Duplicates finder

dup_finder.rb

require 'digest/md5'

hash = {}
dirname = "files"

Dir.glob("#{dirname}/**/*", File::FNM_DOTMATCH).each do |filename|
  next if File.directory?(filename)
  # puts 'Checking ' + filename

  key = Digest::MD5.hexdigest(IO.read(filename)).to_sym
  if hash.has_key? key
    # puts "same file #{filename}"
    hash[key].push filename
  else
    hash[key] = [filename]
  end
end

hash.each_value do |filename_array|
  if filename_array.length > 1
    puts "=== Identical Files ===\n"
    sorted_by_date = filename_array.sort_by {|filename| File.mtime(filename) }
    puts "Original: #{sorted_by_date.first}"
    puts "Copies:"

    sorted_by_date[1..-1].each do |filename|
      puts "\t" + filename
    end
  end
end