Mercurial > hg > xemacs-beta
annotate lisp/mule/latin.el @ 4316:2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
2007-12-09 Aidan Kehoe <kehoea@parhasard.net>
* mule/latin.el:
Create clones of the English language environment with UTF-8 and
Windows-1252 as the associated coding system, for Joachim Schrod's
use case of f8q022$3o3$1@sea.gmane.org.
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Sun, 09 Dec 2007 14:04:13 +0100 |
| parents | f4c3ffe60a4f |
| children | 948c9b232595 |
| rev | line source |
|---|---|
| 3767 | 1 ;;; latin.el --- Roman-alphabet languages -*- coding: iso-2022-7bit; -*- |
| 464 | 2 |
| 3767 | 3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. |
| 4 ;; Licensed to the Free Software Foundation. | |
| 5 ;; Copyright (C) 1997 MORIOKA Tomohiko | |
| 6 ;; Copyright (C) 2001 Ben Wing. | |
| 7 ;; Copyright (C) 2002, 2005, 2006 Free Software Foundation | |
| 8 | |
| 9 ;; Keywords: multilingual, latin, dumped | |
| 464 | 10 |
| 11 ;; This file is part of XEmacs. | |
| 12 | |
| 13 ;; XEmacs is free software; you can redistribute it and/or modify it | |
| 14 ;; under the terms of the GNU General Public License as published by | |
| 15 ;; the Free Software Foundation; either version 2, or (at your option) | |
| 16 ;; any later version. | |
| 17 | |
| 18 ;; XEmacs is distributed in the hope that it will be useful, but | |
| 19 ;; WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 21 ;; General Public License for more details. | |
| 22 | |
| 23 ;; You should have received a copy of the GNU General Public License | |
| 24 ;; along with XEmacs; see the file COPYING. If not, write to the Free | |
| 25 ;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA | |
| 26 ;; 02111-1307, USA. | |
| 27 | |
| 28 ;;; Commentary: | |
| 29 | |
| 3767 | 30 ;; For Roman-alphabet-using Europeans, eight coded character sets, |
| 31 ;; ISO8859-1,2,3,4,9,14,15,16 are supported. | |
| 464 | 32 |
| 33 ;;; Code: | |
| 34 | |
| 35 ;; Case table setup. We set up all the case tables using | |
| 36 ;; put-case-table-pair. The data for this comes from FSF Emacs 20.7 | |
| 37 ;; (lisp/international/latin-*.el), written by several people and | |
| 38 ;; updated by Erik Naggum. | |
| 39 | |
| 40 (defun setup-case-pairs (charset pairs) | |
| 3767 | 41 (loop |
| 42 for (uc lc) in pairs | |
| 43 with table = (standard-case-table) | |
| 44 do (put-case-table-pair | |
| 45 (make-char charset uc) (make-char charset lc) table))) | |
| 46 | |
| 47 ;; Latin-1's case is dealt with in iso8859-1.el, which see. Its syntax is | |
| 48 ;; initialised in syntax.c:complex_vars_of_syntax. | |
| 464 | 49 |
| 3767 | 50 |
| 51 ;; Latin-2 (ISO-8859-2). Central Europe; Czech, Slovak, Hungarian, Polish, | |
| 52 ;; Croatian, other languages. | |
| 53 ;; | |
| 54 ;; (Yes, it really is Central European. German written in Latin 2 and using | |
| 55 ;; only Umlaute and the sharp S in its non-ASCII repertoire is bit-for-bit | |
| 56 ;; identical with the same text in Latin-1.) | |
| 464 | 57 |
| 3767 | 58 ;; The default character syntax is now word. Pay attention to the |
| 59 ;; exceptions in ISO-8859-2, copying them from ISO-8859-1. | |
| 60 (loop | |
| 61 for (latin-2 latin-1) | |
| 62 in '((#xA0 #xA0) ;; NO BREAK SPACE | |
| 63 (#xA2 #xB4) ;; BREVE, ACUTE ACCENT | |
| 64 (#xA4 #xA4) ;; CURRENCY SIGN | |
| 65 (#xA7 #xA7) ;; SECTION SIGN | |
| 66 (#xA8 #xA8) ;; DIAERESIS | |
| 67 (#xAD #xAD) ;; SOFT HYPHEN | |
| 68 (#xB0 #xB0) ;; DEGREE SIGN | |
| 69 (#xB2 #xB4) ;; OGONEK, ACUTE ACCENT | |
| 70 (#xB4 #xB4) ;; ACUTE ACCENT | |
| 71 (#xB7 #xB4) ;; CARON, ACUTE ACCENT | |
| 72 (#xB8 #xB8) ;; CEDILLA | |
| 73 (#xBD #xB4) ;; DOUBLE ACUTE ACCENT, ACUTE ACCENT | |
| 74 (#xD7 #xD7) ;; MULTIPLICATION SIGN | |
| 75 (#xF7 #xF7) ;; DIVISION SIGN | |
| 76 (#xFF #xB4)) ;; DOT ABOVE, ACUTE ACCENT | |
| 77 with syntax-table = (standard-syntax-table) | |
| 78 do (modify-syntax-entry | |
| 79 (make-char 'latin-iso8859-2 latin-2) | |
| 80 (string (char-syntax (make-char 'latin-iso8859-1 latin-1))) | |
| 81 syntax-table)) | |
| 464 | 82 |
| 3767 | 83 ;; Case. |
| 464 | 84 (setup-case-pairs |
| 85 'latin-iso8859-2 | |
| 3767 | 86 '((#xA1 #xB1) ;; A WITH OGONEK |
| 87 (#xA3 #xB3) ;; L WITH STROKE | |
| 88 (#xA5 #xB5) ;; L WITH CARON | |
| 89 (#xA6 #xB6) ;; S WITH ACUTE | |
| 90 (#xA9 #xB9) ;; S WITH CARON | |
| 91 (#xAA #xBA) ;; S WITH CEDILLA | |
| 92 (#xAB #xBB) ;; T WITH CARON | |
| 93 (#xAC #xBC) ;; Z WITH ACUTE | |
| 94 (#xAE #xBE) ;; Z WITH CARON | |
| 95 (#xAF #xBF) ;; Z WITH DOT ABOVE | |
| 96 (#xC0 #xE0) ;; R WITH ACUTE | |
| 97 (#xC1 #xE1) ;; A WITH ACUTE | |
| 98 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 99 (#xC3 #xE3) ;; A WITH BREVE | |
| 100 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 101 (#xC5 #xE5) ;; L WITH ACUTE | |
| 102 (#xC6 #xE6) ;; C WITH ACUTE | |
| 103 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 104 (#xC8 #xE8) ;; C WITH CARON | |
| 105 (#xC9 #xE9) ;; E WITH ACUTE | |
| 106 (#xCA #xEA) ;; E WITH OGONEK | |
| 107 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 108 (#xCC #xEC) ;; E WITH CARON | |
| 109 (#xCD #xED) ;; I WITH ACUTE | |
| 110 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 111 (#xCF #xEF) ;; D WITH CARON | |
| 112 (#xD0 #xF0) ;; D WITH STROKE | |
| 113 (#xD1 #xF1) ;; N WITH ACUTE | |
| 114 (#xD2 #xF2) ;; N WITH CARON | |
| 115 (#xD3 #xF3) ;; O WITH ACUTE | |
| 116 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 117 (#xD5 #xF5) ;; O WITH DOUBLE ACUTE | |
| 118 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 119 (#xD8 #xF8) ;; R WITH CARON | |
| 120 (#xD9 #xF9) ;; U WITH RING ABOVE | |
| 121 (#xDA #xFA) ;; U WITH ACUTE | |
| 122 (#xDB #xFB) ;; U WITH DOUBLE ACUTE | |
| 123 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 124 (#xDD #xFD) ;; Y WITH ACUTE | |
| 125 (#xDE #xFE))) ;; T WITH CEDILLA | |
| 464 | 126 |
| 4299 | 127 (make-8-bit-coding-system |
| 128 'iso-8859-2 | |
| 129 '((#xA1 ?\u0104) ;; LATIN CAPITAL LETTER A WITH OGONEK | |
| 130 (#xA2 ?\u02D8) ;; BREVE | |
| 131 (#xA3 ?\u0141) ;; LATIN CAPITAL LETTER L WITH STROKE | |
| 132 (#xA5 ?\u013D) ;; LATIN CAPITAL LETTER L WITH CARON | |
| 133 (#xA6 ?\u015A) ;; LATIN CAPITAL LETTER S WITH ACUTE | |
| 134 (#xA9 ?\u0160) ;; LATIN CAPITAL LETTER S WITH CARON | |
| 135 (#xAA ?\u015E) ;; LATIN CAPITAL LETTER S WITH CEDILLA | |
| 136 (#xAB ?\u0164) ;; LATIN CAPITAL LETTER T WITH CARON | |
| 137 (#xAC ?\u0179) ;; LATIN CAPITAL LETTER Z WITH ACUTE | |
| 138 (#xAE ?\u017D) ;; LATIN CAPITAL LETTER Z WITH CARON | |
| 139 (#xAF ?\u017B) ;; LATIN CAPITAL LETTER Z WITH DOT ABOVE | |
| 140 (#xB1 ?\u0105) ;; LATIN SMALL LETTER A WITH OGONEK | |
