HDFS的Java API

Java API应用

上传文件

先在本地（客户端）一个文件，比如在D盘下新建一个word2.txt文件，内容随便写

somewhere 
palyer
Hadoop
you belong to me

在IDEA中编写Java程序

package com.hadoop.hdfs;

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

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

public class PutFile {
    public static void main(String[] args) throws IOException, InterruptedException {
        //本地文件路径
        String local = "D:\\word2.txt";
        String dest = "hdfs://192.168.55.128:9000/input/word2.txt";
        Configuration cfg=new Configuration();
        FileSystem fs= FileSystem.get(URI.create(dest),cfg,"root");
        fs.copyFromLocalFile(new Path(local),new Path(dest));
        fs.close();


    }
}

再次说明，String dest="hdfs://192.168.80.128:9000/user/root/input/word2.txt"要与core-site.xml文件中的fs.defaultFS配置对应，其值是hdfs://node1:9000。由于本地Windows系统的hosts文件没有配置node1，所以这里需要IP地址表示。

执行结果

[root@node1 ~]# hdfs dfs -ls /input
Found 2 items
-rw-r--r--   3 root supergroup         52 2018-11-26 07:27 /input/word2.txt
-rw-r--r--   3 root supergroup         42 2018-11-26 04:10 /input/words.txt
[root@node1 ~]#

FileSystem fs= FileSystem.get(URI.create(dest),cfg,"root");语句中指定了root用户，这是因为Windows系统默认用户是Administrator。如果程序中不指定用户名root，则可能抛出异常：Permission denied: user=Administrator

下载文件

package com.hadoop.hdfs;

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

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

public class GetFile {
    public static void main(String[] args) throws IOException {
        String hdfsPath="hdfs://192.168.55.128:9000/input/words.txt";
        String localPath="D:/copy_words.txt";
        Configuration cfg=new Configuration();
        FileSystem fs=FileSystem.get(URI.create(hdfsPath),cfg);
        Path hdfs_path=new Path(hdfsPath);
        Path local_path=new Path(localPath);
        fs.copyToLocalFile(false,hdfs_path,local_path,true);
        fs.close();
    }
}

创建HDFS目录

package com.hadoop.hdfs;

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

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

public class CreateDtt {
    public static void main(String[] args) throws IOException, InterruptedException {
        String url = "hdfs://192.168.55.128:9000/tmp/";
        Configuration cfg=new Configuration();
        FileSystem fs= FileSystem.get(URI.create(url),cfg,"root");
        boolean b=fs.mkdirs(new Path(url));
        System.out.println(b);
        fs.close();
    }
}

删除HDFS文件或文件夹

先上传一个文件到HDFS的/tmp目录

[root@node1 ~]# hdfs dfs -put /root/words.txt /tmp
[root@node1 ~]# hdfs dfs -ls /tmp
Found 1 items
-rw-r--r--   3 root supergroup         42 2018-11-26 08:08 /tmp/words.txt

package com.hadoop.hdfs;

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

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

public class DeleteFile {
    public static void main(String[] args) throws IOException, InterruptedException {
        String url = "hdfs://192.168.55.128:9000/tmp/";
        Configuration cfg=new Configuration();
        FileSystem fs= FileSystem.get(URI.create(url),cfg,"root");
        //参数true表示递归删除文件夹及文件夹下的文件
        boolean b = fs.delete(new Path(url), true);
        System.out.println(b);
        fs.close();
    }
}

通过命令查看HDFS目录，显然HDFS的/tmp目录已经被删除

[root@node1 ~]# hdfs dfs -ls /
Found 2 items
drwxr-xr-x   - root supergroup          0 2018-11-26 07:27 /input
drwxr-xr-x   - root supergroup          0 2018-11-26 04:20 /user
[root@node1 ~]#

下载HDFS目录

package com.hadoop.hdfs;

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

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

public class CopyToLcalFile {
    public static void main(String[] args) throws IOException {
        String hdfspath = "hdfs://192.168.55.128:9000/input";
        String localPath="D:\\input";
        Configuration cfg=new Configuration();
        FileSystem fs= FileSystem.get(URI.create(hdfspath),cfg);
        Path hdfs_path=new Path(hdfspath);
        Path local_path=new Path(localPath);
        fs.copyToLocalFile(false,hdfs_path,local_path,true);
        fs.close();
    }
}

在D盘可以查看到input目录文件

上传本地目录（文件夹）

先在本地准备一个待上传的目录，这里将刚才下载的input目录重命名为words

package com.hadoop.hdfs;

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

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

public class CopyFromLocalFile {
public static void main(String[] args) throws IOException, InterruptedException {
 String hdfsPath="hdfs://192.168.55.128:9000/user/";
 String localPath="D:\\words";
 Configuration conf = new Configuration();
 FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf,"root");
 Path hdfs_path = new Path(hdfsPath);
 Path local_path = new Path(localPath);
 fs.copyFromLocalFile(local_path, hdfs_path);
 fs.close();

 }
}

[root@node1 ~]# hdfs dfs -ls /user/words
Found 2 items
-rw-r--r-- 3 root supergroup 52 10:01 /user/words/word2.txt
-rw-r--r-- 3 root supergroup 42 10:01 /user/words/words.txt
[root@node1 ~]#

来源：oschina

链接：https://my.oschina.net/u/4368017/blog/3747096

标签

apache

.Net Framework

Hadoop 系列 HDFS：HDFS的Java API（ Java API应用）