Commit | Line | Data |
---|---|---|
0168c3d8 KH |
1 | /* Basic character support. |
2 | Copyright (C) 1995, 1997, 1998, 2001 Electrotechnical Laboratory, JAPAN. | |
8f924df7 | 3 | Licensed to the Free Software Foundation. |
76b6f707 | 4 | Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 |
ec62e0ac | 5 | Free Software Foundation, Inc. |
76b6f707 | 6 | Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009 |
0168c3d8 KH |
7 | National Institute of Advanced Industrial Science and Technology (AIST) |
8 | Registration Number H13PRO009 | |
9 | ||
10 | This file is part of GNU Emacs. | |
11 | ||
9ec0b715 | 12 | GNU Emacs is free software: you can redistribute it and/or modify |
0168c3d8 | 13 | it under the terms of the GNU General Public License as published by |
9ec0b715 GM |
14 | the Free Software Foundation, either version 3 of the License, or |
15 | (at your option) any later version. | |
0168c3d8 KH |
16 | |
17 | GNU Emacs is distributed in the hope that it will be useful, | |
18 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
19 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
20 | GNU General Public License for more details. | |
21 | ||
22 | You should have received a copy of the GNU General Public License | |
9ec0b715 | 23 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
0168c3d8 KH |
24 | |
25 | /* At first, see the document in `character.h' to understand the code | |
26 | in this file. */ | |
27 | ||
28 | #ifdef emacs | |
29 | #include <config.h> | |
30 | #endif | |
31 | ||
32 | #include <stdio.h> | |
33 | ||
34 | #ifdef emacs | |
35 | ||
36 | #include <sys/types.h> | |
d7306fe6 | 37 | #include <setjmp.h> |
0168c3d8 KH |
38 | #include "lisp.h" |
39 | #include "character.h" | |
40 | #include "buffer.h" | |
41 | #include "charset.h" | |
42 | #include "composite.h" | |
43 | #include "disptab.h" | |
44 | ||
45 | #else /* not emacs */ | |
46 | ||
47 | #include "mulelib.h" | |
48 | ||
49 | #endif /* emacs */ | |
50 | ||
51 | Lisp_Object Qcharacterp; | |
52 | ||
53 | /* Vector of translation table ever defined. | |
54 | ID of a translation table is used to index this vector. */ | |
55 | Lisp_Object Vtranslation_table_vector; | |
56 | ||
57 | /* A char-table for characters which may invoke auto-filling. */ | |
58 | Lisp_Object Vauto_fill_chars; | |
59 | ||
60 | Lisp_Object Qauto_fill_chars; | |
61 | ||
33f91981 | 62 | /* Char-table of information about which character to unify to which |
6f1b43a0 | 63 | Unicode character. Mainly used by the macro MAYBE_UNIFY_CHAR. */ |
0168c3d8 KH |
64 | Lisp_Object Vchar_unify_table; |
65 | ||
66 | /* A char-table. An element is non-nil iff the corresponding | |
67 | character has a printable glyph. */ | |
68 | Lisp_Object Vprintable_chars; | |
69 | ||
70 | /* A char-table. An elemnent is a column-width of the corresponding | |
71 | character. */ | |
72 | Lisp_Object Vchar_width_table; | |
73 | ||
74 | /* A char-table. An element is a symbol indicating the direction | |
75 | property of corresponding character. */ | |
76 | Lisp_Object Vchar_direction_table; | |
77 | ||
8973478b | 78 | /* Variable used locally in the macro FETCH_MULTIBYTE_CHAR. */ |
0168c3d8 | 79 | unsigned char *_fetch_multibyte_char_p; |
0168c3d8 | 80 | |
c57f3328 KH |
81 | /* Char table of scripts. */ |
82 | Lisp_Object Vchar_script_table; | |
83 | ||
c7e14352 KH |
84 | /* Alist of scripts vs representative characters. */ |
85 | Lisp_Object Vscript_representative_chars; | |
86 | ||
c57f3328 KH |
87 | static Lisp_Object Qchar_script_table; |
88 | ||
a3cbb631 | 89 | Lisp_Object Vunicode_category_table; |
0168c3d8 KH |
90 | \f |
91 | ||
2bde7652 KH |
92 | /* If character code C has modifier masks, reflect them to the |
93 | character code if possible. Return the resulting code. */ | |
94 | ||
95 | int | |
96 | char_resolve_modifier_mask (c) | |
97 | int c; | |
98 | { | |
d0363d44 | 99 | /* A non-ASCII character can't reflect modifier bits to the code. */ |
2bde7652 KH |
100 | if (! ASCII_CHAR_P ((c & ~CHAR_MODIFIER_MASK))) |
101 | return c; | |
102 | ||
103 | /* For Meta, Shift, and Control modifiers, we need special care. */ | |
2bde7652 KH |
104 | if (c & CHAR_SHIFT) |
105 | { | |
106 | /* Shift modifier is valid only with [A-Za-z]. */ | |
107 | if ((c & 0377) >= 'A' && (c & 0377) <= 'Z') | |
108 | c &= ~CHAR_SHIFT; | |
109 | else if ((c & 0377) >= 'a' && (c & 0377) <= 'z') | |
110 | c = (c & ~CHAR_SHIFT) - ('a' - 'A'); | |
03365d0e KH |
111 | /* Shift modifier for control characters and SPC is ignored. */ |
112 | else if ((c & ~CHAR_MODIFIER_MASK) <= 0x20) | |
d0363d44 KH |
113 | c &= ~CHAR_SHIFT; |
114 | } | |
2bde7652 KH |
115 | if (c & CHAR_CTL) |
116 | { | |
117 | /* Simulate the code in lread.c. */ | |
118 | /* Allow `\C- ' and `\C-?'. */ | |
03365d0e KH |
119 | if ((c & 0377) == ' ') |
120 | c &= ~0177 & ~ CHAR_CTL; | |
121 | else if ((c & 0377) == '?') | |
122 | c = 0177 | (c & ~0177 & ~CHAR_CTL); | |
2bde7652 KH |
123 | /* ASCII control chars are made from letters (both cases), |
124 | as well as the non-letters within 0100...0137. */ | |
125 | else if ((c & 0137) >= 0101 && (c & 0137) <= 0132) | |