| 141 (#xB2 ?\u02DB) ;; OGONEK | |
| 142 (#xB3 ?\u0142) ;; LATIN SMALL LETTER L WITH STROKE | |
| 143 (#xB5 ?\u013E) ;; LATIN SMALL LETTER L WITH CARON | |
| 144 (#xB6 ?\u015B) ;; LATIN SMALL LETTER S WITH ACUTE | |
| 145 (#xB7 ?\u02C7) ;; CARON | |
| 146 (#xB9 ?\u0161) ;; LATIN SMALL LETTER S WITH CARON | |
| 147 (#xBA ?\u015F) ;; LATIN SMALL LETTER S WITH CEDILLA | |
| 148 (#xBB ?\u0165) ;; LATIN SMALL LETTER T WITH CARON | |
| 149 (#xBC ?\u017A) ;; LATIN SMALL LETTER Z WITH ACUTE | |
| 150 (#xBD ?\u02DD) ;; DOUBLE ACUTE ACCENT | |
| 151 (#xBE ?\u017E) ;; LATIN SMALL LETTER Z WITH CARON | |
| 152 (#xBF ?\u017C) ;; LATIN SMALL LETTER Z WITH DOT ABOVE | |
| 153 (#xC0 ?\u0154) ;; LATIN CAPITAL LETTER R WITH ACUTE | |
| 154 (#xC3 ?\u0102) ;; LATIN CAPITAL LETTER A WITH BREVE | |
| 155 (#xC5 ?\u0139) ;; LATIN CAPITAL LETTER L WITH ACUTE | |
| 156 (#xC6 ?\u0106) ;; LATIN CAPITAL LETTER C WITH ACUTE | |
| 157 (#xC8 ?\u010C) ;; LATIN CAPITAL LETTER C WITH CARON | |
| 158 (#xCA ?\u0118) ;; LATIN CAPITAL LETTER E WITH OGONEK | |
| 159 (#xCC ?\u011A) ;; LATIN CAPITAL LETTER E WITH CARON | |
| 160 (#xCF ?\u010E) ;; LATIN CAPITAL LETTER D WITH CARON | |
| 161 (#xD0 ?\u0110) ;; LATIN CAPITAL LETTER D WITH STROKE | |
| 162 (#xD1 ?\u0143) ;; LATIN CAPITAL LETTER N WITH ACUTE | |
| 163 (#xD2 ?\u0147) ;; LATIN CAPITAL LETTER N WITH CARON | |
| 164 (#xD5 ?\u0150) ;; LATIN CAPITAL LETTER O WITH DOUBLE ACUTE | |
| 165 (#xD8 ?\u0158) ;; LATIN CAPITAL LETTER R WITH CARON | |
| 166 (#xD9 ?\u016E) ;; LATIN CAPITAL LETTER U WITH RING ABOVE | |
| 167 (#xDB ?\u0170) ;; LATIN CAPITAL LETTER U WITH DOUBLE ACUTE | |
| 168 (#xDE ?\u0162) ;; LATIN CAPITAL LETTER T WITH CEDILLA | |
| 169 (#xE0 ?\u0155) ;; LATIN SMALL LETTER R WITH ACUTE | |
| 170 (#xE3 ?\u0103) ;; LATIN SMALL LETTER A WITH BREVE | |
| 171 (#xE5 ?\u013A) ;; LATIN SMALL LETTER L WITH ACUTE | |
| 172 (#xE6 ?\u0107) ;; LATIN SMALL LETTER C WITH ACUTE | |
| 173 (#xE8 ?\u010D) ;; LATIN SMALL LETTER C WITH CARON | |
| 174 (#xEA ?\u0119) ;; LATIN SMALL LETTER E WITH OGONEK | |
| 175 (#xEC ?\u011B) ;; LATIN SMALL LETTER E WITH CARON | |
| 176 (#xEF ?\u010F) ;; LATIN SMALL LETTER D WITH CARON | |
| 177 (#xF0 ?\u0111) ;; LATIN SMALL LETTER D WITH STROKE | |
| 178 (#xF1 ?\u0144) ;; LATIN SMALL LETTER N WITH ACUTE | |
| 179 (#xF2 ?\u0148) ;; LATIN SMALL LETTER N WITH CARON | |
| 180 (#xF5 ?\u0151) ;; LATIN SMALL LETTER O WITH DOUBLE ACUTE | |
| 181 (#xF8 ?\u0159) ;; LATIN SMALL LETTER R WITH CARON | |
| 182 (#xF9 ?\u016F) ;; LATIN SMALL LETTER U WITH RING ABOVE | |
| 183 (#xFB ?\u0171) ;; LATIN SMALL LETTER U WITH DOUBLE ACUTE | |
| 184 (#xFE ?\u0163) ;; LATIN SMALL LETTER T WITH CEDILLA | |
| 185 (#xFF ?\u02D9));; DOT ABOVE | |
| 186 "ISO-8859-2 (Latin-2) for Central Europe. | |
| 187 See also `windows-1250', and `iso-8859-1', which is compatible with Latin 2 | |
| 188 when used to write German (or English, of course). " | |
| 189 '(mnemonic "Latin 2" | |
| 190 aliases (iso-latin-2 latin-2))) | |
| 3767 | 191 |
| 192 ;; | |
| 193 ;; Latin-3 (ISO-8859-3). Esperanto, Maltese and Turkish. Obsolescent. | |
| 464 | 194 |
| 3767 | 195 ;; Initialise the non-word syntax codes in ISO-8859-3, copying them from |
| 196 ;; ISO-8859-1. | |
| 197 (loop | |
| 198 for (latin-3 latin-1) | |
| 199 in '((#xA0 #xA0) ;; NO BREAK SPACE | |
| 200 (#xA2 #xB4) ;; BREVE, ACUTE ACCENT | |
| 201 (#xA3 #xA3) ;; POUND SIGN | |
| 202 (#xA4 #xA4) ;; CURRENCY SIGN | |
| 203 (#xA7 #xA7) ;; SECTION SIGN | |
| 204 (#xA8 #xA8) ;; DIAERESIS | |
| 205 (#xAD #xAD) ;; SOFT HYPHEN | |
| 206 (#xB0 #xB0) ;; DEGREE SIGN | |
| 207 (#xB2 #xB2) ;; SUPERSCRIPT TWO | |
| 208 (#xB3 #xB3) ;; SUPERSCRIPT THREE | |
| 209 (#xB4 #xB4) ;; ACUTE ACCENT | |
| 210 (#xB5 #xB5) ;; MICRO SIGN | |
| 211 (#xB7 #xB7) ;; MIDDLE DOT | |
| 212 (#xB8 #xB8) ;; CEDILLA | |
| 213 (#xBD #xBD) ;; VULGAR FRACTION ONE HALF | |
| 214 (#xD7 #xD7) ;; MULTIPLICATION SIGN | |
| 215 (#xF7 #xF7) ;; DIVISION SIGN | |
| 216 (#xFF #xB4)) ;; DOT ABOVE, ACUTE ACCENT | |
| 217 with syntax-table = (standard-syntax-table) | |
| 218 do (modify-syntax-entry | |
| 219 (make-char 'latin-iso8859-3 latin-3) | |
| 220 (string (char-syntax (make-char 'latin-iso8859-1 latin-1))) | |
| 221 syntax-table)) | |
| 222 | |
| 223 ;; Case. | |
| 464 | 224 (setup-case-pairs |
| 225 'latin-iso8859-3 | |
| 3767 | 226 '((#xA1 #xB1) ;; H WITH STROKE |
| 227 (#xA6 #xB6) ;; H WITH CIRCUMFLEX | |
| 228 (#xAA #xBA) ;; S WITH CEDILLA | |
| 229 (#xAB #xBB) ;; G WITH BREVE | |
| 230 (#xAC #xBC) ;; J WITH CIRCUMFLEX | |
| 231 (#xAF #xBF) ;; Z WITH DOT ABOVE | |
| 232 (#xC0 #xE0) ;; A WITH GRAVE | |
| 233 (#xC1 #xE1) ;; A WITH ACUTE | |
| 234 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 235 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 236 (#xC5 #xE5) ;; C WITH DOT ABOVE | |
| 237 (#xC6 #xE6) ;; C WITH CIRCUMFLEX | |
| 238 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 239 (#xC8 #xE8) ;; E WITH GRAVE | |
| 240 (#xC9 #xE9) ;; E WITH ACUTE | |
| 241 (#xCA #xEA) ;; E WITH CIRCUMFLEX | |
| 242 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 243 (#xCC #xEC) ;; I WITH GRAVE | |
| 244 (#xCD #xED) ;; I WITH ACUTE | |
| 245 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 246 (#xCF #xEF) ;; I WITH DIAERESIS | |
| 247 (#xD1 #xF1) ;; N WITH TILDE | |
| 248 (#xD2 #xF2) ;; O WITH GRAVE | |
| 249 (#xD3 #xF3) ;; O WITH ACUTE | |
| 250 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 251 (#xD5 #xF5) ;; G WITH DOT ABOVE | |
| 252 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 253 (#xD8 #xF8) ;; G WITH CIRCUMFLEX | |
| 254 (#xD9 #xF9) ;; U WITH GRAVE | |
| 255 (#xDA #xFA) ;; U WITH ACUTE | |
| 256 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 257 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 258 (#xDD #xFD) ;; U WITH BREVE | |
| 259 (#xDE #xFE))) ;; S WITH CIRCUMFLEX | |
| 464 | 260 |
| 4299 | 261 (make-8-bit-coding-system |
| 262 'iso-8859-3 | |
| 263 '((#xA1 ?\u0126) ;; LATIN CAPITAL LETTER H WITH STROKE | |
| 264 (#xA2 ?\u02D8) ;; BREVE | |
| 265 (#xA6 ?\u0124) ;; LATIN CAPITAL LETTER H WITH CIRCUMFLEX | |
| 266 (#xA9 ?\u0130) ;; LATIN CAPITAL LETTER I WITH DOT ABOVE | |
| 267 (#xAA ?\u015E) ;; LATIN CAPITAL LETTER S WITH CEDILLA | |
| 268 (#xAB ?\u011E) ;; LATIN CAPITAL LETTER G WITH BREVE | |
| 269 (#xAC ?\u0134) ;; LATIN CAPITAL LETTER J WITH CIRCUMFLEX | |
| 270 (#xAF ?\u017B) ;; LATIN CAPITAL LETTER Z WITH DOT ABOVE | |
| 271 (#xB1 ?\u0127) ;; LATIN SMALL LETTER H WITH STROKE | |
| 272 (#xB6 ?\u0125) ;; LATIN SMALL LETTER H WITH CIRCUMFLEX | |
| 273 (#xB9 ?\u0131) ;; LATIN SMALL LETTER DOTLESS I | |
| 274 (#xBA ?\u015F) ;; LATIN SMALL LETTER S WITH CEDILLA | |
