Merge pull request 'fix(seo): a school is publishable on any year's results, not the latest' (#112) from fix/sitemap-any-year-data into main

Reviewed-on: #112

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

backend/tests/test_sitemap.py

@@ -176,3 +176,44 @@ def test_children_are_chunked_under_the_limit(monkeypatch):
 def test_build_sitemap_still_returns_the_index(sitemap):
     # lifespan and the admin endpoint call build_sitemap(); keep it working.
     assert "<sitemapindex" in sitemap
+
+
+def test_school_with_results_in_an_earlier_year_is_still_listed(monkeypatch):
+    """Regression: The Mallard Academy (150367).
+
+    Real KS2 results 2015-16 to 2018-19, then null rows from 2022-23 onward
+    because the school stopped reporting. The first cut tested the latest
+    year's row alone and dropped it, along with ~220 others, even though its
+    detail page shows all four years of results.
+    """
+    from backend import app as app_module
+    import pandas as _pd
+
+    base = {"local_authority": "Testshire", "school_type": "Academy",
+            "phase": "Primary", "ofsted_date": None, "ofsted_grade": np.nan,
+            "attainment_8_score": np.nan, "urn": 150367,
+            "school_name": "Mallard Academy"}
+    df = _pd.DataFrame([
+        {**base, "year": 201819, "rwm_expected_pct": 67.0},
+        {**base, "year": 202324, "rwm_expected_pct": np.nan},
+        {**base, "year": 202425, "rwm_expected_pct": np.nan},
+    ])
+    monkeypatch.setattr(app_module, "load_school_data", lambda: df)
+
+    xml = app_module.build_sitemaps()["schools-1.xml"]
+    assert "/school/150367-mallard-academy" in xml
+
+
+def test_school_with_no_results_in_any_year_is_still_omitted(monkeypatch):
+    """The fix must not turn into "list everything"."""
+    from backend import app as app_module
+    import pandas as _pd
+
+    base = {"local_authority": "Testshire", "school_type": "Academy",
+            "phase": "Primary", "ofsted_date": None, "ofsted_grade": np.nan,
+            "attainment_8_score": np.nan, "rwm_expected_pct": np.nan,
+            "urn": 100002, "school_name": "Ghost Primary"}
+    df = _pd.DataFrame([{**base, "year": y} for y in (202324, 202425)])
+    monkeypatch.setattr(app_module, "load_school_data", lambda: df)
+
+    assert "/school/100002" not in app_module.build_sitemaps()["schools-1.xml"]