survey_custom_certificate_template/tests/test_property_pdf_conversion_standalone.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Standalone property-based test for PDF conversion.

This test can run without the full Odoo environment by importing the generator
service directly from the local module structure.

Feature: survey-custom-certificate-template, Property 15: PDF conversion
Validates: Requirements 5.4
"""

import sys
import os
import tempfile
import logging
from io import BytesIO

# Add parent directory to path to import services
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))

try:
    from hypothesis import given, settings, HealthCheck, assume
    HYPOTHESIS_AVAILABLE = True
except ImportError:
    print("ERROR: Hypothesis is not installed. Install with: pip install hypothesis")
    sys.exit(1)

try:
    from docx import Document
    DOCX_AVAILABLE = True
except ImportError:
    print("ERROR: python-docx is not installed. Install with: pip install python-docx")
    sys.exit(1)

# Import the generator service directly
from services.certificate_generator import CertificateGenerator

# Import our custom strategies
from hypothesis_strategies import (
    docx_with_placeholders,
    docx_with_mappings_and_data,
)

_logger = logging.getLogger(__name__)


def test_property_15_pdf_conversion():
    """
    Feature: survey-custom-certificate-template, Property 15: PDF conversion
    
    For any generated certificate DOCX file, the system should convert it to PDF format.
    
    Validates: Requirements 5.4
    
    This property test verifies that:
    1. Any valid DOCX file can be converted to PDF
    2. The conversion produces non-empty PDF content
    3. The PDF content has the correct PDF file signature
    4. The conversion completes without errors
    5. Temporary files are cleaned up properly
    """
    print("\nTesting Property 15: PDF conversion")
    print("=" * 60)
    
    generator = CertificateGenerator()
    
    # Check if LibreOffice is available
    is_available, error_msg = CertificateGenerator.check_libreoffice_availability()
    if not is_available:
        print(f"⚠ SKIPPED: LibreOffice not available: {error_msg}")
        print("  PDF conversion tests require LibreOffice to be installed")
        return True  # Skip but don't fail
    
    test_count = 0
    
    @given(docx_binary=docx_with_placeholders(min_placeholders=0, max_placeholders=5))
    @settings(
        max_examples=100,
        deadline=None,
        suppress_health_check=[HealthCheck.function_scoped_fixture, HealthCheck.too_slow]
    )
    def check_pdf_conversion(docx_binary):
        nonlocal test_count
        test_count += 1
        
        docx_data, placeholders = docx_binary
        
        # Assume we have valid DOCX data
        assume(len(docx_data) > 0)
        
        # Create a temporary DOCX file for conversion
        temp_docx = tempfile.NamedTemporaryFile(
            suffix='.docx',
            delete=False
        )
        temp_docx_path = temp_docx.name
        
        try:
            # Write the DOCX data to the temporary file
            temp_docx.write(docx_data)
            temp_docx.close()
            
            # Property 1: The conversion should complete without raising exceptions
            try:
                pdf_content = generator.convert_to_pdf(temp_docx_path)
            except Exception as e:
                raise AssertionError(
                    f"PDF conversion raised an exception: {type(e).__name__}: {str(e)}"
                )
            
            # Property 2: The PDF content should not be None
            if pdf_content is None:
                raise AssertionError("PDF conversion returned None instead of PDF content")
            
            # Property 3: The PDF content should not be empty
            if len(pdf_content) == 0:
                raise AssertionError("PDF conversion produced empty content")
            
            # Property 4: The PDF content should have the correct PDF file signature
            # PDF files start with "%PDF-" (bytes: 0x25 0x50 0x44 0x46 0x2D)
            if not pdf_content.startswith(b'%PDF-'):
                raise AssertionError(
                    f"PDF content does not have valid PDF signature. "
                    f"First 10 bytes: {pdf_content[:10]}"
                )
            
            # Property 5: The PDF should have a reasonable minimum size
            # A minimal PDF is typically at least 100 bytes
            if len(pdf_content) <= 100:
                raise AssertionError(
                    f"PDF content is suspiciously small ({len(pdf_content)} bytes). "
                    f"This may indicate an incomplete conversion."
                )
            
