#!usr/bin/perl -w

use warnings;
use strict;
use List::Util 'max';

# Read in the file
my $FILENAME3 = "clusters3.txt";
open(DATA, $FILENAME3);

#create arrays and hashes to store stuff
my (%data, %all, @keys);
while (<DATA>) {
# avoid \n on last field
    chomp;
#split the data into chunks
    my @chunks = split;
#create keys for the chunks
    my $key = shift @chunks;
#store the keys in an array unless they already exist
    push @keys, $key unless exists $data{$key};
    foreach my $chunk (@chunks) {
#return references using hashes
        $data{$key}{$chunk}++;
#add all chunks to the hash '%all'
        $all{$chunk} = 1;
    }

#now make a file for the ouput
        my $outputfile = "new_cluster.txt";
           if (! open(POS, ">>$outputfile") ) {
            print "Cannot open file \"$outputfile\" to write to!!\n\n";
                exit;
        }

#sort the fields/columns keys and save them as an array
#my @fields = sort {$a <=> $b} keys %all;
my @fields = sort {lc($a) cmp lc($b)} keys %all; ##<--this sorting didn't work

#find the longest entry in an array
#my $longest = max map {length} @fields;
my $longest = max map {scalar grep $_=~ /\(\d+\)\_\(\d+\)\_\(\d+\)\_/, @fields} @fields; #the line I think has a problem!

#organise the data
foreach my $key (@keys) {
    while (keys %{$data{$key}}) {
        print POS $key, " "; 
        foreach my $field (@fields) {                
            if ($data{$key}{$field}){
                printf POS "%${longest}s ", $field;
                delete $data{$key}{$field} unless --$data{$key}{$field};
            }
            else {
               printf POS "%${longest}s ", "-";
            }
        }
        print POS"\n";
    }}}