Mercurial > hg > xemacs-beta
annotate src/mule-charset.c @ 4901:7504864a986c
Don't use Boyer-Moore if repeated octets & case-insensitive search.
2010-01-30 Aidan Kehoe <kehoea@parhasard.net>
* search.c (search_buffer):
Don't use Boyer-Moore for case-insensitive search if the search
pattern contains repeated Ibytes and the corresponding character
has case information (or, equivalently, if one of its case
equivalents would contain repeated Ibytes).
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Sat, 30 Jan 2010 22:25:39 +0000 |
| parents | a98ca4640147 |
| children | 19a72041c5ed |
| rev | line source |
|---|---|
| 428 | 1 /* Functions to handle multilingual characters. |
| 2 Copyright (C) 1992, 1995 Free Software Foundation, Inc. | |
| 3 Copyright (C) 1995 Sun Microsystems, Inc. | |
| 3025 | 4 Copyright (C) 2001, 2002, 2004, 2005 Ben Wing. |
| 428 | 5 |
| 6 This file is part of XEmacs. | |
| 7 | |
| 8 XEmacs is free software; you can redistribute it and/or modify it | |
| 9 under the terms of the GNU General Public License as published by the | |
| 10 Free Software Foundation; either version 2, or (at your option) any | |
| 11 later version. | |
| 12 | |
| 13 XEmacs is distributed in the hope that it will be useful, but WITHOUT | |
| 14 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | |
| 15 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License | |
| 16 for more details. | |
| 17 | |
| 18 You should have received a copy of the GNU General Public License | |
| 19 along with XEmacs; see the file COPYING. If not, write to | |
| 20 the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
| 21 Boston, MA 02111-1307, USA. */ | |
| 22 | |
| 23 /* Synched up with: FSF 20.3. Not in FSF. */ | |
| 24 | |
| 25 /* Rewritten by Ben Wing <ben@xemacs.org>. */ | |
| 26 | |
| 27 #include <config.h> | |
| 28 #include "lisp.h" | |
| 29 | |
| 30 #include "buffer.h" | |
| 31 #include "chartab.h" | |
| 32 #include "elhash.h" | |
| 33 #include "device.h" | |
| 34 #include "faces.h" | |
| 771 | 35 #include "lstream.h" |
| 428 | 36 #include "mule-ccl.h" |
| 872 | 37 #include "objects.h" |
| 3659 | 38 #include "specifier.h" |
| 428 | 39 |
| 40 /* The various pre-defined charsets. */ | |
| 41 | |
| 42 Lisp_Object Vcharset_ascii; | |
| 43 Lisp_Object Vcharset_control_1; | |
| 44 Lisp_Object Vcharset_latin_iso8859_1; | |
| 45 Lisp_Object Vcharset_latin_iso8859_2; | |
| 46 Lisp_Object Vcharset_latin_iso8859_3; | |
| 47 Lisp_Object Vcharset_latin_iso8859_4; | |
| 48 Lisp_Object Vcharset_thai_tis620; | |
| 49 Lisp_Object Vcharset_greek_iso8859_7; | |
|
4805
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
50 Lisp_Object Vcharset_arabic_iso8859_6; |
| 428 | 51 Lisp_Object Vcharset_hebrew_iso8859_8; |
| 52 Lisp_Object Vcharset_katakana_jisx0201; | |
| 53 Lisp_Object Vcharset_latin_jisx0201; | |
| 54 Lisp_Object Vcharset_cyrillic_iso8859_5; | |
| 55 Lisp_Object Vcharset_latin_iso8859_9; | |
| 728 | 56 Lisp_Object Vcharset_latin_iso8859_15; |
| 428 | 57 Lisp_Object Vcharset_japanese_jisx0208_1978; |
| 58 Lisp_Object Vcharset_chinese_gb2312; | |
| 59 Lisp_Object Vcharset_japanese_jisx0208; | |
| 60 Lisp_Object Vcharset_korean_ksc5601; | |
| 61 Lisp_Object Vcharset_japanese_jisx0212; | |
| 62 Lisp_Object Vcharset_chinese_cns11643_1; | |
| 63 Lisp_Object Vcharset_chinese_cns11643_2; | |
| 64 Lisp_Object Vcharset_chinese_big5_1; | |
| 65 Lisp_Object Vcharset_chinese_big5_2; | |
| 66 Lisp_Object Vcharset_composite; | |
| 67 | |
| 68 struct charset_lookup *chlook; | |
| 69 | |
| 1204 | 70 static const struct memory_description charset_lookup_description_1[] = { |
| 771 | 71 { XD_LISP_OBJECT_ARRAY, offsetof (struct charset_lookup, charset_by_leading_byte), NUM_LEADING_BYTES+4*128*2 }, |
| 428 | 72 { XD_END } |
| 73 }; | |
| 74 | |
| 1204 | 75 static const struct sized_memory_description charset_lookup_description = { |
| 440 | 76 sizeof (struct charset_lookup), |
| 428 | 77 charset_lookup_description_1 |
| 78 }; | |
| 79 | |
| 80 Lisp_Object Qcharsetp; | |
| 81 | |
| 3664 | 82 /* Qdoc_string, Qdimension, Qchars, Qfinal defined in general.c */ |
| 83 Lisp_Object Qregistries, Qgraphic, Qregistry; | |
| 428 | 84 Lisp_Object Qdirection; |
| 85 Lisp_Object Qreverse_direction_charset; | |
| 86 Lisp_Object Qshort_name, Qlong_name; | |
| 87 | |
|
4691
3ba90c659d01
Move Qfrom_unicode to general-slots.h, fix the native Win32 build.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4491
diff
changeset
|
88 Lisp_Object Qto_unicode; |
| 771 | 89 |
| 90 Lisp_Object | |
| 428 | 91 Qlatin_iso8859_1, |
| 92 Qlatin_iso8859_2, | |
| 93 Qlatin_iso8859_3, | |
| 94 Qlatin_iso8859_4, | |
| 95 Qthai_tis620, | |
| 96 Qgreek_iso8859_7, | |
|
4805
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
97 Qarabic_iso8859_6, |
| 428 | 98 Qhebrew_iso8859_8, |
| 99 Qkatakana_jisx0201, | |
| 100 Qlatin_jisx0201, | |
| 101 Qcyrillic_iso8859_5, | |
| 102 Qlatin_iso8859_9, | |
| 728 | 103 Qlatin_iso8859_15, |
| 428 | 104 Qjapanese_jisx0208_1978, |
| 105 Qchinese_gb2312, | |
| 106 Qjapanese_jisx0208, | |
| 107 Qkorean_ksc5601, | |
| 108 Qjapanese_jisx0212, | |
| 109 Qchinese_cns11643_1, | |
| 110 Qchinese_cns11643_2, | |
| 111 Qchinese_big5_1, | |
| 112 Qchinese_big5_2, | |
| 113 Qcomposite; | |
| 114 | |
| 115 Lisp_Object Ql2r, Qr2l; | |
| 116 | |
| 117 Lisp_Object Vcharset_hash_table; | |
| 118 | |
| 119 | |
| 120 /************************************************************************/ | |
| 121 /* charset object */ | |
| 122 /************************************************************************/ | |
| 123 | |
| 124 static Lisp_Object | |
| 125 mark_charset (Lisp_Object obj) | |
| 126 { | |
| 440 | 127 Lisp_Charset *cs = XCHARSET (obj); |
| 428 | 128 |
| 129 mark_object (cs->short_name); | |
| 130 mark_object (cs->long_name); | |
| 131 mark_object (cs->doc_string); | |
| 3659 | 132 mark_object (cs->registries); |
| 428 | 133 mark_object (cs->ccl_program); |
| 134 return cs->name; | |
| 135 } | |
| 136 | |
| 137 static void | |
| 2286 | 138 print_charset (Lisp_Object obj, Lisp_Object printcharfun, |
| 139 int UNUSED (escapeflag)) | |
| 428 | 140 { |
| 440 | 141 Lisp_Charset *cs = XCHARSET (obj); |
| 428 | 142 |
| 143 if (print_readably) | |
| 4846 | 144 printing_unreadable_lcrecord |
| 145 (obj, XSTRING_DATA (XSYMBOL (XCHARSET_NAME (obj))->name)); | |
| 428 | 146 |
| 771 | 147 write_fmt_string_lisp (printcharfun, "#<charset %s %S %S %S", 4, |
| 148 CHARSET_NAME (cs), CHARSET_SHORT_NAME (cs), | |
| 149 CHARSET_LONG_NAME (cs), CHARSET_DOC_STRING (cs)); | |
| 150 write_fmt_string (printcharfun, " %s %s cols=%d g%d final='%c' reg=", | |
| 151 CHARSET_TYPE (cs) == CHARSET_TYPE_94 ? "94" : | |
| 152 CHARSET_TYPE (cs) == CHARSET_TYPE_96 ? "96" : | |
| 153 CHARSET_TYPE (cs) == CHARSET_TYPE_94X94 ? "94x94" : | |
| 154 "96x96", | |
| 155 CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? "l2r" : | |
| 156 "r2l", | |
| 157 CHARSET_COLUMNS (cs), | |
| 158 CHARSET_GRAPHIC (cs), | |
| 159 CHARSET_FINAL (cs)); | |
| 3659 | 160 print_internal (CHARSET_REGISTRIES (cs), printcharfun, 0); |
| 771 | 161 write_fmt_string (printcharfun, " 0x%x>", cs->header.uid); |
| 162 } | |
| 163 | |
| 1204 | 164 static const struct memory_description charset_description[] = { |
| 165 { XD_INT, offsetof (Lisp_Charset, dimension) }, | |
| 166 { XD_INT, offsetof (Lisp_Charset, from_unicode_levels) }, | |
| 440 | 167 { XD_LISP_OBJECT, offsetof (Lisp_Charset, name) }, |
| 168 { XD_LISP_OBJECT, offsetof (Lisp_Charset, doc_string) }, | |
| 3659 | 169 { XD_LISP_OBJECT, offsetof (Lisp_Charset, registries) }, |
| 440 | 170 { XD_LISP_OBJECT, offsetof (Lisp_Charset, short_name) }, |
