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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 
import java.io.IOException;
 
public class WordCount {
 
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
 
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] words = value.toString().split("\\s+");
            for (String w : words) {
                word.set(w);
                context.write(word, one);
            }
        }
    }
 
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
 
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
 
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
 
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
 
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}
public static class CharacterMapper extends Mapper<Object, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text character = new Text();
 
    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        for (int i = 0; i < value.toString().length(); i++) {
            character.set(String.valueOf(value.charAt(i)));
            context.write(character, one);
        }
    }
}

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