minstrel/internal/library/duplicate_resolve_test.go

package library

import (
	"context"
	"errors"
	"os"
	"path/filepath"
	"testing"

	"github.com/jackc/pgx/v5/pgtype"
	"github.com/jackc/pgx/v5/pgxpool"

	"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
	"git.fabledsword.com/bvandeusen/minstrel/internal/lidarr"
	syncpkg "git.fabledsword.com/bvandeusen/minstrel/internal/sync"
)

func TestLidarrPathKey(t *testing.T) {
	// Minstrel and Lidarr see the library under different mounts; the key is
	// what they agree on.
	a := LidarrPathKey("/music/Gorillaz/Humanz (2017)/Gorillaz - Humanz - 01 - Ascension.mp3")
	b := LidarrPathKey("/data/media/music/Gorillaz/Humanz (2017)/Gorillaz - Humanz - 01 - Ascension.mp3")
	if a != b || a != "Gorillaz/Humanz (2017)/Gorillaz - Humanz - 01 - Ascension.mp3" {
		t.Errorf("keys differ or are wrong: %q, %q", a, b)
	}
	if LidarrPathKey("/music/Gorillaz/Humanz (2017)/a.mp3") == LidarrPathKey("/music/Gorillaz/Demon Days (2005)/a.mp3") {
		t.Error("two albums' files share a key")
	}
}

func rt(titles ...string) []lidarr.ReleaseTrack {
	out := make([]lidarr.ReleaseTrack, len(titles))
	for i, title := range titles {
		out[i] = lidarr.ReleaseTrack{ID: i + 1, Title: title}
	}
	return out
}

func TestReleaseRepeats(t *testing.T) {
	if !releaseRepeats(rt("Ascension", "Strobelite", "Ascension")) {
		t.Error("the box set lists Ascension twice, but no repeat was found")
	}
	if releaseRepeats(rt("Charger", "Charger (demo)")) {
		t.Error("a demo was read as a repeat of the song")
	}
}

// The Humanz releases as Lidarr lists them (2026-10-09): the box set is
// monitored, and the 40-track digital release is the one that lists each song
// once and covers what is on disk.
func TestPickRelease(t *testing.T) {
	digital40 := lidarr.AlbumRelease{ID: 10149, Format: "Digital Media", TrackCount: 40}
	deluxe26 := lidarr.AlbumRelease{ID: 10150, Format: "CD", TrackCount: 26}
	standard20 := lidarr.AlbumRelease{ID: 10151, Format: "Digital Media", TrackCount: 20}

	got, ok := pickRelease([]releaseCandidate{
		{release: standard20, coverage: 20}, {release: deluxe26, coverage: 26}, {release: digital40, coverage: 34},
	}, 34)
	if !ok || got.ID != digital40.ID {
		t.Errorf("picked %+v (ok=%v), want the 40-track digital release", got, ok)
	}

	// Equal coverage: the plainer edition, then digital.
	cd := lidarr.AlbumRelease{ID: 1, Format: "CD", TrackCount: 26}
	web := lidarr.AlbumRelease{ID: 2, Format: "Digital Media", TrackCount: 26}
	if got, _ := pickRelease([]releaseCandidate{{release: cd, coverage: 26}, {release: web, coverage: 26}}, 26); got.ID != web.ID {
		t.Errorf("picked %+v, want the digital one of two equal releases", got)
	}

	// Never a release that keeps fewer of the songs on disk than the current one.
	if got, ok := pickRelease([]releaseCandidate{{release: deluxe26, coverage: 26}}, 34); ok {
		t.Errorf("picked %+v, which covers fewer songs on disk than the current release", got)
	}
}

