2 |
|
|
3 |
;; Copyright (C) 1995, 1997, 2001 Electrotechnical Laboratory, JAPAN. |
;; Copyright (C) 1995, 1997, 2001 Electrotechnical Laboratory, JAPAN. |
4 |
;; Licensed to the Free Software Foundation. |
;; Licensed to the Free Software Foundation. |
5 |
;; Copyright (C) 2001 Free Software Foundation, Inc. |
;; Copyright (C) 2001, 2002, 2003 Free Software Foundation, Inc. |
6 |
|
|
7 |
;; Keywords: multilingual, European |
;; Keywords: multilingual, European |
8 |
|
|
32 |
|
|
33 |
;; Latin-1 (ISO-8859-1) |
;; Latin-1 (ISO-8859-1) |
34 |
|
|
|
(make-coding-system |
|
|
'iso-latin-1 2 ?1 |
|
|
"ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)." |
|
|
'(ascii latin-iso8859-1 nil nil |
|
|
nil nil nil nil nil nil nil nil nil nil nil nil t) |
|
|
'((safe-charsets ascii latin-iso8859-1) |
|
|
(mime-charset . iso-8859-1))) |
|
|
|
|
|
(define-coding-system-alias 'iso-8859-1 'iso-latin-1) |
|
|
(define-coding-system-alias 'latin-1 'iso-latin-1) |
|
|
|
|
35 |
(set-language-info-alist |
(set-language-info-alist |
36 |
"Latin-1" '((charset ascii latin-iso8859-1) |
"Latin-1" '((charset ascii latin-iso8859-1) |
37 |
(coding-system iso-latin-1) |
(coding-system iso-latin-1) |
53 |
We also have specific language environments for the following languages: |
We also have specific language environments for the following languages: |
54 |
For Dutch, \"Dutch\". |
For Dutch, \"Dutch\". |
55 |
For German, \"German\". |
For German, \"German\". |
|
For Spanish, \"Spanish\". |
|
56 |
For French, \"French\". |
For French, \"French\". |
57 |
|
For Italian, \"Italian\". |
58 |
|
For Slovenian, \"Slovenian\". |
59 |
|
For Spanish, \"Spanish\". |
60 |
|
|
61 |
Latin-1 also covers several written languages outside Europe, including |
Latin-1 also covers several written languages outside Europe, including |
62 |
Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans.")) |
Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans.")) |
69 |
'iso-latin-2 2 ?2 |
'iso-latin-2 2 ?2 |
70 |
"ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)." |
"ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)." |
71 |
'(ascii latin-iso8859-2 nil nil |
'(ascii latin-iso8859-2 nil nil |
72 |
nil nil nil nil nil nil nil) |
nil nil nil nil nil nil nil nil nil nil nil t) |
73 |
'((safe-charsets ascii latin-iso8859-2) |
'((safe-charsets ascii latin-iso8859-2) |
74 |
(mime-charset . iso-8859-2))) |
(mime-charset . iso-8859-2))) |
75 |
|
|
92 |
and Swedish. |
and Swedish. |
93 |
We also have specific language environments for the following languages: |
We also have specific language environments for the following languages: |
94 |
For Czech, \"Czech\". |
For Czech, \"Czech\". |
95 |
|
For Croatian, \"Croatian\". |
96 |
For Romanian, \"Romanian\". |
For Romanian, \"Romanian\". |
97 |
For Slovak, \"Slovak\".")) |
For Slovak, \"Slovak\".")) |
98 |
'("European")) |
'("European")) |
104 |
'iso-latin-3 2 ?3 |
'iso-latin-3 2 ?3 |
105 |
"ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)." |
"ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)." |
106 |
'(ascii latin-iso8859-3 nil nil |
'(ascii latin-iso8859-3 nil nil |
107 |
nil nil nil nil nil nil nil) |
nil nil nil nil nil nil nil nil nil nil nil t) |
108 |
'((safe-charsets ascii latin-iso8859-3) |
'((safe-charsets ascii latin-iso8859-3) |
109 |
(mime-charset . iso-8859-3))) |
(mime-charset . iso-8859-3))) |
110 |
|
|
132 |
'iso-latin-4 2 ?4 |
'iso-latin-4 2 ?4 |
133 |
"ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)." |
"ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)." |
134 |
