大数据Hadoop（三）HDFS的Java API操作(1)

大家好，我是脚丫先生 (o^^o)

前面介绍了HDFS的基本概念，那么接下来就对HDFS分布式文件系统进行实践。

好了，我们开始今天的正文。

---

一、HDFS的shell(命令行客户端)操作

• 1．基本语法
  bin/hadoop fs 具体命令 或者 bin/hdfs dfs 具体命令
• 2．命令大全

$ bin/hadoop fs
 
[-appendToFile <localsrc> ... <dst>]
        [-cat [-ignoreCrc] <src> ...]
        [-checksum <src> ...]
        [-chgrp [-R] GROUP PATH...]
        [-chmod [-R] <MODE[,MODE]... | OCTALMODE> PATH...]
        [-chown [-R] [OWNER][:[GROUP]] PATH...]
        [-copyFromLocal [-f] [-p] <localsrc> ... <dst>]
        [-copyToLocal [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
        [-count [-q] <path> ...]
        [-cp [-f] [-p] <src> ... <dst>]
        [-createSnapshot <snapshotDir> [<snapshotName>]]
        [-deleteSnapshot <snapshotDir> <snapshotName>]
        [-df [-h] [<path> ...]]
        [-du [-s] [-h] <path> ...]
        [-expunge]
        [-get [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
        [-getfacl [-R] <path>]
        [-getmerge [-nl] <src> <localdst>]
        [-help [cmd ...]]
        [-ls [-d] [-h] [-R] [<path> ...]]
        [-mkdir [-p] <path> ...]
        [-moveFromLocal <localsrc> ... <dst>]
        [-moveToLocal <src> <localdst>]
        [-mv <src> ... <dst>]
        [-put [-f] [-p] <localsrc> ... <dst>]
        [-renameSnapshot <snapshotDir> <oldName> <newName>]
        [-rm [-f] [-r|-R] [-skipTrash] <src> ...]
        [-rmdir [--ignore-fail-on-non-empty] <dir> ...]
        [-setfacl [-R] [{-b|-k} {-m|-x <acl_spec>} <path>]|[--set <acl_spec> <path>]]
        [-setrep [-R] [-w] <rep> <path> ...]
        [-stat [format] <path> ...]
        [-tail [-f] <file>]
        [-test -[defsz] <path>]
        [-text [-ignoreCrc] <src> ...]
        [-touchz <path> ...]
        [-usage [cmd ...]]

• 3．常用命令实操

(0) 启动Hadoop集群

$ sbin/start-dfs.sh
$ sbin/start-yarn.sh

(1) -help：输出这个命令参数

$ hadoop fs -help rm

(2) -ls: 显示目录信息

$ hadoop fs -ls /

(3) -mkdir：在HDFS上创建目录

$ hadoop fs -mkdir -p /sanguo/shuguo

(4) -moveFromLocal：从本地剪切粘贴到HDFS

$ touch kongming.txt
$ hadoop fs  -moveFromLocal  ./kongming.txt  /sanguo/shuguo

(5) -appendToFile：追加一个文件到已经存在的文件末尾

$ touch liubei.txt
$ vi liubei.txt
输入
san gu mao lu
$ hadoop fs -appendToFile liubei.txt /sanguo/shuguo/kongming.txt

(6) -cat：显示文件内容

$ hadoop fs -cat /sanguo/shuguo/kongming.txt

(7) -chgrp 、-chmod、-chown：Linux文件系统中的用法一样，修改文件所属权限

$ hadoop fs  -chmod 777    /sanguo/shuguo/kongming.txt
$ hadoop fs  -chown  atguigu:atguigu   /sanguo/shuguo/kongming.txt

(8) -copyFromLocal：从本地文件系统中拷贝文件到HDFS路径去

$ hadoop fs -copyFromLocal README.txt /

(9) -copyToLocal：从HDFS拷贝到本地

$ hadoop fs -copyToLocal /sanguo/shuguo/kongming.txt ./

(10) -cp ：从HDFS的一个路径拷贝到HDFS的另一个路径

$ hadoop fs -cp /sanguo/shuguo/kongming.txt /zhuge.txt

(11) -mv：在HDFS目录中移动文件

$ hadoop fs -mv /zhuge.txt /sanguo/shuguo/

(12) -get：等同于copyToLocal，就是从HDFS下载文件到本地

$ hadoop fs -get /sanguo/shuguo/kongming.txt ./

(13) -getmerge：合并下载多个文件，比如HDFS的目录 /user/atguigu/test下有多个文件:log.1, log.2,log.3,…

$ hadoop fs -getmerge /user/atguigu/test/* ./zaiyiqi.txt

(14) -put：等同于copyFromLocal

$ hadoop fs -put ./zaiyiqi.txt /user/atguigu/test/

(15) -tail：显示一个文件的末尾

$ hadoop fs -tail /sanguo/shuguo/kongming.txt

(16) -rm：删除文件或文件夹

$ hadoop fs -rm /user/atguigu/test/jinlian2.txt

(17) -rmdir：删除空目录

$ hadoop fs -rmdir /test

(18) 删除不为空的目录

$ hadoop fs -rm -r -f /test

(19) -du统计文件夹的大小信息

$ hadoop fs -du -s -h /user/atguigu/test
2.7 K  /user/atguigu/test
 
$ hadoop fs -du  -h /user/atguigu/test
 
1.3 K  /user/atguigu/test/README.txt
     /user/atguigu/test/jinlian.txt
1.4 K  /user/atguigu/test/zaiyiqi.txt

(20) -setrep：设置HDFS中文件的副本数量

$ hadoop fs -setrep  /sanguo/shuguo/kongming.txt

二、HDFS的java api操作

主

package hdfs;

import org.apache.hadoop.conf.Configuration;

import java.io.IOException;

