SparkSQL 访问 hive

1.1   从 hive读数据

object HiveRead {

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


    val spark = SparkSession.builder()
      .master("local[*]")
      .appName("HiveRead")
      .enableHiveSupport()
      .getOrCreate()

    import spark.implicits._


    spark.sql("show databases")
    spark.sql("use gmall")
    spark.sql("select count(*) from ads_uv_count").show()


    spark.close()

  }

}

1.2   从 hive写数据

object HiveWrite2 {

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

    System.setProperty("HADOOP_USER_NAME","xingmeng")

      val spark = SparkSession.builder()
        .master("local[*]")
        .appName("HiveRead")
        .enableHiveSupport()
        .config("spark.sql.warehouse.dir","hdfs://hadoop102:9000/user/hive/warehouse")
        .getOrCreate()

      //先创建一个数据库

//    spark.sql("create database spark1016")
//    spark.sql("use spark1016")
//    spark.sql("create table user1(id int, name string)").show()
//    spark.sql("insert into table user1 VALUES(10,'lisi')")

    val df = spark.read.json("F:/BaiduNetdiskDownload/15-spark/spark-coreData/users.json")
    spark.sql("use spark1016")


    val df1 = spark.sql("select * from a")
    val df2 = spark.sql("select sum(age) sum_age from a group by name")

    df1.write.saveAsTable("a1")
    //hive 聚合后，分区数会成为200
    df2.coalesce(1).write.mode("overwrite").saveAsTable("a2")


    spark.close()


  }

}