zoukankan      html  css  js  c++  java
  • BroadCast

    package com.bjsxt.spark.others;

    import java.util.Arrays;
    import java.util.List;

    import org.apache.spark.SparkConf;
    import org.apache.spark.api.java.JavaRDD;
    import org.apache.spark.api.java.JavaSparkContext;
    import org.apache.spark.api.java.function.Function;
    import org.apache.spark.api.java.function.VoidFunction;
    import org.apache.spark.broadcast.Broadcast;
    /**
    * 广播变量:
    * 1.不能将一个RDD使用广播变量广播出去,因为RDD是不存数据的,可以将RDD的结果广播出去。
    * 2.广播变量只能在Driver端定义,不能在Executor端定义。
    * 3.在Driver端可以修改广播变量的值,在Executor端不能修改广播变量的值。
    *
    * @author root
    *
    */

    public class BroadCast {
    public static void main(String[] args) {
    SparkConf conf = new SparkConf();
    conf.setMaster("local").setAppName("broadcast");
    JavaSparkContext sc = new JavaSparkContext(conf);

    List<String> list = Arrays.asList("hello bjsxt");
    //广播变量将list广播出去
    final Broadcast<List<String>> broadCastList = sc.broadcast(list);

    JavaRDD<String> lines = sc.textFile("./words.txt");
    JavaRDD<String> result = lines.filter(new Function<String, Boolean>() {

    /**
    *
    */
    private static final long serialVersionUID = 1L;

    @Override
    public Boolean call(String s) throws Exception {
    return broadCastList.value().contains(s);
    }
    });
    result.foreach(new VoidFunction<String>() {

    /**
    *
    */
    private static final long serialVersionUID = 1L;

    @Override
    public void call(String t) throws Exception {
    System.out.println(t);
    }
    });

    sc.close();

    }
    }

  • 相关阅读:
    汽车知识图谱
    医疗知识图谱与自动问答
    MongoDB(单节点)环境配置
    【字符串-01】
    【双指针-01】
    【排序-01】十大排序算法(Python实现)
    【队列-01】队列题目解析
    【栈-01】栈题目解析
    【贪心-02】贪心算法题目解析
    【贪心-01】贪心算法原理介绍
  • 原文地址:https://www.cnblogs.com/huiandong/p/9194601.html
Copyright © 2011-2022 走看看