1 /* Functions to handle multilingual characters.
2 Copyright (C) 1992, 1995 Free Software Foundation, Inc.
3 Copyright (C) 1995 Sun Microsystems, Inc.
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 /* Synched up with: FSF 20.3. Not in FSF. */
24 /* Rewritten by Ben Wing <ben@xemacs.org>. */
37 /* The various pre-defined charsets. */
39 Lisp_Object Vcharset_ascii;
40 Lisp_Object Vcharset_control_1;
41 Lisp_Object Vcharset_latin_iso8859_1;
42 Lisp_Object Vcharset_latin_iso8859_2;
43 Lisp_Object Vcharset_latin_iso8859_3;
44 Lisp_Object Vcharset_latin_iso8859_4;
45 Lisp_Object Vcharset_thai_tis620;
46 Lisp_Object Vcharset_greek_iso8859_7;
47 Lisp_Object Vcharset_arabic_iso8859_6;
48 Lisp_Object Vcharset_hebrew_iso8859_8;
49 Lisp_Object Vcharset_katakana_jisx0201;
50 Lisp_Object Vcharset_latin_jisx0201;
51 Lisp_Object Vcharset_cyrillic_iso8859_5;
52 Lisp_Object Vcharset_latin_iso8859_9;
53 Lisp_Object Vcharset_japanese_jisx0208_1978;
54 Lisp_Object Vcharset_chinese_gb2312;
55 Lisp_Object Vcharset_japanese_jisx0208;
56 Lisp_Object Vcharset_korean_ksc5601;
57 Lisp_Object Vcharset_japanese_jisx0212;
58 Lisp_Object Vcharset_chinese_cns11643_1;
59 Lisp_Object Vcharset_chinese_cns11643_2;
61 Lisp_Object Vcharset_chinese_cns11643_3;
62 Lisp_Object Vcharset_chinese_cns11643_4;
63 Lisp_Object Vcharset_chinese_cns11643_5;
64 Lisp_Object Vcharset_chinese_cns11643_6;
65 Lisp_Object Vcharset_chinese_cns11643_7;
66 Lisp_Object Vcharset_ucs_bmp;
67 Lisp_Object Vcharset_latin_viscii_lower;
68 Lisp_Object Vcharset_latin_viscii_upper;
70 Lisp_Object Vcharset_chinese_big5_1;
71 Lisp_Object Vcharset_chinese_big5_2;
73 #ifdef ENABLE_COMPOSITE_CHARS
74 Lisp_Object Vcharset_composite;
76 /* Hash tables for composite chars. One maps string representing
77 composed chars to their equivalent chars; one goes the
79 Lisp_Object Vcomposite_char_char2string_hash_table;
80 Lisp_Object Vcomposite_char_string2char_hash_table;
82 static int composite_char_row_next;
83 static int composite_char_col_next;
85 #endif /* ENABLE_COMPOSITE_CHARS */
87 /* Table of charsets indexed by leading byte. */
88 Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
90 /* Table of charsets indexed by type/final-byte/direction. */
92 Lisp_Object charset_by_attributes[4][128];
94 Lisp_Object charset_by_attributes[4][128][2];
98 /* Table of number of bytes in the string representation of a character
99 indexed by the first byte of that representation.
101 rep_bytes_by_first_byte(c) is more efficient than the equivalent
102 canonical computation:
104 (BYTE_ASCII_P (c) ? 1 : XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (c))) */
106 Bytecount rep_bytes_by_first_byte[0xA0] =
107 { /* 0x00 - 0x7f are for straight ASCII */
108 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
109 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
110 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
111 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
112 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
113 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
114 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
115 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
116 /* 0x80 - 0x8f are for Dimension-1 official charsets */
118 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3,
120 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
122 /* 0x90 - 0x9d are for Dimension-2 official charsets */
123 /* 0x9e is for Dimension-1 private charsets */
124 /* 0x9f is for Dimension-2 private charsets */
125 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4
130 Emchar_to_byte_table*
131 make_byte_from_character_table ()
133 Emchar_to_byte_table* table
134 = (Emchar_to_byte_table*) xmalloc (sizeof (Emchar_to_byte_table));
141 put_byte_from_character_table (Emchar ch, unsigned char val,
142 Emchar_to_byte_table* table)
144 if (table->base == NULL)
146 table->base = xmalloc (128);
147 table->offset = ch - (ch % 128);
149 table->base[ch - table->offset] = val;
153 int i = ch - table->offset;
157 size_t new_size = table->size - i;
160 new_size += 128 - (new_size % 128);
161 table->base = xrealloc (table->base, new_size);
162 memmove (table->base + (new_size - table->size), table->base,
164 for (j = 0; j < (new_size - table->size); j++)
166 table->offset -= (new_size - table->size);
167 table->base[ch - table->offset] = val;
168 table->size = new_size;
170 else if (i >= table->size)
172 size_t new_size = i + 1;
175 new_size += 128 - (new_size % 128);
176 table->base = xrealloc (table->base, new_size);
177 for (j = table->size; j < new_size; j++)
179 table->base[i] = val;
180 table->size = new_size;
184 table->base[i] = val;
190 get_byte_from_character_table (Emchar ch, Emchar_to_byte_table* table)
192 size_t i = ch - table->offset;
194 return table->base[i];
199 #define CHAR96(ft,b) (MIN_CHAR_96 + (ft - '0') * 96 + (b & 0x7f) - 32)
201 Emchar latin_jisx0201_to_ucs[94] =
203 0x0021 /* 0x21 EXCLAMATION MARK */,
204 0x0022 /* 0x22 QUOTATION MARK */,
205 0x0023 /* 0x23 NUMBER SIGN */,
206 0x0024 /* 0x24 DOLLAR SIGN */,
207 0x0025 /* 0x25 PERCENT SIGN */,
208 0x0026 /* 0x26 AMPERSAND */,
209 0x0027 /* 0x27 APOSTROPHE */,
210 0x0028 /* 0x28 LEFT PARENTHESIS */,
211 0x0029 /* 0x29 RIGHT PARENTHESIS */,
212 0x002A /* 0x2A ASTERISK */,
213 0x002B /* 0x2B PLUS SIGN */,
214 0x002C /* 0x2C COMMA */,
215 0x002D /* 0x2D HYPHEN-MINUS */,
216 0x002E /* 0x2E FULL STOP */,
217 0x002F /* 0x2F SOLIDUS */,
218 0x0030 /* 0x30 DIGIT ZERO */,
219 0x0031 /* 0x31 DIGIT ONE */,
220 0x0032 /* 0x32 DIGIT TWO */,
221 0x0033 /* 0x33 DIGIT THREE */,
222 0x0034 /* 0x34 DIGIT FOUR */,
223 0x0035 /* 0x35 DIGIT FIVE */,
224 0x0036 /* 0x36 DIGIT SIX */,
225 0x0037 /* 0x37 DIGIT SEVEN */,
226 0x0038 /* 0x38 DIGIT EIGHT */,
227 0x0039 /* 0x39 DIGIT NINE */,
228 0x003A /* 0x3A COLON */,
229 0x003B /* 0x3B SEMICOLON */,
230 0x003C /* 0x3C LESS-THAN SIGN */,
231 0x003D /* 0x3D EQUALS SIGN */,
232 0x003E /* 0x3E GREATER-THAN SIGN */,
233 0x003F /* 0x3F QUESTION MARK */,
234 0x0040 /* 0x40 COMMERCIAL AT */,
235 0x0041 /* 0x41 LATIN CAPITAL LETTER A */,
236 0x0042 /* 0x42 LATIN CAPITAL LETTER B */,
237 0x0043 /* 0x43 LATIN CAPITAL LETTER C */,
238 0x0044 /* 0x44 LATIN CAPITAL LETTER D */,
239 0x0045 /* 0x45 LATIN CAPITAL LETTER E */,
240 0x0046 /* 0x46 LATIN CAPITAL LETTER F */,
241 0x0047 /* 0x47 LATIN CAPITAL LETTER G */,
242 0x0048 /* 0x48 LATIN CAPITAL LETTER H */,
243 0x0049 /* 0x49 LATIN CAPITAL LETTER I */,
244 0x004A /* 0x4A LATIN CAPITAL LETTER J */,
245 0x004B /* 0x4B LATIN CAPITAL LETTER K */,
246 0x004C /* 0x4C LATIN CAPITAL LETTER L */,
247 0x004D /* 0x4D LATIN CAPITAL LETTER M */,
248 0x004E /* 0x4E LATIN CAPITAL LETTER N */,
249 0x004F /* 0x4F LATIN CAPITAL LETTER O */,
250 0x0050 /* 0x50 LATIN CAPITAL LETTER P */,
251 0x0051 /* 0x51 LATIN CAPITAL LETTER Q */,
252 0x0052 /* 0x52 LATIN CAPITAL LETTER R */,
253 0x0053 /* 0x53 LATIN CAPITAL LETTER S */,
254 0x0054 /* 0x54 LATIN CAPITAL LETTER T */,
255 0x0055 /* 0x55 LATIN CAPITAL LETTER U */,
256 0x0056 /* 0x56 LATIN CAPITAL LETTER V */,
257 0x0057 /* 0x57 LATIN CAPITAL LETTER W */,
258 0x0058 /* 0x58 LATIN CAPITAL LETTER X */,
259 0x0059 /* 0x59 LATIN CAPITAL LETTER Y */,
260 0x005A /* 0x5A LATIN CAPITAL LETTER Z */,
261 0x005B /* 0x5B LEFT SQUARE BRACKET */,
262 0x00A5 /* 0x5C YEN SIGN */,
263 0x005D /* 0x5D RIGHT SQUARE BRACKET */,
264 0x005E /* 0x5E CIRCUMFLEX ACCENT */,
265 0x005F /* 0x5F LOW LINE */,
266 0x0060 /* 0x60 GRAVE ACCENT */,
267 0x0061 /* 0x61 LATIN SMALL LETTER A */,
268 0x0062 /* 0x62 LATIN SMALL LETTER B */,
269 0x0063 /* 0x63 LATIN SMALL LETTER C */,
270 0x0064 /* 0x64 LATIN SMALL LETTER D */,
271 0x0065 /* 0x65 LATIN SMALL LETTER E */,
272 0x0066 /* 0x66 LATIN SMALL LETTER F */,
273 0x0067 /* 0x67 LATIN SMALL LETTER G */,
274 0x0068 /* 0x68 LATIN SMALL LETTER H */,
275 0x0069 /* 0x69 LATIN SMALL LETTER I */,
276 0x006A /* 0x6A LATIN SMALL LETTER J */,
277 0x006B /* 0x6B LATIN SMALL LETTER K */,
278 0x006C /* 0x6C LATIN SMALL LETTER L */,
279 0x006D /* 0x6D LATIN SMALL LETTER M */,
280 0x006E /* 0x6E LATIN SMALL LETTER N */,
281 0x006F /* 0x6F LATIN SMALL LETTER O */,
282 0x0070 /* 0x70 LATIN SMALL LETTER P */,
283 0x0071 /* 0x71 LATIN SMALL LETTER Q */,
284 0x0072 /* 0x72 LATIN SMALL LETTER R */,
285 0x0073 /* 0x73 LATIN SMALL LETTER S */,
286 0x0074 /* 0x74 LATIN SMALL LETTER T */,
287 0x0075 /* 0x75 LATIN SMALL LETTER U */,
288 0x0076 /* 0x76 LATIN SMALL LETTER V */,
289 0x0077 /* 0x77 LATIN SMALL LETTER W */,
290 0x0078 /* 0x78 LATIN SMALL LETTER X */,
291 0x0079 /* 0x79 LATIN SMALL LETTER Y */,
292 0x007A /* 0x7A LATIN SMALL LETTER Z */,
293 0x007B /* 0x7B LEFT CURLY BRACKET */,
294 0x007C /* 0x7C VERTICAL LINE */,
295 0x007D /* 0x7D RIGHT CURLY BRACKET */,
296 0x203E /* 0x7E OVERLINE */
299 Emchar latin_iso8859_2_to_ucs[96] =
301 0x00A0 /* 0xA0 NO-BREAK SPACE */,
302 0x0104 /* 0xA1 LATIN CAPITAL LETTER A WITH OGONEK */,
303 0x02D8 /* 0xA2 BREVE */,
304 0x0141 /* 0xA3 LATIN CAPITAL LETTER L WITH STROKE */,
305 0x00A4 /* 0xA4 CURRENCY SIGN */,
306 0x013D /* 0xA5 LATIN CAPITAL LETTER L WITH CARON */,
307 0x015A /* 0xA6 LATIN CAPITAL LETTER S WITH ACUTE */,
308 0x00A7 /* 0xA7 SECTION SIGN */,
309 0x00A8 /* 0xA8 DIAERESIS */,
310 0x0160 /* 0xA9 LATIN CAPITAL LETTER S WITH CARON */,
311 0x015E /* 0xAA LATIN CAPITAL LETTER S WITH CEDILLA */,
312 0x0164 /* 0xAB LATIN CAPITAL LETTER T WITH CARON */,
313 0x0179 /* 0xAC LATIN CAPITAL LETTER Z WITH ACUTE */,
314 0x00AD /* 0xAD SOFT HYPHEN */,
315 0x017D /* 0xAE LATIN CAPITAL LETTER Z WITH CARON */,
316 0x017B /* 0xAF LATIN CAPITAL LETTER Z WITH DOT ABOVE */,
317 0x00B0 /* 0xB0 DEGREE SIGN */,
318 0x0105 /* 0xB1 LATIN SMALL LETTER A WITH OGONEK */,
319 0x02DB /* 0xB2 OGONEK */,
320 0x0142 /* 0xB3 LATIN SMALL LETTER L WITH STROKE */,
321 0x00B4 /* 0xB4 ACUTE ACCENT */,
322 0x013E /* 0xB5 LATIN SMALL LETTER L WITH CARON */,
323 0x015B /* 0xB6 LATIN SMALL LETTER S WITH ACUTE */,
324 0x02C7 /* 0xB7 CARON */,
325 0x00B8 /* 0xB8 CEDILLA */,
326 0x0161 /* 0xB9 LATIN SMALL LETTER S WITH CARON */,
