Add functionality to properly handle PDF content:
- Add parse_markdown_text_to_tables method to separate tables and text
- Fix load_data implementation to properly process documents
- Fix lazy_load_data method
- Improve document metadata handling for tables and text sections

The loader now correctly processes PDFs through Mathpix API and converts content to proper Document objects.

…ation

Remove early returns using super() in load_data and lazy_load_data methods that were preventing the actual implementation from being executed. This fixes the "not implemented" error while maintaining the full PDF reader functionality.