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 ISO8859-1,2,3,4,9,10,13,14,15,
29 ;; windows-1250,2,4,7, mac-roman, adobe-standard-encoding, cp850 and
30 ;; next are supported.
34 ;; Latin-1 (ISO-8859-1)
36 (set-language-info-alist
37 "Latin-1" '((charset iso-8859-1)
38 (coding-system iso-latin-1 iso-latin-9 windows-1252)
39 (coding-priority iso-latin-1)
40 (nonascii-translation . iso-8859-1)
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 windows-1250)
79 (coding-priority iso-latin-2)
80 (nonascii-translation . iso-8859-2)
81 (unibyte-display . iso-latin-2)
82 (input-method . "latin-2-prefix")
84 This language environment is a generic one for the Latin-2 (ISO-8859-2)
85 character set which supports the following languages:
86 Albanian, Czech, English, German, Hungarian, Polish, Romanian,
87 Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
89 We also have specific language environments for the following languages:
91 For Polish, \"Polish\".
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-display . iso-latin-3)
115 (input-method . "latin-3-prefix")
117 These languages are supported with the Latin-3 (ISO-8859-3) character set:
118 Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
119 German, Italian, Maltese, Spanish, and Turkish."))
123 ;; Latin-4 (ISO-8859-4)
125 (define-coding-system 'iso-latin-4
126 "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
127 :coding-type 'charset
129 :charset-list '(iso-8859-4)
130 :mime-charset 'iso-8859-4)
132 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
133 (define-coding-system-alias 'latin-4 'iso-latin-4)
135 (set-language-info-alist
136 "Latin-4" '((charset iso-8859-4)
137 (coding-system iso-8859-4)
138 (coding-priority iso-8859-4)
139 (nonascii-translation . iso-8859-4)
140 (unibyte-display . iso-8859-4)
141 (input-method . "latin-4-postfix")
143 These languages are supported with the Latin-4 (ISO-8859-4) character set:
144 Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
145 Latvian, Lithuanian, and Norwegian."))
149 ;; Latin-5 (ISO-8859-9)
151 (define-coding-system 'iso-latin-5
152 "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
153 :coding-type 'charset
155 :charset-list '(iso-8859-9)
156 :mime-charset 'iso-8859-9)
158 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
159 (define-coding-system-alias 'latin-5 'iso-latin-5)
161 (set-language-info-alist
162 "Latin-5" '((charset iso-8859-9)
163 (coding-system iso-latin-5)
164 (coding-priority iso-latin-5)
165 (nonascii-translation . iso-8859-9)
166 (unibyte-display . iso-latin-5)
167 (input-method . "latin-5-postfix")
168 (documentation . "Support for Latin-5.\
169 See also the Turkish environment."))
173 ;; Latin-6 (ISO-8859-10)
175 (define-coding-system 'iso-latin-6
176 "ISO 2022 based 8-bit encoding for Latin-6 (MIME:ISO-8859-10)."
177 :coding-type 'charset
179 :charset-list '(iso-8859-10)
180 :mime-charset 'iso-8859-10)
182 (define-coding-system-alias 'iso-8859-10 'iso-latin-6)
183 (define-coding-system-alias 'latin-6 'iso-latin-6)
185 (set-language-info-alist
186 "Latin-6" '((charset iso-8859-10)
187 (coding-system iso-latin-6)
188 (coding-priority iso-latin-6)
189 (nonascii-translation . iso-8859-10)
190 (unibyte-display . iso-latin-6)
191 ;; Fixme: input method.
192 (documentation . "Support for generic Latin-6 (Northern European)."))
196 ;; Latin-7 (ISO-8859-13)
198 (define-coding-system 'iso-latin-7
199 "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
200 :coding-type 'charset
202 :charset-list '(iso-8859-13)
203 :mime-charset 'iso-8859-13)
205 (define-coding-system-alias 'iso-8859-13 'iso-latin-7)
206 (define-coding-system-alias 'latin-7 'iso-latin-7)
208 (set-language-info-alist
209 "Latin-7" '((charset iso-8859-13)
210 (coding-system iso-latin-7)
211 (coding-priority iso-latin-7)
212 (nonascii-translation . iso-8859-13)
213 (unibyte-display . iso-latin-7)
214 ;; Fixme: input method.
215 (documentation . "Support for generic Latin-7 (Baltic Rim)."))
218 ;; Latin-8 (ISO-8859-14)
220 (define-coding-system 'iso-latin-8
221 "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
222 :coding-type 'charset
223 ;; `W' for `Welsh', since `C' for `Celtic' is taken.
