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, 2002, 2003 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 t 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 French, \"French\".
  68   For Italian, \"Italian\".
  69   For Slovenian, \"Slovenian\".
  70   For Spanish, \"Spanish\".
  71
  72 Latin-1 also covers several written languages outside Europe, including
  73 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  74  '("European"))
  75
  76 \f
  77 ;; Latin-2 (ISO-8859-2)
  78
  79 (make-coding-system
  80  'iso-latin-2 2 ?2
  81  "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  82  '(ascii latin-iso8859-2 nil nil
  83    nil nil nil nil nil nil nil nil nil nil nil t)
  84  '((safe-charsets ascii latin-iso8859-2)
  85    (mime-charset . iso-8859-2)))
  86
  87 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  88 (define-coding-system-alias 'latin-2 'iso-latin-2)
  89
  90 (set-language-info-alist
  91  "Latin-2" '((charset ascii latin-iso8859-2)
  92              (coding-system iso-latin-2)
  93              (coding-priority iso-latin-2)
  94              (nonascii-translation . latin-iso8859-2)
  95              (unibyte-syntax . "latin-2")
  96              (unibyte-display . iso-latin-2)
  97              (input-method . "latin-2-prefix")
  98              (documentation . "\
  99 This language environment is a generic one for the Latin-2 (ISO-8859-2)
 100 character set which supports the following languages:
 101  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 102  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
 103  and Swedish.
 104 We also have specific language environments for the following languages:
 105   For Czech, \"Czech\".
 106   For Croatian, \"Croatian\".
 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 for Latin-3 (MIME:ISO-8859-3)."
 117  '(ascii latin-iso8859-3 nil nil
 118    nil nil nil nil nil nil nil nil nil nil nil t)
 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 for Latin-4 (MIME:ISO-8859-4)."
 145  '(ascii latin-iso8859-4 nil nil
 146    nil nil nil nil nil nil nil nil nil nil nil t)
 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-postfix")
 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 for Latin-5 (MIME:ISO-8859-9)."
 173  '(ascii latin-iso8859-9 nil nil
 174    nil nil nil nil nil nil nil nil nil nil nil t)
 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-postfix")
 189              (documentation . "Support for Turkish language."))
 190  '("European"))
 191
 192 \f
 193 ;; Latin-8 (ISO-8859-14)
 194
 195 (make-coding-system
 196  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 197                                         ; for `Celtic' is taken.
 198  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 199  '(ascii latin-iso8859-14 nil nil
 200    nil nil nil nil nil nil nil nil nil nil nil t t)
 201  '((safe-charsets ascii latin-iso8859-14)
 202    (mime-charset . iso-8859-14)))
 203
 204 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 205 (define-coding-system-alias 'latin-8 'iso-latin-8)
 206
 207 (set-language-info-alist
 208  "Latin-8" '((charset ascii latin-iso8859-14)
 209              (coding-system iso-latin-8)
 210              (coding-priority iso-latin-8)
 211              (nonascii-translation . latin-iso8859-14)
 212              (unibyte-syntax . "latin-8")
 213              (unibyte-display . iso-latin-8)
 214              (input-method . "latin-8-prefix")
 215              ;; Fixme: Welsh/Ga{e}lic greetings
 216              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 217              (documentation . "\
 218 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 219 character set which supports the Celtic languages, including those not
 220 covered by other ISO-8859 character sets:
 221  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 222  '("European"))
 223 \f
 224 ;; Latin-9 (ISO-8859-15)
 225
 226 (make-coding-system
 227  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 228  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 229  '(ascii latin-iso8859-15 nil nil
 230    nil nil nil nil nil nil nil nil nil nil nil t t)
 231  '((safe-charsets ascii latin-iso8859-15)
 232    (mime-charset . iso-8859-15)))
 233
 234 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 235 (define-coding-system-alias 'latin-9 'iso-latin-9)
 236 (define-coding-system-alias 'latin-0 'iso-latin-9)
 237
 238 (set-language-info-alist
 239  "Latin-9" '((charset ascii latin-iso8859-15)
 240              (coding-system iso-latin-9)
 241              (coding-priority iso-latin-9)
 242              (nonascii-translation . latin-iso8859-15)
 243              (unibyte-syntax . "latin-9")
 244              (unibyte-display . iso-latin-9)
 245              (input-method . "latin-9-prefix")
 246              (sample-text
 247               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 248              (documentation . "\
 249 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 250 character set which supports the same languages as Latin-1 with the
 251 addition of the Euro sign and some additional French and Finnish letters.
