mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-30 20:06:30 +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.
53 lines
702 B
Python
53 lines
702 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import ORTH
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
# Source: https://en.wiktionary.org/wiki/Category:Romanian_abbreviations
|
|
for orth in [
|
|
"1-a",
|
|
"2-a",
|
|
"3-a",
|
|
"4-a",
|
|
"5-a",
|
|
"6-a",
|
|
"7-a",
|
|
"8-a",
|
|
"9-a",
|
|
"10-a",
|
|
"11-a",
|
|
"12-a",
|
|
"1-ul",
|
|
"2-lea",
|
|
"3-lea",
|
|
"4-lea",
|
|
"5-lea",
|
|
"6-lea",
|
|
"7-lea",
|
|
"8-lea",
|
|
"9-lea",
|
|
"10-lea",
|
|
"11-lea",
|
|
"12-lea",
|
|
"d-voastră",
|
|
"dvs.",
|
|
"ing.",
|
|
"dr.",
|
|
"Rom.",
|
|
"str.",
|
|
"nr.",
|
|
"etc.",
|
|
"d.p.d.v.",
|
|
"dpdv",
|
|
"șamd.",
|
|
"ș.a.m.d.",
|
|
]:
|
|
_exc[orth] = [{ORTH: orth}]
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|