import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; @HadoopMapper(inputKey = LongWritable.class, inputValue = Text.class, outputKey = Text.class, outputValue = IntWritable.class) public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> { private final static IntWritable one = new IntWritable(1); private Text word = new Text(); @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); StringTokenizer tokenizer = new StringTokenizer(line); while (tokenizer.hasMoreTokens()) { word.set(tokenizer.nextToken()); context.write(word, one); } } } @HadoopReducer(inputKey = Text.class, inputValue = IntWritable.class, outputKey = Text.class, outputValue = IntWritable.class) public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> { @Override public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable value : values) { sum += value.get(); } context.write(key, new IntWritable(sum)); } } public class WordCount implements Tool { private Configuration conf; public static void main(String[] args) throws Exception { int res = ToolRunner.run(new Configuration(), new WordCount(), args); System.exit(res); } public int run(String[] args) throws Exception { Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(WordCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(TextOutputFormat.class); job.setReducerClass(WordCountReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); TextInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); return job.waitForCompletion(true) ? 0 : 1; } public void setConf(Configuration conf) { this.conf = conf; } public Configuration getConf() { return conf; } }