;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
-;; Copyright (C) 1995, 1997, 2001 Electrotechnical Laboratory, JAPAN.
-;; Licensed to the Free Software Foundation.
+;; Copyright (C) 1997, 1998, 2000, 2001, 2002, 2003, 2004
+;; Free Software Foundation, Inc.
+;; Copyright (C) 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H14PRO021
;; Keywords: multilingual, European
;;; Commentary:
-;; For Europeans, character sets ISO8859-1,2,3,4,9,14,15 are supported.
+;; For European scripts, all the ISO Latin character sets are
+;; supported, along with various others.
;;; Code:
;; Latin-1 (ISO-8859-1)
-(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)
-
(set-language-info-alist
"Latin-1" '((charset ascii latin-iso8859-1)
(coding-system iso-latin-1)
We also have specific language environments for the following languages:
For Dutch, \"Dutch\".
For German, \"German\".
+ For French, \"French\".
+ For Italian, \"Italian\".
+ For Slovenian, \"Slovenian\".
For Spanish, \"Spanish\".
Latin-1 also covers several written languages outside Europe, including
Indonesian/Malay, Tagalog (Philippines), Swahili and Afrikaans."))
'("European"))
+(eval-and-compile
+ (setq
+ non-iso-charset-alist
+ (cp-make-coding-system
+ windows-1252
+ [?\\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
+ ?\\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$,1!8\e(B ?\\e,A \e(B ?\\e,A!\e(B
+ ?\\e,A"\e(B ?\\e,A#\e(B ?\\e,A$\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
+ ?\\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
+ ?\\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
+ ?\\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
+ ?\\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
+ ?\\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\7f\e(B])))
\f
;; Latin-2 (ISO-8859-2)
(make-coding-system
'iso-latin-2 2 ?2
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-2)"
+ "ISO 2022 based 8-bit encoding for Latin-2 (MIME:ISO-8859-2)."
'(ascii latin-iso8859-2 nil nil
- nil nil nil nil nil nil nil)
+ nil nil nil nil nil nil nil nil nil nil nil t)
'((safe-charsets ascii latin-iso8859-2)
(mime-charset . iso-8859-2)))
and Swedish.
We also have specific language environments for the following languages:
For Czech, \"Czech\".
+ For Croatian, \"Croatian\".
For Romanian, \"Romanian\".
For Slovak, \"Slovak\"."))
'("European"))
(make-coding-system
'iso-latin-3 2 ?3
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-3)"
+ "ISO 2022 based 8-bit encoding for Latin-3 (MIME:ISO-8859-3)."
'(ascii latin-iso8859-3 nil nil
- nil nil nil nil nil nil nil)
+ nil nil nil nil nil nil nil nil nil nil nil t)
'((safe-charsets ascii latin-iso8859-3)
(mime-charset . iso-8859-3)))
(make-coding-system
'iso-latin-4 2 ?4
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-4)"
+ "ISO 2022 based 8-bit encoding for Latin-4 (MIME:ISO-8859-4)."
'(ascii latin-iso8859-4 nil nil
- nil nil nil nil nil nil nil)
+ nil nil nil nil nil nil nil nil nil nil nil t)
'((safe-charsets ascii latin-iso8859-4)
(mime-charset . iso-8859-4)))
(make-coding-system
'iso-latin-5 2 ?9
- "ISO 2022 based 8-bit encoding (MIME:ISO-8859-9)"
+ "ISO 2022 based 8-bit encoding for Latin-5 (MIME:ISO-8859-9)."
'(ascii latin-iso8859-9 nil nil
- nil nil nil nil nil nil nil)
+ nil nil nil nil nil nil nil nil nil nil nil t)
'((safe-charsets ascii latin-iso8859-9)
(mime-charset . iso-8859-9)))
(unibyte-syntax . "latin-5")
(unibyte-display . iso-latin-5)
(input-method . "latin-5-postfix")
- (documentation . "\
-These languages are supported with the Latin-5 (ISO-8859-9) character set:
-Bulgarian, Byelorussian, (Slavic) Macedonian, Russian, Serbian and
-Ukranian.")) ; says ISO 8859-1
+ (documentation . "Support for Turkish language."))
'("European"))
\f
(make-coding-system
'iso-latin-8 2 ?W ; `W' for `Welsh', since `C'
; for `Celtic' is taken.
- "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)."
'(ascii latin-iso8859-14 nil nil
- 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)
'((safe-charsets ascii latin-iso8859-14)
(mime-charset . iso-8859-14)))
(documentation . "\
This language environment is a generic one for the Latin-8 (ISO-8859-14)
character set which supports the Celtic languages, including those not
-covered by other ISO-8859 character sets: Welsh, Manx Gaelic and
-Irish Gaelic (old orthography)."))
+covered by other ISO-8859 character sets:
+ Welsh, Manx Gaelic and Irish Gaelic (old orthography)."))
'("European"))
\f
;; Latin-9 (ISO-8859-15)
(make-coding-system
'iso-latin-9 2 ?0 ; `0' for `Latin-0'
- "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)."
