locale/FreeBSD/euc.4

   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 .\" $FreeBSD: src/lib/libc/locale/euc.4,v 1.9 2001/07/15 07:53:05 dd Exp $
  37 .\"
  38 .Dd June 4, 1993
  39 .Dt EUC 4
  40 .Os
  41 .Sh NAME
  42 .Nm euc
  43 .Nd EUC encoding of runes
  44 .Sh SYNOPSIS
  45 .Nm ENCODING
  46 .Qq EUC
  47 .Pp
  48 .Nm VARIABLE
  49 .Ar len1
  50 .Ar mask1
  51 .Ar len2
  52 .Ar mask2
  53 .Ar len3
  54 .Ar mask3
  55 .Ar len4
  56 .Ar mask4
  57 .Ar mask
  58 .Sh DESCRIPTION
  59 The
  60 .Nm EUC
  61 encoding is provided for compatibility with
  62 .Ux
  63 based systems.
  64 See
  65 .Xr mklocale 1
  66 for a complete description of the
  67 .Ev LC_CTYPE
  68 source file format.
  69 .Pp
  70 .Nm EUC
  71 implements a system of 4 multibyte codesets.
  72 A multibyte character in the first codeset consists of
  73 .Ar len1
  74 bytes starting with a byte in the range of 0x00 to 0x7f.
  75 To allow use of ASCII,
  76 .Ar len1
  77 is always 1.
  78 A multibyte character in the second codeset consists of
  79 .Ar len2
  80 bytes starting with a byte in the range of 0x80-0xff excluding 0x8e and 0x8f.
  81 A multibyte character in the third codeset consists of
  82 .Ar len3
  83 bytes starting with the byte 0x8e.
  84 A multibyte character in the fourth codeset consists of
  85 .Ar len4
  86 bytes starting with the byte 0x8f.
  87 .Pp
  88 The
  89 .Ev rune_t
  90 encoding of
  91 .Nm EUC
  92 multibyte characters is dependent on the
  93 .Ar len
  94 and
  95 .Ar mask
  96 arguments.
  97 First, the bytes are moved into a
  98 .Ev rune_t
  99 as follows:
 100 .Bd -literal
 101 byte0 << ((\fIlen\fPN-1) * 8) | byte1 << ((\fIlen\fPN-2) * 8) | ... | byte\fIlen\fPN-1
 102 .Ed
 103 .Pp
 104 The result is then ANDed with
 105 .Ar ~mask
 106 and ORed with
 107 .Ar maskN .
 108 Codesets 2 and 3 are special in that the leading byte (0x8e or 0x8f) is
 109 first removed and the
 110 .Ar lenN
 111 argument is reduced by 1.
 112 .Pp
 113 For example, the Japanese locale has the following
 114 .Ev VARIABLE
 115 line:
 116 .Bd -literal
 117 VARIABLE        1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080
 118 .Ed
 119 .Pp
 120 Codeset 1 consists of the values 0x0000 - 0x007f.
 121 .Pp
 122 Codeset 2 consists of the values who have the bits 0x8080 set.
 123 .Pp
 124 Codeset 3 consists of the values 0x0080 - 0x00ff.
 125 .Pp
 126 Codeset 4 consists of the values 0x8000 - 0xff7f excluding the values
 127 which have the 0x0080 bit set.
 128 .Pp
 129 Notice that the global
 130 .Ar mask
 131 is set to 0x8080, this implies that from those 2 bits the codeset can
 132 be determined.
