tikker/tests/test_performance.py

"""
Performance Testing for Tikker Services

Measures response times, throughput, and resource usage.
Identifies bottlenecks and optimization opportunities.
"""

import pytest
import time
import json
from typing import Dict, List, Tuple
import statistics


class PerformanceMetrics:
    """Collect and analyze performance metrics."""
    
    def __init__(self):
        self.measurements: Dict[str, List[float]] = {}
    
    def record(self, name: str, value: float):
        """Record a measurement."""
        if name not in self.measurements:
            self.measurements[name] = []
        self.measurements[name].append(value)
    
    def summary(self, name: str) -> Dict[str, float]:
        """Get summary statistics for measurements."""
        if name not in self.measurements:
            return {}
        
        values = self.measurements[name]
        return {
            "count": len(values),
            "min": min(values),
            "max": max(values),
            "avg": statistics.mean(values),
            "median": statistics.median(values),
            "stdev": statistics.stdev(values) if len(values) > 1 else 0
        }


@pytest.fixture
def metrics():
    """Provide metrics collector."""
    return PerformanceMetrics()


class TestAPIPerformance:
    """Tests for API performance characteristics."""
    
    def test_health_check_latency(self, api_client, metrics):
        """Measure health check endpoint latency."""
        if not api_client:
            pytest.skip("API client not available")
        
        for _ in range(10):
            start = time.time()
            response = api_client.get("/health")
            elapsed = (time.time() - start) * 1000
            
            assert response.status_code == 200
            metrics.record("health_check_latency", elapsed)
        
        summary = metrics.summary("health_check_latency")
        assert summary["avg"] < 100, "Health check should be < 100ms"
        assert summary["max"] < 500, "Health check max should be < 500ms"
    
    def test_daily_stats_latency(self, api_client, metrics):
        """Measure daily stats endpoint latency."""
        if not api_client:
            pytest.skip("API client not available")
        
        for _ in range(5):
            start = time.time()
            response = api_client.get("/api/stats/daily")
            elapsed = (time.time() - start) * 1000
            
            if response.status_code == 200:
                metrics.record("daily_stats_latency", elapsed)
        
        if "daily_stats_latency" in metrics.measurements:
            summary = metrics.summary("daily_stats_latency")
            assert summary["avg"] < 200, "Daily stats should be < 200ms"
    
    def test_top_words_latency(self, api_client, metrics):
        """Measure top words endpoint latency."""
        if not api_client:
            pytest.skip("API client not available")
        
        for limit in [10, 50, 100]:
            for _ in range(3):
                start = time.time()
                response = api_client.get(f"/api/words/top?limit={limit}")
                elapsed = (time.time() - start) * 1000
                
                if response.status_code == 200:
                    metrics.record(f"top_words_latency_{limit}", elapsed)
        
        for limit in [10, 50, 100]:
            key = f"top_words_latency_{limit}"
            if key in metrics.measurements:
                summary = metrics.summary(key)
                assert summary["avg"] < 500, f"Top words (limit={limit}) should be < 500ms"
    
    def test_concurrent_requests(self, api_client, metrics):
        """Test API under concurrent load."""
        if not api_client:
            pytest.skip("API client not available")
        
        endpoints = [
            "/health",
            "/api/stats/daily",
            "/api/words/top?limit=10"
        ]
        
        times = []
        for endpoint in endpoints:
            start = time.time()
            response = api_client.get(endpoint)
            elapsed = (time.time() - start) * 1000
            times.append(elapsed)
            
            if response.status_code == 200:
                metrics.record("concurrent_request_latency", elapsed)
        
        avg_time = statistics.mean(times)
        assert avg_time < 300, "Average concurrent request latency should be < 300ms"


class TestAIPerformance:
    """Tests for AI service performance."""
    
    def test_health_check_latency(self, ai_client, metrics):
        """Measure AI health check latency."""
        if not ai_client:
            pytest.skip("AI client not available")
        
        for _ in range(5):
            start = time.time()
            response = ai_client.get("/health")
            elapsed = (time.time() - start) * 1000
            
            assert response.status_code == 200
            metrics.record("ai_health_latency", elapsed)
        
        summary = metrics.summary("ai_health_latency")
        assert summary["avg"] < 100, "AI health check should be < 100ms"
    
    def test_analysis_latency(self, ai_client, metrics):
        """Measure text analysis latency."""
        if not ai_client:
            pytest.skip("AI client not available")
        
        payload = {
            "text": "This is a test message for analysis of keystroke patterns",
            "analysis_type": "general"
        }
        
        for _ in range(3):
            start = time.time()
            response = ai_client.post("/analyze", json=payload)
            elapsed = (time.time() - start) * 1000
            
            if response.status_code == 200:
                metrics.record("ai_analysis_latency", elapsed)
        
        if "ai_analysis_latency" in metrics.measurements:
            summary = metrics.summary("ai_analysis_latency")
            print(f"\nAI Analysis latency: {summary}")


class TestVizPerformance:
    """Tests for visualization service performance."""
    
