1 ;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
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.
7 ;; Keywords: multilingual, European
9 ;; This file is part of GNU Emacs.
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)
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.
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.
28 ;; For European scripts, character sets ISO8859-1,2,3,4,9,14,15 are
33 ;; Latin-1 (ISO-8859-1)
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")
44 . "Hello, Hej, Tere, Hei, Bonjour, Gr
\e,A|_
\e(B Gott, Ciao,
\e,A!
\e(BHola!")
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:
55 For German, \"German\".
56 For Spanish, \"Spanish\".
57 For French, \"French\".
59 Latin-1 also covers several written languages outside Europe, including
60 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
64 ;; Latin-2 (ISO-8859-2)
66 (define-coding-system 'iso-latin-2
67 "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
70 :charset-list '(iso-8859-2)
71 :mime-charset 'iso-8859-2)
73 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
74 (define-coding-system-alias 'latin-2 'iso-latin-2)
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")
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),
90 We also have specific language environments for the following languages:
92 For Romanian, \"Romanian\".
93 For Slovak, \"Slovak\"."))
97 ;; Latin-3 (ISO-8859-3)
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
103 :charset-list '(iso-8859-3)
104 :mime-charset 'iso-8859-3)
106 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
107 (define-coding-system-alias 'latin-3 'iso-latin-3)
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")
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."))
124 ;; Latin-4 (ISO-8859-4)
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
130 :charset-list '(iso-8859-4)
131 :mime-charset 'iso-8859-4)
133 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
134 (define-coding-system-alias 'latin-4 'iso-latin-4)
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")
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."))
151 ;; Latin-5 (ISO-8859-9)
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
157 :charset-list '(iso-8859-9)
158 :mime-charset 'iso-8859-9)
160 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
161 (define-coding-system-alias 'latin-5 'iso-latin-5)
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."))
175 ;; Latin-8 (ISO-8859-14)
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.
182 :charset-list '(iso-8859-14)
183 :mime-charset 'iso-8859-14)
185 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
186 (define-coding-system-alias 'latin-8 'iso-latin-8)
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")
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)."))
205 ;; Latin-9 (ISO-8859-15)
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
212 :charset-list '(iso-8859-15)
213 :mime-charset 'iso-8859-15)
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)
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")
228 . "AVE.
\e,B)9.>
\e,b<=
\e,_/
\e(B
\e,b$
\e(B")
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'."))
236 (set-language-info-alist
237 "German" '((tutorial . "TUTORIAL.de")
239 (coding-system iso-latin-1)
240 (coding-priority iso-latin-1)
241 (nonascii-translation . iso-8859-1)
242 (input-method . "german-postfix")
243 (unibyte-syntax . "latin-1")
244 (unibyte-display . iso-latin-1)
246 German (Deutsch Nord) Guten Tag
247 German (Deutsch S
\e,A|
\e(Bd) Gr
\e,A|_
\e(B Gott")
249 This language environment is almost the same as Latin-1,
250 but sets the default input method to \"german-postfix\".
251 Additionally, it selects the German tutorial."))
254 (set-language-info-alist
255 "French" '((tutorial . "TUTORIAL.fr")
257 (coding-system iso-latin-1)
258 (coding-priority iso-latin-1)
259 (nonascii-translation . iso-8859-1)
260 (unibyte-syntax . "latin-1")
261 (unibyte-display . iso-latin-1)
262 (input-method . "latin-1-prefix")
263 (sample-text . "French (Fran
\e,Ag
\e(Bais) Bonjour, Salut")
265 This language environment is almost the same as Latin-1,
266 but it selects the French tutorial."))
269 (set-language-info-alist
270 "Slovenian" '((charset iso-8859-2)
271 (coding-system . (iso-8859-2))
272 (coding-priority . (iso-8859-2))
273 (nonascii-translation . iso-8859-2)
274 (input-method . "latin-2-postfix")
275 (unibyte-syntax . "latin-2")
276 (unibyte-display . iso-8859-2)
277 (tutorial . "TUTORIAL.sl")
278 (sample-text . "
\e,B.
\e(Belimo vam uspe
\e,B9
\e(Ben dan!")
282 (set-language-info-alist
283 "Spanish" '((tutorial . "TUTORIAL.es")
285 (coding-system iso-latin-1)
286 (coding-priority iso-latin-1)
287 (nonascii-translation . iso-8859-1)
288 (input-method . "spanish-postfix")
289 (unibyte-syntax . "latin-1")
290 (unibyte-display . iso-latin-1)
291 (sample-text . "Spanish (Espa
\e,Aq
\e(Bol)
\e,A!
\e(BHola!")
