我的大数据之旅-Spark DStreams输入

DStream输入

1. 基本数据源

• 文件数据源

创建方式：

StreamingContext.fileStream[KeyClass, ValueClass, InputFormatClass]

文本文件：

streamingContext.textFileStream(dataDirectory)

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.fengling</groupId>
    <artifactId>streaming</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <spark.version>2.1.1</spark.version>
        <scala.version>2.11.12</scala.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
            <scope>provided</scope>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <!--添加编译支持，都编译成java1.8版本-->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <!--添加Scala编译支持-->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                        <configuration>
                            <archive>
                                <manifest>
                                    <mainClass>com.fengling.TextFileWordCount</mainClass>
                                </manifest>
                            </archive>
                            <descriptorRefs>
                                <descriptorRef>jar-with-dependencies</descriptorRef>
                            </descriptorRefs>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

file word count: 读取HDFS上的/data目录

package com.fengling

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

object TextFileWordCount extends App {

  // 创建StreamingContext
  val conf = new SparkConf().setMaster("local[4]").setAppName("TextFileWordCountV0.1")
  val ssc = new StreamingContext(conf, Seconds(1))

  val lines = ssc.textFileStream("hdfs://hadoop129:9000/data")

  val words = lines.flatMap(_.split(" "))

  val wordCount = words.map(word => (word ,1 )).reduceByKey(_+_)

  wordCount.print()

  ssc.start()
  ssc.awaitTermination()

}

打包：

上传到虚拟机中并spark-submit测试：

 

上传文件到/data目录：

• 自定义数据源

通过继承抽象类Receiver，并实现onStart()、onStop()方法来自定义数据源

package com.fengling

import java.io.{BufferedReader, InputStreamReader}
import java.net.Socket
import java.nio.charset.StandardCharsets

import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.receiver.Receiver

/**
  * @author fengchengliang@126.com
  * @date 2019-10-29
  */
class CustomReceive(host: String, port: Int) extends Receiver[String](StorageLevel.MEMORY_AND_DISK_2) {
  override def onStart(): Unit = {
    new Thread("Socket Receiver") {
      override def run(): Unit = {
        receive()
      }
    }.start()
  }

  /** Create a socket connection and receive data until receiver is stopped */
  private def receive() {
    var socket: Socket = null
    var userInput: String = null
    try {
      // Connect to host:port
      socket = new Socket(host, port)

      // Until stopped or connection broken continue reading
      val reader = new BufferedReader(
        new InputStreamReader(socket.getInputStream(), StandardCharsets.UTF_8))
      userInput = reader.readLine()
      while (!isStopped && userInput != null) {
        store(userInput)
        userInput = reader.readLine()
      }
      reader.close()
      socket.close()

      // Restart in an attempt to connect again when server is active again
      restart("Trying to connect again")
    } catch {
      case e: java.net.ConnectException =>
        // restart if could not connect to server
        restart("Error connecting to " + host + ":" + port, e)
      case t: Throwable =>
        // restart if there is any other error
        restart("Error receiving data", t)
    }
  }

  override def onStop(): Unit = {}
}

object CustomReceiver {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local[*]").setAppName("CustomReceiver")
    val ssc = new StreamingContext(sparkConf, Seconds(1))

    val customReceiverStream = ssc.receiverStream(new CustomReceive("hadoop129", 9999))
    val words = customReceiverStream.flatMap(_.split(" "))

    // 转换成一个二元组，统计每个单词出现的次数
    val wordCount = words.map(word => (word, 1)).reduceByKey(_ + _)
    wordCount.print()

    ssc.start()
    ssc.awaitTermination()

  }
}

测试：

[fengling@hadoop129 spark-2.4.4-bin-hadoop2.7]$ bin/spark-submit --class com.fengling.CustomReceiver ~/streaming-1.0-SNAPSHOT-jar-with-dependencies.jar