# https://www.perlmonks.org/?node_id=11110379
# usage: perl search_in_memory.pl > Outfile.txt

use strict;
use warnings;
use KyotoCabinet;
use MCE;

###########################################################
# Part Three
###########################################################

# construct the database object
my $db = KyotoCabinet::DB->new();

# open the database - in memory (i.e. *)
if (! $db->open('*#msiz=128m', $db->OREADER | $db->OWRITER | $db->OCREATE)) {
    die "open error (db): ", $db->error;
}

open my $fh, '<', 'NR.fasta' or die "open error: $!\n";

my $nrid = '';
my $seq  = '';

while ( <$fh> ) {
    chomp; $_ =~ s/\r$//g;
    if ( /^>/ ) {
        $db->set($nrid, $seq) if $seq;
        $nrid = ( split /\s/, $_, 2 )[0];
        $seq  = '';
    }
    else {
        $seq .= $_;
    }
}

$db->set($nrid, $seq) if $seq;

close $fh;

###########################################################
# Part Five
###########################################################

my $cur;

my $mce = MCE->new(
    max_workers => MCE::Util::get_ncpu(),
    chunk_size  => 1,
    init_relay  => 1,

    user_begin => sub {
        $cur = $db->cursor;
    },

    user_end => sub {
        $cur->disable;
    },

    user_func => sub {
        my $pep = $_; chomp $pep;
        my $ids = '';

        $cur->jump; # first record
        while ( my ($key, $val) = $cur->get(1) ) {
            $ids .= ",$key" if index($val, $pep) >= 0;
        }
    
        # output serially, one worker at a time
        MCE::relay {
            print "$pep\t", substr($ids, 1), "\n" if $ids;
        };
    }
);

$mce->process('peptides.txt');
$mce->shutdown;

$db->close;