#!/usr/bin/perl
use warnings; # Perl interpreter command
use strict;


my %bow1 = ();
my $file1 = shift;
open (FILE1, "$file1")|| die "Failed to open $file1 for reading : $!"; # Open first file

while (<FILE1>) { # Reading first hash
	my ($ID, undef, undef, undef, $Seq) = split;
	$bow1{$ID}[0] = $ID;
	$bow1{$ID}[1] = $Seq;
}
close FILE1 || die "Failed to close $file1 : $!";


my %bow2 = ();
my $file2 = shift;

open (FILE2, "$file2") || die "Failed to open $file2 for reading : $!"; # Open first file

while (<FILE2>) { # Reading second hash
    my ($ID, undef, undef, undef, $Seq) = split;
	$bow2{$ID}[0] = $ID;
	$bow2{$ID}[1] = $Seq;
}
close FILE2 || die "Failed to close $file2 : $!";


print"Match status\t$file1 ID\t$file1 Sequence\t$file2 ID\t$file2 Sequence\n"; # Print title

my $totalCount=0; #initialize variables for counting
my $identical=0;
my $diffSeq=0;
my $unique=0;

foreach my $ID (keys %bow1){ # can use (sort keys %hash) to put items in a specified order
   if (exists $bow2{$ID}[0] ){
      if ( $bow1{$ID}[0] eq $bow2{$ID}[0] ){
         ## id and sequence are stored as key value pairs
		  if ( $bow1{$ID}[1] eq $bow2{$ID}[1] ){
         #print "Identical\t$bow1{$ID}[0]\t$bow1{$ID}[1]\t$bow2{$ID}[0]\t$bow2{$ID}[1]\n"; #display ID and sequences  -->too many: commented out
		 $identical=$identical+1; #count identical pairs
		 }
		 else{
		print "SameID, DiffSeq\t$bow1{$ID}[0]\t$bow1{$ID}[1]\t$bow2{$ID}[0]\t$bow2{$ID}[1]\n"; #display ID and sequences
		$diffSeq=$diffSeq+1; #count pairs with different sequences but identical IDs
		}
      }
	}
	else {
	print "Unique\t$bow1{$ID}[0]\t$bow1{$ID}[1]\t - \t - \n"; #display ID and sequences
	$unique=$unique+1; #count unique IDs from first file
	}
}
$totalCount = $identical + $diffSeq + $unique; #total count - should match with total ID in first file
print "Identical\tSeq is different\tUnique in $file1\tTotal\n"; #print title
print "$identical\t$diffSeq\t$unique\t$totalCount\n"; #print numbers

exit;