Apache Superset: Verify connectivity to CrateDB

Add a few basic integration tests having conversations with the Apache
Superset UI and HTTP API.

.github/workflows/apache-superset.yml

@@ -0,0 +1,75 @@
+name: Apache Superset
+
+on:
+  pull_request:
+    branches: ~
+    paths:
+    - '.github/workflows/apache-superset.yml'
+    - 'framework/apache-superset/**'
+    - 'requirements.txt'
+  push:
+    branches: [ main ]
+    paths:
+    - '.github/workflows/apache-superset.yml'
+    - 'framework/apache-superset/**'
+    - '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:
+
+  tests:
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ ubuntu-22.04 ]
+        superset-spec: [ "<3" ]
+        python-version: [ "3.11" ]
+
+    services:
+      cratedb:
+        image: crate/crate:nightly
+        ports:
+          - 4200:4200
+          - 5432:5432
+
+    name: Python ${{ matrix.python-version }} on OS ${{ matrix.os }}
+    steps:
+
+      - name: Acquire sources
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+          cache: "pip"
+          cache-dependency-path: |
+            pyproject.toml
+            requirements.txt
+            requirements-test.txt
+
+      - name: Install utilities
+        run: |
+          pip install -r requirements.txt
+
+      - name: Install Apache Superset ${{ matrix.superset-spec }}
+        run: |
+          pip install 'apache-superset${{ matrix.superset-spec }}'
+
+      - name: Validate framework/apache-superset
+        run: |
+          ngr test --accept-no-venv framework/apache-superset

.gitignore

@@ -2,7 +2,8 @@
 .venv*
 __pycache__
 .coverage
+.DS_Store
 coverage.xml
 mlruns/
 archive/
-logs.log
+logs.log

framework/apache-superset/README.md

@@ -0,0 +1,58 @@
+# Verify Apache Superset with CrateDB
+
+## About
+
+This folder includes software integration tests for verifying
+that Apache Superset works well together with CrateDB.
+
+## Setup
+
+You can also exercise the configuration and setup steps manually.
+
+Start CrateDB.
+```bash
+docker run --rm -it --name=cratedb \
+  --publish=4200:4200 --publish=5432:5432 \
+  --env=CRATE_HEAP_SIZE=4g crate:latest -Cdiscovery.type=single-node
+```
+
+Setup sandbox and install packages.
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+Configure and initialize Apache Superset.
+```bash
+export FLASK_APP=superset
+export SUPERSET_CONFIG_PATH=superset_config.py
+superset db upgrade
+superset fab create-admin --username=admin --password=admin --firstname=admin --lastname=admin [email protected]
+superset init
+```
+
+Run Superset server.
+```bash
+superset run -p 8088 --with-threads
+open http://127.0.0.1:8088/
+```
+
+## API Usage
+
+```bash
+# Authenticate and acquire a JWT token.
+AUTH_TOKEN=$(http http://localhost:8088/api/v1/security/login username=admin password=admin provider=db | jq -r .access_token)
+
+# Create a data source item / database connection.
+http http://localhost:8088/api/v1/database/ database_name="CrateDB Testdrive" engine=crate sqlalchemy_uri=crate://crate@localhost:4200 Authorization:"Bearer ${AUTH_TOKEN}"
+```
+
+```bash
+# Create datasets and probe them.
+crash < data.sql
+http http://127.0.0.1:8088/api/v1/dataset/ Authorization:"Bearer ${AUTH_TOKEN}" database=1 schema=doc table_name=devices_info
+http http://127.0.0.1:8088/api/v1/dataset/ Authorization:"Bearer ${AUTH_TOKEN}" database=1 schema=doc table_name=devices_readings
+cat probe-1.json | http http://127.0.0.1:8088/api/v1/chart/data Authorization:"Bearer ${AUTH_TOKEN}"
+cat probe-2.json | http http://127.0.0.1:8088/api/v1/chart/data Authorization:"Bearer ${AUTH_TOKEN}"
+```

