;;; 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) 2001 Free Software Foundation, Inc.
+;; 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
;; You should have received a copy of the GNU General Public License
;; along with GNU Emacs; see the file COPYING. If not, write to the
-;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
-;; Boston, MA 02111-1307, USA.
+;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
+;; Boston, MA 02110-1301, USA.
;;; Commentary:
-;; For European scripts, 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)
- (coding-priority iso-latin-1)
+ (coding-priority iso-latin-1 windows-1252)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(unibyte-display . iso-latin-1)
We also have specific language environments for the following languages:
For Dutch, \"Dutch\".
For German, \"German\".
- For Spanish, \"Spanish\".
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])))
+
+(define-coding-system-alias 'cp1252 'windows-1252)
+
\f
;; Latin-2 (ISO-8859-2)
'iso-latin-2 2 ?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"))
'iso-latin-3 2 ?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)))
'iso-latin-4 2 ?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)))
'iso-latin-5 2 ?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)))
; for `Celtic' is taken.
"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)))
'iso-latin-9 2 ?0 ; `0' for `Latin-0'
"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-priority iso-latin-1)
+ (coding-system iso-latin-1 iso-latin-9)
+ (coding-priority iso-latin-1 windows-1252)
(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 . "\
(set-language-info-alist
"French" '((tutorial . "TUTORIAL.fr")
(charset ascii latin-iso8859-1)
- (coding-system iso-latin-1)
+ (coding-system iso-latin-1 iso-latin-9)
(coding-priority iso-latin-1)
(nonascii-translation . latin-iso8859-1)
(unibyte-syntax . "latin-1")
(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."))
+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!")
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 it selects 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")
(unibyte-display . iso-latin-5)
(input-method . "turkish-postfix")
(sample-text . "Turkish (T\e,M|\e(Brk\e,Mg\e(Be) Merhaba")
- (documentation . t)))
+ (documentation . t)
+ (setup-function . turkish-case-conversion-enable)
+ (exit-function . turkish-case-conversion-disable)))
+
+(defun turkish-case-conversion-enable ()
+ "Set up Turkish case conversion of `i' and `I' into `\e$,1 P\e(B' and `\e$,1 Q\e(B'."
+ (let ((table (standard-case-table)))
+ (set-case-syntax-pair ?\e$,1 P\e(B ?i table)
+ (set-case-syntax-pair ?I ?\e$,1 Q\e(B table)))
+
+(defun turkish-case-conversion-disable ()
+ "Set up normal (non-Turkish) case conversion of `i' into `I'."
+ (let ((table (standard-case-table)))
+ (set-case-syntax-pair ?I ?i table)
+ (set-case-syntax ?\e$,1 P\e(B "w" table)
+ (set-case-syntax ?\e$,1 Q\e(B "w" table)))
;; Polish ISO 8859-2 environment.
;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
(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)
- ;; Fixme: input-method
+ (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"))
"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"))
"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")
'mac-roman 4 ?M
"Mac Roman Encoding (MIME:MACINTOSH)."
'(decode-mac-roman . encode-mac-roman)
- '((safe-chars . (get 'mac-roman-encoder 'translation-table))
- (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^+")
(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)
Optional 4th argument STRING, if non-nil, is a string containing text
to compose.
-The return value is number of composed characters."
- (if (< (1+ from) to)
- (prog1 (- to from)
- (if string
- (compose-string string from to)
- (compose-region from to))
- (- to from))))
+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))))
(provide 'european)
+;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
;;; european.el ends here