code.delx.au - gnu-emacs/blob - lisp/language/european.el

   1 ;;; european.el --- European languages -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
   4 ;; Licensed to the Free Software Foundation.
   5
   6 ;; Keywords: multilingual, European
   7
   8 ;; This file is part of GNU Emacs.
   9
  10 ;; GNU Emacs is free software; you can redistribute it and/or modify
  11 ;; it under the terms of the GNU General Public License as published by
  12 ;; the Free Software Foundation; either version 2, or (at your option)
  13 ;; any later version.
  14
  15 ;; GNU Emacs is distributed in the hope that it will be useful,
  16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  18 ;; GNU General Public License for more details.
  19
  20 ;; You should have received a copy of the GNU General Public License
  21 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  23 ;; Boston, MA 02111-1307, USA.
  24
  25 ;;; Commentary:
  26
  27 ;; For Europeans, character sets ISO8859-1,2,3,4,9,14,15 are supported.
  28
  29 ;;; Code:
  30
  31 ;; Latin-1 (ISO-8859-1)
  32
  33 (make-coding-system
  34  'iso-latin-1 2 ?1
  35  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)"
  36  '(ascii latin-iso8859-1 nil nil
  37    nil nil nil nil nil nil nil nil nil nil nil nil t)
  38  '((safe-charsets ascii latin-iso8859-1)
  39    (mime-charset . iso-8859-1)))
  40
  41 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
  42 (define-coding-system-alias 'latin-1 'iso-latin-1)
  43
  44 (set-language-info-alist
  45  "Latin-1" '((charset ascii latin-iso8859-1)
  46              (coding-system iso-latin-1)
  47              (coding-priority iso-latin-1)
  48              (nonascii-translation . latin-iso8859-1)
  49              (unibyte-syntax . "latin-1")
  50              (unibyte-display . iso-latin-1)
  51              (input-method . "latin-1-prefix")
  52              (sample-text
  53               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  54              (documentation . "\
  55 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  56 character set which supports the following European languages:
  57  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  58  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  59  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  60  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  61  Scottish Gaelic, Spanish, and Swedish.
  62 We also have a German specific language environment \"German\".
  63
  64 Latin-1 also covers several written languages outside Europe, including
  65 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  66  '("European"))
  67
  68 \f
  69 ;; Latin-2 (ISO-8859-2)
  70
  71 (make-coding-system
  72  'iso-latin-2 2 ?2
  73  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
  74  '(ascii latin-iso8859-2 nil nil
  75    nil nil nil nil nil nil nil)
  76  '((safe-charsets ascii latin-iso8859-2)
  77    (mime-charset . iso-8859-2)))
  78
  79 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  80 (define-coding-system-alias 'latin-2 'iso-latin-2)
  81
  82 (set-language-info-alist
  83  "Latin-2" '((charset ascii latin-iso8859-2)
  84              (coding-system iso-latin-2)
  85              (coding-priority iso-latin-2)
  86              (nonascii-translation . latin-iso8859-2)
  87              (unibyte-syntax . "latin-2")
  88              (unibyte-display . iso-latin-2)
  89              (input-method . "latin-2-prefix")
  90              (documentation . "\
  91 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  92 character set which supports the following languages:
  93  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
  94  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
  95  and Swedish.
  96 We also have specific language environments for the following languages:
  97   For Czech, \"Czech\".
  98   For Romanian, \"Romanian\".
  99   For Slovak, \"Slovak\"."))
 100  '("European"))
 101
 102 \f
 103 ;; Latin-3 (ISO-8859-3)
 104
 105 (make-coding-system
 106  'iso-latin-3 2 ?3
 107  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
 108  '(ascii latin-iso8859-3 nil nil
 109    nil nil nil nil nil nil nil)
 110  '((safe-charsets ascii latin-iso8859-3)
 111    (mime-charset . iso-8859-3)))
 112
 113 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 114 (define-coding-system-alias 'latin-3 'iso-latin-3)
 115
 116 (set-language-info-alist
 117  "Latin-3" '((charset ascii latin-iso8859-3)
 118              (coding-system iso-latin-3)
 119              (coding-priority iso-latin-3)
 120              (nonascii-translation . latin-iso8859-3)
 121              (unibyte-syntax . "latin-3")
 122              (unibyte-display . iso-latin-3)
 123              (input-method . "latin-3-prefix")
 124              (documentation . "\
 125 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 126  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 127  German, Italian, Maltese, Spanish, and Turkish."))
