org.apache.spark.examples.streaming.JavaKafkaWordCount Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of spark-examples_2.10 Show documentation
The newest version!
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spark.examples.streaming;

import java.util.Map;
import java.util.HashMap;
import java.util.regex.Pattern;


import scala.Tuple2;

import com.google.common.collect.Lists;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.examples.streaming.StreamingExamples;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaPairReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.streaming.kafka.KafkaUtils;

/**
 * Consumes messages from one or more topics in Kafka and does wordcount.
 *
 * Usage: JavaKafkaWordCount    
 *    is a list of one or more zookeeper servers that make quorum
 *    is the name of kafka consumer group
 *    is a list of one or more kafka topics to consume from
 *    is the number of threads the kafka consumer should use
 *
 * To run this example:
 *   `$ bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02, \
 *    zoo03 my-consumer-group topic1,topic2 1`
 */

public final class JavaKafkaWordCount {
  private static final Pattern SPACE = Pattern.compile(" ");

  private JavaKafkaWordCount() {
  }

  public static void main(String[] args) {
    if (args.length < 4) {
      System.err.println("Usage: JavaKafkaWordCount    ");
      System.exit(1);
    }

    StreamingExamples.setStreamingLogLevels();
    SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaWordCount");
    // Create the context with a 1 second batch size
    JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, new Duration(2000));

    int numThreads = Integer.parseInt(args[3]);
    Map topicMap = new HashMap();
    String[] topics = args[2].split(",");
    for (String topic: topics) {
      topicMap.put(topic, numThreads);
    }

    JavaPairReceiverInputDStream messages =
            KafkaUtils.createStream(jssc, args[0], args[1], topicMap);

    JavaDStream lines = messages.map(new Function, String>() {
      @Override
      public String call(Tuple2 tuple2) {
        return tuple2._2();
      }
    });

    JavaDStream words = lines.flatMap(new FlatMapFunction() {
      @Override
      public Iterable call(String x) {
        return Lists.newArrayList(SPACE.split(x));
      }
    });

    JavaPairDStream wordCounts = words.mapToPair(
      new PairFunction() {
        @Override
        public Tuple2 call(String s) {
          return new Tuple2(s, 1);
        }
      }).reduceByKey(new Function2() {
        @Override
        public Integer call(Integer i1, Integer i2) {
          return i1 + i2;
        }
      });

    wordCounts.print();
    jssc.start();
    jssc.awaitTermination();
  }
}