diff --git a/Dockerfile.test b/Dockerfile.test index 802eb3a4..74bee47b 100644 --- a/Dockerfile.test +++ b/Dockerfile.test @@ -1,8 +1,15 @@ FROM python:3.11-slim -# Install PostgreSQL binaries — required by pytest-postgresql to spawn ephemeral test databases +# System binaries: +# - postgresql: pytest-postgresql spawns ephemeral test databases +# - poppler-utils: provides pdfinfo / pdftotext, used by +# backend/documents_parser/tests/test_summary_pdf_mapper_chain.py's +# `_summary_pdf_to_textract_style_pages` helper for layout-preserving +# PDF text extraction. Pure-Python alternatives (pymupdf, pypdf) don't +# reproduce pdftotext -layout's row-major table cell ordering, which +# the Elmhurst Summary extractor depends on. RUN apt-get update \ - && apt-get install -y --no-install-recommends postgresql \ + && apt-get install -y --no-install-recommends postgresql poppler-utils \ && rm -rf /var/lib/apt/lists/* WORKDIR /app diff --git a/backend/documents_parser/tests/test_elmhurst_end_to_end.py b/backend/documents_parser/tests/test_elmhurst_end_to_end.py index 133c7816..f5b339bb 100644 --- a/backend/documents_parser/tests/test_elmhurst_end_to_end.py +++ b/backend/documents_parser/tests/test_elmhurst_end_to_end.py @@ -262,9 +262,15 @@ class TestHeating: assert result.sap_heating.main_heating_details[0].heat_emitter_type == 1 def test_emitter_temperature(self, result: EpcPropertyData) -> None: - assert ( - result.sap_heating.main_heating_details[0].emitter_temperature == "Unknown" - ) + # The Elmhurst Summary §14 lodges "Design flow temperature: Unknown" + # for this cert. `_elmhurst_emitter_temperature_int` (mapper.py) + # converts that to SAP10.2 Table 4d code 1 (high-temp / ≥45 °C — + # the worst-case assumption for an unmeasured gas boiler). This + # int encoding mirrors the API mapper's `MainHeatingDetail. + # emitter_temperature` for cross-mapper field parity; the older + # behaviour of surfacing the raw "Unknown" string was replaced + # when the int conversion landed. + assert result.sap_heating.main_heating_details[0].emitter_temperature == 1 def test_fan_flue_present(self, result: EpcPropertyData) -> None: assert result.sap_heating.main_heating_details[0].fan_flue_present is True diff --git a/datatypes/epc/domain/tests/test_from_rdsap_schema.py b/datatypes/epc/domain/tests/test_from_rdsap_schema.py index e5ef22c5..e91ca73a 100644 --- a/datatypes/epc/domain/tests/test_from_rdsap_schema.py +++ b/datatypes/epc/domain/tests/test_from_rdsap_schema.py @@ -367,7 +367,14 @@ class TestFromRdSapSchema21_0_1: assert result.inspection_date == date(2025, 4, 4) def test_total_floor_area(self, result: EpcPropertyData) -> None: - assert result.total_floor_area_m2 == 55.0 + # Slice 95 (commit f502db8c) changed the API mapper to compute + # `total_floor_area_m2` from the precise sum of per-bp + # `sap_floor_dimensions[*].total_floor_area` (here: 45.82, a + # single ground-floor dimension) rather than the lodged scalar + # (here: 55, an integer-rounded display value that doesn't + # match the per-bp geometry in this synthetic fixture). The + # worksheet uses per-bp sums and the mapper now mirrors that. + assert result.total_floor_area_m2 == 45.82 # --- property flags ---