X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=emu-x20.el;h=5edba281035419b1b80e22826fc3e5d8c487412a;hb=6d770e9fa8ff78b919e748ebeeb97b83c769de43;hp=cd31b152955ea101f00309b925adcf5ac8516940;hpb=8b9c3576bf55a6d7317ceb5e199cf450c130887e;p=elisp%2Fapel.git diff --git a/emu-x20.el b/emu-x20.el index cd31b15..5edba28 100644 --- a/emu-x20.el +++ b/emu-x20.el @@ -1,13 +1,11 @@ -;;; emu-x20.el --- emu API implementation for XEmacs 20 with mule +;;; emu-x20.el --- emu API implementation for XEmacs with mule -;; Copyright (C) 1995 Free Software Foundation, Inc. -;; Copyright (C) 1994,1995,1996 MORIOKA Tomohiko +;; Copyright (C) 1994,1995,1996,1997,1998 MORIOKA Tomohiko ;; Author: MORIOKA Tomohiko -;; Version: $Id: emu-x20.el,v 7.35 1996/09/15 08:04:02 morioka Exp $ ;; Keywords: emulation, compatibility, Mule, XEmacs -;; This file is part of tl (Tiny Library). +;; This file is part of emu. ;; This program is free software; you can redistribute it and/or ;; modify it under the terms of the GNU General Public License as @@ -20,196 +18,239 @@ ;; General Public License for more details. ;; You should have received a copy of the GNU General Public License -;; along with This program; see the file COPYING. If not, write to -;; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, +;; along with GNU Emacs; see the file COPYING. If not, write to the +;; Free Software Foundation, Inc., 59 Temple Place - Suite 330, ;; Boston, MA 02111-1307, USA. -;;; Code: - -(require 'cyrillic) -(require 'emu-xemacs) - -(defvar xemacs-beta-version - (if (string-match "(beta\\([0-9]+\\))" emacs-version) - (string-to-number - (substring emacs-version (match-beginning 1)(match-end 1)) - ))) - +;;; Commentary: -;;; @ character set -;;; +;; This module requires XEmacs 20.3-b5 or later with mule. -(defalias 'charset-description 'charset-doc-string) +;;; Code: -(defun find-charset-string (string) - "Return a list of charsets in the STRING except ascii. -\[emu-x20.el; Mule emulating function]" - (delq 'ascii (charsets-in-string string)) - ) +(and (coding-system-property 'iso-2022-jp 'input-charset-conversion) + (copy-coding-system 'iso-2022-7bit 'iso-2022-jp)) -(defun find-charset-region (start end) - "Return a list of charsets except ascii -in the region between START and END. -\[emu-x20.el; Mule emulating function]" - (delq 'ascii (charsets-in-region start end)) - ) -;;; @@ for Mule emulation +;;; @ without code-conversion ;;; -(defconst lc-ascii 'ascii) -(defconst lc-ltn1 'latin-1) -(defconst lc-ltn2 'latin-2) -(defconst lc-ltn3 'latin-3) -(defconst lc-ltn4 'latin-4) -(defconst lc-crl 'cyrillic) -(defconst lc-arb 'arabic) -(defconst lc-grk 'greek) -(defconst lc-hbw 'hebrew) -(defconst lc-ltn5 'latin-5) -(defconst lc-jp 'japanese) -(defconst lc-jp2 'japanese-2) -(defconst lc-kr 'korean) -(defconst lc-big5-1 'chinese-big5-1) -(defconst lc-big5-2 'chinese-big5-2) -(defconst lc-cn 'chinese-gb) -(defconst lc-cns1 'chinese-cns-1) -(defconst lc-cns2 'chinese-cns-2) -(defconst lc-cns3 'chinese-cns-3) -(defconst lc-cns4 'chinese-cns-4) -(defconst lc-cns5 'chinese-cns-5) -(defconst lc-cns6 'chinese-cns-6) -(defconst lc-cns7 'chinese-cns-7) - - -;;; @ coding-system -;;; - -(defconst *noconv* 'noconv) -(defconst *ctext* 'ctext) -(defconst *hz* 'hz) -(defconst *big5* 'big5) -(defconst *euc-kr* 'euc-kr) -(defconst *koi8* 'koi8) - -(defmacro as-binary-process (&rest body) - `(let (selective-display ; Disable ^M to nl translation. - process-input-coding-system - process-output-coding-system) - ,@body)) - +(define-obsolete-function-alias 'insert-binary-file-contents + 'insert-file-contents-as-binary) + +(defun insert-binary-file-contents-literally (filename + &optional visit beg end replace) + "Like `insert-file-contents-literally', q.v., but don't code conversion. +A buffer may be modified in several ways after reading into the buffer due +to advanced Emacs features, such as file-name-handlers, format decoding, +find-file-hooks, etc. + This function ensures that none of these modifications will take place." + (let ((coding-system-for-read 'binary)) + (insert-file-contents-literally filename visit beg end replace) + )) + ;;; @ MIME charset ;;; -(defvar charsets-mime-charset-alist - '(((ascii) . us-ascii) - ((ascii latin-1) . iso-8859-1) - ((ascii latin-2) . iso-8859-2) - ((ascii latin-3) . iso-8859-3) - ((ascii latin-4) . iso-8859-4) -;;; ((ascii cyrillic) . iso-8859-5) - ((ascii cyrillic) . koi8-r) - ((ascii arabic) . iso-8859-6) - ((ascii greek) . iso-8859-7) - ((ascii hebrew) . iso-8859-8) - ((ascii latin-5) . iso-8859-9) - ((ascii japanese-old japanese) . iso-2022-jp) - ((ascii korean) . euc-kr) - ((ascii chinese-big5-1 chinese-big5-2) . big5) - ((ascii japanese-old chinese-gb japanese korean - japanese-2 latin-1 greek) . iso-2022-jp-2) - ((ascii japanese-old chinese-gb japanese korean - japanese-2 chinese-cns-1 chinese-cns-2 - latin-1 greek) . iso-2022-int-1) - )) - -(defvar default-mime-charset 'iso-2022-int-1) - -(defvar mime-charset-coding-system-alist - '((iso-8859-1 . ctext) - (gb2312 . euc-china) - (koi8-r . koi8) - (iso-2022-jp-2 . iso-2022-ss2-7) - (x-iso-2022-jp-2 . iso-2022-ss2-7) - (shift_jis . sjis) - (x-shiftjis . sjis) - )) - -(defun mime-charset-to-coding-system (charset) - "Return coding-system by MIME charset. [emu-x20.el]" - (if (stringp charset) - (setq charset (intern (downcase charset))) - ) - (or (cdr (assq charset mime-charset-coding-system-alist)) - (and (memq charset (coding-system-list)) charset) - )) - -(defun detect-mime-charset-region (start end) - "Return MIME charset for region between START and END. -\[emu-x20.el]" - (charsets-to-mime-charset (charsets-in-region start end))) - (defun encode-mime-charset-region (start end charset) - "Encode the text between START and END as MIME CHARSET. -\[emu-x20.el]" + "Encode the text between START and END as MIME CHARSET." (let ((cs (mime-charset-to-coding-system charset))) (if cs (encode-coding-region start end cs) ))) -(defun decode-mime-charset-region (start end charset) - "Decode the text between START and END as MIME CHARSET. -\[emu-x20.el]" +(defcustom mime-charset-decoder-alist + '((iso-2022-jp . decode-mime-charset-region-with-iso646-unification) + (iso-2022-jp-2 . decode-mime-charset-region-with-iso646-unification) + (x-ctext . decode-mime-charset-region-with-iso646-unification) + (hz-gb-2312 . decode-mime-charset-region-for-hz) + (t . decode-mime-charset-region-default)) + "Alist MIME-charset vs. decoder function." + :group 'i18n + :type '(repeat (cons mime-charset function))) + +(defsubst decode-mime-charset-region-default (start end charset) (let ((cs (mime-charset-to-coding-system charset))) (if cs (decode-coding-region start end cs) ))) -(defun encode-mime-charset-string (string charset) - "Encode the STRING as MIME