Sorting strings diacritics insensitive and case insensitive. Diacritics are combined characters such as ^,¨,`

diacritics-insentive-sorting.py

import unicodedata

def make_sortable(text):
    """Converts a string to a sortable string by lowercasing
    it and removing diacritics.
    """
    if isinstance(text, str):
        text = text.decode('utf-8')
    if not isinstance(text, unicode):
        return text

    text = text.lower()
    normalized = unicodedata.normalize('NFKD', text)
    text = u''.join([c for c in normalized if not unicodedata.combining(c)])
    text = text.encode('utf-8')
    return text


sorted(['fff', 'zzz', 'ööö', 'ZZZ', 'FFF'], key=make_sortable)
# --> ['fff', 'FFF', 'ööö', 'zzz', 'ZZZ']


sorted(['fff', 'zzz', 'ööö', 'ZZZ', 'FFF'])
# --> ['FFF', 'ZZZ', 'fff', 'zzz', 'ööö']

test_remove_sortable.py

# -*- coding: utf-8 -*-

# import make_sortable
from unittest2 import TestCase


class TestMakeSortable(TestCase):

    def test_accepts_strings(self):
        self.assertEquals('foo', make_sortable('foo'))

    def test_converts_unicodes_to_strings(self):
        self.assertEquals('foo', make_sortable(u'foo'))

    def test_returns_nonstrings_without_modifications(self):
        self.assertEquals(
            [None,
             5,
             True],

            [make_sortable(None),
             make_sortable(5),
             make_sortable(True)])

    def test_lowercases_everything(self):
        self.assertEquals('foo', make_sortable('FoO'))

    def test_removes_diacritics(self):
        self.assertEquals(
            ['francais',
             'hauser'],

            [make_sortable('français'),
             make_sortable('Häuser')])