293 This language environment is almost the same as Latin-1,
294 but it sets the default input method to \"spanish-postfix\",
295 and it selects the Spanish tutorial."))
298 (set-language-info-alist
299 "Dutch" '((tutorial . "TUTORIAL.nl")
301 (coding-system iso-latin-1)
302 (coding-priority iso-latin-1)
303 (nonascii-translation . iso-8859-1)
304 (unibyte-syntax . "latin-1")
305 (unibyte-display . iso-latin-1)
306 (sample-text . "Er is een aantal manieren waarop je dit kan doen")
308 This language environment is almost the same as Latin-1,
309 but it selects the Dutch tutorial."))
312 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
313 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
314 ;; was used for Turkish. Those who use Latin-3 for Turkish should use
315 ;; "Latin-3" language environment.
317 (set-language-info-alist
318 "Turkish" '((charset iso-8859-9)
319 (coding-system iso-latin-5)
320 (coding-priority iso-latin-5)
321 (nonascii-translation . iso-8859-9)
322 (unibyte-syntax . "latin-5")
323 (unibyte-display . iso-latin-5)
324 (input-method . "turkish-postfix")
325 (sample-text . "Turkish (T
\e,A|
\e(Brk
\e,Ag
\e(Be) Merhaba")
326 (documentation . t)))
328 ;; Polish ISO 8859-2 environment.
329 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
330 ;; Keywords: multilingual, Polish
332 (set-language-info-alist
333 "Polish" '((charset . (iso-8859-2))
334 (coding-system . (iso-8859-2))
335 (coding-priority . (iso-8859-2))
336 (nonascii-translation . iso-8859-2)
337 (input-method . "polish-slash")
338 (unibyte-syntax . "latin-2")
339 (unibyte-display . iso-8859-2)
340 (tutorial . "TUTORIAL.pl")
341 (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")
345 (set-language-info-alist
346 "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
347 (coding-priority utf-8 latin-8)
348 (nonascii-translation . iso-8859-14)
349 (input-method . "welsh")
350 (documentation . "Support for Welsh, using Unicode."))
353 (set-language-info-alist
354 "Latin-7" `((coding-system latin-7)
355 (coding-priority latin-7)
356 (nonascii-translation . iso-8859-13)
357 ;; Fixme: input-method
358 (features code-pages)
359 (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
362 (set-language-info-alist
363 "Lithuanian" `((coding-system latin-7)
364 (coding-priority latin-7)
365 (nonascii-translation . iso-8859-13)
366 (input-method . "lithuanian-keyboard")
367 (features code-pages)
368 (documentation . "Support for Lithuanian."))
371 (set-language-info-alist
372 "Latvian" `((coding-system latin-7)
373 (coding-priority latin-7)
374 (nonascii-translation . iso-8859-13)
375 (input-method . "latvian-keyboard")
376 (features code-pages)
377 (documentation . "Support for Latvian."))
381 (define-coding-system 'mac-roman
382 "Mac Roman Encoding (MIME:MACINTOSH)."
383 :coding-type 'charset
385 :charset-list '(mac-roman)
387 :mime-charset 'macintosh)
389 (defconst diacritic-composition-pattern "\\C^\\c^+")
391 (defun diacritic-compose-region (beg end)
392 "Compose diacritic characters in the region.
393 When called from a program, expects two arguments,
394 positions (integers or markers) specifying the region."
397 (narrow-to-region beg end)
398 (goto-char (point-min))
399 (while (re-search-forward diacritic-composition-pattern nil t)
400 (compose-region (match-beginning 0) (match-end 0)))))
402 (defun diacritic-compose-string (string)
403 "Compose diacritic characters in STRING and return the resulting string."
405 (while (setq idx (string-match diacritic-composition-pattern string idx))
406 (compose-string string idx (match-end 0))
407 (setq idx (match-end 0))))
410 (defun diacritic-compose-buffer ()
411 "Compose diacritic characters in the current buffer."
413 (diacritic-compose-region (point-min) (point-max)))
415 (defun diacritic-post-read-conversion (len)
416 (diacritic-compose-region (point) (+ (point) len))
419 (defun diacritic-composition-function (from to pattern &optional string)
420 "Compose diacritic text in the region FROM and TO.
421 The text matches the regular expression PATTERN.
422 Optional 4th argument STRING, if non-nil, is a string containing text
425 The return value is number of composed characters."
429 (compose-string string from to)
430 (compose-region from to))
433 ;; Register a function to compose Unicode diacrtics and marks.
434 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
437 (aset composition-function-table (decode-char 'unicode c) patterns)
441 (aset composition-function-table (decode-char 'unicode c) patterns)
446 ;;; european.el ends here