#!/usr/bin/perl -w
####################
# Arpy Saunders, 10/4/06
#
# read_doubler duplicates the dna found in a single read and formats
# the resulting sequence in fasta format.  Checked 11/9 --> this version works
# to double reads!
#
#

use strict;
use warnings;

################ Declare and initialize variables#################

my $filename = 'repeatextractor_out.txt'; # name of input, dropped reads file
my @all_reads = '';
my $record;
my $read_id;
my $junk; 				# this variable holds useless stuff from a split
my $element;
my $dna;
my $dna_length;
my $crap; 				# this variable holds useless stuff from a split
my $current_window2;
my $query_window2;
my @exact_match = '';
my @reverse_match = '';
my @revcomp_match = '';

##################################################################

# opens the fasta file containing the dropped reads and splits the single scalar
# into an array, where each element is an individual read.  split is done by the
# '>' marker

unless (open(FASTA, $filename)) {
	print "cannot open FASTA file \"$filename\"\n\n";
	exit;
	
}

# set input separator to "//\n" and read in a record to a scalar
$/ = "//\n";

# read the data into the scalar called "$record"
$record = <FASTA>;

#split the scalar "record" into an array, delimited by the "<"

@all_reads = split />/, $record;

###################################################################

### indicates print statements which produce an ongoing graphic as the script runs

# this loop specifies actions to an individual element (read) in the array

 
foreach $element (@all_reads) # takes on one read at a time

{
	if ($element !~ /[A-Z]/)
		{
		next;
		}
		
	 # defining the length of the read

	($read_id, $crap) = split /(^<.*)|(\s)/s, $element; # splits the read
														# id 
	### print "READ_ID:\n$read_id\n\n";
	
	($junk, $dna) = split /\./s, $element;			# pulls out the dna
	
	$dna =~ tr/xy12/ /;
	
	$dna =~ s/\n//g;									# takes out newlines;
	$dna =~ s/\s//g;	
	
	my $dna_double = $dna.$dna;

	print_sequence ($dna_double, 50, $read_id);
}

###################################################
# print_sequence
#
# A subroutine to format and print sequence data 

sub print_sequence {

    my($sequence, $length, $read_id) = @_;

    use strict;
    use warnings;
	
	my $outputfile = 'readdoubler_output.txt';
    unless (open (READDOUBLER_OUT, ">>$outputfile"))
									{
										print "cannot open file \"$outputfile\" to write to!\n\n";
										exit;
									}
									
	print READDOUBLER_OUT ">$read_id\n";
	
    # Print sequence in lines of $length
    for ( my $pos = 0 ; $pos < length($sequence) ; $pos += $length ) {
       print READDOUBLER_OUT substr($sequence, $pos, $length), "\n";
    }
}