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) 1997, 1998, 2000, 2001, 2002, 2003, 2004, 2005, 2006
   4 ;;   Free Software Foundation, Inc.
   5 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
   6 ;;   2005, 2006
   7 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   8 ;;   Registration Number H14PRO021
   9 ;; Copyright (C) 2003
  10 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  11 ;;   Registration Number H13PRO009
  12
  13 ;; Keywords: multilingual, European
  14
  15 ;; This file is part of GNU Emacs.
  16
  17 ;; GNU Emacs is free software; you can redistribute it and/or modify
  18 ;; it under the terms of the GNU General Public License as published by
  19 ;; the Free Software Foundation; either version 2, or (at your option)
  20 ;; any later version.
  21
  22 ;; GNU Emacs is distributed in the hope that it will be useful,
  23 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  24 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  25 ;; GNU General Public License for more details.
  26
  27 ;; You should have received a copy of the GNU General Public License
  28 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  29 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  30 ;; Boston, MA 02110-1301, USA.
  31
  32 ;;; Commentary:
  33
  34 ;; For European scripts, all the ISO Latin character sets are
  35 ;; supported, along with various others.
  36
  37 ;;; Code:
  38
  39 ;; Latin-1 (ISO-8859-1)
  40
  41 (set-language-info-alist
  42  "Latin-1" '((charset iso-8859-1)
  43              (coding-system iso-latin-1 iso-latin-9 windows-1252)
  44              (coding-priority iso-latin-1)
  45              (nonascii-translation . iso-8859-1)
  46              (unibyte-display . iso-latin-1)
  47              (input-method . "latin-1-prefix")
  48              (sample-text
  49               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e$(D+d)N\e(B Gott, Ciao, \e$(D"B\e(BHola!")
  50              (documentation . "\
  51 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  52 character set which supports the following European languages:
  53  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  54  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  55  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  56  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  57  Scottish Gaelic, Spanish, and Swedish.
  58 We also have specific language environments for the following languages:
  59   For Dutch, \"Dutch\".
  60   For German, \"German\".
  61   For French, \"French\".
  62   For Italian, \"Italian\".
  63   For Slovenian, \"Slovenian\".
  64   For Spanish, \"Spanish\".
  65
  66 Latin-1 also covers several written languages outside Europe, including
  67 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  68  '("European"))
  69
  70 \f
  71 ;; Latin-2 (ISO-8859-2)
  72
  73 (define-coding-system 'iso-latin-2
  74    "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  75   :coding-type 'charset
  76   :mnemonic ?2
  77   :charset-list '(iso-8859-2)
  78   :mime-charset 'iso-8859-2)
  79
  80 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  81 (define-coding-system-alias 'latin-2 'iso-latin-2)
  82
  83 (set-language-info-alist
  84  "Latin-2" '((charset iso-8859-2)
  85              (coding-system iso-latin-2 windows-1250)
  86              (coding-priority iso-latin-2)
  87              (nonascii-translation . iso-8859-2)
  88              (unibyte-display . iso-latin-2)
  89              (input-method . "latin-2-prefix")
  90              (documentation . "\
  91 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  92 character set which supports the following languages:
  93  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
  94  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
  95  and Swedish.
  96 We also have specific language environments for the following languages:
  97   For Czech, \"Czech\".
  98   For Croatian, \"Croatian\".
  99   For Polish, \"Polish\".
 100   For Romanian, \"Romanian\".
 101   For Slovak, \"Slovak\"."))
 102  '("European"))
 103
 104 \f
 105 ;; Latin-3 (ISO-8859-3)
 106
 107 (define-coding-system 'iso-latin-3
 108   "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
 109   :coding-type 'charset
 110   :mnemonic ?3
 111   :charset-list '(iso-8859-3)
 112   :mime-charset 'iso-8859-3)
 113
 114 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 115 (define-coding-system-alias 'latin-3 'iso-latin-3)
 116
 117 (set-language-info-alist
 118  "Latin-3" '((charset iso-8859-3)
 119              (coding-system iso-latin-3)
 120              (coding-priority iso-latin-3)
 121              (nonascii-translation . iso-8859-3)
 122              (unibyte-display . iso-latin-3)
 123              (input-method . "latin-3-prefix")
 124              (documentation . "\
 125 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 126  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 127  German, Italian, Maltese, Spanish, and Turkish."))
