minganci.rb

# https://ruby-china.org/topics/7555
# gem 'fast_trie', :require => "trie"
# encoding: utf-8
class SegTrie

  attr_accessor :trie

  def initialize
    self.trie = ::Trie.new
  end

  def all_words(str, offset = 0, words= [])
    words_a ||= []
    str ||= ''
    str.length.times do |i|
      self.word(str, i, words_a)
    end
    words_a
  end

  def word(str, offset = 0, words_a = [])
    len = 0
    while  offset + len < str.length
      status = self.trie.get(str[offset, (len + 1)])
      if status == 2
        len = len + 1
        words_a.push(str[offset, len])
      elsif status == 1
        len = len + 1
      elsif status == 3
        words_a.push(str[offset, len + 1])
        break
      else
        break
      end
    end
    words_a
  end

  def add_words(words)
    words.each_index do |i|
      self.add_word(words[i])
    end
  end

  def add_word(word)
    return false if word.blank?
    word.length.times do |i|
      next if i == 0
      self.trie.add(word[0, i], 1) if self.trie.get(word[0, i]).to_i < 1
    end
    status =self.trie.get(word).to_i
    if status == 1
      self.trie.add(word, 2)
    elsif !([2, 3].include?(status))
      self.trie.add(word, 3)
    end
  end

  def clear_words
    self.trie = ::Trie.new
  end

end