| 171 { XD_LISP_OBJECT, offsetof (Lisp_Charset, long_name) }, | |
| 172 { XD_LISP_OBJECT, offsetof (Lisp_Charset, reverse_direction_charset) }, | |
| 173 { XD_LISP_OBJECT, offsetof (Lisp_Charset, ccl_program) }, | |
| 771 | 174 { XD_UNION, offsetof (Lisp_Charset, to_unicode_table), |
| 2775 | 175 XD_INDIRECT (0, 0), { &to_unicode_description }, XD_FLAG_NO_KKCC }, |
| 771 | 176 { XD_UNION, offsetof (Lisp_Charset, from_unicode_table), |
| 2775 | 177 XD_INDIRECT (1, 0), { &from_unicode_description }, XD_FLAG_NO_KKCC }, |
| 428 | 178 { XD_END } |
| 179 }; | |
| 180 | |
| 934 | 181 DEFINE_LRECORD_IMPLEMENTATION ("charset", charset, |
| 182 1, /* dumpable flag */ | |
| 2367 | 183 mark_charset, print_charset, 0, |
| 934 | 184 0, 0, charset_description, Lisp_Charset); |
| 428 | 185 /* Make a new charset. */ |
| 446 | 186 /* #### SJT Should generic properties be allowed? */ |
| 428 | 187 static Lisp_Object |
| 771 | 188 make_charset (int id, Lisp_Object name, int rep_bytes, |
| 189 int type, int columns, int graphic, | |
| 867 | 190 Ibyte final, int direction, Lisp_Object short_name, |
| 428 | 191 Lisp_Object long_name, Lisp_Object doc, |
| 3439 | 192 Lisp_Object reg, int overwrite, int encode_as_utf_8) |
| 428 | 193 { |
| 194 Lisp_Object obj; | |
| 771 | 195 Lisp_Charset *cs; |
| 196 | |
| 197 if (!overwrite) | |
| 198 { | |
| 3017 | 199 cs = ALLOC_LCRECORD_TYPE (Lisp_Charset, &lrecord_charset); |
| 793 | 200 obj = wrap_charset (cs); |
| 771 | 201 |
| 202 if (final) | |
| 203 { | |
| 204 /* some charsets do not have final characters. This includes | |
| 205 ASCII, Control-1, Composite, and the two faux private | |
| 206 charsets. */ | |
| 207 assert (NILP (chlook-> | |
| 208 charset_by_attributes[type][final][direction])); | |
| 209 chlook->charset_by_attributes[type][final][direction] = obj; | |
| 210 } | |
| 440 | 211 |
| 771 | 212 assert (NILP (chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE])); |
| 213 chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE] = obj; | |
| 214 } | |
| 215 else | |
| 216 { | |
| 217 Lisp_Object ret; | |
| 218 /* Actually overwrite the properties of the existing charset. | |
| 219 We do this because until now charsets could never be "deleted", | |
| 220 so parts of the code don't bother to GC charsets. */ | |
| 221 obj = chlook->charset_by_leading_byte[id - MIN_LEADING_BYTE]; | |
| 222 cs = XCHARSET (obj); | |
| 223 assert (EQ (chlook->charset_by_attributes[type][final][direction], | |
| 224 obj)); | |
| 225 | |
| 226 ret = Fremhash (XCHARSET_NAME (obj), Vcharset_hash_table); | |
| 227 assert (!NILP (ret)); | |
| 228 } | |
| 428 | 229 |
| 230 CHARSET_ID (cs) = id; | |
| 231 CHARSET_NAME (cs) = name; | |
| 232 CHARSET_SHORT_NAME (cs) = short_name; | |
| 233 CHARSET_LONG_NAME (cs) = long_name; | |
| 234 CHARSET_REP_BYTES (cs) = rep_bytes; | |
| 235 CHARSET_DIRECTION (cs) = direction; | |
| 236 CHARSET_TYPE (cs) = type; | |
| 237 CHARSET_COLUMNS (cs) = columns; | |
| 238 CHARSET_GRAPHIC (cs) = graphic; | |
| 239 CHARSET_FINAL (cs) = final; | |
| 240 CHARSET_DOC_STRING (cs) = doc; | |
| 3659 | 241 CHECK_VECTOR(reg); |
| 242 CHARSET_REGISTRIES (cs) = reg; | |
| 3439 | 243 CHARSET_ENCODE_AS_UTF_8 (cs) = encode_as_utf_8 ? 1 : 0; |
| 428 | 244 CHARSET_CCL_PROGRAM (cs) = Qnil; |
| 245 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil; | |
| 246 | |
| 771 | 247 CHARSET_DIMENSION (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 || |
| 248 CHARSET_TYPE (cs) == CHARSET_TYPE_96) ? 1 : 2; | |
| 249 CHARSET_CHARS (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 || | |
| 250 CHARSET_TYPE (cs) == CHARSET_TYPE_94X94) ? 94 : 96; | |
| 428 | 251 |
| 771 | 252 if (id == LEADING_BYTE_ASCII || id == LEADING_BYTE_CONTROL_1 |
| 253 #ifdef ENABLE_COMPOSITE_CHARS | |
| 254 || id == LEADING_BYTE_COMPOSITE | |
| 255 #endif | |
| 256 ) | |
| 257 assert (!overwrite); | |
| 258 else | |
| 428 | 259 { |
| 771 | 260 if (overwrite) |
| 261 free_charset_unicode_tables (obj); | |
| 262 init_charset_unicode_tables (obj); | |
| 428 | 263 } |
| 264 | |
| 265 /* Some charsets are "faux" and don't have names or really exist at | |
| 266 all except in the leading-byte table. */ | |
| 267 if (!NILP (name)) | |
| 771 | 268 { |
| 269 assert (NILP (Fgethash (name, Vcharset_hash_table, Qnil))); | |
| 270 Fputhash (name, obj, Vcharset_hash_table); | |
| 271 } | |
| 272 | |
| 273 recalculate_unicode_precedence (); | |
| 3659 | 274 setup_charset_initial_specifier_tags (obj); |
| 275 | |
| 428 | 276 return obj; |
| 277 } | |
| 278 | |
| 279 static int | |
| 280 get_unallocated_leading_byte (int dimension) | |
| 281 { | |
| 282 int lb; | |
| 283 | |
| 284 if (dimension == 1) | |
| 285 { | |
| 771 | 286 if (chlook->next_allocated_1_byte_leading_byte > |
| 287 MAX_LEADING_BYTE_PRIVATE_1) | |
| 428 | 288 lb = 0; |
| 289 else | |
| 442 | 290 lb = chlook->next_allocated_1_byte_leading_byte++; |
| 428 | 291 } |
| 292 else | |
| 293 { | |
| 1747 | 294 /* awfully fragile, but correct */ |
| 295 #if MAX_LEADING_BYTE_PRIVATE_2 == 255 | |
| 296 if (chlook->next_allocated_2_byte_leading_byte == 0) | |
| 1749 | 297 #else |
| 771 | 298 if (chlook->next_allocated_2_byte_leading_byte > |
| 299 MAX_LEADING_BYTE_PRIVATE_2) | |
| 1747 | 300 #endif |
| 428 | 301 lb = 0; |
| 302 else | |
| 442 | 303 lb = chlook->next_allocated_2_byte_leading_byte++; |
| 428 | 304 } |
| 305 | |
| 306 if (!lb) | |
| 563 | 307 invalid_operation |
| 771 | 308 ("No more character sets free for this dimension", make_int (dimension)); |
| 428 | 309 |
| 310 return lb; | |
| 311 } | |
| 312 | |
| 313 | |
| 314 /************************************************************************/ | |
| 315 /* Basic charset Lisp functions */ | |
| 316 /************************************************************************/ | |
| 317 | |
| 788 | 318 void |
| 319 get_charset_limits (Lisp_Object charset, int *low, int *high) | |
| 320 { | |
| 321 Lisp_Charset *cs = XCHARSET (charset); | |
| 322 | |
| 323 if (EQ (charset, Vcharset_ascii)) *low = 0, *high = 127; | |
| 324 else if (EQ (charset, Vcharset_control_1)) *low = 0, *high = 31; | |
| 325 else if (CHARSET_CHARS (cs) == 94) *low = 33, *high = 126; | |
| 326 else /* CHARSET_CHARS (cs) == 96) */ *low = 32, *high = 127; | |
| 327 } | |
| 328 | |
| 428 | 329 DEFUN ("charsetp", Fcharsetp, 1, 1, 0, /* |
| 330 Return non-nil if OBJECT is a charset. | |
| 331 */ | |
| 332 (object)) | |
| 333 { | |
| 334 return CHARSETP (object) ? Qt : Qnil; | |
| 335 } | |
| 336 | |
| 337 DEFUN ("find-charset", Ffind_charset, 1, 1, 0, /* | |
| 338 Retrieve the charset of the given name. | |
| 339 If CHARSET-OR-NAME is a charset object, it is simply returned. | |
| 340 Otherwise, CHARSET-OR-NAME should be a symbol. If there is no such charset, | |
| 341 nil is returned. Otherwise the associated charset object is returned. | |
| 342 */ | |
| 343 (charset_or_name)) | |
| 344 { | |
| 345 if (CHARSETP (charset_or_name)) | |
| 346 return charset_or_name; | |
| 347 | |
| 348 CHECK_SYMBOL (charset_or_name); | |
| 349 return Fgethash (charset_or_name, Vcharset_hash_table, Qnil); | |
| 350 } | |
| 351 | |
| 352 DEFUN ("get-charset", Fget_charset, 1, 1, 0, /* | |
| 353 Retrieve the charset of the given name. | |
| 354 Same as `find-charset' except an error is signalled if there is no such | |
| 355 charset instead of returning nil. | |
| 356 */ | |
| 357 (name)) | |
| 358 { | |
| 359 Lisp_Object charset = Ffind_charset (name); | |
| 360 | |
| 361 if (NILP (charset)) | |
| 563 | 362 invalid_argument ("No such charset", name); |
| 428 | 363 return charset; |
| 364 } | |
| 365 | |