// fakeLidarr is one Lidarr album with several releases. Switching the
// monitored release changes what ListAlbumTracks answers, as in Lidarr.
type fakeLidarr struct {
	unmapped      []string
	unmappedErr   error
	album         lidarr.LidarrAlbum
	releases      []lidarr.AlbumRelease
	releaseTracks map[int][]lidarr.ReleaseTrack
	setCalls      [][2]int
}

func (f *fakeLidarr) ListUnmappedTrackFiles(context.Context) ([]lidarr.TrackFile, error) {
	out := make([]lidarr.TrackFile, len(f.unmapped))
	for i, p := range f.unmapped {
		out[i] = lidarr.TrackFile{ID: i + 1, Path: p}
	}
	return out, f.unmappedErr
}

func (f *fakeLidarr) LookupAlbumByMBID(_ context.Context, mbid string) (lidarr.LidarrAlbum, error) {
	if f.album.ForeignAlbumID != mbid {
		return lidarr.LidarrAlbum{}, lidarr.ErrNotFound
	}
	return f.album, nil
}

func (f *fakeLidarr) ListAlbumTracks(context.Context, int) ([]lidarr.ReleaseTrack, error) {
	for _, r := range f.releases {
		if r.Monitored {
			return f.releaseTracks[r.ID], nil
		}
	}
	return nil, nil
}

func (f *fakeLidarr) GetAlbumReleases(context.Context, int) ([]lidarr.AlbumRelease, error) {
	return append([]lidarr.AlbumRelease(nil), f.releases...), nil
}

func (f *fakeLidarr) ListReleaseTracks(_ context.Context, releaseID int) ([]lidarr.ReleaseTrack, error) {
	return f.releaseTracks[releaseID], nil
}

func (f *fakeLidarr) SetMonitoredRelease(_ context.Context, albumID, releaseID int) error {
	f.setCalls = append(f.setCalls, [2]int{albumID, releaseID})
	for i := range f.releases {
		f.releases[i].Monitored = f.releases[i].ID == releaseID
	}
	return nil
}

// resolveFixture is the Humanz shape: one album, one song twice, both copies on
// disk under an artist/album folder, in one pending exact-tier group.
type resolveFixture struct {
	pool               *pgxpool.Pool
	clean, rip         dbq.Track
	cleanPath, ripPath string
	groupID            pgtype.UUID
}

func newResolveFixture(t *testing.T) resolveFixture {
	t.Helper()
	pool := newPool(t)
	ctx := context.Background()
	q := dbq.New(pool)
	dir := filepath.Join(t.TempDir(), "Gorillaz", "Humanz (2017)")
	if err := os.MkdirAll(dir, 0o755); err != nil {
		t.Fatal(err)
	}
	f := resolveFixture{pool: pool}
	f.cleanPath = filepath.Join(dir, "Gorillaz - Humanz - 03 - Saturnz Barz.mp3")
	f.ripPath = filepath.Join(dir, "Gorillaz - Humanz - 03 - Saturnz Barz (Official Video).mp3")
	for _, p := range []string{f.cleanPath, f.ripPath} {
		if err := os.WriteFile(p, []byte("audio"), 0o644); err != nil {
			t.Fatal(err)
		}
	}
	var album dbq.Album
	var artist dbq.Artist
	f.clean, album, artist = seedTrack(t, pool, f.cleanPath)
	rip, err := q.UpsertTrack(ctx, dbq.UpsertTrackParams{
		Title: "Saturnz Barz (Official Video)", AlbumID: album.ID, ArtistID: artist.ID,
		DurationMs: 1000, FilePath: f.ripPath, FileSize: 100, FileFormat: "mp3",
	})
	if err != nil {
		t.Fatal(err)
	}
	f.rip = rip
	exec := func(sql string, args ...any) {
		t.Helper()
		if _, err := pool.Exec(ctx, sql, args...); err != nil {
			t.Fatalf("exec %q: %v", sql, err)
		}
	}
	exec(`UPDATE tracks SET title = 'Saturnz Barz' WHERE id = $1`, f.clean.ID)
	exec(`UPDATE albums SET release_group_mbid = 'rg-humanz' WHERE id = $1`, album.ID)
	if err := pool.QueryRow(ctx,
		`INSERT INTO duplicate_groups (member_key, tier) VALUES ('resolve-fixture', 'exact') RETURNING id`,
	).Scan(&f.groupID); err != nil {
		t.Fatal(err)
	}
	exec(`INSERT INTO duplicate_group_members (group_id, track_id) VALUES ($1, $2), ($1, $3)`, f.groupID, f.clean.ID, f.rip.ID)
	return f
}