225 :charset-list '(iso-8859-14)
226 :mime-charset 'iso-8859-14)
228 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
229 (define-coding-system-alias 'latin-8 'iso-latin-8)
231 (set-language-info-alist
232 "Latin-8" '((charset iso-8859-14)
233 (coding-system iso-latin-8)
234 (coding-priority iso-latin-8)
235 (nonascii-translation . iso-8859-14)
236 (unibyte-display . iso-latin-8)
237 (input-method . "latin-8-prefix")
238 ;; Fixme: Welsh/Ga{e}lic greetings
239 (sample-text . "
\e,_"
\e(B
\e,_p
\e(B
\e,_^
\e(B")
241 This language environment is a generic one for the Latin-8 (ISO-8859-14)
242 character set which supports the Celtic languages, including those not
243 covered by other ISO-8859 character sets:
244 Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
247 ;; Latin-9 (ISO-8859-15)
249 (define-coding-system 'iso-latin-9
250 "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
251 :coding-type 'charset
254 :charset-list '(iso-8859-15)
255 :mime-charset 'iso-8859-15)
257 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
258 (define-coding-system-alias 'latin-9 'iso-latin-9)
259 (define-coding-system-alias 'latin-0 'iso-latin-9)
261 (set-language-info-alist
262 "Latin-9" '((charset iso-8859-15)
263 (coding-system iso-latin-9)
264 (coding-priority iso-latin-9)
265 (nonascii-translation . iso-8859-15)
266 (unibyte-display . iso-latin-9)
267 (input-method . "latin-9-prefix")
269 . "AVE.
\e,B)9.>
\e,b<=
\e,_/
\e(B
\e,b$
\e(B")
271 This language environment is a generic one for the Latin-9 (ISO-8859-15)
272 character set which supports the same languages as Latin-1 with the
273 addition of the Euro sign and some additional French and Finnish letters.
274 Latin-9 is sometimes nicknamed `Latin-0'."))
277 (define-coding-system 'iso-latin-7
278 "ISO 2022 based 8-bit encoding for Latin-7 (MIME:ISO-8859-13)."
279 :coding-type 'charset
282 :charset-list '(iso-8859-13)
283 :mime-charset 'iso-8859-13)
285 (define-coding-system-alias 'iso-8859-13 'iso-latin-7)
286 (define-coding-system-alias 'latin-7 'iso-latin-7)
288 (define-coding-system 'windows-1250
289 "windows-1250 (Central European) encoding (MIME: WINDOWS-1250)"
290 :coding-type 'charset
292 :charset-list '(windows-1250)
293 :mime-charset 'windows-1250)
294 (define-coding-system-alias 'cp1250 'windows-1250)
296 (define-coding-system 'windows-1252
297 "windows-1252 (Western European) encoding (MIME: WINDOWS-1252)"
298 :coding-type 'charset
300 :charset-list '(windows-1252)
301 :mime-charset 'windows-1252)
302 (define-coding-system-alias 'cp1252 'windows-1252)
304 (define-coding-system 'windows-1254
305 "windows-1254 (Turkish) encoding (MIME: WINDOWS-1254)"
306 :coding-type 'charset
308 :charset-list '(windows-1254)
309 :mime-charset 'windows-1254)
310 (define-coding-system-alias 'cp1254 'windows-1254)
312 (define-coding-system 'windows-1257
313 "windows-1257 (Baltic) encoding (MIME: WINDOWS-1257)"
314 :coding-type 'charset
316 :charset-list '(windows-1257)
317 :mime-charset 'windows-1257)
318 (define-coding-system-alias 'cp1257 'windows-1257)
320 (define-coding-system 'cp850
321 "DOS codepage 850 (Western European)"
322 :coding-type 'charset
324 :charset-list '(cp850)
325 :mime-charset 'cp850)
326 (define-coding-system-alias 'ibm850 'cp850)
328 (define-coding-system 'cp852
329 "DOS codepage 852 (Slavic)"
330 :coding-type 'charset
332 :charset-list '(cp852)
333 :mime-charset 'cp852)
334 (define-coding-system-alias 'ibm852 'cp852)
336 (define-coding-system 'cp857
337 "DOS codepage 857 (Turkish)"
338 :coding-type 'charset
340 :charset-list '(cp857)
341 :mime-charset 'cp857)
342 (define-coding-system-alias 'ibm857 'cp857)
344 (define-coding-system 'cp858
345 "Codepage 858 (Multilingual Latin I + Euro)"
346 :coding-type 'charset