| 275 (#xBB ?\u011F) ;; LATIN SMALL LETTER G WITH BREVE | |
| 276 (#xBC ?\u0135) ;; LATIN SMALL LETTER J WITH CIRCUMFLEX | |
| 277 (#xBF ?\u017C) ;; LATIN SMALL LETTER Z WITH DOT ABOVE | |
| 278 (#xC5 ?\u010A) ;; LATIN CAPITAL LETTER C WITH DOT ABOVE | |
| 279 (#xC6 ?\u0108) ;; LATIN CAPITAL LETTER C WITH CIRCUMFLEX | |
| 280 (#xD5 ?\u0120) ;; LATIN CAPITAL LETTER G WITH DOT ABOVE | |
| 281 (#xD8 ?\u011C) ;; LATIN CAPITAL LETTER G WITH CIRCUMFLEX | |
| 282 (#xDD ?\u016C) ;; LATIN CAPITAL LETTER U WITH BREVE | |
| 283 (#xDE ?\u015C) ;; LATIN CAPITAL LETTER S WITH CIRCUMFLEX | |
| 284 (#xE5 ?\u010B) ;; LATIN SMALL LETTER C WITH DOT ABOVE | |
| 285 (#xE6 ?\u0109) ;; LATIN SMALL LETTER C WITH CIRCUMFLEX | |
| 286 (#xF5 ?\u0121) ;; LATIN SMALL LETTER G WITH DOT ABOVE | |
| 287 (#xF8 ?\u011D) ;; LATIN SMALL LETTER G WITH CIRCUMFLEX | |
| 288 (#xFD ?\u016D) ;; LATIN SMALL LETTER U WITH BREVE | |
| 289 (#xFE ?\u015D) ;; LATIN SMALL LETTER S WITH CIRCUMFLEX | |
| 290 (#xFF ?\u02D9)) ;; DOT ABOVE | |
| 291 "ISO-8859-3 (Latin-3)" | |
| 292 '(mnemonic "Latin 3" | |
| 293 documentation "Aimed at Turkish, Maltese and Esperanto. " | |
| 294 aliases (iso-latin-3 latin-3))) | |
| 3767 | 295 |
| 296 | |
| 297 ;; Latin-4 (ISO-8859-4) | |
| 298 | |
| 299 ;; Estonian, Latvian, Lithuanian, Greenlandic, and Sami. Obsolescent. | |
| 464 | 300 |
| 3767 | 301 ;; The default character syntax is now word. Pay attention to the |
| 302 ;; exceptions in ISO-8859-4, copying them from ISO-8859-1. | |
| 303 (loop | |
| 304 for (latin-4 latin-1) | |
| 305 in '((#xA0 #xA0) ;; NO BREAK SPACE | |
| 306 (#xA4 #xA4) ;; CURRENCY SIGN | |
| 307 (#xA7 #xA7) ;; SECTION SIGN | |
| 308 (#xA8 #xA8) ;; DIAERESIS | |
| 309 (#xAD #xAD) ;; SOFT HYPHEN | |
| 310 (#xB0 #xB0) ;; DEGREE SIGN | |
| 311 (#xB2 #xB4) ;; OGONEK, ACUTE ACCENT | |
| 312 (#xB4 #xB4) ;; ACUTE ACCENT | |
| 313 (#xB7 #xB4) ;; CARON, ACUTE ACCENT | |
| 314 (#xB8 #xB8) ;; CEDILLA | |
| 315 (#xD7 #xD7) ;; MULTIPLICATION SIGN | |
| 316 (#xF7 #xF7) ;; DIVISION SIGN | |
| 317 (#xFF #xB4)) ;; DOT ABOVE, ACUTE ACCENT | |
| 318 with syntax-table = (standard-syntax-table) | |
| 319 do (modify-syntax-entry | |
| 320 (make-char 'latin-iso8859-4 latin-4) | |
| 321 (string (char-syntax (make-char 'latin-iso8859-1 latin-1))) | |
| 322 syntax-table)) | |
| 323 | |
| 324 ;; Case. | |
| 464 | 325 (setup-case-pairs |
| 326 'latin-iso8859-4 | |
| 3767 | 327 '((#xA1 #xB1) ;; A WITH OGONEK |
| 328 (#xA3 #xB3) ;; R WITH CEDILLA | |
| 329 (#xA5 #xB5) ;; I WITH TILDE | |
| 330 (#xA6 #xB6) ;; L WITH CEDILLA | |
| 331 (#xA9 #xB9) ;; S WITH CARON | |
| 332 (#xAA #xBA) ;; E WITH MACRON | |
| 333 (#xAB #xBB) ;; G WITH CEDILLA | |
| 334 (#xAC #xBC) ;; T WITH STROKE | |
| 335 (#xAE #xBE) ;; Z WITH CARON | |
| 336 (#xBD #xBF) ;; ENG | |
| 337 (#xC0 #xE0) ;; A WITH MACRON | |
| 338 (#xC1 #xE1) ;; A WITH ACUTE | |
| 339 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 340 (#xC3 #xE3) ;; A WITH TILDE | |
| 341 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 342 (#xC5 #xE5) ;; A WITH RING ABOVE | |
| 343 (#xC6 #xE6) ;; AE | |
| 344 (#xC7 #xE7) ;; I WITH OGONEK | |
| 345 (#xC8 #xE8) ;; C WITH CARON | |
| 346 (#xC9 #xE9) ;; E WITH ACUTE | |
| 347 (#xCA #xEA) ;; E WITH OGONEK | |
| 348 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 349 (#xCC #xEC) ;; E WITH DOT ABOVE | |
| 350 (#xCD #xED) ;; I WITH ACUTE | |
| 351 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 352 (#xCF #xEF) ;; I WITH MACRON | |
| 353 (#xD0 #xF0) ;; D WITH STROKE | |
| 354 (#xD1 #xF1) ;; N WITH CEDILLA | |
| 355 (#xD2 #xF2) ;; O WITH MACRON | |
| 356 (#xD3 #xF3) ;; K WITH CEDILLA | |
| 357 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 358 (#xD5 #xF5) ;; O WITH TILDE | |
| 359 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 360 (#xD8 #xF8) ;; O WITH STROKE | |
| 361 (#xD9 #xF9) ;; U WITH OGONEK | |
| 362 (#xDA #xFA) ;; U WITH ACUTE | |
| 363 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 364 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 365 (#xDD #xFD) ;; U WITH TILDE | |
| 366 (#xDE #xFE))) ;; U WITH MACRON | |
| 367 | |
| 4299 | 368 (make-8-bit-coding-system |
| 369 'iso-8859-4 | |
| 370 '((#xA1 ?\u0104) ;; LATIN CAPITAL LETTER A WITH OGONEK | |
| 371 (#xA2 ?\u0138) ;; LATIN SMALL LETTER KRA | |
| 372 (#xA3 ?\u0156) ;; LATIN CAPITAL LETTER R WITH CEDILLA | |
| 373 (#xA5 ?\u0128) ;; LATIN CAPITAL LETTER I WITH TILDE | |
| 374 (#xA6 ?\u013B) ;; LATIN CAPITAL LETTER L WITH CEDILLA | |
| 375 (#xA9 ?\u0160) ;; LATIN CAPITAL LETTER S WITH CARON | |
| 376 (#xAA ?\u0112) ;; LATIN CAPITAL LETTER E WITH MACRON | |
| 377 (#xAB ?\u0122) ;; LATIN CAPITAL LETTER G WITH CEDILLA | |
| 378 (#xAC ?\u0166) ;; LATIN CAPITAL LETTER T WITH STROKE | |
| 379 (#xAE ?\u017D) ;; LATIN CAPITAL LETTER Z WITH CARON | |
| 380 (#xB1 ?\u0105) ;; LATIN SMALL LETTER A WITH OGONEK | |
| 381 (#xB2 ?\u02DB) ;; OGONEK | |
| 382 (#xB3 ?\u0157) ;; LATIN SMALL LETTER R WITH CEDILLA | |
| 383 (#xB5 ?\u0129) ;; LATIN SMALL LETTER I WITH TILDE | |
| 384 (#xB6 ?\u013C) ;; LATIN SMALL LETTER L WITH CEDILLA | |
| 385 (#xB7 ?\u02C7) ;; CARON | |
| 386 (#xB9 ?\u0161) ;; LATIN SMALL LETTER S WITH CARON | |
| 387 (#xBA ?\u0113) ;; LATIN SMALL LETTER E WITH MACRON | |
| 388 (#xBB ?\u0123) ;; LATIN SMALL LETTER G WITH CEDILLA | |
| 389 (#xBC ?\u0167) ;; LATIN SMALL LETTER T WITH STROKE | |
| 390 (#xBD ?\u014A) ;; LATIN CAPITAL LETTER ENG | |
| 391 (#xBE ?\u017E) ;; LATIN SMALL LETTER Z WITH CARON | |
| 392 (#xBF ?\u014B) ;; LATIN SMALL LETTER ENG | |
| 393 (#xC0 ?\u0100) ;; LATIN CAPITAL LETTER A WITH MACRON | |
| 394 (#xC7 ?\u012E) ;; LATIN CAPITAL LETTER I WITH OGONEK | |
| 395 (#xC8 ?\u010C) ;; LATIN CAPITAL LETTER C WITH CARON | |
| 396 (#xCA ?\u0118) ;; LATIN CAPITAL LETTER E WITH OGONEK | |
| 397 (#xCC ?\u0116) ;; LATIN CAPITAL LETTER E WITH DOT ABOVE | |
| 398 (#xCF ?\u012A) ;; LATIN CAPITAL LETTER I WITH MACRON | |
| 399 (#xD0 ?\u0110) ;; LATIN CAPITAL LETTER D WITH STROKE | |
| 400 (#xD1 ?\u0145) ;; LATIN CAPITAL LETTER N WITH CEDILLA | |
| 401 (#xD2 ?\u014C) ;; LATIN CAPITAL LETTER O WITH MACRON | |
| 402 (#xD3 ?\u0136) ;; LATIN CAPITAL LETTER K WITH CEDILLA | |
| 403 (#xD9 ?\u0172) ;; LATIN CAPITAL LETTER U WITH OGONEK | |
| 404 (#xDD ?\u0168) ;; LATIN CAPITAL LETTER U WITH TILDE | |
| 405 (#xDE ?\u016A) ;; LATIN CAPITAL LETTER U WITH MACRON | |
| 406 (#xE0 ?\u0101) ;; LATIN SMALL LETTER A WITH MACRON | |
| 407 (#xE7 ?\u012F) ;; LATIN SMALL LETTER I WITH OGONEK | |
| 408 (#xE8 ?\u010D) ;; LATIN SMALL LETTER C WITH CARON | |
| 409 (#xEA ?\u0119) ;; LATIN SMALL LETTER E WITH OGONEK | |
| 410 (#xEC ?\u0117) ;; LATIN SMALL LETTER E WITH DOT ABOVE | |
