INNER CODE UNIT · Python

language_character_counts

dedsec1121fk/DedSec · Scripts/DedSec Market.py:384

def language_character_counts(text):
    greek = 0
    latin = 0
    for char in str(text):
        code = ord(char)
        if 0x0370 <= code <= 0x03FF or 0x1F00 <= code <= 0x1FFF:
            greek += 1
        elif "A" <= char <= "Z" or "a" <= char <= "z":
            latin += 1
    return greek, latin


def normalize_language_label(text):
    value = strip_markdown(str(text or ""))
    value = html_lib.unescape(value).replace("\xa0", " ").strip().lower()
    value = remove_accents(value)
    value = re.sub(r"\s+", " ", value)
    return value.strip(" \t\r\n#>*_`[](){}.!?")

View source record →