| 366 /* We store the charsets in hash tables with the names as the key and the | |
| 367 actual charset object as the value. Occasionally we need to use them | |
| 368 in a list format. These routines provide us with that. */ | |
| 369 struct charset_list_closure | |
| 370 { | |
| 371 Lisp_Object *charset_list; | |
| 372 }; | |
| 373 | |
| 374 static int | |
| 2286 | 375 add_charset_to_list_mapper (Lisp_Object UNUSED (key), Lisp_Object value, |
| 428 | 376 void *charset_list_closure) |
| 377 { | |
| 378 /* This function can GC */ | |
| 379 struct charset_list_closure *chcl = | |
| 380 (struct charset_list_closure*) charset_list_closure; | |
| 381 Lisp_Object *charset_list = chcl->charset_list; | |
| 382 | |
| 383 *charset_list = Fcons (XCHARSET_NAME (value), *charset_list); | |
| 384 return 0; | |
| 385 } | |
| 386 | |
| 387 DEFUN ("charset-list", Fcharset_list, 0, 0, 0, /* | |
| 388 Return a list of the names of all defined charsets. | |
| 389 */ | |
| 390 ()) | |
| 391 { | |
| 392 Lisp_Object charset_list = Qnil; | |
| 393 struct gcpro gcpro1; | |
| 394 struct charset_list_closure charset_list_closure; | |
| 395 | |
| 396 GCPRO1 (charset_list); | |
| 397 charset_list_closure.charset_list = &charset_list; | |
| 398 elisp_maphash (add_charset_to_list_mapper, Vcharset_hash_table, | |
| 399 &charset_list_closure); | |
| 400 UNGCPRO; | |
| 401 | |
| 402 return charset_list; | |
| 403 } | |
| 404 | |
| 405 DEFUN ("charset-name", Fcharset_name, 1, 1, 0, /* | |
| 444 | 406 Return the name of charset CHARSET. |
| 428 | 407 */ |
| 408 (charset)) | |
| 409 { | |
| 410 return XCHARSET_NAME (Fget_charset (charset)); | |
| 411 } | |
| 412 | |
| 446 | 413 /* #### SJT Should generic properties be allowed? */ |
| 428 | 414 DEFUN ("make-charset", Fmake_charset, 3, 3, 0, /* |
| 415 Define a new character set. | |
| 416 This function is for use with Mule support. | |
| 417 NAME is a symbol, the name by which the character set is normally referred. | |
| 418 DOC-STRING is a string describing the character set. | |
| 419 PROPS is a property list, describing the specific nature of the | |
| 420 character set. Recognized properties are: | |
| 421 | |
| 3025 | 422 `short-name' Short version of the charset name (ex: Latin-1) |
| 423 `long-name' Long version of the charset name (ex: ISO8859-1 (Latin-1)) | |
| 3659 | 424 `registries' A vector of possible XLFD REGISTRY-ENCODING combinations for |
| 425 this character set. Note that this is not a regular expression. | |
| 3025 | 426 `dimension' Number of octets used to index a character in this charset. |
| 428 | 427 Either 1 or 2. Defaults to 1. |
| 3025 | 428 `columns' Number of columns used to display a character in this charset. |
| 428 | 429 Only used in TTY mode. (Under X, the actual width of a |
| 430 character can be derived from the font used to display the | |
| 431 characters.) If unspecified, defaults to the dimension | |
| 432 (this is almost always the correct value). | |
| 3025 | 433 `chars' Number of characters in each dimension (94 or 96). |
| 428 | 434 Defaults to 94. Note that if the dimension is 2, the |
| 435 character set thus described is 94x94 or 96x96. | |
| 3025 | 436 `final' Final byte of ISO 2022 escape sequence. Must be |
| 428 | 437 supplied. Each combination of (DIMENSION, CHARS) defines a |
| 438 separate namespace for final bytes. Note that ISO | |
| 439 2022 restricts the final byte to the range | |
| 440 0x30 - 0x7E if dimension == 1, and 0x30 - 0x5F if | |
| 441 dimension == 2. Note also that final bytes in the range | |
| 442 0x30 - 0x3F are reserved for user-defined (not official) | |
| 443 character sets. | |
| 3025 | 444 `graphic' 0 (use left half of font on output) or 1 (use right half |
| 428 | 445 of font on output). Defaults to 0. For example, for |
| 446 a font whose registry is ISO8859-1, the left half | |
| 447 (octets 0x20 - 0x7F) is the `ascii' character set, while | |
| 448 the right half (octets 0xA0 - 0xFF) is the `latin-1' | |
| 3025 | 449 character set. With `graphic' set to 0, the octets |
| 428 | 450 will have their high bit cleared; with it set to 1, |
| 451 the octets will have their high bit set. | |
| 3025 | 452 `direction' `l2r' (left-to-right) or `r2l' (right-to-left). |
| 453 Defaults to `l2r'. | |
| 454 `ccl-program' A compiled CCL program used to convert a character in | |
| 428 | 455 this charset into an index into the font. This is in |
| 3025 | 456 addition to the `graphic' property. The CCL program |
| 428 | 457 is passed the octets of the character, with the high |
| 458 bit cleared and set depending upon whether the value | |
| 3025 | 459 of the `graphic' property is 0 or 1. |
| 3439 | 460 `encode-as-utf-8' |
| 461 If non-nil, the charset will be written out using the UTF-8 | |
| 462 escape syntax in ISO 2022-oriented coding systems. Used for | |
| 463 supporting characters we know are part of Unicode but not of | |
| 464 any other known character set in escape-quoted and compound | |
| 465 text. | |
| 428 | 466 */ |
| 467 (name, doc_string, props)) | |
| 468 { | |
| 771 | 469 int id, dimension = 1, chars = 94, graphic = 0, columns = -1; |
| 867 | 470 Ibyte final = 0; |
| 428 | 471 int direction = CHARSET_LEFT_TO_RIGHT; |
| 472 int type; | |
| 3659 | 473 Lisp_Object registries = Qnil; |
| 771 | 474 Lisp_Object charset = Qnil; |
| 428 | 475 Lisp_Object ccl_program = Qnil; |
| 476 Lisp_Object short_name = Qnil, long_name = Qnil; | |
| 3439 | 477 int encode_as_utf_8 = 0; |
| 771 | 478 Lisp_Object existing_charset; |
| 479 int temporary = UNBOUNDP (name); | |
| 428 | 480 |
| 771 | 481 /* NOTE: name == Qunbound is a directive from the iso2022 code to |
| 482 create a temporary charset for an unknown final. We allow the final | |
| 483 to be overwritten with a real charset later on. */ | |
| 484 | |
| 428 | 485 if (!NILP (doc_string)) |
| 486 CHECK_STRING (doc_string); | |
| 771 | 487 if (!UNBOUNDP (name)) |
| 488 { | |
| 489 CHECK_SYMBOL (name); | |
| 428 | 490 |
| 771 | 491 charset = Ffind_charset (name); |
| 492 if (!NILP (charset)) | |
| 493 invalid_operation ("Cannot redefine existing charset", name); | |
| 494 } | |
| 428 | 495 |
| 442 | 496 { |
| 497 EXTERNAL_PROPERTY_LIST_LOOP_3 (keyword, value, props) | |
| 498 { | |
| 499 if (EQ (keyword, Qshort_name)) | |
| 500 { | |
| 501 CHECK_STRING (value); | |
| 502 short_name = value; | |
| 503 } | |
| 428 | 504 |
| 519 | 505 else if (EQ (keyword, Qlong_name)) |
| 442 | 506 { |
| 507 CHECK_STRING (value); | |
| 508 long_name = value; | |
| 509 } | |
| 428 | 510 |
| 442 | 511 else if (EQ (keyword, Qdimension)) |
| 512 { | |
| 513 CHECK_INT (value); | |
| 514 dimension = XINT (value); | |
| 515 if (dimension < 1 || dimension > 2) | |
| 3025 | 516 invalid_constant ("Invalid value for `dimension'", value); |
| 442 | 517 } |
| 428 | 518 |
| 442 | 519 else if (EQ (keyword, Qchars)) |
| 520 { | |
| 521 CHECK_INT (value); | |
| 522 chars = XINT (value); | |
| 523 if (chars != 94 && chars != 96) | |
| 3025 | 524 invalid_constant ("Invalid value for `chars'", value); |
| 442 | 525 } |
| 428 | 526 |
| 442 | 527 else if (EQ (keyword, Qcolumns)) |
| 528 { | |
| 529 CHECK_INT (value); | |
| 530 columns = XINT (value); | |
| 531 if (columns != 1 && columns != 2) | |
| 3025 | 532 invalid_constant ("Invalid value for `columns'", value); |
| 442 | 533 } |
| 428 | 534 |
| 442 | 535 else if (EQ (keyword, Qgraphic)) |
| 536 { | |
| 537 CHECK_INT (value); | |
| 538 graphic = XINT (value); | |
| 539 if (graphic < 0 || graphic > 1) | |
| 3025 | 540 invalid_constant ("Invalid value for `graphic'", value); |
| 442 | 541 } |
| 428 | 542 |
| 3659 | 543 else if (EQ (keyword, Qregistries)) |
