(latexenc-find-file-coding-system): Don't inherit the EOL part of the
[emacs.git] / lisp / language / european.el
blob78f7900ffbaa9a648432c4e9b8f2c2341759a39d
1 ;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
3 ;; Copyright (C) 1997, 1998, 2000, 2001, 2002, 2003, 2004
4 ;; Free Software Foundation, Inc.
5 ;; Copyright (C) 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003
6 ;; National Institute of Advanced Industrial Science and Technology (AIST)
7 ;; Registration Number H14PRO021
9 ;; Keywords: multilingual, European
11 ;; This file is part of GNU Emacs.
13 ;; GNU Emacs is free software; you can redistribute it and/or modify
14 ;; it under the terms of the GNU General Public License as published by
15 ;; the Free Software Foundation; either version 2, or (at your option)
16 ;; any later version.
18 ;; GNU Emacs is distributed in the hope that it will be useful,
19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;; GNU General Public License for more details.
23 ;; You should have received a copy of the GNU General Public License
24 ;; along with GNU Emacs; see the file COPYING. If not, write to the
25 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
26 ;; Boston, MA 02111-1307, USA.
28 ;;; Commentary:
30 ;; For European scripts, all the ISO Latin character sets are
31 ;; supported, along with various others.
33 ;;; Code:
35 ;; Latin-1 (ISO-8859-1)
37 (set-language-info-alist
38 "Latin-1" '((charset ascii latin-iso8859-1)
39 (coding-system iso-latin-1)
40 (coding-priority iso-latin-1)
41 (nonascii-translation . latin-iso8859-1)
42 (unibyte-syntax . "latin-1")
43 (unibyte-display . iso-latin-1)
44 (input-method . "latin-1-prefix")
45 (sample-text
46 . "Hello, Hej, Tere, Hei, Bonjour, Gr\e,A|_\e(B Gott, Ciao, \e,A!\e(BHola!")
47 (documentation . "\
48 This language environment is a generic one for the Latin-1 (ISO-8859-1)
49 character set which supports the following European languages:
50 Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
51 Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
52 German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
53 Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
54 Scottish Gaelic, Spanish, and Swedish.
55 We also have specific language environments for the following languages:
56 For Dutch, \"Dutch\".
57 For German, \"German\".
58 For French, \"French\".
59 For Italian, \"Italian\".
60 For Slovenian, \"Slovenian\".
61 For Spanish, \"Spanish\".
63 Latin-1 also covers several written languages outside Europe, including
64 Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
65 '("European"))
67 (eval-and-compile
68 (setq
69 non-iso-charset-alist
70 (cp-make-coding-system
71 windows-1252
72 [?\\e$,1tL\e(B nil ?\\e$,1rz\e(B ?\\e$,1!R\e(B ?\\e$,1r~\e(B ?\\e$,1s&\e(B ?\\e$,1s \e(B ?\\e$,1s!\e(B ?\\e$,1$f\e(B ?\\e$,1s0\e(B ?\\e$,1! \e(B ?\\e$,1s9\e(B ?\\e$,1 r\e(B nil ?\\e$,1!=\e(B nil nil
73 ?\\e$,1rx\e(B ?\\e$,1ry\e(B ?\\e$,1r|\e(B ?\\e$,1r}\e(B ?\\e$,1s"\e(B ?\\e$,1rs\e(B ?\\e$,1rt\e(B ?\\e$,1$|\e(B ?\\e$,1ub\e(B ?\\e$,1!!\e(B ?\\e$,1s:\e(B ?\\e$,1 s\e(B nil ?\\e$,1!>\e(B ?\\e$,1!8\e(B ?\\e,A \e(B ?\\e,A!\e(B
