Library indexing and filesystem scanner with incremental rescans

This commit is contained in:
2026-08-22 23:31:17 -05:00
parent d4ea7a4ca9
commit 49dbee617a
5 changed files with 915 additions and 0 deletions
+276
View File
@@ -0,0 +1,276 @@
// Package scanner walks configured music folders, detects new/changed/
// deleted/renamed files, and indexes them into the library via a bounded
// worker pool.
package scanner
import (
"context"
"database/sql"
"fmt"
"io/fs"
"log/slog"
"os"
"path/filepath"
"strings"
"sync"
"time"
"git.noroutes.net/NoRoutes/vibetunes/internal/database"
"git.noroutes.net/NoRoutes/vibetunes/internal/library"
"git.noroutes.net/NoRoutes/vibetunes/internal/metadata"
)
// recognizedExtensions are the file extensions VibeSonic attempts to
// probe as media. Anything else (art, .nfo, playlists, ...) is skipped
// during a scan rather than passed to ffprobe.
var recognizedExtensions = map[string]bool{
".mp3": true, ".flac": true, ".ogg": true, ".oga": true, ".opus": true,
".aac": true, ".m4a": true, ".m4b": true, ".alac": true,
".wav": true, ".aiff": true, ".aif": true, ".wma": true, ".mp4": true,
}
const maxWorkers = 4
// Scanner indexes one or more music folders into the database.
type Scanner struct {
DB *sql.DB
Prober *metadata.Prober
Log *slog.Logger
mu sync.Mutex
scanning map[string]bool // music_folder_id -> in progress
}
func New(db *sql.DB, prober *metadata.Prober, log *slog.Logger) *Scanner {
return &Scanner{DB: db, Prober: prober, Log: log, scanning: make(map[string]bool)}
}
// ScanFolder walks a single music folder and indexes it incrementally:
// unchanged files (same size+mtime) are only marked seen, changed files
// are reprobed, moved files are matched by content hash and just get
// their path updated, and files no longer found on disk are marked
// missing rather than deleted outright.
func (s *Scanner) ScanFolder(ctx context.Context, folderID string) error {
if !s.beginScan(folderID) {
return fmt.Errorf("scan already in progress for folder %s", folderID)
}
defer s.endScan(folderID)
folder, err := database.GetMusicFolder(s.DB, folderID)
if err != nil {
return err
}
startedAt := time.Now()
if err := database.StartScan(s.DB, folderID); err != nil {
return err
}
var seen, added, updated int
var mu sync.Mutex
sem := make(chan struct{}, maxWorkers)
var wg sync.WaitGroup
var firstErr error
walkErr := filepath.WalkDir(folder.Path, func(path string, d fs.DirEntry, err error) error {
if err != nil {
s.Log.Warn("scan: walk error", "path", path, "err", err)
return nil // keep scanning the rest of the tree
}
if ctx.Err() != nil {
return ctx.Err()
}
if d.IsDir() {
return nil
}
if !recognizedExtensions[strings.ToLower(filepath.Ext(path))] {
return nil
}
rel, err := filepath.Rel(folder.Path, path)
if err != nil {
return nil
}
rel = filepath.ToSlash(rel)
wg.Add(1)
sem <- struct{}{}
go func() {
defer wg.Done()
defer func() { <-sem }()
wasAdded, wasUpdated, err := s.indexOne(ctx, folder.ID, path, rel)
mu.Lock()
defer mu.Unlock()
seen++
if err != nil {
s.Log.Warn("scan: index failed", "path", rel, "err", err)
} else {
if wasAdded {
added++
} else if wasUpdated {
updated++
}
}
if seen%25 == 0 {
_ = database.UpdateScanProgress(s.DB, folder.ID, seen, added, updated)
}
}()
return nil
})
wg.Wait()
if walkErr != nil && firstErr == nil {
firstErr = walkErr
}
_ = database.UpdateScanProgress(s.DB, folder.ID, seen, added, updated)
removed, err := database.MarkFolderFilesMissingExcept(s.DB, folder.ID, startedAt)
if err != nil && firstErr == nil {
firstErr = err
}
errMsg := ""
if firstErr != nil {
errMsg = firstErr.Error()
}
if err := database.FinishScan(s.DB, folder.ID, int(removed), errMsg); err != nil {
return err
}
return firstErr
}
// indexOne probes and indexes a single file, returning whether it was
// newly added or updated so the caller can track progress.
