Merge pull request 'feat(data): publish England only, dropping Welsh and overseas establishments' (#107) from feat/england-only-corpus into main

Reviewed-on: #107

e2e/tests/journeys.spec.ts

@@ -1473,3 +1473,104 @@ test('no single section dominates the height of a school page', async ({ page })
       + sections.map((s) => `${s.id}=${s.h}`).join(', '),
   ).toBeLessThan(2.5);
 });
+
+/*
+ * England-only corpus.
+ *
+ * GIAS ships the whole UK plus overseas and offshore establishments, none of
+ * which carry comparable DfE performance data. dim_school and dim_location
+ * exclude them (vars.non_england_school_type_codes in dbt_project.yml), which
+ * keeps them out of the site, the filter lists and the sitemap together.
+ *
+ * These assert the published surface, not the warehouse: the dbt test
+ * assert_england_only_schools guards the marts, and these guard what the
+ * environment actually serves once the marts have been rebuilt.
+ */
+
+const WELSH_AUTHORITIES = [
+  'Blaenau Gwent', 'Bridgend', 'Caerphilly', 'Cardiff', 'Carmarthenshire',
+  'Ceredigion', 'Conwy', 'Denbighshire', 'Flintshire', 'Gwynedd',
+  'Isle of Anglesey', 'Merthyr Tydfil', 'Monmouthshire', 'Neath Port Talbot',
+  'Newport', 'Pembrokeshire', 'Powys', 'Rhondda Cynon Taf', 'Swansea',
+  'Torfaen', 'Vale of Glamorgan', 'Wrexham',
+];
+
+const NON_ENGLAND_AUTHORITIES = [
+  'BFPO Overseas Establishments', 'Fieldwork Overseas Establishments',
+  'Gibraltar Overseas Establishments', 'Guernsey Offshore Establishments',
+  'Isle of Man Offshore Establishments', 'Jersey Offshore Establishments',
+  'Scotland Offshore Establishments',
+];
+
+const NON_ENGLAND_TYPES = [
+  'Welsh establishment', 'Offshore schools',
+  "Service children's education", 'British schools overseas',
+];
+
+test('the local authority filter offers no Welsh or overseas authority', async ({ page }) => {
+  const res = await page.request.get('/api/filters');
+  expect(res.ok()).toBeTruthy();
+  const { local_authorities: las } = await res.json();
+
+  expect(Array.isArray(las)).toBeTruthy();
+  // Guards against the list being empty, which would pass the check below
+  // for the wrong reason.
+  expect(las.length).toBeGreaterThan(100);
+
+  const leaked = [...WELSH_AUTHORITIES, ...NON_ENGLAND_AUTHORITIES]
+    .filter((la) => las.includes(la));
+  expect(leaked, `non-England authorities still offered: ${leaked.join(', ')}`)
+    .toEqual([]);
+});
+
+test('the school type filter offers no non-England establishment type', async ({ page }) => {
+  const res = await page.request.get('/api/filters');
+  expect(res.ok()).toBeTruthy();
+  const { school_types: types } = await res.json();
+
+  expect(Array.isArray(types)).toBeTruthy();
+  expect(types.length).toBeGreaterThan(10);
+
+  const leaked = NON_ENGLAND_TYPES.filter((t) => types.includes(t));
+  expect(leaked, `non-England types still offered: ${leaked.join(', ')}`)
+    .toEqual([]);
+});
+
+test('searching a Welsh authority by name returns no schools', async ({ page }) => {
+  // Cardiff held 144 Welsh establishments and nothing else, so the authority
+  // should now be absent from the corpus entirely rather than merely thinned.
+  const res = await page.request.get('/api/schools?local_authority=Cardiff&page_size=1');
+  expect(res.ok()).toBeTruthy();
+  const body = await res.json();
+  expect(body.total ?? (body.schools ?? []).length).toBe(0);
+});
+
+test('a Welsh school URL 404s while an English one still resolves', async ({ page }) => {
+  // Paired on purpose: the Welsh assertion alone would also pass if the whole
+  // site were down, which is the failure this test most needs to distinguish.
+  const english = await page.request.get('/api/schools?search=primary&per_page=1');
+  expect(english.ok()).toBeTruthy();
+  const [first] = (await english.json()).schools ?? [];
+  expect(first, 'no English school available to compare against').toBeTruthy();
+
+  const good = await page.goto(`/school/${first.urn}-x`);
+  expect(good?.status(), 'an English school should still resolve').toBeLessThan(400);
+
+  // Adamsdown Primary School, Cardiff — a Welsh establishment (URN 401559).
+  const welsh = await page.goto('/school/401559-adamsdown-primary-school');
+  expect(welsh?.status(), 'a Welsh school should no longer resolve').toBe(404);
+});
+
+test('the sitemap submits no Welsh or overseas school', async ({ page }) => {
+  const res = await page.request.get('/sitemap.xml');
+  expect(res.ok()).toBeTruthy();
+  const xml = await res.text();
+
+  const urlCount = (xml.match(/<url>/g) ?? []).length;
+  expect(urlCount, 'sitemap looks empty or truncated').toBeGreaterThan(1000);
+
+  // 401559 (Cardiff) and 402426 (ACT Schools, Cardiff) were both submitted
+  // before the England-only filter landed.
+  expect(xml).not.toContain('/school/401559');
+  expect(xml).not.toContain('/school/402426');
+});