74 ?\\e,A"\e(B ?\\e,A#\e(B ?\\e,A$\e(B ?\\e,A%\e(B ?\\e,A&\e(B ?\\e,A'\e(B ?\\e,A(\e(B ?\\e,A)\e(B ?\\e,A*\e(B ?\\e,A+\e(B ?\\e,A,\e(B ?\\e,A-\e(B ?\\e,A.\e(B ?\\e,A/\e(B ?\\e,A0\e(B ?\\e,A1\e(B ?\\e,A2\e(B
75 ?\\e,A3\e(B ?\\e,A4\e(B ?\\e,A5\e(B ?\\e,A6\e(B ?\\e,A7\e(B ?\\e,A8\e(B ?\\e,A9\e(B ?\\e,A:\e(B ?\\e,A;\e(B ?\\e,A<\e(B ?\\e,A=\e(B ?\\e,A>\e(B ?\\e,A?\e(B ?\\e,A@\e(B ?\\e,AA\e(B ?\\e,AB\e(B ?\\e,AC\e(B
76 ?\\e,AD\e(B ?\\e,AE\e(B ?\\e,AF\e(B ?\\e,AG\e(B ?\\e,AH\e(B ?\\e,AI\e(B ?\\e,AJ\e(B ?\\e,AK\e(B ?\\e,AL\e(B ?\\e,AM\e(B ?\\e,AN\e(B ?\\e,AO\e(B ?\\e,AP\e(B ?\\e,AQ\e(B ?\\e,AR\e(B ?\\e,AS\e(B ?\\e,AT\e(B
77 ?\\e,AU\e(B ?\\e,AV\e(B ?\\e,AW\e(B ?\\e,AX\e(B ?\\e,AY\e(B ?\\e,AZ\e(B ?\\e,A[\e(B ?\\e,A\\e(B ?\\e,A]\e(B ?\\e,A^\e(B ?\\e,A_\e(B ?\\e,A`\e(B ?\\e,Aa\e(B ?\\e,Ab\e(B ?\\e,Ac\e(B ?\\e,Ad\e(B ?\\e,Ae\e(B
78 ?\\e,Af\e(B ?\\e,Ag\e(B ?\\e,Ah\e(B ?\\e,Ai\e(B ?\\e,Aj\e(B ?\\e,Ak\e(B ?\\e,Al\e(B ?\\e,Am\e(B ?\\e,An\e(B ?\\e,Ao\e(B ?\\e,Ap\e(B ?\\e,Aq\e(B ?\\e,Ar\e(B ?\\e,As\e(B ?\\e,At\e(B ?\\e,Au\e(B ?\\e,Av\e(B
79 ?\\e,Aw\e(B ?\\e,Ax\e(B ?\\e,Ay\e(B ?\\e,Az\e(B ?\\e,A{\e(B ?\\e,A|\e(B ?\\e,A}\e(B ?\\e,A~\e(B ?\\e,A\x7f\e(B])))
81 ;; Latin-2 (ISO-8859-2)
83 (make-coding-system
84 'iso-latin-2 2 ?2
85 "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
86 '(ascii latin-iso8859-2 nil nil
87 nil nil nil nil nil nil nil nil nil nil nil t)
88 '((safe-charsets ascii latin-iso8859-2)
89 (mime-charset . iso-8859-2)))
91 (define-coding-system-alias 'iso-8859-2 'iso-latin-2)
92 (define-coding-system-alias 'latin-2 'iso-latin-2)
94 (set-language-info-alist
95 "Latin-2" '((charset ascii latin-iso8859-2)
96 (coding-system iso-latin-2)
97 (coding-priority iso-latin-2)
98 (nonascii-translation . latin-iso8859-2)
99 (unibyte-syntax . "latin-2")
100 (unibyte-display . iso-latin-2)
101 (input-method . "latin-2-prefix")
102 (documentation . "\
103 This language environment is a generic one for the Latin-2 (ISO-8859-2)
104 character set which supports the following languages:
105 Albanian, Czech, English, German, Hungarian, Polish, Romanian,
106 Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
107 and Swedish.
108 We also have specific language environments for the following languages:
109 For Czech, \"Czech\".
110 For Croatian, \"Croatian\".
111 For Romanian, \"Romanian\".
112 For Slovak, \"Slovak\"."))
113 '("European"))
116 ;; Latin-3 (ISO-8859-3)
118 (make-coding-system
119 'iso-latin-3 2 ?3
120 "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
121 '(ascii latin-iso8859-3 nil nil
122 nil nil nil nil nil nil nil nil nil nil nil t)
123 '((safe-charsets ascii latin-iso8859-3)
124 (mime-charset . iso-8859-3)))
126 (define-coding-system-alias 'iso-8859-3 'iso-latin-3)
127 (define-coding-system-alias 'latin-3 'iso-latin-3)
129 (set-language-info-alist
130 "Latin-3" '((charset ascii latin-iso8859-3)
131 (coding-system iso-latin-3)
132 (coding-priority iso-latin-3)
133 (nonascii-translation . latin-iso8859-3)
134 (unibyte-syntax . "latin-3")
135 (unibyte-display . iso-latin-3)
136 (input-method . "latin-3-prefix")
