diff --git a/std_indic/cleaners.py b/std_indic/cleaners.py index f052530..f419e70 100644 --- a/std_indic/cleaners.py +++ b/std_indic/cleaners.py @@ -1,10 +1,11 @@ import re + def clean_text(text): text = text.lower() - #foction de replacement - text = re.sub(r"i'm","i am",text) - text = re.sub(r"she's","she is",text) - text = re.sub(r"can't","can not",text) - text = re.sub(r"[-()\"#/@;:<>{}-=~|.?,]","",text) + # foction de replacement + text = re.sub(r"i'm", "i am", text) + text = re.sub(r"she's", "she is", text) + text = re.sub(r"can't", "can not", text) + text = re.sub(r"[-()\"#/@;:<>{}-=~|.?,]", "", text) return text