Commit | Line | Data |
---|---|---|
fc2938d1 DL |
1 | ;;; utf-16.el --- UTF-16 encoding/decoding |
2 | ||
cbcd4dc9 | 3 | ;; Copyright (C) 2001, 2002, 2003 Free Software Foundation, Inc. |
fc2938d1 DL |
4 | |
5 | ;; Author: Dave Love <fx@gnu.org> | |
6 | ;; Keywords: Unicode, UTF-16, i18n | |
7 | ||
8 | ;; This file is part of GNU Emacs. | |
9 | ||
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) | |
13 | ;; any later version. | |
14 | ||
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. | |
19 | ||
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. | |
24 | ||
25 | ;;; Commentary: | |
26 | ||
27 | ;; Support for UTF-16, which is a two-byte encoding (modulo | |
cbcd4dc9 DL |
28 | ;; surrogates) of Unicode, defined in RFC 2781. It is written either |
29 | ;; in little or big endian order and either with or without the | |
30 | ;; leading BOM (a two-byte signature which identifies their byte sex). | |
65a0e5fe | 31 | ;; |
cbcd4dc9 | 32 | ;; We provide these base coding systems. |
65a0e5fe KH |
33 | ;; name endian BOM |
34 | ;; ---- ------ --- | |
35 | ;; mule-utf-16le little no | |
36 | ;; mule-utf-16be big no | |
37 | ;; mule-utf-16le-with-signature little yes | |
38 | ;; mule-utf-16be-with-signature big yes | |
39 | ;; mule-utf-16 both yes | |
40 | ;; | |
fc2938d1 DL |
41 | ;; Note that un-decodable sequences aren't (yet?) preserved as raw |
42 | ;; bytes, as they are with utf-8, so reading and writing as utf-16 can | |
43 | ;; corrupt data. | |
44 | ||
45 | ;;; Code: | |
46 | ||
47 | ;; We end up with trivially different -le and -be versions of most | |
48 | ;; things below, sometimes with commonality abstracted into a let | |
49 | ;; binding for maintenance convenience. | |
50 | ||
51 | ;; We'd need new charsets distinct from ascii and eight-bit-control to | |
52 | ;; deal with untranslated sequences, since we can't otherwise | |
53 | ;; distinguish the bytes, as we can with utf-8. | |
54 | ||
55 | ;; ;; Do a multibyte write for bytes in r3 and r4. | |
56 | ;; ;; Intended for untranslatable utf-16 sequences. | |
57 | ;; (define-ccl-program ccl-mule-utf-16-untrans | |
58 | ;; `(0 | |
59 | ;; (if (r3 < 128) | |
60 | ;; (r0 = ,(charset-id 'ascii)) | |
61 | ;; (if (r3 < 160) | |
62 | ;; (r0 = ,(charset-id 'eight-bit-control)) | |
63 | ;; (r0 = ,(charset-id 'eight-bit-graphic)))) | |
64 | ;; (if (r4 < 128) | |
65 | ;; (r0 = ,(charset-id 'ascii)) | |
66 | ;; (if (r4 < 160) | |
67 | ;; (r0 = ,(charset-id 'eight-bit-control)) | |
68 | ;; (r0 = ,(charset-id 'eight-bit-graphic)))) | |
69 | ;; (r1 = r4))) | |
70 | ;; "Do a multibyte write for bytes in r3 and r4. | |
71 | ;; First swap them if we're big endian, indicated by r5==0. | |
72 | ;; Intended for untranslatable utf-16 sequences.") | |
73 | ||
74 | ;; Needed in macro expansion, so can't be let-bound. Zapped after use. | |
75 | (eval-and-compile | |
76 | (defconst utf-16-decode-ucs | |
2217b8e1 | 77 | ;; We have the unicode in r1. Output is charset ID in r0, code |
4fbc4b17 | 78 | ;; point in r1. |
278ce936 KH |
79 | `((lookup-integer utf-subst-table-for-decode r1 r3) |
80 | (if r7 ; got a translation | |
81 | ((r0 = r1) (r1 = r3)) | |
82 | (if (r1 < 128) | |
83 | (r0 = ,(charset-id 'ascii)) | |
