xref: /original-bsd/lib/libc/locale/euc.4 (revision a626204d)

.\" Copyright (c) 1993
.\"	The Regents of the University of California.  All rights reserved.
.\"
.\" This code is derived from software contributed to Berkeley by
.\" Paul Borman at Krystal Technologies.
.\"
.\" %sccs.include.redist.roff%
.\"
.\"	@(#)euc.4	8.1 (Berkeley) 06/04/93
.\"
.Dd ""
.Dt EUC 4
.Os
.Sh NAME
.Nm EUC
.Nd EUC encoding of runes
.Sh SYNOPSIS
\fBENCODING "EUC"\fP
.br
\fBVARIABLE \fP\fIlen1 mask1 len2 mask2 len3 mask3 len4 mask4 mask\fP
.Sh DESCRIPTION
The
.Nm EUC
encoding is provided for compatibility with
.Ux
based systems.
See
.Xr mklocale 1
for a complete description of the
.Ev LC_CTYPE
source file format.
.Pp
.Nm EUC
implements a system of 4 multibyte codesets.
A multibyte character in the first codeset consists of
.Ar len1
bytes starting with a byte in the range of 0x00 to 0x7f.
To allow use of ASCII,
.Ar len1
is always 1.
A multibyte character in the second codeset consists of
.Ar len2
bytes starting with a byte in the range of 0x80-0xff excluding 0x8e and 0x8f.
A multibyte character in the third codeset consists of
.Ar len3
bytes starting with the byte 0x8e.
A multibyte character in the fourth codeset consists of
.Ar len4
bytes starting with the byte 0x8f.
.Pp
The
.Ev rune_t
encoding of
.Nm EUC
multibyte characters is dependent on the
.Ar len
and
.Ar mask
arguments.
First, the bytes are moved into a
.Ev rune_t
as follows:
.Bd -literal
byte0 << ((\fIlen\fPN-1) * 8) | byte1 << ((\fIlen\fPN-2) * 8) | ... | byte\fIlen\fPN-1
.Ed
.sp
The result is then ANDed with
.Ar ~mask
and ORed with
.Ar mask\fPN.
Codesets 2 and 3 are special in that the leading byte (0x8e or 0x8f) is
first removed and the
.Ar len\fPN
argument is reduced by 1.
.sp
For example, the Japanese locale has the following
.Ev VARIABLE
line:
.Bd -literal
VARIABLE	1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080
.Ed
.sp
Codeset 1 consists of the values 0x0000 - 0x007f.
.sp
Codeset 2 consists of the values who have the bits 0x8080 set.
.sp
Codeset 3 consists of the values 0x0080 - 0x00ff.
.sp
Codeset 4 consists of the values 0x8000 - 0xff7f excluding the values
which have the 0x0080 bit set.
.sp
Notice that the global
.Ar mask
is set to 0x8080, this implies that from those 2 bits the codeset can
be determined.
.Sh "EXAMPLE - Japanese Locale"
This is a complete example of an
.Ev LC_CTYPE
source file for the Japanese locale
.Bd -literal
/*
 * Japanese LOCALE_CTYPE definitions using EUC of JIS character sets
 */

ENCODING	"EUC"

/*		JIS	 JIS	  JIS			*/
/*		X201	 X208	  X201 			*/
/*		00-7f		  84-fe			*/

VARIABLE	1 0x0000 2 0x8080 2 0x0080 3 0x8000 0x8080

/*
 * Code Set 1
 */
ALPHA		'A' - 'Z' 'a' - 'z'
CONTROL		0x00 - 0x1f 0x7f
DIGIT		'0' - '9'
GRAPH		0x21 - 0x7e
LOWER		'a' - 'z'
PUNCT		0x21 - 0x2f 0x3a - 0x40 0x5b - 0x60 0x7b - 0x7e
SPACE		0x09 - 0x0d 0x20
UPPER		'A' - 'Z'
XDIGIT		'a' - 'f' 'A' - 'F'
BLANK		' ' '\t'
PRINT		0x20 - 0x7e

MAPLOWER	< 'A' - 'Z' : 'a' > < 'a' - 'z' : 'a' >
MAPUPPER	< 'A' - 'Z' : 'A' > < 'a' - 'z' : 'A' >
TODIGIT		< '0' - '9' : 0 >
TODIGIT		< 'A' - 'F' : 10 > < 'a' - 'f' : 10 >

/*
 * Code Set 2
 */

SPACE		0xa1a1
PHONOGRAM	0xa1bc
SPECIAL		0xa1a2 - 0xa1fe
PUNCT		0xa1a2 - 0xa1f8		/* A few too many in here... */

SPECIAL		0xa2a1 - 0xa2ae 0xa2ba - 0xa2c1 0xa2ca - 0xa2d0 0xa2dc - 0xa2ea
SPECIAL		0xa2f2 - 0xa2f9 0xa2fe

DIGIT		0xa3b0 - 0xa3b9
UPPER		0xa3c1 - 0xa3da				/* Romaji */
LOWER		0xa3e1 - 0xa3fa				/* Romaji */
MAPLOWER	< 0xa3c1 - 0xa3da : 0xa3e1 >			/* English */
MAPLOWER	< 0xa3e1 - 0xa3fa : 0xa3e1 >			/* English */
MAPUPPER	< 0xa3c1 - 0xa3da : 0xa3c1 >
MAPUPPER	< 0xa3e1 - 0xa3fa : 0xa3c1 >