func (s *Scanner) indexOne(ctx context.Context, folderID, absPath, relPath string) (added, updated bool, err error) {
info, err := os.Stat(absPath)
if err != nil {
return false, false, err
}
size := info.Size()
mtime := info.ModTime().Unix()
hash := fingerprint(size, mtime)
existing, err := database.FindMediaFileByPath(s.DB, folderID, relPath)
if err == nil {
if existing.SizeBytes == size && existing.MtimeUnix == mtime {
return false, false, database.TouchMediaFileScanned(s.DB, existing.ID)
}
// Changed: reprobe and update in place; the media_file (and
// therefore song) ID stays the same.
tags, perr := s.Prober.Probe(ctx, absPath)
if perr != nil {
return false, false, perr
}
if err := database.UpdateMediaFileScanned(s.DB, existing.ID, size, mtime, hash, tags.Format, tags.Kind, tags.DurationSeconds, tags.BitrateKbps, tags.SampleRateHz, tags.Channels); err != nil {
return false, false, err
}
mf, err := database.GetMediaFile(s.DB, existing.ID)
if err != nil {
return false, false, err
}
if _, err := library.IndexFile(s.DB, mf, tags); err != nil {
return false, false, err
}
return false, true, nil
}
if err != database.ErrNotFound {
return false, false, err
}
// Not found by path. Check whether this is a rename/move of a file we
// already indexed (same content fingerprint, different path).
if renamed, rerr := database.FindMediaFileByHash(s.DB, folderID, hash); rerr == nil {
if err := database.RenameMediaFile(s.DB, renamed.ID, relPath); err != nil {
return false, false, err
}
return false, true, nil
}
// Genuinely new file.
tags, err := s.Prober.Probe(ctx, absPath)
if err != nil {
return false, false, err
}
mf, err := database.CreateMediaFile(s.DB, folderID, relPath, size, mtime, hash, tags.Format, tags.Kind, tags.DurationSeconds, tags.BitrateKbps, tags.SampleRateHz, tags.Channels)
if err != nil {
return false, false, err
}
if _, err := library.IndexFile(s.DB, mf, tags); err != nil {
return false, false, err
}
return true, false, nil
}
// fingerprint is a cheap, fast rename/change detector based on size and
// mtime rather than hashing file content (which would mean reading every
// byte of every file on every scan).
func fingerprint(size, mtime int64) string {
return fmt.Sprintf("%d-%d", size, mtime)
}
func (s *Scanner) beginScan(folderID string) bool {
s.mu.Lock()
defer s.mu.Unlock()
if s.scanning[folderID] {
return false
}
s.scanning[folderID] = true
return true
}
func (s *Scanner) endScan(folderID string) {
s.mu.Lock()
defer s.mu.Unlock()
delete(s.scanning, folderID)
}
// IsScanning reports whether a scan of folderID is currently running.
func (s *Scanner) IsScanning(folderID string) bool {
s.mu.Lock()
defer s.mu.Unlock()
return s.scanning[folderID]
}
// ScanAllEnabled scans every enabled music folder sequentially (folders
// run one at a time; files within a folder run concurrently via the
// worker pool above).
func (s *Scanner) ScanAllEnabled(ctx context.Context) error {
folders, err := database.ListMusicFolders(s.DB)
if err != nil {
return err
}
var firstErr error
for _, f := range folders {
if !f.Enabled {
continue
}
if err := s.ScanFolder(ctx, f.ID); err != nil && firstErr == nil {
firstErr = err
}
}
return firstErr
}
// RunScheduled runs ScanAllEnabled once at startup and then on the given
// interval, until ctx is cancelled. interval <= 0 disables the periodic
// rescan (startup scan still runs).
