idea 中用spark 2.x 实现 不同数据源join (hive join MySQL )

pom文件中 添加如下 相关依赖 

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-hive_2.11</artifactId>
    <version>${spark.version}</version>
</dependency>


<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-sql -->
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.11</artifactId>
    <version>${spark.version}</version>
</dependency>

resources 文件下 添加 hive-site.xml  ，内容如下： 

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://192.168.137.251:3306/hive?createDatabaseIfNotExist=true</value>
    </property>

    <property>
        <name>javax.jdo.option.ConnectionDriverName</name>
        <value>com.mysql.jdbc.Driver</value>
    </property>

    <property>
        <name>javax.jdo.option.ConnectionUserName</name>
        <value>root</value>
    </property>

    <property>
        <name>javax.jdo.option.ConnectionPassword</name>
        <value>oracle</value>
    </property>
    <property>
        <name>hive.cli.print.current.db</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.cli.print.header</name>
        <value>true</value>
    </property>
</configuration>

 ======= 

package com.spark.sql

import java.io.File
import org.apache.spark.sql.Row
import org.apache.spark.sql.SaveMode
import org.apache.spark.sql.SparkSession


/**
  * Created by 92421 on 2018/4/5.
  */


case class Record(key: Int, value: String)

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


    val warehouseLocation = new File("spark-warehouse").getAbsolutePath
    val format = "yyyy-MM-dd'T'HH:mm:ssz"
    val spark = SparkSession.builder()
      .master("local[2]")
      .appName("Spark SQL Hive App")
      .config("spark.sql.warehouse.dir",warehouseLocation).enableHiveSupport().getOrCreate()

    import spark.sql
    //spark.sql("use default")
  //  val hiveDF = sql("select empno,ename,sal,deptno from default.emp").show()
  val  hiveDF= spark.table("default.emp")

    val mysqlDF = spark.read
      .format("jdbc")
      .option("url", "jdbc:mysql://192.168.137.251:3306/test_tmp")
      .option("dbtable", "dept")
      .option("user", "root")
      .option("password", "oracle")
      .load()


//hiveDF.join(mysqlDF,"deptno")

val resultDF =hiveDF.join(mysqlDF,hiveDF("deptno") === mysqlDF("deptno"),"left").show()
  //write.format("csv").
  //save("result/hive_mysql_join_sql/02/data123.csv")

resultDF.createOrReplaceTempView("result_sql")
spark.sql("select * from result_sql").show()

spark.stop() }}运行结果如下