fix(places): stop the place titles doubling the brand

Every place page shipped as 'Schools in Brentwood - Compare 27 Schools |
schoolcompare | schoolcompare'. The root layout's title template appends
'| schoolcompare' to any plain-string title, and all four place routes already
carried the brand. W8 opted the other routes out with an absolute title; the
place routes were written afterwards and did not inherit the lesson.

~2,600 titles affected, and the repetition pushed them past Google's
truncation point, so the doubled brand displaced real words in the result.

An e2e journey now asserts no title repeats the brand, across the static
routes and a place page, so this cannot come back on a route added later.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj

backend/app.py

@@ -209,12 +209,27 @@ def _place_url(place) -> str:
 
 
 def _place_sitemap_rows(kinds: tuple[str, ...]) -> list[str]:
-    return [
-        _url_element(BASE_URL + _place_url(p))
-        for p in sorted(get_place_registry().values(),
-                        key=lambda p: (p.kind, p.slug))
-        if p.kind in kinds
-    ]
+    """A <url> per place, plus a phase variant wherever that phase clears the
+    threshold on its own.
+
+    Phase is part of the query — "primary schools in beccles" — so each
+    variant is its own indexable page. Submitting only the bare place URL left
+    ~950 of them reachable by nothing: absent from every sitemap, and not
+    linked from the place page either.
+    """
+    rows: list[str] = []
+    for p in sorted(get_place_registry().values(), key=lambda p: (p.kind, p.slug)):
+        if p.kind not in kinds:
+            continue
+        rows.append(_url_element(BASE_URL + _place_url(p)))
+        # Outcodes carry no phase variants: nobody searches "primary schools
+        # in SW11", so the routes do not exist to submit.
+        if p.kind == "outcode":
+            continue
+        for phase in ("primary", "secondary"):
+            if p.publishes_phase(phase):
+                rows.append(_url_element(f"{BASE_URL}{_place_url(p)}/{phase}"))
+    return rows
 
 
 def build_sitemaps() -> dict[str, str]:
@@ -1216,7 +1231,11 @@ async def get_place(request: Request, kind: str, slug: str,
     return {
         "place": {"kind": place.kind, "slug": place.slug, "name": place.name,
                   "count": len(place.urns),
-                  "parent_authority": place.parent_authority},
+                  "parent_authority": place.parent_authority,
+                  # Only phases that clear the threshold, so the page links
+                  # variants that exist rather than 404s.
+                  "phases": [ph for ph in ("primary", "secondary")
+                             if place.publishes_phase(ph)]},
         "schools": clean_for_json(rows[cols]),
         "averages": averages,
     }

backend/localities.py

@@ -20,6 +20,18 @@ A locality whose outcodes hold fewer than MIN_SCHOOLS schools is not
 published, so a typo produces no page rather than an empty one. Places that
 fail that check are logged at startup, because a locality you meant to publish
 quietly not appearing is the failure worth hearing about.
+
+Two rules for anything added here.
+
+**Sub-borough districts only.** A London borough is a local authority and
+already has a page at /schools/authority/[la] covering all of its schools; a
+locality defined by two or three outcodes would be a partial, near-duplicate
+subset of it. Hackney, Islington, Greenwich and Ealing were all in the first
+draft for that reason and have been removed.
+
+**The slug must not match a GIAS town.** "Richmond" did — GIAS has a Richmond
+in North Yorkshire with 37 schools — so the London one could never publish.
+The registry skips any locality that collides and logs it.
 """
 
