SortedWordCount源代码以及过程分析

SortedWordCount源代码以及过程分析

运行截图：

]

代码逻辑：

Sort.java

//Sort.java--目的key从大到小排序

package com;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

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.io.WritableComparable;
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.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class Sort{
    public static class SimpleMapper 
         extends Mapper<IntWritable,Text,RevertKey,Text>{
        public void map(IntWritable key,Text value,Context context/*获取的key为单词数量，value为单词内容*/
                ) throws IOException, InterruptedException{
            RevertKey newkey =new RevertKey(key);/*目的key从大到小排序，hadoop中IntWritable默认从小到大排序，map的输出key作为一个自定义的key命名RevertKey，RevertKey希望实现从大到小的排序*/
            context.write(newkey,value);
        }
    }

    public static class SimpleReducer 
    extends Reducer<RevertKey,Text,Text,IntWritable>{
    public void reduce(RevertKey key,Iterable<Text>values,
            Context context
            ) throws IOException, InterruptedException{
        for (Text val : values) {//value迭代器迭代
        context.write(val,key.getKey());//单词内容，次数
    }
}
}
/*  
public static class SimpleReducer
         extends Reducer<RevertKey,Text,Text,IntWritable>{
        public void reduce(RevertKey key,Iterable<Text> values,
                Context context
                ) throws IOException,InterruptedException{
            for(Text val : values){
                context.write(val,key.getKey());
            }
        }
    }
*/
    public static class RevertKey 
         implements WritableComparable<RevertKey>{

        private IntWritable key;//真实的成员KEY
        public RevertKey(){
            key = new IntWritable();
        }
        public RevertKey(IntWritable key){
            this.key = key;
        }
        public IntWritable getKey(){
            return key;
        }
        @Override
        public int compareTo(RevertKey other) {
            return -key.compareTo(other.getKey());//完成从大到小的排序，设置compareTo方法的一个反序前面加‘-’
        }
        @Override
        public void readFields(DataInput in) throws IOException {
            key.readFields(in);
        }
        @Override
        public void write(DataOutput out) throws IOException {
            key.write(out);
        }

    }
    public static void main(String[] args) throws Exception {


        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        //这里需要配置参数即输入和输出的HDFS的文件路径
        if (otherArgs.length != 2) {
          System.err.println("Usage: wordcount <in> <out>");
          System.exit(2);
        }
       // JobConf conf1 = new JobConf(WordCount.class);
        Job job = new Job(conf, "Sort");//Job(Configuration conf, String jobName) 设置job名称和
        job.setJarByClass(Sort.class);
        job.setMapperClass(SimpleMapper.class); //为job设置Mapper类 

        job.setReducerClass(SimpleReducer.class); //为job设置Reduce类 

        job.setMapOutputKeyClass(RevertKey.class);  
        job.setMapOutputValueClass(Text.class); 

        job.setOutputKeyClass(Text.class);        //设置输出key的类型
        job.setOutputValueClass(IntWritable.class);//  设置输出value的类型

        job.setInputFormatClass(SequenceFileInputFormat.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0])); //为map-reduce任务设置InputFormat实现类   设置输入路径

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//为map-reduce任务设置OutputFormat实现类  设置输出路径
        System.exit(job.waitForCompletion(true) ? 0 : 1);
      }
}

WordCount.java

//WordCount.java，最终结果为单词数量和单词内容形成一个映射
package com;

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.mapred.JobConf;
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.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

     /** 
     * MapReduceBase类:实现了Mapper和Reducer接口的基类（其中的方法只是实现接口，而未作任何事情） 
     * Mapper接口： 
     * WritableComparable接口：实现WritableComparable的类可以相互比较。所有被用作key的类应该实现此接口。 
     * Reporter 则可用于报告整个应用的运行进度，本例中未使用。  
     *  
     */  
  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{

      /** 
       * LongWritable, IntWritable, Text 均是 Hadoop 中实现的用于封装 Java 数据类型的类，这些类实现了WritableComparable接口， 
       * 都能够被串行化从而便于在分布式环境中进行数据交换，你可以将它们分别视为long,int,String 的替代品。 
       */ 
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();//Text 实现了BinaryComparable类可以作为key值