func (s *Scanner) RunScheduled(ctx context.Context, interval time.Duration) {
if err := s.ScanAllEnabled(ctx); err != nil {
s.Log.Warn("startup scan finished with errors", "err", err)
}
if interval <= 0 {
return
}
ticker := time.NewTicker(interval)
defer ticker.Stop()
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
if err := s.ScanAllEnabled(ctx); err != nil {
s.Log.Warn("scheduled scan finished with errors", "err", err)
}
}
}
}
+239
View File
@@ -0,0 +1,239 @@
package scanner
import (
"context"
"io"
"log/slog"
"os"
"os/exec"
"path/filepath"
"testing"
"time"
"git.noroutes.net/NoRoutes/vibetunes/internal/database"
"git.noroutes.net/NoRoutes/vibetunes/internal/metadata"
)
func testLogger() *slog.Logger {
return slog.New(slog.NewTextHandler(io.Discard, nil))
}
func genFile(t *testing.T, dir, name, title, artist string) string {
t.Helper()
if _, err := exec.LookPath("ffmpeg"); err != nil {
t.Skip("ffmpeg not installed, skipping scanner integration test")
}
out := filepath.Join(dir, name)
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
cmd := exec.CommandContext(ctx, "ffmpeg",
"-f", "lavfi", "-i", "sine=frequency=440:duration=1",
"-metadata", "title="+title,
"-metadata", "artist="+artist,
"-metadata", "album=Scan Test Album",
"-codec:a", "libmp3lame", "-b:a", "64k",
out,
)
if combined, err := cmd.CombinedOutput(); err != nil {
t.Fatalf("ffmpeg failed: %v\n%s", err, combined)
}
return out
}
func newTestScanner(t *testing.T) (*Scanner, *database.MusicFolder, string) {
t.Helper()
if _, err := exec.LookPath("ffprobe"); err != nil {
t.Skip("ffprobe not installed, skipping scanner integration test")
}
dbPath := filepath.Join(t.TempDir(), "test.db")
db, err := database.Open(dbPath)
if err != nil {
t.Fatalf("database.Open: %v", err)
}
t.Cleanup(func() { db.Close() })
musicDir := t.TempDir()
folder, err := database.CreateMusicFolder(db, "Test Music", musicDir, "music")
if err != nil {
t.Fatalf("CreateMusicFolder: %v", err)
}
s := New(db, &metadata.Prober{}, testLogger())
return s, folder, musicDir
}
func TestScanFolderAddsNewFiles(t *testing.T) {
s, folder, dir := newTestScanner(t)
genFile(t, dir, "song1.mp3", "Song One", "Artist One")
genFile(t, dir, "song2.mp3", "Song Two", "Artist One")
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder: %v", err)
}
files, err := database.ListMediaFilesForFolder(s.DB, folder.ID)
if err != nil {
t.Fatalf("ListMediaFilesForFolder: %v", err)
}
if len(files) != 2 {
t.Fatalf("got %d media files, want 2", len(files))
}
state, err := database.GetScanState(s.DB, folder.ID)
if err != nil {
t.Fatalf("GetScanState: %v", err)
}
if state.FilesAdded != 2 {
t.Errorf("FilesAdded = %d, want 2", state.FilesAdded)
}
if state.Status != "idle" {
t.Errorf("Status = %q, want idle", state.Status)
}
}
func TestScanFolderIncrementalNoReprobe(t *testing.T) {
s, folder, dir := newTestScanner(t)
genFile(t, dir, "song1.mp3", "Song One", "Artist One")
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (1st): %v", err)
}
files1, _ := database.ListMediaFilesForFolder(s.DB, folder.ID)
id1 := files1[0].ID
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (2nd): %v", err)
}
files2, _ := database.ListMediaFilesForFolder(s.DB, folder.ID)
if len(files2) != 1 {
t.Fatalf("got %d media files after rescan, want 1 (no duplicates)", len(files2))
}
if files2[0].ID != id1 {
t.Errorf("media file ID changed across rescan: %s -> %s", id1, files2[0].ID)
}
state, err := database.GetScanState(s.DB, folder.ID)
if err != nil {