137 (documentation . "\
138 These languages are supported with the Latin-3 (ISO-8859-3) character set:
139 Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
140 German, Italian, Maltese, Spanish, and Turkish."))
141 '("European"))
144 ;; Latin-4 (ISO-8859-4)
146 (make-coding-system
147 'iso-latin-4 2 ?4
148 "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
149 '(ascii latin-iso8859-4 nil nil
150 nil nil nil nil nil nil nil nil nil nil nil t)
151 '((safe-charsets ascii latin-iso8859-4)
152 (mime-charset . iso-8859-4)))
154 (define-coding-system-alias 'iso-8859-4 'iso-latin-4)
155 (define-coding-system-alias 'latin-4 'iso-latin-4)
157 (set-language-info-alist
158 "Latin-4" '((charset ascii latin-iso8859-4)
159 (coding-system iso-8859-4)
160 (coding-priority iso-8859-4)
161 (nonascii-translation . latin-iso8859-4)
162 (unibyte-syntax . "latin-4")
163 (unibyte-display . iso-8859-4)
164 (input-method . "latin-4-postfix")
165 (documentation . "\
166 These languages are supported with the Latin-4 (ISO-8859-4) character set:
167 Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
168 Latvian, Lithuanian, and Norwegian."))
169 '("European"))
172 ;; Latin-5 (ISO-8859-9)
174 (make-coding-system
175 'iso-latin-5 2 ?9
176 "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
177 '(ascii latin-iso8859-9 nil nil
178 nil nil nil nil nil nil nil nil nil nil nil t)
179 '((safe-charsets ascii latin-iso8859-9)
180 (mime-charset . iso-8859-9)))
182 (define-coding-system-alias 'iso-8859-9 'iso-latin-5)
183 (define-coding-system-alias 'latin-5 'iso-latin-5)
185 (set-language-info-alist
186 "Latin-5" '((charset ascii latin-iso8859-9)
187 (coding-system iso-latin-5)
188 (coding-priority iso-latin-5)
189 (nonascii-translation . latin-iso8859-9)
190 (unibyte-syntax . "latin-5")
191 (unibyte-display . iso-latin-5)
192 (input-method . "latin-5-postfix")
193 (documentation . "Support for Turkish language."))
194 '("European"))
197 ;; Latin-8 (ISO-8859-14)
199 (make-coding-system
200 'iso-latin-8 2 ?W ; `W' for `Welsh', since `C'
201 ; for `Celtic' is taken.
202 "ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
203 '(ascii latin-iso8859-14 nil nil
204 nil nil nil nil nil nil nil nil nil nil nil t t)
205 '((safe-charsets ascii latin-iso8859-14)
206 (mime-charset . iso-8859-14)))
208 (define-coding-system-alias 'iso-8859-14 'iso-latin-8)
209 (define-coding-system-alias 'latin-8 'iso-latin-8)
211 (set-language-info-alist
212 "Latin-8" '((charset ascii latin-iso8859-14)
213 (coding-system iso-latin-8)
214 (coding-priority iso-latin-8)
215 (nonascii-translation . latin-iso8859-14)
216 (unibyte-syntax . "latin-8")
217 (unibyte-display . iso-latin-8)
218 (input-method . "latin-8-prefix")
219 ;; Fixme: Welsh/Ga{e}lic greetings
220 (sample-text . "\e,_"\e(B \e,_p\e(B \e,_^\e(B")
221 (documentation . "\
222 This language environment is a generic one for the Latin-8 (ISO-8859-14)
223 character set which supports the Celtic languages, including those not
224 covered by other ISO-8859 character sets:
225 Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
226 '("European"))
228 ;; Latin-9 (ISO-8859-15)
230 (make-coding-system
231 'iso-latin-9 2 ?0 ; `0' for `Latin-0'
232 "ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
233 '(ascii latin-iso8859-15 nil nil
234 nil nil nil nil nil nil nil nil nil nil nil t t)
235 '((safe-charsets ascii latin-iso8859-15)
236 (mime-charset . iso-8859-15)))
238 (define-coding-system-alias 'iso-8859-15 'iso-latin-9)
239 (define-coding-system-alias 'latin-9 'iso-latin-9)
240 (define-coding-system-alias 'latin-0 'iso-latin-9)
242 (set-language-info-alist
243 "Latin-9" '((charset ascii latin-iso8859-15)
244 (coding-system iso-latin-9)
245 (coding-priority iso-latin-9)
246 (nonascii-translation . latin-iso8859-15)
247 (unibyte-syntax . "latin-9")
248 (unibyte-display . iso-latin-9)
249 (input-method . "latin-9-prefix")
250 (sample-text
251 . "AVE. \e,b&(48<=>\e(B \e,b$\e(B")
252 (documentation . "\
253 This language environment is a generic one for the Latin-9 (ISO-8859-15)
254 character set which supports the same languages as Latin-1 with the
255 addition of the Euro sign and some additional French and Finnish letters.
