Hadoop MapReduce程序开发（二）

根据例WordCount写的一个单词计数器

Map类

package com.wordcount.map;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class Map extends Mapper<Object, Text, Text, IntWritable> {

	private static Text word = new Text();
	private final static IntWritable one = new IntWritable(1);
	
	
	@Override
	protected void map(Object key, Text value, Context context)
			throws IOException, InterruptedException {
		//value是每一行数据
		StringTokenizer token = new StringTokenizer(value.toString());
		while(token.hasMoreTokens()) {
			word.set(token.nextToken().toLowerCase());
			context.write(word, one);
		}
	}
	
}

reduce类

package com.wordcount.reduce;

import java.io.IOException;

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

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

	private static IntWritable result = new IntWritable();
	
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values, Context context)
			throws IOException, InterruptedException {
		int total = 0;
		for (IntWritable value : values) {
			total += value.get();
		}
		result.set(total);
		context.write(key, result);
	}
	
}

配置好eclipse后运行下面类

package com.wordcount.main;


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.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import com.wordcount.map.Map;
import com.wordcount.reduce.Reduce;

public class WordCount {

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		String[] params = new GenericOptionsParser(conf, args).
											getRemainingArgs();
		if(params.length != 2) {
			System.err.println("params error!");
			System.exit(2);
		}
		
		Job job = new Job(conf, "WordCount");
		job.setJarByClass(WordCount.class);
		
		job.setMapperClass(Map.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setCombinerClass(Reduce.class);
		
		job.setReducerClass(Reduce.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.addInputPath(job, new Path(params[0]));
		FileOutputFormat.setOutputPath(job, new Path(params[1]));
		
		System.exit((job.waitForCompletion(true) ? 0 : 1));
	}
}

文件words

hello hadoop hello hello world
world cup
just do it
it a test
just try
My World

上传 hadoop fs -put .words /data/input

Run Configuration：

Arguments:

hdfs://master:9000/data/input/words hdfs://master:9000/data/output

结果

a    1
cup    1
do    1
hadoop    1
hello    3
it    2
just    2
my    1
test    1
try    1
world    3