#!/usr/bin/perl -w

use strict;
use File::Find;
no warnings 'File::Find';
use Digest::MD5;
local $| = 1;

my $path = $ARGV[0];
#my $testpath = 'C:/Temp/';

print "Searching for duplicate files in $path\n";
#find(\&check_file, $testpath);
find(\&check_file, $path);
local $" = "";
my %files;
my %md5;
my $wasted = 0;
my $size = 0;
foreach my $size (sort {$b <=> $a} keys %files) {
  next unless @{$files{$size}} > 1;
  foreach my $file (@{$files{$size}}) {
    open(FILE, $file) or next;
    binmode(FILE);
    push @{$md5{Digest::MD5->new->addfile(*FILE)->hexdigest}},$file."\n";
  }
  foreach my $hash (keys %md5) {
    next unless @{$md5{$hash}} > 1;
    print "\n@{$md5{$hash}}";
	print "File size $size\n \n";
    $wasted += $size * (@{$md5{$hash}} - 1);
  }
}
1 while $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;
}