#!/usr/bin/perl
use strict;
use warnings;

my $microsats = $ARGV[0];
my $orths = $ARGV[1];
open (MIC,"<$microsats") or die "Cannot open file $microsats: $!";
open (ORTHS,">$orths") or die "Cannot open file $orths: $!";

my %starthash=();
my %preused = ();

my $startcord = 5;
my $endcord = 7;
# example of input line:
# "NA1182988952620.b.scf 	dinucleotide	AG	555	65	6000	:	6002	a-g"

while (my $line = <MIC>){
	chomp $line;
	my @fields = split(/\t/,$line);
	push @{$starthash{$fields[$startcord]}} , $line;
}

while (my $line = <MIC>){
	chomp $line;
	next if exists $preused{$line};
	$preused{$line} = 1;
	my @fields = split(/\t/,$line);
	my @finalstatement = ();
	push @finalstatement, $line;
	
	my $searchstart = $fields[$startcord]-1;
	my $searchend = $fields[$endcord]+1;
	
	my $printer =0;
	$printer = 1 if $searchstart <= 1297 && 1297 <= $searchend; # turning $printer on at a line that is having the stated problem
	
	for (my $i = $searchstart; $i<= $searchend; $i++){
	
		if (exists $starthash{$i}){
			my @orthologous = @{$starthash{$i}};
			delete $starthash{$i}; 			
	
			foreach my $single (@orthologous){
				next if exists $preused{$single};
				$preused{$single} = 1;
				push @finalstatement, $single;
				my @sields = split("\t",$single);
				$searchend = $sields[$endcord] + 1 if ($sields[$endcord] + 1) > $searchend;
				$i = $sields[$startcord] - 2 if ($sields[$startcord] - 1) < $searchstart;
				$searchstart = $sields[$startcord] - 1 if ($sields[$startcord] - 1) < $searchstart;
			}
						
		}
	}
	my $final = join("\t", @finalstatement)."\n";
	print ORTHS $final;
}