WordCount源码分析

MapReduce WordCount的执行流程如下：

源码如下：

 package org.apache.hadoop.examples;
    
    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 TokenizerMapper 
           extends Mapper<Object, Text, Text, IntWritable>{
      	//实质是包含一个整数的对象  
        private final static IntWritable one = new IntWritable(1);
        //其实质是一个包含byte[] bytes的对象，将传入的字符串转换为byte[]
        private Text word = new Text();
          
        public void map(Object key, Text value, Context context
                        ) throws IOException, InterruptedException {
           //默认将传入的字符串根据" \t\n\r\f"分割，不是真分割，只是记录下了需要分割的位置
          StringTokenizer itr = new StringTokenizer(value.toString());
          while (itr.hasMoreTokens()) {
          	//根据之前做好的标记，截取字符串
            word.set(itr.nextToken());
            context.write(word, one);
          }
        }
      }
      
      public static class IntSumReducer 
           extends Reducer<Text,IntWritable,Text,IntWritable> {
        private IntWritable result = new IntWritable();
    	//将相同key的value累加
        public 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 {
     	 //提供对配置参数的访问
        Configuration conf = new Configuration();
        //获取其他参数，这里是指输入路径和输出路径
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
          System.err.println("Usage: wordcount <in> [<in>...] <out>");
          System.exit(2);
        }
        //初始化一个新的job
        Job job = Job.getInstance(conf, "word count");
        //指定启动类
        job.setJarByClass(WordCount.class);
        //设置map过程类
        job.setMapperClass(TokenizerMapper.class);
        //为作业设置组合器类
        job.setCombinerClass(IntSumReducer.class);
        //设置reduce过程类
        job.setReducerClass(IntSumReducer.class);
        //输出key类型
        job.setOutputKeyClass(Text.class);
        //输出value类型
        job.setOutputValueClass(IntWritable.class);
        //输入文件路径
        for (int i = 0; i < otherArgs.length - 1; ++i) {
          FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        //输出文件路径
        FileOutputFormat.setOutputPath(job,
          new Path(otherArgs[otherArgs.length - 1]));
        //提交作业等待返回结果
        System.exit(job.waitForCompletion(true) ? 0 : 1);
      }
    }