HDFS API编程：常用HDFS操作实现

使用常见API实现对hdfs文件系统的一系列基础操作即‘增删改查’：
创建HDFS文件夹
输出副本系数
创建文件
查看HDFS文件内容
文件名更改
拷贝本地文件到HDFS文件系统
拷贝本地大文件到HDFS文件系统，带进度条
下载HDFS文件到本地
查看文件夹下所有文件
递归查看文件夹下所有文件
查看文件块信息
删除文件

package com.haglife.bigdata.hadoop.hdfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.util.Progressable;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.net.URI;
import java.util.Arrays;

public class HDFSBasicOperation {
    public static final String HDFS_PATH = "hdfs://masternode:8020";
    Configuration configuration = null;
    FileSystem fileSystem = null;

    @Before
    public void setUp() throws Exception {
        System.out.println("----------setUp----------");
        configuration = new Configuration();
        configuration.set("dfs.replication", "2");
        
        fileSystem = FileSystem.get(new URI(HDFS_PATH), configuration, "uname");
    }

    // 创建HDFS文件夹
    @Test
    public void mkdir() throws Exception {
        fileSystem.mkdirs(new Path("/hdfsapi/test"));
    }

    // 输出副本系数
    @Test
    public void Replication() {
        System.out.println(configuration.get("dfs.replication"));
    }

    // 创建文件
    @Test
    public void create_text() throws Exception {
        FSDataOutputStream out = fileSystem.create(new Path("/hdfsapi/test/maven_intro.txt"));
        out.writeUTF("maven翻译为“专家”，“内行”。Maven是Apache下的一个纯java开发的开源项目，它是一个项目管理工具，" +
                        "使用maven对java项目进行构建、依赖管理。当前使用Maven的项目在持续增长。n");
        out.flush();
        out.close();
    }

    // 查看HDFS文件内容
    @Test
    public void text() throws Exception {
        FSDataInputStream in = fileSystem.open(new Path("/hdfsapi/test/maven_intro.txt"));
        IOUtils.copyBytes(in, System.out, 1024);
    }

    // 文件名更改
    @Test
    public void rename() throws Exception {
        Path oldPath = new Path("/hdfsapi/test/maven_intro.txt");
        Path newPath = new Path("/hdfsapi/test/maven_introduce.txt");
        boolean result = fileSystem.rename(oldPath, newPath);
        System.out.println(result);
    }

    // 拷贝本地文件到HDFS文件系统
    @Test
    public void copyFromLocalFile() throws Exception {
        Path localPath = new Path("E:\大数据\hadoop\...\temp.txt");
        Path targetPath = new Path("/hdfsapi/test/");
        fileSystem.copyFromLocalFile(localPath, targetPath);
    }

    // 拷贝本地大文件到HDFS文件系统，带进度条
    @Test
    public void copyFromLocalBigFile() throws Exception {
        InputStream in = new BufferedInputStream(new FileInputStream(new File("E:\大数据\hadoop\...\jdk-8u161-linux-x64.tar.gz")));
        FSDataOutputStream out = fileSystem.create(new Path("/hdfsapi/test/jdk.tar.gz"),
                new Progressable() {
                    @Override
                    public void progress() {
                        System.out.print("#");
                    }
                });

        IOUtils.copyBytes(in, out, 4096);
    }

    // 下载HDFS文件到本地
    @Test
    public void copyToLocalFile() throws Exception {
        Path src = new Path("/hdfsapi/test/maven_introduce.txt");
        Path dst = new Path("E:\大数据\hadoop\...\hdfs");
        fileSystem.copyToLocalFile(false, src, dst, true);
    }

    // 查看文件夹下所有文件
    @Test
    public void listFiles() throws Exception {
        
        FileStatus[] statuses = fileSystem.listStatus(new Path("/hdfsapi/test/"));
        System.out.println("statuses:" + Arrays.toString(statuses));

        for(FileStatus file: statuses) {
            String path = file.getPath().toString();
            String isDir = file.isDirectory() ? "文件夹": "文件";
            String permission = file.getPermission().toString();
            short replication = file.getReplication();
            long length = file.getLen();

            System.out.println(path + 't' +
                    isDir + 't' +
                    permission + 't' +
                    replication + 't' +
                    length);
        }
    }

    // 递归查看文件夹下所有文件
    @Test
    public void listFilesRecursive() throws Exception {
        RemoteIterator files = fileSystem.listFiles(new Path("/hdfsapi/test/"), true);  // 返回一个迭代器
        System.out.println(files);

        // 迭代 迭代器
        while (files.hasNext()) {
            LocatedFileStatus file = files.next();
            String path = file.getPath().toString();
            String isDir = file.isDirectory() ? "文件夹": "文件";
            String permission = file.getPermission().toString();
            short replication = file.getReplication();
            long length = file.getLen();

            System.out.println(path + 't' +
                    isDir + 't' +
                    permission + 't' +
                    replication + 't' +
                    length);
        }

    }

    // 查看文件块信息
    @Test
    public void getFileBlockInfo() throws Exception {
        FileStatus fileStatus = fileSystem.getFileStatus(new Path("/hdfsapi/test/jdk.tar.gz"));
        System.out.println("fileStatus:" + fileStatus);
        BlockLocation[] blocks = fileSystem.getFileBlockLocations(fileStatus, 0, fileStatus.getLen());

        for(BlockLocation block: blocks) {
            System.out.println(block);
            for(String name: block.getNames()) {
                System.out.println(Arrays.toString(block.getHosts()) + " - " + name + " - " + block.getOffset() + " - " + block.getLength());
            }
        }
    }

    // 删除文件
    @Test
    public void delete() throws Exception {
        boolean result = fileSystem.delete(new Path("/hdfsapi/test/jdk.tar.gz"), true);
        System.out.println(result);
    }

    @After
    public void tearDown() {
        configuration = null;
        fileSystem = null;
        System.out.println("----------tearDown----------");
    }
}