SparkSQL读取hive数据本地idea运行 SparkSQL读取hive数据本地idea运行的方法详解

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 <modelVersion>4.0.0</modelVersion>
 
 <groupId>com.spark</groupId>
 <artifactId>spark_practice</artifactId>
 <version>1.0-SNAPSHOT</version>
 
 <properties>
  <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  <maven.compiler.source>1.8</maven.compiler.source>
  <maven.compiler.target>1.8</maven.compiler.target>
  <spark.core.version>2.3.0</spark.core.version>
 </properties>
 
 <dependencies>
  <dependency>
   <groupId>junit</groupId>
   <artifactId>junit</artifactId>
   <version>4.11</version>
   <scope>test</scope>
  </dependency>
  <dependency>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-core_2.11</artifactId>
   <version>${spark.core.version}</version>
  </dependency>
 
  <dependency>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-sql_2.11</artifactId>
   <version>${spark.core.version}</version>
  </dependency>
  <dependency>
   <groupId>mysql</groupId>
   <artifactId>mysql-connector-java</artifactId>
   <version>5.1.38</version>
  </dependency>
  <dependency>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-hive_2.11</artifactId>
   <version>2.3.0</version>
  </dependency>
 </dependencies>
 
</project>

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl" rel="external nofollow" ?>
<configuration> 
<!-- hive元数据服务url -->
 <property>
 <name>hive.metastore.uris</name>
 <value>thrift://192.168.100.201:9083</value>
 </property>
 <property>
 <name>hive.server2.thrift.port</name>
 <value>10000</value>
 </property> 
 <property>  
  <name>javax.jdo.option.ConnectionURL</name>
  <value>jdbc:mysql://node01:3306/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>123456</value>
 </property>
 <property>
  <name>hive.zookeeper.quorum</name>
   <value>node01,node02,node03</value>
  </property>
 
  <property>
  <name>hbase.zookeeper.quorum</name>
   <value>node01,node02,node03</value>
  </property>
  <!-- hive在hdfs上的存储路径 -->
 <property>
 <name>hive.metastore.warehouse.dir</name>
 <value>/user/hive/warehouse</value>
 </property>
 <!-- 集群hdfs访问url -->
 <property>
 <name>fs.defaultFS</name>
 <value>hdfs://192.168.100.201:9000</value>
 </property>
 <property>
 <name>hive.metastore.schema.verification</name>
 <value>false</value>
 </property>
 <property>
 <name>datanucleus.autoCreateSchema</name>
 <value>true</value>
 </property>
 <property>
 <name>datanucleus.autoStartMechanism</name>
 <value>checked</value>
 </property>
 
</configuration>

import org.apache.spark.sql.SparkSession
 
object SparksqlTest2 {
 def main(args: Array[String]): Unit = {
 
 val spark: SparkSession = SparkSession
  .builder
  .master("local[*]")
  .appName("Java Spark Hive Example")
  .enableHiveSupport
  .getOrCreate
 
 spark.sql("show databases").show()
 spark.sql("show tables").show()
 spark.sql("select * from person").show()
 spark.stop()
 }
}

./bin/hive --service metastore