 # slug -> (display name, outcodes)
@@ -30,16 +42,11 @@ LOCALITY_OUTCODES: dict[str, tuple[str, tuple[str, ...]]] = {
     "shoreditch":    ("Shoreditch",    ("EC2A", "E1")),
     "peckham":       ("Peckham",       ("SE15",)),
     "brixton":       ("Brixton",       ("SW2", "SW9")),
-    "hackney":       ("Hackney",       ("E5", "E8", "E9")),
-    "islington":     ("Islington",     ("N1", "N5", "N7")),
     "camden-town":   ("Camden Town",   ("NW1",)),
-    "greenwich":     ("Greenwich",     ("SE10",)),
     "wimbledon":     ("Wimbledon",     ("SW19",)),
     "putney":        ("Putney",        ("SW15",)),
     "fulham":        ("Fulham",        ("SW6",)),
     "chiswick":      ("Chiswick",      ("W4",)),
-    "ealing":        ("Ealing",        ("W5", "W13")),
-    "richmond":      ("Richmond",      ("TW9", "TW10")),
     "stratford":     ("Stratford",     ("E15",)),
     "walthamstow":   ("Walthamstow",   ("E17",)),
     "tooting":       ("Tooting",       ("SW17",)),

backend/places.py

@@ -14,7 +14,7 @@ from __future__ import annotations
 
 import logging
 import re
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 
 logger = logging.getLogger(__name__)
 
@@ -30,6 +30,13 @@ class Place:
     name: str
     urns: tuple[int, ...]
     parent_authority: str | None    # authority NAME, for the 301 target
+    # URNs per phase, so the per-phase threshold can be applied without
+    # re-querying. A place with 30 primaries and 2 secondaries publishes a
+    # primary variant and no secondary one.
+    phase_urns: dict[str, tuple[int, ...]] = field(default_factory=dict)
+
+    def publishes_phase(self, phase: str) -> bool:
+        return len(self.phase_urns.get(phase, ())) >= MIN_SCHOOLS
 
     @property
     def key(self) -> str:
@@ -46,6 +53,24 @@ def _publishable_urns(df) -> set[int]:
     return set(df.loc[df[cols].notna().any(axis=1), "urn"].astype(int))
 
 
+def _phase_urns(group, publishable: set[int]) -> dict[str, tuple[int, ...]]:
+    """URNs per phase. All-through schools count toward both, matching the
+    PHASE_GROUPS mapping the search filters already use."""
+    from backend.app import PHASE_GROUPS
+
+    if "phase" not in group.columns:
+        return {}
+    lowered = group["phase"].fillna("").str.lower()
+    out: dict[str, tuple[int, ...]] = {}
+    for phase in ("primary", "secondary"):
+        wanted = PHASE_GROUPS.get(phase, set())
+        subset = group[lowered.isin(wanted)]
+        urns = tuple(sorted({int(u) for u in subset["urn"]} & publishable))
+        if urns:
+            out[phase] = urns
+    return out
+
+
 def _parent_authority(group) -> str | None:
     """The most common authority in a group — the useful 301 target.
 
@@ -79,6 +104,7 @@ def _group(df, column: str, kind: str, publishable: set[int]) -> dict[str, Place
         place = Place(
             kind=kind, slug=slug, name=name, urns=urns,
             parent_authority=_parent_authority(group) if kind == "town" else None,
+            phase_urns=_phase_urns(group, publishable),
         )
         out[place.key] = place
     return out
@@ -111,7 +137,8 @@ def _outcode_places(df, publishable: set[int]) -> dict[str, Place]:
         if len(urns) < MIN_SCHOOLS:
             continue
         place = Place(kind="outcode", slug=str(oc).lower(), name=str(oc),
-                      urns=urns, parent_authority=_parent_authority(group))
+                      urns=urns, parent_authority=_parent_authority(group),
+                      phase_urns=_phase_urns(group, publishable))
         out[place.key] = place
     return out
 
