iceberg table format support for filesystem destination
#5948
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Tests destinations that can run without credentials. | |
| # i.e. local postgres, duckdb, filesystem (with local fs/memory bucket) | |
| name: dest | postgres, duckdb and fs | |
| on: | |
| pull_request: | |
| branches: | |
| - master | |
| - devel | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| # NOTE: this workflow can't use github secrets! | |
| # DLT_SECRETS_TOML: ${{ secrets.DLT_SECRETS_TOML }} | |
| # RUNTIME__SENTRY_DSN: https://[email protected]/4504819859914752 | |
| RUNTIME__LOG_LEVEL: ERROR | |
| RUNTIME__DLTHUB_TELEMETRY_ENDPOINT: ${{ secrets.RUNTIME__DLTHUB_TELEMETRY_ENDPOINT }} | |
| ACTIVE_DESTINATIONS: "[\"duckdb\", \"postgres\", \"filesystem\", \"weaviate\", \"qdrant\"]" | |
| ALL_FILESYSTEM_DRIVERS: "[\"memory\", \"file\", \"sftp\"]" | |
| DESTINATION__WEAVIATE__VECTORIZER: text2vec-contextionary | |
| DESTINATION__WEAVIATE__MODULE_CONFIG: "{\"text2vec-contextionary\": {\"vectorizeClassName\": false, \"vectorizePropertyName\": true}}" | |
| jobs: | |
| get_docs_changes: | |
| name: docs changes | |
| uses: ./.github/workflows/get_docs_changes.yml | |
| run_loader: | |
| name: dest | postgres, duckdb and fs local tests | |
| 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: postgis/postgis | |
| # 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 | |
| qdrant: | |
| image: qdrant/qdrant:v1.8.4 | |
| ports: | |
| - 6333:6333 | |
| steps: | |
| - name: Check out | |
| uses: actions/checkout@master | |
| - name: Start weaviate | |
| run: docker compose -f "tests/load/weaviate/docker-compose.yml" up -d | |
| - name: Setup Python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: "3.10.x" | |
| - name: Install Poetry | |
| uses: snok/[email protected] | |
| 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-destinations | |
| - name: Install dependencies | |
| run: poetry install --no-interaction -E postgres -E postgis -E duckdb -E parquet -E filesystem -E cli -E weaviate -E qdrant -E sftp --with sentry-sdk --with pipeline -E deltalake -E pyiceberg | |
| - name: Upgrade sqlalchemy | |
| run: poetry run pip install sqlalchemy==2.0.18 # minimum version required by `pyiceberg` | |
| - name: Start SFTP server | |
| run: docker compose -f "tests/load/filesystem_sftp/docker-compose.yml" up -d | |
| - name: Configure SSH Agent for sftp tests | |
| run: | | |
| mkdir -p /home/runner/.ssh | |
| cp tests/load/filesystem_sftp/bootstrap/bobby_rsa /home/runner/.ssh/id_rsa | |
| cp tests/load/filesystem_sftp/bootstrap/bobby_rsa.pub /home/runner/.ssh/id_rsa.pub | |
| # always run full suite, also on branches | |
| - name: Run tests Linux | |
| run: | | |
| eval "$(ssh-agent -s)" | |
| poetry run pytest tests/load --ignore tests/load/sources | |
| poetry run pytest tests/cli | |
| env: | |
| DESTINATION__POSTGRES__CREDENTIALS: postgresql://loader:loader@localhost:5432/dlt_data | |
| DESTINATION__QDRANT__CREDENTIALS__location: http://localhost:6333 | |
| DESTINATION__FILESYSTEM__CREDENTIALS__SFTP_PORT: 2222 | |
| DESTINATION__FILESYSTEM__CREDENTIALS__SFTP_USERNAME: foo | |
| DESTINATION__FILESYSTEM__CREDENTIALS__SFTP_PASSWORD: pass | |
| - name: Stop weaviate | |
| if: always() | |
| run: docker compose -f "tests/load/weaviate/docker-compose.yml" down -v | |
| - name: Stop SFTP server | |
| if: always() | |
| run: docker compose -f "tests/load/filesystem_sftp/docker-compose.yml" down -v |