使用Spark Streaming整合Spark SQL完成词频统计操作

首先在maven工程的pom.xml文件加入以下依赖：

        2.2.0

    
 
        
            org.apache.spark
            spark-streaming_2.11
            ${spark.version}
        

      
        
            org.apache.spark
            spark-sql_2.11
            ${spark.version}
        

SqlNetworkWordCount.scala

package 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}

/**
  * Spark Streaming整合Spark SQL完成词频统计操作
  */
object SqlNetworkWordCount {

  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("ForeachRDDApp").setMaster("local[2]")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    val lines = ssc.socketTextStream("localhost", 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) =>
      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
    }
  }
}

ForeachRDDApp.scala

package spark

import java.sql.DriverManager

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

/**
  * 使用Spark Streaming完成词频统计，并将结果写入到MySQL数据库中
  */
object ForeachRDDApp {

  def main(args: Array[String]): Unit = {

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


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

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

    //result.print()  //此处仅仅是将统计结果输出到控制台

    //TODO... 将结果写入到MySQL
    //    result.foreachRDD(rdd =>{
    //      val connection = createConnection()  // executed at the driver
    //      rdd.foreach { record =>
    //        val sql = "insert into wordcount(word, wordcount) values('"+record._1 + "'," + record._2 +")"
    //        connection.createStatement().execute(sql)
    //      }
    //    })

    result.print()

    result.foreachRDD(rdd => {
      rdd.foreachPartition(partitionOfRecords => {
        val connection = createConnection()
        partitionOfRecords.foreach(record => {
          val sql = "insert into wordcount(word, wordcount) values('" + record._1 + "'," + record._2 + ")"
          connection.createStatement().execute(sql)
        })

        connection.close()
      })
    })


    ssc.start()
    ssc.awaitTermination()
  }


  /**
    * 获取MySQL的连接
    */
  def createConnection() = {
    Class.forName("com.mysql.jdbc.Driver")
    DriverManager.getConnection("jdbc:mysql://localhost:3306/test", "root", "root")
  }

}