mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +03:00
e1a935d71c
* Serbian stopwords added. (cyrillic alphabet) * spaCy Contribution agreement included. * Test initialize updated
29 lines
738 B
Python
29 lines
738 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class SerbianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "rs"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Serbian(Language):
|
|
lang = "rs"
|
|
Defaults = SerbianDefaults
|
|
|
|
|
|
__all__ = ["Serbian"]
|