327 0x015F /* 0xBA LATIN SMALL LETTER S WITH CEDILLA */,
328 0x0165 /* 0xBB LATIN SMALL LETTER T WITH CARON */,
329 0x017A /* 0xBC LATIN SMALL LETTER Z WITH ACUTE */,
330 0x02DD /* 0xBD DOUBLE ACUTE ACCENT */,
331 0x017E /* 0xBE LATIN SMALL LETTER Z WITH CARON */,
332 0x017C /* 0xBF LATIN SMALL LETTER Z WITH DOT ABOVE */,
333 0x0154 /* 0xC0 LATIN CAPITAL LETTER R WITH ACUTE */,
334 0x00C1 /* 0xC1 LATIN CAPITAL LETTER A WITH ACUTE */,
335 0x00C2 /* 0xC2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX */,
336 0x0102 /* 0xC3 LATIN CAPITAL LETTER A WITH BREVE */,
337 0x00C4 /* 0xC4 LATIN CAPITAL LETTER A WITH DIAERESIS */,
338 0x0139 /* 0xC5 LATIN CAPITAL LETTER L WITH ACUTE */,
339 0x0106 /* 0xC6 LATIN CAPITAL LETTER C WITH ACUTE */,
340 0x00C7 /* 0xC7 LATIN CAPITAL LETTER C WITH CEDILLA */,
341 0x010C /* 0xC8 LATIN CAPITAL LETTER C WITH CARON */,
342 0x00C9 /* 0xC9 LATIN CAPITAL LETTER E WITH ACUTE */,
343 0x0118 /* 0xCA LATIN CAPITAL LETTER E WITH OGONEK */,
344 0x00CB /* 0xCB LATIN CAPITAL LETTER E WITH DIAERESIS */,
345 0x011A /* 0xCC LATIN CAPITAL LETTER E WITH CARON */,
346 0x00CD /* 0xCD LATIN CAPITAL LETTER I WITH ACUTE */,
347 0x00CE /* 0xCE LATIN CAPITAL LETTER I WITH CIRCUMFLEX */,
348 0x010E /* 0xCF LATIN CAPITAL LETTER D WITH CARON */,
349 0x0110 /* 0xD0 LATIN CAPITAL LETTER D WITH STROKE */,
350 0x0143 /* 0xD1 LATIN CAPITAL LETTER N WITH ACUTE */,
351 0x0147 /* 0xD2 LATIN CAPITAL LETTER N WITH CARON */,
352 0x00D3 /* 0xD3 LATIN CAPITAL LETTER O WITH ACUTE */,
353 0x00D4 /* 0xD4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX */,
354 0x0150 /* 0xD5 LATIN CAPITAL LETTER O WITH DOUBLE ACUTE */,
355 0x00D6 /* 0xD6 LATIN CAPITAL LETTER O WITH DIAERESIS */,
356 0x00D7 /* 0xD7 MULTIPLICATION SIGN */,
357 0x0158 /* 0xD8 LATIN CAPITAL LETTER R WITH CARON */,
358 0x016E /* 0xD9 LATIN CAPITAL LETTER U WITH RING ABOVE */,
359 0x00DA /* 0xDA LATIN CAPITAL LETTER U WITH ACUTE */,
360 0x0170 /* 0xDB LATIN CAPITAL LETTER U WITH DOUBLE ACUTE */,
361 0x00DC /* 0xDC LATIN CAPITAL LETTER U WITH DIAERESIS */,
362 0x00DD /* 0xDD LATIN CAPITAL LETTER Y WITH ACUTE */,
363 0x0162 /* 0xDE LATIN CAPITAL LETTER T WITH CEDILLA */,
364 0x00DF /* 0xDF LATIN SMALL LETTER SHARP S */,
365 0x0155 /* 0xE0 LATIN SMALL LETTER R WITH ACUTE */,
366 0x00E1 /* 0xE1 LATIN SMALL LETTER A WITH ACUTE */,
367 0x00E2 /* 0xE2 LATIN SMALL LETTER A WITH CIRCUMFLEX */,
368 0x0103 /* 0xE3 LATIN SMALL LETTER A WITH BREVE */,
369 0x00E4 /* 0xE4 LATIN SMALL LETTER A WITH DIAERESIS */,
370 0x013A /* 0xE5 LATIN SMALL LETTER L WITH ACUTE */,
371 0x0107 /* 0xE6 LATIN SMALL LETTER C WITH ACUTE */,
372 0x00E7 /* 0xE7 LATIN SMALL LETTER C WITH CEDILLA */,
373 0x010D /* 0xE8 LATIN SMALL LETTER C WITH CARON */,
374 0x00E9 /* 0xE9 LATIN SMALL LETTER E WITH ACUTE */,
375 0x0119 /* 0xEA LATIN SMALL LETTER E WITH OGONEK */,
376 0x00EB /* 0xEB LATIN SMALL LETTER E WITH DIAERESIS */,
377 0x011B /* 0xEC LATIN SMALL LETTER E WITH CARON */,
378 0x00ED /* 0xED LATIN SMALL LETTER I WITH ACUTE */,
379 0x00EE /* 0xEE LATIN SMALL LETTER I WITH CIRCUMFLEX */,
380 0x010F /* 0xEF LATIN SMALL LETTER D WITH CARON */,
381 0x0111 /* 0xF0 LATIN SMALL LETTER D WITH STROKE */,
382 0x0144 /* 0xF1 LATIN SMALL LETTER N WITH ACUTE */,
383 0x0148 /* 0xF2 LATIN SMALL LETTER N WITH CARON */,
384 0x00F3 /* 0xF3 LATIN SMALL LETTER O WITH ACUTE */,
385 0x00F4 /* 0xF4 LATIN SMALL LETTER O WITH CIRCUMFLEX */,
386 0x0151 /* 0xF5 LATIN SMALL LETTER O WITH DOUBLE ACUTE */,
387 0x00F6 /* 0xF6 LATIN SMALL LETTER O WITH DIAERESIS */,
388 0x00F7 /* 0xF7 DIVISION SIGN */,
389 0x0159 /* 0xF8 LATIN SMALL LETTER R WITH CARON */,
390 0x016F /* 0xF9 LATIN SMALL LETTER U WITH RING ABOVE */,
391 0x00FA /* 0xFA LATIN SMALL LETTER U WITH ACUTE */,
392 0x0171 /* 0xFB LATIN SMALL LETTER U WITH DOUBLE ACUTE */,
393 0x00FC /* 0xFC LATIN SMALL LETTER U WITH DIAERESIS */,
394 0x00FD /* 0xFD LATIN SMALL LETTER Y WITH ACUTE */,
395 0x0163 /* 0xFE LATIN SMALL LETTER T WITH CEDILLA */,
396 0x02D9 /* 0xFF DOT ABOVE */
399 Emchar latin_iso8859_3_to_ucs[96] =
401 0x00A0 /* 0xA0 NO-BREAK SPACE */,
402 0x0126 /* 0xA1 LATIN CAPITAL LETTER H WITH STROKE */,
403 0x02D8 /* 0xA2 BREVE */,
404 0x00A3 /* 0xA3 POUND SIGN */,
405 0x00A4 /* 0xA4 CURRENCY SIGN */,
407 0x0124 /* 0xA6 LATIN CAPITAL LETTER H WITH CIRCUMFLEX */,
408 0x00A7 /* 0xA7 SECTION SIGN */,
409 0x00A8 /* 0xA8 DIAERESIS */,
410 0x0130 /* 0xA9 LATIN CAPITAL LETTER I WITH DOT ABOVE */,
411 0x015E /* 0xAA LATIN CAPITAL LETTER S WITH CEDILLA */,
412 0x011E /* 0xAB LATIN CAPITAL LETTER G WITH BREVE */,
413 0x0134 /* 0xAC LATIN CAPITAL LETTER J WITH CIRCUMFLEX */,
414 0x00AD /* 0xAD SOFT HYPHEN */,
416 0x017B /* 0xAF LATIN CAPITAL LETTER Z WITH DOT ABOVE */,
417 0x00B0 /* 0xB0 DEGREE SIGN */,
418 0x0127 /* 0xB1 LATIN SMALL LETTER H WITH STROKE */,
419 0x00B2 /* 0xB2 SUPERSCRIPT TWO */,
420 0x00B3 /* 0xB3 SUPERSCRIPT THREE */,
421 0x00B4 /* 0xB4 ACUTE ACCENT */,
422 0x00B5 /* 0xB5 MICRO SIGN */,
423 0x0125 /* 0xB6 LATIN SMALL LETTER H WITH CIRCUMFLEX */,
424 0x00B7 /* 0xB7 MIDDLE DOT */,
425 0x00B8 /* 0xB8 CEDILLA */,
426 0x0131 /* 0xB9 LATIN SMALL LETTER DOTLESS I */,
427 0x015F /* 0xBA LATIN SMALL LETTER S WITH CEDILLA */,
428 0x011F /* 0xBB LATIN SMALL LETTER G WITH BREVE */,
429 0x0135 /* 0xBC LATIN SMALL LETTER J WITH CIRCUMFLEX */,
430 0x00BD /* 0xBD VULGAR FRACTION ONE HALF */,
432 0x017C /* 0xBF LATIN SMALL LETTER Z WITH DOT ABOVE */,
433 0x00C0 /* 0xC0 LATIN CAPITAL LETTER A WITH GRAVE */,
434 0x00C1 /* 0xC1 LATIN CAPITAL LETTER A WITH ACUTE */,
435 0x00C2 /* 0xC2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX */,
437 0x00C4 /* 0xC4 LATIN CAPITAL LETTER A WITH DIAERESIS */,
438 0x010A /* 0xC5 LATIN CAPITAL LETTER C WITH DOT ABOVE */,
439 0x0108 /* 0xC6 LATIN CAPITAL LETTER C WITH CIRCUMFLEX */,
440 0x00C7 /* 0xC7 LATIN CAPITAL LETTER C WITH CEDILLA */,
441 0x00C8 /* 0xC8 LATIN CAPITAL LETTER E WITH GRAVE */,
442 0x00C9 /* 0xC9 LATIN CAPITAL LETTER E WITH ACUTE */,
443 0x00CA /* 0xCA LATIN CAPITAL LETTER E WITH CIRCUMFLEX */,
444 0x00CB /* 0xCB LATIN CAPITAL LETTER E WITH DIAERESIS */,
445 0x00CC /* 0xCC LATIN CAPITAL LETTER I WITH GRAVE */,
446 0x00CD /* 0xCD LATIN CAPITAL LETTER I WITH ACUTE */,
447 0x00CE /* 0xCE LATIN CAPITAL LETTER I WITH CIRCUMFLEX */,
448 0x00CF /* 0xCF LATIN CAPITAL LETTER I WITH DIAERESIS */,
450 0x00D1 /* 0xD1 LATIN CAPITAL LETTER N WITH TILDE */,
451 0x00D2 /* 0xD2 LATIN CAPITAL LETTER O WITH GRAVE */,
452 0x00D3 /* 0xD3 LATIN CAPITAL LETTER O WITH ACUTE */,
453 0x00D4 /* 0xD4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX */,
454 0x0120 /* 0xD5 LATIN CAPITAL LETTER G WITH DOT ABOVE */,
455 0x00D6 /* 0xD6 LATIN CAPITAL LETTER O WITH DIAERESIS */,
456 0x00D7 /* 0xD7 MULTIPLICATION SIGN */,
457 0x011C /* 0xD8 LATIN CAPITAL LETTER G WITH CIRCUMFLEX */,
458 0x00D9 /* 0xD9 LATIN CAPITAL LETTER U WITH GRAVE */,
459 0x00DA /* 0xDA LATIN CAPITAL LETTER U WITH ACUTE */,
460 0x00DB /* 0xDB LATIN CAPITAL LETTER U WITH CIRCUMFLEX */,
461 0x00DC /* 0xDC LATIN CAPITAL LETTER U WITH DIAERESIS */,
462 0x016C /* 0xDD LATIN CAPITAL LETTER U WITH BREVE */,
463 0x015C /* 0xDE LATIN CAPITAL LETTER S WITH CIRCUMFLEX */,
464 0x00DF /* 0xDF LATIN SMALL LETTER SHARP S */,
465 0x00E0 /* 0xE0 LATIN SMALL LETTER A WITH GRAVE */,
466 0x00E1 /* 0xE1 LATIN SMALL LETTER A WITH ACUTE */,
467 0x00E2 /* 0xE2 LATIN SMALL LETTER A WITH CIRCUMFLEX */,
469 0x00E4 /* 0xE4 LATIN SMALL LETTER A WITH DIAERESIS */,
470 0x010B /* 0xE5 LATIN SMALL LETTER C WITH DOT ABOVE */,
471 0x0109 /* 0xE6 LATIN SMALL LETTER C WITH CIRCUMFLEX */,
472 0x00E7 /* 0xE7 LATIN SMALL LETTER C WITH CEDILLA */,
473 0x00E8 /* 0xE8 LATIN SMALL LETTER E WITH GRAVE */,
474 0x00E9 /* 0xE9 LATIN SMALL LETTER E WITH ACUTE */,
475 0x00EA /* 0xEA LATIN SMALL LETTER E WITH CIRCUMFLEX */,
476 0x00EB /* 0xEB LATIN SMALL LETTER E WITH DIAERESIS */,
477 0x00EC /* 0xEC LATIN SMALL LETTER I WITH GRAVE */,
478 0x00ED /* 0xED LATIN SMALL LETTER I WITH ACUTE */,
479 0x00EE /* 0xEE LATIN SMALL LETTER I WITH CIRCUMFLEX */,
480 0x00EF /* 0xEF LATIN SMALL LETTER I WITH DIAERESIS */,
482 0x00F1 /* 0xF1 LATIN SMALL LETTER N WITH TILDE */,
483 0x00F2 /* 0xF2 LATIN SMALL LETTER O WITH GRAVE */,
484 0x00F3 /* 0xF3 LATIN SMALL LETTER O WITH ACUTE */,
485 0x00F4 /* 0xF4 LATIN SMALL LETTER O WITH CIRCUMFLEX */,
486 0x0121 /* 0xF5 LATIN SMALL LETTER G WITH DOT ABOVE */,
487 0x00F6 /* 0xF6 LATIN SMALL LETTER O WITH DIAERESIS */,
488 0x00F7 /* 0xF7 DIVISION SIGN */,
489 0x011D /* 0xF8 LATIN SMALL LETTER G WITH CIRCUMFLEX */,
490 0x00F9 /* 0xF9 LATIN SMALL LETTER U WITH GRAVE */,
491 0x00FA /* 0xFA LATIN SMALL LETTER U WITH ACUTE */,
492 0x00FB /* 0xFB LATIN SMALL LETTER U WITH CIRCUMFLEX */,
493 0x00FC /* 0xFC LATIN SMALL LETTER U WITH DIAERESIS */,
494 0x016D /* 0xFD LATIN SMALL LETTER U WITH BREVE */,
495 0x015D /* 0xFE LATIN SMALL LETTER S WITH CIRCUMFLEX */,
496 0x02D9 /* 0xFF DOT ABOVE */
499 Emchar latin_iso8859_4_to_ucs[96] =
501 0x00A0 /* 0xA0 NO-BREAK SPACE */,
502 0x0104 /* 0xA1 LATIN CAPITAL LETTER A WITH OGONEK */,
503 0x0138 /* 0xA2 LATIN SMALL LETTER KRA */,
504 0x0156 /* 0xA3 LATIN CAPITAL LETTER R WITH CEDILLA */,
505 0x00A4 /* 0xA4 CURRENCY SIGN */,
506 0x0128 /* 0xA5 LATIN CAPITAL LETTER I WITH TILDE */,
507 0x013B /* 0xA6 LATIN CAPITAL LETTER L WITH CEDILLA */,
508 0x00A7 /* 0xA7 SECTION SIGN */,
509 0x00A8 /* 0xA8 DIAERESIS */,
510 0x0160 /* 0xA9 LATIN CAPITAL LETTER S WITH CARON */,
511 0x0112 /* 0xAA LATIN CAPITAL LETTER E WITH MACRON */,
512 0x0122 /* 0xAB LATIN CAPITAL LETTER G WITH CEDILLA */,
513 0x0166 /* 0xAC LATIN CAPITAL LETTER T WITH STROKE */,
514 0x00AD /* 0xAD SOFT HYPHEN */,
515 0x017D /* 0xAE LATIN CAPITAL LETTER Z WITH CARON */,
516 0x00AF /* 0xAF MACRON */,
517 0x00B0 /* 0xB0 DEGREE SIGN */,
518 0x0105 /* 0xB1 LATIN SMALL LETTER A WITH OGONEK */,
519 0x02DB /* 0xB2 OGONEK */,
520 0x0157 /* 0xB3 LATIN SMALL LETTER R WITH CEDILLA */,
521 0x00B4 /* 0xB4 ACUTE ACCENT */,
522 0x0129 /* 0xB5 LATIN SMALL LETTER I WITH TILDE */,
523 0x013C /* 0xB6 LATIN SMALL LETTER L WITH CEDILLA */,
524 0x02C7 /* 0xB7 CARON */,
525 0x00B8 /* 0xB8 CEDILLA */,