84 | (if (r1 < 160) | |
85 | (r0 = ,(charset-id 'eight-bit-control)) | |
86 | (if (r1 < 256) | |
87 | ((r0 = ,(charset-id 'latin-iso8859-1)) | |
88 | (r1 -= 128)) | |
89 | (if (r1 < #x2500) | |
90 | ((r0 = ,(charset-id 'mule-unicode-0100-24ff)) | |
91 | (r1 -= #x100) | |
92 | (r2 = (((r1 / 96) + 32) << 7)) | |
93 | (r1 %= 96) | |
94 | (r1 += (r2 + 32))) | |
95 | (if (r1 < #x3400) | |
96 | ((r0 = ,(charset-id 'mule-unicode-2500-33ff)) | |
97 | (r1 -= #x2500) | |
98 | (r2 = (((r1 / 96) + 32) << 7)) | |
99 | (r1 %= 96) | |
100 | (r1 += (r2 + 32))) | |
101 | (if (r1 < #xd800) ; 2 untranslated bytes | |
102 | ;; ;; Assume this is rare, so don't worry about the | |
103 | ;; ;; overhead of the call. | |
104 | ;; (call mule-utf-16-untrans) | |
105 | ((r0 = ,(charset-id 'mule-unicode-e000-ffff)) | |
106 | (r1 = 15037)) ; U+fffd | |
107 | (if (r1 < #xe000) ; surrogate | |
108 | ;; ((call mule-utf-16-untrans) | |
109 | ;; (write-multibyte-character r0 r1) | |
110 | ;; (read r3 r4) | |
111 | ;; (call mule-utf-16-untrans)) | |
112 | ((read r3 r4) | |
113 | (r0 = ,(charset-id 'mule-unicode-e000-ffff)) | |
114 | (r1 = 15037)) | |
115 | ((r0 = ,(charset-id 'mule-unicode-e000-ffff)) | |
116 | (r1 -= #xe000) | |
117 | (r2 = (((r1 / 96) + 32) << 7)) | |
118 | (r1 %= 96) | |
4fbc4b17 KH |
119 | (r1 += (r2 + 32))))))))))))) |
120 | ||
65a0e5fe | 121 | (defconst utf-16le-decode-loop |
4fbc4b17 KH |
122 | `(loop |
123 | (read r3 r4) | |
124 | (r1 = (r4 <8 r3)) | |
125 | ,utf-16-decode-ucs | |
126 | (translate-character utf-translation-table-for-decode r0 r1) | |
127 | (write-multibyte-character r0 r1) | |
128 | (repeat))) | |
129 | ||
65a0e5fe | 130 | (defconst utf-16be-decode-loop |
4fbc4b17 KH |
131 | `(loop |
132 | (read r3 r4) | |
133 | (r1 = (r3 <8 r4)) | |
134 | ,@utf-16-decode-ucs | |
135 | (translate-character utf-translation-table-for-decode r0 r1) | |
136 | (write-multibyte-character r0 r1) | |
137 | (repeat))) | |
138 | ||
139 | ) | |
fc2938d1 | 140 | |
65a0e5fe | 141 | (define-ccl-program ccl-decode-mule-utf-16le |
fc2938d1 | 142 | `(2 ; 2 bytes -> 1 to 4 bytes |
65a0e5fe | 143 | ,utf-16le-decode-loop) |
2217b8e1 | 144 | "Decode UTF-16LE (little endian without signature bytes). |
fc2938d1 | 145 | Basic decoding is done into the charsets ascii, latin-iso8859-1 and |
278ce936 KH |
146 | mule-unicode-*. Un-representable Unicode characters are decoded as |
147 | U+fffd. The result is run through the translation-table named | |
148 | `utf-translation-table-for-decode'.") | |
fc2938d1 | 149 | |
65a0e5fe | 150 | (define-ccl-program ccl-decode-mule-utf-16be |
fc2938d1 | 151 | `(2 ; 2 bytes -> 1 to 4 bytes |
65a0e5fe | 152 | ,utf-16be-decode-loop) |
2217b8e1 | 153 | "Decode UTF-16BE (big endian without signature bytes). |
fc2938d1 DL |
154 | Basic decoding is done into the charsets ascii, latin-iso8859-1 and |
155 | mule-unicode-*. Un-representable Unicode characters are | |
278ce936 KH |
156 | decoded as U+fffd. The result is run through the translation-table of |
157 | name `utf-translation-table-for-decode'.") | |
fc2938d1 | 158 | |
65a0e5fe | 159 | (define-ccl-program ccl-decode-mule-utf-16le-with-signature |
4fbc4b17 KH |
160 | `(2 |
