use strict;
use warnings;

die "Arguments = in, out, temp dir, sort max in MB.\n"
    if $#ARGV != 3;

my ($in, $out, $temp, $max) = @ARGV;

die "$in does not exist.\n"
    if !-e $in;
die "Can't open $in for read.\n"
    if !open(FH, $in);

die "$temp does not exist, or is not a directory."
    if !-d $temp;
$temp =~ s|/$||;

$max *= 1024 * 1024;

my (@b1, $size, $n, @t, $t1, $t2);

$size = 0; $n = 0;
while (<FH>) {
    push @b1, $_;
    $size += length $_;
    if ($size >= $max) {
        ### Over limit, write chunk
        writeTemp();
        @b1 = ();
        $size = 0;
    }
}
### Write whatever's left in buffer
writeTemp() if $#b1 != -1;

### Using this so I don't have to write it twice in the code
sub writeTemp {
    $n++;
    die "Unable to open $temp/$n.txt for write.\n"
        if !open (FHO, ">$temp/$n.txt");
    @b1 = sort @b1;
    print FHO join('', @b1);
    print "$in => $temp/$n.txt ($size)\n";
}

@t = (1..$n);
while ($#t > 0) {
    $t1 = shift @t;
    $t2 = shift @t;
    $n++;
    mergeFiles("$temp/$t1.txt", "$temp/$t2.txt", "$temp/$n.txt");
    print "$temp/$t1.txt + $temp/$t2.txt => $temp/$n.txt\n";
    unlink "$temp/$t1.txt";
    unlink "$temp/$t2.txt";
    push @t, $n;
}
`mv $temp/$n.txt $out`;
print "$temp/$n.txt => $out\n";

sub mergeFiles {
    my ($f1, $f2, $fo) = @_;
    
    die "Unable to open $f1 for read."
        if !open(FH1, $f1);
    die "Unable to open $f2 for read."
        if !open(FH2, $f2);
    die "Unable to open $fo for write."
        if !open(FHO, ">$fo");

    my $l1 = <FH1>;
    my $l2 = <FH2>;

    while ($l1 && $l2) {
        if ($l1 lt $l2) {
            print FHO $l1;
            $l1 = <FH1>;
        }
        else {
            print FHO $l2;
            $l2 = <FH2>;
        }
    }

    local $/ = undef;

    if ($l1) {
        print FHO $l1;
        $l1 = <FH1>;
        print FHO $l1 if $l1;
        
    }
    else {
        print FHO $l2;
        $l2 = <FH2>;
        print FHO $l2 if $l2;
    }
}