MyReduce经典习题练习

实现过程所需的java代码

1，在hdfs目录/tmp/input/wordcount中有一系列文件，内容均为","号分隔，

求按","号分隔的各个元素的出现频率，输出到目录/tmp/个人用户名的hdfs目录中。

实现代码：

package com.tledu.hadoop.mr.homework;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
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 java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;

public class HomeWork1 {
    public static class HomeWork1Mapper extends Mapper<Object, Text, Text, IntWritable> {
        Text word = new Text();
        IntWritable one = new IntWritable(1);

        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer str = new StringTokenizer(value.toString(), ",");
            while (str.hasMoreTokens()) {
                word.set(str.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class HomeWork1Reducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        IntWritable sumRes = 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();
            }
            sumRes.set(sum);
            context.write(key, sumRes);
        }
    }

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        // 1. 创建配置
        Configuration conf = new Configuration();
        // 2. 创建任务
        Job job = Job.getInstance(conf, "homework1");
        // 3. 设置对应类
        job.setJarByClass(HomeWork1.class);
        job.setMapperClass(HomeWork1Mapper.class);
        job.setCombinerClass(HomeWork1Reducer.class);
        job.setReducerClass(HomeWork1Reducer.class);
        // 4. 输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        // 5. 输入和输出的路径
        // 获取所有输入的txt文件
        List<String> fileList = getTxtFileListFromPath(args[0]);
        for (String filePath : fileList) {
            FileInputFormat.addIn