def get_autodoc_sections_helper()

in src/doc_builder/build_embeddings.py [0:0]

• 61 lines of code
• 18 McCabe index (conditional complexity)

def get_autodoc_sections_helper(markdown_text: str) -> List[dict[str, any]]:
    """
    Split markdown text by headings and include parent headings for each section.

    Args:
        markdown_text (str): The input markdown text

    Returns:
        List of dictionaries, each containing:
        - 'heading': the current section heading
        - 'parent_headings': list of parent headings (from highest to lowest level)
        - 'full_heading_path': complete heading path as string
        - 'content': the text content of the section
        - 'level': heading level (1 for #, 2 for ##, etc.)
    """
    lines = markdown_text.split("\n")
    sections = []

    # Pattern to match headings (# ## ### etc.)
    heading_pattern = r"^(#+)\s+(.+)$"

    # Keep track of heading hierarchy
    heading_stack = []  # Stack to maintain parent headings
    current_content = []

    for line in lines:
        heading_match = re.match(heading_pattern, line)

        if heading_match:
            # Save previous section if it exists
            if heading_stack or current_content:
                if heading_stack:
                    sections.append(
                        {
                            "heading": heading_stack[-1]["text"],
                            "parent_headings": [h["text"] for h in heading_stack[:-1]],
                            "full_heading_path": " > ".join([h["text"] for h in heading_stack]),
                            "content": "\n".join(current_content).strip(),
                            "level": heading_stack[-1]["level"],
                        }
                    )
                else:
                    # Content before any heading
                    sections.append(
                        {
                            "heading": "",
                            "parent_headings": [],
                            "full_heading_path": "",
                            "content": "\n".join(current_content).strip(),
                            "level": 0,
                        }
                    )

            # Process new heading
            level = len(heading_match.group(1))
            heading_text = heading_match.group(2).strip()
            full_heading = heading_match.group(1) + " " + heading_text

            # Update heading stack based on level
            # Remove headings at same or lower level
            while heading_stack and heading_stack[-1]["level"] >= level:
                heading_stack.pop()

            # Add current heading to stack
            heading_stack.append({"text": full_heading, "level": level})

            # Reset content for new section
            current_content = []
        else:
            # Add line to current section content
            current_content.append(line)

    # Don't forget the last section
    if heading_stack or current_content:
        if heading_stack:
            sections.append(
                {
                    "heading": heading_stack[-1]["text"],
                    "parent_headings": [h["text"] for h in heading_stack[:-1]],
                    "full_heading_path": " > ".join([h["text"] for h in heading_stack]),
                    "content": "\n".join(current_content).strip(),
                    "level": heading_stack[-1]["level"],
                }
            )
        else:
            # Content at the end without heading
            sections.append(
                {
                    "heading": "",
                    "parent_headings": [],
                    "full_heading_path": "",
                    "content": "\n".join(current_content).strip(),
                    "level": 0,
                }
            )

    return sections