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, all the ISO Latin character sets are
  29 ;; supported, along with various others.
  30
  31 ;;; Code:
  32
  33 ;; Latin-1 (ISO-8859-1)
  34
  35 (set-language-info-alist
  36  "Latin-1" '((charset ascii latin-iso8859-1)
  37              (coding-system iso-latin-1)
  38              (coding-priority iso-latin-1)
  39              (nonascii-translation . latin-iso8859-1)
  40              (unibyte-syntax . "latin-1")
  41              (unibyte-display . iso-latin-1)
  42              (input-method . "latin-1-prefix")
  43              (sample-text
  44               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  45              (documentation . "\
  46 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  47 character set which supports the following European languages:
  48  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  49  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  50  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  51  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  52  Scottish Gaelic, Spanish, and Swedish.
  53 We also have specific language environments for the following languages:
  54   For Dutch, \"Dutch\".
  55   For German, \"German\".
  56   For French, \"French\".
  57   For Italian, \"Italian\".
  58   For Slovenian, \"Slovenian\".
  59   For Spanish, \"Spanish\".
  60
  61 Latin-1 also covers several written languages outside Europe, including
  62 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  63  '("European"))
  64
  65 (eval-and-compile
  66   (setq
  67    non-iso-charset-alist
  68    (cp-make-coding-system
  69     windows-1252
  70     [?\\e$,1tL\e(B nil ?\\e$,1rz\e(B ?\\e$,1!R\e(B ?\\e$,1r~\e(B ?\\e$,1s&\e(B ?\\e$,1s \e(B ?\\e$,1s!\e(B ?\\e$,1$f\e(B ?\\e$,1s0\e(B ?\\e$,1! \e(B ?\\e$,1s9\e(B ?\\e$,1 r\e(B nil ?\\e$,1!=\e(B nil nil
  71          ?\\e$,1rx\e(B ?\\e$,1ry\e(B ?\\e$,1r|\e(B ?\\e$,1r}\e(B ?\\e$,1s"\e(B ?\\e$,1rs\e(B ?\\e$,1rt\e(B ?\\e$,1$|\e(B ?\\e$,1ub\e(B ?\\e$,1!!\e(B ?\\e$,1s:\e(B ?\\e$,1 s\e(B nil ?\\e$,1!>\e(B ?\\e$,1!8\e(B ?\\e,A \e(B ?\\e,A!\e(B
  72          ?\\e,A"\e(B ?\\e,A#\e(B ?\\e,A$\e(B ?\\e,A%\e(B ?\\e,A&\e(B ?\\e,A'\e(B ?\\e,A(\e(B ?\\e,A)\e(B ?\\e,A*\e(B ?\\e,A+\e(B ?\\e,A,\e(B ?\\e,A-\e(B ?\\e,A.\e(B ?\\e,A/\e(B ?\\e,A0\e(B ?\\e,A1\e(B ?\\e,A2\e(B
  73          ?\\e,A3\e(B ?\\e,A4\e(B ?\\e,A5\e(B ?\\e,A6\e(B ?\\e,A7\e(B ?\\e,A8\e(B ?\\e,A9\e(B ?\\e,A:\e(B ?\\e,A;\e(B ?\\e,A<\e(B ?\\e,A=\e(B ?\\e,A>\e(B ?\\e,A?\e(B ?\\e,A@\e(B ?\\e,AA\e(B ?\\e,AB\e(B ?\\e,AC\e(B
  74          ?\\e,AD\e(B ?\\e,AE\e(B ?\\e,AF\e(B ?\\e,AG\e(B ?\\e,AH\e(B ?\\e,AI\e(B ?\\e,AJ\e(B ?\\e,AK\e(B ?\\e,AL\e(B ?\\e,AM\e(B ?\\e,AN\e(B ?\\e,AO\e(B ?\\e,AP\e(B ?\\e,AQ\e(B ?\\e,AR\e(B ?\\e,AS\e(B ?\\e,AT\e(B
  75          ?\\e,AU\e(B ?\\e,AV\e(B ?\\e,AW\e(B ?\\e,AX\e(B ?\\e,AY\e(B ?\\e,AZ\e(B ?\\e,A[\e(B ?\\e,A\\e(B ?\\e,A]\e(B ?\\e,A^\e(B ?\\e,A_\e(B ?\\e,A`\e(B ?\\e,Aa\e(B ?\\e,Ab\e(B ?\\e,Ac\e(B ?\\e,Ad\e(B ?\\e,Ae\e(B
  76          ?\\e,Af\e(B ?\\e,Ag\e(B ?\\e,Ah\e(B ?\\e,Ai\e(B ?\\e,Aj\e(B ?\\e,Ak\e(B ?\\e,Al\e(B ?\\e,Am\e(B ?\\e,An\e(B ?\\e,Ao\e(B ?\\e,Ap\e(B ?\\e,Aq\e(B ?\\e,Ar\e(B ?\\e,As\e(B ?\\e,At\e(B ?\\e,Au\e(B ?\\e,Av\e(B
  77          ?\\e,Aw\e(B ?\\e,Ax\e(B ?\\e,Ay\e(B ?\\e,Az\e(B ?\\e,A{\e(B ?\\e,A|\e(B ?\\e,A}\e(B ?\\e,A~\e(B ?\\e,A\x7f\e(B])))
  78 \f
  79 ;; Latin-2 (ISO-8859-2)
  80
  81 (make-coding-system
