#! C:/Perl/bin
use strict;
use warnings;
use File::Path;

# This script processes a fasta file containing DNA sequences

# Part 1: declare variables, constants, ...

# forward (F) barcodes

my @forward = ("AGCCTAAGCT",
               "TCAAGTTAGC",
               "AGCCTGGCAT",
               "ACGGTCCATG",
               "ACTTGCCGAT",
               "ACGGTGGATC",
               "ATCCGCCTAG",
               "ATGGCGGTAC");

# reverse (R) barcodes

my @reverse = ("AGCTTAGGCT",
               "TAGCCTAAGC",
               "AGCTTGCCAT",
               "ACGTTCAATG",
               "ACTGGCGGAT",
               "ACGTTGAATC",
               "ATCGGCAAGT",
               "ATGCCGTTAC");

# primers used for Variable Region 1 (V1) and Variable Region 3 (V3) of 16S rRNA
# forward primer (V1 region)
my $V1 = 'AGAGTTTGATCCTGGCTCAG';

# reverse primer (V3 region)
my $V3 = 'GTATTACCGCGGCTGCTGGCA';


# locate the import-file with data
my $input_file = "C:/../input.txt";

# concatenate primer to bar codes:
my @processed = map { $_ . $V1 } @forwards;

# construct a regex to search for
my $search_for = join '|', @processed;
# compile it:
$search_for = qr{$search_for};


open my $FASTA_IN, '<', $input_file or die $!;
open my $MATCHED_OUT, '>', 'matched.txt' or die $!
open my $NOT_MATCHED_OUT, '>', 'notmatched.txt' or die $'

# don't read all the data at once,
# rather process it line by line

while (my $line = <$FASTA_IN>) {
    if ($line =~ $search_for) {
        print $MATCHED_OUT $line;
    } else {
        print $NOT_MATCHED_OUT $line;
    }
}

close $FASTA_IN;
close $MATCHED_OUT;
close $NOT_MATCHED_OUT;