european.el

Revision 4220, 27.3 kB (checked in by miyoshi, 9 months ago)
Sync up with Emacs22.2.
Property svn:eol-style set to `LF`

Line
1	;;; european.el --- support for European languages -- coding: iso-2022-7bit; --
2
3	;; Copyright (C) 1997, 1998, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007,
4	;; 2008 Free Software Foundation, Inc.
5	;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
6	;; 2005, 2006, 2007, 2008
7	;; National Institute of Advanced Industrial Science and Technology (AIST)
8	;; Registration Number H14PRO021
9
10	;; Keywords: multilingual, European
11
12	;; This file is part of GNU Emacs.
13
14	;; GNU Emacs is free software; you can redistribute it and/or modify
15	;; it under the terms of the GNU General Public License as published by
16	;; the Free Software Foundation; either version 3, or (at your option)
17	;; any later version.
18
19	;; GNU Emacs is distributed in the hope that it will be useful,
20	;; but WITHOUT ANY WARRANTY; without even the implied warranty of
21	;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22	;; GNU General Public License for more details.
23
24	;; You should have received a copy of the GNU General Public License
25	;; along with GNU Emacs; see the file COPYING. If not, write to the
26	;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
27	;; Boston, MA 02110-1301, USA.
28
29	;;; Commentary:
30
31	;; For European scripts, all the ISO Latin character sets are
32	;; supported, along with various others.
33
34	;;; Code:
35
36	;; Latin-1 (ISO-8859-1)
37
38	(set-language-info-alist
39	"Latin-1" '((charset ascii latin-iso8859-1)
40	(coding-system iso-latin-1)
41	(coding-priority iso-latin-1 windows-1252)
42	(nonascii-translation . latin-iso8859-1)
43	(unibyte-syntax . "latin-1")
44	(unibyte-display . iso-latin-1)
45	(input-method . "latin-1-prefix")
46	(sample-text
47	. "Hello, Hej, Tere, Hei, Bonjour, Gr,A\|_(B Gott, Ciao, ,A!(BHola!")
48	(documentation . "\
49	This language environment is a generic one for the Latin-1 (ISO-8859-1)
50	character set which supports the following European languages:
51	Albanian, Basque, Breton, Catalan, Danish, Dutch, English, Faeroese,
52	Finnish, French (with restrictions -- see Latin-9), Frisian, Galician,
53	German, Greenlandic, Icelandic, Irish Gaelic (new orthography),
54	Italian, Latin, Luxemburgish, Norwegian, Portuguese, Rhaeto-Romanic,
55	Scottish Gaelic, Spanish, and Swedish.
56	We also have specific language environments for the following languages:
57	For Dutch, \"Dutch\".
58	For German, \"German\".
59	For French, \"French\".
60	For Italian, \"Italian\".
61	For Slovenian, \"Slovenian\".
62	For Spanish, \"Spanish\".
63
64	Latin-1 also covers several written languages outside Europe, including
65	Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
66	'("European"))
67
68	(eval-and-compile
69	(setq
70	non-iso-charset-alist
71	(cp-make-coding-system
72	windows-1252
73	[?\$,1tL(B nil ?\$,1rz(B ?\$,1!R(B ?\$,1r~(B ?\$,1s&(B ?\$,1s (B ?\$,1s!(B ?\$,1$f(B ?\$,1s0(B ?\$,1! (B ?\$,1s9(B ?\$,1 r(B nil ?\$,1!=(B nil nil
74	?\$,1rx(B ?\$,1ry(B ?\$,1r\|(B ?\$,1r}(B ?\$,1s"(B ?\$,1rs(B ?\$,1rt(B ?\$,1$\|(B ?\$,1ub(B ?\$,1!!(B ?\$,1s:(B ?\$,1 s(B nil ?\$,1!>(B ?\$,1!8(B ?\,A (B ?\,A!(B
75	?\,A"(B ?\,A#(B ?\,A$(B ?\,A%(B ?\,A&(B ?\,A'(B ?\,A((B ?\,A)(B ?\,A*(B ?\,A+(B ?\,A,(B ?\,A-(B ?\,A.(B ?\,A/(B ?\,A0(B ?\,A1(B ?\,A2(B
76	?\,A3(B ?\,A4(B ?\,A5(B ?\,A6(B ?\,A7(B ?\,A8(B ?\,A9(B ?\,A:(B ?\,A;(B ?\,A<(B ?\,A=(B ?\,A>(B ?\,A?(B ?\,A@(B ?\,AA(B ?\,AB(B ?\,AC(B