// lidarrPath is where Lidarr, mounted elsewhere, sees a fixture file.
func lidarrPath(p string) string { return "/music/" + LidarrPathKey(p) }

func (f resolveFixture) group(t *testing.T) (status string, class *string, note *string, auto bool) {
	t.Helper()
	if err := f.pool.QueryRow(context.Background(),
		`SELECT status, class, resolve_note, resolved_automatically FROM duplicate_groups WHERE id = $1`, f.groupID,
	).Scan(&status, &class, &note, &auto); err != nil {
		t.Fatal(err)
	}
	return status, class, note, auto
}

func exists(p string) bool { _, err := os.Stat(p); return err == nil }

// Lidarr maps the clean copy and holds the rip unmapped: the rip goes, the
// clean copy stays, and the merge is recorded as the resolver's.
func TestResolveDuplicates_MergesTheUnmappedCopy_Integration(t *testing.T) {
	f := newResolveFixture(t)
	lid := &fakeLidarr{unmapped: []string{lidarrPath(f.ripPath)}}

	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true)
	if err != nil {
		t.Fatalf("resolve: %v", err)
	}
	if res.Merged != 1 || !res.LidarrConsulted {
		t.Fatalf("result = %+v, want one merge with Lidarr consulted", res)
	}
	if exists(f.ripPath) || !exists(f.cleanPath) {
		t.Errorf("rip exists=%v clean exists=%v; want only the clean copy left", exists(f.ripPath), exists(f.cleanPath))
	}
	status, class, _, auto := f.group(t)
	if status != "merged" || class == nil || *class != string(ClassSameRelease) || !auto {
		t.Errorf("group = (%s, %v, auto=%v), want merged same_release by the resolver", status, class, auto)
	}
	var audits int
	if err := f.pool.QueryRow(context.Background(),
		`SELECT count(*) FROM audit_log WHERE action = 'duplicate_merge' AND actor_id IS NULL
		    AND metadata->>'group_id' = $1 AND (metadata->>'automatic')::boolean`,
		syncpkg.FormatUUID(f.groupID)).Scan(&audits); err != nil {
		t.Fatal(err)
	}
	if audits != 1 {
		t.Errorf("automatic merge audit rows = %d, want 1", audits)
	}
}

// Lidarr maps both copies, and its release lists the song twice: nothing is
// deleted, the release moves to the one listing each song once, and the next
// pass leaves it there (lesson #4183's fixed point).
func TestResolveDuplicates_ChangesARepeatingRelease_Integration(t *testing.T) {
	f := newResolveFixture(t)
	lid := &fakeLidarr{
		album: lidarr.LidarrAlbum{ID: 4723, ForeignAlbumID: "rg-humanz", Title: "Humanz"},
		releases: []lidarr.AlbumRelease{
			{ID: 10148, Format: "14x12\" Vinyl, Digital Media", TrackCount: 4, Monitored: true},
			{ID: 10149, Format: "Digital Media", TrackCount: 2},
		},
		releaseTracks: map[int][]lidarr.ReleaseTrack{
			10148: rt("Saturnz Barz", "Ascension", "Saturnz Barz", "Ascension"),
			10149: rt("Saturnz Barz", "Ascension"),
		},
	}

	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true)
	if err != nil {
		t.Fatalf("resolve: %v", err)
	}
	if res.Merged != 0 || !exists(f.ripPath) || !exists(f.cleanPath) {
		t.Fatalf("merged %d; a copy Lidarr maps was touched", res.Merged)
	}
	if len(lid.setCalls) != 1 || lid.setCalls[0] != [2]int{4723, 10149} {
		t.Fatalf("release changes = %v, want album 4723 to release 10149", lid.setCalls)
	}
	status, _, note, _ := f.group(t)
	if status != "pending" || note == nil || *note == "" {
		t.Errorf("group = (%s, note %v), want pending with a note saying what changed", status, note)
	}

