
1.2.0:

   * Implemented "filters" that allow tokenization to skip common word
     forms such as URLs, WikiWords, email addresses etc.
   * Now ships with enchant-1.3.0, meaning:
        * PWLs can return a useful list of suggestions rather than
          the empty list
        * Hunspell replaces MySpell as the default Windows backend
   * Tokenization doesnt split words at non-alpha characters by default
   * GtkSpellCheckerDialog contributed by Fredrik Corneliusson
   * Removed deprecated functionality:
   		* Dict.add_to_personal
   		* All registry handling functionality from enchant.utils
   		* enchant.utils.SpellChecker (use enchant.checker.SpellChecker)
   * Removed PyPWL, as native enchant PWLs can now suggest corrections

1.1.5:

   * Fix hang in included MySpell (Windows distribution)
   * Workaround for some MySpell/unicode problems
   * Update to latest setuptools ez_setup.py

1.1.4:

   * No longer need to use the registry under Windows
   * Moved to setuptools for managing distribution
   * Implemented unittest TestCases, works with `python setup.py test`
   * Plugins on Windows moved to "enchant" subdirectory
   * SpellChecker now coerces to/from unicode automatically
   * Use python default encoding rather than UTF-8 where appropriate
   * Various documentation cleanups
   * bug fixes:
        * (1230151): count of live instances done by normalized key
        * Accept unicode strings as broker orderings


1.1.3:

   * support for Python 2.2
   * use 'locale' module to look up default language if none specified
   * more and better regression tests
   * mark deprecated interfaces with warnings
   * removed <data> parameter to Dict constructor, with lots of
     reshuffling behind the scenes
   * add DictNotFoundError as a subclass of Error
   * Remove de_AT from languages in the Windows version, it was
     causing errors
   * bug fixes:
        * memory leak in DictWithPWL._free()
        * incorrect cache handling for PWLs