77	?\,AD(B ?\,AE(B ?\,AF(B ?\,AG(B ?\,AH(B ?\,AI(B ?\,AJ(B ?\,AK(B ?\,AL(B ?\,AM(B ?\,AN(B ?\,AO(B ?\,AP(B ?\,AQ(B ?\,AR(B ?\,AS(B ?\,AT(B
78	?\,AU(B ?\,AV(B ?\,AW(B ?\,AX(B ?\,AY(B ?\,AZ(B ?\,A[(B ?\,A\(B ?\,A](B ?\,A^(B ?\,A_(B ?\,A`(B ?\,Aa(B ?\,Ab(B ?\,Ac(B ?\,Ad(B ?\,Ae(B
79	?\,Af(B ?\,Ag(B ?\,Ah(B ?\,Ai(B ?\,Aj(B ?\,Ak(B ?\,Al(B ?\,Am(B ?\,An(B ?\,Ao(B ?\,Ap(B ?\,Aq(B ?\,Ar(B ?\,As(B ?\,At(B ?\,Au(B ?\,Av(B
80	?\,Aw(B ?\,Ax(B ?\,Ay(B ?\,Az(B ?\,A{(B ?\,A\|(B ?\,A}(B ?\,A~(B ?\,A(B])))
81
82	(define-coding-system-alias 'cp1252 'windows-1252)
83
84
85	;; Latin-2 (ISO-8859-2)
86
87	(make-coding-system
88	'iso-latin-2 2 ?2
89	"ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
90	'(ascii latin-iso8859-2 nil nil
91	nil nil nil nil nil nil nil nil nil nil nil t)
92	'((safe-charsets ascii latin-iso8859-2)
93	(mime-charset . iso-8859-2)))
94
95	(define-coding-system-alias 'iso-8859-2 'iso-latin-2)
96	(define-coding-system-alias 'latin-2 'iso-latin-2)
97
98	(set-language-info-alist
99	"Latin-2" '((charset ascii latin-iso8859-2)
100	(coding-system iso-latin-2)
101	(coding-priority iso-latin-2)
102	(nonascii-translation . latin-iso8859-2)
103	(unibyte-syntax . "latin-2")
104	(unibyte-display . iso-latin-2)
105	(input-method . "latin-2-prefix")
106	(documentation . "\
107	This language environment is a generic one for the Latin-2 (ISO-8859-2)
108	character set which supports the following languages:
109	Albanian, Czech, English, German, Hungarian, Polish, Romanian,
110	Serbo-Croatian or Croatian, Slovak, Slovene, Sorbian (upper and lower),
111	and Swedish.
112	We also have specific language environments for the following languages:
113	For Czech, \"Czech\".
114	For Croatian, \"Croatian\".
115	For Romanian, \"Romanian\".
116	For Slovak, \"Slovak\"."))
117	'("European"))
118
119
120	;; Latin-3 (ISO-8859-3)
121
122	(make-coding-system
123	'iso-latin-3 2 ?3
124	"ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
125	'(ascii latin-iso8859-3 nil nil
126	nil nil nil nil nil nil nil nil nil nil nil t)
127	'((safe-charsets ascii latin-iso8859-3)
128	(mime-charset . iso-8859-3)))
129
130	(define-coding-system-alias 'iso-8859-3 'iso-latin-3)
131	(define-coding-system-alias 'latin-3 'iso-latin-3)
132
133	(set-language-info-alist
134	"Latin-3" '((charset ascii latin-iso8859-3)
135	(coding-system iso-latin-3)
136	(coding-priority iso-latin-3)
137	(nonascii-translation . latin-iso8859-3)
138	(unibyte-syntax . "latin-3")
139	(unibyte-display . iso-latin-3)
140	(input-method . "latin-3-prefix")
141	(documentation . "\
142	These languages are supported with the Latin-3 (ISO-8859-3) character set:
143	Afrikaans, Catalan, Dutch, English, Esperanto, French, Galician,
144	German, Italian, Maltese, Spanish, and Turkish."))
145	'("European"))
146
147
148	;; Latin-4 (ISO-8859-4)
149
150	(make-coding-system
151	'iso-latin-4 2 ?4
152	"ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
153	'(ascii latin-iso8859-4 nil nil
154	nil nil nil nil nil nil nil nil nil nil nil t)
155	'((safe-charsets ascii latin-iso8859-4)
156	(mime-charset . iso-8859-4)))
157
158	(define-coding-system-alias 'iso-8859-4 'iso-latin-4)
159	(define-coding-system-alias 'latin-4 'iso-latin-4)
160
161	(set-language-info-alist
162	"Latin-4" '((charset ascii latin-iso8859-4)
163	(coding-system iso-8859-4)
164	(coding-priority iso-8859-4)
165	(nonascii-translation . latin-iso8859-4)
166	(unibyte-syntax . "latin-4")
167	(unibyte-display . iso-8859-4)
168	(input-method . "latin-4-postfix")
