Add some non-word syntax cases.
[emacs.git] / src / charset.h
blobdd8a872a32861e7a84c15312b824be6c365cc6e1
1 /* Header for charset handler.
2 Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
4 Copyright (C) 2001 Free Software Foundation, Inc.
5 Copyright (C) 2001, 2002
6 National Institute of Advanced Industrial Science and Technology (AIST)
7 Registration Number H13PRO009
9 This file is part of GNU Emacs.
11 GNU Emacs is free software; you can redistribute it and/or modify
12 it under the terms of the GNU General Public License as published by
13 the Free Software Foundation; either version 2, or (at your option)
14 any later version.
16 GNU Emacs is distributed in the hope that it will be useful,
17 but WITHOUT ANY WARRANTY; without even the implied warranty of
18 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 GNU General Public License for more details.
21 You should have received a copy of the GNU General Public License
22 along with GNU Emacs; see the file COPYING. If not, write to
23 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 Boston, MA 02111-1307, USA. */
26 #ifndef EMACS_CHARSET_H
27 #define EMACS_CHARSET_H
29 /* Index to arguments of Fdefine_charset_internal. */
31 enum define_charset_arg_index
33 charset_arg_name,
34 charset_arg_dimension,
35 charset_arg_code_space,
36 charset_arg_min_code,
37 charset_arg_max_code,
38 charset_arg_iso_final,
39 charset_arg_iso_revision,
40 charset_arg_emacs_mule_id,
41 charset_arg_ascii_compatible_p,
42 charset_arg_supplementary_p,
43 charset_arg_invalid_code,
44 charset_arg_code_offset,
45 charset_arg_map,
46 charset_arg_subset,
47 charset_arg_superset,
48 charset_arg_unify_map,
49 charset_arg_plist,
50 charset_arg_max
54 /* Indices to charset attributes vector. */
56 enum charset_attr_index
58 /* ID number of the charset. */
59 charset_id,
61 /* Name of the charset (symbol). */
62 charset_name,
64 /* Property list of the charset. */
65 charset_plist,
67 /* If the method of the charset is `MAP_DEFERRED', the value is a
68 mapping vector or a file name that contains mapping vector.
69 Otherwise, nil. */
70 charset_map,
72 /* If the method of the charset is `MAP', the value is a vector
73 that maps code points of the charset to characters. The vector
74 is indexed by a character index. A character index is
75 calculated from a code point and the code-space table of the
76 charset. */
77 charset_decoder,
79 /* If the method of the charset is `MAP', the value is a
80 char-table that maps characters of the charset to code
81 points. */
82 charset_encoder,
84 /* If the method of the charset is `SUBSET', the value is a vector
85 that has this form:
87 [ CHARSET-ID MIN-CODE MAX-CODE OFFSET ]
89 CHARSET-ID is an ID number of a parent charset. MIN-CODE and
90 MAX-CODE specify the range of characters inherited from the
91 parent. OFFSET is an integer value to add to a code point of
92 the parent charset to get the corresponding code point of this
93 charset. */
94 charset_subset,
96 /* If the method of the charset is `SUPERSET', the value is a list
97 whose elements have this form:
99 (CHARSET-ID . OFFSET)
101 CHARSET-IDs are ID numbers of parent charsets. OFFSET is an
102 integer value to add to a code point of the parent charset to
103 get the corresponding code point of this charset. */
104 charset_superset,
106 /* The value is a mapping vector or a file name that contains the
107 mapping. This defines how characters in the charset should be
108 unified with Unicode. The value of the member
109 `charset_deunifier' is created from this information. */
110 charset_unify_map,
112 /* If characters in the charset must be unified Unicode, the value
113 is a char table that maps a character code in the charset to
114 the corresponding Unicode character. */
115 charset_deunifier,
117 /* The length of the charset attribute vector. */
118 charset_attr_max
121 /* Methods for converting code points and characters of charsets. */
123 enum charset_method
125 /* For a charset of this method, a character code is calculated
126 from a character index (which is calculated from a code point)
127 simply by adding an offset value. */
128 CHARSET_METHOD_OFFSET,
130 /* For a charset of this method, a decoder vector and an encoder
131 char-table is used for code point <-> character code
132 conversion. */
133 CHARSET_METHOD_MAP,
135 /* Same as above but decoder and encoder are loaded from a file on
136 demand. Once loaded, the method is changed to
137 CHARSET_METHOD_MAP. */
138 CHARSET_METHOD_MAP_DEFERRED,
140 /* A charset of this method is a subset of another charset. */
141 CHARSET_METHOD_SUBSET,
143 /* A charset of this method is a superset of other charsets. */
144 CHARSET_METHOD_SUPERSET
147 struct charset
149 /* Index to charset_table. */
150 int id;
152 /* Index to Vcharset_hash_table. */
153 int hash_index;
155 /* Dimension of the charset: 1, 2, 3, or 4. */
156 int dimension;
158 /* Byte code range of each dimension. <code_space>[4N] is a mininum
159 byte code of the (N+1)th dimension, <code_space>[4N+1] is a
160 maximum byte code of the (N+1)th dimension, <code_space>[4N+2] is
161 (<code_space>[4N+1] - <code_space>[4N] + 1), <code_space>[4N+3]
162 is a number of characters containd in the first to (N+1)th
163 dismesions. We get `char-index' of a `code-point' from this
164 information. */
165 int code_space[16];
167 /* If B is a byte of Nth dimension of a code-point, the (N-1)th bit
168 of code_space_mask[B] is set. This array is used to quickly
169 check if a code-point is in a valid range. */
170 unsigned char *code_space_mask;
172 /* 1 if there's no gap in code-points. */
173 int code_linear_p;
175 /* If the charset is treated as 94-chars in ISO-2022, the value is 0.
