annotate lisp/language/china-util.el @ 159:3bb7ccffb0c0 r20-3b6

Import from CVS: tag r20-3b6
author cvs
date Mon, 13 Aug 2007 09:41:43 +0200
parents
children e45d5e7c476e
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 Free Software Foundation, Inc.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
4 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
5
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
6 ;; Keywords: mule, multilingual, Chinese
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
7
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
8 ;; This file is part of GNU Emacs.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
9
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
11 ;; it under the terms of the GNU General Public License as published by
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
12 ;; the Free Software Foundation; either version 2, or (at your option)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
13 ;; any later version.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
14
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
15 ;; GNU Emacs is distributed in the hope that it will be useful,
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
18 ;; GNU General Public License for more details.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
19
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
20 ;; You should have received a copy of the GNU General Public License
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
23 ;; Boston, MA 02111-1307, USA.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
24
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
25 ;;; Code:
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
26
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
27 ;; Hz/ZW encoding stuffs
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
28
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
29 ;; HZ is an encoding method for Chinese character set GB2312 used
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
30 ;; widely in Internet. It is very similar to 7-bit environment of
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
31 ;; ISO-2022. The difference is that HZ uses the sequence "~{" and
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
32 ;; "~}" for designating GB2312 and ASCII respectively, hence, it
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
33 ;; doesn't uses ESC (0x1B) code.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
34
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
35 ;; ZW is another encoding method for Chinese character set GB2312. It
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
36 ;; encodes Chinese characters line by line by starting each line with
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
37 ;; the sequence "zW". It also uses only 7-bit as HZ.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
38
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
39 ;; ISO-2022 escape sequence to designate GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
40 (defvar iso2022-gb-designation "\e$A")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
41 ;; HZ escape sequence to designate GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
42 (defvar hz-gb-designnation "~{")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
43 ;; ISO-2022 escape sequence to designate ASCII.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
44 (defvar iso2022-ascii-designation "\e(B")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
45 ;; HZ escape sequence to designate ASCII.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
46 (defvar hz-ascii-designnation "~}")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
47 ;; Regexp of ZW sequence to start GB2312.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
48 (defvar zw-start-gb "^zW")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
49 ;; Regexp for start of GB2312 in an encoding mixture of HZ and ZW.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
50 (defvar hz/zw-start-gb (concat hz-gb-designnation "\\|" zw-start-gb))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
51
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
52 (defvar decode-hz-line-continuation nil
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
53 "Flag to tell if we should care line continuation convention of Hz.")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
54
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
55 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
56 (defun decode-hz-region (beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
57 "Decode HZ/ZW encoded text in the current region.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
58 Return the length of resulting text."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
59 (interactive "r")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
60 (save-excursion
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
61 (save-restriction
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
62 (narrow-to-region beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
63
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
64 ;; We, at first, convert HZ/ZW to `iso-2022-7',
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
65 ;; then decode it.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
66
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
67 ;; "~\n" -> "\n"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
68 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
69 (while (search-forward "~" nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
70 (if (= (following-char) ?\n) (delete-char -1))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
71 (if (not (eobp)) (forward-char 1)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
72
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
73 ;; "^zW...\n" -> Chinese GB2312
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
74 ;; "~{...~}" -> Chinese GB2312
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
75 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
76 (let ((chinese-found nil))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
77 (while (re-search-forward hz/zw-start-gb nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
78 (if (= (char-after (match-beginning 0)) ?z)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
79 ;; ZW -> iso-20227-7
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
80 (progn
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
81 (delete-char -2)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
82 (insert iso2022-gb-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
83 (end-of-line)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
84 (insert iso2022-ascii-designation))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
85 ;; HZ -> iso-20227-7
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
86 (delete-char -2)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
87 (insert iso2022-gb-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
88 (let ((pos (save-excursion (end-of-line) (point))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
89 (if (search-forward hz-ascii-designnation pos t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
90 (replace-match iso2022-ascii-designation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
91 (if (not decode-hz-line-continuation)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
92 (insert iso2022-ascii-designation)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
93 (setq chinese-found t))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
94 (if (or chinese-found
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
95 (let ((enable-multibyte-characters nil))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
96 ;; Here we check if the text contains EUC (China) codes.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
97 ;; If any, we had better decode them also.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
98 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
99 (re-search-forward "[\240-\377]" nil t)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
100 (decode-coding-region (point-min) (point-max) 'cn-gb-2312)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
101
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
102 ;; "~~" -> "~"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
103 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
104 (while (search-forward "~~" nil t) (delete-char -1))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
105 (- (point-max) (point-min)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
106
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
107 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
108 (defun decode-hz-buffer ()
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
109 "Decode HZ/ZW encoded text in the current buffer."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
110 (interactive)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
111 (decode-hz-region (point-min) (point-max)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
112
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
113 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
114 (defun encode-hz-region (beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
115 "Encode the text in the current region to HZ.
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
116 Return the length of resulting text."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
117 (interactive "r")
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
118 (save-excursion
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
119 (save-restriction
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
120 (narrow-to-region beg end)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
121
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
122 ;; "~" -> "~~"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
123 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
124 (while (search-forward "~" nil t) (insert ?~))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
125
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
126 ;; Chinese GB2312 -> "~{...~}"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
127 (goto-char (point-min))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
128 (if (re-search-forward "\\cc" nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
129 (let ((enable-multibyte-characters nil)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
130 pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
131 (goto-char (setq pos (match-beginning 0)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
132 (encode-coding-region pos (point-max) 'iso-2022-7)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
133 (goto-char pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
134 (while (search-forward iso2022-gb-designation nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
135 (delete-char -3)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
136 (insert hz-gb-designnation))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
137 (goto-char pos)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
138 (while (search-forward iso2022-ascii-designation nil t)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
139 (delete-char -3)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
140 (insert hz-ascii-designnation))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
141 (- (point-max) (point-min)))))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
142
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
143 ;;;###autoload
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
144 (defun encode-hz-buffer ()
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
145 "Encode the text in the current buffer to HZ."
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
146 (interactive)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
147 (encode-hz-region (point-min) (point-max)))
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
148
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
149 ;;
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
150 (provide 'language/china-util)
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
151
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
152 ;;; Local Variables:
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
153 ;;; generated-autoload-file: "../loaddefs.el"
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
154 ;;; End:
3bb7ccffb0c0 Import from CVS: tag r20-3b6
cvs
parents:
diff changeset
155 ;;; china-util.el ends here