'(ascii latin-iso8859-4 nil nil |
'(ascii latin-iso8859-4 nil nil |
135 |
nil nil nil nil nil nil nil) |
nil nil nil nil nil nil nil nil nil nil nil t) |
136 |
'((safe-charsets ascii latin-iso8859-4) |
'((safe-charsets ascii latin-iso8859-4) |
137 |
(mime-charset . iso-8859-4))) |
(mime-charset . iso-8859-4))) |
138 |
|
|
160 |
'iso-latin-5 2 ?9 |
'iso-latin-5 2 ?9 |
161 |
"ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)." |
"ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)." |
162 |
'(ascii latin-iso8859-9 nil nil |
'(ascii latin-iso8859-9 nil nil |
163 |
nil nil nil nil nil nil nil) |
nil nil nil nil nil nil nil nil nil nil nil t) |
164 |
'((safe-charsets ascii latin-iso8859-9) |
'((safe-charsets ascii latin-iso8859-9) |
165 |
(mime-charset . iso-8859-9))) |
(mime-charset . iso-8859-9))) |
166 |
|
|
186 |
; for `Celtic' is taken. |
; for `Celtic' is taken. |
187 |
"ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)." |
"ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)." |
188 |
'(ascii latin-iso8859-14 nil nil |
'(ascii latin-iso8859-14 nil nil |
189 |
nil nil nil nil nil nil nil nil nil nil nil nil t) |
nil nil nil nil nil nil nil nil nil nil nil t t) |
190 |
'((safe-charsets ascii latin-iso8859-14) |
'((safe-charsets ascii latin-iso8859-14) |
191 |
(mime-charset . iso-8859-14))) |
(mime-charset . iso-8859-14))) |
192 |
|
|
216 |
'iso-latin-9 2 ?0 ; `0' for `Latin-0' |
'iso-latin-9 2 ?0 ; `0' for `Latin-0' |
217 |
"ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)." |
"ISO 2022 based 8-bit encoding for Latin-9 (MIME:ISO-8859-15)." |
218 |
'(ascii latin-iso8859-15 nil nil |
'(ascii latin-iso8859-15 nil nil |
219 |
nil nil nil nil nil nil nil nil nil nil nil nil t) |
nil nil nil nil nil nil nil nil nil nil nil t t) |
220 |
'((safe-charsets ascii latin-iso8859-15) |
'((safe-charsets ascii latin-iso8859-15) |
221 |
(mime-charset . iso-8859-15))) |
(mime-charset . iso-8859-15))) |
222 |
|
|
242 |
'("European")) |
'("European")) |
243 |
|
|
244 |
(set-language-info-alist |
(set-language-info-alist |
245 |
|
"Dutch" '((tutorial . "TUTORIAL.nl") |
246 |
|
(charset ascii latin-iso8859-1) |
247 |
|
(coding-system iso-latin-1 iso-latin-9) |
248 |
|
(coding-priority iso-latin-1) |
249 |
|
(nonascii-translation . latin-iso8859-1) |
250 |
|
(unibyte-syntax . "latin-1") |
251 |
|
(unibyte-display . iso-latin-1) |
252 |
|
(input-method . "dutch") |
253 |
|
(sample-text . "Er is een aantal manieren waarop je dit kan doen") |
254 |
|
(documentation . "\ |
255 |
|
This language environment is almost the same as Latin-1, |
256 |
|
but it selects the Dutch tutorial and input method.")) |
257 |
|
'("European")) |
258 |
|
|
259 |
|
(set-language-info-alist |
260 |
"German" '((tutorial . "TUTORIAL.de") |
"German" '((tutorial . "TUTORIAL.de") |
261 |
(charset ascii latin-iso8859-1) |
(charset ascii latin-iso8859-1) |
262 |
(coding-system iso-latin-1) |
(coding-system iso-latin-1 iso-latin-9) |
263 |
(coding-priority iso-latin-1) |
(coding-priority iso-latin-1) |
264 |
(input-method . "german-postfix") |
(input-method . "german-postfix") |
265 |
(nonascii-translation . iso-latin-1) |
(nonascii-translation . latin-iso8859-1) |
266 |
(unibyte-syntax . "latin-1") |
(unibyte-syntax . "latin-1") |
267 |
(unibyte-display . iso-latin-1) |
(unibyte-display . iso-latin-1) |
268 |
(sample-text . "\ |
(sample-text . "\ |
277 |
(set-language-info-alist |
(set-language-info-alist |
278 |
"French" '((tutorial . "TUTORIAL.fr") |
"French" '((tutorial . "TUTORIAL.fr") |
279 |
(charset ascii latin-iso8859-1) |
(charset ascii latin-iso8859-1) |
280 |
