Warp/server/internal/storage/postgres/migrations/0012_relations_search.sql

-- Phase 10: relations (threads, edits, reactions, references) and
-- full-text search.

-- content.m.relates_to of each event, written out so that "the children of
-- this event" is an index lookup. Both are '' for an event that relates to
-- nothing, and are cleared when the event is redacted: the redaction
-- algorithm strips the content they came from.
ALTER TABLE roomserver_events ADD COLUMN relates_to_id TEXT NOT NULL DEFAULT '';
ALTER TABLE roomserver_events ADD COLUMN rel_type TEXT NOT NULL DEFAULT '';

-- The events already stored. Only a relation with both fields a string
-- counts, which is the rule the roomserver applies to new events. The LIKE
-- keeps the cast to jsonb off the events that cannot have one.
UPDATE roomserver_events e SET
    relates_to_id = r.rel ->> 'event_id',
    rel_type      = r.rel ->> 'rel_type'
FROM (
    SELECT event_id, event_json::jsonb -> 'content' -> 'm.relates_to' AS rel
    FROM roomserver_events
    WHERE redacted_by = '' AND event_json LIKE '%m.relates_to%'
) r
WHERE e.event_id = r.event_id
  AND jsonb_typeof(r.rel -> 'event_id') = 'string'
  AND jsonb_typeof(r.rel -> 'rel_type') = 'string';

-- /relations, the bundled summaries and /threads all start from a parent
-- and read its children in stream order.
CREATE INDEX IF NOT EXISTS roomserver_events_relations_idx
    ON roomserver_events (room_id, relates_to_id, rel_type, stream_ordering);

-- The full-text index /search reads: one row per searchable event, keyed by
-- the event's stream ordering, which is unique across the server and is
-- what a redaction finds the row by. Outliers are not here: an event joins
-- the index when it joins a timeline.
--
-- The 'simple' configuration lower-cases and splits on word boundaries
-- without stemming for any one language, which is the right default for a
-- server whose rooms are in every language at once.
CREATE TABLE IF NOT EXISTS roomserver_event_search (
    stream_ordering BIGINT NOT NULL PRIMARY KEY,
    room_id         TEXT   NOT NULL,
    event_id        TEXT   NOT NULL,
    search_key      TEXT   NOT NULL,
    sender          TEXT   NOT NULL,
    event_type      TEXT   NOT NULL,
    body            TEXT   NOT NULL,
    vector          TSVECTOR GENERATED ALWAYS AS (to_tsvector('simple', body)) STORED
);

CREATE INDEX IF NOT EXISTS roomserver_event_search_vector_idx
    ON roomserver_event_search USING GIN (vector);
CREATE INDEX IF NOT EXISTS roomserver_event_search_room_idx
    ON roomserver_event_search (room_id, stream_ordering);

INSERT INTO roomserver_event_search (stream_ordering, room_id, event_id, search_key, sender, event_type, body)
SELECT stream_ordering, room_id, event_id, k.search_key, sender, event_type, k.body
FROM (
    SELECT stream_ordering, room_id, event_id, sender, event_type, event_json::jsonb -> 'content' AS content
    FROM roomserver_events
    WHERE event_type IN ('m.room.message', 'm.room.name', 'm.room.topic')
      AND NOT outlier AND redacted_by = ''
) e
CROSS JOIN LATERAL (
    SELECT CASE e.event_type
               WHEN 'm.room.message' THEN 'content.body'
               WHEN 'm.room.name'    THEN 'content.name'
               ELSE                       'content.topic'
           END AS search_key,
           CASE e.event_type
               WHEN 'm.room.message' THEN e.content ->> 'body'
               WHEN 'm.room.name'    THEN e.content ->> 'name'
               ELSE                       e.content ->> 'topic'
           END AS body
) k
WHERE k.body IS NOT NULL
  AND jsonb_typeof(e.content -> substr(k.search_key, 9)) = 'string'
ON CONFLICT (stream_ordering) DO NOTHING;