minstrel/internal/db/queries/duplicates.sql

-- name: StartDuplicateSweep :one
INSERT INTO duplicate_sweeps DEFAULT VALUES RETURNING id, started_at;

-- name: FinishDuplicateSweep :exec
UPDATE duplicate_sweeps
   SET finished_at       = now(),
       candidates        = sqlc.arg(candidates),
       groups_found      = sqlc.arg(groups_found),
       oversize_clusters = sqlc.arg(oversize_clusters),
       error_message     = NULLIF(sqlc.arg(error_message)::text, '')
 WHERE id = sqlc.arg(id);

-- name: GetInFlightDuplicateSweep :one
-- The guard against two sweeps at once: "in flight" is finished_at IS NULL.
SELECT id, started_at
  FROM duplicate_sweeps
 WHERE finished_at IS NULL
 ORDER BY started_at DESC
 LIMIT 1;

-- name: GetLatestDuplicateSweep :one
SELECT id, started_at, finished_at, candidates, groups_found, oversize_clusters, error_message
  FROM duplicate_sweeps
 ORDER BY started_at DESC
 LIMIT 1;

-- name: GetLatestFingerprintComputedAt :one
-- Whether a sweep has anything new to look at: fingerprints written since the
-- last sweep started.
SELECT max(computed_at)::timestamptz AS latest FROM track_fingerprints;

-- name: ListExactDuplicateHashes :many
-- The exact tier, library-wide in one pass: identical encoded audio shared by
-- more than one present track.
SELECT f.audio_stream_sha256,
       array_agg(t.id ORDER BY t.id)::uuid[] AS track_ids
  FROM track_fingerprints f
  JOIN tracks t ON t.id = f.track_id
 WHERE t.missing_since IS NULL
   AND f.fingerprint_version >= sqlc.arg(current_version)
   AND f.audio_stream_sha256 IS NOT NULL
 GROUP BY f.audio_stream_sha256
HAVING count(*) > 1;

-- name: ListDuplicateCandidates :many
-- The acoustic tier's input, one page at a time in (duration_ms, id) order so the
-- sweep holds only a sliding window of durations. Tracks without a chromaprint
-- cannot be compared acoustically and are left out; any exact duplicates among
-- them come from ListExactDuplicateHashes.
SELECT t.id, t.duration_ms, f.audio_stream_sha256, f.chromaprint
  FROM tracks t
  JOIN track_fingerprints f ON f.track_id = t.id
 WHERE t.missing_since IS NULL
   AND f.fingerprint_version >= sqlc.arg(current_version)
   AND f.chromaprint IS NOT NULL
   -- Only chromaprints taken at the current length: prints at two lengths are not
   -- comparable, and after a length change the backfill is still re-deriving the
   -- rest (#3913).
   AND f.chromaprint_length_sec = sqlc.arg(chromaprint_length_sec)
   AND (t.duration_ms, t.id) > (sqlc.arg(after_duration_ms)::integer, sqlc.arg(after_id)::uuid)
 ORDER BY t.duration_ms, t.id
 LIMIT sqlc.arg(page_limit);

-- name: ListDismissedDuplicateMemberSets :many
-- What the operator has already said are not duplicates. A new proposal whose
-- every member sat together in one of these is not proposed again.
SELECT g.id, array_agg(m.track_id ORDER BY m.track_id)::uuid[] AS track_ids
  FROM duplicate_groups g
  JOIN duplicate_group_members m ON m.group_id = g.id
 WHERE g.status = 'dismissed'
 GROUP BY g.id;

-- name: UpsertDuplicateGroup :one
-- Proposes a group, or refreshes one already pending. A group already dismissed
-- or merged is left exactly as it is: the WHERE on the update makes the conflict
-- a no-op, and the caller sees no row.
INSERT INTO duplicate_groups (member_key, tier, worst_bit_error_rate, last_seen_sweep_id)
VALUES (sqlc.arg(member_key), sqlc.arg(tier), sqlc.narg(worst_bit_error_rate), sqlc.arg(sweep_id))
ON CONFLICT (member_key) DO UPDATE
   SET tier                 = EXCLUDED.tier,
       worst_bit_error_rate = EXCLUDED.worst_bit_error_rate,
       last_seen_sweep_id   = EXCLUDED.last_seen_sweep_id
 WHERE duplicate_groups.status = 'pending'
RETURNING id;

