import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.*; import org.apache.hadoop.mapreduce.*; import org.apache.hadoop.util.*; @KeywordAnnotation(keyword = "big data") public class WordCount { public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { KeywordAnnotation annotation = (KeywordAnnotation) context.getInputAnnotation("KeywordAnnotation"); String line = value.toString(); String[] words = line.split(" "); for (String word : words) { if (word.equals(annotation.getKeyword())) { this.word.set(word); context.write(this.word, one); } } } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "wordcount"); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.waitForCompletion(true); } }