org.apache.spark.examples.streaming.NetworkWordCount.java Source code

Introduction

Here is the source code for org.apache.spark.examples.streaming.NetworkWordCount.java

Source

/*
 * 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 com.google.common.collect.Lists;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.StorageLevels;
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.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import scala.Tuple2;

import java.util.regex.Pattern;

/**
 * Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
 * Usage: NetworkWordCount <hostname> <port>
 * <hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
 * <p>
 * To run this on your local machine, you need to first run a Netcat server
 * `$ nc -lk 9999`
 * and then run the example
 * `$ bin/run-example org.apache.spark.examples.streaming.NetworkWordCount localhost 9999`
 */
public final class NetworkWordCount {
    private static final Pattern SPACE = Pattern.compile(" ");

    public static void main(String[] args) {
        if (args.length < 2) {
            System.err.println("Usage: NetworkWordCount <hostname> <port>");
            System.exit(1);
        }

        final String hostname = args[0];
        final int port = Integer.parseInt(args[1]);

        // Create the context with a 1 second batch size
        final SparkConf sparkConf = new SparkConf().setAppName("NetworkWordCount");
        final JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(1000));

        // Create a JavaReceiverInputDStream on target ip:port and count the
        // words in input stream of \n delimited text (eg. generated by 'nc')
        // Note that no duplication in storage level only for running locally.
        // Replication necessary in distributed scenario for fault tolerance.
        final JavaReceiverInputDStream<String> lines = ssc.socketTextStream(hostname, port,
                StorageLevels.MEMORY_AND_DISK_SER);
        final JavaDStream<String> words = lines.flatMap(x -> Lists.newArrayList(SPACE.split(x)));
        final JavaPairDStream<String, Integer> wordCounts = words.mapToPair(s -> new Tuple2<>(s, 1))
                .reduceByKey((i1, i2) -> i1 + i2);

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