169	(documentation . "\
170	These languages are supported with the Latin-4 (ISO-8859-4) character set:
171	Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
172	Latvian, Lithuanian, and Norwegian."))
173	'("European"))
174
175
176	;; Latin-5 (ISO-8859-9)
177
178	(make-coding-system
179	'iso-latin-5 2 ?9
180	"ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
181	'(ascii latin-iso8859-9 nil nil
182	nil nil nil nil nil nil nil nil nil nil nil t)
183	'((safe-charsets ascii latin-iso8859-9)
184	(mime-charset . iso-8859-9)))
185
186	(define-coding-system-alias 'iso-8859-9 'iso-latin-5)
187	(define-coding-system-alias 'latin-5 'iso-latin-5)
188
189	(set-language-info-alist
190	"Latin-5" '((charset ascii latin-iso8859-9)
191	(coding-system iso-latin-5)
192	(coding-priority iso-latin-5)
193	(nonascii-translation . latin-iso8859-9)
194	(unibyte-syntax . "latin-5")
195	(unibyte-display . iso-latin-5)
196	(input-method . "latin-5-postfix")
197	(documentation . "Support for Turkish language."))
198	'("European"))
199
200
201	;; Latin-8 (ISO-8859-14)
202
203	(make-coding-system
204	'iso-latin-8 2 ?W ; `W' for `Welsh', since `C'
205	; for `Celtic' is taken.
206	"ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
207	'(ascii latin-iso8859-14 nil nil
208	nil nil nil nil nil nil nil nil nil nil nil t t)
209	'((safe-charsets ascii latin-iso8859-14)
210	(mime-charset . iso-8859-14)))
211
212	(define-coding-system-alias 'iso-8859-14 'iso-latin-8)
213	(define-coding-system-alias 'latin-8 'iso-latin-8)
214
215	(set-language-info-alist
216	"Latin-8" '((charset ascii latin-iso8859-14)
217	(coding-system iso-latin-8)
218	(coding-priority iso-latin-8)
219	(nonascii-translation . latin-iso8859-14)
220	(unibyte-syntax . "latin-8")
221	(unibyte-display . iso-latin-8)
222	(input-method . "latin-8-prefix")
223	;; Fixme: Welsh/Ga{e}lic greetings
224	(sample-text . ",_"(B ,_p(B ,_^(B")
225	(documentation . "\
226	This language environment is a generic one for the Latin-8 (ISO-8859-14)
227	character set which supports the Celtic languages, including those not
228	covered by other ISO-8859 character sets:
229	Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
230	'("European"))
231
232	;; Latin-9 (ISO-8859-15)
233
234	(make-coding-system
235	'iso-latin-9 2 ?0 ; `0' for `Latin-0'
236	"ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)."
237	'(ascii latin-iso8859-15 nil nil
238	nil nil nil nil nil nil nil nil nil nil nil t t)
239	'((safe-charsets ascii latin-iso8859-15)
240	(mime-charset . iso-8859-15)))
241
242	(define-coding-system-alias 'iso-8859-15 'iso-latin-9)
243	(define-coding-system-alias 'latin-9 'iso-latin-9)
244	(define-coding-system-alias 'latin-0 'iso-latin-9)
245
246	(set-language-info-alist
247	"Latin-9" '((charset ascii latin-iso8859-15)
248	(coding-system iso-latin-9)
249	(coding-priority iso-latin-9)
250	(nonascii-translation . latin-iso8859-15)
251	(unibyte-syntax . "latin-9")
252	(unibyte-display . iso-latin-9)
253	(input-method . "latin-9-prefix")
254	(sample-text
255	. "AVE. ,b&(48<=>(B ,b$(B")
256	(documentation . "\
257	This language environment is a generic one for the Latin-9 (ISO-8859-15)
258	character set which supports the same languages as Latin-1 with the
259	addition of the Euro sign and some additional French and Finnish letters.
260	Latin-9 is sometimes nicknamed `Latin-0'."))
261	'("European"))
262
263	(set-language-info-alist
264	"Dutch" '((tutorial . "TUTORIAL.nl")
265	(charset ascii latin-iso8859-1)
266	(coding-system iso-latin-1 iso-latin-9)
267	(coding-priority iso-latin-1)
268	(nonascii-translation . latin-iso8859-1)
269	(unibyte-syntax . "latin-1")
270	(unibyte-display . iso-latin-1)
271	(input-method . "dutch")
272	(sample-text . "Er is een aantal manieren waarop je dit kan doen")
273	(documentation . "\
274	This language environment is almost the same as Latin-1,
275	but it selects the Dutch tutorial and input method."))
