Commit | Line | Data |
0e567a6c |
1 | package Encode::CN; |
071db25d |
2 | BEGIN { |
3 | if (ord("A") == 193) { |
4 | die "Encode::CN not supported on EBCDIC\n"; |
5 | } |
6 | } |
b2704119 |
7 | our $VERSION = do { my @r = (q$Revision: 1.22 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; |
c0d88b76 |
8 | |
9 | use Encode; |
0e567a6c |
10 | use XSLoader; |
b2704119 |
11 | XSLoader::load(__PACKAGE__,$VERSION); |
0e567a6c |
12 | |
5d030b67 |
13 | # Relocated from Encode.pm |
5d030b67 |
14 | |
aae85ceb |
15 | use Encode::CN::HZ; |
67d7b5ef |
16 | # use Encode::CN::2022_CN; |
64ffdd5e |
17 | |
0e567a6c |
18 | 1; |
19 | __END__ |
67d7b5ef |
20 | |
b2729934 |
21 | =head1 NAME |
22 | |
23 | Encode::CN - China-based Chinese Encodings |
24 | |
25 | =head1 SYNOPSIS |
26 | |
1b2c56c8 |
27 | use Encode qw/encode decode/; |
2b217bf7 |
28 | $euc_cn = encode("euc-cn", $utf8); # loads Encode::CN implicitly |
ee981de6 |
29 | $utf8 = decode("euc-cn", $euc_cn); # ditto |
b2729934 |
30 | |
31 | =head1 DESCRIPTION |
32 | |
33 | This module implements China-based Chinese charset encodings. |
34 | Encodings supported are as follows. |
35 | |
fab31126 |
36 | Canonical Alias Description |
37 | -------------------------------------------------------------------- |
67d7b5ef |
38 | euc-cn /\beuc.*cn$/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 |
fab31126 |
43 | GB2312 (raw) |
44 | iso-ir-165 GB2312 + GB6345 + GB8565 + additions |
a999c27c |
45 | MacChineseSimp GB2312 + Apple Additions |
fab31126 |
46 | cp936 Code Page 936, also known as GBK |
47 | (Extended GuoBiao) |
48 | hz 7-bit escaped GB2312 encoding |
5129552c |
49 | -------------------------------------------------------------------- |
b2729934 |
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 | |
c0d88b76 |
59 | =head1 BUGS |
b2729934 |
60 | |
67d7b5ef |
61 | When you see C<charset=gb2312> on mails and web pages, they really |
62 | mean "euc-cn" encodings. To fix that, gb2312 is aliased to euc-cn. Use |
63 | gb2312-raw when you really mean it. |
64 | |
b2729934 |
65 | ASCII part (0x00-0x7f) is preserved for all encodings, even though it |
66 | conflicts with mappings by the Unicode Consortium. See |
67 | |
a63c962f |
68 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en> |
b2729934 |
69 | |
70 | to find why it is implemented that way. |
71 | |
72 | =head1 SEE ALSO |
73 | |
67d7b5ef |
74 | L<Encode>,L<Encode::CJKguide> |
b2729934 |
75 | |
76 | =cut |