test_enhanced_conversion.py

#!/usr/bin/env python3
"""
Test script for the enhanced DOCX to PDF conversion system
Tests all the new advanced features and quality verification
"""

import os
import sys
import tempfile
import shutil
from pathlib import Path

# Add the current directory to Python path to import app modules
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from app import (
    validate_docx_structure,
    preprocess_docx_for_perfect_conversion,
    post_process_pdf_for_perfect_formatting,
    generate_comprehensive_quality_report,
    calculate_quality_score,
    setup_libreoffice,
    setup_font_environment
)

def create_test_docx():
    """
    Create a test DOCX file with Arabic content for testing
    This would normally require python-docx, but for testing we'll create a simple structure
    """
    print("📝 Creating test DOCX file...")
    
    # For this test, we'll assume a DOCX file exists or create a simple one
    test_content = """
    Test DOCX content with Arabic text: مرحبا بكم في اختبار التحويل المتقدم
    
    This document contains:
    - Arabic RTL text: النص العربي من اليمين إلى اليسار
    - Placeholders: {{name}}, {{date}}, {{company}}
    - Tables with Arabic content
    - Mixed language content
    
    Table example:
    | English | العربية | Notes |
    |---------|---------|-------|
    | Hello   | مرحبا   | Greeting |
    | World   | العالم  | Noun |
    """
    
    print("✅ Test content prepared")
    return test_content

def test_docx_analysis():
    """Test the enhanced DOCX structure analysis"""
    print("\n🔍 Testing DOCX Structure Analysis...")
    
    # This would test with a real DOCX file
    # For now, we'll simulate the analysis results
    mock_docx_info = {
        'page_count': 1,
        'has_tables': True,
        'has_images': False,
        'text_content_length': 500,
        'font_families': {'Arial', 'Traditional Arabic', 'Calibri'},
        'has_textboxes': False,
        'has_smartart': False,
        'has_complex_shapes': False,
        'table_structure_issues': [],
        'rtl_content_detected': True,
        'placeholder_count': 3,
        'error': None
    }
    
    print("📊 Analysis Results:")
    print(f"  • Tables: {mock_docx_info['has_tables']}")
    print(f"  • RTL Content: {mock_docx_info['rtl_content_detected']}")
    print(f"  • Placeholders: {mock_docx_info['placeholder_count']}")
    print(f"  • Font Families: {len(mock_docx_info['font_families'])}")
    
    return mock_docx_info

def test_quality_scoring():
    """Test the quality scoring system"""
    print("\n📊 Testing Quality Scoring System...")
    
    # Mock validation results
    mock_pdf_validation = {
        'file_size_mb': 0.5,
        'file_exists': True,
        'size_reasonable': True,
        'warnings': [],
        'success_metrics': ['PDF file size is reasonable', 'Font substitution applied']
    }
    
    # Mock post-processing results
    mock_post_process = {
        'pages_processed': 1,
        'placeholders_verified': 3,
        'tables_verified': 1,
        'arabic_text_verified': 150,
        'layout_issues_fixed': 0,
        'warnings': [],
        'success_metrics': ['All 3 placeholders preserved', 'Arabic RTL text verified: 150 characters']
    }
    
    # Mock DOCX info
    mock_docx_info = {
        'has_tables': True,
        'has_images': False,
        'rtl_content_detected': True,
        'placeholder_count': 3,
        'has_textboxes': False,
        'has_smartart': False,
        'has_complex_shapes': False,
        'table_structure_issues': []
    }
    
    # Test quality score calculation
    quality_score = calculate_quality_score(mock_docx_info, mock_pdf_validation, mock_post_process)
    print(f"🏆 Quality Score: {quality_score:.1f}%")
    
    # Test comprehensive report generation
    quality_report = generate_comprehensive_quality_report(mock_docx_info, mock_pdf_validation, mock_post_process)
    print("\n📋 Quality Report:")
    print(quality_report)
    
    return quality_score

def test_font_system():
    """Test the enhanced Arabic font system"""
    print("\n🔤 Testing Enhanced Arabic Font System...")
    
    try:
        setup_font_environment()
        print("✅ Font environment setup completed")
        
        # Test font availability
        import subprocess
        result = subprocess.run(['fc-list'], capture_output=True, text=True, timeout=10)
        available_fonts = result.stdout.lower()
        
        arabic_fonts = ['amiri', 'noto naskh arabic', 'scheherazade', 'cairo']
        found_fonts = []
        
        for font in arabic_fonts:
            if font in available_fonts:
                found_fonts.append(font)
        
        print(f"📊 Arabic Fonts Available: {len(found_fonts)}/{len(arabic_fonts)}")
        for font in found_fonts:
            print(f"  ✓ {font}")
        
        return len(found_fonts) > 0
        
    except Exception as e:
        print(f"❌ Font system test failed: {e}")
        return False

def test_libreoffice_setup():
    """Test LibreOffice configuration"""
    print("\n⚙️ Testing LibreOffice Setup...")
    
    try:
        libreoffice_available = setup_libreoffice()
        if libreoffice_available:
            print("✅ LibreOffice is properly configured")
            
            # Test version
            import subprocess
            result = subprocess.run(['libreoffice', '--version'], 
                                  capture_output=True, text=True, timeout=10)
            if result.returncode == 0:
                print(f"📊 LibreOffice Version: {result.stdout.strip()}")
            
            return True
        else:
            print("❌ LibreOffice setup failed")
            return False
            
    except Exception as e:
        print(f"❌ LibreOffice test failed: {e}")
        return False

def run_comprehensive_test():
    """Run all tests for the enhanced conversion system"""
    print("🚀 ENHANCED DOCX TO PDF CONVERSION SYSTEM TEST")
    print("=" * 60)
    
    test_results = {}
    
    # Test 1: DOCX Analysis
    test_results['docx_analysis'] = test_docx_analysis()
    
    # Test 2: Quality Scoring
    test_results['quality_score'] = test_quality_scoring()
    
    # Test 3: Font System
    test_results['font_system'] = test_font_system()
    
    # Test 4: LibreOffice Setup
    test_results['libreoffice'] = test_libreoffice_setup()
    
    # Summary
    print("\n" + "=" * 60)
    print("📊 TEST SUMMARY")
    print("=" * 60)
    
    passed_tests = 0
    total_tests = len(test_results)
    
    for test_name, result in test_results.items():
        status = "✅ PASS" if result else "❌ FAIL"
        print(f"{test_name.replace('_', ' ').title()}: {status}")
        if result:
            passed_tests += 1
    
    success_rate = (passed_tests / total_tests) * 100
    print(f"\n🎯 Overall Success Rate: {success_rate:.1f}% ({passed_tests}/{total_tests})")
    
    if success_rate >= 75:
        print("🌟 EXCELLENT: Enhanced conversion system is ready!")
    elif success_rate >= 50:
        print("👍 GOOD: Most features are working correctly")
    else:
        print("⚠️ NEEDS ATTENTION: Several components need fixing")
    
    return test_results

if __name__ == "__main__":
    # Run the comprehensive test
    results = run_comprehensive_test()
    
    # Exit with appropriate code
    success_rate = sum(1 for r in results.values() if r) / len(results) * 100
    sys.exit(0 if success_rate >= 75 else 1)