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 ;; Copyright (C) 2001 Free Software Foundation, Inc.
   6
   7 ;; Keywords: multilingual, European
   8
   9 ;; This file is part of GNU Emacs.
  10
  11 ;; GNU Emacs is free software; you can redistribute it and/or modify
  12 ;; it under the terms of the GNU General Public License as published by
  13 ;; the Free Software Foundation; either version 2, or (at your option)
  14 ;; any later version.
  15
  16 ;; GNU Emacs is distributed in the hope that it will be useful,
  17 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19 ;; GNU General Public License for more details.
  20
  21 ;; You should have received a copy of the GNU General Public License
  22 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  23 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  24 ;; Boston, MA 02111-1307, USA.
  25
  26 ;;; Commentary:
  27
  28 ;; For European scripts, character sets ISO8859-1,2,3,4,9,14,15 are
  29 ;; supported.
  30
  31 ;;; Code:
  32
  33 ;; Latin-1 (ISO-8859-1)
  34
  35 (make-coding-system
  36  'iso-latin-1 2 ?1
  37  "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
  38  '(ascii latin-iso8859-1 nil nil
  39    nil nil nil nil nil nil nil nil nil nil nil nil t)
  40  '((safe-charsets ascii latin-iso8859-1)
  41    (mime-charset . iso-8859-1)))
  42
  43 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
  44 (define-coding-system-alias 'latin-1 'iso-latin-1)
  45
  46 (set-language-info-alist
  47  "Latin-1" '((charset ascii latin-iso8859-1)
  48              (coding-system iso-latin-1)
  49              (coding-priority iso-latin-1)
  50              (nonascii-translation . latin-iso8859-1)
  51              (unibyte-syntax . "latin-1")
  52              (unibyte-display . iso-latin-1)
  53              (input-method . "latin-1-prefix")
  54              (sample-text
  55               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  56              (documentation . "\
  57 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  58 character set which supports the following European languages:
  59  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  60  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  61  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  62  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  63  Scottish Gaelic, Spanish, and Swedish.
  64 We also have specific language environments for the following languages:
  65   For Dutch, \"Dutch\".
  66   For German, \"German\".
  67   For Spanish, \"Spanish\".
  68   For French, \"French\".
  69
  70 Latin-1 also covers several written languages outside Europe, including
  71 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  72  '("European"))
  73
  74 \f
  75 ;; Latin-2 (ISO-8859-2)
  76
  77 (make-coding-system
  78  'iso-latin-2 2 ?2
  79  "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  80  '(ascii latin-iso8859-2 nil nil
  81    nil nil nil nil nil nil nil)
  82  '((safe-charsets ascii latin-iso8859-2)
  83    (mime-charset . iso-8859-2)))
  84
  85 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  86 (define-coding-system-alias 'latin-2 'iso-latin-2)
  87
  88 (set-language-info-alist
  89  "Latin-2" '((charset ascii latin-iso8859-2)
  90              (coding-system iso-latin-2)
  91              (coding-priority iso-latin-2)
  92              (nonascii-translation . latin-iso8859-2)
  93              (unibyte-syntax . "latin-2")
  94              (unibyte-display . iso-latin-2)
  95              (input-method . "latin-2-prefix")
  96              (documentation . "\
  97 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  98 character set which supports the following languages:
  99  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 100  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
 101  and Swedish.
 102 We also have specific language environments for the following languages:
 103   For Czech, \"Czech\".
 104   For Romanian, \"Romanian\".
 105   For Slovak, \"Slovak\"."))
 106  '("European"))
 107
 108 \f
 109 ;; Latin-3 (ISO-8859-3)
 110
 111 (make-coding-system
 112  'iso-latin-3 2 ?3
 113  "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
 114  '(ascii latin-iso8859-3 nil nil
 115    nil nil nil nil nil nil nil)
 116  '((safe-charsets ascii latin-iso8859-3)
 117    (mime-charset . iso-8859-3)))
 118
 119 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 120 (define-coding-system-alias 'latin-3 'iso-latin-3)
 121
 122 (set-language-info-alist
 123  "Latin-3" '((charset ascii latin-iso8859-3)
 124              (coding-system iso-latin-3)
 125              (coding-priority iso-latin-3)
 126              (nonascii-translation . latin-iso8859-3)
 127              (unibyte-syntax . "latin-3")
 128              (unibyte-display . iso-latin-3)
 129              (input-method . "latin-3-prefix")
 130              (documentation . "\
 131 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 132  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 133  German, Italian, Maltese, Spanish, and Turkish."))