526 0x0161 /* 0xB9 LATIN SMALL LETTER S WITH CARON */,
527 0x0113 /* 0xBA LATIN SMALL LETTER E WITH MACRON */,
528 0x0123 /* 0xBB LATIN SMALL LETTER G WITH CEDILLA */,
529 0x0167 /* 0xBC LATIN SMALL LETTER T WITH STROKE */,
530 0x014A /* 0xBD LATIN CAPITAL LETTER ENG */,
531 0x017E /* 0xBE LATIN SMALL LETTER Z WITH CARON */,
532 0x014B /* 0xBF LATIN SMALL LETTER ENG */,
533 0x0100 /* 0xC0 LATIN CAPITAL LETTER A WITH MACRON */,
534 0x00C1 /* 0xC1 LATIN CAPITAL LETTER A WITH ACUTE */,
535 0x00C2 /* 0xC2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX */,
536 0x00C3 /* 0xC3 LATIN CAPITAL LETTER A WITH TILDE */,
537 0x00C4 /* 0xC4 LATIN CAPITAL LETTER A WITH DIAERESIS */,
538 0x00C5 /* 0xC5 LATIN CAPITAL LETTER A WITH RING ABOVE */,
539 0x00C6 /* 0xC6 LATIN CAPITAL LETTER AE */,
540 0x012E /* 0xC7 LATIN CAPITAL LETTER I WITH OGONEK */,
541 0x010C /* 0xC8 LATIN CAPITAL LETTER C WITH CARON */,
542 0x00C9 /* 0xC9 LATIN CAPITAL LETTER E WITH ACUTE */,
543 0x0118 /* 0xCA LATIN CAPITAL LETTER E WITH OGONEK */,
544 0x00CB /* 0xCB LATIN CAPITAL LETTER E WITH DIAERESIS */,
545 0x0116 /* 0xCC LATIN CAPITAL LETTER E WITH DOT ABOVE */,
546 0x00CD /* 0xCD LATIN CAPITAL LETTER I WITH ACUTE */,
547 0x00CE /* 0xCE LATIN CAPITAL LETTER I WITH CIRCUMFLEX */,
548 0x012A /* 0xCF LATIN CAPITAL LETTER I WITH MACRON */,
549 0x0110 /* 0xD0 LATIN CAPITAL LETTER D WITH STROKE */,
550 0x0145 /* 0xD1 LATIN CAPITAL LETTER N WITH CEDILLA */,
551 0x014C /* 0xD2 LATIN CAPITAL LETTER O WITH MACRON */,
552 0x0136 /* 0xD3 LATIN CAPITAL LETTER K WITH CEDILLA */,
553 0x00D4 /* 0xD4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX */,
554 0x00D5 /* 0xD5 LATIN CAPITAL LETTER O WITH TILDE */,
555 0x00D6 /* 0xD6 LATIN CAPITAL LETTER O WITH DIAERESIS */,
556 0x00D7 /* 0xD7 MULTIPLICATION SIGN */,
557 0x00D8 /* 0xD8 LATIN CAPITAL LETTER O WITH STROKE */,
558 0x0172 /* 0xD9 LATIN CAPITAL LETTER U WITH OGONEK */,
559 0x00DA /* 0xDA LATIN CAPITAL LETTER U WITH ACUTE */,
560 0x00DB /* 0xDB LATIN CAPITAL LETTER U WITH CIRCUMFLEX */,
561 0x00DC /* 0xDC LATIN CAPITAL LETTER U WITH DIAERESIS */,
562 0x0168 /* 0xDD LATIN CAPITAL LETTER U WITH TILDE */,
563 0x016A /* 0xDE LATIN CAPITAL LETTER U WITH MACRON */,
564 0x00DF /* 0xDF LATIN SMALL LETTER SHARP S */,
565 0x0101 /* 0xE0 LATIN SMALL LETTER A WITH MACRON */,
566 0x00E1 /* 0xE1 LATIN SMALL LETTER A WITH ACUTE */,
567 0x00E2 /* 0xE2 LATIN SMALL LETTER A WITH CIRCUMFLEX */,
568 0x00E3 /* 0xE3 LATIN SMALL LETTER A WITH TILDE */,
569 0x00E4 /* 0xE4 LATIN SMALL LETTER A WITH DIAERESIS */,
570 0x00E5 /* 0xE5 LATIN SMALL LETTER A WITH RING ABOVE */,
571 0x00E6 /* 0xE6 LATIN SMALL LETTER AE */,
572 0x012F /* 0xE7 LATIN SMALL LETTER I WITH OGONEK */,
573 0x010D /* 0xE8 LATIN SMALL LETTER C WITH CARON */,
574 0x00E9 /* 0xE9 LATIN SMALL LETTER E WITH ACUTE */,
575 0x0119 /* 0xEA LATIN SMALL LETTER E WITH OGONEK */,
576 0x00EB /* 0xEB LATIN SMALL LETTER E WITH DIAERESIS */,
577 0x0117 /* 0xEC LATIN SMALL LETTER E WITH DOT ABOVE */,
578 0x00ED /* 0xED LATIN SMALL LETTER I WITH ACUTE */,
579 0x00EE /* 0xEE LATIN SMALL LETTER I WITH CIRCUMFLEX */,
580 0x012B /* 0xEF LATIN SMALL LETTER I WITH MACRON */,
581 0x0111 /* 0xF0 LATIN SMALL LETTER D WITH STROKE */,
582 0x0146 /* 0xF1 LATIN SMALL LETTER N WITH CEDILLA */,
583 0x014D /* 0xF2 LATIN SMALL LETTER O WITH MACRON */,
584 0x0137 /* 0xF3 LATIN SMALL LETTER K WITH CEDILLA */,
585 0x00F4 /* 0xF4 LATIN SMALL LETTER O WITH CIRCUMFLEX */,
586 0x00F5 /* 0xF5 LATIN SMALL LETTER O WITH TILDE */,
587 0x00F6 /* 0xF6 LATIN SMALL LETTER O WITH DIAERESIS */,
588 0x00F7 /* 0xF7 DIVISION SIGN */,
589 0x00F8 /* 0xF8 LATIN SMALL LETTER O WITH STROKE */,
590 0x0173 /* 0xF9 LATIN SMALL LETTER U WITH OGONEK */,
591 0x00FA /* 0xFA LATIN SMALL LETTER U WITH ACUTE */,
592 0x00FB /* 0xFB LATIN SMALL LETTER U WITH CIRCUMFLEX */,
593 0x00FC /* 0xFC LATIN SMALL LETTER U WITH DIAERESIS */,
594 0x0169 /* 0xFD LATIN SMALL LETTER U WITH TILDE */,
595 0x016B /* 0xFE LATIN SMALL LETTER U WITH MACRON */,
596 0x02D9 /* 0xFF DOT ABOVE */
599 Emchar latin_iso8859_9_to_ucs[96] =
601 0x00A0 /* 0xA0 NO-BREAK SPACE */,
602 0x00A1 /* 0xA1 INVERTED EXCLAMATION MARK */,
603 0x00A2 /* 0xA2 CENT SIGN */,
604 0x00A3 /* 0xA3 POUND SIGN */,
605 0x00A4 /* 0xA4 CURRENCY SIGN */,
606 0x00A5 /* 0xA5 YEN SIGN */,
607 0x00A6 /* 0xA6 BROKEN BAR */,
608 0x00A7 /* 0xA7 SECTION SIGN */,
609 0x00A8 /* 0xA8 DIAERESIS */,
610 0x00A9 /* 0xA9 COPYRIGHT SIGN */,
611 0x00AA /* 0xAA FEMININE ORDINAL INDICATOR */,
612 0x00AB /* 0xAB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK */,
613 0x00AC /* 0xAC NOT SIGN */,
614 0x00AD /* 0xAD SOFT HYPHEN */,
615 0x00AE /* 0xAE REGISTERED SIGN */,
616 0x00AF /* 0xAF MACRON */,
617 0x00B0 /* 0xB0 DEGREE SIGN */,
618 0x00B1 /* 0xB1 PLUS-MINUS SIGN */,
619 0x00B2 /* 0xB2 SUPERSCRIPT TWO */,
620 0x00B3 /* 0xB3 SUPERSCRIPT THREE */,
621 0x00B4 /* 0xB4 ACUTE ACCENT */,
622 0x00B5 /* 0xB5 MICRO SIGN */,
623 0x00B6 /* 0xB6 PILCROW SIGN */,
624 0x00B7 /* 0xB7 MIDDLE DOT */,
625 0x00B8 /* 0xB8 CEDILLA */,
626 0x00B9 /* 0xB9 SUPERSCRIPT ONE */,
627 0x00BA /* 0xBA MASCULINE ORDINAL INDICATOR */,
628 0x00BB /* 0xBB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK */,
629 0x00BC /* 0xBC VULGAR FRACTION ONE QUARTER */,
630 0x00BD /* 0xBD VULGAR FRACTION ONE HALF */,
631 0x00BE /* 0xBE VULGAR FRACTION THREE QUARTERS */,
632 0x00BF /* 0xBF INVERTED QUESTION MARK */,
633 0x00C0 /* 0xC0 LATIN CAPITAL LETTER A WITH GRAVE */,
634 0x00C1 /* 0xC1 LATIN CAPITAL LETTER A WITH ACUTE */,
635 0x00C2 /* 0xC2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX */,
636 0x00C3 /* 0xC3 LATIN CAPITAL LETTER A WITH TILDE */,
637 0x00C4 /* 0xC4 LATIN CAPITAL LETTER A WITH DIAERESIS */,
638 0x00C5 /* 0xC5 LATIN CAPITAL LETTER A WITH RING ABOVE */,
639 0x00C6 /* 0xC6 LATIN CAPITAL LETTER AE */,
640 0x00C7 /* 0xC7 LATIN CAPITAL LETTER C WITH CEDILLA */,
641 0x00C8 /* 0xC8 LATIN CAPITAL LETTER E WITH GRAVE */,
642 0x00C9 /* 0xC9 LATIN CAPITAL LETTER E WITH ACUTE */,
643 0x00CA /* 0xCA LATIN CAPITAL LETTER E WITH CIRCUMFLEX */,
644 0x00CB /* 0xCB LATIN CAPITAL LETTER E WITH DIAERESIS */,
645 0x00CC /* 0xCC LATIN CAPITAL LETTER I WITH GRAVE */,
646 0x00CD /* 0xCD LATIN CAPITAL LETTER I WITH ACUTE */,
647 0x00CE /* 0xCE LATIN CAPITAL LETTER I WITH CIRCUMFLEX */,
648 0x00CF /* 0xCF LATIN CAPITAL LETTER I WITH DIAERESIS */,
649 0x011E /* 0xD0 LATIN CAPITAL LETTER G WITH BREVE */,
650 0x00D1 /* 0xD1 LATIN CAPITAL LETTER N WITH TILDE */,
651 0x00D2 /* 0xD2 LATIN CAPITAL LETTER O WITH GRAVE */,
652 0x00D3 /* 0xD3 LATIN CAPITAL LETTER O WITH ACUTE */,
653 0x00D4 /* 0xD4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX */,
654 0x00D5 /* 0xD5 LATIN CAPITAL LETTER O WITH TILDE */,
655 0x00D6 /* 0xD6 LATIN CAPITAL LETTER O WITH DIAERESIS */,
656 0x00D7 /* 0xD7 MULTIPLICATION SIGN */,
657 0x00D8 /* 0xD8 LATIN CAPITAL LETTER O WITH STROKE */,
658 0x00D9 /* 0xD9 LATIN CAPITAL LETTER U WITH GRAVE */,
659 0x00DA /* 0xDA LATIN CAPITAL LETTER U WITH ACUTE */,
660 0x00DB /* 0xDB LATIN CAPITAL LETTER U WITH CIRCUMFLEX */,
661 0x00DC /* 0xDC LATIN CAPITAL LETTER U WITH DIAERESIS */,
662 0x0130 /* 0xDD LATIN CAPITAL LETTER I WITH DOT ABOVE */,
663 0x015E /* 0xDE LATIN CAPITAL LETTER S WITH CEDILLA */,
664 0x00DF /* 0xDF LATIN SMALL LETTER SHARP S */,
665 0x00E0 /* 0xE0 LATIN SMALL LETTER A WITH GRAVE */,
666 0x00E1 /* 0xE1 LATIN SMALL LETTER A WITH ACUTE */,
667 0x00E2 /* 0xE2 LATIN SMALL LETTER A WITH CIRCUMFLEX */,
668 0x00E3 /* 0xE3 LATIN SMALL LETTER A WITH TILDE */,
669 0x00E4 /* 0xE4 LATIN SMALL LETTER A WITH DIAERESIS */,
670 0x00E5 /* 0xE5 LATIN SMALL LETTER A WITH RING ABOVE */,
671 0x00E6 /* 0xE6 LATIN SMALL LETTER AE */,
672 0x00E7 /* 0xE7 LATIN SMALL LETTER C WITH CEDILLA */,
673 0x00E8 /* 0xE8 LATIN SMALL LETTER E WITH GRAVE */,
674 0x00E9 /* 0xE9 LATIN SMALL LETTER E WITH ACUTE */,
675 0x00EA /* 0xEA LATIN SMALL LETTER E WITH CIRCUMFLEX */,
676 0x00EB /* 0xEB LATIN SMALL LETTER E WITH DIAERESIS */,
677 0x00EC /* 0xEC LATIN SMALL LETTER I WITH GRAVE */,
678 0x00ED /* 0xED LATIN SMALL LETTER I WITH ACUTE */,
679 0x00EE /* 0xEE LATIN SMALL LETTER I WITH CIRCUMFLEX */,
680 0x00EF /* 0xEF LATIN SMALL LETTER I WITH DIAERESIS */,
681 0x011F /* 0xF0 LATIN SMALL LETTER G WITH BREVE */,
682 0x00F1 /* 0xF1 LATIN SMALL LETTER N WITH TILDE */,
683 0x00F2 /* 0xF2 LATIN SMALL LETTER O WITH GRAVE */,
684 0x00F3 /* 0xF3 LATIN SMALL LETTER O WITH ACUTE */,
685 0x00F4 /* 0xF4 LATIN SMALL LETTER O WITH CIRCUMFLEX */,
686 0x00F5 /* 0xF5 LATIN SMALL LETTER O WITH TILDE */,
687 0x00F6 /* 0xF6 LATIN SMALL LETTER O WITH DIAERESIS */,
688 0x00F7 /* 0xF7 DIVISION SIGN */,
689 0x00F8 /* 0xF8 LATIN SMALL LETTER O WITH STROKE */,
690 0x00F9 /* 0xF9 LATIN SMALL LETTER U WITH GRAVE */,
691 0x00FA /* 0xFA LATIN SMALL LETTER U WITH ACUTE */,
692 0x00FB /* 0xFB LATIN SMALL LETTER U WITH CIRCUMFLEX */,
693 0x00FC /* 0xFC LATIN SMALL LETTER U WITH DIAERESIS */,
694 0x0131 /* 0xFD LATIN SMALL LETTER DOTLESS I */,
695 0x015F /* 0xFE LATIN SMALL LETTER S WITH CEDILLA */,
696 0x00FF /* 0xFF LATIN SMALL LETTER Y WITH DIAERESIS */,
699 Emchar latin_viscii_lower_to_ucs[96] =
799 Emchar latin_viscii_upper_to_ucs[96] =
899 Emchar latin_tcvn5712_to_ucs[96] =
901 0x00A0 /* 0xA0 NO-BREAK SPACE */,
902 0x0102 /* 0xA1 LATIN CAPITAL LETTER A WITH BREVE */,
903 0x00C2 /* 0xA2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX */,
904 0x00CA /* 0xA3 LATIN CAPITAL LETTER E WITH CIRCUMFLEX */,
905 0x00D4 /* 0xA4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX */,
906 0x01A0 /* 0xA5 LATIN CAPITAL LETTER O WITH HORN */,
907 0x01AF /* 0xA6 LATIN CAPITAL LETTER U WITH HORN */,
908 0x0110 /* 0xA7 LATIN CAPITAL LETTER D WITH STROKE */,
909 0x0103 /* 0xA8 LATIN SMALL LETTER A WITH BREVE */,
910 0x00E2 /* 0xA9 LATIN SMALL LETTER A WITH CIRCUMFLEX */,
911 0x00EA /* 0xAA LATIN SMALL LETTER E WITH CIRCUMFLEX */,
912 0x00F4 /* 0xAB LATIN SMALL LETTER O WITH CIRCUMFLEX */,
913 0x01A1 /* 0xAC LATIN SMALL LETTER O WITH HORN */,
914 0x01B0 /* 0xAD LATIN SMALL LETTER U WITH HORN */,
915 0x0111 /* 0xAE LATIN SMALL LETTER D WITH STROKE */,
