import java.util.*;
import java.io.*;

// This class shows the efficieny of using a Set over a List in
// the case where we count unique words in a file. 
// We also practiced using Maps to store word counts for each
// unique word in the file and printed out the ones that exceed
// our cutoff.
public class WordCount {

   public static final int WORDS_CUTOFF = 300;

   public static void main(String[] args) throws FileNotFoundException {
      Scanner console = new Scanner(System.in);
      System.out.print("Enter file name: ");
      String fileName = console.nextLine();
   
      List<String> list = new ArrayList<String>();
      long start = System.currentTimeMillis();
      int uniqueWords = countUniqueWords(new Scanner(new File(fileName)), list);
      long end = System.currentTimeMillis();
      System.out.println("unique words: " + uniqueWords);
      System.out.println("List operations took " + (end - start) + "ms");
   
      // What set should we use?
   
      Set<String> set = new HashSet<String>();
      start = System.currentTimeMillis();
      uniqueWords = countUniqueWords(new Scanner(new File(fileName)), set);
      end = System.currentTimeMillis();
      System.out.println("unique words: " + uniqueWords);
      System.out.println("Set operations took " + (end - start) + "ms");
        
      printCounts(new Scanner(new File(fileName)));     
   }
    
   // Takes in a Scanner input and List<String> to store unique words and
   // returns the number of unique words in the given input file 
   public static int countUniqueWords(Scanner input, List<String> list) {
      while(input.hasNext()) {
         String token = input.next();
         if(!list.contains(token)) {
            list.add(token);
         }
      }
      return list.size();
   }
   
   // Takes in a Scanner input and Set<String> to store unique words and
   // returns the number of unique words in the given input file  
   public static int countUniqueWords(Scanner input, Set<String> set) {
      while(input.hasNext()) {
         String token = input.next();
         //if(!set.contains(token)) { not necessary!
         set.add(token);
         //}
      }
      return set.size();
   }
    
   
   // Takes in a Scanner input and creates a corresponding word count for
   // each unique word in the input. It prints out all of the words and their
   // respective word counts if they are higher than the WORDS_CUTOFF threshold 
   public static void printCounts(Scanner input) {
    
       // word => count
      Map<String, Integer> wordCount = new TreeMap<String, Integer>();
       
      while(input.hasNext()) {
         String token = input.next();
           
         if(!wordCount.containsKey(token)) {
            wordCount.put(token, 0);
         }
         /*
         int oldCount = wordCount.get(token);
         int newCount = oldCount + 1;
         wordCount.put(token, newCount);
         */  
         wordCount.put(token, wordCount.get(token) + 1);
      }
       
      for(String word : wordCount.keySet()) {
         int count = wordCount.get(word);
         if(count > WORDS_CUTOFF) {
            System.out.println(word + " -> " + count);
         }
      }
    
   }
    
    
    
    
}