"""Rich-text HTML sanitization (XSS defense) using nh3 (ammonia bindings).
Applied server-side to every rich-text field before it is stored."""
import nh3

_ALLOWED_TAGS = {
    "p", "br", "div", "span",
    "strong", "b", "em", "i", "u", "s", "sub", "sup",
    "ul", "ol", "li",
    "h1", "h2", "h3", "h4",
    "blockquote", "pre", "code",
    "a", "hr", "table", "thead", "tbody", "tr", "th", "td",
}

_ALLOWED_ATTRIBUTES = {
    "a": {"href", "title"},
    "th": {"colspan", "rowspan"},
    "td": {"colspan", "rowspan"},
}


def sanitize_html(value: str | None) -> str | None:
    if value is None:
        return None
    cleaned = nh3.clean(
        value,
        tags=_ALLOWED_TAGS,
        attributes=_ALLOWED_ATTRIBUTES,
        link_rel="noopener noreferrer",
        url_schemes={"http", "https", "mailto"},
    )
    return cleaned