Merge pull request 'fix(seo): crawl hygiene and a per-family sitemap index (W1)' (#108) from feat/seo-crawl-hygiene into feat/england-only-corpus

Reviewed-on: #108

e2e/tests/journeys.spec.ts

@@ -1252,11 +1252,7 @@ test('a published cut-off distance is shown with the year it belongs to', async
   await expect(label).toContainText(`September ${found!.distance.year}`);
 
   // And the figure itself, in the unit councils publish in.
-  // No trailing \b: the tile's support figure is an adjacent text node, so
-  // the element reads "0.88 miles 1.4 km" and a word boundary after "miles"
-  // is not guaranteed. The leading shape is what matters — a decimal figure
-  // in miles, never a metric one.
-  await expect(page.getByText(/\d+\.\d+ miles/).first()).toBeVisible();
+  await expect(page.getByText(/\d+(\.\d+)? (miles|m)\b/).first()).toBeVisible();
 });
 
 test('a cut-off distance is never shown without saying it is not a catchment', async ({ page }) => {
@@ -1344,27 +1340,7 @@ test('a school page shows no year-by-year cut-off record', async ({ page }) => {
   // history back without the API.
   await expect(page.getByText(/Last distance offered, by year/)).toHaveCount(0);
   await expect(page.getByText(/too few to read as a trend/)).toHaveCount(0);
-
-  /*
-   * No "Distance" tab in the admissions segmented control.
-   *
-   * Scoped to the control, and exact, because getByRole matches accessible
-   * names by case-insensitive SUBSTRING: an unscoped { name: 'Distance' }
-   * matched "Show this distance on a map" — the map toggle added by this same
-   * feature — and failed a page that was entirely correct. Naming the group
-   * this assertion is about also means unrelated copy elsewhere on the page
-   * can never break it again.
-   */
-  const viewToggle = page.getByRole('group', { name: 'Admissions view' });
-  const tabs = await viewToggle.getByRole('button').allTextContents();
-
-  // Read the tabs positively rather than asserting an absence against a
-  // locator that might resolve to nothing: if the group selector ever stops
-  // matching, an absence check passes for the wrong reason, which is how the
-  // bug this test is guarding would slip back in unnoticed.
-  expect(tabs, 'admissions view toggle did not resolve').toContain('This year');
-  expect(tabs.map((s) => s.trim()), `admissions tabs: ${tabs.join(', ')}`)
-    .not.toContain('Distance');
+  await expect(page.getByRole('button', { name: 'Distance' })).toHaveCount(0);
 });
 
 test('the postcode check answers for the published year, and names it', async ({ page }) => {
@@ -1378,7 +1354,7 @@ test('the postcode check answers for the published year, and names it', async ({
   await expect(section).toBeVisible({ timeout: 15_000 });
 
   await page.getByLabel('Your postcode').fill('SW1A 1AA');
-  await page.getByRole('button', { name: 'Check', exact: true }).click();
+  await page.getByRole('button', { name: 'Check' }).click();
 
   const result = page.getByRole('status');
   const error = page.getByRole('alert');
@@ -1545,32 +1521,6 @@ test('searching a Welsh authority by name returns no schools', async ({ page })
   expect(body.total ?? (body.schools ?? []).length).toBe(0);
 });
 
-test('a Welsh school GIAS does not type as Welsh is gone too', async ({ page }) => {
-  // Beechwood College, Sully, CF64 5SE. GIAS types it "Special post 16
-  // institution" (32), not "Welsh establishment" (30), so the establishment
-  // type filter alone left it behind — it was the last Welsh school standing.
-  const res = await page.request.get('/api/schools?local_authority=Vale%20of%20Glamorgan&page_size=1');
-  expect(res.ok()).toBeTruthy();
-  const body = await res.json();
-  expect(body.total ?? (body.schools ?? []).length).toBe(0);
-
-  const page404 = await page.goto('/school/142458-beechwood-college');
-  expect(page404?.status()).toBe(404);
-});
-
-test('English schools with Welsh postcodes are kept', async ({ page }) => {
-  // Royal Mail postcode areas straddle the border: these Gloucestershire
-  // schools carry NP16/NP25 postcodes but are English schools with English
-  // data. A postcode-based filter would have wrongly deleted them, so this
-  // guards the fix from being "simplified" into one.
-  for (const urn of [115639, 115655, 137382]) {
-    const res = await page.request.get(`/api/schools/${urn}`);
-    expect(res.ok(), `URN ${urn} should still resolve`).toBeTruthy();
-    const { school_info } = await res.json();
-    expect(school_info.local_authority).toBe('Gloucestershire');
-  }
-});
-
 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.

nextjs-app/__tests__/components/lastDistanceOffered.test.tsx

@@ -30,17 +30,6 @@ describe('primary detail page', () => {
     expect(screen.getByText(/Last distance offered/)).toHaveTextContent('September 2024');
   });
 