| 544 { | |
| 545 CHECK_VECTOR (value); | |
| 546 registries = value; | |
| 547 } | |
| 548 | |
| 442 | 549 else if (EQ (keyword, Qregistry)) |
| 550 { | |
| 3659 | 551 Lisp_Object quoted_registry; |
| 552 | |
| 442 | 553 CHECK_STRING (value); |
| 3659 | 554 quoted_registry = Fregexp_quote(value); |
| 3662 | 555 if (qxestrcmp(XSTRING_DATA(quoted_registry), |
| 3659 | 556 XSTRING_DATA(value))) |
| 557 { | |
| 558 warn_when_safe | |
| 559 (Qregistry, Qwarning, | |
| 560 "Regexps no longer allowed for charset-registry. " | |
| 561 "Treating %s as string", XSTRING_DATA(value)); | |
| 562 } | |
| 563 registries = vector1(value); | |
| 442 | 564 } |
| 428 | 565 |
| 442 | 566 else if (EQ (keyword, Qdirection)) |
| 567 { | |
| 568 if (EQ (value, Ql2r)) | |
| 569 direction = CHARSET_LEFT_TO_RIGHT; | |
| 570 else if (EQ (value, Qr2l)) | |
| 571 direction = CHARSET_RIGHT_TO_LEFT; | |
| 572 else | |
| 3025 | 573 invalid_constant ("Invalid value for `direction'", value); |
| 442 | 574 } |
| 428 | 575 |
| 3439 | 576 else if (EQ (keyword, Qencode_as_utf_8)) |
| 577 { | |
| 578 encode_as_utf_8 = NILP (value) ? 0 : 1; | |
| 579 } | |
| 580 | |
| 442 | 581 else if (EQ (keyword, Qfinal)) |
| 582 { | |
| 583 CHECK_CHAR_COERCE_INT (value); | |
| 584 final = XCHAR (value); | |
| 585 if (final < '0' || final > '~') | |
| 3025 | 586 invalid_constant ("Invalid value for `final'", value); |
| 442 | 587 } |
| 588 else if (EQ (keyword, Qccl_program)) | |
| 589 { | |
|
4745
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
590 /* This errors if VALUE is not a valid CCL program. */ |
|
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
591 ccl_program = get_ccl_program (value); |
| 442 | 592 } |
| 593 else | |
| 563 | 594 invalid_constant ("Unrecognized property", keyword); |
| 442 | 595 } |
| 596 } | |
| 428 | 597 |
| 598 if (!final) | |
| 3025 | 599 invalid_argument ("`final' must be specified", Qunbound); |
| 428 | 600 if (dimension == 2 && final > 0x5F) |
| 563 | 601 invalid_constant |
| 428 | 602 ("Final must be in the range 0x30 - 0x5F for dimension == 2", |
| 603 make_char (final)); | |
| 604 | |
| 605 if (dimension == 1) | |
| 606 type = (chars == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96; | |
| 607 else | |
| 608 type = (chars == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96; | |
| 609 | |
| 826 | 610 existing_charset = charset_by_attributes (type, final, direction); |
| 771 | 611 |
| 612 if (!NILP (existing_charset) && !XCHARSET (existing_charset)->temporary) | |
| 578 | 613 invalid_argument |
| 793 | 614 ("Character set already defined for this DIMENSION/CHARS/FINAL/DIRECTION combo", |
| 771 | 615 existing_charset); |
| 616 | |
| 617 if (!NILP (existing_charset)) | |
| 618 /* Reuse same leading byte */ | |
| 619 id = XCHARSET_ID (existing_charset); | |
| 620 else | |
| 621 id = get_unallocated_leading_byte (dimension); | |
| 428 | 622 |
| 771 | 623 if (temporary) |
| 624 { | |
| 867 | 625 Ibyte tempname[80]; |
| 428 | 626 |
| 771 | 627 qxesprintf (tempname, "___temporary___%d__", id); |
|
4813
6f84332672fb
Change build_string to build_intstring, fixing the Visual C++ build.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4807
diff
changeset
|
628 name = Fmake_symbol (build_intstring (tempname)); /* Uninterned. */ |
| 771 | 629 } |
| 428 | 630 if (NILP (doc_string)) |
| 631 doc_string = build_string (""); | |
| 3659 | 632 if (NILP (registries)) |
| 633 registries = make_vector(0, Qnil); | |
| 428 | 634 if (NILP (short_name)) |
| 793 | 635 short_name = XSYMBOL (name)->name; |
| 428 | 636 if (NILP (long_name)) |
| 637 long_name = doc_string; | |
| 638 if (columns == -1) | |
| 639 columns = dimension; | |
| 771 | 640 |
| 428 | 641 charset = make_charset (id, name, dimension + 2, type, columns, graphic, |
| 771 | 642 final, direction, short_name, long_name, |
| 3659 | 643 doc_string, registries, !NILP (existing_charset), |
| 3439 | 644 encode_as_utf_8); |
| 771 | 645 |
| 646 XCHARSET (charset)->temporary = temporary; | |
| 428 | 647 if (!NILP (ccl_program)) |
| 648 XCHARSET_CCL_PROGRAM (charset) = ccl_program; | |
| 771 | 649 |
| 793 | 650 { |
| 651 Lisp_Object revdircs = | |
| 826 | 652 charset_by_attributes (type, final, |
| 793 | 653 direction == CHARSET_LEFT_TO_RIGHT ? |
| 654 CHARSET_RIGHT_TO_LEFT : CHARSET_LEFT_TO_RIGHT); | |
| 655 if (!NILP (revdircs)) | |
| 656 { | |
| 657 XCHARSET_REVERSE_DIRECTION_CHARSET (revdircs) = charset; | |
| 658 XCHARSET_REVERSE_DIRECTION_CHARSET (charset) = revdircs; | |
| 659 } | |
| 660 } | |
| 661 | |
| 428 | 662 return charset; |
| 663 } | |
| 664 | |
| 665 DEFUN ("make-reverse-direction-charset", Fmake_reverse_direction_charset, | |
| 666 2, 2, 0, /* | |
| 667 Make a charset equivalent to CHARSET but which goes in the opposite direction. | |
| 668 NEW-NAME is the name of the new charset. Return the new charset. | |
| 669 */ | |
| 670 (charset, new_name)) | |
| 671 { | |
| 672 Lisp_Object new_charset = Qnil; | |
| 3439 | 673 int id, dimension, columns, graphic, encode_as_utf_8; |
| 867 | 674 Ibyte final; |
| 428 | 675 int direction, type; |
| 3659 | 676 Lisp_Object registries, doc_string, short_name, long_name; |
| 440 | 677 Lisp_Charset *cs; |
| 428 | 678 |
| 679 charset = Fget_charset (charset); | |
| 680 if (!NILP (XCHARSET_REVERSE_DIRECTION_CHARSET (charset))) | |
| 563 | 681 invalid_operation ("Charset already has reverse-direction charset", |
| 793 | 682 charset); |
| 428 | 683 |
| 684 CHECK_SYMBOL (new_name); | |
| 685 if (!NILP (Ffind_charset (new_name))) | |
| 563 | 686 invalid_operation ("Cannot redefine existing charset", new_name); |
| 428 | 687 |
| 688 cs = XCHARSET (charset); | |
| 689 | |
| 690 type = CHARSET_TYPE (cs); | |
| 691 columns = CHARSET_COLUMNS (cs); | |
| 692 dimension = CHARSET_DIMENSION (cs); | |
| 693 id = get_unallocated_leading_byte (dimension); | |
| 694 | |
| 695 graphic = CHARSET_GRAPHIC (cs); | |
| 696 final = CHARSET_FINAL (cs); | |
| 697 direction = CHARSET_RIGHT_TO_LEFT; | |
| 698 if (CHARSET_DIRECTION (cs) == CHARSET_RIGHT_TO_LEFT) | |
| 699 direction = CHARSET_LEFT_TO_RIGHT; | |
| 700 doc_string = CHARSET_DOC_STRING (cs); | |
| 701 short_name = CHARSET_SHORT_NAME (cs); | |
| 702 long_name = CHARSET_LONG_NAME (cs); | |
| 3659 | 703 registries = CHARSET_REGISTRIES (cs); |
| 3439 | 704 encode_as_utf_8 = CHARSET_ENCODE_AS_UTF_8 (cs); |
| 428 | 705 |
| 706 new_charset = make_charset (id, new_name, dimension + 2, type, columns, | |
| 707 graphic, final, direction, short_name, long_name, | |
| 3659 | 708 doc_string, registries, 0, encode_as_utf_8); |
| 428 | 709 |
| 710 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; | |
| 711 XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; | |
| 712 | |
| 713 return new_charset; | |
| 714 } | |
| 715 | |
| 716 DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset, | |
| 717 1, 1, 0, /* | |
| 718 Return the reverse-direction charset parallel to CHARSET, if any. | |
| 719 This is the charset with the same properties (in particular, the same | |
| 720 dimension, number of characters per dimension, and final byte) as | |
| 721 CHARSET but whose characters are displayed in the opposite direction. | |
| 722 */ | |
| 723 (charset)) | |
| 724 { | |
| 725 charset = Fget_charset (charset); | |
| 726 return XCHARSET_REVERSE_DIRECTION_CHARSET (charset); | |
| 727 } | |
| 728 | |
| 729 DEFUN ("charset-from-attributes", Fcharset_from_attributes, 3, 4, 0, /* | |
| 730 Return a charset with the given DIMENSION, CHARS, FINAL, and DIRECTION. | |
| 731 If DIRECTION is omitted, both directions will be checked (left-to-right | |
