MapReduce实例

1.WordCount（统计单词）

经典的运用MapReuce编程模型的实例

1.1 Description

给定一系列的单词/数据，输出每个单词/数据的数量

1.2 Sample

 a is b is not c
 b is a is not d

1.3 Output

 a:
 b:
 c:
 d:
 is:
 not:

1.4 Solution

 /**
  *  Licensed 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 org.apache.hadoop.examples;

 import java.io.File;
 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 {

   //map输出的<key,value>为<输入的单词/数据,1>即<Text,IntWritable>
   public static class TokenizerMapper
        extends Mapper<Object, Text, Text, IntWritable>{
     //value为封装好的int即IntWritable
     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());
       while (itr.hasMoreTokens()) {
         word.set(itr.nextToken());//word为每个单词/数据,以空格为分隔符识别
         context.write(word, one);
       }
     }
   }

   //reduce输入的<key,value>为<输入的单词/数据,各个值的1相加即sum(实际是一个list)>
   //即<Text,IntWrite>
   public static class IntSumReducer
        extends Reducer<Text,IntWritable,Text,IntWritable> {
     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 {
     Configuration conf = new Configuration();
     String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
     if (otherArgs.length != 2) {
       System.err.println("Usage: wordcount <in> <out>");
       System.exit(2);
     }
     //删除已存在的输出文件夹
     judgeFileExist(otherArgs[1]);
     Job job = new Job(conf, "word count");
     job.setJarByClass(WordCount.class);
     job.setMapperClass(TokenizerMapper.class);
     job.setCombinerClass(IntSumReducer.class);
     job.setReducerClass(IntSumReducer.class);
     job.setOutputKeyClass(Text.class);
     job.setOutputValueClass(IntWritable.class);
     FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
     FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
     System.exit(job.waitForCompletion(true) ? 0 : 1);
   }

   //删除文件夹及其目录下的文件
   public static void judgeFileExist(String path){
       File file = new File(path);
       if( file.exists() ){
           deleteFileDir(file);
       }
   }

   public static void deleteFileDir(File path){
       if( path.isDirectory() ){
           String[] files = path.list();
           for( int i=0;i<files.length;i++ ){
               deleteFileDir( new File(path,files[i]) );
           }
       }
       path.delete();
   }

 }

2. 数据去重

2.1 Description

针对给定一系列的数据去重并输出

2.2 Sample

 3-1 a
 3-2 b
 3-3 c
 3-4 d
 3-5 a
 3-6 b
 3-7 c
 3-3 c
 3-1 b
 3-2 a
 3-3 b
 3-4 d
 3-5 a
 3-6 c
 3-7 d
 3-3 c

2.3 Output

 3-1 a
 3-1 b
 3-2 a
 3-2 b
 3-3 b
 3-3 c
 3-4 d
 3-5 a
 3-6 b
 3-6 c
 3-7 c
 3-7 d

2.4 Solution

 /**
  *  Licensed 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 org.apache.hadoop.examples;

 import java.io.File;
 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 Map extends Mapper<Object,Text,Text,Text>{//map最后一个指定Text
      public static Text lineWords= new Text();

      //map输出为<Text,Text>,因为只涉及到是否Key存在的问题，故value可任意
      public void map(Object key,Text value,Context context)
              throws IOException, InterruptedException{
          lineWords = value;
          context.write(lineWords, new Text(""));//<Text,Text>
      }
  }

  public static class Reduce extends Reducer<Text,Text,Text,Text>{
      public void reduce(Text key,Iterable<Text> values,Context context)
              throws IOException, InterruptedException{
          context.write(key,new Text(""));
      }
  }

  public static void main(String args[])
          throws IOException, ClassNotFoundException, InterruptedException{
      Configuration conf = new Configuration();

      String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
      if( otherArgs.length!=2 ){
          System.err.println("Usage: Data Deduplication <in> <out>");
          System.exit(2);
      }

      //删除已存在的输出文件夹
      judgeFileExist(otherArgs[1]);
      Job job = new Job(conf,"Data Dup");
      job.setJarByClass(WordCount.class);
      //设置map combine reduce处理类
      job.setMapperClass(Map.class);
      job.setCombinerClass(Reduce.class);
      job.setReducerClass(Reduce.class);
      //设置key value的类型
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(Text.class);
      //设置输入和输出目录
      FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
      FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
      System.exit(job.waitForCompletion(true) ? 0 : 1);
  }

   //删除文件夹及其目录下的文件
   public static void judgeFileExist(String path){
       File file = new File(path);
       if( file.exists() ){
           deleteFileDir(file);
       }
   }

   public static void deleteFileDir(File path){
       if( path.isDirectory() ){
           String[] files = path.list();
           for( int i=0;i<files.length;i++ ){
               deleteFileDir( new File(path,files[i]) );
           }
       }
       path.delete();
   }

 }

3. 数据排序

3.1 Description

给多个文件的数据排序，每个文件中的每个数据占一行

3.2 Sample

3.3 Output

3.4 Solution

 /**
  *  Licensed 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 org.apache.hadoop.example;

 import java.io.File;
 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.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 dataSort{

     public static class map extends Mapper<Object,Text,IntWritable,IntWritable>{
         private static IntWritable data = new IntWritable();
         String lineWords = new String();
         //map
         public void map(Object key,Text value,Context context)
                 throws IOException, InterruptedException{
             lineWords = value.toString();
             data.set(Integer.parseInt(lineWords));
             context.write(data,new IntWritable(1));
         }
     }

     public static class reduce extends Reducer<IntWritable, IntWritable,IntWritable,IntWritable>{
         private static IntWritable lineNum = new IntWritable(1);
         public void reduce(IntWritable key,Iterable<IntWritable> values,Context context)
                 throws IOException, InterruptedException{
             for(IntWritable val:values){
                 context.write(lineNum,key);
                 lineNum = new IntWritable(lineNum.get()+1);
             }
         }
     }

     public static void main(String args[])
             throws IOException, ClassNotFoundException, InterruptedException{
         Configuration conf = new Configuration();

          String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
          if( otherArgs.length!=2 ){
              System.err.println("Usage: Data Deduplication <in> <out>");
              System.exit(2);
          }

          //删除已存在的输出文件夹
          judgeFileExist(otherArgs[1]);
          Job job = new Job(conf,"Data Dup");
          job.setJarByClass(dataSort.class);
          //设置map combine reduce处理类
          job.setMapperClass(map.class);
          job.setCombinerClass(reduce.class);
          job.setReducerClass(reduce.class);
          //设置key value的类型
          job.setOutputKeyClass(IntWritable.class);
          job.setOutputValueClass(IntWritable.class);
          //设置输入和输出目录
          FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
          FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
          System.exit(job.waitForCompletion(true) ? 0 : 1);
     }
     //删除文件夹及其目录下的文件
       public static void judgeFileExist(String path){
           File file = new File(path);
           if( file.exists() ){
               deleteFileDir(file);
           }
       }

       public static void deleteFileDir(File path){
           if( path.isDirectory() ){
               String[] files = path.list();
               for( int i=0;i<files.length;i++ ){
                   deleteFileDir( new File(path,files[i]) );
               }
           }
           path.delete();
       }
 }