256 Latin-9 is sometimes nicknamed `Latin-0'."))
257 '("European"))
259 (set-language-info-alist
260 "Dutch" '((tutorial . "TUTORIAL.nl")
261 (charset ascii latin-iso8859-1)
262 (coding-system iso-latin-1 iso-latin-9)
263 (coding-priority iso-latin-1)
264 (nonascii-translation . latin-iso8859-1)
265 (unibyte-syntax . "latin-1")
266 (unibyte-display . iso-latin-1)
267 (input-method . "dutch")
268 (sample-text . "Er is een aantal manieren waarop je dit kan doen")
269 (documentation . "\
270 This language environment is almost the same as Latin-1,
271 but it selects the Dutch tutorial and input method."))
272 '("European"))
274 (set-language-info-alist
275 "German" '((tutorial . "TUTORIAL.de")
276 (charset ascii latin-iso8859-1)
277 (coding-system iso-latin-1 iso-latin-9)
278 (coding-priority iso-latin-1)
279 (input-method . "german-postfix")
280 (nonascii-translation . latin-iso8859-1)
281 (unibyte-syntax . "latin-1")
282 (unibyte-display . iso-latin-1)
283 (sample-text . "\
284 German (Deutsch Nord) Guten Tag
285 German (Deutsch S\e,A|\e(Bd) Gr\e,A|_\e(B Gott")
286 (documentation . "\
287 This language environment is almost the same as Latin-1,
288 but sets the default input method to \"german-postfix\".
289 Additionally, it selects the German tutorial."))
290 '("European"))
292 (set-language-info-alist
293 "French" '((tutorial . "TUTORIAL.fr")
294 (charset ascii latin-iso8859-1)
295 (coding-system iso-latin-1 iso-latin-9)
296 (coding-priority iso-latin-1)
297 (nonascii-translation . latin-iso8859-1)
298 (unibyte-syntax . "latin-1")
299 (unibyte-display . iso-latin-1)
300 (input-method . "latin-1-prefix")
301 (sample-text . "French (Fran\e,Ag\e(Bais) Bonjour, Salut")
302 (documentation . "\
303 This language environment is almost the same as Latin-1,
304 but it selects the French tutorial and input method."))
305 '("European"))
307 (set-language-info-alist
308 "Italian" '((tutorial . "TUTORIAL.it")
309 (charset ascii latin-iso8859-1)
310 (coding-system iso-latin-1 iso-latin-9)
311 (coding-priority iso-latin-1)
312 (nonascii-translation . latin-iso8859-1)
313 (unibyte-syntax . "latin-1")
314 (unibyte-display . iso-latin-1)
315 (input-method . "italian-postfix")
316 (sample-text . "Salve, ciao!")
317 (documentation . "\
318 This language environment is almost the same as Latin-1,
319 but sets the default input method to \"italian-postfix\".
320 Additionally, it selects the Italian tutorial."))
321 '("European"))
323 (set-language-info-alist
324 "Slovenian" '((charset . (ascii latin-iso8859-2))
325 (coding-system . (iso-8859-2))
326 (coding-priority . (iso-8859-2))
327 (nonascii-translation . latin-iso8859-2)
328 (input-method . "slovenian")
329 (unibyte-syntax . "latin-2")
330 (unibyte-display . iso-8859-2)
331 (tutorial . "TUTORIAL.sl")
332 (sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
333 (documentation . "\
334 This language environment is almost the same as Latin-2,
335 but it selects the Slovenian tutorial and input method."))