276	'("European"))
277
278	(set-language-info-alist
279	"German" '((tutorial . "TUTORIAL.de")
280	(charset ascii latin-iso8859-1)
281	(coding-system iso-latin-1 iso-latin-9)
282	(coding-priority iso-latin-1 windows-1252)
283	(input-method . "german-postfix")
284	(nonascii-translation . latin-iso8859-1)
285	(unibyte-syntax . "latin-1")
286	(unibyte-display . iso-latin-1)
287	(sample-text . "\
288	German (Deutsch Nord) Guten Tag
289	German (Deutsch S,A\|(Bd) Gr,A\|_(B Gott")
290	(documentation . "\
291	This language environment is almost the same as Latin-1,
292	but sets the default input method to \"german-postfix\".
293	Additionally, it selects the German tutorial."))
294	'("European"))
295
296	(set-language-info-alist
297	"French" '((tutorial . "TUTORIAL.fr")
298	(charset ascii latin-iso8859-1)
299	(coding-system iso-latin-1 iso-latin-9)
300	(coding-priority iso-latin-1)
301	(nonascii-translation . latin-iso8859-1)
302	(unibyte-syntax . "latin-1")
303	(unibyte-display . iso-latin-1)
304	(input-method . "latin-1-prefix")
305	(sample-text . "French (Fran,Ag(Bais) Bonjour, Salut")
306	(documentation . "\
307	This language environment is almost the same as Latin-1,
308	but it selects the French tutorial and input method."))
309	'("European"))
310
311	(set-language-info-alist
312	"Italian" '((tutorial . "TUTORIAL.it")
313	(charset ascii latin-iso8859-1)
314	(coding-system iso-latin-1 iso-latin-9)
315	(coding-priority iso-latin-1)
316	(nonascii-translation . latin-iso8859-1)
317	(unibyte-syntax . "latin-1")
318	(unibyte-display . iso-latin-1)
319	(input-method . "italian-postfix")
320	(sample-text . "Salve, ciao!")
321	(documentation . "\
322	This language environment is almost the same as Latin-1,
323	but sets the default input method to \"italian-postfix\".
324	Additionally, it selects the Italian tutorial."))
325	'("European"))
326
327	(set-language-info-alist
328	"Slovenian" '((charset . (ascii latin-iso8859-2))
329	(coding-system . (iso-8859-2))
330	(coding-priority . (iso-8859-2))
331	(nonascii-translation . latin-iso8859-2)
332	(input-method . "slovenian")
333	(unibyte-syntax . "latin-2")
334	(unibyte-display . iso-8859-2)
335	(tutorial . "TUTORIAL.sl")
336	(sample-text . ",B.(Belimo vam uspe,B9(Ben dan!")
337	(documentation . "\
338	This language environment is almost the same as Latin-2,
339	but it selects the Slovenian tutorial and input method."))
340	'("European"))
341
342	(set-language-info-alist
343	"Spanish" '((tutorial . "TUTORIAL.es")
344	(charset ascii latin-iso8859-1)
345	(coding-system iso-latin-1 iso-latin-9)
346	(coding-priority iso-latin-1)
347	(input-method . "spanish-postfix")
348	(nonascii-translation . latin-iso8859-1)
349	(unibyte-syntax . "latin-1")
350	(unibyte-display . iso-latin-1)
351	(sample-text . "Spanish (Espa,Aq(Bol) ,A!(BHola!")
352	(documentation . "\
353	This language environment is almost the same as Latin-1,
354	but it sets the default input method to \"spanish-postfix\",
355	and it selects the Spanish tutorial."))
356	'("European"))
357
358	;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
359	;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
360	;; was used for Turkish. Those who use Latin-3 for Turkish should use
361	;; "Latin-3" language environment.
362
363	(set-language-info-alist
364	"Turkish" '((charset ascii latin-iso8859-9)
365	(coding-system iso-latin-5 iso-latin-3)
366	(coding-priority iso-latin-5)
367	(nonascii-translation . latin-iso8859-9)
368	(unibyte-syntax . "latin-5")
369	(unibyte-display . iso-latin-5)
370	(input-method . "turkish-postfix")
371	(sample-text . "Turkish (T,M\|(Brk,Mg(Be) Merhaba")
372	(documentation . t)
373	(setup-function . turkish-case-conversion-enable)
374	(exit-function . turkish-case-conversion-disable)))
375
376	(defun turkish-case-conversion-enable ()
377	"Set up Turkish case conversion of `i' and `I' into `$,1 P(B' and `$,1 Q(B'."