  82  'iso-latin-2 2 ?2
  83  "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  84  '(ascii latin-iso8859-2 nil nil
  85    nil nil nil nil nil nil nil nil nil nil nil t)
  86  '((safe-charsets ascii latin-iso8859-2)
  87    (mime-charset . iso-8859-2)))
  88
  89 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  90 (define-coding-system-alias 'latin-2 'iso-latin-2)
  91
  92 (set-language-info-alist
  93  "Latin-2" '((charset ascii latin-iso8859-2)
  94              (coding-system iso-latin-2)
  95              (coding-priority iso-latin-2)
  96              (nonascii-translation . latin-iso8859-2)
  97              (unibyte-syntax . "latin-2")
  98              (unibyte-display . iso-latin-2)
  99              (input-method . "latin-2-prefix")
 100              (documentation . "\
 101 This language environment is a generic one for the Latin-2 (ISO-8859-2)
 102 character set which supports the following languages:
 103  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
 104  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
 105  and Swedish.
 106 We also have specific language environments for the following languages:
 107   For Czech, \"Czech\".
 108   For Croatian, \"Croatian\".
 109   For Romanian, \"Romanian\".
 110   For Slovak, \"Slovak\"."))
 111  '("European"))
 112
 113 \f
 114 ;; Latin-3 (ISO-8859-3)
 115
 116 (make-coding-system
 117  'iso-latin-3 2 ?3
 118  "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
 119  '(ascii latin-iso8859-3 nil nil
 120    nil nil nil nil nil nil nil nil nil nil nil t)
 121  '((safe-charsets ascii latin-iso8859-3)
 122    (mime-charset . iso-8859-3)))
 123
 124 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 125 (define-coding-system-alias 'latin-3 'iso-latin-3)
 126
 127 (set-language-info-alist
 128  "Latin-3" '((charset ascii latin-iso8859-3)
 129              (coding-system iso-latin-3)
 130              (coding-priority iso-latin-3)
 131              (nonascii-translation . latin-iso8859-3)
 132              (unibyte-syntax . "latin-3")
 133              (unibyte-display . iso-latin-3)
 134              (input-method . "latin-3-prefix")
 135              (documentation . "\
 136 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 137  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 138  German, Italian, Maltese, Spanish, and Turkish."))
 139  '("European"))
 140
 141 \f
 142 ;; Latin-4 (ISO-8859-4)
 143
 144 (make-coding-system
 145  'iso-latin-4 2 ?4
 146  "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
 147  '(ascii latin-iso8859-4 nil nil
 148    nil nil nil nil nil nil nil nil nil nil nil t)
 149  '((safe-charsets ascii latin-iso8859-4)
 150    (mime-charset . iso-8859-4)))
 151
 152 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 153 (define-coding-system-alias 'latin-4 'iso-latin-4)
 154
 155 (set-language-info-alist
 156  "Latin-4" '((charset ascii latin-iso8859-4)
 157              (coding-system iso-8859-4)
 158              (coding-priority iso-8859-4)
 159              (nonascii-translation . latin-iso8859-4)
 160              (unibyte-syntax . "latin-4")
 161              (unibyte-display . iso-8859-4)
 162              (input-method . "latin-4-postfix")
 163              (documentation . "\
 164 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 165  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 166  Latvian, Lithuanian, and Norwegian."))
