import { isIP } from "node:net";

const PRIVATE_HOSTS = new Set(["localhost", "localhost.localdomain"]);
const HTML_ENTITIES: Record<string, string> = {
  amp: "&", lt: "<", gt: ">", quot: '"', apos: "'", nbsp: " ",
};

function isPrivateIp(host: string): boolean {
  const normalized = host.replace(/^\[|\]$/g, "").toLowerCase();
  if (!isIP(normalized)) return false;
  if (normalized === "::1" || normalized === "::" || normalized.startsWith("fc") || normalized.startsWith("fd") || normalized.startsWith("fe8") || normalized.startsWith("fe9") || normalized.startsWith("fea") || normalized.startsWith("feb")) return true;
  const octets = normalized.split(".").map(Number);
  if (octets.length !== 4) return false;
  return octets[0] === 10 || octets[0] === 127 || octets[0] === 0 ||
    (octets[0] === 169 && octets[1] === 254) ||
    (octets[0] === 172 && octets[1] >= 16 && octets[1] <= 31) ||
    (octets[0] === 192 && octets[1] === 168);
}

export function validateFetchUrl(raw: string): URL {
  let url: URL;
  try { url = new URL(raw); } catch { throw new Error("fetch_url requer uma URL HTTP(S) válida."); }
  if (url.protocol !== "http:" && url.protocol !== "https:") throw new Error("fetch_url aceita apenas HTTP(S).");
  if (url.username || url.password) throw new Error("fetch_url não aceita credenciais na URL.");
  const host = url.hostname.toLowerCase();
  if (PRIVATE_HOSTS.has(host) || host.endsWith(".localhost") || isPrivateIp(host)) {
    throw new Error("fetch_url bloqueou host local ou IP privado.");
  }
  return url;
}

export function htmlToText(html: string): string {
  return html
    .replace(/<(script|style|noscript|svg)[^>]*>[\s\S]*?<\/\1>/gi, "")
    .replace(/<\s*br\s*\/?>/gi, "\n")
    .replace(/<\/(p|div|li|h[1-6]|tr|section|article)>/gi, "\n")
    .replace(/<[^>]+>/g, "")
    .replace(/&(#x[0-9a-f]+|#\d+|[a-z]+);/gi, (_, entity: string) => {
      if (entity.startsWith("#x")) return String.fromCodePoint(Number.parseInt(entity.slice(2), 16));
      if (entity.startsWith("#")) return String.fromCodePoint(Number.parseInt(entity.slice(1), 10));
      return HTML_ENTITIES[entity.toLowerCase()] ?? `&${entity};`;
    })
    .replace(/[ \t]+/g, " ")
    .replace(/\n\s*\n+/g, "\n")
    .trim();
}

export function truncatePage(text: string, maxChars = 50_000): string {
  return text.length <= maxChars ? text : `${text.slice(0, maxChars)}\n\n[conteúdo truncado]`;
}

export async function fetchPage(rawUrl: string, signal?: AbortSignal): Promise<{ url: string; text: string }> {
  const url = validateFetchUrl(rawUrl);
  const timeout = AbortSignal.timeout(20_000);
  const combined = signal ? AbortSignal.any([signal, timeout]) : timeout;
  const response = await fetch(url, {
    signal: combined,
    redirect: "error",
    headers: { "user-agent": "pi-research-agent/1.0", accept: "text/html,text/plain,application/json" },
  });
  if (!response.ok) throw new Error(`fetch_url: HTTP ${response.status}`);
  const body = await response.text();
  const contentType = response.headers.get("content-type") ?? "";
  return { url: url.href, text: truncatePage(contentType.includes("html") ? htmlToText(body) : body) };
}