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

   1 ;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 1995, 1997, 2001 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 specific language environments for the following languages:
  63   For Dutch, \"Dutch\".
  64   For German, \"German\".
  65   For Spanish, \"Spanish\".
  66   For French, \"French\".
  67
  68 Latin-1 also covers several written languages outside Europe, including
  69 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  70  '("European"))
  71
  72 \f
  73 ;; Latin-2 (ISO-8859-2)
  74
  75 (make-coding-system
  76  'iso-latin-2 2 ?2
  77  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
  78  '(ascii latin-iso8859-2 nil nil
  79    nil nil nil nil nil nil nil)
  80  '((safe-charsets ascii latin-iso8859-2)
  81    (mime-charset . iso-8859-2)))
  82
  83 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  84 (define-coding-system-alias 'latin-2 'iso-latin-2)
  85
  86 (set-language-info-alist
  87  "Latin-2" '((charset ascii latin-iso8859-2)
  88              (coding-system iso-latin-2)
  89              (coding-priority iso-latin-2)
  90              (nonascii-translation . latin-iso8859-2)
  91              (unibyte-syntax . "latin-2")
  92              (unibyte-display . iso-latin-2)
  93              (input-method . "latin-2-prefix")
  94              (documentation . "\
  95 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  96 character set which supports the following languages:
  97  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
  98  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
  99  and Swedish.
 100 We also have specific language environments for the following languages:
 101   For Czech, \"Czech\".
 102   For Romanian, \"Romanian\".
 103   For Slovak, \"Slovak\"."))
 104  '("European"))
 105
 106 \f
 107 ;; Latin-3 (ISO-8859-3)
 108
 109 (make-coding-system
 110  'iso-latin-3 2 ?3
 111  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
 112  '(ascii latin-iso8859-3 nil nil
 113    nil nil nil nil nil nil nil)
 114  '((safe-charsets ascii latin-iso8859-3)
 115    (mime-charset . iso-8859-3)))
 116
 117 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 118 (define-coding-system-alias 'latin-3 'iso-latin-3)
 119
 120 (set-language-info-alist
 121  "Latin-3" '((charset ascii latin-iso8859-3)
 122              (coding-system iso-latin-3)
 123              (coding-priority iso-latin-3)
 124              (nonascii-translation . latin-iso8859-3)
 125              (unibyte-syntax . "latin-3")
 126              (unibyte-display . iso-latin-3)
 127              (input-method . "latin-3-prefix")
 128              (documentation . "\
 129 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 130  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 131  German, Italian, Maltese, Spanish, and Turkish."))
 132  '("European"))
 133
 134 \f
 135 ;; Latin-4 (ISO-8859-4)
 136
 137 (make-coding-system
 138  'iso-latin-4 2 ?4
 139  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
 140  '(ascii latin-iso8859-4 nil nil
 141    nil nil nil nil nil nil nil)
 142  '((safe-charsets ascii latin-iso8859-4)
 143    (mime-charset . iso-8859-4)))
 144
 145 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 146 (define-coding-system-alias 'latin-4 'iso-latin-4)
 147
 148 (set-language-info-alist
 149  "Latin-4" '((charset ascii latin-iso8859-4)
 150              (coding-system iso-8859-4)
 151              (coding-priority iso-8859-4)
 152              (nonascii-translation . latin-iso8859-4)
 153              (unibyte-syntax . "latin-4")
 154              (unibyte-display . iso-8859-4)
 155              (input-method . "latin-4-postfix")
 156              (documentation . "\
 157 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 158  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 159  Latvian, Lithuanian, and Norwegian."))
