utils.py 文件源码

def tokenize(text, lowercase=False, deacc=False, errors="strict", to_lower=False, lower=False):
    """
    Iteratively yield tokens as unicode strings, optionally also lowercasing them
    and removing accent marks.

    Input text may be either unicode or utf8-encoded byte string.

    The tokens on output are maximal contiguous sequences of alphabetic
    characters (no digits!).

    >>> list(tokenize('Nic nem?že let?t rychlostí vyšší, než 300 tisíc kilometr? za sekundu!', deacc = True))
    [u'Nic', u'nemuze', u'letet', u'rychlosti', u'vyssi', u'nez', u'tisic', u'kilometru', u'za', u'sekundu']

    """
    lowercase = lowercase or to_lower or lower
    text = to_unicode(text, errors=errors)
    if lowercase:
        text = text.lower()
    if deacc:
        text = deaccent(text)
    for match in PAT_ALPHABETIC.finditer(text):
        yield match.group()