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 (make-coding-system
  45  'compound-text 2 ?1
  46  "ISO 2022 based encoding used in inter client communication of X"
  47  '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) nil nil
  48    nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil nil t)
  49  '((safe-charsets . t)))
  50
  51 (define-coding-system-alias 'ctext 'compound-text)
  52
  53 (set-language-info-alist
  54  "Latin-1" '((charset ascii latin-iso8859-1)
  55              (coding-system iso-latin-1)
  56              (coding-priority iso-latin-1)
  57              (nonascii-translation . latin-iso8859-1)
  58              (unibyte-syntax . "latin-1")
  59              (unibyte-display . iso-latin-1)
  60              (input-method . "latin-1-prefix")
  61              (sample-text
  62               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  63              (documentation . "\
  64 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  65 character set which supports the following European languages:
  66  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  67  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  68  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  69  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  70  Scottish Gaelic, Spanish, and Swedish.
  71 We also have a German specific language environment \"German\".
  72
  73 Latin-1 also covers several written languages outside Europe, including
  74 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  75  '("European"))
  76
  77 \f
  78 ;; Latin-2 (ISO-8859-2)
  79
  80 (make-coding-system
  81  'iso-latin-2 2 ?2
  82  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
  83  '(ascii latin-iso8859-2 nil nil
  84    nil nil nil nil nil nil nil)
  85  '((safe-charsets ascii latin-iso8859-2)
  86    (mime-charset . iso-8859-2)))
  87
  88 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  89 (define-coding-system-alias 'latin-2 'iso-latin-2)
  90
  91 (set-language-info-alist
  92  "Latin-2" '((charset ascii latin-iso8859-2)
  93              (coding-system iso-latin-2)
  94              (coding-priority iso-latin-2)
  95              (nonascii-translation . latin-iso8859-2)
  96              (unibyte-syntax . "latin-2")
  97              (unibyte-display . iso-latin-2)
  98              (input-method . "latin-2-prefix")
  99              (documentation . "\
 100 This language environment is a generic one for the Latin-2 (ISO-8859-2)
 101 character set which supports the following languages:
 102  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 103  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
 104  and Swedish.
 105 We also have specific language environments for the following languages:
 106   For Czech, \"Czech\".
 107   For Romanian, \"Romanian\".
 108   For Slovak, \"Slovak\"."))
 109  '("European"))
 110
 111 \f
 112 ;; Latin-3 (ISO-8859-3)
 113
 114 (make-coding-system
 115  'iso-latin-3 2 ?3
 116  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
 117  '(ascii latin-iso8859-3 nil nil
 118    nil nil nil nil nil nil nil)
 119  '((safe-charsets ascii latin-iso8859-3)
 120    (mime-charset . iso-8859-3)))
 121
 122 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 123 (define-coding-system-alias 'latin-3 'iso-latin-3)
 124
 125 (set-language-info-alist
 126  "Latin-3" '((charset ascii latin-iso8859-3)
 127              (coding-system iso-latin-3)
 128              (coding-priority iso-latin-3)
 129              (nonascii-translation . latin-iso8859-3)
 130              (unibyte-syntax . "latin-3")
 131              (unibyte-display . iso-latin-3)
 132              (input-method . "latin-3-prefix")
 133              (documentation . "\
 134 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 135  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 136  German, Italian, Maltese, Spanish, and Turkish."))
 137  '("European"))
 138
 139 \f
 140 ;; Latin-4 (ISO-8859-4)
 141
 142 (make-coding-system
 143  'iso-latin-4 2 ?4
 144  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
 145  '(ascii latin-iso8859-4 nil nil
 146    nil nil nil nil nil nil nil)
 147  '((safe-charsets ascii latin-iso8859-4)
 148    (mime-charset . iso-8859-4)))
 149
 150 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 151 (define-coding-system-alias 'latin-4 'iso-latin-4)
 152
 153 (set-language-info-alist
 154  "Latin-4" '((charset ascii latin-iso8859-4)
 155              (coding-system iso-8859-4)
 156              (coding-priority iso-8859-4)
 157              (nonascii-translation . latin-iso8859-4)
 158              (unibyte-syntax . "latin-4")
 159              (unibyte-display . iso-8859-4)
 160              (input-method . "latin-4-prefix")
 161              (documentation . "\
 162 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 163  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 164  Latvian, Lithuanian, and Norwegian."))
 165  '("European"))
 166
 167 \f
 168 ;; Latin-5 (ISO-8859-9)
 169
 170 (make-coding-system
 171  'iso-latin-5 2 ?9
 172  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
 173  '(ascii latin-iso8859-9 nil nil
 174    nil nil nil nil nil nil nil)
 175  '((safe-charsets ascii latin-iso8859-9)
 176    (mime-charset . iso-8859-9)))
 177
 178 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 179 (define-coding-system-alias 'latin-5 'iso-latin-5)
 180
 181 (set-language-info-alist
 182  "Latin-5" '((charset ascii latin-iso8859-9)
 183              (coding-system iso-latin-5)
 184              (coding-priority iso-latin-5)
 185              (nonascii-translation . latin-iso8859-9)
 186              (unibyte-syntax . "latin-5")
 187              (unibyte-display . iso-latin-5)
 188              (input-method . "latin-5-prefix")
 189              (documentation . "\
 190 These languages are supported with the Latin-5 (ISO-8859-9) character set:
 191 Bulgarian, Byelorussian, (Slavic) Macedonian, Russian, Serbian and
 192 Ukranian."))                            ; says ISO 8859-1
 193  '("European"))
 194
 195 \f
 196 ;; Latin-8 (ISO-8859-14)
 197
 198 (make-coding-system
 199  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 200                                         ; for `Celtic' is taken.
 201  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)"
 202  '(ascii latin-iso8859-14 nil nil
 203    nil nil nil nil nil nil nil nil nil nil nil nil t)
 204  '((safe-charsets ascii latin-iso8859-14)
 205    (mime-charset . iso-8859-14)))
 206
 207 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 208 (define-coding-system-alias 'latin-8 'iso-latin-8)
 209
 210 (set-language-info-alist
 211  "Latin-8" '((charset ascii latin-iso8859-14)
 212              (coding-system iso-latin-8)
 213              (coding-priority iso-latin-8)
 214              (nonascii-translation . latin-iso8859-14)
 215              (unibyte-syntax . "latin-8")
 216              (unibyte-display . iso-latin-8)
 217              (input-method . "latin-8-prefix")
 218              ;; Fixme: Welsh/Ga{e}lic greetings
 219              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 220              (documentation . "\
 221 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 222 character set which supports the Celtic languages, including those not
 223 covered by other ISO-8859 character sets: Welsh, Manx Gaelic and
 224 Irish Gaelic (old orthography)."))
 225  '("European"))
 226 \f
 227 ;; Latin-9 (ISO-8859-15)
 228
 229 (make-coding-system
 230  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 231  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)"
 232  '(ascii latin-iso8859-15 nil nil
 233    nil nil nil nil nil nil nil nil nil nil nil nil t)
 234  '((safe-charsets ascii latin-iso8859-15)
 235    (mime-charset . iso-8859-15)))
 236
 237 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 238 (define-coding-system-alias 'latin-9 'iso-latin-9)
 239 (define-coding-system-alias 'latin-0 'iso-latin-9)
 240
 241 (set-language-info-alist
 242  "Latin-9" '((charset ascii latin-iso8859-15)
 243              (coding-system iso-latin-9)
 244              (coding-priority iso-latin-9)
 245              (nonascii-translation . latin-iso8859-15)
 246              (unibyte-syntax . "latin-9")
 247              (unibyte-display . iso-latin-9)
 248              (input-method . "latin-9-prefix")
 249              (sample-text
 250               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 251              (documentation . "\
 252 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 253 character set which supports the same languages as Latin-1 with the
 254 addition of the Euro sign and some additional French and Finnish letters.
