#!/usr/bin/perl 
use strict;
use warnings;
use Text::Levenshtein qw/fastdistance/;
use Data::Dumper;

my $classes = [];
my $index   = {};
my $limit   = 0.5;

sub avg_distance {
	my ($new_word, $class) = @_;
	my $distance = 0;
	for my $word (@$class) {
		$distance += fastdistance($new_word, $word);
	}
	return $distance / @$class;
}

sub put_or_create {
	my ($w) = @_;
	$w =~ s/[^a-z]//g;
	my $found=0;
	return if exists $index->{$w};
	foreach my $class ( @$classes ) {
		if((avg_distance($w,$class)/length($w)) < $limit) {
			push @$class, $w;
			$index->{$w} = $class;
			$found = 1;
			last;
		};
	};
	if(! $found) {
		my $class = [$w];
		push @$classes, $class;
		$index->{$w} = $class;
	};
};



#watch for an error opening the file
open( my $file,"<", "possible_locations.txt") or die "Failed to open file: $!";
my @locations = <$file>;
#remove the line endings
chomp(@locations);

my $count = 0;
for (@locations) {
	#last if ++$count/@locations > 0.2;#not all
	put_or_create($_)
}

for (@$classes) {
	print join(",", sort @$_), "\n";
}