Words

#!/usr/bin/ruby
require 'open-uri'
words = open('http://history.eserver.org/soviet-diary.txt').read
  .scan(/(?:[a-zA-Z]+(?:['-][a-zA-Z]+)*|[A-Z]\.(?:[A-Z]\.)*)/).lazy
  .map(&:downcase).with_object({}) {|e, h| h[e] ||= 0; h[e] += 1}
  .to_a.sort_by {|(w, c)| [c, w]}.reverse
top10 = words.take 10
rest = words.drop 10
top10.each {|(w, c)| puts "#{w}: #{c}"}
puts "Rest: #{rest.size} words"