Scala学习笔记（8）—— Actor版 wordcount

1 数据

2 源码

package wc

import scala.actors.{Actor, Future}
import scala.collection.mutable
import scala.collection.mutable.ListBuffer
import scala.io.Source

class Task extends Actor {
  override def act(): Unit = {
    loop {
      //偏函数
      react {  // react 可以复用线程池
        case SubmitTask(filename) => {
          val result = Source.fromFile(filename).getLines().flatMap(_.split(" "))
            .map((_, 1)).toList.groupBy(_._1).mapValues(_.size)
          sender ! ResultTask(result)
        }
        case StopTask => {
          exit()
        }
      }
    }
  }
}

case class SubmitTask(filename: String)

case class ResultTask(result: Map[String, Int])

case object StopTask


object ActorWordCount {
  def main(args: Array[String]): Unit = {

    //存储异步返回的 future
    val replySet = new mutable.HashSet[Future[Any]]()

    //存储 map 返回的值
    val resultList = new ListBuffer[ResultTask]()

    val files = Array[String]("d://words1.txt", "d://words2.txt")
    for (file <- files) {
      /*
      * 创建消息对象，且异步发送消息
      * 每次启动发送一个异步消息并返回一个 Future, 同 java 的 Callable
      * */
      val actor = new Task
      //actor.start() !! SubmitTask(file)
      actor.start()

      //发送异步消息返回 Future
      val reply = actor !! SubmitTask(file)

      // 放到 HashSet
      replySet += reply
    }

    // reduce 阶段
    while (replySet.size > 0) {
      //取出已经计算好的异步结果， isSet 类似于 Callable 的 isDone,返回 boolean
      val toCompute = replySet.filter(_.isSet)

      for (f <- toCompute) {

        /*
        * apply() 相当于 Callable 的 get(),强转为 ResultTask
        * */
        val result = f.apply().asInstanceOf[ResultTask]

        //返回的 map 放到 list
        resultList += result

        //移除futures 处理过的对象
        replySet -= f
      }
      // 如果文件很大，设置睡眠时间，否则浪费CPU
      Thread.sleep(100)
    }

    /*
    * 对上面处理好的 map 结果进行统计
    * 这里的数据只是打比方
    * resultList{
    *   Map(hello -> 1, tom -> 2,jerry -> 4),
    *   Map(hello -> 4,jerry -> 2)
    * }
    *
    * */

    val fr = resultList.flatMap(_.result).groupBy(_._1).mapValues(_.foldLeft(0)(_ + _._2))
    println(fr)


  }
}

Map(henny -> 1, jack -> 1, tom -> 3, pick -> 1, hello -> 10, jerry -> 4)

3 局部分析

scala> import scala.io.Source
import scala.io.Source

scala> Source.fromFile("d://words1.txt")
res1: scala.io.BufferedSource = non-empty iterator

scala> Source.fromFile("d://words1.txt").getLines()
res2: Iterator[String] = non-empty iterator

scala> Source.fromFile("d://words1.txt").getLines().flatMap(_.split(" "))
res5: Iterator[String] = non-empty iterator

scala> Source.fromFile("d://words1.txt").getLines().flatMap(_.split(" ")).map((_,1))
res6: Iterator[(String, Int)] = non-empty iterator

scala> Source.fromFile("d://words1.txt").getLines().flatMap(_.split(" ")).map((_,1)).toList
res7: List[(String, Int)] = List((hello,1), (tom,1), (hello,1), (jerry,1), (hello,1), (henny,1), (hello,1), (tom,1))

scala> Source.fromFile("d://words1.txt").getLines().flatMap(_.split(" ")).map((_,1)).toList.groupBy(_._1)
res8: scala.collection.immutable.Map[String,List[(String, Int)]] = 
Map(henny -> List((henny,1)), 
tom -> List((tom,1), (tom,1)), jerry -> List((jerry,1)), 
hello -> List((hello,1), (hello,1), (hello,1), (hello,1)))

scala> Source.fromFile("d://words1.txt").getLines().flatMap(_.split(" ")).map((_,1)).toList.groupBy(_._1).mapValues(_.size)
res9: scala.collection.immutable.Map[String,Int] = 
Map(henny -> 1, tom -> 2, jerry -> 1, hello -> 4)