Codecademy export

script.py

# 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()

proprietary_terms = ["she", "personality matrix", "sense of self", "self-preservation", "learning algorithms", "herself", "her", "She", "Her"] 

negative_words = ["concerned", "behind", "dangerous", "danger", "alarming", "alarmed", "out of control", "help", "unhappy", "bad", "upset", "awful", "broken", "damage", "damaging", "dismal", "distressing", "distressed", "concerning", "horrible", "horribly", "questionable"] #distressed was twice, change it to distressing. 

def censor_all_instances (phrase, email):
  if len(phrase) < 2:
    return email # we are not censoring 1 or null characters
  censor_phrase = ""
  email_censored = email
  for i in phrase:
    censor_phrase += "*" # will be the same lenght as phrase
    email_censored = email.replace(phrase, censor_phrase)
  return email_censored
    
def censor_all_words_or_phrases (email):
  """
  While performing tests I noticed that the email says "learning algorithms" instead of "learning algorithm", 
  """
  email_censored = email
  for phrase in proprietary_terms:
    email_censored = censor_all_instances (phrase, email_censored)
  return email_censored

def censor_negative_language (email):
  """
  I decided to censor all negative words in the email if more than 2 are detected and not follow the hint allowing the first negative word to appear and censor all the rest as the task says: "...censor any occurance of a word from the “negative words” list after any “negative” word has occurred twice..."
  """
  censor = []
  email_censored = email
  for word in negative_words:
    if email.find(word) >= 0: # if -1 the word is not found
      censor.append(word)
  if len(censor) > 2: #detected more than 2 negative words
    for word in censor:
      email_censored = censor_all_instances (word, email_censored)
  email_censored = censor_all_words_or_phrases(email_censored)
  return email_censored

def censor_all (email):
  email_censored = email
  censor = negative_words + proprietary_terms
  for word in censor:
    index = 0
    start = 0
    while index < len(email):
      index = email.find(word, index)
      if index == -1: # word not found
        break
      else: # we found one instance of word
        # Looking for all words BEFORE to censor.
        # We will stop if we found a "," or a "."
        before = index - 1
        before = email.rfind(".", start,before)
        if before == -1: # no point before word
          before = email.rfind(",", start, index-1) 
          if before == -1: # no comma before word
            censor_phrase = email[start:index]
            if censor_phrase != " ":
              email_censored = censor_all_instances (censor_phrase, email_censored)
          else: # found a comma
            censor_phrase = email[before+1:index]
            if censor_phrase != " ":
              email_censored = censor_all_instances (censor_phrase, email_censored)
        else: # found a point
          censor_phrase = email[before+1:index]
          if censor_phrase != " ":
            email_censored = censor_all_instances (censor_phrase, email_censored)
        # Looking for all words AFTER to censor.
        # We will stop if we found a "," or a "."
        index += len(word) #looking for the next instance
        start = index
        after = email.find(".", start,len(email))
        if after == -1: # no point after word
          after = email.find(",", start, len(email)) 
          if after == -1: # no comma after word
            censor_phrase = email[start:index]
            email_censored = censor_all_instances (censor_phrase, email_censored)
          else: # found a comma
            censor_phrase = email_censored[start:after]
            email_censored = censor_all_instances (censor_phrase, email_censored)
        else: # found a point
          censor_phrase = email[start:after]
          email_censored = censor_all_instances (censor_phrase, email_censored)
        
    email_censored = censor_all_instances (word, email_censored) # we need to censor the word as well
            
  return email_censored

print (censor_all_instances ("learning algorithms", email_one))
print ("\n")
print (censor_all_words_or_phrases (email_two))
print ("\n")
print (censor_negative_language (email_three))
print ("\n")
print (censor_all(email_four))