From 357eac26aea70cfe183b90ff3ce0da97501a3788 Mon Sep 17 00:00:00 2001 From: RussellLuo Date: Thu, 2 Jul 2026 21:57:43 +0800 Subject: [PATCH] fix(converter): move keep_data_uris to convert call and fix lint --- openkb/converter.py | 4 ++-- tests/test_converter.py | 9 ++++++--- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/openkb/converter.py b/openkb/converter.py index 46d6bf5f..710d7a77 100644 --- a/openkb/converter.py +++ b/openkb/converter.py @@ -231,8 +231,8 @@ def convert_document( markdown = convert_pdf_with_images(src, doc_name, images_dir) else: # Non-PDF, non-MD: use markitdown (docx, pptx, html, etc.) - mid = MarkItDown(keep_data_uris=True) - result = mid.convert(str(src)) + mid = MarkItDown() + result = mid.convert(str(src), keep_data_uris=True) markdown = result.text_content markdown = extract_base64_images(markdown, doc_name, images_dir) diff --git a/tests/test_converter.py b/tests/test_converter.py index d39442d6..1349b6fb 100644 --- a/tests/test_converter.py +++ b/tests/test_converter.py @@ -146,14 +146,17 @@ def test_docx_conversion_enables_keep_data_uris(self, kb_dir, tmp_path): with ( patch("openkb.converter.MarkItDown") as mock_markitdown, - patch("openkb.converter.extract_base64_images", return_value="converted markdown") as mock_extract, + patch( + "openkb.converter.extract_base64_images", + return_value="converted markdown", + ) as mock_extract, ): mock_markitdown.return_value.convert.return_value = mock_result result = convert_document(src, kb_dir) - mock_markitdown.assert_called_once_with(keep_data_uris=True) - mock_markitdown.return_value.convert.assert_called_once_with(str(src)) + mock_markitdown.assert_called_once_with() + mock_markitdown.return_value.convert.assert_called_once_with(str(src), keep_data_uris=True) mock_extract.assert_called_once() assert result.skipped is False assert result.is_long_doc is False