MapReduce API

WordCount

WordCount
package a.b.c;

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.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.output.FileOutputFormat;

//继承Mapper类，重写Reduccer方法
class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
	@Override
	protected void map(LongWritable key, Text value,
			org.apache.hadoop.mapreduce.Mapper.Context context)
			throws IOException, InterruptedException {
		String lineString=value.toString();
		String [] wordStrings=lineString.split(",");
		for (String word:wordStrings){
			context.write(new Text(word), new IntWritable(1));
		}

	}
	
	
/*	protected void mapper(LongWritable key,Text value,Context context) throws IOException,InterruptedException {
		String lineString=value.toString();
		String [] wordStrings=lineString.split(",");
		for (String word:wordStrings){
			context.write(new Text(word), new IntWritable(1));
		}
		
	}*/
}

//继承Reducer类，重写reducer方法
class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,Context context)
			throws IOException, InterruptedException {
		int count=0;
		for (IntWritable value:values){
			count+=value.get();
		}
		context.write(key, new IntWritable(count));
	}
	
/*	protected void reduce(Text key, Iterable<IntWritable> values,
			Context context)
			throws IOException, InterruptedException {
		int count=0;
		for (IntWritable value:values){
			count+=value.get();
		}
		context.write(key, new IntWritable(count));

	}*/
}

public class WordCount {
	public static void main(String[] args) throws IOException ,ClassNotFoundException,InterruptedException{
		//设置程序名
		Configuration configuration=new Configuration();
		Job job=Job.getInstance(configuration,"wordCount");
		job.setJarByClass(WordCount.class);
		
		//mapper设置
		job.setMapperClass(WordCountMapper.class);
		System.out.println("before mapppp");
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		System.out.println("after mapppp");
		
		//reducer设置
		job.setReducerClass(WordCountReducer.class);	
		
		//输入输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//返回执行成功结果
		boolean res=job.waitForCompletion(true);
		System.exit(res?0:1);
				
	
	}
	
	
	

}