"""Backend HTML sanitization for scraped Post.description.

Provenance descriptions come from gallery-dl (untrusted third-party HTML).
We render them via v-html in the UI sub-slice, so they MUST be sanitized
server-side to a tight allowlist. nh3 (Rust/ammonia bindings) is used;
bleach is deprecated upstream and intentionally not used.
"""

import nh3

# A faithful-but-safe set: enough to reproduce the SEMANTIC look of a scraped
# post body (headings, lists, quotes, code, inline images, links, line breaks +
# inline emphasis) without layout-injection wrappers. `div`/`span` are
# deliberately NOT allowed — their text is preserved by nh3 and they only carry
# source-site layout/styling we don't want to import (a test pins this).
ALLOWED_TAGS = {
    "p", "a", "br", "em", "strong", "b", "i", "u", "s",
    "ul", "ol", "li", "blockquote",
    "h1", "h2", "h3", "h4", "h5", "h6", "hr",
    "pre", "code", "img", "figure", "figcaption",
}
ALLOWED_ATTRIBUTES = {
    "a": {"href", "title", "target"},
    "img": {"src", "alt", "title", "width", "height"},
}
# http/https for hotlinked source images today; relative URLs (e.g. a local
# `/api/...` src once inline images are captured) pass through nh3 untouched.
ALLOWED_URL_SCHEMES = {"http", "https"}


def sanitize_post_html(raw: str | None) -> str | None:
    """Return sanitized HTML, or None for null/empty/whitespace input.

    - keeps only ALLOWED_TAGS / ALLOWED_ATTRIBUTES
    - only http/https hrefs survive (javascript: etc. dropped)
    - <script> content removed entirely
    - all <a> get rel="noopener noreferrer" (nh3 default link_rel)
    - never raises
    """
    if raw is None:
        return None
    stripped = raw.strip()
    if not stripped:
        return None
    return nh3.clean(
        stripped,
        tags=ALLOWED_TAGS,
        attributes=ALLOWED_ATTRIBUTES,
        url_schemes=ALLOWED_URL_SCHEMES,
        link_rel="noopener noreferrer",
        clean_content_tags={"script", "style"},
    )