spaCy/spacy/lang/sv/__init__.py

44 lines
1.2 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2017-05-08 16:54:29 +03:00
from __future__ import unicode_literals
2016-12-20 13:05:06 +03:00
2017-05-08 16:54:29 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .tag_map import TAG_MAP
2017-05-08 16:54:29 +03:00
from .stop_words import STOP_WORDS
from .morph_rules import MORPH_RULES
2019-02-08 16:14:49 +03:00
# Punctuation stolen from Danish
from ..da.punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
2017-05-08 16:54:29 +03:00
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-08 23:29:04 +03:00
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2017-05-08 16:54:29 +03:00
2016-12-20 13:05:06 +03:00
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)
morph_rules = MORPH_RULES
tag_map = TAG_MAP
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
stop_words = STOP_WORDS
morph_rules = MORPH_RULES
resources = {
"lemma_lookup": "lemmatizer/lemma_lookup.json",
"lemma_rules": "lemmatizer/lemma_rules.json",
}
2016-12-20 13:05:06 +03:00
2019-02-08 16:14:49 +03:00
class Swedish(Language):
lang = "sv"
Defaults = SwedishDefaults
2017-05-03 12:01:42 +03:00
__all__ = ["Swedish"]