spark自定义接收器无法处理数据

时间:2017-10-04 11:59:54

标签: java maven apache-spark spark-streaming

我编写了一个自定义接收器来处理数据流,代码编译并运行良好但是当我从服务器发送数据时,它会显示在控制台中,但我看不到正在处理的输入。

自定义服务器: -

nc -lk 9999

Java代码: -

import com.google.common.io.Closeables;

import org.apache.spark.SparkConf;
import org.apache.spark.storage.StorageLevel;
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 org.apache.spark.streaming.receiver.Receiver;
import scala.Tuple2;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.ConnectException;
import java.net.Socket;
import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.regex.Pattern;

/**
 * Custom Receiver that receives data over a socket. Received bytes is interpreted as
 * text and \n delimited lines are considered as records. They are then counted and printed.
 *
 * Usage: JavaCustomReceiver <master> <hostname> <port>
 *   <master> is the Spark master URL. In local mode, <master> should be 'local[n]' with n > 1.
 *   <hostname> and <port> of the TCP server that Spark Streaming would connect to receive data.
 *
 * 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.JavaCustomReceiver localhost 9999`
 */

public class JavaCustomReceiver extends Receiver<String> {
  private static final Pattern SPACE = Pattern.compile(" ");

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

//    StreamingExamples.setStreamingLogLevels();

    // Create the context with a 1 second batch size
    SparkConf sparkConf = new SparkConf().setAppName("JavaCustomReceiver").setMaster("local[*]");
    JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(10000));

    // Create an input stream with the custom receiver on target ip:port and count the
    // words in input stream of \n delimited text (eg. generated by 'nc')
    JavaReceiverInputDStream<String> lines = ssc.receiverStream(
      new JavaCustomReceiver("localhost", 9999));    

//    JavaDStream<String> words = lines.flatMap(x -> Arrays.asList(SPACE.split(""))).iterator();
    JavaDStream<String> words = lines.flatMap(x -> Arrays.asList(SPACE.split(" ")).iterator());
    words.foreachRDD(   x-> {
        x.collect().stream().forEach(n-> System.out.println("item of list: "+n));
    });

    JavaPairDStream<String, Integer> wordCounts = words.mapToPair(s -> new Tuple2<>(s, 1))
        .reduceByKey((i1, i2) -> i1 + i2);
    wordCounts.count();
    System.out.println("WordCounts == " + wordCounts);
    wordCounts.print();

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

  // ============= Receiver code that receives data over a socket ==============

  String host = null;
  int port = -1;

  public JavaCustomReceiver(String host_ , int port_) {
    super(StorageLevel.MEMORY_AND_DISK_2());
    host = host_;
    port = port_;
  }

  @Override
  public void onStart() {
    // Start the thread that receives data over a connection
    new Thread(this::receive).start();
  }

  @Override
  public void onStop() {
    // There is nothing much to do as the thread calling receive()
    // is designed to stop by itself isStopped() returns false
  }

  /** Create a socket connection and receive data until receiver is stopped */
  private void receive() {
    try {
      Socket socket = null;
      BufferedReader reader = null;
      try {
        // connect to the server
        socket = new Socket(host, port);
        reader = new BufferedReader(
            new InputStreamReader(socket.getInputStream(), StandardCharsets.UTF_8));
        // Until stopped or connection broken continue reading
        String userInput;
        while (!isStopped() && (userInput = reader.readLine()) != null) {
          System.out.println("Received data '" + userInput + "'");
          store(userInput);
        }
      } finally {
        Closeables.close(reader, /* swallowIOException = */ true);
        Closeables.close(socket,  /* swallowIOException = */ true);
      }
      // Restart in an attempt to connect again when server is active again
      restart("Trying to connect again");
    } catch(ConnectException ce) {
      // restart if could not connect to server
      restart("Could not connect", ce);
    } catch(Throwable t) {
      restart("Error receiving data", t);
    }
  }
}

为什么在print语句的控制台中看不到任何输入。

这是我的pom.xml

<dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>com.microsoft.azure</groupId>
            <artifactId>azure-storage</artifactId>
            <version>5.5.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.0.2</version>
            <scope>provided</scope>
        </dependency>

0 个答案:

没有答案