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 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 ISO8859-1,2,3,4,9,10,13,14,15,
  29 ;; windows-1250,2,4,7, mac-roman, adobe-standard-encoding, cp850 and
  30 ;; next are supported.
  31
  32 ;;; Code:
  33
  34 ;; Latin-1 (ISO-8859-1)
  35
  36 (set-language-info-alist
  37  "Latin-1" '((charset iso-8859-1)
  38              (coding-system iso-latin-1)
  39              (coding-priority iso-latin-1)
  40              (nonascii-translation . iso-8859-1)
  41              (unibyte-syntax . "latin-1")
  42              (unibyte-display . iso-latin-1)
  43              (input-method . "latin-1-prefix")
  44              (sample-text
  45               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  46              (documentation . "\
  47 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  48 character set which supports the following European languages:
  49  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  50  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  51  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  52  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  53  Scottish Gaelic, Spanish, and Swedish.
  54 We also have specific language environments for the following languages:
  55   For Dutch, \"Dutch\".
  56   For German, \"German\".
  57   For Spanish, \"Spanish\".
  58   For French, \"French\".
  59
  60 Latin-1 also covers several written languages outside Europe, including
  61 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  62  '("European"))
  63
  64 \f
  65 ;; Latin-2 (ISO-8859-2)
  66
  67 (define-coding-system 'iso-latin-2
  68    "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  69   :coding-type 'charset
  70   :mnemonic ?2
  71   :charset-list '(iso-8859-2)
  72   :mime-charset 'iso-8859-2)
  73
  74 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  75 (define-coding-system-alias 'latin-2 'iso-latin-2)
  76
  77 (set-language-info-alist
  78  "Latin-2" '((charset iso-8859-2)
  79              (coding-system iso-latin-2)
  80              (coding-priority iso-latin-2)
  81              (nonascii-translation . iso-8859-2)
  82              (unibyte-syntax . "latin-2")
  83              (unibyte-display . iso-latin-2)
  84              (input-method . "latin-2-prefix")
  85              (documentation . "\
  86 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  87 character set which supports the following languages:
  88  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
  89  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
  90  and Swedish.
  91 We also have specific language environments for the following languages:
  92   For Czech, \"Czech\".
  93   For Romanian, \"Romanian\".
  94   For Slovak, \"Slovak\"."))
  95  '("European"))
  96
  97 \f
  98 ;; Latin-3 (ISO-8859-3)
  99
 100 (define-coding-system 'iso-latin-3
 101   "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
 102   :coding-type 'charset
 103   :mnemonic ?3
 104   :charset-list '(iso-8859-3)
 105   :mime-charset 'iso-8859-3)
 106
 107 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 108 (define-coding-system-alias 'latin-3 'iso-latin-3)
 109
 110 (set-language-info-alist
 111  "Latin-3" '((charset iso-8859-3)
 112              (coding-system iso-latin-3)
 113              (coding-priority iso-latin-3)
 114              (nonascii-translation . iso-8859-3)
 115              (unibyte-syntax . "latin-3")
 116              (unibyte-display . iso-latin-3)
 117              (input-method . "latin-3-prefix")
 118              (documentation . "\
 119 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 120  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 121  German, Italian, Maltese, Spanish, and Turkish."))
 122  '("European"))
 123
 124 \f
 125 ;; Latin-4 (ISO-8859-4)
 126
 127 (define-coding-system 'iso-latin-4
 128   "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
 129   :coding-type 'charset
 130   :mnemonic ?4
 131   :charset-list '(iso-8859-4)
 132   :mime-charset 'iso-8859-4)
 133
 134 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 135 (define-coding-system-alias 'latin-4 'iso-latin-4)
 136
 137 (set-language-info-alist
 138  "Latin-4" '((charset iso-8859-4)
 139              (coding-system iso-8859-4)
 140              (coding-priority iso-8859-4)
 141              (nonascii-translation . iso-8859-4)
 142              (unibyte-syntax . "latin-4")
 143              (unibyte-display . iso-8859-4)
 144              (input-method . "latin-4-postfix")
 145              (documentation . "\
 146 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 147  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 148  Latvian, Lithuanian, and Norwegian."))
 149  '("European"))
 150
 151 \f
 152 ;; Latin-5 (ISO-8859-9)
 153
 154 (define-coding-system 'iso-latin-5
 155   "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
 156   :coding-type 'charset
 157   :mnemonic ?9
 158   :charset-list '(iso-8859-9)
 159   :mime-charset 'iso-8859-9)
 160
 161 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 162 (define-coding-system-alias 'latin-5 'iso-latin-5)
 163
 164 (set-language-info-alist
 165  "Latin-5" '((charset iso-8859-9)
 166              (coding-system iso-latin-5)
 167              (coding-priority iso-latin-5)
 168              (nonascii-translation . iso-8859-9)
 169              (unibyte-syntax . "latin-5")
 170              (unibyte-display . iso-latin-5)
 171              (input-method . "latin-5-postfix")
 172              (documentation . "Support for Turkish language."))
