Commit | Line | Data |
0e567a6c |
1 | package Encode::JP; |
0f3b375a |
2 | BEGIN { |
d1256cb1 |
3 | if ( ord("A") == 193 ) { |
4 | die "Encode::JP not supported on EBCDIC\n"; |
0f3b375a |
5 | } |
6 | } |
656ebd29 |
7 | use strict; |
8 | use warnings; |
0e567a6c |
9 | use Encode; |
b2deda17 |
10 | our $VERSION = do { my @r = ( q$Revision: 2.4 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r }; |
ee981de6 |
11 | |
0e567a6c |
12 | use XSLoader; |
d1256cb1 |
13 | XSLoader::load( __PACKAGE__, $VERSION ); |
0e567a6c |
14 | |
aae85ceb |
15 | use Encode::JP::JIS7; |
0e567a6c |
16 | |
17 | 1; |
18 | __END__ |
67d7b5ef |
19 | |
557e5ea9 |
20 | =head1 NAME |
21 | |
22 | Encode::JP - Japanese Encodings |
23 | |
24 | =head1 SYNOPSIS |
25 | |
1b2c56c8 |
26 | use Encode qw/encode decode/; |
2b217bf7 |
27 | $euc_jp = encode("euc-jp", $utf8); # loads Encode::JP implicitly |
ee981de6 |
28 | $utf8 = decode("euc-jp", $euc_jp); # ditto |
557e5ea9 |
29 | |
30 | =head1 ABSTRACT |
31 | |
32 | This module implements Japanese charset encodings. Encodings |
33 | supported are as follows. |
34 | |
fab31126 |
35 | Canonical Alias Description |
36 | -------------------------------------------------------------------- |
67d7b5ef |
37 | euc-jp /\beuc.*jp$/i EUC (Extended Unix Character) |
38 | /\bjp.*euc/i |
d1256cb1 |
39 | /\bujis$/i |
67d7b5ef |
40 | shiftjis /\bshift.*jis$/i Shift JIS (aka MS Kanji) |
d1256cb1 |
41 | /\bsjis$/i |
67d7b5ef |
42 | 7bit-jis /\bjis$/i 7bit JIS |
43 | iso-2022-jp ISO-2022-JP [RFC1468] |
d1256cb1 |
44 | = 7bit JIS with all Halfwidth Kana |
45 | converted to Fullwidth |
67d7b5ef |
46 | iso-2022-jp-1 ISO-2022-JP-1 [RFC2237] |
a999c27c |
47 | = ISO-2022-JP with JIS X 0212-1990 |
d1256cb1 |
48 | support. See below |
a999c27c |
49 | MacJapanese Shift JIS + Apple vendor mappings |
8f1ed24a |
50 | cp932 /\bwindows-31j$/i Code Page 932 |
a999c27c |
51 | = Shift JIS + MS/IBM vendor mappings |
f2a2953c |
52 | jis0201-raw JIS0201, raw format |
53 | jis0208-raw JIS0201, raw format |
54 | jis0212-raw JIS0201, raw format |
5129552c |
55 | -------------------------------------------------------------------- |
557e5ea9 |
56 | |
57 | =head1 DESCRIPTION |
58 | |
0ab8f81e |
59 | To find out how to use this module in detail, see L<Encode>. |
557e5ea9 |
60 | |
a63c962f |
61 | =head1 Note on ISO-2022-JP(-1)? |
62 | |
63 | ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which |
64 | adds support for JIS X 0212-1990. That means you can use the same |
65 | code to decode to utf8 but not vice versa. |
66 | |
67 | $utf8 = decode('iso-2022-jp-1', $stream); |
0ab8f81e |
68 | |
69 | and |
70 | |
a63c962f |
71 | $utf8 = decode('iso-2022-jp', $stream); |
72 | |
0ab8f81e |
73 | yield the same result but |
a63c962f |
74 | |
75 | $with_0212 = encode('iso-2022-jp-1', $utf8); |
76 | |
77 | is now different from |
78 | |
79 | $without_0212 = encode('iso-2022-jp', $utf8 ); |
80 | |
0ab8f81e |
81 | In the latter case, characters that map to 0212 are first converted |
82 | to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu' or |
83 | 'geta mark') then fed to the decoding engine. U+FFFD is not used, |
84 | in order to preserve text layout as much as possible. |
a63c962f |
85 | |
557e5ea9 |
86 | =head1 BUGS |
87 | |
0ab8f81e |
88 | The ASCII region (0x00-0x7f) is preserved for all encodings, even |
b2deda17 |
89 | though this conflicts with mappings by the Unicode Consortium. |
557e5ea9 |
90 | |
91 | =head1 SEE ALSO |
92 | |
85982a32 |
93 | L<Encode> |
557e5ea9 |
94 | |
95 | =cut |