Codecademy export

script.py

import string
# These are the emails you will be censoring. The open() function is opening the text file that the emails are contained in and the .read() method is allowing us to save their contexts to the following variables:email_one = open("email_one.txt", "r").read()
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()


def censor_email(input_text, words_to_censor, before_and_after=False):
  censor_list = []
  censor_char = "********************"
  word_list = []
  split_input_text = split_the_text(input_text)

  for censor_word in words_to_censor:
    find_words = find_the_word_or_index(input_text, censor_word)
    word_list += find_words      

    for word, index in word_list:
      if before_and_after:
        split_input_text[index - 1] = censor_char[:len(split_input_text[index - 1])]
        split_input_text[index] = censor_char[:len(split_input_text[index])]
        split_input_text[index + 1] = censor_char[:len(split_input_text[index + 1])]
      else:
        split_input_text[index] = censor_char[:len(word)]

  output_text = ""
  for word in split_input_text:
    output_text += word + " "
  
  return output_text


def split_the_text(input_text):
  split_input_text = input_text.split()
  text_split = input_text.split(" ")
  newline_index_list = []

  #find \n in text
  newline_list = []
  for i in range(0, len(text_split)):
    if "\n" in text_split[i]:
      for x in range(0, text_split[i].count("\n")):
        newline_list.append(text_split[i].replace("\n", " ").split()[0])
  
  for item in newline_list:
    try:
      index = split_input_text.index(item)
      split_input_text.insert(index + 1, "\n")
    except:
      pass

  return split_input_text


def find_the_word_or_index(input_text, word_or_index):
  get_text = split_the_text(input_text)
  result_list = []
  index_value = 0
  punctuation_list = ["'", ",", ".", "!", "?", "%", "/", "(", ")"]
  punch_flag = False
  unedited_word = word_or_index

  if " " not in word_or_index:
    for punch in punctuation_list:
      if punch in str(word_or_index):
        word_or_index = word_or_index.translate(None, string.punctuation)
        punch_flag = True
  
  try:    
    if str(unedited_word).isdigit():
      return get_text[word_or_index]
    elif str(unedited_word).isalpha() or (punch_flag):
      counter = 0

      for i in range(0, len(get_text)):
        if get_text[i].translate(None, string.punctuation).lower() == word_or_index.lower():
            if punch_flag == False:
              result_list.append((word_or_index, counter))
            else:
              result_list.append((unedited_word, counter))

        counter += 1

      return result_list  

    #deals with multi censor word e.g sense of self.
    elif " " in word_or_index:
      split_word = word_or_index.split()

      for i in range(0, len(get_text)):
        if split_word[0].lower() == get_text[i].lower():
          if get_text[i + 1] == split_word[1]:
          
            counter = 0
            for censor_word in split_word:           
              if censor_word == get_text[i + counter]:
                result_list.append((censor_word, i + counter))
              
              counter += 1
          
      return result_list        
         
  except:
    return result_list

  return result_list


proprietary_terms = ["she", "personality matrix", "sense of self", "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", "distressed", "concerning", "horrible", "horribly", "questionable"]

#print(censor_email(email_one, ["learning algorithms"]))
#print(censor_email(email_two, proprietary_terms))
#print(censor_email(email_three, negative_words))
#print(censor_email(email_four, proprietary_terms + negative_words, True))