 167  '("European"))
 168
 169 \f
 170 ;; Latin-5 (ISO-8859-9)
 171
 172 (make-coding-system
 173  'iso-latin-5 2 ?9
 174  "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
 175  '(ascii latin-iso8859-9 nil nil
 176    nil nil nil nil nil nil nil nil nil nil nil t)
 177  '((safe-charsets ascii latin-iso8859-9)
 178    (mime-charset . iso-8859-9)))
 179
 180 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 181 (define-coding-system-alias 'latin-5 'iso-latin-5)
 182
 183 (set-language-info-alist
 184  "Latin-5" '((charset ascii latin-iso8859-9)
 185              (coding-system iso-latin-5)
 186              (coding-priority iso-latin-5)
 187              (nonascii-translation . latin-iso8859-9)
 188              (unibyte-syntax . "latin-5")
 189              (unibyte-display . iso-latin-5)
 190              (input-method . "latin-5-postfix")
 191              (documentation . "Support for Turkish language."))
 192  '("European"))
 193
 194 \f
 195 ;; Latin-8 (ISO-8859-14)
 196
 197 (make-coding-system
 198  'iso-latin-8 2 ?W                      ; `W' for `Welsh', since `C'
 199                                         ; for `Celtic' is taken.
 200  "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 201  '(ascii latin-iso8859-14 nil nil
 202    nil nil nil nil nil nil nil nil nil nil nil t t)
 203  '((safe-charsets ascii latin-iso8859-14)
 204    (mime-charset . iso-8859-14)))
 205
 206 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 207 (define-coding-system-alias 'latin-8 'iso-latin-8)
 208
 209 (set-language-info-alist
 210  "Latin-8" '((charset ascii latin-iso8859-14)
 211              (coding-system iso-latin-8)
 212              (coding-priority iso-latin-8)
 213              (nonascii-translation . latin-iso8859-14)
 214              (unibyte-syntax . "latin-8")
 215              (unibyte-display . iso-latin-8)
 216              (input-method . "latin-8-prefix")
 217              ;; Fixme: Welsh/Ga{e}lic greetings
 218              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 219              (documentation . "\
 220 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 221 character set which supports the Celtic languages, including those not
 222 covered by other ISO-8859 character sets:
 223  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 224  '("European"))
 225 \f
 226 ;; Latin-9 (ISO-8859-15)
 227
 228 (make-coding-system
 229  'iso-latin-9 2 ?0                      ; `0' for `Latin-0'
 230  "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 231  '(ascii latin-iso8859-15 nil nil
 232    nil nil nil nil nil nil nil nil nil nil nil t t)
 233  '((safe-charsets ascii latin-iso8859-15)
 234    (mime-charset . iso-8859-15)))
 235
 236 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 237 (define-coding-system-alias 'latin-9 'iso-latin-9)
 238 (define-coding-system-alias 'latin-0 'iso-latin-9)
 239
 240 (set-language-info-alist
 241  "Latin-9" '((charset ascii latin-iso8859-15)
 242              (coding-system iso-latin-9)
 243              (coding-priority iso-latin-9)
 244              (nonascii-translation . latin-iso8859-15)
 245              (unibyte-syntax . "latin-9")
 246              (unibyte-display . iso-latin-9)
 247              (input-method . "latin-9-prefix")
 248              (sample-text
 249               . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
 250              (documentation . "\
 251 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 252 character set which supports the same languages as Latin-1 with the
 253 addition of the Euro sign and some additional French and Finnish letters.
