Function parse_readme

website/readme_parser.py:436–462

Parse README.md text into grouped categories. Returns a list of ParsedGroup dicts containing nested categories. Content between the Projects heading and Resources or Contributing is parsed as categories grouped by bold markers (**Group Name**).

(text: str)

def parse_readme(text: str) -> list[ParsedGroup]:
    """Parse README.md text into grouped categories.

    Returns a list of ParsedGroup dicts containing nested categories.
    Content between the Projects heading and Resources or Contributing is parsed
    as categories grouped by bold markers (**Group Name**).
    """
    md = MarkdownIt("commonmark")
    tokens = md.parse(text)
    root = SyntaxTreeNode(tokens)
    children = root.children

    # Find Projects and section boundaries in one pass.
    projects_idx = None
    cat_end_idx = None
    for i, node in enumerate(children):
        if _heading_level(node) in (1, 2):
            text_content = _heading_text(node)
            if projects_idx is None and text_content == "Projects":
                projects_idx = i
            elif cat_end_idx is None and text_content in ("Resources", "Contributing"):
                cat_end_idx = i
    if projects_idx is None:
        return []

    cat_nodes = children[projects_idx + 1 : cat_end_idx or len(children)]
    return _parse_grouped_sections(cat_nodes)