2 .\" The Regents of the University of California. All rights reserved.
4 .\" This code is derived from software contributed to Berkeley by
5 .\" Paul Borman at Krystal Technologies.
7 .\" Redistribution and use in source and binary forms, with or without
8 .\" modification, are permitted provided that the following conditions
10 .\" 1. Redistributions of source code must retain the above copyright
11 .\" notice, this list of conditions and the following disclaimer.
12 .\" 2. Redistributions in binary form must reproduce the above copyright
13 .\" notice, this list of conditions and the following disclaimer in the
14 .\" documentation and/or other materials provided with the distribution.
15 .\" 3. Neither the name of the University nor the names of its contributors
16 .\" may be used to endorse or promote products derived from this software
17 .\" without specific prior written permission.
19 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 .\" @(#)euc.4 8.1 (Berkeley) 6/4/93
32 .\" $FreeBSD: src/lib/libc/locale/euc.4,v 1.8.2.1 2001/07/22 12:06:40 dd Exp $
33 .\" $DragonFly: src/share/man/man5/euc.5,v 1.3 2005/03/24 12:48:04 swildner Exp $
40 .Nd EUC encoding of runes
58 encoding is provided for compatibility with
63 for a complete description of the
68 implements a system of 4 multibyte codesets.
69 A multibyte character in the first codeset consists of
71 bytes starting with a byte in the range of 0x00 to 0x7f.
72 To allow use of ASCII,
75 A multibyte character in the second codeset consists of
77 bytes starting with a byte in the range of 0x80-0xff excluding 0x8e and 0x8f.
78 A multibyte character in the third codeset consists of
80 bytes starting with the byte 0x8e.
81 A multibyte character in the fourth codeset consists of
83 bytes starting with the byte 0x8f.
89 multibyte characters is dependent on the
94 First, the bytes are moved into a
98 byte0 << ((\fIlen\fPN-1) * 8) | byte1 << ((\fIlen\fPN-2) * 8) | ... | byte\fIlen\fPN-1
101 The result is then ANDed with
105 Codesets 2 and 3 are special in that the leading byte (0x8e or 0x8f) is
106 first removed and the
108 argument is reduced by 1.
110 For example, the Japanese locale has the following
114 VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080
117 Codeset 1 consists of the values 0x0000 - 0x007f.
119 Codeset 2 consists of the values who have the bits 0x8080 set.
121 Codeset 3 consists of the values 0x0080 - 0x00ff.
123 Codeset 4 consists of the values 0x8000 - 0xff7f excluding the values
124 which have the 0x0080 bit set.
126 Notice that the global
128 is set to 0x8080, this implies that from those 2 bits the codeset can
130 .Sh "EXAMPLE - Japanese Locale"
131 This is a complete example of an
133 source file for the Japanese locale
136 * Japanese LOCALE_CTYPE definitions using EUC of JIS character sets
145 VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080
150 ALPHA 'A' - 'Z' 'a' - 'z'
151 CONTROL 0x00 - 0x1f 0x7f
