my $test = 0;

use warnings;
use bytes;
use Benchmark;
use Encode qw(encode_utf8 decode_utf8);

my $xml;

{
my $isUTF = 1;
my $sub = sub {$isUTF = 0};
sub byPack {
	$SIG{__WARN__} = $sub;
no warnings 'void';
	my @a=unpack( 'U0U*', $xml);
	delete $SIG{__WARN__};
	return $isUTF;
}
}

sub byRegExp {
	my $bad_utf8 = 0;
	while($xml =~ /(?=[\x80-\xFF])(?:[\xC0-\xFF][\x80-\xBF]+|(.))/g and !$bad_utf8) {
		$bad_utf8++ if defined $1;
	}
	return !$bad_utf8;
}

sub byDecode {
	if (decode_utf8($xml)) {
        return 1
    } else {
        return 0
    }
}

print "OK\n";
open XML, '<test-ok.xml';
$xml = do {local $/; <XML>};
close XML;

if ($test) {
	print "byPack=".byPack()."\n";
	print "byRegExp=".byRegExp()."\n";
	print "byDecode=".byDecode()."\n";
} else {
	timethese (10000, {
		byPack => \&byPack,
		byRegExp => \&byRegExp,
		byDecode => \&byDecode,
	});
}

print "BAD\n";
open XML, '<test-bad.xml';
$xml = do {local $/; <XML>};
close XML;

if ($test) {
	print "byPack=".byPack()."\n";
	print "byRegExp=".byRegExp()."\n";
	print "byDecode=".byDecode()."\n";
} else {
	timethese (10000, {
		byPack => \&byPack,
		byRegExp => \&byRegExp,
		byDecode => \&byDecode,
	});
}
__END__
OK
Benchmark: timing 10000 iterations of byDecode, byPack, byRegExp...
  byDecode:  0 wallclock secs ( 0.22 usr +  0.00 sys =  0.22 CPU) @ 45662.10/s (n=10000)
            (warning: too few iterations for a reliable count)
    byPack: 15 wallclock secs (15.17 usr +  0.00 sys = 15.17 CPU) @ 659.11/s (n=10000)
  byRegExp:  5 wallclock secs ( 4.22 usr +  0.00 sys =  4.22 CPU) @ 2370.79/s (n=10000)
BAD
Benchmark: timing 10000 iterations of byDecode, byPack, byRegExp...
  byDecode:  0 wallclock secs ( 0.08 usr +  0.00 sys =  0.08 CPU) @ 128205.13/s (n=10000)
            (warning: too few iterations for a reliable count)
    byPack: 15 wallclock secs (15.42 usr +  0.00 sys = 15.42 CPU) @ 648.42/s (n=10000)
  byRegExp:  5 wallclock secs ( 4.25 usr +  0.00 sys =  4.25 CPU) @ 2352.94/s (n=10000)