HDFS客户端及API的操作

HDFS客户端环境准备

　　1.根据本机windows操作系统使用对应编译hadoop的jar包到非中文目录下（目录不能包含空格，如:D:\Develop\hadoop-2.7.2）

　　2.配置HADOOP_HOME环境变量

　　3.配置Path环境变量

　　4.使用idea创建一个Maven工程hdfsClient

　　 5.导入相应的依赖包　　　

<?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.hdfs.client</groupId>
    <artifactId>hdfsClient</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
    </dependencies>
</project>

　　　　在项目的src/main/resources目录下，新建一个文件，命名为“log4j.properties”，在文件中填入

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

　　6.创建HdfsClient类

package com.hdfs.client;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.junit.Test;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

public class HdfsClient {
    @Test
    public void testMkdirs() throws IOException, InterruptedException, URISyntaxException {

        // 1 获取文件系统
        Configuration configuration = new Configuration();
        // 配置在集群上运行
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"), configuration, "hadoop");

        // 2 创建目录
        fs.mkdirs(new Path("/test/hdfs"));

        // 3 关闭资源
        fs.close();
    }
}

HDFS的API操作

1.文件上传

    @Test
    public void testCopyFromLocalFile() throws URISyntaxException, IOException, InterruptedException {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),conf,"hadoop");
        fs.copyFromLocalFile(new Path("D:\\Develop\\hadoopWorkSpace\\test.txt"),new Path("/test/hdfs/test.txt"));
        fs.close();
    }

　　注意:hdfs设置生成的副本数，可以在服务器hadoop的hdfs-site.xml中设置，也可以客户端项目中的resources下用户自定义配置文件，也可在代码中设置值

　　服务器的默认配置

　　客户端项目下的配置文件

　　客户端代码中设置的值

　　这三者的优先级

　　　　客户端代码中设置的值 > 客户端项目下的配置文件 > 服务器的默认配置

2.文件下载

    @Test
    public void testCopyToLocalFile() throws IOException, URISyntaxException, InterruptedException {
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),configuration,"hadoop");
        // boolean delSrc 指是否将原文件删除
        // Path src 指要下载的文件路径
        // Path dst 指将文件下载到的路径
        // boolean useRawLocalFileSystem 是否开启文件校验 false 用该方法会生成(.文件名.txt.crc)的文件
//        fs.copyToLocalFile(new Path("/test/hdfs/test.txt"),new Path("d:\\Develop\\hadoopWorkSpace\\test1.txt"));
        fs.copyToLocalFile(false,new Path("/test/hdfs/test.txt"),new Path("d:\\Develop\\hadoopWorkSpace\\test1.txt"),true);
        fs.close();
    }

3.文件夹删除

　　 @Test
    public void testDelete() throws IOException, URISyntaxException, InterruptedException {
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),configuration,"hadoop");
        fs.delete(new Path("/a"),true); //true表示文件夹下的所有文件也要删除(递归) false 只删除文件
        fs.close();
    }

4.文件名更改

    @Test
    public void testRename() throws IOException, URISyntaxException, InterruptedException {
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),configuration,"hadoop");
        fs.rename(new Path("/test/hdfs/test.txt"),new Path("/test/hdfs/test1.txt"));
        fs.close();
    }

5.文件详情查看

    @Test
    public void testListFiles() throws IOException, InterruptedException, URISyntaxException{
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),configuration,"hadoop");

        RemoteIterator<LocatedFileStatus> listFiles = fs.listFiles(new Path("/"), true);

        while(listFiles.hasNext()){
            LocatedFileStatus status = listFiles.next();
            // 输出详情
            // 文件名称
            System.out.println(status.getPath().getName());
            // 长度
            System.out.println(status.getLen());
            // 权限
            System.out.println(status.getPermission());
            // 分组
            System.out.println(status.getGroup());

            // 获取存储的块信息
            BlockLocation[] blockLocations = status.getBlockLocations();

            for (BlockLocation blockLocation : blockLocations) {
                // 获取块存储的主机节点
                String[] hosts = blockLocation.getHosts();
                for (String host : hosts) {
                    System.out.println(host);
                }
            }
            System.out.println("---------分割线----------");
        }
        fs.close();
    }

6.文件和文件夹判断

    @Test
    public void testListStatus() throws IOException, InterruptedException, URISyntaxException{
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"),configuration,"hadoop");

        // 2 判断是文件还是文件夹
        FileStatus[] listStatus = fs.listStatus(new Path("/"));

        for (FileStatus fileStatus : listStatus) {
            // 如果是文件
            if (fileStatus.isFile()) {
                System.out.println("file:"+fileStatus.getPath().getName());
            }else {
                System.out.println("dir:"+fileStatus.getPath().getName());
            }
        }
        fs.close();
    }

HDFS的I/O流操作（上面的API操作HDFS系统都是框架封装好的）

采用IO流的方式实现数据的上传和下载

1.HDFS文件上传

@Test
public void putFileToHDFS() throws IOException, InterruptedException, URISyntaxException {
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"), configuration, "hadoop");

    FileInputStream fis = new FileInputStream(new File("d:/test.txt"));

    FSDataOutputStream fos = fs.create(new Path("/test.txt"));

    // 流对拷
    IOUtils.copyBytes(fis, fos, configuration);

    // 关闭资源
    IOUtils.closeStream(fos);
    IOUtils.closeStream(fis);
    fs.close();
}

2.HDFS文件下载

@Test
public void getFileFromHDFS() throws IOException, InterruptedException, URISyntaxException{
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"), configuration, "hadoop");
        
    FSDataInputStream fis = fs.open(new Path("/test.txt"));
        
    //获取输出流
    FileOutputStream fos = new FileOutputStream(new File("d:/test1.txt"));
        
    // 流的对拷
    IOUtils.copyBytes(fis, fos, configuration);
        
    // 关闭资源
    IOUtils.closeStream(fos);
    IOUtils.closeStream(fis);
    fs.close();
}

3.定位文件读取

下载200M的文件

1)第一步

@Test
public void readFileFirst() throws IOException, InterruptedException, URISyntaxException{

    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"), configuration, "hadoop");
        
    FSDataInputStream fis = fs.open(new Path("/hadoop-2.7.2.tar.gz"));
        
    FileOutputStream fos = new FileOutputStream(new File("d:/hadoop-2.7.2.tar.gz.part1"));
        
    // 流的拷贝,先读取128M大小的文件
    byte[] buf = new byte[1024];
        
    for(int i =0 ; i < 1024 * 128; i++){
        fis.read(buf);
        fos.write(buf);
    }
        
    // 关闭资源
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);
　　 fs.close();
}

2）第二步

@Test
public void readFileSecord() throws IOException, InterruptedException, URISyntaxException{

    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://192.168.1.11:9000"), configuration, "hadoop");
        
    FSDataInputStream fis = fs.open(new Path("/hadoop-2.7.2.tar.gz"));
        
    // 定位输入数据位置(第一步已下载了128M，第二步从128M后开始拷贝)
    fis.seek(1024*1024*128);
        
    FileOutputStream fos = new FileOutputStream(new File("d:/hadoop-2.7.2.tar.gz.part2"));
        
    IOUtils.copyBytes(fis, fos, configuration);
        
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);
    fs.close();
}

3）第三步

在Window命令窗口中进入到目录D:\，然后执行如下命令，对数据进行合并

type hadoop-2.7.2.tar.gz.part2 >> hadoop-2.7.2.tar.gz.part1

合并完成后，将hadoop-2.7.2.tar.gz.part1重新命名为hadoop-2.7.2.tar.gz。解压发现该tar包非常完整。