def normalize(self, name):
name = ascii_text(name)
name = category_replace(name, UNICODE_CATEGORIES)
if name.upper() == name:
name = name.replace(WS, '_')
name = name.lower()
else:
name = stringcase.snakecase(name)
return re.sub('_+', '_', name)
def clean_strict(text, boundary=WS):
"""Super-hardcore string scrubbing."""
# transliterate to ascii
text = ascii_text(text)
# replace punctuation and symbols
text = CHARACTERS_REMOVE_RE.sub('', text)
text = category_replace(text)
# pad out for company type replacements
text = ''.join((boundary, collapse_spaces(text), boundary))
return text
def clean_strict(text, boundary=WS):
"""Super-hardcore string scrubbing."""
# transliterate to ascii
text = ascii_text(text)
# replace punctuation and symbols
text = CHARACTERS_REMOVE_RE.sub('', text)
text = category_replace(text)
# pad out for company type replacements
text = ''.join((boundary, collapse_spaces(text), boundary))
return text
def normalize_strong(text):
"""Perform heavy normalisation of a given text.
The goal of this function is not to retain a readable version of the given
string, but rather to yield a normalised version suitable for comparisons
and machine analysis.
"""
text = latinize_text(string_value(text))
if text is None:
return
text = category_replace(text.lower())
return collapse_spaces(text)
def clean_strict(text: Optional[str], boundary: str = WS) -> Optional[str]:
"""Super-hardcore string scrubbing."""
# transliterate to ascii
text = ascii_text(text)
if not isinstance(text, str):
return None
# replace punctuation and symbols
text = CHARACTERS_REMOVE_RE.sub("", text)
text = category_replace(text)
text = collapse_spaces(text)
if text is None:
return None
# pad out for company type replacements
return "".join((boundary, text, boundary))
def normalize(text):
text = category_replace(text, replacements=UNICODE_CATEGORIES)
text = ascii_text(text)
if text is not None:
return text.lower()