spaCy/spacy/lang/sv/__init__.py

32 lines
852 B
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
2017-05-08 13:54:29 +00:00
from __future__ import unicode_literals
2016-12-20 10:05:06 +00:00
2017-05-08 13:54:29 +00:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .morph_rules import MORPH_RULES
from .lemmatizer import LEMMA_RULES, LOOKUP
from ..language_data import BASE_EXCEPTIONS
2016-12-20 10:05:06 +00:00
from ..language import Language
from ..lemmatizerlookup import Lemmatizer
2017-05-08 13:54:29 +00:00
from ..attrs import LANG
from ..util import update_exc
2016-12-20 10:05:06 +00:00
class Swedish(Language):
lang = 'sv'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'sv'
2017-05-08 13:54:29 +00:00
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
2017-05-03 09:01:42 +00:00
@classmethod
def create_lemmatizer(cls, nlp=None):
2017-05-08 13:54:29 +00:00
return Lemmatizer(LOOKUP)
2017-05-03 09:01:42 +00:00
2017-05-08 13:54:29 +00:00
__all__ = ['Swedish']