 128  '("European"))
 129
 130 \f
 131 ;; Latin-4 (ISO-8859-4)
 132
 133 (define-coding-system 'iso-latin-4
 134   "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
 135   :coding-type 'charset
 136   :mnemonic ?4
 137   :charset-list '(iso-8859-4)
 138   :mime-charset 'iso-8859-4)
 139
 140 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 141 (define-coding-system-alias 'latin-4 'iso-latin-4)
 142
 143 (set-language-info-alist
 144  "Latin-4" '((charset iso-8859-4)
 145              (coding-system iso-8859-4)
 146              (coding-priority iso-8859-4)
 147              (nonascii-translation . iso-8859-4)
 148              (unibyte-display . iso-8859-4)
 149              (input-method . "latin-4-postfix")
 150              (documentation . "\
 151 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 152  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 153  Latvian, Lithuanian, and Norwegian."))
 154  '("European"))
 155
 156 \f
 157 ;; Latin-5 (ISO-8859-9)
 158
 159 (define-coding-system 'iso-latin-5
 160   "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
 161   :coding-type 'charset
 162   :mnemonic ?9
 163   :charset-list '(iso-8859-9)
 164   :mime-charset 'iso-8859-9)
 165
 166 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 167 (define-coding-system-alias 'latin-5 'iso-latin-5)
 168
 169 (set-language-info-alist
 170  "Latin-5" '((charset iso-8859-9)
 171              (coding-system iso-latin-5)
 172              (coding-priority iso-latin-5)
 173              (nonascii-translation . iso-8859-9)
 174              (unibyte-display . iso-latin-5)
 175              (input-method . "latin-5-postfix")
 176              (documentation . "Support for Latin-5.\
 177 See also the Turkish environment."))
 178  '("European"))
 179
 180 \f
 181 ;; Latin-6 (ISO-8859-10)
 182
 183 (define-coding-system 'iso-latin-6
 184   "ISO 2022 based 8-bit encoding for Latin-6 (MIME:ISO-8859-10)."
 185   :coding-type 'charset
 186   :mnemonic ?9
 187   :charset-list '(iso-8859-10)
 188   :mime-charset 'iso-8859-10)
 189
 190 (define-coding-system-alias 'iso-8859-10 'iso-latin-6)
 191 (define-coding-system-alias 'latin-6 'iso-latin-6)
 192
 193 (set-language-info-alist
 194  "Latin-6" '((charset iso-8859-10)
 195              (coding-system iso-latin-6)
 196              (coding-priority iso-latin-6)
 197              (nonascii-translation . iso-8859-10)
 198              (unibyte-display . iso-latin-6)
 199              ;; Fixme: input method.
 200              (documentation . "Support for generic Latin-6 (Northern European)."))
 201  '("European"))
 202
 203 \f
 204 ;; Latin-7 (ISO-8859-13)
 205
 206 (define-coding-system 'iso-latin-7
 207   "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
 208   :coding-type 'charset
 209   :mnemonic ?9
 210   :charset-list '(iso-8859-13)
 211   :mime-charset 'iso-8859-13)
 212
 213 (define-coding-system-alias 'iso-8859-13 'iso-latin-7)
 214 (define-coding-system-alias 'latin-7 'iso-latin-7)
 215
 216 (set-language-info-alist
 217  "Latin-7" '((charset iso-8859-13)
 218              (coding-system iso-latin-7)
 219              (coding-priority iso-latin-7)
 220              (nonascii-translation . iso-8859-13)
 221              (unibyte-display . iso-latin-7)
 222              ;; Fixme: input method.
 223              (documentation . "Support for generic Latin-7 (Baltic Rim)."))
 224  '("European"))
 225 \f
 226 ;; Latin-8 (ISO-8859-14)
 227
 228 (define-coding-system 'iso-latin-8
 229   "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 230   :coding-type 'charset
 231   ;; `W' for `Welsh', since `C' for `Celtic' is taken.
