cloudcomputing.ruc题目1000：WorldCount-CSDN博客

本文链接：https://blog.csdn.net/Kid_U_ForFun/article/details/25060205

WordCount是Hadoop MapReduce中的经典示例，用于统计文本文件中每个单词的出现次数，对于理解MapReduce编程模型至关重要。该程序读取文本，分词并计算每个词的频率。

摘要由CSDN通过智能技术生成

1000 Word_Count

描述

WordCount例子读取文本文件，并统计文件中单词出现的频数。WordCount对于hadoop的重要性，相当于HelloWorld对于JAVA的重要性。如果你想学习Map_Reduce变成模型，那么学习Word_Count 是一个最好的开始。

输入：输入包含一组文件，文件中含有很多单词。
输出：输出是一个文本文件，文件的每一行包含一个单词和这个单词在所有输入文件中出现的次数。

输入样例
input 1: hello world bye world
input 2: hello hadoop bye hadoop

输出样例:
bye 2
hadoop 2
hello 2

world 2

//我就说这代码是我抄的，你能把我咋滴。O(∩_∩)O哈哈哈~

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 void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {


	Configuration conf = new Configuration();
	Job job = new Job(conf,"qw 1000");
	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.setInputPaths(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));
	System.exit(job.waitForCompletion(true) ? 0:1);
}

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);


		} 
	}
}