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