| 732 will be returned if character sets exist for both directions). | |
| 733 */ | |
| 734 (dimension, chars, final, direction)) | |
| 735 { | |
| 736 int dm, ch, fi, di = -1; | |
| 737 int type; | |
| 738 Lisp_Object obj = Qnil; | |
| 739 | |
| 740 CHECK_INT (dimension); | |
| 741 dm = XINT (dimension); | |
| 742 if (dm < 1 || dm > 2) | |
| 563 | 743 invalid_constant ("Invalid value for DIMENSION", dimension); |
| 428 | 744 |
| 745 CHECK_INT (chars); | |
| 746 ch = XINT (chars); | |
| 747 if (ch != 94 && ch != 96) | |
| 563 | 748 invalid_constant ("Invalid value for CHARS", chars); |
| 428 | 749 |
| 750 CHECK_CHAR_COERCE_INT (final); | |
| 751 fi = XCHAR (final); | |
| 752 if (fi < '0' || fi > '~') | |
| 563 | 753 invalid_constant ("Invalid value for FINAL", final); |
| 428 | 754 |
| 755 if (EQ (direction, Ql2r)) | |
| 756 di = CHARSET_LEFT_TO_RIGHT; | |
| 757 else if (EQ (direction, Qr2l)) | |
| 758 di = CHARSET_RIGHT_TO_LEFT; | |
| 759 else if (!NILP (direction)) | |
| 563 | 760 invalid_constant ("Invalid value for DIRECTION", direction); |
| 428 | 761 |
| 762 if (dm == 2 && fi > 0x5F) | |
| 563 | 763 invalid_constant |
| 428 | 764 ("Final must be in the range 0x30 - 0x5F for dimension == 2", final); |
| 765 | |
| 766 if (dm == 1) | |
| 767 type = (ch == 94) ? CHARSET_TYPE_94 : CHARSET_TYPE_96; | |
| 768 else | |
| 769 type = (ch == 94) ? CHARSET_TYPE_94X94 : CHARSET_TYPE_96X96; | |
| 770 | |
| 771 if (di == -1) | |
| 772 { | |
| 826 | 773 obj = charset_by_attributes (type, fi, CHARSET_LEFT_TO_RIGHT); |
| 428 | 774 if (NILP (obj)) |
| 826 | 775 obj = charset_by_attributes (type, fi, CHARSET_RIGHT_TO_LEFT); |
| 428 | 776 } |
| 777 else | |
| 826 | 778 obj = charset_by_attributes (type, fi, di); |
| 428 | 779 |
| 780 if (CHARSETP (obj)) | |
| 781 return XCHARSET_NAME (obj); | |
| 782 return obj; | |
| 783 } | |
| 784 | |
| 785 DEFUN ("charset-short-name", Fcharset_short_name, 1, 1, 0, /* | |
| 786 Return short name of CHARSET. | |
| 787 */ | |
| 788 (charset)) | |
| 789 { | |
| 790 return XCHARSET_SHORT_NAME (Fget_charset (charset)); | |
| 791 } | |
| 792 | |
| 793 DEFUN ("charset-long-name", Fcharset_long_name, 1, 1, 0, /* | |
| 794 Return long name of CHARSET. | |
| 795 */ | |
| 796 (charset)) | |
| 797 { | |
| 798 return XCHARSET_LONG_NAME (Fget_charset (charset)); | |
| 799 } | |
| 800 | |
| 801 DEFUN ("charset-description", Fcharset_description, 1, 1, 0, /* | |
| 802 Return description of CHARSET. | |
| 803 */ | |
| 804 (charset)) | |
| 805 { | |
| 806 return XCHARSET_DOC_STRING (Fget_charset (charset)); | |
| 807 } | |
| 808 | |
| 809 DEFUN ("charset-dimension", Fcharset_dimension, 1, 1, 0, /* | |
| 810 Return dimension of CHARSET. | |
| 811 */ | |
| 812 (charset)) | |
| 813 { | |
| 814 return make_int (XCHARSET_DIMENSION (Fget_charset (charset))); | |
| 815 } | |
| 816 | |
| 817 DEFUN ("charset-property", Fcharset_property, 2, 2, 0, /* | |
| 446 | 818 Return property PROP of CHARSET, a charset object or symbol naming a charset. |
| 428 | 819 Recognized properties are those listed in `make-charset', as well as |
| 3025 | 820 `name' and `doc-string'. |
| 428 | 821 */ |
| 822 (charset, prop)) | |
| 823 { | |
| 440 | 824 Lisp_Charset *cs; |
| 428 | 825 |
| 826 charset = Fget_charset (charset); | |
| 827 cs = XCHARSET (charset); | |
| 828 | |
| 829 CHECK_SYMBOL (prop); | |
| 830 if (EQ (prop, Qname)) return CHARSET_NAME (cs); | |
| 831 if (EQ (prop, Qshort_name)) return CHARSET_SHORT_NAME (cs); | |
| 832 if (EQ (prop, Qlong_name)) return CHARSET_LONG_NAME (cs); | |
| 833 if (EQ (prop, Qdoc_string)) return CHARSET_DOC_STRING (cs); | |
| 834 if (EQ (prop, Qdimension)) return make_int (CHARSET_DIMENSION (cs)); | |
| 835 if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs)); | |
| 836 if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs)); | |
| 837 if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs)); | |
| 838 if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs)); | |
| 3659 | 839 if (EQ (prop, Qregistries)) return CHARSET_REGISTRIES (cs); |
| 3439 | 840 if (EQ (prop, Qencode_as_utf_8)) |
| 841 return CHARSET_ENCODE_AS_UTF_8 (cs) ? Qt : Qnil; | |
| 428 | 842 if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs); |
| 843 if (EQ (prop, Qdirection)) | |
| 844 return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l; | |
| 845 if (EQ (prop, Qreverse_direction_charset)) | |
| 846 { | |
| 847 Lisp_Object obj = CHARSET_REVERSE_DIRECTION_CHARSET (cs); | |
| 446 | 848 /* #### Is this translation OK? If so, error checking sufficient? */ |
| 849 return CHARSETP (obj) ? XCHARSET_NAME (obj) : obj; | |
| 428 | 850 } |
| 563 | 851 invalid_constant ("Unrecognized charset property name", prop); |
| 1204 | 852 RETURN_NOT_REACHED (Qnil); |
| 428 | 853 } |
| 854 | |
| 855 DEFUN ("charset-id", Fcharset_id, 1, 1, 0, /* | |
| 856 Return charset identification number of CHARSET. | |
| 857 */ | |
| 858 (charset)) | |
| 859 { | |
| 793 | 860 return make_int (XCHARSET_LEADING_BYTE (Fget_charset (charset))); |
| 428 | 861 } |
| 862 | |
| 863 /* #### We need to figure out which properties we really want to | |
| 864 allow to be set. */ | |
| 865 | |
| 866 DEFUN ("set-charset-ccl-program", Fset_charset_ccl_program, 2, 2, 0, /* | |
| 3025 | 867 Set the `ccl-program' property of CHARSET to CCL-PROGRAM. |
| 428 | 868 */ |
| 869 (charset, ccl_program)) | |
| 870 { | |
| 871 charset = Fget_charset (charset); | |
|
4745
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
872 XCHARSET_CCL_PROGRAM (charset) = get_ccl_program (ccl_program); |
|
0c54de4c4b9d
Resolve the unregistered-CCL-programs-get-garbage-collected problem correctly
Aidan Kehoe <kehoea@parhasard.net>
parents:
4691
diff
changeset
|
873 |
| 510 | 874 face_property_was_changed (Vdefault_face, Qfont, Qglobal); |
| 428 | 875 return Qnil; |
| 876 } | |
| 877 | |
| 3676 | 878 void |
| 879 set_charset_registries(Lisp_Object charset, Lisp_Object registries) | |
| 880 { | |
| 881 XCHARSET_REGISTRIES (charset) = registries; | |
| 882 invalidate_charset_font_caches (charset); | |
| 883 face_property_was_changed (Vdefault_face, Qfont, Qglobal); | |
| 884 } | |
| 885 | |
| 3711 | 886 DEFUN ("set-charset-registries", Fset_charset_registries, 2, 3, 0, /* |
| 3659 | 887 Set the `registries' property of CHARSET to REGISTRIES. |
| 888 | |
| 889 REGISTRIES is an ordered vector of strings that describe the X11 | |
| 890 CHARSET_REGISTRY and the CHARSET_ENCODINGs appropriate for this charset. | |
| 891 Separate each registry from the corresponding encoding with a dash. The | |
| 892 strings are not regular expressions, in contrast to the old behavior of | |
| 893 the `charset-registry' property. | |
| 894 | |
| 895 One reason to call this function might be if you're in Japan and you'd | |
| 896 prefer the backslash to display as a Yen sign; the corresponding syntax | |
| 897 would be: | |
| 898 | |
| 899 (set-charset-registries 'ascii ["jisx0201.1976-0"]) | |
| 900 | |
| 3711 | 901 If optional argument FORCE is non-nil, avoid sanity-checking the elements of |
| 902 REGISTRIES. Normally the strings are checked to make sure they contain no | |
| 903 XLFD wild cards and that they contain at least one hyphen; the only context | |
| 904 in which one might want not to do this is in order to use a font which | |
| 905 doesn't have a full XLFD--and thus, an effective | |
| 906 CHARSET_REGISTRY-CHARSET_ENCODING of ""--to display ASCII. | |
| 907 | |
| 908 We recommend strongly that you specify a full XLFD, since this makes | |
| 909 multilingual and variant font handling work much better. To get the full | |
| 910 XLFD of any font, start xfd with the short name as the pattern argument: | |
