1 package hdfs;
 2 
 3 import java.io.IOException;
 4 import java.util.*;
 5 
 6 import org.apache.hadoop.fs.Path;
 7 import org.apache.hadoop.conf.*;
 8 import org.apache.hadoop.io.*;
 9 import org.apache.hadoop.mapreduce.*;
10 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
11 import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
12 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
13 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
14 
15 /**
16  * 描述：WordCount explains by xxm
17  * @author xxm
18  */
19 public class WordCount {
20 
21  /**
22  * Map类：自己定义map方法
23  */
24  public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
25     /**
26     * LongWritable, IntWritable, Text 均是 Hadoop 中实现的用于封装 Java 数据类型的类
27     * 都能够被串行化从而便于在分布式环境中进行数据交换，可以将它们分别视为long,int,String 的替代品。
28     */
29     private final static IntWritable one = new IntWritable(1);
30     private Text word = new Text();
31     /**
32     * Mapper类中的map方法：
33     * protected void map(KEYIN key, VALUEIN value, Context context)
34     * 映射一个单个的输入k/v对到一个中间的k/v对
35     * Context类：收集Mapper输出的<k,v>对。
36     */
37     public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
38         String line = value.toString();
39         StringTokenizer tokenizer = new StringTokenizer(line);
40         while (tokenizer.hasMoreTokens()) {
41             word.set(tokenizer.nextToken());
42             context.write(word, one);
43         }
44     }
45  } 
46 
47  /**
48  * Reduce类：自己定义reduce方法
49  */       
50  public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
51 
52     /**
53     * Reducer类中的reduce方法：
54     * protected void reduce(KEYIN key, Interable<VALUEIN> value, Context context)
55     * 映射一个单个的输入k/v对到一个中间的k/v对
56     * Context类：收集Reducer输出的<k,v>对。
57     */
58     public void reduce(Text key, Iterable<IntWritable> values, Context context) 
59       throws IOException, InterruptedException {
60         int sum = 0;
61         for (IntWritable val : values) {
62             sum += val.get();
63         }
64         context.write(key, new IntWritable(sum));
65     }
66  }
67 
68  /**
69  * main主函数
70  */       
71  public static void main(String[] args) throws Exception {
72 
73     Configuration conf = new Configuration();//创建一个配置对象，用来实现所有配置
74 //    conf.set("fs.defaultFS", "hdfs://ssmaster:9000/");
75     
76     Job job = new Job(conf, "wordcount");//新建一个job，并定义名称
77 
78     job.setOutputKeyClass(Text.class);//为job的输出数据设置Key类
79     job.setOutputValueClass(IntWritable.class);//为job输出设置value类
80     
81     job.setMapperClass(Map.class); //为job设置Mapper类
82     job.setReducerClass(Reduce.class);//为job设置Reduce类
83     job.setJarByClass(WordCount.class);
84 
85     job.setInputFormatClass(TextInputFormat.class);//为map-reduce任务设置InputFormat实现类
86     job.setOutputFormatClass(TextOutputFormat.class);//为map-reduce任务设置OutputFormat实现类
87 
88     FileInputFormat.addInputPath(job, new Path(args[0]));//为map-reduce job设置输入路径
89     FileOutputFormat.setOutputPath(job, new Path(args[1]));//为map-reduce job设置输出路径
90     job.waitForCompletion(true); //运行一个job，并等待其结束
91  }
92 
93 }