使用spark将内存中的数据写入到hive表中

使用spark将内存中的数据写入到hive表中

hive-site.xml

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!--
   Licensed to the Apache Software Foundation (ASF) under one or more
   contributor license agreements.  See the NOTICE file distributed with
   this work for additional information regarding copyright ownership.
   The ASF licenses this file to You under the Apache License, Version 2.0
   (the "License"); you may not use this file except in compliance with
   the License.  You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.
-->

<configuration>
    <!--hive 的元数据服务, 供spark SQL 使用-->
    <property>
        　　　　<name>hive.metastore.uris</name>
        　　　　<value>thrift://master:9083</value>
        　　　　<description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description>
        　　</property>

    <!--配置mysql数据库的链接URL和数据库名metastore,?后面的表达式代表如果这个数据库
    不存在,会自动创建-->
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://master:3306/metastore?createDatabaseIfNotExist=true</value>
        <description>JDBC connect string for a JDBC metastore</description>
    </property>
    <!--指定mysql的链接驱动,配置jdbc的驱动-->
    <property>
        <name>javax.jdo.option.ConnectionDriverName</name>
        <value>com.mysql.jdbc.Driver</value>
        <description>Driver class name for a JDBC metastore</description>
    </property>
    <!--配置mysql的用户名和密码-->
    <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>123456</value>
        <description>password to use against metastore database</description>
    </property>

    <property>
        <name>hive.cli.print.header</name>
        <value>true</value>
        <description>Whether to print the names of the columns in query output.</description>
    </property>
    <property>
        <name>hive.cli.print.current.db</name>
        <value>true</value>
        <description>Whether to include the current database in the Hive prompt.</description>
    </property>

</configuration>

下面是示例代码

package spark_sql

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.types.{StringType, StructField, StructType}
import test.ProductData

/**
  * @Program: spark01
  * @Author: 努力就是魅力
  * @Since: 2018-10-19 08:30
  *         Description:
  *
  *         使用spark将内存中的数据写入到hive表中，这是一个可以完整运行的例子
  *
  *
  *    下面是hive表查询的结果
  *         hive (hadoop10)> select * from data_block;
  *         OK
  *         data_block.ip	data_block.time	data_block.phonenum
  *         40.234.66.122	2018-10-12 09:35:21
  *         5.150.203.160	2018-10-03 14:41:09	13389202989
  *
  **/

case class Datablock(ip: String, time:String, phoneNum:String)

object WriteTabletoHive {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder()
      .master("local[*]")
      .appName("WriteTableToHive")
      .config("spark.sql.warehouse.dir","D:\\reference-data\\spark01\\spark-warehouse")
      .enableHiveSupport()
      .getOrCreate()

    import spark.implicits._

    val schemaString = "ip time phoneNum"

    val fields = schemaString.split(" ")
      .map(fieldName => StructField(fieldName, StringType,nullable = true))

    val schema = StructType(fields)

   // val datablockDS = Seq(Datablock(ProductData.getRandomIp,ProductData.getRecentAMonthRandomTime("yyyy-MM-dd HH:mm:ss"),ProductData.getRandomPhoneNumber)).toDS()

 // val datablockDS = Seq(Datablock("192.168.40.122","2018-01-01 12:25:25","18866556699")).toDS()

    datablockDS.show()

    datablockDS.toDF().createOrReplaceTempView("dataBlock")

      spark.sql("select * from dataBlock")
        .write.mode("append")
        .saveAsTable("hadoop10.data_block")

  }
}