161 | ((read r3 r4) | |
65a0e5fe KH |
162 | ,utf-16le-decode-loop)) |
163 | "Like ccl-decode-utf-16le but skip the first 2-byte BOM.") | |
4fbc4b17 | 164 | |
65a0e5fe | 165 | (define-ccl-program ccl-decode-mule-utf-16be-with-signature |
4fbc4b17 KH |
166 | `(2 |
167 | ((read r3 r4) | |
65a0e5fe KH |
168 | ,utf-16be-decode-loop)) |
169 | "Like ccl-decode-utf-16be but skip the first 2-byte BOM.") | |
4fbc4b17 KH |
170 | |
171 | (define-ccl-program ccl-decode-mule-utf-16 | |
172 | `(2 | |
173 | ((read r3 r4) | |
174 | (r1 = (r3 <8 r4)) | |
175 | (if (r1 == #xFFFE) | |
176 | ;; R1 is a BOM for little endian. We keep this character as | |
177 | ;; is temporarily. It is removed by post-read-conversion | |
178 | ;; function. | |
179 | (,@utf-16-decode-ucs | |
180 | (write-multibyte-character r0 r1) | |
65a0e5fe | 181 | ,utf-16le-decode-loop) |
4fbc4b17 KH |
182 | ((if (r1 == #xFEFF) |
183 | ;; R1 is a BOM for big endian, but we can't keep that | |
184 | ;; character in the output because it can't be | |
185 | ;; distinguished with the normal U+FEFF. So, we keep | |
186 | ;; #xFFFF instead. | |
187 | ((r1 = #xFFFF) | |
188 | ,@utf-16-decode-ucs) | |
189 | ;; R1 a normal Unicode character. | |
190 | (,@utf-16-decode-ucs | |
191 | (translate-character utf-translation-table-for-decode r0 r1))) | |
192 | (write-multibyte-character r0 r1) | |
65a0e5fe KH |
193 | ,utf-16be-decode-loop)))) |
194 | "Like ccl-decode-utf-16be/le but check the first BOM.") | |
4fbc4b17 | 195 | |
fc2938d1 | 196 | (makunbound 'utf-16-decode-ucs) ; done with it |
65a0e5fe KH |
197 | (makunbound 'utf-16le-decode-loop) |
198 | (makunbound 'utf-16be-decode-loop) | |
fc2938d1 DL |
199 | |
200 | (eval-and-compile | |
201 | (defconst utf-16-decode-to-ucs | |
202 | ;; CCL which, given the result of a multibyte read in r0 and r1, | |
203 | ;; sets r0 to the character's Unicode if the charset is one of the | |
204 | ;; basic utf-8 coding system ones. Otherwise set to U+fffd. | |
205 | `(if (r0 == ,(charset-id 'ascii)) | |
206 | (r0 = r1) | |
207 | (if (r0 == ,(charset-id 'latin-iso8859-1)) | |
208 | (r0 = (r1 + 128)) | |
209 | (if (r0 == ,(charset-id 'eight-bit-control)) | |
210 | (r0 = r1) | |
211 | (if (r0 == ,(charset-id 'eight-bit-graphic)) | |
212 | (r0 = r1) | |
213 | ((r2 = (r1 & #x7f)) | |
214 | (r1 >>= 7) | |
215 | (r3 = ((r1 - 32) * 96)) | |
216 | (r3 += (r2 - 32)) | |
217 | (if (r0 == ,(charset-id 'mule-unicode-0100-24ff)) | |
218 | (r0 = (r3 + #x100)) | |
219 | (if (r0 == ,(charset-id 'mule-unicode-2500-33ff)) | |
220 | (r0 = (r3 + #x2500)) | |
221 | (if (r0 == ,(charset-id 'mule-unicode-e000-ffff)) | |
222 | (r0 = (r3 + #xe000)) | |
4fbc4b17 KH |
223 | (r0 = #xfffd)))))))))) |
224 | ||
65a0e5fe | 225 | (defconst utf-16le-encode-loop |
4fbc4b17 KH |
226 | `(loop |
227 | (read-multibyte-character r0 r1) | |
228 | (lookup-character utf-subst-table-for-encode r0 r1) | |
229 | (if (r7 == 0) | |
230 | ((translate-character utf-translation-table-for-encode r0 r1) | |
231 | ,utf-16-decode-to-ucs)) | |
232 | (write (r0 & 255)) | |
233 | (write (r0 >> 8)) | |
234 | (repeat))) | |
235 | ||
65a0e5fe | 236 | (defconst utf-16be-encode-loop |
4fbc4b17 KH |
237 | `(loop |
238 | (read-multibyte-character r0 r1) | |
