1 ;;; viet-util.el --- utilities for Vietnamese -*- coding: iso-2022-7bit; -*-
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; Keywords: mule, multilingual, Vietnamese
8 ;; This file is part of GNU Emacs.
10 ;; GNU Emacs is free software; you can redistribute it and/or modify
11 ;; it under the terms of the GNU General Public License as published by
12 ;; the Free Software Foundation; either version 2, or (at your option)
15 ;; GNU Emacs is distributed in the hope that it will be useful,
16 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 ;; GNU General Public License for more details.
20 ;; You should have received a copy of the GNU General Public License
21 ;; along with GNU Emacs; see the file COPYING. If not, write to the
22 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 ;; Boston, MA 02111-1307, USA.
27 ;; Vietnamese uses ASCII characters and additional 134 unique
28 ;; characters (these are Latin alphabets with various diacritical and
29 ;; tone marks). As far as I know, Vietnamese now has 4 different ways
30 ;; for representing these characters: VISCII, VSCII, VIQR, and
31 ;; Unicode. VISCII and VSCII are simple 1-byte code which assigns 134
32 ;; unique characters in control-code area (0x00..0x1F) and right half
33 ;; area (0x80..0xFF). VIQR is a menmonic encoding specification
34 ;; representing diacritical marks by following ASCII characters.
39 (defun viet-encode-viscii-char (char)
40 "Return VISCII character code of CHAR if appropriate."
41 (aref (char-table-extra-slot viet-viscii-nonascii-translation-table 0)
44 ;; VIQR is a menmonic encoding specification for Vietnamese.
45 ;; It represents diacritical marks by ASCII characters as follows:
46 ;; ------------+----------+--------
47 ;; mark | mnemonic | example
48 ;; ------------+----------+---------
49 ;; breve | ( | a( ->
\e,1e
\e(B
50 ;; circumflex | ^ | a^ ->
\e,1b
\e(B
51 ;; horn | + | o+ ->
\e,1=
\e(B
52 ;; ------------+----------+---------
53 ;; acute | ' | a' ->
\e,1a
\e(B
54 ;; grave | ` | a` ->
\e,1`
\e(B
55 ;; hook above | ? | a? ->
\e,1d
\e(B
56 ;; tilde | ~ | a~ ->
\e,1c
\e(B
57 ;; dot below | . | a. ->
\e,1U
\e(B
58 ;; ------------+----------+---------
59 ;; d bar | dd | dd ->
\e,1p
\e(B
60 ;; ------------+----------+---------
62 (defvar viet-viqr-alist
64 (?
\e,1!
\e(B . "a('") ; 161
65 (?
\e,1"
\e(B . "a(`") ; 162
66 (?
\e,1#
\e(B . "a(.") ; 163
67 (?
\e,1$
\e(B . "a^'") ; 164
68 (?
\e,1%
\e(B . "a^`") ; 165
69 (?
\e,1&
\e(B . "a^?") ; 166
70 (?
\e,1'
\e(B . "a^.") ; 167
71 (?
\e,1(
\e(B . "e~") ; 168
72 (?
\e,1)
\e(B . "e.") ; 169
73 (?
\e,1*
\e(B . "e^'") ; 170
74 (?
\e,1+
\e(B . "e^`") ; 171
75 (?
\e,1,
\e(B . "e^?") ; 172
76 (?
\e,1-
\e(B . "e^~") ; 173
77 (?
\e,1.
\e(B . "e^.") ; 174
78 (?
\e,1/
\e(B . "o^'") ; 175
79 (?
\e,10
\e(B . "o^`") ; 176
80 (?
\e,11
\e(B . "o^?") ; 177
81 (?
\e,12
\e(B . "o^~") ; 178
82 (?
\e,15
\e(B . "o^.") ; 181
83 (?
\e,16
\e(B . "o+`") ; 182
84 (?
\e,17
\e(B . "o+?") ; 183
85 (?
\e,18
\e(B . "i.") ; 184
86 (?
\e,1=
\e(B . "o+") ; 189
87 (?
\e,1>
\e(B . "o+'") ; 190
88 (?
\e,1F
\e(B . "a(?") ; 198
89 (?
\e,1G
\e(B . "a(~") ; 199
90 (?
\e,1O
\e(B . "y`") ; 207
91 (?
\e,1Q
\e(B . "u+'") ; 209
92 (?
\e,1U
\e(B . "a.") ; 213
93 (?
\e,1V
\e(B . "y?") ; 214
94 (?
\e,1W
\e(B . "u+`") ; 215
95 (?
\e,1X
\e(B . "u+?") ; 216
96 (?
\e,1[
\e(B . "y~") ; 219
97 (?
\e,1\
\e(B . "y.") ; 220
98 (?