378	(let ((table (standard-case-table)))
379	(set-case-syntax-pair ?$,1 P(B ?i table)
380	(set-case-syntax-pair ?I ?$,1 Q(B table)))
381
382	(defun turkish-case-conversion-disable ()
383	"Set up normal (non-Turkish) case conversion of `i' into `I'."
384	(let ((table (standard-case-table)))
385	(set-case-syntax-pair ?I ?i table)
386	(set-case-syntax ?$,1 P(B "w" table)
387	(set-case-syntax ?$,1 Q(B "w" table)))
388
389	;; Polish ISO 8859-2 environment.
390	;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
391	;; Keywords: multilingual, Polish
392
393	(set-language-info-alist
394	"Polish" '((charset . (ascii latin-iso8859-2))
395	(coding-system . (iso-8859-2))
396	(coding-priority . (iso-8859-2))
397	(input-method . "polish-slash")
398	(nonascii-translation . latin-iso8859-2)
399	(unibyte-syntax . "latin-2")
400	(unibyte-display . iso-8859-2)
401	(tutorial . "TUTORIAL.pl")
402	(sample-text . "P,Bs(Bjd,B<(B, ki,Bq(B-,B?(Be t,Bj(B chmurno,B6f(B w g,B31(Bb flaszy")
403	(documentation . t))
404	'("European"))
405
406	(set-language-info-alist
407	"Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
408	(coding-priority utf-8 latin-8)
409	(nonascii-translation . latin-iso8859-14)
410	(input-method . "welsh")
411	(documentation . "Support for Welsh, using Unicode."))
412	'("European"))
413
414	(set-language-info-alist
415	"Latin-6" `((coding-system latin-6)
416	(coding-priority latin-6)
417	(nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
418	(input-method . "latin-prefix")
419	(features code-pages)
420	(documentation . "Support for Latin-6."))
421	'("European"))
422
423	(set-language-info-alist
424	"Latin-7" `((coding-system latin-7)
425	(coding-priority latin-7)
426	(nonascii-translation . ,(get 'decode-iso-latin-7
427	'translation-table))
428	(input-method . "latin-prefix")
429	(features code-pages)
430	(documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
431	'("European"))
432
433	(set-language-info-alist
434	"Lithuanian" `((coding-system latin-7)
435	(coding-priority latin-7)
436	(input-method . "lithuanian-keyboard")
437	(nonascii-translation . ,(get 'decode-iso-latin-7
438	'translation-table))
439	(features code-pages)
440	(documentation . "Support for Lithuanian."))
441	'("European"))
442
443	(set-language-info-alist
444	"Latvian" `((coding-system latin-7)
445	(coding-priority latin-7)
446	(input-method . "latvian-keyboard")
447	(nonascii-translation . ,(get 'decode-iso-latin-7
448	'translation-table))
449	(features code-pages)
450	(documentation . "Support for Latvian."))
451	'("European"))
452
453	(set-language-info-alist
454	"Swedish" '((tutorial . "TUTORIAL.sv")
455	(charset ascii latin-iso8859-1)
456	(coding-system iso-latin-1)
457	(coding-priority iso-latin-1)
458	(nonascii-translation . latin-iso8859-1)
459	(unibyte-syntax . "latin-1")
460	(unibyte-display . iso-latin-1)
461	(sample-text . "Goddag Hej")
462	(documentation . "Support for Swedish"))
463	'("European"))
464
465	(set-language-info-alist
466	"Croatian" '((charset . (ascii latin-iso8859-2))
467	(coding-system . (iso-8859-2))
468	(coding-priority . (iso-8859-2))
469	(input-method . "croatian")
470	(nonascii-translation . latin-iso8859-2)
471	(unibyte-syntax . "latin-2")
472	(unibyte-display . iso-8859-2)
473	(documentation . "Support for Croatian with Latin-2 encoding."))
474	'("European"))
475
476	(set-language-info-alist
477	"Brazilian Portuguese" '((tutorial . "TUTORIAL.pt_BR")
478	(charset ascii latin-iso8859-1)
479	(coding-system iso-latin-1 iso-latin-9)
480	(coding-priority iso-latin-1)
481	(nonascii-translation . latin-iso8859-1)
482	(unibyte-syntax . "latin-1")
483	(unibyte-display . iso-latin-1)
484	(input-method . "latin-1-prefix")
485	(sample-text . "Oi")
486	(documentation . "Support for Brazilian Portuguese."))
