spaCy/spacy/lang/nl/__init__.py

41 lines
1.2 KiB
Python
Raw Normal View History

2017-05-08 13:51:39 +00:00
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .punctuation import TOKENIZER_SUFFIXES
from .lemmatizer import DutchLemmatizer
2017-05-08 20:29:04 +00:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-08 20:29:04 +00:00
from ...language import Language
from ...lookups import Lookups
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2017-05-08 13:51:39 +00:00
class DutchDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
2019-04-09 09:40:19 +00:00
lex_attr_getters[LANG] = lambda text: "nl"
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
prefixes = TOKENIZER_PREFIXES
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
@classmethod
def create_lemmatizer(cls, nlp=None, lookups=None):
if lookups is None:
lookups = Lookups()
return DutchLemmatizer(lookups)
class Dutch(Language):
2019-04-09 09:40:19 +00:00
lang = "nl"
Defaults = DutchDefaults
2017-05-03 09:01:42 +00:00
2019-04-09 09:40:19 +00:00
__all__ = ["Dutch"]