Remove legacy code for format conversion

solar_relay/storage.py

@@ -20,7 +20,6 @@ import pyarrow.parquet as pq
 
 from .config import retention_cutoff, utc_text
 from .coverage import daily_coverage, milliseconds, sample_coverage
-from .history import normalize_history_sample
 
 NUMBERS = (
     "production_w", "production_ac_w", "consumption_w", "grid_w",
@@ -34,7 +33,6 @@ SCHEMA = pa.schema([
     *((field, pa.float64()) for field in NUMBERS),
     ("boiler_enabled", pa.bool_()), ("boiler_reason", pa.string()),
     ("record_kind", pa.string()),
-    ("interval_energy_wh", pa.struct([(field, pa.float64()) for field in ("production", "consumption", "self_consumption", "bought", "sold")])),
     ("power_ms", pa.int64()), ("power_ok", pa.bool_()),
     ("meter_ms", pa.int64()), ("meter_ok", pa.bool_()),
     ("boiler_ms", pa.int64()), ("boiler_ok", pa.bool_()),
@@ -82,9 +80,13 @@ class Store:
         if not path.exists():
             return []
         parquet = pq.ParquetFile(path, page_checksum_verification=True)
-        if not parquet.schema_arrow.equals(SCHEMA, check_metadata=True):
+        schema = parquet.schema_arrow
+        # Validate the fields this version uses; read only those columns.
+        if schema.metadata != SCHEMA.metadata or any(
+            schema.get_field_index(field.name) < 0 or schema.field(field.name) != field for field in SCHEMA
+        ):
             raise StoreError("Unsupported Parquet archive schema")
-        return parquet.read(columns=columns).to_pylist()
+        return parquet.read(columns=SCHEMA.names if columns is None else columns).to_pylist()
 
     @staticmethod
     def _sync_directory(path):
@@ -125,8 +127,7 @@ class Store:
             "payload": json.dumps(sample, allow_nan=False, separators=(",", ":")),
             **{name: readings.get(name) for name in NUMBERS},
             "boiler_enabled": readings.get("boiler_enabled"), "boiler_reason": readings.get("boiler_reason"),
-            "record_kind": "history" if "history_interval" in sample else "live",
-            "interval_energy_wh": sample.get("history_interval", {}).get("energy_wh"),
+            "record_kind": "history" if "solarweb_history" in sample.get("raw", {}) else "live",
             **{name: bool(value) if name.endswith("_ok") else value
                for name, value in zip(COVERAGE_COLUMNS[1:], coverage[3:])},
         }
@@ -137,32 +138,11 @@ class Store:
             rows = self._read(path)
             for existing in rows:
                 if existing["id"] == row["id"]:
-                    if normalize_history_sample(json.loads(existing["payload"])) != normalize_history_sample(sample):
+                    if json.loads(existing["payload"]) != sample:
                         raise StoreError("Sample ID already contains different data")
                     return
             self._write(path, [*rows, row])
 
-    def normalize_history(self):
-        """Backfill common power columns and queued payloads without changing IDs or acknowledgements."""
-        changed = 0
-        with self._locked(write=True):
-            for path in self._files():
-                rows = self._read(path)
-                dirty = False
-                for index, row in enumerate(rows):
-                    if row["record_kind"] != "history":
-                        continue
-                    sample = json.loads(row["payload"])
-                    normalized = normalize_history_sample(sample)
-                    if normalized == sample:
-                        continue
-                    rows[index] = {**self._row(normalized, row["uploaded_at"]), "recorded_ns": row["recorded_ns"]}
-                    changed += 1
-                    dirty = True
-                if dirty:
-                    self._write(path, rows)
-        return changed
-
     def pending(self, limit):
         with self._locked():
             rows = []