python-testing

Imported from KaustubhLall/agent-toolkit (plugins/ecc-workbench/library/skills/python-testing/SKILL.md). Install upstream with npx skills add KaustubhLall/agent-toolkit --skill python-testing. Copyright stays with the author.

Python Testing Patterns

Comprehensive testing strategies for Python applications using pytest, TDD methodology, and best practices.

When to Activate

• Writing new Python code (follow TDD: red, green, refactor)
• Designing test suites for Python projects
• Reviewing Python test coverage
• Setting up testing infrastructure

Core Testing Philosophy

Test-Driven Development (TDD)

Always follow the TDD cycle:

1. RED: Write a failing test for the desired behavior
2. GREEN: Write minimal code to make the test pass
3. REFACTOR: Improve code while keeping tests green

# Step 1: Write failing test (RED)
def test_add_numbers():
    result = add(2, 3)
    assert result == 5

# Step 2: Write minimal implementation (GREEN)
def add(a, b):
    return a + b

# Step 3: Refactor if needed (REFACTOR)

Coverage Requirements

• Target: 80%+ code coverage
• Critical paths: 100% coverage required
• Use pytest --cov to measure coverage

pytest --cov=mypackage --cov-report=term-missing --cov-report=html

pytest Fundamentals

Basic Test Structure

import pytest

def test_addition():
    """Test basic addition."""
    assert 2 + 2 == 4

def test_string_uppercase():
    """Test string uppercasing."""
    text = "hello"
    assert text.upper() == "HELLO"

def test_list_append():
    """Test list append."""
    items = [1, 2, 3]
    items.append(4)
    assert 4 in items
    assert len(items) == 4

Assertions

# Equality
assert result == expected

# Inequality
assert result != unexpected

# Truthiness
assert result  # Truthy
assert not result  # Falsy
assert result is True  # Exactly True
assert result is False  # Exactly False
assert result is None  # Exactly None

# Membership
assert item in collection
assert item not in collection

# Comparisons
assert result > 0
assert 0 <= result <= 100

# Type checking
assert isinstance(result, str)

# Exception testing (preferred approach)
with pytest.raises(ValueError):
    raise ValueError("error message")

# Check exception message
with pytest.raises(ValueError, match="invalid input"):
    raise ValueError("invalid input provided")

# Check exception attributes
with pytest.raises(ValueError) as exc_info:
    raise ValueError("error message")
assert str(exc_info.value) == "error message"

Fixtures

Basic Fixture Usage

import pytest

@pytest.fixture
def sample_data():
    """Fixture providing sample data."""
    return {"name": "Alice", "age": 30}

def test_sample_data(sample_data):
    """Test using the fixture."""
    assert sample_data["name"] == "Alice"
    assert sample_data["age"] == 30

Fixture with Setup/Teardown

@pytest.fixture
def database():
    """Fixture with setup and teardown."""
    # Setup
    db = Database(":memory:")
    db.create_tables()
    db.insert_test_data()

    yield db  # Provide to test

    # Teardown
    db.close()

def test_database_query(database):
    """Test database operations."""
    result = database.query("SELECT * FROM users")
    assert len(result) > 0

Fixture Scopes

# Function scope (default) - runs for each test
@pytest.fixture
def temp_file():
    with open("temp.txt", "w") as f:
        yield f
    os.remove("temp.txt")

# Module scope - runs once per module
@pytest.fixture(scope="module")
def module_db():
    db = Database(":memory:")
    db.create_tables()
    yield db
    db.close()

# Session scope - runs once per test session
@pytest.fixture(scope="session")
def shared_resource():
    resource = ExpensiveResource()
    yield resource
    resource.cleanup()

Fixture with Parameters

@pytest.fixture(params=[1, 2, 3])
def number(request):
    """Parameterized fixture."""
    return request.param

def test_numbers(number):
    """Test runs 3 times, once for each parameter."""
    assert number > 0

Using Multiple Fixtures

@pytest.fixture
def user():
    return User(id=1, name="Alice")

@pytest.fixture
def admin():
    return User(id=2, name="Admin", role="admin")

def test_user_admin_interaction(user, admin):
    """Test using multiple fixtures."""
    assert admin.can_manage(user)