 255 Latin-9 is sometimes nicknamed `Latin-0'."))
 256  '("European"))
 257 \f
 258 (set-language-info-alist
 259  "German" '((tutorial . "TUTORIAL.de")
 260             (charset ascii latin-iso8859-1)
 261             (coding-system iso-latin-1)
 262             (coding-priority iso-latin-1)
 263             (input-method . "german-postfix")
 264             (nonascii-translation . iso-latin-1)
 265             (unibyte-syntax . "latin-1")
 266             (unibyte-display . iso-latin-1)
 267             (sample-text . "\
 268 German (Deutsch Nord)   Guten Tag
 269 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 270             (documentation . "\
 271 This language environment is almost the same as Latin-1,
 272 but default input method is set to \"german-postfix\"."))
 273  '("European"))
 274
 275 (set-language-info-alist
 276  "Slovenian" '((charset . (ascii latin-iso8859-2))
 277               (coding-system . (iso-8859-2))
 278               (coding-priority . (iso-8859-2))
 279               (nonascii-translation . latin-iso8859-2)
 280               (input-method . "latin-2-postfix")
 281               (unibyte-syntax . "latin-2")
 282               (unibyte-display . iso-8859-2)
 283               (tutorial . "TUTORIAL.sl")
 284               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 285               (documentation . t))
 286  '("European"))
 287
 288 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 289 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 290 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 291 ;; "Latin-3" language environment.
 292
 293 (set-language-info-alist
 294  "Turkish" '((charset ascii latin-iso8859-9)
 295              (coding-system iso-latin-5)
 296              (coding-priority iso-latin-5)
 297              (nonascii-translation . latin-iso8859-9)
 298              (unibyte-syntax . "latin-5")
 299              (unibyte-display . iso-latin-5)
 300              (input-method . "turkish-postfix")
 301              (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be)       Merhaba")
 302              (documentation . t)))
 303
 304 ;; Polish ISO 8859-2 environment.
 305 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 306 ;; Keywords: multilingual, Polish
 307
 308 (set-language-info-alist
 309  "Polish" '((charset . (ascii latin-iso8859-2))
 310            (coding-system . (iso-8859-2))
 311            (coding-priority . (iso-8859-2))
 312            (input-method . "polish-slash")
 313            (nonascii-translation . latin-iso8859-2)
 314            (unibyte-syntax . "latin-2")
 315            (unibyte-display . iso-8859-2)
 316            (tutorial . "TUTORIAL.pl")
 317            (sample-text . "\e,B1!fFjJ3#qQsS6&?/<,\e(B")
 318            (documentation . t))
 319  '("European"))
 320
 321 \f
 322 ;; Definitions for the Mac Roman character sets and coding system.
 323 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 324 ;; 255 for actual characters.  Emacs decode them to one of the
 325 ;; following character sets.
 326 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 327 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 328
 329 (let
 330     ((encoding-vector (make-vector 256 nil))
 331      (i 0)
 332      (vec       ;; mac-roman (128..255) -> UCS mapping
 333       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 334         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 335         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 336         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 337         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 338         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 339         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 340         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 341         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 342         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 343         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 344         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 345         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 346         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 347         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 348         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 349         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 350         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 351         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 352         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 353         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 354         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 355         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 356         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 357         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 358         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 359         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 360         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 361         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 362         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 363         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 364         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 365         #x2020  ;; 160:DAGGER
 366         #x00B0  ;; 161:DEGREE SIGN
 367         #x00A2  ;; 162:CENT SIGN
 368         #x00A3  ;; 163:POUND SIGN
 369         #x00A7  ;; 164:SECTION SIGN
 370         #x2022  ;; 165:BULLET
 371         #x00B6  ;; 166:PILCROW SIGN
 372         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 373         #x00AE  ;; 168:REGISTERED SIGN
 374         #x00A9  ;; 169:COPYRIGHT SIGN
 375         #x2122  ;; 170:TRADE MARK SIGN
 376         #x00B4  ;; 171:ACUTE ACCENT
 377         #x00A8  ;; 172:DIAERESIS
 378         #x2260  ;; 173:NOT EQUAL TO
