Spark Streaming接入HDFS的資料模擬一個wordcount的功能，結果列印到控制檯，使用Local模式，使用Scala語言。

專案目錄

pom.xml

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.sid.spark</groupId>
  <artifactId>spark-train</artifactId>
  <version>1.0</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.8</scala.version>
    <kafka.version>0.9.0.0</kafka.version>
    <spark.version>2.2.0</spark.version>
    <hadoop.version>2.9.0</hadoop.version>
    <hbase.version>1.4.4</hbase.version>
  </properties>

  <repositories>
    <repository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </repository>
  </repositories>

  <pluginRepositories>
    <pluginRepository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
  </pluginRepositories>

  <dependencies>
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>${kafka.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>

    <!--<dependency>-->
      <!--<groupId>org.apache.hbase</groupId>-->
      <!--<artifactId>hbase-clinet</artifactId>-->
      <!--<version>${hbase.version}</version>-->
    <!--</dependency>-->

    <!--<dependency>-->
      <!--<groupId>org.apache.hbase</groupId>-->
      <!--<artifactId>hbase-server</artifactId>-->
      <!--<version>${hbase.version}</version>-->
    <!--</dependency>-->

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

    <dependency>
      <groupId>net.jpountz.lz4</groupId>
      <artifactId>lz4</artifactId>
      <version>1.3.0</version>
    </dependency>

  </dependencies>

  <build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>
 

程式碼

package com.sid.spark

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

/**
  * Created by jy02268879 on 2018/7/16.
  *
  * Spark Streaming 處理 HDFS檔案資料
  */
object HDFSWordCount {
  def  main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local").setAppName("HDFSWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    /**
      * Create an input stream that monitors a Hadoop-compatible filesystem
      * for new files and reads them as text files (using key as LongWritable, value
      * as Text and input format as TextInputFormat). Files must be written to the
      * monitored directory by "moving" them from another location within the same
      * file system. File names starting with . are ignored.
      *
      * param directory HDFS directory to monitor for new file
      */
    val lines = ssc.textFileStream("hdfs://node1:9000/testdata/sparkstreaming/hdfswordcount/")

    val result = lines.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _)

    result.print()

    ssc.start()
    ssc.awaitTermination()
  }


}
 

啟動Hadoop

(只在namenode上面執行，即是node1)

cd /app/hadoop/hadoop-2.9.0/sbin

start-all.sh

在HDFS上建立路徑

cd /app/hadoop/hadoop-2.9.0/bin

hdfs dfs -mkdir -p /testdata/sparkstreaming/hdfswordcount

建立測試資料

cd /app/spark/test_data/monitor_file

vi test.log

IDEA點選run啟動程式

將要計數的檔案放到HDFS上

cd /app/spark/test_data/monitor_file

hdfs dfs -put test.log /testdata/sparkstreaming/hdfswordcount

檢視IDEA控制檯輸出