第一个mapreduce程序WordCount

最新推荐文章于 2021-10-29 14:50:03 发布

Fenice

最新推荐文章于 2021-10-29 14:50:03 发布

阅读量1.2k

点赞数

分类专栏： Java/j2ee

本文链接：https://blog.csdn.net/Kevin_Samuel/article/details/42712279

版权

Java/j2ee 专栏收录该内容

28 篇文章 2 订阅

订阅专栏

提交于http://cloudcomputing.ruc.edu.cn/Chinese/problempage.jsp?id=1000

package cn.edu.ruc.cloudcomputing.book.chapter05;

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

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

public class MyMapre {

	public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

		private final static IntWritable one = new IntWritable(1);
		
		private Text word = new Text();

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

			StringTokenizer itr = new StringTokenizer(value.toString());
			while (itr.hasMoreTokens())	{
				word.set(itr.nextToken());
				context.write(word, one);
			}			
		}
	}

	public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

		private IntWritable result = new IntWritable();

		public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

			int sum = 0;
			for(IntWritable val : values) {
				sum += val.get();
			}

			result.set(sum);
			context.write(key, result);
		}
	}	

	public static void main(String[] args) throws Exception {

		Configuration conf = new Configuration();

		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		if (otherArgs.length != 2) {
			System.err.println("Usage: wordcount <in> <out>");
			System.exit(2);
		}	

		Job job = new Job(conf, "word conut");

		job.setJarByClass(MyMapre.class);
		job.setMapperClass(TokenizerMapper.class);
		job.setCombinerClass(IntSumReducer.class);
		job.setReducerClass(IntSumReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}