23 lines
607 B
Python
23 lines
607 B
Python
|
from ...language import BaseDefaults, Language
|
||
|
|
from .lex_attrs import LEX_ATTRS
|
||
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
|
||
|
|
from .stop_words import STOP_WORDS
|
||
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
|
|
|
||
|
|
|
||
|
|
class SlovenianDefaults(BaseDefaults):
|
||
|
|
stop_words = STOP_WORDS
|
||
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||
|
|
prefixes = TOKENIZER_PREFIXES
|
||
|
|
infixes = TOKENIZER_INFIXES
|
||
|
|
suffixes = TOKENIZER_SUFFIXES
|
||
|
|
lex_attr_getters = LEX_ATTRS
|
||
|
|
|
||
|
|
|
||
|
|
class Slovenian(Language):
|
||
|
|
lang = "sl"
|
||
|
|
Defaults = SlovenianDefaults
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["Slovenian"]
|