gistfile1.java

import java.io.File;
import java.util.Scanner;
import com.google.common.collect.HashMultimap;

/** create in-memory mappings from words to the files that contain them */
public class Indexer {
  public static HashMultimap<String,String> buildIndex(String dirName) throws java.io.IOException {
    HashMultimap<String,String> map = HashMultimap.create();
    for (File f : new File(dirName).listFiles()) {
      String fname = f.getName();
      Scanner s = new Scanner(f).useDelimiter("[^\\p{L}&&[^\\p{M}]]");
      while (s.hasNext()) {
        map.put(s.next().toLowerCase(), fname);
      }
    }
    return map;
  }

  //for testing
  public static void main(String args[]) throws java.io.IOException {
    long start = new java.util.Date().getTime();
    HashMultimap<String,String> index = Indexer.buildIndex(args[0]);
    System.out.println(new java.util.Date().getTime() - start);
    System.out.println(index.get(args[1]));
  }
}