spaCy/spacy/lang/ro/__init__.py
2020-07-25 12:55:18 +02:00

28 lines
793 B
Python

from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
from .lex_attrs import LEX_ATTRS
from ...language import Language
# Lemma data note:
# Original pairs downloaded from http://www.lexiconista.com/datasets/lemmatization/
# Replaced characters using cedillas with the correct ones (ș and ț)
class RomanianDefaults(Language.Defaults):
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
prefixes = TOKENIZER_PREFIXES
suffixes = TOKENIZER_SUFFIXES
infixes = TOKENIZER_INFIXES
lex_attr_getters = LEX_ATTRS
stop_words = STOP_WORDS
class Romanian(Language):
lang = "ro"
Defaults = RomanianDefaults
__all__ = ["Romanian"]