@@ -128,10 +155,19 @@ def _locality_places(df, publishable: set[int],
     out: dict[str, Place] = {}
     for slug, (name, outcodes) in LOCALITY_OUTCODES.items():
         if slug in town_slugs:
-            raise ValueError(
-                f"locality {slug!r} collides with a published town of the same "
-                "slug; publishing both would shadow the town silently"
-            )
+            # Skip, do not raise. The guard exists so a locality never
+            # silently shadows a town — skipping achieves that, and the error
+            # log makes it loud.
+            #
+            # Raising here took down sitemap generation for all 25,000 school
+            # pages when "richmond" met the GIAS town Richmond in North
+            # Yorkshire. Worse, GIAS town names change without any code change,
+            # so a raise means curated data can break the site spontaneously.
+            # A curation mistake must cost one page, not the sitemap.
+            logger.error(
+                "locality %r collides with the published town of the same "
+                "slug and has been skipped; rename it or remove it", slug)
+            continue
         group = working[working["_oc"].isin(outcodes)]
         urns = tuple(sorted({int(u) for u in group["urn"]} & publishable))
         if len(urns) < MIN_SCHOOLS:
@@ -144,7 +180,8 @@ def _locality_places(df, publishable: set[int],
                 slug, ", ".join(outcodes), len(urns), MIN_SCHOOLS)
             continue
         place = Place(kind="locality", slug=slug, name=name, urns=urns,
-                      parent_authority=_parent_authority(group))
+                      parent_authority=_parent_authority(group),
+                      phase_urns=_phase_urns(group, publishable))
         out[place.key] = place
     return out
 

backend/tests/test_places.py

@@ -108,16 +108,42 @@ def test_locality_below_the_threshold_is_not_published(monkeypatch):
     assert "locality:nowhere" not in reg
 
 
-def test_a_locality_may_not_shadow_a_viable_town(monkeypatch):
-    # Silently shadowing a town would lose a page carrying real demand.
+def test_a_locality_may_not_shadow_a_viable_town(monkeypatch, caplog):
+    """A colliding locality is skipped loudly, and the town survives.
+
+    This used to raise, which took down sitemap generation for all 25,000
+    school pages the first time a curated slug met a real GIAS town. Curated
+    data must not be able to break the site — and GIAS town names change with
+    no code change at all, so the raise could fire spontaneously.
+    """
+    import logging
+
     from backend import localities
     monkeypatch.setattr(localities, "LOCALITY_OUTCODES",
                         {"brentwood": ("Brentwood", ("CM13",))})
     rows = _town(MIN_SCHOOLS, "Brentwood", "Essex")
     for r in rows:
         r["postcode"] = "CM13 1AA"
-    with pytest.raises(ValueError, match="brentwood"):
-        build_place_registry(_df(rows))
+
+    with caplog.at_level(logging.ERROR):
+        reg = build_place_registry(_df(rows))
+
+    assert "locality:brentwood" not in reg      # skipped
+    assert "town:brentwood" in reg              # the town is untouched
+    assert "brentwood" in caplog.text           # and it was loud about it
+
+
+def test_a_locality_collision_does_not_break_the_rest_of_the_registry(monkeypatch):
+    # The whole point of skipping rather than raising.
+    from backend import localities
+    monkeypatch.setattr(localities, "LOCALITY_OUTCODES",
+                        {"brentwood": ("Brentwood", ("CM13",))})
+    rows = _town(MIN_SCHOOLS, "Brentwood", "Essex")
+    for r in rows:
+        r["postcode"] = "CM13 1AA"
+    reg = build_place_registry(_df(rows))
+    assert "authority:essex" in reg
+    assert "outcode:cm13" in reg
 
 
 def test_outcode_places_are_built_from_postcodes():
@@ -174,3 +200,32 @@ def test_the_pipeline_seed_mirrors_the_canonical_module():
         for row in csv.DictReader(seed_path.open())
     }
     assert seed == LOCALITY_OUTCODES
+
+
+def test_no_curated_locality_names_a_london_borough():
+    """Boroughs are authorities and already have a page.
+
+    A locality defined by two or three outcodes inside a borough would be a
+    partial, near-duplicate subset of that authority page — the exact
+    thin-content failure the two-namespace design exists to avoid. Hackney,
+    Islington, Greenwich and Ealing were all in the first draft.
+
+    Hardcoded rather than read from the corpus because this must fail in CI,
+    where there is no database.
+    """
+    from backend.localities import LOCALITY_OUTCODES
+
+    boroughs = {
+        "barking-and-dagenham", "barnet", "bexley", "brent", "bromley",
+        "camden", "croydon", "ealing", "enfield", "greenwich", "hackney",
+        "hammersmith-and-fulham", "haringey", "harrow", "havering",
+        "hillingdon", "hounslow", "islington", "kensington-and-chelsea",
+        "kingston-upon-thames", "lambeth", "lewisham", "merton", "newham",
+        "redbridge", "richmond-upon-thames", "southwark", "sutton",
+        "tower-hamlets", "waltham-forest", "wandsworth", "westminster",
+    }
+    named = boroughs & set(LOCALITY_OUTCODES)
+    assert not named, (
+        f"these are boroughs, not districts: {sorted(named)} - they already "
+        "have an authority page covering every school"
+    )