    /** 
     * Mapper接口中的map方法： 
     * void map(K1 key, V1 value, OutputCollector<K2,V2> output, Reporter reporter) 
     * 映射一个单个的输入k/v对到一个中间的k/v对 
     * 输出对不需要和输入对是相同的类型，输入对可以映射到0个或多个输出对。 
     * OutputCollector接口：收集Mapper和Reducer输出的<k,v>对。 
     * OutputCollector接口的collect(k, v)方法:增加一个(k,v)对到output 
     */  

    public void map(Object key, Text value, Context context) throws IOException, 
    InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());//得到什么值
      //System.out.println("value什么东西 ： "+value.toString());
      //System.out.println("key什么东西 ： "+key.toString());

      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());

        context.write(word, one);
      }
    }
  }

  public static class IntSumReducer extends Reducer<Text,IntWritable,IntWritable,Text> {/*数据类型声明设置*/
    private IntWritable result = new IntWritable();
    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(result, key);
    }
  }

  public static class IntSumCombiner/*Combiner设置<不利于查看中间数据>,减少map和reduce中间的数据量，减少reduce拖取数据量，加快任务的性能*/
            extends Reducer<Text,IntWritable,Text,IntWritable>{/*输入数据和输出数据类型必须一致*/
      private IntWritable result = new IntWritable();
      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 {

      /** 
       * JobConf：map/reduce的job配置类，向hadoop框架描述map-reduce执行的工作 
       * 构造方法：JobConf()、JobConf(Class exampleClass)、JobConf(Configuration conf)等 
       */  

    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    //这里需要配置参数即输入和输出的HDFS的文件路径
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
   // JobConf conf1 = new JobConf(WordCount.class);
    Job job = new Job(conf, "word count");//Job(Configuration conf, String jobName) 设置job名称和
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class); //为job设置Mapper类 
    job.setCombinerClass(IntSumCombiner.class); //为job设置Combiner类  
    job.setReducerClass(IntSumReducer.class); //为job设置Reduce类 

    job.setMapOutputKeyClass(Text.class);  
    job.setMapOutputValueClass(IntWritable.class); /*声明map<key,value>类型，如果不声明就是和最终输出是一致的*/

    job.setOutputKeyClass(IntWritable.class);        //设置输出key的类型 ; 将原始的wordcount的最终输出的数据格式<key,value>的数据类型呼唤，做排序的输入
    job.setOutputValueClass(Text.class);//  设置输出value的类型

    job.setOutputFormatClass(SequenceFileOutputFormat.class);//方便第二个任务做输入，SequenceFile是Hadoop API提供的一种二进制文件支持。这种二进制文件直接将<key,value>对序列化到文件中，一般对小文件可以使用这种文件合并，即将文件名作为key，文件内容作为value序列化到大文件中。
    FileInputFormat.addInputPath(job, new Path(otherArgs[0])); //为map-reduce任务设置InputFormat实现类   设置输入路径

    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//为map-reduce任务设置OutputFormat实现类  设置输出路径
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

//shuffle error是计数器输出
可查看下hadoop的源代码，我看的是cdh版本的hadoop源代码hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/reduce/Fetcher.java

这些系统自带的计数器是在配置文件中配置的，可以在以下文件中找到。
./hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/org/apache/hadoop/mapreduce/lib/output/FileOutputFormatCounter.properties

./hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/org/apache/hadoop/mapreduce/lib/input/FileInputFormatCounter.properties

./hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/org/apache/hadoop/mapreduce/TaskCounter.properties

./hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/org/apache/hadoop/mapreduce/JobCounter.properties

./hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/org/apache/hadoop/mapreduce/FileSystemCounter.properties

//另外请注意，SequenceFileOutputFormat，输出的内容是不可读的！

//Shuffle Error统计在Shuffle中的错误情况，我这输出表示任务map到reduce之间没什么错误。

flase，是指当前的mapreduce不是的uber mode的。 uber mode是mapreduce 2.x中一个特殊的mapreduce执行方式，它将map/reduce任务放到ApplicationMaster中执行，而不是分布式执行。这用于执行数据集很小的任务或者测试任务时使用。