#!user/local/perl
#Created by C. Pells, M. R. Snyder, and N. T. Marshall 2017

#Script trims and merges high throughput sequencing reads from fastq files for a specific primer set

use Cwd;
use warnings;

my $StartTime= localtime;

my $MasterDir = getcwd; #obtains the current directory


opendir (DIR, $MasterDir);
my @objects = readdir (DIR);
closedir (DIR);
foreach (@objects){
    print $_,"\n";
}

my @Dirs = ();
foreach my $O (0..$#objects){
    my $CurrDir = "";
    if ((length ($objects[$O]) < 7) && ($O>1)){ #Checking if the length of the object name is < 7 characters. All samples are 6 or less. removing the first two elements: "." and ".."
        $CurrDir = $MasterDir."/".$objects[$O]; #appends directory name to full path
        push (@Dirs, $CurrDir);
    }
}

foreach (@Dirs){
    print $_,"\n";#checks that all directories were read in
}


foreach my $S (0..$#Dirs){
    my @files = ();
    opendir (DIR, $Dirs[$S]) || die "cannot open $Dirs[$S]: $!";
    @files = readdir DIR; #reads in all files in a directory
    closedir DIR;
    my @AbsFiles = ();
    foreach my $F (0..$#files){
        my $AbsFileName = $Dirs[$S]."/".$files[$F]; #appends file name to full path
        push (@AbsFiles, $AbsFileName);
    }

    foreach my $AF (0..$#AbsFiles){
        if ($AbsFiles[$AF] =~ /_R2_001\.fastq$/m){ #finds reverse fastq file
            my @readbuffer=();
            #read in reverse fastq
            my %RSeqHash;
            my $c = 0;
            print "Reading, reversing, complimenting, and trimming reverse fastq file $AbsFiles[$AF]\n";
            open (INPUT1, $AbsFiles[$AF]) || die "Can't open file: $!\n";
            while (<INPUT1>){
                chomp ($_);
                push(@readbuffer, $_);
                if (@readbuffer == 4) {
                    $rsn = substr($readbuffer[0], 0, 45); #trims reverse seq name
                    $cc++ % 10000 == 0 and print "$rsn\n";
                    $RSeqHash{$rsn} = $readbuffer[1];
                @readbuffer = ();
                }
            }
        }
    }
    foreach my $AFx (0..$#AbsFiles){
        if ($AbsFiles[$AFx] =~ /_R1_001\.fastq$/m){ #finds forward fastq file
            print "Reading forward fastq file $AbsFiles[$AFx]\n";
            open (INPUT2, $AbsFiles[$AFx]) || die "Can't open file: $!\n";
            my $OutMergeName = $Dirs[$S]."/"."Merged.fasta";
            open (OUT, ">", "$OutMergeName");
            my $cc=0;
            my @readbuffer = ();
            while (<INPUT2>){
                chomp ($_);
                push(@readbuffer, $_);
                if (@readbuffer == 4) {
                    my $fsn = substr($readbuffer[0], 0, 45); #trims forward seq name
                    #$cc++ % 10000 == 0 and print "$fsn\n$readbuffer[1]\n";
                    if ( exists($RSeqHash{$fsn}) ){ #checks to see if forward seq name is present in reverse seq hash
                        print "$fsn was found in Reverse Seq Hash\n";
                        print OUT "$fsn\n$readbuffer[1]\n"; #ACUAL OUTPUT FILE IS EMPTY!!!
                    }
                    else {
                        $cc++ % 10000 == 0 and print "$fsn not found in Reverse Seq Hash\n"; #PRINTS THIS FOR EVERY LINE IN INPUT2!!!
                    }
                @readbuffer = ();
                }
            }
            close INPUT1;
            close INPUT2;
            close OUT;
        }
    }
}