test_setup.py

#!/usr/bin/env python3
"""
Test script to verify project setup and dependencies
"""

import sys
import os
import importlib
from pathlib import Path

def test_python_version():
    """Test Python version"""
    print("🐍 Python Version Check")
    version = sys.version_info
    print(f"   Python {version.major}.{version.minor}.{version.micro}")
    
    if version.major >= 3 and version.minor >= 8:
        print("   ✅ Python version OK")
        return True
    else:
        print("   ❌ Python 3.8+ required")
        return False

def test_dependencies():
    """Test required dependencies"""
    print("\n📦 Dependency Check")
    
    required_packages = [
        'requests',
        'beautifulsoup4',
        'pandas',
        'numpy',
        'tqdm',
        'gradio'
    ]
    
    optional_packages = [
        'torch',
        'transformers',
        'datasets',
        'peft',
        'bitsandbytes',
        'accelerate'
    ]
    
    all_good = True
    
    for package in required_packages:
        try:
            importlib.import_module(package)
            print(f"   ✅ {package}")
        except ImportError:
            print(f"   ❌ {package} (required)")
            all_good = False
    
    print("\n   Optional ML packages:")
    for package in optional_packages:
        try:
            importlib.import_module(package)
            print(f"   ✅ {package}")
        except ImportError:
            print(f"   ⚠️  {package} (optional, needed for training)")
    
    return all_good

def test_project_structure():
    """Test project file structure"""
    print("\n📁 Project Structure Check")
    
    required_files = [
        'requirements.txt',
        'app.py',
        'run_pipeline.py',
        'README.md',
        'src/scraper.py',
        'src/preprocess.py',
        'src/finetune.py',
        'src/utils.py'
    ]
    
    required_dirs = [
        'src',
        'data',
        'models',
        'models/lora_adapters'
    ]
    
    all_good = True
    
    for file_path in required_files:
        if os.path.exists(file_path):
            print(f"   ✅ {file_path}")
        else:
            print(f"   ❌ {file_path}")
            all_good = False
    
    for dir_path in required_dirs:
        if os.path.exists(dir_path):
            print(f"   ✅ {dir_path}/")
        else:
            print(f"   ❌ {dir_path}/")
            all_good = False
    
    return all_good

def test_gpu_availability():
    """Test GPU availability"""
    print("\n🖥️  Hardware Check")
    
    try:
        import torch
        print(f"   PyTorch version: {torch.__version__}")
        
        if torch.cuda.is_available():
            gpu_count = torch.cuda.device_count()
            print(f"   ✅ CUDA available ({gpu_count} GPU(s))")
            
            for i in range(gpu_count):
                props = torch.cuda.get_device_properties(i)
                memory_gb = props.total_memory / 1e9
                print(f"      GPU {i}: {props.name} ({memory_gb:.1f} GB)")
            
            return True
        else:
            print("   ⚠️  CUDA not available (CPU training only)")
            return False
            
    except ImportError:
        print("   ❌ PyTorch not installed")
        return False

def test_internet_connection():
    """Test internet connectivity"""
    print("\n🌐 Internet Connection Check")
    
    try:
        import requests
        response = requests.get('https://www.lightreading.com', timeout=10)
        if response.status_code == 200:
            print("   ✅ Light Reading accessible")
            return True
        else:
            print(f"   ⚠️  Light Reading returned status {response.status_code}")
            return False
    except Exception as e:
        print(f"   ❌ Internet connection failed: {e}")
        return False

def run_basic_import_test():
    """Test basic imports from project modules"""
    print("\n🔧 Module Import Check")
    
    sys.path.append(str(Path(__file__).parent / "src"))
    
    modules_to_test = [
        ('scraper', 'LightReadingScraper'),
        ('preprocess', 'ArticlePreprocessor'),
        ('utils', 'setup_logging')
    ]
    
    all_good = True
    
    for module_name, class_name in modules_to_test:
        try:
            module = importlib.import_module(module_name)
            getattr(module, class_name)
            print(f"   ✅ {module_name}.{class_name}")
        except Exception as e:
            print(f"   ❌ {module_name}.{class_name}: {e}")
            all_good = False
    
    return all_good

def main():
    """Run all tests"""
    print("🧪 MORRIS-BOT PROJECT SETUP TEST")
    print("=" * 50)
    
    tests = [
        ("Python Version", test_python_version),
        ("Dependencies", test_dependencies),
        ("Project Structure", test_project_structure),
        ("GPU Availability", test_gpu_availability),
        ("Internet Connection", test_internet_connection),
        ("Module Imports", run_basic_import_test)
    ]
    
    results = []
    
    for test_name, test_func in tests:
        try:
            result = test_func()
            results.append((test_name, result))
        except Exception as e:
            print(f"   ❌ Test failed with error: {e}")
            results.append((test_name, False))
    
    # Summary
    print("\n" + "=" * 50)
    print("📊 TEST SUMMARY")
    print("=" * 50)
    
    passed = sum(1 for _, result in results if result)
    total = len(results)
    
    for test_name, result in results:
        status = "✅ PASS" if result else "❌ FAIL"
        print(f"   {status} {test_name}")
    
    print(f"\nOverall: {passed}/{total} tests passed")
    
    if passed == total:
        print("\n🎉 All tests passed! Your setup is ready.")
        print("\nNext steps:")
        print("   1. Run: python run_pipeline.py --status")
        print("   2. Run: python run_pipeline.py --collect")
    else:
        print("\n⚠️  Some tests failed. Please check the issues above.")
        print("\nCommon fixes:")
        print("   - Install missing packages: pip install -r requirements.txt")
        print("   - Check internet connection")
        print("   - Install PyTorch for GPU support")

if __name__ == "__main__":
    main()