gistfile1.java

package textstat;

import static java.util.Comparator.comparingInt;
import static java.util.stream.Collectors.toList;

import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
import java.util.Map.Entry;
import java.util.function.ToIntFunction;

public class TextStat {
  private final HashMap<String, Integer> histogram = new HashMap<>();
  
  public void add(String word) {
    histogram.merge(word, 1, (a, b) -> (a == null? 0: a) + b);
  }
  
  public int totalWords() {
    return histogram.values().stream().mapToInt(Integer::intValue).sum();
  }

  public int uniqueWords() {
    return histogram.size();
  }

  public List<String> mostUsed() {
    return mostUsed(1);
  }
  
  public List<String> mostUsed(int num) {
    Comparator<Entry<String, Integer>> cmp = comparingInt(Entry::getValue);
    return histogram.entrySet().stream().sorted(cmp.reversed()).map(Entry::getKey).limit(num).collect(toList());
  }
  
  public int averageWordLength() {
    ToIntFunction<Entry<String, Integer>> weight = e -> e.getKey().length() * e.getValue();
    return (int)histogram.entrySet().stream().mapToInt(weight).average().orElseThrow(ArithmeticException::new);
  }
}