336 '("European"))
338 (set-language-info-alist
339 "Spanish" '((tutorial . "TUTORIAL.es")
340 (charset ascii latin-iso8859-1)
341 (coding-system iso-latin-1 iso-latin-9)
342 (coding-priority iso-latin-1)
343 (input-method . "spanish-postfix")
344 (nonascii-translation . latin-iso8859-1)
345 (unibyte-syntax . "latin-1")
346 (unibyte-display . iso-latin-1)
347 (sample-text . "Spanish (Espa\e,Aq\e(Bol) \e,A!\e(BHola!")
348 (documentation . "\
349 This language environment is almost the same as Latin-1,
350 but it sets the default input method to \"spanish-postfix\",
351 and it selects the Spanish tutorial."))
352 '("European"))
354 ;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
355 ;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
356 ;; was used for Turkish. Those who use Latin-3 for Turkish should use
357 ;; "Latin-3" language environment.
359 (set-language-info-alist
360 "Turkish" '((charset ascii latin-iso8859-9)
361 (coding-system iso-latin-5 iso-latin-3)
362 (coding-priority iso-latin-5)
363 (nonascii-translation . latin-iso8859-9)
364 (unibyte-syntax . "latin-5")
365 (unibyte-display . iso-latin-5)
366 (input-method . "turkish-postfix")
367 (sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be) Merhaba")
368 (documentation . t)))
370 ;; Polish ISO 8859-2 environment.
371 ;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
372 ;; Keywords: multilingual, Polish
374 (set-language-info-alist
375 "Polish" '((charset . (ascii latin-iso8859-2))
376 (coding-system . (iso-8859-2))
377 (coding-priority . (iso-8859-2))
378 (input-method . "polish-slash")
379 (nonascii-translation . latin-iso8859-2)
380 (unibyte-syntax . "latin-2")
381 (unibyte-display . iso-8859-2)
382 (tutorial . "TUTORIAL.pl")
383 (sample-text . "P\e,Bs\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")
384 (documentation . t))
385 '("European"))
387 (set-language-info-alist
388 "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
389 (coding-priority utf-8 latin-8)
390 (nonascii-translation . latin-iso8859-14)
391 (input-method . "welsh")
392 (documentation . "Support for Welsh, using Unicode."))
393 '("European"))
395 (set-language-info-alist
396 "Latin-6" `((coding-system latin-6)
397 (coding-priority latin-6)
398 (nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
399 (input-method . "latin-prefix")
400 (features code-pages)
401 (documentation . "Support for Latin-6."))
402 '("European"))
404 (set-language-info-alist
405 "Latin-7" `((coding-system latin-7)
406 (coding-priority latin-7)
407 (nonascii-translation . ,(get 'decode-iso-latin-7
408 'translation-table))
409 (input-method . "latin-prefix")
410 (features code-pages)
411 (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
412 '("European"))
414 (set-language-info-alist
415 "Lithuanian" `((coding-system latin-7)
416 (coding-priority latin-7)
417 (input-method . "lithuanian-keyboard")
418 (nonascii-translation . ,(get 'decode-iso-latin-7
419 'translation-table))
420 (features code-pages)
421 (documentation . "Support for Lithuanian."))
422 '("European"))
424 (set-language-info-alist
425 "Latvian" `((coding-system latin-7)
426 (coding-priority latin-7)
427 (input-method . "latvian-keyboard")
428 (nonascii-translation . ,(get 'decode-iso-latin-7
429 'translation-table))
430 (features code-pages)
431 (documentation . "Support for Latvian."))
