Commit | Line | Data |
0e567a6c |
1 | package Encode::JP; |
0f3b375a |
2 | BEGIN { |
3 | if (ord("A") == 193) { |
4 | die "Encode::JP not supported on EBCDIC\n"; |
5 | } |
6 | } |
0e567a6c |
7 | use Encode; |
67d7b5ef |
8 | our $VERSION = do { my @r = (q$Revision: 1.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; |
ee981de6 |
9 | |
0e567a6c |
10 | use XSLoader; |
11 | XSLoader::load('Encode::JP',$VERSION); |
12 | |
13 | use Encode::JP::JIS; |
64ffdd5e |
14 | use Encode::JP::2022_JP; |
15 | use Encode::JP::2022_JP1; |
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 |
39 | /\bujis$/i |
40 | shiftjis /\bshift.*jis$/i Shift JIS (aka MS Kanji) |
41 | /\bsjis$/i |
42 | 7bit-jis /\bjis$/i 7bit JIS |
43 | iso-2022-jp ISO-2022-JP [RFC1468] |
fab31126 |
44 | (7bit JIS with all Halfwidth Kana |
45 | converted to Fullwidth) |
67d7b5ef |
46 | iso-2022-jp-1 ISO-2022-JP-1 [RFC2237] |
a63c962f |
47 | (ISO-2022-JP with JIS X 0212-1990 |
48 | support. See below) |
67d7b5ef |
49 | MacJapanese (Shift JIS + Apple vendor mappings) |
50 | cp932 Code Page 932 |
51 | (Shift JIS + MS/IBM vendor mappings) |
5129552c |
52 | -------------------------------------------------------------------- |
557e5ea9 |
53 | |
54 | =head1 DESCRIPTION |
55 | |
56 | To find how to use this module in detail, see L<Encode>. |
57 | |
a63c962f |
58 | =head1 Note on ISO-2022-JP(-1)? |
59 | |
60 | ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which |
61 | adds support for JIS X 0212-1990. That means you can use the same |
62 | code to decode to utf8 but not vice versa. |
63 | |
64 | $utf8 = decode('iso-2022-jp-1', $stream); |
65 | $utf8 = decode('iso-2022-jp', $stream); |
66 | |
67 | Yields the same result but |
68 | |
69 | $with_0212 = encode('iso-2022-jp-1', $utf8); |
70 | |
71 | is now different from |
72 | |
73 | $without_0212 = encode('iso-2022-jp', $utf8 ); |
74 | |
75 | In the latter case, characters that map to 0212 are at first converted |
76 | to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu') then |
77 | fed to decoding engine. U+FFFD is not used to preserve text layout as |
78 | much as possible. |
79 | |
557e5ea9 |
80 | =head1 BUGS |
81 | |
557e5ea9 |
82 | ASCII part (0x00-0x7f) is preserved for all encodings, even though it |
83 | conflicts with mappings by the Unicode Consortium. See |
84 | |
a63c962f |
85 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en> |
557e5ea9 |
86 | |
87 | to find why it is implemented that way. |
88 | |
89 | =head1 SEE ALSO |
90 | |
67d7b5ef |
91 | L<Encode>,L<Encode::CJKguide> |
557e5ea9 |
92 | |
93 | =cut |