176 If the charset is treated as 96-chars in ISO-2022, the value is 1. */
177 int iso_chars_96;
179 /* ISO final byte of the charset: 48..127. It may be -1 if the
180 charset doesn't conform to ISO-2022. */
181 int iso_final;
183 /* ISO revision number of the charset. */
184 int iso_revision;
186 /* If the charset is identical to what supported by Emacs 21 and the
187 priors, the identification number of the charset used in those
188 version. Otherwise, -1. */
189 int emacs_mule_id;
191 /* Nonzero iff the charset is compatible with ASCII. */
192 int ascii_compatible_p;
194 /* Nonzero iff the charset is supplementary. */
195 int supplementary_p;
197 /* Nonzero iff all the code points are representable by Lisp_Int. */
198 int compact_codes_p;
200 /* The method for encoding/decoding characters of the charset. */
201 enum charset_method method;
203 /* Mininum and Maximum code points of the charset. */
204 unsigned min_code, max_code;
206 /* Offset value used by macros CODE_POINT_TO_INDEX and
207 INDEX_TO_CODE_POINT. . */
208 unsigned char_index_offset;
210 /* Mininum and Maximum character codes of the charset. If the
211 charset is compatible with ASCII, min_char is a minimum non-ASCII
212 character of the charset. If the method of charset is
213 CHARSET_METHOD_OFFSET, even if the charset is unified, min_char
214 and max_char doesn't change. */
215 int min_char, max_char;
217 /* The code returned by ENCODE_CHAR if a character is not encodable
218 by the charset. */
219 unsigned invalid_code;
221 /* If the method of the charset is CHARSET_METHOD_MAP, this is a
222 table of bits used to quickly and roughly guess if a character
223 belongs to the charset.
225 The first 64 elements are 512 bits for characters less than
226 0x10000. Each bit corresponds to 128-character block. The last
227 126 elements are 1008 bits for the greater characters
228 (0x10000..0x3FFFFF). Each bit corresponds to 4096-character
229 block.
231 If a bit is 1, at least one character in the corresponding block is
232 in this charset. */
233 unsigned char fast_map[190];
235 /* Offset value to calculate a character code from code-point, and
236 visa versa. */
237 int code_offset;
239 int unified_p;
242 /* Hash table of charset symbols vs. the correponding attribute
243 vectors. */
244 extern Lisp_Object Vcharset_hash_table;
246 /* Table of struct charset. */
247 extern struct charset *charset_table;
248 extern int charset_table_used;
250 #define CHARSET_FROM_ID(id) (charset_table + (id))
252 extern Lisp_Object Vcharset_ordered_list;
254 /* Incremented everytime we change the priority of charsets. */
255 extern unsigned short charset_ordered_list_tick;
257 extern Lisp_Object Vcharset_list;
258 extern Lisp_Object Viso_2022_charset_list;
259 extern Lisp_Object Vemacs_mule_charset_list;
261 extern struct charset *emacs_mule_charset[256];
264 /* Macros to access information about charset. */
266 /* Return the attribute vector of charset whose symbol is SYMBOL. */
267 #define CHARSET_SYMBOL_ATTRIBUTES(symbol) \
