MapReduce WordCount

我的实现

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.mapred.JobConf;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.JobContext;
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 java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.StringTokenizer;

public class WordCount {
    public static class WordMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable 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 CountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            Iterator<IntWritable> iter = values.iterator();
            while (iter.hasNext()) {
                sum += iter.next().get();
            }
            context.write(key, new IntWritable(sum));
        }
    }

    /*
    hdfs://localhost:9000/user/tqc/text.txt
    hdfs://localhost:9000/user/tqc/wordcount.out
     */
    
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job2 = Job.getInstance(conf, "problem 1");
        job2.setJarByClass(WordCount.class);
        job2.setMapperClass(WordMapper.class);
        job2.setCombinerClass(CountReducer.class);
        job2.setReducerClass(CountReducer.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(IntWritable.class);
        Path input = new Path(args[0]);
        Path output = new Path(args[1]);
//        FileSystem fs = FileSystem.get(conf);
        FileSystem fs = output.getFileSystem(conf);
        if (fs.exists(output)) {
            fs.delete(output, true);
        }
        FileInputFormat.addInputPath(job2, input);
        FileOutputFormat.setOutputPath(job2, output);
        System.exit(job2.waitForCompletion(true) ? 0 : 1);
    }
}