| 411 (#xEF ?\u012B) ;; LATIN SMALL LETTER I WITH MACRON | |
| 412 (#xF0 ?\u0111) ;; LATIN SMALL LETTER D WITH STROKE | |
| 413 (#xF1 ?\u0146) ;; LATIN SMALL LETTER N WITH CEDILLA | |
| 414 (#xF2 ?\u014D) ;; LATIN SMALL LETTER O WITH MACRON | |
| 415 (#xF3 ?\u0137) ;; LATIN SMALL LETTER K WITH CEDILLA | |
| 416 (#xF9 ?\u0173) ;; LATIN SMALL LETTER U WITH OGONEK | |
| 417 (#xFD ?\u0169) ;; LATIN SMALL LETTER U WITH TILDE | |
| 418 (#xFE ?\u016B) ;; LATIN SMALL LETTER U WITH MACRON | |
| 419 (#xFF ?\u02D9));; DOT ABOVE | |
| 420 "ISO-8859-4 (Latin-4)" | |
| 421 '(mnemonic "Latin 4" | |
| 422 aliases (iso-latin-4 latin-4) | |
| 423 documentation "Obsolete coding system for the Baltic rim. ")) | |
| 3767 | 424 |
| 425 | |
| 426 ;; Latin-8 (ISO 8859-14) Celtic. | |
| 427 | |
| 428 ;; Never widely used. Current-orthography Gaelic, both Irish and Scots, is | |
| 429 ;; easily written with Latin-1. Wikipedia says the same about Welsh. | |
| 430 | |
| 431 (make-charset 'latin-iso8859-14 | |
| 432 "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)" | |
| 433 '(dimension 1 | |
| 434 registries ["ISO8859-14"] | |
| 435 chars 96 | |
| 436 columns 1 | |
| 437 direction l2r | |
| 438 final ?_ | |
| 439 graphic 1 | |
| 440 short-name "RHP of Latin-8" | |
| 441 long-name "RHP of Latin-8 (ISO 8859-14)")) | |
| 464 | 442 |
| 3767 | 443 ;; |
| 444 ;; Character syntax defaults to word. The exceptions here shared with Latin-1. | |
| 445 (dolist (code '(#xa0 ;; NO BREAK SPACE | |
| 446 #xa3 ;; POUND SIGN | |
| 447 #xa7 ;; SECTION SIGN | |
| 448 #xa9 ;; COPYRIGHT | |
| 449 #xad ;; SOFT HYPHEN | |
| 450 #xae ;; REGISTERED | |
| 451 #xb6)) ;; PILCROW SIGN | |
| 452 (modify-syntax-entry (make-char 'latin-iso8859-14 code) | |
| 453 (string (char-syntax (make-char 'latin-iso8859-1 code))) | |
| 454 (standard-syntax-table))) | |
| 455 ;; Case. | |
| 456 (setup-case-pairs | |
| 457 'latin-iso8859-14 | |
| 458 '((#xA1 #xA2) ;; B WITH DOT ABOVE | |
| 459 (#xA4 #xA5) ;; C WITH DOT ABOVE | |
| 460 (#xA6 #xAB) ;; D WITH DOT ABOVE | |
| 461 (#xA8 #xB8) ;; W WITH GRAVE | |
| 462 (#xAA #xBA) ;; W WITH ACUTE | |
| 463 (#xAC #xBC) ;; Y WITH GRAVE | |
| 464 (#xAF #xFF) ;; Y WITH DIAERESIS | |
| 465 (#xB0 #xB1) ;; F WITH DOT ABOVE | |
| 466 (#xB2 #xB3) ;; G WITH DOT ABOVE | |
| 467 (#xB4 #xB5) ;; M WITH DOT ABOVE | |
| 468 (#xB7 #xB9) ;; P WITH DOT ABOVE | |
| 469 (#xBB #xBF) ;; S WITH DOT ABOVE | |
| 470 (#xBD #xBE) ;; W WITH DIAERESIS | |
| 471 (#xC0 #xE0) ;; A WITH GRAVE | |
| 472 (#xC1 #xE1) ;; A WITH ACUTE | |
| 473 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 474 (#xC3 #xE3) ;; A WITH TILDE | |
| 475 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 476 (#xC5 #xE5) ;; A WITH RING ABOVE | |
| 477 (#xC6 #xE6) ;; AE | |
| 478 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 479 (#xC8 #xE8) ;; E WITH GRAVE | |
| 480 (#xC9 #xE9) ;; E WITH ACUTE | |
| 481 (#xCA #xEA) ;; E WITH CIRCUMFLEX | |
| 482 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 483 (#xCC #xEC) ;; I WITH GRAVE | |
| 484 (#xCD #xED) ;; I WITH ACUTE | |
| 485 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 486 (#xCF #xEF) ;; I WITH DIAERESIS | |
| 487 (#xD0 #xF0) ;; W WITH CIRCUMFLEX | |
| 488 (#xD1 #xF1) ;; N WITH TILDE | |
| 489 (#xD2 #xF2) ;; O WITH GRAVE | |
| 490 (#xD3 #xF3) ;; O WITH ACUTE | |
| 491 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 492 (#xD5 #xF5) ;; O WITH TILDE | |
| 493 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 494 (#xD7 #xF7) ;; T WITH DOT ABOVE | |
| 495 (#xD8 #xF8) ;; O WITH STROKE | |
| 496 (#xD9 #xF9) ;; U WITH GRAVE | |
| 497 (#xDA #xFA) ;; U WITH ACUTE | |
| 498 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 499 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 500 (#xDD #xFD) ;; Y WITH ACUTE | |
| 501 (#xDE #xFE))) ;; Y WITH CIRCUMFLEX | |
| 464 | 502 |
| 3767 | 503 |
| 504 ;; The syntax table code for ISO 8859-15 and ISO 8859-16 requires that the | |
| 505 ;; guillemets not have parenthesis syntax, which they used to have in the | |
| 506 ;; past. See syntax.c:complex_vars_of_syntax. | |
| 507 (assert (not (memq (char-syntax (make-char 'latin-iso8859-1 #xAB)) '(?\( ?\)))) | |
| 508 t "This code assumes \xAB does not have parenthesis syntax. ") | |
| 509 | |
| 510 (assert (not (memq (char-syntax (make-char 'latin-iso8859-1 #xBB)) '(?\( ?\)))) | |
| 511 t "This code assumes \xBB does not have parenthesis syntax. ") | |
| 512 | |
| 513 | |
| 514 ;; Latin-9 (ISO-8859-15) | |
| 515 ;; | |
| 516 ;; Latin-1 plus Euro, plus a few accented characters for the sake of correct | |
| 517 ;; Finnish and French orthography. Only ever widely used on Unix. | |
| 2765 | 518 |
| 3767 | 519 ;; |
| 520 ;; Based on Latin-1 and differences therefrom. | |
| 521 ;; | |
| 522 ;; First, initialise the syntax from the corresponding Latin-1 characters. | |
| 523 (loop | |
| 524 for c from #xa0 to #xff | |
| 525 with syntax-table = (standard-syntax-table) | |
| 526 do (modify-syntax-entry | |
| 527 (make-char 'latin-iso8859-15 c) | |
| 528 (string (char-syntax (make-char 'latin-iso8859-1 c))) | |
| 529 syntax-table)) | |
| 530 | |
| 531 ;; Now, the exceptions. The Euro sign retains the syntax of CURRENCY SIGN. | |
| 532 (loop | |
| 533 for c in '(?,b&(B ?,b((B ?,b4(B ?,b8(B ?,b<(B ?,b=(B ?,b>(B) | |
| 534 with syntax-table = (standard-syntax-table) | |
| 535 do (modify-syntax-entry c "w" syntax-table)) | |
| 536 | |
| 537 ;; Case. | |
| 2765 | 538 (setup-case-pairs |
| 539 'latin-iso8859-15 | |
| 3767 | 540 '((#xA6 #xA8) ;; S WITH CARON * |
| 541 (#xB4 #xB8) ;; Z WITH CARON * | |
| 542 (#xBC #xBD) ;; LATIN LIGATURE OE * | |
| 543 (#xBE #xFF) ;; Y WITH DIAERESIS * | |
| 544 (#xC0 #xE0) ;; A WITH GRAVE | |
| 545 (#xC1 #xE1) ;; A WITH ACUTE | |
| 546 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 547 (#xC3 #xE3) ;; A WITH TILDE | |
| 548 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 549 (#xC5 #xE5) ;; A WITH RING ABOVE | |
| 550 (#xC6 #xE6) ;; AE | |
| 551 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 552 (#xC8 #xE8) ;; E WITH GRAVE | |
| 553 (#xC9 #xE9) ;; E WITH ACUTE | |
| 554 (#xCA #xEA) ;; E WITH CIRCUMFLEX | |
| 555 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 556 (#xCC #xEC) ;; I WITH GRAVE | |
| 557 (#xCD #xED) ;; I WITH ACUTE | |
| 558 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 559 (#xCF #xEF) ;; I WITH DIAERESIS | |
| 560 (#xD0 #xF0) ;; ETH | |
| 561 (#xD1 #xF1) ;; N WITH TILDE | |
| 562 (#xD2 #xF2) ;; O WITH GRAVE | |
| 563 (#xD3 #xF3) ;; O WITH ACUTE | |
| 564 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 565 (#xD5 #xF5) ;; O WITH TILDE | |
