2017-03-12 12:07:28 +00:00
|
|
|
|
# coding: utf8
|
2017-03-04 06:20:08 +00:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
|
|
# Source: উচ্চতর বাংলা ব্যাকরণ ও রচনা - অধ্যাপক নিরঞ্জন অধিকারী ও অধ্যাপক ড. সফিউদ্দিন আহমদ
|
|
|
|
|
|
|
|
|
|
|
|
LEMMA_RULES = {
|
|
|
|
|
|
"noun": [
|
|
|
|
|
|
["টা", ""],
|
|
|
|
|
|
["টি", ""],
|
|
|
|
|
|
["খান", ""],
|
|
|
|
|
|
["খানা", ""],
|
|
|
|
|
|
["খানি", ""],
|
|
|
|
|
|
["গাছা", ""],
|
|
|
|
|
|
["গাছি", ""],
|
|
|
|
|
|
["ছড়া", ""],
|
|
|
|
|
|
["কে", ""],
|
|
|
|
|
|
["ে", ""],
|
|
|
|
|
|
["তে", ""],
|
|
|
|
|
|
["র", ""],
|
|
|
|
|
|
["রা", ""],
|
|
|
|
|
|
["রে", ""],
|
|
|
|
|
|
["ের", ""], # এর
|
|
|
|
|
|
["েরা", ""], # এরা
|
|
|
|
|
|
["দের", ""],
|
|
|
|
|
|
["দেরকে", ""],
|
|
|
|
|
|
["গুলা", ""],
|
|
|
|
|
|
["গুলো", ""],
|
|
|
|
|
|
["গুলি", ""],
|
|
|
|
|
|
["কুল", ""],
|
|
|
|
|
|
["গণ", ""],
|
|
|
|
|
|
["দল", ""],
|
|
|
|
|
|
["পাল", ""],
|
|
|
|
|
|
["পুঞ্জ", ""],
|
|
|
|
|
|
["মণ্ডলী", ""],
|
|
|
|
|
|
["মালা", ""],
|
|
|
|
|
|
["রাজি", ""],
|
|
|
|
|
|
["বৃন্দ", ""],
|
|
|
|
|
|
["বর্গ", ""],
|
|
|
|
|
|
["শ্রেণী", ""],
|
|
|
|
|
|
["শ্রেনি", ""],
|
|
|
|
|
|
["রাশি", ""],
|
|
|
|
|
|
["সকল", ""],
|
|
|
|
|
|
["মহল", ""],
|
|
|
|
|
|
["াবলি", ""], # আবলি
|
|
|
|
|
|
# Bengali digit representations
|
|
|
|
|
|
["০", "0"],
|
|
|
|
|
|
["১", "1"],
|
|
|
|
|
|
["২", "2"],
|
|
|
|
|
|
["৩", "3"],
|
|
|
|
|
|
["৪", "4"],
|
|
|
|
|
|
["৫", "5"],
|
|
|
|
|
|
["৬", "6"],
|
|
|
|
|
|
["৭", "7"],
|
|
|
|
|
|
["৮", "8"],
|
|
|
|
|
|
["৯", "9"],
|
|
|
|
|
|
],
|
💫 Tidy up and auto-format .py files (#2983)
<!--- 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.
2018-11-30 16:03:03 +00:00
|
|
|
|
"punct": [["“", '"'], ["”", '"'], ["\u2018", "'"], ["\u2019", "'"]],
|
2017-03-04 06:20:08 +00:00
|
|
|
|
}
|