Remove all file duplicates in a directory, based on file content

remove-duplicates.rb

#!/usr/bin/ruby

require 'digest'
require 'fileutils'

entries = Dir.entries('.').select { |x| File.file? x }
hashes  = {}

entries.each do |entry|
  hash = Digest::MD5.file(entry).to_s
  if hashes[hash]
    puts "Removing #{entry} (duplicate of #{hashes[hash]})"
    FileUtils.rm entry
  else
    hashes[hash] = entry
  end
end