#!/usr/bin/perl

use strict;
use warnings;

use List::Util qw(sum);
use Data::Dumper;

my $MAXLEN = 8;

my @data;
my $words_processed = 0;

while (<>) {
    s/[%\s]+//g;

    my $len = length;
    next unless 1 <= $len && $len <= $MAXLEN;

    ++$words_processed;

    my @a = sort split //, lc;
    my $w = join "", @a;
    ++$data[$len - 1]{$w}{count};
    $data[$len - 1]{$w}{contrib}{$w} = 1;
    $data[$len - 1]{$w}{alphas} ||= \@a;
}

print "Done processing dict ($words_processed words). Candidate counts, by number of letters:\n";
print Dumper [map { $_ ? scalar(keys %$_) : 0 } @data];

for my $c (1 .. $MAXLEN - 1) {
    my $data1 = $data[$c - 1];
    my $data2 = $data[$c];
    next unless $data1 && $data2;

    for my $v1 (values %$data1) {
        for my $extra ("a" .. "z") {
            my $new = join "", sort(@{ $v1->{alphas} }, $extra);

            if ($data2->{$new}) {
                $data2->{$new}{contrib}{$_} = 1
                  for keys %{ $v1->{contrib} };
            }
        }
    }
}

my $data_max = $data[$MAXLEN - 1];
for my $v (values %$data_max) {
    $v->{total} = sum(map $data[length($_) - 1]{$_}{count}, keys %{ $v->{contrib} });
}

print "\nDone computation. Result (most words at bottom):\n";

for my $w (sort { $data_max->{$a}{total} <=> $data_max->{$b}{total} } keys %$data_max) {
    print "$w : $data_max->{$w}{total}\n";
}