21 lines
483 B
Python
21 lines
483 B
Python
from ...language import BaseDefaults, Language
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_INFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
|
|
class TatarDefaults(BaseDefaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
infixes = TOKENIZER_INFIXES
|
|
lex_attr_getters = LEX_ATTRS
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Tatar(Language):
|
|
lang = "tt"
|
|
Defaults = TatarDefaults
|
|
|
|
|
|
__all__ = ["Tatar"]
|