[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Emacs-diffs] Changes to emacs/lisp/international/utf-8.el [lexbind]
From: |
Miles Bader |
Subject: |
[Emacs-diffs] Changes to emacs/lisp/international/utf-8.el [lexbind] |
Date: |
Thu, 28 Oct 2004 22:27:54 -0400 |
Index: emacs/lisp/international/utf-8.el
diff -c emacs/lisp/international/utf-8.el:1.13.2.8
emacs/lisp/international/utf-8.el:1.13.2.9
*** emacs/lisp/international/utf-8.el:1.13.2.8 Sat Sep 4 09:26:22 2004
--- emacs/lisp/international/utf-8.el Fri Oct 29 02:05:07 2004
***************
*** 194,206 ****
(defconst utf-translate-cjk-charsets '(chinese-gb2312
chinese-big5-1 chinese-big5-2
japanese-jisx0208 japanese-jisx0212
korean-ksc5601)
"List of charsets supported by `utf-translate-cjk-mode'.")
! (defconst utf-translate-cjk-unicode-range
! '((#x2e80 . #xd7a3)
! (#xff00 . #xffef))
! "List of Unicode code ranges supported by `utf-translate-cjk-mode'.")
;; Return non-nil if CODE-POINT is in `utf-translate-cjk-unicode-range'.
(defsubst utf-translate-cjk-substitutable-p (code-point)
--- 194,281 ----
(defconst utf-translate-cjk-charsets '(chinese-gb2312
chinese-big5-1 chinese-big5-2
japanese-jisx0208 japanese-jisx0212
+ katakana-jisx0201
korean-ksc5601)
"List of charsets supported by `utf-translate-cjk-mode'.")
! (defvar utf-translate-cjk-lang-env nil
! "Language environment in which tables for `utf-translate-cjk-mode' is
loaded.
! The value nil means that the tables are not yet loaded.")
!
! (defvar utf-translate-cjk-unicode-range)
!
! ;; String generated from utf-translate-cjk-unicode-range. It is
! ;; suitable for an argument to skip-chars-forward.
! (defvar utf-translate-cjk-unicode-range-string nil)
!
! (defun utf-translate-cjk-set-unicode-range (range)
! (setq utf-translate-cjk-unicode-range range)
! (setq utf-translate-cjk-unicode-range-string
! (let ((decode-char-no-trans
! #'(lambda (x)
! (cond ((< x #x100) (make-char 'latin-iso8859-1 x))
! ((< x #x2500)
! (setq x (- x #x100))
! (make-char 'mule-unicode-0100-24ff
! (+ (/ x 96) 32) (+ (% x 96) 32)))
! ((< x #x3400)
! (setq x (- x #x2500))
! (make-char 'mule-unicode-2500-33ff
! (+ (/ x 96) 32) (+ (% x 96) 32)))
! (t
! (setq x (- x #xe000))
! (make-char 'mule-unicode-e000-ffff
! (+ (/ x 96) 32) (+ (% x 96) 32))))))
! ranges from to)
! (dolist (elt range)
! (setq from (max #xA0 (car elt)) to (min #xffff (cdr elt)))
! (if (and (>= to #x3400) (< to #xE000))
! (setq to #x33FF))
! (cond ((< from #x100)
! (if (>= to #xE000)
! (setq ranges (cons (cons #xE000 to) ranges)
! to #x33FF))
! (if (>= to #x2500)
! (setq ranges (cons (cons #x2500 to) ranges)
! to #x24FF))
! (if (>= to #x100)
! (setq ranges (cons (cons #x100 to) ranges)
! to #xFF)))
! ((< from #x2500)
! (if (>= to #xE000)
! (setq ranges (cons (cons #xE000 to) ranges)
! to #x33FF))
! (if (>= to #x2500)
! (setq ranges (cons (cons #x2500 to) ranges)
! to #x24FF)))
! ((< from #x3400)
! (if (>= to #xE000)
! (setq ranges (cons (cons #xE000 to) ranges)
! to #x33FF))))
! (if (<= from to)
! (setq ranges (cons (cons from to) ranges))))
! (mapconcat #'(lambda (x)
! (format "%c-%c"
! (funcall decode-char-no-trans (car x))
! (funcall decode-char-no-trans (cdr x))))
! ranges "")))
! ;; These forces loading and settting tables for
! ;; utf-translate-cjk-mode.
! (setq utf-translate-cjk-lang-env nil
! ucs-mule-cjk-to-unicode (make-hash-table :test 'eq)
! ucs-unicode-to-mule-cjk (make-hash-table :test 'eq)))
!
! (defcustom utf-translate-cjk-unicode-range '((#x2e80 . #xd7a3)
! (#xff00 . #xffef))
! "List of Unicode code ranges supported by `utf-translate-cjk-mode'.
! Setting this variable directly does not take effect;
! use either \\[customize] or the function
! `utf-translate-cjk-set-unicode-range'."
! :version "21.4"
! :type '(repeat (cons integer integer))
! :set (lambda (symbol value)
! (utf-translate-cjk-set-unicode-range value))
! :group 'mule)
;; Return non-nil if CODE-POINT is in `utf-translate-cjk-unicode-range'.
