gistfile1.rb

#!/usr/bin/env ruby
BEGIN {$VERBOSE = true} # enable warnings (-w)

class MusicHash < Hash
  def initialize(file)
    parse_file file
  end

  private
    def parse_file(file)
      File.open(file) do |f|
        f.each_line do |l|
          (md5, name) = l.match(/^([\w]+)\s+(.*)$/).captures
          self[md5] = name
        end
      end
    end
end

unsorted = MusicHash.new('unsorted_md5s')
sorted   = MusicHash.new('sorted_md5s')

duplicate_count = 0

unsorted.each do |md5, file|
  if sorted.has_key? md5
    puts "#{file} is a duplicate"
    duplicate_count += 1
  end
end

puts "Found #{duplicate_count} duplicates out of #{unsorted.size} files."