Mercurial > hg > xemacs-beta

view lisp/mule/chinese.el @ 814:a634e3b7acc8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2002-04-14 12:41:59 by ben] latest changes TODO.ben-mule-21-5: Update. make-docfile.c: Add basic support for handling ISO 2022 doc strings -- we parse the basic charset designation sequences so we know whether we're in ASCII and have to pay attention to end quotes and such. Reformat code according to coding standards. abbrev.el: Add `global-abbrev-mode', which turns on or off abbrev-mode in all buffers. Added `defining-abbrev-turns-on-abbrev-mode' -- if non-nil, defining an abbrev through an interactive function will automatically turn on abbrev-mode, either globally or locally depending on the command. This is the "what you'd expect" behavior. indent.el: general function for indenting a balanced expression in a mode-correct way. Works similar to indent-region in that a mode can specify a specific command to do the whole operation; if not, figure out the region using forward-sexp and indent each line using indent-according-to-mode. keydefs.el: Removed. Modify M-C-backslash to do indent-region-or-balanced-expression. Make S-Tab just insert a TAB char, like it's meant to do. make-docfile.el: Now that we're using the call-process-in-lisp, we need to load an extra file win32-native.el because we're running a bare temacs. menubar-items.el: Totally redo the Cmds menu so that most used commands appear directly on the menu and less used commands appear in submenus. The old way may have been very pretty, but rather impractical. process.el: Under Windows, don't ever use old-call-process-internal, even in batch mode. We can do processes in batch mode. subr.el: Someone recoded truncate-string-to-width, saying "the FSF version is too complicated and does lots of hard-to-understand stuff" but the resulting recoded version was *totally* wrong! it misunderstood the basic point of this function, which is work in *columns* not chars. i dumped ours and copied the version from FSF 21.1. Also added truncate-string-with-continuation-dots, since this idiom is used often. config.inc.samp, xemacs.mak: Separate out debug and optimize flags. Remove all vestiges of USE_MINIMAL_TAGBITS, USE_INDEXED_LRECORD_IMPLEMENTATION, and GUNG_HO, since those ifdefs have long been removed. Make error-checking support actually work. Some rearrangement of config.inc.samp to make it more logical. Remove callproc.c and ntproc.c from xemacs.mak, no longer used. Make pdump the default. lisp.h: Add support for strong type-checking of Bytecount, Bytebpos, Charcount, Charbpos, and others, by making them classes, overloading the operators to provide integer-like operation and carefully controlling what operations are allowed. Not currently enabled in C++ builds because there are still a number of compile errors, and it won't really work till we merge in my "8-bit-Mule" workspace, in which I make use of the new types Charxpos, Bytexpos, Memxpos, representing a "position" either in a buffer or a string. (This is especially important in the extent code.) abbrev.c, alloc.c, eval.c, buffer.c, buffer.h, editfns.c, fns.c, text.h: Warning fixes, some of them related to new C++ strict type checking of Bytecount, Charbpos, etc. dired.c: Caught an actual error due to strong type checking -- char len being passed when should be byte len. alloc.c, backtrace.h, bytecode.c, bytecode.h, eval.c, sysdep.c: Further optimize Ffuncall: -- process arg list at compiled-function creation time, converting into an array for extra-quick access at funcall time. -- rewrite funcall_compiled_function to use it, and inline this function. -- change the order of check for magic stuff in SPECBIND_FAST_UNSAFE to be faster. -- move the check for need to garbage collect into the allocation code, so only a single flag needs to be checked in funcall. buffer.c, symbols.c: add debug funs to check on mule optimization info in buffers and strings. eval.c, emacs.c, text.c, regex.c, scrollbar-msw.c, search.c: Fix evil crashes due to eistrings not properly reinitialized under pdump. Redo a bit some of the init routines; convert some complex_vars_of() into simple vars_of(), because they didn't need complex processing. callproc.c, emacs.c, event-stream.c, nt.c, process.c, process.h, sysdep.c, sysdep.h, syssignal.h, syswindows.h, ntproc.c: Delete. Hallelujah, praise the Lord, there is no god but Allah!!! fix so that processes can be invoked in bare temacs -- thereby eliminating any need for callproc.c. (currently only eliminated under NT.) remove all crufty and unnecessary old process code in ntproc.c and elsewhere. move non-callproc-specific stuff (mostly environment) into process.c, so callproc.c can be left out under NT. console-tty.c, doc.c, file-coding.c, file-coding.h, lstream.c, lstream.h: fix doc string handling so it works with Japanese, etc docs. change handling of "character mode" so callers don't have to manually set it (quite error-prone). event-msw.c: spacing fixes. lread.c: eliminate unused crufty vintage-19 "FSF defun hack" code. lrecord.h: improve pdump description docs. buffer.c, ntheap.c, unexnt.c, win32.c, emacs.c: Mule-ize some unexec and startup code. It was pseudo-Mule-ized before by simply always calling the ...A versions of functions, but that won't cut it -- eventually we want to be able to run properly even if XEmacs has been installed in a Japanese directory. (The current problem is the timing of the loading of the Unicode tables; this will eventually be fixed.) Go through and fix various other places where the code was not Mule-clean. Provide a function mswindows_get_module_file_name() to get our own name without resort to PATH_MAX and such. Add a big comment in main() about the problem with Unicode table load timing that I just alluded to. emacs.c: When error-checking is enabled (interpreted as "user is developing XEmacs"), don't ask user to "pause to read messages" when a fatal error has occurred, because it will wedge if we are in an inner modal loop (typically when a menu is popped up) and make us unable to get a useful stack trace in the debugger. text.c: Correct update_entirely_ascii_p_flag to actually work. lisp.h, symsinit.h: declarations for above changes.
author ben
date Sun, 14 Apr 2002 12:43:31 +0000
parents 0f42d0a17667
children c112a340ac91
line wrap: on
line source

