WordCount 实例

 http://www.iteye.com/topic/606962

http://www.iteye.com/topic/1117343

看了到Hadoop的代码，还是不知道他的执行流程，怎么办呢。我想到了日志，在hadoop的目录下，有log4j,那就用户Log4j来记录Hadoop的执行过程吧.

Java代码  

1.   
2.   
3. import java.io.IOException;   
4. import java.util.StringTokenizer;   
5.   
6. import org.apache.hadoop.conf.Configuration;   
7. import org.apache.hadoop.fs.Path;   
8. import org.apache.hadoop.io.IntWritable;   
9. import org.apache.hadoop.io.Text;   
10. import org.apache.hadoop.mapreduce.Job;   
11. import org.apache.hadoop.mapreduce.Mapper;   
12. import org.apache.hadoop.mapreduce.Reducer;   
13. import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;   
14. import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;   
15. import org.apache.hadoop.util.GenericOptionsParser;   
16. import org.apache.log4j.Logger;   
17.   
18. public class WordCount {   
19.   
20.   public static Logger loger = Wloger.loger;   
21.   
22.   /**  
23.    * TokenizerMapper 继续自 Mapper<Object, Text, Text, IntWritable>  
24.    *  
25.    * [一个文件就一个map,两个文件就会有两个map]  
26.    * map[这里读入输入文件内容 以" \t\n\r\f" 进行分割，然后设置 word ==> one 的key/value对]  
27.    *  
28.    * @param Object  Input key Type:  
29.    * @param Text    Input value Type:  
30.    * @param Text    Output key Type:  
31.    * @param IntWritable Output value Type:  
32.    *  
33.    * Writable的主要特点是它使得Hadoop框架知道对一个Writable类型的对象怎样进行serialize以及deserialize.  
34.    * WritableComparable在Writable的基础上增加了compareT接口，使得Hadoop框架知道怎样对WritableComparable类型的对象进行排序。  
35.    *  
36.    * @author yangchunlong.tw  
37.    *  
38.    */  
39.   public static class TokenizerMapper   
40.        extends Mapper<Object, Text, Text, IntWritable>{   
41.   
42.     private final static IntWritable one = new IntWritable(1);   
43.     private Text word = new Text();   
44.     public void map(Object key, Text value, Context context   
45.                     ) throws IOException, InterruptedException {   
46.       loger.info("Map <key>"+key+"</key>");   
47.       loger.info("Map <value>"+value+"</key>");   
48.       StringTokenizer itr = new StringTokenizer(value.toString());   
49.       while (itr.hasMoreTokens()) {   
50.         String wordstr = itr.nextToken();   
51.         word.set(wordstr);   
52.         loger.info("Map <word>"+wordstr+"</word>");   
53.         context.write(word, one);   
54.       }   
55.     }   
56.   }   
57.   
58.   /**  
59.    * IntSumReducer 继承自 Reducer<Text,IntWritable,Text,IntWritable>  
60.    *  
61.    * [不管几个Map,都只有一个Reduce,这是一个汇总]  
62.    * reduce[循环所有的map值,把word ==> one 的key/value对进行汇总]  
63.    *  
64.    * 这里的key为Mapper设置的word[每一个key/value都会有一次reduce]  
65.    *  
66.    * 当循环结束后，最后的确context就是最后的结果.  
67.    *  
68.    * @author yangchunlong.tw  
69.    *  
70.    */  
71.   public static class IntSumReducer   
72.        extends Reducer<Text,IntWritable,Text,IntWritable> {   
73.     private IntWritable result = new IntWritable();   
74.   
75.     public void reduce(Text key, Iterable<IntWritable> values,   
76.                        Context context   
77.                        ) throws IOException, InterruptedException {   
78.       loger.info("Reduce <key>"+key+"</key>");   
79.       loger.info("Reduce <value>"+values+"</key>");   
80.       int sum = 0;   
81.       for (IntWritable val : values) {   
82.         sum += val.get();   
83.       }   
84.       result.set(sum);   
85.       loger.info("Reduce <sum>"+sum+"</sum>");   
86.       context.write(key, result);   
87.     }   
88.   }   
89.   
90.   public static void main(String[] args) throws Exception {   
91.     Configuration conf = new Configuration();   
92.     String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();   
93.     /**  
94.      * 这里必须有输入/输出  
95.      */  
96.     if (otherArgs.length != 2) {   
97.       System.err.println("Usage: wordcount <in> <out>");   
98.       System.exit(2);   
99.     }   
100.     Job job = new Job(conf, "word count");   
101.     job.setJarByClass(WordCount.class);//主类   
102.     job.setMapperClass(TokenizerMapper.class);//mapper   
103.     job.setCombinerClass(IntSumReducer.class);//作业合成类   
104.     job.setReducerClass(IntSumReducer.class);//reducer   
105.     job.setOutputKeyClass(Text.class);//设置作业输出数据的关键类   
106.     job.setOutputValueClass(IntWritable.class);//设置作业输出值类   
107.     FileInputFormat.addInputPath(job, new Path(otherArgs[0]));//文件输入   
108.     FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//文件输出   
109.     System.exit(job.waitForCompletion(true) ? 0 : 1);//等待完成退出.   
110.   }   
111. }  

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;
import org.apache.log4j.Logger;

public class WordCount {

  public static Logger loger = Wloger.loger;

