xref: /onnv-gate/usr/src/cmd/perl/5.8.4/distrib/ext/Encode/CN/CN.pm (revision 0:68f95e015346)
1*0Sstevel@tonic-gatepackage Encode::CN;
2*0Sstevel@tonic-gateBEGIN {
3*0Sstevel@tonic-gate    if (ord("A") == 193) {
4*0Sstevel@tonic-gate	die "Encode::CN not supported on EBCDIC\n";
5*0Sstevel@tonic-gate    }
6*0Sstevel@tonic-gate}
7*0Sstevel@tonic-gateour $VERSION = do { my @r = (q$Revision: 1.24 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
8*0Sstevel@tonic-gate
9*0Sstevel@tonic-gateuse Encode;
10*0Sstevel@tonic-gateuse XSLoader;
11*0Sstevel@tonic-gateXSLoader::load(__PACKAGE__,$VERSION);
12*0Sstevel@tonic-gate
13*0Sstevel@tonic-gate# Relocated from Encode.pm
14*0Sstevel@tonic-gate
15*0Sstevel@tonic-gateuse Encode::CN::HZ;
16*0Sstevel@tonic-gate# use Encode::CN::2022_CN;
17*0Sstevel@tonic-gate
18*0Sstevel@tonic-gate1;
19*0Sstevel@tonic-gate__END__
20*0Sstevel@tonic-gate
21*0Sstevel@tonic-gate=head1 NAME
22*0Sstevel@tonic-gate
23*0Sstevel@tonic-gateEncode::CN - China-based Chinese Encodings
24*0Sstevel@tonic-gate
25*0Sstevel@tonic-gate=head1 SYNOPSIS
26*0Sstevel@tonic-gate
27*0Sstevel@tonic-gate    use Encode qw/encode decode/;
28*0Sstevel@tonic-gate    $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
29*0Sstevel@tonic-gate    $utf8   = decode("euc-cn", $euc_cn); # ditto
30*0Sstevel@tonic-gate
31*0Sstevel@tonic-gate=head1 DESCRIPTION
32*0Sstevel@tonic-gate
33*0Sstevel@tonic-gateThis module implements China-based Chinese charset encodings.
34*0Sstevel@tonic-gateEncodings supported are as follows.
35*0Sstevel@tonic-gate
36*0Sstevel@tonic-gate  Canonical   Alias		Description
37*0Sstevel@tonic-gate  --------------------------------------------------------------------
38*0Sstevel@tonic-gate  euc-cn      /\beuc.*cn$/i	EUC (Extended Unix Character)
39*0Sstevel@tonic-gate	      /\bcn.*euc$/i
40*0Sstevel@tonic-gate              /\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
41*0Sstevel@tonic-gate  gb2312-raw			The raw (low-bit) GB2312 character map
42*0Sstevel@tonic-gate  gb12345-raw			Traditional chinese counterpart to
43*0Sstevel@tonic-gate				GB2312 (raw)
44*0Sstevel@tonic-gate  iso-ir-165			GB2312 + GB6345 + GB8565 + additions
45*0Sstevel@tonic-gate  MacChineseSimp                GB2312 + Apple Additions
46*0Sstevel@tonic-gate  cp936				Code Page 936, also known as GBK
47*0Sstevel@tonic-gate				(Extended GuoBiao)
48*0Sstevel@tonic-gate  hz				7-bit escaped GB2312 encoding
49*0Sstevel@tonic-gate  --------------------------------------------------------------------
50*0Sstevel@tonic-gate
51*0Sstevel@tonic-gateTo find how to use this module in detail, see L<Encode>.
52*0Sstevel@tonic-gate
53*0Sstevel@tonic-gate=head1 NOTES
54*0Sstevel@tonic-gate
55*0Sstevel@tonic-gateDue to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
56*0Sstevel@tonic-gateseparately on CPAN, under the name L<Encode::HanExtra>. That module
57*0Sstevel@tonic-gatealso contains extra Taiwan-based encodings.
58*0Sstevel@tonic-gate
59*0Sstevel@tonic-gate=head1 BUGS
60*0Sstevel@tonic-gate
61*0Sstevel@tonic-gateWhen you see C<charset=gb2312> on mails and web pages, they really
62*0Sstevel@tonic-gatemean C<euc-cn> encodings.  To fix that, C<gb2312> is aliased to C<euc-cn>.
63*0Sstevel@tonic-gateUse C<gb2312-raw> when you really mean it.
64*0Sstevel@tonic-gate
65*0Sstevel@tonic-gateThe ASCII region (0x00-0x7f) is preserved for all encodings, even though
66*0Sstevel@tonic-gatethis conflicts with mappings by the Unicode Consortium.  See
67*0Sstevel@tonic-gate
68*0Sstevel@tonic-gateL<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
69*0Sstevel@tonic-gate
70*0Sstevel@tonic-gateto find out why it is implemented that way.
71*0Sstevel@tonic-gate
72*0Sstevel@tonic-gate=head1 SEE ALSO
73*0Sstevel@tonic-gate
74*0Sstevel@tonic-gateL<Encode>
75*0Sstevel@tonic-gate
76*0Sstevel@tonic-gate=cut
77