feat(scada): add project monitoring replay

app/infra/db/timescaledb/repositories/scada.py

@@ -9,6 +9,86 @@ class ScadaRepository:
     VALUE_FIELDS = frozenset({"monitored_value", "cleaned_value"})
     RESULT_COLUMNS = "time, device_id, monitored_value, cleaned_value"
 
+    @staticmethod
+    async def get_warmup_values(
+        conn: AsyncConnection,
+        device_ids: list[str],
+        before: datetime,
+        per_device_limit: int,
+    ) -> list[dict]:
+        """Return the latest raw values before a replay starts for detector warmup."""
+        async with conn.cursor() as cur:
+            await cur.execute(
+                "SELECT d.device_id,h.monitored_value FROM unnest(%s::text[]) d(device_id) "
+                "CROSS JOIN LATERAL (SELECT monitored_value,time FROM scada.measurements "
+                "WHERE device_id=d.device_id AND time<%s ORDER BY time DESC LIMIT %s) h "
+                "ORDER BY d.device_id,h.time",
+                (device_ids, before, per_device_limit),
+            )
+            return [dict(row) for row in await cur.fetchall()]
+
+    @staticmethod
+    async def get_raw_page(
+        conn: AsyncConnection, device_ids: list[str], start: datetime,
+        end: datetime, through: datetime, limit: int,
+        after: tuple[datetime, str] | None = None, *, frame: bool = False,
+    ) -> list[dict]:
+        """Read raw only, with a stable composite key and a bounded frame/page."""
+        predicate = "device_id=ANY(%s) AND time>=%s AND time<%s AND time<=%s"
+        params: tuple = (device_ids, start, end, through)
+        if after is not None:
+            predicate += " AND (time,device_id)>(%s,%s)"
+            params += after
+        if frame:
+            statement = (
+                "WITH next_time AS (SELECT min(time) AS time FROM scada.measurements WHERE "
+                + predicate + ") SELECT m.time,m.device_id,m.monitored_value,"
+                "md5(COALESCE(m.monitored_value::text,'NULL')) AS source_hash "
+                "FROM scada.measurements m WHERE m.device_id=ANY(%s) "
+                "AND m.time=(SELECT time FROM next_time) ORDER BY m.time,m.device_id LIMIT %s"
+            )
+            params += (device_ids, limit)
+        else:
+            statement = (
+                "SELECT time,device_id,monitored_value,"
+                "md5(COALESCE(monitored_value::text,'NULL')) AS source_hash "
+                "FROM scada.measurements WHERE " + predicate
+                + " ORDER BY time,device_id LIMIT %s"
+            )
+            params += (limit,)
+        async with conn.cursor() as cur:
+            await cur.execute(statement, params)
+            return [dict(row) for row in await cur.fetchall()]
+
+    @staticmethod
+    async def apply_replay_cleaning(conn: AsyncConnection, rows: list[dict]) -> None:
+        """Guard every raw version; update corrected values without inserting raw."""
+        if not rows:
+            return
+        async with conn.transaction():
+            async with conn.cursor() as cur:
+                await cur.execute(
+                    "SELECT m.time,m.device_id,md5(COALESCE(m.monitored_value::text,'NULL')) AS source_hash "
+                    "FROM scada.measurements m JOIN unnest(%s::timestamptz[],%s::text[]) "
+                    "b(time,device_id) USING(time,device_id) FOR UPDATE OF m",
+                    ([r["time"] for r in rows], [r["device_id"] for r in rows]),
+                )
+                existing = {(r["time"].isoformat(), r["device_id"]): r["source_hash"]
+                            for r in await cur.fetchall()}
+                if len(existing) != len(rows) or any(
+                    existing.get((datetime.fromisoformat(r["time"]).isoformat(), r["device_id"]))
+                    != r["source_hash"] for r in rows
+                ):
+                    raise ValueError("SOURCE_CHANGED: SCADA 原始值在处理期间发生变化")
+                await cur.execute(
+                    "UPDATE scada.measurements m SET cleaned_value=b.value "
+                    "FROM unnest(%s::timestamptz[],%s::text[],%s::double precision[]) "
+                    "b(time,device_id,value) WHERE m.time=b.time AND m.device_id=b.device_id "
+                    "AND m.cleaned_value IS DISTINCT FROM b.value",
+                    ([r["time"] for r in rows], [r["device_id"] for r in rows],
+                     [r["cleaned_value"] for r in rows]),
+                )
+
     @staticmethod
     async def insert_scada_batch(conn: AsyncConnection, data: List[dict]):
         if not data: