test_local_sources.yml

# Tests sources against a couple of local destinations

name: src | rest_api, sql_database, filesystem

on:
  pull_request:
    branches:
      - master
      - devel
  workflow_dispatch:

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

env:

  # RUNTIME__SENTRY_DSN: https://6f6f7b6f8e0f458a89be4187603b55fe@o1061158.ingest.sentry.io/4504819859914752
  RUNTIME__LOG_LEVEL: ERROR
  RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }}

  ACTIVE_DESTINATIONS: "[\"duckdb\", \"postgres\", \"filesystem\"]"
  ALL_FILESYSTEM_DRIVERS: "[\"file\"]"

jobs:
  get_docs_changes:
    name: docs changes
    uses: ./.github/workflows/get_docs_changes.yml

  run_loader:
    name: src | rest_api, sql_database, filesystem
    needs: get_docs_changes
    if: needs.get_docs_changes.outputs.changes_outside_docs == 'true'
    strategy:
      fail-fast: false
    defaults:
      run:
        shell: bash
    runs-on: "ubuntu-latest"

    # Service containers to run with `container-job`
    services:
      # Label used to access the service container
      postgres:
        # Docker Hub image
        image: postgres
        # Provide the password for postgres
        env:
          POSTGRES_DB: dlt_data
          POSTGRES_USER: loader
          POSTGRES_PASSWORD: loader
        ports:
          - 5432:5432
        # Set health checks to wait until postgres has started
        options: >-
          --health-cmd pg_isready
          --health-interval 10s
          --health-timeout 5s
          --health-retries 5

    steps:
      - name: Check out
        uses: actions/checkout@master

      - name: Setup Python
        uses: actions/setup-python@v4
        with:
          python-version: "3.10.x"

      - name: Install Poetry
        uses: snok/install-poetry@v1.3.2
        with:
          virtualenvs-create: true
          virtualenvs-in-project: true
          installer-parallel: true

      - name: Load cached venv
        id: cached-poetry-dependencies
        uses: actions/cache@v3
        with:
          path: .venv
          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}-local-sources

      # TODO: which deps should we enable?
      - name: Install dependencies
        run: poetry install --no-interaction -E postgres -E duckdb -E parquet -E filesystem -E cli -E sql_database --with sentry-sdk,pipeline,sources

      # run sources tests in load against configured destinations
      - run: poetry run pytest tests/load/sources
        name: Run tests Linux
        env:
          DESTINATION__POSTGRES__CREDENTIALS: postgresql://loader:loader@localhost:5432/dlt_data

      # here we upgrade sql alchemy to 2 an run the sql_database tests again
      - name: Upgrade sql alchemy
        run: poetry run pip install sqlalchemy==2.0.32

      - run: poetry run pytest tests/load/sources/sql_database
        name: Run tests Linux
        env:
          DESTINATION__POSTGRES__CREDENTIALS: postgresql://loader:loader@localhost:5432/dlt_data