;;; chinese.el --- Support for Chinese -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
;; Copyright (C) 1997 MORIOKA Tomohiko
;; Copyright (C) 2000, 2001, 2002 Ben Wing.

;; Keywords: multilingual, Chinese

;; This file is part of XEmacs.

;; XEmacs is free software; you can redistribute it and/or modify it
;; under the terms of the GNU General Public License as published by
;; the Free Software Foundation; either version 2, or (at your option)
;; any later version.

;; XEmacs is distributed in the hope that it will be useful, but
;; WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;; General Public License for more details.

;; You should have received a copy of the GNU General Public License
;; along with XEmacs; see the file COPYING.  If not, write to the Free
;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
;; 02111-1307, USA.

;;; Commentary:

;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
;; supported.

;;; Code:

(eval-when-compile
  (require 'china-util))

; (make-charset 'chinese-gb2312 
; 	      "GB2312 Chinese simplified: ISO-IR-58"
; 	      '(dimension
; 		2
; 		registry "GB2312.1980"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?A
; 		graphic 0
; 		short-name "GB2312"
; 		long-name "GB2312: ISO-IR-58"
; 		))

; (make-charset 'chinese-cns11643-1 
; 	      "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
; 	      '(dimension
; 		2
; 		registry "CNS11643.1992-1"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?G
; 		graphic 0
; 		short-name "CNS11643-1"
; 		long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
; 		))

; (make-charset 'chinese-cns11643-2 
; 	      "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
; 	      '(dimension
; 		2
; 		registry "CNS11643.1992-2"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?H
; 		graphic 0
; 		short-name "CNS11643-2"
; 		long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
; 		))

; (make-charset 'chinese-big5-1 
; 	      "Frequently used part (A141-C67F) of Big5 (Chinese traditional)"
; 	      '(dimension
; 		2
; 		registry "Big5"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?0
; 		graphic 0
; 		short-name "Big5 (Level-1)"
; 		long-name "Big5 (Level-1) A141-C67F"
; 		))

; (make-charset 'chinese-big5-2 
; 	      "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
; 	      '(dimension
; 		2
; 		registry "Big5"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?1
; 		graphic 0
; 		short-name "Big5 (Level-2)"
; 		long-name "Big5 (Level-2) C940-FEFE"
; 		))

;; Syntax of Chinese characters.
(modify-syntax-entry 'chinese-gb2312 "w")
(loop for row in '(33 34 41)
      do (modify-syntax-entry `[chinese-gb2312 ,row] "."))
;;(loop for row from 35 to  40
;;      do (modify-syntax-entry `[chinese-gb2312 ,row] "w"))
;;(loop for row from 42 to 126
;;      do (modify-syntax-entry `[chinese-gb2312 ,row] "w"))

(modify-syntax-entry 'chinese-cns11643-1  "w")
(modify-syntax-entry 'chinese-cns11643-2  "w")
(modify-syntax-entry 'chinese-big5-1 "w")
(modify-syntax-entry 'chinese-big5-2 "w")

; ;; Chinese CNS11643 Plane3 thru Plane7.  Although these are official
; ;; character sets, the use is rare and don't have to be treated
; ;; space-efficiently in the buffer.
; (make-charset 'chinese-cns11643-3 
; 	      "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
; 	      '(dimension
; 		2
; 		registry "CNS11643.1992-3"
; 		chars 94
; 		columns 2
; 		direction l2r
; 		final ?I
; 		graphic 0
; 		short-name "CNS11643-3"
; 		long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
; 		))

;; CNS11643 Plane3 thru Plane7
;; These represent more and more obscure Chinese characters.
;; By the time you get to Plane 7, we're talking about characters
;; that appear once in some ancient manuscript and whose meaning
;; is unknown.

