spaCy/spacy/lang/sv/__init__.py
ines 417d45f5d0 Add lemmatizer data as variable on language data
Don't create lookup lemmatizer within Language class and just pass in
the data so it can be set on Token creation
2017-10-11 02:24:58 +02:00

32 lines
955 B
Python

# coding: utf8
from __future__ import unicode_literals
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 ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
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)
lemma_rules = dict(LEMMA_RULES)
lemma_lookup = dict(LOOKUP)
class Swedish(Language):
lang = 'sv'
Defaults = SwedishDefaults
__all__ = ['Swedish']