126 | c &= (037 | (~0177 & ~CHAR_CTL)); | |
127 | else if ((c & 0177) >= 0100 && (c & 0177) <= 0137) | |
128 | c &= (037 | (~0177 & ~CHAR_CTL)); | |
129 | } | |
03365d0e KH |
130 | if (c & CHAR_META) |
131 | { | |
132 | /* Move the meta bit to the right place for a string. */ | |
133 | c = (c & ~CHAR_META) | 0x80; | |
134 | } | |
2bde7652 KH |
135 | |
136 | return c; | |
137 | } | |
138 | ||
139 | ||
33f91981 KH |
140 | /* Store multibyte form of character C at P. If C has modifier bits, |
141 | handle them appropriately. */ | |
142 | ||
0168c3d8 | 143 | int |
e3d8eb8c | 144 | char_string (c, p) |
5aa91c9b | 145 | unsigned c; |
1889b238 | 146 | unsigned char *p; |
0168c3d8 KH |
147 | { |
148 | int bytes; | |
149 | ||
e3d8eb8c KH |
150 | if (c & CHAR_MODIFIER_MASK) |
151 | { | |
2bde7652 | 152 | c = (unsigned) char_resolve_modifier_mask ((int) c); |
e3d8eb8c KH |
153 | /* If C still has any modifier bits, just ignore it. */ |
154 | c &= ~CHAR_MODIFIER_MASK; | |
155 | } | |
156 | ||
0168c3d8 KH |
157 | MAYBE_UNIFY_CHAR (c); |
158 | ||
e3d8eb8c | 159 | if (c <= MAX_3_BYTE_CHAR) |
0168c3d8 KH |
160 | { |
161 | bytes = CHAR_STRING (c, p); | |
162 | } | |
163 | else if (c <= MAX_4_BYTE_CHAR) | |
164 | { | |
165 | p[0] = (0xF0 | (c >> 18)); | |
166 | p[1] = (0x80 | ((c >> 12) & 0x3F)); | |
167 | p[2] = (0x80 | ((c >> 6) & 0x3F)); | |
168 | p[3] = (0x80 | (c & 0x3F)); | |
169 | bytes = 4; | |
170 | } | |
e3d8eb8c | 171 | else if (c <= MAX_5_BYTE_CHAR) |
0168c3d8 KH |
172 | { |
173 | p[0] = 0xF8; | |
174 | p[1] = (0x80 | ((c >> 18) & 0x0F)); | |
175 | p[2] = (0x80 | ((c >> 12) & 0x3F)); | |
176 | p[3] = (0x80 | ((c >> 6) & 0x3F)); | |
177 | p[4] = (0x80 | (c & 0x3F)); | |
178 | bytes = 5; | |
179 | } | |
5aa91c9b | 180 | else if (c <= MAX_CHAR) |
e3d8eb8c KH |
181 | { |
182 | c = CHAR_TO_BYTE8 (c); | |
183 | bytes = BYTE8_STRING (c, p); | |
184 | } | |
5aa91c9b KH |
185 | else |
186 | error ("Invalid character: %d", c); | |
1889b238 | 187 | |
0168c3d8 KH |
188 | return bytes; |
189 | } | |
190 | ||
191 | ||
33f91981 KH |
192 | /* Return a character whose multibyte form is at P. Set LEN is not |
193 | NULL, it must be a pointer to integer. In that case, set *LEN to | |
194 | the byte length of the multibyte form. If ADVANCED is not NULL, is | |
195 | must be a pointer to unsigned char. In that case, set *ADVANCED to | |
196 | the ending address (i.e. the starting address of the next | |
197 | character) of the multibyte form. */ | |
198 | ||
0168c3d8 | 199 | int |
e3d8eb8c | 200 | string_char (p, advanced, len) |
15843e6f KH |
201 | const unsigned char *p; |
202 | const unsigned char **advanced; | |
0168c3d8 KH |
203 | int *len; |
204 | { | |
1889b238 | 205 | int c; |
15843e6f | 206 | const unsigned char *saved_p = p; |
0168c3d8 KH |
207 | |
208 | if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10)) | |
209 | { | |
210 | c = STRING_CHAR_ADVANCE (p); | |
211 | } | |
212 | else if (! (*p & 0x08)) | |
213 | { | |
214 | c = ((((p)[0] & 0xF) << 18) | |
215 | | (((p)[1] & 0x3F) << 12) | |
216 | | (((p)[2] & 0x3F) << 6) | |
217 | | ((p)[3] & 0x3F)); | |
218 | p += 4; | |
219 | } | |
220 | else | |
221 | { | |
222 | c = ((((p)[1] & 0x3F) << 18) | |
223 | | (((p)[2] & 0x3F) << 12) | |
224 | | (((p)[3] & 0x3F) << 6) | |
225 | | ((p)[4] & 0x3F)); | |
226 | p += 5; | |
227 | } | |
228 | ||
229 | MAYBE_UNIFY_CHAR (c); | |
230 | ||
231 | if (len) | |
232 | *len = p - saved_p; | |
233 | if (advanced) | |
234 | *advanced = p; | |
235 | return c; | |
236 | } | |
237 | ||
238 | ||
239 | /* Translate character C by translation table TABLE. If C is | |
240 | negative, translate a character specified by CHARSET and CODE. If | |
241 | no translation is found in TABLE, return the untranslated | |
10453be9 KH |
242 | character. If TABLE is a list, elements are char tables. In this |
243 | case, translace C by all tables. */ | |
0168c3d8 KH |
244 | |
245 | int | |
246 | translate_char (table, c) | |
247 | Lisp_Object table; | |
248 | int c; | |
249 | { | |
10453be9 KH |
250 | if (CHAR_TABLE_P (table)) |
251 | { | |
252 | Lisp_Object ch; | |
253 | ||
254 | ch = CHAR_TABLE_REF (table, c); | |
255 | if (CHARACTERP (ch)) | |
256 | c = XINT (ch); | |
257 | } | |
258 | else | |
259 | { | |
260 | for (; CONSP (table); table = XCDR (table)) | |
261 | c = translate_char (XCAR (table), c); | |
262 | } | |
263 | return c; | |
0168c3d8 KH |
264 | } |
265 | ||
2e5db15c KH |
266 | /* Convert ASCII or 8-bit character C to unibyte. If C is none of |
267 | them, return (C & 0xFF). | |
0168c3d8 KH |
268 | |
269 | The argument REV_TBL is now ignored. It will be removed in the | |
270 | future. */ | |
271 | ||
272 | int | |
273 | multibyte_char_to_unibyte (c, rev_tbl) | |
274 | int c; | |
275 | Lisp_Object rev_tbl; | |
276 | { | |
2e5db15c KH |
277 | if (c < 0x80) |
278 | return c; | |
b672c5ae KH |
279 | if (CHAR_BYTE8_P (c)) |
280 | return CHAR_TO_BYTE8 (c); | |
2e5db15c | 281 | return (c & 0xFF); |
0168c3d8 KH |
282 | } |
283 | ||
935d5b02 KH |
284 | /* Like multibyte_char_to_unibyte, but return -1 if C is not supported |
285 | by charset_unibyte. */ | |
286 | ||
287 | int | |