-- name: AddDuplicateGroupMember :exec
INSERT INTO duplicate_group_members (group_id, track_id)
VALUES (sqlc.arg(group_id), sqlc.arg(track_id))
ON CONFLICT DO NOTHING;

-- name: DeleteStalePendingDuplicateGroups :execrows
-- A pending proposal this sweep did not find again no longer describes the
-- library: a member was re-fingerprinted, merged away or went missing. Dismissed
-- groups are kept regardless — they are the memory of a decision.
--
-- Only proposals last confirmed by an EARLIER sweep go. Should two sweeps ever
-- overlap (a manual trigger racing the worker), neither may delete what the other
-- has just found.
DELETE FROM duplicate_groups g
 WHERE g.status = 'pending'
   AND g.last_seen_sweep_id IS DISTINCT FROM sqlc.arg(sweep_id)
   AND (g.last_seen_sweep_id IS NULL
        OR (SELECT s.started_at FROM duplicate_sweeps s WHERE s.id = g.last_seen_sweep_id)
           < (SELECT s.started_at FROM duplicate_sweeps s WHERE s.id = sqlc.arg(sweep_id)));

-- name: CountPendingDuplicateGroups :one
-- Proposals awaiting review. A group left with one member — its other tracks
-- deleted since the sweep — is no proposal at all and is not counted; the next
-- sweep retires it.
SELECT count(*)::bigint
  FROM duplicate_groups g
 WHERE g.status = 'pending'
   AND (SELECT count(*) FROM duplicate_group_members m WHERE m.group_id = g.id) >= 2;

-- name: CountPendingDuplicateGroupsInView :one
-- CountPendingDuplicateGroups narrowed to one view of the report (M498):
--   review         what the operator still has to decide: every class but
--                  cross_release, and groups not yet classified
--   cross_release  the same song on different releases, which is kept, not merged
SELECT count(*)::bigint
  FROM duplicate_groups g
 WHERE g.status = 'pending'
   AND (SELECT count(*) FROM duplicate_group_members m WHERE m.group_id = g.id) >= 2
   AND CASE sqlc.arg(view)::text
         WHEN 'cross_release' THEN g.class = 'cross_release'
         ELSE g.class IS DISTINCT FROM 'cross_release'
       END;

-- name: ListPendingDuplicateGroupMembers :many
-- One page of proposals in one view (see CountPendingDuplicateGroupsInView),
-- newest first, flattened to one row per member so the handler folds them
-- without a query per group. What each copy carries — likes and plays from
-- every user — is here because it is what the operator weighs when deciding
-- which copy to keep.
WITH page AS (
    SELECT g.id, g.tier, g.worst_bit_error_rate, g.detected_at, g.class, g.resolve_note
      FROM duplicate_groups g
     WHERE g.status = 'pending'
       AND (SELECT count(*) FROM duplicate_group_members m WHERE m.group_id = g.id) >= 2
       AND CASE sqlc.arg(view)::text
             WHEN 'cross_release' THEN g.class = 'cross_release'
             ELSE g.class IS DISTINCT FROM 'cross_release'
           END
     ORDER BY g.detected_at DESC, g.id
     LIMIT sqlc.arg(page_limit) OFFSET sqlc.arg(page_offset)
)
SELECT p.id                  AS group_id,
       p.tier,
       p.worst_bit_error_rate,
       p.detected_at,
       p.class,
       p.resolve_note,
       t.disc_number,
       t.track_number,
       (t.mbid IS NOT NULL)::boolean AS has_mbid,
       EXISTS (SELECT 1 FROM tracks o
                WHERE o.album_id = t.album_id AND o.id <> t.id AND o.missing_since IS NULL
                  AND t.track_number IS NOT NULL
                  AND o.disc_number IS NOT DISTINCT FROM t.disc_number
                  AND o.track_number = t.track_number)::boolean AS position_clash,
       t.id                  AS track_id,
       t.title,
       artists.id            AS artist_id,
       artists.name          AS artist_name,
       albums.id             AS album_id,
       albums.title          AS album_title,
       t.file_path,
       t.file_format,
       t.file_size,
       t.duration_ms,
       t.added_at,
       (SELECT count(*) FROM general_likes l WHERE l.track_id = t.id)::bigint AS like_count,
       (SELECT count(*) FROM play_events e WHERE e.track_id = t.id)::bigint   AS play_count
  FROM page p
  JOIN duplicate_group_members m ON m.group_id = p.id
  JOIN tracks t  ON t.id = m.track_id
  JOIN albums    ON albums.id  = t.album_id
  JOIN artists   ON artists.id = t.artist_id
 ORDER BY p.detected_at DESC, p.id, t.id;

