-;;; european.el --- support for European languages -*- coding: iso-2022-7bit; -*-
+;;; european.el --- support for European languages -*- coding: utf-8; -*-
-;; Copyright (C) 1997, 1998, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
-;; Free Software Foundation, Inc.
+;; Copyright (C) 1997-1998, 2000-2016 Free Software Foundation, Inc.
;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
-;; 2005, 2006, 2007
+;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; Registration Number H14PRO021
;; Copyright (C) 2003
;; This file is part of GNU Emacs.
-;; GNU Emacs is free software; you can redistribute it and/or modify
+;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
-;; the Free Software Foundation; either version 2, or (at your option)
-;; any later version.
+;; the Free Software Foundation, either version 3 of the License, or
+;; (at your option) any later version.
;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; GNU General Public License for more details.
;; 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., 51 Franklin Street, Fifth Floor,
-;; Boston, MA 02110-1301, USA.
+;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
;;; Commentary:
(unibyte-display . iso-latin-1)
(input-method . "latin-1-prefix")
(sample-text
- . "Hello, Hej, Tere, Hei, Bonjour, Gr\e$(D+d)N\e(B Gott, Ciao, \e$(D"B\e(BHola!")
+ . "Hello, Hej, Tere, Hei, Bonjour, Grüß Gott, Ciao, ¡Hola!")
(documentation . "\
This language environment is a generic one for the Latin-1 (ISO-8859-1)
character set which supports the following European languages:
(input-method . "latin-4-postfix")
(documentation . "\
These languages are supported with the Latin-4 (ISO-8859-4) character set:
- Danish, English, Estonian, Finnish, German, Greenlandic, Lappish,
- Latvian, Lithuanian, and Norwegian."))
+ Danish, English, Estonian, Finnish, German, Greenlandic, Latvian,
+ Lithuanian, Norwegian, and Sami."))
'("European"))
\f
"ISO 2022 based 8-bit encoding for Latin-8 (MIME:ISO-8859-14)."
:coding-type 'charset
;; `W' for `Welsh', since `C' for `Celtic' is taken.
- :mnemonic ?W
+ :mnemonic ?W
:charset-list '(iso-8859-14)
:mime-charset 'iso-8859-14)
(unibyte-display . iso-latin-8)
(input-method . "latin-8-prefix")
;; Fixme: Welsh/Ga{e}lic greetings
- (sample-text . "\e,_"\e(B \e$(D+q\e(B \e$(D*t\e(B")
+ (sample-text . "ḃ ŵ Ŷ")
(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
(unibyte-display . iso-latin-9)
(input-method . "latin-9-prefix")
(sample-text
- . "AVE. \e$(D*^+^*v+v)-)M*s\e(B \e$(Q)!\e(B")
+ . "AVE. ŠšŽžŒœŸ €")
(documentation . "\
This language environment is a generic one for the Latin-9 (ISO-8859-15)
character set which supports the same languages as Latin-1 with the
(set-language-info-alist
"Esperanto" '((tutorial . "TUTORIAL.eo")
- (charset ascii latin-iso8859-3)
+ (charset iso-8859-3)
(coding-system iso-latin-3)
(coding-priority iso-latin-3)
(nonascii-translation . latin-iso8859-3)
:mime-charset 'windows-1257)
(define-coding-system-alias 'cp1257 'windows-1257)
+(define-coding-system 'cp775
+ "DOS codepage 775 (PC Baltic, MS-DOS Baltic Rim)"
+ :coding-type 'charset
+ :mnemonic ?D
+ :charset-list '(cp775)
+ :mime-charset 'cp775)
+(define-coding-system-alias 'ibm775 'cp775)
+
(define-coding-system 'cp850
"DOS codepage 850 (Western European)"
:coding-type 'charset
(unibyte-display . iso-latin-1)
(sample-text . "\
German (Deutsch Nord) Guten Tag
-German (Deutsch S\e$(D+d\e(Bd) Gr\e$(D+d)N\e(B Gott")
+German (Deutsch Süd) Grüß Gott")
(documentation . "\
This language environment is almost the same as Latin-1,
but sets the default input method to \"german-postfix\".
