1.\" Copyright (c) 1993 2.\" The Regents of the University of California. All rights reserved. 3.\" 4.\" This code is derived from software contributed to Berkeley by 5.\" Paul Borman at Krystal Technologies. 6.\" 7.\" Redistribution and use in source and binary forms, with or without 8.\" modification, are permitted provided that the following conditions 9.\" are met: 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. All advertising materials mentioning features or use of this software 16.\" must display the following acknowledgement: 17.\" This product includes software developed by the University of 18.\" California, Berkeley and its contributors. 19.\" 4. Neither the name of the University nor the names of its contributors 20.\" may be used to endorse or promote products derived from this software 21.\" without specific prior written permission. 22.\" 23.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 24.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 27.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33.\" SUCH DAMAGE. 34.\" 35.\" @(#)euc.4 8.1 (Berkeley) 6/4/93 36.\" 37.Dd "June 4, 1993" 38.Dt EUC 4 39.Os 40.Sh NAME 41.Nm euc 42.Nd EUC encoding of runes 43.Sh SYNOPSIS 44.Nm ENCODING 45.Qq EUC 46.Pp 47.Nm VARIABLE 48.Ar len1 49.Ar mask1 50.Ar len2 51.Ar mask2 52.Ar len3 53.Ar mask3 54.Ar len4 55.Ar mask4 56.Ar mask 57.Sh DESCRIPTION 58The 59.Nm EUC 60encoding is provided for compatibility with 61.Ux 62based systems. 63See 64.Xr mklocale 1 65for a complete description of the 66.Ev LC_CTYPE 67source file format. 68.Pp 69.Nm EUC 70implements a system of 4 multibyte codesets. 71A multibyte character in the first codeset consists of 72.Ar len1 73bytes starting with a byte in the range of 0x00 to 0x7f. 74To allow use of ASCII, 75.Ar len1 76is always 1. 77A multibyte character in the second codeset consists of 78.Ar len2 79bytes starting with a byte in the range of 0x80-0xff excluding 0x8e and 0x8f. 80A multibyte character in the third codeset consists of 81.Ar len3 82bytes starting with the byte 0x8e. 83A multibyte character in the fourth codeset consists of 84.Ar len4 85bytes starting with the byte 0x8f. 86.Pp 87The 88.Ev rune_t 89encoding of 90.Nm EUC 91multibyte characters is dependent on the 92.Ar len 93and 94.Ar mask 95arguments. 96First, the bytes are moved into a 97.Ev rune_t 98as follows: 99.Bd -literal 100byte0 << ((\fIlen\fPN-1) * 8) | byte1 << ((\fIlen\fPN-2) * 8) | ... | byte\fIlen\fPN-1 101.Ed 102.Pp 103The result is then ANDed with 104.Ar ~mask 105and ORed with 106.Ar maskN . 107Codesets 2 and 3 are special in that the leading byte (0x8e or 0x8f) is 108first removed and the 109.Ar lenN 110argument is reduced by 1. 111.Pp 112For example, the Japanese locale has the following 113.Ev VARIABLE 114line: 115.Bd -literal 116VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080 117.Ed 118.Pp 119Codeset 1 consists of the values 0x0000 - 0x007f. 120.Pp 121Codeset 2 consists of the values who have the bits 0x8080 set. 122.Pp 123Codeset 3 consists of the values 0x0080 - 0x00ff. 124.Pp 125Codeset 4 consists of the values 0x8000 - 0xff7f excluding the values 126which have the 0x0080 bit set. 127.Pp 128Notice that the global 129.Ar mask 130is set to 0x8080, this implies that from those 2 bits the codeset can 131be determined. 