dupes.rb

#!/usr/bin/env ruby

require 'digest/md5'
require 'find'

@hashfun = Digest::MD5.new
@digests = {}

def digest filename
	@hashfun.hexdigest File.read(filename)
end

def checkdup base, filename
	hash = digest filename
	filename.sub! base, '' if filename.index(base) == 0
	if @digests.has_key? hash
		old = @digests[hash].first
		old += " (plus #{@digests[hash].size - 1} others)" if @digests[hash].size > 1
		puts "#{filename} and #{old} are duplicates."
		@digests[hash] << filename
	else
		@digests[hash] = [filename]
	end
end

bases = ARGV
if bases.empty?
	print "Enter dir name to search: "
	bases << gets.chomp
end

one_base = bases.size == 1
bases.each do |base|
	Find.find base do |path|
		checkdup( (one_base ? base : ''), path) unless File.directory? path
	end
end