 128  '("European"))
 129
 130 \f
 131 ;; Latin-4 (ISO-8859-4)
 132
 133 (make-coding-system
 134  'iso-latin-4 2 ?4
 135  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
 136  '(ascii latin-iso8859-4 nil nil
 137    nil nil nil nil nil nil nil)
 138  '((safe-charsets ascii latin-iso8859-4)
 139    (mime-charset . iso-8859-4)))
 140
 141 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 142 (define-coding-system-alias 'latin-4 'iso-latin-4)
 143
 144 (set-language-info-alist
 145  "Latin-4" '((charset ascii latin-iso8859-4)
 146              (coding-system iso-8859-4)
 147              (coding-priority iso-8859-4)
 148              (nonascii-translation . latin-iso8859-4)
 149              (unibyte-syntax . "latin-4")
 150              (unibyte-display . iso-8859-4)
 151              (input-method . "latin-4-prefix")
 152              (documentation . "\
 153 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 154  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 155  Latvian, Lithuanian, and Norwegian."))
 156  '("European"))
 157
 158 \f
 159 ;; Latin-5 (ISO-8859-9)
 160
 161 (make-coding-system
 162  'iso-latin-5 2 ?9
 163  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
 164  '(ascii latin-iso8859-9 nil nil
 165    nil nil nil nil nil nil nil)
 166  '((safe-charsets ascii latin-iso8859-9)
 167    (mime-charset . iso-8859-9)))
 168
 169 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 170 (define-coding-system-alias 'latin-5 'iso-latin-5)
 171
 172 (set-language-info-alist
 173  "Latin-5" '((charset ascii latin-iso8859-9)
 174              (coding-system iso-latin-5)
 175              (coding-priority iso-latin-5)
 176              (nonascii-translation . latin-iso8859-9)
 177              (unibyte-syntax . "latin-5")
 178              (unibyte-display . iso-latin-5)
 179              (input-method . "latin-5-prefix")
 180              (documentation . "\
 181 These languages are supported with the Latin-5 (ISO-8859-9) character set:
 182 Bulgarian, Byelorussian, (Slavic) Macedonian, Russian, Serbian and
 183 Ukranian."))                            ; says ISO 8859-1
 184  '("European"))
 185
 186 \f
 187 ;; Latin-8 (ISO-8859-14)
 188
 189 (make-coding-system
 190  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 191                                         ; for `Celtic' is taken.
 192  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)"
 193  '(ascii latin-iso8859-14 nil nil
 194    nil nil nil nil nil nil nil nil nil nil nil nil t)
 195  '((safe-charsets ascii latin-iso8859-14)
 196    (mime-charset . iso-8859-14)))
 197
 198 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 199 (define-coding-system-alias 'latin-8 'iso-latin-8)
 200
 201 (set-language-info-alist
 202  "Latin-8" '((charset ascii latin-iso8859-14)
 203              (coding-system iso-latin-8)
 204              (coding-priority iso-latin-8)
 205              (nonascii-translation . latin-iso8859-14)
 206              (unibyte-syntax . "latin-8")
 207              (unibyte-display . iso-latin-8)
 208              (input-method . "latin-8-prefix")
 209              ;; Fixme: Welsh/Ga{e}lic greetings
 210              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 211              (documentation . "\
 212 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 213 character set which supports the Celtic languages, including those not
 214 covered by other ISO-8859 character sets: Welsh, Manx Gaelic and
 215 Irish Gaelic (old orthography)."))
 216  '("European"))
 217 \f
 218 ;; Latin-9 (ISO-8859-15)
 219
 220 (make-coding-system
 221  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 222  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)"
 223  '(ascii latin-iso8859-15 nil nil
 224    nil nil nil nil nil nil nil nil nil nil nil nil t)
 225  '((safe-charsets ascii latin-iso8859-15)
 226    (mime-charset . iso-8859-15)))
 227
 228 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 229 (define-coding-system-alias 'latin-9 'iso-latin-9)
 230 (define-coding-system-alias 'latin-0 'iso-latin-9)
 231
 232 (set-language-info-alist
 233  "Latin-9" '((charset ascii latin-iso8859-15)
 234              (coding-system iso-latin-9)
 235              (coding-priority iso-latin-9)
 236              (nonascii-translation . latin-iso8859-15)
 237              (unibyte-syntax . "latin-9")
 238              (unibyte-display . iso-latin-9)
 239              (input-method . "latin-9-prefix")
 240              (sample-text
 241               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 242              (documentation . "\
 243 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 244 character set which supports the same languages as Latin-1 with the
 245 addition of the Euro sign and some additional French and Finnish letters.
