2020-10-07

最新推荐文章于 2025-08-24 22:05:35 发布

奋斗的憨憨小S

最新推荐文章于 2025-08-24 22:05:35 发布

阅读量106

点赞数 1

CC 4.0 BY-SA版权

分类专栏： hdfs 文章标签： hadoop

本文链接：https://blog.csdn.net/weixin_43796131/article/details/108950870

hdfs 专栏收录该内容

4 篇文章

订阅专栏

本文介绍了如何使用Apache Hadoop的压缩和解压功能，特别是通过BZip2Codec进行文件压缩，并展示了如何自定义编解码器实现流复制。涉及配置、实例化和操作压缩/解压流的详细步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package Chapter7;
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.io.compress.CompressionOutputStream;
import org.apache.hadoop.util.ReflectionUtils;

import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;

public class compress {
    public static void compress(String filePath, String method){
        Configuration conf = new Configuration();
        FileOutputStream fos = null;
        CompressionOutputStream outputStream = null;
        FileInputStream fis = null;
        //1创建编译码器
        //通过反射机制实例化编译码器对象
        try {
            Class<?> codecClass = Class.forName(method);
            CompressionCodec codec = (CompressionCodec) ReflectionUtils.
                    newInstance(codecClass,conf);

        //2.获取压缩的输出字节流
            fos  = new FileOutputStream(filePath +
                    codec.getDefaultExtension());
            outputStream=  codec.createOutputStream(fos);

             fis = new FileInputStream(filePath);

            /*byte[] buf = new byte[1024];
            int ret = 0;
            //输入流去读，输出流去写
            while ((ret = fis.read(buf)) != -1){
                outputStream.write(buf);
            }*/
            //3.流的复制，写1020个字节
            IOUtils.copyBytes(fis,outputStream,1020);




        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            IOUtils.closeStream(outputStream);
            IOUtils.closeStream(fis);

        }
    }
    
    public static void decompress(String filePath){
        Configuration conf = new Configuration();
        CompressionCodecFactory factory = new CompressionCodecFactory(conf);
        //1.获取编译码器对象
        CompressionCodec codec = factory.getCodec(new Path(filePath));
        if (codec == null){
            System.out.println("No codec found" + filePath);
            return;
        }
        FileInputStream fis = null;
        CompressionInputStream inputStream = null;
        FileOutputStream fos = null;
        try {
            //2获取解码的输入字节流
            fis = new FileInputStream(filePath);
            inputStream = codec.createInputStream(fis);
            
            String newFile = CompressionCodecFactory.removeSuffix(filePath,
                    codec.getDefaultExtension());
            fos = new FileOutputStream(newFile);
            //流的复制
            IOUtils.copyBytes(inputStream,fos,1020);
            
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            IOUtils.closeStream(inputStream);
            IOUtils.closeStream(fis);
            IOUtils.closeStream(fos);
        }


    }
    public static void main(String[] args) {
   // compress("D:/input.txt","org.apache.hadoop.io.compress.BZip2Codec");
        
    }
}