// author: simon-pierre boucher <contact@spboucher.ai>
import { describe, expect, it } from "vitest";
import { parseSitemap } from "./sitemap.js";

describe("parseSitemap", () => {
  it("parses a urlset with lastmod", () => {
    const xml = `<?xml version="1.0"?><urlset>
      <url><loc>https://e.com/a</loc><lastmod>2026-01-01</lastmod></url>
      <url><loc>https://e.com/b</loc></url>
    </urlset>`;
    const r = parseSitemap(xml);
    expect(r.urls).toEqual([
      { loc: "https://e.com/a", lastModified: "2026-01-01" },
      { loc: "https://e.com/b" },
    ]);
    expect(r.childSitemaps).toEqual([]);
  });

  it("parses a sitemap index into child sitemaps", () => {
    const xml = `<sitemapindex>
      <sitemap><loc>https://e.com/sitemap-1.xml</loc></sitemap>
      <sitemap><loc>https://e.com/sitemap-2.xml</loc></sitemap>
    </sitemapindex>`;
    const r = parseSitemap(xml);
    expect(r.childSitemaps).toEqual(["https://e.com/sitemap-1.xml", "https://e.com/sitemap-2.xml"]);
    expect(r.urls).toEqual([]);
  });

  it("decodes entities and CDATA in loc", () => {
    const xml = `<urlset><url><loc>https://e.com/s?a=1&amp;b=2</loc></url>
      <url><loc><![CDATA[https://e.com/c]]></loc></url></urlset>`;
    const r = parseSitemap(xml);
    expect(r.urls[0]?.loc).toBe("https://e.com/s?a=1&b=2");
    expect(r.urls[1]?.loc).toBe("https://e.com/c");
  });

  it("falls back to bare <loc> tags", () => {
    const r = parseSitemap("<loc>https://e.com/x</loc><loc>https://e.com/y</loc>");
    expect(r.urls.map((u) => u.loc)).toEqual(["https://e.com/x", "https://e.com/y"]);
  });
});