\e,1^
\e(B . "o+~") ; 222
99 (?
\e,1_
\e(B . "u+") ; 223
100 (?
\e,1`
\e(B . "a`") ; 224
101 (?
\e,1a
\e(B . "a'") ; 225
102 (?
\e,1b
\e(B . "a^") ; 226
103 (?
\e,1c
\e(B . "a~") ; 227
104 (?
\e,1d
\e(B . "a?") ; 228
105 (?
\e,1e
\e(B . "a(") ; 229
106 (?
\e,1f
\e(B . "u+~") ; 230
107 (?
\e,1g
\e(B . "a^~") ; 231
108 (?
\e,1h
\e(B . "e`") ; 232
109 (?
\e,1i
\e(B . "e'") ; 233
110 (?
\e,1j
\e(B . "e^") ; 234
111 (?
\e,1k
\e(B . "e?") ; 235
112 (?
\e,1l
\e(B . "i`") ; 236
113 (?
\e,1m
\e(B . "i'") ; 237
114 (?
\e,1n
\e(B . "i~") ; 238
115 (?
\e,1o
\e(B . "i?") ; 239
116 (?
\e,1p
\e(B . "dd") ; 240
117 (?
\e,1q
\e(B . "u+.") ; 241
118 (?
\e,1r
\e(B . "o`") ; 242
119 (?
\e,1s
\e(B . "o'") ; 243
120 (?
\e,1t
\e(B . "o^") ; 244
121 (?
\e,1u
\e(B . "o~") ; 245
122 (?
\e,1v
\e(B . "o?") ; 246
123 (?
\e,1w
\e(B . "o.") ; 247
124 (?
\e,1x
\e(B . "u.") ; 248
125 (?
\e,1y
\e(B . "u`") ; 249
126 (?
\e,1z
\e(B . "u'") ; 250
127 (?
\e,1{
\e(B . "u~") ; 251
128 (?
\e,1|
\e(B . "u?") ; 252
129 (?
\e,1}
\e(B . "y'") ; 253
130 (?
\e,1~
\e(B . "o+.") ; 254
133 (?
\e,2!
\e(B . "A('") ; 161
134 (?
\e,2"
\e(B . "A(`") ; 162
135 (?
\e,2#
\e(B . "A(.") ; 163
136 (?
\e,2$
\e(B . "A^'") ; 164
137 (?
\e,2%
\e(B . "A^`") ; 165
138 (?
\e,2&
\e(B . "A^?") ; 166
139 (?
\e,2'
\e(B . "A^.") ; 167
140 (?
\e,2(
\e(B . "E~") ; 168
141 (?
\e,2)
\e(B . "E.") ; 169
142 (?
\e,2*
\e(B . "E^'") ; 170
143 (?
\e,2+
\e(B . "E^`") ; 171
144 (?
\e,2,
\e(B . "E^?") ; 172
145 (?
\e,2-
\e(B . "E^~") ; 173
146 (?
\e,2.
\e(B . "E^.") ; 174
147 (?
\e,2/
\e(B . "O^'") ; 175
148 (?
\e,20
\e(B . "O^`") ; 176
149 (?
\e,21
\e(B . "O^?") ; 177
150 (?
\e,22
\e(B . "O^~") ; 178
151 (?
\e,25
\e(B . "O^.") ; 181
152 (?
\e,26
\e(B . "O+`") ; 182
153 (?
\e,27
\e(B . "O+?") ; 183
154 (?
\e,28
\e(B . "I.") ; 184
155 (?
\e,2=
\e(B . "O+") ; 189
156 (?
\e,2>
\e(B . "O+'") ; 190
157 (?
\e,2F
\e(B . "A(?") ; 198
158 (?
\e,2G
\e(B . "A(~") ; 199
159 (?
\e,2O
\e(B . "Y`") ; 207
160 (?
\e,2Q
\e(B . "U+'") ; 209
161 (?
\e,2U
\e(B . "A.") ; 213
162 (?
\e,2V
\e(B . "Y?") ; 214
163 (?
\e,2W
\e(B . "U+`") ; 215
164 (?
\e,2X
\e(B . "U+?") ; 216
165 (?
\e,2[
\e(B . "Y~") ; 219
166 (?
\e,2\
\e(B . "Y.") ; 220
167 (?
\e,2^
\e(B . "O+~") ; 222
168 (?
\e,2_
\e(B . "U+") ; 223
169 (?
\e,2`
\e(B . "A`") ; 224
170 (?
\e,2a
\e(B . "A'") ; 225
171 (?
\e,2b
\e(B . "A^") ; 226
172 (?
\e,2c
\e(B . "A~") ; 227
173 (?
\e,2d
\e(B . "A?") ; 228
174 (?
\e,2e
\e(B . "A(") ; 229
175 (?
