use warnings;
use strict;
use File::Basename;
my $name = basename($0);
my $usage = "\nUsage (OSX Terminal/Windows Cmd-Prompt): perl <$name> <.FASTA or.FA File> <Results Directory>\n\n";

#Scanning for restriction sites and length-output
my $infile1 = shift or die $usage;
open(my $in, "<", shift);
open(my $out, ">", shift);

my $DNA = read_fasta($in);

my $len = length($$DNA);
print "\n FASTA/Sequence Length is: $len bp \n";

my @pats=qw( GATCR GGCC );

for (@pats) {
  s/K/[GT]/g;
  s/M/[AC]/g;
  s/Y/[CT]/g;
  s/S/[CG]/g;
  s/W/[AT]/g;
  s/B/[CGT]/g;
  s/V/[ACG]/g;
  s/H/[ACT]/g;
  s/D/[AGT]/g;
  s/X/[AGCT]/g;
  s/R/[AG]/g;
  s/N/[AGCT]/g;
  
}

for (@pats) {
    my $m = () = $$DNA =~ /$_/gi;
    print "\n Total DNA matches to $_ are: $m \n";
}

my $pat=join("|",@pats);
my @cutarr = split(/$pat/, $$DNA);

for (@cutarr) {
    my $len = length($_);
    print $out "$len \n";
}
close($out);
close($in);

#Subfunction - Reading formatted FASTA/FA files
sub read_fasta {
    my ($in) = @_;
    my $sequence = "";

    while(<$in>) {
        my $line = $_;
        chomp($line);
        if($line =~ /^>/){ next }
        else { $sequence .= $line }
    }
    return(\$sequence);
}