#!/usr/bin/perl

use strict;
use Digest::MD5 qw/md5_base64/;

@files = <>;  # read list of file names (from @ARGV or STDIN)
chomp @files;

my %sigs;
for my $file ( @files ) {
    local $/;  # use "slurp" input mode: whole file in 1 read
    open( I, "<", $file ) or do {
        warn "$file: $!\n";
        next;
    }
    $_ = <I>;
    close I;
    my $siz = -s $file;
    my $sig = md5_base64( $_ );
    push @{$sigs{"$sig $siz"}, $file;
}

# now check for possible duplicate files
my $path = "/media/hda3/2967test";
for my $sig ( grep { @{$sigs{$_}} > 1 } keys %sigs ) {
    my @files = @{$sigs{$sig}};
    for my $i ( 1 .. $#files ) {
        for my $j ( 0 .. $i-1 ) {
            $diff = `cmp $path/$files[$i] $path/$files[$j] | wc -l`;
            print "$files[$i] - $files[$j] are duplicates\n"
               if ( $diff =~ /^\s*0/ );
        }
    }
}