spaCy/spacy/lang/nl/__init__.py

51 lines
1.5 KiB
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
2017-05-08 13:51:39 +00:00
from __future__ import unicode_literals
2017-05-08 13:51:39 +00:00
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
2017-11-05 12:48:07 +00:00
from .tag_map import TAG_MAP
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
from .lemmatizer import LOOKUP, LEMMA_EXC, LEMMA_INDEX, RULES
from .lemmatizer.lemmatizer import DutchLemmatizer
2017-05-08 13:51:39 +00:00
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 ...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)
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
2017-11-05 12:48:07 +00:00
tag_map = TAG_MAP
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
@classmethod
def create_lemmatizer(cls, nlp=None):
rules = RULES
lemma_index = LEMMA_INDEX
lemma_exc = LEMMA_EXC
lemma_lookup = LOOKUP
return DutchLemmatizer(index=lemma_index,
exceptions=lemma_exc,
lookup=lemma_lookup,
rules=rules)
class Dutch(Language):
lang = 'nl'
Defaults = DutchDefaults
2017-05-03 09:01:42 +00:00
__all__ = ['Dutch']