feat(places): registry of towns and authorities

Two namespaces because 67 town names collide with an authority name and
neither set contains the other — postal towns cross authority boundaries, so
Bedford the town holds 104 schools against the authority's 86.

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

backend/places.py

@@ -0,0 +1,92 @@
+"""The place registry: what places the site publishes, and what is in each.
+
+One module owns this question. The pages, the sitemap and the internal-link
+modules all read from here, so the threshold and the collision rules exist in
+exactly one place and are testable without a browser or a database.
+
+Two namespaces, never one. 67 viable town names collide with a local
+authority name, and the authority is the larger set in only 43 of them —
+postal towns cross authority boundaries, so neither can absorb the other.
+Keys are "<kind>:<slug>" so the collision cannot reappear in the dict.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+# Five schools with publishable data. Below this a place has nothing to say
+# that a list of schools does not, and publishing it is index bloat.
+MIN_SCHOOLS = 5
+
+
+@dataclass(frozen=True)
+class Place:
+    kind: str                       # "town" | "locality" | "authority" | "outcode"
+    slug: str
+    name: str
+    urns: tuple[int, ...]
+    parent_authority: str | None    # authority NAME, for the 301 target
+
+    @property
+    def key(self) -> str:
+        return f"{self.kind}:{self.slug}"
+
+
+def _publishable_urns(df) -> set[int]:
+    """URNs with something a page could state, deduplicated across years."""
+    from backend.app import _PUBLISHABLE_FIELDS
+
+    cols = [c for c in _PUBLISHABLE_FIELDS if c in df.columns]
+    if not cols:
+        return set()
+    return set(df.loc[df[cols].notna().any(axis=1), "urn"].astype(int))
+
+
+def _parent_authority(group) -> str | None:
+    """The most common authority in a group — the useful 301 target.
+
+    A town spanning several authorities has no single parent, so the mode is
+    the honest answer rather than an arbitrary first row.
+    """
+    if "local_authority" not in group.columns:
+        return None
+    top = group["local_authority"].dropna()
+    return str(top.mode().iloc[0]) if not top.empty else None
+
+
+def _group(df, column: str, kind: str, publishable: set[int]) -> dict[str, Place]:
+    """One Place per distinct value of `column` that clears the threshold."""
+    from backend.app import _slugify
+
+    if column not in df.columns:
+        return {}
+
+    out: dict[str, Place] = {}
+    for name, group in df.groupby(column, dropna=True):
+        name = str(name).strip()
+        if not name:
+            continue
+        urns = tuple(sorted({int(u) for u in group["urn"]} & publishable))
+        if len(urns) < MIN_SCHOOLS:
+            continue
+        slug = _slugify(name)
+        if not slug:
+            continue
+        place = Place(
+            kind=kind, slug=slug, name=name, urns=urns,
+            parent_authority=_parent_authority(group) if kind == "town" else None,
+        )
+        out[place.key] = place
+    return out
+
+
+def build_place_registry(df) -> dict[str, Place]:
+    """Every place the site publishes, keyed by "<kind>:<slug>"."""
+    if df.empty or "urn" not in df.columns:
+        return {}
+
+    publishable = _publishable_urns(df)
+    registry: dict[str, Place] = {}
+    registry.update(_group(df, "local_authority", "authority", publishable))
+    registry.update(_group(df, "town", "town", publishable))
+    return registry