XDIGIT		0xa3c1 - 0xa3c6 0xa3e1 - 0xa3e6

TODIGIT		< 0xa3b0 - 0xa3b9 : 0 >
TODIGIT		< 0xa3c1 - 0xa3c6 : 10 > < 0xa3e1 - 0xa3e6 : 10 >

PHONOGRAM	0xa4a1 - 0xa4f3
PHONOGRAM	0xa5a1 - 0xa5f6

UPPER		0xa6a1 - 0xa6b8				/* Greek */
LOWER		0xa6c1 - 0xa6d8				/* Greek */
MAPLOWER	< 0xa6a1 - 0xa6b8 : 0xa6c1 > < 0xa6c1 - 0xa6d8 : 0xa6c1 >
MAPUPPER	< 0xa6a1 - 0xa6b8 : 0xa6a1 > < 0xa6c1 - 0xa6d8 : 0xa6a1 >

UPPER		0xa7a1 - 0xa7c1				/* Cyrillic */
LOWER		0xa7d1 - 0xa7f1				/* Cyrillic */
MAPLOWER	< 0xa7a1 - 0xa7c1 : 0xa7d1 > < 0xa7d1 - 0xa7f1 : 0xa7d1 >
MAPUPPER	< 0xa7a1 - 0xa7c1 : 0xa7a1 > < 0xa7d1 - 0xa7f1 : 0xa7a1 >

SPECIAL		0xa8a1 - 0xa8c0

IDEOGRAM	0xb0a1 - 0xb0fe 0xb1a1 - 0xb1fe 0xb2a1 - 0xb2fe
IDEOGRAM	0xb3a1 - 0xb3fe 0xb4a1 - 0xb4fe 0xb5a1 - 0xb5fe
IDEOGRAM	0xb6a1 - 0xb6fe 0xb7a1 - 0xb7fe 0xb8a1 - 0xb8fe
IDEOGRAM	0xb9a1 - 0xb9fe 0xbaa1 - 0xbafe 0xbba1 - 0xbbfe
IDEOGRAM	0xbca1 - 0xbcfe 0xbda1 - 0xbdfe 0xbea1 - 0xbefe
IDEOGRAM	0xbfa1 - 0xbffe 0xc0a1 - 0xc0fe 0xc1a1 - 0xc1fe
IDEOGRAM	0xc2a1 - 0xc2fe 0xc3a1 - 0xc3fe 0xc4a1 - 0xc4fe
IDEOGRAM	0xc5a1 - 0xc5fe 0xc6a1 - 0xc6fe 0xc7a1 - 0xc7fe
IDEOGRAM	0xc8a1 - 0xc8fe 0xc9a1 - 0xc9fe 0xcaa1 - 0xcafe
IDEOGRAM	0xcba1 - 0xcbfe 0xcca1 - 0xccfe 0xcda1 - 0xcdfe
IDEOGRAM	0xcea1 - 0xcefe 0xcfa1 - 0xcfd3 0xd0a1 - 0xd0fe
IDEOGRAM	0xd1a1 - 0xd1fe 0xd2a1 - 0xd2fe 0xd3a1 - 0xd3fe
IDEOGRAM	0xd4a1 - 0xd4fe 0xd5a1 - 0xd5fe 0xd6a1 - 0xd6fe
IDEOGRAM	0xd7a1 - 0xd7fe 0xd8a1 - 0xd8fe 0xd9a1 - 0xd9fe
IDEOGRAM	0xdaa1 - 0xdafe 0xdba1 - 0xdbfe 0xdca1 - 0xdcfe
IDEOGRAM	0xdda1 - 0xddfe 0xdea1 - 0xdefe 0xdfa1 - 0xdffe
IDEOGRAM	0xe0a1 - 0xe0fe 0xe1a1 - 0xe1fe 0xe2a1 - 0xe2fe
IDEOGRAM	0xe3a1 - 0xe3fe 0xe4a1 - 0xe4fe 0xe5a1 - 0xe5fe
IDEOGRAM	0xe6a1 - 0xe6fe 0xe7a1 - 0xe7fe 0xe8a1 - 0xe8fe
IDEOGRAM	0xe9a1 - 0xe9fe 0xeaa1 - 0xeafe 0xeba1 - 0xebfe
IDEOGRAM	0xeca1 - 0xecfe 0xeda1 - 0xedfe 0xeea1 - 0xeefe
IDEOGRAM	0xefa1 - 0xeffe 0xf0a1 - 0xf0fe 0xf1a1 - 0xf1fe
IDEOGRAM	0xf2a1 - 0xf2fe 0xf3a1 - 0xf3fe 0xf4a1 - 0xf4a4
/*
 * This is for Code Set 3, half-width kana
 */
SPECIAL		0xa1 - 0xdf
PHONOGRAM	0xa1 - 0xdf
CONTROL		0x84 - 0x97 0x9b - 0x9f 0xe0 - 0xfe
.Ed
.Sh "SEE ALSO"
.Xr mklocale 1 ,
.Xr setlocale 3