487	'("European"))
488
489	(set-language-info-alist
490	"Esperanto" '((tutorial . "TUTORIAL.eo")
491	(charset ascii latin-iso8859-3)
492	(coding-system iso-latin-3)
493	(coding-priority iso-latin-3)
494	(nonascii-translation . latin-iso8859-3)
495	(unibyte-syntax . "latin-3")
496	(unibyte-display . iso-latin-3)
497	(input-method . "latin-3-prefix")
498	(documentation . "Support for Esperanto with ISO-8859-3 character set."))
499	'("European"))
500
501
502	;; Definitions for the Mac Roman character sets and coding system.
503	;; The Mac Roman encoding uses all 128 code points in the range 128 to
504	;; 255 for actual characters. Emacs decodes them to one of the
505	;; following character sets.
506	;; ascii, latin-iso8859-1, mule-unicode-0100-24ff,
507	;; mule-unicode-2500-33ff, mule-unicode-e000-ffff
508
509	(let
510	((encoding-vector (make-vector 256 nil))
511	(i 0)
512	(vec ;; mac-roman (128..255) -> UCS mapping
513	[ #x00C4 ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS
514	#x00C5 ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE
515	#x00C7 ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA
516	#x00C9 ;; 131:LATIN CAPITAL LETTER E WITH ACUTE
517	#x00D1 ;; 132:LATIN CAPITAL LETTER N WITH TILDE
518	#x00D6 ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS
519	#x00DC ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS
520	#x00E1 ;; 135:LATIN SMALL LETTER A WITH ACUTE
521	#x00E0 ;; 136:LATIN SMALL LETTER A WITH GRAVE
522	#x00E2 ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX
523	#x00E4 ;; 138:LATIN SMALL LETTER A WITH DIAERESIS
524	#x00E3 ;; 139:LATIN SMALL LETTER A WITH TILDE
525	#x00E5 ;; 140:LATIN SMALL LETTER A WITH RING ABOVE
526	#x00E7 ;; 141:LATIN SMALL LETTER C WITH CEDILLA
527	#x00E9 ;; 142:LATIN SMALL LETTER E WITH ACUTE
528	#x00E8 ;; 143:LATIN SMALL LETTER E WITH GRAVE
529	#x00EA ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX
530	#x00EB ;; 145:LATIN SMALL LETTER E WITH DIAERESIS
531	#x00ED ;; 146:LATIN SMALL LETTER I WITH ACUTE
532	#x00EC ;; 147:LATIN SMALL LETTER I WITH GRAVE
533	#x00EE ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX
534	#x00EF ;; 149:LATIN SMALL LETTER I WITH DIAERESIS
535	#x00F1 ;; 150:LATIN SMALL LETTER N WITH TILDE
536	#x00F3 ;; 151:LATIN SMALL LETTER O WITH ACUTE
537	#x00F2 ;; 152:LATIN SMALL LETTER O WITH GRAVE
538	#x00F4 ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX
539	#x00F6 ;; 154:LATIN SMALL LETTER O WITH DIAERESIS
540	#x00F5 ;; 155:LATIN SMALL LETTER O WITH TILDE
541	#x00FA ;; 156:LATIN SMALL LETTER U WITH ACUTE
542	#x00F9 ;; 157:LATIN SMALL LETTER U WITH GRAVE
543	#x00FB ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX
544	#x00FC ;; 159:LATIN SMALL LETTER U WITH DIAERESIS
545	#x2020 ;; 160:DAGGER
546	#x00B0 ;; 161:DEGREE SIGN
547	#x00A2 ;; 162:CENT SIGN
548	#x00A3 ;; 163:POUND SIGN
549	#x00A7 ;; 164:SECTION SIGN
550	#x2022 ;; 165:BULLET
551	#x00B6 ;; 166:PILCROW SIGN
552	#x00DF ;; 167:LATIN SMALL LETTER SHARP S
553	#x00AE ;; 168:REGISTERED SIGN
554	#x00A9 ;; 169:COPYRIGHT SIGN
555	#x2122 ;; 170:TRADE MARK SIGN
556	#x00B4 ;; 171:ACUTE ACCENT
557	#x00A8 ;; 172:DIAERESIS
558	#x2260 ;; 173:NOT EQUAL TO
559	#x00C6 ;; 174:LATIN CAPITAL LETTER AE
560	#x00D8 ;; 175:LATIN CAPITAL LETTER O WITH STROKE
561	#x221E ;; 176:INFINITY
562	#x00B1 ;; 177:PLUS-MINUS SIGN
563	#x2264 ;; 178:LESS-THAN OR EQUAL TO
564	#x2265 ;; 179:GREATER-THAN OR EQUAL TO
565	#x00A5 ;; 180:YEN SIGN
566	#x00B5 ;; 181:MICRO SIGN
567	#x2202 ;; 182:PARTIAL DIFFERENTIAL
