共享变量 BroadcastVariable 实例

2019独角兽企业重金招聘Python工程师标准>>>

package cn.hhb.spark.core;

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;

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

/**
 * Created by dell on 2017/7/13.
 */
public class BroadcastVariable {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf()
                .setAppName("BroadcastVariable")
                .setMaster("local")
                .set("spark.testing.memory", "2147480000");

        JavaSparkContext sc = new JavaSparkContext(conf);

        /**
         * 在java中，创建共享变量，就是调用SparkContext的broadcast方法
         * 获取的返回结果Broadcast<Integer>类型
         */
        final int factor = 3;
        final Broadcast<Integer> factorBroadcast = sc.broadcast(factor);

        List<Integer> numberList = Arrays.asList(1,2,3,4,5);
        JavaRDD<Integer> number = sc.parallelize(numberList);

        // 让集合中的每个数字，都乘以外部定义的那个factor
        JavaRDD<Integer> multipleNumbers = number.map(new Function<Integer, Integer>() {
            @Override
            public Integer call(Integer number) throws Exception {
                // 使用共享变量时，调用其value()，即可获取其内部共享的值
                int factor = factorBroadcast.value();
                return number * factor;
            }
        });

        multipleNumbers.foreach(new VoidFunction<Integer>() {
            @Override
            public void call(Integer integer) throws Exception {
                System.out.println(integer);
            }
        });


        sc.close();
    }
}

转载于:https://my.oschina.net/hehongbo/blog/1486268