【十一】Spark Streaming整合Spark SQL的操作Local模式（使用Scala语言）

DataFrames and SQL操作可以作用在流数据上。

首先创建一个SparkSession使用SparkContext。这个SparkContext也能被StreamingContext使用。

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>org.apache.spark</groupId>
      <artifactId>spark-sql_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.rdd.RDD
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.{Seconds, StreamingContext, Time}

/**
  * Use DataFrames and SQL to count words in UTF8 encoded, '\n' delimited text received from the
  * network every second.
  *
  * Usage: SqlNetworkWordCount <hostname> <port>
  * <hostname> and <port> describe 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.SqlNetworkWordCount localhost 9999`
  *
  *    Spark Streaming整合Spark SQL完成词频统计
  */

object SqlNetworkWordCount {
  def main(args: Array[String]) {

    val sparkConf = new SparkConf().setMaster("local[2]").setAppName("SocketWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    // Create a socket stream 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.
    val lines = ssc.socketTextStream("node1", 6789)
    val words = lines.flatMap(_.split(" "))

    // Convert RDDs of the words DStream to DataFrame and run SQL query
    words.foreachRDD { (rdd: RDD[String], time: Time) =>
      // Get the singleton instance of SparkSession
      val spark = SparkSessionSingleton.getInstance(rdd.sparkContext.getConf)
      import spark.implicits._

      // Convert RDD[String] to RDD[case class] to DataFrame
      val wordsDataFrame = rdd.map(w => Record(w)).toDF()

      // Creates a temporary view using the DataFrame
      wordsDataFrame.createOrReplaceTempView("words")

      // Do word count on table using SQL and print it
      val wordCountsDataFrame =
        spark.sql("select word, count(*) as total from words group by word")
      println(s"========= $time =========")
      wordCountsDataFrame.show()
    }

    ssc.start()
    ssc.awaitTermination()
  }

  /** Case class for converting RDD to DataFrame */
  case class Record(word: String)


  /** Lazily instantiated singleton instance of SparkSession */
  object SparkSessionSingleton {

    @transient  private var instance: SparkSession = _

    def getInstance(sparkConf: SparkConf): SparkSession = {
      if (instance == null) {
        instance = SparkSession
          .builder
          .config(sparkConf)
          .getOrCreate()
      }
      instance
    }
  }
}

启动nc -lk 6789

IDEA启动项目

nc输入a a a a a

IDEA控制台结果

nc再输入a a 

IDEA控制台结果

未完成：

Spark Streaming 结合 Spark SQL做词频统计时需要保留上一个批次状态。该例子期望结果是 a 7。

回头再补充完