虚拟机复制

1. package com.simple.mr;
2. 　
3. import java.io.IOException;
4. import java.util.StringTokenizer;
5. import org.apache.hadoop.io.IntWritable;
6. import org.apache.hadoop.io.LongWritable;
7. import org.apache.hadoop.io.Text;
8. import org.apache.hadoop.mapreduce.Mapper;
9. 　
10. public class TotalScoreMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
11. @Override
12. protected void map(LongWritable key, Text value, Context context)
13. throws IOException, InterruptedException {
14. // 读取一行数据
15. String val = value.toString();
16. 　
17. // 把读取的数据以换行作为分割符
18. StringTokenizer stringTokenizer = new StringTokenizer(val, "\t");
19. 　
20. while(stringTokenizer.hasMoreElements()) {
21. StringTokenizer tmp = new StringTokenizer(stringTokenizer.nextToken());
22. 　
23. // 对读取的一行的名称和成绩进行切分并写入到context对象中
24. String username = tmp.nextToken();
25. String score = tmp.nextToken();
26. 　
27. context.write(new Text(username), new IntWritable(Integer.valueOf(score)));
28. }
29. }
30. }

1. package com.simple.mr;
2. 　
3. import java.io.IOException;
4. import java.util.Iterator;
5. import org.apache.hadoop.io.IntWritable;
6. import org.apache.hadoop.io.Text;
7. import org.apache.hadoop.mapreduce.Reducer;
8. 　
9. public class TotalScoreReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
10. 　
11. @Override
12. protected void reduce(Text key, Iterable<IntWritable> values,Context context)
13. throws IOException, InterruptedException {
14. 　
15. // 获取对键值集合遍历对象
16. Iterator<IntWritable> iterator = values.iterator();
17. 　
18. int sum =0;
19. // 循环获取相同键的所有值并计算和
20. while(iterator.hasNext()){
21. int v = iterator.next().get();
22. sum += v;
23. }
24. 　
25. context.write(key, new IntWritable(sum));
26. }
27. }

1. package com.simple.mr;
2. 　
3. import org.apache.hadoop.conf.Configuration;
4. import org.apache.hadoop.fs.Path;
5. import org.apache.hadoop.io.IntWritable;
6. import org.apache.hadoop.io.Text;
7. import org.apache.hadoop.mapreduce.Job;
8. import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
9. import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
10. 　
11. public class TotalScoreDriver {
12. public static void main(String[] args) throws Exception{
13. //获取作业对象
14. Job job = Job.getInstance(new Configuration());
15. 　
16. //设置主类
17. job.setJarByClass(TotalScoreDriver.class);
18. 　
19. //设置job参数
20. job.setMapperClass(TotalScoreMapper.class);
21. job.setReducerClass(TotalScoreReducer.class);
22. 　
23. job.setMapOutputKeyClass(Text.class);
24. job.setMapOutputValueClass(IntWritable.class);
25. 　
26. job.setOutputKeyClass(Text.class);
27. job.setOutputValueClass(IntWritable.class);
28. 　
29. //设置job输入输出
30. FileInputFormat.setInputPaths(job, new Path("hdfs://localhost:9000/data/dataset/input/score.txt"));
31. FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/data/dataset/output"));
32. 　
33. System.exit(job.waitForCompletion(true) ? 0 : 1);
34. }
35. }