Spark join demo

package spark;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.Optional;
import org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;

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

/**
 * Created by wei on 2018/11/14.
 */
public class Join {

    public static void main(String args[]) {
        join();
    }

    public static void join() {
        SparkConf conf = new SparkConf()
                .setMaster("local")
                .setAppName("join");

        JavaSparkContext sc = new JavaSparkContext(conf);

        List<Tuple2<String, String>> data = Arrays.asList(
                new Tuple2<>("age", "s1"),
                new Tuple2<>("name", "s2"),
                new Tuple2<>("sex", "s3"),
                new Tuple2<>("add", "s1")
        );


        JavaPairRDD<String, String> javaPairRDD = sc.parallelizePairs(data);

        List<Tuple2<String, String>> data2 = Arrays.asList(

                new Tuple2<>("age", "s1"),
                new Tuple2<>("name", "s2"),
                new Tuple2<>("sex", "s3"),
                new Tuple2<>("age", "s134")
        );


        JavaPairRDD<String, String> javaPairRDD2 = sc.parallelizePairs(data2);
        System.out.println("Join------------------------------>");
//        (name,(s2,s2))
//        (sex,(s3,s3))
//        (age,(s1,s1))
//        (age,(s1,s134))
        javaPairRDD.join(javaPairRDD2).foreach(new VoidFunction<Tuple2<String, Tuple2<String, String>>>() {
            @Override
            public void call(Tuple2<String, Tuple2<String, String>> stringTuple2Tuple2) throws Exception {
                System.out.println(stringTuple2Tuple2);
            }
        });

        System.out.println("leftOuterJoin------------------------------>");
//        (name,(s2,Optional[s2]))
//        (sex,(s3,Optional[s3]))
//        (add,(s1,Optional.empty))
//        (age,(s1,Optional[s1]))
//        (age,(s1,Optional[s134]))
        javaPairRDD.leftOuterJoin(javaPairRDD2).foreach(new VoidFunction<Tuple2<String, Tuple2<String, Optional<String>>>>() {
            @Override
            public void call(Tuple2<String, Tuple2<String, Optional<String>>> stringTuple2Tuple2) throws Exception {
                System.out.println(stringTuple2Tuple2);
            }
        });




        System.out.println("rightOuterJoin------------------------------>");
//        (name,(Optional[s2],s2))
//        (sex,(Optional[s3],s3))
//        (age,(Optional[s1],s1))
//        (age,(Optional[s1],s134))
        javaPairRDD.rightOuterJoin(javaPairRDD2).foreach(new VoidFunction<Tuple2<String, Tuple2<Optional<String>, String>>>() {
            @Override
            public void call(Tuple2<String, Tuple2<Optional<String>, String>> stringTuple2Tuple2) throws Exception {
                System.out.println(stringTuple2Tuple2);
            }
        });


    }
}

猜你喜欢

转载自blog.csdn.net/u010225915/article/details/84075687