 379         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 380         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 381         #x221E  ;; 176:INFINITY
 382         #x00B1  ;; 177:PLUS-MINUS SIGN
 383         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 384         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 385         #x00A5  ;; 180:YEN SIGN
 386         #x00B5  ;; 181:MICRO SIGN
 387         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 388         #x2211  ;; 183:N-ARY SUMMATION
 389         #x220F  ;; 184:N-ARY PRODUCT
 390         #x03C0  ;; 185:GREEK SMALL LETTER PI
 391         #x222B  ;; 186:INTEGRAL
 392         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 393         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 394         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 395         #x00E6  ;; 190:LATIN SMALL LETTER AE
 396         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 397         #x00BF  ;; 192:INVERTED QUESTION MARK
 398         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 399         #x00AC  ;; 194:NOT SIGN
 400         #x221A  ;; 195:SQUARE ROOT
 401         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 402         #x2248  ;; 197:ALMOST EQUAL TO
 403         #x2206  ;; 198:INCREMENT
 404         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 405         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 406         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 407         #x00A0  ;; 202:NO-BREAK SPACE
 408         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 409         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 410         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 411         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 412         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 413         #x2013  ;; 208:EN DASH
 414         #x2014  ;; 209:EM DASH
 415         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 416         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 417         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 418         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 419         #x00F7  ;; 214:DIVISION SIGN
 420         #x25CA  ;; 215:LOZENGE
 421         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 422         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 423         #x2044  ;; 218:FRACTION SLASH
 424         #x20AC  ;; 219:EURO SIGN
 425         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 426         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 427         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 428         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 429         #x2021  ;; 224:DOUBLE DAGGER
 430         #x00B7  ;; 225:MIDDLE DOT
 431         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 432         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 433         #x2030  ;; 228:PER MILLE SIGN
 434         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 435         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 436         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 437         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 438         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 439         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 440         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 441         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 442         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 443         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 444         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 445         #xF8FF  ;; 240:Apple logo
 446         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 447         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 448         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 449         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 450         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 451         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 452         #x02DC  ;; 247:SMALL TILDE
 453         #x00AF  ;; 248:MACRON
 454         #x02D8  ;; 249:BREVE
 455         #x02D9  ;; 250:DOT ABOVE
 456         #x02DA  ;; 251:RING ABOVE
 457         #x00B8  ;; 252:CEDILLA
 458         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 459         #x02DB  ;; 254:OGONEK
 460         #x02C7  ;; 255:CARON
 461         ])
 462      translation-table)
 463   (while (< i 128)
 464     (aset encoding-vector i i)
 465     (setq i (1+ i)))
 466   (while (< i 256)
 467     (aset encoding-vector i
 468           (decode-char 'ucs (aref vec (- i 128))))
 469     (setq i (1+ i)))
 470   (setq translation-table
 471         (make-translation-table-from-vector encoding-vector))
 472   (define-translation-table 'mac-roman-decoder translation-table)
 473   (define-translation-table 'mac-roman-encoder
 474     (char-table-extra-slot translation-table 0)))
 475
 476 (define-ccl-program decode-mac-roman
 477   `(4
 478     ((loop
 479       (read r1)
 480       (if (r1 < 128)  ;; ASCII
 481           (r0 = ,(charset-id 'ascii))
 482         (if (r0 < 160)
 483             (r0 = ,(charset-id 'eight-bit-control))
 484           (r0 = ,(charset-id 'eight-bit-graphic))))
 485       (translate-character mac-roman-decoder r0 r1)
 486       (write-multibyte-character r0 r1)
 487       (repeat))))
 488   "CCL program to decode Mac Roman")
 489
 490 (define-ccl-program encode-mac-roman
 491   `(1
 492     ((loop
 493       (read-multibyte-character r0 r1)
 494       (translate-character mac-roman-encoder r0 r1)
 495       (write-repeat r1))))
 496   "CCL program to encode Mac Roman")
 497
 498 (make-coding-system
 499  'mac-roman 4 ?M "Mac Roman Encoding"
 500  '(decode-mac-roman . encode-mac-roman)
 501  '((safe-chars . mac-roman-encoder)
 502    (valid-codes (0 . 255))))
 503
 504 (provide 'european)
 505
 506 ;;; european.el ends here