916 0x1EB0 /* 0xAF LATIN CAPITAL LETTER A WITH BREVE AND GRAVE */,
917 0x0300 /* 0xB0 COMBINING GRAVE ACCENT */,
918 0x0309 /* 0xB1 COMBINING HOOK ABOVE */,
919 0x0303 /* 0xB2 COMBINING TILDE */,
920 0x0301 /* 0xB3 COMBINING ACUTE ACCENT */,
921 0x0323 /* 0xB4 COMBINING DOT BELOW */,
922 0x00E0 /* 0xB5 LATIN SMALL LETTER A WITH GRAVE */,
923 0x1EA3 /* 0xB6 LATIN SMALL LETTER A WITH HOOK ABOVE */,
924 0x00E3 /* 0xB7 LATIN SMALL LETTER A WITH TILDE */,
925 0x00E1 /* 0xB8 LATIN SMALL LETTER A WITH ACUTE */,
926 0x1EA1 /* 0xB9 LATIN SMALL LETTER A WITH DOT BELOW */,
927 0x1EB2 /* 0xBA LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE */,
928 0x1EB1 /* 0xBB LATIN SMALL LETTER A WITH BREVE AND GRAVE */,
929 0x1EB3 /* 0xBC LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE */,
930 0x1EB5 /* 0xBD LATIN SMALL LETTER A WITH BREVE AND TILDE */,
931 0x1EAF /* 0xBE LATIN SMALL LETTER A WITH BREVE AND ACUTE */,
932 0x1EB4 /* 0xBF LATIN CAPITAL LETTER A WITH BREVE AND TILDE */,
933 0x1EAE /* 0xC0 LATIN CAPITAL LETTER A WITH BREVE AND ACUTE */,
934 0x1EA6 /* 0xC1 LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE */,
935 0x1EA8 /* 0xC2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE */,
936 0x1EAA /* 0xC3 LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE */,
937 0x1EA4 /* 0xC4 LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE */,
938 0x1EC0 /* 0xC5 LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE */,
939 0x1EB7 /* 0xC6 LATIN SMALL LETTER A WITH BREVE AND DOT BELOW */,
940 0x1EA7 /* 0xC7 LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE */,
941 0x1EA9 /* 0xC8 LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE */,
942 0x1EAB /* 0xC9 LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE */,
943 0x1EA5 /* 0xCA LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE */,
944 0x1EAD /* 0xCB LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW */,
945 0x00E8 /* 0xCC LATIN SMALL LETTER E WITH GRAVE */,
946 0x1EC2 /* 0xCD LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE */,
947 0x1EBB /* 0xCE LATIN SMALL LETTER E WITH HOOK ABOVE */,
948 0x1EBD /* 0xCF LATIN SMALL LETTER E WITH TILDE */,
949 0x00E9 /* 0xD0 LATIN SMALL LETTER E WITH ACUTE */,
950 0x1EB9 /* 0xD1 LATIN SMALL LETTER E WITH DOT BELOW */,
951 0x1EC1 /* 0xD2 LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE */,
952 0x1EC3 /* 0xD3 LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE */,
953 0x1EC5 /* 0xD4 LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE */,
954 0x1EBF /* 0xD5 LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE */,
955 0x1EC7 /* 0xD6 LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW */,
956 0x00EC /* 0xD7 LATIN SMALL LETTER I WITH GRAVE */,
957 0x1EC9 /* 0xD8 LATIN SMALL LETTER I WITH HOOK ABOVE */,
958 0x1EC4 /* 0xD9 LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE */,
959 0x1EBE /* 0xDA LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE */,
960 0x1ED2 /* 0xDB LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE */,
961 0x0129 /* 0xDC LATIN SMALL LETTER I WITH TILDE */,
962 0x00ED /* 0xDD LATIN SMALL LETTER I WITH ACUTE */,
963 0x1ECB /* 0xDE LATIN SMALL LETTER I WITH DOT BELOW */,
964 0x00F2 /* 0xDF LATIN SMALL LETTER O WITH GRAVE */,
965 0x1ED4 /* 0xE0 LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE */,
966 0x1ECF /* 0xE1 LATIN SMALL LETTER O WITH HOOK ABOVE */,
967 0x00F5 /* 0xE2 LATIN SMALL LETTER O WITH TILDE */,
968 0x00F3 /* 0xE3 LATIN SMALL LETTER O WITH ACUTE */,
969 0x1ECD /* 0xE4 LATIN SMALL LETTER O WITH DOT BELOW */,
970 0x1ED3 /* 0xE5 LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE */,
971 0x1ED5 /* 0xE6 LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE */,
972 0x1ED7 /* 0xE7 LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE */,
973 0x1ED1 /* 0xE8 LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE */,
974 0x1ED9 /* 0xE9 LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW */,
975 0x1EDD /* 0xEA LATIN SMALL LETTER O WITH HORN AND GRAVE */,
976 0x1EDF /* 0xEB LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE */,
977 0x1EE1 /* 0xEC LATIN SMALL LETTER O WITH HORN AND TILDE */,
978 0x1EDB /* 0xED LATIN SMALL LETTER O WITH HORN AND ACUTE */,
979 0x1EE3 /* 0xEE LATIN SMALL LETTER O WITH HORN AND DOT BELOW */,
980 0x00F9 /* 0xEF LATIN SMALL LETTER U WITH GRAVE */,
981 0x1ED6 /* 0xF0 LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE */,
982 0x1EE7 /* 0xF1 LATIN SMALL LETTER U WITH HOOK ABOVE */,
983 0x0169 /* 0xF2 LATIN SMALL LETTER U WITH TILDE */,
984 0x00FA /* 0xF3 LATIN SMALL LETTER U WITH ACUTE */,
985 0x1EE5 /* 0xF4 LATIN SMALL LETTER U WITH DOT BELOW */,
986 0x1EEB /* 0xF5 LATIN SMALL LETTER U WITH HORN AND GRAVE */,
987 0x1EED /* 0xF6 LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE */,
988 0x1EEF /* 0xF7 LATIN SMALL LETTER U WITH HORN AND TILDE */,
989 0x1EE9 /* 0xF8 LATIN SMALL LETTER U WITH HORN AND ACUTE */,
990 0x1EF1 /* 0xF9 LATIN SMALL LETTER U WITH HORN AND DOT BELOW */,
991 0x1EF3 /* 0xFA LATIN SMALL LETTER Y WITH GRAVE */,
992 0x1EF7 /* 0xFB LATIN SMALL LETTER Y WITH HOOK ABOVE */,
993 0x1EF9 /* 0xFC LATIN SMALL LETTER Y WITH TILDE */,
994 0x00FD /* 0xFD LATIN SMALL LETTER Y WITH ACUTE */,
995 0x1EF5 /* 0xFE LATIN SMALL LETTER Y WITH DOT BELOW */,
996 0x1ED0 /* 0xFF LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE */
999 Lisp_Object Vutf_2000_version;
1003 int leading_code_private_11;
1006 Lisp_Object Qcharsetp;
1008 /* Qdoc_string, Qdimension, Qchars defined in general.c */
1009 Lisp_Object Qregistry, Qfinal, Qgraphic;
1010 Lisp_Object Qdirection;
1011 Lisp_Object Qreverse_direction_charset;
1012 Lisp_Object Qleading_byte;
1013 Lisp_Object Qshort_name, Qlong_name;
1027 Qcyrillic_iso8859_5,
1029 Qjapanese_jisx0208_1978,
1034 Qchinese_cns11643_1,
1035 Qchinese_cns11643_2,
1037 Qchinese_cns11643_3,
1038 Qchinese_cns11643_4,
1039 Qchinese_cns11643_5,
1040 Qchinese_cns11643_6,
1041 Qchinese_cns11643_7,
1043 Qlatin_viscii_lower,
1044 Qlatin_viscii_upper,
1050 Lisp_Object Ql2r, Qr2l;
1052 Lisp_Object Vcharset_hash_table;
1054 static Charset_ID next_allocated_1_byte_leading_byte;
1055 static Charset_ID next_allocated_2_byte_leading_byte;
1057 /* Composite characters are characters constructed by overstriking two
1058 or more regular characters.
1060 1) The old Mule implementation involves storing composite characters
1061 in a buffer as a tag followed by all of the actual characters
1062 used to make up the composite character. I think this is a bad
1063 idea; it greatly complicates code that wants to handle strings
1064 one character at a time because it has to deal with the possibility
1065 of great big ungainly characters. It's much more reasonable to
1066 simply store an index into a table of composite characters.
1068 2) The current implementation only allows for 16,384 separate
1069 composite characters over the lifetime of the XEmacs process.
1070 This could become a potential problem if the user
1071 edited lots of different files that use composite characters.
1072 Due to FSF bogosity, increasing the number of allowable
1073 composite characters under Mule would decrease the number
1074 of possible faces that can exist. Mule already has shrunk
1075 this to 2048, and further shrinkage would become uncomfortable.
1076 No such problems exist in XEmacs.
1078 Composite characters could be represented as 0x80 C1 C2 C3,
1079 where each C[1-3] is in the range 0xA0 - 0xFF. This allows
1080 for slightly under 2^20 (one million) composite characters
1081 over the XEmacs process lifetime, and you only need to
1082 increase the size of a Mule character from 19 to 21 bits.
1083 Or you could use 0x80 C1 C2 C3 C4, allowing for about
1084 85 million (slightly over 2^26) composite characters. */
1087 /************************************************************************/
1088 /* Basic Emchar functions */
1089 /************************************************************************/
1091 /* Convert a non-ASCII Mule character C into a one-character Mule-encoded
1092 string in STR. Returns the number of bytes stored.
1093 Do not call this directly. Use the macro set_charptr_emchar() instead.
1097 non_ascii_set_charptr_emchar (Bufbyte *str, Emchar c)
1103 Lisp_Object charset;
1112 else if ( c <= 0x7ff )
1114 *p++ = (c >> 6) | 0xc0;
1115 *p++ = (c & 0x3f) | 0x80;
1117 else if ( c <= 0xffff )
1119 *p++ = (c >> 12) | 0xe0;
1120 *p++ = ((c >> 6) & 0x3f) | 0x80;
1121 *p++ = (c & 0x3f) | 0x80;
1123 else if ( c <= 0x1fffff )
1125 *p++ = (c >> 18) | 0xf0;
1126 *p++ = ((c >> 12) & 0x3f) | 0x80;
1127 *p++ = ((c >> 6) & 0x3f) | 0x80;
1128 *p++ = (c & 0x3f) | 0x80;
1130 else if ( c <= 0x3ffffff )
1132 *p++ = (c >> 24) | 0xf8;
1133 *p++ = ((c >> 18) & 0x3f) | 0x80;
1134 *p++ = ((c >> 12) & 0x3f) | 0x80;
1135 *p++ = ((c >> 6) & 0x3f) | 0x80;
1136 *p++ = (c & 0x3f) | 0x80;
1140 *p++ = (c >> 30) | 0xfc;
1141 *p++ = ((c >> 24) & 0x3f) | 0x80;
1142 *p++ = ((c >> 18) & 0x3f) | 0x80;
1143 *p++ = ((c >> 12) & 0x3f) | 0x80;
1144 *p++ = ((c >> 6) & 0x3f) | 0x80;
1145 *p++ = (c & 0x3f) | 0x80;
1148 BREAKUP_CHAR (c, charset, c1, c2);
1149 lb = CHAR_LEADING_BYTE (c);
1150 if (LEADING_BYTE_PRIVATE_P (lb))
1151 *p++ = PRIVATE_LEADING_BYTE_PREFIX (lb);
1153 if (EQ (charset, Vcharset_control_1))
1162 /* Return the first character from a Mule-encoded string in STR,
1163 assuming it's non-ASCII. Do not call this directly.
1164 Use the macro charptr_emchar() instead. */
1167 non_ascii_charptr_emchar (CONST Bufbyte *str)
1180 else if ( b >= 0xf8 )
1185 else if ( b >= 0xf0 )
1190 else if ( b >= 0xe0 )
1195 else if ( b >= 0xc0 )
1205 for( ; len > 0; len-- )
1208 ch = ( ch << 6 ) | ( b & 0x3f );
1212 Bufbyte i0 = *str, i1, i2 = 0;
1213 Lisp_Object charset;
1215 if (i0 == LEADING_BYTE_CONTROL_1)
1216 return (Emchar) (*++str - 0x20);
1218 if (LEADING_BYTE_PREFIX_P (i0))
1223 charset = CHARSET_BY_LEADING_BYTE (i0);
1224 if (XCHARSET_DIMENSION (charset) == 2)
1227 return MAKE_CHAR (charset, i1, i2);
1231 /* Return whether CH is a valid Emchar, assuming it's non-ASCII.
