2023-06-14 15:48:41 +00:00
|
|
|
|
from ...symbols import NORM, ORTH
|
2020-07-22 20:18:46 +00:00
|
|
|
|
from ...util import update_exc
|
2023-06-14 15:48:41 +00:00
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2018-06-19 08:17:53 +00:00
|
|
|
|
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
|
|
|
|
|
|
_abbrev_exc = [
|
|
|
|
|
|
# Weekdays abbreviations
|
2020-07-22 21:09:01 +00:00
|
|
|
|
{ORTH: "дш", NORM: "дүшәмбе"},
|
|
|
|
|
|
{ORTH: "сш", NORM: "сишәмбе"},
|
|
|
|
|
|
{ORTH: "чш", NORM: "чәршәмбе"},
|
|
|
|
|
|
{ORTH: "пш", NORM: "пәнҗешәмбе"},
|
|
|
|
|
|
{ORTH: "җм", NORM: "җомга"},
|
|
|
|
|
|
{ORTH: "шб", NORM: "шимбә"},
|
|
|
|
|
|
{ORTH: "яш", NORM: "якшәмбе"},
|
2018-06-19 08:17:53 +00:00
|
|
|
|
# Months abbreviations
|
2020-07-22 21:09:01 +00:00
|
|
|
|
{ORTH: "гый", NORM: "гыйнвар"},
|
|
|
|
|
|
{ORTH: "фев", NORM: "февраль"},
|
|
|
|
|
|
{ORTH: "мар", NORM: "март"},
|
|
|
|
|
|
{ORTH: "мар", NORM: "март"},
|
|
|
|
|
|
{ORTH: "апр", NORM: "апрель"},
|
|
|
|
|
|
{ORTH: "июн", NORM: "июнь"},
|
|
|
|
|
|
{ORTH: "июл", NORM: "июль"},
|
|
|
|
|
|
{ORTH: "авг", NORM: "август"},
|
|
|
|
|
|
{ORTH: "сен", NORM: "сентябрь"},
|
|
|
|
|
|
{ORTH: "окт", NORM: "октябрь"},
|
|
|
|
|
|
{ORTH: "ноя", NORM: "ноябрь"},
|
|
|
|
|
|
{ORTH: "дек", NORM: "декабрь"},
|
2018-06-19 08:17:53 +00:00
|
|
|
|
# Number abbreviations
|
2020-07-22 21:09:01 +00:00
|
|
|
|
{ORTH: "млрд", NORM: "миллиард"},
|
|
|
|
|
|
{ORTH: "млн", NORM: "миллион"},
|
2018-06-19 08:17:53 +00:00
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
for abbr in _abbrev_exc:
|
|
|
|
|
|
for orth in (abbr[ORTH], abbr[ORTH].capitalize(), abbr[ORTH].upper()):
|
2020-07-22 21:09:01 +00:00
|
|
|
|
_exc[orth] = [{ORTH: orth, NORM: abbr[NORM]}]
|
|
|
|
|
|
_exc[orth + "."] = [{ORTH: orth + ".", NORM: abbr[NORM]}]
|
2018-06-19 08:17:53 +00:00
|
|
|
|
|
|
|
|
|
|
for exc_data in [ # "etc." abbreviations
|
|
|
|
|
|
{ORTH: "һ.б.ш.", NORM: "һәм башка шундыйлар"},
|
|
|
|
|
|
{ORTH: "һ.б.", NORM: "һәм башка"},
|
|
|
|
|
|
{ORTH: "б.э.к.", NORM: "безнең эрага кадәр"},
|
💫 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
|
|
|
|
{ORTH: "б.э.", NORM: "безнең эра"},
|
|
|
|
|
|
]:
|
2018-06-19 08:17:53 +00:00
|
|
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
|
|
|
2020-07-22 20:18:46 +00:00
|
|
|
|
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|