 160  '("European"))
 161
 162 \f
 163 ;; Latin-5 (ISO-8859-9)
 164
 165 (make-coding-system
 166  'iso-latin-5 2 ?9
 167  "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
 168  '(ascii latin-iso8859-9 nil nil
 169    nil nil nil nil nil nil nil)
 170  '((safe-charsets ascii latin-iso8859-9)
 171    (mime-charset . iso-8859-9)))
 172
 173 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 174 (define-coding-system-alias 'latin-5 'iso-latin-5)
 175
 176 (set-language-info-alist
 177  "Latin-5" '((charset ascii latin-iso8859-9)
 178              (coding-system iso-latin-5)
 179              (coding-priority iso-latin-5)
 180              (nonascii-translation . latin-iso8859-9)
 181              (unibyte-syntax . "latin-5")
 182              (unibyte-display . iso-latin-5)
 183              (input-method . "latin-5-postfix")
 184              (documentation . "\
 185 These languages are supported with the Latin-5 (ISO-8859-9) character set:
 186 Bulgarian, Byelorussian, (Slavic) Macedonian, Russian, Serbian and
 187 Ukranian."))                            ; says ISO 8859-1
 188  '("European"))
 189
 190 \f
 191 ;; Latin-8 (ISO-8859-14)
 192
 193 (make-coding-system
 194  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 195                                         ; for `Celtic' is taken.
 196  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)"
 197  '(ascii latin-iso8859-14 nil nil
 198    nil nil nil nil nil nil nil nil nil nil nil nil t)
 199  '((safe-charsets ascii latin-iso8859-14)
 200    (mime-charset . iso-8859-14)))
 201
 202 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 203 (define-coding-system-alias 'latin-8 'iso-latin-8)
 204
 205 (set-language-info-alist
 206  "Latin-8" '((charset ascii latin-iso8859-14)
 207              (coding-system iso-latin-8)
 208              (coding-priority iso-latin-8)
 209              (nonascii-translation . latin-iso8859-14)
 210              (unibyte-syntax . "latin-8")
 211              (unibyte-display . iso-latin-8)
 212              (input-method . "latin-8-prefix")
 213              ;; Fixme: Welsh/Ga{e}lic greetings
 214              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 215              (documentation . "\
 216 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 217 character set which supports the Celtic languages, including those not
 218 covered by other ISO-8859 character sets: Welsh, Manx Gaelic and
 219 Irish Gaelic (old orthography)."))
 220  '("European"))
 221 \f
 222 ;; Latin-9 (ISO-8859-15)
 223
 224 (make-coding-system
 225  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 226  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)"
 227  '(ascii latin-iso8859-15 nil nil
 228    nil nil nil nil nil nil nil nil nil nil nil nil t)
 229  '((safe-charsets ascii latin-iso8859-15)
 230    (mime-charset . iso-8859-15)))
 231
 232 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 233 (define-coding-system-alias 'latin-9 'iso-latin-9)
 234 (define-coding-system-alias 'latin-0 'iso-latin-9)
 235
 236 (set-language-info-alist
 237  "Latin-9" '((charset ascii latin-iso8859-15)
 238              (coding-system iso-latin-9)
 239              (coding-priority iso-latin-9)
 240              (nonascii-translation . latin-iso8859-15)
 241              (unibyte-syntax . "latin-9")
 242              (unibyte-display . iso-latin-9)
 243              (input-method . "latin-9-prefix")
 244              (sample-text
 245               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 246              (documentation . "\
 247 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 248 character set which supports the same languages as Latin-1 with the
 249 addition of the Euro sign and some additional French and Finnish letters.
 250 Latin-9 is sometimes nicknamed `Latin-0'."))
 251  '("European"))
 252 \f
 253 (set-language-info-alist
 254  "German" '((tutorial . "TUTORIAL.de")
 255             (charset ascii latin-iso8859-1)
 256             (coding-system iso-latin-1)
 257             (coding-priority iso-latin-1)
 258             (input-method . "german-postfix")
 259             (nonascii-translation . iso-latin-1)
 260             (unibyte-syntax . "latin-1")
 261             (unibyte-display . iso-latin-1)
 262             (sample-text . "\
 263 German (Deutsch Nord)   Guten Tag
 264 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 265             (documentation . "\
 266 This language environment is almost the same as Latin-1,
 267 but the default input method is set to \"german-postfix\"."))