 173  '("European"))
 174
 175 \f
 176 ;; Latin-6 (ISO-8859-10)
 177
 178 (define-coding-system 'iso-latin-6
 179   "ISO 2022 based 8-bit encoding for Latin-6 (MIME:ISO-8859-10)."
 180   :coding-type 'charset
 181   :mnemonic ?9
 182   :charset-list '(iso-8859-10)
 183   :mime-charset 'iso-8859-10)
 184
 185 (define-coding-system-alias 'iso-8859-10 'iso-latin-6)
 186 (define-coding-system-alias 'latin-6 'iso-latin-6)
 187
 188 (set-language-info-alist
 189  "Latin-6" '((charset iso-8859-10)
 190              (coding-system iso-latin-6)
 191              (coding-priority iso-latin-6)
 192              (nonascii-translation . iso-8859-10)
 193              (unibyte-syntax . "latin-6")
 194              (unibyte-display . iso-latin-6)
 195              ;; Fixme: input method.
 196              (documentation . "Support for generic Latin-6 (Northern European)."))
 197  '("European"))
 198
 199 \f
 200 ;; Latin-7 (ISO-8859-13)
 201
 202 (define-coding-system 'iso-latin-7
 203   "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
 204   :coding-type 'charset
 205   :mnemonic ?9
 206   :charset-list '(iso-8859-13)
 207   :mime-charset 'iso-8859-13)
 208
 209 (define-coding-system-alias 'iso-8859-13 'iso-latin-7)
 210 (define-coding-system-alias 'latin-7 'iso-latin-7)
 211
 212 (set-language-info-alist
 213  "Latin-7" '((charset iso-8859-13)
 214              (coding-system iso-latin-7)
 215              (coding-priority iso-latin-7)
 216              (nonascii-translation . iso-8859-13)
 217              (unibyte-syntax . "latin-7")
 218              (unibyte-display . iso-latin-7)
 219              ;; Fixme: input method.
 220              (documentation . "Support for generic Latin-7 (Baltic Rim)."))
 221  '("European"))
 222 \f
 223 ;; Latin-8 (ISO-8859-14)
 224
 225 (define-coding-system 'iso-latin-8
 226   "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 227   :coding-type 'charset
 228   ;; `W' for `Welsh', since `C' for `Celtic' is taken.
 229   :mnemonic ?W
 230   :charset-list '(iso-8859-14)
 231   :mime-charset 'iso-8859-14)
 232
 233 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 234 (define-coding-system-alias 'latin-8 'iso-latin-8)
 235
 236 (set-language-info-alist
 237  "Latin-8" '((charset iso-8859-14)
 238              (coding-system iso-latin-8)
 239              (coding-priority iso-latin-8)
 240              (nonascii-translation . iso-8859-14)
 241              (unibyte-syntax . "latin-8")
 242              (unibyte-display . iso-latin-8)
 243              (input-method . "latin-8-prefix")
 244              ;; Fixme: Welsh/Ga{e}lic greetings
 245              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 246              (documentation . "\
 247 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 248 character set which supports the Celtic languages, including those not
 249 covered by other ISO-8859 character sets:
 250  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 251  '("European"))
 252 \f
 253 ;; Latin-9 (ISO-8859-15)
 254
 255 (define-coding-system 'iso-latin-9
 256   "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 257   :coding-type 'charset
 258   ;; `0' for `Latin-0'
 259   :mnemonic ?0
 260   :charset-list '(iso-8859-15)
 261   :mime-charset 'iso-8859-15)
 262
 263 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 264 (define-coding-system-alias 'latin-9 'iso-latin-9)
 265 (define-coding-system-alias 'latin-0 'iso-latin-9)
 266
 267 (set-language-info-alist
 268  "Latin-9" '((charset iso-8859-15)
 269              (coding-system iso-latin-9)
 270              (coding-priority iso-latin-9)
 271              (nonascii-translation . iso-8859-15)
 272              (unibyte-syntax . "latin-9")
 273              (unibyte-display . iso-latin-9)
 274              (input-method . "latin-9-prefix")
 275              (sample-text
 276               . "AVE. \e,B)9.>\e,b<=\e,_/\e(B \e,b$\e(B")
 277              (documentation . "\
 278 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 279 character set which supports the same languages as Latin-1 with the
 280 addition of the Euro sign and some additional French and Finnish letters.
