2019-10-18 12:27:38 +03:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
2019-11-15 18:16:47 +03:00
|
|
|
from .punctuation import TOKENIZER_INFIXES
|
2019-10-14 13:27:50 +03:00
|
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
from .tag_map import TAG_MAP
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
from ...language import Language
|
2020-05-19 16:59:14 +03:00
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
2019-10-14 13:27:50 +03:00
|
|
|
|
|
|
|
|
|
|
|
class LuxembourgishDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
2019-10-18 12:27:38 +03:00
|
|
|
lex_attr_getters[LANG] = lambda text: "lb"
|
2019-10-14 13:27:50 +03:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
|
|
stop_words = STOP_WORDS
|
2019-10-18 12:27:38 +03:00
|
|
|
tag_map = TAG_MAP
|
2019-11-15 18:16:47 +03:00
|
|
|
infixes = TOKENIZER_INFIXES
|
2019-10-18 12:27:38 +03:00
|
|
|
|
2019-10-14 13:27:50 +03:00
|
|
|
|
|
|
|
class Luxembourgish(Language):
|
2019-10-18 12:27:38 +03:00
|
|
|
lang = "lb"
|
2019-10-14 13:27:50 +03:00
|
|
|
Defaults = LuxembourgishDefaults
|
|
|
|
|
|
|
|
|
2019-10-18 12:27:38 +03:00
|
|
|
__all__ = ["Luxembourgish"]
|