spark2.0+ 使用Sparksession替代HiveContext
1.添加MAVEN依赖
<!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.35</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>2.1.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-hive -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.1.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.1.1</version>
</dependency>
2.编写SparkSession
package com.hualala.bi
import java.io.File
import org.apache.spark.sql.SparkSession
/**
*
* @author jiaquanyu
*
*/
object SparkSqlApp {
def main(args: Array[String]): Unit = {
case class Record(key: Int, value: String)
val warehouseLocation = new File("spark-warehouse").getAbsolutePath
val spark = SparkSession
.builder()
.appName("Spark SQL on hive")
.master("spark://192.168.4.4:7077")
.config("spark.sql.warehouse.dir", warehouseLocation)
.enableHiveSupport()
.getOrCreate()
spark.sql("show databases").collect().foreach(println)
}
}
3.将hive-site.xml保存到项目中的resources下 没有需创建
注:如需debug 建议spark-shell下进行