1232 Do not call this directly. Use the macro valid_char_p() instead. */
1236 non_ascii_valid_char_p (Emchar ch)
1240 /* Must have only lowest 19 bits set */
1244 f1 = CHAR_FIELD1 (ch);
1245 f2 = CHAR_FIELD2 (ch);
1246 f3 = CHAR_FIELD3 (ch);
1250 Lisp_Object charset;
1252 if (f2 < MIN_CHAR_FIELD2_OFFICIAL ||
1253 (f2 > MAX_CHAR_FIELD2_OFFICIAL && f2 < MIN_CHAR_FIELD2_PRIVATE) ||
1254 f2 > MAX_CHAR_FIELD2_PRIVATE)
1259 if (f3 != 0x20 && f3 != 0x7F)
1263 NOTE: This takes advantage of the fact that
1264 FIELD2_TO_OFFICIAL_LEADING_BYTE and
1265 FIELD2_TO_PRIVATE_LEADING_BYTE are the same.
1267 charset = CHARSET_BY_LEADING_BYTE (f2 + FIELD2_TO_OFFICIAL_LEADING_BYTE);
1268 return (XCHARSET_CHARS (charset) == 96);
1272 Lisp_Object charset;
1274 if (f1 < MIN_CHAR_FIELD1_OFFICIAL ||
1275 (f1 > MAX_CHAR_FIELD1_OFFICIAL && f1 < MIN_CHAR_FIELD1_PRIVATE) ||
1276 f1 > MAX_CHAR_FIELD1_PRIVATE)
1278 if (f2 < 0x20 || f3 < 0x20)
1281 #ifdef ENABLE_COMPOSITE_CHARS
1282 if (f1 + FIELD1_TO_OFFICIAL_LEADING_BYTE == LEADING_BYTE_COMPOSITE)
1284 if (UNBOUNDP (Fgethash (make_int (ch),
1285 Vcomposite_char_char2string_hash_table,
1290 #endif /* ENABLE_COMPOSITE_CHARS */
1292 if (f2 != 0x20 && f2 != 0x7F && f3 != 0x20 && f3 != 0x7F)
1295 if (f1 <= MAX_CHAR_FIELD1_OFFICIAL)
1297 CHARSET_BY_LEADING_BYTE (f1 + FIELD1_TO_OFFICIAL_LEADING_BYTE);
1300 CHARSET_BY_LEADING_BYTE (f1 + FIELD1_TO_PRIVATE_LEADING_BYTE);
1302 return (XCHARSET_CHARS (charset) == 96);
1308 /************************************************************************/
1309 /* Basic string functions */
1310 /************************************************************************/
1312 /* Copy the character pointed to by PTR into STR, assuming it's
1313 non-ASCII. Do not call this directly. Use the macro
1314 charptr_copy_char() instead. */
1317 non_ascii_charptr_copy_char (CONST Bufbyte *ptr, Bufbyte *str)
1319 Bufbyte *strptr = str;
1321 switch (REP_BYTES_BY_FIRST_BYTE (*strptr))
1323 /* Notice fallthrough. */
1325 case 6: *++strptr = *ptr++;
1326 case 5: *++strptr = *ptr++;
1328 case 4: *++strptr = *ptr++;
1329 case 3: *++strptr = *ptr++;
1330 case 2: *++strptr = *ptr;
1335 return strptr + 1 - str;
1339 /************************************************************************/
1340 /* streams of Emchars */
1341 /************************************************************************/
1343 /* Treat a stream as a stream of Emchar's rather than a stream of bytes.
1344 The functions below are not meant to be called directly; use
1345 the macros in insdel.h. */
1348 Lstream_get_emchar_1 (Lstream *stream, int ch)
1350 Bufbyte str[MAX_EMCHAR_LEN];
1351 Bufbyte *strptr = str;
1353 str[0] = (Bufbyte) ch;
1354 switch (REP_BYTES_BY_FIRST_BYTE (ch))
1356 /* Notice fallthrough. */
1359 ch = Lstream_getc (stream);
1361 *++strptr = (Bufbyte) ch;
1363 ch = Lstream_getc (stream);
1365 *++strptr = (Bufbyte) ch;
1368 ch = Lstream_getc (stream);
1370 *++strptr = (Bufbyte) ch;
1372 ch = Lstream_getc (stream);
1374 *++strptr = (Bufbyte) ch;
1376 ch = Lstream_getc (stream);
1378 *++strptr = (Bufbyte) ch;
1383 return charptr_emchar (str);
1387 Lstream_fput_emchar (Lstream *stream, Emchar ch)
1389 Bufbyte str[MAX_EMCHAR_LEN];
1390 Bytecount len = set_charptr_emchar (str, ch);
1391 return Lstream_write (stream, str, len);
1395 Lstream_funget_emchar (Lstream *stream, Emchar ch)
1397 Bufbyte str[MAX_EMCHAR_LEN];
1398 Bytecount len = set_charptr_emchar (str, ch);
1399 Lstream_unread (stream, str, len);
1403 /************************************************************************/
1404 /* charset object */
1405 /************************************************************************/
1408 mark_charset (Lisp_Object obj, void (*markobj) (Lisp_Object))
1410 struct Lisp_Charset *cs = XCHARSET (obj);
1412 markobj (cs->short_name);
1413 markobj (cs->long_name);
1414 markobj (cs->doc_string);
1415 markobj (cs->registry);
1416 markobj (cs->ccl_program);
1421 print_charset (Lisp_Object obj, Lisp_Object printcharfun, int escapeflag)
1423 struct Lisp_Charset *cs = XCHARSET (obj);
1427 error ("printing unreadable object #<charset %s 0x%x>",
1428 string_data (XSYMBOL (CHARSET_NAME (cs))->name),
1431 write_c_string ("#<charset ", printcharfun);
1432 print_internal (CHARSET_NAME (cs), printcharfun, 0);
1433 write_c_string (" ", printcharfun);
1434 print_internal (CHARSET_SHORT_NAME (cs), printcharfun, 1);
1435 write_c_string (" ", printcharfun);
1436 print_internal (CHARSET_LONG_NAME (cs), printcharfun, 1);
1437 write_c_string (" ", printcharfun);
1438 print_internal (CHARSET_DOC_STRING (cs), printcharfun, 1);
1439 sprintf (buf, " %s %s cols=%d g%d final='%c' reg=",
1440 CHARSET_TYPE (cs) == CHARSET_TYPE_94 ? "94" :
1441 CHARSET_TYPE (cs) == CHARSET_TYPE_96 ? "96" :
1442 CHARSET_TYPE (cs) == CHARSET_TYPE_94X94 ? "94x94" :
1444 CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? "l2r" : "r2l",
1445 CHARSET_COLUMNS (cs),
1446 CHARSET_GRAPHIC (cs),
1447 CHARSET_FINAL (cs));
1448 write_c_string (buf, printcharfun);
1449 print_internal (CHARSET_REGISTRY (cs), printcharfun, 0);
1450 sprintf (buf, " 0x%x>", cs->header.uid);
1451 write_c_string (buf, printcharfun);
1454 static const struct lrecord_description charset_description[] = {
1455 { XD_LISP_OBJECT, offsetof(struct Lisp_Charset, name), 7 },
1459 DEFINE_LRECORD_IMPLEMENTATION ("charset", charset,
1460 mark_charset, print_charset, 0, 0, 0,
1461 charset_description,
1462 struct Lisp_Charset);
1463 /* Make a new charset. */
1466 make_charset (Charset_ID id, Lisp_Object name,
1467 unsigned char type, unsigned char columns, unsigned char graphic,
1468 Bufbyte final, unsigned char direction, Lisp_Object short_name,
1469 Lisp_Object long_name, Lisp_Object doc,
1471 Emchar* decoding_table,
1472 Emchar ucs_min, Emchar ucs_max, Emchar code_offset)
1475 struct Lisp_Charset *cs =
1476 alloc_lcrecord_type (struct Lisp_Charset, &lrecord_charset);
1477 XSETCHARSET (obj, cs);
1479 CHARSET_ID (cs) = id;
1480 CHARSET_NAME (cs) = name;
1481 CHARSET_SHORT_NAME (cs) = short_name;
1482 CHARSET_LONG_NAME (cs) = long_name;
1483 CHARSET_DIRECTION (cs) = direction;
1484 CHARSET_TYPE (cs) = type;
1485 CHARSET_COLUMNS (cs) = columns;
1486 CHARSET_GRAPHIC (cs) = graphic;
1487 CHARSET_FINAL (cs) = final;
1488 CHARSET_DOC_STRING (cs) = doc;
1489 CHARSET_REGISTRY (cs) = reg;
1490 CHARSET_CCL_PROGRAM (cs) = Qnil;
1491 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil;
1493 CHARSET_DECODING_TABLE(cs) = decoding_table;
1494 CHARSET_UCS_MIN(cs) = ucs_min;
1495 CHARSET_UCS_MAX(cs) = ucs_max;
1496 CHARSET_CODE_OFFSET(cs) = code_offset;
1499 switch ( CHARSET_TYPE (cs) )
1501 case CHARSET_TYPE_94:
1502 CHARSET_DIMENSION (cs) = 1;
1503 CHARSET_CHARS (cs) = 94;
1505 if (decoding_table != NULL)
1508 CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
1509 for (i = 0; i < 94; i++)
1511 Emchar c = decoding_table[i];
1514 put_byte_from_character_table (c, i + 33,
1515 CHARSET_TO_BYTE1_TABLE(cs));
1519 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1520 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1523 case CHARSET_TYPE_96:
1524 CHARSET_DIMENSION (cs) = 1;
1525 CHARSET_CHARS (cs) = 96;
1527 if (decoding_table != NULL)
1530 CHARSET_TO_BYTE1_TABLE(cs) = make_byte_from_character_table();
1531 for (i = 0; i < 96; i++)
1533 Emchar c = decoding_table[i];
1536 put_byte_from_character_table (c, i + 32,
1537 CHARSET_TO_BYTE1_TABLE(cs));
1541 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1542 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1545 case CHARSET_TYPE_94X94:
1546 CHARSET_DIMENSION (cs) = 2;
1547 CHARSET_CHARS (cs) = 94;
1549 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1550 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1553 case CHARSET_TYPE_96X96:
1554 CHARSET_DIMENSION (cs) = 2;
1555 CHARSET_CHARS (cs) = 96;
1557 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1558 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1562 case CHARSET_TYPE_128X128:
1563 CHARSET_DIMENSION (cs) = 2;
1564 CHARSET_CHARS (cs) = 128;
1566 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1567 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1570 case CHARSET_TYPE_256X256:
1571 CHARSET_DIMENSION (cs) = 2;
1572 CHARSET_CHARS (cs) = 256;
1574 CHARSET_TO_BYTE1_TABLE(cs) = NULL;
1575 CHARSET_TO_BYTE2_TABLE(cs) = NULL;
1582 if (id == LEADING_BYTE_ASCII)
1583 CHARSET_REP_BYTES (cs) = 1;
1585 CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 1;
1587 CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 2;
1592 /* some charsets do not have final characters. This includes
1593 ASCII, Control-1, Composite, and the two faux private
1596 assert (NILP (charset_by_attributes[type][final]));
1597 charset_by_attributes[type][final] = obj;
1599 assert (NILP (charset_by_attributes[type][final][direction]));
1600 charset_by_attributes[type][final][direction] = obj;
1604 assert (NILP (charset_by_leading_byte[id - MIN_LEADING_BYTE]));
1605 charset_by_leading_byte[id - MIN_LEADING_BYTE] = obj;
1608 /* official leading byte */
1609 rep_bytes_by_first_byte[id] = CHARSET_REP_BYTES (cs);
1612 /* Some charsets are "faux" and don't have names or really exist at
1613 all except in the leading-byte table. */
1615 Fputhash (name, obj, Vcharset_hash_table);
1620 get_unallocated_leading_byte (int dimension)
1626 if (next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1)
1629 lb = next_allocated_1_byte_leading_byte++;
1633 if (next_allocated_2_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_2)
1636 lb = next_allocated_2_byte_leading_byte++;
1641 ("No more character sets free for this dimension",
1642 make_int (dimension));
1649 charset_get_byte1 (Lisp_Object charset, Emchar ch)
1651 Emchar_to_byte_table* table;
1654 if ((table = XCHARSET_TO_BYTE1_TABLE (charset)) != NULL)
1655 return get_byte_from_character_table (ch, table);
1656 else if ((CHARSET_UCS_MIN (XCHARSET (charset)) <= ch)
1657 && (ch <= CHARSET_UCS_MAX (XCHARSET (charset))))
1658 return ch - CHARSET_UCS_MIN (XCHARSET (charset))
1659 + CHARSET_CODE_OFFSET (XCHARSET (charset));
1660 else if (XCHARSET_DIMENSION (charset) == 1)
1662 if (XCHARSET_CHARS (charset) == 94)
1664 if (((d = ch - (MIN_CHAR_94
1665 + (XCHARSET_FINAL (charset) - '0') * 94)) >= 0)
1669 else if (XCHARSET_CHARS (charset) == 96)
1671 if (((d = ch - (MIN_CHAR_96
1672 + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0)
1679 else if (XCHARSET_DIMENSION (charset) == 2)
1681 if (XCHARSET_CHARS (charset) == 94)
1683 if (((d = ch - (MIN_CHAR_94x94
1684 + (XCHARSET_FINAL (charset) - '0') * 94 * 94)) >= 0)
1686 return (d / 94) + 33;
1688 else if (XCHARSET_CHARS (charset) == 96)
1690 if (((d = ch - (MIN_CHAR_96x96
1691 + (XCHARSET_FINAL (charset) - '0') * 96 * 96)) >= 0)
1693 return (d / 96) + 32;
1700 charset_get_byte2 (Lisp_Object charset, Emchar ch)
1702 if (XCHARSET_DIMENSION (charset) == 1)
1706 Emchar_to_byte_table* table;
1708 if ((table = XCHARSET_TO_BYTE2_TABLE (charset)) != NULL)
1709 return get_byte_from_character_table (ch, table);
1710 else if (EQ (charset, Vcharset_ucs_bmp))
1711 return (ch >> 8) & 0xff;
1712 else if (XCHARSET_CHARS (charset) == 94)
1713 return (MIN_CHAR_94x94
1714 + (XCHARSET_FINAL (charset) - '0') * 94 * 94 <= ch)
1715 && (ch < MIN_CHAR_94x94
1716 + (XCHARSET_FINAL (charset) - '0' + 1) * 94 * 94) ?
1717 ((ch - MIN_CHAR_94x94) % 94) + 33 : 0;
1718 else /* if (XCHARSET_CHARS (charset) == 96) */
1719 return (MIN_CHAR_96x96
1720 + (XCHARSET_FINAL (charset) - '0') * 96 * 96 <= ch)
1721 && (ch < MIN_CHAR_96x96
1722 + (XCHARSET_FINAL (charset) - '0' + 1) * 96 * 96) ?
