【十】Spark Streaming中transform、leftjoin的使用Local模式（使用Scala语言）

transform方法把DStream转换成新的RDD

需求：黑名单过滤。

访问日志 ==>DStream

20180718，sid

20180718，lee

20180718，leo

      ==>（sid:20180718，sid）（lee:20180718，lee）（leo:20180718，leo）

 

leftjoin

黑名单表 ==>RDD

lee

leo

    ==>  (lee:true)(leo:true)

 

结果

sid:[<20180718，sid>,<false>]）  X

lee:[<20180718，lee>,<true>]）   X

leo:[<20180718，leo>,<true>]）  ==> tuple 1

项目目录

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>
      <exclusions>
        <exclusion>
          <artifactId>servlet-api</artifactId>
          <groupId>javax.servlet</groupId>
        </exclusion>
      </exclusions>
    </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>

    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.31</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>

代码

package com.sid.spark

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

/**
  * Created by jy02268879 on 2018/7/18.
  *
  * 黑名单过滤
  */
object TransformApp {
  def main(args: Array[String]): Unit = {

    /**
      * 当运行Spark Streaming应用程序的时候如果使用的Local模式，
      * 不要使用local或者local[1]作为master的URL。
      * 因为这种写法意味着仅仅只有一个线程能被使用，
      * 如果使用基于Receiver的input DStream（如果用的HDFS上面的文件就可以用local[1]或local），
      * Receiver就已经占用了线程了，
      * 主流程就处理不了数据了。
      * 所以要用local[n]，n>Receiver的数量。
      * */
    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("SocketWordCount")

    //构建StreamingContext
    /**
      * 创建StreamingContext需要两个参数：sparkConf和batch interval
      * */
    val ssc = new StreamingContext(sparkConf,Seconds(5))

    /**
      * 构建黑名单
      * */
    val blacks = List("lee","leo")
    //把一个集合转换成RDD
    val blacksRDD = ssc.sparkContext.parallelize(blacks).map(x=>(x,true))


    val lines = ssc.socketTextStream("node1",6789)

    /**
      *
    访问日志 ==>DStream

    20180718，sid
    20180718，lee
    20180718，leo
      ==>（sid:20180718，sid）（lee:20180718，lee）（leo:20180718，leo）

    leftjoin

    黑名单表 ==>RDD

    lew
    leo
       ==>(lee:true)(leo:true)

    结果

    sid:[<20180718，sid>,<false>]）  ==> tuple 1
    lee:[<20180718，lee>,<true>]）   X
    leo:[<20180718，leo>,<true>]）   X
      *
      * */
    val clicklog = lines.map(x => (x.split(",")(1),x)).transform(rdd => {
        rdd.leftOuterJoin(blacksRDD)
          .filter(x => x._2._2.getOrElse(false) != true)
          .map(x => x._2._1)
    })
    clicklog.print()

    ssc.start()

    ssc.awaitTermination()
  }

}

启动nc -lk 6789

IDEA启动项目

在nc输入

20180718，sid

20180718，lee

20180718，leo