 254 Latin-9 is sometimes nicknamed `Latin-0'."))
 255  '("European"))
 256 \f
 257 (set-language-info-alist
 258  "Dutch" '((tutorial . "TUTORIAL.nl")
 259            (charset ascii latin-iso8859-1)
 260            (coding-system iso-latin-1 iso-latin-9)
 261            (coding-priority iso-latin-1)
 262            (nonascii-translation . latin-iso8859-1)
 263            (unibyte-syntax . "latin-1")
 264            (unibyte-display . iso-latin-1)
 265            (input-method . "dutch")
 266            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 267            (documentation . "\
 268 This language environment is almost the same as Latin-1,
 269 but it selects the Dutch tutorial and input method."))
 270  '("European"))
 271
 272 (set-language-info-alist
 273  "German" '((tutorial . "TUTORIAL.de")
 274             (charset ascii latin-iso8859-1)
 275             (coding-system iso-latin-1 iso-latin-9)
 276             (coding-priority iso-latin-1)
 277             (input-method . "german-postfix")
 278             (nonascii-translation . latin-iso8859-1)
 279             (unibyte-syntax . "latin-1")
 280             (unibyte-display . iso-latin-1)
 281             (sample-text . "\
 282 German (Deutsch Nord)   Guten Tag
 283 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 284             (documentation . "\
 285 This language environment is almost the same as Latin-1,
 286 but sets the default input method to \"german-postfix\".
 287 Additionally, it selects the German tutorial."))
 288  '("European"))
 289
 290 (set-language-info-alist
 291  "French" '((tutorial . "TUTORIAL.fr")
 292             (charset ascii latin-iso8859-1)
 293             (coding-system iso-latin-1 iso-latin-9)
 294             (coding-priority iso-latin-1)
 295             (nonascii-translation . latin-iso8859-1)
 296             (unibyte-syntax . "latin-1")
 297             (unibyte-display . iso-latin-1)
 298             (input-method . "latin-1-prefix")
 299             (sample-text . "French (Fran\e,Ag\e(Bais)     Bonjour, Salut")
 300             (documentation . "\
 301 This language environment is almost the same as Latin-1,
 302 but it selects the French tutorial and input method."))
 303  '("European"))
 304
 305 (set-language-info-alist
 306  "Italian" '((tutorial . "TUTORIAL.it")
 307             (charset ascii latin-iso8859-1)
 308             (coding-system iso-latin-1 iso-latin-9)
 309             (coding-priority iso-latin-1)
 310             (nonascii-translation . latin-iso8859-1)
 311             (unibyte-syntax . "latin-1")
 312             (unibyte-display . iso-latin-1)
 313             (input-method . "italian-postfix")
 314             (sample-text . "Salve, ciao!")
 315             (documentation . "\
 316 This language environment is almost the same as Latin-1,
 317 but sets the default input method to \"italian-postfix\".
 318 Additionally, it selects the Italian tutorial."))
 319  '("European"))
 320
 321 (set-language-info-alist
 322  "Slovenian" '((charset . (ascii latin-iso8859-2))
 323               (coding-system . (iso-8859-2))
 324               (coding-priority . (iso-8859-2))
 325               (nonascii-translation . latin-iso8859-2)
 326               (input-method . "slovenian")
 327               (unibyte-syntax . "latin-2")
 328               (unibyte-display . iso-8859-2)
 329               (tutorial . "TUTORIAL.sl")
 330               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 331               (documentation . "\
 332 This language environment is almost the same as Latin-2,
 333 but it selects the Slovenian tutorial and input method."))
 334  '("European"))
 335
 336 (set-language-info-alist
 337  "Spanish" '((tutorial . "TUTORIAL.es")
 338             (charset ascii latin-iso8859-1)
 339             (coding-system iso-latin-1 iso-latin-9)
 340             (coding-priority iso-latin-1)
 341             (input-method . "spanish-postfix")
 342             (nonascii-translation . latin-iso8859-1)
 343             (unibyte-syntax . "latin-1")
 344             (unibyte-display . iso-latin-1)
 345             (sample-text . "Spanish (Espa\e,Aq\e(Bol)     \e,A!\e(BHola!")
 346             (documentation . "\
 347 This language environment is almost the same as Latin-1,
 348 but it sets the default input method to \"spanish-postfix\",
 349 and it selects the Spanish tutorial."))
