mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
a9559e7435
* Handle Russian, Ukrainian and Bulgarian * Corrections * Correction * Correction to comment * Changes based on review * Correction * Reverted irrelevant change in punctuation.py * Remove unnecessary group * Reverted accidental change
30 lines
919 B
Python
30 lines
919 B
Python
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
|
|
from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
|
|
from ...language import Language, BaseDefaults
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class BulgarianDefaults(BaseDefaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "bg"
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
stop_words = STOP_WORDS
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
|
|
infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
|
|
|
|
|
|
class Bulgarian(Language):
|
|
lang = "bg"
|
|
Defaults = BulgarianDefaults
|
|
|
|
|
|
__all__ = ["Bulgarian"]
|