Code source de mlstatpy.nlp.normalize

# -*- coding: utf-8 -*-
"""
Text normalization


:githublink:`%|py|6`
"""
import unicodedata


def remove_diacritics(input_str):
    """
    remove diacritics

    :param      input_str:       string to clean
    :return:                     cleaned string

    Example::

        enguérand --> enguerand

    .. versionadded:: 1.0


    :githublink:`%|py|21`
    """
    nkfd_form = unicodedata.normalize('NFKD', input_str)
    only_ascii = nkfd_form.encode('ASCII', 'ignore')
    return only_ascii.decode("utf8")