  /**
   * TokenizerMapper 继续自 Mapper<Object, Text, Text, IntWritable>
   *
   * [一个文件就一个map,两个文件就会有两个map]
   * map[这里读入输入文件内容 以" \t\n\r\f" 进行分割，然后设置 word ==> one 的key/value对]
   *
   * @param Object  Input key Type:
   * @param Text    Input value Type:
   * @param Text    Output key Type:
   * @param IntWritable Output value Type:
   *
   * Writable的主要特点是它使得Hadoop框架知道对一个Writable类型的对象怎样进行serialize以及deserialize.
   * WritableComparable在Writable的基础上增加了compareT接口，使得Hadoop框架知道怎样对WritableComparable类型的对象进行排序。
   *
   * @author yangchunlong.tw
   *
   */
  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, 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 {
      loger.info("Map <key>"+key+"</key>");
      loger.info("Map <value>"+value+"</key>");
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
    	String wordstr = itr.nextToken();
        word.set(wordstr);
        loger.info("Map <word>"+wordstr+"</word>");
        context.write(word, one);
      }
    }
  }

  /**
   * IntSumReducer 继承自 Reducer<Text,IntWritable,Text,IntWritable>
   *
   * [不管几个Map,都只有一个Reduce,这是一个汇总]
   * reduce[循环所有的map值,把word ==> one 的key/value对进行汇总]
   *
   * 这里的key为Mapper设置的word[每一个key/value都会有一次reduce]
   *
   * 当循环结束后，最后的确context就是最后的结果.
   *
   * @author yangchunlong.tw
   *
   */
  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 {
      loger.info("Reduce <key>"+key+"</key>");
      loger.info("Reduce <value>"+values+"</key>");
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      loger.info("Reduce <sum>"+sum+"</sum>");
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    /**
     * 这里必须有输入/输出
     */
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);//主类
    job.setMapperClass(TokenizerMapper.class);//mapper
    job.setCombinerClass(IntSumReducer.class);//作业合成类
    job.setReducerClass(IntSumReducer.class);//reducer
    job.setOutputKeyClass(Text.class);//设置作业输出数据的关键类
    job.setOutputValueClass(IntWritable.class);//设置作业输出值类
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));//文件输入
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//文件输出
    System.exit(job.waitForCompletion(true) ? 0 : 1);//等待完成退出.
  }
}

这里输出了每一次Map，每一次Reduce.结果如下:

Java代码  

1. f1 ==>Map Result   
2. Map <key>0</key>   
3. Map <value>ycl ycl is ycl good</key>   
4. Map <word>ycl</word>   
5. Map <word>ycl</word>   
6. Map <word>is</word>   
7. Map <word>ycl</word>   
8. Map <word>good</word>   
9.   
10. f1 ==>Reduce Result   
11. Reduce <key>good</key>   
12. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>   
13. Reduce <sum>1</sum>   
14. Reduce <key>is</key>   
15. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>   
16. Reduce <sum>1</sum>   
17. Reduce <key>ycl</key>   
18. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>   
19. Reduce <sum>3</sum>   
20.   
21. f2 ==>Map Result   
22. Map <key>0</key>   
23. Map <value>hello ycl hello lg</key>   
24. Map <word>hello</word>   
25. Map <word>ycl</word>   
26. Map <word>hello</word>   
27. Map <word>lg</word>   
28.   
29. f2 ==>Reduce Result   
30. Reduce <key>hello</key>   
31. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>   
32. Reduce <sum>2</sum>   
33. Reduce <key>lg</key>   
34. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>   
35. Reduce <sum>1</sum>   
36. Reduce <key>ycl</key>   
37. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>   
38. Reduce <sum>1</sum>   
39.   
40. f1,f2 ==> Reduce Result   
41. Reduce <key>good</key>   
42. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>   
43. Reduce <sum>1</sum>   
44. Reduce <key>hello</key>   
45. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>   
46. Reduce <sum>2</sum>   
47. Reduce <key>is</key>   
48. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>   
49. Reduce <sum>1</sum>   
50. Reduce <key>lg</key>   
51. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>   
52. Reduce <sum>1</sum>   
53. Reduce <key>ycl</key>   
54. Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>   
55. Reduce <sum>4</sum>  

f1 ==>Map Result
Map <key>0</key>
Map <value>ycl ycl is ycl good</key>
Map <word>ycl</word>
Map <word>ycl</word>
Map <word>is</word>
Map <word>ycl</word>
Map <word>good</word>

f1 ==>Reduce Result
Reduce <key>good</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>
Reduce <sum>1</sum>
Reduce <key>is</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>
Reduce <sum>1</sum>
Reduce <key>ycl</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1dfc547</key>
Reduce <sum>3</sum>

f2 ==>Map Result
Map <key>0</key>
Map <value>hello ycl hello lg</key>
Map <word>hello</word>
Map <word>ycl</word>
Map <word>hello</word>
Map <word>lg</word>

f2 ==>Reduce Result
Reduce <key>hello</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>
Reduce <sum>2</sum>
Reduce <key>lg</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>
Reduce <sum>1</sum>
Reduce <key>ycl</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@10f6d3</key>
Reduce <sum>1</sum>

f1,f2 ==> Reduce Result
Reduce <key>good</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>
Reduce <sum>1</sum>
Reduce <key>hello</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>
Reduce <sum>2</sum>
Reduce <key>is</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>
Reduce <sum>1</sum>
Reduce <key>lg</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>
Reduce <sum>1</sum>
Reduce <key>ycl</key>
Reduce <value>org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@1989f84</key>
Reduce <sum>4</sum>

正常人应该能分析出map/reduce的执行机制，比如有两个输入文件，map/reduce是一个文件一个文件进行处理的，每map一个输入文件就会reduce一次，最后再进行总的reduce.