minstrel/internal/db/migrations/0069_acoustid_lookup.up.sql

-- 0069_acoustid_lookup.up.sql — recording MBIDs looked up through AcoustID
-- for tracks whose tags carry none.
--
-- A track with no recording MBID is invisible to the ListenBrainz similarity
-- arm in both directions, so this fills the ids the tags leave empty.

-- Where tracks.mbid came from. The file's own tag always outranks a lookup:
-- the scan's upsert keeps a looked-up id while the tag carries
-- none, and replaces it the moment the tag carries one.
ALTER TABLE tracks ADD COLUMN mbid_source text;
-- Every id stored so far was read from a tag (the scan or the tag backfill),
-- or inherited from a merged duplicate's tag.
UPDATE tracks SET mbid_source = 'tag' WHERE mbid IS NOT NULL;
ALTER TABLE tracks
    ADD CONSTRAINT tracks_mbid_source_check CHECK (mbid_source IN ('tag', 'acoustid')),
    ADD CONSTRAINT tracks_mbid_source_pair CHECK ((mbid IS NULL) = (mbid_source IS NULL));

-- What happened the last time a track was looked up. A table of its own, as
-- track_loudness is (0065): tracks is read with SELECT * on the hot path.
--
-- What a row means, which the lookup worker depends on:
--   no row       never looked up, or the file changed since (the scan deletes
--                the row): look it up
--   matched      one recording cleared the score threshold, or one was left
--                after disambiguating by title and length; recording_mbid is it
--   ambiguous    several recordings cleared it and nothing told them apart.
--                Nothing is written: a wrong MBID would feed similarity the
--                wrong neighbours, which is worse than none
--   no_match     AcoustID linked nothing at or above the threshold
--   failed       fpcalc rejected the file, or AcoustID rejected its print
-- Every state is settled until the file changes. A failure that says nothing
-- about the file (AcoustID unreachable, a timeout, a cancelled pass) writes no
-- row, so the worker tries again.
CREATE TABLE track_acoustid_lookups (
    track_id       uuid        PRIMARY KEY REFERENCES tracks (id) ON DELETE CASCADE,
    state          text        NOT NULL,
    -- The best score any linked recording had; NULL when none was linked.
    best_score     real,
    -- How many distinct recordings were linked, at any score.
    candidates     integer     NOT NULL DEFAULT 0,
    recording_mbid text,
    -- Why a lookup failed, for the admin list.
    detail         text,
    looked_up_at   timestamptz NOT NULL DEFAULT now(),

    CONSTRAINT track_acoustid_lookups_state_check
        CHECK (state IN ('matched', 'ambiguous', 'no_match', 'failed')),
    CONSTRAINT track_acoustid_lookups_matched_has_mbid
        CHECK ((state = 'matched') = (recording_mbid IS NOT NULL))
);
CREATE INDEX track_acoustid_lookups_state ON track_acoustid_lookups (state);

-- AcoustID's knobs, in admin Settings. Singleton in the style of
-- loudness_settings (0065).
CREATE TABLE acoustid_settings (
    id         boolean     PRIMARY KEY DEFAULT true,
    -- Off by default: AcoustID needs a key an admin registers, and the lookup
    -- sends fingerprints to a third party.
    enabled    boolean     NOT NULL DEFAULT false,
    api_key    text,
    -- The score a recording needs before it is considered at all. AcoustID
    -- scores a true match close to 1; 0.85 leaves room for a lossy encode.
    min_score  real        NOT NULL DEFAULT 0.85,
    updated_at timestamptz NOT NULL DEFAULT now(),

    CONSTRAINT acoustid_settings_singleton CHECK (id = true),
    CONSTRAINT acoustid_settings_min_score_range CHECK (min_score >= 0.5 AND min_score <= 1)
);
INSERT INTO acoustid_settings (id) VALUES (true) ON CONFLICT (id) DO NOTHING;