288 | multibyte_char_to_unibyte_safe (c) | |
289 | int c; | |
290 | { | |
2e5db15c KH |
291 | if (c < 0x80) |
292 | return c; | |
935d5b02 KH |
293 | if (CHAR_BYTE8_P (c)) |
294 | return CHAR_TO_BYTE8 (c); | |
2e5db15c | 295 | return -1; |
935d5b02 | 296 | } |
0168c3d8 KH |
297 | |
298 | DEFUN ("characterp", Fcharacterp, Scharacterp, 1, 2, 0, | |
299 | doc: /* Return non-nil if OBJECT is a character. */) | |
300 | (object, ignore) | |
301 | Lisp_Object object, ignore; | |
302 | { | |
303 | return (CHARACTERP (object) ? Qt : Qnil); | |
304 | } | |
305 | ||
306 | DEFUN ("max-char", Fmax_char, Smax_char, 0, 0, 0, | |
307 | doc: /* Return the character of the maximum code. */) | |
308 | () | |
309 | { | |
310 | return make_number (MAX_CHAR); | |
311 | } | |
312 | ||
313 | DEFUN ("unibyte-char-to-multibyte", Funibyte_char_to_multibyte, | |
314 | Sunibyte_char_to_multibyte, 1, 1, 0, | |
5556875b | 315 | doc: /* Convert the byte CH to multibyte character. */) |
0168c3d8 KH |
316 | (ch) |
317 | Lisp_Object ch; | |
318 | { | |
319 | int c; | |
0168c3d8 KH |
320 | |
321 | CHECK_CHARACTER (ch); | |
322 | c = XFASTINT (ch); | |
2e5db15c KH |
323 | if (c >= 0x100) |
324 | error ("Not a unibyte character: %d", c); | |
4c0354d7 | 325 | MAKE_CHAR_MULTIBYTE (c); |
0168c3d8 KH |
326 | return make_number (c); |
327 | } | |
328 | ||
329 | DEFUN ("multibyte-char-to-unibyte", Fmultibyte_char_to_unibyte, | |
330 | Smultibyte_char_to_unibyte, 1, 1, 0, | |
5556875b SM |
331 | doc: /* Convert the multibyte character CH to a byte. |
332 | If the multibyte character does not represent a byte, return -1. */) | |
0168c3d8 KH |
333 | (ch) |
334 | Lisp_Object ch; | |
335 | { | |
5556875b | 336 | int cm; |
0168c3d8 KH |
337 | |
338 | CHECK_CHARACTER (ch); | |
5556875b SM |
339 | cm = XFASTINT (ch); |
340 | if (cm < 256) | |
341 | /* Can't distinguish a byte read from a unibyte buffer from | |
342 | a latin1 char, so let's let it slide. */ | |
343 | return ch; | |
344 | else | |
345 | { | |
2afc21f5 | 346 | int cu = CHAR_TO_BYTE_SAFE (cm); |
5556875b SM |
347 | return make_number (cu); |
348 | } | |
0168c3d8 KH |
349 | } |
350 | ||
351 | DEFUN ("char-bytes", Fchar_bytes, Schar_bytes, 1, 1, 0, | |
352 | doc: /* Return 1 regardless of the argument CHAR. | |
add553ac JB |
353 | This is now an obsolete function. We keep it just for backward compatibility. |
354 | usage: (char-bytes CHAR) */) | |
0168c3d8 KH |
355 | (ch) |
356 | Lisp_Object ch; | |
357 | { | |
358 | CHECK_CHARACTER (ch); | |
359 | return make_number (1); | |
360 | } | |
361 | ||
362 | DEFUN ("char-width", Fchar_width, Schar_width, 1, 1, 0, | |
363 | doc: /* Return width of CHAR when displayed in the current buffer. | |
364 | The width is measured by how many columns it occupies on the screen. | |
add553ac JB |
365 | Tab is taken to occupy `tab-width' columns. |
366 | usage: (char-width CHAR) */) | |
0168c3d8 KH |
367 | (ch) |
368 | Lisp_Object ch; | |
369 | { | |
370 | Lisp_Object disp; | |
371 | int c, width; | |
372 | struct Lisp_Char_Table *dp = buffer_display_table (); | |
373 | ||
374 | CHECK_CHARACTER (ch); | |
375 | c = XINT (ch); | |
376 | ||
377 | /* Get the way the display table would display it. */ | |
378 | disp = dp ? DISP_CHAR_VECTOR (dp, c) : Qnil; | |
379 | ||
380 | if (VECTORP (disp)) | |
381 | width = ASIZE (disp); | |
382 | else | |
383 | width = CHAR_WIDTH (c); | |
384 | ||
385 | return make_number (width); | |
386 | } | |
387 | ||
0168c3d8 KH |
388 | /* Return width of string STR of length LEN when displayed in the |
389 | current buffer. The width is measured by how many columns it | |
390 | occupies on the screen. If PRECISION > 0, return the width of | |
391 | longest substring that doesn't exceed PRECISION, and set number of | |
392 | characters and bytes of the substring in *NCHARS and *NBYTES | |
393 | respectively. */ | |
394 | ||
1889b238 | 395 | int |
63c125ab | 396 | c_string_width (const unsigned char *str, int len, int precision, int *nchars, int *nbytes) |
0168c3d8 KH |
397 | { |
398 | int i = 0, i_byte = 0; | |
399 | int width = 0; | |
400 | struct Lisp_Char_Table *dp = buffer_display_table (); | |
401 | ||
402 | while (i_byte < len) | |
403 | { | |
404 | int bytes, thiswidth; | |
405 | Lisp_Object val; | |
406 | int c = STRING_CHAR_AND_LENGTH (str + i_byte, len - i_byte, bytes); | |
407 | ||
408 | if (dp) | |
409 | { | |
410 | val = DISP_CHAR_VECTOR (dp, c); | |
411 | if (VECTORP (val)) | |
412 | thiswidth = XVECTOR (val)->size; | |
413 | else | |
414 | thiswidth = CHAR_WIDTH (c); | |
415 | } | |
416 | else | |
417 | { | |
418 | thiswidth = CHAR_WIDTH (c); | |
419 | } | |
420 | ||
421 | if (precision > 0 | |
422 | && (width + thiswidth > precision)) | |
423 | { | |
424 | *nchars = i; | |
425 | *nbytes = i_byte; | |
426 | return width; | |
427 | } | |
428 | i++; | |
429 | i_byte += bytes; | |
430 | width += thiswidth; | |
431 | } | |
432 | ||
433 | if (precision > 0) | |
434 | { | |
435 | *nchars = i; | |
436 | *nbytes = i_byte; | |
437 | } | |
438 | ||
439 | return width; | |
440 | } | |
441 | ||
1889b238 KH |
442 | /* Return width of string STR of length LEN when displayed in the |