(nonascii-translation . iso-8859-1)
(unibyte-display . iso-latin-1)
(input-method . "latin-1-prefix")
- (sample-text . "French (Fran\e$(D+.\e(Bais) Bonjour, Salut")
+ (sample-text . "French (Français) Bonjour, Salut")
(documentation . "\
This language environment is almost the same as Latin-1,
but it selects the French tutorial and input method."))
(input-method . "slovenian")
(unibyte-display . iso-8859-2)
(tutorial . "TUTORIAL.sl")
- (sample-text . "\e$(D*v\e(Belimo vam uspe\e$(D+^\e(Ben dan!")
+ (sample-text . "Želimo vam uspešen dan!")
(documentation . "\
This language environment is almost the same as Latin-2,
but it selects the Slovenian tutorial and input method."))
(input-method . "spanish-postfix")
(nonascii-translation . iso-8859-1)
(unibyte-display . iso-latin-1)
- (sample-text . "Spanish (Espa\e$(D+P\e(Bol) \e$(D"B\e(BHola!")
+ (sample-text . "Spanish (Español) ¡Hola!")
(documentation . "\
This language environment is almost the same as Latin-1,
but it sets the default input method to \"spanish-postfix\",
(nonascii-translation . iso-8859-9)
(unibyte-display . iso-latin-5)
(input-method . "turkish-postfix")
- (sample-text . "Turkish (T\e$(D+d\e(Brk\e$(D+.\e(Be) Merhaba")
+ (sample-text . "Turkish (Türkçe) Merhaba")
(setup-function . turkish-case-conversion-enable)
(setup-function . turkish-case-conversion-disable)
(documentation . "Support for Turkish.
Differs from the Latin-5 environment in using the `turkish-postfix' input
-method and applying Turkish case rules for the characters i, I, \e$(D)E\e(B, \e$(D*D\e(B.")))
+method and applying Turkish case rules for the characters i, I, ı, İ.")))
(defun turkish-case-conversion-enable ()
- "Set up Turkish case conversion of `i' and `I' into `\e$(D*D\e(B' and `\e$(D)E\e(B'."
+ "Set up Turkish case conversion of `i' and `I' into `İ' and `ı'."
(let ((table (standard-case-table)))
- (set-case-syntax-pair ?\e$(D*D\e(B ?i table)
- (set-case-syntax-pair ?I ?\e$(D)E\e(B table)))
+ (set-case-syntax-pair ?İ ?i table)
+ (set-case-syntax-pair ?I ?ı table)))
(defun turkish-case-conversion-disable ()
"Set up normal (non-Turkish) case conversion of `i' into `I'."
(let ((table (standard-case-table)))
(set-case-syntax-pair ?I ?i table)
- (set-case-syntax ?\e$(D*D\e(B "w" table)
- (set-case-syntax ?\e$(D)E\e(B "w" table)))
+ (set-case-syntax ?İ "w" table)
+ (set-case-syntax ?ı "w" table)))
;; Polish ISO 8859-2 environment.
;; Maintainer: Wlodek Bzyl <matwb@univ.gda.pl>
(nonascii-translation . iso-8859-2)
(unibyte-display . iso-8859-2)
(tutorial . "TUTORIAL.pl")
- (sample-text . "P\e$(D+Q\e(Bjd\e$(D+u\e(B, ki\e$(D+M\e(B-\e$(D+w\e(Be t\e$(D+8\e(B chmurno\e$(D+\++\e(B w g\e$(D)H+(\e(Bb flaszy")
+ (sample-text . "Pójdź, kiń-że tę chmurność w głąb flaszy")
(documentation . t))
'("European"))
(documentation . "Support for Brazilian Portuguese."))
'("European"))
+(set-language-info-alist
+ "Catalan" '((charset iso-8859-1)
+ (coding-system iso-8859-1 iso-8859-15)
+ (coding-priority iso-8859-1)
+ (input-method . "catalan-prefix")
+ (nonascii-translation . iso-8859-1)
+ (unibyte-display . iso-8859-1)
+ (setup-function
+ . (lambda ()
+ (modify-syntax-entry ?· "w" (standard-syntax-table))))
+ (exit-function
+ . (lambda ()
+ (modify-syntax-entry ?· "_" (standard-syntax-table))))
+ (sample-text . "\
+Catalan (Català) Avui demà i ahir s'esfullarà una rosa.")
