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