name: Tutorials

on:
  workflow_dispatch:  # Activate this workflow manually
  pull_request:
    paths:
      - 'tutorials/*.*'


env:
  # Tutorials that require a GPU to run, so can't be run on CI without self-hosted runners
  DONT_RUN: Tutorial2_ Tutorial9_ Tutorial13_ Tutorial18_


jobs:

  docs-check:
    runs-on: ubuntu-latest
    steps:

      - uses: actions/checkout@v2

      - name: Setup Python
        uses: ./.github/actions/python_cache/

      - name: Install Haystack
        run: |
          pip install --upgrade pip
          pip install .[dev]

      - name: Docs Check
        run: python .github/utils/convert_notebooks_into_webpages.py

      - name: Status
        run: |
          if [[ `git status --porcelain` ]]; then
            git status
            echo "##################################################################################################"
            echo "#"
            echo "# CHECK FAILED! You need to update the static version of the tutorials."
            echo "#"
            echo "# Please run the tutorials documentation update script:"
            echo "#"
            echo "#    python .github/utils/convert_notebooks_into_webpages.py"
            echo "#"
            echo "# or see https://github.com/deepset-ai/haystack/blob/main/CONTRIBUTING.md for help."
            echo "#"
            echo "# If you have further problems, please open an issue: https://github.com/deepset-ai/haystack/issues"
            echo "#"
            echo "##################################################################################################"
            exit 1
          fi

  run:
    runs-on: ubuntu-latest

    steps:
    - uses: actions/checkout@v2

    - name: Setup Python
      uses: ./.github/actions/python_cache/

    - name: Install pdftotext
      run: wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz && tar -xvf xpdf-tools-linux-4.04.tar.gz && sudo cp xpdf-tools-linux-4.04/bin64/pdftotext /usr/local/bin

      # Some tutorials require these libraries to run 
      #  - Tutorial 17 for the audio libs
      #  - Tutorial 11, 14, 15, 16 for pygraphviz
    - name: Install graphviz and audio libs
      run: sudo apt install libgraphviz-dev graphviz libsndfile1 ffmpeg

      # Some tutorials require these libraries to run 
      #  - Tutorial 15
    - name: Install torch-scatter
      run: pip install torch-scatter -f https://data.pyg.org/whl/torch-1.12.0+cpu.html

    # Haystack needs to be reinstalled at this stage to make sure the current commit's version is the one getting tested.
    # The cache can last way longer than a specific action's run, so older Haystack version could be carried over.
    - name: Reinstall Haystack
      run: |
        pip install --upgrade pip
        pip install .[all]
        pip install pygraphviz
        pip install ipython nbformat

    - name: Cache mini GoT dataset
      run: |
        mkdir -p data/tutorials
        cd data/tutorials
        wget https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt1_mini.zip -q &> /dev/null
        unzip wiki_gameofthrones_txt1_mini.zip
        rm wiki_gameofthrones_txt1_mini.zip

    - uses: jitterbit/get-changed-files@v1
      id: diff
      continue-on-error: true
      with:
        format: space-delimited
        token: ${{ secrets.GITHUB_TOKEN }}

    - name: Run tutorials
      run: ./.github/utils/tutorials.sh ${{ env.pythonLocation }} "${{ steps.diff.outputs.added_modified }}" "${{ env.DONT_RUN }}" "EDITABLE" "RESTART"