	// The next pass: Lidarr has not rescanned yet, so both copies still read
	// as tracked. The album is settling, so nothing changes.
	if _, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true); err != nil {
		t.Fatalf("second resolve: %v", err)
	}
	if len(lid.setCalls) != 1 {
		t.Errorf("release changed again: %v", lid.setCalls)
	}
	// And once it has settled, the check itself finds nothing to do: the
	// release it chose lists each song once.
	change, _, err := changeRelease(context.Background(), dbq.New(f.pool), lid,
		&repeatingAlbum{albumID: f.clean.AlbumID, releaseGroupMbid: "rg-humanz"})
	if err != nil || change != nil || len(lid.setCalls) != 1 {
		t.Errorf("after the change, changeRelease = (%+v, %v) with %d calls; want no change", change, err, len(lid.setCalls))
	}
}

// After a release change Lidarr unmaps every file of the album until it has
// rescanned. A pass in that window must not read "every copy unmapped" as
// licence to merge: the copy it would remove may be the one Lidarr maps next.
func TestResolveDuplicates_LeavesAnAlbumAloneWhileLidarrRescans_Integration(t *testing.T) {
	f := newResolveFixture(t)
	lid := &fakeLidarr{
		album: lidarr.LidarrAlbum{ID: 4723, ForeignAlbumID: "rg-humanz"},
		releases: []lidarr.AlbumRelease{
			{ID: 10148, TrackCount: 2, Monitored: true}, {ID: 10149, TrackCount: 1},
		},
		releaseTracks: map[int][]lidarr.ReleaseTrack{10148: rt("Saturnz Barz", "Saturnz Barz"), 10149: rt("Saturnz Barz")},
	}
	if _, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true); err != nil {
		t.Fatal(err)
	}
	lid.unmapped = []string{lidarrPath(f.cleanPath), lidarrPath(f.ripPath)}
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true)
	if err != nil {
		t.Fatal(err)
	}
	if res.Merged != 0 || !exists(f.ripPath) || !exists(f.cleanPath) {
		t.Errorf("merged %d during the rescan window", res.Merged)
	}
}

// Without Lidarr, or with auto-resolve off, the pass classifies and removes
// nothing.
func TestResolveDuplicates_ClassifiesOnlyWithoutLidarrOrPermission_Integration(t *testing.T) {
	for name, run := range map[string]func(resolveFixture) (DuplicateResolveResult, error){
		"lidarr disabled": func(f resolveFixture) (DuplicateResolveResult, error) {
			return ResolveDuplicates(context.Background(), f.pool, nil, "", nil, true)
		},
		"lidarr unreachable": func(f resolveFixture) (DuplicateResolveResult, error) {
			return ResolveDuplicates(context.Background(), f.pool, nil, "", &fakeLidarr{unmappedErr: errors.New("timeout")}, true)
		},
		"auto-resolve off": func(f resolveFixture) (DuplicateResolveResult, error) {
			lid := &fakeLidarr{unmapped: []string{lidarrPath(f.ripPath)}}
			return ResolveDuplicates(context.Background(), f.pool, nil, "", lid, false)
		},
	} {
		t.Run(name, func(t *testing.T) {
			f := newResolveFixture(t)
			res, err := run(f)
			if err != nil {
				t.Fatal(err)
			}
			if res.Merged != 0 || !exists(f.ripPath) {
				t.Errorf("merged %d", res.Merged)
			}
			status, class, _, _ := f.group(t)
			if status != "pending" || class == nil || *class != string(ClassSameRelease) {
				t.Errorf("group = (%s, %v), want pending and classified", status, class)
			}
		})
	}
}

