| 1 | package Encode::KR;
|
|---|
| 2 | BEGIN {
|
|---|
| 3 | if (ord("A") == 193) {
|
|---|
| 4 | die "Encode::KR not supported on EBCDIC\n";
|
|---|
| 5 | }
|
|---|
| 6 | }
|
|---|
| 7 | our $VERSION = do { my @r = (q$Revision: 2.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
|
|---|
| 8 |
|
|---|
| 9 | use Encode;
|
|---|
| 10 | use XSLoader;
|
|---|
| 11 | XSLoader::load(__PACKAGE__,$VERSION);
|
|---|
| 12 |
|
|---|
| 13 | use Encode::KR::2022_KR;
|
|---|
| 14 |
|
|---|
| 15 | 1;
|
|---|
| 16 | __END__
|
|---|
| 17 |
|
|---|
| 18 | =head1 NAME
|
|---|
| 19 |
|
|---|
| 20 | Encode::KR - Korean Encodings
|
|---|
| 21 |
|
|---|
| 22 | =head1 SYNOPSIS
|
|---|
| 23 |
|
|---|
| 24 | use Encode qw/encode decode/;
|
|---|
| 25 | $euc_kr = encode("euc-kr", $utf8); # loads Encode::KR implicitly
|
|---|
| 26 | $utf8 = decode("euc-kr", $euc_kr); # ditto
|
|---|
| 27 |
|
|---|
| 28 | =head1 DESCRIPTION
|
|---|
| 29 |
|
|---|
| 30 | This module implements Korean charset encodings. Encodings supported
|
|---|
| 31 | are as follows.
|
|---|
| 32 |
|
|---|
| 33 |
|
|---|
| 34 | Canonical Alias Description
|
|---|
| 35 | --------------------------------------------------------------------
|
|---|
| 36 | euc-kr /\beuc.*kr$/i EUC (Extended Unix Character)
|
|---|
| 37 | /\bkr.*euc$/i
|
|---|
| 38 | ksc5601-raw Korean standard code set (as is)
|
|---|
| 39 | cp949 /(?:x-)?uhc$/i
|
|---|
| 40 | /(?:x-)?windows-949$/i
|
|---|
| 41 | /\bks_c_5601-1987$/i
|
|---|
| 42 | Code Page 949 (EUC-KR + 8,822
|
|---|
| 43 | (additional Hangul syllables)
|
|---|
| 44 | MacKorean EUC-KR + Apple Vendor Mappings
|
|---|
| 45 | johab JOHAB A supplementary encoding defined in
|
|---|
| 46 | Annex 3 of KS X 1001:1998
|
|---|
| 47 | iso-2022-kr iso-2022-kr [RFC1557]
|
|---|
| 48 | --------------------------------------------------------------------
|
|---|
| 49 |
|
|---|
| 50 | To find how to use this module in detail, see L<Encode>.
|
|---|
| 51 |
|
|---|
| 52 | =head1 BUGS
|
|---|
| 53 |
|
|---|
| 54 | When you see C<charset=ks_c_5601-1987> on mails and web pages, they really
|
|---|
| 55 | mean "cp949" encodings. To fix that, the following aliases are set;
|
|---|
| 56 |
|
|---|
| 57 | qr/(?:x-)?uhc$/i => '"cp949"'
|
|---|
| 58 | qr/(?:x-)?windows-949$/i => '"cp949"'
|
|---|
| 59 | qr/ks_c_5601-1987$/i => '"cp949"'
|
|---|
| 60 |
|
|---|
| 61 | The ASCII region (0x00-0x7f) is preserved for all encodings, even
|
|---|
| 62 | though this conflicts with mappings by the Unicode Consortium. See
|
|---|
| 63 |
|
|---|
| 64 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
|
|---|
| 65 |
|
|---|
| 66 | to find out why it is implemented that way.
|
|---|
| 67 |
|
|---|
| 68 | =head1 SEE ALSO
|
|---|
| 69 |
|
|---|
| 70 | L<Encode>
|
|---|
| 71 |
|
|---|
| 72 | =cut
|
|---|
