MapReduce-二进制输入

Hadoop的MapReduce不只是可以处理文本信息,它还可以处理二进制格式的数据
1. 关于SequenceFileInputFormat类
Hadoop的顺序文件格式存储二进制的键/值对的序列。由于它们是可分割的(它们有同步点,所以reader可以从文件中的任意一点雨记录边界进行同步,例如分片的起点),所以它们很符合MapReduce数据的格式要求,并且它们还支持压缩,可以使用一些序列化技术来存储任意类型。
如果要用顺序文件数据作为MapReduce的输入,应用SequenceFileInputFormat。键和值是由顺序文件决定,所以只需要保证map输入的类型匹配。
虽然从名称上看不出来,但SequenceFileInputFormat可以读MapFile(排序后的SequenceFile)和SequenceFile。如果在处理顺序文件时遇到目录,SequenceFileInputFormat类会认为自己正在读MapFile,使用的是其数据文件。

2. 关于SequenceFileAsTextInputFormat类
SequenceFileAsTextInputFormat是SequenceFileInputFormat的变体,它将顺序文件的键和值转换为Text对象。这个转换通过在键和值上调用toString方法实现。这个格式是顺序文件作为Streaming的合适的输入类型。

3. 关于SequenceFileAsBinaryInputFormat类
SequenceFileAsBinaryInputFormat是SequenceFileInputFormat的一种变体,它获取顺序文件的键和值作为二进制对象。它们被封装为BytesWritable对象,因而应用程序可以任意地解释这些字节数组。结合使用SequenceFile.Reader的appendRaw()方法或SequenceFileAsBinaryOutputFormat,它提供了在MapReduce中可以使用任意二进制数据类型的方法。

 

例子

将数据文件存为SequenceFile

package com.zhen.mapreduce.sequenceToText;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile.CompressionType;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.VLongWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;

/**
 * @author FengZhen
 * @date 2018年8月18日
 * 输出为SequenceFile
 */
public class TextToSequence {

	 public static void main(String[] args) throws Exception {        
	        Configuration conf = new Configuration();
	        Job job = Job.getInstance(conf);
	        job.setJarByClass(TextToSequence.class);

	        job.setMapperClass(WCMapper.class);
	        job.setReducerClass(WCReducer.class);

	        job.setOutputKeyClass(Text.class);
	        job.setOutputValueClass(VLongWritable.class);        

	        // 设置输出类
	        job.setOutputFormatClass(SequenceFileOutputFormat.class);

	        /**
	         * 设置sequecnfile的格式,对于sequencefile的输出格式,有多种组合方式,
	         * 从下面的模式中选择一种,并将其余的注释掉
	         */

	        // 组合方式1:不压缩模式
	        SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.NONE);

	        //组合方式2:record压缩模式,并指定采用的压缩方式 :默认、gzip压缩等
	        //        SequenceFileOutputFormat.setOutputCompressionType(job,
	        //                CompressionType.RECORD);
	        //        SequenceFileOutputFormat.setOutputCompressorClass(job,
	        //                DefaultCodec.class);


	        //组合方式3:block压缩模式,并指定采用的压缩方式 :默认、gzip压缩等
	        //        SequenceFileOutputFormat.setOutputCompressionType(job,
	        //                CompressionType.BLOCK);
	        //        SequenceFileOutputFormat.setOutputCompressorClass(job,
	        //                DefaultCodec.class);

	        FileInputFormat.addInputPaths(job, "hdfs://fz/user/hdfs/MapReduce/data/squenceFile/origin");
	        SequenceFileOutputFormat.setOutputPath(job, new Path("hdfs://fz/user/hdfs/MapReduce/data/squenceFile/textToSequence/output"));

	        System.exit(job.waitForCompletion(true)?0:1);
	    }
	    //map
	    public static class WCMapper extends
	    Mapper<LongWritable, Text, Text, VLongWritable> {
	        public void map(LongWritable key, Text value, Context context)
	                throws IOException, InterruptedException {
	            String[] split = value.toString().split("");
                for(String s : split){
                    context.write(new Text(s), new VLongWritable(1L));
                }            
	        }
	    }
	    //reduce
	    public static class WCReducer extends Reducer<Text, VLongWritable, Text, VLongWritable>{
	        @Override
	        protected void reduce(Text key, Iterable<VLongWritable> v2s, Context context)
	                throws IOException, InterruptedException {

	            long sum=0;

	            for(VLongWritable vl : v2s){
	                sum += vl.get();                 
	            }
	            context.write(key, new VLongWritable(sum));
	        }
	    }
}

 

读取SequenceFile存为Text

package com.zhen.mapreduce.sequenceToText;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.VLongWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * @author FengZhen
 * @date 2018年8月18日
 * 输入为SequenceFile
 */
public class SequenceToText extends Configured implements Tool{

	static class SequenceToTextMapper extends Mapper<Text, VLongWritable, Text, VLongWritable>{
		@Override
		protected void map(Text key, VLongWritable value,
				Mapper<Text, VLongWritable, Text, VLongWritable>.Context context)
				throws IOException, InterruptedException {
			String contents = value.toString();
			System.out.println(contents);
			context.write(key, value);
		}
	}
	
	static class SequenceToTextReducer extends Reducer<Text, VLongWritable, Text, VLongWritable>{
		@Override
		protected void reduce(Text key, Iterable<VLongWritable> value,
				Reducer<Text, VLongWritable, Text, VLongWritable>.Context context)
				throws IOException, InterruptedException {
			long sum = 0;
			while (value.iterator().hasNext()) {
				sum += Integer.parseInt(value.iterator().next().toString());
			}
			context.write(key, new VLongWritable(sum));
		}
	}
	
	public int run(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		job.setJobName("SequenceToText");
		job.setJarByClass(SequenceToText.class);
		
		job.setInputFormatClass(SequenceFileInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
		
		job.setMapperClass(SequenceToTextMapper.class);
		job.setReducerClass(SequenceToTextReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(VLongWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(VLongWritable.class);
		
		SequenceFileInputFormat.setInputPaths(job, new Path(args[0]));
		TextOutputFormat.setOutputPath(job, new Path(args[1]));
		
		return job.waitForCompletion(true) ? 0 : 1;
	}

	public static void main(String[] args) throws Exception {
		String[] params = new String[]{"hdfs://fz/user/hdfs/MapReduce/data/squenceFile/textToSequence/output","hdfs://fz/user/hdfs/MapReduce/data/squenceFile/sequenceToText/output"};
		int exitCode = ToolRunner.run(new SequenceToText(), params);
		System.out.println(exitCode);
		System.exit(exitCode);
	}
	
}

 

 

 

 

    原文作者:MapReduce
    原文地址: https://www.cnblogs.com/EnzoDin/p/9520702.html
    本文转自网络文章,转载此文章仅为分享知识,如有侵权,请联系博主进行删除。
点赞