// The guard itself: a merge asked to remove a copy the check refuses changes
// nothing, file or row.
func TestMergeDuplicateGroupGuarded_RefusesATrackedCopy_Integration(t *testing.T) {
	f := newResolveFixture(t)
	refuse := func(p string) bool { return p != f.ripPath }
	_, err := MergeDuplicateGroupGuarded(context.Background(), f.pool, nil, "", f.groupID, f.clean.ID, refuse)
	if !errors.Is(err, ErrCopyTrackedByLidarr) {
		t.Fatalf("err = %v, want ErrCopyTrackedByLidarr", err)
	}
	if !exists(f.ripPath) {
		t.Error("the refused copy's file was removed")
	}
	if status, _, _, _ := f.group(t); status != "pending" {
		t.Errorf("group status = %s, want pending", status)
	}
}

// crossReleaseRipFixture is a video rip on one release with the clean copy on
// another: the album cut, and the same song's video filed as a single.
type crossReleaseRipFixture struct {
	pool               *pgxpool.Pool
	clean, rip         dbq.Track
	cleanPath, ripPath string
	groupID            pgtype.UUID
}

func newCrossReleaseRipFixture(t *testing.T) crossReleaseRipFixture {
	t.Helper()
	pool := newPool(t)
	ctx := context.Background()
	q := dbq.New(pool)
	root := t.TempDir()
	f := crossReleaseRipFixture{pool: pool}
	f.cleanPath = filepath.Join(root, "Gorillaz", "Demon Days (2005)", "06 - Feel Good Inc.mp3")
	f.ripPath = filepath.Join(root, "Gorillaz", "Feel Good Inc (2005)", "01 - Feel Good Inc. (Official Video).mp3")
	artist, err := q.UpsertArtist(ctx, dbq.UpsertArtistParams{Name: "Gorillaz", SortName: "Gorillaz"})
	if err != nil {
		t.Fatal(err)
	}
	track := func(albumTitle, title, path string) dbq.Track {
		t.Helper()
		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
			t.Fatal(err)
		}
		if err := os.WriteFile(path, []byte("audio"), 0o644); err != nil {
			t.Fatal(err)
		}
		album, err := q.UpsertAlbum(ctx, dbq.UpsertAlbumParams{Title: albumTitle, SortTitle: albumTitle, ArtistID: artist.ID})
		if err != nil {
			t.Fatal(err)
		}
		tr, err := q.UpsertTrack(ctx, dbq.UpsertTrackParams{
			Title: title, AlbumID: album.ID, ArtistID: artist.ID,
			DurationMs: 1000, FilePath: path, FileSize: 100, FileFormat: "mp3",
		})
		if err != nil {
			t.Fatal(err)
		}
		return tr
	}
	f.clean = track("Demon Days", "Feel Good Inc.", f.cleanPath)
	f.rip = track("Feel Good Inc.", "Feel Good Inc. (Official Video)", f.ripPath)
	if err := pool.QueryRow(ctx,
		`INSERT INTO duplicate_groups (member_key, tier) VALUES ('cross-rip', 'acoustic') RETURNING id`,
	).Scan(&f.groupID); err != nil {
		t.Fatal(err)
	}
	if _, err := pool.Exec(ctx,
		`INSERT INTO duplicate_group_members (group_id, track_id) VALUES ($1, $2), ($1, $3)`,
		f.groupID, f.clean.ID, f.rip.ID); err != nil {
		t.Fatal(err)
	}
	return f
}

// The rip fulfils nothing in Lidarr while the clean copy on the album does:
// the rip goes and the album copy stays (#5439, D-a rule 1).
func TestResolveDuplicates_MergesAnUnmappedRipAcrossReleases_Integration(t *testing.T) {
	f := newCrossReleaseRipFixture(t)
	lid := &fakeLidarr{unmapped: []string{lidarrPath(f.ripPath)}}
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", lid, true)
	if err != nil {
		t.Fatal(err)
	}
	if res.Classes[ClassCrossRelease] != 1 || res.Merged != 1 {
		t.Fatalf("classes %v, merged %d; want the cross-release group merged", res.Classes, res.Merged)
	}
	if exists(f.ripPath) || !exists(f.cleanPath) {
		t.Errorf("rip exists %v, clean exists %v; want only the clean copy", exists(f.ripPath), exists(f.cleanPath))
	}
}