 252 Latin-9 is sometimes nicknamed `Latin-0'."))
 253  '("European"))
 254 \f
 255 (set-language-info-alist
 256  "Dutch" '((tutorial . "TUTORIAL.nl")
 257            (charset ascii latin-iso8859-1)
 258            (coding-system iso-latin-1 iso-latin-9)
 259            (coding-priority iso-latin-1)
 260            (nonascii-translation . latin-iso8859-1)
 261            (unibyte-syntax . "latin-1")
 262            (unibyte-display . iso-latin-1)
 263            (input-method . "dutch")
 264            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 265            (documentation . "\
 266 This language environment is almost the same as Latin-1,
 267 but it selects the Dutch tutorial and input method."))
 268  '("European"))
 269
 270 (set-language-info-alist
 271  "German" '((tutorial . "TUTORIAL.de")
 272             (charset ascii latin-iso8859-1)
 273             (coding-system iso-latin-1 iso-latin-9)
 274             (coding-priority iso-latin-1)
 275             (input-method . "german-postfix")
 276             (nonascii-translation . latin-iso8859-1)
 277             (unibyte-syntax . "latin-1")
 278             (unibyte-display . iso-latin-1)
 279             (sample-text . "\
 280 German (Deutsch Nord)   Guten Tag
 281 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 282             (documentation . "\
 283 This language environment is almost the same as Latin-1,
 284 but sets the default input method to \"german-postfix\".
 285 Additionally, it selects the German tutorial."))
 286  '("European"))
 287
 288 (set-language-info-alist
 289  "French" '((tutorial . "TUTORIAL.fr")
 290             (charset ascii latin-iso8859-1)
 291             (coding-system iso-latin-1 iso-latin-9)
 292             (coding-priority iso-latin-1)
 293             (nonascii-translation . latin-iso8859-1)
 294             (unibyte-syntax . "latin-1")
 295             (unibyte-display . iso-latin-1)
 296             (input-method . "latin-1-prefix")
 297             (sample-text . "French (Fran\e,Ag\e(Bais)     Bonjour, Salut")
 298             (documentation . "\
 299 This language environment is almost the same as Latin-1,
 300 but it selects the French tutorial and input method."))
 301  '("European"))
 302
 303 (set-language-info-alist
 304  "Italian" '((tutorial . "TUTORIAL.it")
 305             (charset ascii latin-iso8859-1)
 306             (coding-system iso-latin-1 iso-latin-9)
 307             (coding-priority iso-latin-1)
 308             (nonascii-translation . latin-iso8859-1)
 309             (unibyte-syntax . "latin-1")
 310             (unibyte-display . iso-latin-1)
 311             (input-method . "italian-postfix")
 312             (sample-text . "Salve, ciao!")
 313             (documentation . "\
 314 This language environment is almost the same as Latin-1,
 315 but sets the default input method to \"italian-postfix\".
 316 Additionally, it selects the Italian tutorial."))
 317  '("European"))
 318
 319 (set-language-info-alist
 320  "Slovenian" '((charset . (ascii latin-iso8859-2))
 321               (coding-system . (iso-8859-2))
 322               (coding-priority . (iso-8859-2))
 323               (nonascii-translation . latin-iso8859-2)
 324               (input-method . "slovenian")
 325               (unibyte-syntax . "latin-2")
 326               (unibyte-display . iso-8859-2)
 327               (tutorial . "TUTORIAL.sl")
 328               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 329               (documentation . "\
 330 This language environment is almost the same as Latin-2,
 331 but it selects the Slovenian tutorial and input method."))
 332  '("European"))
 333
 334 (set-language-info-alist
 335  "Spanish" '((tutorial . "TUTORIAL.es")
 336             (charset ascii latin-iso8859-1)
 337             (coding-system iso-latin-1 iso-latin-9)
 338             (coding-priority iso-latin-1)
 339             (input-method . "spanish-postfix")
 340             (nonascii-translation . latin-iso8859-1)
 341             (unibyte-syntax . "latin-1")
 342             (unibyte-display . iso-latin-1)
 343             (sample-text . "Spanish (Espa\e,Aq\e(Bol)     \e,A!\e(BHola!")
