Hadoop HDFS 编程

HDFS是一个分布式文件系统，然而对于程序员来说，HDFS就是一个普通文件系统，Hadoop进行的底层封装，程序员按照相应的API来对HDFS上的文件操作，和对本地磁盘文件操作没有太多区别。但是最初接触时可能还是会碰到这样那样的问题。

例如：获取FileSystem实例时会出现

java.lang.NullPointerException
    at org.apache.hadoop.conf.Configuration.get(Configuration.java:382)
    at org.apache.hadoop.conf.Configuration.getBoolean(Configuration.java:570)
    at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:192)
    at hadoop.test.URLCat.copyFileToAnotherFile(URLCat.java:38) //这个是我写的一个方法，报错了
    at hadoop.test.URLCat.main(URLCat.java:83)

代码：

package hadoop.test;

import java.io.BufferedInputStream;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.MalformedURLException;
import java.net.URI;
import java.net.URL;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FsUrlStreamHandlerFactory;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.DistributedFileSystem;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.util.Progressable;

public class URLCat extends Configured {
   
    /×static{
        Configuration.addDefaultResource("hdfs-default.xml");
        Configuration.addDefaultResource("hdfs-site.xml");
        Configuration.addDefaultResource("mapred-default.xml");
        Configuration.addDefaultResource("mapred-site.xml");
    } ×/没有这个static块时就会报上面对错误

    public  void copyFileToAnotherFile(String[] args)
    {
        InputStream in = null;
        OutputStream out = null;
        try {
            String sourceFile = args[0];
            String targetFile = args[1];
            in = new BufferedInputStream(new FileInputStream(sourceFile));
           
            Configuration conf = new Configuration();
            System.out.println(conf);
            System.out.println(URI.create(targetFile)==null);
            System.out.println(conf==null);
            System.out.println(FileSystem.get(URI.create(targetFile),conf)==null);
           
            FileSystem fs = DistributedFileSystem.get(URI.create(targetFile),conf);
            System.out.println(fs);
            out = fs.create(new Path(targetFile),new Progressable(){
                public void progress(){System.out.print(".");}
            });
            IOUtils.copyBytes(in, out, 4096,true);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }finally
        {
            IOUtils.closeStream(in);
            IOUtils.closeStream(out);
        }
    }
   
    static {
        URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
    }

    public static void displayFile(String[] args)
    {
         InputStream in = null;
            try {
                in = new URL(args[0]).openStream();
                IOUtils.copyBytes(in, System.out, 4096,false);
            } catch (MalformedURLException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }finally
            {
                IOUtils.closeStream(in);
            }
    }
    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        new URLCat().copyFileToAnotherFile(args);
        //URLCat.displayFile(args);
        //
    }

}