fix: make vector ingestion canonical and atomic

2026-07-14 15:28:14 +02:00
parent 7fa4f1fac9
commit 8c694fa9ce
8 changed files with 145 additions and 25 deletions
@@ -376,32 +376,37 @@ class DatasetService:
            metadata_json=metadata,
            status=status,
        )
-        db.add(dataset)
-        db.add(
-            DatasetVersion(
-                dataset_id=dataset.id,
-                version=1,
-                storage_path=dataset.storage_path,
-                source_version=dataset.source_version,
-                observed_at=dataset.observed_at,
-                valid_from=dataset.valid_from,
-                valid_to=dataset.valid_to,
-                checksum_sha256=dataset.checksum_sha256,
-                source_metadata=dataset.source_metadata,
-                provenance_metadata=dataset.provenance_metadata,
-            )
-        )
-        db.commit()
-        db.refresh(dataset)
-
-        if canonical_type == "vector" and vector_payload is not None and status == "ready":
-            feature_class = reference_layer_name if normalized_role == "reference" else None
-            VectorFeatureService.persist_geojson_features(
-                db=db,
-                dataset_id=dataset.id,
-                payload=vector_payload,
-                feature_class=feature_class,
+        try:
+            db.add(dataset)
+            db.add(
+                DatasetVersion(
+                    dataset_id=dataset.id,
+                    version=1,
+                    storage_path=dataset.storage_path,
+                    source_version=dataset.source_version,
+                    observed_at=dataset.observed_at,
+                    valid_from=dataset.valid_from,
+                    valid_to=dataset.valid_to,
+                    checksum_sha256=dataset.checksum_sha256,
+                    source_metadata=dataset.source_metadata,
+                    provenance_metadata=dataset.provenance_metadata,
+                )
            )
+            if canonical_type == "vector" and vector_payload is not None and status == "ready":
+                feature_class = reference_layer_name if normalized_role == "reference" else None
+                VectorFeatureService.persist_geojson_features(
+                    db=db,
+                    dataset_id=dataset.id,
+                    payload=vector_payload,
+                    feature_class=feature_class,
+                    commit=False,
+                )
+            db.commit()
+            db.refresh(dataset)
+        except Exception:
+            db.rollback()
+            StorageService.remove_dataset_file(storage_info["storage_path"])
+            raise

        return DatasetService._to_response(dataset)