Fix non-strings in the `event_search` table (#12037)

Don't attempt to add non-string `value`s to `event_search` and add a
background update to clear out bad rows from `event_search` when
using sqlite.

Signed-off-by: Sean Quah <seanq@element.io>

1 files changed, 26 insertions, 0 deletions

diff --git a/synapse/storage/databases/main/search.py b/synapse/storage/databases/main/search.py

index acea300ed3..e23b119072 100644
--- a/synapse/storage/databases/main/search.py
+++ b/synapse/storage/databases/main/search.py
@@ -115,6 +115,7 @@ class SearchBackgroundUpdateStore(SearchWorkerStore):
     EVENT_SEARCH_ORDER_UPDATE_NAME = "event_search_order"
     EVENT_SEARCH_USE_GIST_POSTGRES_NAME = "event_search_postgres_gist"
     EVENT_SEARCH_USE_GIN_POSTGRES_NAME = "event_search_postgres_gin"
+    EVENT_SEARCH_DELETE_NON_STRINGS = "event_search_sqlite_delete_non_strings"
 
     def __init__(
         self,
@@ -147,6 +148,10 @@ class SearchBackgroundUpdateStore(SearchWorkerStore):
             self.EVENT_SEARCH_USE_GIN_POSTGRES_NAME, self._background_reindex_gin_search
         )
 
+        self.db_pool.updates.register_background_update_handler(
+            self.EVENT_SEARCH_DELETE_NON_STRINGS, self._background_delete_non_strings
+        )
+
     async def _background_reindex_search(self, progress, batch_size):
         # we work through the events table from highest stream id to lowest
         target_min_stream_id = progress["target_min_stream_id_inclusive"]
@@ -372,6 +377,27 @@ class SearchBackgroundUpdateStore(SearchWorkerStore):
 
         return num_rows
 
+    async def _background_delete_non_strings(
+        self, progress: JsonDict, batch_size: int
+    ) -> int:
+        """Deletes rows with non-string `value`s from `event_search` if using sqlite.
+
+        Prior to Synapse 1.44.0, malformed events received over federation could cause integers
+        to be inserted into the `event_search` table when using sqlite.
+        """
+
+        def delete_non_strings_txn(txn: LoggingTransaction) -> None:
+            txn.execute("DELETE FROM event_search WHERE typeof(value) != 'text'")
+
+        await self.db_pool.runInteraction(
+            self.EVENT_SEARCH_DELETE_NON_STRINGS, delete_non_strings_txn
+        )
+
+        await self.db_pool.updates._end_background_update(
+            self.EVENT_SEARCH_DELETE_NON_STRINGS
+        )
+        return 1
+
 
 class SearchStore(SearchBackgroundUpdateStore):
     def __init__(