(flet
    ((make-chinese-cns11643-charset
      (name plane final)
      (make-charset
       name (concat "CNS 11643 Plane " plane " (Chinese traditional)")
       `(registry 
         ,(concat "CNS11643[.-]\\(.*[.-]\\)?" plane "$")
         dimension 2
         chars 94
         final ,final
         graphic 0
	 short-name ,(concat "CNS11643-" plane)
	 long-name ,(format "CNS11643-%s (Chinese traditional): ISO-IR-183"
			    plane)))
      (modify-syntax-entry   name "w")
      (modify-category-entry name ?t)
      ))
  (make-chinese-cns11643-charset 'chinese-cns11643-3 "3" ?I)
  (make-chinese-cns11643-charset 'chinese-cns11643-4 "4" ?J)
  (make-chinese-cns11643-charset 'chinese-cns11643-5 "5" ?K)
  (make-chinese-cns11643-charset 'chinese-cns11643-6 "6" ?L)
  (make-chinese-cns11643-charset 'chinese-cns11643-7 "7" ?M)
  )

;; ISO-IR-165 (CCITT Extended GB)
;;    It is based on CCITT Recommendation T.101, includes GB 2312-80 +
;;    GB 8565-88 table A4 + 293 characters.
(make-charset ;; not in FSF 21.1
 'chinese-isoir165
 "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"
 `(registry "isoir165"
   dimension 2
   chars 94
   final ?E
   graphic 0
   short-name "ISO-IR-165"
   long-name "ISO-IR-165 (CCITT Extended GB; Chinese simplified)"))

;; PinYin-ZhuYin
(make-charset 'chinese-sisheng 
	      "SiSheng characters for PinYin/ZhuYin"
	      '(dimension
		1
		;; XEmacs addition: second half of registry spec
		registry "sisheng_cwnn\\|OMRON_UDC_ZH"
		chars 94
		columns 1
		direction l2r
		final ?0
		graphic 0
		short-name "SiSheng"
		long-name "SiSheng (PinYin/ZhuYin)"
		))

;; If you prefer QUAIL to EGG, please modify below as you wish.
;;(when (and (featurep 'egg) (featurep 'wnn))
;;  (setq wnn-server-type 'cserver)
;;  (load "pinyin")
;;  (setq its:*standard-modes*
;;        (cons (its:get-mode-map "PinYin") its:*standard-modes*)))

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;; Chinese (general)
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;; (make-coding-system
;;  'iso-2022-cn 2 ?C
;;  "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)"
;;  '(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)))

;; (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)

;; (make-coding-system
;;  'iso-2022-cn-ext 2 ?C
;;  "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)"
;;  '(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 GB2312 (simplified) 
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;; (make-coding-system
;;  'chinese-iso-8bit 2 ?c
;;  "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:CN-GB-2312)"
;;  '(ascii chinese-gb2312 nil nil
;;    nil ascii-eol ascii-cntl nil nil nil nil)
;;  '((safe-charsets ascii chinese-gb2312)
;;    (mime-charset . cn-gb-2312)))

(make-coding-system
 'cn-gb-2312 'iso2022
 "Chinese EUC"
 '(charset-g0 ascii
   charset-g1 chinese-gb2312
   charset-g2 chinese-sisheng
   charset-g3 t
   mnemonic "Zh-GB/EUC"
   documentation
   "Chinese EUC (Extended Unix Code), the standard Chinese encoding on Unix.
This follows the same overall EUC principles as Japanese EUC (see the
description under Japanese EUC), but specifies different character sets:

G0: ASCII
G1: Chinese-GB2312
G2: Sisheng (PinYin - ZhuYin)"
   ))

;; (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 'gb2312 'cn-gb-2312)
(define-coding-system-alias 'chinese-euc 'cn-gb-2312)

;; (make-coding-system
;;  'chinese-hz 0 ?z
;;  "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)))
;; (put 'chinese-hz 'post-read-conversion 'post-read-decode-hz)
;; (put 'chinese-hz 'pre-write-conversion 'pre-write-encode-hz)

