summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/Encode/KR.pm
diff options
context:
space:
mode:
authorReinhard Kotucha <reinhard.kotucha@web.de>2008-01-05 21:23:03 +0000
committerReinhard Kotucha <reinhard.kotucha@web.de>2008-01-05 21:23:03 +0000
commit61700e8be90ff6f495c0b1a9835fe07e9848de8d (patch)
treeba85dbc1413d5f834a501a8828e3b67678ba8524 /Master/tlpkg/tlperl/lib/Encode/KR.pm
parent270728c6f3efcac6728d2c335c79824c356f428d (diff)
tlperl: Perl for scripts provided by TeX Live.
git-svn-id: svn://tug.org/texlive/trunk@6046 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Master/tlpkg/tlperl/lib/Encode/KR.pm')
-rw-r--r--Master/tlpkg/tlperl/lib/Encode/KR.pm72
1 files changed, 72 insertions, 0 deletions
diff --git a/Master/tlpkg/tlperl/lib/Encode/KR.pm b/Master/tlpkg/tlperl/lib/Encode/KR.pm
new file mode 100644
index 00000000000..e9d4073b7b4
--- /dev/null
+++ b/Master/tlpkg/tlperl/lib/Encode/KR.pm
@@ -0,0 +1,72 @@
+package Encode::KR;
+BEGIN {
+ if (ord("A") == 193) {
+ die "Encode::KR not supported on EBCDIC\n";
+ }
+}
+our $VERSION = do { my @r = (q$Revision: 2.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+
+use Encode;
+use XSLoader;
+XSLoader::load(__PACKAGE__,$VERSION);
+
+use Encode::KR::2022_KR;
+
+1;
+__END__
+
+=head1 NAME
+
+Encode::KR - Korean Encodings
+
+=head1 SYNOPSIS
+
+ use Encode qw/encode decode/;
+ $euc_kr = encode("euc-kr", $utf8); # loads Encode::KR implicitly
+ $utf8 = decode("euc-kr", $euc_kr); # ditto
+
+=head1 DESCRIPTION
+
+This module implements Korean charset encodings. Encodings supported
+are as follows.
+
+
+ Canonical Alias Description
+ --------------------------------------------------------------------
+ euc-kr /\beuc.*kr$/i EUC (Extended Unix Character)
+ /\bkr.*euc$/i
+ ksc5601-raw Korean standard code set (as is)
+ cp949 /(?:x-)?uhc$/i
+ /(?:x-)?windows-949$/i
+ /\bks_c_5601-1987$/i
+ Code Page 949 (EUC-KR + 8,822
+ (additional Hangul syllables)
+ MacKorean EUC-KR + Apple Vendor Mappings
+ johab JOHAB A supplementary encoding defined in
+ Annex 3 of KS X 1001:1998
+ iso-2022-kr iso-2022-kr [RFC1557]
+ --------------------------------------------------------------------
+
+To find how to use this module in detail, see L<Encode>.
+
+=head1 BUGS
+
+When you see C<charset=ks_c_5601-1987> on mails and web pages, they really
+mean "cp949" encodings. To fix that, the following aliases are set;
+
+ qr/(?:x-)?uhc$/i => '"cp949"'
+ qr/(?:x-)?windows-949$/i => '"cp949"'
+ qr/ks_c_5601-1987$/i => '"cp949"'
+
+The ASCII region (0x00-0x7f) is preserved for all encodings, even
+though this conflicts with mappings by the Unicode Consortium. See
+
+L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
+
+to find out why it is implemented that way.
+
+=head1 SEE ALSO
+
+L<Encode>
+
+=cut