2020-08-07 16:27:13 +03:00
|
|
|
from typing import Optional
|
|
|
|
from thinc.api import Model
|
2020-07-22 14:42:59 +03:00
|
|
|
|
2018-07-10 14:48:38 +03:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from .lex_attrs import LEX_ATTRS
|
2020-07-24 15:50:26 +03:00
|
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
2018-07-10 14:48:38 +03:00
|
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
2020-08-07 16:27:13 +03:00
|
|
|
from .lemmatizer import GreekLemmatizer
|
2018-07-10 14:48:38 +03:00
|
|
|
from ...language import Language
|
|
|
|
|
|
|
|
|
|
|
|
class GreekDefaults(Language.Defaults):
|
2020-07-22 23:18:46 +03:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
2018-07-10 14:48:38 +03:00
|
|
|
prefixes = TOKENIZER_PREFIXES
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
infixes = TOKENIZER_INFIXES
|
2020-07-24 15:50:26 +03:00
|
|
|
lex_attr_getters = LEX_ATTRS
|
|
|
|
stop_words = STOP_WORDS
|
|
|
|
syntax_iterators = SYNTAX_ITERATORS
|
2018-08-14 03:31:32 +03:00
|
|
|
|
2018-07-10 14:48:38 +03:00
|
|
|
|
|
|
|
class Greek(Language):
|
2019-08-22 15:21:32 +03:00
|
|
|
lang = "el"
|
|
|
|
Defaults = GreekDefaults
|
2018-07-10 14:48:38 +03:00
|
|
|
|
|
|
|
|
2020-08-07 16:27:13 +03:00
|
|
|
@Greek.factory(
|
|
|
|
"lemmatizer",
|
|
|
|
assigns=["token.lemma"],
|
2020-10-02 16:42:36 +03:00
|
|
|
default_config={"model": None, "mode": "rule"},
|
2020-08-07 16:27:13 +03:00
|
|
|
default_score_weights={"lemma_acc": 1.0},
|
|
|
|
)
|
2020-10-02 16:42:36 +03:00
|
|
|
def make_lemmatizer(nlp: Language, model: Optional[Model], name: str, mode: str):
|
|
|
|
return GreekLemmatizer(nlp.vocab, model, name, mode=mode)
|
2020-08-07 16:27:13 +03:00
|
|
|
|
|
|
|
|
💫 Tidy up and auto-format .py files (#2983)
<!--- 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.
2018-11-30 19:03:03 +03:00
|
|
|
__all__ = ["Greek"]
|