【hadoop】看懂WordCount例子

前言：今天刚开始看到map和reduce类里面的内容时，说实话一片迷茫，who are you?，最后实在没办法，上B站看别人的解说视频，再加上自己去网上查java的包的解释，终于把WordCount例子看懂，准备后面自己写一遍！实话说，现在实在肝不动了，每天只有晚上有点时间来学习，代码贴上来，睡觉！

正文：实在不想写太多，解释都在代码的注释里面，饶了我吧！

贴一个讲的比较好的网址：https://www.cnblogs.com/houji/p/7161468.html

代码如下：

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package com.hadoop;

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 {//WordCount是类名，要用public class进行修饰，java程序由类（class）组成，一个源文件可以包含多个类

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{
/***
               Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
                      行偏移量 输入值  输出key  输出值
***/

    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 {
      StringTokenizer itr = new StringTokenizer(value.toString());//value.toString()获取输入值,并用StringTokenizer进行分隔（默认空格）
      while (itr.hasMoreTokens()) { //判断itr是否还有字符串，返回true或false
        word.set(itr.nextToken()); //set方法给word赋值，nextToken()返回下一个标记
        context.write(word, one);//输出<'word',1>
      }
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values,  //values 里面存储着map输出数据，格式为 'word list<1,1,1,1,1>'
                       Context context
                       ) throws IOException, InterruptedException {

      int sum = 0;//自定义一个计数器
      for (IntWritable val : values) { //循环list里面的值
        sum += val.get();//求和
      }
      result.set(sum);//赋值给result
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception { //1、Java程序的入口，public static void main(String[] args){}是固定用法，public static void都是关键字。2、throws：声明一个异常可能被抛出
    /***
    Create a new Job
    ***/
    Configuration conf = new Configuration();  //实例化Configuration，读取Hadoop配置信息
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); //读取Hadoop的argument填入地址信息
    if (otherArgs.length < 2) {//若填入的地址小于2，报错并输出"Usage: wordcount <in> [<in>...] <out>"
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");//单例模式getInstance(),在主函数开始时调用，返回一个实例化对象，此对象是static的，在内存中保留着它的引用
    job.setJarByClass(WordCount.class);
    //设置Job处理的Map（拆分）、Combiner（中间结果合并）以及Reduce（合并）的相关处理类
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    //设置job输出结果<key,value>的中key和value数据类型
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    /***
    调用addInputPath()和setOutputPath()设置输入输出路径置
    InputFormat()方法是用来生成可供map处理的<key,value>对的
    ***/
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1); //运行job
  }
}