Codecademy export

script.py

def censor_text(text, phrases, limit=0, near=False, letters="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'"):

  # Words and word positions
  words = []
  word_positions = []
  letter_inds = [i for i in range(len(text)) if text[i] in letters]
  noletter_inds = [i for i in range(len(text)) if not i in letter_inds]
  point = -1
  while [i for i in letter_inds if i > point]:
    first_letter = [i for i in letter_inds if i > point][0]
    word_positions.append(first_letter)
    if [i for i in noletter_inds if i > first_letter]:
      first_noletter = [i for i in noletter_inds if i > first_letter][0]
      words.append(text[first_letter:first_noletter].lower())
      point = first_noletter
    else:
      words.append(text[first_letter:].lower())
      point = len(text)
      
  # Censor words 
  censor_words = []
  phrases_lists = [phrase.split() for phrase in phrases]
  check = 0
  for num_position in range(len(words)):
    for phrase_list in phrases_lists:
      if num_position + len(phrase_list) <= len(words):
        if [words[i] for i in range(num_position, num_position + len(phrase_list))] == phrase_list:
          if check >= limit:          
            censor_words += range(num_position, num_position + len(phrase_list))
          check +=1
          break
  if near == True:
    near_censor_words = []
    for position in censor_words:
        if position > 0 and not (position - 1) in near_censor_words:
          near_censor_words.append(position - 1)
        if position < len(words) - 1 and not (position + 1) in near_censor_words:
          near_censor_words.append(position + 1)
    censor_words += near_censor_words

  # Censor full text
  censor_text = text
  for num_position in censor_words:
    length = len(words[num_position])
    first_letter = word_positions[num_position]
    first_noletter = word_positions[num_position] + length
    censor_text = censor_text[:first_letter]+"X"*length+censor_text[first_noletter:]
  
  return censor_text

email_one = open("email_one.txt", "r").read()
email_two = open("email_two.txt", "r").read()
email_three = open("email_three.txt", "r").read()
email_four = open("email_four.txt", "r").read()

proprietary_terms = ["she", "personality matrix", "sense of self", "self-preservation", "learning algorithm", "learning algorithms", "her", "herself"]
negative_words = ["concerned", "behind", "danger", "dangerous", "alarming", "alarmed", "out of control", "help", "unhappy", "bad", "upset", "awful", "broken", "damage", "damaging", "dismal", "distressed", "distressing", "concerning", "horrible", "horribly", "questionable"]

email_one_censored = censor_text(email_one, ["learning algorithms"])
email_two_censored = censor_text(email_two, proprietary_terms)
email_three_censored = censor_text(censor_text(email_three, proprietary_terms), negative_words, 2)
email_four_censored = censor_text(email_four, negative_words + proprietary_terms, near=True)

# print(email_one_censored)
# print(email_two_censored)
# print(email_three_censored)
# print(email_four_censored)