| 1 | package Encode::CN;
|
|---|
| 2 | BEGIN {
|
|---|
| 3 | if (ord("A") == 193) {
|
|---|
| 4 | die "Encode::CN not supported on EBCDIC\n";
|
|---|
| 5 | }
|
|---|
| 6 | }
|
|---|
| 7 | our $VERSION = do { my @r = (q$Revision: 2.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
|
|---|
| 8 |
|
|---|
| 9 | use Encode;
|
|---|
| 10 | use XSLoader;
|
|---|
| 11 | XSLoader::load(__PACKAGE__,$VERSION);
|
|---|
| 12 |
|
|---|
| 13 | # Relocated from Encode.pm
|
|---|
| 14 |
|
|---|
| 15 | use Encode::CN::HZ;
|
|---|
| 16 | # use Encode::CN::2022_CN;
|
|---|
| 17 |
|
|---|
| 18 | 1;
|
|---|
| 19 | __END__
|
|---|
| 20 |
|
|---|
| 21 | =head1 NAME
|
|---|
| 22 |
|
|---|
| 23 | Encode::CN - China-based Chinese Encodings
|
|---|
| 24 |
|
|---|
| 25 | =head1 SYNOPSIS
|
|---|
| 26 |
|
|---|
| 27 | use Encode qw/encode decode/;
|
|---|
| 28 | $euc_cn = encode("euc-cn", $utf8); # loads Encode::CN implicitly
|
|---|
| 29 | $utf8 = decode("euc-cn", $euc_cn); # ditto
|
|---|
| 30 |
|
|---|
| 31 | =head1 DESCRIPTION
|
|---|
| 32 |
|
|---|
| 33 | This module implements China-based Chinese charset encodings.
|
|---|
| 34 | Encodings supported are as follows.
|
|---|
| 35 |
|
|---|
| 36 | Canonical Alias Description
|
|---|
| 37 | --------------------------------------------------------------------
|
|---|
| 38 | euc-cn /\beuc.*cn$/i EUC (Extended Unix Character)
|
|---|
| 39 | /\bcn.*euc$/i
|
|---|
| 40 | /\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
|
|---|
| 41 | gb2312-raw The raw (low-bit) GB2312 character map
|
|---|
| 42 | gb12345-raw Traditional chinese counterpart to
|
|---|
| 43 | GB2312 (raw)
|
|---|
| 44 | iso-ir-165 GB2312 + GB6345 + GB8565 + additions
|
|---|
| 45 | MacChineseSimp GB2312 + Apple Additions
|
|---|
| 46 | cp936 Code Page 936, also known as GBK
|
|---|
| 47 | (Extended GuoBiao)
|
|---|
| 48 | hz 7-bit escaped GB2312 encoding
|
|---|
| 49 | --------------------------------------------------------------------
|
|---|
| 50 |
|
|---|
| 51 | To find how to use this module in detail, see L<Encode>.
|
|---|
| 52 |
|
|---|
| 53 | =head1 NOTES
|
|---|
| 54 |
|
|---|
| 55 | Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
|
|---|
| 56 | separately on CPAN, under the name L<Encode::HanExtra>. That module
|
|---|
| 57 | also contains extra Taiwan-based encodings.
|
|---|
| 58 |
|
|---|
| 59 | =head1 BUGS
|
|---|
| 60 |
|
|---|
| 61 | When you see C<charset=gb2312> on mails and web pages, they really
|
|---|
| 62 | mean C<euc-cn> encodings. To fix that, C<gb2312> is aliased to C<euc-cn>.
|
|---|
| 63 | Use C<gb2312-raw> when you really mean it.
|
|---|
| 64 |
|
|---|
| 65 | The ASCII region (0x00-0x7f) is preserved for all encodings, even though
|
|---|
| 66 | this conflicts with mappings by the Unicode Consortium. See
|
|---|
| 67 |
|
|---|
| 68 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
|
|---|
| 69 |
|
|---|
| 70 | to find out why it is implemented that way.
|
|---|
| 71 |
|
|---|
| 72 | =head1 SEE ALSO
|
|---|
| 73 |
|
|---|
| 74 | L<Encode>
|
|---|
| 75 |
|
|---|
| 76 | =cut
|
|---|