348 :charset-list '(cp858)
349 :mime-charset 'cp858)
351 (define-coding-system 'cp860
352 "DOS codepage 860 (Portuguese)"
353 :coding-type 'charset
355 :charset-list '(cp860)
356 :mime-charset 'cp860)
357 (define-coding-system-alias 'ibm860 'cp860)
359 (define-coding-system 'cp861
360 "DOS codepage 861 (Icelandic)"
361 :coding-type 'charset
363 :charset-list '(cp861)
364 :mime-charset 'cp861)
365 (define-coding-system-alias 'ibm861 'cp861)
367 (define-coding-system 'cp863
368 "DOS codepage 863 (French Canadian)"
369 :coding-type 'charset
371 :charset-list '(cp863)
372 :mime-charset 'cp863)
373 (define-coding-system-alias 'ibm863 'cp863)
375 (define-coding-system 'cp865
376 "DOS codepage 865 (Norwegian/Danish)"
377 :coding-type 'charset
379 :charset-list '(cp865)
380 :mime-charset 'cp865)
381 (define-coding-system-alias 'ibm865 'cp865)
383 (define-coding-system 'cp437
385 :coding-type 'charset
387 :charset-list '(cp437)
388 :mime-charset 'cp437)
389 (define-coding-system-alias 'ibm437 'cp437)
391 (set-language-info-alist
392 "German" '((tutorial . "TUTORIAL.de")
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-display . iso-latin-1)
400 German (Deutsch Nord) Guten Tag
401 German (Deutsch S
\e,A|
\e(Bd) Gr
\e,A|_
\e(B Gott")
403 This language environment is almost the same as Latin-1,
404 but sets the default input method to \"german-postfix\".
405 Additionally, it selects the German tutorial."))
408 (set-language-info-alist
409 "French" '((tutorial . "TUTORIAL.fr")
411 (coding-system iso-latin-1 iso-latin-9)
412 (coding-priority iso-latin-1)
413 (nonascii-translation . iso-8859-1)
414 (unibyte-display . iso-latin-1)
415 (input-method . "latin-1-prefix")
416 (sample-text . "French (Fran
\e,Ag
\e(Bais) Bonjour, Salut")
418 This language environment is almost the same as Latin-1,
419 but it selects the French tutorial."))
422 (set-language-info-alist
423 "Slovenian" '((charset iso-8859-2)
424 (coding-system . (iso-8859-2 windows-1250))
425 (coding-priority . (iso-8859-2))
426 (nonascii-translation . iso-8859-2)
427 (input-method . "latin-2-postfix")
428 (unibyte-display . iso-8859-2)
429 (tutorial . "TUTORIAL.sl")
430 (sample-text . "
\e,B.
\e(Belimo vam uspe
\e,B9
\e(Ben dan!")
434 (set-language-info-alist
435 "Spanish" '((tutorial . "TUTORIAL.es")
437 (coding-system iso-latin-1 iso-latin-9)
438 (coding-priority iso-latin-1)
439 (nonascii-translation . iso-8859-1)
440 (input-method . "spanish-postfix")
441 (unibyte-display . iso-latin-1)
442 (sample-text . "Spanish (Espa
\e,Aq
\e(Bol)
\e,A!
\e(BHola!")
444 This language environment is almost the same as Latin-1,
445 but it sets the default input method to \"spanish-postfix\",
446 and it selects the Spanish tutorial."))
449 (set-language-info-alist
450 "Dutch" '((tutorial . "TUTORIAL.nl")
452 (coding-system iso-latin-1 iso-latin-9)
453 (coding-priority iso-latin-1)
454 (nonascii-translation . iso-8859-1)
455 (unibyte-display . iso-latin-1)
456 (input-method . "dutch")
457 (sample-text . "Er is een aantal manieren waarop je dit kan doen")
459 This language environment is almost the same as Latin-1,
460 but it selects the Dutch tutorial and input method."))
463 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
464 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
465 ;; was used for Turkish. Those who use Latin-3 for Turkish should use
466 ;; "Latin-3" language environment.
468 (set-language-info-alist
469 "Turkish" '((charset iso-8859-9)
470 (coding-system iso-latin-5 windows-1254 iso-latin-3)
471 (coding-priority iso-latin-5)
472 (nonascii-translation . iso-8859-9)
473 (unibyte-display . iso-latin-5)
474 (input-method . "turkish-postfix")
475 (sample-text . "Turkish (T
\e,A|
\e(Brk
\e,Ag
\e(Be) Merhaba")
478 (set-case-syntax-pair ?I ?
