[Emacs-diffs] Changes to emacs/lisp/language/chinese.el,v

[Miles Bader]

CVSROOT:        /cvsroot/emacs
Module name:    emacs
Changes by:     Miles Bader <miles>     08/02/01 16:01:31

Index: lisp/language/chinese.el
===================================================================
RCS file: /cvsroot/emacs/emacs/lisp/language/chinese.el,v
retrieving revision 1.37
retrieving revision 1.38
diff -u -b -r1.37 -r1.38
--- lisp/language/chinese.el    8 Jan 2008 20:45:57 -0000       1.37
+++ lisp/language/chinese.el    1 Feb 2008 16:01:02 -0000       1.38
@@ -6,6 +6,9 @@
 ;;   2005, 2006, 2007, 2008
 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
 ;;   Registration Number H14PRO021
+;; Copyright (C) 2003
+;;   National Institute of Advanced Industrial Science and Technology (AIST)
+;;   Registration Number H13PRO009
 
 ;; Keywords: multilingual, Chinese
 
@@ -37,85 +40,72 @@
 ;;; Chinese (general)
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-(make-coding-system
- 'iso-2022-cn 2 ?C
+
+(define-coding-system 'iso-2022-cn
  "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)."
- '(ascii
+  :coding-type 'iso-2022
+  :mnemonic ?C
+  :charset-list '(ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
+  :designation [ascii
    (nil chinese-gb2312 chinese-cns11643-1)
    (nil chinese-cns11643-2)
-   nil
-   nil ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
-   init-bol)
- '((safe-charsets ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
-   (mime-charset . iso-2022-cn)))
+               nil]
+  :flags '(ascii-at-eol ascii-at-cntl 7-bit
+                       designation locking-shift single-shift init-at-bol)
+  :mime-charset 'iso-2022-cn
+  :suitable-for-keyboard t)
 
 (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
 
-(make-coding-system
- 'iso-2022-cn-ext 2 ?C
+(define-coding-system 'iso-2022-cn-ext
  "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)."
- '(ascii
+  :coding-type 'iso-2022
+  :mnemonic ?C
+  :charset-list '(ascii
+                 chinese-gb2312 chinese-cns11643-1
+                 chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
+                 chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
+  :designation '[ascii
    (nil chinese-gb2312 chinese-cns11643-1)
    (nil chinese-cns11643-2)
    (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
-       chinese-cns11643-6 chinese-cns11643-7)
-   nil ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
-   init-bol)
- '((safe-charsets ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2
-                 chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
-                 chinese-cns11643-6 chinese-cns11643-7)
-   (mime-charset . iso-2022-cn-ext)))
+                     chinese-cns11643-6 chinese-cns11643-7)]
+  :flags '(ascii-at-eol ascii-at-cntl 7-bit
+                       designation locking-shift single-shift init-at-bol)
+  :mime-charset 'iso-2022-cn-ext
+  :suitable-for-keyboard t)
 
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;; Chinese GB2312 (simplified)
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-(make-coding-system
- 'chinese-iso-8bit 2 ?c
+(define-coding-system 'chinese-iso-8bit
  "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:GB2312)."
- '(ascii chinese-gb2312 nil nil
-   nil ascii-eol ascii-cntl nil nil nil nil)
- '((safe-charsets ascii chinese-gb2312)
-   (mime-charset . gb2312)))
+  :coding-type 'iso-2022
+  :mnemonic ?c
+  :charset-list '(ascii chinese-gb2312)
+  :designation [ascii chinese-gb2312 nil nil]
+  :mime-charset 'gb2312)
 
 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
-(define-coding-system-alias 'cp936 'chinese-iso-8bit)
 
-(make-coding-system
- 'chinese-hz 0 ?z
+(define-coding-system 'chinese-hz
  "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
- nil
- '((safe-charsets ascii chinese-gb2312)
-   (mime-charset . hz-gb-2312)
-   (post-read-conversion . post-read-decode-hz)
-   (pre-write-conversion . pre-write-encode-hz)))
+  :coding-type 'utf-8
+  :mnemonic ?z
+  :charset-list '(ascii chinese-gb2312)
+  :mime-charset 'hz-gb-2312
+  :post-read-conversion 'post-read-decode-hz
+  :pre-write-conversion 'pre-write-encode-hz)
 
 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 (define-coding-system-alias 'hz 'chinese-hz)
 
