Files
buzz/schema/tables/public/events.sql

72 lines
4.0 KiB
SQL

-- ── Events (partitioned by month on created_at) ──────────────────────────────
-- Conformance: "Channel-less global events and DMs". `community_id` leads the
-- PK and every hot-path index. Partition stays BY RANGE (created_at) — the
-- monthly partition manager is unchanged (Max's call, plan §5/Lane0 contract).
-- Cross-community dedup: same signed event may exist in two communities;
-- (community_id, created_at, id) dedupes within one, allows across.
CREATE TABLE events (
community_id UUID NOT NULL REFERENCES communities(id),
id BYTEA NOT NULL,
pubkey BYTEA NOT NULL,
created_at TIMESTAMPTZ NOT NULL,
kind INT NOT NULL,
tags JSONB NOT NULL,
content TEXT NOT NULL,
-- Full-text search vector (Typesense → Postgres FTS). Generated/STORED so
-- it is a single source of truth — no sidecar indexer to keep coherent
-- (Quinn option A, Lane-0 call). 'simple' config = no stemming/stopwords,
-- matching the existing substring-ish search semantics; the search lane can
-- revisit the config behind evidence. Tenant scoping is by the
-- community-leading btree filters BitmapAnd-ed with the GIN probe, so the
-- GIN index itself stays the minimal `GIN (search_tsv)` (Max's caveat:
-- avoid btree_gin unless EXPLAIN proves it buys something).
-- Privacy: encrypted/private routing wrappers and p-gated membership notices
-- must never be discoverable through NIP-50 full-text search. NULL tsvector
-- never matches `@@`.
-- Keep in sync with migrations (final state: 0001 + 0005 + 0014 + 0033).
search_tsv TSVECTOR GENERATED ALWAYS AS (
CASE WHEN kind IN (1059, 30179, 30300, 30350, 30622, 44100, 44101, 44200) THEN NULL::tsvector
ELSE to_tsvector('simple', content)
END
) STORED,
sig BYTEA NOT NULL,
received_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
channel_id UUID,
deleted_at TIMESTAMPTZ,
d_tag TEXT,
not_before BIGINT,
delivered_at BIGINT,
PRIMARY KEY (community_id, created_at, id)
) PARTITION BY RANGE (created_at);
-- Direct id lookup: the PK can't serve `WHERE id=$1` because created_at sits
-- between community_id and id. This index makes the scoped form
-- `WHERE community_id=$ AND id=$` index-served, not a partition scan.
CREATE INDEX idx_events_community_id ON events (community_id, id, created_at DESC);
-- Hot-path indexes, all community-leading.
CREATE INDEX idx_events_community_channel_created
ON events (community_id, channel_id, created_at DESC, id);
CREATE INDEX idx_events_community_pubkey_kind_created
ON events (community_id, pubkey, kind, created_at DESC, id);
CREATE INDEX idx_events_community_kind_created
ON events (community_id, kind, created_at DESC, id);
CREATE INDEX idx_events_community_deleted ON events (community_id, deleted_at);
-- Addressable (replaceable) and NIP-33 parameterized lookups.
CREATE INDEX idx_events_addressable
ON events (community_id, kind, pubkey, channel_id, deleted_at);
CREATE INDEX idx_events_parameterized
ON events (community_id, kind, pubkey, d_tag, created_at DESC, id)
WHERE d_tag IS NOT NULL AND deleted_at IS NULL;
CREATE INDEX idx_events_not_before ON events (community_id, not_before)
WHERE not_before IS NOT NULL AND deleted_at IS NULL AND delivered_at IS NULL;
-- Full-text search. Minimal GIN over the generated tsvector; community scoping
-- is supplied by the community-leading btree filters above (BitmapAnd), so this
-- stays a single-column GIN. The search lane confirms the final spelling with
-- EXPLAIN before its work lands (Quinn option A; Max's index-spelling caveat).
CREATE INDEX idx_events_search_tsv ON events USING GIN (search_tsv);
-- e-tag containment (`tags @> '[["e","<hex>"]]'`) for the aux closure and #e
-- reads. Mirrors migrations/0004; jsonb_path_ops supports exactly @>.
CREATE INDEX idx_events_tags_gin ON events USING GIN (tags jsonb_path_ops);