 232   :mnemonic ?W
 233   :charset-list '(iso-8859-14)
 234   :mime-charset 'iso-8859-14)
 235
 236 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 237 (define-coding-system-alias 'latin-8 'iso-latin-8)
 238
 239 (set-language-info-alist
 240  "Latin-8" '((charset iso-8859-14)
 241              (coding-system iso-latin-8)
 242              (coding-priority iso-latin-8)
 243              (nonascii-translation . iso-8859-14)
 244              (unibyte-display . iso-latin-8)
 245              (input-method . "latin-8-prefix")
 246              ;; Fixme: Welsh/Ga{e}lic greetings
 247              (sample-text . "\e,_"\e(B \e$(D+q\e(B \e$(D*t\e(B")
 248              (documentation . "\
 249 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 250 character set which supports the Celtic languages, including those not
 251 covered by other ISO-8859 character sets:
 252  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 253  '("European"))
 254 \f
 255 ;; Latin-9 (ISO-8859-15)
 256
 257 (define-coding-system 'iso-latin-9
 258   "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 259   :coding-type 'charset
 260   ;; `0' for `Latin-0'
 261   :mnemonic ?0
 262   :charset-list '(iso-8859-15)
 263   :mime-charset 'iso-8859-15)
 264
 265 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 266 (define-coding-system-alias 'latin-9 'iso-latin-9)
 267 (define-coding-system-alias 'latin-0 'iso-latin-9)
 268
 269 (set-language-info-alist
 270  "Latin-9" '((charset iso-8859-15)
 271              (coding-system iso-latin-9)
 272              (coding-priority iso-latin-9)
 273              (nonascii-translation . iso-8859-15)
 274              (unibyte-display . iso-latin-9)
 275              (input-method . "latin-9-prefix")
 276              (sample-text
 277               . "AVE. \e$(D*^+^*v+v)-)M*s\e(B \e$(Q)!\e(B")
 278              (documentation . "\
 279 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 280 character set which supports the same languages as Latin-1 with the
 281 addition of the Euro sign and some additional French and Finnish letters.
 282 Latin-9 is sometimes nicknamed `Latin-0'."))
 283  '("European"))
 284 \f
 285 (define-coding-system 'windows-1250
 286   "windows-1250 (Central European) encoding (MIME: WINDOWS-1250)"
 287   :coding-type 'charset
 288   :mnemonic ?*
 289   :charset-list '(windows-1250)
 290   :mime-charset 'windows-1250)
 291 (define-coding-system-alias 'cp1250 'windows-1250)
 292
 293 (define-coding-system 'windows-1252
 294   "windows-1252 (Western European) encoding (MIME: WINDOWS-1252)"
 295   :coding-type 'charset
 296   :mnemonic ?*
 297   :charset-list '(windows-1252)
 298   :mime-charset 'windows-1252)
 299 (define-coding-system-alias 'cp1252 'windows-1252)
 300
 301 (define-coding-system 'windows-1254
 302   "windows-1254 (Turkish) encoding (MIME: WINDOWS-1254)"
 303   :coding-type 'charset
 304   :mnemonic ?*
 305   :charset-list '(windows-1254)
 306   :mime-charset 'windows-1254)
 307 (define-coding-system-alias 'cp1254 'windows-1254)
 308
 309 (define-coding-system 'windows-1257
 310   "windows-1257 (Baltic) encoding (MIME: WINDOWS-1257)"
 311   :coding-type 'charset
 312   :mnemonic ?*
 313   :charset-list '(windows-1257)
 314   :mime-charset 'windows-1257)
 315 (define-coding-system-alias 'cp1257 'windows-1257)
 316
 317 (define-coding-system 'cp850
 318   "DOS codepage 850 (Western European)"
 319   :coding-type 'charset
 320   :mnemonic ?D
 321   :charset-list '(cp850)
 322   :mime-charset 'cp850)
 323 (define-coding-system-alias 'ibm850 'cp850)
 324
 325 (define-coding-system 'cp852
 326   "DOS codepage 852 (Slavic)"
 327   :coding-type 'charset
 328   :mnemonic ?D
 329   :charset-list '(cp852)
 330   :mime-charset 'cp852)
 331 (define-coding-system-alias 'ibm852 'cp852)
 332
 333 (define-coding-system 'cp857
 334   "DOS codepage 857 (Turkish)"
 335   :coding-type 'charset
 336   :mnemonic ?D
 337   :charset-list '(cp857)
 338   :mime-charset 'cp857)