 134  '("European"))
 135
 136 \f
 137 ;; Latin-4 (ISO-8859-4)
 138
 139 (make-coding-system
 140  'iso-latin-4 2 ?4
 141  "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
 142  '(ascii latin-iso8859-4 nil nil
 143    nil nil nil nil nil nil nil)
 144  '((safe-charsets ascii latin-iso8859-4)
 145    (mime-charset . iso-8859-4)))
 146
 147 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 148 (define-coding-system-alias 'latin-4 'iso-latin-4)
 149
 150 (set-language-info-alist
 151  "Latin-4" '((charset ascii latin-iso8859-4)
 152              (coding-system iso-8859-4)
 153              (coding-priority iso-8859-4)
 154              (nonascii-translation . latin-iso8859-4)
 155              (unibyte-syntax . "latin-4")
 156              (unibyte-display . iso-8859-4)
 157              (input-method . "latin-4-postfix")
 158              (documentation . "\
 159 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 160  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 161  Latvian, Lithuanian, and Norwegian."))
 162  '("European"))
 163
 164 \f
 165 ;; Latin-5 (ISO-8859-9)
 166
 167 (make-coding-system
 168  'iso-latin-5 2 ?9
 169  "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
 170  '(ascii latin-iso8859-9 nil nil
 171    nil nil nil nil nil nil nil)
 172  '((safe-charsets ascii latin-iso8859-9)
 173    (mime-charset . iso-8859-9)))
 174
 175 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 176 (define-coding-system-alias 'latin-5 'iso-latin-5)
 177
 178 (set-language-info-alist
 179  "Latin-5" '((charset ascii latin-iso8859-9)
 180              (coding-system iso-latin-5)
 181              (coding-priority iso-latin-5)
 182              (nonascii-translation . latin-iso8859-9)
 183              (unibyte-syntax . "latin-5")
 184              (unibyte-display . iso-latin-5)
 185              (input-method . "latin-5-postfix")
 186              (documentation . "Support for Turkish language."))
 187  '("European"))
 188
 189 \f
 190 ;; Latin-8 (ISO-8859-14)
 191
 192 (make-coding-system
 193  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 194                                         ; for `Celtic' is taken.
 195  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 196  '(ascii latin-iso8859-14 nil nil
 197    nil nil nil nil nil nil nil nil nil nil nil nil t)
 198  '((safe-charsets ascii latin-iso8859-14)
 199    (mime-charset . iso-8859-14)))
 200
 201 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 202 (define-coding-system-alias 'latin-8 'iso-latin-8)
 203
 204 (set-language-info-alist
 205  "Latin-8" '((charset ascii latin-iso8859-14)
 206              (coding-system iso-latin-8)
 207              (coding-priority iso-latin-8)
 208              (nonascii-translation . latin-iso8859-14)
 209              (unibyte-syntax . "latin-8")
 210              (unibyte-display . iso-latin-8)
 211              (input-method . "latin-8-prefix")
 212              ;; Fixme: Welsh/Ga{e}lic greetings
 213              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 214              (documentation . "\
 215 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 216 character set which supports the Celtic languages, including those not
 217 covered by other ISO-8859 character sets:
 218  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 219  '("European"))
 220 \f
 221 ;; Latin-9 (ISO-8859-15)
 222
 223 (make-coding-system
 224  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 225  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 226  '(ascii latin-iso8859-15 nil nil
 227    nil nil nil nil nil nil nil nil nil nil nil nil t)
 228  '((safe-charsets ascii latin-iso8859-15)
 229    (mime-charset . iso-8859-15)))
 230
 231 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 232 (define-coding-system-alias 'latin-9 'iso-latin-9)
 233 (define-coding-system-alias 'latin-0 'iso-latin-9)
 234
 235 (set-language-info-alist
 236  "Latin-9" '((charset ascii latin-iso8859-15)
 237              (coding-system iso-latin-9)
 238              (coding-priority iso-latin-9)
 239              (nonascii-translation . latin-iso8859-15)
 240              (unibyte-syntax . "latin-9")
 241              (unibyte-display . iso-latin-9)
 242              (input-method . "latin-9-prefix")
 243              (sample-text
 244               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 245              (documentation . "\
 246 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 247 character set which supports the same languages as Latin-1 with the
 248 addition of the Euro sign and some additional French and Finnish letters.
 249 Latin-9 is sometimes nicknamed `Latin-0'."))
 250  '("European"))
 251 \f
 252 (set-language-info-alist
 253  "German" '((tutorial . "TUTORIAL.de")
 254             (charset ascii latin-iso8859-1)
 255             (coding-system iso-latin-1)
 256             (coding-priority iso-latin-1)
 257             (input-method . "german-postfix")
 258             (nonascii-translation . iso-latin-1)
 259             (unibyte-syntax . "latin-1")
 260             (unibyte-display . iso-latin-1)
 261             (sample-text . "\
 262 German (Deutsch Nord)   Guten Tag
 263 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 264             (documentation . "\
 265 This language environment is almost the same as Latin-1,
 266 but sets the default input method to \"german-postfix\".
