У меня есть соединил два queueStream, используя Spark java. Пожалуйста, смотрите ниже код.
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Queue;
import org.apache.commons.lang3.tuple.Pair;
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.PairFunction;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaInputDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import com.google.common.collect.Queues;
import scala.Tuple2;
public class SparkQueueStreamJoin {
public static void main(String[] args) throws InterruptedException {
// Test data
List<Pair<Integer, Boolean>> input1 = Arrays.asList(Pair.of(1,true), Pair.of(2,false), Pair.of(3,false), Pair.of(4,true), Pair.of(5,false));
List<Pair<Integer, Boolean>> input2 = Arrays.asList(Pair.of(1,false), Pair.of(2,false), Pair.of(3,true), Pair.of(4,true), Pair.of(5,true));
SparkConf conf = new SparkConf().setMaster("local[*]").setAppName("SparkQueueStreamJoin ")
.set("spark.testing.memory", "2147480000");
//System.setProperty("hadoop.home.dir", "C:/H`enter code here`adoop/hadoop-2.7.1");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<Pair<Integer, Boolean>> input1RDD = sc.parallelize(input1);
JavaRDD<Pair<Integer, Boolean>> input2RDD = sc.parallelize(input2);
JavaStreamingContext streamingContext = new JavaStreamingContext(sc, Durations.seconds(3));
Queue<JavaRDD<Pair<Integer, Boolean>>> queue1RDD = Queues.newLinkedBlockingQueue();
queue1RDD.add(input1RDD);
Queue<JavaRDD<Pair<Integer, Boolean>>> queue2RDD = Queues.newLinkedBlockingQueue();
queue2RDD.add(input2RDD);
// Creates a DStream from the test data
JavaInputDStream<Pair<Integer, Boolean>> input1DStream = streamingContext.queueStream(queue1RDD, false);
JavaInputDStream<Pair<Integer, Boolean>> input2DStream = streamingContext.queueStream(queue2RDD, false);
JavaPairDStream<Integer, Boolean> pair1DStream = input1DStream.mapToPair(new PairFunction<Pair<Integer, Boolean>, Integer, Boolean>() {
@Override
public Tuple2<Integer, Boolean> call(Pair<Integer, Boolean> rawEvent) throws Exception {
return new Tuple2<>(rawEvent.getKey(), rawEvent.getValue());
}
});
JavaPairDStream<Integer, Boolean> pair2DStream = input2DStream.mapToPair(new PairFunction<Pair<Integer, Boolean>, Integer, Boolean>() {
@Override
public Tuple2<Integer, Boolean> call(Pair<Integer, Boolean> rawEvent) throws Exception {
return new Tuple2<>(rawEvent.getKey(), rawEvent.getValue());
}
});
// Union two streams together by merging them into a single dstream
//JavaDStream<Pair<Integer, Boolean>> joinedDStream = input1DStream.union(input2DStream);
// Join the two streams together by merging them into a single dstream
JavaPairDStream<Integer, Tuple2<Boolean, Boolean>> joinedDStream = pair1DStream.join(pair2DStream);
// Print the result
joinedDStream.print();
// Start the context, time out after one batch, and then stop it
streamingContext.start();
streamingContext.awaitTerminationOrTimeout(5000);
streamingContext.stop();
}
}
Выход:
-------------------------------------------
Time: 1511444352000 ms
-------------------------------------------
(1,(true,false))
(2,(false,false))
(3,(false,true))
(4,(true,true))
(5,(false,true))
Оба ваших РДУ состоять только из ключей, вы должны иметь PairRDD правильно использовать 'join' операцию со следующим RDD структурного типа:' (ключ, значение) ' –