Spring配置Hadoop

核心

• 将Hadoop中的FileSystem的创建通过Spring的依赖注入的方式进行创建
• 其他的操作与Java操作Hadoop的API方式是一致的

项目工程

• Maven工程

Maven的setting.xml文件配置

。。。
<mirror>
    <id>nexus</id>
    <mirrorOf>*,!cloudera</mirrorOf>
    <url>http://repo1.maven.org/maven2/</url>
</mirror>
。。。

pom配置

<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.peng</groupId>
    <artifactId>hdfstest</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <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>


    <!--配置下载的仓库-->
    <repositories>
        <repository>
            <id>repo</id>
            <url>http://repo1.maven.org/maven2/</url>
        </repository>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/content/repositories/releases/</url>
        </repository>
    </repositories>


    <!--配置依赖【注：源pom文件有冲突的依赖配置进行手动删除】-->
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-cdh5.7.0</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.10</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.mortbay.jetty</groupId>
            <artifactId>jetty</artifactId>
            <version>6.1.26</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.25</version>
            <scope>test</scope>
        </dependency>

        <!--spring hadoop start-->
        <dependency>
            <groupId>org.springframework.data</groupId>
            <artifactId>spring-data-hadoop</artifactId>
            <version>2.5.0.RELEASE</version>
        </dependency>
        <!--spring hadoop end-->

    </dependencies>

</project>

配置文件【resources下】

• application.properties【配置文件，映射键值对】

  spring.hadoop.fsUri=hdfs://centos00:8020
  

• beans.xml【依赖注入的功能】

  <xml version="1.0" encoding="UTF-8">
  <beans xmlns="http://www.springframework.org/schema/beans"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xmlns:hdp="http://www.springframework.org/schema/hadoop"
         xmlns:context="http://www.springframework.org/schema/context"
         xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd
          http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context.xsd
          http://www.springframework.org/schema/hadoop http://www.springframework.org/schema/hadoop/spring-hadoop.xsd">
  
      <!--加载配置文件-->
      <context:property-placeholder location="application.properties"/>
  
      <!--hadoop的配置-->
      <hdp:configuration id="hadoopConfiguration">
          fs.defaultFS=${spring.hadoop.fsUri}
      </hdp:configuration>
  
      <!--文件系统的配置-->
      <hdp:file-system id="fileSystem" configuration-ref="hadoopConfiguration" user="root"></hdp:file-system>
  
  </beans>
  

测试程序

• SpringHadoopTest.java

  package com.peng;
  
  import org.apache.hadoop.fs.FileSystem;
  import org.apache.hadoop.fs.Path;
  import org.junit.After;
  import org.junit.Before;
  import org.junit.Test;
  import org.springframework.context.ApplicationContext;
  import org.springframework.context.support.ClassPathXmlApplicationContext;
  
  public class SpringHadoopTest {
      private ApplicationContext ctx;
      FileSystem fileSystem;
  
      @Test
      public void testMain() throws Exception {
          fileSystem.mkdirs(new Path("/springfile"));
      }
  
      @Before
      public void setUp() throws Exception {
          System.out.println("==================start======================");
          ctx = new ClassPathXmlApplicationContext("beans.xml");
          fileSystem = (FileSystem) ctx.getBean("fileSystem");
      }
  
      @After
      public void clearTail() throws Exception {
          ctx = null;
          fileSystem.close();
          System.out.println("====================end======================");
      }
  }