| 911 | |
| 912 xfd -fn 8x16kana | |
| 913 | |
| 914 and use the text that appears at the top of the window. | |
| 428 | 915 */ |
| 3711 | 916 (charset, registries, force)) |
| 428 | 917 { |
| 3659 | 918 int i; |
| 428 | 919 charset = Fget_charset (charset); |
| 3659 | 920 CHECK_VECTOR (registries); |
| 921 | |
| 922 for (i = 0; i < XVECTOR_LENGTH(registries); ++i) | |
| 923 { | |
| 924 CHECK_STRING (XVECTOR_DATA(registries)[i]); | |
| 3711 | 925 |
| 926 if (!NILP(force)) | |
| 927 { | |
| 928 continue; | |
| 929 } | |
| 930 | |
| 3659 | 931 if (NULL == qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '-')) |
| 932 { | |
| 933 invalid_argument("Not an X11 REGISTRY-ENCODING combination", | |
| 934 XVECTOR_DATA(registries)[i]); | |
| 935 } | |
| 3676 | 936 |
| 937 if (qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '*') || | |
| 938 qxestrchr(XSTRING_DATA(XVECTOR_DATA(registries)[i]), '?')) | |
| 939 { | |
| 940 invalid_argument | |
| 941 ("XLFD wildcards not allowed in charset-registries", | |
| 942 XVECTOR_DATA(registries)[i]); | |
| 943 | |
| 944 } | |
| 3659 | 945 } |
| 946 | |
| 3676 | 947 set_charset_registries(charset, registries); |
| 948 | |
| 428 | 949 return Qnil; |
| 950 } | |
| 951 | |
| 3681 | 952 DEFUN ("charsets-in-region", Fcharsets_in_region, 2, 3, 0, /* |
| 953 Return a list of the charsets in the region between START and END. | |
| 954 BUFFER defaults to the current buffer if omitted. | |
| 955 */ | |
| 956 (start, end, buffer)) | |
| 957 { | |
| 958 /* This function can GC */ | |
| 959 struct buffer *buf = decode_buffer (buffer, 1); | |
| 960 Charbpos pos, stop; /* Limits of the region. */ | |
| 961 Lisp_Object res = Qnil; | |
| 962 int charsets[NUM_LEADING_BYTES]; | |
| 963 Ibyte lb; | |
| 964 struct gcpro gcpro1; | |
| 965 | |
| 966 memset(charsets, 0, sizeof(charsets)); | |
| 967 get_buffer_range_char (buf, start, end, &pos, &stop, 0); | |
| 968 | |
| 969 GCPRO1 (res); | |
| 970 while (pos < stop) | |
| 971 { | |
| 972 lb = ichar_leading_byte(BUF_FETCH_CHAR (buf, pos)); | |
| 973 if (0 == charsets[lb - MIN_LEADING_BYTE]) | |
| 974 { | |
| 975 charsets[lb - MIN_LEADING_BYTE] = 1; | |
| 976 res = Fcons (XCHARSET_NAME(charset_by_leading_byte(lb)), res); | |
| 977 } | |
| 978 ++pos; | |
| 979 } | |
| 980 UNGCPRO; | |
| 981 | |
| 982 return res; | |
| 983 } | |
| 984 | |
| 428 | 985 |
| 986 /************************************************************************/ | |
| 771 | 987 /* memory usage */ |
| 428 | 988 /************************************************************************/ |
| 989 | |
| 771 | 990 #ifdef MEMORY_USAGE_STATS |
| 428 | 991 |
| 771 | 992 struct charset_stats |
| 993 { | |
| 994 int from_unicode; | |
| 995 int to_unicode; | |
| 996 int other; | |
| 997 }; | |
| 428 | 998 |
| 771 | 999 static void |
| 1000 compute_charset_usage (Lisp_Object charset, struct charset_stats *stats, | |
| 1001 struct overhead_stats *ovstats) | |
| 428 | 1002 { |
| 771 | 1003 struct Lisp_Charset *c = XCHARSET (charset); |
| 1004 xzero (*stats); | |
| 3024 | 1005 stats->other += LISPOBJ_STORAGE_SIZE (c, sizeof (*c), ovstats); |
| 771 | 1006 stats->from_unicode += compute_from_unicode_table_size (charset, ovstats); |
| 1007 stats->to_unicode += compute_to_unicode_table_size (charset, ovstats); | |
| 438 | 1008 } |
| 1009 | |
| 771 | 1010 DEFUN ("charset-memory-usage", Fcharset_memory_usage, 1, 1, 0, /* |
| 1011 Return stats about the memory usage of charset CHARSET. | |
| 1012 The values returned are in the form of an alist of usage types and | |
| 1013 byte counts. The byte counts attempt to encompass all the memory used | |
| 1014 by the charset (separate from the memory logically associated with a | |
| 1015 charset or frame), including internal structures and any malloc() | |
| 1016 overhead associated with them. In practice, the byte counts are | |
| 1017 underestimated for various reasons, e.g. because certain memory usage | |
| 1018 is very hard to determine \(e.g. the amount of memory used inside the | |
| 1019 Xt library or inside the X server). | |
| 428 | 1020 |
| 771 | 1021 Multiple slices of the total memory usage may be returned, separated |
| 1022 by a nil. Each slice represents a particular view of the memory, a | |
| 1023 particular way of partitioning it into groups. Within a slice, there | |
| 1024 is no overlap between the groups of memory, and each slice collectively | |
| 1025 represents all the memory concerned. | |
| 1026 */ | |
| 1027 (charset)) | |
| 1028 { | |
| 1029 struct charset_stats stats; | |
| 1030 struct overhead_stats ovstats; | |
| 1031 Lisp_Object val = Qnil; | |
| 428 | 1032 |
| 771 | 1033 charset = Fget_charset (charset); |
| 1034 xzero (ovstats); | |
| 1035 compute_charset_usage (charset, &stats, &ovstats); | |
| 428 | 1036 |
| 771 | 1037 val = acons (Qfrom_unicode, make_int (stats.from_unicode), val); |
| 1038 val = acons (Qto_unicode, make_int (stats.to_unicode), val); | |
| 1039 val = Fcons (Qnil, val); | |
| 1040 val = acons (Qactually_requested, make_int (ovstats.was_requested), val); | |
| 1041 val = acons (Qmalloc_overhead, make_int (ovstats.malloc_overhead), val); | |
| 1042 val = acons (Qgap_overhead, make_int (ovstats.gap_overhead), val); | |
| 1043 val = acons (Qdynarr_overhead, make_int (ovstats.dynarr_overhead), val); | |
| 1044 | |
| 1045 return Fnreverse (val); | |
| 428 | 1046 } |
| 1047 | |
| 771 | 1048 #endif /* MEMORY_USAGE_STATS */ |
| 428 | 1049 |
| 1050 | |
| 1051 /************************************************************************/ | |
| 1052 /* initialization */ | |
| 1053 /************************************************************************/ | |
| 1054 | |
| 1055 void | |
| 1056 syms_of_mule_charset (void) | |
| 1057 { | |
| 442 | 1058 INIT_LRECORD_IMPLEMENTATION (charset); |
| 1059 | |
| 428 | 1060 DEFSUBR (Fcharsetp); |
| 1061 DEFSUBR (Ffind_charset); | |
| 1062 DEFSUBR (Fget_charset); | |
| 1063 DEFSUBR (Fcharset_list); | |
| 1064 DEFSUBR (Fcharset_name); | |
| 1065 DEFSUBR (Fmake_charset); | |
| 1066 DEFSUBR (Fmake_reverse_direction_charset); | |
| 793 | 1067 DEFSUBR (Fcharset_reverse_direction_charset); |
| 428 | 1068 DEFSUBR (Fcharset_from_attributes); |
| 1069 DEFSUBR (Fcharset_short_name); | |
| 1070 DEFSUBR (Fcharset_long_name); | |
| 1071 DEFSUBR (Fcharset_description); | |
| 1072 DEFSUBR (Fcharset_dimension); | |
| 1073 DEFSUBR (Fcharset_property); | |
| 1074 DEFSUBR (Fcharset_id); | |
| 1075 DEFSUBR (Fset_charset_ccl_program); | |
| 3659 | 1076 DEFSUBR (Fset_charset_registries); |
| 3681 | 1077 DEFSUBR (Fcharsets_in_region); |
| 428 | 1078 |
| 771 | 1079 #ifdef MEMORY_USAGE_STATS |
| 1080 DEFSUBR (Fcharset_memory_usage); | |
| 428 | 1081 #endif |
| 1082 | |
| 563 | 1083 DEFSYMBOL (Qcharsetp); |
| 3659 | 1084 DEFSYMBOL (Qregistries); |
| 563 | 1085 DEFSYMBOL (Qfinal); |
| 1086 DEFSYMBOL (Qgraphic); | |
| 3659 | 1087 DEFSYMBOL (Qregistry); |
| 563 | 1088 DEFSYMBOL (Qdirection); |
| 1089 DEFSYMBOL (Qreverse_direction_charset); | |
| 1090 DEFSYMBOL (Qshort_name); | |
| 1091 DEFSYMBOL (Qlong_name); | |
| 428 | 1092 |
| 771 | 1093 DEFSYMBOL (Qto_unicode); |
| 1094 | |
| 563 | 1095 DEFSYMBOL (Ql2r); |
| 1096 DEFSYMBOL (Qr2l); | |
| 428 | 1097 |
| 1098 /* Charsets, compatible with FSF 20.3 | |
| 1099 Naming convention is Script-Charset[-Edition] */ | |
| 563 | 1100 DEFSYMBOL (Qlatin_iso8859_1); |
| 1101 DEFSYMBOL (Qlatin_iso8859_2); | |
| 1102 DEFSYMBOL (Qlatin_iso8859_3); | |
| 1103 DEFSYMBOL (Qlatin_iso8859_4); | |
| 1104 DEFSYMBOL (Qthai_tis620); | |
| 1105 DEFSYMBOL (Qgreek_iso8859_7); | |
|
4805
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1106 DEFSYMBOL (Qarabic_iso8859_6); |