 281 Latin-9 is sometimes nicknamed `Latin-0'."))
 282  '("European"))
 283 \f
 284 (define-coding-system 'iso-latin-7
 285   "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
 286   :coding-type 'charset
 287   ;; `0' for `Latin-0'
 288   :mnemonic ?*
 289   :charset-list '(iso-8859-13)
 290   :mime-charset 'iso-8859-13)
 291
 292 (define-coding-system-alias 'iso-8859-13 'iso-latin-7)
 293 (define-coding-system-alias 'latin-7 'iso-latin-7)
 294 \f
 295 (define-coding-system 'windows-1250
 296   "windows-1250 (Central European) encoding (MIME: WINDOWS-1250)"
 297   :coding-type 'charset
 298   :mnemonic ?*
 299   :charset-list '(windows-1250)
 300   :mime-charset 'windows-1250)
 301 (define-coding-system-alias 'cp1250 'windows-1250)
 302
 303 (define-coding-system 'windows-1252
 304   "windows-1252 (Western European) encoding (MIME: WINDOWS-1252)"
 305   :coding-type 'charset
 306   :mnemonic ?*
 307   :charset-list '(windows-1252)
 308   :mime-charset 'windows-1252)
 309 (define-coding-system-alias 'cp1252 'windows-1252)
 310
 311 (define-coding-system 'windows-1254
 312   "windows-1254 (Turkish) encoding (MIME: WINDOWS-1254)"
 313   :coding-type 'charset
 314   :mnemonic ?*
 315   :charset-list '(windows-1254)
 316   :mime-charset 'windows-1254)
 317 (define-coding-system-alias 'cp1254 'windows-1254)
 318
 319 (define-coding-system 'windows-1257
 320   "windows-1257 (Baltic) encoding (MIME: WINDOWS-1257)"
 321   :coding-type 'charset
 322   :mnemonic ?*
 323   :charset-list '(windows-1257)
 324   :mime-charset 'windows-1257)
 325 (define-coding-system-alias 'cp1257 'windows-1257)
 326
 327 (define-coding-system 'cp850
 328   "DOS codepage 850 (Western European)"
 329   :coding-type 'charset
 330   :mnemonic ?D
 331   :charset-list '(cp850)
 332   :mime-charset 'cp850)
 333 (define-coding-system-alias 'ibm850 'cp850)
 334
 335 (define-coding-system 'cp852
 336   "DOS codepage 852 (Slavic)"
 337   :coding-type 'charset
 338   :mnemonic ?D
 339   :charset-list '(cp852)
 340   :mime-charset 'cp852)
 341 (define-coding-system-alias 'ibm852 'cp852)
 342
 343 (define-coding-system 'cp857
 344   "DOS codepage 857 (Turkish)"
 345   :coding-type 'charset
 346   :mnemonic ?D
 347   :charset-list '(cp857)
 348   :mime-charset 'cp857)
 349 (define-coding-system-alias 'ibm857 'cp857)
 350
 351 (define-coding-system 'cp860
 352   "DOS codepage 860 (Portuguese)"
 353   :coding-type 'charset
 354   :mnemonic ?D
 355   :charset-list '(cp860)
 356   :mime-charset 'cp860)
 357 (define-coding-system-alias 'ibm860 'cp860)
 358
 359 (define-coding-system 'cp861
 360   "DOS codepage 861 (Icelandic)"
 361   :coding-type 'charset
 362   :mnemonic ?D
 363   :charset-list '(cp861)
 364   :mime-charset 'cp861)
 365 (define-coding-system-alias 'ibm861 'cp861)
 366
 367 (define-coding-system 'cp863
 368   "DOS codepage 863 (French Canadian)"
 369   :coding-type 'charset
 370   :mnemonic ?D
 371   :charset-list '(cp863)
 372   :mime-charset 'cp863)
 373 (define-coding-system-alias 'ibm863 'cp863)
 374
 375 (define-coding-system 'cp865
 376   "DOS codepage 865 (Norwegian/Danish)"
 377   :coding-type 'charset
 378   :mnemonic ?D
 379   :charset-list '(cp865)
 380   :mime-charset 'cp865)
 381 (define-coding-system-alias 'ibm865 'cp865)
 382
 383 (define-coding-system 'cp437
 384   "DOS codepage 437"
 385   :coding-type 'charset
 386   :mnemonic ?D
 387   :charset-list '(cp437)
 388   :mime-charset 'cp437)
 389 (define-coding-system-alias 'ibm437 'cp437)
 390 \f
 391 (set-language-info-alist
 392  "German" '((tutorial . "TUTORIAL.de")
 393             (charset iso-8859-1)
 394             (coding-system iso-latin-1 iso-latin-9)
 395             (coding-priority iso-latin-1)
 396             (nonascii-translation . iso-8859-1)
 397             (input-method . "german-postfix")
 398             (unibyte-syntax . "latin-1")
 399             (unibyte-display . iso-latin-1)
 400             (sample-text . "\
 401 German (Deutsch Nord)   Guten Tag
 402 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 403             (documentation . "\
 404 This language environment is almost the same as Latin-1,
 405 but sets the default input method to \"german-postfix\".
