自定义combiner实现文件倒排索引

Posted 2021-02-04 guoziyi

package com.zuoyan.hadoop;

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.Text;
import org.apache.hadoop.mapreduce.InputSplit;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * 
 * @author root 
 * 1：输入文件中并没有地址的输入,那么我们需要在mapper端读取数据的时候，插入其地址。
 * 按“”空格分割字符串，mapper的输出 <key,value>=<值 地址，1>或者<值 地址，(1,1)>
 * 2：利用mapper和reducer之间一个极其重要的组件combiner进行首次的处理，
 * 并且分离key中的值与地址，此时的输出结果<key,value>=<值，地址 1>或者<值，地址 2> 
 * 注意：此组件是属于mapper端阶段的。 
 * 3：reducer开始进行最后的处理。
 */
public class CombinerTest {
	
	// main
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		job.setJarByClass(CombinerTest.class);
		//1
		job.setMapperClass(LastSearchMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		//2
		job.setCombinerClass(LastSearchComb.class);
		//3
		job.setReducerClass(LastSearchReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		boolean x = job.waitForCompletion(true);
		System.out.println(x);
	}
		
	// mapper
	public class LastSearchMapper extends Mapper<LongWritable, Text, Text, Text> {
		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			String line = value.toString();
			String words[] = line.split(" ");
			InputSplit input = context.getInputSplit();
			String pathname = ((FileSplit) input).getPath().getName();// 得到此时数据的地址
			for (String word : words) {
				String word1 = word + " " + pathname;
				context.write(new Text(word1), new Text("1"));
			}
		}
	}

	// combiner
	public class LastSearchComb extends Reducer<Text, Text, Text, Text> {
		@Override
		protected void reduce(Text arg0, Iterable<Text> arg1, Context arg2) throws IOException, InterruptedException {
			int sum = 0;
			for (Text arg : arg1) {
				String word = arg.toString();
				int wordINT = Integer.parseInt(word);
				sum = wordINT + sum;
			}
			String line = arg0.toString();
			String word[] = line.split(" ");
			arg2.write(new Text(word[0]), new Text(word[1] + ":" + sum));
		}
	}

	// reducer
	public class LastSearchReducer extends Reducer<Text, Text, Text, Text> {
		@Override
		protected void reduce(Text arg0, Iterable<Text> arg1, Context arg2) throws IOException, InterruptedException {
			String newword = new String();
			for (Text word : arg1) {
				String wordString = word.toString();
				newword = newword + wordString + " ";
			}
			arg2.write(arg0, new Text(newword));
		}
	}

}

　　

pom导入hadoop-Client即可