CHARSET. [emu-x20.el]" +(defcustom mime-iso646-character-unification-alist + `,(let (dest + (i 33)) + (while (< i 92) + (setq dest + (cons (cons (char-to-string (make-char 'latin-jisx0201 i)) + (format "%c" i)) + dest)) + (setq i (1+ i))) + (setq i 93) + (while (< i 126) + (setq dest + (cons (cons (char-to-string (make-char 'latin-jisx0201 i)) + (format "%c" i)) + dest)) + (setq i (1+ i))) + (nreverse dest)) + "Alist unified string vs. canonical string." + :group 'i18n + :type '(repeat (cons string string))) + +(defcustom mime-unified-character-face nil + "*Face of unified character." + :group 'i18n + :type 'face) + +(defcustom mime-character-unification-limit-size 2048 + "*Limit size to unify characters." + :group 'i18n + :type 'integer) + +(defun decode-mime-charset-region-with-iso646-unification (start end charset) + (decode-mime-charset-region-default start end charset) + (if (<= (- end start) mime-character-unification-limit-size) + (save-excursion + (let ((rest mime-iso646-character-unification-alist)) + (while rest + (let ((pair (car rest))) + (goto-char (point-min)) + (while (search-forward (car pair) nil t) + (let ((str (cdr pair))) + (put-text-property 0 (length str) + 'face mime-unified-character-face str) + (replace-match str 'fixed-case 'literal) + ) + )) + (setq rest (cdr rest))))) + )) + +(defun decode-mime-charset-region-for-hz (start end charset) + (decode-hz-region start end)) + +(defun decode-mime-charset-region (start end charset) + "Decode the text between START and END as MIME CHARSET." + (if (stringp charset) + (setq charset (intern (downcase charset))) + ) + (let ((func (cdr (or (assq charset mime-charset-decoder-alist) + (assq t mime-charset-decoder-alist))))) + (funcall func start end charset) + )) + +(defsubst encode-mime-charset-string (string charset) + "Encode the STRING as MIME CHARSET." (let ((cs (mime-charset-to-coding-system charset))) (if cs (encode-coding-string string cs) string))) +;; (defsubst decode-mime-charset-string (string charset) +;; "Decode the STRING as MIME CHARSET." +;; (let ((cs (mime-charset-to-coding-system charset))) +;; (if cs +;; (decode-coding-string string cs) +;; string))) (defun decode-mime-charset-string (string charset) - "Decode the STRING as MIME CHARSET. [emu-x20.el]" - (let ((cs (mime-charset-to-coding-system charset))) - (if cs - (decode-coding-string string cs) - string))) + "Decode the STRING as MIME CHARSET." + (with-temp-buffer + (insert string) + (decode-mime-charset-region (point-min)(point-max) charset) + (buffer-string) + )) -;;; @ character -;;; +(defvar charsets-mime-charset-alist + '(((ascii) . us-ascii) + ((ascii latin-iso8859-1) . iso-8859-1) + ((ascii latin-iso8859-2) . iso-8859-2) + ((ascii latin-iso8859-3) . iso-8859-3) + ((ascii latin-iso8859-4) . iso-8859-4) + ((ascii cyrillic-iso8859-5) . iso-8859-5) +;;; ((ascii cyrillic-iso8859-5) . koi8-r) + ((ascii arabic-iso8859-6) . iso-8859-6) + ((ascii greek-iso8859-7) . iso-8859-7) + ((ascii hebrew-iso8859-8) . iso-8859-8) + ((ascii latin-iso8859-9) . iso-8859-9) + ((ascii latin-jisx0201 + japanese-jisx0208-1978 japanese-jisx0208) . iso-2022-jp) + ((ascii latin-jisx0201 + katakana-jisx0201 japanese-jisx0208) . shift_jis) + ((ascii korean-ksc5601) . euc-kr) + ((ascii chinese-gb2312) . cn-gb-2312) + ((ascii chinese-big5-1 chinese-big5-2) . cn-big5) + ((ascii latin-iso8859-1 greek-iso8859-7 + latin-jisx0201 