443 | current buffer. The width is measured by how many columns it | |
444 | occupies on the screen. */ | |
445 | ||
446 | int | |
447 | strwidth (str, len) | |
448 | unsigned char *str; | |
449 | int len; | |
450 | { | |
451 | return c_string_width (str, len, -1, NULL, NULL); | |
452 | } | |
453 | ||
0168c3d8 KH |
454 | /* Return width of Lisp string STRING when displayed in the current |
455 | buffer. The width is measured by how many columns it occupies on | |
456 | the screen while paying attention to compositions. If PRECISION > | |
457 | 0, return the width of longest substring that doesn't exceed | |
458 | PRECISION, and set number of characters and bytes of the substring | |
459 | in *NCHARS and *NBYTES respectively. */ | |
460 | ||
461 | int | |
462 | lisp_string_width (string, precision, nchars, nbytes) | |
463 | Lisp_Object string; | |
464 | int precision, *nchars, *nbytes; | |
465 | { | |
8f924df7 | 466 | int len = SCHARS (string); |
0aee65b9 KH |
467 | /* This set multibyte to 0 even if STRING is multibyte when it |
468 | contains only ascii and eight-bit-graphic, but that's | |
469 | intentional. */ | |
470 | int multibyte = len < SBYTES (string); | |
8f924df7 | 471 | unsigned char *str = SDATA (string); |
0168c3d8 KH |
472 | int i = 0, i_byte = 0; |
473 | int width = 0; | |
474 | struct Lisp_Char_Table *dp = buffer_display_table (); | |
475 | ||
476 | while (i < len) | |
477 | { | |
478 | int chars, bytes, thiswidth; | |
479 | Lisp_Object val; | |
480 | int cmp_id; | |
f4bc0685 | 481 | EMACS_INT ignore, end; |
0168c3d8 KH |
482 | |
483 | if (find_composition (i, -1, &ignore, &end, &val, string) | |
484 | && ((cmp_id = get_composition_id (i, i_byte, end - i, val, string)) | |
485 | >= 0)) | |
486 | { | |
487 | thiswidth = composition_table[cmp_id]->width; | |
488 | chars = end - i; | |
489 | bytes = string_char_to_byte (string, end) - i_byte; | |
490 | } | |
0168c3d8 KH |
491 | else |
492 | { | |
0aee65b9 | 493 | int c; |
0168c3d8 | 494 | |
0aee65b9 KH |
495 | if (multibyte) |
496 | c = STRING_CHAR_AND_LENGTH (str + i_byte, len - i_byte, bytes); | |
497 | else | |
498 | c = str[i_byte], bytes = 1; | |
0168c3d8 | 499 | chars = 1; |
0aee65b9 KH |
500 | if (dp) |
501 | { | |
502 | val = DISP_CHAR_VECTOR (dp, c); | |
503 | if (VECTORP (val)) | |
504 | thiswidth = XVECTOR (val)->size; | |
505 | else | |
506 | thiswidth = CHAR_WIDTH (c); | |
507 | } | |
508 | else | |
509 | { | |
510 | thiswidth = CHAR_WIDTH (c); | |
511 | } | |
0168c3d8 KH |
512 | } |
513 | ||
514 | if (precision > 0 | |
515 | && (width + thiswidth > precision)) | |
516 | { | |
517 | *nchars = i; | |
518 | *nbytes = i_byte; | |
519 | return width; | |
520 | } | |
521 | i += chars; | |
522 | i_byte += bytes; | |
523 | width += thiswidth; | |
524 | } | |
525 | ||
526 | if (precision > 0) | |
527 | { | |
528 | *nchars = i; | |
529 | *nbytes = i_byte; | |
530 | } | |
531 | ||
532 | return width; | |
533 | } | |
534 | ||
535 | DEFUN ("string-width", Fstring_width, Sstring_width, 1, 1, 0, | |
536 | doc: /* Return width of STRING when displayed in the current buffer. | |
537 | Width is measured by how many columns it occupies on the screen. | |
538 | When calculating width of a multibyte character in STRING, | |
539 | only the base leading-code is considered; the validity of | |
540 | the following bytes is not checked. Tabs in STRING are always | |
add553ac JB |
541 | taken to occupy `tab-width' columns. |
542 | usage: (string-width STRING) */) | |
0168c3d8 KH |
543 | (str) |
544 | Lisp_Object str; | |
545 | { | |
546 | Lisp_Object val; | |
547 | ||
548 | CHECK_STRING (str); | |
549 | XSETFASTINT (val, lisp_string_width (str, -1, NULL, NULL)); | |
550 | return val; | |
551 | } | |
552 | ||
553 | DEFUN ("char-direction", Fchar_direction, Schar_direction, 1, 1, 0, | |
554 | doc: /* Return the direction of CHAR. | |
add553ac JB |
555 | The returned value is 0 for left-to-right and 1 for right-to-left. |
556 | usage: (char-direction CHAR) */) | |
0168c3d8 KH |
557 | (ch) |
558 | Lisp_Object ch; | |
559 | { | |
560 | int c; | |
561 | ||
562 | CHECK_CHARACTER (ch); | |
563 | c = XINT (ch); | |
564 | return CHAR_TABLE_REF (Vchar_direction_table, c); | |
565 | } | |
566 | ||
0168c3d8 KH |
567 | /* Return the number of characters in the NBYTES bytes at PTR. |
568 | This works by looking at the contents and checking for multibyte | |
569 | sequences while assuming that there's no invalid sequence. | |
570 | However, if the current buffer has enable-multibyte-characters = | |
571 | nil, we treat each byte as a character. */ | |
572 | ||
13818c30 | 573 | EMACS_INT |
0168c3d8 | 574 | chars_in_text (ptr, nbytes) |
8f924df7 | 575 | const unsigned char *ptr; |
13818c30 | 576 | EMACS_INT nbytes; |
0168c3d8 KH |
577 | { |
578 | /* current_buffer is null at early stages of Emacs initialization. */ | |
579 | if (current_buffer == 0 | |
580 | || NILP (current_buffer->enable_multibyte_characters)) | |
581 | return nbytes; | |
582 | ||
583 | return multibyte_chars_in_text (ptr, nbytes); | |
584 | } | |
585 | ||
586 | /* Return the number of characters in the NBYTES bytes at PTR. | |
