【Spark】帮你搞明白怎么通过SparkSQL整合Hive

文章目录

• 一、创建maven工程，导包
• 二、开发代码

---

一、创建maven工程，导包

<properties>
    <scala.version>2.11.8</scala.version>
    <spark.version>2.2.0</spark.version>
</properties>
<dependencies>
    <dependency>
        <groupId>org.scala-lang</groupId>
        <artifactId>scala-library</artifactId>
        <version>${scala.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.11</artifactId>
        <version>${spark.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.11</artifactId>
        <version>${spark.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.7.5</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.11</artifactId>
        <version>2.2.0</version>
    </dependency>
</dependencies>
<build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>3.0</version>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
                <encoding>UTF-8</encoding>
                <!--    <verbal>true</verbal>-->
            </configuration>
        </plugin>
        <plugin>
            <groupId>net.alchim31.maven</groupId>
            <artifactId>scala-maven-plugin</artifactId>
            <version>3.2.0</version>
            <executions>
                <execution>
                    <goals>
                        <goal>compile</goal>
                        <goal>testCompile</goal>
                    </goals>
                    <configuration>
                        <args>
                            <arg>-dependencyfile</arg>
                            <arg>${project.build.directory}/.scala_dependencies</arg>
                        </args>
                    </configuration>
                </execution>
            </executions>
        </plugin>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-shade-plugin</artifactId>
            <version>3.1.1</version>
            <executions>
                <execution>
                    <phase>package</phase>
                    <goals>
                        <goal>shade</goal>
                    </goals>
                    <configuration>
                        <filters>
                            <filter>
                                <artifact>*:*</artifact>
                                <excludes>
                                    <exclude>META-INF/*.SF</exclude>
                                    <exclude>META-INF/*.DSA</exclude>
                                    <exclude>META-INF/*.RSA</exclude>
                                </excludes>
                            </filter>
                        </filters>
                        <transformers>
                            <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                <mainClass></mainClass>
                            </transformer>
                        </transformers>
                    </configuration>
                </execution>
            </executions>
        </plugin>
    </plugins>
</build>

二、开发代码

package cn.itcast.sparksql.demo1

import org.apache.spark.SparkContext
import org.apache.spark.sql.SparkSession

object SparkSQLWithHive {
  def main(args: Array[String]): Unit = {
    // 获取SparkSession
    val sparkSession: SparkSession = SparkSession.builder().appName("sparksql_with_hive").master("local[2]").config("spark.driver.host", "localhost").enableHiveSupport().getOrCreate()

    // 获取SparkContext  这主要是为了筛选日志，是可选项，可以不创建
    val sparkContext: SparkContext = sparkSession.sparkContext
    sparkContext.setLogLevel("WARN")

    // 直接创建
    sparkSession.sql("create table if not exists student(id Int,name String,age Int) row format delimited fields terminated by ','")
    // 导入数据
    sparkSession.sql("load data local inpath './datas/student.csv' overwrite into table student")
    // 查询数据
    sparkSession.sql("select * from student").show()

    sparkContext.stop()
    sparkSession.close()
  }

}

控制台结果

+---+--------+---+
| id|    name|age|
+---+--------+---+
|  1|zhangsan| 18|
|  2|    lisi| 28|
|  3|      王五| 50|
+---+--------+---+

Process finished with exit code 0