junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Slice S0380.58: Elmhurst per-extension Room(s) in Roof extraction + TFA fix

Browse source 
Cert 000565 surfaced a per-extension Room(s) in Roof coverage gap.
§4 Dimensions lodges an RR floor area for every BP (Main + each
extension) and §8.1 lodges full construction details per BP. The
old extractor parsed RR from §4 + §8.1 for Main only — the 4
extensions' RR areas (34 + 5 + 32 + 2 = 73 m²) were silently
dropped, leaving TFA at 246.91 m² vs the worksheet's 319.91 m²
(23% deficit).

Schema:
- `ExtensionPart.room_in_roof: Optional[RoomInRoof] = None` field.
  None for single-storey extensions (no RR lodged); populated for
  every extension that lodges a §4 RR floor area > 0.

Extractor:
- `_room_in_roof_from_bodies(dim_body, rir_body, age_band)`
  parameterises the previously Main-only `_extract_room_in_roof`
  so the same parsing applies to each extension.
- `_extract_extensions` now slices §8.1 by BP (alongside the
  existing §4/§7/§8/§9 slicing) and reads each extension's RR age
  band from §3's "<N>th Ext. Room(s) in Roof <band>" line via a
  new regex.
- A new defensive "§4 lodges RR area but §8.1 has no construction
  details" branch returns a partial `RoomInRoof` with empty surfaces
  so the cascade still attributes the floor area to TFA. (Not
  triggered on 000565 — all 5 BPs lodge construction details — but
  needed for older Elmhurst variants per the existing extractor
  comment style.)

Mapper:
- `_map_elmhurst_building_parts` now passes each extension's
  `room_in_roof` through `_map_elmhurst_room_in_roof` to the
  extension's `SapBuildingPart.sap_room_in_roof`. Previously the
  loop hardcoded the field as None.
- `total_floor_area_m2` derivation now also sums each extension's
  `room_in_roof.floor_area_m2`. Without this, the per-BP RR floor
  area is lodged on the BP but the cert's top-level TFA stays at
  the pre-fix value.

Cert 000565 cascade impact:
- TFA: 246.91 → 319.91 ✓ (matches U985-0001-000565.pdf Block 1)
- space_heating_kwh_per_yr:  Δ −9,107.71 → −1,099.50  (88% reduction)
- main_heating_fuel_kwh_per_yr: Δ −5,357.47 → −646.76  (88% reduction;
    space_heating × 1/HP COP — main_heating tracks space_heating)
- lighting_kwh_per_yr:       Δ −236.19 → +2.18  (essentially closed —
    RdSAP §12-1 lighting is TFA-proportional)
- hot_water_kwh_per_yr:      Δ +214.50 → +271.84
- co2_kg_per_yr:             Δ −1,438.16 → −751.06
- total_fuel_cost_gbp:       Δ −1,055.62 → −564.05
- sap_score_continuous:      Δ +1.70 → +6.75  (cost/TFA dropped because
    cost rose ~14% but TFA rose ~30% — the remaining −564 cost gap
    has to close before SAP catches up)

Single-storey-extension certs: `room_in_roof=None` for each extension
(no §4 RR lodgement), no behavioural change. Cohort regression check:
415 pass + 10 expected 000565 fails — no regression on the 14 Summary
fixtures + JSON fixtures that don't carry per-extension RR.

Pyright net-zero on all 3 touched files (32 / 0 / 0).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Khalim Conn-Kowlessar 2026-05-28 22:58:43 +00:00 • committed by Jun-te Kim
parent 358b4dcd01
commit 10437143c4
3 changed files with 77 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

