mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +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.
59 lines
1.1 KiB
Python
59 lines
1.1 KiB
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
|
||
ADJECTIVE_RULES = [
|
||
["ین", ""],
|
||
["\u200cترین", ""],
|
||
["ترین", ""],
|
||
["\u200cتر", ""],
|
||
["تر", ""],
|
||
["\u200cای", ""],
|
||
# ["ایی", "ا"],
|
||
# ["ویی", "و"],
|
||
# ["ی", ""],
|
||
# ["مند", ""],
|
||
# ["گین", ""],
|
||
# ["مین", ""],
|
||
# ["ناک", ""],
|
||
# ["سار", ""],
|
||
# ["\u200cوار", ""],
|
||
# ["وار", ""]
|
||
]
|
||
|
||
|
||
NOUN_RULES = [
|
||
["ایان", "ا"],
|
||
["ویان", "و"],
|
||
["ایانی", "ا"],
|
||
["ویانی", "و"],
|
||
["گان", "ه"],
|
||
["گانی", "ه"],
|
||
["گان", ""],
|
||
["گانی", ""],
|
||
["ان", ""],
|
||
["انی", ""],
|
||
["ات", ""],
|
||
["ات", "ه"],
|
||
["ات", "ت"],
|
||
["اتی", ""],
|
||
["اتی", "ه"],
|
||
["اتی", "ت"],
|
||
# ['ین', ''],
|
||
# ['ینی', ''],
|
||
# ['ون', ''],
|
||
# ['ونی', ''],
|
||
["\u200cها", ""],
|
||
["ها", ""],
|
||
["\u200cهای", ""],
|
||
["های", ""],
|
||
["\u200cهایی", ""],
|
||
["هایی", ""],
|
||
]
|
||
|
||
|
||
VERB_RULES = []
|
||
|
||
|
||
PUNCT_RULES = [["“", '"'], ["”", '"'], ["\u2018", "'"], ["\u2019", "'"]]
|