 339 (define-coding-system-alias 'ibm857 'cp857)
 340
 341 (define-coding-system 'cp858
 342   "Codepage 858 (Multilingual Latin I + Euro)"
 343   :coding-type 'charset
 344   :mnemonic ?D
 345   :charset-list '(cp858)
 346   :mime-charset 'cp858)
 347
 348 (define-coding-system 'cp860
 349   "DOS codepage 860 (Portuguese)"
 350   :coding-type 'charset
 351   :mnemonic ?D
 352   :charset-list '(cp860)
 353   :mime-charset 'cp860)
 354 (define-coding-system-alias 'ibm860 'cp860)
 355
 356 (define-coding-system 'cp861
 357   "DOS codepage 861 (Icelandic)"
 358   :coding-type 'charset
 359   :mnemonic ?D
 360   :charset-list '(cp861)
 361   :mime-charset 'cp861)
 362 (define-coding-system-alias 'ibm861 'cp861)
 363
 364 (define-coding-system 'cp863
 365   "DOS codepage 863 (French Canadian)"
 366   :coding-type 'charset
 367   :mnemonic ?D
 368   :charset-list '(cp863)
 369   :mime-charset 'cp863)
 370 (define-coding-system-alias 'ibm863 'cp863)
 371
 372 (define-coding-system 'cp865
 373   "DOS codepage 865 (Norwegian/Danish)"
 374   :coding-type 'charset
 375   :mnemonic ?D
 376   :charset-list '(cp865)
 377   :mime-charset 'cp865)
 378 (define-coding-system-alias 'ibm865 'cp865)
 379
 380 (define-coding-system 'cp437
 381   "DOS codepage 437"
 382   :coding-type 'charset
 383   :mnemonic ?D
 384   :charset-list '(cp437)
 385   :mime-charset 'cp437)
 386 (define-coding-system-alias 'ibm437 'cp437)
 387 \f
 388 (set-language-info-alist
 389  "Dutch" '((tutorial . "TUTORIAL.nl")
 390            (charset iso-8859-1)
 391            (coding-system iso-latin-1 iso-latin-9)
 392            (coding-priority iso-latin-1)
 393            (nonascii-translation . iso-8859-1)
 394            (unibyte-display . iso-latin-1)
 395            (input-method . "dutch")
 396            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 397            (documentation . "\
 398 This language environment is almost the same as Latin-1,
 399 but it selects the Dutch tutorial and input method."))
 400  '("European"))
 401
 402 (set-language-info-alist
 403  "German" '((tutorial . "TUTORIAL.de")
 404             (charset iso-8859-1)
 405             (coding-system iso-latin-1 iso-latin-9)
 406             (coding-priority iso-latin-1)
 407             (nonascii-translation . iso-8859-1)
 408             (input-method . "german-postfix")
 409             (unibyte-display . iso-latin-1)
 410             (sample-text . "\
 411 German (Deutsch Nord)   Guten Tag
 412 German (Deutsch S\e$(D+d\e(Bd)    Gr\e$(D+d)N\e(B Gott")
 413             (documentation . "\
 414 This language environment is almost the same as Latin-1,
 415 but sets the default input method to \"german-postfix\".
 416 Additionally, it selects the German tutorial."))
 417  '("European"))
 418
 419 (set-language-info-alist
 420  "French" '((tutorial . "TUTORIAL.fr")
 421             (charset iso-8859-1)
 422             (coding-system iso-latin-1 iso-latin-9)
 423             (coding-priority iso-latin-1)
 424             (nonascii-translation . iso-8859-1)
 425             (unibyte-display . iso-latin-1)
 426             (input-method . "latin-1-prefix")
 427             (sample-text . "French (Fran\e$(D+.\e(Bais)   Bonjour, Salut")
 428             (documentation . "\
 429 This language environment is almost the same as Latin-1,
 430 but it selects the French tutorial and input method."))
 431  '("European"))
 432
 433 (set-language-info-alist
 434  "Italian" '((tutorial . "TUTORIAL.it")
 435             (charset iso-8859-1)
 436             (coding-system iso-latin-1 iso-latin-9)
 437             (coding-priority iso-latin-1)
 438             (nonascii-translation . iso-8859-1)
 439             (unibyte-display . iso-latin-1)
 440             (input-method . "italian-postfix")
 441             (sample-text . "Salve, ciao!")
 442             (documentation . "\
 443 This language environment is almost the same as Latin-1,
 444 but sets the default input method to \"italian-postfix\".
