scala Spark 讀取hive數據

import org.apache.spark.SparkConf
import org.apache.spark.sql.{DataFrame, SparkSession}

object SparkOperaterHive {

  def main(args: Array[String]) {
    val sparkConf: SparkConf = new SparkConf().setMaster("local[*]").setAppName(SparkOperaterHive.getClass.getSimpleName)
    val sparkSession: SparkSession = SparkSession.builder().config(sparkConf).enableHiveSupport().getOrCreate()

    sparkSession.sql("use tyxdb")
    val sql: DataFrame = sparkSession.sql("select * from name")
    sql.show()

    sparkSession.stop()
  }
}

編輯 hive-site.xml，添加：

<property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://localhost:3306/hive?createDatabaseIfNotExist=true</value>
    <description>JDBC connect string for a JDBC metastore</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
    <description>Driver class name for a JDBC metastore</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
    <description>username to use against metastore database</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>password</value>
    <description>password to use against metastore database</description>
  </property>