spaCy/spacy/lang/sv/__init__.py
Ines Montani 5ca7dd0f94
💫 WIP: Basic lookup class scaffolding and JSON for all lemmati… (#4167)
* Improve load_language_data helper

* WIP: Add Lookups implementation

* Start moving lemma data over to JSON

* WIP: move data over for more languages

* Convert more languages

* Fix lemmatizer fixtures in tests

* Finish conversion

* Auto-format JSON files

* Fix test for now

* Make sure tables are stored on instance
2019-08-22 14:21:32 +02:00

44 lines
1.2 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .morph_rules import MORPH_RULES
# Punctuation stolen from Danish
from ..da.punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
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)
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",
}
class Swedish(Language):
lang = "sv"
Defaults = SwedishDefaults
__all__ = ["Swedish"]