| 563 | 1107 DEFSYMBOL (Qhebrew_iso8859_8); |
| 1108 DEFSYMBOL (Qkatakana_jisx0201); | |
| 1109 DEFSYMBOL (Qlatin_jisx0201); | |
| 1110 DEFSYMBOL (Qcyrillic_iso8859_5); | |
| 1111 DEFSYMBOL (Qlatin_iso8859_9); | |
| 728 | 1112 DEFSYMBOL (Qlatin_iso8859_15); |
| 563 | 1113 DEFSYMBOL (Qjapanese_jisx0208_1978); |
| 1114 DEFSYMBOL (Qchinese_gb2312); | |
| 1115 DEFSYMBOL (Qjapanese_jisx0208); | |
| 1116 DEFSYMBOL (Qkorean_ksc5601); | |
| 1117 DEFSYMBOL (Qjapanese_jisx0212); | |
| 1118 DEFSYMBOL (Qchinese_cns11643_1); | |
| 1119 DEFSYMBOL (Qchinese_cns11643_2); | |
| 1120 DEFSYMBOL (Qchinese_big5_1); | |
| 1121 DEFSYMBOL (Qchinese_big5_2); | |
| 428 | 1122 |
| 563 | 1123 DEFSYMBOL (Qcomposite); |
| 428 | 1124 } |
| 1125 | |
| 1126 void | |
| 1127 vars_of_mule_charset (void) | |
| 1128 { | |
| 1129 int i, j, k; | |
| 1130 | |
| 452 | 1131 chlook = xnew_and_zero (struct charset_lookup); /* zero for Purify. */ |
| 2367 | 1132 dump_add_root_block_ptr (&chlook, &charset_lookup_description); |
| 428 | 1133 |
| 1134 /* Table of charsets indexed by leading byte. */ | |
| 1135 for (i = 0; i < countof (chlook->charset_by_leading_byte); i++) | |
| 1136 chlook->charset_by_leading_byte[i] = Qnil; | |
| 1137 | |
| 1138 /* Table of charsets indexed by type/final-byte/direction. */ | |
| 1139 for (i = 0; i < countof (chlook->charset_by_attributes); i++) | |
| 1140 for (j = 0; j < countof (chlook->charset_by_attributes[0]); j++) | |
| 1141 for (k = 0; k < countof (chlook->charset_by_attributes[0][0]); k++) | |
| 1142 chlook->charset_by_attributes[i][j][k] = Qnil; | |
| 1143 | |
| 442 | 1144 chlook->next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; |
| 1145 chlook->next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; | |
| 771 | 1146 |
| 1147 staticpro (&Vcharset_hash_table); | |
| 1148 Vcharset_hash_table = | |
| 1149 make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ); | |
| 428 | 1150 } |
| 1151 | |
| 1152 void | |
| 1153 complex_vars_of_mule_charset (void) | |
| 1154 { | |
| 1155 /* Predefined character sets. We store them into variables for | |
| 1156 ease of access. */ | |
| 1157 | |
| 1158 staticpro (&Vcharset_ascii); | |
| 1159 Vcharset_ascii = | |
| 1160 make_charset (LEADING_BYTE_ASCII, Qascii, 1, | |
| 1161 CHARSET_TYPE_94, 1, 0, 'B', | |
| 1162 CHARSET_LEFT_TO_RIGHT, | |
| 1163 build_string ("ASCII"), | |
| 771 | 1164 build_msg_string ("ASCII"), |
| 1165 build_msg_string ("ASCII (ISO646 IRV)"), | |
| 3659 | 1166 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1167 staticpro (&Vcharset_control_1); |
| 1168 Vcharset_control_1 = | |
| 1169 make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, | |
| 1170 CHARSET_TYPE_94, 1, 1, 0, | |
| 1171 CHARSET_LEFT_TO_RIGHT, | |
| 1172 build_string ("C1"), | |
| 771 | 1173 build_msg_string ("Control characters"), |
| 1174 build_msg_string ("Control characters 128-191"), | |
| 3659 | 1175 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1176 staticpro (&Vcharset_latin_iso8859_1); |
| 1177 Vcharset_latin_iso8859_1 = | |
| 1178 make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, | |
| 1179 CHARSET_TYPE_96, 1, 1, 'A', | |
| 1180 CHARSET_LEFT_TO_RIGHT, | |
| 1181 build_string ("Latin-1"), | |
| 771 | 1182 build_msg_string ("ISO8859-1 (Latin-1)"), |
| 1183 build_msg_string ("ISO8859-1 (Latin-1)"), | |
| 3659 | 1184 vector1(build_string("iso8859-1")), 0, 0); |
| 428 | 1185 staticpro (&Vcharset_latin_iso8859_2); |
| 1186 Vcharset_latin_iso8859_2 = | |
| 1187 make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, | |
| 1188 CHARSET_TYPE_96, 1, 1, 'B', | |
| 1189 CHARSET_LEFT_TO_RIGHT, | |
| 1190 build_string ("Latin-2"), | |
| 771 | 1191 build_msg_string ("ISO8859-2 (Latin-2)"), |
| 1192 build_msg_string ("ISO8859-2 (Latin-2)"), | |
| 3659 | 1193 vector1(build_string("iso8859-2")), 0, 0); |
| 428 | 1194 staticpro (&Vcharset_latin_iso8859_3); |
| 1195 Vcharset_latin_iso8859_3 = | |
| 1196 make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, | |
| 1197 CHARSET_TYPE_96, 1, 1, 'C', | |
| 1198 CHARSET_LEFT_TO_RIGHT, | |
| 1199 build_string ("Latin-3"), | |
| 771 | 1200 build_msg_string ("ISO8859-3 (Latin-3)"), |
| 1201 build_msg_string ("ISO8859-3 (Latin-3)"), | |
| 3659 | 1202 vector1(build_string("iso8859-3")), 0, 0); |
| 428 | 1203 staticpro (&Vcharset_latin_iso8859_4); |
| 1204 Vcharset_latin_iso8859_4 = | |
| 1205 make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, | |
| 1206 CHARSET_TYPE_96, 1, 1, 'D', | |
| 1207 CHARSET_LEFT_TO_RIGHT, | |
| 1208 build_string ("Latin-4"), | |
| 771 | 1209 build_msg_string ("ISO8859-4 (Latin-4)"), |
| 1210 build_msg_string ("ISO8859-4 (Latin-4)"), | |
| 3816 | 1211 vector1(build_string("iso8859-4")), 0, 0); |
| 428 | 1212 staticpro (&Vcharset_thai_tis620); |
| 1213 Vcharset_thai_tis620 = | |
| 1214 make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, | |
| 1215 CHARSET_TYPE_96, 1, 1, 'T', | |
| 1216 CHARSET_LEFT_TO_RIGHT, | |
| 1217 build_string ("TIS620"), | |
| 771 | 1218 build_msg_string ("TIS620 (Thai)"), |
| 1219 build_msg_string ("TIS620.2529 (Thai)"), | |
| 3659 | 1220 vector1(build_string("tis620.2529-1")), 0, 0); |
| 428 | 1221 staticpro (&Vcharset_greek_iso8859_7); |
| 1222 Vcharset_greek_iso8859_7 = | |
| 1223 make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, | |
| 1224 CHARSET_TYPE_96, 1, 1, 'F', | |
| 1225 CHARSET_LEFT_TO_RIGHT, | |
| 1226 build_string ("ISO8859-7"), | |
| 771 | 1227 build_msg_string ("ISO8859-7 (Greek)"), |
| 1228 build_msg_string ("ISO8859-7 (Greek)"), | |
| 3659 | 1229 vector1(build_string("iso8859-7")), 0, 0); |
|
4805
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1230 staticpro (&Vcharset_arabic_iso8859_6); |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1231 Vcharset_arabic_iso8859_6 = |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1232 make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2, |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1233 CHARSET_TYPE_96, 1, 1, 'G', |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1234 CHARSET_RIGHT_TO_LEFT, |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1235 build_string ("ISO8859-6"), |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1236 build_msg_string ("ISO8859-6 (Arabic)"), |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1237 build_msg_string ("ISO8859-6 (Arabic)"), |
|
980575c76541
Move the arabic-iso8859-6 character set back to C, otherwise X11 lookup fails.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4745
diff
changeset
|
1238 vector1(build_string ("iso8859-6")), 0, 0); |
| 428 | 1239 staticpro (&Vcharset_hebrew_iso8859_8); |
| 1240 Vcharset_hebrew_iso8859_8 = | |
| 1241 make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, | |
| 1242 CHARSET_TYPE_96, 1, 1, 'H', | |
| 1243 CHARSET_RIGHT_TO_LEFT, | |
| 1244 build_string ("ISO8859-8"), | |
| 771 | 1245 build_msg_string ("ISO8859-8 (Hebrew)"), |
| 1246 build_msg_string ("ISO8859-8 (Hebrew)"), | |
| 3659 | 1247 vector1(build_string ("iso8859-8")), 0, 0); |
| 428 | 1248 staticpro (&Vcharset_katakana_jisx0201); |
| 1249 Vcharset_katakana_jisx0201 = | |
| 1250 make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, | |
| 1251 CHARSET_TYPE_94, 1, 1, 'I', | |
| 1252 CHARSET_LEFT_TO_RIGHT, | |
| 1253 build_string ("JISX0201 Kana"), | |
| 771 | 1254 build_msg_string ("JISX0201.1976 (Japanese Kana)"), |
| 1255 build_msg_string ("JISX0201.1976 Japanese Kana"), | |
| 3659 | 1256 vector1(build_string ("jisx0201.1976-0")), 0, 0); |
| 428 | 1257 staticpro (&Vcharset_latin_jisx0201); |
| 1258 Vcharset_latin_jisx0201 = | |