Autouse Fixtures

@pytest.fixture(autouse=True)
def reset_config():
    """Automatically runs before every test."""
    Config.reset()
    yield
    Config.cleanup()

def test_without_fixture_call():
    # reset_config runs automatically
    assert Config.get_setting("debug") is False

Conftest.py for Shared Fixtures

# tests/conftest.py
import pytest

@pytest.fixture
def client():
    """Shared fixture for all tests."""
    app = create_app(testing=True)
    with app.test_client() as client:
        yield client

@pytest.fixture
def auth_headers(client):
    """Generate auth headers for API testing."""
    response = client.post("/api/login", json={
        "username": "test",
        "password": "test"
    })
    token = response.json["token"]
    return {"Authorization": f"Bearer {token}"}

Parametrization

Basic Parametrization

@pytest.mark.parametrize("input,expected", [
    ("hello", "HELLO"),
    ("world", "WORLD"),
    ("PyThOn", "PYTHON"),
])
def test_uppercase(input, expected):
    """Test runs 3 times with different inputs."""
    assert input.upper() == expected

Multiple Parameters

@pytest.mark.parametrize("a,b,expected", [
    (2, 3, 5),
    (0, 0, 0),
    (-1, 1, 0),
    (100, 200, 300),
])
def test_add(a, b, expected):
    """Test addition with multiple inputs."""
    assert add(a, b) == expected

Parametrize with IDs

@pytest.mark.parametrize("input,expected", [
    ("valid@email.com", True),
    ("invalid", False),
    ("@no-domain.com", False),
], ids=["valid-email", "missing-at", "missing-domain"])
def test_email_validation(input, expected):
    """Test email validation with readable test IDs."""
    assert is_valid_email(input) is expected

Parametrized Fixtures

@pytest.fixture(params=["sqlite", "postgresql", "mysql"])
def db(request):
    """Test against multiple database backends."""
    if request.param == "sqlite":
        return Database(":memory:")
    elif request.param == "postgresql":
        return Database("postgresql://localhost/test")
    elif request.param == "mysql":
        return Database("mysql://localhost/test")

def test_database_operations(db):
    """Test runs 3 times, once for each database."""
    result = db.query("SELECT 1")
    assert result is not None

Markers and Test Selection

Custom Markers

# Mark slow tests
@pytest.mark.slow
def test_slow_operation():
    time.sleep(5)

# Mark integration tests
@pytest.mark.integration
def test_api_integration():
    response = requests.get("https://api.example.com")
    assert response.status_code == 200

# Mark unit tests
@pytest.mark.unit
def test_unit_logic():
    assert calculate(2, 3) == 5

Run Specific Tests

# Run only fast tests
pytest -m "not slow"

# Run only integration tests
pytest -m integration

# Run integration or slow tests
pytest -m "integration or slow"

# Run tests marked as unit but not slow
pytest -m "unit and not slow"

Configure Markers in pytest.ini

[pytest]
markers =
    slow: marks tests as slow
    integration: marks tests as integration tests
    unit: marks tests as unit tests
    django: marks tests as requiring Django

Mocking and Patching

Mocking Functions

from unittest.mock import patch, Mock

@patch("mypackage.external_api_call")
def test_with_mock(api_call_mock):
    """Test with mocked external API."""
    api_call_mock.return_value = {"status": "success"}

    result = my_function()

    api_call_mock.assert_called_once()
    assert result["status"] == "success"

Mocking Return Values

@patch("mypackage.Database.connect")
def test_database_connection(connect_mock):
    """Test with mocked database connection."""
    connect_mock.return_value = MockConnection()

    db = Database()
    db.connect()

    connect_mock.assert_called_once_with("localhost")

Mocking Exceptions

@patch("mypackage.api_call")
def test_api_error_handling(api_call_mock):
    """Test error handling with mocked exception."""
    api_call_mock.side_effect = ConnectionError("Network error")

    with pytest.raises(ConnectionError):
        api_call()

    api_call_mock.assert_called_once()

