Hadoop集成Spring的使用详细教程(快速入门大数据)

官网sprng-hadoop

https://spring.io/projects/spring-hadoop

添加依赖

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

使用spring hadoop配置及查看HDFS文件

新建资源文件beans.xml

<?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"
  xsi:schemaLocation="
  http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd
  http://www.springframework.org/schema/hadoop
  http://www.springframework.org/schema/hadoop/spring-hadoop.xsd">

 <hdp:configuration id="hadoopConfiguration">
  fs.defaultFS=hdfs://hadoop01:9000
  hadoop.tmp.dir=/tmp/hadoop
  electric=sea
 </hdp:configuration>

 <hdp:file-system id="fileSystem"
      configuration-ref="hadoopConfiguration"
      user="root"
 />

</beans>

测试文件

package com.bennyrhys.hadoop.spring;

import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import org.springframework.context.ApplicationContext;
import org.springframework.context.support.ClassPathXmlApplicationContext;

import java.io.IOException;

/**
 * @Author bennyrhys
 * @Date 1/21/21 2:35 PM
 */
public class SpringHadoopHDFSApp {
 private ApplicationContext ctx;
 // apache hadoop
 private FileSystem fileSystem;

 /**
  * 创建HDFS文件夹
  */
 @Test
 public void testMkdirs() throws Exception {
  fileSystem.mkdirs(new Path("/springhdfs"));
 }

 /**
  * 查看HDFS文件
  */
 @Test
 public void testText() throws Exception {
  FSDataInputStream in = fileSystem.open(new Path("/springhdfs/hello.txt"));
  IOUtils.copyBytes(in, System.out, 1024);
  in.close();
 }

 @Before
 public void setUp() {
  ctx = new ClassPathXmlApplicationContext("beans.xml");
  fileSystem = (FileSystem) ctx.getBean("fileSystem");
 }

 @After
 public void tearDown() throws Exception {
  ctx = null;
  fileSystem.close();
 }
}

spring hadoop 配置文件详解

提取变量

使用xml中的头文件替换bean，使其允许使用上下文
${}导入变量

新建配置文件application.properties

spring.hadoop.fsUri=hdfs://hadoop01:9000

获取context上下文引入变量
beans.xml

<?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">

 <hdp:configuration id="hadoopConfiguration">
  fs.defaultFS=${spring.hadoop.fsUri}
  hadoop.tmp.dir=/tmp/hadoop
  electric=sea
 </hdp:configuration>
 <context:property-placeholder location="application.properties"/>

 <hdp:file-system id="fileSystem"
      configuration-ref="hadoopConfiguration"
      user="root"
 />

</beans>

SpringBoot访问HDFS系统

pom.xml

<!-- 添加spring boot的依赖操作hadoop -->
 <dependency>
  <groupId>org.springframework.data</groupId>
  <artifactId>spring-data-hadoop-boot</artifactId>
  <version>2.5.0.RELEASE</version>
 </dependency>

SpringBootHDFSApp

package com.bennyrhys.hadoop.spring;

import org.apache.hadoop.fs.FileStatus;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.data.hadoop.fs.FsShell;

/**
 * @Author bennyrhys
 * @Date 1/21/21 11:33 PM
 */
@SpringBootApplication
public class SpringBootHDFSApp implements CommandLineRunner {

 @Autowired
 FsShell fsShell; //引入spring的

 @Override
 public void run(String... strings) throws Exception {
  for (FileStatus fileStatus : fsShell.lsr("/springhdfs")) {
   System.out.println("> " + fileStatus.getPath());
  }
 }

 /**
  * > hdfs://hadoop01:9000/springhdfs
  * > hdfs://hadoop01:9000/springhdfs/hello.txt
  * @param args
  */
 public static void main(String[] args) {
  SpringApplication.run(SpringBootHDFSApp.class, args);
 }
}

到此这篇关于Hadoop集成Spring的使用详细教程(快速入门大数据)的文章就介绍到这了,更多相关Hadoop集成Spring的使用内容请搜索呐喊教程以前的文章或继续浏览下面的相关文章希望大家以后多多支持呐喊教程！

声明：本文内容来源于网络，版权归原作者所有，内容由互联网用户自发贡献自行上传，本网站不拥有所有权，未作人工编辑处理，也不承担相关法律责任。如果您发现有涉嫌版权的内容，欢迎发送邮件至：notice#nhooo.com（发邮件时，请将#更换为@）进行举报，并提供相关证据，一经查实，本站将立刻删除涉嫌侵权内容。