[Emacs-diffs] Changes to emacs/lisp/international/utf-8.el [lexbind]

[Miles Bader]

Index: emacs/lisp/international/utf-8.el
diff -c emacs/lisp/international/utf-8.el:1.13.2.6 
emacs/lisp/international/utf-8.el:1.13.2.7
*** emacs/lisp/international/utf-8.el:1.13.2.6  Tue Jul  6 10:14:26 2004
--- emacs/lisp/international/utf-8.el   Sat Sep  4 09:19:26 2004
***************
*** 273,279 ****
        (utf-translate-cjk-load-tables))
    (gethash code-point
           (get 'utf-subst-table-for-decode 'translation-hash-table)))
!   
  
  (defun utf-lookup-subst-table-for-encode (char)
    (if (and utf-translate-cjk-mode
--- 273,279 ----
        (utf-translate-cjk-load-tables))
    (gethash code-point
           (get 'utf-subst-table-for-decode 'translation-hash-table)))
! 
  
  (defun utf-lookup-subst-table-for-encode (char)
    (if (and utf-translate-cjk-mode
***************
*** 282,290 ****
        (utf-translate-cjk-load-tables))
    (gethash char
           (get 'utf-subst-table-for-encode 'translation-hash-table)))
!   
  (define-minor-mode utf-translate-cjk-mode
!   "Whether the UTF based coding systems should decode/encode CJK characters.
  Enabling this allows the coding systems mule-utf-8,
  mule-utf-16le and mule-utf-16be to encode characters in the charsets
  `korean-ksc5601', `chinese-gb2312', `chinese-big5-1',
--- 282,292 ----
        (utf-translate-cjk-load-tables))
    (gethash char
           (get 'utf-subst-table-for-encode 'translation-hash-table)))
! 
  (define-minor-mode utf-translate-cjk-mode
!   "Toggle whether UTF based coding systems de/encode CJK characters.
! If ARG is an integer, enable if ARG is positive and disable if
! zero or negative.  This is a minor mode.
  Enabling this allows the coding systems mule-utf-8,
  mule-utf-16le and mule-utf-16be to encode characters in the charsets
  `korean-ksc5601', `chinese-gb2312', `chinese-big5-1',
***************
*** 296,304 ****
  turned on: ksc5601 for Korean, gb2312 for Chinese-GB, big5 for
  Chinese-Big5 and jisx for other environments.
  
! This option is on by default.  If you are not interested in CJK
  characters and want to avoid some overhead on encoding/decoding
! by the above coding systems, you can customize this option to nil."
    :init-value t
    :version "21.4"
    :type 'boolean
--- 298,307 ----
  turned on: ksc5601 for Korean, gb2312 for Chinese-GB, big5 for
  Chinese-Big5 and jisx for other environments.
  
! This mode is on by default.  If you are not interested in CJK
  characters and want to avoid some overhead on encoding/decoding
! by the above coding systems, you can customize the user option
! `utf-translate-cjk-mode' to nil."
    :init-value t
    :version "21.4"
    :type 'boolean
***************
*** 605,611 ****
    ;; UTF-8 decoder generates an UTF-8 sequence represented by a
    ;; sequence eight-bit-control/graphic chars for an untranslatable
    ;; character and an invalid byte.
!   ;; 
    ;; This CCL parses that sequence (the first byte is already in r1),
    ;; writes out the original bytes of that sequence, and sets r5 to
    ;; -1.
--- 608,614 ----
    ;; UTF-8 decoder generates an UTF-8 sequence represented by a
    ;; sequence eight-bit-control/graphic chars for an untranslatable
    ;; character and an invalid byte.
!   ;;
    ;; This CCL parses that sequence (the first byte is already in r1),
    ;; writes out the original bytes of that sequence, and sets r5 to
    ;; -1.
***************
*** 624,630 ****
       (read-multibyte-character r5 r6)
       (r0 = (r5 != ,(charset-id 'eight-bit-control)))
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
!        ((write r1)                    ; invalid UTF-8 
          (r1 = -1)
          (end)))
  
--- 627,633 ----
       (read-multibyte-character r5 r6)
       (r0 = (r5 != ,(charset-id 'eight-bit-control)))
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
!        ((write r1)                    ; invalid UTF-8
          (r1 = -1)
          (end)))
  
***************
*** 641,647 ****
       (r1 = -1)
       ;; Read the 3rd byte.
       (read-multibyte-character r5 r6)
!      (r0 = (r5 != ,(charset-id 'eight-bit-control)))         
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
         (end))                         ; invalid UTF-8
       (write r6)
--- 644,650 ----
       (r1 = -1)
       ;; Read the 3rd byte.
       (read-multibyte-character r5 r6)
!      (r0 = (r5 != ,(charset-id 'eight-bit-control)))
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
         (end))                         ; invalid UTF-8
       (write r6)
***************
*** 651,657 ****
          (end)))
       ;; Read the 4th byte.
       (read-multibyte-character r5 r6)
!      (r0 = (r5 != ,(charset-id 'eight-bit-control)))         
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
         (end))                 ; invalid UTF-8
       ;; 4-byte sequence for an untranslated character.
--- 654,660 ----
          (end)))
       ;; Read the 4th byte.
       (read-multibyte-character r5 r6)
!      (r0 = (r5 != ,(charset-id 'eight-bit-control)))
       (if ((r5 != ,(charset-id 'eight-bit-graphic)) & r0)
         (end))                 ; invalid UTF-8
       ;; 4-byte sequence for an untranslated character.