класс Bundler::SimilarityDetector

# File lib/bundler/similarity_detector.rb, line 8
def initialize(corpus)
  @corpus = corpus
end

# File lib/bundler/similarity_detector.rb, line 20
def similar_word_list(word, limit = 3)
  words = similar_words(word, limit)
  if words.length == 1
    words[0]
  elsif words.length > 1
    [words[0..-2].join(", "), words[-1]].join(" or ")
  end
end

# File lib/bundler/similarity_detector.rb, line 13
def similar_words(word, limit = 3)
  words_by_similarity = @corpus.map {|w| SimilarityScore.new(w, levenshtein_distance(word, w)) }
  words_by_similarity.select {|s| s.distance <= limit }.sort_by(&:distance).map(&:string)
end

# File lib/bundler/similarity_detector.rb, line 32
def levenshtein_distance(this, that, ins = 2, del = 2, sub = 1)
  # ins, del, sub are weighted costs
  return nil if this.nil?
  return nil if that.nil?
  dm = [] # distance matrix

  # Initialize first row values
  dm[0] = (0..this.length).collect {|i| i * ins }
  fill = [0] * (this.length - 1)

  # Initialize first column values
  (1..that.length).each do |i|
    dm[i] = [i * del, fill.flatten]
  end

  # populate matrix
  (1..that.length).each do |i|
    (1..this.length).each do |j|
      # critical comparison
      dm[i][j] = [
        dm[i - 1][j - 1] + (this[j - 1] == that[i - 1] ? 0 : sub),
        dm[i][j - 1] + ins,
        dm[i - 1][j] + del
      ].min
    end
  end

  # The last value in matrix is the Levenshtein distance between the strings
  dm[that.length][this.length]
end