Vellum/internal/metadata/enrich_test.go

package metadata

import (
	"context"
	"database/sql"
	"errors"
	"io"
	"log/slog"
	"path/filepath"
	"testing"

	"github.com/mithral/vellum/internal/core"
	"github.com/mithral/vellum/internal/media"
	"github.com/mithral/vellum/migrations"
)

func testDB(t *testing.T) *sql.DB {
	t.Helper()
	db, err := core.OpenDB(filepath.Join(t.TempDir(), "meta.db"))
	if err != nil {
		t.Fatalf("OpenDB: %v", err)
	}
	t.Cleanup(func() { _ = db.Close() })
	if err := core.Migrate(context.Background(), db, migrations.FS, discard()); err != nil {
		t.Fatalf("Migrate: %v", err)
	}
	return db
}

func discard() *slog.Logger { return slog.New(slog.NewTextHandler(io.Discard, nil)) }

func seedItem(t *testing.T, db *sql.DB, title string) int64 {
	t.Helper()
	ctx := context.Background()
	var libID int64
	if err := db.QueryRowContext(ctx,
		`INSERT INTO libraries (name, kind, root_path) VALUES ('Ebooks','ebooks','/tmp/e') RETURNING id`).Scan(&libID); err != nil {
		t.Fatal(err)
	}
	var itemID int64
	if err := db.QueryRowContext(ctx, `
		INSERT INTO media_items (library_id, kind, path, title, sort_title)
		VALUES (?, 'ebooks', 'book.epub', ?, ?) RETURNING id`,
		libID, title, title).Scan(&itemID); err != nil {
		t.Fatal(err)
	}
	// A file row so catalog.Load can resolve a modtime.
	if _, err := db.ExecContext(ctx,
		`INSERT INTO media_files (item_id, path, size, mtime) VALUES (?, 'book.epub', 1, '1')`, itemID); err != nil {
		t.Fatal(err)
	}
	return itemID
}

// fakeProvider is a Provider with scripted results.
type fakeProvider struct {
	name    string
	kinds   []string
	results []Candidate
	err     error
	calls   int
}

func (f *fakeProvider) Name() string    { return f.name }
func (f *fakeProvider) Kinds() []string { return f.kinds }
func (f *fakeProvider) Search(context.Context, Query) ([]Candidate, error) {
	f.calls++
	return f.results, f.err
}

func enricherWith(t *testing.T, db *sql.DB, provs ...Provider) *Enricher {
	t.Helper()
	e := NewEnricher(db, discard(), t.TempDir())
	e.providers = func(string) []Provider { return provs }
	return e
}

func TestEnrichAppliesCandidate(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "the hobbit")

	fake := &fakeProvider{
		name:  "fake",
		kinds: []string{"ebooks"},
		results: []Candidate{{
			Provider:   "fake",
			ExternalID: "OL123W",
			Title:      "The Hobbit",
			Authors:    []string{"J.R.R. Tolkien"},
			Year:       1937,
			Publisher:  "Allen & Unwin",
		}},
	}
	e := enricherWith(t, db, fake)

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatalf("EnrichItem: %v", err)
	}

	ctx := context.Background()
	var title string
	var year sql.NullInt64
	if err := db.QueryRowContext(ctx,
		`SELECT title, year FROM media_items WHERE id = ?`, itemID).Scan(&title, &year); err != nil {
		t.Fatal(err)
	}
	if title != "The Hobbit" {
		t.Errorf("title = %q, want The Hobbit", title)
	}
	if !year.Valid || year.Int64 != 1937 {
		t.Errorf("year = %v, want 1937", year)
	}

	var provider, external string
	if err := db.QueryRowContext(ctx,
		`SELECT provider, external_id FROM provider_ids WHERE item_id = ?`, itemID).Scan(&provider, &external); err != nil {
		t.Fatalf("provider_ids not written: %v", err)
	}
	if provider != "fake" || external != "OL123W" {
		t.Errorf("provider_ids = %s/%s", provider, external)
	}

	var author string
	if err := db.QueryRowContext(ctx, `
		SELECT p.name FROM item_people ip JOIN people p ON p.id = ip.person_id
		WHERE ip.item_id = ? AND ip.role = 'author'`, itemID).Scan(&author); err != nil {
		t.Fatalf("author not linked: %v", err)
	}
	if author != "J.R.R. Tolkien" {
		t.Errorf("author = %q", author)
	}

	var status string
	if err := db.QueryRowContext(ctx,
		`SELECT status FROM metadata_fetch WHERE item_id = ? AND provider = 'fake'`, itemID).Scan(&status); err != nil {
		t.Fatal(err)
	}
	if status != "ok" {
		t.Errorf("fetch status = %q, want ok", status)
	}
}

func TestEnrichFallsBackToSecondProvider(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "some book")

	empty := &fakeProvider{name: "empty", kinds: []string{"ebooks"}}
	good := &fakeProvider{
		name:    "good",
		kinds:   []string{"ebooks"},
		results: []Candidate{{Provider: "good", ExternalID: "g1", Title: "Some Book"}},
	}
	e := enricherWith(t, db, empty, good)