86
backend/documents_parser/elmhurst_extractor.py
View file

@ -389,34 +389,59 @@ class ElmhurstSiteNotesExtractor:
def _extract_room_in_roof(
self, main_dim_body: str, age_band_text: str
) -> Optional[RoomInRoof]:
"""Parse the §8.1 Rooms in Roof section for the Main bp. Returns
None when no RR is lodged (single-storey or simple loft houses).
`main_dim_body` is the Main-property §4 chunk used to pull the
RR floor area; `age_band_text` is the §3 raw text holding the
"Main Prop. Room(s) in Roof <band>" line."""
# RR floor area lives in §4 Dimensions immediately above the
# storey floor entries: "Room(s) in Roof: 15.06".
m = re.search(r"Room\(s\) in Roof:\s+(\d+(?:\.\d+)?)", main_dim_body)
"""Parse the §8.1 Rooms in Roof block for the Main bp."""
section = self._between("8.1 Rooms in Roof:", "9.0 Floors:")
bp_chunks = self._split_section_by_bp(section) if section.strip() else []
main_body = bp_chunks[0][1] if bp_chunks else ""
# Age band from §3: "Main Prop. Room(s) in Roof H 1991-1995"
age_m = re.search(
r"Main Prop\. Room\(s\) in Roof\s+([A-M] [^\n]+)", age_band_text
)
age_band = age_m.group(1).strip() if age_m else None
return self._room_in_roof_from_bodies(
dim_body=main_dim_body,
rir_body=main_body,
age_band=age_band,
)
def _room_in_roof_from_bodies(
self,
dim_body: str,
rir_body: str,
age_band: Optional[str],
) -> Optional[RoomInRoof]:
"""Parse a single-BP Room(s) in Roof from the §4 dimension body
(floor area) and §8.1 construction body (assessment + surfaces).
Used for both Main and each extension — extensions get their
own per-BP slice of §4 and §8.1 + the per-extension age band
from §3's "<N>th Ext. Room(s) in Roof <age>" line.
"""
m = re.search(r"Room\(s\) in Roof:\s+(\d+(?:\.\d+)?)", dim_body)
if m is None:
return None
floor_area = float(m.group(1))
if floor_area <= 0:
return None
section = self._between("8.1 Rooms in Roof:", "9.0 Floors:")
if not section.strip() or "Room in roof type" not in section:
return None
bp_chunks = self._split_section_by_bp(section)
main_body = bp_chunks[0][1] if bp_chunks else section
lines = [l.strip() for l in main_body.splitlines() if l.strip()]
if not rir_body.strip() or "Room in roof type" not in rir_body:
# §4 lodged an RR area but §8.1 has no construction details
# for this BP — surface as a partial RR so the cascade can
# still attribute the floor area to TFA. Empty surfaces
# tuple is the sentinel the mapper consumes.
return RoomInRoof(
floor_area_m2=floor_area,
construction_age_band=age_band,
assessment="",
surfaces=[],
)
lines = [l.strip() for l in rir_body.splitlines() if l.strip()]
assessment_idx = next(
(i for i, l in enumerate(lines) if l == "Assessment"), None
)
assessment = (
lines[assessment_idx + 1] if assessment_idx is not None and assessment_idx + 1 < len(lines) else ""
lines[assessment_idx + 1]
if assessment_idx is not None and assessment_idx + 1 < len(lines)
else ""
)
surfaces: List[RoomInRoofSurface] = []
for name in self._RIR_SURFACE_NAMES:
try:
@ -424,13 +449,6 @@ class ElmhurstSiteNotesExtractor:
except ValueError:
continue
surfaces.append(self._parse_rir_surface_row(name, lines, idx))
# Age band from §3: "Main Prop. Room(s) in Roof B 1900-1929"
age_m = re.search(
r"Main Prop\. Room\(s\) in Roof\s+([A-M] [^\n]+)", age_band_text
)
age_band = age_m.group(1).strip() if age_m else None
return RoomInRoof(
floor_area_m2=floor_area,
construction_age_band=age_band,
@ -522,14 +540,26 @@ class ElmhurstSiteNotesExtractor:
dim_section = self._between("4.0 Dimensions:", "5.0 Conservatory:")
wall_section = self._between("7.0 Walls:", "8.0 Roofs:")
roof_section = self._between("8.0 Roofs:", "8.1 Rooms in Roof:")
rir_section = self._between("8.1 Rooms in Roof:", "9.0 Floors:")
floor_section = self._between("9.0 Floors:", "10.0 Doors:")
dim_type = self._str_val("Dimension type")
dim_chunks = dict(self._split_section_by_bp(dim_section))
wall_chunks = dict(self._split_section_by_bp(wall_section))
roof_chunks = dict(self._split_section_by_bp(roof_section))
rir_chunks = dict(self._split_section_by_bp(rir_section)) if rir_section.strip() else {}
floor_chunks = dict(self._split_section_by_bp(floor_section))
# Per-extension RR age bands from §3: "1st Ext. Room(s) in Roof I 1996-2002".
ext_rir_age_re = re.compile(
r"(\d+(?:st|nd|rd|th))\s+Ext\.\s+Room\(s\) in Roof\s+([A-M] [^\n]+)",
re.MULTILINE,
)
ext_rir_age_bands: dict[str, str] = {
f"{m.group(1)} Extension": m.group(2).strip()
for m in ext_rir_age_re.finditer(self._text)
}
main_walls = self._extract_walls()
main_roof = self._extract_roof()
main_floor = self._extract_floor()
@ -580,6 +610,11 @@ class ElmhurstSiteNotesExtractor:
roof = main_roof if self._local_bool(roof_lines, "As Main") else self._roof_details_from_lines(roof_lines)
floor = main_floor if self._local_bool(floor_lines, "As Main") else self._floor_details_from_lines(floor_lines)
rir = self._room_in_roof_from_bodies(
dim_body=dim_body,
rir_body=rir_chunks.get(name, ""),
age_band=ext_rir_age_bands.get(name),
)
extensions.append(
ExtensionPart(
name=name,
@ -591,6 +626,7 @@ class ElmhurstSiteNotesExtractor:
walls=walls,
roof=roof,
floor=floor,
room_in_roof=rir,
)
)
return extensions

10
datatypes/epc/domain/mapper.py
View file

@ -378,7 +378,12 @@ class EpcPropertyDataMapper:
for ext in survey.extensions
for f in ext.dimensions.floors
)
+ (survey.room_in_roof.floor_area_m2 if survey.room_in_roof else 0.0),
+ (survey.room_in_roof.floor_area_m2 if survey.room_in_roof else 0.0)
+ sum(
ext.room_in_roof.floor_area_m2
for ext in survey.extensions
if ext.room_in_roof is not None
),
2,
),
built_form=built_form,
@ -3142,6 +3147,9 @@ def _map_elmhurst_building_parts(
walls=ext.walls,
roof=ext.roof,
floor=ext.floor,
room_in_roof=_map_elmhurst_room_in_roof(
ext.room_in_roof, is_flat=is_flat,
),
)
)
return parts

7
datatypes/epc/surveys/elmhurst_site_notes.py
View file

@ -340,6 +340,13 @@ class ExtensionPart:
walls: WallDetails
roof: RoofDetails
floor: FloorDetails
# §4 + §8.1 Room(s) in Roof on this extension. None when no RR is
# lodged for the extension (typical single-storey extensions). For
# multi-storey extensions with a top-floor RR (cert 000565: Ext1=34
# m², Ext2=5 m², Ext3=32 m², Ext4=2 m²), drops 73 m² of TFA from
# the cascade when None, pulling space_heating and lighting kWh
# down by ~23% on the cert.
room_in_roof: Optional[RoomInRoof] = None
@dataclass