| 566 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 567 (#xD8 #xF8) ;; O WITH STROKE | |
| 568 (#xD9 #xF9) ;; U WITH GRAVE | |
| 569 (#xDA #xFA) ;; U WITH ACUTE | |
| 570 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 571 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 572 (#xDD #xFD) ;; Y WITH ACUTE | |
| 573 (#xDE #xFE))) ;; THORN | |
| 574 | |
| 4299 | 575 (make-8-bit-coding-system |
| 576 'iso-8859-15 | |
| 577 '((#xA4 ?\u20AC) ;; EURO SIGN | |
| 578 (#xA6 ?\u0160) ;; LATIN CAPITAL LETTER S WITH CARON | |
| 579 (#xA8 ?\u0161) ;; LATIN SMALL LETTER S WITH CARON | |
| 580 (#xB4 ?\u017D) ;; LATIN CAPITAL LETTER Z WITH CARON | |
| 581 (#xB8 ?\u017E) ;; LATIN SMALL LETTER Z WITH CARON | |
| 582 (#xBC ?\u0152) ;; LATIN CAPITAL LIGATURE OE | |
| 583 (#xBD ?\u0153) ;; LATIN SMALL LIGATURE OE | |
| 584 (#xBE ?\u0178)) ;; LATIN CAPITAL LETTER Y WITH DIAERESIS | |
| 585 "ISO 4873 conforming 8-bit code (ASCII + Latin 9; aka Latin-1 with Euro)" | |
| 586 '(mnemonic "Latin 9" | |
| 587 aliases (iso-latin-9 latin-9 latin-0))) | |
| 2765 | 588 |
| 3767 | 589 ;; end of ISO 8859-15. |
| 590 | |
| 591 ;; | |
| 592 ;; Latin-10 (ISO 8859-16). | |
| 593 ;; | |
| 594 ;; "South-Eastern European." Not, to my knowledge, ever widely used. | |
| 595 | |
| 596 (make-charset 'latin-iso8859-16 | |
| 597 "Right-Hand Part of Latin Alphabet 10 (ISO/IEC 8859-16)" | |
| 598 '(dimension 1 | |
| 599 registries ["ISO8859-16"] | |
| 600 chars 96 | |
| 601 columns 1 | |
| 602 direction l2r | |
| 603 final ?f ; octet 06/06; cf ISO-IR 226 | |
| 604 graphic 1 | |
| 605 short-name "RHP of Latin-10" | |
| 606 long-name "RHP of Latin-10 (ISO 8859-16)")) | |
| 2765 | 607 |
| 3767 | 608 ;; Copy over the non-word syntax this charset has in common with Latin 1. |
| 609 (dolist (code '(#xa0 ;; NO BREAK SPACE | |
| 610 #xa7 ;; SECTION SIGN | |
| 611 #xa9 ;; COPYRIGHT | |
| 612 #xab ;; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK | |
| 613 #xad ;; SOFT HYPHEN | |
| 614 #xb0 ;; DEGREE | |
| 615 #xb1 ;; PLUS-MINUS SIGN | |
| 616 #xb6 ;; PILCROW SIGN | |
| 617 #xb7 ;; MIDDLE DOT | |
| 618 #xbb)) ;; RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK | |
| 619 (modify-syntax-entry (make-char 'latin-iso8859-16 code) | |
| 620 (string (char-syntax (make-char 'latin-iso8859-1 code))) | |
| 621 (standard-syntax-table))) | |
| 622 | |
| 623 ;; EURO SIGN. Take its syntax from the pound sign. | |
| 624 (modify-syntax-entry (make-char 'latin-iso8859-16 #xa4) | |
| 625 (string (char-syntax (make-char 'latin-iso8859-1 #xa3))) | |
| 626 (standard-syntax-table)) | |
| 627 | |
| 628 ;; Take DOUBLE LOW-9 QUOTATION MARK's syntax from that of LEFT-POINTING | |
| 629 ;; DOUBLE ANGLE QUOTATION MARK. | |
| 630 (modify-syntax-entry (make-char 'latin-iso8859-16 #xa5) | |
| 631 (string (char-syntax (make-char 'latin-iso8859-1 #xab))) | |
| 632 (standard-syntax-table)) | |
| 633 | |
| 634 ;; Take RIGHT DOUBLE QUOTATION MARK's syntax from that of RIGHT-POINTING | |
| 635 ;; DOUBLE ANGLE QUOTATION MARK. | |
| 636 (modify-syntax-entry (make-char 'latin-iso8859-16 #xb5) | |
| 637 (string (char-syntax (make-char 'latin-iso8859-1 #xbb))) | |
| 638 (standard-syntax-table)) | |
| 639 | |
| 640 ;; Case. | |
| 2765 | 641 (setup-case-pairs |
| 642 'latin-iso8859-16 | |
| 3767 | 643 '((#xA1 #xA2) ;; A WITH OGONEK |
| 644 (#xA3 #xB3) ;; L WITH STROKE | |
| 645 (#xA6 #xA8) ;; S WITH CARON | |
| 646 (#xAA #xBA) ;; S WITH COMMA BELOW | |
| 647 (#xAC #xAE) ;; Z WITH ACUTE | |
| 648 (#xAF #xBF) ;; Z WITH DOT ABOVE | |
| 649 (#xB2 #xB9) ;; C WITH CARON | |
| 650 (#xB4 #xB8) ;; Z WITH CARON | |
| 651 (#xBE #xFF) ;; Y WITH DIAERESIS | |
| 652 (#xC0 #xE0) ;; A WITH GRAVE | |
| 653 (#xC1 #xE1) ;; A WITH ACUTE | |
| 654 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 655 (#xC3 #xE3) ;; A WITH BREVE | |
| 656 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 657 (#xC5 #xE5) ;; C WITH ACUTE | |
| 658 (#xC6 #xE6) ;; AE | |
| 659 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 660 (#xC8 #xE8) ;; E WITH GRAVE | |
| 661 (#xC9 #xE9) ;; E WITH ACUTE | |
| 662 (#xCA #xEA) ;; E WITH CIRCUMFLEX | |
| 663 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 664 (#xCC #xEC) ;; I WITH GRAVE | |
| 665 (#xCD #xED) ;; I WITH ACUTE | |
| 666 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 667 (#xCF #xEF) ;; I WITH DIAERESIS | |
| 668 (#xD0 #xF0) ;; D WITH STROKE | |
| 669 (#xD1 #xF1) ;; N WITH ACUTE | |
| 670 (#xD2 #xF2) ;; O WITH GRAVE | |
| 671 (#xD3 #xF3) ;; O WITH ACUTE | |
| 672 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 673 (#xD5 #xF5) ;; O WITH DOUBLE ACUTE | |
| 674 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 675 (#xD7 #xF7) ;; S WITH ACUTE | |
| 676 (#xD8 #xF8) ;; U WITH DOUBLE ACUTE | |
| 677 (#xD9 #xF9) ;; U WITH GRAVE | |
| 678 (#xDA #xFA) ;; U WITH ACUTE | |
| 679 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 680 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 681 (#xDD #xFD) ;; E WITH OGONEK | |
| 682 (#xDE #xFE))) ;; T WITH COMMA BELOW | |
| 683 | |
| 684 ;; Add a coding system for ISO 8859-16. | |
| 4299 | 685 (make-8-bit-coding-system |
| 686 'iso-8859-16 | |
| 687 '((#xA1 ?\u0104) ;; LATIN CAPITAL LETTER A WITH OGONEK | |
| 688 (#xA2 ?\u0105) ;; LATIN SMALL LETTER A WITH OGONEK | |
| 689 (#xA3 ?\u0141) ;; LATIN CAPITAL LETTER L WITH STROKE | |
| 690 (#xA4 ?\u20AC) ;; EURO SIGN | |
| 691 (#xA5 ?\u201E) ;; DOUBLE LOW-9 QUOTATION MARK | |
| 692 (#xA6 ?\u0160) ;; LATIN CAPITAL LETTER S WITH CARON | |
| 693 (#xA8 ?\u0161) ;; LATIN SMALL LETTER S WITH CARON | |
| 694 (#xAA ?\u0218) ;; LATIN CAPITAL LETTER S WITH COMMA BELOW | |
| 695 (#xAC ?\u0179) ;; LATIN CAPITAL LETTER Z WITH ACUTE | |
| 696 (#xAE ?\u017A) ;; LATIN SMALL LETTER Z WITH ACUTE | |
| 697 (#xAF ?\u017B) ;; LATIN CAPITAL LETTER Z WITH DOT ABOVE | |
| 698 (#xB2 ?\u010C) ;; LATIN CAPITAL LETTER C WITH CARON | |
| 699 (#xB3 ?\u0142) ;; LATIN SMALL LETTER L WITH STROKE | |
| 700 (#xB4 ?\u017D) ;; LATIN CAPITAL LETTER Z WITH CARON | |
| 701 (#xB5 ?\u201D) ;; RIGHT DOUBLE QUOTATION MARK | |
| 702 (#xB8 ?\u017E) ;; LATIN SMALL LETTER Z WITH CARON | |
| 703 (#xB9 ?\u010D) ;; LATIN SMALL LETTER C WITH CARON | |
| 704 (#xBA ?\u0219) ;; LATIN SMALL LETTER S WITH COMMA BELOW | |
| 705 (#xBC ?\u0152) ;; LATIN CAPITAL LIGATURE OE | |
| 706 (#xBD ?\u0153) ;; LATIN SMALL LIGATURE OE | |
| 707 (#xBE ?\u0178) ;; LATIN CAPITAL LETTER Y WITH DIAERESIS | |
| 708 (#xBF ?\u017C) ;; LATIN SMALL LETTER Z WITH DOT ABOVE | |
| 709 (#xC3 ?\u0102) ;; LATIN CAPITAL LETTER A WITH BREVE | |
| 710 (#xC5 ?\u0106) ;; LATIN CAPITAL LETTER C WITH ACUTE | |
| 711 (#xD0 ?\u0110) ;; LATIN CAPITAL LETTER D WITH STROKE | |