 406 Additionally, it selects the German tutorial."))
 407  '("European"))
 408
 409 (set-language-info-alist
 410  "French" '((tutorial . "TUTORIAL.fr")
 411             (charset iso-8859-1)
 412             (coding-system iso-latin-1 iso-latin-9)
 413             (coding-priority iso-latin-1)
 414             (nonascii-translation . iso-8859-1)
 415             (unibyte-syntax . "latin-1")
 416             (unibyte-display . iso-latin-1)
 417             (input-method . "latin-1-prefix")
 418             (sample-text . "French (Fran\e,Ag\e(Bais)     Bonjour, Salut")
 419             (documentation . "\
 420 This language environment is almost the same as Latin-1,
 421 but it selects the French tutorial."))
 422  '("European"))
 423
 424 (set-language-info-alist
 425  "Slovenian" '((charset iso-8859-2)
 426               (coding-system . (iso-8859-2 windows-1250))
 427               (coding-priority . (iso-8859-2))
 428               (nonascii-translation . iso-8859-2)
 429               (input-method . "latin-2-postfix")
 430               (unibyte-syntax . "latin-2")
 431               (unibyte-display . iso-8859-2)
 432               (tutorial . "TUTORIAL.sl")
 433               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 434               (documentation . t))
 435  '("European"))
 436
 437 (set-language-info-alist
 438  "Spanish" '((tutorial . "TUTORIAL.es")
 439             (charset iso-8859-1)
 440             (coding-system iso-latin-1 iso-latin-9)
 441             (coding-priority iso-latin-1)
 442             (nonascii-translation . iso-8859-1)
 443             (input-method . "spanish-postfix")
 444             (unibyte-syntax . "latin-1")
 445             (unibyte-display . iso-latin-1)
 446             (sample-text . "Spanish (Espa\e,Aq\e(Bol)     \e,A!\e(BHola!")
 447             (documentation . "\
 448 This language environment is almost the same as Latin-1,
 449 but it sets the default input method to \"spanish-postfix\",
 450 and it selects the Spanish tutorial."))
 451  '("European"))
 452
 453 (set-language-info-alist
 454  "Dutch" '((tutorial . "TUTORIAL.nl")
 455            (charset iso-8859-1)
 456            (coding-system iso-latin-1 iso-latin-9)
 457            (coding-priority iso-latin-1)
 458            (nonascii-translation . iso-8859-1)
 459            (unibyte-syntax . "latin-1")
 460            (unibyte-display . iso-latin-1)
 461            (input-method . "dutch")
 462            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 463            (documentation . "\
 464 This language environment is almost the same as Latin-1,
 465 but it selects the Dutch tutorial and input method."))
 466  '("European"))
 467
 468 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 469 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 470 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 471 ;; "Latin-3" language environment.
 472
 473 (set-language-info-alist
 474  "Turkish" '((charset iso-8859-9)
 475              (coding-system iso-latin-5 windows-1254 iso-latin-3)
 476              (coding-priority iso-latin-5)
 477              (nonascii-translation . iso-8859-9)
 478              (unibyte-syntax . "latin-5")
 479              (unibyte-display . iso-latin-5)
 480              (input-method . "turkish-postfix")
 481              (sample-text . "Turkish (T\e,A|\e(Brk\e,Ag\e(Be)       Merhaba")
 482              (documentation . t)))
 483
 484 ;; Polish ISO 8859-2 environment.
 485 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 486 ;; Keywords: multilingual, Polish
 487
 488 (set-language-info-alist
 489  "Polish" '((charset . (iso-8859-2))
 490            (coding-system . (iso-8859-2 windows-1250))
 491            (coding-priority . (iso-8859-2))
 492            (nonascii-translation . iso-8859-2)
 493            (input-method . "polish-slash")
 494            (unibyte-syntax . "latin-2")
 495            (unibyte-display . iso-8859-2)
 496            (tutorial . "TUTORIAL.pl")
 497            (sample-text . "P\e,As\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")
 498            (documentation . t))
 499  '("European"))
 500
 501 (set-language-info-alist
 502  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 503            (coding-priority utf-8 latin-8)
 504            (nonascii-translation . iso-8859-14)
 505            (input-method . "welsh")
 506            (documentation . "Support for Welsh, using Unicode."))
