
477 return LEADING_BYTE_CONTROL_1;
479 return LEADING_BYTE_LATIN_ISO8859_1;
480 else if (c <= MAX_CHAR_GREEK)
481 return LEADING_BYTE_GREEK_ISO8859_7;
482 else if (c <= MAX_CHAR_CYRILLIC)
483 return LEADING_BYTE_CYRILLIC_ISO8859_5;
484 else if (c <= MAX_CHAR_HEBREW)
485 return LEADING_BYTE_HEBREW_ISO8859_8;
486 else if (c <= MAX_CHAR_THAI)
487 return LEADING_BYTE_THAI_TIS620;
488 else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
489 return LEADING_BYTE_KATAKANA_JISX0201;
490 else if (c < MIN_CHAR_PRIVATE_TYPE9NX9N)
491 return CHAR_FIELD2 (c) + FIELD2_TO_OFFICIAL_LEADING_BYTE;
492 else if (c < MIN_CHAR_OFFICIAL_TYPE9NX9N)
493 return CHAR_FIELD1 (c) + FIELD1_TO_PRIVATE_LEADING_BYTE;
494 else if (c < MIN_CHAR_COMPOSITION)
495 return CHAR_FIELD1 (c) + FIELD1_TO_OFFICIAL_LEADING_BYTE;
498 #ifdef ENABLE_COMPOSITE_CHARS
499 return LEADING_BYTE_COMPOSITE;
503 #endif /* ENABLE_COMPOSITE_CHARS */
507 #define CHAR_CHARSET(c) CHARSET_BY_LEADING_BYTE (CHAR_LEADING_BYTE (c))
509 /* Return a character whose charset is CHARSET and position-codes
510 are C1 and C2. TYPE9N character ignores C2.
512 NOTE: This takes advantage of the fact that
513 FIELD2_TO_OFFICIAL_LEADING_BYTE and
514 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
517 INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
519 MAKE_CHAR (Lisp_Object charset, int c1, int c2)
521 if (EQ (charset, Vcharset_ascii))
523 else if (EQ (charset, Vcharset_control_1))
525 else if (EQ (charset, Vcharset_latin_iso8859_1))
527 else if (EQ (charset, Vcharset_greek_iso8859_7))
528 return c1 + MIN_CHAR_GREEK - 0x20;
529 else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
530 return c1 + MIN_CHAR_CYRILLIC - 0x20;
531 else if (EQ (charset, Vcharset_hebrew_iso8859_8))
532 return c1 + MIN_CHAR_HEBREW - 0x20;
533 else if (EQ (charset, Vcharset_thai_tis620))
534 return c1 + MIN_CHAR_THAI - 0x20;
535 else if (EQ (charset, Vcharset_katakana_jisx0201))
537 return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
540 #ifdef ENABLE_COMPOSITE_CHARS
541 else if (EQ (charset, Vcharset_composite))
542 return (0x1F << 14) | ((c1) << 7) | (c2);
544 else if (XCHARSET_DIMENSION (charset) == 1)
545 return MULE_CHAR_PRIVATE_OFFSET
546 | ((XCHARSET_LEADING_BYTE (charset) -
547 FIELD2_TO_OFFICIAL_LEADING_BYTE) << 7) | (c1);
548 else if (!XCHARSET_PRIVATE_P (charset))
549 return MULE_CHAR_PRIVATE_OFFSET
550 | ((XCHARSET_LEADING_BYTE (charset) -
551 FIELD1_TO_OFFICIAL_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
553 return MULE_CHAR_PRIVATE_OFFSET
554 | ((XCHARSET_LEADING_BYTE (charset) -
555 FIELD1_TO_PRIVATE_LEADING_BYTE) << 14) | ((c1) << 7) | (c2);
558 /* The charset of character C is set to CHARSET, and the
559 position-codes of C are set to C1 and C2. C2 of TYPE9N character
562 /* BREAKUP_CHAR_1_UNSAFE assumes that the charset has already been
563 calculated, and just computes c1 and c2.
565 BREAKUP_CHAR also computes and stores the charset. */
567 #define BREAKUP_CHAR_1_UNSAFE(c, charset, c1, c2) \
568 XCHARSET_DIMENSION (charset) == 1 \
569 ? ((c1) = CHAR_FIELD3 (c), (c2) = 0) \
570 : ((c1) = CHAR_FIELD2 (c), \
571 (c2) = CHAR_FIELD3 (c))
573 INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
575 breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
577 *charset = CHAR_CHARSET (c);
578 BREAKUP_CHAR_1_UNSAFE (c, *charset, *c1, *c2);
581 #define BREAKUP_CHAR(c, charset, c1, c2) \
582 breakup_char_1 (c, &(charset), &(c1), &(c2))
586 #ifdef ENABLE_COMPOSITE_CHARS
587 /************************************************************************/
588 /* Composite characters */
589 /************************************************************************/
591 Emchar lookup_composite_char (Bufbyte *str, int len);
592 Lisp_Object composite_char_string (Emchar ch);
593 #endif /* ENABLE_COMPOSITE_CHARS */
596 /************************************************************************/
597 /* Exported functions */
598 /************************************************************************/
600 EXFUN (Ffind_charset, 1);
601 EXFUN (Fget_charset, 1);
603 extern Lisp_Object Vcharset_chinese_big5_1;
604 extern Lisp_Object Vcharset_chinese_big5_2;
605 extern Lisp_Object Vcharset_japanese_jisx0208;
607 Emchar Lstream_get_emchar_1 (Lstream *stream, int first_char);
608 int Lstream_fput_emchar (Lstream *stream, Emchar ch);
609 void Lstream_funget_emchar (Lstream *stream, Emchar ch);
611 int copy_internal_to_external (CONST Bufbyte *internal, Bytecount len,
612 unsigned char *external);
613 Bytecount copy_external_to_internal (CONST unsigned char *external,
614 int len, Bufbyte *internal);
616 #endif /* CHAR_IS_UCS4 */
617 #endif /* _XEMACS_CHARACTER_H */