mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +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.
55 lines
1.6 KiB
Python
55 lines
1.6 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
|
|
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .tag_map import TAG_MAP
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .lemmatizer import LEMMA_RULES, LEMMA_INDEX, LEMMA_EXC, LOOKUP
|
|
from .lemmatizer.lemmatizer import FrenchLemmatizer
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
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 FrenchDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "fr"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
token_match = TOKEN_MATCH
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
@classmethod
|
|
def create_lemmatizer(cls, nlp=None):
|
|
lemma_rules = LEMMA_RULES
|
|
lemma_index = LEMMA_INDEX
|
|
lemma_exc = LEMMA_EXC
|
|
lemma_lookup = LOOKUP
|
|
return FrenchLemmatizer(
|
|
index=lemma_index,
|
|
exceptions=lemma_exc,
|
|
rules=lemma_rules,
|
|
lookup=lemma_lookup,
|
|
)
|
|
|
|
|
|
class French(Language):
|
|
lang = "fr"
|
|
Defaults = FrenchDefaults
|
|
|
|
|
|
__all__ = ["French"]
|