spaCy/spacy/lang/ru/__init__.py
Adriane Boyd 2f981d5af1 Remove corpus-specific tag maps
Remove corpus-specific tag maps from the language data for languages
without custom tokenizers. For languages with custom word segmenters
that also provide tags (Japanese and Korean), the tag maps for the
custom tokenizers are kept as the default.

The default tag maps for languages without custom tokenizers are now the
default tag map from `lang/tag_map/py`, UPOS -> UPOS.
2020-07-15 15:58:29 +02:00

33 lines
911 B
Python

from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from .lemmatizer import RussianLemmatizer
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...util import update_exc
from ...language import Language
from ...lookups import Lookups
from ...attrs import LANG
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"
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
@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"]