2020-07-22 23:18:46 +03:00
|
|
|
from typing import Set, Dict, Callable, Any, Pattern
|
2020-07-22 14:42:59 +03:00
|
|
|
from thinc.api import Config
|
|
|
|
|
2017-05-08 16:49:05 +03:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
|
2020-03-25 13:27:42 +03:00
|
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
2017-05-08 16:49:05 +03:00
|
|
|
from .stop_words import STOP_WORDS
|
2017-09-26 17:47:45 +03:00
|
|
|
from .lex_attrs import LEX_ATTRS
|
2020-07-22 14:42:59 +03:00
|
|
|
from .lemmatizer import FrenchLemmatizer, is_base_form
|
2020-07-22 23:18:46 +03:00
|
|
|
from .syntax_iterators import noun_chunks
|
2017-05-08 23:29:04 +03:00
|
|
|
from ...language import Language
|
2020-07-22 23:18:46 +03:00
|
|
|
from ...util import registry
|
2020-07-22 14:42:59 +03:00
|
|
|
|
|
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
|
|
[nlp]
|
|
|
|
lang = "fr"
|
|
|
|
stop_words = {"@language_data": "spacy.fr.stop_words"}
|
|
|
|
lex_attr_getters = {"@language_data": "spacy.fr.lex_attr_getters"}
|
2020-07-22 23:18:46 +03:00
|
|
|
get_noun_chunks = {"@language_data": "spacy.fr.get_noun_chunks"}
|
|
|
|
|
|
|
|
[nlp.tokenizer]
|
|
|
|
@tokenizers = "spacy.Tokenizer.v1"
|
|
|
|
token_match = {"@language_data": "spacy.fr.token_match"}
|
2020-07-22 14:42:59 +03:00
|
|
|
|
|
|
|
[nlp.lemmatizer]
|
|
|
|
@lemmatizers = "spacy.FrenchLemmatizer.v1"
|
|
|
|
|
2020-07-22 16:59:37 +03:00
|
|
|
[nlp.lemmatizer.data]
|
2020-07-22 14:42:59 +03:00
|
|
|
@language_data = "spacy-lookups-data"
|
|
|
|
lang = ${nlp:lang}
|
2020-07-22 16:59:37 +03:00
|
|
|
tables = ["lemma_rules", "lemma_index", "lemma_exc", "lemma_lookup"]
|
2020-07-22 14:42:59 +03:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
@registry.lemmatizers("spacy.FrenchLemmatizer.v1")
|
2020-07-22 16:59:37 +03:00
|
|
|
def create_french_lemmatizer(data: Dict[str, dict] = {}) -> FrenchLemmatizer:
|
|
|
|
return FrenchLemmatizer(data=data, is_base_form=is_base_form)
|
2020-07-22 14:42:59 +03:00
|
|
|
|
|
|
|
|
2020-07-22 23:18:46 +03:00
|
|
|
@registry.language_data("spacy.fr.token_match")
|
|
|
|
def token_match() -> Pattern:
|
|
|
|
return TOKEN_MATCH
|
|
|
|
|
|
|
|
|
2020-07-22 14:42:59 +03:00
|
|
|
@registry.language_data("spacy.fr.stop_words")
|
|
|
|
def stop_words() -> Set[str]:
|
|
|
|
return STOP_WORDS
|
|
|
|
|
|
|
|
|
|
|
|
@registry.language_data("spacy.fr.lex_attr_getters")
|
|
|
|
def lex_attr_getters() -> Dict[int, Callable[[str], Any]]:
|
|
|
|
return LEX_ATTRS
|
2017-04-24 17:39:00 +03:00
|
|
|
|
2016-11-02 22:02:41 +03:00
|
|
|
|
2020-07-22 23:18:46 +03:00
|
|
|
@registry.language_data("spacy.fr.get_noun_chunks")
|
|
|
|
def get_noun_chunks() -> Callable:
|
|
|
|
return noun_chunks
|
|
|
|
|
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class FrenchDefaults(Language.Defaults):
|
2020-07-22 23:18:46 +03:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
2020-03-25 13:27:42 +03:00
|
|
|
prefixes = TOKENIZER_PREFIXES
|
2017-10-11 16:34:55 +03:00
|
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
💫 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
|
|
|
|
2017-05-08 16:49:05 +03:00
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class French(Language):
|
💫 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
|
|
|
lang = "fr"
|
2017-05-20 20:02:27 +03:00
|
|
|
Defaults = FrenchDefaults
|
2020-07-22 14:42:59 +03:00
|
|
|
default_config = Config().from_str(DEFAULT_CONFIG)
|
2017-05-03 12:01:42 +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__ = ["French"]
|