\e,2f
\e(B . "U+~") ; 230
176 (?
\e,2g
\e(B . "A^~") ; 231
177 (?
\e,2h
\e(B . "E`") ; 232
178 (?
\e,2i
\e(B . "E'") ; 233
179 (?
\e,2j
\e(B . "E^") ; 234
180 (?
\e,2k
\e(B . "E?") ; 235
181 (?
\e,2l
\e(B . "I`") ; 236
182 (?
\e,2m
\e(B . "I'") ; 237
183 (?
\e,2n
\e(B . "I~") ; 238
184 (?
\e,2o
\e(B . "I?") ; 239
185 (?
\e,2p
\e(B . "DD") ; 240
186 (?
\e,2p
\e(B . "dD") ; 240
187 (?
\e,2p
\e(B . "Dd") ; 240
188 (?
\e,2q
\e(B . "U+.") ; 241
189 (?
\e,2r
\e(B . "O`") ; 242
190 (?
\e,2s
\e(B . "O'") ; 243
191 (?
\e,2t
\e(B . "O^") ; 244
192 (?
\e,2u
\e(B . "O~") ; 245
193 (?
\e,2v
\e(B . "O?") ; 246
194 (?
\e,2w
\e(B . "O.") ; 247
195 (?
\e,2x
\e(B . "U.") ; 248
196 (?
\e,2y
\e(B . "U`") ; 249
197 (?
\e,2z
\e(B . "U'") ; 250
198 (?
\e,2{
\e(B . "U~") ; 251
199 (?
\e,2|
\e(B . "U?") ; 252
200 (?
\e,2}
\e(B . "Y'") ; 253
201 (?
\e,2~
\e(B . "O+.") ; 254
203 ;; escape from composition
204 (?\( . "\\(") ; breve (left parenthesis)
205 (?^ . "\\^") ; circumflex (caret)
206 (?+ . "\\+") ; horn (plus sign)
207 (?' . "\\'") ; acute (apostrophe)
208 (?` . "\\`") ; grave (backquote)
209 (?? . "\\?") ; hook above (question mark)
210 (?~ . "\\~") ; tilde (tilde)
211 (?. . "\\.") ; dot below (period)
212 (?d . "\\d") ; d-bar (d)
213 (?\\ . "\\\\") ; literal backslash
215 "Alist of Vietnamese characters vs corresponding `VIQR' string.")
217 ;; Regular expression matching single Vietnamese character represented
219 (defconst viqr-regexp
220 "[aeiouyAEIOUY]\\([(^+]?['`?~.]\\|[(^+]\\)\\|[Dd][Dd]")
223 (defun viet-decode-viqr-region (from to)
224 "Convert `VIQR' mnemonics of the current region to Vietnamese characaters.
225 When called from a program, expects two arguments,
226 positions (integers or markers) specifying the stretch of the region."
229 (narrow-to-region from to)
230 (goto-char (point-min))
231 (while (re-search-forward viqr-regexp nil t)
232 (let* ((viqr (buffer-substring (match-beginning 0) (match-end 0)))
233 (ch (car (rassoc viqr viet-viqr-alist))))
236 (delete-region (match-beginning 0) (match-end 0))
240 (defun viet-decode-viqr-buffer ()
241 "Convert `VIQR' mnemonics of the current buffer to Vietnamese characaters."
243 (viet-decode-viqr-region (point-min) (point-max)))
246 (defun viet-encode-viqr-region (from to)
247 "Convert Vietnamese characaters of the current region to `VIQR' mnemonics.
248 When called from a program, expects two arguments,
249 positions (integers or markers) specifying the stretch of the region."
252 (narrow-to-region from to)
253 (goto-char (point-min))
254 (while (re-search-forward "\\cv" nil t)
255 (let* ((ch (preceding-char))
256 (viqr (cdr (assq ch viet-viqr-alist))))
263 (defun viet-encode-viqr-buffer ()
264 "Convert Vietnamese characaters of the current buffer to `VIQR' mnemonics."
266 (viet-encode-viqr-region (point-min) (point-max)))
269 (defun viqr-post-read-conversion (len)
272 (narrow-to-region (point) (+ (point) len))
273 (let ((buffer-modified-p (buffer-modified-p)))
274 (viet-decode-viqr-region (point-min) (point-max))
275 (set-buffer-modified-p buffer-modified-p)
276 (- (point-max) (point-min))))))
279 (defun viqr-pre-write-conversion (from to)
280 (let ((old-buf (current-buffer)))
281 (set-buffer (generate-new-buffer " *temp*"))
284 (insert-buffer-substring old-buf from to))
285 (viet-encode-viqr-region (point-min) (point-max))
286 ;; Should return nil as annotations.
292 ;;; viet-util.el ends here