Apache Spark Streaming with Java & Kafka

I’m trying to run Spark Streaming example from the official Spark website

Those are the dependencies I use in my pom file:

<dependency>
  <groupId>org.apache.spark</groupId>
  <artifactId>spark-core_2.11</artifactId>
  <version>2.3.1</version>
</dependency>

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming_2.11</artifactId>
    <version>2.3.1</version>
</dependency>

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
    <version>2.2.0</version>
</dependency>

This is my Java code:

package com.myproject.spark;

import java.util.Arrays;
import java.util.Collection;
import java.util.HashMap;
import java.util.Map;

import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.common.serialization.StringDeserializer;
import org.apache.spark.SparkConf;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.streaming.kafka010.ConsumerStrategies;
import org.apache.spark.streaming.kafka010.KafkaUtils;
import org.apache.spark.streaming.kafka010.LocationStrategies;

import com.myproject.spark.serialization.JsonDeserializer;

import scala.Tuple2;

public class MainEntryPoint {
  public static void main(String[] args) {
    Map<String, Object> kafkaParams = new HashMap<String, Object>();
    kafkaParams.put("bootstrap.servers", "localhost:9092,localhost:9093,localhost:9094");
    kafkaParams.put("key.deserializer", StringDeserializer.class);
    kafkaParams.put("value.deserializer",JsonDeserializer.class.getName());
    kafkaParams.put("group.id", "ttk-event-listener");
    kafkaParams.put("auto.offset.reset", "latest");
    kafkaParams.put("enable.auto.commit", false);

    Collection<String> topics = Arrays.asList("topic1", "topic2");

    SparkConf conf = new SparkConf()
        .setMaster("local[*]")
        .setAppName("EMSStreamingApp");
    JavaStreamingContext streamingContext =
        new JavaStreamingContext(conf, Durations.seconds(1));

    JavaInputDStream<ConsumerRecord<String, String>> stream =
      KafkaUtils.createDirectStream(
        streamingContext,
        LocationStrategies.PreferConsistent(),
        ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams)
      );

    stream.mapToPair(record -> new Tuple2<>(record.key(), record.value()));


    streamingContext.start();
    try {
      streamingContext.awaitTermination();
    } catch (InterruptedException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
  }
}

When I try to run it from Eclipse I get following exception:

18/07/16 13:35:27 INFO BlockManagerMaster: Registered BlockManager BlockManagerId(driver, 192.168.1.106, 51604, None)
18/07/16 13:35:27 INFO BlockManager: Initialized BlockManager: BlockManagerId(driver, 192.168.1.106, 51604, None)
Exception in thread "main" java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.streaming.kafka010.KafkaUtils$.initializeLogIfNecessary(KafkaUtils.scala:39)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.streaming.kafka010.KafkaUtils$.log(KafkaUtils.scala:39)
at org.apache.spark.internal.Logging$class.logWarning(Logging.scala:66)
at org.apache.spark.streaming.kafka010.KafkaUtils$.logWarning(KafkaUtils.scala:39)
at org.apache.spark.streaming.kafka010.KafkaUtils$.fixKafkaParams(KafkaUtils.scala:201)
at org.apache.spark.streaming.kafka010.DirectKafkaInputDStream.<init>(DirectKafkaInputDStream.scala:63)
at org.apache.spark.streaming.kafka010.KafkaUtils$.createDirectStream(KafkaUtils.scala:147)
at org.apache.spark.streaming.kafka010.KafkaUtils$.createDirectStream(KafkaUtils.scala:124)
at org.apache.spark.streaming.kafka010.KafkaUtils$.createDirectStream(KafkaUtils.scala:168)
at org.apache.spark.streaming.kafka010.KafkaUtils.createDirectStream(KafkaUtils.scala)
at com.myproject.spark.MainEntryPoint.main(MainEntryPoint.java:47)
18/07/16 13:35:28 INFO SparkContext: Invoking stop() from shutdown hook

I run this from my IDE (eclipse). Do I have to create and deploy the JAR into spark to make it run. If anyone knows about the exception, please share your experience. Thanks in advance

Answer

Try using 2.3.1 also for the spark-streaming-kafka dependency.

Check also other related questions and their answers about java.lang.AbstractMethodError.

It usually means a mismatch between used libraries and their interfaces/implementations.