 268  '("European"))
 269
 270 (set-language-info-alist
 271  "French" '((tutorial . "TUTORIAL.fr")
 272             (charset ascii latin-iso8859-1)
 273             (coding-system iso-latin-1)
 274             (coding-priority iso-latin-1)
 275             (nonascii-translation . latin-iso8859-1)
 276             (unibyte-syntax . "latin-1")
 277             (unibyte-display . iso-latin-1)
 278             (input-method . "latin-1-prefix")
 279             (sample-text . "French (Fran\e,Ag\e(Bais)     Bonjour, Salut")
 280             (documentation . "\
 281 This language environment is almost the same as Latin-1,
 282 but the tutorial is set to \"TUTORIAL.fr\"."))
 283  '("European"))
 284
 285 (set-language-info-alist
 286  "Slovenian" '((charset . (ascii latin-iso8859-2))
 287               (coding-system . (iso-8859-2))
 288               (coding-priority . (iso-8859-2))
 289               (nonascii-translation . latin-iso8859-2)
 290               (input-method . "latin-2-postfix")
 291               (unibyte-syntax . "latin-2")
 292               (unibyte-display . iso-8859-2)
 293               (tutorial . "TUTORIAL.sl")
 294               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 295               (documentation . t))
 296  '("European"))
 297
 298 (set-language-info-alist
 299  "Spanish" '((tutorial . "TUTORIAL.es")
 300             (charset ascii latin-iso8859-1)
 301             (coding-system iso-latin-1)
 302             (coding-priority iso-latin-1)
 303             (input-method . "spanish-postfix")
 304             (nonascii-translation . iso-latin-1)
 305             (unibyte-syntax . "latin-1")
 306             (unibyte-display . iso-latin-1)
 307             (sample-text . "Spanish (Espa\e,Aq\e(Bol)     \e,A!\e(BHola!")
 308             (documentation . "\
 309 This language environment is almost the same as Latin-1,
 310 but the default input method is set to \"spanish-postfix\",
 311 and it selects the Spanish tutorial."))
 312  '("European"))
 313
 314 (set-language-info-alist
 315  "Dutch" '((tutorial . "TUTORIAL.nl")
 316            (charset ascii latin-iso8859-1)
 317            (coding-system iso-latin-1)
 318            (coding-priority iso-latin-1)
 319            (nonascii-translation . iso-latin-1)
 320            (unibyte-syntax . "latin-1")
 321            (unibyte-display . iso-latin-1)
 322            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 323            (documentation . "\
 324 This language environment is almost the same as Latin-1,
 325 but select's the Dutch tutorial."))
 326  '("European"))
 327
 328 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 329 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 330 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 331 ;; "Latin-3" language environment.
 332
 333 (set-language-info-alist
 334  "Turkish" '((charset ascii latin-iso8859-9)
 335              (coding-system iso-latin-5)
 336              (coding-priority iso-latin-5)
 337              (nonascii-translation . latin-iso8859-9)
 338              (unibyte-syntax . "latin-5")
 339              (unibyte-display . iso-latin-5)
 340              (input-method . "turkish-postfix")
 341              (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be)       Merhaba")
 342              (documentation . t)))
 343
 344 ;; Polish ISO 8859-2 environment.
 345 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 346 ;; Keywords: multilingual, Polish
 347
 348 (set-language-info-alist
 349  "Polish" '((charset . (ascii latin-iso8859-2))
 350            (coding-system . (iso-8859-2))
 351            (coding-priority . (iso-8859-2))
 352            (input-method . "polish-slash")
 353            (nonascii-translation . latin-iso8859-2)
 354            (unibyte-syntax . "latin-2")
 355            (unibyte-display . iso-8859-2)
 356            (tutorial . "TUTORIAL.pl")
 357            (sample-text . "P\e,Bs\e(Bjd\e,B<\e(B, ki\e,Bq\e(B-\e,B?\e(Be t\e,Bj\e(B chmurno\e,B6f\e(B w g\e,B31\e(Bb flaszy")
 358            (documentation . t))
 359  '("European"))
 360
 361 \f
 362 ;; Definitions for the Mac Roman character sets and coding system.
