fix(reporting): age-band and property-type breakdowns for new-approach properties

getCountByAgeBand and getCountByPropertyType read year_built / property_type straight off the property row, which is NULL for new-approach properties — every one fell into the Unknown bucket on /portfolio/[slug]/reporting. Branch them like their already-migrated siblings (getCountByEpcBand, getEstimatedCounts): - propertyTypeSql: epc_property (lodged, else predicted) with RdSAP code→label mapping and dwelling_type fallback, mirroring resolvePropertyDescriptors; legacy stays on property.property_type. - constructionYearSql: the main building part's construction age band mapped to a representative start year (correlated subquery, since extension parts would multiply a plain JOIN), so both paths share the same year→band bucketing; legacy stays on numeric year_built. - The RdSAP label maps move into the shared-fragments section as the single source of truth; AGE_BAND_YEARS becomes CONSTRUCTION_AGE_BANDS carrying label + representative year. Band I (1996–2002) straddles the 1976–1999 / 2000+ boundary and buckets by its start year. Verified live against portfolio 814 (all 338 properties resolve, buckets match the epc_building_part distribution exactly) and legacy portfolios 419/433 (output identical to the pre-fix SQL). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-12 13:28:55 +00:00 · 2026-07-02 11:43:32 +00:00 · 2026-07-02 11:43:32 +00:00 · 051927dda4
commit 051927dda4
parent 9bf36ad4b6
3 changed files with 200 additions and 59 deletions
--- a/src/app/portfolio/[slug]/(portfolio)/reporting/databaseFunctions.ts
+++ b/src/app/portfolio/[slug]/(portfolio)/reporting/databaseFunctions.ts
@ -11,6 +11,8 @@ import {
  isExpiredSql,
  effectiveSapSql,
  effectiveEpcBandSql,
+  propertyTypeSql,
+  constructionYearSql,
 } from "@/lib/services/epcSources";

 import type {
@ -71,20 +73,21 @@ export async function getCountByAgeBand(
  const result = await db.execute<AgeBandCount>(sql`
    SELECT
      CASE
-        WHEN year_built ~ '^[0-9]+$' THEN
-          CASE
-            WHEN CAST(year_built AS int) < 1900 THEN '<1900'
-            WHEN CAST(year_built AS int) BETWEEN 1900 AND 1929 THEN '1900–1929'
-            WHEN CAST(year_built AS int) BETWEEN 1930 AND 1949 THEN '1930–1949'
-            WHEN CAST(year_built AS int) BETWEEN 1950 AND 1975 THEN '1950–1975'
-            WHEN CAST(year_built AS int) BETWEEN 1976 AND 1999 THEN '1976–1999'
-            ELSE '2000+'
-          END
+        WHEN q.built_year < 1900 THEN '<1900'
+        WHEN q.built_year BETWEEN 1900 AND 1929 THEN '1900–1929'
+        WHEN q.built_year BETWEEN 1930 AND 1949 THEN '1930–1949'
+        WHEN q.built_year BETWEEN 1950 AND 1975 THEN '1950–1975'
+        WHEN q.built_year BETWEEN 1976 AND 1999 THEN '1976–1999'
+        WHEN q.built_year >= 2000 THEN '2000+'
        ELSE 'Unknown'
      END AS age_band,
      COUNT(*)::int AS count
-    FROM property
-    WHERE portfolio_id = ${portfolioId}
+    FROM (
+      SELECT ${constructionYearSql} AS built_year
+      FROM property p
+      ${newApproachJoins}
+      WHERE p.portfolio_id = ${portfolioId}
+    ) q
    GROUP BY age_band
    ORDER BY age_band;
  `);
@ -149,10 +152,11 @@ export async function getCountByPropertyType(
  portfolioId: number,
 ): Promise<PropertyTypeCount[]> {
  const result = await db.execute<PropertyTypeCount>(sql`
-    SELECT property_type AS type, COUNT(*)::int AS count
-    FROM property
-    WHERE portfolio_id = ${portfolioId}
-    GROUP BY property_type
+    SELECT ${propertyTypeSql} AS type, COUNT(*)::int AS count
+    FROM property p
+    ${newApproachJoins}
+    WHERE p.portfolio_id = ${portfolioId}
+    GROUP BY type
    ORDER BY count DESC;
  `);

--- a/src/lib/services/epcSources.test.ts
+++ b/src/lib/services/epcSources.test.ts
@ -0,0 +1,68 @@
+import { describe, expect, it } from "vitest";
+import {
+  CONSTRUCTION_AGE_BANDS,
+  PROPERTY_TYPE_LABELS,
+} from "./epcSources";
+import { PROPERTY_TYPE_OPTIONS } from "@/app/utils/propertyFilters";
+
+// The reporting age-band bucketing in getCountByAgeBand (databaseFunctions.ts),
+// mirrored so the CONSTRUCTION_AGE_BANDS representative years stay anchored to
+// the buckets the chart renders.
