Function _parse_grouped_sections

website/readme_parser.py:308–360

Parse nodes into groups of categories using bold markers as group boundaries. Bold-only paragraphs (**Group Name**) delimit groups. H3 headings under each bold marker become categories within that group. Categories appearing before any bold marker go into an "Other" group.

(
    nodes: list[SyntaxTreeNode],
)

def _parse_grouped_sections(
    nodes: list[SyntaxTreeNode],
) -> list[ParsedGroup]:
    """Parse nodes into groups of categories using bold markers as group boundaries.

    Bold-only paragraphs (**Group Name**) delimit groups. H3 headings under each
    bold marker become categories within that group. Categories appearing before
    any bold marker go into an "Other" group.
    """
    groups: list[ParsedGroup] = []
    current_group_name: str | None = None
    current_group_cats: list[ParsedSection] = []
    current_cat_name: str | None = None
    current_cat_body: list[SyntaxTreeNode] = []

    def flush_cat() -> None:
        nonlocal current_cat_name
        if current_cat_name is None:
            return
        current_group_cats.append(_build_section(current_cat_name, current_cat_body))
        current_cat_name = None

    def flush_group() -> None:
        nonlocal current_group_name, current_group_cats
        if current_group_cats:
            name = current_group_name or "Other"
            groups.append(
                ParsedGroup(
                    name=name,
                    slug=slugify(name),
                    categories=list(current_group_cats),
                )
            )
        current_group_name = None
        current_group_cats = []

    for node in nodes:
        bold_name = _is_bold_marker(node)
        if bold_name is not None:
            flush_cat()
            flush_group()
            current_group_name = bold_name
            current_cat_body = []
        elif node.type == "heading" and node.tag in ("h2", "h3"):
            flush_cat()
            current_cat_name = _heading_text(node)
            current_cat_body = []
        elif current_cat_name is not None:
            current_cat_body.append(node)

    flush_cat()
    flush_group()
    return groups


_SPONSOR_SEP_RE = re.compile(r"^\s*[:\-\u2013\u2014]\s*")