587 | This works by looking at the contents and checking for multibyte | |
588 | sequences while assuming that there's no invalid sequence. It | |
589 | ignores enable-multibyte-characters. */ | |
590 | ||
13818c30 | 591 | EMACS_INT |
0168c3d8 | 592 | multibyte_chars_in_text (ptr, nbytes) |
8f924df7 | 593 | const unsigned char *ptr; |
13818c30 | 594 | EMACS_INT nbytes; |
0168c3d8 | 595 | { |
8f924df7 | 596 | const unsigned char *endp = ptr + nbytes; |
0168c3d8 KH |
597 | int chars = 0; |
598 | ||
599 | while (ptr < endp) | |
600 | { | |
601 | int len = MULTIBYTE_LENGTH (ptr, endp); | |
602 | ||
603 | if (len == 0) | |
604 | abort (); | |
605 | ptr += len; | |
606 | chars++; | |
607 | } | |
608 | ||
609 | return chars; | |
610 | } | |
611 | ||
612 | /* Parse unibyte text at STR of LEN bytes as a multibyte text, count | |
613 | characters and bytes in it, and store them in *NCHARS and *NBYTES | |
614 | respectively. On counting bytes, pay attention to that 8-bit | |
615 | characters not constructing a valid multibyte sequence are | |
616 | represented by 2-byte in a multibyte text. */ | |
617 | ||
618 | void | |
619 | parse_str_as_multibyte (str, len, nchars, nbytes) | |
8f924df7 | 620 | const unsigned char *str; |
0168c3d8 KH |
621 | int len, *nchars, *nbytes; |
622 | { | |
8f924df7 | 623 | const unsigned char *endp = str + len; |
0168c3d8 KH |
624 | int n, chars = 0, bytes = 0; |
625 | ||
626 | if (len >= MAX_MULTIBYTE_LENGTH) | |
627 | { | |
8f924df7 | 628 | const unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH; |
0168c3d8 KH |
629 | while (str < adjusted_endp) |
630 | { | |
631 | if ((n = MULTIBYTE_LENGTH_NO_CHECK (str)) > 0) | |
632 | str += n, bytes += n; | |
633 | else | |
634 | str++, bytes += 2; | |
635 | chars++; | |
636 | } | |
637 | } | |
638 | while (str < endp) | |
639 | { | |
640 | if ((n = MULTIBYTE_LENGTH (str, endp)) > 0) | |
641 | str += n, bytes += n; | |
642 | else | |
643 | str++, bytes += 2; | |
644 | chars++; | |
645 | } | |
646 | ||
647 | *nchars = chars; | |
648 | *nbytes = bytes; | |
649 | return; | |
650 | } | |
651 | ||
652 | /* Arrange unibyte text at STR of NBYTES bytes as a multibyte text. | |
653 | It actually converts only such 8-bit characters that don't contruct | |
654 | a multibyte sequence to multibyte forms of Latin-1 characters. If | |
655 | NCHARS is nonzero, set *NCHARS to the number of characters in the | |
656 | text. It is assured that we can use LEN bytes at STR as a work | |
657 | area and that is enough. Return the number of bytes of the | |
658 | resulting text. */ | |
659 | ||
660 | int | |
661 | str_as_multibyte (str, len, nbytes, nchars) | |
662 | unsigned char *str; | |
663 | int len, nbytes, *nchars; | |
664 | { | |
665 | unsigned char *p = str, *endp = str + nbytes; | |
666 | unsigned char *to; | |
667 | int chars = 0; | |
668 | int n; | |
669 | ||
670 | if (nbytes >= MAX_MULTIBYTE_LENGTH) | |
671 | { | |
672 | unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH; | |
673 | while (p < adjusted_endp | |
674 | && (n = MULTIBYTE_LENGTH_NO_CHECK (p)) > 0) | |
675 | p += n, chars++; | |
676 | } | |
677 | while ((n = MULTIBYTE_LENGTH (p, endp)) > 0) | |
678 | p += n, chars++; | |
679 | if (nchars) | |
680 | *nchars = chars; | |
681 | if (p == endp) | |
682 | return nbytes; | |
683 | ||
684 | to = p; | |
685 | nbytes = endp - p; | |
686 | endp = str + len; | |
687 | safe_bcopy ((char *) p, (char *) (endp - nbytes), nbytes); | |
688 | p = endp - nbytes; | |
689 | ||
690 | if (nbytes >= MAX_MULTIBYTE_LENGTH) | |
691 | { | |
692 | unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH; | |
693 | while (p < adjusted_endp) | |
694 | { | |
695 | if ((n = MULTIBYTE_LENGTH_NO_CHECK (p)) > 0) | |
696 | { | |
697 | while (n--) | |
698 | *to++ = *p++; | |
699 | } | |
700 | else | |
701 | { | |
702 | int c = *p++; | |
703 | c = BYTE8_TO_CHAR (c); | |
704 | to += CHAR_STRING (c, to); | |
705 | } | |
706 | } | |
707 | chars++; | |
708 | } | |
709 | while (p < endp) | |
710 | { | |
711 | if ((n = MULTIBYTE_LENGTH (p, endp)) > 0) | |
712 | { | |
713 | while (n--) | |
714 | *to++ = *p++; | |
8f924df7 | 715 | } |
0168c3d8 KH |
716 | else |
717 | { | |
718 | int c = *p++; | |
719 | c = BYTE8_TO_CHAR (c); | |
720 | to += CHAR_STRING (c, to); | |
721 | } | |
722 | chars++; | |
723 | } | |
724 | if (nchars) | |
725 | *nchars = chars; | |
726 | return (to - str); | |
727 | } | |
728 | ||
729 | /* Parse unibyte string at STR of LEN bytes, and return the number of | |
730 | bytes it may ocupy when converted to multibyte string by | |
731 | `str_to_multibyte'. */ | |
732 | ||
733 | int | |
734 | parse_str_to_multibyte (str, len) | |
735 | unsigned char *str; | |
736 | int len; | |
737 | { | |
738 | unsigned char *endp = str + len; | |
739 | int bytes; | |
740 | ||
741 | for (bytes = 0; str < endp; str++) | |
742 | bytes += (*str < 0x80) ? 1 : 2; | |
743 | return bytes; | |
744 | } | |
745 | ||
746 | ||
747 | /* Convert unibyte text at STR of NBYTES bytes to a multibyte text | |
748 | that contains the same single-byte characters. It actually | |
749 | converts all 8-bit characters to multibyte forms. It is assured | |