 350  '("European"))
 351
 352 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 353 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 354 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 355 ;; "Latin-3" language environment.
 356
 357 (set-language-info-alist
 358  "Turkish" '((charset ascii latin-iso8859-9)
 359              (coding-system iso-latin-5 iso-latin-3)
 360              (coding-priority iso-latin-5)
 361              (nonascii-translation . latin-iso8859-9)
 362              (unibyte-syntax . "latin-5")
 363              (unibyte-display . iso-latin-5)
 364              (input-method . "turkish-postfix")
 365              (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be)       Merhaba")
 366              (documentation . t)))
 367
 368 ;; Polish ISO 8859-2 environment.
 369 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 370 ;; Keywords: multilingual, Polish
 371
 372 (set-language-info-alist
 373  "Polish" '((charset . (ascii latin-iso8859-2))
 374            (coding-system . (iso-8859-2))
 375            (coding-priority . (iso-8859-2))
 376            (input-method . "polish-slash")
 377            (nonascii-translation . latin-iso8859-2)
 378            (unibyte-syntax . "latin-2")
 379            (unibyte-display . iso-8859-2)
 380            (tutorial . "TUTORIAL.pl")
 381            (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")
 382            (documentation . t))
 383  '("European"))
 384
 385 (set-language-info-alist
 386  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 387            (coding-priority utf-8 latin-8)
 388            (nonascii-translation . latin-iso8859-14)
 389            (input-method . "welsh")
 390            (documentation . "Support for Welsh, using Unicode."))
 391  '("European"))
 392
 393 (set-language-info-alist
 394  "Latin-6" `((coding-system latin-6)
 395              (coding-priority latin-6)
 396              (nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
 397              (input-method . "latin-prefix")
 398              (features code-pages)
 399              (documentation . "Support for Latin-6."))
 400  '("European"))
 401
 402 (set-language-info-alist
 403  "Latin-7" `((coding-system latin-7)
 404              (coding-priority latin-7)
 405              (nonascii-translation . ,(get 'decode-iso-latin-7
 406                                            'translation-table))
 407              (input-method . "latin-prefix")
 408              (features code-pages)
 409              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 410  '("European"))
 411
 412 (set-language-info-alist
 413  "Lithuanian" `((coding-system latin-7)
 414                 (coding-priority latin-7)
 415                 (input-method . "lithuanian-keyboard")
 416                 (nonascii-translation . ,(get 'decode-iso-latin-7
 417                                               'translation-table))
 418                 (features code-pages)
 419                 (documentation . "Support for Lithuanian."))
 420  '("European"))
 421
 422 (set-language-info-alist
 423  "Latvian" `((coding-system latin-7)
 424              (coding-priority latin-7)
 425              (input-method . "latvian-keyboard")
 426              (nonascii-translation . ,(get 'decode-iso-latin-7
 427                                            'translation-table))
 428              (features code-pages)
 429              (documentation . "Support for Latvian."))
 430  '("European"))
 431
 432 (set-language-info-alist
 433  "Swedish" '((tutorial . "TUTORIAL.sv")
 434             (charset ascii latin-iso8859-1)
 435             (coding-system iso-latin-1)
 436             (coding-priority iso-latin-1)
 437             (nonascii-translation . latin-iso8859-1)
 438             (unibyte-syntax . "latin-1")
 439             (unibyte-display . iso-latin-1)
 440             (sample-text . "Goddag Hej")
 441             (documentation . "Support for Swedish"))
 442  '("European"))
 443
 444 (set-language-info-alist
 445  "Croatian" '((charset . (ascii latin-iso8859-2))
 446               (coding-system . (iso-8859-2))
 447               (coding-priority . (iso-8859-2))
 448               (input-method . "croatian")
 449               (nonascii-translation . latin-iso8859-2)
 450               (unibyte-syntax . "latin-2")
 451               (unibyte-display . iso-8859-2)
 452               (documentation . "Support for Croatian with Latin-2 encoding."))
 453  '("European"))
 454 \f
 455 ;; Definitions for the Mac Roman character sets and coding system.
