fix(burst-location): normalize simulation ids

app/services/burst_location.py

@@ -40,7 +40,7 @@ def _normalize_series(data: SeriesInput, field_name: str) -> pd.Series:
     else:
         raise ValueError(f"Unsupported data format for {field_name}.")
 
-    series.index = series.index.map(str)
+    series.index = series.index.map(_normalize_identifier)
     return pd.to_numeric(series, errors="raise")
 
 
@@ -385,6 +385,7 @@ def _build_observed_series_from_scada(
     data_type: str,
     series_name: str,
 ) -> tuple[pd.Series, int]:
+    sensor_ids = _dedupe_ids(sensor_ids)
     scada_mapping = _build_scada_mapping(network=network, data_type=data_type)
     missing_ids = [
         sensor_id for sensor_id in sensor_ids if sensor_id not in scada_mapping
@@ -400,6 +401,7 @@ def _build_observed_series_from_scada(
         start_time=start_dt.isoformat(),
         end_time=end_dt.isoformat(),
     )
+    scada_data = _normalize_timeseries_by_id(scada_data)
     values: dict[str, float] = {}
     sample_counts: list[int] = []
     for sensor_id, query_id in zip(sensor_ids, query_ids):
@@ -427,6 +429,7 @@ def _build_observed_series_from_simulation(
     simulation_scheme_name: str | None,
     simulation_scheme_type: str,
 ) -> tuple[pd.Series, int]:
+    sensor_ids = _dedupe_ids(sensor_ids)
     sensor_metadata = _build_sensor_metadata(network=network, data_type=data_type)
     missing_ids = [
         sensor_id for sensor_id in sensor_ids if sensor_id not in sensor_metadata
@@ -446,6 +449,7 @@ def _build_observed_series_from_simulation(
         simulation_scheme_name=simulation_scheme_name,
         simulation_scheme_type=simulation_scheme_type,
     )
+    simulation_data = _normalize_timeseries_by_id(simulation_data)
     values: dict[str, float] = {}
     sample_counts: list[int] = []
     for sensor_id in sensor_ids:
@@ -476,6 +480,7 @@ def _query_simulation_data_by_sensor_ids(
     if simulation_source not in {"scheme", "realtime"}:
         raise ValueError(f"Unsupported simulation_source: {simulation_source}")
 
+    sensor_ids = _dedupe_ids(sensor_ids)
     result: dict[str, list[dict[str, Any]]] = {
         sensor_id: [] for sensor_id in sensor_ids
     }
@@ -556,6 +561,7 @@ def _query_simulation_values(
     simulation_scheme_name: str | None,
     simulation_scheme_type: str,
 ) -> dict[str, list[dict[str, Any]]]:
+    element_ids = _dedupe_ids(element_ids)
     if not element_ids:
         return {}
     if simulation_source == "scheme":
@@ -595,14 +601,9 @@ def _build_sensor_metadata(network: str, data_type: str) -> dict[str, dict[str,
                 continue
         else:
             raise ValueError(f"Unsupported data_type: {data_type}")
-        element_id = item.get("associated_element_id")
-        query_id = item.get("api_query_id")
-        if (
-            isinstance(element_id, str)
-            and element_id
-            and isinstance(query_id, str)
-            and query_id
-        ):
+        element_id = _normalize_identifier(item.get("associated_element_id"))
+        query_id = _normalize_identifier(item.get("api_query_id"))
+        if element_id and query_id:
             metadata[element_id] = {"query_id": query_id, "scada_type": scada_type}
     return metadata
 
@@ -638,7 +639,31 @@ def _get_sensor_nodes(network: str, data_type: str) -> list[str]:
 def _dedupe_ids(ids: list[str] | None) -> list[str]:
     if ids is None:
         return []
-    return list(dict.fromkeys([str(item) for item in ids if item]))
+    return list(
+        dict.fromkeys(
+            normalized
+            for normalized in (_normalize_identifier(item) for item in ids)
+            if normalized
+        )
+    )
+
+
+def _normalize_identifier(value: Any) -> str:
+    if value is None:
+        return ""
+    return str(value).strip()
+
+
+def _normalize_timeseries_by_id(
+    data: dict[Any, list[dict[str, Any]]] | None,
+) -> dict[str, list[dict[str, Any]]]:
+    normalized_data: dict[str, list[dict[str, Any]]] = {}
+    for raw_id, records in (data or {}).items():
+        normalized_id = _normalize_identifier(raw_id)
+        if not normalized_id:
+            continue
+        normalized_data.setdefault(normalized_id, []).extend(records or [])
+    return normalized_data
 
 
 def _to_datetime(value: datetime | str) -> datetime: