-- HTML to Markdown conversion tests
SELECT rag.markdown_from_html('<p>Hello</p>');
 markdown_from_html 
--------------------
 Hello
(1 row)

SELECT rag.markdown_from_html('<p>Hello <i>world</i></p>');
 markdown_from_html 
--------------------
 Hello _world_
(1 row)

SELECT rag.markdown_from_html('<h1>Title</h1><p>Paragraph</p>');
 markdown_from_html 
--------------------
 # Title           +
                   +
 Paragraph
(1 row)

SELECT rag.markdown_from_html('<ul><li>Item 1</li><li>Item 2</li></ul>');
 markdown_from_html 
--------------------
 *   Item 1        +
 *   Item 2
(1 row)

SELECT rag.markdown_from_html('<a href="https://example.com">Link</a>');
     markdown_from_html      
-----------------------------
 [Link](https://example.com)
(1 row)

-- Note: text_from_pdf and text_from_docx require binary input which is harder to test in regression tests
-- We'll test that the functions exist and have the right signature
SELECT 'text_from_pdf_exists' AS test_name,
       count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_pdf'
  AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
      test_name       | result 
----------------------+--------
 text_from_pdf_exists | t
(1 row)

SELECT 'text_from_docx_exists' AS test_name,
       count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_docx'
  AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
       test_name       | result 
-----------------------+--------
 text_from_docx_exists | t
(1 row)