目的:

学习用java进行的常用hdfs操作

参考：

[0002] Hadoop HDFS cmd常用命令练手

环境：

hadoop2.6.4

win7 下的eclipse环境调试已经配置好，参考前面的文章

代码：

1. 创建文件夹

 1 package hdfs;
 2
 3 import java.io.IOException;
 4
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.FileSystem;
 7 import org.apache.hadoop.fs.Path;
 8
 9 /**
10  *
11  * @author Administrator
12  *  创建文件夹,如果不存在
13  */
14 public class CreateFolder {
15
16     public static void main(String[] args) throws IOException {
17         Configuration conf =new Configuration();
18         conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
19         FileSystem fs =  FileSystem.get(conf) ;
20         Path path = new Path("/output");
21
22         if(! fs.exists(path)){
23             fs.mkdirs(path);
24         }
25     }
26 }

以流的方式下载文件

 1 package hdfs;
 2
 3 import java.io.FileNotFoundException;
 4 import java.io.FileOutputStream;
 5 import java.io.IOException;
 6
 7 import org.apache.commons.compress.utils.IOUtils;
 8 import org.apache.hadoop.conf.Configuration;
 9 import org.apache.hadoop.fs.FSDataInputStream;
10 import org.apache.hadoop.fs.FileSystem;
11 import org.apache.hadoop.fs.Path;
12
13 /**
14  *  功能：      将 hdfs://ssmaster:9000/data/paper.txt下载到Windows下c:\paper.txt
15  *  调用方式：windows下执行,eclipse中执行
16  */
17
18 public class Down_Load {
19
20     public static void main(String[] args) {
21
22     Configuration conf =new Configuration();
23     conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
24
25     FileSystem fs = null;
26     Path src = null;
27     FSDataInputStream in = null;
28     FileOutputStream out = null;
29
30     src = new Path("hdfs://ssmaster:9000/data/paper.txt" );
31
32     try {
33
34       fs = FileSystem.get(conf) ;
35       in = fs.open(src);
36
37        } catch (IOException e) {
38         e.printStackTrace();
39     }
40
41     try {
42         out = new FileOutputStream ("c:\\paper.txt"); //等效  c:/paper.txt
43     } catch (FileNotFoundException e) {
44         e.printStackTrace();
45     }
46
47     try {
48         IOUtils.copy(in, out);
49     } catch (IOException e) {
50         e.printStackTrace();
51     }
52
53 }
54 }

2 上传文件

 1 package hdfs;
 2
 3 import java.io.IOException;
 4
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.FileSystem;
 7 import org.apache.hadoop.fs.Path;
 8
 9 /**
10  *
11  * @author Administrator
12  *  上传本地文件
13  */
14 public class UploadFile {
15
16     public static void main(String[] args) throws IOException {
17         Configuration conf =new Configuration();
18         conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
19         FileSystem fs =  FileSystem.get(conf) ;
20         Path path = new Path("/output");
21         Path src  = new Path("c:/paper.txt");
22
23         fs.copyFromLocalFile(false, true, src, path);
24
25     }
26 }

3 下载文件

 1 package hdfs;
 2
 3 import java.io.IOException;
 4
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.FileSystem;
 7 import org.apache.hadoop.fs.Path;
 8
 9 /**
10  *
11  * @author Administrator
12  *  上传本地文件
13  */
14 public class DownFile {
15
16     public static void main(String[] args) throws IOException {
17         Configuration conf =new Configuration();
18         conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
19         FileSystem fs =  FileSystem.get(conf) ;
20         Path hdfs = new Path("/output/paper.txt");
21         Path win7  = new Path("c:/paper_download.txt");
22
23         fs.copyToLocalFile(hdfs, win7);
24
25     }
26 }

4 删除文件

 1 package hdfs;
 2
 3 import java.io.IOException;
 4
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.FileSystem;
 7 import org.apache.hadoop.fs.Path;
 8
 9 /**
10  *
11  * @author Administrator
12  *  删除hdfs文件,如何文件不存在，也运行正常
13  */
14 public class DeleteFile {
15
16     public static void main(String[] args) throws IOException {
17         Configuration conf =new Configuration();
18         conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
19         FileSystem fs =  FileSystem.get(conf) ;
20         Path hdfs = new Path("/output/paper.txt");
21         fs.delete(hdfs, true);
22
23     }
24 }

5 显示目录信息

 1 package hdfs;
 2
 3 import java.io.IOException;
 4
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.FileStatus;
 7 import org.apache.hadoop.fs.FileSystem;
 8 import org.apache.hadoop.fs.Path;
 9
10 /**
11  *
12  * @author Administrator
13  *  显示某个目录下的文件
14  */
15 public class ListFiles {
16
17     public static void main(String[] args) throws IOException {
18         Configuration conf =new Configuration();
19         conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
20         FileSystem fs =  FileSystem.get(conf) ;
21         Path hdfs = new Path("/");
22
23
24         FileStatus [] files = fs.listStatus(hdfs);
25         for (FileStatus file:files) {
26
27            System.out.print(file.getPath().getName());
28            System.out.print("\t"+ file.isDirectory());
29            System.out.print("\t"+ file.getOwner());
30            System.out.print("\n");
31         }
32
33     }
34 }

总结：

HDFS JAVA API 调用初步学会使用。该篇章翻过去，后续用什么再学

后续：

有空将文件系统的常用操作实现，搜索、递归显示、查看文件内容

参考:

1 hadoop 2.x hdfs api