mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +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
1.4 KiB
Python
50 lines
1.4 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import ORTH, LEMMA
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
# Time
|
|
for exc_data in [
|
|
{LEMMA: "قبل الميلاد", ORTH: "ق.م"},
|
|
{LEMMA: "بعد الميلاد", ORTH: "ب. م"},
|
|
{LEMMA: "ميلادي", ORTH: ".م"},
|
|
{LEMMA: "هجري", ORTH: ".هـ"},
|
|
{LEMMA: "توفي", ORTH: ".ت"},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
# Scientific abv.
|
|
for exc_data in [
|
|
{LEMMA: "صلى الله عليه وسلم", ORTH: "صلعم"},
|
|
{LEMMA: "الشارح", ORTH: "الشـ"},
|
|
{LEMMA: "الظاهر", ORTH: "الظـ"},
|
|
{LEMMA: "أيضًا", ORTH: "أيضـ"},
|
|
{LEMMA: "إلى آخره", ORTH: "إلخ"},
|
|
{LEMMA: "انتهى", ORTH: "اهـ"},
|
|
{LEMMA: "حدّثنا", ORTH: "ثنا"},
|
|
{LEMMA: "حدثني", ORTH: "ثنى"},
|
|
{LEMMA: "أنبأنا", ORTH: "أنا"},
|
|
{LEMMA: "أخبرنا", ORTH: "نا"},
|
|
{LEMMA: "مصدر سابق", ORTH: "م. س"},
|
|
{LEMMA: "مصدر نفسه", ORTH: "م. ن"},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
# Other abv.
|
|
for exc_data in [
|
|
{LEMMA: "دكتور", ORTH: "د."},
|
|
{LEMMA: "أستاذ دكتور", ORTH: "أ.د"},
|
|
{LEMMA: "أستاذ", ORTH: "أ."},
|
|
{LEMMA: "بروفيسور", ORTH: "ب."},
|
|
]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
for exc_data in [{LEMMA: "تلفون", ORTH: "ت."}, {LEMMA: "صندوق بريد", ORTH: "ص.ب"}]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|