mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
dda86118bd
* Update Ukrainian lemmatizer with new lookups * Add missing import Co-authored-by: Ines Montani <ines@ines.io>
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
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
|
|
from .lemmatizer import UkrainianLemmatizer
|
|
|
|
|
|
class UkrainianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "uk"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
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 UkrainianLemmatizer(lookups)
|
|
|
|
|
|
class Ukrainian(Language):
|
|
lang = "uk"
|
|
Defaults = UkrainianDefaults
|
|
|
|
|
|
__all__ = ["Ukrainian"]
|