2020-07-22 23:18:46 +03:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2020-07-23 00:09:01 +03:00
|
|
|
from ...symbols import ORTH, NORM
|
2020-07-22 23:18:46 +03:00
|
|
|
from ...util import update_exc
|
2017-03-04 09:20:08 +03:00
|
|
|
|
|
|
|
|
|
2017-05-08 23:29:49 +03:00
|
|
|
_exc = {}
|
2017-03-04 09:20:08 +03:00
|
|
|
|
2017-05-08 23:29:49 +03:00
|
|
|
|
|
|
|
|
for exc_data in [
|
2020-07-23 00:09:01 +03:00
|
|
|
{ORTH: "ডঃ", NORM: "ডক্টর"},
|
|
|
|
|
{ORTH: "ডাঃ", NORM: "ডাক্তার"},
|
|
|
|
|
{ORTH: "ড.", NORM: "ডক্টর"},
|
|
|
|
|
{ORTH: "ডা.", NORM: "ডাক্তার"},
|
|
|
|
|
{ORTH: "মোঃ", NORM: "মোহাম্মদ"},
|
|
|
|
|
{ORTH: "মো.", NORM: "মোহাম্মদ"},
|
|
|
|
|
{ORTH: "সে.", NORM: "সেলসিয়াস"},
|
|
|
|
|
{ORTH: "কি.মি.", NORM: "কিলোমিটার"},
|
|
|
|
|
{ORTH: "কি.মি", NORM: "কিলোমিটার"},
|
|
|
|
|
{ORTH: "সে.মি.", NORM: "সেন্টিমিটার"},
|
|
|
|
|
{ORTH: "সে.মি", NORM: "সেন্টিমিটার"},
|
|
|
|
|
{ORTH: "মি.লি.", NORM: "মিলিলিটার"},
|
💫 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
|
|
|
]:
|
2017-11-02 01:02:45 +03:00
|
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
2017-05-08 23:29:49 +03:00
|
|
|
|
|
|
|
|
|
2020-07-22 23:18:46 +03:00
|
|
|
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|
