hadoop之MapReduce---压缩实操案例

数据流的压缩和解压缩

CompressionCodec有两个方法可以用于轻松地压缩或解压缩数据。
要想对正在被写入一个输出流的数据进行压缩，我们可以使用createOutputStream(OutputStreamout)方法创建一个CompressionOutputStream，将其以压缩格式写入底层的流。
相反，要想对从输入流读取而来的数据进行解压缩，则调用createInputStream(InputStreamin)函数，从而获得一个CompressionInputStream，从而从底层的流读取未压缩的数据。
测试一下如下压缩方式

DEFLATE	org.apache.hadoop.io.compress.DefaultCodec
gzip	org.apache.hadoop.io.compress.GzipCodec
bzip2	org.apache.hadoop.io.compress.BZip2CodecA

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
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.io.compress.CompressionOutputStream;
import org.apache.hadoop.util.ReflectionUtils;

public class TestCompress {

	public static void main(String[] args) throws Exception {
		compress("e:/hello.txt","org.apache.hadoop.io.compress.BZip2Codec");
//		decompress("e:/hello.txt.bz2");
	}

	// 1、压缩
	private static void compress(String filename, String method) throws Exception {
		
		// （1）获取输入流
		FileInputStream fis = new FileInputStream(new File(filename));
		
		Class codecClass = Class.forName(method);
		
		CompressionCodec codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, new Configuration());
		
		// （2）获取输出流
		FileOutputStream fos = new FileOutputStream(new File(filename + codec.getDefaultExtension()));
		CompressionOutputStream cos = codec.createOutputStream(fos);
		
		// （3）流的对拷
		IOUtils.copyBytes(fis, cos, 1024*1024*5, false);
		
// （4）关闭资源
		cos.close();
		fos.close();
fis.close();
	}

	// 2、解压缩
	private static void decompress(String filename) throws FileNotFoundException, IOException {
		
		// （0）校验是否能解压缩
		CompressionCodecFactory factory = new CompressionCodecFactory(new Configuration());

		CompressionCodec codec = factory.getCodec(new Path(filename));
		
		if (codec == null) {
			System.out.println("cannot find codec for file " + filename);
			return;
		}
		
		// （1）获取输入流
		CompressionInputStream cis = codec.createInputStream(new FileInputStream(new File(filename)));
		
		// （2）获取输出流
		FileOutputStream fos = new FileOutputStream(new File(filename + ".decoded"));
		
		// （3）流的对拷
		IOUtils.copyBytes(cis, fos, 1024*1024*5, false);
		
		// （4）关闭资源
		cis.close();
		fos.close();
	}
}

Map输出端采用压缩

即使你的MapReduce的输入输出文件都是未压缩的文件，你仍然可以对Map任务的中间结果输出做压缩，因为它要写在硬盘并且通过网络传输到Reduce节点，对其压缩可以提高很多性能，这些工作只要设置两个属性即可，我们来看下代码怎么设置。

1. 提供的Hadoop源码支持的压缩格式有：BZip2Codec 、DefaultCodec

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.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
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();

		// 开启map端输出压缩
	configuration.setBoolean("mapreduce.map.output.compress", true);
		// 设置map端输出压缩方式
	configuration.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);

		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]));

		boolean result = job.waitForCompletion(true);

		System.exit(result ? 1 : 0);
	}
}

2. Mapper保持不变

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

Text k = new Text();
	IntWritable v = new IntWritable(1);

	@Override
	protected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {

		// 1 获取一行
		String line = value.toString();

		// 2 切割
		String[] words = line.split(" ");

		// 3 循环写出
		for(String word:words){
k.set(word);
			context.write(k, v);
		}
	}
}

3. Reducer保持不变

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

	IntWritable v = new IntWritable();

	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Context context) throws IOException, InterruptedException {
		
		int sum = 0;

		// 1 汇总
		for(IntWritable value:values){
			sum += value.get();
		}
		
        v.set(sum);

        // 2 输出
		context.write(key, v);
	}
}

Reduce输出端采用压缩

基于WordCount案例处理
修改驱动

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);
	}
}

Mapper和Reducer保持不变

简书：https://www.jianshu.com/u/0278602aea1d
CSDN：https://blog.csdn.net/u012387141