 363 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 364 ;; 255 for actual characters.  Emacs decodes them to one of the
 365 ;; following character sets.
 366 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 367 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 368
 369 (let
 370     ((encoding-vector (make-vector 256 nil))
 371      (i 0)
 372      (vec       ;; mac-roman (128..255) -> UCS mapping
 373       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 374         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 375         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 376         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 377         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 378         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 379         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 380         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 381         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 382         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 383         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 384         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 385         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 386         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 387         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 388         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 389         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 390         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 391         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 392         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 393         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 394         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 395         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 396         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 397         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 398         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 399         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 400         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 401         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 402         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 403         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 404         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 405         #x2020  ;; 160:DAGGER
 406         #x00B0  ;; 161:DEGREE SIGN
 407         #x00A2  ;; 162:CENT SIGN
 408         #x00A3  ;; 163:POUND SIGN
 409         #x00A7  ;; 164:SECTION SIGN
 410         #x2022  ;; 165:BULLET
 411         #x00B6  ;; 166:PILCROW SIGN
 412         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 413         #x00AE  ;; 168:REGISTERED SIGN
 414         #x00A9  ;; 169:COPYRIGHT SIGN
 415         #x2122  ;; 170:TRADE MARK SIGN
 416         #x00B4  ;; 171:ACUTE ACCENT
 417         #x00A8  ;; 172:DIAERESIS
 418         #x2260  ;; 173:NOT EQUAL TO
 419         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 420         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 421         #x221E  ;; 176:INFINITY
 422         #x00B1  ;; 177:PLUS-MINUS SIGN
 423         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 424         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 425         #x00A5  ;; 180:YEN SIGN
 426         #x00B5  ;; 181:MICRO SIGN
 427         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 428         #x2211  ;; 183:N-ARY SUMMATION
 429         #x220F  ;; 184:N-ARY PRODUCT
 430         #x03C0  ;; 185:GREEK SMALL LETTER PI
 431         #x222B  ;; 186:INTEGRAL
 432         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 433         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 434         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 435         #x00E6  ;; 190:LATIN SMALL LETTER AE
 436         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 437         #x00BF  ;; 192:INVERTED QUESTION MARK
 438         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 439         #x00AC  ;; 194:NOT SIGN
 440         #x221A  ;; 195:SQUARE ROOT
 441         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 442         #x2248  ;; 197:ALMOST EQUAL TO
 443         #x2206  ;; 198:INCREMENT
 444         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 445         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 446         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 447         #x00A0  ;; 202:NO-BREAK SPACE
 448         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 449         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 450         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 451         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 452         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 453         #x2013  ;; 208:EN DASH
 454         #x2014  ;; 209:EM DASH
 455         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 456         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 457         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 458         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 459         #x00F7  ;; 214:DIVISION SIGN
 460         #x25CA  ;; 215:LOZENGE
 461         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 462         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 463         #x2044  ;; 218:FRACTION SLASH
 464         #x20AC  ;; 219:EURO SIGN
 465         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 466         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 467         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 468         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 469         #x2021  ;; 224:DOUBLE DAGGER