 344             (documentation . "\
 345 This language environment is almost the same as Latin-1,
 346 but it sets the default input method to \"spanish-postfix\",
 347 and it selects the Spanish tutorial."))
 348  '("European"))
 349
 350 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 351 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 352 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 353 ;; "Latin-3" language environment.
 354
 355 (set-language-info-alist
 356  "Turkish" '((charset ascii latin-iso8859-9)
 357              (coding-system iso-latin-5 iso-latin-3)
 358              (coding-priority iso-latin-5)
 359              (nonascii-translation . latin-iso8859-9)
 360              (unibyte-syntax . "latin-5")
 361              (unibyte-display . iso-latin-5)
 362              (input-method . "turkish-postfix")
 363              (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be)       Merhaba")
 364              (documentation . t)))
 365
 366 ;; Polish ISO 8859-2 environment.
 367 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 368 ;; Keywords: multilingual, Polish
 369
 370 (set-language-info-alist
 371  "Polish" '((charset . (ascii latin-iso8859-2))
 372            (coding-system . (iso-8859-2))
 373            (coding-priority . (iso-8859-2))
 374            (input-method . "polish-slash")
 375            (nonascii-translation . latin-iso8859-2)
 376            (unibyte-syntax . "latin-2")
 377            (unibyte-display . iso-8859-2)
 378            (tutorial . "TUTORIAL.pl")
 379            (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")
 380            (documentation . t))
 381  '("European"))
 382
 383 (set-language-info-alist
 384  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 385            (coding-priority utf-8 latin-8)
 386            (nonascii-translation . latin-iso8859-14)
 387            (input-method . "welsh")
 388            (documentation . "Support for Welsh, using Unicode."))
 389  '("European"))
 390
 391 (set-language-info-alist
 392  "Latin-6" `((coding-system latin-6)
 393              (coding-priority latin-6)
 394              (nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
 395              (input-method . latin-pre)
 396              (input-method . latin-pre)
 397              (features code-pages)
 398              (documentation . "Support for Latin-6."))
 399  '("European"))
 400
 401 (set-language-info-alist
 402  "Latin-7" `((coding-system latin-7)
 403              (coding-priority latin-7)
 404              (nonascii-translation . ,(get 'decode-iso-latin-7
 405                                            'translation-table))
 406              (input-method . latin-pre)
 407              (features code-pages)
 408              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 409  '("European"))
 410
 411 (set-language-info-alist
 412  "Lithuanian" `((coding-system latin-7)
 413                 (coding-priority latin-7)
 414                 (input-method . "lithuanian-keyboard")
 415                 (nonascii-translation . ,(get 'decode-iso-latin-7
 416                                               'translation-table))
 417                 (features code-pages)
 418                 (documentation . "Support for Lithuanian."))
 419  '("European"))
 420
 421 (set-language-info-alist
 422  "Latvian" `((coding-system latin-7)
 423              (coding-priority latin-7)
 424              (input-method . "latvian-keyboard")
 425              (nonascii-translation . ,(get 'decode-iso-latin-7
 426                                            'translation-table))
 427              (features code-pages)
 428              (documentation . "Support for Latvian."))
 429  '("European"))
 430
 431 (set-language-info-alist
 432  "Swedish" '((tutorial . "TUTORIAL.sv")
 433             (charset ascii latin-iso8859-1)
 434             (coding-system iso-latin-1)
 435             (coding-priority iso-latin-1)
 436             (nonascii-translation . latin-iso8859-1)
 437             (unibyte-syntax . "latin-1")
 438             (unibyte-display . iso-latin-1)
 439             (sample-text . "Goddag Hej")
 440             (documentation . "Support for Swedish"))
 441  '("European"))
 442
 443 (set-language-info-alist
 444  "Croatian" '((charset . (ascii latin-iso8859-2))
 445               (coding-system . (iso-8859-2))
 446               (coding-priority . (iso-8859-2))
 447               (input-method . "croatian")
 448               (nonascii-translation . latin-iso8859-2)
 449               (unibyte-syntax . "latin-2")
 450               (unibyte-display . iso-8859-2)
 451               (documentation . "Support for Croatian with Latin-2 encoding."))