 456 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
 457 ;; 255 for actual characters.  Emacs decodes them to one of the
 458 ;; following character sets.
 459 ;;      ascii, latin-iso8859-1, mule-unicode-0100-24ff,
 460 ;;      mule-unicode-2500-33ff, mule-unicode-e000-ffff
 461
 462 (let
 463     ((encoding-vector (make-vector 256 nil))
 464      (i 0)
 465      (vec       ;; mac-roman (128..255) -> UCS mapping
 466       [ #x00C4  ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
 467         #x00C5  ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
 468         #x00C7  ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
 469         #x00C9  ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
 470         #x00D1  ;; 132:LATIN CAPITAL LETTER N WITH TILDE
 471         #x00D6  ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
 472         #x00DC  ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
 473         #x00E1  ;; 135:LATIN SMALL LETTER A WITH ACUTE
 474         #x00E0  ;; 136:LATIN SMALL LETTER A WITH GRAVE
 475         #x00E2  ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
 476         #x00E4  ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
 477         #x00E3  ;; 139:LATIN SMALL LETTER A WITH TILDE
 478         #x00E5  ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
 479         #x00E7  ;; 141:LATIN SMALL LETTER C WITH CEDILLA
 480         #x00E9  ;; 142:LATIN SMALL LETTER E WITH ACUTE
 481         #x00E8  ;; 143:LATIN SMALL LETTER E WITH GRAVE
 482         #x00EA  ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
 483         #x00EB  ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
 484         #x00ED  ;; 146:LATIN SMALL LETTER I WITH ACUTE
 485         #x00EC  ;; 147:LATIN SMALL LETTER I WITH GRAVE
 486         #x00EE  ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
 487         #x00EF  ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
 488         #x00F1  ;; 150:LATIN SMALL LETTER N WITH TILDE
 489         #x00F3  ;; 151:LATIN SMALL LETTER O WITH ACUTE
 490         #x00F2  ;; 152:LATIN SMALL LETTER O WITH GRAVE
 491         #x00F4  ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
 492         #x00F6  ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
 493         #x00F5  ;; 155:LATIN SMALL LETTER O WITH TILDE
 494         #x00FA  ;; 156:LATIN SMALL LETTER U WITH ACUTE
 495         #x00F9  ;; 157:LATIN SMALL LETTER U WITH GRAVE
 496         #x00FB  ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
 497         #x00FC  ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
 498         #x2020  ;; 160:DAGGER
 499         #x00B0  ;; 161:DEGREE SIGN
 500         #x00A2  ;; 162:CENT SIGN
 501         #x00A3  ;; 163:POUND SIGN
 502         #x00A7  ;; 164:SECTION SIGN
 503         #x2022  ;; 165:BULLET
 504         #x00B6  ;; 166:PILCROW SIGN
 505         #x00DF  ;; 167:LATIN SMALL LETTER SHARP S
 506         #x00AE  ;; 168:REGISTERED SIGN
 507         #x00A9  ;; 169:COPYRIGHT SIGN
 508         #x2122  ;; 170:TRADE MARK SIGN
 509         #x00B4  ;; 171:ACUTE ACCENT
 510         #x00A8  ;; 172:DIAERESIS
 511         #x2260  ;; 173:NOT EQUAL TO
 512         #x00C6  ;; 174:LATIN CAPITAL LETTER AE
 513         #x00D8  ;; 175:LATIN CAPITAL LETTER O WITH STROKE
 514         #x221E  ;; 176:INFINITY
 515         #x00B1  ;; 177:PLUS-MINUS SIGN
 516         #x2264  ;; 178:LESS-THAN OR EQUAL TO
 517         #x2265  ;; 179:GREATER-THAN OR EQUAL TO
 518         #x00A5  ;; 180:YEN SIGN
 519         #x00B5  ;; 181:MICRO SIGN
 520         #x2202  ;; 182:PARTIAL DIFFERENTIAL
 521         #x2211  ;; 183:N-ARY SUMMATION
 522         #x220F  ;; 184:N-ARY PRODUCT
 523         #x03C0  ;; 185:GREEK SMALL LETTER PI
 524         #x222B  ;; 186:INTEGRAL
 525         #x00AA  ;; 187:FEMININE ORDINAL INDICATOR
 526         #x00BA  ;; 188:MASCULINE ORDINAL INDICATOR
 527         #x03A9  ;; 189:GREEK CAPITAL LETTER OMEGA