backend/tests/test_places.py

@@ -0,0 +1,86 @@
+"""Tests for the place registry (spec 2026-08-21).
+
+The registry is built from the in-memory school DataFrame, so these build a
+small frame directly rather than touching a database.
+"""
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from backend.places import MIN_SCHOOLS, build_place_registry
+
+
+def _df(rows: list[dict]) -> pd.DataFrame:
+    base = {
+        "year": 202425, "ofsted_grade": 2.0, "ofsted_date": None,
+        "rwm_expected_pct": 60.0, "attainment_8_score": np.nan,
+        "phase": "Primary", "postcode": "AA1 1AA",
+    }
+    return pd.DataFrame([{**base, **r} for r in rows])
+
+
+def _town(n: int, town: str, la: str, start: int = 100000, **kw) -> list[dict]:
+    """`start` offsets the URNs so two calls can describe different schools —
+    the Bedford case needs two authorities' worth of distinct URNs in one
+    town."""
+    return [
+        {"urn": start + i, "school_name": f"{town} School {i}",
+         "town": town, "local_authority": la, **kw}
+        for i in range(n)
+    ]
+
+
+def test_town_clearing_the_threshold_is_published():
+    reg = build_place_registry(_df(_town(MIN_SCHOOLS, "Brentwood", "Essex")))
+    assert "town:brentwood" in reg
+    assert reg["town:brentwood"].name == "Brentwood"
+    assert len(reg["town:brentwood"].urns) == MIN_SCHOOLS
+
+
+def test_town_below_the_threshold_is_not_published():
+    reg = build_place_registry(_df(_town(MIN_SCHOOLS - 1, "Crosby", "Sefton")))
+    assert "town:crosby" not in reg
+
+
+def test_a_town_below_threshold_still_names_its_authority():
+    # The route layer needs somewhere to 301 to.
+    reg = build_place_registry(_df(
+        _town(MIN_SCHOOLS - 1, "Crosby", "Sefton") + _town(MIN_SCHOOLS, "Bootle", "Sefton")))
+    assert "authority:sefton" in reg
+
+
+def test_town_and_authority_of_the_same_name_are_separate_places():
+    # 67 real collisions. Neither set contains the other: Bedford the town has
+    # 104 schools, Bedford the authority 86, because postal towns cross
+    # authority boundaries.
+    rows = (_town(MIN_SCHOOLS, "Bedford", "Bedford")
+            + _town(MIN_SCHOOLS, "Bedford", "Central Bedfordshire", start=200000))
+    reg = build_place_registry(_df(rows))
+    town, authority = reg["town:bedford"], reg["authority:bedford"]
+    assert set(town.urns) != set(authority.urns)
+    assert len(town.urns) == MIN_SCHOOLS * 2      # both authorities' schools
+    assert len(authority.urns) == MIN_SCHOOLS     # only this authority's
+
+
+def test_schools_without_publishable_data_do_not_count_toward_the_threshold():
+    rows = _town(MIN_SCHOOLS, "Ghosttown", "Nowhere")
+    for r in rows:
+        r["rwm_expected_pct"] = np.nan
+        r["ofsted_grade"] = np.nan
+    reg = build_place_registry(_df(rows))
+    assert "town:ghosttown" not in reg
+
+
+def test_blank_town_is_ignored():
+    rows = _town(MIN_SCHOOLS, "", "Essex")
+    reg = build_place_registry(_df(rows))
+    assert not any(k.startswith("town:") for k in reg)
+
+
+def test_a_school_is_counted_once_even_with_several_years_of_rows():
+    rows = []
+    for year in (202324, 202425):
+        rows += [{**r, "year": year} for r in _town(MIN_SCHOOLS, "Beccles", "Suffolk")]
+    reg = build_place_registry(_df(rows))
+    assert len(reg["town:beccles"].urns) == MIN_SCHOOLS

docs/superpowers/plans/2026-08-21-w2-location-layer.md

@@ -132,9 +132,12 @@ def _df(rows: list[dict]) -> pd.DataFrame:
     return pd.DataFrame([{**base, **r} for r in rows])
 
 
-def _town(n: int, town: str, la: str, **kw) -> list[dict]:
+def _town(n: int, town: str, la: str, start: int = 100000, **kw) -> list[dict]:
+    """`start` offsets the URNs so two calls can describe different schools —
+    the Bedford case needs two authorities' worth of distinct URNs in one
+    town."""
     return [
-        {"urn": 100000 + i, "school_name": f"{town} School {i}",
+        {"urn": start + i, "school_name": f"{town} School {i}",
          "town": town, "local_authority": la, **kw}
         for i in range(n)
     ]
@@ -164,7 +167,7 @@ def test_town_and_authority_of_the_same_name_are_separate_places():
     # 104 schools, Bedford the authority 86, because postal towns cross
     # authority boundaries.
     rows = (_town(MIN_SCHOOLS, "Bedford", "Bedford")
-            + _town(MIN_SCHOOLS, "Bedford", "Central Bedfordshire"))
+            + _town(MIN_SCHOOLS, "Bedford", "Central Bedfordshire", start=200000))
     reg = build_place_registry(_df(rows))
     town, authority = reg["town:bedford"], reg["authority:bedford"]
     assert set(town.urns) != set(authority.urns)