def normalize_emb_code(emb_code: str):
emb_code = (emb_code.strip().lower().replace(' ', '').replace('-',
'').replace(
'.', ''))
emb_code = strip_accents_ascii(emb_code)
if emb_code.endswith('ce'):
emb_code = emb_code[:-2] + 'ec'
return emb_code
def normalize_emb_code(emb_code: str):
emb_code = (
emb_code.strip().lower().replace(" ", "").replace("-", "").replace(".", "")
)
emb_code = strip_accents_ascii(emb_code)
if emb_code.endswith("ce"):
emb_code = emb_code[:-2] + "ec"
return emb_code
def preprocess_product_name(text: str, lower: bool, strip_accent: bool,
remove_punct: bool, remove_digit: bool) -> str:
if strip_accent:
text = strip_accents_ascii(text)
if lower:
text = text.lower()
if remove_punct:
text = PUNCTUATION_REGEX.sub(" ", text)
if remove_digit:
text = DIGIT_REGEX.sub(" ", text)
return MULTIPLE_SPACES_REGEX.sub(" ", text)
def get_tag(brand: str) -> str:
brand = strip_accents_ascii(brand)
return brand.lower().replace(" & ", "-").replace(" ",
"-").replace("'", "-")
def normalize_text(text: str) -> str:
text = text.lower()
text = strip_accents_ascii(text)
return text.replace("'", " ").replace("-", " ")