#!/usr/bin/env perl

use strict;
use warnings;
use autodie;
use constant {
    GENE_FILE    => 'pm_1192233_genes.txt',
    MISSING_FILE => 'pm_1192233_missing.txt',
    OUT_PREFIX   => 'pm_1192233_out_',
};

my @ano_files = @ARGV;

my ($gene_list, $gene_re) = get_gene_data(GENE_FILE);

for my $ano_file (@ano_files) {
    open my $fh, '<', $ano_file;
    while (<$fh>) {
        print { get_out_fh($1) } $_ if /$gene_re/;
    }
}

gen_missing_report($gene_list);

{
    my %fh_for;

    sub get_out_fh {
        unless (exists $fh_for{$_[0]}) {
            open $fh_for{$_[0]}, '>', OUT_PREFIX . $_[0];
        }
        return $fh_for{$_[0]};
    }

    sub gen_missing_report {
        my ($genes) = @_;
        open my $fh, '>', MISSING_FILE;
        print $fh "--- START MISSING LIST ---\n";
        print $fh "$_\n" for grep { ! exists $fh_for{$_} } @$genes;
        print $fh "--- END MISSING LIST ---\n";
    } 
} 

sub get_gene_data {
    my ($file) = @_;
    my @list;
    open my $fh, '<', $file;
    push @list, $_ while <$fh>;
    chomp @list;
    @list = sort { length $b <=> length $a } @list;
    my $alt = join '|', @list;
    return (\@list, qr{($alt)});
}