bugfix: always prefer unthreaded receipt when >1 exist (MSC4102) (#16927)

Co-authored-by: Andrew Morgan <1342360+anoadragon453@users.noreply.github.com>

1 files changed, 18 insertions, 3 deletions

diff --git a/synapse/storage/databases/main/receipts.py b/synapse/storage/databases/main/receipts.py
index 3c7708f5f3..8a426d2875 100644
--- a/synapse/storage/databases/main/receipts.py
+++ b/synapse/storage/databases/main/receipts.py
@@ -472,9 +472,24 @@ class ReceiptsWorkerStore(SQLBaseStore):
             event_entry = room_event["content"].setdefault(event_id, {})
             receipt_type_dict = event_entry.setdefault(receipt_type, {})
 
-            receipt_type_dict[user_id] = db_to_json(data)
-            if thread_id:
-                receipt_type_dict[user_id]["thread_id"] = thread_id
+            # MSC4102: always replace threaded receipts with unthreaded ones if there is a clash.
+            # Specifically:
+            # - if there is no existing receipt, great, set the data.
+            # - if there is an existing receipt, is it threaded (thread_id present)?
+            #    YES: replace if this receipt has no thread id. NO: do not replace.
+            # This means we will drop some receipts, but MSC4102 is designed to drop semantically
+            # meaningless receipts, so this is okay. Previously, we would drop meaningful data!
+            receipt_data = db_to_json(data)
+            if user_id in receipt_type_dict:  # existing receipt
+                # is the existing receipt threaded and we are currently processing an unthreaded one?
+                if "thread_id" in receipt_type_dict[user_id] and not thread_id:
+                    receipt_type_dict[
+                        user_id
+                    ] = receipt_data  # replace with unthreaded one
+            else:  # receipt does not exist, just set it
+                receipt_type_dict[user_id] = receipt_data
+                if thread_id:
+                    receipt_type_dict[user_id]["thread_id"] = thread_id
 
         results = {
             room_id: [results[room_id]] if room_id in results else []