[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.

;;; china-util.el --- utilities for Chinese -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.

;; Keywords: mule, 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.

;;; Synched up with: Emacs 21.1 (language/china-util.el).

;;; Commentary:

;;; Code:

;; Hz/ZW encoding stuffs

;; HZ is an encoding method for Chinese character set GB2312 used
;; widely in Internet.  It is very similar to 7-bit environment of
;; ISO-2022.  The difference is that HZ uses the sequence "~{" and
;; "~}" for designating GB2312 and ASCII respectively, hence, it
;; doesn't uses ESC (0x1B) code.

;; ZW is another encoding method for Chinese character set GB2312.  It
;; encodes Chinese characters line by line by starting each line with
;; the sequence "zW".  It also uses only 7-bit as HZ.

;; ISO-2022 escape sequence to designate GB2312.
(defvar iso2022-gb-designation "\e$A")
;; HZ escape sequence to designate GB2312.
(defvar hz-gb-designnation "~{")
;; ISO-2022 escape sequence to designate ASCII.
(defvar iso2022-ascii-designation "\e(B")
;; HZ escape sequence to designate ASCII.
(defvar hz-ascii-designnation "~}")
;; Regexp of ZW sequence to start GB2312.
(defvar zw-start-gb "^zW")
;; Regexp for start of GB2312 in an encoding mixture of HZ and ZW.
(defvar hz/zw-start-gb
  (concat hz-gb-designnation "\\|" zw-start-gb "\\|[^\0-\177]"))

(defvar decode-hz-line-continuation nil
  "Flag to tell if we should care line continuation convention of Hz.")

(defconst hz-set-msb-table
  (let ((str (make-string 127 0))
	(i 0))
    (while (< i 33)
      (aset str i i)
      (setq i (1+ i)))
    (while (< i 127)
      (aset str i (+ i 128))
      (setq i (1+ i)))
    str))

;;;###autoload
(defun decode-hz-region (beg end)
  "Decode HZ/ZW encoded text in the current region.
Return the length of resulting text."
  (interactive "r")
  (save-excursion
    (save-restriction
      (let (pos ch)
	(narrow-to-region beg end)

	;; We, at first, convert HZ/ZW to `euc-china',
	;; then decode it.

	;; "~\n" -> "\n", "~~" -> "~"
	(goto-char (point-min))
	(while (search-forward "~" nil t)
	  (setq ch (following-char))
	  (if (or (= ch ?\n) (= ch ?~)) (delete-char -1)))

	;; "^zW...\n" -> Chinese GB2312
	;; "~{...~}"  -> Chinese GB2312
	(goto-char (point-min))
	(setq beg nil)
	(while (re-search-forward hz/zw-start-gb nil t)
	  (setq pos (match-beginning 0)
		ch (char-after pos))
	  ;; Record the first position to start conversion.
	  (or beg (setq beg pos))
	  (end-of-line)
	  (setq end (point))
	  (if (>= ch 128)		; 8bit GB2312
	      nil
	    (goto-char pos)
	    (delete-char 2)
	    (setq end (- end 2))
	    (if (= ch ?z)			; ZW -> euc-china
		(progn
		  (translate-region (point) end hz-set-msb-table)
		  (goto-char end))
	      (if (search-forward hz-ascii-designnation
				  (if decode-hz-line-continuation nil end)
				  t)
		  (delete-char -2))
	      (setq end (point))
	      (translate-region pos (point) hz-set-msb-table))))
	(if beg
	    (decode-coding-region beg end 'euc-china)))
      (- (point-max) (point-min)))))

;;;###autoload
(defun decode-hz-buffer ()
  "Decode HZ/ZW encoded text in the current buffer."
  (interactive)
  (decode-hz-region (point-min) (point-max)))

;;;###autoload
(defun encode-hz-region (beg end)
  "Encode the text in the current region to HZ.
Return the length of resulting text."
  (interactive "r")
  (save-excursion
    (save-restriction
      (narrow-to-region beg end)

      ;; "~" -> "~~"
      (goto-char (point-min))
      (while (search-forward "~" nil t)	(insert ?~))

      ;; Chinese GB2312 -> "~{...~}"
      (goto-char (point-min))
      (if (re-search-forward "\\cc" nil t)
	  (let (pos)
	    (goto-char (setq pos (match-beginning 0)))
	    (encode-coding-region pos (point-max) 'iso-2022-7bit)
	    (goto-char pos)
	    (while (search-forward iso2022-gb-designation nil t)
	      (delete-char -3)
	      (insert hz-gb-designnation))
	    (goto-char pos)
	    (while (search-forward iso2022-ascii-designation nil t)
	      (delete-char -3)
	      (insert hz-ascii-designnation))))
      (- (point-max) (point-min)))))

;;;###autoload
(defun encode-hz-buffer ()
  "Encode the text in the current buffer to HZ."
  (interactive)
  (encode-hz-region (point-min) (point-max)))

;;
(provide 'china-util)

;;; china-util.el ends here