spaCy/spacy/lang/sv/__init__.py

35 lines
1.0 KiB
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
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 ...lemmatizerlookup import Lemmatizer
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2017-05-08 13:54:29 +00:00
2016-12-20 10:05:06 +00:00
class SwedishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'sv'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
2016-12-20 10:05:06 +00:00
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
2016-12-20 10:05:06 +00:00
2017-05-03 09:01:42 +00:00
class Swedish(Language):
lang = 'sv'
Defaults = SwedishDefaults
2017-05-03 09:01:42 +00:00
2017-05-08 13:54:29 +00:00
__all__ = ['Swedish']