| 1259 make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, | |
| 1260 CHARSET_TYPE_94, 1, 0, 'J', | |
| 1261 CHARSET_LEFT_TO_RIGHT, | |
| 1262 build_string ("JISX0201 Roman"), | |
| 771 | 1263 build_msg_string ("JISX0201.1976 (Japanese Roman)"), |
| 1264 build_msg_string ("JISX0201.1976 Japanese Roman"), | |
| 3659 | 1265 vector1(build_string ("jisx0201.1976-0")), 0, 0); |
| 428 | 1266 staticpro (&Vcharset_cyrillic_iso8859_5); |
| 1267 Vcharset_cyrillic_iso8859_5 = | |
| 1268 make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, | |
| 1269 CHARSET_TYPE_96, 1, 1, 'L', | |
| 1270 CHARSET_LEFT_TO_RIGHT, | |
| 1271 build_string ("ISO8859-5"), | |
| 771 | 1272 build_msg_string ("ISO8859-5 (Cyrillic)"), |
| 1273 build_msg_string ("ISO8859-5 (Cyrillic)"), | |
| 3659 | 1274 vector1(build_string ("iso8859-5")), 0, 0); |
| 428 | 1275 staticpro (&Vcharset_latin_iso8859_9); |
| 1276 Vcharset_latin_iso8859_9 = | |
| 1277 make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, | |
| 1278 CHARSET_TYPE_96, 1, 1, 'M', | |
| 1279 CHARSET_LEFT_TO_RIGHT, | |
| 1280 build_string ("Latin-5"), | |
| 771 | 1281 build_msg_string ("ISO8859-9 (Latin-5)"), |
| 1282 build_msg_string ("ISO8859-9 (Latin-5)"), | |
| 3659 | 1283 vector1(build_string ("iso8859-9")), 0, 0); |
| 728 | 1284 staticpro (&Vcharset_latin_iso8859_15); |
| 1285 Vcharset_latin_iso8859_15 = | |
| 1286 make_charset (LEADING_BYTE_LATIN_ISO8859_15, Qlatin_iso8859_15, 2, | |
| 1287 CHARSET_TYPE_96, 1, 1, 'b', | |
| 1288 CHARSET_LEFT_TO_RIGHT, | |
| 1289 build_string ("Latin-9"), | |
| 771 | 1290 build_msg_string ("ISO8859-15 (Latin-9)"), |
| 1291 build_msg_string ("ISO8859-15 (Latin-9)"), | |
| 3659 | 1292 vector1(build_string ("iso8859-15")), 0, 0); |
| 428 | 1293 staticpro (&Vcharset_japanese_jisx0208_1978); |
| 1294 Vcharset_japanese_jisx0208_1978 = | |
| 1295 make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, | |
| 1296 CHARSET_TYPE_94X94, 2, 0, '@', | |
| 1297 CHARSET_LEFT_TO_RIGHT, | |
| 1298 build_string ("JISX0208.1978"), | |
| 771 | 1299 build_msg_string ("JISX0208.1978 (Japanese)"), |
| 1300 build_msg_string | |
| 428 | 1301 ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), |
| 3659 | 1302 vector2(build_string("jisx0208.1978-0"), |
| 1303 build_string("jisc6226.1978-0")), 0, 0); | |
| 428 | 1304 staticpro (&Vcharset_chinese_gb2312); |
| 1305 Vcharset_chinese_gb2312 = | |
| 1306 make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, | |
| 1307 CHARSET_TYPE_94X94, 2, 0, 'A', | |
| 1308 CHARSET_LEFT_TO_RIGHT, | |
| 1309 build_string ("GB2312"), | |
| 771 | 1310 build_msg_string ("GB2312)"), |
| 1311 build_msg_string ("GB2312 Chinese simplified"), | |
| 3659 | 1312 vector2(build_string("gb2312.1980-0"), |
| 1313 build_string("gb2312.80&gb8565.88-0")), 0, 0); | |
| 428 | 1314 staticpro (&Vcharset_japanese_jisx0208); |
| 1315 Vcharset_japanese_jisx0208 = | |
| 1316 make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, | |
| 1317 CHARSET_TYPE_94X94, 2, 0, 'B', | |
| 1318 CHARSET_LEFT_TO_RIGHT, | |
| 1319 build_string ("JISX0208"), | |
| 771 | 1320 build_msg_string ("JISX0208.1983/1990 (Japanese)"), |
| 1321 build_msg_string ("JISX0208.1983/1990 Japanese Kanji"), | |
| 3659 | 1322 vector2(build_string("jisx0208.1983-0"), |
| 1323 build_string("jisx0208.1990-0")), 0, 0); | |
| 428 | 1324 staticpro (&Vcharset_korean_ksc5601); |
| 1325 Vcharset_korean_ksc5601 = | |
| 1326 make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, | |
| 1327 CHARSET_TYPE_94X94, 2, 0, 'C', | |
| 1328 CHARSET_LEFT_TO_RIGHT, | |
| 1329 build_string ("KSC5601"), | |
| 771 | 1330 build_msg_string ("KSC5601 (Korean"), |
| 1331 build_msg_string ("KSC5601 Korean Hangul and Hanja"), | |
| 3659 | 1332 vector1(build_string("ksc5601.1987-0")), 0, 0); |
| 428 | 1333 staticpro (&Vcharset_japanese_jisx0212); |
| 1334 Vcharset_japanese_jisx0212 = | |
| 1335 make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, | |
| 1336 CHARSET_TYPE_94X94, 2, 0, 'D', | |
| 1337 CHARSET_LEFT_TO_RIGHT, | |
| 1338 build_string ("JISX0212"), | |
| 771 | 1339 build_msg_string ("JISX0212 (Japanese)"), |
| 1340 build_msg_string ("JISX0212 Japanese Supplement"), | |
| 3659 | 1341 vector1(build_string("jisx0212.1990-0")), 0, 0); |
| 428 | 1342 |
| 3659 | 1343 #define CHINESE_CNS_PLANE(n) "cns11643.1992-" n |
| 428 | 1344 staticpro (&Vcharset_chinese_cns11643_1); |
| 1345 Vcharset_chinese_cns11643_1 = | |
| 1346 make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3, | |
| 1347 CHARSET_TYPE_94X94, 2, 0, 'G', | |
| 1348 CHARSET_LEFT_TO_RIGHT, | |
| 1349 build_string ("CNS11643-1"), | |
| 771 | 1350 build_msg_string ("CNS11643-1 (Chinese traditional)"), |
| 1351 build_msg_string | |
| 428 | 1352 ("CNS 11643 Plane 1 Chinese traditional"), |
| 3659 | 1353 vector1(build_string (CHINESE_CNS_PLANE("1"))), 0, 0); |
| 428 | 1354 staticpro (&Vcharset_chinese_cns11643_2); |
| 1355 Vcharset_chinese_cns11643_2 = | |
| 1356 make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, | |
| 1357 CHARSET_TYPE_94X94, 2, 0, 'H', | |
| 1358 CHARSET_LEFT_TO_RIGHT, | |
| 1359 build_string ("CNS11643-2"), | |
| 771 | 1360 build_msg_string ("CNS11643-2 (Chinese traditional)"), |
| 1361 build_msg_string | |
| 428 | 1362 ("CNS 11643 Plane 2 Chinese traditional"), |
| 3659 | 1363 vector1(build_string (CHINESE_CNS_PLANE("2"))), 0, 0); |
| 428 | 1364 staticpro (&Vcharset_chinese_big5_1); |
| 1365 Vcharset_chinese_big5_1 = | |
| 1366 make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, | |
| 1367 CHARSET_TYPE_94X94, 2, 0, '0', | |
| 1368 CHARSET_LEFT_TO_RIGHT, | |
| 1369 build_string ("Big5"), | |
| 771 | 1370 build_msg_string ("Big5 (Level-1)"), |
| 1371 build_msg_string | |
| 428 | 1372 ("Big5 Level-1 Chinese traditional"), |
| 3659 | 1373 vector1(build_string ("big5.eten-0")), 0, 0); |
| 428 | 1374 staticpro (&Vcharset_chinese_big5_2); |
| 1375 Vcharset_chinese_big5_2 = | |
| 1376 make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, | |
| 1377 CHARSET_TYPE_94X94, 2, 0, '1', | |
| 1378 CHARSET_LEFT_TO_RIGHT, | |
| 1379 build_string ("Big5"), | |
| 771 | 1380 build_msg_string ("Big5 (Level-2)"), |
| 1381 build_msg_string | |
| 428 | 1382 ("Big5 Level-2 Chinese traditional"), |
| 3659 | 1383 vector1(build_string ("big5.eten-0")), 0, 0); |
| 428 | 1384 |
| 1385 | |
| 1386 #ifdef ENABLE_COMPOSITE_CHARS | |
| 1387 /* #### For simplicity, we put composite chars into a 96x96 charset. | |
| 1388 This is going to lead to problems because you can run out of | |
| 1389 room, esp. as we don't yet recycle numbers. */ | |
| 1390 staticpro (&Vcharset_composite); | |
| 1391 Vcharset_composite = | |
| 1392 make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 3, | |
| 1393 CHARSET_TYPE_96X96, 2, 0, 0, | |
| 1394 CHARSET_LEFT_TO_RIGHT, | |
| 1395 build_string ("Composite"), | |
| 771 | 1396 build_msg_string ("Composite characters"), |
| 1397 build_msg_string ("Composite characters"), | |
| 3659 | 1398 vector1(build_string ("")), 0, 0); |
| 771 | 1399 #else |
| 1400 /* We create a hack so that we have a way of storing ESC 0 and ESC 1 | |
| 1401 sequences as "characters", so that they will be output correctly. */ | |
| 1402 staticpro (&Vcharset_composite); | |
| 1403 Vcharset_composite = | |
| 1404 make_charset (LEADING_BYTE_COMPOSITE_REPLACEMENT, Qcomposite, 2, | |
| 1405 CHARSET_TYPE_96, 1, 1, '|', | |
| 1406 CHARSET_LEFT_TO_RIGHT, | |
| 1407 build_string ("Composite hack"), | |
| 1408 build_msg_string ("Composite characters hack"), | |
| 1409 build_msg_string ("Composite characters hack"), | |
| 3659 | 1410 vector1(build_string ("")), 0, 0); |
| 428 | 1411 #endif /* ENABLE_COMPOSITE_CHARS */ |
| 1412 } |