239 | (lookup-character utf-subst-table-for-encode r0 r1) | |
240 | (if (r7 == 0) | |
241 | ((translate-character utf-translation-table-for-encode r0 r1) | |
242 | ,utf-16-decode-to-ucs)) | |
243 | (write (r0 >> 8)) | |
244 | (write (r0 & 255)) | |
245 | (repeat))) | |
246 | ) | |
fc2938d1 | 247 | |
65a0e5fe KH |
248 | |
249 | (define-ccl-program ccl-encode-mule-utf-16le | |
fc2938d1 | 250 | `(1 |
65a0e5fe | 251 | ,utf-16le-encode-loop) |
2217b8e1 | 252 | "Encode to UTF-16LE (little endian without signature). |
fc2938d1 DL |
253 | Characters from the charsets ascii, eight-bit-control, |
254 | eight-bit-graphic, latin-iso8859-1 and mule-unicode-* are encoded | |
278ce936 KH |
255 | after translation through the translation-table of name |
256 | `utf-translation-table-for-encode'. | |
fc2938d1 DL |
257 | Others are encoded as U+FFFD.") |
258 | ||
65a0e5fe | 259 | (define-ccl-program ccl-encode-mule-utf-16be |
fc2938d1 | 260 | `(1 |
65a0e5fe | 261 | ,utf-16be-encode-loop) |
2217b8e1 | 262 | "Encode to UTF-16BE (big endian without signature). |
fc2938d1 DL |
263 | Characters from the charsets ascii, eight-bit-control, |
264 | eight-bit-graphic, latin-iso8859-1 and mule-unicode-* are encoded | |
278ce936 KH |
265 | after translation through the translation-table named |
266 | `utf-translation-table-for-encode'. | |
fc2938d1 DL |
267 | Others are encoded as U+FFFD.") |
268 | ||
65a0e5fe | 269 | (define-ccl-program ccl-encode-mule-utf-16le-with-signature |
4fbc4b17 KH |
270 | `(1 |
271 | ((write #xFF) | |
272 | (write #xFE) | |
65a0e5fe | 273 | ,utf-16le-encode-loop)) |
4fbc4b17 KH |
274 | "Encode to UTF-16 (little endian with signature). |
275 | Characters from the charsets ascii, eight-bit-control, | |
276 | eight-bit-graphic, latin-iso8859-1 and mule-unicode-* are encoded | |
277 | after translation through the translation-table of name | |
278 | `utf-translation-table-for-encode'. | |
279 | Others are encoded as U+FFFD.") | |
280 | ||
65a0e5fe | 281 | (define-ccl-program ccl-encode-mule-utf-16be-with-signature |
4fbc4b17 KH |
282 | `(1 |
283 | ((write #xFE) | |
284 | (write #xFF) | |
65a0e5fe | 285 | ,utf-16be-encode-loop)) |
4fbc4b17 KH |
286 | "Encode to UTF-16 (big endian with signature). |
287 | Characters from the charsets ascii, eight-bit-control, | |
288 | eight-bit-graphic, latin-iso8859-1 and mule-unicode-* are encoded | |
289 | after translation through the translation-table named | |
290 | `utf-translation-table-for-encode'. | |
291 | Others are encoded as U+FFFD.") | |
292 | ||
fc2938d1 | 293 | (makunbound 'utf-16-decode-to-ucs) |
65a0e5fe KH |
294 | (makunbound 'utf-16le-encode-loop) |
295 | (makunbound 'utf-16be-encode-loop) | |
4fbc4b17 KH |
296 | |
297 | (defun mule-utf-16-post-read-conversion (length) | |
298 | (when (> length 0) | |
299 | (let ((char (following-char))) | |
300 | (cond ((= char (decode-char 'ucs #xFFFE)) | |
301 | (delete-char 1) | |
302 | (setq last-coding-system-used | |
303 | (coding-system-change-text-conversion | |
304 | last-coding-system-used | |
65a0e5fe | 305 | 'mule-utf-16le-with-signature)) |
4fbc4b17 KH |
306 | (setq length (1- length))) |
307 | ((= char (decode-char 'ucs #xFFFF)) | |
