slugify-variants.py

"""Django 1.8.X"""
def slugify(value):
    """
    Converts to ASCII. Converts spaces to hyphens. Removes characters that
    aren't alphanumerics, underscores, or hyphens. Converts to lowercase.
    Also strips leading and trailing whitespace.
    """
    value = force_text(value)
    value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
    value = re.sub('[^\w\s-]', '', value).strip().lower()
    return mark_safe(re.sub('[-\s]+', '-', value))
slugify = allow_lazy(slugify, six.text_type, SafeText)



"""django-missing"""
@register.filter(is_safe=True)
@defaultfilters.stringfilter
def slugify2(value):
    """
    Normalizes string, converts to lowercase, removes non-alpha characters,
    and converts spaces to hyphens.

    It is similar to built-in :filter:`slugify` but it also handles special characters in variety of languages
    so that they are not simply removed but properly transliterated/downcoded.
    """

    try:
        value = unicodedata.normalize('NFC', value)
        value = downcode(value)
        value = unicodedata.normalize('NFD', value).encode('ascii', 'ignore')
        value = unicode(re.sub('[^\w\s-]', '', value).strip().lower())
        return safestring.mark_safe(re.sub('[-\s]+', '-', value))
    except:
        if settings.TEMPLATE_DEBUG:
            raise
        else:
            return u''

"""Unused, but existing solutions"""
# https://pypi.python.org/pypi/Unidecode
#>>> from unidecode import unidecode:
#>>> unidecode(u"\u5317\u4EB0")
#"Bei Jing "

"""Unused, popular pytils"""
def slugify(in_string):
    """
    Prepare string for slug (i.e. URL or file/dir name)
    @param in_string: input string
    @type in_string: C{basestring}
    @return: slug-string
    @rtype: C{str}
    @raise ValueError: if in_string is C{str}, but it isn't ascii
    """
    try:
        u_in_string = six.text_type(in_string).lower()
    except UnicodeDecodeError:
        raise ValueError("We expects when in_string is str type," + \
                         "it is an ascii, but now it isn't. Use unicode " + \
                         "in this case.")
    # convert & to "and"
    u_in_string = re.sub('\&amp\;|\&', ' and ', u_in_string)
    # replace spaces by hyphen
    u_in_string = re.sub('[-\s]+', '-', u_in_string)
    # remove symbols that not in alphabet
    u_in_string = u''.join([symb for symb in u_in_string if symb in ALPHABET])
    # translify it
    out_string = translify(u_in_string)
    # remove non-alpha
    return re.sub('[^\w\s-]', '', out_string).strip().lower()