+function reportingAgeBand(year: number): string {
+  if (year < 1900) return "<1900";
+  if (year <= 1929) return "1900–1929";
+  if (year <= 1949) return "1930–1949";
+  if (year <= 1975) return "1950–1975";
+  if (year <= 1999) return "1976–1999";
+  return "2000+";
+}
+
+describe("CONSTRUCTION_AGE_BANDS", () => {
+  it("keeps each representative year consistent with the band's label", () => {
+    for (const { label, year } of Object.values(CONSTRUCTION_AGE_BANDS)) {
+      if (label.startsWith("before")) {
+        expect(year).toBeLessThan(1900);
+      } else {
+        const start = Number(label.match(/\d{4}/)![0]);
+        expect(year).toBe(start);
+      }
+    }
+  });
+
+  it("buckets every RdSAP band into the expected reporting age band", () => {
+    const buckets = Object.fromEntries(
+      Object.entries(CONSTRUCTION_AGE_BANDS).map(([code, { year }]) => [
+        code,
+        reportingAgeBand(year),
+      ]),
+    );
+    expect(buckets).toEqual({
+      A: "<1900",
+      B: "1900–1929",
+      C: "1930–1949",
+      D: "1950–1975",
+      E: "1950–1975",
+      F: "1976–1999",
+      G: "1976–1999",
+      H: "1976–1999",
+      // I (1996–2002) straddles the 1976–1999 / 2000+ boundary; it buckets by
+      // its start year.
+      I: "1976–1999",
+      J: "2000+",
+      K: "2000+",
+      L: "2000+",
+      M: "2000+",
+    });
+  });
+});
+
+describe("PROPERTY_TYPE_LABELS", () => {
+  it("maps codes to the labels the property-type filter options use", () => {
+    const optionLabels = new Set(PROPERTY_TYPE_OPTIONS.map((o) => o.label));
+    for (const label of Object.values(PROPERTY_TYPE_LABELS)) {
+      // Park home has no filter option — it's rare and charts render it as-is.
+      if (label === "Park home") continue;
+      expect(optionLabels).toContain(label);
+    }
+  });
+});
--- a/src/lib/services/epcSources.ts
+++ b/src/lib/services/epcSources.ts
@ -193,6 +193,116 @@ export const isExpiredSql = (e: Alias) =>
 export const mainfuelSql = (e: Alias) =>
  sql`CASE WHEN ${isNewApproachSql} THEN NULL ELSE ${e}.mainfuel END`;

+// ─────────────────────────────────────────────────────────────────────────────
+// RdSAP code → label maps for the descriptive fields the new pipeline stores as
+// codes on epc_property / epc_building_part (the property-row text columns
+// aren't written for new-approach properties). Unknown codes fall back to the
+// raw value. Shared by the SQL fragments below and resolvePropertyDescriptors —
+// the single source of truth for code→label mapping.