backend/tests/test_sitemap.py

@@ -268,3 +268,23 @@ def test_place_urls_carry_no_priority_or_changefreq(place_sitemaps):
     for name in ("places-1.xml", "outcodes-1.xml"):
         assert "<priority>" not in place_sitemaps[name]
         assert "<changefreq>" not in place_sitemaps[name]
+
+
+def test_phase_variants_are_submitted_where_the_phase_clears_the_threshold(place_sitemaps):
+    # "primary schools in beccles" is the query shape the baseline showed, so
+    # each variant is its own page and has to be submitted. Emitting only the
+    # bare place URL left ~950 of them reachable by nothing.
+    xml = place_sitemaps["places-1.xml"]
+    assert "<loc>https://www.schoolcompare.co.uk/schools/brentwood/primary</loc>" in xml
+
+
+def test_a_phase_below_its_own_threshold_is_not_submitted(place_sitemaps):
+    # The fixture is six primaries and no secondaries.
+    xml = place_sitemaps["places-1.xml"]
+    assert "/schools/brentwood/secondary" not in xml
+
+
+def test_outcodes_get_no_phase_variants(place_sitemaps):
+    # Nobody searches "primary schools in CM13"; the routes do not exist.
+    xml = place_sitemaps["outcodes-1.xml"]
+    assert "/primary" not in xml and "/secondary" not in xml

e2e/tests/journeys.spec.ts

@@ -1842,3 +1842,46 @@ test('a place page states the local average against England', async ({ page }) =
   await page.goto(`/schools/${place.slug}`);
   await expect(page.getByTestId('local-vs-england')).toContainText(/across England/i);
 });
+
+test('a place page links its phase variants, and they resolve', async ({ page }) => {
+  // "primary schools in beccles" is the query shape the baseline showed. The
+  // first cut submitted only the bare place URL and linked nothing, leaving
+  // ~950 variant pages reachable by nothing at all.
+  const res = await page.request.get('/api/places');
+  const { places } = await res.json();
+  const town = places.find((p: { kind: string }) => p.kind === 'town');
+  expect(town).toBeTruthy();
+
+  const detail = await (await page.request.get(`/api/places/town/${town.slug}`)).json();
+  test.skip(!(detail.place.phases ?? []).length, 'no phase clears the threshold here');
+
+  await page.goto(`/schools/${town.slug}`);
+  const phase = detail.place.phases[0];
+  const link = page.locator(`a[href="/schools/${town.slug}/${phase}"]`).first();
+  await expect(link).toBeVisible();
+
+  await link.click();
+  await expect(page.locator('h1')).toContainText(new RegExp(`${phase} schools in`, 'i'));
+});
+
+test('phase variants are submitted in the places sitemap', async ({ page }) => {
+  const xml = await (await page.request.get('/sitemaps/places-1.xml')).text();
+  expect(xml).toMatch(/\/schools\/[a-z0-9-]+\/primary</);
+});
+
+test('no page title repeats the brand', async ({ page }) => {
+  // The root layout appends '| schoolcompare' to a plain-string title. Any
+  // route whose title already carries the brand must opt out with
+  // `absolute`, or it ships '... | schoolcompare | schoolcompare' — which is
+  // how ~2,600 place pages first went out.
+  const res = await page.request.get('/api/places');
+  const { places } = await res.json();
+  const town = places.find((p: { kind: string }) => p.kind === 'town');
+
+  for (const path of ['/', '/rankings', '/admissions', `/schools/${town.slug}`]) {
+    await page.goto(path);
+    const title = await page.title();
+    const brands = (title.match(/schoolcompare/gi) ?? []).length;
+    expect(brands, `${path} repeats the brand: ${title}`).toBeLessThanOrEqual(1);
+  }
+});

