summary refs log tree commit diff
path: root/synapse/storage/databases/main
diff options
context:
space:
mode:
authorHillery Shay <shaysquared@gmail.com>2021-09-22 08:25:26 -0700
committerGitHub <noreply@github.com>2021-09-22 08:25:26 -0700
commitf78b68a96b1f179043b38b4109e09fa0a315643d (patch)
tree385b7aaa1987b730e15eb396dedaa71d4ac0557c /synapse/storage/databases/main
parentFix invalidating OTK count cache after claim (#10875) (diff)
downloadsynapse-f78b68a96b1f179043b38b4109e09fa0a315643d.tar.xz
Treat "\u0000" as "\u0020" for the purposes of message search (message indexing) (#10820)
* add test to check if null code points are being inserted

* add logic to detect and replace null code points before insertion into db

* lints

* add license to test

* change approach to null substitution

* add type hint for SearchEntry

* Add changelog entry

Signed-off-by: H.Shay <shaysquared@gmail.com>

* updated changelog

* update chanelog message

* remove duplicate changelog

* Update synapse/storage/databases/main/events.py remove extra space

Co-authored-by: Patrick Cloke <clokep@users.noreply.github.com>

* rename and move test file, update tests, delete old test file

* fix typo in comments

* update _find_highlights_in_postgres to replace null byte with space

* replace null byte in sqlite search insertion

* beef up and reorganize test for this pr

* update changelog

* add type hints and update docstring

* check db engine directly vs using env variable

* refactor tests to be less repetetive

* move rplace logic into seperate function

* requested changes

* Fix typo.

* Update synapse/storage/databases/main/search.py

Co-authored-by: reivilibre <olivier@librepush.net>

* Update changelog.d/10820.misc

Co-authored-by: Aaron Raimist <aaron@raim.ist>

Co-authored-by: Patrick Cloke <clokep@users.noreply.github.com>
Co-authored-by: reivilibre <olivier@librepush.net>
Co-authored-by: Aaron Raimist <aaron@raim.ist>
Diffstat (limited to 'synapse/storage/databases/main')
-rw-r--r--synapse/storage/databases/main/search.py34
1 files changed, 25 insertions, 9 deletions
diff --git a/synapse/storage/databases/main/search.py b/synapse/storage/databases/main/search.py
index 6480d5a9f5..2a1e99e17a 100644
--- a/synapse/storage/databases/main/search.py
+++ b/synapse/storage/databases/main/search.py
@@ -15,12 +15,12 @@
 import logging
 import re
 from collections import namedtuple
-from typing import Collection, List, Optional, Set
+from typing import Collection, Iterable, List, Optional, Set
 
 from synapse.api.errors import SynapseError
 from synapse.events import EventBase
 from synapse.storage._base import SQLBaseStore, db_to_json, make_in_list_sql_clause
-from synapse.storage.database import DatabasePool
+from synapse.storage.database import DatabasePool, LoggingTransaction
 from synapse.storage.databases.main.events_worker import EventRedactBehaviour
 from synapse.storage.engines import PostgresEngine, Sqlite3Engine
 
@@ -32,14 +32,24 @@ SearchEntry = namedtuple(
 )
 
 
+def _clean_value_for_search(value: str) -> str:
+    """
+    Replaces any null code points in the string with spaces as
+    Postgres and SQLite do not like the insertion of strings with
+    null code points into the full-text search tables.
+    """
+    return value.replace("\u0000", " ")
+
+
 class SearchWorkerStore(SQLBaseStore):
-    def store_search_entries_txn(self, txn, entries):
+    def store_search_entries_txn(
+        self, txn: LoggingTransaction, entries: Iterable[SearchEntry]
+    ) -> None:
         """Add entries to the search table
 
         Args:
-            txn (cursor):
-            entries (iterable[SearchEntry]):
-                entries to be added to the table
+            txn:
+            entries: entries to be added to the table
         """
         if not self.hs.config.enable_search:
             return
@@ -55,7 +65,7 @@ class SearchWorkerStore(SQLBaseStore):
                     entry.event_id,
                     entry.room_id,
                     entry.key,
-                    entry.value,
+                    _clean_value_for_search(entry.value),
                     entry.stream_ordering,
                     entry.origin_server_ts,
                 )
@@ -70,11 +80,16 @@ class SearchWorkerStore(SQLBaseStore):
                 " VALUES (?,?,?,?)"
             )
             args = (
-                (entry.event_id, entry.room_id, entry.key, entry.value)
+                (
+                    entry.event_id,
+                    entry.room_id,
+                    entry.key,
+                    _clean_value_for_search(entry.value),
+                )
                 for entry in entries
             )
-
             txn.execute_batch(sql, args)
+
         else:
             # This should be unreachable.
             raise Exception("Unrecognized database engine")
@@ -646,6 +661,7 @@ class SearchStore(SearchBackgroundUpdateStore):
                 for key in ("body", "name", "topic"):
                     v = event.content.get(key, None)
                     if v:
+                        v = _clean_value_for_search(v)
                         values.append(v)
 
                 if not values: