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 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 (set-language-info-alist
  36  "Latin-1" '((charset iso-8859-1)
  37              (coding-system iso-latin-1)
  38              (coding-priority iso-latin-1)
  39              (nonascii-translation . iso-8859-1)
  40              (unibyte-syntax . "latin-1")
  41              (unibyte-display . iso-latin-1)
  42              (input-method . "latin-1-prefix")
  43              (sample-text
  44               . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
  45              (documentation . "\
  46 This language environment is a generic one for the Latin-1 (ISO-8859-1)
  47 character set which supports the following European languages:
  48  Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
  49  Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
  50  German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
  51  Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
  52  Scottish Gaelic, Spanish, and Swedish.
  53 We also have specific language environments for the following languages:
  54   For Dutch, \"Dutch\".
  55   For German, \"German\".
  56   For Spanish, \"Spanish\".
  57   For French, \"French\".
  58
  59 Latin-1 also covers several written languages outside Europe, including
  60 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
  61  '("European"))
  62
  63 \f
  64 ;; Latin-2 (ISO-8859-2)
  65
  66 (define-coding-system 'iso-latin-2
  67    "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
  68   :coding-type 'charset
  69   :mnemonic ?2
  70   :charset-list '(iso-8859-2)
  71   :mime-charset 'iso-8859-2)
  72
  73 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
  74 (define-coding-system-alias 'latin-2 'iso-latin-2)
  75
  76 (set-language-info-alist
  77  "Latin-2" '((charset iso-8859-2)
  78              (coding-system iso-latin-2)
  79              (coding-priority iso-latin-2)
  80              (nonascii-translation . iso-8859-2)
  81              (unibyte-syntax . "latin-2")
  82              (unibyte-display . iso-latin-2)
  83              (input-method . "latin-2-prefix")
  84              (documentation . "\
  85 This language environment is a generic one for the Latin-2 (ISO-8859-2)
  86 character set which supports the following languages:
  87  Albanian, Czech, English, German, Hungarian, Polish, Romanian,
  88  Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
  89  and Swedish.
  90 We also have specific language environments for the following languages:
  91   For Czech, \"Czech\".
  92   For Romanian, \"Romanian\".
  93   For Slovak, \"Slovak\"."))
  94  '("European"))
  95
  96 \f
  97 ;; Latin-3 (ISO-8859-3)
  98
  99 (define-coding-system 'iso-latin-3
 100   "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
 101   :coding-type 'charset
 102   :mnemonic ?3
 103   :charset-list '(iso-8859-3)
 104   :mime-charset 'iso-8859-3)
 105
 106 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
 107 (define-coding-system-alias 'latin-3 'iso-latin-3)
 108
 109 (set-language-info-alist
 110  "Latin-3" '((charset iso-8859-3)
 111              (coding-system iso-latin-3)
 112              (coding-priority iso-latin-3)
 113              (nonascii-translation . iso-8859-3)
 114              (unibyte-syntax . "latin-3")
 115              (unibyte-display . iso-latin-3)
 116              (input-method . "latin-3-prefix")
 117              (documentation . "\
 118 These languages are supported with the Latin-3 (ISO-8859-3) character set:
 119  Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
 120  German, Italian, Maltese, Spanish, and Turkish."))
 121  '("European"))
 122
 123 \f
 124 ;; Latin-4 (ISO-8859-4)
 125
 126 (define-coding-system 'iso-latin-4
 127   "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
 128   :coding-type 'charset
 129   :mnemonic ?4
 130   :charset-list '(iso-8859-4)
 131   :mime-charset 'iso-8859-4)
 132
 133 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
 134 (define-coding-system-alias 'latin-4 'iso-latin-4)
 135
 136 (set-language-info-alist
 137  "Latin-4" '((charset iso-8859-4)
 138              (coding-system iso-8859-4)
 139              (coding-priority iso-8859-4)
 140              (nonascii-translation . iso-8859-4)
 141              (unibyte-syntax . "latin-4")
 142              (unibyte-display . iso-8859-4)
 143              (input-method . "latin-4-postfix")