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatalf("EnrichItem: %v", err)
	}
	if empty.calls != 1 || good.calls != 1 {
		t.Errorf("calls: empty=%d good=%d, want 1/1", empty.calls, good.calls)
	}

	var provider string
	if err := db.QueryRow(
		`SELECT provider FROM provider_ids WHERE item_id = ?`, itemID).Scan(&provider); err != nil {
		t.Fatal(err)
	}
	if provider != "good" {
		t.Errorf("matched provider = %q, want good", provider)
	}
}

func TestEnrichContinuesAfterProviderError(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "some book")

	broken := &fakeProvider{name: "broken", kinds: []string{"ebooks"}, err: errors.New("network down")}
	good := &fakeProvider{
		name:    "good",
		kinds:   []string{"ebooks"},
		results: []Candidate{{Provider: "good", ExternalID: "g1", Title: "Some Book"}},
	}
	e := enricherWith(t, db, broken, good)

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatalf("a provider error must not fail the item: %v", err)
	}
	if good.calls != 1 {
		t.Error("fallback was not consulted after an error")
	}

	var status string
	if err := db.QueryRow(
		`SELECT status FROM metadata_fetch WHERE item_id = ? AND provider = 'broken'`, itemID).Scan(&status); err != nil {
		t.Fatal(err)
	}
	if status != "error" {
		t.Errorf("error status = %q, want error", status)
	}
}

func TestEnrichSkipsAlreadyMatched(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "book")

	fake := &fakeProvider{name: "fake", kinds: []string{"ebooks"},
		results: []Candidate{{Provider: "fake", ExternalID: "x", Title: "Book"}}}
	e := enricherWith(t, db, fake)

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatal(err)
	}
	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatal(err)
	}
	if fake.calls != 1 {
		t.Errorf("provider called %d times, want 1 (second run must skip)", fake.calls)
	}
}

func TestEnrichDoesNotRetryRecentNotFound(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "unmatchable")

	empty := &fakeProvider{name: "empty", kinds: []string{"ebooks"}}
	e := enricherWith(t, db, empty)

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatal(err)
	}
	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Fatal(err)
	}
	if empty.calls != 1 {
		t.Errorf("provider called %d times, want 1 (notfound is cached)", empty.calls)
	}
}

func TestEnrichIgnoresUnknownKind(t *testing.T) {
	db := testDB(t)
	itemID := seedItem(t, db, "book")
	e := enricherWith(t, db) // no providers at all

	if err := e.EnrichItem(context.Background(), itemID); err != nil {
		t.Errorf("EnrichItem with no providers errored: %v", err)
	}
}

func TestNormalizeTitle(t *testing.T) {
	cases := map[string]string{
		"Random Access Memories":              "random access memories",
		"The Hobbit, or There and Back Again": "the hobbit or there and back again",
		"AC/DC — Back in Black!":              "ac dc back in black",
		"  spaced   out  ":                    "spaced out",
	}
	for in, want := range cases {
		if got := normalizeTitle(in); got != want {
			t.Errorf("normalizeTitle(%q) = %q, want %q", in, got, want)
		}
	}
}

func TestSearchTitleStripsReleaseTags(t *testing.T) {
	cases := map[string]string{
		"Sonic the Hedgehog (USA)":     "Sonic the Hedgehog",
		"Super Mario Bros. (World)":    "Super Mario Bros.",
		"Game [!]":                     "Game",
		"Pokemon (USA) (Rev 1)":        "Pokemon",
		"The Legend of Zelda":          "The Legend of Zelda",
		"Chrono Trigger (USA) [En,Fr]": "Chrono Trigger",
		"(Just Brackets)":              "(Just Brackets)",
	}
	for in, want := range cases {
		if got := searchTitle(in); got != want {
			t.Errorf("searchTitle(%q) = %q, want %q", in, got, want)
		}
	}
}

func TestPickBestRejectsUnrelated(t *testing.T) {
	candidates := []Candidate{
		{Title: "Random Access Memories", ExternalID: "right"},
	}

	// The exact title is accepted.
	if c, ok := pickBest(candidates, "Random Access Memories"); !ok || c.ExternalID != "right" {
		t.Errorf("exact match rejected: ok=%v c=%+v", ok, c)
	}

	// Containment in either direction is accepted.
	long := []Candidate{{Title: "The Hobbit, or There and Back Again"}}
	if _, ok := pickBest(long, "The Hobbit"); !ok {
		t.Error("containment should be accepted")
	}

	// A same-named release by a different artist is still accepted by title —
	// the artist hint, not the title check, is what disambiguates that.
	// But a genuinely unrelated title must be rejected.
	if _, ok := pickBest(candidates, "Franz Kirmann"); ok {
		t.Error("unrelated title should be rejected")
	}

	// Too-short titles are never matched, to avoid substring false positives.
	if _, ok := pickBest(candidates, "a"); ok {
		t.Error("a one-character query should be rejected")
	}
}

func TestArtistHint(t *testing.T) {
	// Directory-grouped kinds take the artist from the parent directory.
	album := media.Item{Kind: "music", Path: "Daft Punk/Random Access Memories"}
	if got := artistHint(album); got != "Daft Punk" {
		t.Errorf("artistHint(album) = %q, want Daft Punk", got)
	}

	// A loose root-level file has no artist to infer.
	loose := media.Item{Kind: "music", Path: "."}
	if got := artistHint(loose); got != "" {
		t.Errorf("artistHint(loose) = %q, want empty", got)
	}

	// File-grouped kinds (ebooks) never take a hint: their parent directory is
	// usually a series, not an author.
	book := media.Item{Kind: "ebooks", Path: "Series/Book.epub"}
	if got := artistHint(book); got != "" {
		t.Errorf("artistHint(ebook) = %q, want empty", got)
	}
}