-- name: DismissDuplicateGroup :execrows
-- "These are not duplicates." Only a pending group can be dismissed; zero rows
-- means it was already resolved or no longer exists.
UPDATE duplicate_groups
   SET status = 'dismissed', resolved_at = now()
 WHERE id = sqlc.arg(id) AND status = 'pending';

-- name: ListDuplicateGroupsForResolve :many
-- Every pending group's present copies, for the resolver (M498 #5435): what it
-- needs to classify the group and to choose the copy to keep. One row per copy,
-- grouped by group. position_clash is true when another present track on the
-- same album claims the same disc and track number: tags that do not fit the
-- album, which the survivor rule weighs against a copy. source_verdict says
-- whether the copy is a video rip ('suspect') or one the operator kept ('fine').
-- prior_class is the class the last pass gave the group, NULL for a group no
-- pass has seen. release_group_mbid is the album's MusicBrainz group, from its
-- tags or the library listing's match; '' when neither names one.
SELECT g.id                  AS group_id,
       g.tier,
       g.class               AS prior_class,
       t.id                  AS track_id,
       t.album_id,
       t.title,
       t.source_verdict,
       artists.name          AS artist_name,
       t.file_path,
       t.file_format,
       t.file_size,
       t.duration_ms,
       t.added_at,
       t.disc_number,
       t.track_number,
       (t.mbid IS NOT NULL)::boolean AS has_mbid,
       EXISTS (SELECT 1 FROM tracks o
                WHERE o.album_id = t.album_id AND o.id <> t.id AND o.missing_since IS NULL
                  AND t.track_number IS NOT NULL
                  AND o.disc_number IS NOT DISTINCT FROM t.disc_number
                  AND o.track_number = t.track_number)::boolean AS position_clash,
       COALESCE(NULLIF(al.release_group_mbid, ''), lam.release_group_mbid, '')::text AS release_group_mbid
  FROM duplicate_groups g
  JOIN duplicate_group_members m ON m.group_id = g.id
  JOIN tracks t   ON t.id = m.track_id
  JOIN artists    ON artists.id = t.artist_id
  JOIN albums al  ON al.id = t.album_id
  LEFT JOIN library_album_matches lam ON lam.album_id = t.album_id AND lam.outcome = 'listed'
 WHERE g.status = 'pending'
   AND t.missing_since IS NULL
 ORDER BY g.id, t.id;

-- name: SetDuplicateGroupClasses :exec
-- The resolver's verdicts, written in one statement. Only rows whose class or
-- note actually changed are touched, so an hourly pass over thousands of
-- unchanged groups writes nothing. An empty note clears it.
UPDATE duplicate_groups g
   SET class = v.class, resolve_note = NULLIF(v.note, '')
  FROM (SELECT unnest(sqlc.arg(group_ids)::uuid[]) AS id,
               unnest(sqlc.arg(classes)::text[])   AS class,
               unnest(sqlc.arg(notes)::text[])     AS note) v
 WHERE g.id = v.id
   AND g.status = 'pending'
   AND (g.class IS DISTINCT FROM v.class OR g.resolve_note IS DISTINCT FROM NULLIF(v.note, ''));

-- name: SettleDuplicateGroupAutomatically :execrows
-- The resolver closing a group itself: 'dismissed' for versions that are not
-- duplicates, 'merged' when it removed the wrong copies. Only a pending group.
UPDATE duplicate_groups
   SET status = sqlc.arg(status), resolved_at = now(), resolved_automatically = true
 WHERE id = sqlc.arg(id) AND status = 'pending';

-- name: MarkDuplicateGroupResolvedAutomatically :exec
UPDATE duplicate_groups SET resolved_automatically = true WHERE id = sqlc.arg(id);