+ (documentation . "\
+This language environment uses the ISO-8859-1 character set,
+sets the default input method to \"catalan-prefix\", and sets
+the syntax of the middle dot character `·' to word."))
+ '("European"))
+
+
\f
(define-coding-system 'mac-roman
"Mac Roman Encoding (MIME:MACINTOSH)."
:coding-type 'charset
- :mnemonic ?M
+ :mnemonic ?M
:charset-list '(mac-roman)
:mime-charset 'macintosh)
+(define-coding-system-alias 'macintosh 'mac-roman)
(define-coding-system 'next
"NeXTstep encoding"
:charset-list '(adobe-standard-encoding)
:mime-charset 'adobe-standard-encoding)
-\f
-;; For automatic composing of diacritics and combining marks.
-(dolist (range '( ;; combining diacritical marks
- (#x0300 #x0314 (tc . bc))
- (#x0315 (tr . bl))
- (#x0316 #x0319 (bc . tc))
- (#x031A (tr . cl))
- (#x031B #x0320 (bc . tc))
- (#x0321 (Br . tr))
- (#x0322 (Br . tl))
- (#x0323 #x0333 (bc . tc))
- (#x0334 #x0338 (Bc . Bc))
- (#x0339 #x033C (bc . tc))
- (#x033D #x033F (tc . bc))
- (#x0340 (tl . bc))
- (#x0341 (tr . bc))
- (#x0342 #x0344 (tc . bc))
- (#x0345 (bc . tc))
- (#x0346 (tc . bc))
- (#x0347 #x0349 (bc . tc))
- (#x034A #x034C (tc . bc))
- (#x034D #x034E (bc . tc))
- ;; combining diacritical marks for symbols
- (#x20D0 #x20D1 (tc . bc))
- (#x20D2 #x20D3 (Bc . Bc))
- (#x20D4 #x20D7 (tc . bc))
- (#x20D8 #x20DA (Bc . Bc))
- (#x20DB #x20DC (tc . bc))
- (#x20DD #x20E0 (Bc . Bc))
- (#x20E1 (tc . bc))
- (#x20E2 #x20E3 (Bc . Bc))))
- (let* ((from (car range))
- (to (if (= (length range) 3)
- (nth 1 range)
- from))
- (composition (car (last range))))
- (while (<= from to)
- (put-char-code-property from 'diacritic-composition composition)
- (aset composition-function-table from 'diacritic-composition-function)
- (setq from (1+ from)))))
-
-(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)
- (if (= (char-syntax (char-after (match-beginning 0))) ?w)
- (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))
- (if (= (char-syntax (aref string idx)) ?w)
- (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-composition-function (pos &optional string)
- "Compose diacritic text around POS.
-Optional 2nd argument STRING, if non-nil, is a string containing text
-to compose.
-
-The return value is the end position of composed characters,
-or nil if no characters are composed."
- (setq pos (1- pos))
- (if string
- (if (>= pos 0)
- (let ((ch (aref string pos))
- start end components ch composition)
- (when (= (char-syntax ch) ?w)
- (setq start pos
- end (length string)
- components (list ch)
- pos (1+ pos))
- (while (and
- (< pos end)
- (setq ch (aref string pos)
- composition
- (get-char-code-property ch
- 'diacritic-composition)))
- (setq components (cons ch (cons composition components))
- pos (1+ pos)))
- (compose-string string start pos (nreverse components))
- pos)))
- (if (>= pos (point-min))
- (let ((ch (char-after pos))
- start end components composition)
- (when (= (char-syntax ch) ?w)
- (setq start pos
- end (point-max)
- components (list ch)
- pos (1+ pos))
- (while (and
- (< pos end)
- (setq ch (char-after pos)
- composition
- (get-char-code-property ch 'diacritic-composition)))
- (setq components (cons ch (cons composition components))
- pos (1+ pos)))
- (compose-region start pos (nreverse components))
- pos)))))
-
(provide 'european)
-;;; arch-tag: 9e018b12-fb02-4120-907b-9adeaf84b5c2
;;; european.el ends here