1 ;;; china-util.el --- utilities for Chinese -*- coding: utf-8 -*-
3 ;; Copyright (C) 1995, 2001-2017 Free Software Foundation, Inc.
4 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
5 ;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
6 ;; National Institute of Advanced Industrial Science and Technology (AIST)
7 ;; Registration Number H14PRO021
9 ;; National Institute of Advanced Industrial Science and Technology (AIST)
10 ;; Registration Number H13PRO009
12 ;; Keywords: mule, multilingual, Chinese
14 ;; This file is part of GNU Emacs.
16 ;; GNU Emacs is free software: you can redistribute it and/or modify
17 ;; it under the terms of the GNU General Public License as published by
18 ;; the Free Software Foundation, either version 3 of the License, or
19 ;; (at your option) any later version.
21 ;; GNU Emacs is distributed in the hope that it will be useful,
22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24 ;; GNU General Public License for more details.
26 ;; You should have received a copy of the GNU General Public License
27 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
33 ;; Hz/ZW/EUC-TW encoding stuff
35 ;; HZ is an encoding method for Chinese character set GB2312 used
36 ;; widely in Internet. It is very similar to 7-bit environment of
37 ;; ISO-2022. The difference is that HZ uses the sequence "~{" and
38 ;; "~}" for designating GB2312 and ASCII respectively, hence, it
39 ;; doesn't uses ESC (0x1B) code.
41 ;; ZW is another encoding method for Chinese character set GB2312. It
42 ;; encodes Chinese characters line by line by starting each line with
43 ;; the sequence "zW". It also uses only 7-bit as HZ.
45 ;; EUC-TW is similar to EUC-KS or EUC-JP. Its main character set is
46 ;; plane 1 of CNS 11643; characters of planes 2 to 7 are accessed with
47 ;; a single shift escape followed by three bytes: the first gives the
48 ;; plane, the second and third the character code. Note that characters
49 ;; of plane 1 are (redundantly) accessible with a single shift escape
52 ;; ISO-2022 escape sequence to designate GB2312.
53 (defvar iso2022-gb-designation
"\e$A")
54 ;; HZ escape sequence to designate GB2312.
55 (defvar hz-gb-designation
"~{")
56 ;; ISO-2022 escape sequence to designate ASCII.
57 (defvar iso2022-ascii-designation
"\e(B")
58 ;; HZ escape sequence to designate ASCII.
59 (defvar hz-ascii-designation
"~}")
60 ;; Regexp of ZW sequence to start GB2312.
61 (defvar zw-start-gb
"^zW")
62 ;; Regexp for start of GB2312 in an encoding mixture of HZ and ZW.
63 (defvar hz
/zw-start-gb
64 (concat hz-gb-designation
"\\|" zw-start-gb
"\\|[^\0-\177]"))
66 (defvar decode-hz-line-continuation nil
67 "Flag to tell if we should care line continuation convention of Hz.")
69 (defconst hz-set-msb-table
77 (push (decode-char 'eight-bit
(+ i
128)) chars
)
79 (apply 'string
(nreverse chars
)))))
82 (defun decode-hz-region (beg end
)
83 "Decode HZ/ZW encoded text in the current region.
84 Return the length of resulting text."
89 (narrow-to-region beg end
)
91 ;; We, at first, convert HZ/ZW to `iso-2022-7bit',
94 ;; "~\n" -> "", "~~" -> "~"
95 (goto-char (point-min))
96 (while (search-forward "~" nil t
)
97 (setq ch
(following-char))
99 (delete-region (1- (point)) (1+ (point)))
101 (insert iso2022-gb-designation
)
102 (if (looking-at "\\([!-}][!-~]\\)*")
103 (goto-char (match-end 0)))
104 (if (looking-at hz-ascii-designation
)
105 (delete-region (match-beginning 0) (match-end 0)))
106 (insert iso2022-ascii-designation
)
107 (decode-coding-region pos
(point) 'iso-2022-7bit
))
113 decode-hz-line-continuation
)
114 (delete-region (1- (point)) (1+ (point))))
119 (- (point-max) (point-min)))))
122 (defun decode-hz-buffer ()
123 "Decode HZ/ZW encoded text in the current buffer."
125 (decode-hz-region (point-min) (point-max)))
127 (defvar hz-category-table nil
)
130 (defun encode-hz-region (beg end
)
131 "Encode the text in the current region to HZ.
132 Return the length of resulting text."
134 (unless hz-category-table
135 (setq hz-category-table
(make-category-table))
136 (with-category-table hz-category-table
137 (define-category ?c
"hz encodable")
138 (map-charset-chars #'modify-category-entry
'ascii ?c
)
139 (map-charset-chars #'modify-category-entry
'chinese-gb2312 ?c
)))
142 (narrow-to-region beg end
)
143 (with-category-table hz-category-table
145 (goto-char (point-min))
146 (while (search-forward "~" nil t
) (insert ?~
))
149 (goto-char (point-min))
150 (while (search-forward "\e" nil t
) (insert ?\e
))
152 ;; Non-ASCII-GB2312 -> \uXXXX
153 (goto-char (point-min))
154 (while (re-search-forward "\\Cc" nil t
)
155 (let ((ch (preceding-char)))
157 (insert (format (if (< ch
#x10000
) "\\u%04X" "\\U%08X") ch
))))
159 ;; Prefer chinese-gb2312 for Chinese characters.
160 (put-text-property (point-min) (point-max) 'charset
'chinese-gb2312
)
161 (encode-coding-region (point-min) (point-max) 'iso-2022-7bit
)
163 ;; ESC $ B ... ESC ( B -> ~{ ... ~}
165 (goto-char (point-min))
166 (while (search-forward "\e" nil t
)
167 (if (= (following-char) ?\e
)
171 (if (looking-at iso2022-gb-designation
)
173 (delete-region (match-beginning 0) (match-end 0))
174 (insert hz-gb-designation
)
175 (search-forward iso2022-ascii-designation nil
'move
)
176 (delete-region (match-beginning 0) (match-end 0))
177 (insert hz-ascii-designation
))))))
178 (- (point-max) (point-min)))))
181 (defun encode-hz-buffer ()
182 "Encode the text in the current buffer to HZ."
184 (encode-hz-region (point-min) (point-max)))
187 (defun post-read-decode-hz (len)
189 (buffer-modified-p (buffer-modified-p))
190 last-coding-system-used
)
192 (decode-hz-region pos
(+ pos len
))
193 (set-buffer-modified-p buffer-modified-p
))))
196 (defun pre-write-encode-hz (from to
)
197 (let ((buf (current-buffer)))
198 (set-buffer (generate-new-buffer " *temp*"))
201 (insert-buffer-substring buf from to
))
202 (let (last-coding-system-used)
203 (encode-hz-region 1 (point-max)))
206 (provide 'china-util
)
208 ;;; china-util.el ends here