 507  '("European"))
 508
 509 (set-language-info-alist
 510  "Latin-7" `((coding-system latin-7)
 511              (coding-priority latin-7)
 512              (nonascii-translation . iso-8859-13)
 513              ;; Fixme: input-method
 514              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 515  '("European"))
 516
 517 (set-language-info-alist
 518  "Lithuanian" `((coding-system latin-7 windows-1257)
 519                 (coding-priority latin-7)
 520                 (nonascii-translation . iso-8859-13)
 521                 (input-method . "lithuanian-keyboard")
 522                 (documentation . "Support for Lithuanian."))
 523  '("European"))
 524
 525 (set-language-info-alist
 526  "Latvian" `((coding-system latin-7 windows-1257)
 527              (coding-priority latin-7)
 528              (nonascii-translation . iso-8859-13)
 529              (input-method . "latvian-keyboard")
 530              (documentation . "Support for Latvian."))
 531  '("European"))
 532
 533 \f
 534 (define-coding-system 'mac-roman
 535   "Mac Roman Encoding (MIME:MACINTOSH)."
 536   :coding-type 'charset
 537   :mnemonic ?M
 538   :charset-list '(mac-roman)
 539   :mime-charset 'macintosh)
 540
 541 (define-coding-system 'next
 542   "NeXTstep encoding"
 543   :coding-type 'charset
 544   :mnemonic ?*
 545   :charset-list '(next)
 546   :mime-charset 'next)
 547
 548 (define-coding-system 'hp-roman8
 549   "Hewlet-Packard roman-8 encoding (MIME:ROMAN-8)"
 550   :coding-type 'charset
 551   :mnemonic ?*
 552   :charset-list '(hp-roman8)
 553   :mime-charset 'hp-roman8)
 554 (define-coding-system-alias 'roman8 'hp-roman8)
 555
 556 (define-coding-system 'adobe-standard-encoding
 557   "Adobe `standard' encoding for PostScript"
 558   :coding-type 'charset
 559   :mnemonic ?*
 560   :charset-list '(adobe-standard-encoding)
 561   :mime-charset 'adobe-standard-encoding)
 562 \f
 563 (defconst diacritic-composition-pattern "\\C^\\c^+")
 564
 565 (defun diacritic-compose-region (beg end)
 566   "Compose diacritic characters in the region.
 567 When called from a program, expects two arguments,
 568 positions (integers or markers) specifying the region."
 569   (interactive "r")
 570   (save-restriction
 571     (narrow-to-region beg end)
 572     (goto-char (point-min))
 573     (while (re-search-forward diacritic-composition-pattern nil t)
 574       (compose-region (match-beginning 0) (match-end 0)))))
 575
 576 (defun diacritic-compose-string (string)
 577   "Compose diacritic characters in STRING and return the resulting string."
 578   (let ((idx 0))
 579     (while (setq idx (string-match diacritic-composition-pattern string idx))
 580       (compose-string string idx (match-end 0))
 581       (setq idx (match-end 0))))
 582   string)
 583
 584 (defun diacritic-compose-buffer ()
 585   "Compose diacritic characters in the current buffer."
 586   (interactive)
 587   (diacritic-compose-region (point-min) (point-max)))
 588
 589 (defun diacritic-post-read-conversion (len)
 590   (diacritic-compose-region (point) (+ (point) len))
 591   len)
 592
 593 (defun diacritic-composition-function (from to pattern &optional string)
 594   "Compose diacritic text in the region FROM and TO.
 595 The text matches the regular expression PATTERN.
 596 Optional 4th argument STRING, if non-nil, is a string containing text
 597 to compose.
 598
 599 The return value is number of composed characters."
 600   (if (< (1+ from) to)
 601       (prog1 (- to from)
 602         (if string
 603             (compose-string string from to)
 604           (compose-region from to))
 605         (- to from))))
 606
 607 ;; Register a function to compose Unicode diacrtics and marks.
 608 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
 609   (let ((c #x300))
 610     (while (<= c #x362)
 611       (aset composition-function-table c patterns)
 612       (setq c (1+ c)))
 613     (setq c #x20d0)
 614     (while (<= c #x20e3)
 615       (aset composition-function-table c patterns)
 616       (setq c (1+ c)))))
 617
 618 (provide 'european)
 619
 620 ;;; european.el ends here