Mercurial > hg > xemacs-beta

diff lisp/mule/mule-coding.el @ 4568:1d74a1d115ee

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add #'query-coding-region tests; do the work necessary to get them running. lisp/ChangeLog addition: 2008-12-28 Aidan Kehoe <kehoea@parhasard.net> * coding.el (default-query-coding-region): Declare using defun*, so we can #'return-from to it on encountering a safe-charsets value of t. Comment out a few debug messages. (query-coding-region): Correct the docstring, it deals with a region, not a string. (unencodable-char-position): Correct the implementation for non-nil COUNT, special-case a zero value for count, treat it as one. Don't rely on dynamic scope when calling the main lambda. * unicode.el (unicode-query-coding-region): Comment out some debug messages here. * mule/mule-coding.el (8-bit-fixed-query-coding-region): Comment out some debug messages here. * code-init.el (raw-text): Add a safe-charsets property to this coding system. * mule/korean.el (iso-2022-int-1): * mule/korean.el (euc-kr): * mule/korean.el (iso-2022-kr): Add safe-charsets properties for these coding systems. * mule/japanese.el (iso-2022-jp): * mule/japanese.el (jis7): * mule/japanese.el (jis8): * mule/japanese.el (shift-jis): * mule/japanese.el (iso-2022-jp-1978-irv): * mule/japanese.el (euc-jp): Add safe-charsets properties for all these coding systems. * mule/iso-with-esc.el: Add safe-charsets properties to all the coding systems in here. Comment on the downside of a safe-charsets value of t for iso-latin-1-with-esc. * mule/hebrew.el (ctext-hebrew): Add a safe-charsets property for this coding system. * mule/devanagari.el (in-is13194-devanagari): Add a safe-charsets property for this coding system. * mule/chinese.el (cn-gb-2312): * mule/chinese.el (hz-gb-2312): * mule/chinese.el (big5): Add safe-charsets properties for these coding systems. * mule/latin.el (iso-8859-14): Add an implementation for this, using #'make-8-bit-coding-system. * mule/mule-coding.el (ctext): * mule/mule-coding.el (iso-2022-8bit-ss2): * mule/mule-coding.el (iso-2022-7bit-ss2): * mule/mule-coding.el (iso-2022-jp-2): * mule/mule-coding.el (iso-2022-7bit): * mule/mule-coding.el (iso-2022-8): * mule/mule-coding.el (escape-quoted): * mule/mule-coding.el (iso-2022-lock): Add safe-charsets properties for all these coding systems. src/ChangeLog addition: 2008-12-28 Aidan Kehoe <kehoea@parhasard.net> * file-coding.c (Fmake_coding_system): Document our use of the safe-chars and safe-charsets properties, and the differences compared to GNU. (make_coding_system_1): Don't drop the safe-chars and safe-charsets properties. (Fcoding_system_property): Return the safe-chars and safe-charsets properties when asked for them. * file-coding.h (CODING_SYSTEM_SAFE_CHARSETS): * coding-system-slots.h: Make the safe-chars and safe-charsets slots available in these headers. tests/ChangeLog addition: 2008-12-28 Aidan Kehoe <kehoea@parhasard.net> * automated/query-coding-tests.el: New file, testing the functionality of #'query-coding-region and #'query-coding-string.
author Aidan Kehoe <kehoea@parhasard.net>
date Sun, 28 Dec 2008 14:46:24 +0000
parents 84d618b355f5
children e0a8715fdb1f
line wrap: on
line diff
--- a/lisp/mule/mule-coding.el	Sat Aug 09 13:15:09 2008 +0200
+++ b/lisp/mule/mule-coding.el	Sun Dec 28 14:46:24 2008 +0000
@@ -104,6 +104,7 @@
  '(charset-g0 ascii
    charset-g1 latin-iso8859-1
    eol-type nil
+   safe-charsets t ;; Reasonable
    mnemonic "CText"))
 