(coding-system iso-latin-1) |
(coding-system iso-latin-1 iso-latin-9) |
281 |
(coding-priority iso-latin-1) |
(coding-priority iso-latin-1) |
282 |
(nonascii-translation . latin-iso8859-1) |
(nonascii-translation . latin-iso8859-1) |
283 |
(unibyte-syntax . "latin-1") |
(unibyte-syntax . "latin-1") |
286 |
(sample-text . "French (Fran,Ag(Bais) Bonjour, Salut") |
(sample-text . "French (Fran,Ag(Bais) Bonjour, Salut") |
287 |
(documentation . "\ |
(documentation . "\ |
288 |
This language environment is almost the same as Latin-1, |
This language environment is almost the same as Latin-1, |
289 |
but it selects the French tutorial.")) |
but it selects the French tutorial and input method.")) |
290 |
|
'("European")) |
291 |
|
|
292 |
|
(set-language-info-alist |
293 |
|
"Italian" '((tutorial . "TUTORIAL.it") |
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 . "italian-postfix") |
301 |
|
(sample-text . "Salve, ciao!") |
302 |
|
(documentation . "\ |
303 |
|
This language environment is almost the same as Latin-1, |
304 |
|
but sets the default input method to \"italian-postfix\". |
305 |
|
Additionally, it selects the Italian tutorial.")) |
306 |
'("European")) |
'("European")) |
307 |
|
|
308 |
(set-language-info-alist |
(set-language-info-alist |
310 |
(coding-system . (iso-8859-2)) |
(coding-system . (iso-8859-2)) |
311 |
(coding-priority . (iso-8859-2)) |
(coding-priority . (iso-8859-2)) |
312 |
(nonascii-translation . latin-iso8859-2) |
(nonascii-translation . latin-iso8859-2) |
313 |
(input-method . "latin-2-postfix") |
(input-method . "slovenian") |
314 |
(unibyte-syntax . "latin-2") |
(unibyte-syntax . "latin-2") |
315 |
(unibyte-display . iso-8859-2) |
(unibyte-display . iso-8859-2) |
316 |
(tutorial . "TUTORIAL.sl") |
(tutorial . "TUTORIAL.sl") |
317 |
(sample-text . ",B.(Belimo vam uspe,B9(Ben dan!") |
(sample-text . ",B.(Belimo vam uspe,B9(Ben dan!") |
318 |
(documentation . t)) |
(documentation . "\ |
319 |
|
This language environment is almost the same as Latin-2, |
320 |
|
but it selects the Slovenian tutorial and input method.")) |
321 |
'("European")) |
'("European")) |
322 |
|
|
323 |
(set-language-info-alist |
(set-language-info-alist |
324 |
"Spanish" '((tutorial . "TUTORIAL.es") |
"Spanish" '((tutorial . "TUTORIAL.es") |
325 |
(charset ascii latin-iso8859-1) |
(charset ascii latin-iso8859-1) |
326 |
(coding-system iso-latin-1) |
(coding-system iso-latin-1 iso-latin-9) |
327 |
(coding-priority iso-latin-1) |
(coding-priority iso-latin-1) |
328 |
(input-method . "spanish-postfix") |
(input-method . "spanish-postfix") |
329 |
(nonascii-translation . iso-latin-1) |
(nonascii-translation . latin-iso8859-1) |
330 |
(unibyte-syntax . "latin-1") |
(unibyte-syntax . "latin-1") |
331 |
(unibyte-display . iso-latin-1) |
(unibyte-display . iso-latin-1) |
332 |
(sample-text . "Spanish (Espa,Aq(Bol) ,A!(BHola!") |
(sample-text . "Spanish (Espa,Aq(Bol) ,A!(BHola!") |
336 |
and it selects the Spanish tutorial.")) |
and it selects the Spanish tutorial.")) |
337 |
'("European")) |
'("European")) |
338 |
|
|
|
(set-language-info-alist |
|
|
"Dutch" '((tutorial . "TUTORIAL.nl") |
|
|
(charset ascii latin-iso8859-1) |
|
|
(coding-system iso-latin-1) |
|
|
(coding-priority iso-latin-1) |
|
|
(nonascii-translation . iso-latin-1) |
|
|
(unibyte-syntax . "latin-1") |
|
|
(unibyte-display . iso-latin-1) |
|
|
(sample-text . "Er is een aantal manieren waarop je dit kan doen") |
|
|
(documentation . "\ |
|
|
This language environment is almost the same as Latin-1, |
|
|
but it selects the Dutch tutorial.")) |
|
|