750 | that we can use LEN bytes at STR as a work area and that is | |
751 | enough. */ | |
752 | ||
753 | int | |
754 | str_to_multibyte (str, len, bytes) | |
755 | unsigned char *str; | |
756 | int len, bytes; | |
757 | { | |
758 | unsigned char *p = str, *endp = str + bytes; | |
759 | unsigned char *to; | |
760 | ||
761 | while (p < endp && *p < 0x80) p++; | |
762 | if (p == endp) | |
763 | return bytes; | |
764 | to = p; | |
765 | bytes = endp - p; | |
766 | endp = str + len; | |
767 | safe_bcopy ((char *) p, (char *) (endp - bytes), bytes); | |
768 | p = endp - bytes; | |
8f924df7 | 769 | while (p < endp) |
0168c3d8 KH |
770 | { |
771 | int c = *p++; | |
772 | ||
773 | if (c >= 0x80) | |
774 | c = BYTE8_TO_CHAR (c); | |
775 | to += CHAR_STRING (c, to); | |
776 | } | |
777 | return (to - str); | |
778 | } | |
779 | ||
780 | /* Arrange multibyte text at STR of LEN bytes as a unibyte text. It | |
781 | actually converts characters in the range 0x80..0xFF to | |
782 | unibyte. */ | |
783 | ||
784 | int | |
785 | str_as_unibyte (str, bytes) | |
786 | unsigned char *str; | |
787 | int bytes; | |
788 | { | |
15843e6f KH |
789 | const unsigned char *p = str, *endp = str + bytes; |
790 | unsigned char *to; | |
0168c3d8 KH |
791 | int c, len; |
792 | ||
793 | while (p < endp) | |
794 | { | |
795 | c = *p; | |
796 | len = BYTES_BY_CHAR_HEAD (c); | |
797 | if (CHAR_BYTE8_HEAD_P (c)) | |
798 | break; | |
799 | p += len; | |
800 | } | |
15843e6f | 801 | to = str + (p - str); |
8f924df7 | 802 | while (p < endp) |
0168c3d8 KH |
803 | { |
804 | c = *p; | |
805 | len = BYTES_BY_CHAR_HEAD (c); | |
806 | if (CHAR_BYTE8_HEAD_P (c)) | |
807 | { | |
808 | c = STRING_CHAR_ADVANCE (p); | |
809 | *to++ = CHAR_TO_BYTE8 (c); | |
810 | } | |
811 | else | |
812 | { | |
813 | while (len--) *to++ = *p++; | |
814 | } | |
815 | } | |
816 | return (to - str); | |
817 | } | |
818 | ||
4aa40bb8 KH |
819 | /* Convert eight-bit chars in SRC (in multibyte form) to the |
820 | corresponding byte and store in DST. CHARS is the number of | |
821 | characters in SRC. The value is the number of bytes stored in DST. | |
822 | Usually, the value is the same as CHARS, but is less than it if SRC | |
823 | contains a non-ASCII, non-eight-bit characater. If ACCEPT_LATIN_1 | |
824 | is nonzero, a Latin-1 character is accepted and converted to a byte | |
f27f70ec KH |
825 | of that character code. |
826 | Note: Currently the arg ACCEPT_LATIN_1 is not used. */ | |
4aa40bb8 KH |
827 | |
828 | EMACS_INT | |
829 | str_to_unibyte (src, dst, chars, accept_latin_1) | |
830 | const unsigned char *src; | |
831 | unsigned char *dst; | |
832 | EMACS_INT chars; | |
833 | int accept_latin_1; | |
834 | { | |
835 | EMACS_INT i; | |
836 | ||
837 | for (i = 0; i < chars; i++) | |
838 | { | |
839 | int c = STRING_CHAR_ADVANCE (src); | |
840 | ||
841 | if (CHAR_BYTE8_P (c)) | |
842 | c = CHAR_TO_BYTE8 (c); | |
843 | else if (! ASCII_CHAR_P (c) | |
844 | && (! accept_latin_1 || c >= 0x100)) | |
845 | return i; | |
846 | *dst++ = c; | |
847 | } | |
848 | return i; | |
849 | } | |
850 | ||
851 | ||
0168c3d8 KH |
852 | int |
853 | string_count_byte8 (string) | |
854 | Lisp_Object string; | |
855 | { | |
856 | int multibyte = STRING_MULTIBYTE (string); | |
8f924df7 KH |
857 | int nbytes = SBYTES (string); |
858 | unsigned char *p = SDATA (string); | |
0168c3d8 KH |
859 | unsigned char *pend = p + nbytes; |
860 | int count = 0; | |
861 | int c, len; | |
862 | ||
863 | if (multibyte) | |
864 | while (p < pend) | |
865 | { | |
866 | c = *p; | |
867 | len = BYTES_BY_CHAR_HEAD (c); | |
868 | ||
869 | if (CHAR_BYTE8_HEAD_P (c)) | |
870 | count++; | |
871 | p += len; | |
872 | } | |
873 | else | |
874 | while (p < pend) | |
875 | { | |
876 | if (*p++ >= 0x80) | |
877 | count++; | |
878 | } | |
879 | return count; | |
880 | } | |
881 | ||
882 | ||
883 | Lisp_Object | |
884 | string_escape_byte8 (string) | |
885 | Lisp_Object string; | |
886 | { | |
8f924df7 KH |
887 | int nchars = SCHARS (string); |
888 | int nbytes = SBYTES (string); | |
0168c3d8 KH |
889 | int multibyte = STRING_MULTIBYTE (string); |
890 | int byte8_count; | |
15843e6f KH |
891 | const unsigned char *src, *src_end; |
892 | unsigned char *dst; | |
0168c3d8 KH |
893 | Lisp_Object val; |
894 | int c, len; | |
895 | ||
896 | if (multibyte && nchars == nbytes) | |
897 | return string; | |
898 | ||
899 | byte8_count = string_count_byte8 (string); | |
900 | ||
901 | if (byte8_count == 0) | |
902 | return string; | |
903 | ||
904 | if (multibyte) | |
905 | /* Convert 2-byte sequence of byte8 chars to 4-byte octal. */ | |
7b40ebaf | 906 | val = make_uninit_multibyte_string (nchars + byte8_count * 3, |
0168c3d8 KH |
907 | nbytes + byte8_count * 2); |
908 | else | |
909 | /* Convert 1-byte sequence of byte8 chars to 4-byte octal. */ | |
910 | val = make_uninit_string (nbytes + byte8_count * 3); | |
911 | ||
8f924df7 | 912 | src = SDATA (string); |
0168c3d8 | 913 | src_end = src + nbytes; |
8f924df7 | 914 | dst = SDATA (val); |
0168c3d8 KH |
915 | if (multibyte) |
916 | while (src < src_end) | |
917 | { | |
918 | c = *src; | |
