#!/usr/bin/perl -lw

$a="à"; # A high latin1 character, doesn't even need unicode

print '$a Normal substr: ', ord(substr($a,0,1));
{
    use bytes;
    print '$a Bytes  substr: ', ord(substr($a,0,1));
}

$b = $a . chr(256); chop $b;
print '$a equals $b, but $b is internally in UTF8' if $a eq $b;

print '$b Normal substr: ', ord(substr($b,0,1));
{
    use bytes;
    print '$b Bytes  substr: ', ord(substr($b,0,1));
}

Giving:

$a Normal substr: 224
$a Bytes  substr: 224
$a equals $b but $b is internally in UTF8
$b Normal substr: 224
$b Bytes  substr: 195

##</code><code>##

use Encode;
$octets = encode("utf8", $string);