一个简单的demo，将hdfs的一个文件的内容拷贝到另外hdfs一个文件
相关阅读：
import java.util.*;
import java.io.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.io.IOUtils;
public class ShortestPath {
public static void main(String[] args) throws Exception
{
Configuration conf = new Configuration();
conf.addResource(new Path("/usr/local/hadoop/conf/core-site.xml"));
//The two lines' code below is quite useful when debugging Configuration, see reference[3].
//System.out.println(conf.getRaw("fs.default.name"));
//System.out.println(conf.toString());
FileSystem fs = FileSystem.get(conf);
FSDataInputStream in= fs.open(new Path(fs.getWorkingDirectory()+"/input/data"));
BufferedReader br = new BufferedReader(new InputStreamReader(in));
FSDataOutputStream out = fs.create(new Path(fs.getWorkingDirectory() +"/testInput/copyData.txt"));
String str = br.readLine();
while(str!=null)
{
out.writeBytes(str);
out.writeBytes("\n");
str = br.readLine();
}
out.close();
br.close();
}
}
以上的拷贝操作也可以通过IOUtils来完成，例如：
import java.util.*;
import java.io.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.io.IOUtils;
public class ShortestPath {
public static void main(String[] args) throws Exception
{
Configuration conf = new Configuration();
conf.addResource(new Path("/usr/local/hadoop/conf/core-site.xml"));
//System.out.println(conf.getRaw("fs.default.name"));
//System.out.println(conf.toString());
FileSystem fs = FileSystem.get(conf);
FSDataInputStream in= fs.open(new Path(fs.getWorkingDirectory()+"/input/data"));
FSDataOutputStream out = fs.create(new Path(fs.getWorkingDirectory() +"/testInput/copyData.txt"));
IOUtils.copyBytes(in, out, conf);
in.close();
out.close();
}
}
上面的
conf.addResource(new Path("/usr/local/hadoop/conf/core-site.xml"));
这行代码让我挺困惑的，我一直以为Configuration是自己在构造函数的时候就自动载入这些默认的core-site.xml之类，但是看来不是。而且调用Configuration的toString()函数后显示它载入了多个core-site.xml，更加困惑。菜鸟对配置文件不熟悉，知道的兄弟讲讲。
System.out.println(conf.toString());
其他更多的文件操作，比如删除等，可以参考reference[1,2]，基本大同小异。
Reference
(2)http://eclipse.sys-con.com/node/1287801/mobile
(3)http://www.opensourceconnections.com/2013/03/24/hdfs-debugging-wrong-fs-expected-file-exception/