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 | } |
a999c27c |
7 | our $VERSION = do { my @r = (q$Revision: 1.20 $ =~ /\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", $euc_kr); # ditto |
b2729934 |
24 | |
25 | =head1 DESCRIPTION |
26 | |
27 | This module implements Korean charset encodings. Encodings supported |
28 | are as follows. |
29 | |
fab31126 |
30 | |
31 | Canonical Alias Description |
32 | -------------------------------------------------------------------- |
67d7b5ef |
33 | euc-kr /\beuc.*kr$/i EUC (Extended Unix Character) |
34 | /\bkr.*euc$/i |
a999c27c |
35 | ksc5601-raw Korean standard code set (as is) |
36 | cp949 /(?:x-)?uhc$/i |
37 | /(?:x-)?windows-949$/i |
38 | /\bks_c_5601-1987$/i |
39 | Code Page 949 (EUC-KR + 8,822 |
67d7b5ef |
40 | (additional Hangul syllables) |
a999c27c |
41 | MacKorean EUC-KR + Apple Vendor Mappings |
67d7b5ef |
42 | johab JOHAB A supplementary encoding defined in |
a999c27c |
43 | Annex 3 of KS X 1001:1998 |
67d7b5ef |
44 | iso-2022-kr iso-2022-kr [RFC1557] |
5129552c |
45 | -------------------------------------------------------------------- |
b2729934 |
46 | |
47 | To find how to use this module in detail, see L<Encode>. |
48 | |
49 | =head1 BUGS |
50 | |
67d7b5ef |
51 | When you see C<charset=ks_c_5601-1987> on mails and web pages, they really |
52 | mean "cp949" encodings. To fix that, the following aliases are set; |
53 | |
54 | qr/(?:x-)?uhc$/i => '"cp949"' |
55 | qr/(?:x-)?windows-949$/i => '"cp949"' |
56 | qr/ks_c_5601-1987$/i => '"cp949"' |
b2729934 |
57 | |
58 | ASCII part (0x00-0x7f) is preserved for all encodings, even though it |
59 | conflicts with mappings by the Unicode Consortium. See |
60 | |
a63c962f |
61 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en> |
b2729934 |
62 | |
63 | to find why it is implemented that way. |
64 | |
65 | =head1 SEE ALSO |
66 | |
67 | L<Encode> |
68 | |
69 | =cut |