mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .tag_map import TAG_MAP
|
|
from .lemmatizer import RussianLemmatizer
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...util import update_exc, add_lookups
|
|
from ...language import Language
|
|
from ...lookups import Lookups
|
|
from ...attrs import LANG, NORM
|
|
|
|
|
|
class RussianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "ru"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
tag_map = TAG_MAP
|
|
|
|
@classmethod
|
|
def create_lemmatizer(cls, nlp=None, lookups=None):
|
|
if lookups is None:
|
|
lookups = Lookups()
|
|
return RussianLemmatizer(lookups)
|
|
|
|
|
|
class Russian(Language):
|
|
lang = "ru"
|
|
Defaults = RussianDefaults
|
|
|
|
|
|
__all__ = ["Russian"]
|