Hadoop API的使用

本次实验环境是在windows系统下，通过windows的hadoop依赖在IDEA进行

首先需要下载windows支持的hadoop依赖程序

以下是下载链接

winutils-1: winutils.exe hadoop.dll and hdfs.dll binaries for hadoop windows - Gitee.com 

解压后还需要配置环境变量

 

 

 

---

接下来就可以在 IDEA 通过 Maven 来使用 Hadoop 的API函数啦，以下是项目目录结构

 以下是 pom.xml 依赖

<?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.atguigu</groupId>
    <artifactId>HDFSClient</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.2.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.36</version>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13.2</version>
            <scope>compile</scope>
        </dependency>
    </dependencies>

</project>

 以下是 log4j.properties 的配置信息

log4j.rootLogger=INFO, stdout  
log4j.appender.stdout=org.apache.log4j.ConsoleAppender  
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  
log4j.appender.logfile=org.apache.log4j.FileAppender  
log4j.appender.logfile.File=target/spring.log  
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

以下是 HdfsClient.java 测试HadoopAPI函数的源码，这里要注意导包别导错了

package com.atguigu.hdfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.junit.*;


import java.io.IOException;
import java.lang.reflect.Array;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.Arrays;


public class HdfsClient {

    private FileSystem fs;

    @Before
    public void init() throws URISyntaxException, IOException, InterruptedException {

        // 连接的集群nn地址
        URI uri = new URI("hdfs://hadoop102:8020");

        // 创建一个配置文件
        Configuration configuration = new Configuration();

        configuration.set("dfs.replication", "2");

        // 指定用户
        String user = "hadoop";

        // 获取客户端对象
        fs = FileSystem.get(uri, configuration, user);

    }

    @After
    public void close() throws IOException {

        // 关闭资源
        fs.close();
    }

    @Test
    public void testMkdir() throws IOException {

        // 创建一个文件夹
        fs.mkdirs(new Path("/xiyou/huaguoshan1"));

    }

    /**
     * 参数优先级
     * hdfs-default.xml => hdfs.site.xml => 在项目资源目录下的配置文件 => 代码里面的配置
     *
     * @throws IOException
     */
    // 上传
    @Test
    public void testPut() throws IOException {

        fs.copyFromLocalFile(false, true, new Path("D:\\sunwukong.txt"), new Path("hdfs://hadoop102/xiyou/huaguoshan"));

    }

    // 文件下载
    @Test
    public void testGet() throws IOException {

        fs.copyToLocalFile(true, new Path("hdfs://hadoop102/xiyou/huaguoshan"), new Path("D:\\"), true);

    }

    // 删除
    @Test
    public void testRm() throws IOException {

        // 删除文件
//        fs.delete(new Path("/jdk-8u321-linux-x64.tar.gz"), false);

        // 删除空目录
//        fs.delete(new Path("/xiyou"), false);

        // 删除非空目录
        fs.delete(new Path("/jinguo"), true);

    }

    // 文件的更名和移动
    @Test
    public void testMv() throws IOException {

        // 修改文件名
//        fs.rename(new Path("/input/word.txt"), new Path("/input/ss.txt"));

        // 移动文件
//        fs.rename(new Path("/input/ss.txt"), new Path("/cls.txt"));

        // 目录更名
        fs.rename(new Path("/input"), new Path("/output"));

    }
    // 获取文件详细信息
    @Test
    public void fileDetail() throws IOException {

        // 获取所有文件信息
        RemoteIterator<LocatedFileStatus> listFiles = fs.listFiles(new Path("/"), true);

        // 遍历文件
        while (listFiles.hasNext()) {
            LocatedFileStatus fileStatus = listFiles.next();

            System.out.println("========" + fileStatus.getPath() + "========");
            System.out.println(fileStatus.getPermission());
            System.out.println(fileStatus.getOwner());
            System.out.println(fileStatus.getGroup());
            System.out.println(fileStatus.getLen());
            System.out.println(fileStatus.getModificationTime());
            System.out.println(fileStatus.getReplication());
            System.out.println(fileStatus.getBlockSize());
            System.out.println(fileStatus.getPath().getName());

            // 获取块信息
            BlockLocation[] blockLocations = fileStatus.getBlockLocations();
//  从0位置读取128M                              从134217728位置读128M
// [0,134217728,hadoop103,hadoop104,hadoop102, 134217728,134217728,hadoop104,hadoop103,hadoop102, 268435456,134217728,hadoop104,hadoop103,hadoop102, 402653184,89588777,hadoop104,hadoop103,hadoop102]
            System.out.println(Arrays.toString(blockLocations));

        }
    }
    
    // 判断是文件夹还是文件
    @Test
    public void testFile() throws IOException {

        FileStatus[] fileStatuses = fs.listStatus(new Path("/"));

        for (FileStatus status : fileStatuses) {
            if (status.isFile()) {
                System.out.println("文件:" + status.getPath().getName());
            } else {
                System.out.println("目录:" + status.getPath().getName());
            }
        }
    }

}