尚硅谷大数据技术之Hadoop（MapReduce）（新）第4章 Hadoop数据压缩

package com.atguigu.mapreduce.compress;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.io.compress.BZip2Codec;

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

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

import org.apache.hadoop.io.compress.Lz4Codec;

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

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountDriver {

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

Configuration configuration = new Configuration();

Job job = Job.getInstance(configuration);

job.setJarByClass(WordCountDriver.class);

job.setMapperClass(WordCountMapper.class);

job.setReducerClass(WordCountReducer.class);

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(IntWritable.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);

FileInputFormat.setInputPaths(job, new Path(args[0]));

FileOutputFormat.setOutputPath(job, new Path(args[1]));

// 设置reduce端输出压缩开启

FileOutputFormat.setCompressOutput(job, true);

// 设置压缩的方式

    FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);

//     FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

//     FileOutputFormat.setOutputCompressorClass(job, DefaultCodec.class);

boolean result = job.waitForCompletion(true);

System.exit(result?1:0);

}

}