            # Property 6: The PDF should contain the PDF EOF marker
            # PDF files typically end with "%%EOF"
            if b'%%EOF' not in pdf_content:
                raise AssertionError("PDF content does not contain the expected EOF marker")
            
        finally:
            # Clean up the temporary DOCX file
            if os.path.exists(temp_docx_path):
                try:
                    os.unlink(temp_docx_path)
                except Exception as e:
                    _logger.warning(f"Failed to delete temporary file {temp_docx_path}: {e}")
    
    try:
        check_pdf_conversion()
        print(f"✓ Property 15 verified across {test_count} test cases")
        print("  All DOCX files were successfully converted to valid PDF format")
        return True
    except Exception as e:
        print(f"✗ Property 15 FAILED after {test_count} test cases")
        print(f"  Error: {e}")
        import traceback
        traceback.print_exc()
        return False


def test_property_15_pdf_conversion_with_replacements():
    """
    Feature: survey-custom-certificate-template, Property 15: PDF conversion (with replacements)
    
    For any generated certificate DOCX file (with placeholder replacements),
    the system should convert it to PDF format.
    
    Validates: Requirements 5.4
    
    This test verifies that PDF conversion works correctly even after
    placeholder replacements have been made to the document.
    """
    print("\nTesting Property 15: PDF conversion (with placeholder replacements)")
    print("=" * 60)
    
    generator = CertificateGenerator()
    
    # Check if LibreOffice is available
    is_available, error_msg = CertificateGenerator.check_libreoffice_availability()
    if not is_available:
        print(f"⚠ SKIPPED: LibreOffice not available: {error_msg}")
        return True  # Skip but don't fail
    
    test_count = 0
    
    @given(test_data=docx_with_mappings_and_data())
    @settings(
        max_examples=50,
        deadline=None,
        suppress_health_check=[HealthCheck.function_scoped_fixture, HealthCheck.too_slow]
    )
    def check_pdf_conversion_with_replacements(test_data):
        nonlocal test_count
        test_count += 1
        
        docx_binary, mappings, data = test_data
        
        # Assume we have valid data
        assume(len(docx_binary) > 0)
        
        # Load the document and perform placeholder replacements
        doc = Document(BytesIO(docx_binary))
        modified_doc = generator.replace_placeholders(doc, mappings, data)
        
        # Save the modified document to a temporary file
        temp_docx = tempfile.NamedTemporaryFile(
            suffix='.docx',
            delete=False
        )
        temp_docx_path = temp_docx.name
        temp_docx.close()
        
        try:
            # Save the modified document
            modified_doc.save(temp_docx_path)
            
            # Convert to PDF
            pdf_content = generator.convert_to_pdf(temp_docx_path)
            
            # Verify the PDF is valid
            if pdf_content is None:
                raise AssertionError("PDF conversion returned None")
            if len(pdf_content) == 0:
                raise AssertionError("PDF conversion produced empty content")
            if not pdf_content.startswith(b'%PDF-'):
                raise AssertionError("PDF does not have valid signature")
            if b'%%EOF' not in pdf_content:
                raise AssertionError("PDF does not contain EOF marker")
            
        finally:
            # Clean up
            if os.path.exists(temp_docx_path):
                try:
                    os.unlink(temp_docx_path)
                except Exception as e:
                    _logger.warning(f"Failed to delete temporary file {temp_docx_path}: {e}")
    
    try:
        check_pdf_conversion_with_replacements()
        print(f"✓ Property 15 (with replacements) verified across {test_count} test cases")
        print("  All modified DOCX files were successfully converted to valid PDF format")
        return True
    except Exception as e:
        print(f"✗ Property 15 (with replacements) FAILED after {test_count} test cases")
        print(f"  Error: {e}")
        import traceback
        traceback.print_exc()
        return False


def main():
    """Run the property tests."""
    print("=" * 60)
    print("Property-Based Test: PDF Conversion")
    print("=" * 60)
    
    # Run both test variants
    success1 = test_property_15_pdf_conversion()
    success2 = test_property_15_pdf_conversion_with_replacements()
    
    print("\n" + "=" * 60)
    if success1 and success2:
        print("✓ All property tests PASSED")
        print("=" * 60)
        return 0
    else:
        print("✗ Some property tests FAILED")
        print("=" * 60)
        return 1


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