155 PUNCT 0x21 - 0x2f 0x3a - 0x40 0x5b - 0x60 0x7b - 0x7e
156 SPACE 0x09 - 0x0d 0x20
158 XDIGIT 'a' - 'f' 'A' - 'F'
162 MAPLOWER < 'A' - 'Z' : 'a' > < 'a' - 'z' : 'a' >
163 MAPUPPER < 'A' - 'Z' : 'A' > < 'a' - 'z' : 'A' >
164 TODIGIT < '0' - '9' : 0 >
165 TODIGIT < 'A' - 'F' : 10 > < 'a' - 'f' : 10 >
173 SPECIAL 0xa1a2 - 0xa1fe
174 PUNCT 0xa1a2 - 0xa1f8 /* A few too many in here... */
176 SPECIAL 0xa2a1 - 0xa2ae 0xa2ba - 0xa2c1 0xa2ca - 0xa2d0 0xa2dc - 0xa2ea
177 SPECIAL 0xa2f2 - 0xa2f9 0xa2fe
179 DIGIT 0xa3b0 - 0xa3b9
180 UPPER 0xa3c1 - 0xa3da /* Romaji */
181 LOWER 0xa3e1 - 0xa3fa /* Romaji */
182 MAPLOWER < 0xa3c1 - 0xa3da : 0xa3e1 > /* English */
183 MAPLOWER < 0xa3e1 - 0xa3fa : 0xa3e1 > /* English */
184 MAPUPPER < 0xa3c1 - 0xa3da : 0xa3c1 >
185 MAPUPPER < 0xa3e1 - 0xa3fa : 0xa3c1 >
187 XDIGIT 0xa3c1 - 0xa3c6 0xa3e1 - 0xa3e6
189 TODIGIT < 0xa3b0 - 0xa3b9 : 0 >
190 TODIGIT < 0xa3c1 - 0xa3c6 : 10 > < 0xa3e1 - 0xa3e6 : 10 >
192 PHONOGRAM 0xa4a1 - 0xa4f3
193 PHONOGRAM 0xa5a1 - 0xa5f6
195 UPPER 0xa6a1 - 0xa6b8 /* Greek */
196 LOWER 0xa6c1 - 0xa6d8 /* Greek */
197 MAPLOWER < 0xa6a1 - 0xa6b8 : 0xa6c1 > < 0xa6c1 - 0xa6d8 : 0xa6c1 >
198 MAPUPPER < 0xa6a1 - 0xa6b8 : 0xa6a1 > < 0xa6c1 - 0xa6d8 : 0xa6a1 >
200 UPPER 0xa7a1 - 0xa7c1 /* Cyrillic */
201 LOWER 0xa7d1 - 0xa7f1 /* Cyrillic */
202 MAPLOWER < 0xa7a1 - 0xa7c1 : 0xa7d1 > < 0xa7d1 - 0xa7f1 : 0xa7d1 >
203 MAPUPPER < 0xa7a1 - 0xa7c1 : 0xa7a1 > < 0xa7d1 - 0xa7f1 : 0xa7a1 >
205 SPECIAL 0xa8a1 - 0xa8c0
207 IDEOGRAM 0xb0a1 - 0xb0fe 0xb1a1 - 0xb1fe 0xb2a1 - 0xb2fe
208 IDEOGRAM 0xb3a1 - 0xb3fe 0xb4a1 - 0xb4fe 0xb5a1 - 0xb5fe
209 IDEOGRAM 0xb6a1 - 0xb6fe 0xb7a1 - 0xb7fe 0xb8a1 - 0xb8fe
210 IDEOGRAM 0xb9a1 - 0xb9fe 0xbaa1 - 0xbafe 0xbba1 - 0xbbfe
211 IDEOGRAM 0xbca1 - 0xbcfe 0xbda1 - 0xbdfe 0xbea1 - 0xbefe
212 IDEOGRAM 0xbfa1 - 0xbffe 0xc0a1 - 0xc0fe 0xc1a1 - 0xc1fe
213 IDEOGRAM 0xc2a1 - 0xc2fe 0xc3a1 - 0xc3fe 0xc4a1 - 0xc4fe
214 IDEOGRAM 0xc5a1 - 0xc5fe 0xc6a1 - 0xc6fe 0xc7a1 - 0xc7fe
215 IDEOGRAM 0xc8a1 - 0xc8fe 0xc9a1 - 0xc9fe 0xcaa1 - 0xcafe
216 IDEOGRAM 0xcba1 - 0xcbfe 0xcca1 - 0xccfe 0xcda1 - 0xcdfe
217 IDEOGRAM 0xcea1 - 0xcefe 0xcfa1 - 0xcfd3 0xd0a1 - 0xd0fe
218 IDEOGRAM 0xd1a1 - 0xd1fe 0xd2a1 - 0xd2fe 0xd3a1 - 0xd3fe
219 IDEOGRAM 0xd4a1 - 0xd4fe 0xd5a1 - 0xd5fe 0xd6a1 - 0xd6fe
220 IDEOGRAM 0xd7a1 - 0xd7fe 0xd8a1 - 0xd8fe 0xd9a1 - 0xd9fe
221 IDEOGRAM 0xdaa1 - 0xdafe 0xdba1 - 0xdbfe 0xdca1 - 0xdcfe
222 IDEOGRAM 0xdda1 - 0xddfe 0xdea1 - 0xdefe 0xdfa1 - 0xdffe
223 IDEOGRAM 0xe0a1 - 0xe0fe 0xe1a1 - 0xe1fe 0xe2a1 - 0xe2fe
224 IDEOGRAM 0xe3a1 - 0xe3fe 0xe4a1 - 0xe4fe 0xe5a1 - 0xe5fe
225 IDEOGRAM 0xe6a1 - 0xe6fe 0xe7a1 - 0xe7fe 0xe8a1 - 0xe8fe
226 IDEOGRAM 0xe9a1 - 0xe9fe 0xeaa1 - 0xeafe 0xeba1 - 0xebfe
227 IDEOGRAM 0xeca1 - 0xecfe 0xeda1 - 0xedfe 0xeea1 - 0xeefe
228 IDEOGRAM 0xefa1 - 0xeffe 0xf0a1 - 0xf0fe 0xf1a1 - 0xf1fe
229 IDEOGRAM 0xf2a1 - 0xf2fe 0xf3a1 - 0xf3fe 0xf4a1 - 0xf4a4
231 * This is for Code Set 3, half-width kana
234 PHONOGRAM 0xa1 - 0xdf
235 CONTROL 0x84 - 0x97 0x9b - 0x9f 0xe0 - 0xfe