4:27
ˆÀÅ
0¿Ã / ˆl–Ðz¾”êC]ŠeA
à_¸ÔÅ£Æ
ƒyöÛ_‹ uÐb
&=LV[(ÁÅ "û package Encode::Unicode;
use strict;
use warnings;
no warnings 'redefine';
our $VERSION = do { my @r = ( q$Revision: 2.7 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
use XSLoader;
XSLoader::load( __PACKAGE__, $VERSION );
#
# Object Generator 8 transcoders all at once!
#
require Encode;
our %BOM_Unknown = map { $_ => 1 } qw(UTF-16 UTF-32);
for my $name (
qw(UTF-16 UTF-16BE UTF-16LE
UTF-32 UTF-32BE UTF-32LE
UCS-2BE UCS-2LE)
)
{
my ( $size, $endian, $ucs2, $mask );
$name =~ /^(\w+)-(\d+)(\w*)$/o;
if ( $ucs2 = ( $1 eq 'UCS' ) ) {
$size = 2;
}
else {
$size = $2 / 8;
}
$endian = ( $3 eq 'BE' ) ? 'n' : ( $3 eq 'LE' ) ? 'v' : '';
$size == 4 and $endian = uc($endian);
$Encode::Encoding{$name} = bless {
Name => $name,
size => $size,
endian => $endian,
ucs2 => $ucs2,
} => __PACKAGE__;
}
use base qw(Encode::Encoding);
sub renew {
my $self = shift;
$BOM_Unknown{ $self->name } or return $self;
my $clone = bless {%$self} => ref($self);
$clone->{renewed}++; # so the caller knows it is renewed.
return $clone;
}
# There used to be a perl implemntation of (en|de)code but with
# XS version is ripe, perl version is zapped for optimal speed
*decode = \&decode_xs;
*encode = \&encode_xs;
1;
__END__
=head1 NAME
Encode::Unicode -- Various Unicode Transformation Formats
=cut
=head1 SYNOPSIS
use Encode qw/encode decode/;
$ucs2 = encode("UCS-2BE", $utf8);
$utf8 = decode("UCS-2BE", $ucs2);
=head1 ABSTRACT
This module implements all Character Encoding Schemes of Unicode that
are officially documented by Unicode Consortium (except, of course,
for UTF-8, which is a native format in perl).
=over 4
=item L says:
I A character encoding form plus byte
serialization. There are Seven character encoding schemes in Unicode:
UTF-8, UTF-16, UTF-16BE, UTF-16LE, UTF-32 (UCS-4), UTF-32BE (UCS-4BE) and
UTF-32LE (UCS-4LE), and UTF-7.
Since UTF-7 is a 7-bit (re)encoded version of UTF-16BE, It is not part of
Unicode's Character Encoding Scheme. It is separately implemented in
Encode::Unicode::UTF7. For details see L.
=item Quick Reference
Decodes from ord(N) Encodes chr(N) to...
octet/char BOM S.P d800-dfff ord > 0xffff \x{1abcd} ==
---------------+-----------------+------------------------------
UCS-2BE 2 N N is bogus Not Available
UCS-2LE 2 N N bogus Not Available
UTF-16 2/4 Y Y is S.P S.P BE/LE
UTF-16BE 2/4 N Y S.P S.P 0xd82a,0xdfcd
UTF-16LE 2/4 N Y S.P S.P 0x2ad8,0xcddf
UTF-32 4 Y - is bogus As is BE/LE
UTF-32BE 4 N - bogus As is 0x0001abcd
UTF-32LE 4 N - bogus As is 0xcdab0100
UTF-8 1-4 - - bogus >= 4 octets \xf0\x9a\af\8d
---------------+-----------------+------------------------------
=back
=head1 Size, Endianness, and BOM
You can categorize these CES by 3 criteria: size of each character,
endianness, and Byte Order Mark.
=head2 by size
UCS-2 is a fixed-length encoding with each character taking 16 bits.
It B support I. When a surrogate pair
is encountered during decode(), its place is filled with \x{FFFD}
if I is 0, or the routine croaks if I is 1. When a
character whose ord value is larger than 0xFFFF is encountered,
its place is filled with \x{FFFD} if I is 0, or the routine
croaks if I is 1.
UTF-16 is almost the same as UCS-2 but it supports I.
When it encounters a high surrogate (0xD800-0xDBFF), it fetches the
following low surrogate (0xDC00-0xDFFF) and Cs them to
form a character. Bogus surrogates result in death. When