432 '("European"))
434 (set-language-info-alist
435 "Swedish" '((tutorial . "TUTORIAL.sv")
436 (charset ascii latin-iso8859-1)
437 (coding-system iso-latin-1)
438 (coding-priority iso-latin-1)
439 (nonascii-translation . latin-iso8859-1)
440 (unibyte-syntax . "latin-1")
441 (unibyte-display . iso-latin-1)
442 (sample-text . "Goddag Hej")
443 (documentation . "Support for Swedish"))
444 '("European"))
446 (set-language-info-alist
447 "Croatian" '((charset . (ascii latin-iso8859-2))
448 (coding-system . (iso-8859-2))
449 (coding-priority . (iso-8859-2))
450 (input-method . "croatian")
451 (nonascii-translation . latin-iso8859-2)
452 (unibyte-syntax . "latin-2")
453 (unibyte-display . iso-8859-2)
454 (documentation . "Support for Croatian with Latin-2 encoding."))
455 '("European"))
457 (set-language-info-alist
458 "Brazilian Portuguese" '((tutorial . "TUTORIAL.pt_BR")
459 (charset ascii latin-iso8859-1)
460 (coding-system iso-latin-1 iso-latin-9)
461 (coding-priority iso-latin-1)
462 (nonascii-translation . latin-iso8859-1)
463 (unibyte-syntax . "latin-1")
464 (unibyte-display . iso-latin-1)
465 (input-method . "latin-1-prefix")
466 (sample-text . "Oi")
467 (documentation . "Support for Brazilian Portuguese."))
468 '("European"))
470 ;; Definitions for the Mac Roman character sets and coding system.
471 ;; The Mac Roman encoding uses all 128 code points in the range 128 to
472 ;; 255 for actual characters. Emacs decodes them to one of the
473 ;; following character sets.
474 ;; ascii, latin-iso8859-1, mule-unicode-0100-24ff,
475 ;; mule-unicode-2500-33ff, mule-unicode-e000-ffff
477 (let
478 ((encoding-vector (make-vector 256 nil))
479 (i 0)
480 (vec ;; mac-roman (128..255) -> UCS mapping
481 [ #x00C4 ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
482 #x00C5 ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
483 #x00C7 ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
484 #x00C9 ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
485 #x00D1 ;; 132:LATIN CAPITAL LETTER N WITH TILDE
486 #x00D6 ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
487 #x00DC ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
488 #x00E1 ;; 135:LATIN SMALL LETTER A WITH ACUTE
489 #x00E0 ;; 136:LATIN SMALL LETTER A WITH GRAVE
490 #x00E2 ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
491 #x00E4 ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
492 #x00E3 ;; 139:LATIN SMALL LETTER A WITH TILDE
493 #x00E5 ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
494 #x00E7 ;; 141:LATIN SMALL LETTER C WITH CEDILLA
495 #x00E9 ;; 142:LATIN SMALL LETTER E WITH ACUTE
496 #x00E8 ;; 143:LATIN SMALL LETTER E WITH GRAVE
497 #x00EA ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
498 #x00EB ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
499 #x00ED ;; 146:LATIN SMALL LETTER I WITH ACUTE
500 #x00EC ;; 147:LATIN SMALL LETTER I WITH GRAVE
501 #x00EE ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
502 #x00EF ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
503 #x00F1 ;; 150:LATIN SMALL LETTER N WITH TILDE
504 #x00F3 ;; 151:LATIN SMALL LETTER O WITH ACUTE
505 #x00F2 ;; 152:LATIN SMALL LETTER O WITH GRAVE
506 #x00F4 ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
507 #x00F6 ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
508 #x00F5 ;; 155:LATIN SMALL LETTER O WITH TILDE
509 #x00FA ;; 156:LATIN SMALL LETTER U WITH ACUTE
510 #x00F9 ;; 157:LATIN SMALL LETTER U WITH GRAVE
511 #x00FB ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
512 #x00FC ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
513 #x2020 ;; 160:DAGGER
514 #x00B0 ;; 161:DEGREE SIGN
515 #x00A2 ;; 162:CENT SIGN
516 #x00A3 ;; 163:POUND SIGN
517 #x00A7 ;; 164:SECTION SIGN
518 #x2022 ;; 165:BULLET
