;;; mule-conf.el --- configure multilingual environment
-;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
-;; 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
-;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
+;; Copyright (C) 1997-2012 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
(put-charset-property
'emacs :long-name "Emacs")
-(put-charset-property 'eight-bit :docstring "Raw bytes 0-255")
+(put-charset-property 'eight-bit :docstring "Raw bytes 128-255")
(put-charset-property 'eight-bit :short-name "Raw bytes")
(define-charset-alias 'ucs 'unicode)
(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"
:code-offset #x27c218 ; ... #x280839
:unify-map "BIG5-HKSCS")
-;; Fixme: Korean cp949/UHC
+(define-charset 'cp949-2-byte
+ "2-byte part of CP949"
+ :dimension 2
+ :map "CP949-2BYTE"
+ :code-space [#x41 #xFE #x81 #xFD]
+ :supplementary-p t)
+
+(define-charset 'cp949
+ "CP949 (Korean)"
+ :short-name "CP949"
+ :long-name "CP949 (Korean)"
+ :code-space [#x00 #xFE #x00 #xFD]
+ :superset '(ascii cp949-2-byte))
(define-charset 'chinese-sisheng
"SiSheng characters for PinYin/ZhuYin"
(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"
"Raw text, which means text contains random 8-bit codes.
Encoding text with this coding system produces the actual byte
sequence of the text in buffers and strings. An exception is made for
-eight-bit-control characters. Each of them is encoded into a single
-byte.
+characters from the `eight-bit' character set. Each of them is encoded
+into a single byte.
When you visit a file with this coding, the file is read into a
unibyte buffer as is (except for EOL format), thus each byte of a file
:coding-type 'raw-text
:eol-type 'unix
:mnemonic ?=)
-
+
(define-coding-system 'iso-latin-1
"ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
:coding-type 'charset
:mnemonic ?U
:charset-list '(emacs))
+;; The encoding used internally. This encoding is meant to be able to save
+;; any multibyte buffer without losing information. It can change between
+;; Emacs releases, tho, so should only be used for internal files.
+(define-coding-system-alias 'emacs-internal 'utf-8-emacs-unix)
+
(define-coding-system 'utf-16le
"UTF-16LE (little endian, no signature (BOM))."
:coding-type 'utf-16
:mime-charset 'utf-16)
(define-coding-system 'utf-16be-with-signature
- "UTF-16 (big endian, with signature)."
+ "UTF-16 (big endian, with signature (BOM))."
:coding-type 'utf-16
:mnemonic ?U
:charset-list '(unicode)
: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)
;; Tar files are not decoded at all, but we treat them as raw bytes.
(setq file-coding-system-alist
+ (mapcar (lambda (arg) (cons (purecopy (car arg)) (cdr arg)))
'(("\\.elc\\'" . utf-8-emacs)
("\\.utf\\(-8\\)?\\'" . utf-8)
("\\.xml\\'" . xml-find-file-coding-system)
("\\.tar\\'" . (no-conversion . no-conversion))
( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
- ("" . (undecided . nil))))
+ ("" . (undecided . nil)))))
\f
;;; Setting coding categories and their priorities.
;; code.
(provide 'code-pages)
-;; Local variables:
-;; no-byte-compile: t
-;; End:
-
-;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
;;; mule-conf.el ends here