'(ascii latin-iso8859-15 nil nil
- 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)
'((safe-charsets ascii latin-iso8859-15)
(mime-charset . iso-8859-15)))
Latin-9 is sometimes nicknamed `Latin-0'."))
'("European"))
\f
+(set-language-info-alist
+ "Dutch" '((tutorial . "TUTORIAL.nl")
+ (charset ascii latin-iso8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "dutch")
+ (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 and input method."))
+ '("European"))
+
(set-language-info-alist
"German" '((tutorial . "TUTORIAL.de")
(charset ascii latin-iso8859-1)
- (coding-system iso-latin-1)
+ (coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(input-method . "german-postfix")
- (nonascii-translation . iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(sample-text . "\
German (Deutsch S\e,A|\e(Bd) Gr\e,A|_\e(B Gott")
(documentation . "\
This language environment is almost the same as Latin-1,
-but the default input method is set to \"german-postfix\"."))
+but sets the default input method to \"german-postfix\".
+Additionally, it selects the German tutorial."))
+ '("European"))
+
+(set-language-info-alist
+ "French" '((tutorial . "TUTORIAL.fr")
+ (charset ascii latin-iso8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "latin-1-prefix")
+ (sample-text . "French (Fran\e,Ag\e(Bais) Bonjour, Salut")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but it selects the French tutorial and input method."))
+ '("European"))
+
+(set-language-info-alist
+ "Italian" '((tutorial . "TUTORIAL.it")
+ (charset ascii latin-iso8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "italian-postfix")
+ (sample-text . "Salve, ciao!")
+ (documentation . "\
+This language environment is almost the same as Latin-1,
+but sets the default input method to \"italian-postfix\".
+Additionally, it selects the Italian tutorial."))
'("European"))
(set-language-info-alist
(coding-system . (iso-8859-2))
(coding-priority . (iso-8859-2))
(nonascii-translation . latin-iso8859-2)
- (input-method . "latin-2-postfix")
+ (input-method . "slovenian")
(unibyte-syntax . "latin-2")
(unibyte-display . iso-8859-2)
(tutorial . "TUTORIAL.sl")
(sample-text . "\e,B.\e(Belimo vam uspe\e,B9\e(Ben dan!")
- (documentation . t))
+ (documentation . "\
+This language environment is almost the same as Latin-2,
+but it selects the Slovenian tutorial and input method."))
'("European"))
(set-language-info-alist
"Spanish" '((tutorial . "TUTORIAL.es")
(charset ascii latin-iso8859-1)
- (coding-system iso-latin-1)
+ (coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(input-method . "spanish-postfix")
- (nonascii-translation . iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
(sample-text . "Spanish (Espa\e,Aq\e(Bol) \e,A!\e(BHola!")
(documentation . "\
This language environment is almost the same as Latin-1,
-but the default input method is set to \"spanish-postfix\",
+but it sets the default input method to \"spanish-postfix\",
and it selects the Spanish tutorial."))
'("European"))
-(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 select's the Dutch tutorial."))
- '("European"))
-
;; For Turkish, the character set ISO-8859-9 (Latin-5) is used. But,
;; before the introduction of ISO-8859-9 in 1988, ISO-8859-3 (Latin-3)
;; was used for Turkish. Those who use Latin-3 for Turkish should use
(set-language-info-alist
"Turkish" '((charset ascii latin-iso8859-9)
- (coding-system iso-latin-5)
+ (coding-system iso-latin-5 iso-latin-3)
(coding-priority iso-latin-5)
(nonascii-translation . latin-iso8859-9)
(unibyte-syntax . "latin-5")
(documentation . t))
'("European"))
+(set-language-info-alist
+ "Welsh" `((coding-system utf-8 latin-8) ; the input method is Unicode-based
+ (coding-priority utf-8 latin-8)
+ (nonascii-translation . latin-iso8859-14)
+ (input-method . "welsh")
+ (documentation . "Support for Welsh, using Unicode."))
+ '("European"))
+
+(set-language-info-alist
+ "Latin-6" `((coding-system latin-6)
+ (coding-priority latin-6)
+ (nonascii-translation . ,(get 'decode-iso-latin-6 'translation-table))
+ (input-method . "latin-prefix")
+ (features code-pages)
+ (documentation . "Support for Latin-6."))
+ '("European"))
+
+(set-language-info-alist
+ "Latin-7" `((coding-system latin-7)
+ (coding-priority latin-7)
+ (nonascii-translation . ,(get 'decode-iso-latin-7
+ 'translation-table))
+ (input-method . "latin-prefix")
+ (features code-pages)
+ (documentation . "Support for Latin-7, e.g. Latvian, Lithuanian."))
+ '("European"))
+
+(set-language-info-alist
+ "Lithuanian" `((coding-system latin-7)
+ (coding-priority latin-7)
+ (input-method . "lithuanian-keyboard")
+ (nonascii-translation . ,(get 'decode-iso-latin-7
+ 'translation-table))
+ (features code-pages)
+ (documentation . "Support for Lithuanian."))