 452  '("European"))
 453 \f
 454 ;; Definitions for the Mac Roman character sets and coding system.
 455 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 456 ;; 255 for actual characters.  Emacs decodes them to one of the
 457 ;; following character sets.
 458 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 459 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 460
 461 (let
 462     ((encoding-vector (make-vector 256 nil))
 463      (i 0)
 464      (vec       ;; mac-roman (128..255) -> UCS mapping
 465       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 466         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 467         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 468         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 469         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 470         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 471         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 472         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 473         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 474         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 475         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 476         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 477         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 478         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 479         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 480         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 481         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 482         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 483         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 484         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 485         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 486         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 487         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 488         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 489         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 490         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 491         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 492         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 493         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 494         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 495         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 496         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 497         #x2020  ;; 160:DAGGER
 498         #x00B0  ;; 161:DEGREE SIGN
 499         #x00A2  ;; 162:CENT SIGN
 500         #x00A3  ;; 163:POUND SIGN
 501         #x00A7  ;; 164:SECTION SIGN
 502         #x2022  ;; 165:BULLET
 503         #x00B6  ;; 166:PILCROW SIGN
 504         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 505         #x00AE  ;; 168:REGISTERED SIGN
 506         #x00A9  ;; 169:COPYRIGHT SIGN
 507         #x2122  ;; 170:TRADE MARK SIGN
 508         #x00B4  ;; 171:ACUTE ACCENT
 509         #x00A8  ;; 172:DIAERESIS
 510         #x2260  ;; 173:NOT EQUAL TO
 511         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 512         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 513         #x221E  ;; 176:INFINITY
 514         #x00B1  ;; 177:PLUS-MINUS SIGN
 515         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 516         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 517         #x00A5  ;; 180:YEN SIGN
 518         #x00B5  ;; 181:MICRO SIGN
 519         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 520         #x2211  ;; 183:N-ARY SUMMATION
 521         #x220F  ;; 184:N-ARY PRODUCT
 522         #x03C0  ;; 185:GREEK SMALL LETTER PI
 523         #x222B  ;; 186:INTEGRAL
 524         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 525         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 526         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 527         #x00E6  ;; 190:LATIN SMALL LETTER AE
 528         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 529         #x00BF  ;; 192:INVERTED QUESTION MARK
 530         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 531         #x00AC  ;; 194:NOT SIGN
 532         #x221A  ;; 195:SQUARE ROOT
 533         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 534         #x2248  ;; 197:ALMOST EQUAL TO
 535         #x2206  ;; 198:INCREMENT
 536         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 537         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 538         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 539         #x00A0  ;; 202:NO-BREAK SPACE
 540         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 541         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 542         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 543         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 544         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 545         #x2013  ;; 208:EN DASH
 546         #x2014  ;; 209:EM DASH
 547         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 548         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 549         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 550         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 551         #x00F7  ;; 214:DIVISION SIGN
 552         #x25CA  ;; 215:LOZENGE
 553         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 554         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 555         #x2044  ;; 218:FRACTION SLASH
 556         #x20AC  ;; 219:EURO SIGN
 557         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 558         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 559         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 560         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 561         #x2021  ;; 224:DOUBLE DAGGER
