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\fBENCODING "EUC"\fP 45.br 46\fBVARIABLE \fP\fIlen1 mask1 len2 mask2 len3 mask3 len4 mask4 mask\fP 47.Sh DESCRIPTION 48The 49.Nm EUC 50encoding is provided for compatibility with 51.Ux 52based systems. 53See 54.Xr mklocale 1 55for a complete description of the 56.Ev LC_CTYPE 57source file format. 58.Pp 59.Nm EUC 60implements a system of 4 multibyte codesets. 61A multibyte character in the first codeset consists of 62.Ar len1 63bytes starting with a byte in the range of 0x00 to 0x7f. 64To allow use of ASCII, 65.Ar len1 66is always 1. 67A multibyte character in the second codeset consists of 68.Ar len2 69bytes starting with a byte in the range of 0x80-0xff excluding 0x8e and 0x8f. 70A multibyte character in the third codeset consists of 71.Ar len3 72bytes starting with the byte 0x8e. 73A multibyte character in the fourth codeset consists of 74.Ar len4 75bytes starting with the byte 0x8f. 76.Pp 77The 78.Ev rune_t 79encoding of 80.Nm EUC 81multibyte characters is dependent on the 82.Ar len 83and 84.Ar mask 85arguments. 86First, the bytes are moved into a 87.Ev rune_t 88as follows: 89.Bd -literal 90byte0 << ((\fIlen\fPN-1) * 8) | byte1 << ((\fIlen\fPN-2) * 8) | ... | byte\fIlen\fPN-1 91.Ed 92.sp 93The result is then ANDed with 94.Ar ~mask 95and ORed with 96.Ar mask\fPN. 97Codesets 2 and 3 are special in that the leading byte (0x8e or 0x8f) is 98first removed and the 99.Ar len\fPN 100argument is reduced by 1. 101.sp 102For example, the Japanese locale has the following 103.Ev VARIABLE 104line: 105.Bd -literal 106VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080 107.Ed 108.sp 109Codeset 1 consists of the values 0x0000 - 0x007f. 110.sp 111Codeset 2 consists of the values who have the bits 0x8080 set. 112.sp 113Codeset 3 consists of the values 0x0080 - 0x00ff. 114.sp 115Codeset 4 consists of the values 0x8000 - 0xff7f excluding the values 116which have the 0x0080 bit set. 117.sp 118Notice that the global 119.Ar mask 120is set to 0x8080, this implies that from those 2 bits the codeset can 121be determined. 122.Sh "EXAMPLE - Japanese Locale" 123This is a complete example of an 124.Ev LC_CTYPE 125source file for the Japanese locale 126.Bd -literal 127/* 128 * Japanese LOCALE_CTYPE definitions using EUC of JIS character sets 129 */ 130 131ENCODING "EUC" 132 133/* JIS JIS JIS */ 134/* X201 X208 X201 */ 135/* 00-7f 84-fe */ 136 137VARIABLE 1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080 138 139/* 140 * Code Set 1 141 */ 142ALPHA 'A' - 'Z' 'a' - 'z' 143CONTROL 0x00 - 0x1f 0x7f 144DIGIT '0' - '9' 145GRAPH 0x21 - 0x7e 146LOWER 'a' - 'z' 147PUNCT 0x21 - 0x2f 0x3a - 0x40 0x5b - 0x60 0x7b - 0x7e 148SPACE 0x09 - 0x0d 0x20 149UPPER 'A' - 'Z' 150XDIGIT 'a' - 'f' 'A' - 'F' 151BLANK ' ' '\t' 152PRINT 0x20 - 0x7e 153 154MAPLOWER < 'A' - 'Z' : 'a' > < 'a' - 'z' : 'a' > 155MAPUPPER < 'A' - 'Z' : 'A' > < 'a' - 'z' : 'A' > 156TODIGIT < '0' - '9' : 0 > 157TODIGIT < 'A' - 'F' : 10 > < 'a' - 'f' : 10 > 158 159/* 160 * Code Set 2 161 */ 162 163SPACE 0xa1a1 164PHONOGRAM 0xa1bc 165SPECIAL 0xa1a2 - 0xa1fe 166PUNCT 0xa1a2 - 0xa1f8 /* A few too many in here... */ 167 168SPECIAL 0xa2a1 - 0xa2ae 0xa2ba - 0xa2c1 0xa2ca - 0xa2d0 0xa2dc - 0xa2ea 169SPECIAL 0xa2f2 - 0xa2f9 0xa2fe 170 171DIGIT 0xa3b0 - 0xa3b9 172UPPER 0xa3c1 - 0xa3da /* Romaji */ 173LOWER 0xa3e1 - 0xa3fa /* Romaji */ 174MAPLOWER < 0xa3c1 - 0xa3da : 0xa3e1 > /* English */ 175MAPLOWER < 0xa3e1 - 0xa3fa : 0xa3e1 > /* English */ 176MAPUPPER < 0xa3c1 - 0xa3da : 0xa3c1 > 177MAPUPPER < 0xa3e1 - 0xa3fa : 0xa3c1 > 178 179XDIGIT 0xa3c1 - 0xa3c6 0xa3e1 - 0xa3e6 180 181TODIGIT < 0xa3b0 - 0xa3b9 : 0 > 182TODIGIT < 0xa3c1 - 0xa3c6 : 10 > < 0xa3e1 - 0xa3e6 : 10 > 183 184PHONOGRAM 0xa4a1 - 0xa4f3 185PHONOGRAM 0xa5a1 - 0xa5f6 186 187UPPER 0xa6a1 - 0xa6b8 /* Greek */ 188LOWER 0xa6c1 - 0xa6d8 /* Greek */ 189MAPLOWER < 0xa6a1 - 0xa6b8 : 0xa6c1 > < 0xa6c1 - 0xa6d8 : 0xa6c1 > 190MAPUPPER < 0xa6a1 - 0xa6b8 : 0xa6a1 > < 0xa6c1 - 0xa6d8 : 0xa6a1 > 191 192UPPER 0xa7a1 - 0xa7c1 /* Cyrillic */ 193LOWER 0xa7d1 - 0xa7f1 /* Cyrillic */ 194MAPLOWER < 0xa7a1 - 0xa7c1 : 0xa7d1 > < 0xa7d1 - 0xa7f1 : 0xa7d1 > 195MAPUPPER < 0xa7a1 - 0xa7c1 : 0xa7a1 > < 0xa7d1 - 0xa7f1 : 0xa7a1 > 196 197SPECIAL 0xa8a1 - 0xa8c0 198 199IDEOGRAM 0xb0a1 - 0xb0fe 0xb1a1 - 0xb1fe 0xb2a1 - 0xb2fe 200IDEOGRAM 0xb3a1 - 0xb3fe 0xb4a1 - 0xb4fe 0xb5a1 - 0xb5fe 201IDEOGRAM 0xb6a1 - 0xb6fe 0xb7a1 - 0xb7fe 0xb8a1 - 0xb8fe 202IDEOGRAM 0xb9a1 - 0xb9fe 0xbaa1 - 0xbafe 0xbba1 - 0xbbfe 203IDEOGRAM 0xbca1 - 0xbcfe 0xbda1 - 0xbdfe 0xbea1 - 0xbefe 204IDEOGRAM 0xbfa1 - 0xbffe 0xc0a1 - 0xc0fe 0xc1a1 - 0xc1fe 205IDEOGRAM 0xc2a1 - 0xc2fe 0xc3a1 - 0xc3fe 0xc4a1 - 0xc4fe 206IDEOGRAM 0xc5a1 - 0xc5fe 0xc6a1 - 0xc6fe 0xc7a1 - 0xc7fe 207IDEOGRAM 0xc8a1 - 0xc8fe 0xc9a1 - 0xc9fe 0xcaa1 - 0xcafe 208IDEOGRAM 0xcba1 - 0xcbfe 0xcca1 - 0xccfe 0xcda1 - 0xcdfe 209IDEOGRAM 0xcea1 - 0xcefe 0xcfa1 - 0xcfd3 0xd0a1 - 0xd0fe 210IDEOGRAM 0xd1a1 - 0xd1fe 0xd2a1 - 0xd2fe 0xd3a1 - 0xd3fe 211IDEOGRAM 0xd4a1 - 0xd4fe 0xd5a1 - 0xd5fe 0xd6a1 - 0xd6fe 212IDEOGRAM 0xd7a1 - 0xd7fe 0xd8a1 - 0xd8fe 0xd9a1 - 0xd9fe 213IDEOGRAM 0xdaa1 - 0xdafe 0xdba1 - 0xdbfe 0xdca1 - 0xdcfe 214IDEOGRAM 0xdda1 - 0xddfe 0xdea1 - 0xdefe 0xdfa1 - 0xdffe 215IDEOGRAM 0xe0a1 - 0xe0fe 0xe1a1 - 0xe1fe 0xe2a1 - 0xe2fe 216IDEOGRAM 0xe3a1 - 0xe3fe 0xe4a1 - 0xe4fe 0xe5a1 - 0xe5fe 217IDEOGRAM 0xe6a1 - 0xe6fe 0xe7a1 - 0xe7fe 0xe8a1 - 0xe8fe 218IDEOGRAM 0xe9a1 - 0xe9fe 0xeaa1 - 0xeafe 0xeba1 - 0xebfe 219IDEOGRAM 0xeca1 - 0xecfe 0xeda1 - 0xedfe 0xeea1 - 0xeefe 220IDEOGRAM 0xefa1 - 0xeffe 0xf0a1 - 0xf0fe 0xf1a1 - 0xf1fe 221IDEOGRAM 0xf2a1 - 0xf2fe 0xf3a1 - 0xf3fe 0xf4a1 - 0xf4a4 222/* 223 * This is for Code Set 3, half-width kana 224 */ 225SPECIAL 0xa1 - 0xdf 226PHONOGRAM 0xa1 - 0xdf 227CONTROL 0x84 - 0x97 0x9b - 0x9f 0xe0 - 0xfe 228.Ed 229.Sh "SEE ALSO" 230.Xr mklocale 1 , 231.Xr setlocale 3 232