 246 Latin-9 is sometimes nicknamed `Latin-0'."))
 247  '("European"))
 248 \f
 249 (set-language-info-alist
 250  "German" '((tutorial . "TUTORIAL.de")
 251             (charset ascii latin-iso8859-1)
 252             (coding-system iso-latin-1)
 253             (coding-priority iso-latin-1)
 254             (input-method . "german-postfix")
 255             (nonascii-translation . iso-latin-1)
 256             (unibyte-syntax . "latin-1")
 257             (unibyte-display . iso-latin-1)
 258             (sample-text . "\
 259 German (Deutsch Nord)   Guten Tag
 260 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 261             (documentation . "\
 262 This language environment is almost the same as Latin-1,
 263 but default input method is set to \"german-postfix\"."))
 264  '("European"))
 265
 266 (set-language-info-alist
 267  "Slovenian" '((charset . (ascii latin-iso8859-2))
 268               (coding-system . (iso-8859-2))
 269               (coding-priority . (iso-8859-2))
 270               (nonascii-translation . latin-iso8859-2)
 271               (input-method . "latin-2-postfix")
 272               (unibyte-syntax . "latin-2")
 273               (unibyte-display . iso-8859-2)
 274               (tutorial . "TUTORIAL.sl")
 275               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 276               (documentation . t))
 277  '("European"))
 278
 279 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 280 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 281 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 282 ;; "Latin-3" language environment.
 283
 284 (set-language-info-alist
 285  "Turkish" '((charset ascii latin-iso8859-9)
 286              (coding-system iso-latin-5)
 287              (coding-priority iso-latin-5)
 288              (nonascii-translation . latin-iso8859-9)
 289              (unibyte-syntax . "latin-5")
 290              (unibyte-display . iso-latin-5)
 291              (input-method . "turkish-postfix")
 292              (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be)       Merhaba")
 293              (documentation . t)))
 294
 295 ;; Polish ISO 8859-2 environment.
 296 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 297 ;; Keywords: multilingual, Polish
 298
 299 (set-language-info-alist
 300  "Polish" '((charset . (ascii latin-iso8859-2))
 301            (coding-system . (iso-8859-2))
 302            (coding-priority . (iso-8859-2))
 303            (input-method . "polish-slash")
 304            (nonascii-translation . latin-iso8859-2)
 305            (unibyte-syntax . "latin-2")
 306            (unibyte-display . iso-8859-2)
 307            (tutorial . "TUTORIAL.pl")
 308            (sample-text . "\e,B1!fFjJ3#qQsS6&?/<,\e(B")
 309            (documentation . t))
 310  '("European"))
 311
 312 \f
 313 ;; Definitions for the Mac Roman character sets and coding system.
 314 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 315 ;; 255 for actual characters.  Emacs decode them to one of the
 316 ;; following character sets.
