summary refs log tree commit diff
path: root/synapse/storage/schema
diff options
context:
space:
mode:
authorJames Salter <iteration@gmail.com>2022-10-25 19:05:22 +0100
committerGitHub <noreply@github.com>2022-10-25 14:05:22 -0400
commitd902181de98399d90c46c4e4e2cf631064757941 (patch)
treefedb176982c540a8187b3222efec08bb06dbc7ab /synapse/storage/schema
parentMerge branch 'release-v1.70' into develop (diff)
downloadsynapse-d902181de98399d90c46c4e4e2cf631064757941.tar.xz
Unified search query syntax using the full-text search capabilities of the underlying DB. (#11635)
Support a unified search query syntax which leverages more of the full-text
search of each database supported by Synapse.

Supports, with the same syntax across Postgresql 11+ and Sqlite:

- quoted "search terms"
- `AND`, `OR`, `-` (negation) operators
- Matching words based on their stem, e.g. searches for "dog" matches
  documents containing "dogs". 

This is achieved by 

- If on postgresql 11+, pass the user input to `websearch_to_tsquery`
- If on sqlite, manually parse the query and transform it into the sqlite-specific
  query syntax.

Note that postgresql 10, which is close to end-of-life, falls back to using
`phraseto_tsquery`, which only supports a subset of the features.

Multiple terms separated by a space are implicitly ANDed.

Note that:

1. There is no escaping of full-text syntax that might be supported by the database;
  e.g. `NOT`, `NEAR`, `*` in sqlite. This runs the risk that people might discover this
  as accidental functionality and depend on something we don't guarantee.
2. English text is assumed for stemming. To support other languages, either the target
  language needs to be known at the time of indexing the message (via room metadata,
  or otherwise), or a separate index for each language supported could be created.

Sqlite docs: https://www.sqlite.org/fts3.html#full_text_index_queries
Postgres docs: https://www.postgresql.org/docs/11/textsearch-controls.html
Diffstat (limited to 'synapse/storage/schema')
-rw-r--r--synapse/storage/schema/main/delta/73/10_update_sqlite_fts4_tokenizer.py62
1 files changed, 62 insertions, 0 deletions
diff --git a/synapse/storage/schema/main/delta/73/10_update_sqlite_fts4_tokenizer.py b/synapse/storage/schema/main/delta/73/10_update_sqlite_fts4_tokenizer.py
new file mode 100644
index 0000000000..3de0a709eb
--- /dev/null
+++ b/synapse/storage/schema/main/delta/73/10_update_sqlite_fts4_tokenizer.py
@@ -0,0 +1,62 @@
+# Copyright 2022 The Matrix.org Foundation C.I.C.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import json
+
+from synapse.storage.engines import BaseDatabaseEngine, Sqlite3Engine
+from synapse.storage.types import Cursor
+
+
+def run_create(cur: Cursor, database_engine: BaseDatabaseEngine) -> None:
+    """
+    Upgrade the event_search table to use the porter tokenizer if it isn't already
+
+    Applies only for sqlite.
+    """
+    if not isinstance(database_engine, Sqlite3Engine):
+        return
+
+    # Rebuild the table event_search table with tokenize=porter configured.
+    cur.execute("DROP TABLE event_search")
+    cur.execute(
+        """
+        CREATE VIRTUAL TABLE event_search
+        USING fts4 (tokenize=porter, event_id, room_id, sender, key, value )
+        """
+    )
+
+    # Re-run the background job to re-populate the event_search table.
+    cur.execute("SELECT MIN(stream_ordering) FROM events")
+    row = cur.fetchone()
+    min_stream_id = row[0]
+
+    # If there are not any events, nothing to do.
+    if min_stream_id is None:
+        return
+
+    cur.execute("SELECT MAX(stream_ordering) FROM events")
+    row = cur.fetchone()
+    max_stream_id = row[0]
+
+    progress = {
+        "target_min_stream_id_inclusive": min_stream_id,
+        "max_stream_id_exclusive": max_stream_id + 1,
+    }
+    progress_json = json.dumps(progress)
+
+    sql = """
+    INSERT into background_updates (ordering, update_name, progress_json)
+    VALUES (?, ?, ?)
+    """
+
+    cur.execute(sql, (7310, "event_search", progress_json))