+// ─────────────────────────────────────────────────────────────────────────────
+
+export const PROPERTY_TYPE_LABELS: Record<string, string> = {
+  "0": "House",
+  "1": "Bungalow",
+  "2": "Flat",
+  "3": "Maisonette",
+  "4": "Park home",
+};
+const BUILT_FORM_LABELS: Record<string, string> = {
+  "1": "Detached",
+  "2": "Semi-Detached",
+  "3": "End-Terrace",
+  "4": "Mid-Terrace",
+  "5": "Enclosed End-Terrace",
+  "6": "Enclosed Mid-Terrace",
+};
+// SAP tenure codes → the text labels already used in the data. NOTE: best-effort
+// (standard SAP 1/2/3); most rows store the text label directly, only a few use
+// codes. Confirm against the backend tenure enum.
+const TENURE_LABELS: Record<string, string> = {
+  "1": "Owner Occupied",
+  "2": "Rented Social",
+  "3": "Rented Private",
+};
+/**
+ * Matches the backend ConstructionAgeBand enum (RdSAP England & Wales letters).
+ * `year` is a representative construction year (the band's start) for reporting
+ * queries that bucket by year — band I (1996–2002) straddles the reporting
+ * 1976–1999 / 2000+ boundary, so it buckets with its start year.
+ */
+export const CONSTRUCTION_AGE_BANDS: Record<
+  string,
+  { label: string; year: number }
+> = {
+  A: { label: "before 1900", year: 1899 }, // no start year — any pre-1900 value
+  B: { label: "1900–1929", year: 1900 },
+  C: { label: "1930–1949", year: 1930 },
+  D: { label: "1950–1966", year: 1950 },
+  E: { label: "1967–1975", year: 1967 },
+  F: { label: "1976–1982", year: 1976 },
+  G: { label: "1983–1990", year: 1983 },
+  H: { label: "1991–1995", year: 1991 },
+  I: { label: "1996–2002", year: 1996 },
+  J: { label: "2003–2006", year: 2003 },
+  K: { label: "2007–2011", year: 2007 },
+  L: { label: "2012–2022", year: 2012 },
+  M: { label: "2023 onwards", year: 2023 },
+};
+
+/** `CASE <col> WHEN <code> THEN <label> … ELSE <col> END` from a code→label map. */
+const codeLabelCaseSql = (col: Alias, labels: Record<string, string>) =>
+  sql`CASE ${col} ${sql.join(
+    Object.entries(labels).map(([code, label]) => sql`WHEN ${code} THEN ${label}`),
+    sql` `,
+  )} ELSE ${col} END`;
+
+/** Property-type label from one epc_property alias (mirrors resolvePropertyDescriptors). */
+const epcPropertyTypeSql = (ep: Alias) =>
+  sql`COALESCE(${codeLabelCaseSql(sql`${ep}.property_type`, PROPERTY_TYPE_LABELS)}, ${ep}.dwelling_type)`;
+
+/**
+ * Property type label. New: epc_property (lodged, else predicted) — RdSAP codes
+ * mapped via PROPERTY_TYPE_LABELS, text passed through, dwelling_type fallback,
+ * mirroring resolvePropertyDescriptors. Legacy: property.property_type.
+ */
+export const propertyTypeSql = sql`CASE
+  WHEN ${isNewApproachSql} THEN (CASE WHEN epl.id IS NOT NULL THEN ${epcPropertyTypeSql(sql`epl`)} ELSE ${epcPropertyTypeSql(sql`epp`)} END)
+  ELSE p.property_type
+END`;
+
+/**
+ * The main building part's construction age band for one epc_property alias, as
+ * a correlated scalar subquery — properties can also have extension parts, so a
+ * plain JOIN on epc_building_part would multiply rows and break COUNTs.