 267 Additionally, it selects the German tutorial."))
 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 it selects the French tutorial."))
 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 it sets the default input method 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 it selects 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 (set-language-info-alist
 362  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 363            (coding-priority utf-8 latin-8)
 364            (input-method . "welsh")
 365            (documentation . "Support for Welsh, using Unicode."))
 366  '("European"))
 367
 368 (set-language-info-alist
 369  "Latin-7" `((coding-system latin-7)
 370              (coding-priority latin-7)
 371              ;; Fixme: input-method
 372              (features code-pages)
 373              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 374  '("European"))
 375
 376 (set-language-info-alist
 377  "Lithuanian" `((coding-system latin-7)
 378                 (coding-priority latin-7)
 379                 (input-method . "lithuanian-keyboard")
 380                 (features code-pages)
 381                 (documentation . "Support for Lithuanian."))
 382  '("European"))
 383
 384 (set-language-info-alist
 385  "Latvian" `((coding-system latin-7)
 386              (coding-priority latin-7)
 387              (input-method . "latvian-keyboard")
 388              (features code-pages)
 389              (documentation . "Support for Latvian."))
 390  '("European"))
 391 \f
 392 ;; Definitions for the Mac Roman character sets and coding system.
 393 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 394 ;; 255 for actual characters.  Emacs decodes them to one of the
 395 ;; following character sets.
 396 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 397 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 398
 399 (let
 400     ((encoding-vector (make-vector 256 nil))
 401      (i 0)
 402      (vec       ;; mac-roman (128..255) -> UCS mapping
 403       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 404         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 405         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 406         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 407         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 408         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 409         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 410         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 411         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 412         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 413         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 414         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 415         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 416         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 417         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 418         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 419         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 420         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 421         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 422         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 423         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 424         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 425         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 426         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 427         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 428         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 429         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 430         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 431         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 432         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 433         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 434         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 435         #x2020  ;; 160:DAGGER
 436         #x00B0  ;; 161:DEGREE SIGN
 437         #x00A2  ;; 162:CENT SIGN
 438         #x00A3  ;; 163:POUND SIGN
 439         #x00A7  ;; 164:SECTION SIGN
 440         #x2022  ;; 165:BULLET
 441         #x00B6  ;; 166:PILCROW SIGN
 442         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 443         #x00AE  ;; 168:REGISTERED SIGN
 444         #x00A9  ;; 169:COPYRIGHT SIGN
 445         #x2122  ;; 170:TRADE MARK SIGN
 446         #x00B4  ;; 171:ACUTE ACCENT
 447         #x00A8  ;; 172:DIAERESIS
 448         #x2260  ;; 173:NOT EQUAL TO
 449         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 450         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 451         #x221E  ;; 176:INFINITY
 452         #x00B1  ;; 177:PLUS-MINUS SIGN
 453         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 454         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 455         #x00A5  ;; 180:YEN SIGN
 456         #x00B5  ;; 181:MICRO SIGN
 457         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 458         #x2211  ;; 183:N-ARY SUMMATION
 459         #x220F  ;; 184:N-ARY PRODUCT
 460         #x03C0  ;; 185:GREEK SMALL LETTER PI
 461         #x222B  ;; 186:INTEGRAL
 462         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 463         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 464         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 465         #x00E6  ;; 190:LATIN SMALL LETTER AE
 466         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 467         #x00BF  ;; 192:INVERTED QUESTION MARK
 468         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 469         #x00AC  ;; 194:NOT SIGN
 470         #x221A  ;; 195:SQUARE ROOT
 471         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 472         #x2248  ;; 197:ALMOST EQUAL TO
 473         #x2206  ;; 198:INCREMENT
 474         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 475         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 476         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 477         #x00A0  ;; 202:NO-BREAK SPACE
 478         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 479         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 480         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 481         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 482         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 483         #x2013  ;; 208:EN DASH
