utils/markdown_utils.py

"""
Markdown utilities for converting markdown to HTML.
"""

import re
import html


def convert_markdown_to_html(markdown_text: str) -> str:
    """
    Convert markdown text to HTML with basic formatting.
    
    Args:
        markdown_text: The markdown text to convert
        
    Returns:
        HTML formatted string
    """
    if not markdown_text or not isinstance(markdown_text, str):
        return ""
    
    # Escape HTML special characters first
    text = html.escape(markdown_text.strip())
    
    # Convert markdown to HTML
    # Headers
    text = re.sub(r'^### (.*?)$', r'<h3>\1</h3>', text, flags=re.MULTILINE)
    text = re.sub(r'^## (.*?)$', r'<h2>\1</h2>', text, flags=re.MULTILINE)
    text = re.sub(r'^# (.*?)$', r'<h1>\1</h1>', text, flags=re.MULTILINE)
    
    # Bold text
    text = re.sub(r'\*\*(.*?)\*\*', r'<strong>\1</strong>', text)
    text = re.sub(r'__(.*?)__', r'<strong>\1</strong>', text)
    
    # Special handling for "Confidence Notes:" to ensure proper styling
    text = re.sub(r'<strong>Confidence Notes:</strong>', r'<strong style="color: #212529 !important;">Confidence Notes:</strong>', text)
    text = re.sub(r'\*\*Confidence Notes:\*\*', r'<strong style="color: #212529 !important;">Confidence Notes:</strong>', text)
    
    # Italic text
    text = re.sub(r'\*(.*?)\*', r'<em>\1</em>', text)
    text = re.sub(r'_(.*?)_', r'<em>\1</em>', text)
    
    # Code blocks (triple backticks)
    text = re.sub(r'```(.*?)```', r'<pre><code>\1</code></pre>', text, flags=re.DOTALL)
    
    # Inline code
    text = re.sub(r'`(.*?)`', r'<code>\1</code>', text)
    
    # Convert line breaks to paragraphs
    paragraphs = text.split('\n\n')
    html_paragraphs = []
    
    for paragraph in paragraphs:
        paragraph = paragraph.strip()
        if paragraph:
            # Check if it's already wrapped in HTML tags
            if not (paragraph.startswith('<') and paragraph.endswith('>')):
                # Replace single line breaks with <br>
                paragraph = paragraph.replace('\n', '<br>')
                paragraph = f'<p>{paragraph}</p>'
            html_paragraphs.append(paragraph)
    
    return '\n'.join(html_paragraphs)