#
-# $Id: Encode.pm,v 2.9 2004/12/03 19:16:40 dankogai Exp $
+# $Id: Encode.pm,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $
#
package Encode;
use strict;
-# our $VERSION = do { my @r = (q$Revision: 2.9 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
-our $VERSION = '2.0902_01';
+our $VERSION = sprintf "%d.%02d", q$Revision: 2.12 $ =~ /(\d+)/g;
sub DEBUG () { 0 }
use XSLoader ();
XSLoader::load(__PACKAGE__, $VERSION);
);
our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
- PERLQQ HTMLCREF XMLCREF);
+ PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL);
our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
FB_PERLQQ FB_HTMLCREF FB_XMLCREF);
if ($check){
return decode("utf8", $str, $check);
}else{
- return undef unless utf8::decode($str);
+ return decode("utf8", $str);
return $str;
}
}
=head1 Handling Malformed Data
-The optional I<CHECK> argument is used as follows. When you omit it,
-Encode::FB_DEFAULT ( == 0 ) is assumed.
+The optional I<CHECK> argument tells Encode what to do when it
+encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 )
+is assumed.
+
+As of version 2.12 Encode supports coderef values for CHECK. See below.
=over 2
-=item B<NOTE:> Not all encoding suppport this feature
+=item B<NOTE:> Not all encoding support this feature
Some encodings ignore I<CHECK> argument. For example,
L<Encode::Unicode> ignores I<CHECK> and it always croaks on error.
=back
-=head2 Unimplemented fallback schemes
+=head2 coderef for CHECK
+
+As of Encode 2.12 CHECK can also be a code reference which takes the
+ord value of unmapped caharacter as an argument and returns a string
+that represents the fallback character. For instance,
-In the future, you will be able to use a code reference to a callback
-function for the value of I<CHECK> but its API is still undecided.
+ $ascii = encode("ascii", $utf8, sub{ sprintf "<U+%04X>", shift });
-The fallback scheme does not work on EBCDIC platforms.
+Acts like FB_PERLQQ but E<lt>U+I<XXXX>E<gt> is used instead of
+\x{I<XXXX>}.
=head1 Defining Encodings
In any other Encoding ON
---------------------------------------------
-As you see, there is one exception, In ASCII. That way you can assue
+As you see, there is one exception, In ASCII. That way you can assume
Goal #1. And with Encode Goal #2 is assumed but you still have to be
careful in such cases mentioned in B<CAVEAT> paragraphs.
For what it's worth, that's how I've always kept them straight in my
head.
-
+
Also for what it's worth, Perl 6 will mostly default to strict but
make it easy to switch back to lax.