 562         #x00B7  ;; 225:MIDDLE DOT
 563         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 564         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 565         #x2030  ;; 228:PER MILLE SIGN
 566         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 567         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 568         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 569         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 570         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 571         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 572         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 573         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 574         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 575         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 576         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 577         #xF8FF  ;; 240:Apple logo
 578         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 579         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 580         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 581         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 582         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 583         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 584         #x02DC  ;; 247:SMALL TILDE
 585         #x00AF  ;; 248:MACRON
 586         #x02D8  ;; 249:BREVE
 587         #x02D9  ;; 250:DOT ABOVE
 588         #x02DA  ;; 251:RING ABOVE
 589         #x00B8  ;; 252:CEDILLA
 590         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 591         #x02DB  ;; 254:OGONEK
 592         #x02C7  ;; 255:CARON
 593         ])
 594      translation-table)
 595   (while (< i 128)
 596     (aset encoding-vector i i)
 597     (setq i (1+ i)))
 598   (while (< i 256)
 599     (aset encoding-vector i
 600           (decode-char 'ucs (aref vec (- i 128))))
 601     (setq i (1+ i)))
 602   (setq translation-table
 603         (make-translation-table-from-vector encoding-vector))
 604   (define-translation-table 'mac-roman-decoder translation-table)
 605   (define-translation-table 'mac-roman-encoder
 606     (char-table-extra-slot translation-table 0)))
 607
 608 (define-ccl-program decode-mac-roman
 609   `(4
 610     ((loop
 611       (read r1)
 612       (if (r1 < 128)  ;; ASCII
 613           (r0 = ,(charset-id 'ascii))
 614         (if (r1 < 160)
 615             (r0 = ,(charset-id 'eight-bit-control))
 616           (r0 = ,(charset-id 'eight-bit-graphic))))
 617       (translate-character mac-roman-decoder r0 r1)
 618       (write-multibyte-character r0 r1)
 619       (repeat))))
 620   "CCL program to decode Mac Roman")
 621
 622 (define-ccl-program encode-mac-roman
 623   `(1
 624     ((loop
 625       (read-multibyte-character r0 r1)
 626       (translate-character ucs-mule-to-mule-unicode r0 r1)
 627       (translate-character mac-roman-encoder r0 r1)
 628       (if (r0 != ,(charset-id 'ascii))
 629           (if (r0 != ,(charset-id 'eight-bit-graphic))
 630               (if (r0 != ,(charset-id 'eight-bit-control))
 631                   (r1 = ??))))
 632       (write-repeat r1))))
 633   "CCL program to encode Mac Roman")
 634
 635 (make-coding-system
 636  'mac-roman 4 ?M
 637  "Mac Roman Encoding (MIME:MACINTOSH)."
 638  '(decode-mac-roman . encode-mac-roman)
 639  (list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table))
 640        '(valid-codes (0 . 255))
 641        '(mime-charset . macintosh)))            ; per IANA, rfc1345
 642
 643 (defconst diacritic-composition-pattern "\\C^\\c^+")
 644
 645 (defun diacritic-compose-region (beg end)
 646   "Compose diacritic characters in the region.
 647 When called from a program, expects two arguments,
 648 positions (integers or markers) specifying the region."
 649   (interactive "r")
 650   (save-restriction
 651     (narrow-to-region beg end)
 652     (goto-char (point-min))
 653     (while (re-search-forward diacritic-composition-pattern nil t)
 654       (compose-region (match-beginning 0) (match-end 0)))))
 655
 656 (defun diacritic-compose-string (string)
 657   "Compose diacritic characters in STRING and return the resulting string."
 658   (let ((idx 0))
 659     (while (setq idx (string-match diacritic-composition-pattern string idx))
 660       (compose-string string idx (match-end 0))
 661       (setq idx (match-end 0))))
 662   string)
 663
 664 (defun diacritic-compose-buffer ()
 665   "Compose diacritic characters in the current buffer."
 666   (interactive)
 667   (diacritic-compose-region (point-min) (point-max)))
 668
 669 (defun diacritic-post-read-conversion (len)
 670   (diacritic-compose-region (point) (+ (point) len))
 671   len)
 672
 673 (defun diacritic-composition-function (from to pattern &optional string)
 674   "Compose diacritic text in the region FROM and TO.
 675 The text matches the regular expression PATTERN.
 676 Optional 4th argument STRING, if non-nil, is a string containing text
 677 to compose.
 678
 679 The return value is the number of composed characters."
 680   (when (< (1+ from) to)
 681       (if string
 682           (compose-string string from to)
 683         (compose-region from to))
 684       (- to from)))
 685
 686 ;; Register a function to compose Unicode diacrtics and marks.
 687 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
 688   (let ((c #x300))
 689     (while (<= c #x362)
 690       (aset composition-function-table (decode-char 'ucs c) patterns)
 691       (setq c (1+ c)))
 692     (setq c #x20d0)
 693     (while (<= c #x20e3)
 694       (aset composition-function-table (decode-char 'ucs c) patterns)
 695       (setq c (1+ c)))))
 696
 697 (provide 'european)
 698
 699 ;;; european.el ends here