Alphabetical sorts

[Leo Kislov]

On Oct 16, 2:39 pm, Tuomas <tuomas.vesteri... at pp.inet.fi> wrote:
> My application needs to handle different language sorts. Do you know a
> way to apply strxfrm dynamically i.e. without setting the locale?

Collation is almost always locale dependant. So you have to set locale.
One day I needed collation that worked on Windows and Linux. It's not
that polished and not that tested but it worked for me:

import locale, os, codecs

current_encoding = 'ascii'
current_locale = ''

def get_collate_encoding(s):
    '''Grab character encoding from locale name'''
    split_name = s.split('.')
    if len(split_name) != 2:
        return 'ascii'
    encoding = split_name[1]
    if os.name == "nt":
        encoding = 'cp' + encoding
    try:
        codecs.lookup(encoding)
        return encoding
    except LookupError:
        return 'ascii'

def setup_locale(locale_name):
    '''Switch to new collation locale or do nothing if locale
       is the same'''
    global current_locale, current_encoding
    if current_locale == locale_name:
        return
    current_encoding = get_collate_encoding(
        locale.setlocale(locale.LC_COLLATE, locale_name))
    current_locale = locale_name

def collate_key(s):
    '''Return collation weight of a string'''
    return locale.strxfrm(s.encode(current_encoding, 'ignore'))

def collate(lst, locale_name):
    '''Sort a list of unicode strings according to locale rules.
       Locale is specified as 2 letter code'''
    setup_locale(locale_name)
    return sorted(lst, key = collate_key)


words = u'c ch f'.split()
print ' '.join(collate(words, 'en'))
print ' '.join(collate(words, 'cz'))

Prints:

c ch f
c f ch