communicaite / services /bad_words.py
seduerr's picture
init
190f036
import re
def identify_bad_words(text):
bad_words = []
with open('./src/bad_words.txt', 'r') as filehandle:
bad_words = [current_place.rstrip()
for current_place in filehandle.readlines()]
pattern = re.compile('[A-Z]*[a-z]+')
cleaned_text = pattern.findall(text)
long_word_set = set(bad_words)
return (set(cleaned_text) & long_word_set)