-(defun post-read-decode-hz (len)
-  (let ((pos (point))
-       (buffer-modified-p (buffer-modified-p))
-       last-coding-system-used)
-    (prog1
-       (decode-hz-region pos (+ pos len))
-      (set-buffer-modified-p buffer-modified-p))))
-
-(defun pre-write-encode-hz (from to)
-  (let ((buf (current-buffer)))
-    (set-buffer (generate-new-buffer " *temp*"))
-    (if (stringp from)
-       (insert from)
-      (insert-buffer-substring buf from to))
-    (let (last-coding-system-used)
-      (encode-hz-region 1 (point-max)))
-    nil))
-
 (set-language-info-alist
  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
                (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
@@ -131,181 +121,47 @@
 ;; Chinese BIG5 (traditional)
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-(make-coding-system
- 'chinese-big5 3 ?B
- "BIG5 8-bit encoding for Chinese (MIME:Big5)."
- nil
- '((safe-charsets ascii chinese-big5-1 chinese-big5-2)
-   (mime-charset . big5)
-   (charset-origin-alist (chinese-big5-1  "BIG5" encode-big5-char)
-                        (chinese-big5-2  "BIG5" encode-big5-char))))
+(define-coding-system 'chinese-big5
+  "BIG5 8-bit encoding for Chinese (MIME:Big5)"
+  :coding-type 'charset
+  :mnemonic ?B 
+  :charset-list '(ascii big5)
+  :mime-charset 'big5)
 
 (define-coding-system-alias 'big5 'chinese-big5)
 (define-coding-system-alias 'cn-big5 'chinese-big5)
 (define-coding-system-alias 'cp950 'chinese-big5)
 
-;; Big5 font requires special encoding.
-(define-ccl-program ccl-encode-big5-font
-  `(0
-    ;; In:  R0:chinese-big5-1 or chinese-big5-2
-    ;;      R1:position code 1
-    ;;      R2:position code 2
-    ;; Out: R1:font code point 1
-    ;;      R2:font code point 2
-    ((r2 = ((((r1 - ?\x21) * 94) + r2) - ?\x21))
-     (if (r0 == ,(charset-id 'chinese-big5-2)) (r2 += 6280))
-     (r1 = ((r2 / 157) + ?\xA1))
-     (r2 %= 157)
-     (if (r2 < ?\x3F) (r2 += ?\x40) (r2 += ?\x62))))
-  "CCL program to encode a Big5 code to code point of Big5 font.")
-
-(setq font-ccl-encoder-alist
-      (cons (cons "big5" ccl-encode-big5-font) font-ccl-encoder-alist))
-
 (set-language-info-alist
  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
                  (coding-system chinese-big5 chinese-iso-7bit)
                  (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
                  (input-method . "chinese-py-punct-b5")
+                 (ctext-non-standard-encodings "big5-0")
                  (features china-util)
-                 (sample-text . "Cantonese ($(0GnM$(B,$(0N]0*Hd(B) 
$(0*/=((B, $(0+$)p(B")
+                 (sample-text . "Cantonese ($(Gemk#(B,$(Gl]N)fc(B) 
$ATg3?(B, $ADc:C(B")
                  (documentation . "Support for Chinese Big5 character set.")
                  (tutorial . "TUTORIAL.zh"))
  '("Chinese"))
 