nextjs-app/__tests__/app/placeMetadata.test.ts

@@ -14,7 +14,7 @@ jest.mock('@/lib/places', () => ({
 describe('place page metadata', () => {
   it('titles the page the way the place is searched', async () => {
     const m = await placeMeta({ params: Promise.resolve({ place: 'brentwood' }) });
-    expect(m.title).toMatch(/schools in brentwood/i);
+    expect((m.title as { absolute: string }).absolute).toMatch(/schools in brentwood/i);
   });
 
   it('canonicalises to its own path on the www host', async () => {
@@ -23,6 +23,18 @@ describe('place page metadata', () => {
       .toBe('https://www.schoolcompare.co.uk/schools/brentwood');
   });
 
+  it('opts out of the layout template, which would double the brand', () => {
+    // The root layout appends '| schoolcompare' to a plain string title, and
+    // these titles already carry it — every place page shipped reading
+    // '... | schoolcompare | schoolcompare' until this was made absolute.
+    return placeMeta({ params: Promise.resolve({ place: 'brentwood' }) })
+      .then((m) => {
+        expect(typeof m.title).toBe('object');
+        expect((m.title as { absolute: string }).absolute)
+          .not.toMatch(/schoolcompare.*schoolcompare/);
+      });
+  });
+
   it('an unknown place gets a not-found title rather than inventing one', async () => {
     const m = await placeMeta({ params: Promise.resolve({ place: 'atlantis' }) });
     expect(m.title).toMatch(/not found/i);

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

@@ -4,7 +4,7 @@ import type { PlaceDetail } from '@/lib/places';
 
 const detail: PlaceDetail = {
   place: { kind: 'town', slug: 'brentwood', name: 'Brentwood', count: 29,
-           parent_authority: 'Essex' },
+           parent_authority: 'Essex', phases: ['primary'] },
   schools: [
     { urn: 1, school_name: 'Alpha Primary', rwm_expected_pct: 82,
       ofsted_grade: 1 } as never,
@@ -91,3 +91,24 @@ describe('PlaceView structured data', () => {
     }
   });
 });
+
+describe('PlaceView phase variants', () => {
+  it('links the phase variants that exist', () => {
+    render(<PlaceView detail={detail} englandAverage={61} neighbours={[]} />);
+    expect(screen.getByRole('link', { name: /Primary schools in Brentwood/i }))
+      .toHaveAttribute('href', '/schools/brentwood/primary');
+  });
+
+  it('links no variant for a phase below its own threshold', () => {
+    render(<PlaceView detail={detail} englandAverage={61} neighbours={[]} />);
+    expect(screen.queryByRole('link', { name: /Secondary schools in Brentwood/i }))
+      .not.toBeInTheDocument();
+  });
+
+  it('does not link sideways from a variant page to itself', () => {
+    render(<PlaceView detail={detail} phase="primary" englandAverage={61}
+      neighbours={[]} />);
+    expect(screen.queryByRole('link', { name: /Primary schools in Brentwood/i }))
+      .not.toBeInTheDocument();
+  });
+});

nextjs-app/app/schools/[place]/[phase]/page.tsx

@@ -37,7 +37,7 @@ export async function generateMetadata({ params }: Props): Promise<Metadata> {
   const word = phase === 'secondary' ? 'Secondary' : 'Primary';
   const { name } = detail.place;
   return {
-    title: `${word} Schools in ${name} — Ranked | schoolcompare`,
+    title: { absolute: `${word} Schools in ${name} — Ranked | schoolcompare` },
     description:
       `Every ${phase} school in ${name} ranked by results, with Ofsted grades and `
       + `the local average against England.`,

nextjs-app/app/schools/[place]/page.tsx

@@ -53,7 +53,10 @@ export async function generateMetadata({ params }: Props): Promise<Metadata> {
 
