feat(scanner): implement selective folder scanning and file system watcher improvements (#4674)

* feat: Add selective folder scanning capability

Implement targeted scanning of specific library/folder pairs without
full recursion. This enables efficient rescanning of individual folders
when changes are detected, significantly reducing scan time for large
libraries.

Key changes:
- Add ScanTarget struct and ScanFolders API to Scanner interface
- Implement CLI flag --targets for specifying libraryID:folderPath pairs
- Add FolderRepository.GetByPaths() for batch folder info retrieval
- Create loadSpecificFolders() for non-recursive directory loading
- Scope GC operations to affected libraries only (with TODO for full impl)
- Add comprehensive tests for selective scanning behavior

The selective scan:
- Only processes specified folders (no subdirectory recursion)
- Maintains library isolation
- Runs full maintenance pipeline scoped to affected libraries
- Supports both full and quick scan modes

Examples:
  navidrome scan --targets "1:Music/Rock,1:Music/Jazz"
  navidrome scan --full --targets "2:Classical"

* feat(folder): replace GetByPaths with GetFolderUpdateInfo for improved folder updates retrieval

Signed-off-by: Deluan <deluan@navidrome.org>

* test: update parseTargets test to handle folder names with spaces

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(folder): remove unused LibraryPath struct and update GC logging message

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(folder): enhance external scanner to support target-specific scanning

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): simplify scanner methods

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(watcher): implement folder scanning notifications with deduplication

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(watcher): add resolveFolderPath function for testability

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(watcher): implement path ignoring based on .ndignore patterns

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): implement IgnoreChecker for managing .ndignore patterns

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(ignore_checker): rename scanner to lineScanner for clarity

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): enhance ScanTarget struct with String method for better target representation

Signed-off-by: Deluan <deluan@navidrome.org>

* fix(scanner): validate library ID to prevent negative values

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): simplify GC method by removing library ID parameter

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(scanner): update folder scanning to include all descendants of specified folders

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(subsonic): allow selective scan in the /startScan endpoint

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): update CallScan to handle specific library/folder pairs

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): streamline scanning logic by removing scanAll method

Signed-off-by: Deluan <deluan@navidrome.org>

* test: enhance mockScanner for thread safety and improve test reliability

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): move scanner.ScanTarget to model.ScanTarget

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor: move scanner types to model,implement MockScanner

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): update scanner interface and implementations to use model.Scanner

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(folder_repository): normalize target path handling by using filepath.Clean

Signed-off-by: Deluan <deluan@navidrome.org>

* test(folder_repository): add comprehensive tests for folder retrieval and child exclusion

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): simplify selective scan logic using slice.Filter

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): streamline phase folder and album creation by removing unnecessary library parameter

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): move initialization logic from phase_1 to the scanner itself

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(tests): rename selective scan test file to scanner_selective_test.go

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(configuration): add DevSelectiveWatcher configuration option

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(watcher): enhance .ndignore handling for folder deletions and file changes

Signed-off-by: Deluan <deluan@navidrome.org>

* docs(scanner): comments

Signed-off-by: Deluan <deluan@navidrome.org>

* refactor(scanner): enhance walkDirTree to support target folder scanning

Signed-off-by: Deluan <deluan@navidrome.org>

* fix(scanner, watcher): handle errors when pushing ignore patterns for folders

Signed-off-by: Deluan <deluan@navidrome.org>

* Update scanner/phase_1_folders.go

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* refactor(scanner): replace parseTargets function with direct call to scanner.ParseTargets

Signed-off-by: Deluan <deluan@navidrome.org>

* test(scanner): add tests for ScanBegin and ScanEnd functionality

Signed-off-by: Deluan <deluan@navidrome.org>

* fix(library): update PRAGMA optimize to check table sizes without ANALYZE

Signed-off-by: Deluan <deluan@navidrome.org>

* test(scanner): refactor tests

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(ui): add selective scan options and update translations

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(ui): add quick and full scan options for individual libraries

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(ui): add Scan buttonsto the LibraryList

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(scan): update scanning parameters from 'path' to 'target' for selective scans.

* refactor(scan): move ParseTargets function to model package

* test(scan): suppress unused return value from SetUserLibraries in tests

* feat(gc): enhance garbage collection to support selective library purging

Signed-off-by: Deluan <deluan@navidrome.org>

* fix(scanner): prevent race condition when scanning deleted folders

When the watcher detects changes in a folder that gets deleted before
the scanner runs (due to the 10-second delay), the scanner was
prematurely removing these folders from the tracking map, preventing
them from being marked as missing.

The issue occurred because `newFolderEntry` was calling `popLastUpdate`
before verifying the folder actually exists on the filesystem.

Changes:
- Move fs.Stat check before newFolderEntry creation in loadDir to
  ensure deleted folders remain in lastUpdates for finalize() to handle
- Add early existence check in walkDirTree to skip non-existent target
  folders with a warning log
- Add unit test verifying non-existent folders aren't removed from
  lastUpdates prematurely
- Add integration test for deleted folder scenario with ScanFolders

Fixes the issue where deleting entire folders (e.g., /music/AC_DC)
wouldn't mark tracks as missing when using selective folder scanning.

