hadoop2.2编程: 数据压缩

 本文主要讨论hadoop的数据压缩与解压缩代码的书写

Compressing and decompressing streams with CompressionCodec

 1 import org.apache.hadoop.io.*;

 2 import org.apache.hadoop.io.compress.CompressionOutputStream;

 3 import org.apache.hadoop.io.compress.CompressionCodec; 
 5 import org.apache.hadoop.io.IOUtils;

 6 import org.apache.hadoop.util.ReflectionUtils;

 7 

 8 public class StreamCompressor {

 9   public static void main(String[] args) throws Exception {

10     String codeClassname = args[0];

11     Class<?> codeClass = Class.forName(codeClassname);

12     Configuration conf = new Configuration();

13     CompressionCodec codec = (CompressionCodec)ReflectionUtils.newInstance(codeClass,conf);

14 

15     CompressionOutputStream out = codec.createOutputStream(System.out);

16     IOUtils.copyBytes(System.in,out,4096,false);

17     out.finish();

18   }

19 }