268 Fgethash ((symbol), Vcharset_hash_table, Qnil)
270 #define CHARSET_ATTR_ID(attrs) AREF ((attrs), charset_id)
271 #define CHARSET_ATTR_NAME(attrs) AREF ((attrs), charset_name)
272 #define CHARSET_ATTR_PLIST(attrs) AREF ((attrs), charset_plist)
273 #define CHARSET_ATTR_MAP(attrs) AREF ((attrs), charset_map)
274 #define CHARSET_ATTR_DECODER(attrs) AREF ((attrs), charset_decoder)
275 #define CHARSET_ATTR_ENCODER(attrs) AREF ((attrs), charset_encoder)
276 #define CHARSET_ATTR_SUBSET(attrs) AREF ((attrs), charset_subset)
277 #define CHARSET_ATTR_SUPERSET(attrs) AREF ((attrs), charset_superset)
278 #define CHARSET_ATTR_UNIFY_MAP(attrs) AREF ((attrs), charset_unify_map)
279 #define CHARSET_ATTR_DEUNIFIER(attrs) AREF ((attrs), charset_deunifier)
281 #define CHARSET_SYMBOL_ID(symbol) \
282 CHARSET_ATTR_ID (CHARSET_SYMBOL_ATTRIBUTES (symbol))
284 /* Return an index to Vcharset_hash_table of the charset whose symbol
285 is SYMBOL. */
286 #define CHARSET_SYMBOL_HASH_INDEX(symbol) \
287 hash_lookup (XHASH_TABLE (Vcharset_hash_table), symbol, NULL)
289 /* Return the attribute vector of CHARSET. */
290 #define CHARSET_ATTRIBUTES(charset) \
291 (HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), (charset)->hash_index))
293 #define CHARSET_ID(charset) ((charset)->id)
294 #define CHARSET_HASH_INDEX(charset) ((charset)->hash_index)
295 #define CHARSET_DIMENSION(charset) ((charset)->dimension)
296 #define CHARSET_CODE_SPACE(charset) ((charset)->code_space)
297 #define CHARSET_CODE_LINEAR_P(charset) ((charset)->code_linear_p)
298 #define CHARSET_ISO_CHARS_96(charset) ((charset)->iso_chars_96)
299 #define CHARSET_ISO_FINAL(charset) ((charset)->iso_final)
300 #define CHARSET_ISO_PLANE(charset) ((charset)->iso_plane)
301 #define CHARSET_ISO_REVISION(charset) ((charset)->iso_revision)
302 #define CHARSET_EMACS_MULE_ID(charset) ((charset)->emacs_mule_id)
303 #define CHARSET_ASCII_COMPATIBLE_P(charset) ((charset)->ascii_compatible_p)
304 #define CHARSET_COMPACT_CODES_P(charset) ((charset)->compact_codes_p)
305 #define CHARSET_METHOD(charset) ((charset)->method)
306 #define CHARSET_MIN_CODE(charset) ((charset)->min_code)
307 #define CHARSET_MAX_CODE(charset) ((charset)->max_code)
308 #define CHARSET_INVALID_CODE(charset) ((charset)->invalid_code)
309 #define CHARSET_MIN_CHAR(charset) ((charset)->min_char)
310 #define CHARSET_MAX_CHAR(charset) ((charset)->max_char)
311 #define CHARSET_CODE_OFFSET(charset) ((charset)->code_offset)
312 #define CHARSET_UNIFIED_P(charset) ((charset)->unified_p)
314 #define CHARSET_NAME(charset) \
315 (CHARSET_ATTR_NAME (CHARSET_ATTRIBUTES (charset)))
316 #define CHARSET_MAP(charset) \
317 (CHARSET_ATTR_MAP (CHARSET_ATTRIBUTES (charset)))
318 #define CHARSET_DECODER(charset) \
319 (CHARSET_ATTR_DECODER (CHARSET_ATTRIBUTES (charset)))
320 #define CHARSET_ENCODER(charset) \
321 (CHARSET_ATTR_ENCODER (CHARSET_ATTRIBUTES (charset)))
322 #define CHARSET_SUBSET(charset) \
323 (CHARSET_ATTR_SUBSET (CHARSET_ATTRIBUTES (charset)))
324 #define CHARSET_SUPERSET(charset) \
325 (CHARSET_ATTR_SUPERSET (CHARSET_ATTRIBUTES (charset)))
