;;; mule-conf.el --- configure multilingual environment
-;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
-;; 2004, 2005, 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
-;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
+;; Copyright (C) 1997-2014 Free Software Foundation, Inc.
+;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; Registration Number H14PRO021
;; Copyright (C) 2003
(fmakunbound 'define-iso-single-byte-charset)
;; Can this be shared with 8859-11?
-;; N.b. not all of these are defined unicodes.
+;; N.b. not all of these are defined in Unicode.
(define-charset 'thai-tis620
"TIS620.2533"
:short-name "TIS620.2533"
(define-charset-alias 'cp866u 'cp1125)
;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
-;; shows this as not ASCII comptaible, with various graphics in
+;; shows this as not ASCII compatible, with various graphics in
;; 0x01-0x1F.
(define-charset 'cp437
"CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
;; Lao script.
;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
-;; Not all of them are defined unicodes.
+;; Not all of them are defined in Unicode.
(define-charset 'lao
"Lao characters (ISO10646 0E81..0EDF)"
:short-name "Lao"
;; script which IS-13194 supports.
(define-charset 'indian-is13194
- "Generic Indian charset for data exchange with IS 13194"
- :short-name "IS 13194"
- :long-name "Indian IS 13194"
+ "7-bit representation of IS 13194 (ISCII) for Devanagari"
+ :short-name "IS 13194 (DEV)"
+ :long-name "Indian IS 13194 (DEV)"
:iso-final-char ?5
:emacs-mule-id 225
:supplementary-p t
:code-space [33 126]
- :code-offset #x180000)
+ :code-offset #x180000
+ :unify-map "MULE-is13194")
(let ((code-offset #x180100))
(dolist (script '(devanagari sanskrit bengali tamil telugu assamese
(unify-charset 'ipa)
(unify-charset 'tibetan)
(unify-charset 'ethiopic)
+(unify-charset 'indian-is13194)
(unify-charset 'japanese-jisx0208-1978)
(unify-charset 'japanese-jisx0208)
(unify-charset 'japanese-jisx0212)
(define-coding-system-alias 'dos 'undecided-dos)
(define-coding-system-alias 'mac 'undecided-mac)
+(define-coding-system 'prefer-utf-8
+ "Like `undecided' but prefer UTF-8 when appropriate.
+On decoding, if the source contains 8-bit codes and they all
+are valid UTF-8 sequences, detect the source as UTF-8 encoding
+regardless of the coding priority.
+On encoding, if the source contains non-ASCII characters, encode them
+by UTF-8."
+ :coding-type 'undecided
+ :mnemonic ?-
+ :charset-list '(emacs)
+ :prefer-utf-8 t)
+
(define-coding-system 'raw-text
"Raw text, which means text contains random 8-bit codes.
Encoding text with this coding system produces the actual byte
:flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
(define-coding-system 'compound-text
- "Compound text based generic encoding for decoding unknown messages.
-
-This coding system does not support extended segments of CTEXT."
+ "Compound text based generic encoding.
+This coding system is an extension of X's \"Compound Text Encoding\".
+It encodes many characters using the normal ISO-2022 designation sequences,
+but it doesn't support extended segments of CTEXT."
:coding-type 'iso-2022
:mnemonic ?x
:charset-list 'iso-2022
;; not have a mime-charset property, to prevent it from showing up
;; close to the beginning of coding systems ordered by priority.
(define-coding-system 'ctext-no-compositions
- "Compound text based generic encoding for decoding unknown messages.
+ "Compound text based generic encoding.
Like `compound-text', but does not produce escape sequences for compositions."
:coding-type 'iso-2022
(define-coding-system 'compound-text-with-extensions
"Compound text encoding with ICCCM Extended Segment extensions.
-See the variable `ctext-non-standard-encodings-alist' for the
-detail about how extended segments are handled.
+See the variables `ctext-standard-encodings' and
+`ctext-non-standard-encodings-alist' for the detail about how
+extended segments are handled.
This coding system should be used only for X selections. It is inappropriate
for decoding and encoding files, process I/O, etc."
:flags '(ascii-at-eol ascii-at-cntl long-form
designation locking-shift single-shift)
:post-read-conversion 'ctext-post-read-conversion
- :pre-write-conversion 'ctext-pre-write-conversion)
+ :pre-write-conversion 'ctext-pre-write-conversion
+ :mime-charset 'x-ctext)
(define-coding-system-alias
'x-ctext-with-extensions 'compound-text-with-extensions)
(setq file-coding-system-alist
(mapcar (lambda (arg) (cons (purecopy (car arg)) (cdr arg)))
'(("\\.elc\\'" . utf-8-emacs)
+ ("\\.el\\'" . prefer-utf-8)
("\\.utf\\(-8\\)?\\'" . utf-8)
("\\.xml\\'" . xml-find-file-coding-system)
;; We use raw-text for reading loaddefs.el so that if it
;; code.
(provide 'code-pages)
-;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
;;; mule-conf.el ends here