Some UTF-8 characters here�

Some more UTF-8 characters here�

�There could be UTF-8 characters anywhere

]]> ##

##

#!/usr/bin/perl
use strict;
use warnings;
use utf8;
use XML::Twig;
use HTML::Entities;
use HTML::Parser;
 
my $xml = $ARGV[0] or die "Usage:  $0  file.xml\n";
#print $xml;

my $twig = XML::Twig->new( 
    pretty_print => 'indented',
    twig_handlers => { '#CDATA' => \&encodeCorrectly });
$twig->parsefile( $xml );
$twig->flush;
exit;

sub encodeCorrectly { 
    my( $twig, $property)= @_;

    my $htmlToEncode = $property->text;        
    my $htmlEncoded = encode_entities( $htmlToEncode, '&\'"[]\200-\377' );
#    print "\n\n\n" . $htmlEncoded ."\n\n\n"; 
    $property->set_text( $htmlEncoded );        
#    print "\n\n\n" . $property->text ."\n\n\n"; 
}

##

##

perl -CS -pe 's/([^[:ascii:]])/sprintf("&#%d",ord($1))/eg' < orig.xml > encoded.xml