mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
eddeb36c96
<!--- 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.
50 lines
1.8 KiB
Python
50 lines
1.8 KiB
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ...symbols import ORTH, LEMMA, NORM
|
||
|
||
_exc = {}
|
||
|
||
_abbrev_exc = [
|
||
# Weekdays abbreviations
|
||
{ORTH: "дш", LEMMA: "дүшәмбе"},
|
||
{ORTH: "сш", LEMMA: "сишәмбе"},
|
||
{ORTH: "чш", LEMMA: "чәршәмбе"},
|
||
{ORTH: "пш", LEMMA: "пәнҗешәмбе"},
|
||
{ORTH: "җм", LEMMA: "җомга"},
|
||
{ORTH: "шб", LEMMA: "шимбә"},
|
||
{ORTH: "яш", LEMMA: "якшәмбе"},
|
||
# Months abbreviations
|
||
{ORTH: "гый", LEMMA: "гыйнвар"},
|
||
{ORTH: "фев", LEMMA: "февраль"},
|
||
{ORTH: "мар", LEMMA: "март"},
|
||
{ORTH: "мар", LEMMA: "март"},
|
||
{ORTH: "апр", LEMMA: "апрель"},
|
||
{ORTH: "июн", LEMMA: "июнь"},
|
||
{ORTH: "июл", LEMMA: "июль"},
|
||
{ORTH: "авг", LEMMA: "август"},
|
||
{ORTH: "сен", LEMMA: "сентябрь"},
|
||
{ORTH: "окт", LEMMA: "октябрь"},
|
||
{ORTH: "ноя", LEMMA: "ноябрь"},
|
||
{ORTH: "дек", LEMMA: "декабрь"},
|
||
# Number abbreviations
|
||
{ORTH: "млрд", LEMMA: "миллиард"},
|
||
{ORTH: "млн", LEMMA: "миллион"},
|
||
]
|
||
|
||
for abbr in _abbrev_exc:
|
||
for orth in (abbr[ORTH], abbr[ORTH].capitalize(), abbr[ORTH].upper()):
|
||
_exc[orth] = [{ORTH: orth, LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}]
|
||
_exc[orth + "."] = [{ORTH: orth + ".", LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}]
|
||
|
||
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"},
|
||
{ORTH: "б.э.", NORM: "безнең эра"},
|
||
]:
|
||
exc_data[LEMMA] = exc_data[NORM]
|
||
_exc[exc_data[ORTH]] = [exc_data]
|
||
|
||
TOKENIZER_EXCEPTIONS = _exc
|