519 #x00B6 ;; 166:PILCROW SIGN
520 #x00DF ;; 167:LATIN SMALL LETTER SHARP S
521 #x00AE ;; 168:REGISTERED SIGN
522 #x00A9 ;; 169:COPYRIGHT SIGN
523 #x2122 ;; 170:TRADE MARK SIGN
524 #x00B4 ;; 171:ACUTE ACCENT
525 #x00A8 ;; 172:DIAERESIS
526 #x2260 ;; 173:NOT EQUAL TO
527 #x00C6 ;; 174:LATIN CAPITAL LETTER AE
528 #x00D8 ;; 175:LATIN CAPITAL LETTER O WITH STROKE
529 #x221E ;; 176:INFINITY
530 #x00B1 ;; 177:PLUS-MINUS SIGN
531 #x2264 ;; 178:LESS-THAN OR EQUAL TO
532 #x2265 ;; 179:GREATER-THAN OR EQUAL TO
533 #x00A5 ;; 180:YEN SIGN
534 #x00B5 ;; 181:MICRO SIGN
535 #x2202 ;; 182:PARTIAL DIFFERENTIAL
536 #x2211 ;; 183:N-ARY SUMMATION
537 #x220F ;; 184:N-ARY PRODUCT
538 #x03C0 ;; 185:GREEK SMALL LETTER PI
539 #x222B ;; 186:INTEGRAL
540 #x00AA ;; 187:FEMININE ORDINAL INDICATOR
541 #x00BA ;; 188:MASCULINE ORDINAL INDICATOR
542 #x03A9 ;; 189:GREEK CAPITAL LETTER OMEGA
543 #x00E6 ;; 190:LATIN SMALL LETTER AE
544 #x00F8 ;; 191:LATIN SMALL LETTER O WITH STROKE
545 #x00BF ;; 192:INVERTED QUESTION MARK
546 #x00A1 ;; 193:INVERTED EXCLAMATION MARK
547 #x00AC ;; 194:NOT SIGN
548 #x221A ;; 195:SQUARE ROOT
549 #x0192 ;; 196:LATIN SMALL LETTER F WITH HOOK
550 #x2248 ;; 197:ALMOST EQUAL TO
551 #x2206 ;; 198:INCREMENT
552 #x00AB ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
553 #x00BB ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
554 #x2026 ;; 201:HORIZONTAL ELLIPSIS
555 #x00A0 ;; 202:NO-BREAK SPACE
556 #x00C0 ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
557 #x00C3 ;; 204:LATIN CAPITAL LETTER A WITH TILDE
558 #x00D5 ;; 205:LATIN CAPITAL LETTER O WITH TILDE
559 #x0152 ;; 206:LATIN CAPITAL LIGATURE OE
560 #x0153 ;; 207:LATIN SMALL LIGATURE OE
561 #x2013 ;; 208:EN DASH
562 #x2014 ;; 209:EM DASH
563 #x201C ;; 210:LEFT DOUBLE QUOTATION MARK
564 #x201D ;; 211:RIGHT DOUBLE QUOTATION MARK
565 #x2018 ;; 212:LEFT SINGLE QUOTATION MARK
566 #x2019 ;; 213:RIGHT SINGLE QUOTATION MARK
567 #x00F7 ;; 214:DIVISION SIGN
568 #x25CA ;; 215:LOZENGE
569 #x00FF ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
570 #x0178 ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
571 #x2044 ;; 218:FRACTION SLASH
572 #x20AC ;; 219:EURO SIGN
573 #x2039 ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
574 #x203A ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
575 #xFB01 ;; 222:LATIN SMALL LIGATURE FI
576 #xFB02 ;; 223:LATIN SMALL LIGATURE FL
577 #x2021 ;; 224:DOUBLE DAGGER
578 #x00B7 ;; 225:MIDDLE DOT
579 #x201A ;; 226:SINGLE LOW-9 QUOTATION MARK
580 #x201E ;; 227:DOUBLE LOW-9 QUOTATION MARK
581 #x2030 ;; 228:PER MILLE SIGN
582 #x00C2 ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
583 #x00CA ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
584 #x00C1 ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
585 #x00CB ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
586 #x00C8 ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
587 #x00CD ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
588 #x00CE ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
589 #x00CF ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
590 #x00CC ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
591 #x00D3 ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
592 #x00D4 ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
593 #xF8FF ;; 240:Apple logo
594 #x00D2 ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
595 #x00DA ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
596 #x00DB ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
597 #x00D9 ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
598 #x0131 ;; 245:LATIN SMALL LETTER DOTLESS I
599 #x02C6 ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
600 #x02DC ;; 247:SMALL TILDE
601 #x00AF ;; 248:MACRON
602 #x02D8 ;; 249:BREVE
