#!/usr/bin/perl
#This script matches words that are repeated within <num> words and marks them and prints out the original text with repeated words marked.
use strict;
use warnings;
print "Enter the name of the file to check: ";
my $inputfile = <>;
#Define how many words between matching a repeat.
my $numwords = 40;
open(TEXTFILE, $inputfile);
my @importedtextfile = <TEXTFILE>;
close(TEXTFILE);
my $counter = 0;
my @words;
#Split the sentences imported.
foreach (@importedtextfile) {
	my @tempsplit = split(/\s+/,  $_);
	foreach(@tempsplit) {
		push @words, $_;
	}
}
my @filteredlist = @words;
my $wordslength = scalar(@words);
$counter = 0;
foreach(@words) {
	my $i = 0;
	my $currentword = $_;
	$currentword =~ s/[\,\.]//g;
	#Start counting one word "right" of the one you are trying to match.
	my $startposition = $counter + 1;
	#Check <num> words and make sure you don't check empty strings in array.
	while ($i < $numwords and $counter + $i < $wordslength) {
		if ($counter + $i + 1 < $wordslength) {
			my $matchword = $words[$startposition];
			$matchword =~ s/[\,\.]//g;
			#Match and replace in new array.
			if ($currentword =~ /\b$matchword\b/i) {
			$filteredlist[$startposition] = "*".$words[$startposition]."*";
			}
		}
		++$startposition;
		++$i;
	}
	++$counter;
}
my $printedlist = join(" ", @filteredlist);
print "$printedlist\n";