 445 Additionally, it selects the Italian tutorial."))
 446  '("European"))
 447
 448 (set-language-info-alist
 449  "Slovenian" '((charset iso-8859-2)
 450               (coding-system . (iso-8859-2 windows-1250))
 451               (coding-priority . (iso-8859-2))
 452               (nonascii-translation . iso-8859-2)
 453               (input-method . "slovenian")
 454               (unibyte-display . iso-8859-2)
 455               (tutorial . "TUTORIAL.sl")
 456               (sample-text . "\e$(D*v\e(Belimo vam uspe\e$(D+^\e(Ben dan!")
 457               (documentation . "\
 458 This language environment is almost the same as Latin-2,
 459 but it selects the Slovenian tutorial and input method."))
 460  '("European"))
 461
 462 (set-language-info-alist
 463  "Spanish" '((tutorial . "TUTORIAL.es")
 464             (charset iso-8859-1)
 465             (coding-system iso-latin-1 iso-latin-9)
 466             (coding-priority iso-latin-1)
 467             (input-method . "spanish-postfix")
 468             (nonascii-translation . iso-8859-1)
 469             (unibyte-display . iso-latin-1)
 470             (sample-text . "Spanish (Espa\e$(D+P\e(Bol)   \e$(D"B\e(BHola!")
 471             (documentation . "\
 472 This language environment is almost the same as Latin-1,
 473 but it sets the default input method to \"spanish-postfix\",
 474 and it selects the Spanish tutorial."))
 475  '("European"))
 476
 477 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 478 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 479 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 480 ;; "Latin-3" language environment.
 481
 482 (set-language-info-alist
 483  "Turkish" '((charset iso-8859-9)
 484              (coding-system iso-latin-5 windows-1254 iso-latin-3)
 485              (coding-priority iso-latin-5)
 486              (nonascii-translation . iso-8859-9)
 487              (unibyte-display . iso-latin-5)
 488              (input-method . "turkish-postfix")
 489              (sample-text . "Turkish (T\e$(D+d\e(Brk\e$(D+.\e(Be)   Merhaba")
 490              (setup-function . turkish-case-conversion-enable)
 491              (setup-function . turkish-case-conversion-disable)
 492              (documentation . "Support for Turkish.
 493 Differs from the Latin-5 environment in using the `turkish-postfix' input
 494 method and applying Turkish case rules for the characters i, I, \e$(D)E\e(B, \e$(D*D\e(B.")))
 495
 496 (defun turkish-case-conversion-enable ()
 497   "Set up Turkish case conversion of `i' and `I' into `\e$(D*D\e(B' and `\e$(D)E\e(B'."
 498   (let ((table (standard-case-table)))
 499     (set-case-syntax-pair ?\e$(D*D\e(B ?i table)
 500     (set-case-syntax-pair ?I ?\e$(D)E\e(B table)))
 501
 502 (defun turkish-case-conversion-disable ()
 503   "Set up normal (non-Turkish) case conversion of `i' into `I'."
 504   (let ((table (standard-case-table)))
 505     (set-case-syntax-pair ?I ?i table)
 506     (set-case-syntax ?\e$(D*D\e(B "w" table)
 507     (set-case-syntax ?\e$(D)E\e(B "w" table)))
 508
 509 ;; Polish ISO 8859-2 environment.
 510 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 511 ;; Keywords: multilingual, Polish
 512
 513 (set-language-info-alist
 514  "Polish" '((charset iso-8859-2)
 515            (coding-system iso-8859-2 windows-1250)
 516            (coding-priority iso-8859-2)
 517            (input-method . "polish-slash")
 518            (nonascii-translation . iso-8859-2)
 519            (unibyte-display . iso-8859-2)
 520            (tutorial . "TUTORIAL.pl")
 521            (sample-text . "P\e$(D+Q\e(Bjd\e$(D+u\e(B, ki\e$(D+M\e(B-\e$(D+w\e(Be t\e$(D+8\e(B chmurno\e$(D+\++\e(B w g\e$(D)H+(\e(Bb flaszy")
 522            (documentation . t))
 523  '("European"))
 524
 525 (set-language-info-alist
 526  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 527            (coding-priority utf-8 latin-8)
 528            (nonascii-translation . iso-8859-14)
 529            (input-method . "welsh")
 530            (documentation . "Support for Welsh, using Unicode."))