603 #x02D9 ;; 250:DOT ABOVE
604 #x02DA ;; 251:RING ABOVE
605 #x00B8 ;; 252:CEDILLA
606 #x02DD ;; 253:DOUBLE ACUTE ACCENT
607 #x02DB ;; 254:OGONEK
608 #x02C7 ;; 255:CARON
610 translation-table)
611 (while (< i 128)
612 (aset encoding-vector i i)
613 (setq i (1+ i)))
614 (while (< i 256)
615 (aset encoding-vector i
616 (decode-char 'ucs (aref vec (- i 128))))
617 (setq i (1+ i)))
618 (setq translation-table
619 (make-translation-table-from-vector encoding-vector))
620 (define-translation-table 'mac-roman-decoder translation-table)
621 (define-translation-table 'mac-roman-encoder
622 (char-table-extra-slot translation-table 0)))
624 (define-ccl-program decode-mac-roman
626 ((loop
627 (read r1)
628 (if (r1 < 128) ;; ASCII
629 (r0 = ,(charset-id 'ascii))
630 (if (r1 < 160)
631 (r0 = ,(charset-id 'eight-bit-control))
632 (r0 = ,(charset-id 'eight-bit-graphic))))
633 (translate-character mac-roman-decoder r0 r1)
634 (write-multibyte-character r0 r1)
635 (repeat))))
636 "CCL program to decode Mac Roman")
638 (define-ccl-program encode-mac-roman
640 ((loop
641 (read-multibyte-character r0 r1)
642 (translate-character ucs-mule-to-mule-unicode r0 r1)
643 (translate-character mac-roman-encoder r0 r1)
644 (if (r0 != ,(charset-id 'ascii))
645 (if (r0 != ,(charset-id 'eight-bit-graphic))
646 (if (r0 != ,(charset-id 'eight-bit-control))
647 (r1 = ??))))
648 (write-repeat r1))))
649 "CCL program to encode Mac Roman")
651 (make-coding-system
652 'mac-roman 4 ?M
653 "Mac Roman Encoding (MIME:MACINTOSH)."
654 '(decode-mac-roman . encode-mac-roman)
655 (list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table))
656 '(valid-codes (0 . 255))
657 '(mime-charset . macintosh))) ; per IANA, rfc1345
659 (defconst diacritic-composition-pattern "\\C^\\c^+")
661 (defun diacritic-compose-region (beg end)
662 "Compose diacritic characters in the region.
663 When called from a program, expects two arguments,
664 positions (integers or markers) specifying the region."
665 (interactive "r")
666 (save-restriction
667 (narrow-to-region beg end)
668 (goto-char (point-min))
669 (while (re-search-forward diacritic-composition-pattern nil t)
670 (compose-region (match-beginning 0) (match-end 0)))))
672 (defun diacritic-compose-string (string)
673 "Compose diacritic characters in STRING and return the resulting string."
674 (let ((idx 0))
675 (while (setq idx (string-match diacritic-composition-pattern string idx))
676 (compose-string string idx (match-end 0))
677 (setq idx (match-end 0))))
678 string)
680 (defun diacritic-compose-buffer ()
681 "Compose diacritic characters in the current buffer."
682 (interactive)
683 (diacritic-compose-region (point-min) (point-max)))
685 (defun diacritic-post-read-conversion (len)
686 (diacritic-compose-region (point) (+ (point) len))
687 len)
689 (defun diacritic-composition-function (from to pattern &optional string)
690 "Compose diacritic text in the region FROM and TO.
691 The text matches the regular expression PATTERN.
692 Optional 4th argument STRING, if non-nil, is a string containing text
693 to compose.
695 The return value is the number of composed characters."
696 (when (< (1+ from) to)
697 (if string
698 (compose-string string from to)
699 (compose-region from to))
700 (- to from)))
702 ;; Register a function to compose Unicode diacrtics and marks.
703 (let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
704 (let ((c #x300))
705 (while (<= c #x362)
706 (aset composition-function-table (decode-char 'ucs c) patterns)
707 (setq c (1+ c)))
708 (setq c #x20d0)
709 (while (<= c #x20e3)
710 (aset composition-function-table (decode-char 'ucs c) patterns)
711 (setq c (1+ c)))))
713 (provide 'european)
715 ;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
716 ;;; european.el ends here