#!/usr/bin/perl
use warnings;
use strict;

my %stops;
my %terms;

open (FILE, $ARGV[0]);
while (<FILE>) {
    chomp;
    $stops{$_} = 1;
}

open (FILE, $ARGV[1]);
while (<FILE>) {
    chomp;
    $terms{$_} = 1;
}

open (FILE, $ARGV[2]);
while (<FILE>) {
    chomp;

#Starting with the longest term from ARGV[1], then going to the next largest, and so on, if the term also exists in ARGV[2], surround it by *, print the term, and remove the term from further processing. 

#after that, remove the stop words from the remainder of the file that didn't match a string in [ARGV[1]
    
    $_ =~ tr/A-Z/a-z/;
    my @words = split ('[^a-z0-9]', $_);
    for my $word (@words) {
	unless ($stops{$word}++){
	    print "$word\n" 
	}
    }
}