#! perl -w
use strict;
use File::Find;
use Digest::MD5;

local $|   = 1;
my $path   = $ARGV[0];

print "Searching for duplicate files in $path\n";
find(\&check_file, $path);

local $"   = '';
my %files;
my %md5;
my $wasted = 0;
my $size   = 0;

for my $size (sort {$b <=> $a} keys %files)
{
    next unless   @{ $files{$size} } > 1;

    for my $file (@{ $files{$size} })
    {
        open(FILE, $file) or next;
        binmode(FILE);
        my $key = Digest::MD5->new->addfile(*FILE)->hexdigest;
        $md5{$key}{size} = $size;
        push @{ $md5{$key}{files} }, $file . "\n";
    }
}

for my $hash (keys %md5)
{
    next unless @{ $md5{$hash}{files} } > 1;
    print "\n@{$md5{$hash}{files}}";
    my $s = $md5{$hash}{size};
    print "File size $s\n";
    $wasted += $s * (@{ $md5{$hash}{files} } - 1);
}

$wasted =~ s/^([-+]?\d+)(\d{3})/$1,$2/;
print "\n$wasted bytes in duplicated files\n";

sub check_file
{
	(my $fn = $File::Find::name) =~ tr#/#\\#;
    -f && push @{ $files{ (stat(_))[7] } }, $fn;
}

##</code><code>##

17:56 >perl 1201_SoPW.pl .
Searching for duplicate files in .

.\fox1.txt
.\fox2.txt
File size 52

.\party1.txt
.\party2.txt
.\party3.txt
File size 65

182 bytes in duplicated files

17:56 >