| 712 (#xD1 ?\u0143) ;; LATIN CAPITAL LETTER N WITH ACUTE | |
| 713 (#xD5 ?\u0150) ;; LATIN CAPITAL LETTER O WITH DOUBLE ACUTE | |
| 714 (#xD7 ?\u015A) ;; LATIN CAPITAL LETTER S WITH ACUTE | |
| 715 (#xD8 ?\u0170) ;; LATIN CAPITAL LETTER U WITH DOUBLE ACUTE | |
| 716 (#xDD ?\u0118) ;; LATIN CAPITAL LETTER E WITH OGONEK | |
| 717 (#xDE ?\u021A) ;; LATIN CAPITAL LETTER T WITH COMMA BELOW | |
| 718 (#xE3 ?\u0103) ;; LATIN SMALL LETTER A WITH BREVE | |
| 719 (#xE5 ?\u0107) ;; LATIN SMALL LETTER C WITH ACUTE | |
| 720 (#xF0 ?\u0111) ;; LATIN SMALL LETTER D WITH STROKE | |
| 721 (#xF1 ?\u0144) ;; LATIN SMALL LETTER N WITH ACUTE | |
| 722 (#xF5 ?\u0151) ;; LATIN SMALL LETTER O WITH DOUBLE ACUTE | |
| 723 (#xF7 ?\u015B) ;; LATIN SMALL LETTER S WITH ACUTE | |
| 724 (#xF8 ?\u0171) ;; LATIN SMALL LETTER U WITH DOUBLE ACUTE | |
| 725 (#xFD ?\u0119) ;; LATIN SMALL LETTER E WITH OGONEK | |
| 726 (#xFE ?\u021B)) ;; LATIN SMALL LETTER T WITH COMMA BELOW | |
| 727 "ISO-8859-16 (Latin-10)" | |
| 728 '(mnemonic "Latin 10" | |
| 729 aliases (iso-latin-10))) | |
| 3767 | 730 |
| 731 ;; end of ISO 8859-16. | |
| 732 | |
| 733 | |
| 734 (provide 'romanian) | |
| 735 | |
| 736 ;; Czech support originally from czech.el | |
| 737 ;; Author: Milan Zamazal <pdm@zamazal.org> | |
| 738 ;; Maintainer (FSF): Pavel Jan,Am(Bk <Pavel@Janik.cz> | |
| 739 ;; Maintainer (for XEmacs): David Sauer <davids@penguin.cz> | |
| 740 | |
| 741 (provide 'czech) | |
| 742 | |
| 743 ;; Slovak support originally from slovak.el | |
| 744 ;; Authors: Tibor ,B)(Bimko <tibor.simko@fmph.uniba.sk>, | |
| 745 ;; Milan Zamazal <pdm@fi.muni.cz> | |
| 746 ;; Maintainer: Milan Zamazal <pdm@fi.muni.cz> | |
| 747 | |
| 748 (provide 'slovenian) | |
| 749 | |
| 750 ;; Latin-5 (ISO-8859-9) | |
| 751 | |
| 752 ;; Turkish (more generally Turkic.) This is identical to Latin-1, with the | |
| 753 ;; exception that the Icelandic-specific letters have been replaced by | |
| 754 ;; Turkish-specific letters. As such, we can simply copy the Latin-1 syntax | |
| 755 ;; table. | |
| 756 | |
| 757 (loop | |
| 758 for i from #xA0 to #xFF | |
| 759 with syntax-table = (standard-syntax-table) | |
| 760 do (modify-syntax-entry | |
| 761 (make-char 'latin-iso8859-9 i) | |
| 762 (string (char-syntax (make-char 'latin-iso8859-1 i))) | |
| 763 syntax-table)) | |
| 764 | |
| 4145 | 765 ;; Case. The Turkish case idiosyncracy is handled with its language environment. |
| 3767 | 766 (setup-case-pairs |
| 767 'latin-iso8859-9 | |
| 768 '((#xC0 #xE0) ;; A WITH GRAVE | |
| 769 (#xC1 #xE1) ;; A WITH ACUTE | |
| 770 (#xC2 #xE2) ;; A WITH CIRCUMFLEX | |
| 771 (#xC3 #xE3) ;; A WITH TILDE | |
| 772 (#xC4 #xE4) ;; A WITH DIAERESIS | |
| 773 (#xC5 #xE5) ;; A WITH RING ABOVE | |
| 774 (#xC6 #xE6) ;; AE | |
| 775 (#xC7 #xE7) ;; C WITH CEDILLA | |
| 776 (#xC8 #xE8) ;; E WITH GRAVE | |
| 777 (#xC9 #xE9) ;; E WITH ACUTE | |
| 778 (#xCB #xEB) ;; E WITH DIAERESIS | |
| 779 (#xCD #xED) ;; I WITH ACUTE | |
| 780 (#xCE #xEE) ;; I WITH CIRCUMFLEX | |
| 781 (#xD0 #xF0) ;; G WITH BREVE | |
| 782 (#xD1 #xF1) ;; N WITH TILDE | |
| 783 (#xD2 #xF2) ;; O WITH GRAVE | |
| 784 (#xD3 #xF3) ;; O WITH ACUTE | |
| 785 (#xD4 #xF4) ;; O WITH CIRCUMFLEX | |
| 786 (#xD5 #xF5) ;; O WITH TILDE | |
| 787 (#xD6 #xF6) ;; O WITH DIAERESIS | |
| 788 (#xD8 #xF8) ;; O WITH STROKE | |
| 789 (#xD9 #xF9) ;; U WITH GRAVE | |
| 790 (#xDA #xFA) ;; U WITH ACUTE | |
| 791 (#xDB #xFB) ;; U WITH CIRCUMFLEX | |
| 792 (#xDC #xFC) ;; U WITH DIAERESIS | |
| 793 (#xDE #xFE))) ;; S WITH CEDILLA | |
| 794 | |
| 4145 | 795 ;; LATIN CAPITAL LETTER I WITH DOT ABOVE |
| 796 (put-case-table 'downcase | |
| 797 (make-char 'latin-iso8859-9 #xdd) | |
| 798 ?i (standard-case-table)) | |
| 799 | |
| 800 ;; LATIN SMALL LETTER DOTLESS I | |
| 801 (put-case-table 'upcase | |
| 802 (make-char 'latin-iso8859-9 #xfd) | |
| 803 ?I (standard-case-table)) | |
| 804 | |
| 4299 | 805 (make-8-bit-coding-system |
| 806 'iso-8859-9 | |
| 807 '((#xD0 ?\u011E) ;; LATIN CAPITAL LETTER G WITH BREVE | |
| 808 (#xDD ?\u0130) ;; LATIN CAPITAL LETTER I WITH DOT ABOVE | |
| 809 (#xDE ?\u015E) ;; LATIN CAPITAL LETTER S WITH CEDILLA | |
| 810 (#xF0 ?\u011F) ;; LATIN SMALL LETTER G WITH BREVE | |
| 811 (#xFD ?\u0131) ;; LATIN SMALL LETTER DOTLESS I | |
| 812 (#xFE ?\u015F)) ;; LATIN SMALL LETTER S WITH CEDILLA | |
| 813 "ISO-8859-9 (Latin-5)" | |
| 814 '(mnemonic "Latin 5" | |
| 815 aliases (iso-latin-5 latin-5))) | |
| 3767 | 816 |
| 817 ;; end of ISO-8859-9 | |
| 818 | |
| 819 ;; This is a utility function; we don't want it in the dumped XEmacs. | |
| 820 | |
| 821 (fmakunbound 'setup-case-pairs) | |
| 2765 | 822 |
| 464 | 823 |
| 3767 | 824 ;; Language environments. |
| 825 (loop | |
| 826 for ((charset codesys default-input nice-charset-1 nice-charset-2 | |
| 827 ;; supported-langs is a list if the doc string is replaced | |
| 828 ;; entirely | |
| 829 supported-langs) | |
| 830 langenvs) in | |
| 831 '(((latin-iso8859-1 iso-8859-1 "latin-1-prefix" "Latin-1" "ISO-8859-1" | |
| 832 " Danish, Dutch, English, Faeroese, Finnish, French, German, Icelandic, | |
| 833 Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish.") | |
| 834 (("Danish" "da") | |
| 835 ("Dutch" "nl" "TUTORIAL.nl") | |
| 4090 | 836 ("Faeroese" "fo") |
| 3767 | 837 ("Finnish" "fi") |
| 838 ("French" "fr" "TUTORIAL.fr" "Bonjour, ,Ag(Ba va?") | |
| 839 ("German" "de" "TUTORIAL.de" "\ | |
| 840 German (Deutsch Nord) Guten Tag | |
| 841 German (Deutsch S,A|(Bd) Gr,A|_(B Gott" | |
| 842 "german-postfix") | |
| 843 ("Icelandic" "is") | |
| 844 ("Irish" "ga") | |
| 845 ("Italian" "it") | |
| 846 ("Norwegian" "no" "TUTORIAL.no") | |
| 847 ("Portuguese" "pt" nil "Bem-vindo! Tudo bem?") | |
| 848 ("Spanish" "es" "TUTORIAL.es" ",A!(BHola!") | |
| 849 ("Swedish" "sv" "TUTORIAL.se" "Hej!"))) | |
| 850 ((latin-iso8859-15 iso-8859-15 "latin-1-prefix" ;; #### FIXME | |
| 851 "Latin-9" "ISO-8859-15") | |
| 852 ()) | |
| 853 ((latin-iso8859-2 iso-8859-2 "latin-2-prefix" "Latin-2" "ISO-8859-2" | |
| 854 " Albanian, Czech, English, German, Hungarian, Polish, Romanian, | |
| 855 Serbian, Croatian, Slovak, Slovene, Sorbian (upper and lower), | |
| 856 and Swedish.") ;; " added because fontification got screwed up, CVS-20061203. | |
| 4090 | 857 (("Albanian" "sq") |
| 3767 | 858 ("Croatian" ("hrvatski" "hr") "TUTORIAL.hr") |
| 859 ("Czech" ("cs" "cz") "TUTORIAL.cs" "P,Bx(Bejeme v,Ba(Bm hezk,B}(B den!" | |
| 860 "latin-2-postfix") | |
| 861 ("Hungarian" ("hungarian" "hu")) | |
| 4240 | 862 ("Polish" ("pl" "po") "TUTORIAL.pl") ;; #### Is "po" actually used? |
| 3767 | 863 ("Romanian" "ro" "TUTORIAL.ro" "Bun,Bc(B ziua, bine a,B~(Bi venit!" |
