大数据MapReduce词频统计

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.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 java.io.IOException;
import java.util.StringTokenizer;

public class wc {
    public static class WCMapper extends Mapper<LongWritable, Text,Text,IntWritable>{
        private final static IntWritable one=new IntWritable(1);
        private Text words=new Text();
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer stringTokenizer = new StringTokenizer(value.toString());
            while (stringTokenizer.hasMoreElements()){
                String word= stringTokenizer.nextToken();
                words.set(word);
                context.write(words,one);
            }

        }
    }
    public static class WCReduce extends Reducer<Text,IntWritable,Text,IntWritable>{
        private IntWritable result=new IntWritable();
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum=0;
            for (IntWritable val:values){
                sum+=val.get();
            }
            result.set(sum);
            context.write(key,result);
        }
    }

    public static void main(String[] args) throws Exception{
        //配置文件
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf,"wordcount");
        job.setJarByClass(wc.class);
        //map端和reduce端
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReduce.class);
        //map端输出的字节码
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //reduce端输出的字节码
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //输入文件地址
        FileInputFormat.setInputPaths(job, new Path("E:\\学习\\大三第二学期课程\\大数据架构技术\\wordCount\\word.txt"));
        //输出文件地址
        Path path=new Path("E:\\学习\\大三第二学期课程\\大数据架构技术\\wordCount\\word_out");
        FileSystem fs=FileSystem.get(conf);
        if (fs.exists(path)){
            fs.delete(path,true);
        }
        FileOutputFormat.setOutputPath(job,path);
        job.waitForCompletion(true);
    }
}