Support DuckDB Dialect

.github/workflows/databricks_testing.yml

@@ -37,8 +37,8 @@ jobs:
       - name: Install dependencies
         run: uv pip install -e ".[databricks]"
 
-      - name: Run DEFOG refresh if stale (locked by date)
-        run: uv run python -m tests.gen_data.databricks_task
+      - name: Run DEFOG refresh
+        run: uv run python -m tests.gen_data.databricks_task --force
 
   databricks-tests:
     name: Databricks Tests (Python ${{ matrix.python-version }})

.github/workflows/duckdb_testing.yml

@@ -0,0 +1,47 @@
+name: Run DuckDB Tests
+
+on:
+  workflow_call:
+    inputs:
+      python-versions:
+        description: "JSON string of Python versions"
+        type: string
+        required: true
+
+jobs:
+  duckdb-tests:
+    name: DuckDB Tests (Python ${{ matrix.python-version }})
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ${{ fromJSON(inputs.python-versions) }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python ${{ matrix.python-version }}
+        id: setup-python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "0.6.0"
+
+      - name: Create virtual environment
+        # See sf_testing.yml on why we use `uv venv`
+        run: uv venv
+
+      - name: Install dependencies
+        run: uv pip install -e ".[duckdb]"
+
+      - name: Confirm DuckDB connector is installed
+        run: uv run python -c "import duckdb; print('DuckDB connector installed')"
+
+      - name: Download TPCH DB
+        run: ./demos/setup_tpch.sh ./tpch.db
+
+      - name: Run DuckDB Tests
+        run: uv run pytest -m duckdb tests/ -rs

.github/workflows/pr_testing.yml

@@ -61,6 +61,11 @@ on:
         type: boolean
         required: false
         default: false        
+      run-duckdb:
+        description: "Run DuckDB Tests"
+        type: boolean
+        required: false
+        default: false        
       run-sf_masked:
         description: "Run Snowflake Masked Tests"
         type: boolean
@@ -181,10 +186,10 @@ jobs:
         run: uv run ruff check .
 
       - name: Run Tests
-        run: uv run pytest tests/ -m "not (snowflake or mysql or postgres or sf_masked or s3 or bodosql or oracle or trino or databricks)" -rs
+        run: uv run pytest tests/ -m "not (snowflake or mysql or postgres or sf_masked or s3 or bodosql or oracle or trino or databricks or duckdb)" -rs
 
-  run-defog-daily-update:
-    name: Run DEFOG Daily Update
+  run-sf-defog-daily-update:
+    name: Run Snowflake DEFOG Daily Update
     needs: [get-msg]
     if: |
       (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run all]')) ||
@@ -199,7 +204,7 @@ jobs:
 
   run-sf-tests:
     name: Snowflake Tests
-    needs: [run-defog-daily-update, get-msg, get-py-ver-matrix]
+    needs: [run-sf-defog-daily-update, get-msg, get-py-ver-matrix]
     if: |
       (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run all]')) ||
       (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run dialects]')) ||
@@ -365,3 +370,17 @@ jobs:
       python-versions: ${{ github.event_name == 'workflow_dispatch'
                       && needs.get-py-ver-matrix.outputs.matrix
                       || '["3.11", "3.12", "3.13"]' }}
+
+  run-duckdb-tests:
+    name: DuckDB Tests
+    needs: [get-msg, get-py-ver-matrix]
+    if: |
+      (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run all]')) ||
+      (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run dialects]')) ||
+      (github.event_name == 'pull_request' && contains(needs.get-msg.outputs.commitMsg, '[run duckdb]')) ||
+      (github.event_name == 'workflow_dispatch' && (inputs.run-all || inputs.run-dialects || inputs.run-duckdb))
+    uses: ./.github/workflows/duckdb_testing.yml
+    with:
+      python-versions: ${{ github.event_name == 'workflow_dispatch'
+                      && needs.get-py-ver-matrix.outputs.matrix
+                      || '["3.11", "3.12", "3.13"]' }}

README.md

@@ -185,7 +185,48 @@ To run **Trino CI tests**, add the flag `[run trino]` to your commit message.
         export MONGO_USER="your_username"
         export MONGO_PASSWORD="your_password"
     ```
+## Running Oracle Tests on CI
+To run **Oracle CI tests**, add the flag `[run oracle]` to your commit message.
 
+**Running Oracle tests locally:**
+1. Make sure you have [**Docker Desktop**](https://www.docker.com/get-started/)
+ installed and running.
+2. Install the Oracle Connector for Python
+    ```bash
+    pip install oracledb
+    ```
+3. Set your Oracle credentials as environment variables:
+    ```bash
+        export ORACLE_PASSWORD="your_password"
+    ``` 
+## Running Databricks Tests on CI
+To run **Databricks CI tests**, add the flag `[run databricks]` to your commit message.
+
+**Running Databricks tests locally:**
+
+1. Install the Databricks Connector for Python with Pandas support
+    ```bash
+    pip install databricks-sql-connector"
+    ```
+
+2. Set your Databricks credentials as environment variables:
+    ```bash
+        export DATABRICKS_HOST="databricks_instance"
+        export DATABRICKS_HTTP_PATH="server_http_path"
+        export DATABRICKS_TOKEN="databricks_token"
+    ```
+
+## Running DuckDB Tests on CI
+To run **DuckDB CI tests**, add the flag `[run duckdb]` to your commit message.
+
+** Running DuckDB tests locally:**
+1. Install the DuckDB Connector for Python with Pandas support
+    ```bash
+    pip install duckdb
+    ```
+2. DuckDB does not require any additional environment variables to be set up for testing.
+
+3. DuckDB TPC-H and Defog tests require the `tpch.db` and `defog.db` files to be located in the `tests` directory. Please refer to the sqlite setup instructions above for more information on how to set up these files.
 
 ## Runtime Dependencies
 

demos/README.md

@@ -30,4 +30,4 @@ Once the introduction notebook is complete, you can explore the other notebooks:
 - [Oracle_TPCH.ipynb](notebooks/Oracle_TPCH.ipynb) demonstrates how to connect an Oracle database with PyDough.
 - [Databricks_TPCH.ipynb](notebooks/Databricks_TPCH.ipynb) demonstrates how to connect a Databricks database with PyDough.
 - [Trino_TPCH.ipynb](notebooks/Trino_TPCH.ipynb) demonstrates how to connect a Trino database with PyDough.
-
+- [DuckDB_TPCH.ipynb](notebooks/DuckDB_TPCH.ipynb) demonstrates how to connect a DuckDB database with PyDough.