+(define-coding-system 'chinese-big5-hkscs
+  "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement 
(MIME:Big5-HKSCS)"
+  :coding-type 'charset
+  :mnemonic ?B 
+  :charset-list '(ascii big5-hkscs)
+  :mime-charset 'big5-hkscs)
+(define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
+(define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;; Chinese CNS11643 (traditional)
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-(defvar big5-to-cns (make-translation-table)
-  "Translation table for encoding to `euc-tw'.")
-;; Could have been done by china-util loaded before.
-(unless (get 'big5-to-cns 'translation-table)
-  (define-translation-table 'big5-to-cns big5-to-cns))
-
-(define-ccl-program ccl-decode-euc-tw
-  ;; CNS plane 1 needs either two or four bytes in EUC-TW encoding;
-  ;; CNS planes 2 to 7 always need four bytes.  In internal encoding of
-  ;; Emacs, CNS planes 1 and 2 need three bytes, and planes 3 to 7 need
-  ;; four bytes.  Thus a buffer magnification value of 2 (for both
-  ;; encoding and decoding) is sufficient.
-  `(2
-    ;; we don't have enough registers to hold all charset-ids
-    ((r4 = ,(charset-id 'chinese-cns11643-1))
-     (r5 = ,(charset-id 'chinese-cns11643-2))
-     (r6 = ,(charset-id 'chinese-cns11643-3))
-     (loop
-      (read-if (r0 < #x80)
-         ;; ASCII
-         (write-repeat r0)
-       ;; not ASCII
-       (if (r0 == #x8E)
-           ;; single shift
-           (read-if (r1 < #xA1)
-               ;; invalid byte
-               ((write r0)
-                (write-repeat r1))
-             (if (r1 > #xA7)
-                 ;; invalid plane
-                 ((write r0)
-                  (write-repeat r1))
-               ;; OK, we have a plane
-               (read-if (r2 < #xA1)
-                   ;; invalid first byte
-                   ((write r0 r1)
-                    (write-repeat r2))
-                 (read-if (r3 < #xA1)
-                     ;; invalid second byte
-                     ((write r0 r1 r2)
-                      (write-repeat r3))
-                   ;; CNS 1-7, finally
-                   ((branch (r1 - #xA1)
-                     (r1 = r4)
-                     (r1 = r5)
-                     (r1 = r6)
-                     (r1 = ,(charset-id 'chinese-cns11643-4))
-                     (r1 = ,(charset-id 'chinese-cns11643-5))
-                     (r1 = ,(charset-id 'chinese-cns11643-6))
-                     (r1 = ,(charset-id 'chinese-cns11643-7)))
-                    (r2 = ((((r2 - #x80) << 7) + r3) - #x80))
-                    (write-multibyte-character r1 r2)
-                    (repeat))))))
-         ;; standard EUC
-         (if (r0 < #xA1)
-             ;; invalid first byte
-             (write-repeat r0)
-           (read-if (r1 < #xA1)
-               ;; invalid second byte
-               ((write r0)
-                (write-repeat r1))
-             ;; CNS 1, finally
-             ((r1 = ((((r0 - #x80) << 7) + r1) - #x80))
-              (write-multibyte-character r4 r1)
-              (repeat)))))))))
-  "CCL program to decode EUC-TW encoding."
-)
-
-(define-ccl-program ccl-encode-euc-tw
-  `(2
-    ;; we don't have enough registers to hold all charset-ids
-    ((r2 = ,(charset-id 'ascii))
-     (r3 = ,(charset-id 'chinese-big5-1))
-     (r4 = ,(charset-id 'chinese-big5-2))
-     (r5 = ,(charset-id 'chinese-cns11643-1))
-     (r6 = ,(charset-id 'chinese-cns11643-2))
-     (loop
-      (read-multibyte-character r0 r1)
-      (if (r0 == r2)
-         (write-repeat r1)
-       (;; Big 5 encoded characters are first translated to CNS
-        (if (r0 == r3)
-            (translate-character big5-to-cns r0 r1)
-          (if (r0 == r4)
-              (translate-character big5-to-cns r0 r1)))
-        (if (r0 == r5)
-            (r0 = #xA1)
-          (if (r0 == r6)
-              (r0 = #xA2)
-            (if (r0 == ,(charset-id 'chinese-cns11643-3))
-                (r0 = #xA3)
-              (if (r0 == ,(charset-id 'chinese-cns11643-4))
-                  (r0 = #xA4)
-                (if (r0 == ,(charset-id 'chinese-cns11643-5))
-                    (r0 = #xA5)
-                  (if (r0 == ,(charset-id 'chinese-cns11643-6))
-                      (r0 = #xA6)
-                    (if (r0 == ,(charset-id 'chinese-cns11643-7))
-                        (r0 = #xA7)
-                      ;; not CNS.  We use a dummy character which
-                      ;; can't occur in EUC-TW encoding to indicate
-                      ;; this.
-                      (write-repeat #xFF))))))))))
-      (if (r0 != #xA1)
-         ;; single shift and CNS plane
-         ((write #x8E)
-          (write r0)))
-      (write ((r1 >> 7) + #x80))
-      (write ((r1 % #x80) + #x80))
-      (repeat))))
-  "CCL program to encode EUC-TW encoding."
-)
-
-(defun euc-tw-pre-write-conversion (beg end)
-  "Semi-dummy pre-write function effectively to autoload china-util."
-  ;; Ensure translation table is loaded.
-  (require 'china-util)
-  ;; Don't do this again.
-  (coding-system-put 'euc-tw 'pre-write-conversion nil)
-  nil)
-
-(make-coding-system
-  'euc-tw 4 ?Z
-  "ISO 2022 based EUC encoding for Chinese CNS11643.
-Big5 encoding is accepted for input also (which is then converted to CNS)."
-  '(ccl-decode-euc-tw . ccl-encode-euc-tw)
-  '((safe-charsets ascii
-                  chinese-big5-1
-                  chinese-big5-2
+(define-coding-system 'euc-tw
+  "ISO 2022 based EUC encoding for Chinese CNS11643."
+  :coding-type 'iso-2022
+  :mnemonic ?Z
+  :charset-list '(ascii
                   chinese-cns11643-1
                   chinese-cns11643-2
                   chinese-cns11643-3
@@ -313,8 +169,14 @@
                   chinese-cns11643-5
                   chinese-cns11643-6
                   chinese-cns11643-7)
-    (valid-codes (0 . 255))
-    (pre-write-conversion . euc-tw-pre-write-conversion)))
+  :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
+                                         chinese-cns11643-2
+                                         chinese-cns11643-3
+                                         chinese-cns11643-4
+                                         chinese-cns11643-5
+                                         chinese-cns11643-6
+                                         chinese-cns11643-7) nil]
+  :mime-charset 'euc-tw)
 
