等于（=）

大于（>）

大于或等于（> =）

小于（<）

小于等于（<=）

import org.apache.kudu.spark.kudu._

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.SparkSession

/**

  * Created by angel；

  */

object Predicate_pushDown {

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

    val sparkConf = new SparkConf().setAppName("AcctfileProcess")

      //设置Master_IP并设置spark参数

      .setMaster("local")

      .set("spark.worker.timeout", "500")

      .set("spark.cores.max", "10")

      .set("spark.rpc.askTimeout", "600s")

      .set("spark.network.timeout", "600s")

      .set("spark.task.maxFailures", "1")

      .set("spark.speculationfalse", "false")

      .set("spark.driver.allowMultipleContexts", "true")

      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")

    val sparkContext = SparkContext.getOrCreate(sparkConf)

    val sqlContext = SparkSession.builder().config(sparkConf).getOrCreate().sqlContext

    //使用spark创建kudu表

    val kuduMasters = "hadoop01:7051,hadoop02:7051,hadoop03:7051"

    val kuduContext = new KuduContext(kuduMasters, sqlContext.sparkContext)

    //TODO 1：定义kudu表

    val kuduTableName = "spark_kudu_tbl"

    //TODO 2：配置kudu参数

    val kuduOptions: Map[String, String] = Map(

      "kudu.table"  -> kuduTableName,

      "kudu.master" -> kuduMasters)

    //TODO 3：注册kudu表作为spark的临时表

    sqlContext.read.options(kuduOptions).kudu.registerTempTable(kuduTableName)

    //TODO 4：执行sparkSQL语句，spark会自动将谓词推入kudu引擎

    val customerNameAgeDF = sqlContext.

      sql(s"""SELECT name, age FROM $kuduTableName WHERE age >= 30""")

    //TODO 5：展示结果

    customerNameAgeDF.show()

    //TODO 6：使用sparkSQL的查询计划

    customerNameAgeDF.explain()

  }

}