WordCount.java 2.1 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162
  1. package me.yoqi.hadoop.test;
  2. import java.io.IOException;
  3. import java.util.StringTokenizer;
  4. import org.apache.hadoop.conf.Configuration;
  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. public class WordCount {
  14. public static class TokenizerMapper
  15. extends Mapper<Object, Text, Text, IntWritable>{
  16. private final static IntWritable one = new IntWritable(1);
  17. private Text word = new Text();
  18. public void map(Object key, Text value, Context context
  19. ) throws IOException, InterruptedException {
  20. StringTokenizer itr = new StringTokenizer(value.toString());
  21. while (itr.hasMoreTokens()) {
  22. word.set(itr.nextToken());
  23. context.write(word, one);
  24. }
  25. }
  26. }
  27. public static class IntSumReducer
  28. extends Reducer<Text,IntWritable,Text,IntWritable> {
  29. private IntWritable result = new IntWritable();
  30. public void reduce(Text key, Iterable<IntWritable> values,
  31. Context context
  32. ) throws IOException, InterruptedException {
  33. int sum = 0;
  34. for (IntWritable val : values) {
  35. sum += val.get();
  36. }
  37. result.set(sum);
  38. context.write(key, result);
  39. }
  40. }
  41. public static void main(String[] args) throws Exception {
  42. Configuration conf = new Configuration();
  43. Job job = Job.getInstance(conf, "word count");
  44. job.setJarByClass(WordCount.class);
  45. job.setMapperClass(TokenizerMapper.class);
  46. job.setCombinerClass(IntSumReducer.class);
  47. job.setReducerClass(IntSumReducer.class);
  48. job.setOutputKeyClass(Text.class);
  49. job.setOutputValueClass(IntWritable.class);
  50. FileInputFormat.addInputPath(job, new Path(args[0]));
  51. FileOutputFormat.setOutputPath(job, new Path(args[1]));
  52. System.exit(job.waitForCompletion(true) ? 0 : 1);
  53. }
  54. }