Mocking Context Managers

@patch("builtins.open", new_callable=mock_open)
def test_file_reading(mock_file):
    """Test file reading with mocked open."""
    mock_file.return_value.read.return_value = "file content"

    result = read_file("test.txt")

    mock_file.assert_called_once_with("test.txt", "r")
    assert result == "file content"

Using Autospec

@patch("mypackage.DBConnection", autospec=True)
def test_autospec(db_mock):
    """Test with autospec to catch API misuse."""
    db = db_mock.return_value
    db.query("SELECT * FROM users")

    # This would fail if DBConnection doesn't have query method
    db_mock.assert_called_once()

Mock Class Instances

class TestUserService:
    @patch("mypackage.UserRepository")
    def test_create_user(self, repo_mock):
        """Test user creation with mocked repository."""
        repo_mock.return_value.save.return_value = User(id=1, name="Alice")

        service = UserService(repo_mock.return_value)
        user = service.create_user(name="Alice")

        assert user.name == "Alice"
        repo_mock.return_value.save.assert_called_once()

Mock Property

@pytest.fixture
def mock_config():
    """Create a mock with a property."""
    config = Mock()
    type(config).debug = PropertyMock(return_value=True)
    type(config).api_key = PropertyMock(return_value="test-key")
    return config

def test_with_mock_config(mock_config):
    """Test with mocked config properties."""
    assert mock_config.debug is True
    assert mock_config.api_key == "test-key"

Testing Async Code

Async Tests with pytest-asyncio

import pytest

@pytest.mark.asyncio
async def test_async_function():
    """Test async function."""
    result = await async_add(2, 3)
    assert result == 5

@pytest.mark.asyncio
async def test_async_with_fixture(async_client):
    """Test async with async fixture."""
    response = await async_client.get("/api/users")
    assert response.status_code == 200

Async Fixture

@pytest.fixture
async def async_client():
    """Async fixture providing async test client."""
    app = create_app()
    async with app.test_client() as client:
        yield client

@pytest.mark.asyncio
async def test_api_endpoint(async_client):
    """Test using async fixture."""
    response = await async_client.get("/api/data")
    assert response.status_code == 200

Mocking Async Functions

@pytest.mark.asyncio
@patch("mypackage.async_api_call")
async def test_async_mock(api_call_mock):
    """Test async function with mock."""
    api_call_mock.return_value = {"status": "ok"}

    result = await my_async_function()

    api_call_mock.assert_awaited_once()
    assert result["status"] == "ok"

Testing Exceptions

Testing Expected Exceptions

def test_divide_by_zero():
    """Test that dividing by zero raises ZeroDivisionError."""
    with pytest.raises(ZeroDivisionError):
        divide(10, 0)

def test_custom_exception():
    """Test custom exception with message."""
    with pytest.raises(ValueError, match="invalid input"):
        validate_input("invalid")

Testing Exception Attributes

def test_exception_with_details():
    """Test exception with custom attributes."""
    with pytest.raises(CustomError) as exc_info:
        raise CustomError("error", code=400)

    assert exc_info.value.code == 400
    assert "error" in str(exc_info.value)

Testing Side Effects

Testing File Operations

import tempfile
import os

def test_file_processing():
    """Test file processing with temp file."""
    with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt') as f:
        f.write("test content")
        temp_path = f.name

    try:
        result = process_file(temp_path)
        assert result == "processed: test content"
    finally:
        os.unlink(temp_path)

Testing with pytest's tmp_path Fixture

def test_with_tmp_path(tmp_path):
    """Test using pytest's built-in temp path fixture."""
    test_file = tmp_path / "test.txt"
    test_file.write_text("hello world")

    result = process_file(str(test_file))
    assert result == "hello world"
    # tmp_path automatically cleaned up

Testing with tmpdir Fixture

def test_with_tmpdir(tmpdir):
    """Test using pytest's tmpdir fixture."""
    test_file = tmpdir.join("test.txt")
    test_file.write("data")

    result = process_file(str(test_file))
    assert result == "data"

Test Organization

Directory Structure

tests/
├── conftest.py                 # Shared fixtures
├── __init__.py
├── unit/                       # Unit tests
│   ├── __init__.py
│   ├── test_models.py
│   ├── test_utils.py
│   └── test_services.py
├── integration/                # Integration tests
│   ├── __init__.py
│   ├── test_api.py
│   └── test_database.py
└── e2e/                        # End-to-end tests
    ├── __init__.py
    └── test_user_flow.py

Test Classes

class TestUserService:
    """Group related tests in a class."""

