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

 import org.apache.hadoop.io.*;
 import org.apache.hadoop.io.compress.CompressionOutputStream;
 import org.apache.hadoop.io.compress.CompressionCodec;  5 import org.apache.hadoop.io.IOUtils;
 import org.apache.hadoop.util.ReflectionUtils;

 public class StreamCompressor {
   public static void main(String[] args) throws Exception {
     String codeClassname = args[0];
     Class<?> codeClass = Class.forName(codeClassname);
     Configuration conf = new Configuration();
     CompressionCodec codec = (CompressionCodec)ReflectionUtils.newInstance(codeClass,conf);

     CompressionOutputStream out = codec.createOutputStream(System.out);
     IOUtils.copyBytes(System.in,out,4096,false);
     out.finish();
   }
 }