1723 ((ch - MIN_CHAR_96x96) % 96) + 32 : 0;
1727 Lisp_Object Vdefault_coded_charset_priority_list;
1731 /************************************************************************/
1732 /* Basic charset Lisp functions */
1733 /************************************************************************/
1735 DEFUN ("charsetp", Fcharsetp, 1, 1, 0, /*
1736 Return non-nil if OBJECT is a charset.
1740 return CHARSETP (object) ? Qt : Qnil;
1743 DEFUN ("find-charset", Ffind_charset, 1, 1, 0, /*
1744 Retrieve the charset of the given name.
1745 If CHARSET-OR-NAME is a charset object, it is simply returned.
1746 Otherwise, CHARSET-OR-NAME should be a symbol. If there is no such charset,
1747 nil is returned. Otherwise the associated charset object is returned.
1751 if (CHARSETP (charset_or_name))
1752 return charset_or_name;
1754 CHECK_SYMBOL (charset_or_name);
1755 return Fgethash (charset_or_name, Vcharset_hash_table, Qnil);
1758 DEFUN ("get-charset", Fget_charset, 1, 1, 0, /*
1759 Retrieve the charset of the given name.
1760 Same as `find-charset' except an error is signalled if there is no such
1761 charset instead of returning nil.
1765 Lisp_Object charset = Ffind_charset (name);
1768 signal_simple_error ("No such charset", name);
1772 /* We store the charsets in hash tables with the names as the key and the
1773 actual charset object as the value. Occasionally we need to use them
1774 in a list format. These routines provide us with that. */
1775 struct charset_list_closure
1777 Lisp_Object *charset_list;
1781 add_charset_to_list_mapper (Lisp_Object key, Lisp_Object value,
1782 void *charset_list_closure)
1784 /* This function can GC */
1785 struct charset_list_closure *chcl =
1786 (struct charset_list_closure*) charset_list_closure;
1787 Lisp_Object *charset_list = chcl->charset_list;
1789 *charset_list = Fcons (XCHARSET_NAME (value), *charset_list);
1793 DEFUN ("charset-list", Fcharset_list, 0, 0, 0, /*
1794 Return a list of the names of all defined charsets.
1798 Lisp_Object charset_list = Qnil;
1799 struct gcpro gcpro1;
1800 struct charset_list_closure charset_list_closure;
1802 GCPRO1 (charset_list);
1803 charset_list_closure.charset_list = &charset_list;
1804 elisp_maphash (add_charset_to_list_mapper, Vcharset_hash_table,
1805 &charset_list_closure);
1808 return charset_list;
1811 DEFUN ("charset-name", Fcharset_name, 1, 1, 0, /*
1812 Return the name of the given charset.
1816 return XCHARSET_NAME (Fget_charset (charset));
1819 DEFUN ("make-charset", Fmake_charset, 3, 3, 0, /*
1820 Define a new character set.
1821 This function is for use with Mule support.
1822 NAME is a symbol, the name by which the character set is normally referred.
1823 DOC-STRING is a string describing the character set.
1824 PROPS is a property list, describing the specific nature of the
1825 character set. Recognized properties are:
1827 'short-name Short version of the charset name (ex: Latin-1)
1828 'long-name Long version of the charset name (ex: ISO8859-1 (Latin-1))
1829 'registry A regular expression matching the font registry field for
1831 'dimension Number of octets used to index a character in this charset.
1832 Either 1 or 2. Defaults to 1.
1833 'columns Number of columns used to display a character in this charset.
1834 Only used in TTY mode. (Under X, the actual width of a
1835 character can be derived from the font used to display the
1836 characters.) If unspecified, defaults to the dimension
1837 (this is almost always the correct value).
1838 'chars Number of characters in each dimension (94 or 96).
1839 Defaults to 94. Note that if the dimension is 2, the
1840 character set thus described is 94x94 or 96x96.
1841 'final Final byte of ISO 2022 escape sequence. Must be
1842 supplied. Each combination of (DIMENSION, CHARS) defines a
1843 separate namespace for final bytes. Note that ISO
1844 2022 restricts the final byte to the range
1845 0x30 - 0x7E if dimension == 1, and 0x30 - 0x5F if
1846 dimension == 2. Note also that final bytes in the range
1847 0x30 - 0x3F are reserved for user-defined (not official)
1849 'graphic 0 (use left half of font on output) or 1 (use right half
1850 of font on output). Defaults to 0. For example, for
1851 a font whose registry is ISO8859-1, the left half
1852 (octets 0x20 - 0x7F) is the `ascii' character set, while
1853 the right half (octets 0xA0 - 0xFF) is the `latin-1'
1854 character set. With 'graphic set to 0, the octets
1855 will have their high bit cleared; with it set to 1,
1856 the octets will have their high bit set.
1857 'direction 'l2r (left-to-right) or 'r2l (right-to-left).
1859 'ccl-program A compiled CCL program used to convert a character in
1860 this charset into an index into the font. This is in
1861 addition to the 'graphic property. The CCL program
1862 is passed the octets of the character, with the high
1863 bit cleared and set depending upon whether the value
1864 of the 'graphic property is 0 or 1.
1866 (name, doc_string, props))
1868 int id, dimension = 1, chars = 94, graphic = 0, final = 0, columns = -1;
1869 int direction = CHARSET_LEFT_TO_RIGHT;
1871 Lisp_Object registry = Qnil;
1872 Lisp_Object charset;
1873 Lisp_Object rest, keyword, value;
1874 Lisp_Object ccl_program = Qnil;
1875 Lisp_Object short_name = Qnil, long_name = Qnil;
1877 CHECK_SYMBOL (name);
1878 if (!NILP (doc_string))
1879 CHECK_STRING (doc_string);
1881 charset = Ffind_charset (name);
1882 if (!NILP (charset))
1883 signal_simple_error ("Cannot redefine existing charset", name);
1885 EXTERNAL_PROPERTY_LIST_LOOP (rest, keyword, value, props)
1887 if (EQ (keyword, Qshort_name))
1889 CHECK_STRING (value);
1893 if (EQ (keyword, Qlong_name))
1895 CHECK_STRING (value);
1899 else if (EQ (keyword, Qdimension))
1902 dimension = XINT (value);
1903 if (dimension < 1 || dimension > 2)
1904 signal_simple_error ("Invalid value for 'dimension", value);
1907 else if (EQ (keyword, Qchars))
1910 chars = XINT (value);
1911 if (chars != 94 && chars != 96)
1912 signal_simple_error ("Invalid value for 'chars", value);
1915 else if (EQ (keyword, Qcolumns))
1918 columns = XINT (value);
1919 if (columns != 1 && columns != 2)
1920 signal_simple_error ("Invalid value for 'columns", value);
1923 else if (EQ (keyword, Qgraphic))
1926 graphic = XINT (value);
1927 if (graphic < 0 || graphic > 1)
1928 signal_simple_error ("Invalid value for 'graphic", value);
1931 else if (EQ (keyword, Qregistry))
1933 CHECK_STRING (value);
1937 else if (EQ (keyword, Qdirection))
1939 if (EQ (value, Ql2r))
1940 direction = CHARSET_LEFT_TO_RIGHT;
1941 else if (EQ (value, Qr2l))
1942 direction = CHARSET_RIGHT_TO_LEFT;
1944 signal_simple_error ("Invalid value for 'direction", value);
1947 else if (EQ (keyword, Qfinal))
1949 CHECK_CHAR_COERCE_INT (value);
1950 final = XCHAR (value);
1951 if (final < '0' || final > '~')
1952 signal_simple_error ("Invalid value for 'final", value);
1955 else if (EQ (keyword, Qccl_program))
1957 CHECK_VECTOR (value);
1958 ccl_program = value;
1962 signal_simple_error ("Unrecognized property", keyword);
1966 error ("'final must be specified");
1967 if (dimension == 2 && final > 0x5F)
1969 ("Final must be in the range 0x30 - 0x5F for dimension == 2",
1973 type = (chars == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96;
1975 type = (chars == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96;
1977 if (!NILP (CHARSET_BY_ATTRIBUTES (type, final, CHARSET_LEFT_TO_RIGHT)) ||
1978 !NILP (CHARSET_BY_ATTRIBUTES (type, final, CHARSET_RIGHT_TO_LEFT)))
1980 ("Character set already defined for this DIMENSION/CHARS/FINAL combo");
1987 /* id = CHARSET_ID_OFFSET_94 + final; */
1988 id = get_unallocated_leading_byte (dimension);
1990 else if (chars == 96)
1992 id = get_unallocated_leading_byte (dimension);
1999 else if (dimension == 2)
2003 id = get_unallocated_leading_byte (dimension);
2005 else if (chars == 96)
2007 id = get_unallocated_leading_byte (dimension);
2019 id = get_unallocated_leading_byte (dimension);
2022 if (NILP (doc_string))
2023 doc_string = build_string ("");
2025 if (NILP (registry))
2026 registry = build_string ("");
2028 if (NILP (short_name))
2029 XSETSTRING (short_name, XSYMBOL (name)->name);
2031 if (NILP (long_name))
2032 long_name = doc_string;
2035 columns = dimension;
2036 charset = make_charset (id, name, type, columns, graphic,
2037 final, direction, short_name, long_name,
2038 doc_string, registry,
2040 if (!NILP (ccl_program))
2041 XCHARSET_CCL_PROGRAM (charset) = ccl_program;
2045 DEFUN ("make-reverse-direction-charset", Fmake_reverse_direction_charset,
2047 Make a charset equivalent to CHARSET but which goes in the opposite direction.
2048 NEW-NAME is the name of the new charset. Return the new charset.
2050 (charset, new_name))
2052 Lisp_Object new_charset = Qnil;
2053 int id, dimension, columns, graphic, final;
2054 int direction, type;
2055 Lisp_Object registry, doc_string, short_name, long_name;
2056 struct Lisp_Charset *cs;
2058 charset = Fget_charset (charset);
2059 if (!NILP (XCHARSET_REVERSE_DIRECTION_CHARSET (charset)))
2060 signal_simple_error ("Charset already has reverse-direction charset",
2063 CHECK_SYMBOL (new_name);
2064 if (!NILP (Ffind_charset (new_name)))
2065 signal_simple_error ("Cannot redefine existing charset", new_name);
2067 cs = XCHARSET (charset);
2069 type = CHARSET_TYPE (cs);
2070 columns = CHARSET_COLUMNS (cs);
2071 dimension = CHARSET_DIMENSION (cs);
2072 id = get_unallocated_leading_byte (dimension);
2074 graphic = CHARSET_GRAPHIC (cs);
2075 final = CHARSET_FINAL (cs);
2076 direction = CHARSET_RIGHT_TO_LEFT;
2077 if (CHARSET_DIRECTION (cs) == CHARSET_RIGHT_TO_LEFT)
2078 direction = CHARSET_LEFT_TO_RIGHT;
2079 doc_string = CHARSET_DOC_STRING (cs);
2080 short_name = CHARSET_SHORT_NAME (cs);
2081 long_name = CHARSET_LONG_NAME (cs);
2082 registry = CHARSET_REGISTRY (cs);
2084 new_charset = make_charset (id, new_name, type, columns,
2085 graphic, final, direction, short_name, long_name,
2086 doc_string, registry,
2087 CHARSET_DECODING_TABLE(cs),
2088 CHARSET_UCS_MIN(cs),
2089 CHARSET_UCS_MAX(cs),
2090 CHARSET_CODE_OFFSET(cs));
2092 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset;
2093 XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset;
2098 /* #### Reverse direction charsets not yet implemented. */
2100 DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset,
2102 Return the reverse-direction charset parallel to CHARSET, if any.
2103 This is the charset with the same properties (in particular, the same
2104 dimension, number of characters per dimension, and final byte) as
2105 CHARSET but whose characters are displayed in the opposite direction.
2109 charset = Fget_charset (charset);
2110 return XCHARSET_REVERSE_DIRECTION_CHARSET (charset);
2114 DEFUN ("charset-from-attributes", Fcharset_from_attributes, 3, 4, 0, /*
2115 Return a charset with the given DIMENSION, CHARS, FINAL, and DIRECTION.
2116 If DIRECTION is omitted, both directions will be checked (left-to-right
2117 will be returned if character sets exist for both directions).
2119 (dimension, chars, final, direction))
2121 int dm, ch, fi, di = -1;
2123 Lisp_Object obj = Qnil;
2125 CHECK_INT (dimension);
2126 dm = XINT (dimension);
2127 if (dm < 1 || dm > 2)
2128 signal_simple_error ("Invalid value for DIMENSION", dimension);
2132 if (ch != 94 && ch != 96)
2133 signal_simple_error ("Invalid value for CHARS", chars);
2135 CHECK_CHAR_COERCE_INT (final);
2137 if (fi < '0' || fi > '~')
2138 signal_simple_error ("Invalid value for FINAL", final);
2140 if (EQ (direction, Ql2r))
2141 di = CHARSET_LEFT_TO_RIGHT;
2142 else if (EQ (direction, Qr2l))
2143 di = CHARSET_RIGHT_TO_LEFT;
2144 else if (!NILP (direction))
2145 signal_simple_error ("Invalid value for DIRECTION", direction);
2147 if (dm == 2 && fi > 0x5F)
2149 ("Final must be in the range 0x30 - 0x5F for dimension == 2", final);
2152 type = (ch == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96;
2154 type = (ch == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96;
2158 obj = CHARSET_BY_ATTRIBUTES (type, fi, CHARSET_LEFT_TO_RIGHT);
2160 obj = CHARSET_BY_ATTRIBUTES (type, fi, CHARSET_RIGHT_TO_LEFT);
2163 obj = CHARSET_BY_ATTRIBUTES (type, fi, di);
2166 return XCHARSET_NAME (obj);
2170 DEFUN ("charset-short-name", Fcharset_short_name, 1, 1, 0, /*
2171 Return short name of CHARSET.
2175 return XCHARSET_SHORT_NAME (Fget_charset (charset));
2178 DEFUN ("charset-long-name", Fcharset_long_name, 1, 1, 0, /*
2179 Return long name of CHARSET.
2183 return XCHARSET_LONG_NAME (Fget_charset (charset));
2186 DEFUN ("charset-description", Fcharset_description, 1, 1, 0, /*
2187 Return description of CHARSET.
2191 return XCHARSET_DOC_STRING (Fget_charset (charset));
2194 DEFUN ("charset-dimension", Fcharset_dimension, 1, 1, 0, /*
2195 Return dimension of CHARSET.
2199 return make_int (XCHARSET_DIMENSION (Fget_charset (charset)));
2202 DEFUN ("charset-property", Fcharset_property, 2, 2, 0, /*
2203 Return property PROP of CHARSET.
2204 Recognized properties are those listed in `make-charset', as well as
2205 'name and 'doc-string.