308 | (delete-char 1) | |
309 | (setq last-coding-system-used | |
310 | (coding-system-change-text-conversion | |
311 | last-coding-system-used | |
65a0e5fe | 312 | 'mule-utf-16be-with-signature)) |
4fbc4b17 KH |
313 | (setq length (1- length))) |
314 | (t | |
65a0e5fe | 315 | (setq last-coding-system-used 'mule-utf-16be))))) |
4fbc4b17 | 316 | length) |
fc2938d1 | 317 | |
fc2938d1 DL |
318 | (let ((doc " |
319 | ||
278ce936 KH |
320 | It supports Unicode characters of these ranges: |
321 | U+0000..U+33FF, U+E000..U+FFFF. | |
322 | They correspond to these Emacs character sets: | |
323 | ascii, latin-iso8859-1, mule-unicode-0100-24ff, | |
324 | mule-unicode-2500-33ff, mule-unicode-e000-ffff | |
325 | ||
326 | On decoding (e.g. reading a file), Unicode characters not in the above | |
327 | ranges are decoded as U+FFFD, effectively corrupting the data | |
a1506d29 | 328 | if they are re-encoded. |
278ce936 KH |
329 | |
330 | On encoding (e.g. writing a file), Emacs characters not belonging to | |
331 | any of the character sets listed above are encoded into the byte | |
332 | sequence representing U+FFFD (REPLACEMENT CHARACTER).")) | |
fc2938d1 | 333 | (make-coding-system |
65a0e5fe | 334 | 'mule-utf-16le 4 |
fc2938d1 DL |
335 | ?u ; Mule-UCS uses ?U, but code-pages uses that for koi8-u. |
336 | (concat | |
65a0e5fe | 337 | "UTF-16LE encoding for Emacs-supported Unicode characters." |
fc2938d1 DL |
338 | doc) |
339 | ||
65a0e5fe | 340 | '(ccl-decode-mule-utf-16le . ccl-encode-mule-utf-16le) |
fc2938d1 DL |
341 | '((safe-charsets |
342 | ascii | |
343 | eight-bit-control | |
344 | latin-iso8859-1 | |
345 | mule-unicode-0100-24ff | |
346 | mule-unicode-2500-33ff | |
347 | mule-unicode-e000-ffff) | |
348 | (mime-charset . utf-16le) | |
cbcd4dc9 | 349 | (mime-text-unsuitable . t) |
fc2938d1 | 350 | (valid-codes (0 . 255)) |
278ce936 KH |
351 | (dependency unify-8859-on-encoding-mode |
352 | unify-8859-on-decoding-mode | |
353 | utf-fragment-on-decoding | |
354 | utf-translate-cjk))) | |
fc2938d1 DL |
355 | |
356 | (make-coding-system | |
65a0e5fe | 357 | 'mule-utf-16be 4 ?u |
fc2938d1 | 358 | (concat |
65a0e5fe | 359 | "UTF-16BE encoding for Emacs-supported Unicode characters." |
fc2938d1 DL |
360 | doc) |
361 | ||
65a0e5fe | 362 | '(ccl-decode-mule-utf-16be . ccl-encode-mule-utf-16be) |
fc2938d1 DL |
363 | '((safe-charsets |
364 | ascii | |
365 | eight-bit-control | |
366 | latin-iso8859-1 | |
367 | mule-unicode-0100-24ff | |
368 | mule-unicode-2500-33ff | |
369 | mule-unicode-e000-ffff) | |
370 | (mime-charset . utf-16be) | |
4fbc4b17 KH |
371 | (valid-codes (0 . 255)) |
372 | (dependency unify-8859-on-encoding-mode | |
373 | unify-8859-on-decoding-mode | |
374 | utf-fragment-on-decoding | |
375 | utf-translate-cjk))) | |
376 | ||
377 | (make-coding-system | |
65a0e5fe | 378 | 'mule-utf-16le-with-signature 4 ?u |
4fbc4b17 KH |
379 | (concat |
380 | "Little endian UTF-16 (with BOM) for Emacs-supported Unicode characters." | |
381 | doc) | |
382 | ||
65a0e5fe KH |
383 | '(ccl-decode-mule-utf-16le-with-signature |
384 | . ccl-encode-mule-utf-16le-with-signature) | |
4fbc4b17 KH |
385 | '((safe-charsets |
386 | ascii | |
387 | eight-bit-control | |
