// Hunter Schafer, CSE 143
// This program counts the number of unique words in a large file.
// This program calculates 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 + " words.");
        System.out.println("Took " + elapsed + " ms.");
    }

    // pre: input is not null
    // post: returns the number of unique tokens in input
    public static int countUnique(Scanner input) {
        Set<String> words = new HashSet<String>();

        while (input.hasNext()) {
            String word = input.next();
            words.add(word);
        }

        // Wanted to remove all odd length words
        //
        /* Doesn't work

        for (String word : words) {
            if (word.length() % 2 == 1) {
                words.remove(word);
            }
        }
        */

        // Iterator Interface
        //      hasNext()
        //      next()
        //      remove

        // Iterable Interface
        //      iterator()

        Iterator<String> itr = words.iterator();
        while (itr.hasNext()) {
            String word = itr.next();

            if (word.length() % 2 == 1) {
                itr.remove();
            }
        }

        return words.size();
    }
}