package test.invertedIndex

import java.util.StringTokenizer;

// inverted Import type for input and output keys and values.

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;

import scala.collection.JavaConversions._

class invertedMapper() extends MapReduceBase
        with Mapper[Text, Text, Text, Text] {

    private val word = new Text();

    def map(key: Text,
            value: Text,
            output: OutputCollector[Text, Text],
            reporter: Reporter)
     {

        val wordList = new StringTokenizer(value.toString());

        wordList.foreach( w => {
            word.set(w.toString().replaceAll("[\\W]", ""));
            output.collect(word, key);
            })

    }
}