Mapreduce-實現webcount代碼

參考博文：https://blog.csdn.net/qq_41035588/article/details/90514824

首先安裝一個Hadoop-Eclipse-Plugin 方便來對於hdfs進行管理

參考地址：http://dblab.xmu.edu.cn/blog/hadoop-build-project-using-eclipse/

配置好Hadoop-Ecllipse-Plugin以後

創建一個txt文檔，裏面的內容以下：

 1 買家id 商品id 收藏日期
 2 10181 1000481 2010-04-04 16:54:31
 3 20001 1001597 2010-04-07 15:07:52
 4 20001 1001560 2010-04-07 15:08:27
 5 20042 1001368 2010-04-08 08:20:30
 6 20067 1002061 2010-04-08 16:45:33
 7 20056 1003289 2010-04-12 10:50:55
 8 20056 1003290 2010-04-12 11:57:35
 9 20056 1003292 2010-04-12 12:05:29
10 20054 1002420 2010-04-14 15:24:12
11 20055 1001679 2010-04-14 19:46:04
12 20054 1010675 2010-04-14 15:23:53
13 20054 1002429 2010-04-14 17:52:45
14 20076 1002427 2010-04-14 19:35:39
15 20054 1003326 2010-04-20 12:54:44
16 20056 1002420 2010-04-15 11:24:49
17 20064 1002422 2010-04-15 11:35:54
18 20056 1003066 2010-04-15 11:43:01
19 20056 1003055 2010-04-15 11:43:06
20 20056 1010183 2010-04-15 11:45:24
21 20056 1002422 2010-04-15 11:45:49
22 20056 1003100 2010-04-15 11:45:54
23 20056 1003094 2010-04-15 11:45:57
24 20056 1003064 2010-04-15 11:46:04
25 20056 1010178 2010-04-15 16:15:20
26 20076 1003101 2010-04-15 16:37:27
27 20076 1003103 2010-04-15 16:37:05
28 20076 1003100 2010-04-15 16:37:18
29 20076 1003066 2010-04-15 16:37:31
30 20054 1003103 2010-04-15 16:40:14
31 20054 1003100 2010-04-15 16:40:16

而後創建一個java項目

而後把全部的包都導進去，重點是mapreduce,common,yarn,hdfs的包

而後再輸入代碼：

 1 package mapreduce;
 2 
 3 import java.io.IOException;
 4 import java.util.StringTokenizer;
 5 import org.apache.hadoop.fs.Path;
 6 import org.apache.hadoop.io.IntWritable;
 7 import org.apache.hadoop.io.Text;
 8 import org.apache.hadoop.mapreduce.Job;
 9 import org.apache.hadoop.mapreduce.Mapper;
10 import org.apache.hadoop.mapreduce.Reducer;
11 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
12 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
13 
14 
15 public class WordCount {
16 
17 public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{
18     //第一個object表示輸入key的類型，第二個text表示輸入value的類型；第三個text表示輸出建的類型；
19     //第四個INtWritable表示輸出值的類型
20     
21 public static final IntWritable one = new IntWritable(1);
22 public static Text word = new Text();
23 @Override
24 protected void map(Object key, Text value, Context context)
25 //key value是輸入的key value context是記錄輸入的key,value
26 throws IOException, InterruptedException {
27 StringTokenizer tokenizer = new StringTokenizer(value.toString(), "\t");
28 //StringTokenizer是Java的工具包中的一個類，用於將字符串進行拆分
29 word.set(tokenizer.nextToken());
30 //返回當前位置到下一個分隔符之間的字符串
31 context.write(word, one);
32 //講word存到容器中計一個數
33 }
34 }
35 public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
36     //輸入鍵類型，輸入值類型 輸出建類型，輸出值類型
37 private IntWritable result = new IntWritable();
38 @Override
39 protected void reduce(Text key, Iterable<IntWritable> values, Context context)
40 throws IOException, InterruptedException {
41 int sum = 0;
42 for (IntWritable value : values) {
43 sum += value.get();
44 }
45 result.set(sum);
46 context.write(key, result);
47 }
48 }
49 public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
50 Job job = Job.getInstance();
51 job.setJobName("WordCount");
52 job.setJarByClass(WordCount.class);
53 job.setMapperClass(doMapper.class);
54 job.setReducerClass(doReducer.class);
55 job.setOutputKeyClass(Text.class);
56 job.setOutputValueClass(IntWritable.class);
57 Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/buyer_favorite1");
58 Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");
59 FileInputFormat.addInputPath(job, in);
60 FileOutputFormat.setOutputPath(job, out);
61 System.exit(job.waitForCompletion(true) ? 0 : 1);    
62 }
63 }

而後運行以後查看左邊的菜單：

 

雙擊part-r-00000就有返回的值了

 

 

 最重要的問題就是分隔的問題

1.     StringTokenizer tokenizer = new StringTokenizer(value.toString(),"\t");  

這個是根據tab鍵來進行分割，可是咱們複製粘貼後就是空格因此要換成空格