Class

org.apache.hadoop.io.compress .CompressionCodecFactory

A factory that will find the correct codec for a given filename.

Method

CompressionCodec getCodec(Path file)

Find the relevant compression codec for the given file based on its filename suffix.

获得这个压缩数据文件採用哪种压缩数据算法。

package Compress;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileOutputStream;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IOUtils;

import org.apache.hadoop.io.compress.CompressionCodec;

import org.apache.hadoop.io.compress.CompressionCodecFactory;

import org.apache.hadoop.io.compress.CompressionInputStream;

import org.apache.hadoop.mapreduce.Job;

/**

 * 解压缩

 * @author liguodong

 */

public class Decompression {

    final static String file = "/liguodong/data.gz";

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

        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf, "DeCodec");

        //打包执行必须执行的方法

        job.setJarByClass(Decompression.class);

        CompressionCodecFactory codecFactory = new CompressionCodecFactory(conf);

        //返回一个解压缩的实例

        CompressionCodec codec = codecFactory.getCodec(new Path(file));

        //返回被算法解压了的输入流

        CompressionInputStream inputStream = codec.createInputStream

                (new FileInputStream(new File(file)));

        //将输入流文件写出到去除了扩展名的文件

        FileOutputStream outputStream = new FileOutputStream

                (new File(codecFactory.removeSuffix(file, codec.getDefaultExtension())));

        IOUtils.copyBytes(inputStream, outputStream, conf);

    }

}

打成jar包：Decodec.jar

[root@master liguodong]# yarn jar Decodec.jar

15/06/05 21:54:25 INFO zlib.ZlibFactory: Successfully loaded & initialized native-zlib library

[root@master liguodong]# ll

总用量 524824

-rw-r--r-- 1 root root      1492 6月   5 19:47 codec.jar

-rw-r--r-- 1 root root 536870912 6月   5 21:54 data

-rw-r--r-- 1 root root    521844 6月   5 21:40 data.gz