'("European")) |
|
|
|
|
339 |
;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But, |
;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But, |
340 |
;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3) |
;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3) |
341 |
;; was used for Turkish. Those who use Latin-3 for Turkish should use |
;; was used for Turkish. Those who use Latin-3 for Turkish should use |
343 |
|
|
344 |
(set-language-info-alist |
(set-language-info-alist |
345 |
"Turkish" '((charset ascii latin-iso8859-9) |
"Turkish" '((charset ascii latin-iso8859-9) |
346 |
(coding-system iso-latin-5) |
(coding-system iso-latin-5 iso-latin-3) |
347 |
(coding-priority iso-latin-5) |
(coding-priority iso-latin-5) |
348 |
(nonascii-translation . latin-iso8859-9) |
(nonascii-translation . latin-iso8859-9) |
349 |
(unibyte-syntax . "latin-5") |
(unibyte-syntax . "latin-5") |
372 |
(set-language-info-alist |
(set-language-info-alist |
373 |
"Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based |
"Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based |
374 |
(coding-priority utf-8 latin-8) |
(coding-priority utf-8 latin-8) |
375 |
|
(nonascii-translation . latin-iso8859-14) |
376 |
(input-method . "welsh") |
(input-method . "welsh") |
377 |
(documentation . "Support for Welsh, using Unicode.")) |
(documentation . "Support for Welsh, using Unicode.")) |
378 |
'("European")) |
'("European")) |
379 |
|
|
380 |
(set-language-info-alist |
(set-language-info-alist |
381 |
|
"Latin-6" `((coding-system latin-6) |
382 |
|
(coding-priority latin-6) |
383 |
|
(nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table)) |
384 |
|
(input-method . "latin-prefix") |
385 |
|
(features code-pages) |
386 |
|
(documentation . "Support for Latin-6.")) |
387 |
|
'("European")) |
388 |
|
|
389 |
|
(set-language-info-alist |
390 |
"Latin-7" `((coding-system latin-7) |
"Latin-7" `((coding-system latin-7) |
391 |
(coding-priority latin-7) |
(coding-priority latin-7) |
392 |
;; Fixme: input-method |
(nonascii-translation . ,(get 'decode-iso-latin-7 |
393 |
|
'translation-table)) |
394 |
|
(input-method . "latin-prefix") |
395 |
(features code-pages) |
(features code-pages) |
396 |
(documentation . "Support for Latin-7, e.g. Latvian, Lithuanian.")) |
(documentation . "Support for Latin-7, e.g. Latvian, Lithuanian.")) |
397 |
'("European")) |
'("European")) |
400 |
"Lithuanian" `((coding-system latin-7) |
"Lithuanian" `((coding-system latin-7) |
401 |
(coding-priority latin-7) |
(coding-priority latin-7) |
402 |
(input-method . "lithuanian-keyboard") |
(input-method . "lithuanian-keyboard") |
403 |
|
(nonascii-translation . ,(get 'decode-iso-latin-7 |
404 |
|
'translation-table)) |
405 |
(features code-pages) |
(features code-pages) |
406 |
(documentation . "Support for Lithuanian.")) |
(documentation . "Support for Lithuanian.")) |
407 |
'("European")) |
'("European")) |
410 |
"Latvian" `((coding-system latin-7) |
"Latvian" `((coding-system latin-7) |
411 |
(coding-priority latin-7) |
(coding-priority latin-7) |
412 |
(input-method . "latvian-keyboard") |
(input-method . "latvian-keyboard") |
413 |
|
(nonascii-translation . ,(get 'decode-iso-latin-7 |
414 |
|
'translation-table)) |
415 |
(features code-pages) |
(features code-pages) |
416 |
(documentation . "Support for Latvian.")) |
(documentation . "Support for Latvian.")) |
417 |
'("European")) |
'("European")) |
418 |
|
|
419 |
|
(set-language-info-alist |
420 |
|
"Swedish" '((tutorial . "TUTORIAL.sv") |
421 |
|
(charset ascii latin-iso8859-1) |
422 |
|
(coding-system iso-latin-1) |