+ */
+const mainPartAgeBandSql = (ep: Alias) => sql`(
+  SELECT ebp.construction_age_band
+  FROM epc_building_part ebp
+  WHERE ebp.epc_property_id = ${ep}.id
+  ORDER BY CASE WHEN ebp.identifier = 'main' THEN 0 ELSE 1 END, ebp.id
+  LIMIT 1
+)`;
+
+const ageBandYearCaseSql = (band: Alias) =>
+  sql`CASE ${band} ${sql.join(
+    Object.entries(CONSTRUCTION_AGE_BANDS).map(
+      ([code, { year }]) => sql`WHEN ${code} THEN ${year}::int`,
+    ),
+    sql` `,
+  )} END`;
+
+/**
+ * Representative construction year (int) for age-band reporting buckets. New:
+ * the main building part's RdSAP construction age band (lodged EPC, else
+ * predicted) mapped to the band's start year via CONSTRUCTION_AGE_BANDS.
+ * Legacy: property.year_built when numeric. NULL → the caller's Unknown bucket.
+ */
+export const constructionYearSql = sql`CASE
+  WHEN ${isNewApproachSql} THEN (CASE WHEN epl.id IS NOT NULL THEN ${ageBandYearCaseSql(mainPartAgeBandSql(sql`epl`))} ELSE ${ageBandYearCaseSql(mainPartAgeBandSql(sql`epp`))} END)
+  WHEN p.year_built ~ '^[0-9]+$' THEN CAST(p.year_built AS int)
+  ELSE NULL
+END`;
+
 // ─────────────────────────────────────────────────────────────────────────────
 // Per-property resolvers (TypeScript object building).
 // ─────────────────────────────────────────────────────────────────────────────
@ -586,49 +696,6 @@ export async function resolveDetailsEpcMeta(
  };
 }

-// RdSAP code → label maps for the descriptive fields the new pipeline stores as
-// codes on epc_property / epc_building_part (the property-row text columns aren't
-// written for new-approach properties). Unknown codes fall back to the raw value.
-const PROPERTY_TYPE_LABELS: Record<string, string> = {
-  "0": "House",
-  "1": "Bungalow",
-  "2": "Flat",
-  "3": "Maisonette",
-  "4": "Park home",
-};
-const BUILT_FORM_LABELS: Record<string, string> = {
-  "1": "Detached",
-  "2": "Semi-Detached",
-  "3": "End-Terrace",
-  "4": "Mid-Terrace",
-  "5": "Enclosed End-Terrace",
-  "6": "Enclosed Mid-Terrace",
-};
-// SAP tenure codes → the text labels already used in the data. NOTE: best-effort
-// (standard SAP 1/2/3); most rows store the text label directly, only a few use
-// codes. Confirm against the backend tenure enum.
-const TENURE_LABELS: Record<string, string> = {
-  "1": "Owner Occupied",
-  "2": "Rented Social",
-  "3": "Rented Private",
-};
-// Matches the backend ConstructionAgeBand enum (RdSAP England & Wales letters).
-const AGE_BAND_YEARS: Record<string, string> = {
-  A: "before 1900",
-  B: "1900–1929",
-  C: "1930–1949",
-  D: "1950–1966",
-  E: "1967–1975",
-  F: "1976–1982",
-  G: "1983–1990",
-  H: "1991–1995",
-  I: "1996–2002",
-  J: "2003–2006",
-  K: "2007–2011",
-  L: "2012–2022",
-  M: "2023 onwards",
-};
-
 /**
 * Resolve the descriptive property fields (type / built form / age) from the
 * epc_property graph for new-approach properties, since the property-row text
@ -692,7 +759,9 @@ async function resolvePropertyDescriptors(
    ? BUILT_FORM_LABELS[ep.builtForm] ?? ep.builtForm
    : null;
  const ageBand = mainPart?.constructionAgeBand ?? null;
-  const yearBuilt = ageBand ? AGE_BAND_YEARS[ageBand] ?? ageBand : null;
+  const yearBuilt = ageBand
+    ? CONSTRUCTION_AGE_BANDS[ageBand]?.label ?? ageBand
+    : null;

  const tenure = ep.tenure
    ? TENURE_LABELS[ep.tenure] ?? ep.tenure