#!/usr/bin/perl

$file1="a";
$file2="b";
$out="test";
$pos=0;
$hsize=0;
merge_file3($file1, $file2, $out, $pos,$hsize );
sub merge_file3{
my ($file1,$file2,$out,$position,$hsize) = ($_[0],$_[1],$_[2],$_[3],$_[4]);
print "merging: \n$file1 and \n$file2, to: \n$out\n";
my $OUTSTRING = undef;
my $header;

my (@file1,@file2);
open FILE1, "<$file1" or die;
while (<FILE1>){
   # if ($.==1){
   #     $header = $_;
   #     next;
   # }
    print "$.\n" if ($.%100000) == 0;
    chomp;
    push @file1, [split '\t', $_];
}
close FILE1;

open FILE2, "<$file2" or die;
while (<FILE2>){
#    next if $.==1;
    print "$.\n" if ($.%100000) == 0;
    chomp;
    push @file2, [split '\t', $_];
}
close FILE2;

print "sorting files\n";
my @sortedf1 = sort {$a->[$position] <=> $b->[$position]} @file1;
my @sortedf2 = sort {$a->[$position] <=> $b->[$position]} @file2;   
print "sorted\n";
@file1 = undef;
@file2 = undef;
#foreach my $line (@file1){print "\t [ @$line ],\n";    }

my ($i,$j) = (0,0);
while ($i < $#sortedf1 and $j < $#sortedf2){
    my $key1 = $sortedf1[$i][$position];
    my $key2 = $sortedf2[$j][$position];
    if ($key1 eq $key2){
        foreach(0..$hsize){ #header size.
            $sortedf2[$j][$_] = $sortedf1[$i][$_] if $sortedf1[$i][$_] ne undef;
        }
        $i++;
        $j++;
    }
    elsif ( $key1 < $key2){
       # push(@sortedf2,[@{$sortedf1[$i]}]);
        $i++;
    }
    elsif ( $key1 > $key2){ 
        $j++;
    }
}

#foreach my $line (@sortedf2){print "\t [ @$line ],\n"; }

print "outputting to file\n";
open OUT, ">$out";
print OUT $header;
print $header;

foreach(@sortedf2){
    print OUT (join "\t", @{$_})."\n";

 print  (join "\t", @{$_})."\n";
}
close OUT;

}