diff --git a/backend/documents_parser/tests/fixtures/Summary_000565_case52.pdf b/backend/documents_parser/tests/fixtures/Summary_000565_case52.pdf new file mode 100644 index 00000000..82d1891f Binary files /dev/null and b/backend/documents_parser/tests/fixtures/Summary_000565_case52.pdf differ diff --git a/tests/domain/sap10_calculator/worksheet/_elmhurst_worksheet_000565_case52.py b/tests/domain/sap10_calculator/worksheet/_elmhurst_worksheet_000565_case52.py new file mode 100644 index 00000000..8f368476 --- /dev/null +++ b/tests/domain/sap10_calculator/worksheet/_elmhurst_worksheet_000565_case52.py @@ -0,0 +1,110 @@ +"""Mapper-driven cascade pin against the Elmhurst U985-0001-000565 +"simulated case 52" worksheet — a REGULAR (non-combi) mains-gas boiler +feeding a hot-water CYLINDER, on standard tariff. + +Like 000565 / the _rr cases, this fixture does NOT hand-build the +EpcPropertyData: it routes the Summary PDF through +ElmhurstSiteNotesExtractor + from_elmhurst_site_notes so the SAP-result +pin grid exercises the WHOLE extractor + mapper + calculator pipeline. + +This case was hand-built (Khalim) to ground-truth the LAST untested +branch of the cylinder/water-heating chain that the combi/immersion +fixtures don't reach: a regular boiler + cylinder heated from the main, +exercising SAP 10.2 §4 — + - Cylinder storage loss via Table 2 loss factor (51) 0.0181, Table 2a + volume factor (52) 0.9086, Table 2b temperature factor (53) 0.7020 + (NO cylinder thermostat) → (55) 1.8466. + - PRIMARY circuit loss (59) 128.3772 (winter) — the Table 3 path for + UNINSULATED primary pipework + no cylinder stat. Case 50 (immersion, + no boiler) couldn't reach this branch. + - Combi loss (61) correctly 0 (regular boiler, not a combi). +The whole chain reconciles to the U985 worksheet EXACTLY with no +calculator change — it pins the cylinder-loss derivation as correct. + +Cert shape: 000565 semi shell, single main = mains-gas REGULAR boiler +(SAP code 102, control 2106 programmer + room stat + TRVs), water +heating from main (WHC 901) via a 160 L foam-insulated cylinder (no +cylinder stat, uninsulated primary pipework, in heated space), one +instantaneous electric shower, no secondary, no PV, standard tariff. + +Source: user-simulated PDFs at `sap worksheets/golden fixture debugging/ +simulated case 52/`. The Summary is mirrored into the tracked +`backend/documents_parser/tests/fixtures/Summary_000565_case52.pdf` so the +test runs without depending on the unstaged workspace. + +Worksheet pin targets (U985-0001-000565 block 1 — existing dwelling SAP): +- SAP rating 57 (258); continuous 57.2904; ECF 3.0616 (257) +- Total fuel cost £911.1973 (255) +- Total CO2 3834.8434 kg/year (272) +- Space heating 10563.5170 kWh/year ((98c)) +- Main 1 fuel 13371.5405 kWh/year (211) +- Secondary fuel 0.0 kWh/year (215) +- Hot water fuel 3929.7635 kWh/year (219) +- Lighting 435.3204 kWh/year (232) +- Pumps/fans 401.6384 kWh/year (231) + +Per [[feedback-zero-error-strict]] + [[feedback-e2e-validation- +philosophy]]: pins are abs=1e-4 against the worksheet PDF. The pin +values live in `test_e2e_elmhurst_sap_score._FIXTURE_PINS`. +""" + +from __future__ import annotations + +import re +import subprocess +from pathlib import Path +from typing import Final + +from backend.documents_parser.elmhurst_extractor import ElmhurstSiteNotesExtractor +from datatypes.epc.domain.epc_property_data import EpcPropertyData +from datatypes.epc.domain.mapper import EpcPropertyDataMapper + +# parents[0]=worksheet/, [1]=sap10_calculator/, [2]=domain/, [3]=tests/, +# [4]=repo root. +_SUMMARY_PDF: Final[Path] = ( + Path(__file__).resolve().parents[4] + / "backend" / "documents_parser" / "tests" / "fixtures" + / "Summary_000565_case52.pdf" +) + + +def _summary_pdf_to_textract_style_pages(pdf_path: Path) -> list[str]: + """Convert a Summary PDF into the per-page text format the + ElmhurstSiteNotesExtractor expects (label\\nvalue sequences). Mirror + of the helper in the other `_elmhurst_worksheet_*` fixtures. + """ + 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 + parts = [p for p in re.split(r"\s{2,}", line.strip()) if p] + tokens.extend(parts) + pages.append("\n".join(tokens)) + return pages + + +def build_epc() -> EpcPropertyData: + """Route the simulated case-52 Summary through extractor + mapper. + No hand-built EpcPropertyData — the extractor and mapper are part of + the test target. + """ + pages = _summary_pdf_to_textract_style_pages(_SUMMARY_PDF) + site_notes = ElmhurstSiteNotesExtractor(pages).extract() + return EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes) diff --git a/tests/domain/sap10_calculator/worksheet/test_e2e_elmhurst_sap_score.py b/tests/domain/sap10_calculator/worksheet/test_e2e_elmhurst_sap_score.py index 1625bcbc..13b1b1bb 100644 --- a/tests/domain/sap10_calculator/worksheet/test_e2e_elmhurst_sap_score.py +++ b/tests/domain/sap10_calculator/worksheet/test_e2e_elmhurst_sap_score.py @@ -48,6 +48,7 @@ from tests.domain.sap10_calculator.worksheet import ( _elmhurst_worksheet_001431_case6 as _w001431_case6, _elmhurst_worksheet_001431_case7 as _w001431_case7, _elmhurst_worksheet_001431_case20 as _w001431_case20, + _elmhurst_worksheet_000565_case52 as _w000565_case52, ) from tests.domain.sap10_calculator.worksheet._elmhurst_fixtures import ( ALL_FIXTURES as _ELMHURST_FIXTURES, @@ -296,6 +297,23 @@ _FIXTURE_PINS: Final[dict[str, FixtureCascadePins]] = { lighting_kwh_per_yr=246.3083, pumps_fans_kwh_per_yr=0.0, ), + # Mapper-driven — Summary_000565_case52.pdf → extractor → mapper → + # calculator. Regular (non-combi) mains-gas boiler (SAP 102) + a + # 160 L foam cylinder heated from the main (WHC 901), no cylinder + # stat + uninsulated primary pipework, standard tariff. Validates the + # cylinder storage loss (51-55) + PRIMARY loss (59) chain — the + # branch immersion/combi fixtures can't reach. Reconciles to the + # worksheet EXACTLY with no calculator change. + "000565_case52": FixtureCascadePins( + sap_score=57, sap_score_continuous=57.2904, ecf=3.0616, + total_fuel_cost_gbp=911.1973, co2_kg_per_yr=3834.8434, + space_heating_kwh_per_yr=10563.5170, + main_heating_fuel_kwh_per_yr=13371.5405, + secondary_heating_fuel_kwh_per_yr=0.0, + hot_water_kwh_per_yr=3929.7635, + lighting_kwh_per_yr=435.3204, + pumps_fans_kwh_per_yr=401.6384, + ), } @@ -315,6 +333,7 @@ _FIXTURE_MODULES: Final[dict[str, ModuleType]] = { "001431_case6": _w001431_case6, "001431_case7": _w001431_case7, "001431_case20": _w001431_case20, + "000565_case52": _w000565_case52, }