test_api.py

#!/usr/bin/env python3
"""
Test script for HandyHome OCR API
Tests all endpoints with sample document URLs
"""

import requests
import json
import sys

# Configuration
BASE_URL = "http://localhost:7860"  # Change to your Hugging Face Space URL for remote testing

# Sample test URLs (replace with your actual test image URLs)
TEST_URLS = {
    'national_id': 'https://example.com/national_id.jpg',
    'drivers_license': 'https://example.com/drivers_license.jpg',
    'prc': 'https://example.com/prc.jpg',
    'umid': 'https://example.com/umid.jpg',
    'sss': 'https://example.com/sss.jpg',
    'passport': 'https://example.com/passport.jpg',
    'postal': 'https://example.com/postal.jpg',
    'phic': 'https://example.com/phic.jpg',
    'nbi': 'https://example.com/nbi.jpg',
    'police': 'https://example.com/police.jpg',
    'tesda': 'https://example.com/tesda.jpg',
}

def test_health():
    """Test health endpoint"""
    print("\n" + "="*60)
    print("Testing Health Endpoint")
    print("="*60)
    
    try:
        response = requests.get(f"{BASE_URL}/health", timeout=10)
        print(f"Status Code: {response.status_code}")
        print(f"Response: {json.dumps(response.json(), indent=2)}")
        return response.status_code == 200
    except Exception as e:
        print(f"Error: {str(e)}")
        return False

def test_index():
    """Test index/documentation endpoint"""
    print("\n" + "="*60)
    print("Testing Index/Documentation Endpoint")
    print("="*60)
    
    try:
        response = requests.get(f"{BASE_URL}/", timeout=10)
        print(f"Status Code: {response.status_code}")
        data = response.json()
        print(f"Service: {data.get('service')}")
        print(f"Version: {data.get('version')}")
        print(f"Available Endpoints: {len(data.get('endpoints', {}))}")
        return response.status_code == 200
    except Exception as e:
        print(f"Error: {str(e)}")
        return False

def test_extraction_endpoint(endpoint, document_type, document_url):
    """Test an OCR extraction endpoint"""
    print("\n" + "="*60)
    print(f"Testing: {document_type}")
    print("="*60)
    print(f"Endpoint: {endpoint}")
    print(f"Document URL: {document_url}")
    
    try:
        response = requests.post(
            f"{BASE_URL}{endpoint}",
            json={'document_url': document_url},
            timeout=300
        )
        print(f"Status Code: {response.status_code}")
        
        try:
            data = response.json()
            print(f"Response: {json.dumps(data, indent=2)}")
            return response.status_code == 200 and data.get('success', False)
        except:
            print(f"Response (non-JSON): {response.text[:200]}")
            return False
            
    except requests.exceptions.Timeout:
        print("Error: Request timed out (>5 minutes)")
        return False
    except Exception as e:
        print(f"Error: {str(e)}")
        return False

def main():
    """Run all tests"""
    print("\n" + "="*60)
    print("HandyHome OCR API Test Suite")
    print("="*60)
    print(f"Base URL: {BASE_URL}")
    
    results = {}
    
    # Test utility endpoints
    results['health'] = test_health()
    results['index'] = test_index()
    
    # Test OCR endpoints
    endpoints_to_test = [
        ('/api/extract-national-id', 'National ID', TEST_URLS['national_id']),
        ('/api/extract-drivers-license', "Driver's License", TEST_URLS['drivers_license']),
        ('/api/extract-prc', 'PRC ID', TEST_URLS['prc']),
        ('/api/extract-umid', 'UMID', TEST_URLS['umid']),
        ('/api/extract-sss', 'SSS ID', TEST_URLS['sss']),
        ('/api/extract-passport', 'Passport', TEST_URLS['passport']),
        ('/api/extract-postal', 'Postal ID', TEST_URLS['postal']),
        ('/api/extract-phic', 'PhilHealth ID', TEST_URLS['phic']),
        ('/api/extract-nbi', 'NBI Clearance', TEST_URLS['nbi']),
        ('/api/extract-police-clearance', 'Police Clearance', TEST_URLS['police']),
        ('/api/extract-tesda', 'TESDA Certificate', TEST_URLS['tesda']),
    ]
    
    for endpoint, doc_type, url in endpoints_to_test:
        key = doc_type.lower().replace(' ', '_').replace("'", '')
        results[key] = test_extraction_endpoint(endpoint, doc_type, url)
    
    # Print summary
    print("\n" + "="*60)
    print("Test Summary")
    print("="*60)
    
    passed = sum(1 for v in results.values() if v)
    total = len(results)
    
    for test_name, passed_test in results.items():
        status = "✓ PASS" if passed_test else "✗ FAIL"
        print(f"{status} - {test_name}")
    
    print("\n" + "="*60)
    print(f"Results: {passed}/{total} tests passed")
    print("="*60)
    
    return 0 if passed == total else 1

if __name__ == '__main__':
    sys.exit(main())