2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2017-05-08 13:48:31 +00:00
|
|
|
from __future__ import unicode_literals
|
2017-01-31 22:27:29 +00:00
|
|
|
|
2017-05-08 13:48:31 +00:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
2017-05-08 20:29:04 +00:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2017-06-03 20:29:21 +00:00
|
|
|
from ..norm_exceptions import BASE_NORMS
|
2017-05-08 20:29:04 +00:00
|
|
|
from ...language import Language
|
2017-06-03 20:29:21 +00:00
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
from ...util import update_exc, add_lookups
|
2017-01-31 22:27:29 +00:00
|
|
|
|
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class FinnishDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'fi'
|
2017-06-03 20:29:21 +00:00
|
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
2017-05-20 17:02:27 +00:00
|
|
|
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
stop_words = set(STOP_WORDS)
|
2017-01-31 22:27:29 +00:00
|
|
|
|
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class Finnish(Language):
|
|
|
|
lang = 'fi'
|
|
|
|
Defaults = FinnishDefaults
|
2017-05-03 09:01:42 +00:00
|
|
|
|
|
|
|
|
2017-05-08 13:48:31 +00:00
|
|
|
__all__ = ['Finnish']
|