Refactor getting replication updates from database. (#7636)

The aim here is to make it easier to reason about when streams are limited and when they're not, by moving the logic into the database functions themselves. This should mean we can kill of `db_query_to_update_function` function.

synapse/storage/data_stores/main/receipts.py

@@ -16,6 +16,7 @@
 
 import abc
 import logging
+from typing import List, Tuple
 
 from canonicaljson import json
 
@@ -267,26 +268,79 @@ class ReceiptsWorkerStore(SQLBaseStore):
         }
         return results
 
-    def get_all_updated_receipts(self, last_id, current_id, limit=None):
+    def get_users_sent_receipts_between(self, last_id: int, current_id: int):
+        """Get all users who sent receipts between `last_id` exclusive and
+        `current_id` inclusive.
+
+        Returns:
+            Deferred[List[str]]
+        """
+
         if last_id == current_id:
             return defer.succeed([])
 
-        def get_all_updated_receipts_txn(txn):
-            sql = (
-                "SELECT stream_id, room_id, receipt_type, user_id, event_id, data"
-                " FROM receipts_linearized"
-                " WHERE ? < stream_id AND stream_id <= ?"
-                " ORDER BY stream_id ASC"
-            )
-            args = [last_id, current_id]
-            if limit is not None:
-                sql += " LIMIT ?"
-                args.append(limit)
-            txn.execute(sql, args)
+        def _get_users_sent_receipts_between_txn(txn):
+            sql = """
+                SELECT DISTINCT user_id FROM receipts_linearized
+                WHERE ? < stream_id AND stream_id <= ?
+            """
+            txn.execute(sql, (last_id, current_id))
 
-            return [r[0:5] + (json.loads(r[5]),) for r in txn]
+            return [r[0] for r in txn]
 
         return self.db.runInteraction(
+            "get_users_sent_receipts_between", _get_users_sent_receipts_between_txn
+        )
+
+    async def get_all_updated_receipts(
+        self, instance_name: str, last_id: int, current_id: int, limit: int
+    ) -> Tuple[List[Tuple[int, list]], int, bool]:
+        """Get updates for receipts replication stream.
+
+        Args:
+            instance_name: The writer we want to fetch updates from. Unused
+                here since there is only ever one writer.
+            last_id: The token to fetch updates from. Exclusive.
+            current_id: The token to fetch updates up to. Inclusive.
+            limit: The requested limit for the number of rows to return. The
+                function may return more or fewer rows.
+
+        Returns:
+            A tuple consisting of: the updates, a token to use to fetch
+            subsequent updates, and whether we returned fewer rows than exists
+            between the requested tokens due to the limit.
+
+            The token returned can be used in a subsequent call to this
+            function to get further updatees.
+
+            The updates are a list of 2-tuples of stream ID and the row data
+        """
+
+        if last_id == current_id:
+            return [], current_id, False
+
+        def get_all_updated_receipts_txn(txn):
+            sql = """
+                SELECT stream_id, room_id, receipt_type, user_id, event_id, data
+                FROM receipts_linearized
+                WHERE ? < stream_id AND stream_id <= ?
+                ORDER BY stream_id ASC
+                LIMIT ?
+            """
+            txn.execute(sql, (last_id, current_id, limit))
+
+            updates = [(r[0], r[1:5] + (json.loads(r[5]),)) for r in txn]
+
+            limited = False
+            upper_bound = current_id
+
+            if len(updates) == limit:
+                limited = True
+                upper_bound = updates[-1][0]
+
+            return updates, upper_bound, limited
+
+        return await self.db.runInteraction(
             "get_all_updated_receipts", get_all_updated_receipts_txn
         )