| Commit | Line | Data |
|---|
| 0e567a6c |
1 | package Encode::KR; |
| 071db25d |
2 | BEGIN { |
| 3 | if (ord("A") == 193) { |
| 4 | die "Encode::KR not supported on EBCDIC\n"; |
| 5 | } |
| 6 | } |
| 48e3bbdd |
7 | our $VERSION = do { my @r = (q$Revision: 1.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; |
| c0d88b76 |
8 | |
| 9 | use Encode; |
| 0e567a6c |
10 | use XSLoader; |
| 11 | XSLoader::load('Encode::KR',$VERSION); |
| 12 | |
| 13 | 1; |
| 14 | __END__ |
| b2729934 |
15 | =head1 NAME |
| 0e567a6c |
16 | |
| b2729934 |
17 | Encode::KR - Korean Encodings |
| 0e567a6c |
18 | |
| b2729934 |
19 | =head1 SYNOPSIS |
| 20 | |
| 1b2c56c8 |
21 | use Encode qw/encode decode/; |
| 2b217bf7 |
22 | $euc_kr = encode("euc-kr", $utf8); # loads Encode::KR implicitly |
| ee981de6 |
23 | $utf8 = decode("euc-kr", $euc_kr); # ditto |
| b2729934 |
24 | |
| 25 | =head1 DESCRIPTION |
| 26 | |
| 27 | This module implements Korean charset encodings. Encodings supported |
| 28 | are as follows. |
| 29 | |
| fab31126 |
30 | |
| 31 | Canonical Alias Description |
| 32 | -------------------------------------------------------------------- |
| 48e3bbdd |
33 | euc-kr /\beuc.*kr$/i EUC (Extended Unix Character) |
| 34 | /\bkr.*euc$/i |
| fab31126 |
35 | ksc5601 Korean standard code set |
| 48e3bbdd |
36 | cp949 Code Page 949 (EUC-KR + 8,822 |
| 37 | (additional Hangul syllables) |
| 38 | johab JOHAB A supplementary encoding defined in |
| 39 | Annex 3 of KS X 1001:1998 |
| 40 | iso-2022-kr iso-2022-kr [RFC1557] |
| 5129552c |
41 | -------------------------------------------------------------------- |
| b2729934 |
42 | |
| 43 | To find how to use this module in detail, see L<Encode>. |
| 44 | |
| 45 | =head1 BUGS |
| 46 | |
| 48e3bbdd |
47 | When you see C<charset=ks_c_5601-1987> on mails and web pages, they really |
| 48 | mean "cp949" encodings. To fix that, the following aliases are set; |
| 49 | |
| 50 | qr/(?:x-)?uhc$/i => '"cp949"' |
| 51 | qr/(?:x-)?windows-949$/i => '"cp949"' |
| 52 | qr/ks_c_5601-1987$/i => '"cp949"' |
| b2729934 |
53 | |
| 54 | ASCII part (0x00-0x7f) is preserved for all encodings, even though it |
| 55 | conflicts with mappings by the Unicode Consortium. See |
| 56 | |
| a63c962f |
57 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en> |
| b2729934 |
58 | |
| 59 | to find why it is implemented that way. |
| 60 | |
| 61 | =head1 SEE ALSO |
| 62 | |
| 63 | L<Encode> |
| 64 | |
| 65 | =cut |
projects / p5sagit/p5-mst-13.2.git / blame