 531  '("European"))
 532
 533 (set-language-info-alist
 534  "Latin-6" `((coding-system latin-6)
 535              (coding-priority latin-6)
 536              (nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
 537              (input-method . "latin-prefix")
 538              (features code-pages)
 539              (documentation . "Support for Latin-6."))
 540  '("European"))
 541
 542 (set-language-info-alist
 543  "Latin-7" `((coding-system latin-7)
 544              (coding-priority latin-7)
 545              (nonascii-translation . iso-8859-13)
 546              (input-method . "latin-prefix")
 547              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 548  '("European"))
 549
 550 (set-language-info-alist
 551  "Lithuanian" `((coding-system latin-7 windows-1257)
 552                 (coding-priority latin-7)
 553                 (nonascii-translation . iso-8859-13)
 554                 (input-method . "lithuanian-keyboard")
 555                 (documentation . "Support for Lithuanian."))
 556  '("European"))
 557
 558 (set-language-info-alist
 559  "Latvian" `((coding-system latin-7 windows-1257)
 560              (coding-priority latin-7)
 561              (nonascii-translation . iso-8859-13)
 562              (input-method . "latvian-keyboard")
 563              (documentation . "Support for Latvian."))
 564  '("European"))
 565
 566 (set-language-info-alist
 567  "Swedish" '((tutorial . "TUTORIAL.sv")
 568             (charset iso-8859-1)
 569             (coding-system iso-latin-1)
 570             (coding-priority iso-latin-1)
 571             (nonascii-translation . iso-8859-1)
 572             (unibyte-display . iso-latin-1)
 573             (sample-text . "Goddag Hej")
 574             (documentation . "Support for Swedish"))
 575  '("European"))
 576
 577 (set-language-info-alist
 578  "Croatian" '((charset iso-8859-2)
 579               (coding-system iso-8859-2)
 580               (coding-priority iso-8859-2)
 581               (input-method . "croatian")
 582               (nonascii-translation . iso-8859-2)
 583               (unibyte-display . iso-8859-2)
 584               (documentation . "Support for Croatian with Latin-2 encoding."))
 585  '("European"))
 586
 587 (set-language-info-alist
 588  "Brazilian Portuguese" '((tutorial . "TUTORIAL.pt_BR")
 589             (charset iso-8859-1)
 590             (coding-system iso-latin-1 iso-latin-9)
 591             (coding-priority iso-latin-1)
 592             (nonascii-translation . iso-8859-1)
 593             (unibyte-display . iso-8859-1)
 594             (input-method . "latin-1-prefix")
 595             (sample-text . "Oi")
 596             (documentation . "Support for Brazilian Portuguese."))
 597  '("European"))
 598
 599 \f
 600 (define-coding-system 'mac-roman
 601   "Mac Roman Encoding (MIME:MACINTOSH)."
 602   :coding-type 'charset
 603   :mnemonic ?M
 604   :charset-list '(mac-roman)
 605   :mime-charset 'macintosh)
 606
 607 (define-coding-system 'next
 608   "NeXTstep encoding"
 609   :coding-type 'charset
 610   :mnemonic ?*
 611   :charset-list '(next)
 612   :mime-charset 'next)
 613
 614 (define-coding-system 'hp-roman8
 615   "Hewlet-Packard roman-8 encoding (MIME:ROMAN-8)"
 616   :coding-type 'charset
 617   :mnemonic ?*
 618   :charset-list '(hp-roman8)
 619   :mime-charset 'hp-roman8)
 620 (define-coding-system-alias 'roman8 'hp-roman8)
 621
 622 (define-coding-system 'adobe-standard-encoding
 623   "Adobe `standard' encoding for PostScript"
 624   :coding-type 'charset
 625   :mnemonic ?*
 626   :charset-list '(adobe-standard-encoding)
 627   :mime-charset 'adobe-standard-encoding)
 628
 629 \f
 630 ;; For automatic composing of diacritics and combining marks.
