#!/usr/bin/perl
#-------------------------
# Find Duplcate files
#-------------------------
#
# load the modules, Load The Modules, LOAD THE MODULES
#
use File::Find;  # used to traverse directory
use Digest::MD5; # use to find md5 of each file
#
# 1=print extra output, 0=more silent
#
my $debug=0;
#
# hash containing all data, md5 is the key, value array of file names.
#
my %unique=();
my $ref_unique=\%unique;
#
# If no arguments are given, use current dir
#
@ARGV = (".") unless @ARGV;
#
# Function calcuates md5 on files
# and populates the %unique hash using $ref_unique reference
#
sub md5sum   {
  #
  # Unless a file, exit function
  #
  return unless -f ; 
  #
  # Assign file name to variable
  #
  my $file="$File::Find::name";  
  #
  # Create md5 object
  #
  my $md5 = Digest::MD5->new;
  #
  # Add file name to the object
  #
  $md5->add($file);
  #
  # Calculate md5sum, store in variable
  #
  my $number=$md5->clone->hexdigest;
  #
  # Print values if debug is turn;
  #
  if ( $debug == 1 ){ print "$number:$file\n"; }    
  #
  # Now Add this info to the hash %unique
  #
  if ( exists $$ref_unique{$number} ){
     #
     # If the md5 has been seen before, append to hash elements array
     #
     push @{ $$ref_unique{"$number"} }, "$file" ;
  } else {
     #
     # Otherwise Start a new hash element
     # And add the file name to the array
     #
     my @array = ( $file );
     $$ref_unique{$number} = [ ( $file ) ];
  }
}
#
# Finally call find
#
find(\&md5sum, @ARGV);
#
# Print out the results
#
foreach my $x ( keys %unique ) {
     my $y = $#{$unique{$x}} + 1;
     print "$x:$y \t @{ $unique{$x} }\n"
}