java hdfs 压缩_HDFS支持数据压缩的几种方法探讨

本文探讨了在Java中使用HDFS进行数据压缩的方法,包括利用CompressionCodec进行压缩和解压缩,以及通过文件扩展名推断codec类型进行解压缩。示例代码展示了如何使用GzipCodec进行操作。
摘要由CSDN通过智能技术生成

package com.hdfs;

import java.io.IOException;

import java.io.InputStream;

import java.io.OutputStream;

import java.net.URI;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.FSDataInputStream;

import org.apache.hadoop.fs.FSDataOutputStream;

import org.apache.hadoop.fs.FileSystem;

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;

public class CodecTest {

//压缩文件

public static void compress(String codecClassName) throws Exception{

Class> codecClass = Class.forName(codecClassName);

Configuration conf = new Configuration();

FileSystem fs = FileSystem.get(conf);

CompressionCodec codec = (CompressionCodec)ReflectionUtils.newInstance(codecClass, conf);

//指定压缩文件路径

FSDataOutputStream outputStream = fs.create(new Path("/user/hadoop/text.gz"));

//指定要被压缩的文件路径

FSDataInputStream in = fs.open(new Path("/user/hadoop/aa.txt"));

//创建压缩输出流

CompressionOutputStream out = codec.createOutputStream(outputStream);

IOUtils.copyBytes(in, out, conf);

IOUtils.closeStream(in);

IOUtils.closeStream(out);

}

//解压缩

public static void uncompress(String fileName) throws Exception{

Class> codecClass = Class.forName("org.apache.hadoop.io.compress.GzipCodec");

Configuration conf = new Configuration();

FileSystem fs = FileSystem.get(conf);

CompressionCodec codec = (CompressionCodec)ReflectionUtils.newInstance(codecClass, conf);

FSDataInputStream inputStream = fs.open(new Path("/user/hadoop/text.gz"));

//把text文件里到数据解压,然后输出到控制台

InputStream in = codec.createInputStream(inputStream);

IOUtils.copyBytes(in, System.out, conf);

IOUtils.closeStream(in);

}

//使用文件扩展名来推断二来的codec来对文件进行解压缩

public static void uncompress1(String uri) throws IOException{

Configuration conf = new Configuration();

FileSystem fs = FileSystem.get(URI.create(uri), conf);

Path inputPath = new Path(uri);

CompressionCodecFactory factory = new CompressionCodecFactory(conf);

CompressionCodec codec = factory.getCodec(inputPath);

if(codec == null){

System.out.println("no codec found for " + uri);

System.exit(1);

}

String outputUri = CompressionCodecFactory.removeSuffix(uri, codec.getDefaultExtension());

InputStream in = null;

OutputStream out = null;

try {

in = codec.createInputStream(fs.open(inputPath));

out = fs.create(new Path(outputUri));

IOUtils.copyBytes(in, out, conf);

} finally{

IOUtils.closeStream(out);

IOUtils.closeStream(in);

}

}

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

//compress("org.apache.hadoop.io.compress.GzipCodec");

//uncompress("text");

uncompress1("hdfs://master:9000/user/hadoop/text.gz");

}

}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值