Simple Perl script to find UTF8 encoding errors in documents

utftest.pl

#!/usr/bin/perl -- # -*- Perl -*-

use strict;
use Encode qw/encode decode/;

my $file = shift @ARGV || "-";

my $count = 0;
open (F, $file);
while (<F>) {
    chop;
    $count++;
    my $orig = $_;
    my $utf8 = encode("utf-8", $orig);
    if ($orig ne $utf8) {
	print "$count: $orig\n";
    }
}
close (F);