基于案例贯通 Spark Streaming 流计算框架的运行源码

本期内容 :

Spark Streaming+Spark SQL案例展示
基于案例贯穿Spark Streaming的运行源码

一、案例代码阐述 :

　　在线动态计算电商中不同类别中最热门的商品排名，例如:手机类别中最热门的三种手机、电视类别中最热门的三种电视等。

　　1、案例运行代码 :

import org.apache.spark.SparkConf
import org.apache.spark.sql.Row
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object OnlineTheTop3ItemForEachCategory2DB {
  def main(args: Array[String]){
　　　/**
　　　　*
　　　　* 第1步：创建Spark的配置对象SparkConf，设置Spark程序的运行时的配置信息，
　　　　*/
    val conf = new SparkConf() //创建SparkConf对象
    conf.setAppName("OnlineTheTop3ItemForEachCategory2DB") //设置应用程序的名称，在程序运行的监控界面可以看到名称
　　//conf.setMaster("spark://Master:7077") //此时，程序在Spark集群
    conf.setMaster("local[6]")
    //设置batchDuration时间间隔来控制Job生成的频率并且创建Spark Streaming执行的入口
    val ssc = new StreamingContext(conf, Seconds(5))

    ssc.checkpoint("/root/Documents/SparkApps/checkpoint")

    val userClickLogsDStream = ssc.socketTextStream("Master", 9999)

    val formattedUserClickLogsDStream = userClickLogsDStream.map(clickLog =>
        (clickLog.split(" ")(2) + "_" + clickLog.split(" ")(1), 1))

　　//val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow((v1:Int, v2: Int) => v1 + v2,
　　//(v1:Int, v2: Int) => v1 - v2, Seconds(60), Seconds(20))

    val categoryUserClickLogsDStream = formattedUserClickLogsDStream.reduceByKeyAndWindow(_+_,
      _-_, Seconds(60), Seconds(20))

    categoryUserClickLogsDStream.foreachRDD { rdd => {
      if (rdd.isEmpty()) {
        println("No data inputted!!!")
      } else {
        val categoryItemRow = rdd.map(reducedItem => {
          val category = reducedItem._1.split("_")(0)
          val item = reducedItem._1.split("_")(1)
          val click_count = reducedItem._2
          Row(category, item, click_count)
        })

        val structType = StructType(Array(
          StructField("category", StringType, true),
          StructField("item", StringType, true),
          StructField("click_count", IntegerType, true)
        ))

        val hiveContext = new HiveContext(rdd.context)
        val categoryItemDF = hiveContext.createDataFrame(categoryItemRow, structType)

        categoryItemDF.registerTempTable("categoryItemTable")

        val reseltDataFram = hiveContext.sql("SELECT category,item,click_count FROM (SELECT category,item,click_count,row_number()" +
          " OVER (PARTITION BY category ORDER BY click_count DESC) rank FROM categoryItemTable) subquery " +
          " WHERE rank <= 3")
        reseltDataFram.show()

        val resultRowRDD = reseltDataFram.rdd

        resultRowRDD.foreachPartition { partitionOfRecords => {

          if (partitionOfRecords.isEmpty){
            println("This RDD is not null but partition is null")
          } else {
            // ConnectionPool is a static, lazily initialized pool of connections
            val connection = ConnectionPool.getConnection()
            partitionOfRecords.foreach(record => {
              val sql = "insert into categorytop3(category,item,client_count) values('" + record.getAs("category") + "','" +
                record.getAs("item") + "'," + record.getAs("click_count") + ")"
              val stmt = connection.createStatement();
              stmt.executeUpdate(sql);

            })
            ConnectionPool.returnConnection(connection) // return to the pool for future reuse

          }
        }
        }
      }
    }
    ssc.start()
    ssc.awaitTermination()

  }
　}
}