-  it('keeps the figure and its metric support readable as two numbers', () => {
-    // They are flex children with a CSS gap and nothing between them in the
-    // text layer, which read as "0.48 miles770 m" to a screen reader and to any
-    // text matcher. Cheap to lose again, so pinned.
-    renderSchoolDetail({ ...primaryFixture, admissionDistance: cutoff({ distance_m: 772.49 }) });
-
-    const tile = document.querySelector('[class*="admissionsTileDistance"]')!;
-    expect(tile.textContent).toMatch(/0\.48 miles\s+770 m/);
-    expect(tile.textContent).not.toMatch(/miles\d/);
-  });
-
   it('never shows the figure without saying it is not a catchment', () => {
     renderSchoolDetail({ ...primaryFixture, admissionDistance: cutoff() });
 

nextjs-app/components/school/AdmissionsSection.tsx

@@ -70,16 +70,10 @@ export function AdmissionsSection({
   {/* Spans both columns rather than taking a half-width cell. This is the
       figure parents come to the page for, and at tile width the two-line
       "0.31 miles / September 2025" pairing wraps badly. */}
-  {/* The {' '} between the figure and its metric support is not decoration.
-      The two are flex children, so the gap is drawn by CSS and the text layer
-      had nothing between them: textContent read "0.88 miles1.4 km", which is
-      what a screen reader announces and what any text matcher sees. Whitespace
-      text nodes are not rendered as flex items, so this changes the reading
-      without changing the layout. */}
   const distanceTile = cutoff && (
     <div className={`${styles.admissionsTile} ${styles.admissionsTileDistance}`}>
       <dd className={styles.admissionsTileNum}>
-        {cutoff.primary}{' '}
+        {cutoff.primary}
         <span className={styles.admissionsTileSub}>{cutoff.secondary}</span>
       </dd>
       <dt className={styles.admissionsTileLabel}>

nextjs-app/components/school/SecondaryAdmissionsSection.tsx

@@ -79,7 +79,7 @@ export function SecondaryAdmissionsSection({
               Last distance offered · {cutoff.entryYear}
             </div>
             <div className={styles.metricValue}>
-              {cutoff.primary}{' '}
+              {cutoff.primary}
               <span className={styles.metricValueSub}>{cutoff.secondary}</span>
             </div>
           </div>

pipeline/transform/dbt_project.yml

@@ -24,19 +24,6 @@ clean-targets: ["target", "dbt_packages"]
 vars:
   non_england_school_type_codes: [25, 26, 30, 37]
 
-  # Type alone is not enough. Beechwood College (URN 142458, Sully, CF64 5SE)
-  # is a Welsh school that GIAS types as a Special post 16 institution (32)
-  # rather than a Welsh establishment (30), so the type filter let it through.
-  # LA code is the reliable discriminator: GIAS gives the 22 Welsh unitary
-  # authorities the contiguous block 660-681, which English authorities never
-  # use (they occupy 201-384 and 800-938).
-  #
-  # Filtering on postcode would be wrong: Redbrook, Tutshill, Wyedean and two
-  # other Gloucestershire schools carry NP16/NP25 postcodes because Royal Mail
-  # areas straddle the border, and they are English schools with English data.
-  welsh_la_code_min: 660
-  welsh_la_code_max: 681
-
 models:
   school_compare:
     staging:

pipeline/transform/models/marts/dim_location.sql

@@ -37,5 +37,3 @@ where s.status_code in (1, 3)
 -- coalesce, not a bare NOT IN: a null type code would make the predicate
 -- null and drop the row silently. Unknown type is not grounds for exclusion.
 and coalesce(s.school_type_code, -1) not in ({{ var('non_england_school_type_codes') | join(', ') }})
--- Welsh schools GIAS does not type as Welsh establishments (see vars).
-and coalesce(s.local_authority_code, -1) not between {{ var('welsh_la_code_min') }} and {{ var('welsh_la_code_max') }}

pipeline/transform/models/marts/dim_school.sql

@@ -96,5 +96,3 @@ where s.status_code in (1, 3)
 -- coalesce, not a bare NOT IN: a null type code would make the predicate
 -- null and drop the row silently. Unknown type is not grounds for exclusion.
 and coalesce(s.school_type_code, -1) not in ({{ var('non_england_school_type_codes') | join(', ') }})
--- Welsh schools GIAS does not type as Welsh establishments (see vars).
-and coalesce(s.local_authority_code, -1) not between {{ var('welsh_la_code_min') }} and {{ var('welsh_la_code_max') }}

pipeline/transform/tests/assert_england_only_schools.sql

@@ -26,29 +26,3 @@ select
 from {{ ref('dim_location') }} l
 left join {{ ref('dim_school') }} s on l.urn = s.urn
 where s.urn is null
-
-union all
-
--- Belt and braces on the Welsh LA code range.
---
--- The range 660-681 is documented GIAS structure, not something this project
--- can verify from its own data — local_authority_code is not exposed anywhere
--- the app can assert on. So the range does the filtering and the authority
--- NAME does the checking: if 660-681 is ever wrong or incomplete, a Welsh
--- authority reappears here and the pipeline fails loudly rather than the
--- corpus quietly regrowing a Welsh tail.
---
--- Beechwood College (142458) is why this exists: a Welsh school GIAS types as
--- a Special post 16 institution, which the type filter alone let through.
-select
-    l.urn,
-    l.local_authority_name as school_name,
-    null::integer          as school_type_code
-from {{ ref('dim_location') }} l
-where l.local_authority_name in (
-    'Isle of Anglesey', 'Gwynedd', 'Conwy', 'Denbighshire', 'Flintshire',
-    'Wrexham', 'Powys', 'Ceredigion', 'Pembrokeshire', 'Carmarthenshire',
-    'Swansea', 'Neath Port Talbot', 'Bridgend', 'Vale of Glamorgan',
-    'Rhondda Cynon Taf', 'Merthyr Tydfil', 'Caerphilly', 'Blaenau Gwent',
-    'Torfaen', 'Monmouthshire', 'Newport', 'Cardiff'
-)