java实现spark常用算子之intersection

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.VoidFunction;

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

/**
 * intersection 算子：
 * 将两个RDD求交集
 * 然后去重
 */
public class IntersectionOperator {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setMaster("local").setAppName("intersection");
        JavaSparkContext sc = new JavaSparkContext(conf);
        List<String> list1 = Arrays.asList("w1","w2","w3");
        JavaRDD<String> listRdd = sc.parallelize(list1);
        List<String> list2 = Arrays.asList("w2","w3","w4");
        JavaRDD<String> list2Rdd = sc.parallelize(list2);

        listRdd.intersection(list2Rdd).foreach(new VoidFunction<String>() {
            @Override
            public void call(String s) throws Exception {
                System.err.println(s);
            }
        });

    }
}

微信扫描下图二维码加入博主知识星球,获取更多大数据、人工智能、算法等免费学习资料哦！