mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
eddeb36c96
<!--- Provide a general summary of your changes in the title. --> ## Description - [x] Use [`black`](https://github.com/ambv/black) to auto-format all `.py` files. - [x] Update flake8 config to exclude very large files (lemmatization tables etc.) - [x] Update code to be compatible with flake8 rules - [x] Fix various small bugs, inconsistencies and messy stuff in the language data - [x] Update docs to explain new code style (`black`, `flake8`, when to use `# fmt: off` and `# fmt: on` and what `# noqa` means) Once #2932 is merged, which auto-formats and tidies up the CLI, we'll be able to run `flake8 spacy` actually get meaningful results. At the moment, the code style and linting isn't applied automatically, but I'm hoping that the new [GitHub Actions](https://github.com/features/actions) will let us auto-format pull requests and post comments with relevant linting information. ### Types of change enhancement, code style ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
# encoding: utf8
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .tag_map import TAG_MAP
|
|
from .lemmatizer import RussianLemmatizer
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...util import update_exc, add_lookups
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
|
|
|
|
class RussianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "ru"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
tag_map = TAG_MAP
|
|
|
|
@classmethod
|
|
def create_lemmatizer(cls, nlp=None):
|
|
return RussianLemmatizer()
|
|
|
|
|
|
class Russian(Language):
|
|
lang = "ru"
|
|
Defaults = RussianDefaults
|
|
|
|
|
|
__all__ = ["Russian"]
|