* refactor(scan): streamline folder entry creation and update handling

Signed-off-by: Deluan <deluan@navidrome.org>

* feat(scan): add '@Recycle' (QNAP) to ignored directories list

Signed-off-by: Deluan <deluan@navidrome.org>

* fix(log): improve thread safety in logging level management

* test(scan): move unit tests for ParseTargets function

Signed-off-by: Deluan <deluan@navidrome.org>

* review

Signed-off-by: Deluan <deluan@navidrome.org>

---------

Signed-off-by: Deluan <deluan@navidrome.org>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: deluan <deluan.quintao@mechanical-orchard.com>
This commit is contained in:
Deluan Quintão
2025-11-14 22:15:43 -05:00
committed by GitHub
parent bca76069c3
commit 28d5299ffc
52 changed files with 3221 additions and 374 deletions
+17 -25
View File
@@ -26,24 +26,8 @@ var (
ErrAlreadyScanning = errors.New("already scanning")
)
type Scanner interface {
// ScanAll starts a full scan of the music library. This is a blocking operation.
ScanAll(ctx context.Context, fullScan bool) (warnings []string, err error)
Status(context.Context) (*StatusInfo, error)
}
type StatusInfo struct {
Scanning bool
LastScan time.Time
Count uint32
FolderCount uint32
LastError string
ScanType string
ElapsedTime time.Duration
}
func New(rootCtx context.Context, ds model.DataStore, cw artwork.CacheWarmer, broker events.Broker,
pls core.Playlists, m metrics.Metrics) Scanner {
pls core.Playlists, m metrics.Metrics) model.Scanner {
c := &controller{
rootCtx: rootCtx,
ds: ds,
@@ -65,9 +49,10 @@ func (s *controller) getScanner() scanner {
return &scannerImpl{ds: s.ds, cw: s.cw, pls: s.pls}
}
// CallScan starts an in-process scan of the music library.
// CallScan starts an in-process scan of specific library/folder pairs.
// If targets is empty, it scans all libraries.
// This is meant to be called from the command line (see cmd/scan.go).
func CallScan(ctx context.Context, ds model.DataStore, pls core.Playlists, fullScan bool) (<-chan *ProgressInfo, error) {
func CallScan(ctx context.Context, ds model.DataStore, pls core.Playlists, fullScan bool, targets []model.ScanTarget) (<-chan *ProgressInfo, error) {
release, err := lockScan(ctx)
if err != nil {
return nil, err
@@ -79,7 +64,7 @@ func CallScan(ctx context.Context, ds model.DataStore, pls core.Playlists, fullS
go func() {
defer close(progress)
scanner := &scannerImpl{ds: ds, cw: artwork.NoopCacheWarmer(), pls: pls}
scanner.scanAll(ctx, fullScan, progress)
scanner.scanFolders(ctx, fullScan, targets, progress)
}()
return progress, nil
}
@@ -99,8 +84,11 @@ type ProgressInfo struct {
ForceUpdate bool
}
// scanner defines the interface for different scanner implementations.
// This allows for swapping between in-process and external scanners.
type scanner interface {
scanAll(ctx context.Context, fullScan bool, progress chan<- *ProgressInfo)
// scanFolders performs the actual scanning of folders. If targets is nil, it scans all libraries.
scanFolders(ctx context.Context, fullScan bool, targets []model.ScanTarget, progress chan<- *ProgressInfo)
}
type controller struct {
@@ -158,7 +146,7 @@ func (s *controller) getScanInfo(ctx context.Context) (scanType string, elapsed
return scanType, elapsed, lastErr
}
func (s *controller) Status(ctx context.Context) (*StatusInfo, error) {
func (s *controller) Status(ctx context.Context) (*model.ScannerStatus, error) {
lastScanTime, err := s.getLastScanTime(ctx)
if err != nil {
return nil, fmt.Errorf("getting last scan time: %w", err)
@@ -167,7 +155,7 @@ func (s *controller) Status(ctx context.Context) (*StatusInfo, error) {
scanType, elapsed, lastErr := s.getScanInfo(ctx)
if running.Load() {
status := &StatusInfo{
status := &model.ScannerStatus{
Scanning: true,
LastScan: lastScanTime,
Count: s.count.Load(),
@@ -183,7 +171,7 @@ func (s *controller) Status(ctx context.Context) (*StatusInfo, error) {
if err != nil {
return nil, fmt.Errorf("getting library stats: %w", err)
}
return &StatusInfo{
return &model.ScannerStatus{
Scanning: false,
LastScan: lastScanTime,
Count: uint32(count),
@@ -208,6 +196,10 @@ func (s *controller) getCounters(ctx context.Context) (int64, int64, error) {
}
func (s *controller) ScanAll(requestCtx context.Context, fullScan bool) ([]string, error) {
return s.ScanFolders(requestCtx, fullScan, nil)
}
func (s *controller) ScanFolders(requestCtx context.Context, fullScan bool, targets []model.ScanTarget) ([]string, error) {
release, err := lockScan(requestCtx)
if err != nil {
return nil, err
@@ -224,7 +216,7 @@ func (s *controller) ScanAll(requestCtx context.Context, fullScan bool) ([]strin
go func() {
defer close(progress)
scanner := s.getScanner()
scanner.scanAll(ctx, fullScan, progress)
scanner.scanFolders(ctx, fullScan, targets, progress)
}()
// Wait for the scan to finish, sending progress events to all connected clients