MapReduce写WordCount案例：Map, Reduce, Driver

Map：

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	
	Text k = new Text();
	IntWritable v = new IntWritable(1);
	
	@Override
	protected void map(LongWritable key, Text value, Context context)	throws IOException, InterruptedException {
		
		// 1 获取一行
		String line = value.toString();
		
		// 2 切割
		String[] words = line.split(" ");
		
		// 3 输出
		for (String word : words) {
			
			k.set(word);
			context.write(k, v);
		}
	}
}

Reduce：

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
int sum;
IntWritable v = new IntWritable();

	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
		
		// 1 累加求和
		sum = 0;
		for (IntWritable count : values) {
			sum += count.get();
		}
		
		// 2 输出
       v.set(sum);
		context.write(key,v);
	}
}

Driver:

import java.io.IOException;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordcountDriver {

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

		// 1 获取配置信息以及封装任务
		Configuration configuration = new Configuration();
		Job job = Job.getInstance(configuration);

		// 2 设置jar加载路径
		job.setJarByClass(WordcountDriver.class);

		// 3 设置map和reduce类
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReducer.class);

		// 4 设置map输出
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);

		// 5 设置最终输出kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		// 6 设置输入和输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		// 7 提交
		boolean result = job.waitForCompletion(true);

		System.exit(result ? 0 : 1);
	}
}