| 864 "latin-2-postfix") | |
| 865 ("Serbian" "sr") | |
| 866 ("Slovak" "sk" "TUTORIAL.sk" "Prajeme V,Ba(Bm pr,Bm(Bjemn,B}(B de,Br(B!" | |
| 867 "latin-2-postfix") | |
| 868 ("Slovenian" "sl" "TUTORIAL.sl" ",B.(Belimo vam uspe,B9(Ben dan!" | |
| 869 "latin-2-postfix") | |
| 870 ("Sorbian" nil))) | |
| 871 ((latin-iso8859-3 iso-8859-3 "latin-3-prefix" "Latin-3" "ISO-8859-3" | |
| 872 " Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician, | |
| 873 German, Italian, Maltese, Spanish, and Turkish.") | |
| 874 (("Afrikaans" "af") | |
| 875 ("Catalan" ("catalan" "ca")) | |
| 4090 | 876 ("Esperanto" "eo") |
| 877 ("Galician" "gl") | |
| 878 ("Maltese" "mt"))) | |
| 3767 | 879 ((latin-iso8859-4 iso-8859-4 "latin-4-prefix" "Latin-4" "ISO-8859-4" |
| 880 " Danish, English, Estonian, Finnish, German, Greenlandic, Lappish, | |
| 881 Latvian, Lithuanian, and Norwegian.") | |
| 882 (("Estonian" "et") | |
| 4090 | 883 ("Greenlandic" "kl") |
| 884 ("Lappish" "se") | |
| 3767 | 885 ("Latvian" "lv") |
| 886 ("Lithuanian" "li"))) | |
| 3977 | 887 ((latin-iso8859-9 iso-8859-9 "latin-5-prefix" "Latin-5" "ISO-8859-9") |
| 3767 | 888 (("Turkish" "tr")))) |
| 889 do | |
| 890 (set-language-info-alist | |
| 891 nice-charset-1 | |
| 892 `((charset ascii ,charset) | |
| 893 (coding-system ,codesys) | |
| 894 (coding-priority ,codesys) | |
| 895 (native-coding-system ,codesys) | |
| 896 (documentation . ,(if (listp supported-langs) (car supported-langs) | |
| 897 (format "\ | |
| 898 Generic language environment for %s (%s)." nice-charset-1 nice-charset-2)))) | |
| 899 '("European")) | |
| 900 (loop for (name locale tutorial sample-text input-method) in langenvs | |
| 901 do | |
| 902 (set-language-info-alist | |
| 903 name | |
| 904 `((charset ascii ,charset) | |
| 905 (coding-system ,codesys) | |
| 906 (coding-priority ,codesys) | |
| 907 (native-coding-system ,codesys) | |
| 908 ,@(if locale `((locale . ,locale))) | |
| 4240 | 909 ,@(if tutorial `((tutorial . ,tutorial) |
| 910 (tutorial-coding-system ,codesys))) | |
| 3767 | 911 ,@(if sample-text `((sample-text . ,sample-text))) |
| 912 (input-method . ,(or input-method default-input)) | |
| 913 (documentation . ,(format "\ | |
| 914 This language environment supports %s. " name))) | |
| 915 '("European")))) | |
| 464 | 916 |
| 4145 | 917 ;; The case table for Turkish is special: |
| 918 ;; #### Maybe we should limit this change to interactive functions; this may | |
| 919 ;; well be awkward for protocols and so on. | |
| 920 (set-language-info "Turkish" | |
| 921 'setup-function | |
| 922 (lambda () | |
| 923 ;; The lowercase version of I is dotless i | |
| 924 (put-case-table-pair ?I | |
| 925 (make-char 'latin-iso8859-9 #xfd) | |
| 926 (standard-case-table)) | |
| 927 ;; The uppercase version of i is I with dot | |
| 928 (put-case-table-pair (make-char 'latin-iso8859-9 #xdd) | |
| 929 ?i (standard-case-table)))) | |
| 930 | |
| 931 (set-language-info "Turkish" | |
| 932 'exit-function | |
| 933 (lambda () | |
| 934 ;; Restore the normal case mappings for the characters. | |
| 935 (put-case-table-pair ?I ?i (standard-case-table)))) | |
| 936 | |
| 937 (make-8-bit-coding-system | |
| 938 'macintosh | |
| 939 '((#x80 ?\u00C4) ;; LATIN CAPITAL LETTER A WITH DIAERESIS | |
| 940 (#x81 ?\u00C5) ;; LATIN CAPITAL LETTER A WITH RING ABOVE | |
| 941 (#x82 ?\u00C7) ;; LATIN CAPITAL LETTER C WITH CEDILLA | |
| 942 (#x83 ?\u00C9) ;; LATIN CAPITAL LETTER E WITH ACUTE | |
| 943 (#x84 ?\u00D1) ;; LATIN CAPITAL LETTER N WITH TILDE | |
| 944 (#x85 ?\u00D6) ;; LATIN CAPITAL LETTER O WITH DIAERESIS | |
| 945 (#x86 ?\u00DC) ;; LATIN CAPITAL LETTER U WITH DIAERESIS | |
| 946 (#x87 ?\u00E1) ;; LATIN SMALL LETTER A WITH ACUTE | |
| 947 (#x88 ?\u00E0) ;; LATIN SMALL LETTER A WITH GRAVE | |
| 948 (#x89 ?\u00E2) ;; LATIN SMALL LETTER A WITH CIRCUMFLEX | |
| 949 (#x8A ?\u00E4) ;; LATIN SMALL LETTER A WITH DIAERESIS | |
| 950 (#x8B ?\u00E3) ;; LATIN SMALL LETTER A WITH TILDE | |
| 951 (#x8C ?\u00E5) ;; LATIN SMALL LETTER A WITH RING ABOVE | |
| 952 (#x8D ?\u00E7) ;; LATIN SMALL LETTER C WITH CEDILLA | |
| 953 (#x8E ?\u00E9) ;; LATIN SMALL LETTER E WITH ACUTE | |
| 954 (#x8F ?\u00E8) ;; LATIN SMALL LETTER E WITH GRAVE | |
| 955 (#x90 ?\u00EA) ;; LATIN SMALL LETTER E WITH CIRCUMFLEX | |
| 956 (#x91 ?\u00EB) ;; LATIN SMALL LETTER E WITH DIAERESIS | |
| 957 (#x92 ?\u00ED) ;; LATIN SMALL LETTER I WITH ACUTE | |
| 958 (#x93 ?\u00EC) ;; LATIN SMALL LETTER I WITH GRAVE | |
| 959 (#x94 ?\u00EE) ;; LATIN SMALL LETTER I WITH CIRCUMFLEX | |
| 960 (#x95 ?\u00EF) ;; LATIN SMALL LETTER I WITH DIAERESIS | |
| 961 (#x96 ?\u00F1) ;; LATIN SMALL LETTER N WITH TILDE | |
| 962 (#x97 ?\u00F3) ;; LATIN SMALL LETTER O WITH ACUTE | |
| 963 (#x98 ?\u00F2) ;; LATIN SMALL LETTER O WITH GRAVE | |
| 964 (#x99 ?\u00F4) ;; LATIN SMALL LETTER O WITH CIRCUMFLEX | |
| 965 (#x9A ?\u00F6) ;; LATIN SMALL LETTER O WITH DIAERESIS | |
| 966 (#x9B ?\u00F5) ;; LATIN SMALL LETTER O WITH TILDE | |
| 967 (#x9C ?\u00FA) ;; LATIN SMALL LETTER U WITH ACUTE | |
| 968 (#x9D ?\u00F9) ;; LATIN SMALL LETTER U WITH GRAVE | |
| 969 (#x9E ?\u00FB) ;; LATIN SMALL LETTER U WITH CIRCUMFLEX | |
| 970 (#x9F ?\u00FC) ;; LATIN SMALL LETTER U WITH DIAERESIS | |
| 971 (#xA0 ?\u2020) ;; DAGGER | |
| 972 (#xA1 ?\u00B0) ;; DEGREE SIGN | |
| 973 (#xA2 ?\u00A2) ;; CENT SIGN | |
| 974 (#xA3 ?\u00A3) ;; POUND SIGN | |
| 975 (#xA4 ?\u00A7) ;; SECTION SIGN | |
| 976 (#xA5 ?\u2022) ;; BULLET | |
| 977 (#xA6 ?\u00B6) ;; PILCROW SIGN | |
| 978 (#xA7 ?\u00DF) ;; LATIN SMALL LETTER SHARP S | |
| 979 (#xA8 ?\u00AE) ;; REGISTERED SIGN | |
| 980 (#xA9 ?\u00A9) ;; COPYRIGHT SIGN | |
| 981 (#xAA ?\u2122) ;; TRADE MARK SIGN | |
| 982 (#xAB ?\u00B4) ;; ACUTE ACCENT | |
| 983 (#xAC ?\u00A8) ;; DIAERESIS | |
| 984 (#xAD ?\u2260) ;; NOT EQUAL TO | |
| 985 (#xAE ?\u00C6) ;; LATIN CAPITAL LETTER AE | |
| 986 (#xAF ?\u00D8) ;; LATIN CAPITAL LETTER O WITH STROKE | |
| 987 (#xB0 ?\u221E) ;; INFINITY | |
| 988 (#xB1 ?\u00B1) ;; PLUS-MINUS SIGN | |
| 989 (#xB2 ?\u2264) ;; LESS-THAN OR EQUAL TO | |
| 990 (#xB3 ?\u2265) ;; GREATER-THAN OR EQUAL TO | |
| 991 (#xB4 ?\u00A5) ;; YEN SIGN | |
| 992 (#xB5 ?\u00B5) ;; MICRO SIGN | |
| 993 (#xB6 ?\u2202) ;; PARTIAL DIFFERENTIAL | |
| 994 (#xB7 ?\u2211) ;; N-ARY SUMMATION | |
| 995 (#xB8 ?\u220F) ;; N-ARY PRODUCT | |
| 996 (#xB9 ?\u03C0) ;; GREEK SMALL LETTER PI | |
| 997 (#xBA ?\u222B) ;; INTEGRAL | |
| 998 (#xBB ?\u00AA) ;; FEMININE ORDINAL INDICATOR | |
| 999 (#xBC ?\u00BA) ;; MASCULINE ORDINAL INDICATOR | |
| 1000 (#xBD ?\u03A9) ;; GREEK CAPITAL LETTER OMEGA | |
| 1001 (#xBE ?\u00E6) ;; LATIN SMALL LETTER AE | |
| 1002 (#xBF ?\u00F8) ;; LATIN SMALL LETTER O WITH STROKE | |