    @pytest.fixture(autouse=True)
    def setup(self):
        """Setup runs before each test in this class."""
        self.service = UserService()

    def test_create_user(self):
        """Test user creation."""
        user = self.service.create_user("Alice")
        assert user.name == "Alice"

    def test_delete_user(self):
        """Test user deletion."""
        user = User(id=1, name="Bob")
        self.service.delete_user(user)
        assert not self.service.user_exists(1)

Best Practices

DO

• Follow TDD: Write tests before code (red-green-refactor)
• Test one thing: Each test should verify a single behavior
• Use descriptive names: test_user_login_with_invalid_credentials_fails
• Use fixtures: Eliminate duplication with fixtures
• Mock external dependencies: Don't depend on external services
• Test edge cases: Empty inputs, None values, boundary conditions
• Aim for 80%+ coverage: Focus on critical paths
• Keep tests fast: Use marks to separate slow tests

DON'T

• Don't test implementation: Test behavior, not internals
• Don't use complex conditionals in tests: Keep tests simple
• Don't ignore test failures: All tests must pass
• Don't test third-party code: Trust libraries to work
• Don't share state between tests: Tests should be independent
• Don't catch exceptions in tests: Use pytest.raises
• Don't use print statements: Use assertions and pytest output
• Don't write tests that are too brittle: Avoid over-specific mocks

Common Patterns

Testing API Endpoints (FastAPI/Flask)

@pytest.fixture
def client():
    app = create_app(testing=True)
    return app.test_client()

def test_get_user(client):
    response = client.get("/api/users/1")
    assert response.status_code == 200
    assert response.json["id"] == 1

def test_create_user(client):
    response = client.post("/api/users", json={
        "name": "Alice",
        "email": "alice@example.com"
    })
    assert response.status_code == 201
    assert response.json["name"] == "Alice"

Testing Database Operations

@pytest.fixture
def db_session():
    """Create a test database session."""
    session = Session(bind=engine)
    session.begin_nested()
    yield session
    session.rollback()
    session.close()

def test_create_user(db_session):
    user = User(name="Alice", email="alice@example.com")
    db_session.add(user)
    db_session.commit()

    retrieved = db_session.query(User).filter_by(name="Alice").first()
    assert retrieved.email == "alice@example.com"

Testing Class Methods

class TestCalculator:
    @pytest.fixture
    def calculator(self):
        return Calculator()

    def test_add(self, calculator):
        assert calculator.add(2, 3) == 5

    def test_divide_by_zero(self, calculator):
        with pytest.raises(ZeroDivisionError):
            calculator.divide(10, 0)

pytest Configuration

pytest.ini

[pytest]
testpaths = tests
python_files = test_*.py
python_classes = Test*
python_functions = test_*
addopts =
    --strict-markers
    --disable-warnings
    --cov=mypackage
    --cov-report=term-missing
    --cov-report=html
markers =
    slow: marks tests as slow
    integration: marks tests as integration tests
    unit: marks tests as unit tests

pyproject.toml

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
addopts = [
    "--strict-markers",
    "--cov=mypackage",
    "--cov-report=term-missing",
    "--cov-report=html",
]
markers = [
    "slow: marks tests as slow",
    "integration: marks tests as integration tests",
    "unit: marks tests as unit tests",
]

Running Tests

# Run all tests
pytest

# Run specific file
pytest tests/test_utils.py

# Run specific test
pytest tests/test_utils.py::test_function

# Run with verbose output
pytest -v

# Run with coverage
pytest --cov=mypackage --cov-report=html

# Run only fast tests
pytest -m "not slow"

# Run until first failure
pytest -x

# Run and stop on N failures
pytest --maxfail=3

# Run last failed tests
pytest --lf

# Run tests with pattern
pytest -k "test_user"

# Run with debugger on failure
pytest --pdb

Quick Reference

Remember: Tests are code too. Keep them clean, readable, and maintainable. Good tests catch bugs; great tests prevent them.