scala> val broadcastVar = sc.broadcast(Array(1, 2, 3))
broadcastVar: org.apache.spark.broadcast.Broadcast[Array[Int]] = Broadcast(0)
scala> broadcastVar.value
res0: Array[Int] = Array(1, 2, 3)

scala> val accum = sc.accumulator(0, "My Accumulator")
accum: spark.Accumulator[Int] = 0
scala> sc.parallelize(Array(1, 2, 3, 4)).foreach(x => accum += x)
...
10/09/29 18:41:08 INFO SparkContext: Tasks finished in 0.317106 s
scala> accum.value
res2: Int = 10

object VectorAccumulatorParam extends AccumulatorParam[Vector] {
 def zero(initialValue: Vector): Vector = {
  Vector.zeros(initialValue.size)
 }
 def addInPlace(v1: Vector, v2: Vector): Vector = {
  v1 += v2
 }
}
// Then, create an Accumulator of this type:
val vecAccum = sc.accumulator(new Vector(...))(VectorAccumulatorParam)

val accum = sc.accumulator(0)
data.map { x => accum += x; f(x) }
//在這里,accum的值仍然是0，因?yàn)闆](méi)有動(dòng)作操作引起map被實(shí)際的計(jì)算.

/**
 * 實(shí)例：利用廣播進(jìn)行黑名單過(guò)濾！
 * 檢查新的數(shù)據(jù) 根據(jù)是否在廣播變量-黑名單內(nèi)，從而實(shí)現(xiàn)過(guò)濾數(shù)據(jù)。
 */
public class BroadcastAccumulator {
 /**
  * 創(chuàng)建一個(gè)List的廣播變量
  *
  */
 private static volatile Broadcast<List<String>> broadcastList = null;
 /**
  * 計(jì)數(shù)器！
  */
 private static volatile Accumulator<Integer> accumulator = null;
 public static void main(String[] args) {
  SparkConf conf = new SparkConf().setMaster("local[2]").
    setAppName("WordCountOnlineBroadcast");
  JavaStreamingContext jsc = new JavaStreamingContext(conf, Durations.seconds(5));

  /**
   * 注意：分發(fā)廣播需要一個(gè)action操作觸發(fā)。
   * 注意：廣播的是Arrays的asList 而非對(duì)象的引用。廣播Array數(shù)組的對(duì)象引用會(huì)出錯(cuò)。
   * 使用broadcast廣播黑名單到每個(gè)Executor中！
   */
  broadcastList = jsc.sc().broadcast(Arrays.asList("Hadoop","Mahout","Hive"));
  /**
   * 累加器作為全局計(jì)數(shù)器！用于統(tǒng)計(jì)在線過(guò)濾了多少個(gè)黑名單！
   * 在這里實(shí)例化。
   */
  accumulator = jsc.sparkContext().accumulator(0,"OnlineBlackListCounter");

  JavaReceiverInputDStream<String> lines = jsc.socketTextStream("Master", 9999);

  /**
   * 這里省去flatmap因?yàn)槊麊问且粋€(gè)個(gè)的！
   */
  JavaPairDStream<String, Integer> pairs = lines.mapToPair(new PairFunction<String, String, Integer>() {
   @Override
   public Tuple2<String, Integer> call(String word) {
    return new Tuple2<String, Integer>(word, 1);
   }
  });
  JavaPairDStream<String, Integer> wordsCount = pairs.reduceByKey(new Function2<Integer, Integer, Integer>() {
   @Override
   public Integer call(Integer v1, Integer v2) {
    return v1 + v2;
   }
  });
  /**
   * Funtion里面 前幾個(gè)參數(shù)是 入?yún)ⅰ?
   * 后面的出參。
   * 體現(xiàn)在call方法里面！
   *
   */
  wordsCount.foreach(new Function2<JavaPairRDD<String, Integer>, Time, Void>() {
   @Override
   public Void call(JavaPairRDD<String, Integer> rdd, Time time) throws Exception {
    rdd.filter(new Function<Tuple2<String, Integer>, Boolean>() {
     @Override
     public Boolean call(Tuple2<String, Integer> wordPair) throws Exception {
      if (broadcastList.value().contains(wordPair._1)) {
       /**
        * accumulator不僅僅用來(lái)計(jì)數(shù)。
        * 可以同時(shí)寫進(jìn)數(shù)據(jù)庫(kù)或者緩存中。
        */
       accumulator.add(wordPair._2);
       return false;
      }else {
       return true;
      }
     };
     /**
      * 廣播和計(jì)數(shù)器的執(zhí)行，需要進(jìn)行一個(gè)action操作！
      */
    }).collect();
    System.out.println("廣播器里面的值"+broadcastList.value());
    System.out.println("計(jì)時(shí)器里面的值"+accumulator.value());
    return null;
   }
  });

  jsc.start();
  jsc.awaitTermination();
  jsc.close();
 }
 }

package com.Streaming
import java.util
import org.apache.spark.streaming.{Duration, StreamingContext}
import org.apache.spark.{Accumulable, Accumulator, SparkContext, SparkConf}
import org.apache.spark.broadcast.Broadcast
/**
 * Created by lxh on 2016/6/30.
 */
object BroadcastAccumulatorStreaming {
 /**
 * 聲明一個(gè)廣播和累加器！
 */
 private var broadcastList:Broadcast[List[String]] = _
 private var accumulator:Accumulator[Int] = _
 def main(args: Array[String]) {
 val sparkConf = new SparkConf().setMaster("local[4]").setAppName("broadcasttest")
 val sc = new SparkContext(sparkConf)
 /**
  * duration是ms
  */
 val ssc = new StreamingContext(sc,Duration(2000))
 // broadcastList = ssc.sparkContext.broadcast(util.Arrays.asList("Hadoop","Spark"))
 broadcastList = ssc.sparkContext.broadcast(List("Hadoop","Spark"))
 accumulator= ssc.sparkContext.accumulator(0,"broadcasttest")
 /**
  * 獲取數(shù)據(jù)！
  */
 val lines = ssc.socketTextStream("localhost",9999)
 /**
  * 1.flatmap把行分割成詞。
  * 2.map把詞變成tuple(word,1)
  * 3.reducebykey累加value
  * (4.sortBykey排名)
  * 4.進(jìn)行過(guò)濾。 value是否在累加器中。
  * 5.打印顯示。
  */
 val words = lines.flatMap(line => line.split(" "))
 val wordpair = words.map(word => (word,1))
 wordpair.filter(record => {broadcastList.value.contains(record._1)})
 val pair = wordpair.reduceByKey(_+_)
 /**
  * 這個(gè)pair 是PairDStream<String, Integer>
  * 查看這個(gè)id是否在黑名單中，如果是的話，累加器就+1
  */
/* pair.foreachRDD(rdd => {
  rdd.filter(record => {
  if (broadcastList.value.contains(record._1)) {
   accumulator.add(1)
   return true
  } else {
   return false
  }
  })
 })*/
 val filtedpair = pair.filter(record => {
  if (broadcastList.value.contains(record._1)) {
   accumulator.add(record._2)
   true
  } else {
   false
  }
  }).print
 println("累加器的值"+accumulator.value)
 // pair.filter(record => {broadcastList.value.contains(record._1)})
 /* val keypair = pair.map(pair => (pair._2,pair._1))*/
 /**
  * 如果DStream自己沒(méi)有某個(gè)算子操作。就通過(guò)轉(zhuǎn)化transform！
  */
 /* keypair.transform(rdd => {
  rdd.sortByKey(false)//TODO
 })*/
 pair.print()
 ssc.start()
 ssc.awaitTermination()
 }
}