database.yml

name: Database

on:
  workflow_dispatch:
  schedule:
    # * is a special character in YAML so you have to quote this string
    - cron:  '0 0 1 * *'

jobs:
  generate_tsv_files:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        type: ['database', 'suffix-array']
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
      - uses: Swatinem/rust-cache@v2
        id: cache
        with:
          shared-key: ${{ env.CACHE_KEY }}
      - run: cd scripts/helper_scripts/unipept-database-rs && cargo fetch
        if: ${{ !steps.cache.outputs.cache-hit }}
      - run: ./scripts/build_binaries.sh
      - name: Get current date
        id: date
        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
      - name: Install required utilities
        run: |
          sudo apt-get update
          sudo apt-get -y install git curl unzip gawk sqlite3 libsqlite3-dev pv nodejs wget uuid-runtime pigz lz4 parallel
      - name: Prepare temporary directories
        run: sudo mkdir -p "index" "unipept-temp"
      - name: Generate tsv.gz files
        shell: bash
        run: sudo ./scripts/build_database.sh -i "index" -d "unipept-temp" -m "256M" "${{ matrix.type }}" "swissprot" "https://ftp.expasy.org/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.xml.gz" "output"
      - name: Zip all tsv.gz files
        shell: bash
        run: cd output && zip "${{ matrix.type }}.zip" "*.tsv.lz4"
      - name: Upload or Update Release
        id: upload_or_update_release
        uses: softprops/action-gh-release@v1
        with:
          files: ${{ matrix.type }}.zip
          tag_name: database-${{ env.date }}
          name: Database ${{ env.date }}
          commitish: ${{ github.sha }}
          draft: false
          prerelease: false
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}