 144              (documentation . "\
 145 These languages are supported with the Latin-4 (ISO-8859-4) character set:
 146  Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
 147  Latvian, Lithuanian, and Norwegian."))
 148  '("European"))
 149
 150 \f
 151 ;; Latin-5 (ISO-8859-9)
 152
 153 (define-coding-system 'iso-latin-5
 154   "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
 155   :coding-type 'charset
 156   :mnemonic ?9
 157   :charset-list '(iso-8859-9)
 158   :mime-charset 'iso-8859-9)
 159
 160 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
 161 (define-coding-system-alias 'latin-5 'iso-latin-5)
 162
 163 (set-language-info-alist
 164  "Latin-5" '((charset iso-8859-9)
 165              (coding-system iso-latin-5)
 166              (coding-priority iso-latin-5)
 167              (nonascii-translation . iso-8859-9)
 168              (unibyte-syntax . "latin-5")
 169              (unibyte-display . iso-latin-5)
 170              (input-method . "latin-5-postfix")
 171              (documentation . "Support for Turkish language."))
 172  '("European"))
 173
 174 \f
 175 ;; Latin-8 (ISO-8859-14)
 176
 177 (define-coding-system 'iso-latin-8
 178   "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
 179   :coding-type 'charset
 180   ;; `W' for `Welsh', since `C' for `Celtic' is taken.
 181   :mnemonic ?W
 182   :charset-list '(iso-8859-14)
 183   :mime-charset 'iso-8859-14)
 184
 185 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
 186 (define-coding-system-alias 'latin-8 'iso-latin-8)
 187
 188 (set-language-info-alist
 189  "Latin-8" '((charset iso-8859-14)
 190              (coding-system iso-latin-8)
 191              (coding-priority iso-latin-8)
 192              (nonascii-translation . iso-8859-14)
 193              (unibyte-syntax . "latin-8")
 194              (unibyte-display . iso-latin-8)
 195              (input-method . "latin-8-prefix")
 196              ;; Fixme: Welsh/Ga{e}lic greetings
 197              (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
 198              (documentation . "\
 199 This language environment is a generic one for the Latin-8 (ISO-8859-14)
 200 character set which supports the Celtic languages, including those not
 201 covered by other ISO-8859 character sets:
 202  Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
 203  '("European"))
 204 \f
 205 ;; Latin-9 (ISO-8859-15)
 206
 207 (define-coding-system 'iso-latin-9
 208   "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
 209   :coding-type 'charset
 210   ;; `0' for `Latin-0'
 211   :mnemonic ?0
 212   :charset-list '(iso-8859-15)
 213   :mime-charset 'iso-8859-15)
 214
 215 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
 216 (define-coding-system-alias 'latin-9 'iso-latin-9)
 217 (define-coding-system-alias 'latin-0 'iso-latin-9)
 218
 219 (set-language-info-alist
 220  "Latin-9" '((charset iso-8859-15)
 221              (coding-system iso-latin-9)
 222              (coding-priority iso-latin-9)
 223              (nonascii-translation . iso-8859-15)
 224              (unibyte-syntax . "latin-9")
 225              (unibyte-display . iso-latin-9)
 226              (input-method . "latin-9-prefix")
 227              (sample-text
 228               . "AVE. \e,B)9.>\e,b<=\e,_/\e(B \e,b$\e(B")
 229              (documentation . "\
 230 This language environment is a generic one for the Latin-9 (ISO-8859-15)
 231 character set which supports the same languages as Latin-1 with the
 232 addition of the Euro sign and some additional French and Finnish letters.
 233 Latin-9 is sometimes nicknamed `Latin-0'."))
 234  '("European"))
 235 \f
 236 (define-coding-system 'windows-1252
 237   "windows-1252 8-bit encoding for Cyrillic (MIME: WINDOWS-1252)"
 238   :coding-type 'charset
 239   :mnemonic ?*
 240   :charset-list '(windows-1252)
 241   :mime-charset 'windows-1252)
 242 (define-coding-system-alias 'cp1252 'windows-1252)
 243 \f
 244 (set-language-info-alist
 245  "German" '((tutorial . "TUTORIAL.de")
 246             (charset iso-8859-1)
 247             (coding-system iso-latin-1)
 248             (coding-priority iso-latin-1)
 249             (nonascii-translation . iso-8859-1)
 250             (input-method . "german-postfix")
 251             (unibyte-syntax . "latin-1")
 252             (unibyte-display . iso-latin-1)
 253             (sample-text . "\
 254 German (Deutsch Nord)   Guten Tag
 255 German (Deutsch S\e,A|\e(Bd)      Gr\e,A|_\e(B Gott")
 256             (documentation . "\
 257 This language environment is almost the same as Latin-1,
 258 but sets the default input method to \"german-postfix\".
 259 Additionally, it selects the German tutorial."))
 260  '("European"))
 261
 262 (set-language-info-alist
 263  "French" '((tutorial . "TUTORIAL.fr")
 264             (charset iso-8859-1)
 265             (coding-system iso-latin-1)
 266             (coding-priority iso-latin-1)
 267             (nonascii-translation . iso-8859-1)
 268             (unibyte-syntax . "latin-1")
 269             (unibyte-display . iso-latin-1)
 270             (input-method . "latin-1-prefix")
 271             (sample-text . "French (Fran\e,Ag\e(Bais)     Bonjour, Salut")
 272             (documentation . "\
 273 This language environment is almost the same as Latin-1,
 274 but it selects the French tutorial."))
 275  '("European"))
 276
 277 (set-language-info-alist
 278  "Slovenian" '((charset iso-8859-2)
 279               (coding-system . (iso-8859-2))
 280               (coding-priority . (iso-8859-2))
 281               (nonascii-translation . iso-8859-2)
 282               (input-method . "latin-2-postfix")
 283               (unibyte-syntax . "latin-2")
 284               (unibyte-display . iso-8859-2)
 285               (tutorial . "TUTORIAL.sl")
 286               (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
 287               (documentation . t))
 288  '("European"))
 289
 290 (set-language-info-alist
 291  "Spanish" '((tutorial . "TUTORIAL.es")
 292             (charset iso-8859-1)
 293             (coding-system iso-latin-1)
 294             (coding-priority iso-latin-1)
 295             (nonascii-translation . iso-8859-1)
 296             (input-method . "spanish-postfix")
 297             (unibyte-syntax . "latin-1")
 298             (unibyte-display . iso-latin-1)
 299             (sample-text . "Spanish (Espa\e,Aq\e(Bol)     \e,A!\e(BHola!")
 300             (documentation . "\
 301 This language environment is almost the same as Latin-1,
 302 but it sets the default input method to \"spanish-postfix\",
 303 and it selects the Spanish tutorial."))
 304  '("European"))
 305
 306 (set-language-info-alist
 307  "Dutch" '((tutorial . "TUTORIAL.nl")
 308            (charset iso-8859-1)
 309            (coding-system iso-latin-1)
 310            (coding-priority iso-latin-1)
 311            (nonascii-translation . iso-8859-1)
 312            (unibyte-syntax . "latin-1")
 313            (unibyte-display . iso-latin-1)
 314            (sample-text . "Er is een aantal manieren waarop je dit kan doen")
 315            (documentation . "\
 316 This language environment is almost the same as Latin-1,
 317 but it selects the Dutch tutorial."))
 318  '("European"))
 319
 320 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used.  But,
 321 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
 322 ;; was used for Turkish.  Those who use Latin-3 for Turkish should use
 323 ;; "Latin-3" language environment.
 324
 325 (set-language-info-alist
 326  "Turkish" '((charset iso-8859-9)
 327              (coding-system iso-latin-5)
 328              (coding-priority iso-latin-5)
 329              (nonascii-translation . iso-8859-9)
 330              (unibyte-syntax . "latin-5")
 331              (unibyte-display . iso-latin-5)
 332              (input-method . "turkish-postfix")
 333              (sample-text . "Turkish (T\e,A|\e(Brk\e,Ag\e(Be)       Merhaba")
 334              (documentation . t)))
 335
 336 ;; Polish ISO 8859-2 environment.
