Spark SQL程序操作HiveContext

HiveContext是对应spark-hive这个项目,与hive有部分耦合, 支持hql,是SqlContext的子类,也就是说兼容SqlContext;

1、添加依赖

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-hive_2.11</artifactId>
    <version>2.0.2</version>
</dependency>

2、代码实现

package cn.cheng.sql

import org.apache.spark.sql.SparkSession
/**
  * todo:支持hive的sql操作
  */
object HiveSupport {
  def main(args: Array[String]): Unit = {
      val warehouseLocation = "D:\\workSpace_IDEA_NEW\\day2017-10-12\\spark-warehouse"
      //todo:1、创建sparkSession
     val spark: SparkSession = SparkSession.builder()
       .appName("HiveSupport")
       .master("local[2]")
       .config("spark.sql.warehouse.dir", warehouseLocation)
       .enableHiveSupport() //开启支持hive
       .getOrCreate()
    spark.sparkContext.setLogLevel("WARN")  //设置日志输出级别
    import spark.implicits._
    import spark.sql

    //todo:2、操作sql语句
    sql("CREATE TABLE IF NOT EXISTS person (id int, name string, age int) row format delimited fields terminated by ' '")
    sql("LOAD DATA LOCAL INPATH '/person.txt' INTO TABLE person")
    sql("select * from person ").show()
    spark.stop()
  }
}