 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 
@@ -328,6 +190,7 @@
                                  chinese-iso-8bit)
                 (features china-util)
                 (input-method . "chinese-cns-quick")
+                ;; Fixme: presumably it won't accept big5 now.
                 (documentation . "\
 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 accepts Big5 for input also (which is then converted to CNS)."))
@@ -349,6 +212,60 @@
 converted to CNS)."))
  '("Chinese"))
 
+
+;;; Chinese GBK
+
+(define-coding-system 'chinese-gbk
+  "GBK encoding for Chinese (MIME:GBK)."
+  :coding-type 'charset
+  :mnemonic ?c
+  :charset-list '(ascii chinese-gbk)
+  :mime-charset 'gbk)
+(define-coding-system-alias 'gbk 'chinese-gbk)
+(define-coding-system-alias 'cp936 'chinese-gbk)
+(define-coding-system-alias 'windows-936 'chinese-gbk)
+
+(set-language-info-alist
+ "Chinese-GBK" '((charset chinese-gbk)
+                (coding-system chinese-gbk)
+                (coding-priority gbk iso-2022-cn chinese-big5
+                                 chinese-iso-8bit) ; fixme?
+                (ctext-non-standard-encodings "gbk-0")          
+                (input-method . "chinese-py-punct") ; fixme?
+                (sample-text . "Chinese 
($BCfJ8(B,$BIaDL$A;0(B,$A::So(B) $(D95$B9%(B")
+                (features china-util)
+                (documentation . "Support for Chinese GBK character set.")
+                (tutorial . "TUTORIAL.cn"))
+ '("Chinese"))
+
+;;; Chinese GB18030
+
+(define-coding-system 'chinese-gb18030
+  "GB18030 encoding for Chinese (MIME:GB18030)."
+  :coding-type 'charset
+  :mnemonic ?c
+  :charset-list '(ascii gb18030-2-byte
+                       gb18030-4-byte-bmp gb18030-4-byte-smp
+                       gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
+  :mime-charset 'gb18030)
+
+(define-coding-system-alias 'gb18030 'chinese-gb18030)
+
+(set-language-info-alist
+ "Chinese-GB18030" '((charset gb18030)
+                    (coding-system chinese-gb18030)
+                    (coding-priority gb18030 gbk iso-2022-cn chinese-big5
+                                     chinese-iso-8bit) ; fixme?
+                    (input-method . "chinese-py-punct") ; fixme?
+                    (sample-text . "Chinese 
($BCfJ8(B,$BIaDL$A;0(B,$A::So(B) $(D0_$B9%(B")
+                    (features china-util)
+                    (documentation
+                     . "Support for Chinese GB18030 character set.")
+                    (tutorial . "TUTORIAL.cn"))
+ '("Chinese"))
+
+;; Fixme: add HKSCS
+
 (provide 'chinese)
 
 ;;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f