 337 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
 338 ;; Keywords: multilingual, Polish
 339
 340 (set-language-info-alist
 341  "Polish" '((charset . (iso-8859-2))
 342            (coding-system . (iso-8859-2))
 343            (coding-priority . (iso-8859-2))
 344            (nonascii-translation . iso-8859-2)
 345            (input-method . "polish-slash")
 346            (unibyte-syntax . "latin-2")
 347            (unibyte-display . iso-8859-2)
 348            (tutorial . "TUTORIAL.pl")
 349            (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")
 350            (documentation . t))
 351  '("European"))
 352
 353 (set-language-info-alist
 354  "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
 355            (coding-priority utf-8 latin-8)
 356            (nonascii-translation . iso-8859-14)
 357            (input-method . "welsh")
 358            (documentation . "Support for Welsh, using Unicode."))
 359  '("European"))
 360
 361 (set-language-info-alist
 362  "Latin-7" `((coding-system latin-7)
 363              (coding-priority latin-7)
 364              (nonascii-translation . iso-8859-13)
 365              ;; Fixme: input-method
 366              (features code-pages)
 367              (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
 368  '("European"))
 369
 370 (set-language-info-alist
 371  "Lithuanian" `((coding-system latin-7)
 372                 (coding-priority latin-7)
 373                 (nonascii-translation . iso-8859-13)
 374                 (input-method . "lithuanian-keyboard")
 375                 (features code-pages)
 376                 (documentation . "Support for Lithuanian."))
 377  '("European"))
 378
 379 (set-language-info-alist
 380  "Latvian" `((coding-system latin-7)
 381              (coding-priority latin-7)
 382              (nonascii-translation . iso-8859-13)
 383              (input-method . "latvian-keyboard")
 384              (features code-pages)
 385              (documentation . "Support for Latvian."))
 386  '("European"))
 387
 388 \f
 389 (define-coding-system 'mac-roman
 390   "Mac Roman Encoding (MIME:MACINTOSH)."
 391   :coding-type 'charset
 392   :mnemonic ?M
 393   :charset-list '(mac-roman)
 394   ;; per IANA, rfc1345
 395   :mime-charset 'macintosh)
 396
 397 (defconst diacritic-composition-pattern "\\C^\\c^+")
 398
 399 (defun diacritic-compose-region (beg end)
 400   "Compose diacritic characters in the region.
 401 When called from a program, expects two arguments,
 402 positions (integers or markers) specifying the region."
 403   (interactive "r")
 404   (save-restriction
 405     (narrow-to-region beg end)
 406     (goto-char (point-min))
 407     (while (re-search-forward diacritic-composition-pattern nil t)
 408       (compose-region (match-beginning 0) (match-end 0)))))
 409
 410 (defun diacritic-compose-string (string)
 411   "Compose diacritic characters in STRING and return the resulting string."
 412   (let ((idx 0))
 413     (while (setq idx (string-match diacritic-composition-pattern string idx))
 414       (compose-string string idx (match-end 0))
 415       (setq idx (match-end 0))))
 416   string)
 417
 418 (defun diacritic-compose-buffer ()
 419   "Compose diacritic characters in the current buffer."
 420   (interactive)
 421   (diacritic-compose-region (point-min) (point-max)))
 422
 423 (defun diacritic-post-read-conversion (len)
 424   (diacritic-compose-region (point) (+ (point) len))
 425   len)
 426
 427 (defun diacritic-composition-function (from to pattern &optional string)
 428   "Compose diacritic text in the region FROM and TO.
 429 The text matches the regular expression PATTERN.
 430 Optional 4th argument STRING, if non-nil, is a string containing text
 431 to compose.
 432
 433 The return value is number of composed characters."
 434   (if (< (1+ from) to)
 435       (prog1 (- to from)
 436         (if string
 437             (compose-string string from to)
 438           (compose-region from to))
 439         (- to from))))
 440
 441 ;; Register a function to compose Unicode diacrtics and marks.
 442 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
 443   (let ((c #x300))
 444     (while (<= c #x362)
 445       (aset composition-function-table (decode-char 'unicode c) patterns)
 446       (setq c (1+ c)))
 447     (setq c #x20d0)
 448     (while (<= c #x20e3)
 449       (aset composition-function-table (decode-char 'unicode c) patterns)
 450       (setq c (1+ c)))))
 451
 452 (provide 'european)
 453
 454 ;;; european.el ends here