#!/usr/bin/perl

use strict;
use warnings;
use Devel::Peek;
use Encode;
#use utf8;

binmode STDOUT, ":utf8";

my $string1 = "123\x{444}\x{444}\x{444}\x{444}";
_display ($string1, 'STRING1' );

my $utfstring = "123 \x{439}\x{439}\x{439}\x{439}";
_display ($utfstring, 'UTF_STRING' );

my ($ascii_but_utf, undef) = split ' ', $utfstring;
_display ($ascii_but_utf, 'ASCII_BUT_UTF' );

#my $bytestring = encode ("UTF-8", "\x{444}\x{444}\x{444}\x{444}");
my $bytestring = "\x{444}\x{444}\x{444}\x{444}";
_display ($bytestring, 'BYTESTRING' );

my $mixedstring = "$ascii_but_utf$bytestring"; # simulate The Unicode Bug here
_display ($mixedstring, 'MIXEDSTRING' );

print "MIXEDSTRING and STRING1 are supposed to be identical...\n";

exit;

###############

sub _display {
   my ($string, $name) = @_;

   print "$name:\n";
   Dump $string;

   my $l1 = length($string);
   my $l2 = bytes::length($string);
   if ($l1 != $l2) {
       print "LENGTHs DIFFERS: length: $l1, bytes: $l2\n" 
   }

   print "UTF IS ON\n" if utf8::is_utf8($string);
   print "\n";
}