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

Go to download
Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.10 Show documentation
SnappyData distributed data store and execution engine
There is a newer version: 1.6.2-6
Show 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.HashMap;
import java.util.HashSet;
import java.util.Arrays;
import java.util.regex.Pattern;

import scala.Tuple2;

import com.google.common.collect.Lists;
import kafka.serializer.StringDecoder;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.*;
import org.apache.spark.streaming.api.java.*;
import org.apache.spark.streaming.kafka.KafkaUtils;
import org.apache.spark.streaming.Durations;

/**
 * Consumes messages from one or more topics in Kafka and does wordcount.
 * Usage: JavaDirectKafkaWordCount  
 *    is a list of one or more Kafka brokers
 *    is a list of one or more kafka topics to consume from
 *
 * Example:
 *    $ bin/run-example streaming.JavaDirectKafkaWordCount broker1-host:port,broker2-host:port topic1,topic2
 */

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

  public static void main(String[] args) {
    if (args.length < 2) {
      System.err.println("Usage: JavaDirectKafkaWordCount  \n" +
          "   is a list of one or more Kafka brokers\n" +
          "   is a list of one or more kafka topics to consume from\n\n");
      System.exit(1);
    }

    StreamingExamples.setStreamingLogLevels();

    String brokers = args[0];
    String topics = args[1];

    // Create context with a 2 seconds batch interval
    SparkConf sparkConf = new SparkConf().setAppName("JavaDirectKafkaWordCount");
    JavaStreamingContext jssc = new JavaStreamingContext(sparkConf, Durations.seconds(2));

    HashSet topicsSet = new HashSet(Arrays.asList(topics.split(",")));
    HashMap kafkaParams = new HashMap();
    kafkaParams.put("metadata.broker.list", brokers);

    // Create direct kafka stream with brokers and topics
    JavaPairInputDStream messages = KafkaUtils.createDirectStream(
        jssc,
        String.class,
        String.class,
        StringDecoder.class,
        StringDecoder.class,
        kafkaParams,
        topicsSet
    );

    // Get the lines, split them into words, count the words and print
    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();

    // Start the computation
    jssc.start();
    jssc.awaitTermination();
  }
}