| 1003 (#xC0 ?\u00BF) ;; INVERTED QUESTION MARK | |
| 1004 (#xC1 ?\u00A1) ;; INVERTED EXCLAMATION MARK | |
| 1005 (#xC2 ?\u00AC) ;; NOT SIGN | |
| 1006 (#xC3 ?\u221A) ;; SQUARE ROOT | |
| 1007 (#xC4 ?\u0192) ;; LATIN SMALL LETTER F WITH HOOK | |
| 1008 (#xC5 ?\u2248) ;; ALMOST EQUAL TO | |
| 1009 (#xC6 ?\u2206) ;; INCREMENT | |
| 1010 (#xC7 ?\u00AB) ;; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK | |
| 1011 (#xC8 ?\u00BB) ;; RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK | |
| 1012 (#xC9 ?\u2026) ;; HORIZONTAL ELLIPSIS | |
| 1013 (#xCA ?\u00A0) ;; NO-BREAK SPACE | |
| 1014 (#xCB ?\u00C0) ;; LATIN CAPITAL LETTER A WITH GRAVE | |
| 1015 (#xCC ?\u00C3) ;; LATIN CAPITAL LETTER A WITH TILDE | |
| 1016 (#xCD ?\u00D5) ;; LATIN CAPITAL LETTER O WITH TILDE | |
| 1017 (#xCE ?\u0152) ;; LATIN CAPITAL LIGATURE OE | |
| 1018 (#xCF ?\u0153) ;; LATIN SMALL LIGATURE OE | |
| 1019 (#xD0 ?\u2013) ;; EN DASH | |
| 1020 (#xD1 ?\u2014) ;; EM DASH | |
| 1021 (#xD2 ?\u201C) ;; LEFT DOUBLE QUOTATION MARK | |
| 1022 (#xD3 ?\u201D) ;; RIGHT DOUBLE QUOTATION MARK | |
| 1023 (#xD4 ?\u2018) ;; LEFT SINGLE QUOTATION MARK | |
| 1024 (#xD5 ?\u2019) ;; RIGHT SINGLE QUOTATION MARK | |
| 1025 (#xD6 ?\u00F7) ;; DIVISION SIGN | |
| 1026 (#xD7 ?\u25CA) ;; LOZENGE | |
| 1027 (#xD8 ?\u00FF) ;; LATIN SMALL LETTER Y WITH DIAERESIS | |
| 1028 (#xD9 ?\u0178) ;; LATIN CAPITAL LETTER Y WITH DIAERESIS | |
| 1029 (#xDA ?\u2044) ;; FRACTION SLASH | |
| 1030 (#xDB ?\u20AC) ;; EURO SIGN | |
| 1031 (#xDC ?\u2039) ;; SINGLE LEFT-POINTING ANGLE QUOTATION MARK | |
| 1032 (#xDD ?\u203A) ;; SINGLE RIGHT-POINTING ANGLE QUOTATION MARK | |
| 1033 (#xDE ?\uFB01) ;; LATIN SMALL LIGATURE FI | |
| 1034 (#xDF ?\uFB02) ;; LATIN SMALL LIGATURE FL | |
| 1035 (#xE0 ?\u2021) ;; DOUBLE DAGGER | |
| 1036 (#xE1 ?\u00B7) ;; MIDDLE DOT | |
| 1037 (#xE2 ?\u201A) ;; SINGLE LOW-9 QUOTATION MARK | |
| 1038 (#xE3 ?\u201E) ;; DOUBLE LOW-9 QUOTATION MARK | |
| 1039 (#xE4 ?\u2030) ;; PER MILLE SIGN | |
| 1040 (#xE5 ?\u00C2) ;; LATIN CAPITAL LETTER A WITH CIRCUMFLEX | |
| 1041 (#xE6 ?\u00CA) ;; LATIN CAPITAL LETTER E WITH CIRCUMFLEX | |
| 1042 (#xE7 ?\u00C1) ;; LATIN CAPITAL LETTER A WITH ACUTE | |
| 1043 (#xE8 ?\u00CB) ;; LATIN CAPITAL LETTER E WITH DIAERESIS | |
| 1044 (#xE9 ?\u00C8) ;; LATIN CAPITAL LETTER E WITH GRAVE | |
| 1045 (#xEA ?\u00CD) ;; LATIN CAPITAL LETTER I WITH ACUTE | |
| 1046 (#xEB ?\u00CE) ;; LATIN CAPITAL LETTER I WITH CIRCUMFLEX | |
| 1047 (#xEC ?\u00CF) ;; LATIN CAPITAL LETTER I WITH DIAERESIS | |
| 1048 (#xED ?\u00CC) ;; LATIN CAPITAL LETTER I WITH GRAVE | |
| 1049 (#xEE ?\u00D3) ;; LATIN CAPITAL LETTER O WITH ACUTE | |
| 1050 (#xEF ?\u00D4) ;; LATIN CAPITAL LETTER O WITH CIRCUMFLEX | |
| 1051 (#xF0 ?\uF8FF) ;; Apple logo | |
| 1052 (#xF1 ?\u00D2) ;; LATIN CAPITAL LETTER O WITH GRAVE | |
| 1053 (#xF2 ?\u00DA) ;; LATIN CAPITAL LETTER U WITH ACUTE | |
| 1054 (#xF3 ?\u00DB) ;; LATIN CAPITAL LETTER U WITH CIRCUMFLEX | |
| 1055 (#xF4 ?\u00D9) ;; LATIN CAPITAL LETTER U WITH GRAVE | |
| 1056 (#xF5 ?\u0131) ;; LATIN SMALL LETTER DOTLESS I | |
| 1057 (#xF6 ?\u02C6) ;; MODIFIER LETTER CIRCUMFLEX ACCENT | |
| 1058 (#xF7 ?\u02DC) ;; SMALL TILDE | |
| 1059 (#xF8 ?\u00AF) ;; MACRON | |
| 1060 (#xF9 ?\u02D8) ;; BREVE | |
| 1061 (#xFA ?\u02D9) ;; DOT ABOVE | |
| 1062 (#xFB ?\u02DA) ;; RING ABOVE | |
| 1063 (#xFC ?\u00B8) ;; CEDILLA | |
| 1064 (#xFD ?\u02DD) ;; DOUBLE ACUTE ACCENT | |
| 1065 (#xFE ?\u02DB) ;; OGONEK | |
| 1066 (#xFF ?\u02C7)) ;; CARON | |
| 1067 "The Macintosh encoding for Western Europe and the Americas" | |
| 1068 '(mnemonic "MR" | |
| 1069 documentation "MacRoman, MIME name macintosh" | |
| 1070 aliases (cp10000 MacRoman))) | |
| 1071 | |
| 1072 (make-8-bit-coding-system | |
| 1073 'windows-1252 | |
| 1074 '((#x80 ?\u20AC) ;; EURO SIGN | |
| 1075 (#x82 ?\u201A) ;; SINGLE LOW-9 QUOTATION MARK | |
| 1076 (#x83 ?\u0192) ;; LATIN SMALL LETTER F WITH HOOK | |
| 1077 (#x84 ?\u201E) ;; DOUBLE LOW-9 QUOTATION MARK | |
| 1078 (#x85 ?\u2026) ;; HORIZONTAL ELLIPSIS | |
| 1079 (#x86 ?\u2020) ;; DAGGER | |
| 1080 (#x87 ?\u2021) ;; DOUBLE DAGGER | |
| 1081 (#x88 ?\u02C6) ;; MODIFIER LETTER CIRCUMFLEX ACCENT | |
| 1082 (#x89 ?\u2030) ;; PER MILLE SIGN | |
| 1083 (#x8A ?\u0160) ;; LATIN CAPITAL LETTER S WITH CARON | |
| 1084 (#x8B ?\u2039) ;; SINGLE LEFT-POINTING ANGLE QUOTATION MARK | |
| 1085 (#x8C ?\u0152) ;; LATIN CAPITAL LIGATURE OE | |
| 1086 (#x8E ?\u017D) ;; LATIN CAPITAL LETTER Z WITH CARON | |
| 1087 (#x91 ?\u2018) ;; LEFT SINGLE QUOTATION MARK | |
| 1088 (#x92 ?\u2019) ;; RIGHT SINGLE QUOTATION MARK | |
| 1089 (#x93 ?\u201C) ;; LEFT DOUBLE QUOTATION MARK | |
| 1090 (#x94 ?\u201D) ;; RIGHT DOUBLE QUOTATION MARK | |
| 1091 (#x95 ?\u2022) ;; BULLET | |
| 1092 (#x96 ?\u2013) ;; EN DASH | |
| 1093 (#x97 ?\u2014) ;; EM DASH | |
| 1094 (#x98 ?\u02DC) ;; SMALL TILDE | |
| 1095 (#x99 ?\u2122) ;; TRADE MARK SIGN | |
| 1096 (#x9A ?\u0161) ;; LATIN SMALL LETTER S WITH CARON | |
| 1097 (#x9B ?\u203A) ;; SINGLE RIGHT-POINTING ANGLE QUOTATION MARK | |
| 1098 (#x9C ?\u0153) ;; LATIN SMALL LIGATURE OE | |
| 1099 (#x9E ?\u017E) ;; LATIN SMALL LETTER Z WITH CARON | |
| 1100 (#x9F ?\u0178));; LATIN CAPITAL LETTER Y WITH DIAERESIS | |
| 1101 "Microsoft's extension of iso-8859-1 for Western Europe and the Americas. " | |
| 1102 '(mnemonic "cp1252" | |
| 1103 aliases (cp1252))) | |
| 1104 | |
|
4316
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1105 ;; Provide language environments that prefer specific coding systems. |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1106 (loop |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1107 for coding-system in '(utf-8 windows-1252 macintosh) |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1108 with name = nil |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1109 with assocked = nil |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1110 do |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1111 (setq name (create-variant-language-environment "English" coding-system) |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1112 assocked (assoc name language-info-alist)) |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1113 (setcar assocked |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1114 (upcase (symbol-name coding-system))) |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1115 (setcdr assocked |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1116 (remassq 'locale (cdr assocked)))) |
|
2e528ccfe690
Create "UTF-8" and "WINDOWS-1252" language environments.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4299
diff
changeset
|
1117 |
| 3767 | 1118 ;;; latin.el ends here |