132.Sh "EXAMPLE - Japanese Locale" 133This is a complete example of an 134.Ev LC_CTYPE 135source file for the Japanese locale 136.Bd -literal 137/* 138 * Japanese LOCALE_CTYPE definitions using EUC of JIS character sets 139 */ 140 141ENCODING "EUC" 142 143/* JIS JIS JIS */ 144/* X201 X208 X201 */ 145/* 00-7f 84-fe */ 146 147VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080 148 149/* 150 * Code Set 1 151 */ 152ALPHA 'A' - 'Z' 'a' - 'z' 153CONTROL 0x00 - 0x1f 0x7f 154DIGIT '0' - '9' 155GRAPH 0x21 - 0x7e 156LOWER 'a' - 'z' 157PUNCT 0x21 - 0x2f 0x3a - 0x40 0x5b - 0x60 0x7b - 0x7e 158SPACE 0x09 - 0x0d 0x20 159UPPER 'A' - 'Z' 160XDIGIT 'a' - 'f' 'A' - 'F' 161BLANK ' ' '\t' 162PRINT 0x20 - 0x7e 163 164MAPLOWER < 'A' - 'Z' : 'a' > < 'a' - 'z' : 'a' > 165MAPUPPER < 'A' - 'Z' : 'A' > < 'a' - 'z' : 'A' > 166TODIGIT < '0' - '9' : 0 > 167TODIGIT < 'A' - 'F' : 10 > < 'a' - 'f' : 10 > 168 169/* 170 * Code Set 2 171 */ 172 173SPACE 0xa1a1 174PHONOGRAM 0xa1bc 175SPECIAL 0xa1a2 - 0xa1fe 176PUNCT 0xa1a2 - 0xa1f8 /* A few too many in here... */ 177 178SPECIAL 0xa2a1 - 0xa2ae 0xa2ba - 0xa2c1 0xa2ca - 0xa2d0 0xa2dc - 0xa2ea 179SPECIAL 0xa2f2 - 0xa2f9 0xa2fe 180 181DIGIT 0xa3b0 - 0xa3b9 182UPPER 0xa3c1 - 0xa3da /* Romaji */ 183LOWER 0xa3e1 - 0xa3fa /* Romaji */ 184MAPLOWER < 0xa3c1 - 0xa3da : 0xa3e1 > /* English */ 185MAPLOWER < 0xa3e1 - 0xa3fa : 0xa3e1 > /* English */ 186MAPUPPER < 0xa3c1 - 0xa3da : 0xa3c1 > 187MAPUPPER < 0xa3e1 - 0xa3fa : 0xa3c1 > 188 189XDIGIT 0xa3c1 - 0xa3c6 0xa3e1 - 0xa3e6 190 191TODIGIT < 0xa3b0 - 0xa3b9 : 0 > 192TODIGIT < 0xa3c1 - 0xa3c6 : 10 > < 0xa3e1 - 0xa3e6 : 10 > 193 194PHONOGRAM 0xa4a1 - 0xa4f3 195PHONOGRAM 0xa5a1 - 0xa5f6 196 197UPPER 0xa6a1 - 0xa6b8 /* Greek */ 198LOWER 0xa6c1 - 0xa6d8 /* Greek */ 199MAPLOWER < 0xa6a1 - 0xa6b8 : 0xa6c1 > < 0xa6c1 - 0xa6d8 : 0xa6c1 > 200MAPUPPER < 0xa6a1 - 0xa6b8 : 0xa6a1 > < 0xa6c1 - 0xa6d8 : 0xa6a1 > 201 202UPPER 0xa7a1 - 0xa7c1 /* Cyrillic */ 203LOWER 0xa7d1 - 0xa7f1 /* Cyrillic */ 204MAPLOWER < 0xa7a1 - 0xa7c1 : 0xa7d1 > < 0xa7d1 - 0xa7f1 : 0xa7d1 > 205MAPUPPER < 0xa7a1 - 0xa7c1 : 0xa7a1 > < 0xa7d1 - 0xa7f1 : 0xa7a1 > 206 207SPECIAL 0xa8a1 - 0xa8c0 208 209IDEOGRAM 0xb0a1 - 0xb0fe 0xb1a1 - 0xb1fe 0xb2a1 - 0xb2fe 210IDEOGRAM 0xb3a1 - 0xb3fe 0xb4a1 - 0xb4fe 0xb5a1 - 0xb5fe 211IDEOGRAM 0xb6a1 - 0xb6fe 0xb7a1 - 0xb7fe 0xb8a1 - 0xb8fe 212IDEOGRAM 0xb9a1 - 0xb9fe 0xbaa1 - 0xbafe 0xbba1 - 0xbbfe 213IDEOGRAM 0xbca1 - 0xbcfe 0xbda1 - 0xbdfe 0xbea1 - 0xbefe 214IDEOGRAM 0xbfa1 - 0xbffe 0xc0a1 - 0xc0fe 0xc1a1 - 0xc1fe 215IDEOGRAM 0xc2a1 - 0xc2fe 0xc3a1 - 0xc3fe 0xc4a1 - 0xc4fe 216IDEOGRAM 0xc5a1 - 0xc5fe 0xc6a1 - 0xc6fe 0xc7a1 - 0xc7fe 217IDEOGRAM 0xc8a1 - 0xc8fe 0xc9a1 - 0xc9fe 0xcaa1 - 0xcafe 218IDEOGRAM 0xcba1 - 0xcbfe 0xcca1 - 0xccfe 0xcda1 - 0xcdfe 219IDEOGRAM 0xcea1 - 0xcefe 0xcfa1 - 0xcfd3 0xd0a1 - 0xd0fe 220IDEOGRAM 0xd1a1 - 0xd1fe 0xd2a1 - 0xd2fe 0xd3a1 - 0xd3fe 221IDEOGRAM 0xd4a1 - 0xd4fe 0xd5a1 - 0xd5fe 0xd6a1 - 0xd6fe 222IDEOGRAM 0xd7a1 - 0xd7fe 0xd8a1 - 0xd8fe 0xd9a1 - 0xd9fe 223IDEOGRAM 0xdaa1 - 0xdafe 0xdba1 - 0xdbfe 0xdca1 - 0xdcfe 224IDEOGRAM 0xdda1 - 0xddfe 0xdea1 - 0xdefe 0xdfa1 - 0xdffe 225IDEOGRAM 0xe0a1 - 0xe0fe 0xe1a1 - 0xe1fe 0xe2a1 - 0xe2fe 226IDEOGRAM 0xe3a1 - 0xe3fe 0xe4a1 - 0xe4fe 0xe5a1 - 0xe5fe 227IDEOGRAM 0xe6a1 - 0xe6fe 0xe7a1 - 0xe7fe 0xe8a1 - 0xe8fe 228IDEOGRAM 0xe9a1 - 0xe9fe 0xeaa1 - 0xeafe 0xeba1 - 0xebfe 229IDEOGRAM 0xeca1 - 0xecfe 0xeda1 - 0xedfe 0xeea1 - 0xeefe 230IDEOGRAM 0xefa1 - 0xeffe 0xf0a1 - 0xf0fe 0xf1a1 - 0xf1fe 231IDEOGRAM 0xf2a1 - 0xf2fe 0xf3a1 - 0xf3fe 0xf4a1 - 0xf4a4 232/* 233 * This is for Code Set 3, half-width kana 234 */ 235SPECIAL 0xa1 - 0xdf 236PHONOGRAM 0xa1 - 0xdf 237CONTROL 0x84 - 0x97 0x9b - 0x9f 0xe0 - 0xfe 238.Ed 239.Sh "SEE ALSO" 240.Xr mklocale 1 , 241.Xr setlocale 3 242