framework/apache-superset/conftest.py

@@ -0,0 +1,131 @@
+import os
+import shlex
+import shutil
+import subprocess
+import time
+
+import pytest
+import requests
+
+from util import get_auth_headers
+
+
+superset_env = {
+    "FLASK_APP": "superset",
+    "SUPERSET_CONFIG_PATH": "superset_config.py",
+}
+superset_bin = shutil.which("superset")
+
+
+uri_database = "http://localhost:8088/api/v1/database/"
+
+
+# Utility functions.
+
+def invoke_superset(command: str):
+    """
+    Invoke `superset` command.
+    """
+    command = f"{superset_bin} {command}"
+    subprocess.check_call(shlex.split(command), env=superset_env, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+
+
+# Test suite fixtures.
+
+@pytest.fixture(scope="session")
+def fix_greenlet():
+    """
+    Install more recent greenlet, because Playwright installs version 3.0.1, which breaks Superset.
+    """
+    os.system("pip install --upgrade greenlet")
+
+
+@pytest.fixture(scope="session")
+def playwright_install_firefox():
+    """
+    Playwright needs a browser.
+    """
+    os.system("playwright install firefox")
+
+
+@pytest.fixture(scope="session")
+def initialize_superset():
+    """
+    Run the Apache Superset setup procedure.
+    """
+    invoke_superset("db upgrade")
+    invoke_superset("fab create-admin --username=admin --password=admin --firstname=admin --lastname=admin [email protected]")
+    invoke_superset("init")
+
+
+@pytest.fixture(scope="session")
+def reset_superset():
+    """
+    Reset database connections and datasets.
+    """
+    resources_to_delete = [
+        "http://localhost:8088/api/v1/dataset/1",
+        "http://localhost:8088/api/v1/dataset/2",
+        "http://localhost:8088/api/v1/database/1",
+        "http://localhost:8088/api/v1/database/2",
+    ]
+    for resource_to_delete in resources_to_delete:
+        response = requests.delete(resource_to_delete, headers=get_auth_headers())
+        assert response.status_code in [200, 404], response.json()
+
+
+@pytest.fixture(scope="session")
+def start_superset():
+    """
+    Start the Apache Superset server.
+    """
+    command = f"{superset_bin} run -p 8088 --with-threads"
+    daemon = subprocess.Popen(shlex.split(command), env=superset_env, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+    # Give the server time to start
+    time.sleep(4)
+    # Check it started successfully
+    assert not daemon.poll(), daemon.stdout.read().decode("utf-8")
+    yield daemon
+    # Shut it down at the end of the pytest session
+    daemon.terminate()
+
+
+@pytest.fixture(scope="session")
+def provision_superset(start_superset):
+    """
+    Provision Superset by creating a database connection object for CrateDB.
+    """
+
+    # Create a data source item / database connection.
+    response = requests.post(
+        uri_database,
+        headers=get_auth_headers(),
+        json={"database_name": "CrateDB Testdrive", "engine": "crate", "sqlalchemy_uri": "crate://crate@localhost:4200"},
+    )
+
+    assert response.status_code == 201
+    assert response.json() == {
+        "id": 1,
+        "result": {
+            "configuration_method": "sqlalchemy_form",
+            "database_name": "CrateDB Testdrive",
+            "driver": "crate-python",
+            "expose_in_sqllab": True,
+            "sqlalchemy_uri": "crate://crate@localhost:4200",
+        },
+    }
+
+
+@pytest.fixture(scope="session", autouse=True)
+def do_setup(
+        fix_greenlet,
+        playwright_install_firefox,
+        initialize_superset,
+        start_superset,
+        reset_superset,
+        provision_superset,
+):
+    """
+    Provide a fully configured and provisioned Apache Superset instance to the test suite.
+    """
+    pass

