hadoop的wordcount的例子

大地之子 2014-04-03 10:27:49



package com.asp;

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 WorldCount {



	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);

			}

		}

	}



	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: simple kpi1 <in> <out>");

			System.exit(2);

		}  

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

		job.setJarByClass(WorldCount.class);// 主类

		job.setMapperClass(TokenizerMapper.class);// mapper

		job.setReducerClass(IntSumReducer.class);// reducer

		job.setOutputKeyClass(Text.class);// 设置作业输出数据的关键类

		job.setOutputValueClass(IntWritable.class);// 设置作业输出值类

		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

		System.exit(job.waitForCompletion(true) ? 0 : 1);

	}

}