my %fnameof;
my %valueof;

my @relation;
my @second;

my $mainfile;
my $subfiles;
{
  open ($testdataset, "datasetnew.txt") or die "Cannot open file";
  @testdataset =  <$testdataset>;
  close ($testdataset);

  open (STDOUT, ">>result.txt");

	$fcount = 1;
	
	$secondcount = 0;
	
 
	@testdataset = grep { $_ ne '' } @testdataset;
	@testdataset = grep /\S/, @testdataset;
  
	foreach $dataline (@testdataset) {
		($mainfile, $subfiles) = GetFileName($dataline);
		
		for ($mainfile) {
			$mainfile =~ s/^\s+//;
			$mainfile =~ s/\s+$//;
		}
		addtoHash($mainfile);
		
		@subfiles = @keywords = split(/;/, $subfiles);
		@subfiles = grep { $_ ne '' } @subfiles;
		@subfiles = grep /\S/, @subfiles;

		foreach $subfile (@subfiles) {
			$subfile =~ s/^\s+//;
			$subfile =~ s/\s+$//;
			addtoHash($subfile) unless ($_ ne '');
		}

		#defining the relation of mainfile with subfiles. Each mainfile has relation weight = 1 with subfile.
		foreach $subfile (@subfiles) {
				$relation[$valueof{$mainfile}][$valueof{$subfile}] = 1;
				$second[$secondcount] = "$valueof{$mainfile};$valueof{$subfile}";
				$secondcount++;
		}
	}
	#creating transitive relationship. ie: if A->B and B->C, then A->C
	foreach  $seconditem (@second) {
			@test = split(/;/, $seconditem);
			$b = $test[0];
			$c = $test[1];

			for ($k = 1; $k<=$secondcount; $k++) {
				if ($relation[$c][$k] gt 0) {
						$relation[$b][$k] = $relation[$b][$k]+1;
				}
			}
	}
	PrintArray();
}

#get mainfile and subfiles
sub GetFileName{
    my $item = $_[0];
    @datasplit = split(/\t/, $item);
	$mainfile = @datasplit[0];
	$subfiles = @datasplit[1];

    return ($mainfile, $subfiles);
}

sub addtoHash{
    my $file = $_[0];
    $exist = 0;
		for ($i = 0; $i < $fcount; $i++)
    {
				if ($fnameof{$i} eq $file)
				{
					$exist = $i;
				}
    }
    if ($exist == 0)
    {
        $fnameof{$fcount}= $file;
			  $valueof{$file} = $fcount;
              
		 	  $fcount++;
    }
}

sub PrintArray(){

	for($i=1;$i<$fcount; $i++) {
		for($j=1;$j<$fcount;$j++){
			if (defined ($relation[$i][$j])) {
				print $fnameof{$i}."-".$relation[$i][$j]."->".$fnameof{$j}."\n";
			}
		}
	}
	print "\n";
}

##</code><code>##

 cancer	breast cancer; lung cancer; heart cancer; stomach cancer;
 breast cancer	foot cancer;
 foot cancer	some cancer;
 lung cancer	blood cancer; foot cancer;
 heart cancer	foot cancer;
 stomach cancer	foot cancer;
 blood cancer	some cancer;