Merge pull request 'fix(data): drop the Welsh school GIAS does not type as Welsh' (#109) from fix/welsh-establishment-leak into main

Reviewed-on: #109

e2e/tests/journeys.spec.ts

@@ -1545,6 +1545,32 @@ 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.

pipeline/transform/dbt_project.yml

@@ -24,6 +24,19 @@ 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

@@ -37,3 +37,5 @@ 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

@@ -96,3 +96,5 @@ 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

@@ -26,3 +26,29 @@ 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'
+)