(make-coding-system
 'hz-gb-2312 'no-conversion
 "Hz/ZW (Chinese)"
 '(mnemonic "Zh-GB/Hz"
   eol-type lf
   post-read-conversion post-read-decode-hz
   pre-write-conversion pre-write-encode-hz
   documentation "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)"
))

;; (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
;; (define-coding-system-alias 'hz 'chinese-hz)

(define-coding-system-alias 'hz 'hz-gb-2312)

(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" '((setup-function . setup-chinese-gb-environment-internal)
		(charset chinese-gb2312 chinese-sisheng)
		(coding-system cn-gb-2312 iso-2022-7bit hz-gb-2312)
		(coding-priority cn-gb-2312 big5 iso-2022-7bit)
		(cygwin-locale "zh")
		(locale "zh_CN.eucCN" "zh_CN.EUC" "zh_CN"
			"chinese-s" "zh"
			 (lambda (arg)
			      (and arg (let ((case-fold-search t))
					 (string-match "^zh_.*.GB.*" arg)))))
		(mswindows-locale ("CHINESE" . "CHINESE_SIMPLIFIED"))
		(native-coding-system cn-gb-2312)
		(input-method . "chinese-py-punct")
		(features china-util)
		(sample-text . "Chinese ($AVPND(B,$AFUM(;0(B,$A::So(B)	$ADc:C(B")
		(documentation .
"Supports Simplified Chinese, used in mainland China.
Uses the GB2312 character set."))
 '("Chinese"))

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; Chinese BIG5 (traditional)
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;; (make-coding-system
;;  'chinese-big5 3 ?B "BIG5 8-bit encoding for Chinese (MIME:CN-BIG5)"
;;  nil
;;  '((safe-charsets ascii chinese-big5-1 chinese-big5-2)
;;    (mime-charset . cn-big5)
;;    (charset-origin-alist (chinese-big5-1  "BIG5" encode-big5-char)
;;                          (chinese-big5-2  "BIG5" encode-big5-char))))

(make-coding-system
 'big5 'big5
 "Big5"
 '(mnemonic "Zh/Big5"
   documentation
   "A non-modal encoding formed by five large Taiwanese companies
\(hence \"Big5\") to produce a character set and encoding for
traditional Chinese writing.  Big5 encodes some 13,000+ characters.
ASCII is encoded as normal, and Chinese characters as two bytes, but
Chinese characters do not exclusively use the high half.  The first
byte is in the high half standard position A1-FE, but the second byte
is in either low 40-7E or high A1-FE.  Thus Big5 suffers from the
classic \"it might look like a slash, but it's really the second byte
of a Chinese character\"."))

;; (define-coding-system-alias 'big5 'chinese-big5)
;; (define-coding-system-alias 'cn-big5 'chinese-big5)

(define-coding-system-alias 'cn-big5 '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-charset-ccl-program 'chinese-big5-1 'ccl-encode-big5-font)
(set-charset-ccl-program 'chinese-big5-2 'ccl-encode-big5-font)

(set-language-info-alist
 "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
		  (coding-system big5 iso-2022-7bit)
		  (coding-priority big5 cn-gb-2312 iso-2022-7bit)
		  (cygwin-locale "zh_TW")
		  (locale "zh_TW.Big5" "zh_TW.big5" "zh_CN.big5" "zh_TW"
			  "chinese-t"
			  (lambda (arg)
			      (and arg (let ((case-fold-search t))
					 (string-match "^zh_.*.BIG5.*" arg)))))
		  (mswindows-locale ("CHINESE" . "CHINESE_TRADITIONAL"))
		  (native-coding-system big5)
		  (input-method . "chinese-py-punct-b5")
		  (features china-util)
		  (sample-text . "Cantonese ($(0GnM$(B,$(0N]0*Hd(B)	$(0*/=((B, $(0+$)p(B")
		  (documentation .
"Supports Traditional Chinese, used in Taiwan, Hong Kong, and Singapore.
Uses the Chinese Big5 character set."
))
 '("Chinese"))

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; Chinese CNS11643 (traditional)
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

;; (set-language-info-alist
;;  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
;;                           chinese-cns11643-3 chinese-cns11643-4
;;                           chinese-cns11643-5 chinese-cns11643-6
;;                           chinese-cns11643-7)
;;                  (coding-system iso-2022-cn)
;;                  (coding-priority iso-2022-cn chinese-big5 chinese-iso-8bit)
;;                  (features china-util)
;;                  (input-method . "chinese-cns-quick")
;;                  (documentation . "Support for Chinese CNS character sets."))
;;  '("Chinese"))

;;; chinese.el ends here