388 | latin-iso8859-1 | |
389 | mule-unicode-0100-24ff | |
390 | mule-unicode-2500-33ff | |
391 | mule-unicode-e000-ffff) | |
392 | (coding-category . coding-category-utf-16-le) | |
393 | (mime-charset . utf-16) | |
cbcd4dc9 | 394 | (mime-text-unsuitable . t) |
4fbc4b17 KH |
395 | (valid-codes (0 . 255)) |
396 | (dependency unify-8859-on-encoding-mode | |
397 | unify-8859-on-decoding-mode | |
398 | utf-fragment-on-decoding | |
399 | utf-translate-cjk))) | |
400 | ||
401 | (make-coding-system | |
65a0e5fe | 402 | 'mule-utf-16be-with-signature 4 ?u |
4fbc4b17 KH |
403 | (concat |
404 | "Big endian UTF-16 (with BOM) for Emacs-supported Unicode characters." | |
405 | doc) | |
406 | ||
65a0e5fe KH |
407 | '(ccl-decode-mule-utf-16be-with-signature |
408 | . ccl-encode-mule-utf-16be-with-signature) | |
4fbc4b17 KH |
409 | '((safe-charsets |
410 | ascii | |
411 | eight-bit-control | |
412 | latin-iso8859-1 | |
413 | mule-unicode-0100-24ff | |
414 | mule-unicode-2500-33ff | |
415 | mule-unicode-e000-ffff) | |
416 | (coding-category . coding-category-utf-16-be) | |
417 | (mime-charset . utf-16) | |
418 | (valid-codes (0 . 255)) | |
419 | (dependency unify-8859-on-encoding-mode | |
420 | unify-8859-on-decoding-mode | |
421 | utf-fragment-on-decoding | |
422 | utf-translate-cjk))) | |
423 | ||
424 | (make-coding-system | |
425 | 'mule-utf-16 4 ?u | |
426 | (concat | |
427 | "UTF-16 (with or without BOM) for Emacs-supported Unicode characters." | |
428 | doc) | |
429 | ||
65a0e5fe | 430 | '(ccl-decode-mule-utf-16 . ccl-encode-mule-utf-16be-with-signature) |
4fbc4b17 KH |
431 | '((safe-charsets |
432 | ascii | |
433 | eight-bit-control | |
434 | latin-iso8859-1 | |
435 | mule-unicode-0100-24ff | |
436 | mule-unicode-2500-33ff | |
437 | mule-unicode-e000-ffff) | |
fc2938d1 | 438 | (coding-category . coding-category-utf-16-be) |
4fbc4b17 | 439 | (mime-charset . utf-16) |
cbcd4dc9 | 440 | (mime-text-unsuitable . t) |
fc2938d1 | 441 | (valid-codes (0 . 255)) |
278ce936 KH |
442 | (dependency unify-8859-on-encoding-mode |
443 | unify-8859-on-decoding-mode | |
444 | utf-fragment-on-decoding | |
4fbc4b17 KH |
445 | utf-translate-cjk) |
446 | (post-read-conversion . mule-utf-16-post-read-conversion))) | |
447 | ) | |
fc2938d1 | 448 | |
65a0e5fe KH |
449 | (define-coding-system-alias 'utf-16le 'mule-utf-16le) |
450 | (define-coding-system-alias 'utf-16be 'mule-utf-16be) | |
451 | (define-coding-system-alias 'utf-16le-with-signature | |
452 | 'mule-utf-16le-with-signature) | |
453 | (define-coding-system-alias 'utf-16be-with-signature | |
454 | 'mule-utf-16be-with-signature) | |
4fbc4b17 | 455 | (define-coding-system-alias 'utf-16 'mule-utf-16) |
fc2938d1 | 456 | |
65a0e5fe KH |
457 | ;; For backward compatibility. |
458 | (define-coding-system-alias 'mule-utf-16-le 'mule-utf-16le-with-signature) | |
459 | (define-coding-system-alias 'utf-16-le 'mule-utf-16le-with-signature) | |
460 | (define-coding-system-alias 'mule-utf-16-be 'mule-utf-16be-with-signature) | |
461 | (define-coding-system-alias 'utf-16-be 'mule-utf-16be-with-signature) | |
462 | ||
ab5796a9 | 463 | ;;; arch-tag: 85455d46-d9c9-466d-a6f3-c3582a7367c4 |
fc2938d1 | 464 | ;;; utf-16.el ends here |