comparison lisp/international/utf-8.el @ 50179:65bb5afb37ef

(utf-fragment-on-decoding): Don't call register-char-codings. (utf-fragment-on-decoding): Don't update char-coding-system-table. (utf-translate-cjk): Don't call register-char-codings nor optimize-char-coding-system-table. Don't update char-coding-system-table.

50178:61194aef8668

;; Fixme: note that reading and writing invalid utf-8 may not be
;; idempotent -- to represent the bytes to fix that needs a new charset.
;;
;; Characters from other character sets can be encoded with mule-utf-8
;; by populating the translation table
;; `utf-translation-table-for-encode' and registering the translation
;; with `register-char-codings'.  Hash tables
;; `utf-subst-table-for-decode' and `utf-subst-table-for-encode' are
;; used to support encoding and decoding of about a quarter of the CJK
;; space between U+3400 and U+DFFF.

;; UTF-8 is defined in RFC 2279.  A sketch of the encoding is:

	       ;; utf-fragmentation-table.
	       (unless (eq (get 'utf-translation-table-for-encode
				'translation-table)
			   ucs-mule-to-mule-unicode)
		 (define-translation-table 'utf-translation-table-for-encode
		   utf-defragmentation-table)
		 (dolist (coding '(mule-utf-8 mule-utf-16-be mule-utf-16-le))
		   (register-char-codings coding utf-defragmentation-table))))
	   (define-translation-table 'utf-translation-table-for-decode)
	   ;; When unify-8859-on-encoding-mode is off, be sure to make
	   ;; mule-utf-* disabled for characters in
	   ;; utf-fragmentation-table.
	   (unless (eq (get 'utf-translation-table-for-encode
			    'translation-table)
		       ucs-mule-to-mule-unicode)
	     (define-translation-table 'utf-translation-table-for-encode)
	     (map-char-table
	      (lambda (key val)
		(if (and (>= key 128) val)
		    (aset char-coding-system-table key
			  (remq 'mule-utf-8
				(remq 'mule-utf-16-le
				      (remq 'mule-utf-16-be
					    (aref char-coding-system-table
						  key)))))))
	      utf-defragmentation-table)))
	 (set-default s v))
  :version "21.4"
  :type 'boolean
  :group 'mule)

		 (load "subst-jis")))   ; jis covers as much as big5, gb2312
	       (let ((table (make-char-table 'translation-table)))
		 (maphash (lambda (k v)
			    (aset table k t))
			  ucs-mule-cjk-to-unicode)
		 (register-char-codings 'mule-utf-8 table)
		 (register-char-codings 'mule-utf-16-le table)
		 (register-char-codings 'mule-utf-16-be table))
	       (define-translation-hash-table 'utf-subst-table-for-decode
		 ucs-unicode-to-mule-cjk)
	       (define-translation-hash-table 'utf-subst-table-for-encode
		 ucs-mule-cjk-to-unicode))
	   (map-char-table
	    (lambda (k v)
	      (if (gethash k ucs-mule-cjk-to-unicode)
		  (aset char-coding-system-table k
			(remq 'mule-utf-8
			      (remq 'mule-utf-16-le
				    (remq 'mule-utf-16-be v))))))
	    char-coding-system-table)
	   (define-translation-hash-table 'utf-subst-table-for-decode
	     (make-hash-table :test 'eq))
	   (define-translation-hash-table 'utf-subst-table-for-encode
	     (make-hash-table :test 'eq)))
	 (optimize-char-coding-system-table)
	 (set-default s v))
  :version "21.4"
  :type 'boolean
  :set-after '(current-language-environment)
  :group 'mule)

50179:65bb5afb37ef

;; Fixme: note that reading and writing invalid utf-8 may not be
;; idempotent -- to represent the bytes to fix that needs a new charset.
;;
;; Characters from other character sets can be encoded with mule-utf-8
;; by populating the translation table
;; `utf-translation-table-for-encode'.  Hash tables
;; `utf-subst-table-for-decode' and `utf-subst-table-for-encode' are
;; used to support encoding and decoding of about a quarter of the CJK
;; space between U+3400 and U+DFFF.

;; UTF-8 is defined in RFC 2279.  A sketch of the encoding is:

	       ;; utf-fragmentation-table.
	       (unless (eq (get 'utf-translation-table-for-encode
				'translation-table)
			   ucs-mule-to-mule-unicode)
		 (define-translation-table 'utf-translation-table-for-encode
		   utf-defragmentation-table)))
	   (define-translation-table 'utf-translation-table-for-decode)
	   ;; When unify-8859-on-encoding-mode is off, be sure to make
	   ;; mule-utf-* disabled for characters in
	   ;; utf-fragmentation-table.
	   (unless (eq (get 'utf-translation-table-for-encode
			    'translation-table)
		       ucs-mule-to-mule-unicode)
	     (define-translation-table 'utf-translation-table-for-encode)))
	 (set-default s v))
  :version "21.4"
  :type 'boolean
  :group 'mule)

		 (load "subst-jis")))   ; jis covers as much as big5, gb2312
	       (let ((table (make-char-table 'translation-table)))
		 (maphash (lambda (k v)
			    (aset table k t))
			  ucs-mule-cjk-to-unicode)
	       (define-translation-hash-table 'utf-subst-table-for-decode
		 ucs-unicode-to-mule-cjk)
	       (define-translation-hash-table 'utf-subst-table-for-encode
		 ucs-mule-cjk-to-unicode))
	   (define-translation-hash-table 'utf-subst-table-for-decode
	     (make-hash-table :test 'eq))
	   (define-translation-hash-table 'utf-subst-table-for-encode
	     (make-hash-table :test 'eq))))
	 (set-default s v))
  :version "21.4"
  :type 'boolean
  :set-after '(current-language-environment)
  :group 'mule)