568	#x2211 ;; 183:N-ARY SUMMATION
569	#x220F ;; 184:N-ARY PRODUCT
570	#x03C0 ;; 185:GREEK SMALL LETTER PI
571	#x222B ;; 186:INTEGRAL
572	#x00AA ;; 187:FEMININE ORDINAL INDICATOR
573	#x00BA ;; 188:MASCULINE ORDINAL INDICATOR
574	#x03A9 ;; 189:GREEK CAPITAL LETTER OMEGA
575	#x00E6 ;; 190:LATIN SMALL LETTER AE
576	#x00F8 ;; 191:LATIN SMALL LETTER O WITH STROKE
577	#x00BF ;; 192:INVERTED QUESTION MARK
578	#x00A1 ;; 193:INVERTED EXCLAMATION MARK
579	#x00AC ;; 194:NOT SIGN
580	#x221A ;; 195:SQUARE ROOT
581	#x0192 ;; 196:LATIN SMALL LETTER F WITH HOOK
582	#x2248 ;; 197:ALMOST EQUAL TO
583	#x2206 ;; 198:INCREMENT
584	#x00AB ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
585	#x00BB ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
586	#x2026 ;; 201:HORIZONTAL ELLIPSIS
587	#x00A0 ;; 202:NO-BREAK SPACE
588	#x00C0 ;; 203:LATIN CAPITAL LETTER A WITH GRAVE
589	#x00C3 ;; 204:LATIN CAPITAL LETTER A WITH TILDE
590	#x00D5 ;; 205:LATIN CAPITAL LETTER O WITH TILDE
591	#x0152 ;; 206:LATIN CAPITAL LIGATURE OE
592	#x0153 ;; 207:LATIN SMALL LIGATURE OE
593	#x2013 ;; 208:EN DASH
594	#x2014 ;; 209:EM DASH
595	#x201C ;; 210:LEFT DOUBLE QUOTATION MARK
596	#x201D ;; 211:RIGHT DOUBLE QUOTATION MARK
597	#x2018 ;; 212:LEFT SINGLE QUOTATION MARK
598	#x2019 ;; 213:RIGHT SINGLE QUOTATION MARK
599	#x00F7 ;; 214:DIVISION SIGN
600	#x25CA ;; 215:LOZENGE
601	#x00FF ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS
602	#x0178 ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS
603	#x2044 ;; 218:FRACTION SLASH
604	#x20AC ;; 219:EURO SIGN
605	#x2039 ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK
606	#x203A ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
607	#xFB01 ;; 222:LATIN SMALL LIGATURE FI
608	#xFB02 ;; 223:LATIN SMALL LIGATURE FL
609	#x2021 ;; 224:DOUBLE DAGGER
610	#x00B7 ;; 225:MIDDLE DOT
611	#x201A ;; 226:SINGLE LOW-9 QUOTATION MARK
612	#x201E ;; 227:DOUBLE LOW-9 QUOTATION MARK
613	#x2030 ;; 228:PER MILLE SIGN
614	#x00C2 ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX
615	#x00CA ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX
616	#x00C1 ;; 231:LATIN CAPITAL LETTER A WITH ACUTE
617	#x00CB ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS
618	#x00C8 ;; 233:LATIN CAPITAL LETTER E WITH GRAVE
619	#x00CD ;; 234:LATIN CAPITAL LETTER I WITH ACUTE
620	#x00CE ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX
621	#x00CF ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS
622	#x00CC ;; 237:LATIN CAPITAL LETTER I WITH GRAVE
623	#x00D3 ;; 238:LATIN CAPITAL LETTER O WITH ACUTE
624	#x00D4 ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX
625	#xF8FF ;; 240:Apple logo
626	#x00D2 ;; 241:LATIN CAPITAL LETTER O WITH GRAVE
627	#x00DA ;; 242:LATIN CAPITAL LETTER U WITH ACUTE
628	#x00DB ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX
629	#x00D9 ;; 244:LATIN CAPITAL LETTER U WITH GRAVE
630	#x0131 ;; 245:LATIN SMALL LETTER DOTLESS I
631	#x02C6 ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT
632	#x02DC ;; 247:SMALL TILDE
633	#x00AF ;; 248:MACRON
634	#x02D8 ;; 249:BREVE
635	#x02D9 ;; 250:DOT ABOVE
636	#x02DA ;; 251:RING ABOVE
637	#x00B8 ;; 252:CEDILLA
638	#x02DD ;; 253:DOUBLE ACUTE ACCENT
639	#x02DB ;; 254:OGONEK
640	#x02C7 ;; 255:CARON
641	])
642	translation-table)
643	(while (< i 128)
644	(aset encoding-vector i i)
645	(setq i (1+ i)))
646	(while (< i 256)
647	(aset encoding-vector i
648	(decode-char 'ucs (aref vec (- i 128))))
649	(setq i (1+ i)))
650	(setq translation-table
651	(make-translation-table-from-vector encoding-vector))