326 #define CHARSET_UNIFY_MAP(charset) \
327 (CHARSET_ATTR_UNIFY_MAP (CHARSET_ATTRIBUTES (charset)))
328 #define CHARSET_DEUNIFIER(charset) \
329 (CHARSET_ATTR_DEUNIFIER (CHARSET_ATTRIBUTES (charset)))
332 /* Nonzero iff OBJ is a valid charset symbol. */
333 #define CHARSETP(obj) (CHARSET_SYMBOL_HASH_INDEX (obj) >= 0)
335 /* Check if X is a valid charset symbol. If not, signal an error. */
336 #define CHECK_CHARSET(x) \
337 do { \
338 if (! SYMBOLP (x) || CHARSET_SYMBOL_HASH_INDEX (x) < 0) \
339 x = wrong_type_argument (Qcharsetp, (x)); \
340 } while (0)
343 /* Check if X is a valid charset symbol. If valid, set ID to the id
344 number of the charset. Otherwise, signal an error. */
345 #define CHECK_CHARSET_GET_ID(x, id) \
346 do { \
347 int idx; \
349 if (! SYMBOLP (x) || (idx = CHARSET_SYMBOL_HASH_INDEX (x)) < 0) \
350 x = wrong_type_argument (Qcharsetp, (x)); \
351 id = XINT (AREF (HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), idx), \
352 charset_id)); \
353 } while (0)
356 /* Check if X is a valid charset symbol. If valid, set ATTR to the
357 attr vector of the charset. Otherwise, signal an error. */
358 #define CHECK_CHARSET_GET_ATTR(x, attr) \
359 do { \
360 if (!SYMBOLP (x) || NILP (attr = CHARSET_SYMBOL_ATTRIBUTES (x))) \
361 x = wrong_type_argument (Qcharsetp, (x)); \
362 } while (0)
365 #define CHECK_CHARSET_GET_CHARSET(x, charset) \
366 do { \
367 int id; \
368 CHECK_CHARSET_GET_ID (x, id); \
369 charset = CHARSET_FROM_ID (id); \
370 } while (0)
373 /* Lookup Vcharset_order_list and return the first charset that
374 contains the character C. */
375 #define CHAR_CHARSET(c) \
376 char_charset ((c), Qnil, NULL)
378 #if 0
379 /* Char-table of charset-sets. Each element is a bool vector indexed
380 by a charset ID. */
381 extern Lisp_Object Vchar_charset_set;
383 /* Charset-bag of character C. */
384 #define CHAR_CHARSET_SET(c) \
385 CHAR_TABLE_REF (Vchar_charset_set, c)
387 /* Check if two characters C1 and C2 belong to the same charset. */
388 #define SAME_CHARSET_P(c1, c2) \
389 intersection_p (CHAR_CHARSET_SET (c1), CHAR_CHARSET_SET (c2))
391 #endif
394 /* Return a character correponding to the code-point CODE of CHARSET.
395 Try some optimization before calling decode_char. */
397 #define DECODE_CHAR(charset, code) \
398 ((ASCII_BYTE_P (code) && (charset)->ascii_compatible_p) \
399 ? (code) \
400 : ((code) < (charset)->min_code || (code) > (charset)->max_code) \
401 ? -1 \
402 : (charset)->unified_p \
403 ? decode_char ((charset), (code)) \
404 : (charset)->method == CHARSET_METHOD_OFFSET \
405 ? ((charset)->code_linear_p \
406 ? (code) - (charset)->min_code + (charset)->code_offset \
407 : decode_char ((charset), (code))) \
408 : (charset)->method == CHARSET_METHOD_MAP \
409 ? ((charset)->code_linear_p \
410 ? XINT (AREF (CHARSET_DECODER (charset), \
411 (code) - (charset)->min_code)) \
412 : decode_char ((charset), (code))) \
413 : decode_char ((charset), (code)))
416 extern Lisp_Object charset_work;
418 /* Return a code point of CHAR in CHARSET.
