aol_query_count.rb

  inputs = args
  spec = Gisting::Spec.new
  inputs.each do |file_input|
    input = spec.add_input
    input.file_pattern = file_input
    input.map do |map_input|
      # 2722	mailbox	2006-05-23 00:08:39
      # 217	-	2006-05-23 15:41:48
      # 1326	www.crazyradiodeals.com	2006-05-23 18:00:30
      # 2722	mailbox	2006-05-23 00:08:39
      # 2722	mailbox	2006-05-23 00:08:42
      # 2722	jc whitney	2006-05-23 00:25:47	1	http://www.jcwhitney.com
      words = map_input.strip.split("\t")
      Emit(words[1], "1")
    end
  end
  output = spec.output
  output.filebase = "/Volumes/gisting/datasets/output"
  output.num_tasks = 2
  output.reduce do |reduce_input|
    count = 0
    reduce_input.each do |value|
      count += value.to_i
    end
    Emit(count)
  end

  result = MapReduce(spec)
  pp result