Dataframe/Polars: Add test wrapper and CI configuration

Author: amotl

.github/dependabot.yml

@@ -33,6 +33,11 @@ updates:
     schedule:
       interval: "daily"
 
+  - directory: "/by-dataframe/polars"
+    package-ecosystem: "pip"
+    schedule:
+      interval: "daily"
+
   - directory: "/by-language/csharp-efcore"
     package-ecosystem: "nuget"
     schedule:

.github/workflows/dataframe-polars.yml

@@ -0,0 +1,74 @@
+name: Polars
+
+on:
+  pull_request:
+    paths:
+    - '.github/workflows/dataframe-polars.yml'
+    - 'by-dataframe/polars/**'
+    - '/requirements.txt'
+  push:
+    branches: [ main ]
+    paths:
+    - '.github/workflows/dataframe-polars.yml'
+    - 'by-dataframe/polars/**'
+    - '/requirements.txt'
+
+  # Allow job to be triggered manually.
+  workflow_dispatch:
+
+  # Run job each night after CrateDB nightly has been published.
+  schedule:
+    - cron: '0 3 * * *'
+
+# Cancel in-progress jobs when pushing to the same branch.
+concurrency:
+  cancel-in-progress: true
+  group: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  test:
+    name: "
+     Python: ${{ matrix.python-version }}
+     CrateDB: ${{ matrix.cratedb-version }}
+     on ${{ matrix.os }}"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ 'ubuntu-latest' ]
+        python-version: [
+          '3.10',
+          '3.13',
+        ]
+        cratedb-version: [ 'nightly' ]
+
+    services:
+      cratedb:
+        image: crate/crate:${{ matrix.cratedb-version }}
+        ports:
+          - 4200:4200
+          - 5432:5432
+        env:
+          CRATE_HEAP_SIZE: 4g
+
+    steps:
+
+      - name: Acquire sources
+        uses: actions/checkout@v5
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+          cache: 'pip'
+          cache-dependency-path: |
+            by-dataframe/polars/requirements.txt
+            by-dataframe/polars/requirements-dev.txt
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v7
+
+      - name: Validate by-dataframe/polars
+        run: |
+          uv run --with=pueblo ngr test --accept-no-venv by-dataframe/polars

by-dataframe/polars/README.md

@@ -0,0 +1,32 @@
+# Connect to CrateDB and CrateDB Cloud using Polars
+
+## About
+
+Example programs demonstrating connectivity with [Polars] and [CrateDB].
+
+## Usage
+
+```shell
+python read_pg.py
+python read_sqlalchemy.py
+python write_pg.py
+python write_sqlalchemy.py
+python write_adbc.py
+python one_db_to_another.py
+```
+
+> [!TIP]
+> For more information, please refer to the header sections of each of the
+provided example programs.
+
+## Tests
+
+To test the accompanied example programs all at once, invoke the software tests:
+```shell
+pytest
+```
+
+
+[CrateDB]: https://github.com/crate/crate
+[CrateDB Cloud]: https://console.cratedb.cloud/
+[Polars]: https://pola.rs/

by-dataframe/polars/pyproject.toml

@@ -0,0 +1,24 @@
+[tool.pytest.ini_options]
+minversion = "2.0"
+addopts = """
+  -rfEX -p pytester --strict-markers --verbosity=3
+  --cov --cov-report=term-missing
+  --capture=no
+  """
+log_level = "DEBUG"
+log_cli_level = "DEBUG"
+testpaths = ["*.py"]
+xfail_strict = true
+markers = [
+]
+
+
+[tool.coverage.run]
+branch = false
+omit = [
+    "test*",
+]
+
+[tool.coverage.report]
+fail_under = 0
+show_missing = true

by-dataframe/polars/requirements-test.txt

@@ -0,0 +1,2 @@
+pytest<9
+pytest-cov<8

by-dataframe/polars/requirements.txt

@@ -0,0 +1,6 @@
+adbc-driver-postgresql<1.9
+connectorx>=0.4.5a1
+pandas<2.4
+polars<1.36
+pyarrow<23
+sqlalchemy-cratedb>=0.42.0.dev2

by-dataframe/polars/test.py

@@ -0,0 +1,57 @@
+import shlex
+import subprocess
+import pytest
+import sqlalchemy as sa
+
+
+DBURI = "crate://localhost:4200"
+
+
+def run(command: str):
+    subprocess.check_call(shlex.split(command))
+
+
+def test_read_pg():
+    cmd = "time python read_pg.py"
+    run(cmd)
+
+
+def test_read_sqlalchemy():
+    cmd = "time python read_sqlalchemy.py"
+    run(cmd)
+
+
+@pytest.mark.skip
+def test_write_adbc(reset_table):
+    cmd = "time python write_adbc.py"
+    run(cmd)
+    assert get_table_cardinality() == 20
+
+
+def test_write_sqlalchemy(reset_table):
+    cmd = "time python write_sqlalchemy.py"
+    run(cmd)
+    assert get_table_cardinality() == 20
+
+
+@pytest.fixture
+def reset_table():
+    """Drop database tables used for testing."""
+    engine = get_engine()
+    with engine.connect() as conn:
+        conn.exec_driver_sql("DROP TABLE IF EXISTS testdrive_polars;")
+
+
+def get_engine():
+    """Provide an SQLAlchemy `engine` instance."""
+    return sa.create_engine(DBURI)
+
+
+def get_table_cardinality():
+    """Get number of records in table used for testing."""
+    engine = get_engine()
+    with engine.connect() as conn:
+        conn.exec_driver_sql("REFRESH TABLE testdrive_polars;")
+        result = conn.exec_driver_sql("SELECT COUNT(*) FROM testdrive_polars;")
+        table_size = result.scalar_one()
+        return table_size