919 | len = BYTES_BY_CHAR_HEAD (c); | |
920 | ||
921 | if (CHAR_BYTE8_HEAD_P (c)) | |
922 | { | |
923 | c = STRING_CHAR_ADVANCE (src); | |
924 | c = CHAR_TO_BYTE8 (c); | |
1889b238 | 925 | sprintf ((char *) dst, "\\%03o", c); |
0168c3d8 KH |
926 | dst += 4; |
927 | } | |
928 | else | |
929 | while (len--) *dst++ = *src++; | |
930 | } | |
931 | else | |
932 | while (src < src_end) | |
933 | { | |
934 | c = *src++; | |
935 | if (c >= 0x80) | |
936 | { | |
1889b238 | 937 | sprintf ((char *) dst, "\\%03o", c); |
0168c3d8 KH |
938 | dst += 4; |
939 | } | |
940 | else | |
941 | *dst++ = c; | |
942 | } | |
943 | return val; | |
944 | } | |
945 | ||
946 | \f | |
8f924df7 | 947 | DEFUN ("string", Fstring, Sstring, 0, MANY, 0, |
0168c3d8 | 948 | doc: /* |
d2e83296 DL |
949 | Concatenate all the argument characters and make the result a string. |
950 | usage: (string &rest CHARACTERS) */) | |
0168c3d8 KH |
951 | (n, args) |
952 | int n; | |
953 | Lisp_Object *args; | |
954 | { | |
955 | int i; | |
956 | unsigned char *buf = (unsigned char *) alloca (MAX_MULTIBYTE_LENGTH * n); | |
957 | unsigned char *p = buf; | |
958 | int c; | |
959 | ||
960 | for (i = 0; i < n; i++) | |
961 | { | |
962 | CHECK_CHARACTER (args[i]); | |
963 | c = XINT (args[i]); | |
964 | p += CHAR_STRING (c, p); | |
965 | } | |
966 | ||
967 | return make_string_from_bytes ((char *) buf, n, p - buf); | |
968 | } | |
969 | ||
70b4969d | 970 | DEFUN ("unibyte-string", Funibyte_string, Sunibyte_string, 0, MANY, 0, |
87d6f965 KH |
971 | doc: /* Concatenate all the argument bytes and make the result a unibyte string. |
972 | usage: (unibyte-string &rest BYTES) */) | |
70b4969d KH |
973 | (n, args) |
974 | int n; | |
975 | Lisp_Object *args; | |
976 | { | |
977 | int i; | |
978 | unsigned char *buf = (unsigned char *) alloca (n); | |
979 | unsigned char *p = buf; | |
980 | unsigned c; | |
981 | ||
982 | for (i = 0; i < n; i++) | |
983 | { | |
984 | CHECK_NATNUM (args[i]); | |
985 | c = XFASTINT (args[i]); | |
986 | if (c >= 256) | |
987 | args_out_of_range_3 (args[i], make_number (0), make_number (255)); | |
988 | *p++ = c; | |
989 | } | |
990 | ||
991 | return make_string_from_bytes ((char *) buf, n, p - buf); | |
992 | } | |
993 | ||
c73ae4ae | 994 | DEFUN ("char-resolve-modifiers", Fchar_resolve_modifiers, |
d0363d44 KH |
995 | Schar_resolve_modifiers, 1, 1, 0, |
996 | doc: /* Resolve modifiers in the character CHAR. | |
997 | The value is a character with modifiers resolved into the character | |
998 | code. Unresolved modifiers are kept in the value. | |
c73ae4ae | 999 | usage: (char-resolve-modifiers CHAR) */) |
d0363d44 KH |
1000 | (character) |
1001 | Lisp_Object character; | |
1002 | { | |
1003 | int c; | |
1004 | ||
1005 | CHECK_NUMBER (character); | |
1006 | c = XINT (character); | |
1007 | return make_number (char_resolve_modifier_mask (c)); | |
1008 | } | |
1009 | ||
ee107a89 KH |
1010 | DEFUN ("get-byte", Fget_byte, Sget_byte, 0, 2, 0, |
1011 | doc: /* Return a byte value of a character at point. | |
1012 | Optional 1st arg POSITION, if non-nil, is a position of a character to get | |
1013 | a byte value. | |
1014 | Optional 2nd arg STRING, if non-nil, is a string of which first | |
1015 | character is a target to get a byte value. In this case, POSITION, if | |
1016 | non-nil, is an index of a target character in the string. | |
1017 | ||
1018 | If the current buffer (or STRING) is multibyte, and the target | |
1019 | character is not ASCII nor 8-bit character, an error is signalled. */) | |
1020 | (position, string) | |
1021 | Lisp_Object position, string; | |
1022 | { | |
1023 | int c; | |
1024 | EMACS_INT pos; | |
1025 | unsigned char *p; | |
1026 | ||
1027 | if (NILP (string)) | |
1028 | { | |
1029 | if (NILP (position)) | |
1030 | { | |
1031 | p = PT_ADDR; | |
4d8e170e | 1032 | } |
ee107a89 KH |
1033 | else |
1034 | { | |
1035 | CHECK_NUMBER_COERCE_MARKER (position); | |
1036 | if (XINT (position) < BEGV || XINT (position) >= ZV) | |
1037 | args_out_of_range_3 (position, make_number (BEGV), make_number (ZV)); | |
1038 | pos = XFASTINT (position); | |
1039 | p = CHAR_POS_ADDR (pos); | |
1040 | } | |
d5998e03 KH |
1041 | if (NILP (current_buffer->enable_multibyte_characters)) |
1042 | return make_number (*p); | |
ee107a89 KH |
1043 | } |
1044 | else | |
1045 | { | |
1046 | CHECK_STRING (string); | |
1047 | if (NILP (position)) | |
1048 | { | |
1049 | p = SDATA (string); | |
1050 | } | |
1051 | else | |
1052 | { | |
1053 | CHECK_NATNUM (position); | |
1054 | if (XINT (position) >= SCHARS (string)) | |
1055 | args_out_of_range (string, position); | |
1056 | pos = XFASTINT (position); | |
1057 | p = SDATA (string) + string_char_to_byte (string, pos); | |
1058 | } | |
d5998e03 KH |
1059 | if (! STRING_MULTIBYTE (string)) |
1060 | return make_number (*p); | |
ee107a89 KH |
1061 | } |
1062 | c = STRING_CHAR (p, 0); | |
1063 | if (CHAR_BYTE8_P (c)) | |
1064 | c = CHAR_TO_BYTE8 (c); | |
1065 | else if (! ASCII_CHAR_P (c)) | |
1066 | error ("Not an ASCII nor an 8-bit character: %d", c); | |
1067 | return make_number (c); | |
1068 | } | |
1069 | ||
1070 | ||