(defsubst utf-translate-cjk-substitutable-p (code-point)
***************
*** 213,222 ****
(setq elt nil)))
elt))
- (defvar utf-translate-cjk-lang-env nil
- "Language environment in which tables for `utf-translate-cjk-mode' is
loaded.
- The value nil means that the tables are not yet loaded.")
-
(defun utf-translate-cjk-load-tables ()
"Load tables for `utf-translate-cjk-mode'."
;; Fixme: Allow the use of the CJK charsets to be
--- 288,293 ----
***************
*** 425,449 ****
;; 2-byte encoding 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
((r1 &= #x3F)
(r1 |= ((r0 & #x1F) << 6))
! ;; Now r2 holds scalar value. We don't have to check
;; `overlong sequence' because r0 >= 0xC2.
(if (r1 >= 256)
;; mule-unicode-0100-24ff (< 0800)
! ((r0 = ,(charset-id 'mule-unicode-0100-24ff))
! (r1 -= #x0100)
! (r2 = (((r1 / 96) + 32) << 7))
! (r1 %= 96)
! (r1 += (r2 + 32))
! (translate-character
! utf-translation-table-for-decode r0 r1)
(write-multibyte-character r0 r1)
(read r0)
(repeat))
(if (r1 >= 160)
;; latin-iso8859-1
! ((r1 -= 128)
! (write-multibyte-character r6 r1)
(read r0)
(repeat))
;; eight-bit-control
--- 496,527 ----
;; 2-byte encoding 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
((r1 &= #x3F)
(r1 |= ((r0 & #x1F) << 6))
! ;; Now r1 holds scalar value. We don't have to check
;; `overlong sequence' because r0 >= 0xC2.
(if (r1 >= 256)
;; mule-unicode-0100-24ff (< 0800)
! ((r0 = r1)
! (lookup-integer utf-subst-table-for-decode r0 r1)
! (if (r7 == 0)
! ((r0 = ,(charset-id 'mule-unicode-0100-24ff))
! (r1 -= #x0100)
! (r2 = (((r1 / 96) + 32) << 7))
! (r1 %= 96)
! (r1 += (r2 + 32))
! (translate-character
! utf-translation-table-for-decode r0 r1)))
(write-multibyte-character r0 r1)
(read r0)
(repeat))
(if (r1 >= 160)
;; latin-iso8859-1
! ((r0 = r1)
! (lookup-integer utf-subst-table-for-decode r0 r1)
! (if (r7 == 0)
! ((r1 -= 128)
! (write-multibyte-character r6 r1))
! ((write-multibyte-character r0 r1)))
(read r0)
(repeat))
;; eight-bit-control
***************
*** 482,494 ****
(if (r3 < #x2500)
;; mule-unicode-0100-24ff (>= 0800)
! ((r0 = ,(charset-id 'mule-unicode-0100-24ff))
! (r3 -= #x0100)
! (r3 //= 96)
! (r1 = (r7 + 32))
! (r1 += ((r3 + 32) << 7))
! (translate-character
! utf-translation-table-for-decode r0 r1)
(write-multibyte-character r0 r1)
(read r0)
(repeat)))
--- 560,575 ----
(if (r3 < #x2500)
;; mule-unicode-0100-24ff (>= 0800)
! ((r0 = r3)
! (lookup-integer utf-subst-table-for-decode r0 r1)
! (if (r7 == 0)
! ((r0 = ,(charset-id 'mule-unicode-0100-24ff))
! (r3 -= #x0100)
! (r3 //= 96)
! (r1 = (r7 + 32))
! (r1 += ((r3 + 32) << 7))
! (translate-character
! utf-translation-table-for-decode r0 r1)))
(write-multibyte-character r0 r1)
(read r0)
(repeat)))
***************
*** 874,890 ****
hash-table ch)
(set-buffer-multibyte t)
(when utf-translate-cjk-mode
! (if (not utf-translate-cjk-lang-env)
! ;; Check these characters:
! ;; "U+2e80-U+33ff", "U+ff00-U+ffef"
! ;; We may have to translate them to CJK charsets.
! (let ((range2 "$,address@hidden(B-$,2G$,3r`(B-$,3u/(B"))
! (skip-chars-forward (concat range range2))
! (unless (eobp)
! (utf-translate-cjk-load-tables)
! (setq range (concat range range2)))
! (setq hash-table (get 'utf-subst-table-for-decode
! 'translation-hash-table)))))
(while (and (skip-chars-forward range)
(not (eobp)))
(setq ch (following-char))
--- 955,971 ----
hash-table ch)
(set-buffer-multibyte t)
(when utf-translate-cjk-mode
! (unless utf-translate-cjk-lang-env
! ;; Check these characters in utf-translate-cjk-range.
! ;; We may have to translate them to CJK charsets.
! (skip-chars-forward
! (concat range utf-translate-cjk-unicode-range-string))
! (unless (eobp)
! (utf-translate-cjk-load-tables)
! (setq range
! (concat range utf-translate-cjk-unicode-range-string)))
! (setq hash-table (get 'utf-subst-table-for-decode
! 'translation-hash-table))))
(while (and (skip-chars-forward range)
(not (eobp)))
(setq ch (following-char))
[Prev in Thread] |
Current Thread |
[Next in Thread] |
- [Emacs-diffs] Changes to emacs/lisp/international/utf-8.el [lexbind],
Miles Bader <=