spaCy/spacy/lang/ro/__init__.py
ines c6fea3e5f6 Add Romanian and Croatian skeletons (experimental)
Add language data templates to make it easier for others to contribute to the language support
2017-11-01 23:04:28 +01:00

29 lines
806 B
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
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 RomanianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'ro'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
class Romanian(Language):
lang = 'ro'
Defaults = RomanianDefaults
__all__ = ['Romanian']