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 71: RED tracer-bullet diff test for cohort 000477

Browse source 
Mirror the cohort 000474 mapper-vs-hand-built diff test for cert
U985-0001-000477 (single-bp mid-terrace, age band B, RIR with stud
walls + party gables, no extension). RED with 24 load-bearing
divergences — the toolchain (allow-list, exclusion list, diff helper)
from Slice 63 transfers cleanly; closing 000477's diffs will follow
the same patterns as Slices 64-70 (Cat A bulk-fix, mapper surfacing,
hand-built updates).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Khalim Conn-Kowlessar 2026-05-25 17:40:07 +00:00
parent 86eff23f08
commit 69bfac2204
1 changed files with 34 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
backend/documents_parser/tests/test_summary_pdf_mapper_chain.py
View file

@ -38,7 +38,10 @@ from backend.documents_parser.elmhurst_extractor import ElmhurstSiteNotesExtract
from datatypes.epc.domain.mapper import EpcPropertyDataMapper
from domain.sap.calculator import calculate_sap_from_inputs
from domain.sap.rdsap.cert_to_inputs import SAP_10_2_SPEC_PRICES, cert_to_inputs
from domain.sap.worksheet.tests import _elmhurst_worksheet_000474 as _w000474
from domain.sap.worksheet.tests import (
_elmhurst_worksheet_000474 as _w000474,
_elmhurst_worksheet_000477 as _w000477,
)
_FIXTURES = Path(__file__).parent / "fixtures"
_SUMMARY_000474_PDF = _FIXTURES / "Summary_000474.pdf"
@ -564,3 +567,33 @@ def test_from_elmhurst_site_notes_matches_hand_built_000474() -> None:
f"hand-built EpcPropertyData for cohort cert 000474:\n " +
"\n ".join(diffs)
)
def test_from_elmhurst_site_notes_matches_hand_built_000477() -> None:
# Arrange — _elmhurst_worksheet_000477.build_epc() is the canonical
# hand-built EpcPropertyData for cert U985-0001-000477 (single-bp
# mid-terrace, age band B, RIR with stud walls + party gables, no
# extension); it cascades to the worksheet PDF's `SAP value 65.0057`
# at 1e-4. Routing the Summary PDF through the Elmhurst mapper MUST
# produce a load-bearing-field-equivalent EpcPropertyData; any
# divergence is a mapper-coverage gap to close as its own slice.
pages = _summary_pdf_to_textract_style_pages(_SUMMARY_000477_PDF)
site_notes = ElmhurstSiteNotesExtractor(pages).extract()
mapped = EpcPropertyDataMapper.from_elmhurst_site_notes(site_notes)
hand_built = _w000477.build_epc()
# Act
diffs: list[str] = []
for field_name in _LOAD_BEARING_FIELDS:
diffs.extend(_diff_load_bearing(
getattr(mapped, field_name, None),
getattr(hand_built, field_name, None),
field_name,
))
# Assert
assert not diffs, (
f"{len(diffs)} load-bearing divergence(s) between mapped and "
f"hand-built EpcPropertyData for cohort cert 000477:\n " +
"\n ".join(diffs)
)