2021-02-10 18:12:33 +00:00
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
|
from .punctuation import TOKENIZER_INFIXES
|
|
|
|
|
from ...language import Language
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class SetswanaDefaults(Language.Defaults):
|
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
2021-02-11 19:20:46 +00:00
|
|
|
infixes = TOKENIZER_INFIXES
|
2021-02-10 18:12:33 +00:00
|
|
|
stop_words = STOP_WORDS
|
|
|
|
|
lex_attr_getters = LEX_ATTRS
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Setswana(Language):
|
|
|
|
|
lang = "tn"
|
|
|
|
|
Defaults = SetswanaDefaults
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
__all__ = ["Setswana"]
|
