minstrel/internal/library/duplicate_resolve_test.go

package library

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

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

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

// 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)
	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
}

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 }

// autoMergeAudit reads the resolver's audit row for a group: how many there
// are, and the reason the last one gave for its survivor.
func autoMergeAudit(t *testing.T, pool *pgxpool.Pool, groupID pgtype.UUID) (n int, reason string) {
	t.Helper()
	if err := pool.QueryRow(context.Background(),
		`SELECT count(*), coalesce(max(metadata->>'survivor_reason'), '') FROM audit_log
		  WHERE action = 'duplicate_merge' AND actor_id IS NULL
		    AND metadata->>'group_id' = $1 AND (metadata->>'automatic')::boolean`,
		syncpkg.FormatUUID(groupID)).Scan(&n, &reason); err != nil {
		t.Fatal(err)
	}
	return n, reason
}

// One album holding a song twice: the extra copy goes, the copy whose name and
// tags fit the album stays, and the merge is recorded as the resolver's. No
// Lidarr is asked (M502 #5517): Minstrel is the only program writing the
// library.
func TestResolveDuplicates_MergesASameReleaseCopy_Integration(t *testing.T) {
	f := newResolveFixture(t)
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", true)
	if err != nil {
		t.Fatalf("resolve: %v", err)
	}
	if res.Merged != 1 || res.Classes[ClassSameRelease] != 1 {
		t.Fatalf("result = %+v, want the same-release group merged", 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)
	}
	if n, _ := autoMergeAudit(t, f.pool, f.groupID); n != 1 {
		t.Errorf("automatic merge audit rows = %d, want 1", n)
	}
}

// With auto-resolve off, the pass classifies and removes nothing.
func TestResolveDuplicates_ClassifiesOnlyWithoutPermission_Integration(t *testing.T) {
	f := newResolveFixture(t)
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", false)
	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)
	}
}

// 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
}

// A video rip on one release with the clean copy on another: the rip is no
// release's copy, so it goes and the album cut stays (#5439, now without
// Lidarr).
func TestResolveDuplicates_MergesARipAcrossReleases_Integration(t *testing.T) {
	f := newCrossReleaseRipFixture(t)
	res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", 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))
	}
	if _, reason := autoMergeAudit(t, f.pool, f.groupID); reason != "the copy that is not a video rip" {
		t.Errorf("survivor reason %q, want the rip rule", reason)
	}
}

// Copies on two releases that are both clean each belong to their release:
// nothing is removed, and they are linked as one song. A rip the operator
// marked fine counts as clean.
func TestResolveDuplicates_KeepsCleanCopiesOnTwoReleases_Integration(t *testing.T) {
	for name, prepare := range map[string]func(f crossReleaseRipFixture) (string, []any){
		"renamed": func(f crossReleaseRipFixture) (string, []any) {
			return `UPDATE tracks SET title = 'Feel Good Inc.', file_path = $2 WHERE id = $1`,
				[]any{f.rip.ID, filepath.Join(filepath.Dir(f.ripPath), "01 - Feel Good Inc.mp3")}
		},
		"kept as fine": func(f crossReleaseRipFixture) (string, []any) {
			return `UPDATE tracks SET source_verdict = 'fine' WHERE id = $1`, []any{f.rip.ID}
		},
	} {
		t.Run(name, func(t *testing.T) {
			f := newCrossReleaseRipFixture(t)
			sql, args := prepare(f)
			if _, err := f.pool.Exec(context.Background(), sql, args...); err != nil {
				t.Fatal(err)
			}
			res, err := ResolveDuplicates(context.Background(), f.pool, nil, "", 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)
			}
		})
	}
}

// Identical audio under two titles on two albums, neither a rip: which tags
// are wrong is the operator's call, so nothing is merged or linked.
func TestResolveDuplicates_LeavesAMismatchForTheOperator_Integration(t *testing.T) {
	f := newCrossReleaseRipFixture(t)
	ctx := context.Background()
	if _, err := f.pool.Exec(ctx, `UPDATE duplicate_groups SET tier = 'exact' WHERE id = $1`, f.groupID); err != nil {
		t.Fatal(err)
	}
	if _, err := f.pool.Exec(ctx, `UPDATE tracks SET title = 'DARE', file_path = $2 WHERE id = $1`,
		f.rip.ID, filepath.Join(filepath.Dir(f.ripPath), "01 - DARE.mp3")); err != nil {
		t.Fatal(err)
	}
	res, err := ResolveDuplicates(ctx, f.pool, nil, "", true)
	if err != nil {
		t.Fatal(err)
	}
	if res.Classes[ClassMismatch] != 1 || res.Merged != 0 || res.SongsLinked != 0 {
		t.Fatalf("classes %v, merged %d, linked %d; want a mismatch left alone", res.Classes, res.Merged, res.SongsLinked)
	}
	if status, _, note, _ := (resolveFixture{pool: f.pool, groupID: f.groupID}).group(t); status != "pending" || note == nil || *note == "" {
		t.Errorf("group = (%s, note %v), want pending with a note", status, note)
	}
}

// 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)
	// Without its group the rip has no clean copy to merge into, so it stays
	// on disk and only its verdict changes.
	if _, err := f.pool.Exec(ctx, `DELETE FROM duplicate_groups WHERE id = $1`, f.groupID); err != nil {
		t.Fatal(err)
	}
	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, "", 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)
	}
}