 317 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 318 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 319
 320 (let
 321     ((encoding-vector (make-vector 256 nil))
 322      (i 0)
 323      (vec       ;; mac-roman (128..255) -> UCS mapping
 324       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 325         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 326         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 327         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 328         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 329         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 330         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 331         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 332         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 333         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 334         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 335         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 336         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 337         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 338         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 339         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 340         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 341         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 342         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 343         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 344         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 345         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 346         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 347         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 348         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 349         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 350         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 351         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 352         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 353         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 354         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 355         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 356         #x2020  ;; 160:DAGGER
 357         #x00B0  ;; 161:DEGREE SIGN
 358         #x00A2  ;; 162:CENT SIGN
 359         #x00A3  ;; 163:POUND SIGN
 360         #x00A7  ;; 164:SECTION SIGN
 361         #x2022  ;; 165:BULLET
 362         #x00B6  ;; 166:PILCROW SIGN
 363         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 364         #x00AE  ;; 168:REGISTERED SIGN
 365         #x00A9  ;; 169:COPYRIGHT SIGN
 366         #x2122  ;; 170:TRADE MARK SIGN
 367         #x00B4  ;; 171:ACUTE ACCENT
 368         #x00A8  ;; 172:DIAERESIS
 369         #x2260  ;; 173:NOT EQUAL TO
 370         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 371         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 372         #x221E  ;; 176:INFINITY
 373         #x00B1  ;; 177:PLUS-MINUS SIGN
 374         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 375         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 376         #x00A5  ;; 180:YEN SIGN
 377         #x00B5  ;; 181:MICRO SIGN
 378         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 379         #x2211  ;; 183:N-ARY SUMMATION
 380         #x220F  ;; 184:N-ARY PRODUCT
 381         #x03C0  ;; 185:GREEK SMALL LETTER PI
 382         #x222B  ;; 186:INTEGRAL
 383         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 384         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 385         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 386         #x00E6  ;; 190:LATIN SMALL LETTER AE
 387         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 388         #x00BF  ;; 192:INVERTED QUESTION MARK
 389         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 390         #x00AC  ;; 194:NOT SIGN
 391         #x221A  ;; 195:SQUARE ROOT
 392         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 393         #x2248  ;; 197:ALMOST EQUAL TO
 394         #x2206  ;; 198:INCREMENT
 395         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 396         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 397         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 398         #x00A0  ;; 202:NO-BREAK SPACE
 399         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 400         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 401         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 402         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 403         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 404         #x2013  ;; 208:EN DASH
 405         #x2014  ;; 209:EM DASH
 406         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 407         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 408         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 409         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 410         #x00F7  ;; 214:DIVISION SIGN
 411         #x25CA  ;; 215:LOZENGE
 412         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 413         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 414         #x2044  ;; 218:FRACTION SLASH
 415         #x20AC  ;; 219:EURO SIGN
 416         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 417         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 418         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 419         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 420         #x2021  ;; 224:DOUBLE DAGGER
 421         #x00B7  ;; 225:MIDDLE DOT
 422         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 423         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 424         #x2030  ;; 228:PER MILLE SIGN
 425         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 426         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 427         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 428         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 429         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 430         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 431         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 432         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 433         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 434         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 435         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 436         #xF8FF  ;; 240:Apple logo
 437         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 438         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 439         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 440         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 441         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 442         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 443         #x02DC  ;; 247:SMALL TILDE
 444         #x00AF  ;; 248:MACRON
 445         #x02D8  ;; 249:BREVE
 446         #x02D9  ;; 250:DOT ABOVE
 447         #x02DA  ;; 251:RING ABOVE
 448         #x00B8  ;; 252:CEDILLA
 449         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 450         #x02DB  ;; 254:OGONEK
 451         #x02C7  ;; 255:CARON
 452         ])
 453      translation-table)
 454   (while (< i 128)
 455     (aset encoding-vector i i)
 456     (setq i (1+ i)))
 457   (while (< i 256)
 458     (aset encoding-vector i
 459           (decode-char 'ucs (aref vec (- i 128))))
 460     (setq i (1+ i)))
 461   (setq translation-table
 462         (make-translation-table-from-vector encoding-vector))
 463   (define-translation-table 'mac-roman-decoder translation-table)
 464   (define-translation-table 'mac-roman-encoder
 465     (char-table-extra-slot translation-table 0)))
 466
 467 (define-ccl-program decode-mac-roman
 468   `(4
 469     ((loop
 470       (read r1)
 471       (if (r1 < 128)  ;; ASCII
 472           (r0 = ,(charset-id 'ascii))
 473         (if (r1 < 160)
 474             (r0 = ,(charset-id 'eight-bit-control))
 475           (r0 = ,(charset-id 'eight-bit-graphic))))
 476       (translate-character mac-roman-decoder r0 r1)
 477       (write-multibyte-character r0 r1)
 478       (repeat))))
 479   "CCL program to decode Mac Roman")
 480
 481 (define-ccl-program encode-mac-roman
 482   `(1
 483     ((loop
 484       (read-multibyte-character r0 r1)
 485       (translate-character mac-roman-encoder r0 r1)
 486       (write-repeat r1))))
 487   "CCL program to encode Mac Roman")
 488
 489 (make-coding-system
 490  'mac-roman 4 ?M "Mac Roman Encoding"
 491  '(decode-mac-roman . encode-mac-roman)
 492  '((safe-chars . mac-roman-encoder)
 493    (valid-codes (0 . 255))))
 494
 495 (provide 'european)
 496
 497 ;;; european.el ends here