    def test_health_check_latency(self, viz_client, metrics):
        """Measure visualization health check latency."""
        if not viz_client:
            pytest.skip("Visualization client not available")
        
        for _ in range(5):
            start = time.time()
            response = viz_client.get("/health")
            elapsed = (time.time() - start) * 1000
            
            assert response.status_code == 200
            metrics.record("viz_health_latency", elapsed)
        
        summary = metrics.summary("viz_health_latency")
        assert summary["avg"] < 100, "Viz health check should be < 100ms"
    
    def test_chart_generation_latency(self, viz_client, metrics):
        """Measure chart generation latency."""
        if not viz_client:
            pytest.skip("Visualization client not available")
        
        for chart_type in ["bar", "line", "pie"]:
            payload = {
                "title": f"Test {chart_type} Chart",
                "data": {f"Item{i}": i*100 for i in range(10)},
                "chart_type": chart_type
            }
            
            for _ in range(2):
                start = time.time()
                response = viz_client.post("/chart", json=payload)
                elapsed = (time.time() - start) * 1000
                
                if response.status_code == 200:
                    metrics.record(f"chart_{chart_type}_latency", elapsed)
        
        for chart_type in ["bar", "line", "pie"]:
            key = f"chart_{chart_type}_latency"
            if key in metrics.measurements:
                summary = metrics.summary(key)
                assert summary["avg"] < 1000, f"{chart_type} chart should be < 1000ms"


class TestThroughput:
    """Tests for service throughput."""
    
    def test_sequential_requests(self, api_client):
        """Test sequential request throughput."""
        if not api_client:
            pytest.skip("API client not available")
        
        start = time.time()
        count = 0
        
        while time.time() - start < 5:
            response = api_client.get("/health")
            if response.status_code == 200:
                count += 1
        
        elapsed = time.time() - start
        throughput = count / elapsed
        
        print(f"\nSequential throughput: {throughput:.2f} req/s")
        assert throughput > 10, "Throughput should be > 10 req/s"
    
    def test_word_search_throughput(self, api_client):
        """Test word search throughput."""
        if not api_client:
            pytest.skip("API client not available")
        
        words = ["the", "and", "test", "python", "data"]
        start = time.time()
        count = 0
        
        while time.time() - start < 5:
            for word in words:
                response = api_client.get(f"/api/words/find?word={word}")
                if response.status_code in [200, 404]:
                    count += 1
        
        elapsed = time.time() - start
        throughput = count / elapsed
        
        print(f"\nWord search throughput: {throughput:.2f} req/s")


class TestMemoryUsage:
    """Tests for memory consumption patterns."""
    
    def test_large_data_response(self, api_client):
        """Test API with large data response."""
        if not api_client:
            pytest.skip("API client not available")
        
        response = api_client.get("/api/words/top?limit=100")
        
        if response.status_code == 200:
            data = response.json()
            size_mb = len(json.dumps(data)) / (1024 * 1024)
            print(f"\nResponse size: {size_mb:.2f} MB")
            assert size_mb < 10, "Response should be < 10 MB"
    
    def test_repeated_requests(self, api_client):
        """Test for memory leaks with repeated requests."""
        if not api_client:
            pytest.skip("API client not available")
        
        for _ in range(100):
            response = api_client.get("/health")
            assert response.status_code == 200


class TestResponseQuality:
    """Tests for response quality metrics."""
    
    def test_daily_stats_response_structure(self, api_client):
        """Verify daily stats response structure."""
        if not api_client:
            pytest.skip("API client not available")
        
        response = api_client.get("/api/stats/daily")
        
        if response.status_code == 200:
            data = response.json()
            required_fields = ["presses", "releases", "repeats", "total"]
            for field in required_fields:
                assert field in data, f"Missing field: {field}"
    
    def test_top_words_response_structure(self, api_client):
        """Verify top words response structure."""
        if not api_client:
            pytest.skip("API client not available")
        
        response = api_client.get("/api/words/top?limit=5")
        
        if response.status_code == 200:
            data = response.json()
            assert isinstance(data, list), "Response should be a list"
            if len(data) > 0:
                word = data[0]
                required_fields = ["rank", "word", "count", "percentage"]
                for field in required_fields:
                    assert field in word, f"Missing field in word: {field}"


class TestErrorRecovery:
    """Tests for error handling and recovery."""
    
    def test_invalid_parameter_handling(self, api_client, metrics):
        """Test handling of invalid parameters."""
        if not api_client:
            pytest.skip("API client not available")
        
        start = time.time()
        response = api_client.get("/api/words/find?word=")
        elapsed = (time.time() - start) * 1000
        
        metrics.record("invalid_param_latency", elapsed)
        assert response.status_code in [200, 400]
        assert elapsed < 100, "Error response should be quick"
    
    def test_missing_required_parameter(self, api_client):
        """Test missing required parameter."""
        if not api_client:
            pytest.skip("API client not available")
        
        response = api_client.get("/api/stats/hourly")
        assert response.status_code in [400, 422, 200]