\e,C9
\e(B (standard-case-table))
479 (set-case-syntax-pair ?
\e,C)
\e(B ?i (standard-case-table))))
482 (set-case-syntax-pair ?I ?i (standard-case-table))
483 (set-case-syntax ?
\e,C9
\e(B "w" (standard-case-table))
484 (set-case-syntax ?
\e,C)
\e(B "w" (standard-case-table))))
485 (documentation . "Support for Turkish.
486 Differs from the Latin-5 environment in using the `turkish-postfix' input
487 method and applying Turkish case rules for the characters i, I,
\e,C9
\e(B,
\e,C)
\e(B.")))
489 ;; Polish ISO 8859-2 environment.
490 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
491 ;; Keywords: multilingual, Polish
493 (set-language-info-alist
494 "Polish" '((charset . (iso-8859-2))
495 (coding-system . (iso-8859-2 windows-1250))
496 (coding-priority . (iso-8859-2))
497 (nonascii-translation . iso-8859-2)
498 (input-method . "polish-slash")
499 (unibyte-display . iso-8859-2)
500 (tutorial . "TUTORIAL.pl")
501 (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")
505 (set-language-info-alist
506 "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
507 (coding-priority utf-8 latin-8)
508 (nonascii-translation . iso-8859-14)
509 (input-method . "welsh")
510 (documentation . "Support for Welsh, using Unicode."))
513 (set-language-info-alist
514 "Latin-7" `((coding-system latin-7)
515 (coding-priority latin-7)
516 (nonascii-translation . iso-8859-13)
517 ;; Fixme: input-method
518 (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
521 (set-language-info-alist
522 "Lithuanian" `((coding-system latin-7 windows-1257)
523 (coding-priority latin-7)
524 (nonascii-translation . iso-8859-13)
525 (input-method . "lithuanian-keyboard")
526 (documentation . "Support for Lithuanian."))
529 (set-language-info-alist
530 "Latvian" `((coding-system latin-7 windows-1257)
531 (coding-priority latin-7)
532 (nonascii-translation . iso-8859-13)
533 (input-method . "latvian-keyboard")
534 (documentation . "Support for Latvian."))
538 (define-coding-system 'mac-roman
539 "Mac Roman Encoding (MIME:MACINTOSH)."
540 :coding-type 'charset
542 :charset-list '(mac-roman)
543 :mime-charset 'macintosh)
545 (define-coding-system 'next
547 :coding-type 'charset
549 :charset-list '(next)
552 (define-coding-system 'hp-roman8
553 "Hewlet-Packard roman-8 encoding (MIME:ROMAN-8)"
554 :coding-type 'charset
556 :charset-list '(hp-roman8)
557 :mime-charset 'hp-roman8)
558 (define-coding-system-alias 'roman8 'hp-roman8)
560 (define-coding-system 'adobe-standard-encoding
561 "Adobe `standard' encoding for PostScript"
562 :coding-type 'charset
564 :charset-list '(adobe-standard-encoding)
565 :mime-charset 'adobe-standard-encoding)
567 (defconst diacritic-composition-pattern "\\C^\\c^+")
569 (defun diacritic-compose-region (beg end)
570 "Compose diacritic characters in the region.
571 When called from a program, expects two arguments,
572 positions (integers or markers) specifying the region."
575 (narrow-to-region beg end)
576 (goto-char (point-min))
577 (while (re-search-forward diacritic-composition-pattern nil t)
578 (compose-region (match-beginning 0) (match-end 0)))))
580 (defun diacritic-compose-string (string)
581 "Compose diacritic characters in STRING and return the resulting string."
583 (while (setq idx (string-match diacritic-composition-pattern string idx))
584 (compose-string string idx (match-end 0))
585 (setq idx (match-end 0))))
588 (defun diacritic-compose-buffer ()
589 "Compose diacritic characters in the current buffer."
591 (diacritic-compose-region (point-min) (point-max)))
593 (defun diacritic-post-read-conversion (len)
594 (diacritic-compose-region (point) (+ (point) len))
597 (defun diacritic-composition-function (from to pattern &optional string)
598 "Compose diacritic text in the region FROM and TO.
599 The text matches the regular expression PATTERN.
600 Optional 4th argument STRING, if non-nil, is a string containing text
603 The return value is number of composed characters."
607 (compose-string string from to)
608 (compose-region from to))
611 ;; Register a function to compose Unicode diacrtics and marks.
612 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
615 (aset composition-function-table c patterns)
619 (aset composition-function-table c patterns)
624 ;;; european.el ends here