annotate lisp/language/china-util.el @ 213:78f53ef88e17 r20-4b5

Import from CVS: tag r20-4b5
author cvs
date Mon, 13 Aug 2007 10:06:47 +0200
parents e45d5e7c476e
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
1 ;;; china-util.el --- utilities for Chinese
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
2
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
4 ;; Licensed to the Free Software Foundation.
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
5 ;; Copyright (C) 1997 MORIOKA Tomohiko
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
6
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
7 ;; Keywords: mule, multilingual, Chinese
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
8
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
9 ;; This file is part of XEmacs.
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
10
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
11 ;; XEmacs is free software; you can redistribute it and/or modify it
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
12 ;; under the terms of the GNU General Public License as published by
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
13 ;; the Free Software Foundation; either version 2, or (at your option)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
14 ;; any later version.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
15
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
16 ;; XEmacs is distributed in the hope that it will be useful, but
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
17 ;; WITHOUT ANY WARRANTY; without even the implied warranty of
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
18 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
19 ;; General Public License for more details.
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
20
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
21 ;; You should have received a copy of the GNU General Public License
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
22 ;; along with XEmacs; see the file COPYING. If not, write to the Free
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
23 ;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
24 ;; 02111-1307, USA.
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
25
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
26 ;;; Code:
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
27
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
28 ;;;###autoload
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
29 (defun setup-chinese-gb-environment ()
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
30 "Setup multilingual environment (MULE) for Chinese GB2312 users."
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
31 (interactive)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
32 (setup-english-environment)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
33
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
34 (set-default-coding-systems 'cn-gb-2312)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
35 ;; (setq coding-category-iso-8-2 'chinese-iso-8bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
36 (set-coding-category-system 'iso-8-2 'cn-gb-2312)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
37 ;; (setq coding-category-iso-7-else 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
38 ;; (setq coding-category-big5 'chinese-big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
39
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
40 ;; (set-coding-priority
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
41 ;; '(coding-category-iso-7
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
42 ;; coding-category-iso-7-else
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
43 ;; coding-category-iso-8-2
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
44 ;; coding-category-big5
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
45 ;; coding-category-iso-8-1
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
46 ;; coding-category-emacs-mule
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
47 ;; coding-category-iso-8-else))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
48 (set-coding-priority-list
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
49 '(iso-7
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
50 iso-8-2
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
51 big5
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
52 iso-8-1
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
53 no-conversion
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
54 iso-8-designate
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
55 iso-lock-shift
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
56 shift-jis))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
57
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
58 ;; (when (eq 'x (device-type (selected-device)))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
59 ;; (x-use-halfwidth-roman-font 'chinese-gb2312 "gb1988"))))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
60 (when (featurep 'egg)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
61 (setq-default its:*current-map* (its:get-mode-map "PinYin")))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
62 (setq default-input-method "chinese-py-punct")
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
63 )
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
64
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
65 ;;;###autoload
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
66 (defun setup-chinese-big5-environment ()
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
67 "Setup multilingual environment (MULE) for Chinese Big5 users."
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
68 (interactive)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
69 (setup-english-environment)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
70
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
71 (set-default-coding-systems 'big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
72 ;; (setq coding-category-iso-8-2 'chinese-big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
73 (set-coding-category-system 'iso-8-2 'cn-gb-2312)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
74 ;; (setq coding-category-iso-7-else 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
75 ;; (setq coding-category-big5 'chinese-big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
76
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
77 ;; (set-coding-priority
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
78 ;; '(coding-category-iso-7
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
79 ;; coding-category-iso-7-else
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
80 ;; coding-category-big5
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
81 ;; coding-category-iso-8-2
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
82 ;; coding-category-emacs-mule
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
83 ;; coding-category-iso-8-else))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
84 (set-coding-priority-list
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
85 '(iso-7
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
86 big5
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
87 iso-8-2
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
88 no-conversion
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
89 iso-8-1
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
90 iso-8-designate
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
91 iso-lock-shift
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
92 shift-jis))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
93
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
94 (setq default-input-method "chinese-py-punct-b5")
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
95 )
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
96
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
97 ;; ;;;###autoload
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
98 ;; (defun setup-chinese-cns-environment ()
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
99 ;; "Setup multilingual environment (MULE) for Chinese CNS11643 family users."
