sparksql读取hive中的数据保存到hdfs中

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012719230/article/details/82492745

package wondersgroup_0905_Test

import org.apache.spark.sql.SparkSession

object sparkHive {
  def main(args: Array[String]): Unit = {
    //数据库名称
    val database ="hivetest"
    //表名称
    val table = "tb_his_zy_fee_detail"
    //hive warehouse在hdfs上的存储目录
    val warehouse = "/user/hive/warehouse"

    val path = "/user/hdfs/test/hivespark"
    val spark = SparkSession
      .builder()
      .appName("Spark Hive Example")
      .config("spark.sql.warehouse.dir", warehouse)
      .enableHiveSupport()
      .getOrCreate()

    val sql="select * from hivetest.tb_his_zy_fee_detail where tb_his_zy_fee_detail."

    val data=spark.sql(sql)
    //显示查询结果
    data.show
    //将结果保存只HDFS
    data.coalesce(1).write.save(path)
    spark.stop()
  }
}