Unicode string normalization

string_normalization.py

def normalize(s):
    """ Expects a unicode string, not encoded byte string.
        Returns unicode string
    """
    out = ''.join( c for c in unicodedata.normalize("NFKD", s)
                    if not unicodedata.combining(c) )
    out = _regexAlpha.sub(' ', out)
    out = _regexSpace.sub(' ', out)
    out = out.strip().upper()
    return out