 (make-coding-system
@@ -113,6 +114,9 @@
    charset-g1 latin-iso8859-1
    charset-g2 t ;; unspecified but can be used later.
    short t
+   safe-charsets (ascii katakana-jisx0201 japanese-jisx0208-1978
+                  japanese-jisx0208 japanese-jisx0212 japanese-jisx0213-1
+                  japanese-jisx0213-2)
    mnemonic "ISO8/SS"
    documentation "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
    ))
@@ -124,6 +128,7 @@
    charset-g2 t ;; unspecified but can be used later.
    seven t
    short t
+   safe-charsets t
    mnemonic "ISO7/SS"
    documentation "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
    eol-type nil))
@@ -136,6 +141,7 @@
    charset-g2 t ;; unspecified but can be used later.
    seven t
    short t
+   safe-charsets t
    mnemonic "ISO7/SS"
    eol-type nil))
 
@@ -145,6 +151,7 @@
  '(charset-g0 ascii
    seven t
    short t
+   safe-charsets t
    mnemonic "ISO7"
    documentation "ISO-2022-based 7-bit encoding using only G0"
    ))
@@ -158,6 +165,7 @@
  '(charset-g0 ascii
    charset-g1 latin-iso8859-1
    short t
+   safe-charsets t
    mnemonic "ISO8"
    documentation "ISO-2022 eight-bit coding system.  No single-shift or locking-shift."
    ))
@@ -169,6 +177,7 @@
    charset-g1 latin-iso8859-1
    eol-type lf
    escape-quoted t
+   safe-charsets t
    mnemonic "ESC/Quot"
    documentation "ISO-2022 eight-bit coding system with escape quoting; used for .ELC files."
    ))
@@ -180,6 +189,7 @@
    charset-g1 t ;; unspecified but can be used later.
    seven t
    lock-shift t
+   safe-charsets t
    mnemonic "ISO7/Lock"
    documentation "ISO-2022 coding system using Locking-Shift for 96-charset."
    ))
@@ -574,14 +584,14 @@
       (goto-char begin buffer)
       (skip-chars-forward skip-chars-arg end buffer)
       (while (< (point buffer) end)
-        (message
-	 "fail-range-start is %S, previous-fail %S, point is %S, end is %S"
-	 fail-range-start previous-fail (point buffer) end)
+        ; (message
+	; "fail-range-start is %S, previous-fail %S, point is %S, end is %S"
+	; fail-range-start previous-fail (point buffer) end)
 	(setq char-after (char-after (point buffer) buffer)
 	      fail-range-start (point buffer))
-	(message "arguments are %S %S"
-		 (< (point buffer) end)
-		 (not (gethash (encode-char char-after 'ucs) from-unicode)))
+	; (message "arguments are %S %S"
+	;	 (< (point buffer) end)
+	;	 (not (gethash (encode-char char-after 'ucs) from-unicode)))
 	(while (and
 		(< (point buffer) end)
 		(not (gethash (encode-char char-after 'ucs) from-unicode)))
@@ -593,7 +603,7 @@
 	    ;; system; check the characters past it.
 	    (forward-char 1 buffer)
 	  ;; The character actually failed. 
-	  (message "past the move through, point now %S" (point buffer))
+	  ; (message "past the move through, point now %S" (point buffer))
 	  (when errorp 
 	    (error 'text-conversion-error
 		   (format "Cannot encode %s using coding system"
@@ -608,12 +618,12 @@
 						  (point-max buffer)))
 			   t ranges)
 	  (when highlightp
-	    (message "highlighting")
+	    ; (message "highlighting")
 	    (setq extent (make-extent fail-range-start fail-range-end buffer))
 	    (set-extent-priority extent (+ mouse-highlight-priority 2))
 	    (set-extent-face extent 'query-coding-warning-face))
 	  (skip-chars-forward skip-chars-arg end buffer)))
-      (message "about to give the result, ranges %S" ranges)
+      ; (message "about to give the result, ranges %S" ranges)
       (if failed 
 	  (values nil ranges)
 	(values t nil)))))