mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +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.
24 lines
1000 B
Python
24 lines
1000 B
Python
# encoding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import ORTH, LEMMA
|
|
|
|
|
|
_exc = {
|
|
"ม.ค.": [{ORTH: "ม.ค.", LEMMA: "มกราคม"}],
|
|
"ก.พ.": [{ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}],
|
|
"มี.ค.": [{ORTH: "มี.ค.", LEMMA: "มีนาคม"}],
|
|
"เม.ย.": [{ORTH: "เม.ย.", LEMMA: "เมษายน"}],
|
|
"พ.ค.": [{ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}],
|
|
"มิ.ย.": [{ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}],
|
|
"ก.ค.": [{ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}],
|
|
"ส.ค.": [{ORTH: "ส.ค.", LEMMA: "สิงหาคม"}],
|
|
"ก.ย.": [{ORTH: "ก.ย.", LEMMA: "กันยายน"}],
|
|
"ต.ค.": [{ORTH: "ต.ค.", LEMMA: "ตุลาคม"}],
|
|
"พ.ย.": [{ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}],
|
|
"ธ.ค.": [{ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}],
|
|
}
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|