| | 1 | import java.io.IOException; |
| | 2 | import java.util.StringTokenizer; |
| | 3 | |
| | 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 | import org.apache.hadoop.util.GenericOptionsParser; |
| | 14 | |
| | 15 | public class WordCount { |
| | 16 | |
| | 17 | public static class TokenizerMapper |
| | 18 | extends Mapper<Object, Text, Text, IntWritable>{ |
| | 19 | |
| | 20 | private final static IntWritable one = new IntWritable(1); |
| | 21 | private Text word = new Text(); |
| | 22 | |
| | 23 | public void map(Object key, Text value, Context context |
| | 24 | ) throws IOException, InterruptedException { |
| | 25 | StringTokenizer itr = new StringTokenizer(value.toString()); |
| | 26 | while (itr.hasMoreTokens()) { |
| | 27 | word.set(itr.nextToken()); |
| | 28 | context.write(word, one); |
| | 29 | } |
| | 30 | } |
| | 31 | } |
| | 32 | |
| | 33 | public static class IntSumReducer |
| | 34 | extends Reducer<Text,IntWritable,Text,IntWritable> { |
| | 35 | private IntWritable result = new IntWritable(); |
| | 36 | |
| | 37 | public void reduce(Text key, Iterable<IntWritable> values, |
| | 38 | Context context |
| | 39 | ) throws IOException, InterruptedException { |
| | 40 | int sum = 0; |
| | 41 | for (IntWritable val : values) { |
| | 42 | sum += val.get(); |
| | 43 | } |
| | 44 | result.set(sum); |
| | 45 | context.write(key, result); |
| | 46 | } |
| | 47 | } |
| | 48 | |
| | 49 | public static void main(String[] args) throws Exception { |
| | 50 | Configuration conf = new Configuration(); |
| | 51 | String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); |
| | 52 | if (otherArgs.length != 2) { |
| | 53 | System.err.println("Usage: wordcount <in> <out>"); |
| | 54 | System.exit(2); |
| | 55 | } |
| | 56 | Job job = new Job(conf, "word count"); |
| | 57 | job.setJarByClass(WordCount.class); |
| | 58 | job.setMapperClass(TokenizerMapper.class); |
| | 59 | job.setCombinerClass(IntSumReducer.class); |
| | 60 | job.setReducerClass(IntSumReducer.class); |
| | 61 | job.setOutputKeyClass(Text.class); |
| | 62 | job.setOutputValueClass(IntWritable.class); |
| | 63 | FileInputFormat.addInputPath(job, new Path(otherArgs[0])); |
| | 64 | FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); |
| | 65 | System.exit(job.waitForCompletion(true) ? 0 : 1); |
| | 66 | } |
| | 67 | } |