self.train!

in lib/linguist/classifier.rb [19:42]

• 20 lines of code
• 10 McCabe index (conditional complexity)

    def self.train!(db, language, data)
      tokens = Tokenizer.tokenize(data)

      db['tokens_total'] ||= 0
      db['languages_total'] ||= 0
      db['tokens'] ||= {}
      db['language_tokens'] ||= {}
      db['languages'] ||= {}

      tokens.each do |token|
        db['tokens'][language] ||= {}
        db['tokens'][language][token] ||= 0
        db['tokens'][language][token] += 1
        db['language_tokens'][language] ||= 0
        db['language_tokens'][language] += 1
        db['tokens_total'] += 1
      end
      db['languages'][language] ||= 0
      db['languages'][language] += 1
      db['languages_total'] += 1

      nil
    end