MapReduce之wordCount计数

1. 新建一个words.txt，上传到hadoop服务器。

2. 打开eclipse，编写代码。

（1）WCMapper.java

import java.io.IOException;

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

public class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

	/**
	 * 实现map方法，只用到value
	 */
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
			throws IOException, InterruptedException {
		// 接收数据
		String line = value.toString();
		// 切分数据
		String[] words = line.split(" ");
		// 循环
		for (String w : words) {
			// 出现一次，记一个1，输出
			context.write(new Text(w), new LongWritable(1));
		}

	}

}

（2）WCReducer.java

import java.io.IOException;

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

public class WCReducer extends Reducer<Text, LongWritable , Text, LongWritable> {

	@Override
	protected void reduce(Text key, Iterable<LongWritable> v2s,
			Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
		// 接收数据
		// 定义一个计数器
		long counter = 0;
		// 循环v2s
		for (LongWritable i : v2s){
			counter += i.get();
		}
		// 输出
		context.write(key, new LongWritable(counter));
	}

}

（3）WordCount.java

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

public class WordCount {

	public static void main(String[] args) throws Exception {
		Job job = Job.getInstance(new Configuration());
		// 将main方法所在类设置进去
		job.setJarByClass(WordCount.class);
		// 设置自定义的mapper类型
		job.setMapperClass(WCMapper.class);
		// 设置mapper输出的key类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);
		FileInputFormat.setInputPaths(job, new Path("/words.txt"));	// hadoop文件系统上
		job.setReducerClass(WCReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		FileOutputFormat.setOutputPath(job, new Path("/wcount312"));
		
		// 提交任务
		job.waitForCompletion(true);
	}
	
}

3. 打包成jar文件wc.jar，移动到/usr/local/src/demo/下。

4. 执行jar文件：hadoop jar /usr/local/src/demo/wc.jar 

5. 查看运行结果：