#!/usr/local/bin/perl

 use strict;
 use warnings;

 open (M, 'M.dumpy');
 print "File M.dump opened \n";
 open (F, 'F.dumpy'); 
 print "File F.dump opened \n";
 open (OUT, '>kmer_differencey');
 print "Output file kmer_differences opened \n";

# Set block size
 my $blocksize = 1000;
 print "Blocksize set to $blocksize \n";

# Initialize the counters
 my $commontally = 0;
 my $common;
 my $lncount;
 my $iteration = 0;
# Initialise scalars and arrays
 my $line;
 my $fkey;
 my $count;
 my $kmer;
# Initialize the hash tables
 my %mhash;
 my %fhash;
 my %tmphash1;
 my %tmphash2;

# Progress through the files one block at a time
 do {
  # Increment the iteration counter
    $iteration=$iteration+1;
    print "\nITERATION $iteration \n\n";

  # Read in a block of records from the male dataset 
  # and append to the male hash table

  $lncount = 0;
  foreach (1..$blocksize){
   $line = <M>;
   $lncount = $lncount + 1;
   # Split the line into k-mer and count
   ($kmer, $count) = split(/ /, $line);
   # Push the record into the hash
   $mhash{$kmer}=$count;
   # Clean exit on end of file
   last if (eof(M));
 }
  print "$lncount records from file M.dump added to male hash \n";
  print "     now ".keys(%mhash)." records \n";

  # Read in a block of records from the female dataset
  # and append to the female hash table

  $lncount = 0;
  foreach (1..$blocksize){
   $line = <F>;
   $lncount = $lncount + 1;
   # Split the line into k-mer and count
   ($kmer, $count) = split(/ /, $line);
   # Push the record into the hash
   $fhash{$kmer}=$count;
   # Clean exit on end of file
   last if (eof(F));
 }
  print "$lncount records from file F.dump added to female hash \n";
  print "     now ".keys(%fhash)." records \n";

  # Two hash tables created, containing the retained female differences, with a new block added
  # Now compare the hash tables, looking for female unique k-mers

  # For each female kmer, check to see if it is in the male kmer set
   print "Checking F k-mers for match in M k-mer set \n";
   $common=0;
   while ( ($fkey, $count) = each %fhash ){
    # Does %mhash have a value for $fkey?
    if (exists($mhash{$fkey})) {
    $commontally = $commontally + 1;
    $common = $common + 1;
    # Remove the record from each hash
    delete ($mhash{$fkey});
    delete ($fhash{$fkey});
    } else {
     # Write the record out to diff.txt
    }
   }
   # Processing of block of data completed
 
   print "$common records common to both M and F deleted \n";
   print "Male hash has now ".keys(%mhash)." records \n";
   print "Female hash has now ".keys(%fhash)." records \n";

 } until eof(M) || eof(F);
 # Processing of the comparisons completed

 # Print the outcome to a file
 foreach $kmer (keys %fhash)
 {
  print OUT "$kmer $fhash{$kmer}\n";
 }

 close (OUT);
 print "\n\nFile k-mer_differences closed \n";
 close (M);
 print "File M.dump closed \n";
 close (F);
 print "File F.dump closed \n";

 print "\nTotal kmers in common: $commontally, \n";
 print "Total kmers unique to F: ".keys(%fhash)." \n"; 
 print "Refer to output file k-mer_differences for unique female kmers";
 print "\n\n\n Dats all folks";