 528         #x00E6  ;; 190:LATIN SMALL LETTER AE
 529         #x00F8  ;; 191:LATIN SMALL LETTER O WITH STROKE
 530         #x00BF  ;; 192:INVERTED QUESTION MARK
 531         #x00A1  ;; 193:INVERTED EXCLAMATION MARK
 532         #x00AC  ;; 194:NOT SIGN
 533         #x221A  ;; 195:SQUARE ROOT
 534         #x0192  ;; 196:LATIN SMALL LETTER F WITH HOOK
 535         #x2248  ;; 197:ALMOST EQUAL TO
 536         #x2206  ;; 198:INCREMENT
 537         #x00AB  ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
 538         #x00BB  ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 539         #x2026  ;; 201:HORIZONTAL ELLIPSIS
 540         #x00A0  ;; 202:NO-BREAK SPACE
 541         #x00C0  ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
 542         #x00C3  ;; 204:LATIN CAPITAL LETTER A WITH TILDE
 543         #x00D5  ;; 205:LATIN CAPITAL LETTER O WITH TILDE
 544         #x0152  ;; 206:LATIN CAPITAL LIGATURE OE
 545         #x0153  ;; 207:LATIN SMALL LIGATURE OE
 546         #x2013  ;; 208:EN DASH
 547         #x2014  ;; 209:EM DASH
 548         #x201C  ;; 210:LEFT DOUBLE QUOTATION MARK
 549         #x201D  ;; 211:RIGHT DOUBLE QUOTATION MARK
 550         #x2018  ;; 212:LEFT SINGLE QUOTATION MARK
 551         #x2019  ;; 213:RIGHT SINGLE QUOTATION MARK
 552         #x00F7  ;; 214:DIVISION SIGN
 553         #x25CA  ;; 215:LOZENGE
 554         #x00FF  ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
 555         #x0178  ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
 556         #x2044  ;; 218:FRACTION SLASH
 557         #x20AC  ;; 219:EURO SIGN
 558         #x2039  ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 559         #x203A  ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 560         #xFB01  ;; 222:LATIN SMALL LIGATURE FI
 561         #xFB02  ;; 223:LATIN SMALL LIGATURE FL
 562         #x2021  ;; 224:DOUBLE DAGGER
 563         #x00B7  ;; 225:MIDDLE DOT
 564         #x201A  ;; 226:SINGLE LOW-9 QUOTATION MARK
 565         #x201E  ;; 227:DOUBLE LOW-9 QUOTATION MARK
 566         #x2030  ;; 228:PER MILLE SIGN
 567         #x00C2  ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
 568         #x00CA  ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
 569         #x00C1  ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
 570         #x00CB  ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
 571         #x00C8  ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
 572         #x00CD  ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
 573         #x00CE  ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 574         #x00CF  ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
 575         #x00CC  ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
 576         #x00D3  ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
 577         #x00D4  ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
 578         #xF8FF  ;; 240:Apple logo
 579         #x00D2  ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
 580         #x00DA  ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
 581         #x00DB  ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
 582         #x00D9  ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
 583         #x0131  ;; 245:LATIN SMALL LETTER DOTLESS I
 584         #x02C6  ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
 585         #x02DC  ;; 247:SMALL TILDE
 586         #x00AF  ;; 248:MACRON
 587         #x02D8  ;; 249:BREVE
 588         #x02D9  ;; 250:DOT ABOVE
 589         #x02DA  ;; 251:RING ABOVE
 590         #x00B8  ;; 252:CEDILLA
 591         #x02DD  ;; 253:DOUBLE ACUTE ACCENT
 592         #x02DB  ;; 254:OGONEK
 593         #x02C7  ;; 255:CARON
 594         ])
 595      translation-table)
 596   (while (< i 128)
 597     (aset encoding-vector i i)
 598     (setq i (1+ i)))
 599   (while (< i 256)
 600     (aset encoding-vector i
 601           (decode-char 'ucs (aref vec (- i 128))))
