2020-07-22 11:42:59 +00:00
|
|
|
from typing import Set
|
|
|
|
|
from thinc.api import Config
|
|
|
|
|
|
2017-05-08 13:43:50 +00:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
|
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
|
|
|
from .stop_words import STOP_WORDS
|
2017-05-08 20:29:04 +00:00
|
|
|
from ...language import Language
|
2020-07-22 20:18:46 +00:00
|
|
|
from ...util import registry
|
2020-07-22 11:42:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
|
|
|
[nlp]
|
|
|
|
|
lang = "bn"
|
|
|
|
|
stop_words = {"@language_data": "spacy.bn.stop_words"}
|
|
|
|
|
|
|
|
|
|
[nlp.lemmatizer]
|
|
|
|
|
@lemmatizers = "spacy.Lemmatizer.v1"
|
|
|
|
|
|
2020-07-22 13:59:37 +00:00
|
|
|
[nlp.lemmatizer.data]
|
2020-07-22 11:42:59 +00:00
|
|
|
@language_data = "spacy-lookups-data"
|
|
|
|
|
lang = ${nlp:lang}
|
2020-07-22 13:59:37 +00:00
|
|
|
tables = ["lemma_rules"]
|
2020-07-22 11:42:59 +00:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@registry.language_data("spacy.bn.stop_words")
|
|
|
|
|
def stop_words() -> Set[str]:
|
|
|
|
|
return STOP_WORDS
|
2017-02-28 01:48:37 +00:00
|
|
|
|
|
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class BengaliDefaults(Language.Defaults):
|
2020-07-22 20:18:46 +00:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
2017-10-11 13:34:55 +00:00
|
|
|
prefixes = TOKENIZER_PREFIXES
|
|
|
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
|
infixes = TOKENIZER_INFIXES
|
2017-02-28 01:48:37 +00:00
|
|
|
|
2017-02-28 15:07:14 +00:00
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class Bengali(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 16:03:03 +00:00
|
|
|
lang = "bn"
|
2017-05-20 17:02:27 +00:00
|
|
|
Defaults = BengaliDefaults
|
2020-07-22 11:42:59 +00:00
|
|
|
default_config = Config().from_str(DEFAULT_CONFIG)
|
2017-05-03 09:01:42 +00:00
|
|
|
|
2017-05-08 13:43:50 +00:00
|
|
|
|
💫 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 16:03:03 +00:00
|
|
|
__all__ = ["Bengali"]
|