Skip to content

Update S3 Data

Update S3 Data #6

name: Update S3 Data
on:
workflow_dispatch:
# schedule:
# - cron: "30 16 * * 5" # Runs at 10:30 PM IST every Friday
env:
AWS_ACCOUNT_ID: ${{ secrets.AWS_ACCOUNT_ID }}
jobs:
update-s3-data:
runs-on: ubuntu-latest
permissions:
contents: write
id-token: write
steps:
- name: Check out this repo
uses: actions/checkout@v4
- name: install uv
uses: astral-sh/setup-uv@v6
with:
version: "0.8.3"
- name: Install dependencies
run: uv sync --locked --all-extras --dev
- name: Authenticate with AWS using OIDC
uses: aws-actions/configure-aws-credentials@v4
with:
role-to-assume: arn:aws:iam::${{ env.AWS_ACCOUNT_ID }}:role/github-actions
aws-region: ap-south-1
- name: Update S3 data
run: uv run download.py --sync-s3
- name: Update dataset sizes
run: uv run calculate_dataset_sizes.py
- name: Commit and push changes
run: |
git config user.name "Automated"
git config user.email "[email protected]"
git add -A
timestamp=$(date -u)
git commit -m "Update dataset sizes" || exit 0
git push