"""
Unit tests for DocumentToHtmlConverter.
Tests Word document conversion including format normalization and LibreOffice integration.
"""
import pytest
from pathlib import Path
from unittest.mock import patch, MagicMock
from src.extraction_v2.document_converter import DocumentToHtmlConverter
class TestDocumentToHtmlConverter:
"""Test suite for DocumentToHtmlConverter class."""
def test_init(self):
"""Test converter initialization."""
converter = DocumentToHtmlConverter()
assert converter.converter is not None
assert converter._last_doc is None
assert converter._last_sheet_names == []
def test_convert_to_html_routes_excel(self):
"""Test that Excel files are routed to Excel converter."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_convert_excel_to_html', return_value="test") as mock_excel:
result = converter.convert_to_html("test.xlsx")
mock_excel.assert_called_once_with("test.xlsx")
assert result == "test"
def test_convert_to_html_routes_word(self):
"""Test that Word files are routed to Word converter."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_convert_word_to_markdown', return_value="# Test") as mock_word:
result = converter.convert_to_html("test.docx")
mock_word.assert_called_once_with("test.docx")
assert result == "# Test"
def test_convert_to_html_unsupported_format(self):
"""Test that unsupported file formats return None."""
converter = DocumentToHtmlConverter()
result = converter.convert_to_html("test.pdf")
assert result is None
def test_validate_word_file_success(self):
"""Test Word file validation with valid .docx file."""
converter = DocumentToHtmlConverter()
# Create a mock Path object
mock_path = MagicMock(spec=Path)
mock_path.exists.return_value = True
mock_path.suffix = ".docx"
mock_path.stat.return_value = MagicMock(st_size=1024 * 1024) # 1MB
# Mock zipfile for .docx validation
with patch('zipfile.ZipFile') as mock_zipfile:
mock_zip = MagicMock()
mock_zip.namelist.return_value = ['word/document.xml', 'word/styles.xml']
mock_zipfile.return_value.__enter__.return_value = mock_zip
is_valid, error_msg = converter._validate_word_file(mock_path)
assert is_valid is True
assert error_msg is None
def test_validate_word_file_not_found(self):
"""Test Word file validation with non-existent file."""
converter = DocumentToHtmlConverter()
mock_path = MagicMock(spec=Path)
mock_path.exists.return_value = False
is_valid, error_msg = converter._validate_word_file(mock_path)
assert is_valid is False
assert error_msg == "File not found"
def test_validate_word_file_too_large(self):
"""Test Word file validation with file over 100MB."""
converter = DocumentToHtmlConverter()
mock_path = MagicMock(spec=Path)
mock_path.exists.return_value = True
mock_path.suffix = ".docx"
mock_path.stat.return_value = MagicMock(st_size=150 * 1024 * 1024) # 150MB
is_valid, error_msg = converter._validate_word_file(mock_path)
assert is_valid is False
assert "too large" in error_msg
def test_validate_word_file_unsupported_extension(self):
"""Test Word file validation with unsupported extension."""
converter = DocumentToHtmlConverter()
mock_path = MagicMock(spec=Path)
mock_path.exists.return_value = True
mock_path.suffix = ".pdf"
mock_path.stat.return_value = MagicMock(st_size=1024 * 1024) # 1MB
is_valid, error_msg = converter._validate_word_file(mock_path)
assert is_valid is False
assert "Unsupported format" in error_msg
def test_validate_word_file_corrupted_docx(self):
"""Test Word file validation with corrupted .docx file."""
converter = DocumentToHtmlConverter()
mock_path = MagicMock(spec=Path)
mock_path.exists.return_value = True
mock_path.suffix = ".docx"
mock_path.stat.return_value = MagicMock(st_size=1024 * 1024) # 1MB
# Mock zipfile to raise BadZipFile exception
with patch('zipfile.ZipFile', side_effect=Exception("Bad ZIP")):
is_valid, error_msg = converter._validate_word_file(mock_path)
assert is_valid is False
assert "File validation error" in error_msg
def test_convert_doc_to_docx_libreoffice_not_found(self):
"""Test .doc conversion when LibreOffice is not installed."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_find_libreoffice_command', return_value=None):
result = converter._convert_doc_to_docx(Path("test.doc"))
assert result is None
def test_convert_doc_to_docx_timeout(self):
"""Test .doc conversion timeout handling."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_find_libreoffice_command', return_value='libreoffice'):
with patch('subprocess.run', side_effect=Exception("Timeout")):
result = converter._convert_doc_to_docx(Path("test.doc"))
assert result is None
@pytest.mark.parametrize("extension", ['.xlsx', '.xls', '.xlsm'])
def test_excel_extensions_routed_correctly(self, extension):
"""Test that all Excel extensions are routed to Excel converter."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_convert_excel_to_html', return_value="test") as mock_excel:
converter.convert_to_html(f"test{extension}")
assert mock_excel.called
@pytest.mark.parametrize("extension", ['.docx', '.doc', '.docm'])
def test_word_extensions_routed_correctly(self, extension):
"""Test that all Word extensions are routed to Word converter."""
converter = DocumentToHtmlConverter()
with patch.object(converter, '_convert_word_to_markdown', return_value="# Test") as mock_word:
converter.convert_to_html(f"test{extension}")
assert mock_word.called
class TestConvenienceFunctions:
"""Test suite for convenience functions."""
def test_convert_excel_to_html(self):
"""Test convert_excel_to_html convenience function."""
from src.extraction_v2.document_converter import convert_excel_to_html
with patch.object(DocumentToHtmlConverter, 'convert_to_html', return_value="test"):
result = convert_excel_to_html("test.xlsx")
assert result == "test"
def test_convert_word_to_markdown(self):
"""Test convert_word_to_markdown convenience function."""
from src.extraction_v2.document_converter import convert_word_to_markdown
with patch.object(DocumentToHtmlConverter, 'convert_to_html', return_value="# Test"):
result = convert_word_to_markdown("test.docx")
assert result == "# Test"