 484         #x2014  ;; 209:EM DASH
 485         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 486         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 487         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 488         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 489         #x00F7  ;; 214:DIVISION SIGN
 490         #x25CA  ;; 215:LOZENGE
 491         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 492         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 493         #x2044  ;; 218:FRACTION SLASH
 494         #x20AC  ;; 219:EURO SIGN
 495         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 496         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 497         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 498         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 499         #x2021  ;; 224:DOUBLE DAGGER
 500         #x00B7  ;; 225:MIDDLE DOT
 501         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 502         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 503         #x2030  ;; 228:PER MILLE SIGN
 504         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 505         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 506         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 507         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 508         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 509         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 510         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 511         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 512         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 513         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 514         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 515         #xF8FF  ;; 240:Apple logo
 516         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 517         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 518         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 519         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 520         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 521         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 522         #x02DC  ;; 247:SMALL TILDE
 523         #x00AF  ;; 248:MACRON
 524         #x02D8  ;; 249:BREVE
 525         #x02D9  ;; 250:DOT ABOVE
 526         #x02DA  ;; 251:RING ABOVE
 527         #x00B8  ;; 252:CEDILLA
 528         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 529         #x02DB  ;; 254:OGONEK
 530         #x02C7  ;; 255:CARON
 531         ])
 532      translation-table)
 533   (while (< i 128)
 534     (aset encoding-vector i i)
 535     (setq i (1+ i)))
 536   (while (< i 256)
 537     (aset encoding-vector i
 538           (decode-char 'ucs (aref vec (- i 128))))
 539     (setq i (1+ i)))
 540   (setq translation-table
 541         (make-translation-table-from-vector encoding-vector))
 542   (define-translation-table 'mac-roman-decoder translation-table)
 543   (define-translation-table 'mac-roman-encoder
 544     (char-table-extra-slot translation-table 0)))
 545
 546 (define-ccl-program decode-mac-roman
 547   `(4
 548     ((loop
 549       (read r1)
 550       (if (r1 < 128)  ;; ASCII
 551           (r0 = ,(charset-id 'ascii))
 552         (if (r1 < 160)
 553             (r0 = ,(charset-id 'eight-bit-control))
 554           (r0 = ,(charset-id 'eight-bit-graphic))))
 555       (translate-character mac-roman-decoder r0 r1)
 556       (write-multibyte-character r0 r1)
 557       (repeat))))
 558   "CCL program to decode Mac Roman")
 559
 560 (define-ccl-program encode-mac-roman
 561   `(1
 562     ((loop
 563       (read-multibyte-character r0 r1)
 564       (translate-character mac-roman-encoder r0 r1)
 565       (write-repeat r1))))
 566   "CCL program to encode Mac Roman")
 567
 568 (make-coding-system
 569  'mac-roman 4 ?M
 570  "Mac Roman Encoding (MIME:MACINTOSH)."
 571  '(decode-mac-roman . encode-mac-roman)
 572  '((safe-chars . mac-roman-encoder)
 573    (valid-codes (0 . 255))
 574    (mime-charset . macintosh)))         ; per IANA, rfc1345
 575
 576 (defconst diacritic-composition-pattern "\\C^\\c^+")
 577
 578 (defun diacritic-compose-region (beg end)
 579   "Compose diacritic characters in the region.
 580 When called from a program, expects two arguments,
 581 positions (integers or markers) specifying the region."
 582   (interactive "r")
 583   (save-restriction
 584     (narrow-to-region beg end)
 585     (goto-char (point-min))
 586     (while (re-search-forward diacritic-composition-pattern nil t)
 587       (compose-region (match-beginning 0) (match-end 0)))))
 588
 589 (defun diacritic-compose-string (string)
 590   "Compose diacritic characters in STRING and return the resulting string."
 591   (let ((idx 0))
 592     (while (setq idx (string-match diacritic-composition-pattern string idx))
 593       (compose-string string idx (match-end 0))
 594       (setq idx (match-end 0))))
 595   string)
 596
 597 (defun diacritic-compose-buffer ()
 598   "Compose diacritic characters in the current buffer."
 599   (interactive)
 600   (diacritic-compose-region (point-min) (point-max)))
 601
 602 (defun diacritic-post-read-conversion (len)
 603   (diacritic-compose-region (point) (+ (point) len))
 604   len)
 605
 606 (defun diacritic-composition-function (from to pattern &optional string)
 607   "Compose diacritic text in the region FROM and TO.
 608 The text matches the regular expression PATTERN.
 609 Optional 4th argument STRING, if non-nil, is a string containing text
 610 to compose.
 611
 612 The return value is number of composed characters."
 613   (if (< (1+ from) to)
 614       (prog1 (- to from)
 615         (if string
 616             (compose-string string from to)
 617           (compose-region from to))
 618         (- to from))))
 619
 620 ;; Register a function to compose Unicode diacrtics and marks.
 621 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
 622   (let ((c #x300))
 623     (while (<= c #x362)
 624       (aset composition-function-table (decode-char 'ucs c) patterns)
 625       (setq c (1+ c)))
 626     (setq c #x20d0)
 627     (while (<= c #x20e3)
 628       (aset composition-function-table (decode-char 'ucs c) patterns)
 629       (setq c (1+ c)))))
 630
 631 (provide 'european)
 632
 633 ;;; european.el ends here