OCR/backend/tests/conftest_v1.py

"""
Tool_OCR - Pytest Fixtures and Configuration
Shared fixtures for all tests
"""

import pytest
import tempfile
import shutil
from pathlib import Path
from PIL import Image
import io

from app.services.preprocessor import DocumentPreprocessor


@pytest.fixture
def temp_dir():
    """Create a temporary directory for test files"""
    temp_path = Path(tempfile.mkdtemp())
    yield temp_path
    # Cleanup after test
    shutil.rmtree(temp_path, ignore_errors=True)


@pytest.fixture
def sample_image_path(temp_dir):
    """Create a valid PNG image file for testing"""
    image_path = temp_dir / "test_image.png"

    # Create a simple 100x100 white image
    img = Image.new('RGB', (100, 100), color='white')
    img.save(image_path, 'PNG')

    return image_path


@pytest.fixture
def sample_jpg_path(temp_dir):
    """Create a valid JPG image file for testing"""
    image_path = temp_dir / "test_image.jpg"

    # Create a simple 100x100 white image
    img = Image.new('RGB', (100, 100), color='white')
    img.save(image_path, 'JPEG')

    return image_path


@pytest.fixture
def sample_pdf_path(temp_dir):
    """Create a valid PDF file for testing"""
    pdf_path = temp_dir / "test_document.pdf"

    # Create minimal valid PDF
    pdf_content = b"""%PDF-1.4
1 0 obj
<<
/Type /Catalog
/Pages 2 0 R
>>
endobj
2 0 obj
<<
/Type /Pages
/Kids [3 0 R]
/Count 1
>>
endobj
3 0 obj
<<
/Type /Page
/Parent 2 0 R
/MediaBox [0 0 612 792]
/Contents 4 0 R
/Resources <<
/Font <<
/F1 <<
/Type /Font
/Subtype /Type1
/BaseFont /Helvetica
>>
>>
>>
>>
endobj
4 0 obj
<<
/Length 44
>>
stream
BT
/F1 12 Tf
100 700 Td
(Test PDF) Tj
ET
endstream
endobj
xref
0 5
0000000000 65535 f
0000000009 00000 n
0000000058 00000 n
0000000115 00000 n
0000000317 00000 n
trailer
<<
/Size 5
/Root 1 0 R
>>
startxref
410
%%EOF
"""

    with open(pdf_path, 'wb') as f:
        f.write(pdf_content)

    return pdf_path


@pytest.fixture
def corrupted_image_path(temp_dir):
    """Create a corrupted image file for testing"""
    image_path = temp_dir / "corrupted.png"

    # Write invalid PNG data
    with open(image_path, 'wb') as f:
        f.write(b'\x89PNG\r\n\x1a\n\x00\x00\x00corrupted data')

    return image_path


@pytest.fixture
def large_file_path(temp_dir):
    """Create a valid PNG file larger than the upload limit"""
    file_path = temp_dir / "large_file.png"

    # Create a large PNG image with random data (to prevent compression)
    # 15000x15000 with random pixels should be > 20MB
    import numpy as np
    random_data = np.random.randint(0, 256, (15000, 15000, 3), dtype=np.uint8)
    img = Image.fromarray(random_data, 'RGB')
    img.save(file_path, 'PNG', compress_level=0)  # No compression

    # Verify it's actually large
    file_size = file_path.stat().st_size
    assert file_size > 20 * 1024 * 1024, f"File only {file_size / (1024*1024):.2f} MB"

    return file_path


@pytest.fixture
def unsupported_file_path(temp_dir):
    """Create a file with unsupported format"""
    file_path = temp_dir / "test.txt"

    with open(file_path, 'w') as f:
        f.write("This is a text file, not an image")

    return file_path


@pytest.fixture
def preprocessor():
    """Create a DocumentPreprocessor instance"""
    return DocumentPreprocessor()


@pytest.fixture
def sample_image_with_text():
    """Return path to a real image with text from demo_docs for OCR testing"""
    # Use the english.png sample from demo_docs
    demo_image_path = Path(__file__).parent.parent.parent / "demo_docs" / "basic" / "english.png"

    # Check if demo image exists, otherwise skip the test
    if not demo_image_path.exists():
        pytest.skip(f"Demo image not found at {demo_image_path}")

    return demo_image_path