// author: simon-pierre boucher <contact@spboucher.ai>
import { parse } from "./dom.js";
import type { PageLink } from "./types.js";

export function extractLinksFromHtml(html: string, base: string): PageLink[] {
  return extractLinks(parse(html).document, base);
}

export function extractLinks(document: Document, base: string): PageLink[] {
  let baseHost: string;
  try {
    baseHost = new URL(base).hostname.toLowerCase();
  } catch {
    baseHost = "";
  }

  const seen = new Set<string>();
  const links: PageLink[] = [];
  for (const a of Array.from(document.querySelectorAll("a[href]"))) {
    const raw = a.getAttribute("href");
    if (raw === null || raw === "" || /^(javascript:|mailto:|tel:|#)/i.test(raw)) continue;
    let abs: URL;
    try {
      abs = new URL(raw, base);
    } catch {
      continue;
    }
    if (abs.protocol !== "http:" && abs.protocol !== "https:") continue;
    const url = abs.toString();
    if (seen.has(url)) continue;
    seen.add(url);
    links.push({
      url,
      text: (a.textContent ?? "").replace(/\s+/g, " ").trim(),
      rel: a.getAttribute("rel"),
      isInternal: abs.hostname.toLowerCase() === baseHost,
    });
  }
  return links;
}