| 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; |
| a63c962f |
8 | our $VERSION = do { my @r = (q$Revision: 0.98 $ =~ /\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; |
| 14 | use Encode::JP::ISO_2022_JP; |
| a63c962f |
15 | use Encode::JP::ISO_2022_JP_1; |
| 0e567a6c |
16 | |
| 17 | 1; |
| 18 | __END__ |
| 557e5ea9 |
19 | =head1 NAME |
| 20 | |
| 21 | Encode::JP - Japanese Encodings |
| 22 | |
| 23 | =head1 SYNOPSIS |
| 24 | |
| 1b2c56c8 |
25 | use Encode qw/encode decode/; |
| 2b217bf7 |
26 | $euc_jp = encode("euc-jp", $utf8); # loads Encode::JP implicitly |
| ee981de6 |
27 | $utf8 = decode("euc-jp", $euc_jp); # ditto |
| 557e5ea9 |
28 | |
| 29 | =head1 ABSTRACT |
| 30 | |
| 31 | This module implements Japanese charset encodings. Encodings |
| 32 | supported are as follows. |
| 33 | |
| fab31126 |
34 | Canonical Alias Description |
| 35 | -------------------------------------------------------------------- |
| 36 | euc-jp /euc.*jp$/i EUC (Extended Unix Character) |
| 37 | /jp.*euc/i |
| 38 | /ujis$/i |
| 39 | shiftjis /shift.*jis$/i Shift JIS (aka MS Kanji) |
| 40 | /sjis$/i |
| 41 | 7bit-jis /^jis$/i 7bit JIS |
| 42 | iso-2022-jp ISO-2022-JP |
| 43 | (7bit JIS with all Halfwidth Kana |
| 44 | converted to Fullwidth) |
| a63c962f |
45 | iso-2022-jp-1 ISO-2022-JP-1 |
| 46 | (ISO-2022-JP with JIS X 0212-1990 |
| 47 | support. See below) |
| fab31126 |
48 | macjapan Mac Japan (Shift JIS + Apple vendor mappings) |
| 5129552c |
49 | cp932 Code Page 932 (Shift JIS + MS/IBM vendor mappings) |
| 50 | -------------------------------------------------------------------- |
| 557e5ea9 |
51 | |
| 52 | =head1 DESCRIPTION |
| 53 | |
| 54 | To find how to use this module in detail, see L<Encode>. |
| 55 | |
| a63c962f |
56 | =head1 Note on ISO-2022-JP(-1)? |
| 57 | |
| 58 | ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which |
| 59 | adds support for JIS X 0212-1990. That means you can use the same |
| 60 | code to decode to utf8 but not vice versa. |
| 61 | |
| 62 | $utf8 = decode('iso-2022-jp-1', $stream); |
| 63 | $utf8 = decode('iso-2022-jp', $stream); |
| 64 | |
| 65 | Yields the same result but |
| 66 | |
| 67 | $with_0212 = encode('iso-2022-jp-1', $utf8); |
| 68 | |
| 69 | is now different from |
| 70 | |
| 71 | $without_0212 = encode('iso-2022-jp', $utf8 ); |
| 72 | |
| 73 | In the latter case, characters that map to 0212 are at first converted |
| 74 | to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu') then |
| 75 | fed to decoding engine. U+FFFD is not used to preserve text layout as |
| 76 | much as possible. |
| 77 | |
| 557e5ea9 |
78 | =head1 BUGS |
| 79 | |
| 557e5ea9 |
80 | ASCII part (0x00-0x7f) is preserved for all encodings, even though it |
| 81 | conflicts with mappings by the Unicode Consortium. See |
| 82 | |
| a63c962f |
83 | L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en> |
| 557e5ea9 |
84 | |
| 85 | to find why it is implemented that way. |
| 86 | |
| 87 | =head1 SEE ALSO |
| 88 | |
| 89 | L<Encode> |
| 90 | |
| 91 | =cut |
projects / p5sagit/p5-mst-13.2.git / blame