Explorations in Go: A dupe checker in Go and Ruby #2

bm-go

➜  dupe git:(master) time ./dupe ~      
Total duped files found: 49432
./dupe ~  6.73s user 16.67s system 77% cpu 30.309 total
➜  dupe git:(master) time ./dupe ~
Total duped files found: 49432
./dupe ~  6.74s user 16.95s system 77% cpu 30.564 total
➜  dupe git:(master) time ./dupe ~
Total duped files found: 49432
./dupe ~  6.70s user 16.85s system 77% cpu 30.423 total

bm-ruby

➜  dupe git:(master) time ruby dupe.rb ~
Total duped files found: 49326
ruby dupe.rb ~  10.70s user 20.32s system 81% cpu 38.042 total
➜  dupe git:(master) time ruby dupe.rb ~
Total duped files found: 49326
ruby dupe.rb ~  10.69s user 20.34s system 80% cpu 38.660 total
➜  dupe git:(master) time ruby dupe.rb ~
Total duped files found: 49326
ruby dupe.rb ~  10.86s user 21.47s system 74% cpu 43.27

bm-summary

Go: 30.432 sec
Ruby: 39.991 sec

print-results-2.rb

@full_paths_by_filename.select! { |filename, fullpaths| fullpaths.length >= 2 }

print-results.go

func PrintResults() {
  dupes := 0
  for key, value := range fullPathsByFilename {
    if (len(value) < 2) {
      continue
    }
    dupes++
    if (*verbose) {
      println(key, ":")
      for _, filename := range value {
        println("  ", filename)
        fmt.Printf("    %x\n", MD5OfFile(filename))
      }
    }
  }
  println("Total duped files found:", dupes)
}

print-results.rb

def print_results
  @full_paths_by_filename.select! { |filename, fullpaths| fullpaths.length >= 2 }
  if (VERBOSE)
    @full_paths_by_filename.each do |filename, fullpaths|
      puts "#{filename}:"
      for path in fullpaths do
        puts "  #{path}"
        puts "    #{md5_of_file(path)}"
      end
    end
  end
  puts "Total duped files found: #{@full_paths_by_filename.length}"
end