spaCy/spacy/lang/lt/__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

42 lines
1.1 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .tag_map import TAG_MAP
from .morph_rules import MORPH_RULES
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
def _return_lt(_):
return "lt"
class LithuanianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = _return_lt
lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
)
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
tag_map = TAG_MAP
morph_rules = MORPH_RULES
resources = {"lemma_lookup": "lemma_lookup.json"}
class Lithuanian(Language):
lang = "lt"
Defaults = LithuanianDefaults
__all__ = ["Lithuanian"]