import { metadata as homeMetadata } from '@/app/page';
import { metadata as rankingsMetadata } from '@/app/rankings/page';
import { metadata as admissionsMetadata } from '@/app/admissions/page';
import { generateMetadata as compareMetadata } from '@/app/compare/page';

describe('canonical URLs', () => {
  it('the homepage canonicalises to the bare root', () => {
    // page.tsx reads eleven search params. Without this, every filter
    // combination is a crawlable near-duplicate of the one page we want to
    // rank for "compare schools".
    expect(homeMetadata.alternates?.canonical)
      .toBe('https://www.schoolcompare.co.uk/');
  });

  it('rankings canonicalises to the bare path', () => {
    expect(rankingsMetadata.alternates?.canonical)
      .toBe('https://www.schoolcompare.co.uk/rankings');
  });

  it('admissions canonicalises to the bare path', () => {
    expect(admissionsMetadata.alternates?.canonical)
      .toBe('https://www.schoolcompare.co.uk/admissions');
  });
});

describe('/compare indexability', () => {
  it('the bare compare page is indexable and canonical to itself', async () => {
    // This is the landing page for the "compare schools" head term.
    const meta = await compareMetadata({ searchParams: Promise.resolve({}) });
    expect(meta.alternates?.canonical)
      .toBe('https://www.schoolcompare.co.uk/compare');
    expect(meta.robots).toBeUndefined();
  });

  it('a comparison of specific schools is noindex, follow', async () => {
    // ~317 million pairs before triples. Indexing the parameter space would
    // swamp everything else in the corpus.
    const meta = await compareMetadata({
      searchParams: Promise.resolve({ urns: '100001,100002' }),
    });
    expect(meta.robots).toEqual({ index: false, follow: true });
  });

  it('a parameterised comparison still canonicalises to the bare path', async () => {
    // follow:true plus a canonical means the outbound links to each school
    // page still pass value even though this URL is not indexed.
    const meta = await compareMetadata({
      searchParams: Promise.resolve({ urns: '100001,100002' }),
    });
    expect(meta.alternates?.canonical)
      .toBe('https://www.schoolcompare.co.uk/compare');
  });
});

/*
 * W8 — snippet copy for the C1 cluster.
 *
 * The baseline (GSC, 16 months to 2026-08-20) showed these pages ranking on
 * page one and converting at a tenth of the normal rate: "compare school
 * performance" at position 6.1 with 0.43% CTR, against 9.16% for the brand
 * query from the same neighbourhood. The SERP is dominated by the DfE's own
 * "Compare school performance" service, so the job of this copy is to say
 * what that service does not offer, without losing intent match on the title.
 *
 * These tests guard the mechanics that make a snippet work — length, intent
 * keyword, differentiator, no brand-first — not the exact wording, which
 * should stay free to iterate.
 */

// Google truncates titles near 60 characters and descriptions near 155.
const TITLE_MAX = 60;
const DESC_MIN = 110;
const DESC_MAX = 155;

type Meta = { title?: unknown; description?: unknown };
const titleOf = (m: Meta): string => {
  const t = m.title as string | { absolute?: string } | undefined;
  return typeof t === 'string' ? t : (t?.absolute ?? '');
};

describe('C1 snippet copy', () => {
  const pages: Array<[string, Meta, RegExp]> = [
    ['home', homeMetadata as Meta, /compare schools/i],
    ['rankings', rankingsMetadata as Meta, /league table/i],
    ['admissions', admissionsMetadata as Meta, /admission/i],
  ];

  for (const [name, meta, intent] of pages) {
    it(`${name}: title carries the search intent and fits the SERP`, () => {
      const t = titleOf(meta);
      expect(t).toMatch(intent);
      expect(t.length).toBeLessThanOrEqual(TITLE_MAX);
    });

    it(`${name}: title does not open with the brand`, () => {
      // The measured 0.43% CTR came from a brand-first title. The most
      // valuable pixels go to the thing the searcher typed.
      expect(titleOf(meta).toLowerCase().startsWith('schoolcompare')).toBe(false);
    });

    it(`${name}: description is long enough to be worth reading, short enough to survive`, () => {
      const d = meta.description as string;
      expect(d.length).toBeGreaterThanOrEqual(DESC_MIN);
      expect(d.length).toBeLessThanOrEqual(DESC_MAX);
    });
  }

  it('the homepage description names what gov.uk does not publish', () => {
    // Admissions distance is the one fact the DfE service has no equivalent
    // for. If it ever leaves this description, the snippet is competing with
    // gov.uk on gov.uk's own ground.
    expect(homeMetadata.description).toMatch(/close you had to live|distance/i);
  });

  it('/compare targets the tool phrasing rather than repeating the homepage', () => {
    // Two pages chasing one phrase is how a site competes with itself.
    return compareMetadata({ searchParams: Promise.resolve({}) }).then((m) => {
      expect(m.title).toMatch(/comparison tool/i);
      expect(m.title).not.toBe(titleOf(homeMetadata as Meta));
    });
  });

  it('no C1 page claims a school count that will drift', () => {
    // The corpus moves with every data refresh; this repo has already shipped
    // one copy bug of that kind ("three schools" against MAX_SCHOOLS = 5).
    for (const [, meta] of pages) {
      expect(meta.description as string).not.toMatch(/\b\d{2},\d{3}\b|\b\d{2},000\b/);
    }
  });
});