// This program counts the number of unique words in a file
// and prints out information about how long it took to run
import java.io.*;
import java.util.*;

public class UniqueWords {
   public static void main(String[] args) throws FileNotFoundException {
      System.out.println("Reading file...");
      Scanner input = new Scanner(new File("mobydick.txt"));
      
      long start = System.currentTimeMillis();
      
      int uniqueWords = countUnique(input);
      
      long end = System.currentTimeMillis();
      long elapsed = end - start;
      
      System.out.println("The file has " + uniqueWords + " unique words.");
      System.out.println("Took " + elapsed + " ms.");
   }
   
   // post: returns the number of unique words that appear in the 
   // given Scanner's data
   public static int countUnique(Scanner input) {
      /* 
      // Code using a list:
      List<String> list = new ArrayList<>();
      while (input.hasNext()) {
         String word = input.next();
         if (!list.contains(word) {
            list.add(word);
         }
      }
      return list.size();
      */
      
      // Improved code using a set!
      Set<String> set = new HashSet<>();
      while (input.hasNext()) {
         String word = input.next();
         // don't need to check contains here, the set
         // ignores duplicates for us
         set.add(word);
      }
      return set.size();
   }
}