423 |
|
(coding-priority iso-latin-1) |
424 |
|
(nonascii-translation . latin-iso8859-1) |
425 |
|
(unibyte-syntax . "latin-1") |
426 |
|
(unibyte-display . iso-latin-1) |
427 |
|
(sample-text . "Goddag Hej") |
428 |
|
(documentation . "Support for Swedish")) |
429 |
|
'("European")) |
430 |
|
|
431 |
|
(set-language-info-alist |
432 |
|
"Croatian" '((charset . (ascii latin-iso8859-2)) |
433 |
|
(coding-system . (iso-8859-2)) |
434 |
|
(coding-priority . (iso-8859-2)) |
435 |
|
(input-method . "croatian") |
436 |
|
(nonascii-translation . latin-iso8859-2) |
437 |
|
(unibyte-syntax . "latin-2") |
438 |
|
(unibyte-display . iso-8859-2) |
439 |
|
(documentation . "Support for Croatian with Latin-2 encoding.")) |
440 |
|
'("European")) |
441 |
|
|
442 |
;; Definitions for the Mac Roman character sets and coding system. |
;; Definitions for the Mac Roman character sets and coding system. |
443 |
;; The Mac Roman encoding uses all 128 code points in the range 128 to |
;; The Mac Roman encoding uses all 128 code points in the range 128 to |
590 |
(setq translation-table |
(setq translation-table |
591 |
(make-translation-table-from-vector encoding-vector)) |
(make-translation-table-from-vector encoding-vector)) |
592 |
(define-translation-table 'mac-roman-decoder translation-table) |
(define-translation-table 'mac-roman-decoder translation-table) |
593 |
(define-translation-table 'mac-roman-encoder |
(define-translation-table 'mac-roman-encoder |
594 |
(char-table-extra-slot translation-table 0))) |
(char-table-extra-slot translation-table 0))) |
595 |
|
|
596 |
(define-ccl-program decode-mac-roman |
(define-ccl-program decode-mac-roman |
611 |
`(1 |
`(1 |
612 |
((loop |
((loop |
613 |
(read-multibyte-character r0 r1) |
(read-multibyte-character r0 r1) |
614 |
|
(translate-character ucs-mule-to-mule-unicode r0 r1) |
615 |
(translate-character mac-roman-encoder r0 r1) |
(translate-character mac-roman-encoder r0 r1) |
616 |
|
(if (r0 != ,(charset-id 'ascii)) |
617 |
|
(if (r0 != ,(charset-id 'eight-bit-graphic)) |
618 |
|
(if (r0 != ,(charset-id 'eight-bit-control)) |
619 |
|
(r1 = ??)))) |
620 |
(write-repeat r1)))) |
(write-repeat r1)))) |
621 |
"CCL program to encode Mac Roman") |
"CCL program to encode Mac Roman") |
622 |
|
|
648 |
(compose-string string idx (match-end 0)) |
(compose-string string idx (match-end 0)) |
649 |
(setq idx (match-end 0)))) |
(setq idx (match-end 0)))) |
650 |
string) |
string) |
651 |
|
|
652 |
(defun diacritic-compose-buffer () |
(defun diacritic-compose-buffer () |
653 |
"Compose diacritic characters in the current buffer." |
"Compose diacritic characters in the current buffer." |
654 |
(interactive) |
(interactive) |
664 |
Optional 4th argument STRING, if non-nil, is a string containing text |
Optional 4th argument STRING, if non-nil, is a string containing text |
665 |
to compose. |
to compose. |
666 |
|
|
667 |
The return value is number of composed characters." |
The return value is the number of composed characters." |
668 |
(if (< (1+ from) to) |
(when (< (1+ from) to) |
669 |
(prog1 (- to from) |
(if string |
670 |
(if string |
(compose-string string from to) |
671 |
(compose-string string from to) |
(compose-region from to)) |
672 |
(compose-region from to)) |
(- to from))) |
|
(- to from)))) |
|
673 |
|
|
674 |
;; Register a function to compose Unicode diacrtics and marks. |
;; Register a function to compose Unicode diacrtics and marks. |
675 |
(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function)))) |
(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function)))) |