首先新建个maven项目:
<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.lm.hive</groupId>
<artifactId>SparkHive</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<name>SparkHive</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.10</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.10</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.10</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka_2.10</artifactId>
<version>1.5.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-graphx_2.10</artifactId>
<version>1.5.2</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/java</sourceDirectory>
<testSourceDirectory>src/main/test</testSourceDirectory>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<archive>
<manifest>
<mainClass></mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>exec-maven-plugin</artifactId>
<version>1.2.1</version>
<executions>
<execution>
<goals>
<goal>exec</goal>
</goals>
</execution>
</executions>
<configuration>
<executable>java</executable>
<includeProjectDependencies>true</includeProjectDependencies>
<includePluginDependencies>false</includePluginDependencies>
<classpathScope>compile</classpathScope>
<mainClass>com.lm.hive.SparkHive.App</mainClass>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
</plugins>
</build>
</project>
新建个java 文件
import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.hive.HiveContext;
public class App {
public static void main(String[] args) {
SparkConf sparkConf = new SparkConf().setAppName("SparkHive").setMaster("local[2]");
SparkContext sc = new SparkContext(sparkConf);
try {
HiveContext hiveContext = new HiveContext(sc);
DataFrame myHiveData = hiveContext.sql("select * from bicoredata.dws_device_service_active_dm");
myHiveData.show();
DataFrame myBuilder = myHiveData.describe("pt_service");
} catch (Exception e) {
e.printStackTrace();
} finally {
if (null != sc) {
sc.stop();
}
}
}
}
./spark-submit --class com.lm.hive.SparkHive.App --master local[2] --files /home/hadoopuser/spark/conf/hive-site.xml /home/hadoopuser/SparkHive-0.0.1-SNAPSHOT.jar