Functional testing

Running functional tests

Run functional tests

# Run TYPO3 functional tests
Build/Scripts/runTests.sh -s functional

# Alternative: Via Composer script
composer ci:test:php:functional

Functional test example

Example: Functional test

<?php

namespace Netresearch\NrLlm\Tests\Functional\Repository;

use Netresearch\NrLlm\Domain\Model\Provider;
use Netresearch\NrLlm\Domain\Repository\ProviderRepository;
use TYPO3\TestingFramework\Core\Functional\FunctionalTestCase;

class ProviderRepositoryTest extends FunctionalTestCase
{
    protected array $testExtensionsToLoad = [
        'netresearch/nr-llm',
    ];

    private ProviderRepository $repository;

    protected function setUp(): void
    {
        parent::setUp();
        $this->repository = $this->get(ProviderRepository::class);
    }

    public function testFindOneByIdentifierReturnsProvider(): void
    {
        $this->importCSVDataSet(__DIR__ . '/Fixtures/providers.csv');

        $provider = $this->repository->findOneByIdentifier('openai-test');

        $this->assertInstanceOf(Provider::class, $provider);
        $this->assertEquals('OpenAI Test', $provider->getName());
    }
}

Test fixtures

CSV fixtures

Tests/Functional/Fixtures/providers.csv

"tx_nrllm_provider"
"uid","pid","identifier","name","adapter_type","is_active"
1,0,"openai-test","OpenAI Test","openai",1

JSON response fixtures

Tests/Fixtures/openai_chat_response.json

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Test response"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 5,
    "total_tokens": 15
  }
}

Mutation testing

The extension uses Infection for mutation testing to ensure test quality.

Running mutation tests

Run mutation tests

# Run mutation tests via runTests.sh
Build/Scripts/runTests.sh -s mutation

# Alternative: Via Composer script
composer ci:test:php:mutation

Interpreting results

MSI (Mutation Score Indicator): Percentage of mutations killed.
Target: >60% MSI indicates good test quality.
Current: 58% MSI (459 tests).

Mutation testing results

Mutation Score Indicator (MSI): 58%
Mutation Code Coverage: 85%
Covered Code MSI: 68%

Best practices

Isolate tests: Each test should be independent.
Mock external APIs: Never call real APIs in unit tests.
Use data providers: For testing multiple scenarios.
Test edge cases: Empty inputs, null values, boundaries.
Descriptive names: Test method names should describe behavior.
Arrange-Act-Assert: Follow AAA pattern.
Fast tests: Unit tests should complete in milliseconds.
Coverage goals: Aim for >80% line coverage.