 631 (dolist (range '( ;; combining diacritical marks
 632                  (#x0300 #x0314 (tc . bc))
 633                  (#x0315        (tr . bl))
 634                  (#x0316 #x0319 (bc . tc))
 635                  (#x031A        (tr . cl))
 636                  (#x031B #x0320 (bc . tc))
 637                  (#x0321        (Br . tr))
 638                  (#x0322        (Br . tl))
 639                  (#x0323 #x0333 (bc . tc))
 640                  (#x0334 #x0338 (Bc . Bc))
 641                  (#x0339 #x033C (bc . tc))
 642                  (#x033D #x033F (tc . bc))
 643                  (#x0340        (tl . bc))
 644                  (#x0341        (tr . bc))
 645                  (#x0342 #x0344 (tc . bc))
 646                  (#x0345        (bc . tc))
 647                  (#x0346        (tc . bc))
 648                  (#x0347 #x0349 (bc . tc))
 649                  (#x034A #x034C (tc . bc))
 650                  (#x034D #x034E (bc . tc))
 651                  ;; combining diacritical marks for symbols
 652                  (#x20D0 #x20D1 (tc . bc))
 653                  (#x20D2 #x20D3 (Bc . Bc))
 654                  (#x20D4 #x20D7 (tc . bc))
 655                  (#x20D8 #x20DA (Bc . Bc))
 656                  (#x20DB #x20DC (tc . bc))
 657                  (#x20DD #x20E0 (Bc . Bc))
 658                  (#x20E1        (tc . bc))
 659                  (#x20E2 #x20E3 (Bc . Bc))))
 660   (let* ((from (car range))
 661          (to (if (= (length range) 3)
 662                  (nth 1 range)
 663                from))
 664          (composition (car (last range))))
 665     (while (<= from to)
 666       (put-char-code-property from 'diacritic-composition composition)
 667       (aset composition-function-table from 'diacritic-composition-function)
 668       (setq from (1+ from)))))
 669
 670 (defconst diacritic-composition-pattern "\\C^\\c^+")
 671
 672 (defun diacritic-compose-region (beg end)
 673   "Compose diacritic characters in the region.
 674 When called from a program, expects two arguments,
 675 positions (integers or markers) specifying the region."
 676   (interactive "r")
 677   (save-restriction
 678     (narrow-to-region beg end)
 679     (goto-char (point-min))
 680     (while (re-search-forward diacritic-composition-pattern nil t)
 681       (if (= (char-syntax (char-after (match-beginning 0))) ?w)
 682           (compose-region (match-beginning 0) (match-end 0))))))
 683
 684 (defun diacritic-compose-string (string)
 685   "Compose diacritic characters in STRING and return the resulting string."
 686   (let ((idx 0))
 687     (while (setq idx (string-match diacritic-composition-pattern string idx))
 688       (if (= (char-syntax (aref string idx)) ?w)
 689           (compose-string string idx (match-end 0)))
 690       (setq idx (match-end 0))))
 691   string)
 692
 693 (defun diacritic-compose-buffer ()
 694   "Compose diacritic characters in the current buffer."
 695   (interactive)
 696   (diacritic-compose-region (point-min) (point-max)))
 697
 698 (defun diacritic-composition-function (pos &optional string)
 699   "Compose diacritic text around POS.
 700 Optional 2nd argument STRING, if non-nil, is a string containing text
 701 to compose.
 702
 703 The return value is the end position of composed characters,
 704 or nil if no characters are composed."
 705   (setq pos (1- pos))
 706   (if string
 707       (if (>= pos 0)
 708           (let ((ch (aref string pos))
 709                 start end components ch composition)
 710             (when (= (char-syntax ch) ?w)
 711               (setq start pos
 712                     end (length string)
 713                     components (list ch)
 714                     pos (1+ pos))
 715               (while (and
 716                       (< pos end)
 717                       (setq ch (aref string pos)
 718                             composition
 719                             (get-char-code-property ch
 720                                                     'diacritic-composition)))
 721                 (setq components (cons ch (cons composition components))
 722                       pos (1+ pos)))
 723               (compose-string string start pos (nreverse components))
 724               pos)))
 725     (if (>= pos (point-min))
 726         (let ((ch (char-after pos))
 727               start end components composition)
 728           (when (= (char-syntax ch) ?w)
 729             (setq start pos
 730                   end (point-max)
 731                   components (list ch)
 732                   pos (1+ pos))
 733             (while (and
 734                     (< pos end)
 735                     (setq ch (char-after pos)
 736                           composition
 737                           (get-char-code-property ch 'diacritic-composition)))
 738               (setq components (cons ch (cons composition components))
 739                     pos (1+ pos)))
 740             (compose-region start pos (nreverse components))
 741             pos)))))
 742
 743 (provide 'european)
 744
 745 ;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
 746 ;;; european.el ends here