2209 struct Lisp_Charset *cs;
2211 charset = Fget_charset (charset);
2212 cs = XCHARSET (charset);
2214 CHECK_SYMBOL (prop);
2215 if (EQ (prop, Qname)) return CHARSET_NAME (cs);
2216 if (EQ (prop, Qshort_name)) return CHARSET_SHORT_NAME (cs);
2217 if (EQ (prop, Qlong_name)) return CHARSET_LONG_NAME (cs);
2218 if (EQ (prop, Qdoc_string)) return CHARSET_DOC_STRING (cs);
2219 if (EQ (prop, Qdimension)) return make_int (CHARSET_DIMENSION (cs));
2220 if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs));
2221 if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs));
2222 if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs));
2223 if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs));
2224 if (EQ (prop, Qregistry)) return CHARSET_REGISTRY (cs);
2225 if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs);
2226 if (EQ (prop, Qdirection))
2227 return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l;
2228 if (EQ (prop, Qreverse_direction_charset))
2230 Lisp_Object obj = CHARSET_REVERSE_DIRECTION_CHARSET (cs);
2234 return XCHARSET_NAME (obj);
2236 signal_simple_error ("Unrecognized charset property name", prop);
2237 return Qnil; /* not reached */
2240 DEFUN ("charset-id", Fcharset_id, 1, 1, 0, /*
2241 Return charset identification number of CHARSET.
2245 return make_int(XCHARSET_LEADING_BYTE (Fget_charset (charset)));
2248 /* #### We need to figure out which properties we really want to
2251 DEFUN ("set-charset-ccl-program", Fset_charset_ccl_program, 2, 2, 0, /*
2252 Set the 'ccl-program property of CHARSET to CCL-PROGRAM.
2254 (charset, ccl_program))
2256 charset = Fget_charset (charset);
2257 CHECK_VECTOR (ccl_program);
2258 XCHARSET_CCL_PROGRAM (charset) = ccl_program;
2263 invalidate_charset_font_caches (Lisp_Object charset)
2265 /* Invalidate font cache entries for charset on all devices. */
2266 Lisp_Object devcons, concons, hash_table;
2267 DEVICE_LOOP_NO_BREAK (devcons, concons)
2269 struct device *d = XDEVICE (XCAR (devcons));
2270 hash_table = Fgethash (charset, d->charset_font_cache, Qunbound);
2271 if (!UNBOUNDP (hash_table))
2272 Fclrhash (hash_table);
2276 /* Japanese folks may want to (set-charset-registry 'ascii "jisx0201") */
2277 DEFUN ("set-charset-registry", Fset_charset_registry, 2, 2, 0, /*
2278 Set the 'registry property of CHARSET to REGISTRY.
2280 (charset, registry))
2282 charset = Fget_charset (charset);
2283 CHECK_STRING (registry);
2284 XCHARSET_REGISTRY (charset) = registry;
2285 invalidate_charset_font_caches (charset);
2286 face_property_was_changed (Vdefault_face, Qfont, Qglobal);
2291 /************************************************************************/
2292 /* Lisp primitives for working with characters */
2293 /************************************************************************/
2295 DEFUN ("make-char", Fmake_char, 2, 3, 0, /*
2296 Make a character from CHARSET and octets ARG1 and ARG2.
2297 ARG2 is required only for characters from two-dimensional charsets.
2298 For example, (make-char 'latin-iso8859-2 185) will return the Latin 2
2299 character s with caron.
2301 (charset, arg1, arg2))
2303 struct Lisp_Charset *cs;
2305 int lowlim, highlim;
2307 charset = Fget_charset (charset);
2308 cs = XCHARSET (charset);
2310 if (EQ (charset, Vcharset_ascii)) lowlim = 0, highlim = 127;
2311 else if (EQ (charset, Vcharset_control_1)) lowlim = 0, highlim = 31;
2313 else if (CHARSET_CHARS (cs) == 256) lowlim = 0, highlim = 255;
2315 else if (CHARSET_CHARS (cs) == 94) lowlim = 33, highlim = 126;
2316 else /* CHARSET_CHARS (cs) == 96) */ lowlim = 32, highlim = 127;
2319 /* It is useful (and safe, according to Olivier Galibert) to strip
2320 the 8th bit off ARG1 and ARG2 becaue it allows programmers to
2321 write (make-char 'latin-iso8859-2 CODE) where code is the actual
2322 Latin 2 code of the character. */
2330 if (a1 < lowlim || a1 > highlim)
2331 args_out_of_range_3 (arg1, make_int (lowlim), make_int (highlim));
2333 if (CHARSET_DIMENSION (cs) == 1)
2337 ("Charset is of dimension one; second octet must be nil", arg2);
2338 return make_char (MAKE_CHAR (charset, a1, 0));
2347 a2 = XINT (arg2) & 0x7f;
2349 if (a2 < lowlim || a2 > highlim)
2350 args_out_of_range_3 (arg2, make_int (lowlim), make_int (highlim));
2352 return make_char (MAKE_CHAR (charset, a1, a2));
2355 DEFUN ("char-charset", Fchar_charset, 1, 1, 0, /*
2356 Return the character set of char CH.
2360 CHECK_CHAR_COERCE_INT (ch);
2362 return XCHARSET_NAME (CHAR_CHARSET (XCHAR (ch)));
2365 DEFUN ("split-char", Fsplit_char, 1, 1, 0, /*
2366 Return list of charset and one or two position-codes of CHAR.
2370 /* This function can GC */
2371 struct gcpro gcpro1, gcpro2;
2372 Lisp_Object charset = Qnil;
2373 Lisp_Object rc = Qnil;
2376 GCPRO2 (charset, rc);
2377 CHECK_CHAR_COERCE_INT (character);
2379 BREAKUP_CHAR (XCHAR (character), charset, c1, c2);
2381 if (XCHARSET_DIMENSION (Fget_charset (charset)) == 2)
2383 rc = list3 (XCHARSET_NAME (charset), make_int (c1), make_int (c2));
2387 rc = list2 (XCHARSET_NAME (charset), make_int (c1));
2395 #ifdef ENABLE_COMPOSITE_CHARS
2396 /************************************************************************/
2397 /* composite character functions */
2398 /************************************************************************/
2401 lookup_composite_char (Bufbyte *str, int len)
2403 Lisp_Object lispstr = make_string (str, len);
2404 Lisp_Object ch = Fgethash (lispstr,
2405 Vcomposite_char_string2char_hash_table,
2411 if (composite_char_row_next >= 128)
2412 signal_simple_error ("No more composite chars available", lispstr);
2413 emch = MAKE_CHAR (Vcharset_composite, composite_char_row_next,
2414 composite_char_col_next);
2415 Fputhash (make_char (emch), lispstr,
2416 Vcomposite_char_char2string_hash_table);
2417 Fputhash (lispstr, make_char (emch),
2418 Vcomposite_char_string2char_hash_table);
2419 composite_char_col_next++;
2420 if (composite_char_col_next >= 128)
2422 composite_char_col_next = 32;
2423 composite_char_row_next++;
2432 composite_char_string (Emchar ch)
2434 Lisp_Object str = Fgethash (make_char (ch),
2435 Vcomposite_char_char2string_hash_table,
2437 assert (!UNBOUNDP (str));
2441 xxDEFUN ("make-composite-char", Fmake_composite_char, 1, 1, 0, /*
2442 Convert a string into a single composite character.
2443 The character is the result of overstriking all the characters in
2448 CHECK_STRING (string);
2449 return make_char (lookup_composite_char (XSTRING_DATA (string),
2450 XSTRING_LENGTH (string)));
2453 xxDEFUN ("composite-char-string", Fcomposite_char_string, 1, 1, 0, /*
2454 Return a string of the characters comprising a composite character.
2462 if (CHAR_LEADING_BYTE (emch) != LEADING_BYTE_COMPOSITE)
2463 signal_simple_error ("Must be composite char", ch);
2464 return composite_char_string (emch);
2466 #endif /* ENABLE_COMPOSITE_CHARS */
2469 /************************************************************************/
2470 /* initialization */
2471 /************************************************************************/
2474 syms_of_mule_charset (void)
2476 DEFSUBR (Fcharsetp);
2477 DEFSUBR (Ffind_charset);
2478 DEFSUBR (Fget_charset);
2479 DEFSUBR (Fcharset_list);
2480 DEFSUBR (Fcharset_name);
2481 DEFSUBR (Fmake_charset);
2482 DEFSUBR (Fmake_reverse_direction_charset);
2483 /* DEFSUBR (Freverse_direction_charset); */
2484 DEFSUBR (Fcharset_from_attributes);
2485 DEFSUBR (Fcharset_short_name);
2486 DEFSUBR (Fcharset_long_name);
2487 DEFSUBR (Fcharset_description);
2488 DEFSUBR (Fcharset_dimension);
2489 DEFSUBR (Fcharset_property);
2490 DEFSUBR (Fcharset_id);
2491 DEFSUBR (Fset_charset_ccl_program);
2492 DEFSUBR (Fset_charset_registry);
2494 DEFSUBR (Fmake_char);
2495 DEFSUBR (Fchar_charset);
2496 DEFSUBR (Fsplit_char);
2498 #ifdef ENABLE_COMPOSITE_CHARS
2499 DEFSUBR (Fmake_composite_char);
2500 DEFSUBR (Fcomposite_char_string);
2503 defsymbol (&Qcharsetp, "charsetp");
2504 defsymbol (&Qregistry, "registry");
2505 defsymbol (&Qfinal, "final");
2506 defsymbol (&Qgraphic, "graphic");
2507 defsymbol (&Qdirection, "direction");
2508 defsymbol (&Qreverse_direction_charset, "reverse-direction-charset");
2509 defsymbol (&Qshort_name, "short-name");
2510 defsymbol (&Qlong_name, "long-name");
2512 defsymbol (&Ql2r, "l2r");
2513 defsymbol (&Qr2l, "r2l");
2515 /* Charsets, compatible with FSF 20.3
2516 Naming convention is Script-Charset[-Edition] */
2517 defsymbol (&Qascii, "ascii");
2518 defsymbol (&Qcontrol_1, "control-1");
2519 defsymbol (&Qlatin_iso8859_1, "latin-iso8859-1");
2520 defsymbol (&Qlatin_iso8859_2, "latin-iso8859-2");
2521 defsymbol (&Qlatin_iso8859_3, "latin-iso8859-3");
2522 defsymbol (&Qlatin_iso8859_4, "latin-iso8859-4");
2523 defsymbol (&Qthai_tis620, "thai-tis620");
2524 defsymbol (&Qgreek_iso8859_7, "greek-iso8859-7");
2525 defsymbol (&Qarabic_iso8859_6, "arabic-iso8859-6");
2526 defsymbol (&Qhebrew_iso8859_8, "hebrew-iso8859-8");
2527 defsymbol (&Qkatakana_jisx0201, "katakana-jisx0201");
2528 defsymbol (&Qlatin_jisx0201, "latin-jisx0201");
2529 defsymbol (&Qcyrillic_iso8859_5, "cyrillic-iso8859-5");
2530 defsymbol (&Qlatin_iso8859_9, "latin-iso8859-9");
2531 defsymbol (&Qjapanese_jisx0208_1978, "japanese-jisx0208-1978");
2532 defsymbol (&Qchinese_gb2312, "chinese-gb2312");
2533 defsymbol (&Qjapanese_jisx0208, "japanese-jisx0208");
2534 defsymbol (&Qkorean_ksc5601, "korean-ksc5601");
2535 defsymbol (&Qjapanese_jisx0212, "japanese-jisx0212");
2536 defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1");
2537 defsymbol (&Qchinese_cns11643_2, "chinese-cns11643-2");
2539 defsymbol (&Qchinese_cns11643_3, "chinese-cns11643-3");
2540 defsymbol (&Qchinese_cns11643_4, "chinese-cns11643-4");
2541 defsymbol (&Qchinese_cns11643_5, "chinese-cns11643-5");
2542 defsymbol (&Qchinese_cns11643_6, "chinese-cns11643-6");
2543 defsymbol (&Qchinese_cns11643_7, "chinese-cns11643-7");
2544 defsymbol (&Qucs_bmp, "ucs-bmp");
2545 defsymbol (&Qlatin_viscii_lower, "vietnamese-viscii-lower");
2546 defsymbol (&Qlatin_viscii_upper, "vietnamese-viscii-upper");
2548 defsymbol (&Qchinese_big5_1, "chinese-big5-1");
2549 defsymbol (&Qchinese_big5_2, "chinese-big5-2");
2551 defsymbol (&Qcomposite, "composite");
2555 vars_of_mule_charset (void)
2562 /* Table of charsets indexed by leading byte. */
2563 for (i = 0; i < countof (charset_by_leading_byte); i++)
2564 charset_by_leading_byte[i] = Qnil;
2567 /* Table of charsets indexed by type/final-byte. */
2568 for (i = 0; i < countof (charset_by_attributes); i++)
2569 for (j = 0; j < countof (charset_by_attributes[0]); j++)
2570 charset_by_attributes[i][j] = Qnil;
2572 /* Table of charsets indexed by type/final-byte/direction. */
2573 for (i = 0; i < countof (charset_by_attributes); i++)
2574 for (j = 0; j < countof (charset_by_attributes[0]); j++)
2575 for (k = 0; k < countof (charset_by_attributes[0][0]); k++)
2576 charset_by_attributes[i][j][k] = Qnil;
2579 next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1;
2581 next_allocated_2_byte_leading_byte = LEADING_BYTE_CHINESE_BIG5_2 + 1;
2583 next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2;
2587 leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1;
2588 DEFVAR_INT ("leading-code-private-11", &leading_code_private_11 /*
2589 Leading-code of private TYPE9N charset of column-width 1.
2591 leading_code_private_11 = PRE_LEADING_BYTE_PRIVATE_1;
