fix(seo): a school is publishable on any year's results, not the latest

_school_sitemap_rows tested only the latest year's row, which quietly dropped
every school with results in its history but a null row for the most recent
year — a school that stopped reporting, or whose figures were suppressed for
small-cohort disclosure.

The Mallard Academy (150367) is the case that caught it: real KS2 results for
2015-16 through 2018-19, then null rows from 2022-23 on. Its detail page shows
all four years; the sitemap omitted it. Sampling 40 of the 2,206 excluded
schools found 4 like this, so roughly 220 real pages were being withheld.

Publishable is now a property of the school, computed across every row, while
lastmod still comes from the latest row so the most recent Ofsted date wins.
The field list is a module constant shared with _has_publishable_data so the
two checks cannot drift.

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

backend/app.py

@@ -79,6 +79,12 @@ def _school_url(urn: int, school_name: str) -> str:
 STATIC_SITEMAP_PATHS = ("/", "/rankings", "/compare", "/admissions")
 
 
+# A page has something a search result could state if any of these is present
+# in any year. Shared by _has_publishable_data and the per-school check in
+# _school_sitemap_rows so the two can never drift.
+_PUBLISHABLE_FIELDS = ("rwm_expected_pct", "attainment_8_score", "ofsted_grade")
+
+
 def _has_publishable_data(row) -> bool:
     """True when a school page has something a search result could state.
 
@@ -87,7 +93,7 @@ def _has_publishable_data(row) -> bool:
     signal down, so it stays out of the sitemap. The page itself still resolves
     for anyone who has the URL.
     """
-    for field in ("rwm_expected_pct", "attainment_8_score", "ofsted_grade"):
+    for field in _PUBLISHABLE_FIELDS:
         value = row.get(field)
         if value is not None and not pd.isna(value):
             return True
@@ -115,6 +121,21 @@ def _school_sitemap_rows(df) -> list[str]:
     rows: list[str] = []
     seen: set[int] = set()
 
+    # Publishable is a property of the SCHOOL, not of its latest row.
+    #
+    # The first cut tested the latest year's row alone, which quietly dropped
+    # every school that has results in its history but a null row for the most
+    # recent year — a school that stopped reporting, or whose figures were
+    # suppressed for small-cohort disclosure. The Mallard Academy (150367) is
+    # the case that caught it: real KS2 results for 2015-16 through 2018-19,
+    # then null rows for 2022-23 onward. Its page shows all four years; the
+    # sitemap omitted it. Roughly 220 schools were affected.
+    publishable_cols = [c for c in _PUBLISHABLE_FIELDS if c in df.columns]
+    publishable: set[int] = (
+        set(df.loc[df[publishable_cols].notna().any(axis=1), "urn"].astype(int))
+        if publishable_cols else set()
+    )
+
     # Latest row per URN first, so a school's most recent Ofsted date wins.
     ordered = df.sort_values("year", ascending=False) if "year" in df.columns else df
 
@@ -123,7 +144,7 @@ def _school_sitemap_rows(df) -> list[str]:
         if urn in seen:
             continue
         seen.add(urn)
-        if not _has_publishable_data(row):
+        if urn not in publishable:
             continue
 
         lastmod = None