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
100 ;; (interactive)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
101 ;; (setup-english-environment)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
102 ;;
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
103 ;; (setq coding-category-iso-7-else 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
104 ;; (setq coding-category-big5 'chinese-big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
105 ;; (setq coding-category-iso-8-2 'chinese-big5)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
106 ;; (set-default-coding-systems 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
107 ;;
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
108 ;; (set-coding-priority
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
109 ;; '(coding-category-iso-7
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
110 ;; coding-category-iso-7-else
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
111 ;; coding-category-iso-8-2
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
112 ;; coding-category-big5
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
113 ;; coding-category-iso-7-else))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
114 ;;
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
115 ;; (setq-default buffer-file-coding-system 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
116 ;; (setq default-terminal-coding-system 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
117 ;; (setq default-keyboard-coding-system 'chinese-iso-7bit)
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
118 ;;
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
119 ;; (setq default-input-method "chinese-quick-cns"))
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
120
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
121 ;; Hz/ZW encoding stuffs
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
122
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
123 ;; HZ is an encoding method for Chinese character set GB2312 used
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
124 ;; widely in Internet. It is very similar to 7-bit environment of
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
125 ;; ISO-2022. The difference is that HZ uses the sequence "~{" and
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
126 ;; "~}" for designating GB2312 and ASCII respectively, hence, it
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
127 ;; doesn't uses ESC (0x1B) code.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
128
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
129 ;; ZW is another encoding method for Chinese character set GB2312. It
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
130 ;; encodes Chinese characters line by line by starting each line with
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
131 ;; the sequence "zW". It also uses only 7-bit as HZ.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
132
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
133 ;; ISO-2022 escape sequence to designate GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
134 (defvar iso2022-gb-designation "\e$A")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
135 ;; HZ escape sequence to designate GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
136 (defvar hz-gb-designnation "~{")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
137 ;; ISO-2022 escape sequence to designate ASCII.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
138 (defvar iso2022-ascii-designation "\e(B")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
139 ;; HZ escape sequence to designate ASCII.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
140 (defvar hz-ascii-designnation "~}")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
141 ;; Regexp of ZW sequence to start GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
142 (defvar zw-start-gb "^zW")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
143 ;; Regexp for start of GB2312 in an encoding mixture of HZ and ZW.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
144 (defvar hz/zw-start-gb (concat hz-gb-designnation "\\|" zw-start-gb))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
145
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
146 (defvar decode-hz-line-continuation nil
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
147 "Flag to tell if we should care line continuation convention of Hz.")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
148
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
149 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
150 (defun decode-hz-region (beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
151 "Decode HZ/ZW encoded text in the current region.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
152 Return the length of resulting text."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
153 (interactive "r")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
154 (save-excursion
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
155 (save-restriction
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
156 (narrow-to-region beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
157
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
158 ;; We, at first, convert HZ/ZW to `iso-2022-7bit',
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
159 ;; then decode it.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
160
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
161 ;; "~\n" -> "\n"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
162 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
163 (while (search-forward "~" nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
164 (if (= (following-char) ?\n) (delete-char -1))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
165 (if (not (eobp)) (forward-char 1)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
166
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
167 ;; "^zW...\n" -> Chinese GB2312
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
168 ;; "~{...~}" -> Chinese GB2312
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
169 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
170 (let ((chinese-found nil))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
171 (while (re-search-forward hz/zw-start-gb nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
172 (if (= (char-after (match-beginning 0)) ?z)
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
173 ;; ZW -> iso-2022-7bit
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
174 (progn
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
175 (delete-char -2)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
176 (insert iso2022-gb-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
177 (end-of-line)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
178 (insert iso2022-ascii-designation))
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
179 ;; HZ -> iso-2022-7bit
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
180 (delete-char -2)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
181 (insert iso2022-gb-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
182 (let ((pos (save-excursion (end-of-line) (point))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
183 (if (search-forward hz-ascii-designnation pos t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
184 (replace-match iso2022-ascii-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
185 (if (not decode-hz-line-continuation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
186 (insert iso2022-ascii-designation)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
187 (setq chinese-found t))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
188 (if (or chinese-found
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
189 (let ((enable-multibyte-characters nil))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
190 ;; Here we check if the text contains EUC (China) codes.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
191 ;; If any, we had better decode them also.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
192 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
193 (re-search-forward "[\240-\377]" nil t)))
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
194 (decode-coding-region (point-min) (point-max) 'euc-china)))
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
195
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
196 ;; "~~" -> "~"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
197 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
198 (while (search-forward "~~" nil t) (delete-char -1))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
199 (- (point-max) (point-min)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
200
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
201 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
202 (defun decode-hz-buffer ()
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
203 "Decode HZ/ZW encoded text in the current buffer."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
204 (interactive)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
205 (decode-hz-region (point-min) (point-max)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
206
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
207 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
208 (defun encode-hz-region (beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
209 "Encode the text in the current region to HZ.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
210 Return the length of resulting text."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
211 (interactive "r")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
212 (save-excursion
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
213 (save-restriction
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
214 (narrow-to-region beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
215
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
216 ;; "~" -> "~~"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
217 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
218 (while (search-forward "~" nil t) (insert ?~))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
219
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
220 ;; Chinese GB2312 -> "~{...~}"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
221 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
222 (if (re-search-forward "\\cc" nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
223 (let ((enable-multibyte-characters nil)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
224 pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
225 (goto-char (setq pos (match-beginning 0)))
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
226 (encode-coding-region pos (point-max) 'iso-2022-7bit)
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
227 (goto-char pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
228 (while (search-forward iso2022-gb-designation nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
229 (delete-char -3)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
230 (insert hz-gb-designnation))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
231 (goto-char pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
232 (while (search-forward iso2022-ascii-designation nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
233 (delete-char -3)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
234 (insert hz-ascii-designnation))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
235 (- (point-max) (point-min)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
236
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
237 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
238 (defun encode-hz-buffer ()
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
239 "Encode the text in the current buffer to HZ."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
240 (interactive)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
241 (encode-hz-region (point-min) (point-max)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
242
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
243 ;;
207
e45d5e7c476e Import from CVS: tag r20-4b2
cvs
parents: 159
diff changeset
244 (provide 'china-util)
159
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
245
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
246 ;;; china-util.el ends here