t.Fatalf("GetScanState: %v", err)
}
if state.FilesAdded != 0 || state.FilesUpdated != 0 {
t.Errorf("second scan should add/update nothing, got added=%d updated=%d", state.FilesAdded, state.FilesUpdated)
}
}
func TestScanFolderMarksDeletedFilesMissing(t *testing.T) {
s, folder, dir := newTestScanner(t)
path := genFile(t, dir, "song1.mp3", "Song One", "Artist One")
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (1st): %v", err)
}
if err := os.Remove(path); err != nil {
t.Fatalf("os.Remove: %v", err)
}
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (2nd): %v", err)
}
files, err := database.ListMediaFilesForFolder(s.DB, folder.ID)
if err != nil {
t.Fatalf("ListMediaFilesForFolder: %v", err)
}
if len(files) != 1 {
t.Fatalf("got %d media files, want 1 (row kept, not deleted)", len(files))
}
if !files[0].Missing {
t.Error("expected the removed file's row to be marked missing")
}
state, err := database.GetScanState(s.DB, folder.ID)
if err != nil {
t.Fatalf("GetScanState: %v", err)
}
if state.FilesRemoved != 1 {
t.Errorf("FilesRemoved = %d, want 1", state.FilesRemoved)
}
}
func TestScanFolderDetectsRename(t *testing.T) {
s, folder, dir := newTestScanner(t)
oldPath := genFile(t, dir, "old_name.mp3", "Song One", "Artist One")
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (1st): %v", err)
}
files1, _ := database.ListMediaFilesForFolder(s.DB, folder.ID)
id1 := files1[0].ID
newPath := filepath.Join(dir, "new_name.mp3")
if err := os.Rename(oldPath, newPath); err != nil {
t.Fatalf("os.Rename: %v", err)
}
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder (2nd): %v", err)
}
files2, err := database.ListMediaFilesForFolder(s.DB, folder.ID)
if err != nil {
t.Fatalf("ListMediaFilesForFolder: %v", err)
}
if len(files2) != 1 {
t.Fatalf("got %d media files after rename, want 1 (matched by content, not duplicated)", len(files2))
}
if files2[0].ID != id1 {
t.Errorf("media file ID changed across rename: %s -> %s (should reuse the same row)", id1, files2[0].ID)
}
if files2[0].RelativePath != "new_name.mp3" {
t.Errorf("RelativePath = %q, want new_name.mp3", files2[0].RelativePath)
}
if files2[0].Missing {
t.Error("renamed file should not be marked missing")
}
}
func TestScanFolderIndexesLibraryTags(t *testing.T) {
s, folder, dir := newTestScanner(t)
genFile(t, dir, "song1.mp3", "Song One", "Shared Artist")
genFile(t, dir, "song2.mp3", "Song Two", "Shared Artist")
if err := s.ScanFolder(context.Background(), folder.ID); err != nil {
t.Fatalf("ScanFolder: %v", err)
}
artists, err := database.ListArtists(s.DB)
if err != nil {
t.Fatalf("ListArtists: %v", err)
}
if len(artists) != 1 {
t.Fatalf("artists = %v, want 1 shared artist reused across both songs", artists)
}
albums, err := database.ListAlbumsByArtist(s.DB, artists[0].ID)
if err != nil {
t.Fatalf("ListAlbumsByArtist: %v", err)
}
if len(albums) != 1 {
t.Fatalf("albums = %v, want 1", albums)
}
songs, err := database.ListSongsByAlbum(s.DB, albums[0].ID)
if err != nil {
t.Fatalf("ListSongsByAlbum: %v", err)
}
if len(songs) != 2 {
t.Fatalf("songs = %v, want 2", songs)
}
}
func TestScanFolderRejectsConcurrentScan(t *testing.T) {
s, folder, dir := newTestScanner(t)
genFile(t, dir, "song1.mp3", "Song One", "Artist One")
if !s.beginScan(folder.ID) {
t.Fatal("beginScan should succeed the first time")
}
defer s.endScan(folder.ID)
if err := s.ScanFolder(context.Background(), folder.ID); err == nil {
t.Fatal("expected error scanning a folder that is already being scanned")
}
}