Spark Streaming进阶与案例实战

1.updateStateByKey算子的使用

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

/**
  * 使用Spark Streaming完成有状态统计
  */
object StatefulWordCount {

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


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

    // 如果使用了stateful的算子，必须要设置checkpoint
    // 在生产环境中，建议大家把checkpoint设置到HDFS的某个文件夹中
    ssc.checkpoint(".")

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

    val result = lines.flatMap(_.split(" ")).map((_,1))
    val state = result.updateStateByKey[Int](updateFunction _)

    state.print()

    ssc.start()
    ssc.awaitTermination()
  }


  /**
    * 把当前的数据去更新已有的或者是老的数据
    * @param currentValues  当前的
    * @param preValues  老的
    * @return
    */
  def updateFunction(currentValues: Seq[Int], preValues: Option[Int]): Option[Int] = {
    val current = currentValues.sum
    val pre = preValues.getOrElse(0)

    Some(current + pre)
  }
}

2.将累计出现的单词个数统计结果写入到MySQL数据库中

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")
  }

}