chore(debug): summary_to_sap.py — Elmhurst Summary PDF -> our SAP + trail 🟪

Runs a Summary PDF through the chain-test path (pdftotext ->
ElmhurstSiteNotesExtractor -> from_elmhurst_site_notes) into Sap10Calculator
and dumps SAP + per-end-use kWh + the intermediate worksheet trail, for
diffing our calc against the accompanying Elmhurst U985 worksheet PDF.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

scripts/summary_to_sap.py

@@ -0,0 +1,94 @@
+"""Elmhurst Summary PDF -> EpcPropertyData -> Sap10Calculator, with a dump of
+our SAP score + per-end-use kWh + the `intermediate` worksheet trail, for
+diffing against the accompanying Elmhurst worksheet PDF.
+
+Usage:
+    python -m scripts.summary_to_sap "<path to Summary_*.pdf>"
+
+Reuses the exact preprocessing the Summary->EpcPropertyData chain test uses
+(`backend/documents_parser/tests/test_summary_pdf_mapper_chain.py`):
+`pdftotext -layout` -> Textract-style label/value stream -> extractor ->
+`from_elmhurst_site_notes` mapper.
+"""
+
+from __future__ import annotations
+
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+from backend.documents_parser.elmhurst_extractor import ElmhurstSiteNotesExtractor
+from datatypes.epc.domain.mapper import EpcPropertyDataMapper
+from domain.sap10_calculator.calculator import Sap10Calculator
+from domain.sap10_calculator.rdsap.cert_to_inputs import cert_to_inputs
+
+
+def _summary_pdf_to_textract_style_pages(pdf_path: Path) -> list[str]:
+    info = subprocess.run(
+        ["pdfinfo", str(pdf_path)], capture_output=True, text=True, check=True
+    ).stdout
+    m = re.search(r"Pages:\s+(\d+)", info)
+    if m is None:
+        raise RuntimeError(f"Could not parse page count from {pdf_path}")
+    page_count = int(m.group(1))
+    pages: list[str] = []
+    for i in range(1, page_count + 1):
+        layout = subprocess.run(
+            ["pdftotext", "-layout", "-f", str(i), "-l", str(i), str(pdf_path), "-"],
+            capture_output=True, text=True, check=True,
+        ).stdout
+        tokens: list[str] = []
+        for line in layout.splitlines():
+            if not line.strip():
+                tokens.append("")
+                continue
+            tokens.extend(p for p in re.split(r"\s{2,}", line.strip()) if p)
+        pages.append("\n".join(tokens))
+    return pages
+
+
+def main(pdf: str) -> None:
+    pdf_path = Path(pdf)
+    pages = _summary_pdf_to_textract_style_pages(pdf_path)
+    survey = ElmhurstSiteNotesExtractor(pages).extract()
+    epc = EpcPropertyDataMapper.from_elmhurst_site_notes(survey)
+    inp = cert_to_inputs(epc)
+    r = Sap10Calculator().calculate(epc)
+    p = epc.sap_building_parts[0] if epc.sap_building_parts else None
+
+    print(f"=== {pdf_path.name} ===")
+    print(f"dwelling_type={epc.dwelling_type!r} property_type={epc.property_type!r} "
+          f"age_band={p.construction_age_band if p else None} TFA={epc.total_floor_area_m2}")
+    print(f"OUR SAP = {r.sap_score} ({r.sap_score_continuous:.4f})  "
+          f"CO2={r.co2_kg_per_yr/1000:.3f} t/yr  PEUI={r.primary_energy_kwh_per_m2:.1f}")
+    print("--- per end use (kWh/yr) ---")
+    print(f"  space_heating useful = {r.space_heating_kwh_per_yr:.1f}")
+    print(f"  main_heating fuel    = {r.main_heating_fuel_kwh_per_yr:.1f}")
+    print(f"  secondary fuel       = {r.secondary_heating_fuel_kwh_per_yr:.1f}")
+    print(f"  hot_water            = {r.hot_water_kwh_per_yr:.1f}")
+    print(f"  lighting             = {r.lighting_kwh_per_yr:.1f}")
+    print(f"  pumps_fans           = {r.pumps_fans_kwh_per_yr:.1f}")
+    print(f"  delivered fuel total = {r.intermediate.get('delivered_fuel_kwh_per_yr', float('nan')):.1f}")
+    print("--- costs / rating ---")
+    for k in ("main_heating_cost_gbp", "secondary_heating_cost_gbp", "hot_water_cost_gbp",
+              "pumps_fans_cost_gbp", "lighting_cost_gbp", "ecf"):
+        print(f"  {k:28s} {r.intermediate.get(k, float('nan')):.4f}")
+    print(f"  is_off_peak={r.is_off_peak_meter} main_hrf={r.main_heating_high_rate_fraction} "
+          f"hw_hrf={r.hot_water_high_rate_fraction:.4f} other_hrf={r.other_electricity_high_rate_fraction}")
+    print(f"  space £/kWh={inp.space_heating_fuel_cost_gbp_per_kwh} "
+          f"hw £/kWh={inp.hot_water_fuel_cost_gbp_per_kwh} other £/kWh={inp.other_fuel_cost_gbp_per_kwh}")
+    print("--- heat balance (intermediate) ---")
+    for k in ("heat_transfer_coefficient_w_per_k", "heat_loss_parameter_w_per_m2k",
+              "walls_w_per_k", "roof_w_per_k", "floor_w_per_k", "party_walls_w_per_k",
+              "windows_w_per_k", "doors_w_per_k", "thermal_bridging_w_per_k",
+              "infiltration_w_per_k", "infiltration_ach", "internal_gains_annual_avg_w",
+              "mean_internal_temp_annual_avg_c", "useful_space_heating_kwh_per_yr"):
+        print(f"  {k:38s} {r.intermediate.get(k, float('nan')):.4f}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print(__doc__)
+        sys.exit(2)
+    main(sys.argv[1])