ruby和pig处理流式文件实例

define tracking_parser `/usr/ruby parse_click.rb --map` SHIP('parse_click.rb', 'click_tracking.rb');

strmo = stream log through tra_parser;

store strmo into '$OUTFILE' using PigStorage('\t');

module ParseClick
  class Mapper < Wukong::Streamer::RecordStreamer
    def before_stream
      @bad_count = 0
    end

    def after_stream
      raise RuntimeError, "Exceeded bad records : #{@bad_count}" if @bad_count > 10
    end

    def process *records
      yield ClickTra.new(JSON.parse(records[2])).to_a
    rescue => e
      @bad_count += 1
      warn "Bad record #{e}: #{records[2]}"
    end
  end
end

Wukong.run ParseClick::Mapper, nil

class ClickTra
 
  output :ip
  output :c_date
  #output your other atrributes

  def c_date
    click_date.strftime("%Y%m%d").to_i
  end 

  def ip
    browser_ip.to_i
  end

end