xref: /onnv-gate/usr/src/cmd/perl/5.8.4/distrib/ext/Encode/TW/TW.pm (revision 0:68f95e015346)
1package Encode::TW;
2BEGIN {
3    if (ord("A") == 193) {
4	die "Encode::TW not supported on EBCDIC\n";
5    }
6}
7our $VERSION = do { my @r = (q$Revision: 1.26 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
8
9use Encode;
10use XSLoader;
11XSLoader::load(__PACKAGE__,$VERSION);
12
131;
14__END__
15
16=head1 NAME
17
18Encode::TW - Taiwan-based Chinese Encodings
19
20=head1 SYNOPSIS
21
22    use Encode qw/encode decode/;
23    $big5 = encode("big5", $utf8); # loads Encode::TW implicitly
24    $utf8 = decode("big5", $big5); # ditto
25
26=head1 DESCRIPTION
27
28This module implements tradition Chinese charset encodings as used
29in Taiwan and Hong Kong.
30Encodings supported are as follows.
31
32  Canonical   Alias		Description
33  --------------------------------------------------------------------
34  big5-eten   /\bbig-?5$/i	Big5 encoding (with ETen extensions)
35	      /\bbig5-?et(en)?$/i
36	      /\btca-?big5$/i
37  big5-hkscs  /\bbig5-?hk(scs)?$/i
38              /\bhk(scs)?-?big5$/i
39                                Big5 + Cantonese characters in Hong Kong
40  MacChineseTrad		Big5 + Apple Vendor Mappings
41  cp950		                Code Page 950
42                                = Big5 + Microsoft vendor mappings
43  --------------------------------------------------------------------
44
45To find out how to use this module in detail, see L<Encode>.
46
47=head1 NOTES
48
49Due to size concerns, C<EUC-TW> (Extended Unix Character), C<CCCII>
50(Chinese Character Code for Information Interchange), C<BIG5PLUS>
51(CMEX's Big5+) and C<BIG5EXT> (CMEX's Big5e) are distributed separately
52on CPAN, under the name L<Encode::HanExtra>. That module also contains
53extra China-based encodings.
54
55=head1 BUGS
56
57Since the original C<big5> encoding (1984) is not supported anywhere
58(glibc and DOS-based systems uses C<big5> to mean C<big5-eten>; Microsoft
59uses C<big5> to mean C<cp950>), a conscious decision was made to alias
60C<big5> to C<big5-eten>, which is the de facto superset of the original
61big5.
62
63The C<CNS11643> encoding files are not complete. For common C<CNS11643>
64manipulation, please use C<EUC-TW> in L<Encode::HanExtra>, which contains
65planes 1-7.
66
67The ASCII region (0x00-0x7f) is preserved for all encodings, even
68though this conflicts with mappings by the Unicode Consortium.  See
69
70L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
71
72to find out why it is implemented that way.
73
74=head1 SEE ALSO
75
76L<Encode>
77
78=cut
79