X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/ed7f1a6c5caaf4159125c08db5d18c5471fdd032..73d213f2816876fe9c6c429e75a3be5454a42b34:/lisp/international/mule-conf.el

diff --git a/lisp/international/mule-conf.el b/lisp/international/mule-conf.el
index 9ba95e4d11..cacfc6b6e9 100644
--- a/lisp/international/mule-conf.el
+++ b/lisp/international/mule-conf.el
@@ -1,6 +1,6 @@
 ;;; mule-conf.el --- configure multilingual environment
 
-;; Copyright (C) 1997-2011  Free Software Foundation, Inc.
+;; Copyright (C) 1997-2016 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
@@ -35,7 +35,9 @@
 
 ;;; Remarks
 
-;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/.
+;; The ISO-IR registry is maintained by the Information Processing
+;; Society of Japan/Information Technology Standards Commission of
+;; Japan (IPSJ/ITSCJ) at https://www.itscj.ipsj.or.jp/itscj_english/.
 ;; Standards docs equivalent to iso-2022 and iso-8859 are at
 ;; http://www.ecma.ch/.
 
@@ -218,7 +220,7 @@
 (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"
@@ -708,7 +710,7 @@
 (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)"
@@ -865,7 +867,7 @@
 
 ;; 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"
@@ -888,21 +890,23 @@
 ;; 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
 			       oriya kannada malayalam gujarati punjabi))
     (define-charset (intern (format "%s-cdac" script))
-      (format "Glyphs of %s script for CDAC font.  Subset of `indian-glyph'."
-	      (capitalize (symbol-name script)))
+      (format
+       "Glyphs of %s script for CDAC font.  Subset of `indian-glyph'."
+       (capitalize (symbol-name script)))
       :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script)))
       :supplementary-p t
       :code-space [0 255]
@@ -912,8 +916,9 @@
   (dolist (script '(devanagari bengali punjabi gujarati
 			       oriya tamil telugu kannada malayalam))
     (define-charset (intern (format "%s-akruti" script))
-      (format "Glyphs of %s script for AKRUTI font.  Subset of `indian-glyph'."
-	      (capitalize (symbol-name script)))
+      (format
+       "Glyphs of %s script for AKRUTI font.  Subset of `indian-glyph'."
+       (capitalize (symbol-name script)))
       :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script)))
       :supplementary-p t
       :code-space [0 255]
@@ -1109,7 +1114,7 @@
   :map "MIK")
 
 (define-charset 'ptcp154
-  "`Paratype' codepage (Asian Cyrillic)"
+  "ParaType codepage (Asian Cyrillic)"
   :short-name "PT154"
   :ascii-compatible-p t
   :code-space [0 255]
@@ -1192,6 +1197,7 @@
 (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)
@@ -1225,6 +1231,18 @@
 (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
@@ -1458,7 +1476,8 @@ 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)
@@ -1507,6 +1526,7 @@ for decoding and encoding files, process I/O, etc."
 (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