2595 Vutf_2000_version = build_string("0.8 (Kami)");
2596 DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /*
2597 Version number of UTF-2000.
2600 Vdefault_coded_charset_priority_list = Qnil;
2601 DEFVAR_LISP ("default-coded-charset-priority-list",
2602 &Vdefault_coded_charset_priority_list /*
2603 Default order of preferred coded-character-set.
2609 complex_vars_of_mule_charset (void)
2611 staticpro (&Vcharset_hash_table);
2612 Vcharset_hash_table =
2613 make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ);
2615 /* Predefined character sets. We store them into variables for
2620 make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp,
2621 CHARSET_TYPE_256X256, 1, 0, 0,
2622 CHARSET_LEFT_TO_RIGHT,
2623 build_string ("BMP"),
2624 build_string ("BMP"),
2625 build_string ("BMP"),
2627 NULL, 0, 0xFFFF, 0);
2629 # define latin_iso8859_2_to_ucs NULL
2630 # define latin_iso8859_3_to_ucs NULL
2631 # define latin_iso8859_4_to_ucs NULL
2632 # define latin_iso8859_9_to_ucs NULL
2633 # define latin_jisx0201_to_ucs NULL
2634 # define MIN_CHAR_THAI 0
2635 # define MAX_CHAR_THAI 0
2636 # define MIN_CHAR_GREEK 0
2637 # define MAX_CHAR_GREEK 0
2638 # define MIN_CHAR_HEBREW 0
2639 # define MAX_CHAR_HEBREW 0
2640 # define MIN_CHAR_HALFWIDTH_KATAKANA 0
2641 # define MAX_CHAR_HALFWIDTH_KATAKANA 0
2642 # define MIN_CHAR_CYRILLIC 0
2643 # define MAX_CHAR_CYRILLIC 0
2646 make_charset (LEADING_BYTE_ASCII, Qascii,
2647 CHARSET_TYPE_94, 1, 0, 'B',
2648 CHARSET_LEFT_TO_RIGHT,
2649 build_string ("ASCII"),
2650 build_string ("ASCII)"),
2651 build_string ("ASCII (ISO646 IRV)"),
2652 build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"),
2654 Vcharset_control_1 =
2655 make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1,
2656 CHARSET_TYPE_94, 1, 1, 0,
2657 CHARSET_LEFT_TO_RIGHT,
2658 build_string ("C1"),
2659 build_string ("Control characters"),
2660 build_string ("Control characters 128-191"),
2662 NULL, 0x80, 0x9F, 0);
2663 Vcharset_latin_iso8859_1 =
2664 make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1,
2665 CHARSET_TYPE_96, 1, 1, 'A',
2666 CHARSET_LEFT_TO_RIGHT,
2667 build_string ("Latin-1"),
2668 build_string ("ISO8859-1 (Latin-1)"),
2669 build_string ("ISO8859-1 (Latin-1)"),
2670 build_string ("iso8859-1"),
2671 NULL, 0xA0, 0xFF, 32);
2672 Vcharset_latin_iso8859_2 =
2673 make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2,
2674 CHARSET_TYPE_96, 1, 1, 'B',
2675 CHARSET_LEFT_TO_RIGHT,
2676 build_string ("Latin-2"),
2677 build_string ("ISO8859-2 (Latin-2)"),
2678 build_string ("ISO8859-2 (Latin-2)"),
2679 build_string ("iso8859-2"),
2680 latin_iso8859_2_to_ucs, 0, 0, 32);
2681 Vcharset_latin_iso8859_3 =
2682 make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3,
2683 CHARSET_TYPE_96, 1, 1, 'C',
2684 CHARSET_LEFT_TO_RIGHT,
2685 build_string ("Latin-3"),
2686 build_string ("ISO8859-3 (Latin-3)"),
2687 build_string ("ISO8859-3 (Latin-3)"),
2688 build_string ("iso8859-3"),
2689 latin_iso8859_3_to_ucs, 0, 0, 32);
2690 Vcharset_latin_iso8859_4 =
2691 make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4,
2692 CHARSET_TYPE_96, 1, 1, 'D',
2693 CHARSET_LEFT_TO_RIGHT,
2694 build_string ("Latin-4"),
2695 build_string ("ISO8859-4 (Latin-4)"),
2696 build_string ("ISO8859-4 (Latin-4)"),
2697 build_string ("iso8859-4"),
2698 latin_iso8859_4_to_ucs, 0, 0, 32);
2699 Vcharset_thai_tis620 =
2700 make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620,
2701 CHARSET_TYPE_96, 1, 1, 'T',
2702 CHARSET_LEFT_TO_RIGHT,
2703 build_string ("TIS620"),
2704 build_string ("TIS620 (Thai)"),
2705 build_string ("TIS620.2529 (Thai)"),
2706 build_string ("tis620"),
2707 NULL, MIN_CHAR_THAI, MAX_CHAR_THAI, 32);
2708 Vcharset_greek_iso8859_7 =
2709 make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7,
2710 CHARSET_TYPE_96, 1, 1, 'F',
2711 CHARSET_LEFT_TO_RIGHT,
2712 build_string ("ISO8859-7"),
2713 build_string ("ISO8859-7 (Greek)"),
2714 build_string ("ISO8859-7 (Greek)"),
2715 build_string ("iso8859-7"),
2716 NULL, MIN_CHAR_GREEK, MAX_CHAR_GREEK, 32);
2717 Vcharset_arabic_iso8859_6 =
2718 make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6,
2719 CHARSET_TYPE_96, 1, 1, 'G',
2720 CHARSET_RIGHT_TO_LEFT,
2721 build_string ("ISO8859-6"),
2722 build_string ("ISO8859-6 (Arabic)"),
2723 build_string ("ISO8859-6 (Arabic)"),
2724 build_string ("iso8859-6"),
2726 Vcharset_hebrew_iso8859_8 =
2727 make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8,
2728 CHARSET_TYPE_96, 1, 1, 'H',
2729 CHARSET_RIGHT_TO_LEFT,
2730 build_string ("ISO8859-8"),
2731 build_string ("ISO8859-8 (Hebrew)"),
2732 build_string ("ISO8859-8 (Hebrew)"),
2733 build_string ("iso8859-8"),
2734 NULL, MIN_CHAR_HEBREW, MAX_CHAR_HEBREW, 32);
2735 Vcharset_katakana_jisx0201 =
2736 make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201,
2737 CHARSET_TYPE_94, 1, 1, 'I',
2738 CHARSET_LEFT_TO_RIGHT,
2739 build_string ("JISX0201 Kana"),
2740 build_string ("JISX0201.1976 (Japanese Kana)"),
2741 build_string ("JISX0201.1976 Japanese Kana"),
2742 build_string ("jisx0201.1976"),
2744 MIN_CHAR_HALFWIDTH_KATAKANA,
2745 MAX_CHAR_HALFWIDTH_KATAKANA, 33);
2746 Vcharset_latin_jisx0201 =
2747 make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201,
2748 CHARSET_TYPE_94, 1, 0, 'J',
2749 CHARSET_LEFT_TO_RIGHT,
2750 build_string ("JISX0201 Roman"),
2751 build_string ("JISX0201.1976 (Japanese Roman)"),
2752 build_string ("JISX0201.1976 Japanese Roman"),
2753 build_string ("jisx0201.1976"),
2754 latin_jisx0201_to_ucs, 0, 0, 33);
2755 Vcharset_cyrillic_iso8859_5 =
2756 make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5,
2757 CHARSET_TYPE_96, 1, 1, 'L',
2758 CHARSET_LEFT_TO_RIGHT,
2759 build_string ("ISO8859-5"),
2760 build_string ("ISO8859-5 (Cyrillic)"),
2761 build_string ("ISO8859-5 (Cyrillic)"),
2762 build_string ("iso8859-5"),
2763 NULL, MIN_CHAR_CYRILLIC, MAX_CHAR_CYRILLIC, 32);
2764 Vcharset_latin_iso8859_9 =
2765 make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9,
2766 CHARSET_TYPE_96, 1, 1, 'M',
2767 CHARSET_LEFT_TO_RIGHT,
2768 build_string ("Latin-5"),
2769 build_string ("ISO8859-9 (Latin-5)"),
2770 build_string ("ISO8859-9 (Latin-5)"),
2771 build_string ("iso8859-9"),
2772 latin_iso8859_9_to_ucs, 0, 0, 32);
2773 Vcharset_japanese_jisx0208_1978 =
2774 make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978,
2775 CHARSET_TYPE_94X94, 2, 0, '@',
2776 CHARSET_LEFT_TO_RIGHT,
2777 build_string ("JISX0208.1978"),
2778 build_string ("JISX0208.1978 (Japanese)"),
2780 ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"),
2781 build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"),
2783 Vcharset_chinese_gb2312 =
2784 make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312,
2785 CHARSET_TYPE_94X94, 2, 0, 'A',
2786 CHARSET_LEFT_TO_RIGHT,
2787 build_string ("GB2312"),
2788 build_string ("GB2312)"),
2789 build_string ("GB2312 Chinese simplified"),
2790 build_string ("gb2312"),
2792 Vcharset_japanese_jisx0208 =
2793 make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208,
2794 CHARSET_TYPE_94X94, 2, 0, 'B',
2795 CHARSET_LEFT_TO_RIGHT,
2796 build_string ("JISX0208"),
2797 build_string ("JISX0208.1983/1990 (Japanese)"),
2798 build_string ("JISX0208.1983/1990 Japanese Kanji"),
2799 build_string ("jisx0208.19\\(83\\|90\\)"),
2801 Vcharset_korean_ksc5601 =
2802 make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601,
2803 CHARSET_TYPE_94X94, 2, 0, 'C',
2804 CHARSET_LEFT_TO_RIGHT,
2805 build_string ("KSC5601"),
2806 build_string ("KSC5601 (Korean"),
2807 build_string ("KSC5601 Korean Hangul and Hanja"),
2808 build_string ("ksc5601"),
2810 Vcharset_japanese_jisx0212 =
2811 make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212,
2812 CHARSET_TYPE_94X94, 2, 0, 'D',
2813 CHARSET_LEFT_TO_RIGHT,
2814 build_string ("JISX0212"),
2815 build_string ("JISX0212 (Japanese)"),
2816 build_string ("JISX0212 Japanese Supplement"),
2817 build_string ("jisx0212"),
2820 #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
2821 Vcharset_chinese_cns11643_1 =
2822 make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1,
2823 CHARSET_TYPE_94X94, 2, 0, 'G',
2824 CHARSET_LEFT_TO_RIGHT,
2825 build_string ("CNS11643-1"),
2826 build_string ("CNS11643-1 (Chinese traditional)"),
2828 ("CNS 11643 Plane 1 Chinese traditional"),
2829 build_string (CHINESE_CNS_PLANE_RE("1")),
2831 Vcharset_chinese_cns11643_2 =
2832 make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2,
2833 CHARSET_TYPE_94X94, 2, 0, 'H',
2834 CHARSET_LEFT_TO_RIGHT,
2835 build_string ("CNS11643-2"),
2836 build_string ("CNS11643-2 (Chinese traditional)"),
2838 ("CNS 11643 Plane 2 Chinese traditional"),
2839 build_string (CHINESE_CNS_PLANE_RE("2")),
2842 Vcharset_chinese_cns11643_3 =
2843 make_charset (LEADING_BYTE_CHINESE_CNS11643_3, Qchinese_cns11643_3,
2844 CHARSET_TYPE_94X94, 2, 0, 'I',
2845 CHARSET_LEFT_TO_RIGHT,
2846 build_string ("CNS11643-3"),
2847 build_string ("CNS11643-3 (Chinese traditional)"),
2849 ("CNS 11643 Plane 3 Chinese traditional"),
2850 build_string (CHINESE_CNS_PLANE_RE("3")),
2852 Vcharset_chinese_cns11643_4 =
2853 make_charset (LEADING_BYTE_CHINESE_CNS11643_4, Qchinese_cns11643_4,
2854 CHARSET_TYPE_94X94, 2, 0, 'J',
2855 CHARSET_LEFT_TO_RIGHT,
2856 build_string ("CNS11643-4"),
2857 build_string ("CNS11643-4 (Chinese traditional)"),
2859 ("CNS 11643 Plane 4 Chinese traditional"),
2860 build_string (CHINESE_CNS_PLANE_RE("4")),
2862 Vcharset_chinese_cns11643_5 =
2863 make_charset (LEADING_BYTE_CHINESE_CNS11643_5, Qchinese_cns11643_5,
2864 CHARSET_TYPE_94X94, 2, 0, 'K',
2865 CHARSET_LEFT_TO_RIGHT,
2866 build_string ("CNS11643-5"),
2867 build_string ("CNS11643-5 (Chinese traditional)"),
2869 ("CNS 11643 Plane 5 Chinese traditional"),
2870 build_string (CHINESE_CNS_PLANE_RE("5")),
2872 Vcharset_chinese_cns11643_6 =
2873 make_charset (LEADING_BYTE_CHINESE_CNS11643_6, Qchinese_cns11643_6,
2874 CHARSET_TYPE_94X94, 2, 0, 'L',
2875 CHARSET_LEFT_TO_RIGHT,
2876 build_string ("CNS11643-6"),
2877 build_string ("CNS11643-6 (Chinese traditional)"),
2879 ("CNS 11643 Plane 6 Chinese traditional"),
2880 build_string (CHINESE_CNS_PLANE_RE("6")),
2882 Vcharset_chinese_cns11643_7 =
2883 make_charset (LEADING_BYTE_CHINESE_CNS11643_7, Qchinese_cns11643_7,
2884 CHARSET_TYPE_94X94, 2, 0, 'M',
2885 CHARSET_LEFT_TO_RIGHT,
2886 build_string ("CNS11643-7"),
2887 build_string ("CNS11643-7 (Chinese traditional)"),
2889 ("CNS 11643 Plane 7 Chinese traditional"),
2890 build_string (CHINESE_CNS_PLANE_RE("7")),
2892 Vcharset_latin_viscii_lower =
2893 make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower,
2894 CHARSET_TYPE_96, 1, 1, '1',
2895 CHARSET_LEFT_TO_RIGHT,
2896 build_string ("VISCII lower"),
2897 build_string ("VISCII lower (Vietnamese)"),
2898 build_string ("VISCII lower (Vietnamese)"),
2899 build_string ("VISCII1.1"),
2900 latin_viscii_lower_to_ucs, 0, 0, 32);
2901 Vcharset_latin_viscii_upper =
2902 make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper,
2903 CHARSET_TYPE_96, 1, 1, '2',
2904 CHARSET_LEFT_TO_RIGHT,
2905 build_string ("VISCII upper"),
2906 build_string ("VISCII upper (Vietnamese)"),
2907 build_string ("VISCII upper (Vietnamese)"),
2908 build_string ("VISCII1.1"),
2909 latin_viscii_upper_to_ucs, 0, 0, 32);
2911 Vcharset_chinese_big5_1 =
2912 make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1,
2913 CHARSET_TYPE_94X94, 2, 0, '0',
2914 CHARSET_LEFT_TO_RIGHT,
2915 build_string ("Big5"),
2916 build_string ("Big5 (Level-1)"),
2918 ("Big5 Level-1 Chinese traditional"),
2919 build_string ("big5"),
2921 Vcharset_chinese_big5_2 =
2922 make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2,
2923 CHARSET_TYPE_94X94, 2, 0, '1',
2924 CHARSET_LEFT_TO_RIGHT,
2925 build_string ("Big5"),
2926 build_string ("Big5 (Level-2)"),
2928 ("Big5 Level-2 Chinese traditional"),
2929 build_string ("big5"),
2932 #ifdef ENABLE_COMPOSITE_CHARS
2933 /* #### For simplicity, we put composite chars into a 96x96 charset.
2934 This is going to lead to problems because you can run out of
2935 room, esp. as we don't yet recycle numbers. */
2936 Vcharset_composite =
2937 make_charset (LEADING_BYTE_COMPOSITE, Qcomposite,
2938 CHARSET_TYPE_96X96, 2, 0, 0,
2939 CHARSET_LEFT_TO_RIGHT,
2940 build_string ("Composite"),
2941 build_string ("Composite characters"),
2942 build_string ("Composite characters"),
2945 composite_char_row_next = 32;
2946 composite_char_col_next = 32;
2948 Vcomposite_char_string2char_hash_table =
2949 make_lisp_hash_table (500, HASH_TABLE_NON_WEAK, HASH_TABLE_EQUAL);
2950 Vcomposite_char_char2string_hash_table =
2951 make_lisp_hash_table (500, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ);
2952 staticpro (&Vcomposite_char_string2char_hash_table);
2953 staticpro (&Vcomposite_char_char2string_hash_table);
2954 #endif /* ENABLE_COMPOSITE_CHARS */