// When Lidarr maps both copies, each fulfils its own release: nothing is
// removed, and the copies are linked as one song instead.
func TestResolveDuplicates_KeepsCopiesLidarrMapsOnTwoReleases_Integration(t *testing.T) {
	f := newCrossReleaseRipFixture(t)
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", &fakeLidarr{}, true)
	if err != nil {
		t.Fatal(err)
	}
	if res.Merged != 0 || !exists(f.ripPath) {
		t.Errorf("merged %d; want both copies kept", res.Merged)
	}
	if res.SongsLinked != 1 {
		t.Errorf("linked %d, want the pair linked as one song", res.SongsLinked)
	}
}

// A rip is held back from radio and the mixes; the operator's "fine" sticks
// through later passes; a renamed file is released.
func TestResolveDuplicates_HoldsBackRips_Integration(t *testing.T) {
	f := newCrossReleaseRipFixture(t)
	ctx := context.Background()
	q := dbq.New(f.pool)
	verdict := func(id pgtype.UUID) *string {
		t.Helper()
		var v *string
		if err := f.pool.QueryRow(ctx, `SELECT source_verdict FROM tracks WHERE id = $1`, id).Scan(&v); err != nil {
			t.Fatal(err)
		}
		return v
	}
	resolve := func() DuplicateResolveResult {
		t.Helper()
		res, err := ResolveDuplicates(ctx, f.pool, nil, "", &fakeLidarr{}, true)
		if err != nil {
			t.Fatal(err)
		}
		return res
	}

	if res := resolve(); res.HeldBack != 1 {
		t.Errorf("held back %d, want the rip", res.HeldBack)
	}
	if v := verdict(f.rip.ID); v == nil || *v != "suspect" {
		t.Errorf("rip verdict %v, want suspect", v)
	}
	if v := verdict(f.clean.ID); v != nil {
		t.Errorf("clean copy verdict %v, want none", *v)
	}

	if n, err := q.SetTrackSourceVerdict(ctx, dbq.SetTrackSourceVerdictParams{Verdict: "fine", ID: f.rip.ID}); err != nil || n != 1 {
		t.Fatalf("set fine: %d, %v", n, err)
	}
	if res := resolve(); res.HeldBack != 0 {
		t.Errorf("held back %d after the operator's fine, want 0", res.HeldBack)
	}
	if v := verdict(f.rip.ID); v == nil || *v != "fine" {
		t.Errorf("rip verdict %v, want fine kept", v)
	}

	// Held back again, then renamed: the next pass lets it go.
	if _, err := q.SetTrackSourceVerdict(ctx, dbq.SetTrackSourceVerdictParams{Verdict: "suspect", ID: f.rip.ID}); err != nil {
		t.Fatal(err)
	}
	if _, err := f.pool.Exec(ctx, `UPDATE tracks SET file_path = $2 WHERE id = $1`,
		f.rip.ID, filepath.Join(filepath.Dir(f.ripPath), "01 - Feel Good Inc.mp3")); err != nil {
		t.Fatal(err)
	}
	if res := resolve(); res.Released != 1 {
		t.Errorf("released %d, want the renamed track", res.Released)
	}
	if v := verdict(f.rip.ID); v != nil {
		t.Errorf("renamed track verdict %v, want none", *v)
	}

	// The clean copy can't be flagged by hand: there is nothing to judge.
	if n, err := q.SetTrackSourceVerdict(ctx, dbq.SetTrackSourceVerdictParams{Verdict: "fine", ID: f.clean.ID}); err != nil || n != 0 {
		t.Errorf("set on an unflagged track: %d, %v; want 0 rows", n, err)
	}
}