652	(define-translation-table 'mac-roman-decoder translation-table)
653	(define-translation-table 'mac-roman-encoder
654	(char-table-extra-slot translation-table 0)))
655
656	(define-ccl-program decode-mac-roman
657	`(4
658	((loop
659	(read r1)
660	(if (r1 < 128) ;; ASCII
661	(r0 = ,(charset-id 'ascii))
662	(if (r1 < 160)
663	(r0 = ,(charset-id 'eight-bit-control))
664	(r0 = ,(charset-id 'eight-bit-graphic))))
665	(translate-character mac-roman-decoder r0 r1)
666	(write-multibyte-character r0 r1)
667	(repeat))))
668	"CCL program to decode Mac Roman")
669
670	(define-ccl-program encode-mac-roman
671	`(1
672	((loop
673	(read-multibyte-character r0 r1)
674	(translate-character ucs-mule-to-mule-unicode r0 r1)
675	(translate-character mac-roman-encoder r0 r1)
676	(if (r0 != ,(charset-id 'ascii))
677	(if (r0 != ,(charset-id 'eight-bit-graphic))
678	(if (r0 != ,(charset-id 'eight-bit-control))
679	(r1 = ??))))
680	(write-repeat r1))))
681	"CCL program to encode Mac Roman")
682
683	(make-coding-system
684	'mac-roman 4 ?M
685	"Mac Roman Encoding (MIME:MACINTOSH)."
686	'(decode-mac-roman . encode-mac-roman)
687	(list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table))
688	'(valid-codes (0 . 255))
689	'(mime-charset . macintosh))) ; per IANA, rfc1345
690
691	(defconst diacritic-composition-pattern "\\C^\\c^+")
692
693	(defun diacritic-compose-region (beg end)
694	"Compose diacritic characters in the region.
695	When called from a program, expects two arguments,
696	positions (integers or markers) specifying the region."
697	(interactive "r")
698	(save-restriction
699	(narrow-to-region beg end)
700	(goto-char (point-min))
701	(while (re-search-forward diacritic-composition-pattern nil t)
702	(compose-region (match-beginning 0) (match-end 0)))))
703
704	(defun diacritic-compose-string (string)
705	"Compose diacritic characters in STRING and return the resulting string."
706	(let ((idx 0))
707	(while (setq idx (string-match diacritic-composition-pattern string idx))
708	(compose-string string idx (match-end 0))
709	(setq idx (match-end 0))))
710	string)
711
712	(defun diacritic-compose-buffer ()
713	"Compose diacritic characters in the current buffer."
714	(interactive)
715	(diacritic-compose-region (point-min) (point-max)))
716
717	(defun diacritic-post-read-conversion (len)
718	(diacritic-compose-region (point) (+ (point) len))
719	len)
720
721	(defun diacritic-composition-function (from to pattern &optional string)
722	"Compose diacritic text in the region FROM and TO.
723	The text matches the regular expression PATTERN.
724	Optional 4th argument STRING, if non-nil, is a string containing text
725	to compose.
726
727	The return value is the number of composed characters."
728	(when (< (1+ from) to)
729	(if string
730	(compose-string string from to)
731	(compose-region from to))
732	(- to from)))
733
734	;; Register a function to compose Unicode diacrtics and marks.
735	(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
736	(let ((c #x300))
737	(while (<= c #x362)
738	(aset composition-function-table (decode-char 'ucs c) patterns)
739	(setq c (1+ c)))
740	(setq c #x20d0)
741	(while (<= c #x20e3)
742	(aset composition-function-table (decode-char 'ucs c) patterns)
743	(setq c (1+ c)))))
744
745	(provide 'european)
746
747	;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
748	;;; european.el ends here
749

Note: See TracBrowser for help on using the browser.

root/trunk/lisp/language/european.el

Download in other formats: