python-ci.yml

# This file is part of MediaWiki Code2Code Search
# <https://github.com/ftosoni/mediawiki-code2code-search>.
# Copyright (c) 2026 Francesco Tosoni.

name: Python CI

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]
  workflow_dispatch:

# translatewiki.org pushes i18n updates daily; queue deploys instead of racing them.
concurrency:
  group: toolforge-deploy
  cancel-in-progress: false

jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
    - name: Set up Python
      uses: actions/setup-python@v5
      with:
        python-version: '3.11'
    - name: Install Linting dependencies
      run: |
        python -m pip install --upgrade pip
        pip install flake8
    - name: Lint with flake8
      run: |
        # stop the build if there are Python syntax errors or undefined names
        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=tests/example.py
        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics --exclude=tests/example.py

  test:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
    - name: Set up Python
      uses: actions/setup-python@v5
      with:
        python-version: '3.11'
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        # We install dependencies but exclude heavy ones if possible, 
        # however app.py imports them so we need them for TestClient to work.
        pip install -r requirements.txt
        pip install pytest pytest-asyncio
    - name: Run tests
      run: |
        # Run structural parser tests for all languages
        # These are lightweight and do not require heavy model downloads.
        # Also run mocked API tests and connectivity tests.
        pytest tests/test_*_parser.py tests/test_api.py tests/test_hf_availability.py

  deploy:
    name: Deploy to Toolforge
    needs: [ lint, test ]
    if: github.ref == 'refs/heads/main' && github.event_name != 'pull_request'
    runs-on: ubuntu-latest
    steps:
      - name: Rebuild image and restart webservice
        uses: appleboy/ssh-action@v1.2.2
        with:
          host: login.toolforge.org
          username: ${{ secrets.TOOLFORGE_USERNAME }}
          key: ${{ secrets.TOOLFORGE_SSH_KEY }}
          port: 22
          # `toolforge build start` streams the build log and only returns once the
          # build finishes, so the restart below always picks up the new image.
          request_pty: true
          command_timeout: 30m
          # ssh-action dropped the `script_stop` input in v1.1.0; `set -e` replaces it.
          # Without it a failed build would still fall through to the restart below.
          script: |
            set -e
            become code2codesearch toolforge build clean -y
            become code2codesearch toolforge build start https://github.com/ftosoni/mediawiki-code2code-search
            become code2codesearch toolforge webservice buildservice stop --mount=all || true
            become code2codesearch toolforge webservice buildservice start --mount=all -m 6Gi
            # `buildservice start` returns once the pod is scheduled, not once gunicorn has
            # loaded the models, which takes minutes. Without this wait the job goes green
            # while the site is still serving nothing, or the previous image.
            for attempt in $(seq 1 60); do
              if curl -fsS https://code2codesearch.toolforge.org/health | grep -q '"status":"ok"'; then
                echo "Webservice healthy after ${attempt} attempt(s)."
                exit 0
              fi
              sleep 10
            done
            echo "Webservice did not answer /health within 10 minutes." >&2
            exit 1