# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
# Copyright:: Copyright (c) 2005 Lucas Carlson
# License::   LGPL

module Classifier

module WordHash  
  def without_punctuation
    tr( ',?.!;:\'"@#$%^&*()_=+[]{}\|<>/`~', " " )
  end
  
	def word_hash
		d = Hash.new
		corpus = without_punctuation
		(corpus.split + gsub(/[\w]/,"").split).each do |word|
			key = word.downcase.stem.intern
			d[key] ||= 0
			d[key] += 1
		end
		return d
	end
end

end