From 312400759f68fc3fbb6b902a8e07f49ebdae4474 Mon Sep 17 00:00:00 2001
From: Codex <codex@geointel.local>
Date: Wed, 15 Jul 2026 15:53:10 +0200
Subject: [PATCH] fix: normalize official agricultural crop groups

---
 CHANGELOG.md                                  |  2 ++
 .../app/services/vector_feature_service.py    | 22 ++++++++++++++++++-
 ...t_sprint205_agricultural_parcel_history.py | 14 ++++++++++++
 .../provision_agricultural_parcel_history.py  |  2 ++
 4 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index e71a9979..61078d85 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,8 @@
 - Added a scope-specific 18-edition temporal series while explicitly disabling
   parcel-level lineage and excluding the provisional current campaign.
 - Added focused source, clipping, metric, pagination, packaging and UI tests.
+- Added compatibility for the official comma-separated grain and horticulture
+  group labels after live source validation exposed their exact wording.
 
 ## Sprint 204 Governed BWK and Natura 2000 for Mol (2026-07-15)
 
diff --git a/backend/app/services/vector_feature_service.py b/backend/app/services/vector_feature_service.py
index e50f3b12..81340537 100644
--- a/backend/app/services/vector_feature_service.py
+++ b/backend/app/services/vector_feature_service.py
@@ -101,8 +101,25 @@ SEMANTIC_COUNT_LABELS = {
     "agriculture": "Landbouwgebruikspercelen",
 }
 
+# Sprint 205 initially normalized two official comma-separated ALZ group labels
+# mechanically. Keep those persisted values queryable while new artifacts use
+# the explicit controlled keys.
+SELECTION_FILTER_VALUE_ALIASES: dict[tuple[str, str], tuple[str, ...]] = {
+    ("main_crop_group_key", "grains_seeds_legumes"): ("granen,_zaden_en_peulvruchten",),
+    ("main_crop_group_key", "horticulture"): ("groenten,_kruiden_en_sierplanten",),
+}
+
 
 class VectorFeatureService:
+    @staticmethod
+    def _expanded_selection_filter_values(filter_property: str, filter_values: list[Any]) -> list[str]:
+        expanded: list[str] = []
+        for value in filter_values:
+            normalized = str(value)
+            expanded.append(normalized)
+            expanded.extend(SELECTION_FILTER_VALUE_ALIASES.get((filter_property, normalized), ()))
+        return list(dict.fromkeys(expanded))
+
     @staticmethod
     def _dataset_theme(dataset: Dataset) -> str | None:
         source_metadata = dataset.source_metadata if isinstance(dataset.source_metadata, dict) else {}
@@ -453,7 +470,10 @@ class VectorFeatureService:
                     details={"dataset_id": str(dataset.id), "filter_property": filter_property},
                     status_code=500,
                 )
-            normalized_filter_values = [str(value) for value in filter_values]
+            normalized_filter_values = VectorFeatureService._expanded_selection_filter_values(
+                filter_property,
+                filter_values,
+            )
             metric_filter += (
                 VectorFeature.properties_json.op("->>")(filter_property).in_(normalized_filter_values),
             )
diff --git a/backend/tests/test_sprint205_agricultural_parcel_history.py b/backend/tests/test_sprint205_agricultural_parcel_history.py
index 94485fd7..3523058c 100644
--- a/backend/tests/test_sprint205_agricultural_parcel_history.py
+++ b/backend/tests/test_sprint205_agricultural_parcel_history.py
@@ -150,6 +150,20 @@ def test_crop_code_list_preserves_year_specific_titles_and_reports_conflicts() -
     assert result["code_title_conflicts"] == {"201": ["Korrelmais", "Mais"]}
     assert "maincropgroup_title" in result["historical_comparison_rule"]
     assert module.normalized_group_title("Maïs") == "maize"
+    assert module.normalized_group_title("Granen, zaden en peulvruchten") == "grains_seeds_legumes"
+    assert module.normalized_group_title("Groenten, kruiden en sierplanten") == "horticulture"
+
+
+def test_persisted_first_import_group_keys_remain_query_compatible() -> None:
+    assert VectorFeatureService._expanded_selection_filter_values(
+        "main_crop_group_key",
+        ["grains_seeds_legumes", "horticulture"],
+    ) == [
+        "grains_seeds_legumes",
+        "granen,_zaden_en_peulvruchten",
+        "horticulture",
+        "groenten,_kruiden_en_sierplanten",
+    ]
 
 
 def test_features_are_exactly_clipped_in_lambert72_and_keep_source_fields() -> None:
diff --git a/scripts/provision_agricultural_parcel_history.py b/scripts/provision_agricultural_parcel_history.py
index e922d5dd..04548e64 100644
--- a/scripts/provision_agricultural_parcel_history.py
+++ b/scripts/provision_agricultural_parcel_history.py
@@ -94,8 +94,10 @@ GROUP_ALIASES = {
     "grasland": "grassland",
     "mais": "maize",
     "granen/zaden/peulvruchten": "grains_seeds_legumes",
+    "granen, zaden en peulvruchten": "grains_seeds_legumes",
     "aardappelen": "potatoes",
     "groenten/kruiden/sierplanten": "horticulture",
+    "groenten, kruiden en sierplanten": "horticulture",
     "suikerbieten": "sugar_beets",
     "voedergewassen": "fodder_crops",
     "fruit en noten": "fruit_nuts",