   const { name, count } = detail.place;
   return {
-    title: `Schools in ${name} — Compare ${count} Schools | schoolcompare`,
+    // absolute: the root layout's template appends '| schoolcompare' to a
+    // plain string, and this title already carries it. Without this every
+    // place title read '... | schoolcompare | schoolcompare'.
+    title: { absolute: `Schools in ${name} — Compare ${count} Schools | schoolcompare` },
     description:
       `Every school in ${name} ranked by SATs and GCSE results, with Ofsted grades, `
       + `the local average against England, and how close you had to live to get a place.`,

nextjs-app/app/schools/authority/[la]/page.tsx

@@ -43,7 +43,7 @@ export async function generateMetadata({ params }: Props): Promise<Metadata> {
 
   const { name, count } = detail.place;
   return {
-    title: `Schools in ${name} — Local Authority | schoolcompare`,
+    title: { absolute: `Schools in ${name} — Local Authority | schoolcompare` },
     description:
       `All ${count} schools in the ${name} local authority, ranked by SATs and GCSE `
       + `results, with Ofsted grades and the authority average against England.`,

nextjs-app/app/schools/near/[outcode]/page.tsx

@@ -38,7 +38,7 @@ export async function generateMetadata({ params }: Props): Promise<Metadata> {
 
   const { name, count } = detail.place;
   return {
-    title: `Schools near ${name} | schoolcompare`,
+    title: { absolute: `Schools near ${name} | schoolcompare` },
     description:
       `${count} schools in the ${name} postcode district, ranked by results, with `
       + `Ofsted grades and how close you had to live to get a place.`,

nextjs-app/components/places/PlaceView.module.css

@@ -106,3 +106,13 @@
   padding: 0;
   margin: 0;
 }
+
+/* Phase variants are separate indexable pages, so the bare place page has to
+   link them — a sitemap entry alone leaves them with no internal path in. */
+.phaseLinks {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 0.5rem 1rem;
+  margin: 0 0 1.25rem;
+  font-size: 0.9375rem;
+}

nextjs-app/components/places/PlaceView.tsx

@@ -89,6 +89,16 @@ export function PlaceView({ detail, phase, englandAverage, neighbours }: Props)
         </p>
       </header>
 
+      {!phase && (place.phases ?? []).length > 0 && (
+        <nav className={styles.phaseLinks} aria-label="By phase">
+          {(place.phases ?? []).map((ph) => (
+            <Link key={ph} href={`/schools/${place.slug}/${ph}`}>
+              {ph === 'secondary' ? 'Secondary schools' : 'Primary schools'} in {place.name}
+            </Link>
+          ))}
+        </nav>
+      )}
+
       {local != null && englandAverage != null && (
         <p className={styles.compare} data-testid="local-vs-england">
           {place.name} averages <strong>{Math.round(local)}</strong> against{' '}

nextjs-app/lib/places.ts

@@ -13,6 +13,9 @@ export interface PlaceSummary {
   slug: string;
   name: string;
   count: number;
+  /** Phases that clear the threshold on their own, so the page links
+   *  variants that exist rather than 404s. Absent on the registry listing. */
+  phases?: string[];
 }
 
 export interface PlaceDetail {

pipeline/transform/seeds/locality_outcodes.csv

@@ -5,16 +5,11 @@ clapham,Clapham,SW4,London
 shoreditch,Shoreditch,EC2A|E1,London
 peckham,Peckham,SE15,London
 brixton,Brixton,SW2|SW9,London
-hackney,Hackney,E5|E8|E9,London
-islington,Islington,N1|N5|N7,London
 camden-town,Camden Town,NW1,London
-greenwich,Greenwich,SE10,London
 wimbledon,Wimbledon,SW19,London
 putney,Putney,SW15,London
 fulham,Fulham,SW6,London
 chiswick,Chiswick,W4,London
-ealing,Ealing,W5|W13,London
-richmond,Richmond,TW9|TW10,London
 stratford,Stratford,E15,London
 walthamstow,Walthamstow,E17,London
 tooting,Tooting,SW17,London