MapReduce性能分析实验

package MyPackage;


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 WordCount {
        
 public static class Map 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 {
        String line = value.toString();
        StringTokenizer tokenizer = new StringTokenizer(line);
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            context.write(word, one);
        }
    }
 } 


 
 public static class Reduce 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));
    }
 }

 
 
 public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
        
        Job job = new Job(conf, "wordcount");
    
        job.setJarByClass(WordCount.class);
        
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    
    job.setCombinerClass(Reduce.class);
    
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);
    
        
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
    
    job.waitForCompletion(true);
 }
        
}

 job.setCombinerClass(Reduce.class);