Code Tests: Words Sequencer (sequencer.rb w/ sample output text files)

first_10_sequences.txt

aaas
aarh
arhu
rhus
aaro
abab
bacu
balo
bbas
bbey

first_10_words.txt

AAAS
Aarhus
Aarhus
Aarhus
Aaron
Ababa
abacus
abalone
abbas
abbey

sequencer.rb

class Sequencer

  def initialize(data)
    parse_data(data)
  end

  # build the sequence hash and save the output
  def parse_data(data)
    sequence_hash = build_sequence_hash(data)
    save_file('sequences.txt', sequence_hash.keys.join("\n"))
    save_file('words.txt', sequence_hash.values.join("\n"))
  end

  # Iterate dictionary data and create 
  # a sequence => word hash
  def build_sequence_hash(data)
    data.inject({}) do |repo, word|
      scan_for_sequences(repo, word)
    end.reject!{|sequence, word| word.count > 1 }
  end

  # Scan individual words for potential sequences
  # and assign words to their corresponding sequence
  def scan_for_sequences(repo, word)
    word.scan(/(?=([A-Za-z]{4}))/).flatten.each do |seq|
      set_sequence_key(repo, seq.downcase, word)
    end
    repo
  end

  # Verify if sequence hash key exists.
  # If the key does not exists then create an array with 
  # the necessary word value else append the word value to the
  # existing word array
  def set_sequence_key(repo, key, value)
    repo.has_key?(key) ? repo[key] << value : repo[key] = [value]
  end

  # Split hash and save the results to their
  # respective destinations('sequences.txt', 'words.txt')
  def save_file(file_name, contents)
    file_path = File.join(__dir__, file_name)
    File.open(file_path, 'w+') { |f| f.write(contents) }
  end

end

dictionary_file = File.join(__dir__, 'dictionary.txt')
dictionary = IO.read(dictionary_file).split
Sequencer.new(dictionary)