 133 .Sh "EXAMPLE - Japanese Locale"
 134 This is a complete example of an
 135 .Ev LC_CTYPE
 136 source file for the Japanese locale
 137 .Bd -literal
 138 /*
 139  * Japanese LOCALE_CTYPE definitions using EUC of JIS character sets
 140  */
 141
 142 ENCODING        "EUC"
 143
 144 /*              JIS      JIS      JIS                   */
 145 /*              X201     X208     X201                  */
 146 /*              00-7f             84-fe                 */
 147
 148 VARIABLE        1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080
 149
 150 /*
 151  * Code Set 1
 152  */
 153 ALPHA           'A' - 'Z' 'a' - 'z'
 154 CONTROL         0x00 - 0x1f 0x7f
 155 DIGIT           '0' - '9'
 156 GRAPH           0x21 - 0x7e
 157 LOWER           'a' - 'z'
 158 PUNCT           0x21 - 0x2f 0x3a - 0x40 0x5b - 0x60 0x7b - 0x7e
 159 SPACE           0x09 - 0x0d 0x20
 160 UPPER           'A' - 'Z'
 161 XDIGIT          'a' - 'f' 'A' - 'F'
 162 BLANK           ' ' '\t'
 163 PRINT           0x20 - 0x7e
 164
 165 MAPLOWER        < 'A' - 'Z' : 'a' > < 'a' - 'z' : 'a' >
 166 MAPUPPER        < 'A' - 'Z' : 'A' > < 'a' - 'z' : 'A' >
 167 TODIGIT         < '0' - '9' : 0 >
 168 TODIGIT         < 'A' - 'F' : 10 > < 'a' - 'f' : 10 >
 169
 170 /*
 171  * Code Set 2
 172  */
 173
 174 SPACE           0xa1a1
 175 PHONOGRAM       0xa1bc
 176 SPECIAL         0xa1a2 - 0xa1fe
 177 PUNCT           0xa1a2 - 0xa1f8         /* A few too many in here... */
 178
 179 SPECIAL         0xa2a1 - 0xa2ae 0xa2ba - 0xa2c1 0xa2ca - 0xa2d0 0xa2dc - 0xa2ea
 180 SPECIAL         0xa2f2 - 0xa2f9 0xa2fe
 181
 182 DIGIT           0xa3b0 - 0xa3b9
 183 UPPER           0xa3c1 - 0xa3da                         /* Romaji */
 184 LOWER           0xa3e1 - 0xa3fa                         /* Romaji */
 185 MAPLOWER        < 0xa3c1 - 0xa3da : 0xa3e1 >                    /* English */
 186 MAPLOWER        < 0xa3e1 - 0xa3fa : 0xa3e1 >                    /* English */
 187 MAPUPPER        < 0xa3c1 - 0xa3da : 0xa3c1 >
 188 MAPUPPER        < 0xa3e1 - 0xa3fa : 0xa3c1 >
 189
 190 XDIGIT          0xa3c1 - 0xa3c6 0xa3e1 - 0xa3e6
 191
 192 TODIGIT         < 0xa3b0 - 0xa3b9 : 0 >
 193 TODIGIT         < 0xa3c1 - 0xa3c6 : 10 > < 0xa3e1 - 0xa3e6 : 10 >
 194
 195 PHONOGRAM       0xa4a1 - 0xa4f3
 196 PHONOGRAM       0xa5a1 - 0xa5f6
 197
 198 UPPER           0xa6a1 - 0xa6b8                         /* Greek */
