Codecademy export

script.py

import re
# 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_two = open("email_two.txt", "r").read()
email_three = open("email_three.txt", "r").read()
email_four = open("email_four.txt", "r").read()

punctuation = [' ', '.',',','!','?',';',':','-','[',']','{','}','(',')',"'",'"']

def censor_one(email, word):
  censored_text = ""
  for i in range(len(word)):
    if (word[i] in punctuation):
      censored_text = censored_text + word[i]
    else:
      censored_text = censored_text + "X"
  return re.sub(r'\b' + word + r'\b', censored_text, email)

#print(censor_one(email_one, "learning algorithms"))

def cencor_word_list(lists_censor, email):
  for word in lists_censor:
    censored_text = ""
    for i in range(len(word)):
      if(word[i] in punctuation):
        censored_text = censored_text + word[i]
      else:
        censored_text = censored_text + "X"
    email = re.sub(r'\b' + word + r'\b', censored_text, email)
  return email
  
proprietary_terms = ["she", "personality matrix", "sense of self", "self-preservation", "learning algorithm", "her", "herself"]

#print(cencor_word_list(proprietary_terms, email_two))

def cencor_negative_words(negative_words, proprietary_terms, email):
  for word in negative_words:
    word_list = re.findall(r'\b' + word + r'\b', email)
    if (len(word_list) > 2):
      censored_text = ""
      for i in range(len(word)):
        if(word[i] in punctuation):
          censored_text = censored_text + word[i]
        else:
          censored_text = censored_text + 'X'
      email = re.sub(r'\b' + word + r'\b', censored_text, email)
  email = cencor_word_list(proprietary_terms, email)
  return email

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(cencor_negative_words(negative_words, proprietary_terms, email_three))

def cencor_any_words(proprietary_terms, negative_words, email):
  lists = proprietary_terms + negative_words
  for word in lists:
    censored_text = ""
    for i in range(len(word)):
      if word[i] in punctuation:
        censored_text = censored_text + word[i]
      else:
        censored_text = censored_text + "X"
    email = re.sub(r'\b' + word + r'\b', censored_text, email)
  email_split = email.split('\n')
  new_email_split = []
  for item in email_split:
    if item != '':
      item_split = item.split()
      new_item_split = [word for word in item_split]
      for i in range(len(item_split)):
        if not 'X' in item_split[i]:
          continue
        if(i > 0):
          word_before = item_split[i-1]
          if not 'X' in word_before:
            censored_text = ""
            for letter in word_before:
              if letter in punctuation:
                censored_text = censored_text + letter
              else:
                censored_text = censored_text + 'X'
            new_item_split[i - 1] = censored_text
        if (i < len(item_split) - 2):
          word_after = item_split[i + 1]
          if not 'X' in word_after:
            censored_text = ""
            for letter in word_after:
              if letter in punctuation:
                censored_text = censored_text + letter
              else:
                censored_text = censored_text + 'X'
            new_item_split[i + 1] = censored_text
      new_item = ' '.join(new_item_split)
      new_email_split.append(new_item)
    else:
      new_email_split.append(' ')
  new_email = '\n'.join(new_email_split)
  return new_email
#print(cencor_any_words(proprietary_terms, negative_words, email_two))