| 1 |
root |
1.1 |
package Encode::Byte; |
| 2 |
|
|
use Encode; |
| 3 |
|
|
our $VERSION = do { my @r = (q$Revision: 2.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; |
| 4 |
|
|
|
| 5 |
|
|
use XSLoader; |
| 6 |
|
|
XSLoader::load(__PACKAGE__,$VERSION); |
| 7 |
|
|
|
| 8 |
|
|
1; |
| 9 |
|
|
__END__ |
| 10 |
|
|
|
| 11 |
|
|
=head1 NAME |
| 12 |
|
|
|
| 13 |
|
|
Encode::Byte - Single Byte Encodings |
| 14 |
|
|
|
| 15 |
|
|
=head1 SYNOPSIS |
| 16 |
|
|
|
| 17 |
|
|
use Encode qw/encode decode/; |
| 18 |
|
|
$greek = encode("iso-8859-7", $utf8); # loads Encode::Byte implicitly |
| 19 |
|
|
$utf8 = decode("iso-8859-7", $greek); # ditto |
| 20 |
|
|
|
| 21 |
|
|
=head1 ABSTRACT |
| 22 |
|
|
|
| 23 |
|
|
This module implements various single byte encodings. For most cases it uses |
| 24 |
|
|
\x80-\xff (upper half) to map non-ASCII characters. Encodings |
| 25 |
|
|
supported are as follows. |
| 26 |
|
|
|
| 27 |
|
|
Canonical Alias Description |
| 28 |
|
|
-------------------------------------------------------------------- |
| 29 |
|
|
# ISO 8859 series |
| 30 |
|
|
(iso-8859-1 is in built-in) |
| 31 |
|
|
iso-8859-2 latin2 [ISO] |
| 32 |
|
|
iso-8859-3 latin3 [ISO] |
| 33 |
|
|
iso-8859-4 latin4 [ISO] |
| 34 |
|
|
iso-8859-5 [ISO] |
| 35 |
|
|
iso-8859-6 [ISO] |
| 36 |
|
|
iso-8859-7 [ISO] |
| 37 |
|
|
iso-8859-8 [ISO] |
| 38 |
|
|
iso-8859-9 latin5 [ISO] |
| 39 |
|
|
iso-8859-10 latin6 [ISO] |
| 40 |
|
|
iso-8859-11 |
| 41 |
|
|
(iso-8859-12 is nonexistent) |
| 42 |
|
|
iso-8859-13 latin7 [ISO] |
| 43 |
|
|
iso-8859-14 latin8 [ISO] |
| 44 |
|
|
iso-8859-15 latin9 [ISO] |
| 45 |
|
|
iso-8859-16 latin10 [ISO] |
| 46 |
|
|
|
| 47 |
|
|
# Cyrillic |
| 48 |
|
|
koi8-f |
| 49 |
|
|
koi8-r cp878 [RFC1489] |
| 50 |
|
|
koi8-u [RFC2319] |
| 51 |
|
|
|
| 52 |
|
|
# Vietnamese |
| 53 |
|
|
viscii |
| 54 |
|
|
|
| 55 |
|
|
# all cp* are also available as ibm-*, ms-*, and windows-* |
| 56 |
|
|
# also see L<http://msdn.microsoft.com/workshop/author/dhtml/reference/charsets/charset4.asp> |
| 57 |
|
|
|
| 58 |
|
|
cp424 |
| 59 |
|
|
cp437 |
| 60 |
|
|
cp737 |
| 61 |
|
|
cp775 |
| 62 |
|
|
cp850 |
| 63 |
|
|
cp852 |
| 64 |
|
|
cp855 |
| 65 |
|
|
cp856 |
| 66 |
|
|
cp857 |
| 67 |
|
|
cp860 |
| 68 |
|
|
cp861 |
| 69 |
|
|
cp862 |
| 70 |
|
|
cp863 |
| 71 |
|
|
cp864 |
| 72 |
|
|
cp865 |
| 73 |
|
|
cp866 |
| 74 |
|
|
cp869 |
| 75 |
|
|
cp874 |
| 76 |
|
|
cp1006 |
| 77 |
|
|
cp1250 WinLatin2 |
| 78 |
|
|
cp1251 WinCyrillic |
| 79 |
|
|
cp1252 WinLatin1 |
| 80 |
|
|
cp1253 WinGreek |
| 81 |
|
|
cp1254 WinTurkish |
| 82 |
|
|
cp1255 WinHebrew |
| 83 |
|
|
cp1256 WinArabic |
| 84 |
|
|
cp1257 WinBaltic |
| 85 |
|
|
cp1258 WinVietnamese |
| 86 |
|
|
|
| 87 |
|
|
# Macintosh |
| 88 |
|
|
# Also see L<http://developer.apple.com/technotes/tn/tn1150.html> |
| 89 |
|
|
MacArabic |
| 90 |
|
|
MacCentralEurRoman |
| 91 |
|
|
MacCroatian |
| 92 |
|
|
MacCyrillic |
| 93 |
|
|
MacFarsi |
| 94 |
|
|
MacGreek |
| 95 |
|
|
MacHebrew |
| 96 |
|
|
MacIcelandic |
| 97 |
|
|
MacRoman |
| 98 |
|
|
MacRomanian |
| 99 |
|
|
MacRumanian |
| 100 |
|
|
MacSami |
| 101 |
|
|
MacThai |
| 102 |
|
|
MacTurkish |
| 103 |
|
|
MacUkrainian |
| 104 |
|
|
|
| 105 |
|
|
# More vendor encodings |
| 106 |
|
|
AdobeStandardEncoding |
| 107 |
|
|
nextstep |
| 108 |
|
|
gsm0338 # used in GSM handsets |
| 109 |
|
|
hp-roman8 |
| 110 |
|
|
|
| 111 |
|
|
=head1 DESCRIPTION |
| 112 |
|
|
|
| 113 |
|
|
To find how to use this module in detail, see L<Encode>. |
| 114 |
|
|
|
| 115 |
|
|
=head1 SEE ALSO |
| 116 |
|
|
|
| 117 |
|
|
L<Encode> |
| 118 |
|
|
|
| 119 |
|
|
=cut |
