hello wordcount for hadoop

最新推荐文章于 2024-11-19 22:39:34 发布

追寻北极

最新推荐文章于 2024-11-19 22:39:34 发布

阅读量441

点赞数

分类专栏： cloud

cloud 专栏收录该内容

234 篇文章

订阅专栏

本文详细解析了使用Hadoop实现的WordCount示例，包括配置、Mapper、Reducer类的实现以及运行流程。重点讲解了如何利用Hadoop进行大规模数据处理，通过MapReduce模式实现单词计数。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package org.jediael.hadoopdemo.toolrunnerdemo;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool{

	public static class WordCountMap extends
			Mapper<LongWritable, Text, Text, IntWritable> {

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

		public void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			String line = value.toString();
			StringTokenizer token = new StringTokenizer(line);
			while (token.hasMoreTokens()) {
				word.set(token.nextToken());
				context.write(word, one);
			}
		}
	}

	public static class WordCountReduce extends
			Reducer<Text, IntWritable, Text, IntWritable> {
		
		public void reduce(Text key, Iterable<IntWritable> values,
				Context context) throws IOException, InterruptedException {
			int sum = 0;
			for (IntWritable val : values) {
				sum += val.get();
			}
			context.write(key, new IntWritable(sum));
		}
	}


	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = new Job(conf);
		job.setJarByClass(WordCount.class);
		job.setJobName("wordcount");

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

		job.setMapperClass(WordCountMap.class);
		job.setReducerClass(WordCountReduce.class);

		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);

		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		return(job.waitForCompletion(true)?0:-1);
		
	}
	
	public static void main(String[] args) throws Exception {
		int exitCode = ToolRunner.run(new WordCount(), args);
		System.exit(exitCode);
	}
	
	
}

参考： http://blog.youkuaiyun.com/jediael_lu/article/details/38751885