 602     (setq i (1+ i)))
 603   (setq translation-table
 604         (make-translation-table-from-vector encoding-vector))
 605   (define-translation-table 'mac-roman-decoder translation-table)
 606   (define-translation-table 'mac-roman-encoder
 607     (char-table-extra-slot translation-table 0)))
 608
 609 (define-ccl-program decode-mac-roman
 610   `(4
 611     ((loop
 612       (read r1)
 613       (if (r1 < 128)  ;; ASCII
 614           (r0 = ,(charset-id 'ascii))
 615         (if (r1 < 160)
 616             (r0 = ,(charset-id 'eight-bit-control))
 617           (r0 = ,(charset-id 'eight-bit-graphic))))
 618       (translate-character mac-roman-decoder r0 r1)
 619       (write-multibyte-character r0 r1)
 620       (repeat))))
 621   "CCL program to decode Mac Roman")
 622
 623 (define-ccl-program encode-mac-roman
 624   `(1
 625     ((loop
 626       (read-multibyte-character r0 r1)
 627       (translate-character ucs-mule-to-mule-unicode r0 r1)
 628       (translate-character mac-roman-encoder r0 r1)
 629       (if (r0 != ,(charset-id 'ascii))
 630           (if (r0 != ,(charset-id 'eight-bit-graphic))
 631               (if (r0 != ,(charset-id 'eight-bit-control))
 632                   (r1 = ??))))
 633       (write-repeat r1))))
 634   "CCL program to encode Mac Roman")
 635
 636 (make-coding-system
 637  'mac-roman 4 ?M
 638  "Mac Roman Encoding (MIME:MACINTOSH)."
 639  '(decode-mac-roman . encode-mac-roman)
 640  (list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table))
 641        '(valid-codes (0 . 255))
 642        '(mime-charset . macintosh)))            ; per IANA, rfc1345
 643
 644 (defconst diacritic-composition-pattern "\\C^\\c^+")
 645
 646 (defun diacritic-compose-region (beg end)
 647   "Compose diacritic characters in the region.
 648 When called from a program, expects two arguments,
 649 positions (integers or markers) specifying the region."
 650   (interactive "r")
 651   (save-restriction
 652     (narrow-to-region beg end)
 653     (goto-char (point-min))
 654     (while (re-search-forward diacritic-composition-pattern nil t)
 655       (compose-region (match-beginning 0) (match-end 0)))))
 656
 657 (defun diacritic-compose-string (string)
 658   "Compose diacritic characters in STRING and return the resulting string."
 659   (let ((idx 0))
 660     (while (setq idx (string-match diacritic-composition-pattern string idx))
 661       (compose-string string idx (match-end 0))
 662       (setq idx (match-end 0))))
 663   string)
 664
 665 (defun diacritic-compose-buffer ()
 666   "Compose diacritic characters in the current buffer."
 667   (interactive)
 668   (diacritic-compose-region (point-min) (point-max)))
 669
 670 (defun diacritic-post-read-conversion (len)
 671   (diacritic-compose-region (point) (+ (point) len))
 672   len)
 673
 674 (defun diacritic-composition-function (from to pattern &optional string)
 675   "Compose diacritic text in the region FROM and TO.
 676 The text matches the regular expression PATTERN.
 677 Optional 4th argument STRING, if non-nil, is a string containing text
 678 to compose.
 679
 680 The return value is the number of composed characters."
 681   (when (< (1+ from) to)
 682       (if string
 683           (compose-string string from to)
 684         (compose-region from to))
 685       (- to from)))
 686
 687 ;; Register a function to compose Unicode diacrtics and marks.
 688 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
 689   (let ((c #x300))
 690     (while (<= c #x362)
 691       (aset composition-function-table (decode-char 'ucs c) patterns)
 692       (setq c (1+ c)))
 693     (setq c #x20d0)
 694     (while (<= c #x20e3)
 695       (aset composition-function-table (decode-char 'ucs c) patterns)
 696       (setq c (1+ c)))))
 697
 698 (provide 'european)
 699
 700 ;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
 701 ;;; european.el ends here