// author: simon-pierre boucher <contact@spboucher.ai>
import type { PageMetadata, StructuredData } from "./types.js";

function flattenJsonLd(node: unknown, out: unknown[]): void {
  if (Array.isArray(node)) {
    for (const item of node) flattenJsonLd(item, out);
    return;
  }
  if (node !== null && typeof node === "object") {
    const obj = node as Record<string, unknown>;
    if ("@graph" in obj) {
      flattenJsonLd(obj["@graph"], out);
      const rest = { ...obj };
      delete rest["@graph"];
      delete rest["@context"];
      if (Object.keys(rest).length > 0) out.push(rest);
      return;
    }
    out.push(obj);
  }
}

function harvestJsonLd(document: Document): unknown[] {
  const out: unknown[] = [];
  for (const el of Array.from(document.querySelectorAll('script[type="application/ld+json"]'))) {
    const raw = el.textContent ?? "";
    if (raw.trim() === "") continue;
    try {
      flattenJsonLd(JSON.parse(raw), out);
    } catch {
      continue;
    }
  }
  return out;
}

function harvestMetaPrefixed(document: Document, attr: "property" | "name", prefix: string): Record<string, string> {
  const map: Record<string, string> = {};
  for (const el of Array.from(document.querySelectorAll(`meta[${attr}^="${prefix}"]`))) {
    const key = (el.getAttribute(attr) ?? "").slice(prefix.length);
    const content = el.getAttribute("content");
    if (key !== "" && content !== null && !(key in map)) map[key] = content;
  }
  return map;
}

function metaContent(document: Document, name: string): string | undefined {
  const el = document.querySelector(`meta[name="${name}" i]`);
  const content = el?.getAttribute("content");
  return content !== null && content !== undefined && content !== "" ? content : undefined;
}

function firstDefined(...values: Array<string | undefined>): string | undefined {
  for (const v of values) if (v !== undefined && v !== "") return v;
  return undefined;
}

function jsonLdString(nodes: unknown[], types: string[], keys: string[]): string | undefined {
  for (const node of nodes) {
    if (node === null || typeof node !== "object") continue;
    const obj = node as Record<string, unknown>;
    const t = obj["@type"];
    const typeStr = Array.isArray(t) ? t.map(String) : typeof t === "string" ? [t] : [];
    if (types.length > 0 && !typeStr.some((x) => types.includes(x))) continue;
    for (const key of keys) {
      const val = obj[key];
      if (typeof val === "string" && val !== "") return val;
      if (Array.isArray(val) && typeof val[0] === "string" && val[0] !== "") return val[0];
      if (val !== null && typeof val === "object") {
        const obj2 = val as Record<string, unknown>;
        for (const nested of ["name", "url"]) {
          const nv = obj2[nested];
          if (typeof nv === "string" && nv !== "") return nv;
        }
      }
    }
  }
  return undefined;
}

export function harvestStructured(document: Document): { metadata: PageMetadata; structured: StructuredData } {
  const jsonld = harvestJsonLd(document);
  const openGraph = harvestMetaPrefixed(document, "property", "og:");
  const twitter = harvestMetaPrefixed(document, "name", "twitter:");
  const structured: StructuredData = { jsonld, openGraph, twitter };

  const htmlLang = document.querySelector("html")?.getAttribute("lang") ?? undefined;
  const canonical = document.querySelector('link[rel="canonical"]')?.getAttribute("href") ?? undefined;
  const docTitle = firstDefined(document.querySelector("title")?.textContent?.trim());
  const h1 = firstDefined(document.querySelector("h1")?.textContent?.trim());

  let firstPara: string | undefined;
  for (const p of Array.from(document.querySelectorAll("p"))) {
    const text = (p.textContent ?? "").trim();
    if (text.length > 100) {
      firstPara = text;
      break;
    }
  }

  const metadata: PageMetadata = {};
  const set = <K extends keyof PageMetadata>(key: K, value: PageMetadata[K] | undefined): void => {
    if (value !== undefined) metadata[key] = value;
  };

  set("title", firstDefined(jsonLdString(jsonld, [], ["headline", "name"]), openGraph["title"], docTitle, h1));
  set(
    "description",
    firstDefined(jsonLdString(jsonld, [], ["description"]), openGraph["description"], metaContent(document, "description"), firstPara),
  );
  set("author", firstDefined(jsonLdString(jsonld, [], ["author"]), metaContent(document, "author")));
  set("image", firstDefined(jsonLdString(jsonld, [], ["image"]), openGraph["image"], twitter["image"]));
  set("siteName", firstDefined(openGraph["site_name"]));
  set("type", firstDefined(openGraph["type"]));
  set("publishedTime", firstDefined(jsonLdString(jsonld, [], ["datePublished"]), openGraph["article:published_time"]));
  set("modifiedTime", firstDefined(jsonLdString(jsonld, [], ["dateModified"]), openGraph["article:modified_time"]));
  set("canonical", canonical);
  set("lang", htmlLang);

  const keywords = metaContent(document, "keywords");
  if (keywords !== undefined) {
    const list = keywords.split(",").map((k) => k.trim()).filter((k) => k !== "");
    if (list.length > 0) metadata.keywords = list;
  }

  return { metadata, structured };
}