 199 LOWER           0xa6c1 - 0xa6d8                         /* Greek */
 200 MAPLOWER        < 0xa6a1 - 0xa6b8 : 0xa6c1 > < 0xa6c1 - 0xa6d8 : 0xa6c1 >
 201 MAPUPPER        < 0xa6a1 - 0xa6b8 : 0xa6a1 > < 0xa6c1 - 0xa6d8 : 0xa6a1 >
 202
 203 UPPER           0xa7a1 - 0xa7c1                         /* Cyrillic */
 204 LOWER           0xa7d1 - 0xa7f1                         /* Cyrillic */
 205 MAPLOWER        < 0xa7a1 - 0xa7c1 : 0xa7d1 > < 0xa7d1 - 0xa7f1 : 0xa7d1 >
 206 MAPUPPER        < 0xa7a1 - 0xa7c1 : 0xa7a1 > < 0xa7d1 - 0xa7f1 : 0xa7a1 >
 207
 208 SPECIAL         0xa8a1 - 0xa8c0
 209
 210 IDEOGRAM        0xb0a1 - 0xb0fe 0xb1a1 - 0xb1fe 0xb2a1 - 0xb2fe
 211 IDEOGRAM        0xb3a1 - 0xb3fe 0xb4a1 - 0xb4fe 0xb5a1 - 0xb5fe
 212 IDEOGRAM        0xb6a1 - 0xb6fe 0xb7a1 - 0xb7fe 0xb8a1 - 0xb8fe
 213 IDEOGRAM        0xb9a1 - 0xb9fe 0xbaa1 - 0xbafe 0xbba1 - 0xbbfe
 214 IDEOGRAM        0xbca1 - 0xbcfe 0xbda1 - 0xbdfe 0xbea1 - 0xbefe
 215 IDEOGRAM        0xbfa1 - 0xbffe 0xc0a1 - 0xc0fe 0xc1a1 - 0xc1fe
 216 IDEOGRAM        0xc2a1 - 0xc2fe 0xc3a1 - 0xc3fe 0xc4a1 - 0xc4fe
 217 IDEOGRAM        0xc5a1 - 0xc5fe 0xc6a1 - 0xc6fe 0xc7a1 - 0xc7fe
 218 IDEOGRAM        0xc8a1 - 0xc8fe 0xc9a1 - 0xc9fe 0xcaa1 - 0xcafe
 219 IDEOGRAM        0xcba1 - 0xcbfe 0xcca1 - 0xccfe 0xcda1 - 0xcdfe
 220 IDEOGRAM        0xcea1 - 0xcefe 0xcfa1 - 0xcfd3 0xd0a1 - 0xd0fe
 221 IDEOGRAM        0xd1a1 - 0xd1fe 0xd2a1 - 0xd2fe 0xd3a1 - 0xd3fe
 222 IDEOGRAM        0xd4a1 - 0xd4fe 0xd5a1 - 0xd5fe 0xd6a1 - 0xd6fe
 223 IDEOGRAM        0xd7a1 - 0xd7fe 0xd8a1 - 0xd8fe 0xd9a1 - 0xd9fe
 224 IDEOGRAM        0xdaa1 - 0xdafe 0xdba1 - 0xdbfe 0xdca1 - 0xdcfe
 225 IDEOGRAM        0xdda1 - 0xddfe 0xdea1 - 0xdefe 0xdfa1 - 0xdffe
 226 IDEOGRAM        0xe0a1 - 0xe0fe 0xe1a1 - 0xe1fe 0xe2a1 - 0xe2fe
 227 IDEOGRAM        0xe3a1 - 0xe3fe 0xe4a1 - 0xe4fe 0xe5a1 - 0xe5fe
 228 IDEOGRAM        0xe6a1 - 0xe6fe 0xe7a1 - 0xe7fe 0xe8a1 - 0xe8fe
 229 IDEOGRAM        0xe9a1 - 0xe9fe 0xeaa1 - 0xeafe 0xeba1 - 0xebfe
 230 IDEOGRAM        0xeca1 - 0xecfe 0xeda1 - 0xedfe 0xeea1 - 0xeefe
 231 IDEOGRAM        0xefa1 - 0xeffe 0xf0a1 - 0xf0fe 0xf1a1 - 0xf1fe
 232 IDEOGRAM        0xf2a1 - 0xf2fe 0xf3a1 - 0xf3fe 0xf4a1 - 0xf4a4
 233 /*
 234  * This is for Code Set 3, half-width kana
 235  */
 236 SPECIAL         0xa1 - 0xdf
 237 PHONOGRAM       0xa1 - 0xdf
 238 CONTROL         0x84 - 0x97 0x9b - 0x9f 0xe0 - 0xfe
 239 .Ed
 240 .Sh "SEE ALSO"
 241 .Xr mklocale 1 ,
 242 .Xr setlocale 3