word count from pptx

gistfile1.rb

#!/usr/bin/ruby

require 'zip'
require 'nokogiri'

#Zip::ZipFile.open("sample.pptx").each{ |entry| puts Nokogiri::XML.parse(zip.find_entry(entry.to_s).get_input_stream).text.split(' ').uniq.length if entry.to_s.match(/ppt\/slides\/slide[0-9]+\.xml$/) }

class Pptx

  def self.word_count(file, zip=Zip::ZipFile.open(file), count=nil)
    zip.each{ |entry| count = uniq_words_from entry, input_stream(zip, entry) if is_slide?(entry) }
    count
  end

  def self.input_stream(zip, entry)
    Nokogiri::XML.parse(zip.find_entry(entry.to_s).get_input_stream).text
  end

  def self.uniq_words_from(entry, text)
    text.split(' ').uniq.length if is_slide? entry
  end

  def self.is_slide?(entry)
    entry.to_s.match(/ppt\/slides\/slide[0-9]+\.xml$/)
  end
end

puts Pptx.word_count("sample.pptx")