}
}
use Encode;
-our $VERSION = '0.02';
+our $VERSION = do { my @r = (q$Revision: 1.21 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+
use XSLoader;
XSLoader::load('Encode::JP',$VERSION);
use Encode::JP::JIS;
-use Encode::JP::ISO_2022_JP;
+use Encode::JP::2022_JP;
+use Encode::JP::2022_JP1;
1;
__END__
+
=head1 NAME
Encode::JP - Japanese Encodings
=head1 SYNOPSIS
- use Encode 'encode';
+ use Encode qw/encode decode/;
$euc_jp = encode("euc-jp", $utf8); # loads Encode::JP implicitly
- $utf8 = encode("euc-jp", $euc_jp); # ditto
+ $utf8 = decode("euc-jp", $euc_jp); # ditto
=head1 ABSTRACT
This module implements Japanese charset encodings. Encodings
supported are as follows.
- euc-jp EUC (Extended Unix Character)
- shiftjis Shift JIS (aka MS Kanji)
- 7bit-jis 7bit JIS
- iso-2022-jp ISO-2022-JP (7bit JIS with all X201 converted to X208)
- macjapan Mac Japan (Shift JIS + Apple vendor mappings)
- cp932 Code Page 932 (Shift JIS + Microsoft vendor mappings)
+ Canonical Alias Description
+ --------------------------------------------------------------------
+ euc-jp /\beuc.*jp$/i EUC (Extended Unix Character)
+ /\bjp.*euc/i
+ /\bujis$/i
+ shiftjis /\bshift.*jis$/i Shift JIS (aka MS Kanji)
+ /\bsjis$/i
+ 7bit-jis /\bjis$/i 7bit JIS
+ iso-2022-jp ISO-2022-JP [RFC1468]
+ = 7bit JIS with all Halfwidth Kana
+ converted to Fullwidth
+ iso-2022-jp-1 ISO-2022-JP-1 [RFC2237]
+ = ISO-2022-JP with JIS X 0212-1990
+ support. See below
+ MacJapanese Shift JIS + Apple vendor mappings
+ cp932 Code Page 932
+ = Shift JIS + MS/IBM vendor mappings
+ jis0201-raw JIS0201, raw format
+ jis0208-raw JIS0201, raw format
+ jis0212-raw JIS0201, raw format
+ --------------------------------------------------------------------
=head1 DESCRIPTION
To find how to use this module in detail, see L<Encode>.
-=head1 BUGS
+=head1 Note on ISO-2022-JP(-1)?
+
+ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which
+adds support for JIS X 0212-1990. That means you can use the same
+code to decode to utf8 but not vice versa.
+
+ $utf8 = decode('iso-2022-jp-1', $stream);
+ $utf8 = decode('iso-2022-jp', $stream);
+
+Yields the same result but
-JIS X0212-1990 is not supported.
+ $with_0212 = encode('iso-2022-jp-1', $utf8);
+
+is now different from
+
+ $without_0212 = encode('iso-2022-jp', $utf8 );
+
+In the latter case, characters that map to 0212 are at first converted
+to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu') then
+fed to decoding engine. U+FFFD is not used to preserve text layout as
+much as possible.
+
+=head1 BUGS
ASCII part (0x00-0x7f) is preserved for all encodings, even though it
conflicts with mappings by the Unicode Consortium. See
-F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
+L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
to find why it is implemented that way.
=head1 SEE ALSO
-L<Encode>
+L<Encode>,L<Encode::CJKguide>
=cut