0168c3d8 KH |
1071 | void |
1072 | init_character_once () | |
1073 | { | |
1074 | } | |
1075 | ||
1076 | #ifdef emacs | |
1077 | ||
1078 | void | |
1079 | syms_of_character () | |
1080 | { | |
1081 | DEFSYM (Qcharacterp, "characterp"); | |
1082 | DEFSYM (Qauto_fill_chars, "auto-fill-chars"); | |
1083 | ||
1084 | staticpro (&Vchar_unify_table); | |
1085 | Vchar_unify_table = Qnil; | |
1086 | ||
1087 | defsubr (&Smax_char); | |
1088 | defsubr (&Scharacterp); | |
1089 | defsubr (&Sunibyte_char_to_multibyte); | |
1090 | defsubr (&Smultibyte_char_to_unibyte); | |
1091 | defsubr (&Schar_bytes); | |
1092 | defsubr (&Schar_width); | |
1093 | defsubr (&Sstring_width); | |
1094 | defsubr (&Schar_direction); | |
0168c3d8 | 1095 | defsubr (&Sstring); |
70b4969d | 1096 | defsubr (&Sunibyte_string); |
d0363d44 | 1097 | defsubr (&Schar_resolve_modifiers); |
ee107a89 | 1098 | defsubr (&Sget_byte); |
0168c3d8 KH |
1099 | |
1100 | DEFVAR_LISP ("translation-table-vector", &Vtranslation_table_vector, | |
1101 | doc: /* | |
68978cf0 DL |
1102 | Vector recording all translation tables ever defined. |
1103 | Each element is a pair (SYMBOL . TABLE) relating the table to the | |
1104 | symbol naming it. The ID of a translation table is an index into this vector. */); | |
0168c3d8 KH |
1105 | Vtranslation_table_vector = Fmake_vector (make_number (16), Qnil); |
1106 | ||
1107 | DEFVAR_LISP ("auto-fill-chars", &Vauto_fill_chars, | |
1108 | doc: /* | |
1109 | A char-table for characters which invoke auto-filling. | |
1110 | Such characters have value t in this table. */); | |
1111 | Vauto_fill_chars = Fmake_char_table (Qauto_fill_chars, Qnil); | |
6cc0e1ca DL |
1112 | CHAR_TABLE_SET (Vauto_fill_chars, ' ', Qt); |
1113 | CHAR_TABLE_SET (Vauto_fill_chars, '\n', Qt); | |
0168c3d8 KH |
1114 | |
1115 | DEFVAR_LISP ("char-width-table", &Vchar_width_table, | |
1116 | doc: /* | |
1117 | A char-table for width (columns) of each character. */); | |
1118 | Vchar_width_table = Fmake_char_table (Qnil, make_number (1)); | |
be8b50bc KH |
1119 | char_table_set_range (Vchar_width_table, 0x80, 0x9F, make_number (4)); |
1120 | char_table_set_range (Vchar_width_table, MAX_5_BYTE_CHAR + 1, MAX_CHAR, | |
1121 | make_number (4)); | |
0168c3d8 KH |
1122 | |
1123 | DEFVAR_LISP ("char-direction-table", &Vchar_direction_table, | |
1124 | doc: /* A char-table for direction of each character. */); | |
1125 | Vchar_direction_table = Fmake_char_table (Qnil, make_number (1)); | |
1126 | ||
1127 | DEFVAR_LISP ("printable-chars", &Vprintable_chars, | |
1128 | doc: /* A char-table for each printable character. */); | |
db6d4189 | 1129 | Vprintable_chars = Fmake_char_table (Qnil, Qnil); |
67dde660 KH |
1130 | Fset_char_table_range (Vprintable_chars, |
1131 | Fcons (make_number (32), make_number (126)), Qt); | |
1132 | Fset_char_table_range (Vprintable_chars, | |
1133 | Fcons (make_number (160), | |
1134 | make_number (MAX_5_BYTE_CHAR)), Qt); | |
15843e6f | 1135 | |
c57f3328 KH |
1136 | DEFVAR_LISP ("char-script-table", &Vchar_script_table, |
1137 | doc: /* Char table of script symbols. | |
1138 | It has one extra slot whose value is a list of script symbols. */); | |
1139 | ||
1140 | /* Intern this now in case it isn't already done. | |
1141 | Setting this variable twice is harmless. | |
1142 | But don't staticpro it here--that is done in alloc.c. */ | |
1143 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
1144 | DEFSYM (Qchar_script_table, "char-script-table"); | |
1145 | Fput (Qchar_script_table, Qchar_table_extra_slots, make_number (1)); | |
1146 | Vchar_script_table = Fmake_char_table (Qchar_script_table, Qnil); | |
c7e14352 KH |
1147 | |
1148 | DEFVAR_LISP ("script-representative-chars", &Vscript_representative_chars, | |
c3bb7671 | 1149 | doc: /* Alist of scripts vs the representative characters. |
f4427a54 | 1150 | Each element is a cons (SCRIPT . CHARS). |
4d8e170e | 1151 | SCRIPT is a symbol representing a script or a subgroup of a script. |
c3bb7671 | 1152 | CHARS is a list or a vector of characters. |
472a4dc9 | 1153 | If it is a list, all characters in the list are necessary for supporting SCRIPT. |
c3bb7671 KH |
1154 | If it is a vector, one of the characters in the vector is necessary. |
1155 | This variable is used to find a font for a specific script. */); | |
c7e14352 | 1156 | Vscript_representative_chars = Qnil; |
a3cbb631 KH |
1157 | |
1158 | DEFVAR_LISP ("unicode-category-table", &Vunicode_category_table, | |
1159 | doc: /* Char table of Unicode's "General Category". | |
472a4dc9 JB |
1160 | All Unicode characters have one of the following values (symbol): |
1161 | Lu, Ll, Lt, Lm, Lo, Mn, Mc, Me, Nd, Nl, No, Pc, Pd, Ps, Pe, Pi, Pf, Po, | |
a3cbb631 KH |
1162 | Sm, Sc, Sk, So, Zs, Zl, Zp, Cc, Cf, Cs, Co, Cn |
1163 | See The Unicode Standard for the meaning of those values. */); | |
1164 | /* The correct char-table is setup in characters.el. */ | |
1165 | Vunicode_category_table = Qnil; | |
0168c3d8 KH |
1166 | } |
1167 | ||
1168 | #endif /* emacs */ | |
fbaf0946 MB |
1169 | |
1170 | /* arch-tag: b6665960-3c3d-4184-85cd-af4318197999 | |
1171 | (do not change this comment) */ |