framework/apache-superset/data.sql

@@ -0,0 +1,36 @@
+-- https://github.com/crate/cratedb-datasets
+
+CREATE TABLE IF NOT EXISTS devices_readings (
+   "ts" TIMESTAMP WITH TIME ZONE,
+   "device_id" TEXT,
+   "battery" OBJECT(DYNAMIC) AS (
+      "level" BIGINT,
+      "status" TEXT,
+      "temperature" DOUBLE PRECISION
+   ),
+   "cpu" OBJECT(DYNAMIC) AS (
+      "avg_1min" DOUBLE PRECISION,
+      "avg_5min" DOUBLE PRECISION,
+      "avg_15min" DOUBLE PRECISION
+   ),
+   "memory" OBJECT(DYNAMIC) AS (
+      "free" BIGINT,
+      "used" BIGINT
+   )
+);
+
+CREATE TABLE IF NOT EXISTS devices_info (
+    "device_id" TEXT,
+    "api_version" TEXT,
+    "manufacturer" TEXT,
+    "model" TEXT,
+    "os_name" TEXT
+);
+
+COPY "devices_readings"
+  FROM 'https://github.com/crate/cratedb-datasets/raw/main/cloud-tutorials/devices_readings.json.gz'
+  WITH (compression = 'gzip');
+
+COPY "devices_info"
+  FROM 'https://github.com/crate/cratedb-datasets/raw/main/cloud-tutorials/devices_info.json.gz'
+  WITH (compression = 'gzip');

framework/apache-superset/pyproject.toml

@@ -0,0 +1,11 @@
+[tool.pytest.ini_options]
+minversion = "2.0"
+addopts = """
+  -rfEXs -p pytester --strict-markers --verbosity=3
+  """
+log_level = "DEBUG"
+log_cli_level = "DEBUG"
+testpaths = ["*.py"]
+xfail_strict = true
+markers = [
+]

framework/apache-superset/requirements-test.txt

@@ -0,0 +1,3 @@
+playwright<2
+pytest<8
+requests<3

framework/apache-superset/requirements.txt

@@ -0,0 +1,3 @@
+apache-superset<3
+crate[sqlalchemy]==0.34.0
+marshmallow_enum<2  # Seems to be missing from `apache-superset`?

framework/apache-superset/superset_config.py

@@ -0,0 +1,32 @@
+# Superset specific config
+ROW_LIMIT = 5000
+
+# Flask App Builder configuration
+# Your App secret key will be used for securely signing the session cookie
+# and encrypting sensitive information on the database
+# Make sure you are changing this key for your deployment with a strong key.
+# Alternatively you can set it with `SUPERSET_SECRET_KEY` environment variable.
+# You MUST set this for production environments or the server will not refuse
+# to start and you will see an error in the logs accordingly.
+SECRET_KEY = 'VcKzHS4g2h+dP33tCbqOghtKaU37wvFECMhVqrfccaoI/17qh/j3+VDV'
+
+# The SQLAlchemy connection string to your database backend
+# This connection defines the path to the database that stores your
+# superset metadata (slices, connections, tables, dashboards, ...).
+# Note that the connection information to connect to the datasources
+# you want to explore are managed directly in the web UI
+# The check_same_thread=false property ensures the sqlite client does not attempt
+# to enforce single-threaded access, which may be problematic in some edge cases
+# When not configured, the default location is `~/.superset/superset.db`.
+# See also https://superset.apache.org/docs/installation/configuring-superset/.
+# SQLALCHEMY_DATABASE_URI = 'sqlite:////path/to/superset.db?check_same_thread=false'
+
+# Flask-WTF flag for CSRF
+WTF_CSRF_ENABLED = True
+# Add endpoints that need to be exempt from CSRF protection
+WTF_CSRF_EXEMPT_LIST = []
+# A CSRF token that expires in 1 year
+WTF_CSRF_TIME_LIMIT = 60 * 60 * 24 * 365
+
+# Set this API key to enable Mapbox visualizations
+MAPBOX_API_KEY = ''