 470         #x00B7  ;; 225:MIDDLE DOT
 471         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 472         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 473         #x2030  ;; 228:PER MILLE SIGN
 474         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 475         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 476         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 477         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 478         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 479         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 480         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 481         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 482         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 483         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 484         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 485         #xF8FF  ;; 240:Apple logo
 486         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 487         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 488         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 489         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 490         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 491         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 492         #x02DC  ;; 247:SMALL TILDE
 493         #x00AF  ;; 248:MACRON
 494         #x02D8  ;; 249:BREVE
 495         #x02D9  ;; 250:DOT ABOVE
 496         #x02DA  ;; 251:RING ABOVE
 497         #x00B8  ;; 252:CEDILLA
 498         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 499         #x02DB  ;; 254:OGONEK
 500         #x02C7  ;; 255:CARON
 501         ])
 502      translation-table)
 503   (while (< i 128)
 504     (aset encoding-vector i i)
 505     (setq i (1+ i)))
 506   (while (< i 256)
 507     (aset encoding-vector i
 508           (decode-char 'ucs (aref vec (- i 128))))
 509     (setq i (1+ i)))
 510   (setq translation-table
 511         (make-translation-table-from-vector encoding-vector))
 512   (define-translation-table 'mac-roman-decoder translation-table)
 513   (define-translation-table 'mac-roman-encoder
 514     (char-table-extra-slot translation-table 0)))
 515
 516 (define-ccl-program decode-mac-roman
 517   `(4
 518     ((loop
 519       (read r1)
 520       (if (r1 < 128)  ;; ASCII
 521           (r0 = ,(charset-id 'ascii))
 522         (if (r1 < 160)
 523             (r0 = ,(charset-id 'eight-bit-control))
 524           (r0 = ,(charset-id 'eight-bit-graphic))))
 525       (translate-character mac-roman-decoder r0 r1)
 526       (write-multibyte-character r0 r1)
 527       (repeat))))
 528   "CCL program to decode Mac Roman")
 529
 530 (define-ccl-program encode-mac-roman
 531   `(1
 532     ((loop
 533       (read-multibyte-character r0 r1)
 534       (translate-character mac-roman-encoder r0 r1)
 535       (write-repeat r1))))
 536   "CCL program to encode Mac Roman")
 537
 538 (make-coding-system
 539  'mac-roman 4 ?M "Mac Roman Encoding"
 540  '(decode-mac-roman . encode-mac-roman)
 541  '((safe-chars . mac-roman-encoder)
 542    (valid-codes (0 . 255))
 543    (mime-charset . macintosh)))         ; per IANA, rfc1345
 544
 545 (defconst diacritic-composition-pattern "\\C^\\c^+")
 546
 547 ;;;###autoload
 548 (defun diacritic-compose-region (beg end)
 549   "Compose diacritic characters in the region.
 550 When called from a program, expects two arguments,
 551 positions (integers or markers) specifying the region."
 552   (interactive "r")
 553   (save-restriction
 554     (narrow-to-region beg end)
 555     (goto-char (point-min))
 556     (while (re-search-forward diacritic-composition-pattern nil t)
 557       (compose-region (match-beginning 0) (match-end 0)))))
 558
 559 ;;;###autoload
 560 (defun diacritic-compose-string (string)
 561   "Compose diacritic characters in STRING and return the resulting string."
 562   (let ((idx 0))
 563     (while (setq idx (string-match diacritic-composition-pattern string idx))
 564       (compose-string string idx (match-end 0))
 565       (setq idx (match-end 0))))
 566   string)
 567
 568 ;;;###autoload
 569 (defun diacritic-compose-buffer ()
 570   "Compose diacritic characters in the current buffer."
 571   (interactive)
 572   (diacritic-compose-region (point-min) (point-max)))
 573
 574 ;;;###autoload
 575 (defun diacritic-post-read-conversion (len)
 576   (diacritic-compose-region (point) (+ (point) len))
 577   len)
 578
 579 ;;;###autoload
 580 (defun diacritic-composition-function (from to pattern &optional string)
 581   "Compose diacritic text in the region FROM and TO.
 582 The text matches the regular expression PATTERN.
 583 Optional 4th argument STRING, if non-nil, is a string containing text
 584 to compose.
 585
 586 The return value is number of composed characters."
 587   (if (< (1+ from) to)
 588       (prog1 (- to from)
 589         (if string
 590             (compose-string string from to)
 591           (compose-region from to))
 592         (- to from))))
 593
 594 ;; Register a function to compose Unicode diacrtics and marks.
 595 (let ((patterns '(("\\C^\\c^+" . diacrtic-composition-function))))
 596   (let ((c #x300))
 597     (while (<= c #x362)
 598       (aset composition-function-table (decode-char 'ucs c) patterns)
 599       (setq c (1+ c)))
 600     (setq c #x20d0)
 601     (while (<= c #x20e3)
 602       (aset composition-function-table (decode-char 'ucs c) patterns)
 603       (setq c (1+ c)))))
 604
 605 (provide 'european)
 606
 607 ;;; european.el ends here