/**
 * @date : 14:06 2020/11/29
 */
public class HdfsOperotor {

    public static void main(String[] args) throws IOException {
        // 1 获取文件系统
        Configuration conf = new Configuration();
        //配置在集群上运行
        conf.set("fs.defaultFS", "hdfs://192.168.239.128:8020");
        //设置用户(设置为集群的用户，才会有权限)
        System.setProperty("HADOOP_USER_NAME","bigdata");
        //Path path = new Path("hdfs://192.168.239.128:9000/bigdata/shujuelin");
        HDFSUtil.mkdir(conf, "hdfs://192.168.239.128:8020/bigdata");

    }

}

工具类

package hdfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

import java.io.ByteArrayOutputStream;
import java.io.IOException;


/**
 *
 * @date : 13:57 2020/11/29
 * HDFS 工具类
 */
public  class HDFSUtil {

    private HDFSUtil() {
    }
    /**
     * 新建文件
     *
     * @param conf
     * @param filePath
     * @param data
     * @throws IOException
     */
    public static void createFile(Configuration conf, String filePath,
                                  byte[] data) throws IOException {
        //JavaApi对HDFS的操作只要或得一个fileSystem对象就可以了
        FileSystem fs = FileSystem.get(conf);
        //FileSystem 使用FSDataOutputStream 及FSDataInputStream来读写流的内容
        FSDataOutputStream outputStream = fs.create(new Path(filePath));
        outputStream.write(data);
        //字节输出流
        outputStream.close();
        fs.close();
    }

    /**
     * 新建文件
     *
     * @param conf
     * @param filePath
     * @param data
     * @throws IOException
     */
    public static void createFile(Configuration conf, String filePath,
                                  String data) throws IOException {
        //data.getBytes()获取字节
        createFile(conf, filePath, data.getBytes());
    }

    /**
     * 从本地上传到HDFS
     * @param conf
     * @param localPath 本地文件路径
     * @param remotePath HDF文件S路径
     * @throws IllegalArgumentException
     * @throws IOException
     */
    public static void copyFileFromLocal(Configuration conf,String localPath,String remotePath) throws IllegalArgumentException, IOException{
        FileSystem fs = FileSystem.get(conf);
        fs.copyFromLocalFile(new Path(localPath), new Path(remotePath));
    }

    /**
     * 归删除文件
     * @param conf
     * @param filePath
     * recursive  是否递归
     * @return
     * @throws IllegalArgumentException
     * @throws IOException
     */
    public static boolean deleteFileRecursive(Configuration conf, String filePath) throws IllegalArgumentException, IOException{
        return deleteFile(conf,filePath,true);
    }

    /**
     * 非递归删除文件
     * @param conf
     * @param filePath
     * @return
     * @throws IllegalArgumentException
     * @throws IOException
     */
    public static boolean deleteFile(Configuration conf, String filePath) throws IllegalArgumentException, IOException{
        return deleteFile(conf,filePath,false);
    }

    /**
     * 删除文件
     * @param conf
     * @param filePath
     * @param recursive
     * @return
     * @throws IllegalArgumentException
     * @throws IOException
     */
    private static boolean deleteFile(Configuration conf, String filePath,boolean recursive) throws IllegalArgumentException, IOException{
        FileSystem fs = FileSystem.get(conf);
        return fs.delete(new Path(filePath),recursive);
    }

    /**
     * 创建文件夹
     *
     * @param conf
     * @param dirPath
     * @return
     * @throws IllegalArgumentException
     * @throws IOException
     */
    public static boolean mkdir(Configuration conf, String dirPath)
            throws IllegalArgumentException, IOException {
        FileSystem fs = FileSystem.get(conf);
        return fs.mkdirs(new Path(dirPath));
    }

    /**
     * 读取文件内容
     * @param conf
     * @param filePath
     * @return
     * @throws IOException
     */
    public static String readFile(Configuration conf, String filePath)
            throws IOException {
        String res = null;
        FileSystem fs = null;
        FSDataInputStream inputStream = null;
        ByteArrayOutputStream outputStream = null;
        try {
            fs = FileSystem.get(conf);
            //字节输入流
            inputStream = fs.open(new Path(filePath));
            //字节输出流
            outputStream = new ByteArrayOutputStream(inputStream.available());
            IOUtils.copyBytes(inputStream, outputStream, conf);
            res = outputStream.toString();
        } finally {
            if (inputStream != null)
                IOUtils.closeStream(inputStream);
            if (outputStream != null)
                IOUtils.closeStream(outputStream);
        }
        return res;
    }

    /**
     * 判断路径在HDFS上是否存在
     *
     * @param conf
     *            配置
     * @param path
     *            路径
     * @return
     * @throws IOException
     */
    public static boolean exits(Configuration conf, String path)
            throws IOException {
        FileSystem fs = FileSystem.get(conf);
        return fs.exists(new Path(path));
    }
}