workflow.yml

name: Run Pytest on Branches

concurrency:
  group: ${{github.workflow}}-${{github.ref}}
  cancel-in-progress: true

on:
  pull_request:
    branches:
      - main
  push:
    branches:
      - main

env:
  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
  GOOGLE_APPLICATION_CREDENTIALS: ${{ secrets.GOOGLE_APPLICATION_CREDENTIALS }}
  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
  AZURE_STORAGE_ACCOUNT_URL: ${{ secrets.AZURE_STORAGE_ACCOUNT_URL }}
  AZURE_STORAGE_ACCOUNT_KEY: ${{ secrets.AZURE_STORAGE_ACCOUNT_KEY }}
  PYPI_API_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
  SLACK_ACCESS_KEY: ${{ secrets.SLACK_ACCESS_KEY }}
  DROPBOX_APP_KEY: ${{ secrets.DROPBOX_APP_KEY }}
  DROPBOX_APP_SECRET: ${{secrets.DROPBOX_APP_SECRET}}
  DROPBOX_REFRESH_TOKEN: ${{secrets.DROPBOX_REFRESH_TOKEN}}
  USERNAME_GITHUB: ${{secrets.USERNAME_GITHUB}}
  ACCESS_TOKEN_GITHUB: ${{secrets.ACCESS_TOKEN_GITHUB}}
  REPOSITORY_NAME_GITHUB: ${{secrets.REPOSITORY_NAME_GITHUB}}
  DRIVE_SCOPES: ${{secrets.DRIVE_SCOPES}}
  DRIVE_REFRESH_TOKEN: ${{secrets.DRIVE_REFRESH_TOKEN}}
  DRIVE_TOKEN: ${{secrets.DRIVE_TOKEN}}
  DRIVE_CLIENT_ID: ${{secrets.DRIVE_CLIENT_ID}}
  DRIVE_CLIENT_SECRET: ${{secrets.DRIVE_CLIENT_SECRET}}
  IMAP_PASSWORD: ${{secrets.IMAP_PASSWORD}}
  JIRA_API_TOKEN: ${{secrets.JIRA_API_TOKEN}}
  OPENAI_API_KEY: ${{secrets.OPENAI_API_KEY}}
  NEWS_API_KEY: ${{secrets.NEWS_API_KEY}}
  GOOGLE_BUCKET_PRIVATE_KEY_ID: ${{secrets.GOOGLE_BUCKET_PRIVATE_KEY_ID}}
  GOOGLE_BUCKET_PRIVATE_KEY: ${{secrets.GOOGLE_BUCKET_PRIVATE_KEY}}
  GOOGLE_BUCKET_CLIENT_ID: ${{secrets.GOOGLE_BUCKET_CLIENT_ID}}

jobs:
  pytest:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout code
        uses: actions/checkout@v2
      
      - name: Set up Python
        uses: actions/setup-python@v2
        with:
          python-version: '3.10'

      - name: Check if requirements.txt has changed
        id: check-requirements
        run: |
          git fetch origin main
          git diff --quiet origin/main -- requirements.txt || echo "Requirements changed"
        continue-on-error: true

      - name: Cache Python dependencies
        uses: actions/cache@v2
        with:
          path: ~/.cache/pip
          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
          restore-keys: |
            ${{ runner.os }}-pip-
        if: steps.check-requirements.outputs['check-requirements'] == 'Requirements changed'

      - name: Apt install dependencies
        run: |
          sudo apt-get update
          sudo apt install tesseract-ocr
          sudo apt install libtesseract-dev
          sudo apt-get install ffmpeg
          sudo apt install antiword
          sudo apt install libreoffice
      - id: "auth"
        name: "Authenticate to Google Cloud"
        uses: "google-github-actions/auth@v1"
        with:
          credentials_json: "${{ secrets.GOOGLE_APPLICATION_CREDENTIALS }}"
      - name: "Copy to tmp"
        run: |
          mkdir -p /tmp/.config/gcloud
          cp $GOOGLE_APPLICATION_CREDENTIALS /tmp/.config/gcloud/application_default_credentials.json
      - name: "Set up Google Cloud SDK"
        uses: "google-github-actions/setup-gcloud@v0.2.0"
        with:
          project_id: "protocolstreams-ai"
          service_account_key: "${{ secrets.GOOGLE_APPLICATION_CREDENTIALS }}"
          export_default_credentials: true
      - name: Install curl
        run: |
             sudo apt-get update
             sudo apt-get install curl -y
             sudo apt-get install -y jq

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt
      - name: Cache NLTK punkt
        id: cache-nltk
        uses: actions/cache@v2
        with:
          path: ~/nltk_data/tokenizers/punkt
          key: nltk-punkt-${{ runner.os }}
          restore-keys: |
            nltk-punkt-${{ runner.os }}  
      - name: Download NLTK punkt
        run: |
          python -m nltk.downloader punkt
          python -m nltk.downloader wordnet
          python -m nltk.downloader stopwords
      - name: Cache spaCy large model
        id: cache-spacy
        uses: actions/cache@v2
        with:
            path: ~/.cache/spacy
            key: spacy-large-${{ runner.os }}
            restore-keys: |
              spacy-large-${{ runner.os }}
      - name: Download spaCy large model
        run: |
            python -m spacy download en_core_web_lg
      
      # - name: Run Pytest
      #   run: python -B -m pytest -v --disable-warnings .
      #   env:
      #         PYTHONDONTWRITEBYTECODE: 1

      - name: Test Code Coverage
        run: pytest -s --cov=querent -vv --durations=0
        env:
          PYTHONDONTWRITEBYTECODE: 1

  package:
    runs-on: ubuntu-latest
    needs: pytest
    if: github.ref == 'refs/heads/main' && github.event_name == 'push'
    steps:
      - name: Checkout code
        uses: actions/checkout@v2

      - name: Set up Python
        uses: actions/setup-python@v2
        with:
          python-version: '3.10'

      - name: Package
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt
          pip install --upgrade wheel setuptools
          python setup.py sdist bdist_wheel

      - name: Publish to PyPI
        run: |
          python -m pip install --upgrade pip
          pip install --upgrade twine
          python -m twine upload dist/* --skip-existing
        env:
          TWINE_USERNAME: __token__
          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}