419 Try some optimization before calling encode_char. */
421 #define ENCODE_CHAR(charset, c) \
422 ((ASCII_CHAR_P (c) && (charset)->ascii_compatible_p) \
423 ? (c) \
424 : (charset)->unified_p \
425 ? encode_char ((charset), (c)) \
426 : ((c) < (charset)->min_char || (c) > (charset)->max_char) \
427 ? (charset)->invalid_code \
428 : (charset)->method == CHARSET_METHOD_OFFSET \
429 ? ((charset)->code_linear_p \
430 ? (c) - (charset)->code_offset + (charset)->min_code \
431 : encode_char ((charset), (c))) \
432 : (charset)->method == CHARSET_METHOD_MAP \
433 ? ((charset)->compact_codes_p \
434 ? (charset_work = CHAR_TABLE_REF (CHARSET_ENCODER (charset), (c)), \
435 (NILP (charset_work) \
436 ? (charset)->invalid_code \
437 : XFASTINT (charset_work))) \
438 : encode_char ((charset), (c))) \
439 : encode_char ((charset), (c)))
442 /* Set to 1 when a charset map is loaded to warn that a buffer text
443 and a string data may be relocated. */
444 extern int charset_map_loaded;
447 /* Set CHARSET to the charset highest priority of C, CODE to the
448 code-point of C in CHARSET. */
449 #define SPLIT_CHAR(c, charset, code) \
450 ((charset) = char_charset ((c), Qnil, &(code)))
453 #define ISO_MAX_DIMENSION 3
454 #define ISO_MAX_CHARS 2
455 #define ISO_MAX_FINAL 0x80 /* only 0x30..0xFF are used */
457 /* Mapping table from ISO2022's charset (specified by DIMENSION,
458 CHARS, and FINAL_CHAR) to Emacs' charset ID. Should be accessed by
459 macro ISO_CHARSET_TABLE (DIMENSION, CHARS, FINAL_CHAR). */
460 extern int iso_charset_table[ISO_MAX_DIMENSION][ISO_MAX_CHARS][ISO_MAX_FINAL];
462 /* A charset of type iso2022 who has DIMENSION, CHARS, and FINAL
463 (final character). */
464 #define ISO_CHARSET_TABLE(dimension, chars_96, final) \
465 iso_charset_table[(dimension) - 1][(chars_96)][(final)]
467 /* Nonzero iff the charset who has FAST_MAP may contain C. */
468 #define CHARSET_FAST_MAP_REF(c, fast_map) \
469 ((c) < 0x10000 \
470 ? fast_map[(c) >> 10] & (1 << (((c) >> 7) & 7)) \
471 : fast_map[((c) >> 15) + 62] & (1 << (((c) >> 12) & 7)))
473 #define CHARSET_FAST_MAP_SET(c, fast_map) \
474 do { \
475 if ((c) < 0x10000) \
476 (fast_map)[(c) >> 10] |= 1 << (((c) >> 7) & 7); \
477 else \
478 (fast_map)[((c) >> 15) + 62] |= 1 << (((c) >> 12) & 7); \
479 } while (0)
483 /* 1 iff CHARSET may contain the character C. */
484 #define CHAR_CHARSET_P(c, charset) \
485 ((ASCII_CHAR_P (c) && (charset)->ascii_compatible_p) \
486 || (CHARSET_UNIFIED_P (charset) \
487 ? encode_char ((charset), (c)) != (charset)->invalid_code \
488 : (CHARSET_FAST_MAP_REF ((c), (charset)->fast_map) \
489 && ((charset)->method == CHARSET_METHOD_OFFSET \
490 ? (c) >= (charset)->min_char && (c) <= (charset)->max_char \
491 : ((charset)->method == CHARSET_METHOD_MAP \
492 && (charset)->compact_codes_p) \
493 ? ! NILP (CHAR_TABLE_REF (CHARSET_ENCODER (charset), (c))) \
494 : encode_char ((charset), (c)) != (charset)->invalid_code))))
497 /* Special macros for emacs-mule encoding. */
499 /* Leading-code followed by extended leading-code. DIMENSION/COLUMN */
500 #define EMACS_MULE_LEADING_CODE_PRIVATE_11 0x9A /* 1/1 */
501 #define EMACS_MULE_LEADING_CODE_PRIVATE_12 0x9B /* 1/2 */
502 #define EMACS_MULE_LEADING_CODE_PRIVATE_21 0x9C /* 2/2 */
503 #define EMACS_MULE_LEADING_CODE_PRIVATE_22 0x9D /* 2/2 */
505 extern struct charset *emacs_mule_charset[256];
509 extern Lisp_Object Qcharsetp;
511 extern Lisp_Object Qascii, Qunicode;
512 extern int charset_ascii, charset_eight_bit;
513 extern int charset_iso_8859_1;
514 extern int charset_jisx0201_roman;
515 extern int charset_jisx0208_1978;
516 extern int charset_jisx0208;
518 extern int charset_unibyte;
520 extern struct charset *char_charset P_ ((int, Lisp_Object, unsigned *));
521 extern Lisp_Object charset_attributes P_ ((int));
523 extern int decode_char P_ ((struct charset *, unsigned));
524 extern unsigned encode_char P_ ((struct charset *, int));
525 extern int string_xstring_p P_ ((Lisp_Object));
527 extern void map_charset_chars P_ ((void (*) (Lisp_Object, Lisp_Object),
528 Lisp_Object, Lisp_Object,
529 struct charset *, unsigned, unsigned));
531 EXFUN (Funify_charset, 3);
533 #endif /* EMACS_CHARSET_H */