fetch-data #124

	name: fetch-data

	on:
	schedule:
	# * is a special character in YAML so you have to quote this string
	- cron: '40 4 * * 4' # 4:40am on Thursdays
	workflow_dispatch:
	inputs:
	dataset_name:
	description: 'Space-separated list of dataset names (or "all" to select all)'
	default: 'all'
	required: true

	jobs:
	latest-data-github:
	runs-on: ubuntu-latest
	env:
	DEFAULT_DATASET_NAME: 'all'
	steps:
	- name: Check out repository
	uses: actions/checkout@v2
	with:
	ref: data
	- name: Pull from main
	run: \|
	git config user.name intoverflow
	git config user.email intoverflow@users.noreply.github.com
	git fetch origin main
	git merge -s recursive -X theirs --allow-unrelated-histories origin/main
	- name: Install the dependencies
	run: pip install -r requirements.txt
	- name: Get the data
	run: python3 src/github/main.py -o data -t ${{ secrets.GITHUB_TOKEN }} ${{ github.event.inputs.dataset_name \|\| env.DEFAULT_DATASET_NAME }}
	- name: Commit the data
	run: \|
	git config user.name intoverflow
	git config user.email intoverflow@users.noreply.github.com
	git add data
	git commit -m "$(date +'%Y-%m-%d') ${{ github.event.inputs.dataset_name }}"
	git push
	- name: Track the size
	run: \|
	du -h data

Provide feedback