add re

utils/data_utils.py

@@ -1,8 +1,11 @@
+__copyright__ = "Copyright (C) 2023 Ali Mustapha"
+__license__ = "GPL-3.0-or-later"
+
 from unidecode import unidecode
 import pandas as od
 import regex
 import unicodedata
-
+import re
 def is_most_common_char(s):
     max_count = len(s) * 0.90  # calculate the maximum count of a single character
     char_count = {}  # create an empty dictionary to store character counts