japanese-jisx0208-1978 + chinese-gb2312 japanese-jisx0208 + korean-ksc5601 japanese-jisx0212) . iso-2022-jp-2) + ((ascii latin-iso8859-1 greek-iso8859-7 + latin-jisx0201 japanese-jisx0208-1978 + chinese-gb2312 japanese-jisx0208 + korean-ksc5601 japanese-jisx0212 + chinese-cns11643-1 chinese-cns11643-2) . iso-2022-int-1) + ((ascii latin-iso8859-1 latin-iso8859-2 + cyrillic-iso8859-5 greek-iso8859-7 + latin-jisx0201 japanese-jisx0208-1978 + chinese-gb2312 japanese-jisx0208 + korean-ksc5601 japanese-jisx0212 + chinese-cns11643-1 chinese-cns11643-2 + chinese-cns11643-3 chinese-cns11643-4 + chinese-cns11643-5 chinese-cns11643-6 + chinese-cns11643-7) . iso-2022-int-1) + )) -(defun char-bytes (chr) 1) -(defun char-length (character) - "Return number of elements a CHARACTER occupies in a string or buffer. -\[emu-x20.el]" - 1) +;;; @ buffer representation +;;; -(defun char-columns (character) - "Return number of columns a CHARACTER occupies when displayed. -\[emu-x20.el]" - (charset-columns (char-charset character)) +(defmacro-maybe set-buffer-multibyte (flag) + "Set the multibyte flag of the current buffer to FLAG. +If FLAG is t, this makes the buffer a multibyte buffer. +If FLAG is nil, this makes the buffer a single-byte buffer. +The buffer contents remain unchanged as a sequence of bytes +but the contents viewed as characters do change. +\[Emacs 20.3 emulating macro]" ) + +;;; @ character +;;; + +;; avoid bug of XEmacs +(or (integerp (cdr (split-char ?a))) + (defun split-char (char) + "Return list of charset and one or two position-codes of CHAR." + (let ((charset (char-charset char))) + (if (eq charset 'ascii) + (list charset (char-int char)) + (let ((i 0) + (len (charset-dimension charset)) + (code (if (integerp char) + char + (char-int char))) + dest) + (while (< i len) + (setq dest (cons (logand code 127) dest) + code (lsh code -7) + i (1+ i))) + (cons charset dest) + )))) + ) + +(defmacro char-next-index (char index) + "Return index of character succeeding CHAR whose index is INDEX." + `(1+ ,index)) + ;;; @@ Mule emulating aliases ;;; ;;; You should not use them. -(defalias 'char-width 'char-columns) - -(defalias 'char-leading-char 'char-charset) +;;(defalias 'char-leading-char 'char-charset) (defun char-category (character) "Return string of category mnemonics for CHAR in TABLE. CHAR can be any multilingual character -TABLE defaults to the current buffer's category table. -\[emu-x20.el; Mule emulating function]" +TABLE defaults to the current buffer's category table." (mapconcat (lambda (chr) (char-to-string (int-char chr)) ) @@ -220,34 +261,11 @@ TABLE defaults to the current buffer's category table. ;;; @ string ;;; -(defun string-columns (string) - "Return number of columns STRING occupies when displayed. -\[emu-x20.el]" - (let ((col 0) - (len (length string)) - (i 0)) - (while (< i len) - (setq col (+ col (char-columns (aref string i)))) - (setq i (1+ i)) - ) - col)) - -(defalias 'string-width 'string-column) - (defun string-to-int-list (str) (mapcar #'char-int str) ) -(defalias 'sref 'aref) - -(defun truncate-string (str width &optional start-column) - "Truncate STR to fit in WIDTH columns. -Optional non-nil arg START-COLUMN specifies the starting column. -\[emu-x20.el; Mule 2.3 emulating function]" - (or start-column - (setq start-column 0)) - (substring str start-column width) - ) +(defalias 'looking-at-as-unibyte 'looking-at) ;;; @ end