Java对HDFS的操作

Hadoop文件系统
基本的文件系统命令操作, 通过hadoop fs -help可以获取所有的命令的详细帮助文件。

Java抽象类org.apache.hadoop.fs.FileSystem定义了hadoop的一个文件系统接口。该类是一个抽象类，通过以下两种静态工厂方法可以过去FileSystem实例：
public static FileSystem.get(Configuration conf) throws IOException
public static FileSystem.get(URI uri, Configuration conf) throws IOException

具体方法实现：
1、public boolean mkdirs(Path f) throws IOException
一次性新建所有目录（包括父目录）， f是完整的目录路径。

2、public FSOutputStream create(Path f) throws IOException
创建指定path对象的一个文件，返回一个用于写入数据的输出流
create()有多个重载版本，允许我们指定是否强制覆盖已有的文件、文件备份数量、写入文件缓冲区大小、文件块大小以及文件权限。

3、public boolean copyFromLocal(Path src, Path dst) throws IOException
将本地文件拷贝到文件系统

4、public boolean exists(Path f) throws IOException
检查文件或目录是否存在

5、public boolean delete(Path f, Boolean recursive)
永久性删除指定的文件或目录，如果f是一个空目录或者文件，那么recursive的值就会被忽略。只有recursive＝true时，一个非空目录及其内容才会被删除。

6、FileStatus类封装了文件系统中文件和目录的元数据，包括文件长度、块大小、备份、修改时间、所有者以及权限信息。
通过"FileStatus.getPath（）"可查看指定HDFS中某个目录下所有文件。

package hdfsTest;

import java.io.IOException;

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

public class OperatingFiles {
	//initialization
	static Configuration conf = new Configuration();
	static FileSystem hdfs;
	static {
		String path = "/usr/java/hadoop-1.0.3/conf/";
		conf.addResource(new Path(path + "core-site.xml"));
		conf.addResource(new Path(path + "hdfs-site.xml"));
		conf.addResource(new Path(path + "mapred-site.xml"));
		path = "/usr/java/hbase-0.90.3/conf/";
		conf.addResource(new Path(path + "hbase-site.xml"));
		try {
			hdfs = FileSystem.get(conf);
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	//create a direction
	public void createDir(String dir) throws IOException {
		Path path = new Path(dir);
		hdfs.mkdirs(path);
		System.out.println("new dir \t" + conf.get("fs.default.name") + dir);
	}	
	
	//copy from local file to HDFS file
	public void copyFile(String localSrc, String hdfsDst) throws IOException{
		Path src = new Path(localSrc);		
		Path dst = new Path(hdfsDst);
		hdfs.copyFromLocalFile(src, dst);
		
		//list all the files in the current direction
		FileStatus files[] = hdfs.listStatus(dst);
		System.out.println("Upload to \t" + conf.get("fs.default.name") + hdfsDst);
		for (FileStatus file : files) {
			System.out.println(file.getPath());
		}
	}
	
	//create a new file
	public void createFile(String fileName, String fileContent) throws IOException {
		Path dst = new Path(fileName);
		byte[] bytes = fileContent.getBytes();
		FSDataOutputStream output = hdfs.create(dst);
		output.write(bytes);
		System.out.println("new file \t" + conf.get("fs.default.name") + fileName);
	}
	
	//list all files
	public void listFiles(String dirName) throws IOException {
		Path f = new Path(dirName);
		FileStatus[] status = hdfs.listStatus(f);
		System.out.println(dirName + " has all files:");
		for (int i = 0; i< status.length; i++) {
			System.out.println(status[i].getPath().toString());
		}
	}

	//judge a file existed? and delete it!
	public void deleteFile(String fileName) throws IOException {
		Path f = new Path(fileName);
		boolean isExists = hdfs.exists(f);
		if (isExists) {	//if exists, delete
			boolean isDel = hdfs.delete(f,true);
			System.out.println(fileName + "  delete? \t" + isDel);
		} else {
			System.out.println(fileName + "  exist? \t" + isExists);
		}
	}

	public static void main(String[] args) throws IOException {
		OperatingFiles ofs = new OperatingFiles();
		System.out.println("\n=======create dir=======");
		String dir = "/test";
		ofs.createDir(dir);
		System.out.println("\n=======copy file=======");
		String src = "/home/ictclas/Configure.xml";
		ofs.copyFile(src, dir);
		System.out.println("\n=======create a file=======");
		String fileContent = "Hello, world! Just a test.";
		ofs.createFile(dir+"/word.txt", fileContent);
	}
}

//output~
=======create dir=======
new dir hdfs://sfserver20.localdomain:9000/test

=======copy file=======
Upload to hdfs://sfserver20.localdomain:9000/test
hdfs://sfserver20.localdomain:9000/test/Configure.xml
hdfs://sfserver20.localdomain:9000/test/word.txt

=======create file=======
new file hdfs://sfserver20.localdomain:9000/test/word.txt

=======before delete file=======
new dir hdfs://sfserver20.localdomain:9000/test/del
new file hdfs://sfserver20.localdomain:9000/test/del.txt
/test has all files:
hdfs://sfserver20.localdomain:9000/test/Configure.xml
hdfs://sfserver20.localdomain:9000/test/del
hdfs://sfserver20.localdomain:9000/test/del.txt
hdfs://sfserver20.localdomain:9000/test/word.txt

=======after delete file=======
/test/del  delete? true
/test/del.txt  delete? true
/test/no  exist? false
/test has all files:
hdfs://sfserver20.localdomain:9000/test/Configure.xml
hdfs://sfserver20.localdomain:9000/test/word.txt