has issues

pipeline/transform/test_merge.py

@@ -1,11 +1,17 @@
 import polars as pl
 import pytest
+from shapely import box
 
 from pipeline.transform.merge import (
     _AREA_COLUMNS,
+    CONSERVATION_AREA_FEATURE,
+    LISTED_BUILDING_FEATURE,
     TREE_DENSITY_FEATURE,
     _is_dynamic_poi_metric_column,
     _less_deprived_percentile_expr,
+    _matched_listed_building_flags,
+    _postcode_conservation_area_flags,
+    _postcode_listed_building_candidates,
     _tree_density_by_postcode,
     _validate_lad_source_coverage,
     _validate_property_postcodes,
@@ -48,6 +54,106 @@ def test_country_code_is_kept_in_postcode_area_columns() -> None:
     assert "ctry25cd" in _AREA_COLUMNS
 
 
+def test_conservation_area_feature_is_area_level() -> None:
+    assert CONSERVATION_AREA_FEATURE in _AREA_COLUMNS
+
+
+def test_listed_building_feature_is_property_level() -> None:
+    assert LISTED_BUILDING_FEATURE not in _AREA_COLUMNS
+
+
+def test_postcode_conservation_area_flags_marks_point_membership() -> None:
+    postcodes = pl.DataFrame(
+        {
+            "postcode": ["AA1 1AA", "BB1 1BB", "CC1 1CC"],
+            "lat": [0.5, 2.0, None],
+            "lon": [0.5, 2.0, 0.5],
+        }
+    )
+
+    result = _postcode_conservation_area_flags(
+        postcodes, [box(0, 0, 1, 1)], "EPSG:4326", batch_size=2
+    ).sort("postcode")
+
+    assert result.to_dicts() == [
+        {"postcode": "AA1 1AA", CONSERVATION_AREA_FEATURE: "Yes"},
+        {"postcode": "BB1 1BB", CONSERVATION_AREA_FEATURE: "No"},
+        {"postcode": "CC1 1CC", CONSERVATION_AREA_FEATURE: "No"},
+    ]
+
+
+def test_postcode_listed_building_candidates_uses_nearby_postcodes() -> None:
+    listed_points = pl.DataFrame(
+        {
+            "ListEntry": [1234, 5678],
+            "Name": ["1 and 2 High Street", "Distant Hall"],
+            "Grade": ["II", "I"],
+            "Easting": [100.0, 1000.0],
+            "Northing": [100.0, 1000.0],
+        }
+    ).with_columns(
+        pl.col("Name")
+        .str.to_uppercase()
+        .str.replace_all(r"[^0-9A-Z]+", " ")
+        .str.replace_all(r"\s+", " ")
+        .str.strip_chars()
+        .alias("_listed_match_name")
+    )
+    active_postcodes = pl.DataFrame(
+        {
+            "postcode": ["AA1 1AA", "BB1 1BB"],
+            "east1m": [105.0, 5000.0],
+            "north1m": [105.0, 5000.0],
+        }
+    )
+
+    result = _postcode_listed_building_candidates(
+        listed_points,
+        active_postcodes,
+        nearest_postcodes=1,
+        max_distance_m=25,
+    )
+
+    assert result.select("postcode", "_listed_match_name").to_dicts() == [
+        {"postcode": "AA1 1AA", "_listed_match_name": "1 AND 2 HIGH STREET"}
+    ]
+
+
+def test_matched_listed_building_flags_requires_address_match() -> None:
+    properties = pl.DataFrame(
+        {
+            "postcode": ["AA1 1AA", "AA1 1AA", "BB1 1BB"],
+            "pp_address": ["1 HIGH STREET", "99 HIGH STREET", "THE OLD RECTORY"],
+            "epc_address": ["1, High Street", "99, High Street", "Old Rectory"],
+        }
+    )
+    listed_candidates = pl.DataFrame(
+        {
+            "postcode": ["AA1 1AA", "BB1 1BB"],
+            "_listed_match_name": ["1 AND 2 HIGH STREET", "OLD RECTORY"],
+            "_listed_grade": ["II", "II*"],
+            "_listed_entry": [1234, 5678],
+        }
+    )
+
+    result = _matched_listed_building_flags(
+        properties.lazy(), listed_candidates, min_score=95
+    ).sort("postcode", "pp_address")
+
+    assert result.to_dicts() == [
+        {
+            "postcode": "AA1 1AA",
+            "pp_address": "1 HIGH STREET",
+            LISTED_BUILDING_FEATURE: "Yes",
+        },
+        {
+            "postcode": "BB1 1BB",
+            "pp_address": "THE OLD RECTORY",
+            LISTED_BUILDING_FEATURE: "Yes",
+        },
+    ]
+
+
 def test_validate_property_postcodes_rejects_blank_rows() -> None:
     df = pl.DataFrame(
         {