+ '("European"))
+
+(set-language-info-alist
+ "Latvian" `((coding-system latin-7)
+ (coding-priority latin-7)
+ (input-method . "latvian-keyboard")
+ (nonascii-translation . ,(get 'decode-iso-latin-7
+ 'translation-table))
+ (features code-pages)
+ (documentation . "Support for Latvian."))
+ '("European"))
+
+(set-language-info-alist
+ "Swedish" '((tutorial . "TUTORIAL.sv")
+ (charset ascii latin-iso8859-1)
+ (coding-system iso-latin-1)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (sample-text . "Goddag Hej")
+ (documentation . "Support for Swedish"))
+ '("European"))
+
+(set-language-info-alist
+ "Croatian" '((charset . (ascii latin-iso8859-2))
+ (coding-system . (iso-8859-2))
+ (coding-priority . (iso-8859-2))
+ (input-method . "croatian")
+ (nonascii-translation . latin-iso8859-2)
+ (unibyte-syntax . "latin-2")
+ (unibyte-display . iso-8859-2)
+ (documentation . "Support for Croatian with Latin-2 encoding."))
+ '("European"))
+
+(set-language-info-alist
+ "Brazilian Portuguese" '((tutorial . "TUTORIAL.pt_BR")
+ (charset ascii latin-iso8859-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1)
+ (nonascii-translation . latin-iso8859-1)
+ (unibyte-syntax . "latin-1")
+ (unibyte-display . iso-latin-1)
+ (input-method . "latin-1-prefix")
+ (sample-text . "Oi")
+ (documentation . "Support for Brazilian Portuguese."))
+ '("European"))
\f
;; Definitions for the Mac Roman character sets and coding system.
;; The Mac Roman encoding uses all 128 code points in the range 128 to
(setq translation-table
(make-translation-table-from-vector encoding-vector))
(define-translation-table 'mac-roman-decoder translation-table)
- (define-translation-table 'mac-roman-encoder
+ (define-translation-table 'mac-roman-encoder
(char-table-extra-slot translation-table 0)))
(define-ccl-program decode-mac-roman
`(1
((loop
(read-multibyte-character r0 r1)
+ (translate-character ucs-mule-to-mule-unicode r0 r1)
(translate-character mac-roman-encoder r0 r1)
+ (if (r0 != ,(charset-id 'ascii))
+ (if (r0 != ,(charset-id 'eight-bit-graphic))
+ (if (r0 != ,(charset-id 'eight-bit-control))
+ (r1 = ??))))
(write-repeat r1))))
"CCL program to encode Mac Roman")
(make-coding-system
- 'mac-roman 4 ?M "Mac Roman Encoding"
+ 'mac-roman 4 ?M
+ "Mac Roman Encoding (MIME:MACINTOSH)."
'(decode-mac-roman . encode-mac-roman)
- '((safe-chars . mac-roman-encoder)
- (valid-codes (0 . 255))
- (mime-charset . macintosh))) ; per IANA, rfc1345
+ (list (cons 'safe-chars (get 'mac-roman-encoder 'translation-table))
+ '(valid-codes (0 . 255))
+ '(mime-charset . macintosh))) ; per IANA, rfc1345
+
+(defconst diacritic-composition-pattern "\\C^\\c^+")
+
+(defun diacritic-compose-region (beg end)
+ "Compose diacritic characters in the region.
+When called from a program, expects two arguments,
+positions (integers or markers) specifying the region."
+ (interactive "r")
+ (save-restriction
+ (narrow-to-region beg end)
+ (goto-char (point-min))
+ (while (re-search-forward diacritic-composition-pattern nil t)
+ (compose-region (match-beginning 0) (match-end 0)))))
+
+(defun diacritic-compose-string (string)
+ "Compose diacritic characters in STRING and return the resulting string."
+ (let ((idx 0))
+ (while (setq idx (string-match diacritic-composition-pattern string idx))
+ (compose-string string idx (match-end 0))
+ (setq idx (match-end 0))))
+ string)
+
+(defun diacritic-compose-buffer ()
+ "Compose diacritic characters in the current buffer."
+ (interactive)
+ (diacritic-compose-region (point-min) (point-max)))
+
+(defun diacritic-post-read-conversion (len)
+ (diacritic-compose-region (point) (+ (point) len))
+ len)
+
+(defun diacritic-composition-function (from to pattern &optional string)
+ "Compose diacritic text in the region FROM and TO.
+The text matches the regular expression PATTERN.
+Optional 4th argument STRING, if non-nil, is a string containing text
+to compose.
+
+The return value is the number of composed characters."
+ (when (< (1+ from) to)
+ (if string
+ (compose-string string from to)
+ (compose-region from to))
+ (- to from)))
+
+;; Register a function to compose Unicode diacrtics and marks.
+(let ((patterns '(("\\C^\\c^+" . diacritic-composition-function))))
+ (let ((c #x300))
+ (while (<= c #x362)
+ (aset composition-function-table (decode-char 'ucs c) patterns)
+ (setq c (1+ c)))
+ (setq c #x20d0)
+ (while (<= c #x20e3)
+ (aset composition-function-table (decode-char 'ucs c) patterns)
+ (setq c (1+ c)))))
(provide 'european)
+;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
;;; european.el ends here