Files
bookhoard/internal/services/media_scanner_test.go
T
john-okeefe d225e1dff4 feat(scanner): add directory mtime-based fast polling for container environments
Podman rootless containers with overlay storage do not propagate inotify
events through bind mounts, making the fsnotify file watcher ineffective.
This caused new files added on the host to go undetected until the
5-minute full-filesystem-walk polling fallback caught them.

Add a lightweight directory mtime polling mechanism that runs every 10
seconds, checking stat() on all subdirectories under watched library
folders against a cached mtime value. When a directory's mtime changes
(indicating files were added/removed/renamed), it feeds into the existing
markDirectoryDirty() → processDirtyDirectories() → job queue pipeline.

Changes:
- Add dirMtimes cache + mutex to MediaScanner struct
- Add seedDirectoryMtimes() to populate cache on startup (prevents
  false-positive flood on first poll)
- Add pollDirectoryChanges() goroutine (10s ticker) and
  checkDirectoryMtimes() (walks directories, compares mtimes)
- Launch mtime poller from WatchChanges() alongside existing goroutines
- Rename StartPolling logs to [ORPHAN-CLEANUP] to clarify its role
- Change default poll interval from 60s → 30m (new file detection now
  handled by the fast mtime poll; full sync focuses on orphan cleanup)
- Update GetScanSettings default from 60 → 1800 seconds
- Add 5 tests: seed cache, skip nonexistent, detect new dir, skip
  unchanged, detect modified dir

Expected result: new files detected in ~20 seconds (10s poll + 10s
debounce) regardless of inotify/container support.
2026-05-12 16:54:35 -04:00

223 lines
6.9 KiB
Go

package services
import (
"bookhoard/internal/database"
"context"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// Helper function to setup test database
func setupTestDB(t *testing.T) *database.Queries {
// Use existing test database setup
// This would connect to the test database
return &database.Queries{} // Placeholder - use your actual test DB setup
}
func TestMarkDirectoryDirty(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.markDirectoryDirty("/test/folder/subdir")
scanner.dirtyDirsMu.RLock()
_, exists := scanner.dirtyDirs["/test/folder/subdir"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, exists, "Directory should be marked dirty")
}
func TestMarkDirectoryDirty_IgnoresNonWatchedPaths(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
scanner.markDirectoryDirty("/other/folder")
scanner.dirtyDirsMu.RLock()
_, exists := scanner.dirtyDirs["/other/folder"]
scanner.dirtyDirsMu.RUnlock()
assert.False(t, exists, "Non-watched directory should be ignored")
}
func TestMarkDirectoryDirty_SmartEventMerging(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
// Mark subdirectory first
scanner.markDirectoryDirty("/test/folder/subdir1")
scanner.dirtyDirsMu.RLock()
_, exists1 := scanner.dirtyDirs["/test/folder/subdir1"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, exists1)
// Mark parent directory - should replace subdirectory
scanner.markDirectoryDirty("/test/folder")
scanner.dirtyDirsMu.RLock()
_, parentExists := scanner.dirtyDirs["/test/folder"]
_, childExists := scanner.dirtyDirs["/test/folder/subdir1"]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, parentExists, "Parent should exist")
assert.False(t, childExists, "Child should be removed (consolidated)")
}
func TestWaitForFileStability_StableFile(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
// Create a stable file
tmpDir := t.TempDir()
filePath := filepath.Join(tmpDir, "stable.epub")
err := os.WriteFile(filePath, []byte("test content"), 0644)
require.NoError(t, err)
// Should return true immediately (file already stable)
assert.True(t, scanner.waitForFileStability(filePath))
}
func TestWaitForFileStability_UnstableFile(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
// Create a file
tmpDir := t.TempDir()
filePath := filepath.Join(tmpDir, "unstable.epub")
file, err := os.Create(filePath)
require.NoError(t, err)
defer file.Close()
// Start stability check in background
stableChan := make(chan bool)
go func() {
stableChan <- scanner.waitForFileStability(filePath)
}()
// Modify file repeatedly
for i := 0; i < 3; i++ {
time.Sleep(100 * time.Millisecond)
file.WriteString("more data\n")
}
file.Close()
// Should eventually return true
select {
case stable := <-stableChan:
assert.True(t, stable)
case <-time.After(7 * time.Second):
t.Fatal("waitForFileStability timeout")
}
}
func TestProcessDirtyDirectories_BatchesScans(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/test/folder"}
ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
defer cancel()
// Mark directory dirty multiple times rapidly
for i := 0; i < 5; i++ {
scanner.markDirectoryDirty("/test/folder/subdir")
time.Sleep(100 * time.Millisecond)
}
go scanner.processDirtyDirectories(ctx)
// Should wait 10 seconds before processing
scanner.dirtyDirsMu.RLock()
count := len(scanner.dirtyDirs)
scanner.dirtyDirsMu.RUnlock()
assert.Equal(t, 1, count, "Directory should still be in dirty list")
// Wait for batch to complete
time.Sleep(15 * time.Second)
scanner.dirtyDirsMu.RLock()
count = len(scanner.dirtyDirs)
scanner.dirtyDirsMu.RUnlock()
assert.Equal(t, 0, count, "All dirty directories should be processed after 10s")
}
func TestSeedDirectoryMtimes(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
subDir := filepath.Join(tmpDir, "author")
require.NoError(t, os.Mkdir(subDir, 0755))
require.NoError(t, os.WriteFile(filepath.Join(subDir, "book.epub"), []byte("test"), 0644))
scanner.folders = []string{tmpDir}
scanner.seedDirectoryMtimes()
scanner.dirMtimesMu.RLock()
defer scanner.dirMtimesMu.RUnlock()
_, rootExists := scanner.dirMtimes[tmpDir]
_, subExists := scanner.dirMtimes[subDir]
assert.True(t, rootExists, "Root directory should be cached")
assert.True(t, subExists, "Subdirectory should be cached")
assert.Equal(t, 2, len(scanner.dirMtimes), "Should have exactly 2 directories cached")
}
func TestSeedDirectoryMtimes_SkipsNonexistentFolders(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
scanner.folders = []string{"/nonexistent/path"}
scanner.seedDirectoryMtimes()
scanner.dirMtimesMu.RLock()
count := len(scanner.dirMtimes)
scanner.dirMtimesMu.RUnlock()
assert.Equal(t, 0, count, "Nonexistent folder should produce empty cache")
}
func TestCheckDirectoryMtimes_DetectsNewDirectory(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
scanner.folders = []string{tmpDir}
scanner.seedDirectoryMtimes()
newDir := filepath.Join(tmpDir, "new_author")
require.NoError(t, os.Mkdir(newDir, 0755))
require.NoError(t, os.WriteFile(filepath.Join(newDir, "book.cbz"), []byte("test"), 0644))
scanner.checkDirectoryMtimes()
scanner.dirtyDirsMu.RLock()
_, dirty := scanner.dirtyDirs[newDir]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, dirty, "New directory should be marked dirty")
}
func TestCheckDirectoryMtimes_SkipsUnchangedDirectories(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
subDir := filepath.Join(tmpDir, "author")
require.NoError(t, os.Mkdir(subDir, 0755))
scanner.folders = []string{tmpDir}
scanner.seedDirectoryMtimes()
scanner.dirtyDirsMu.Lock()
scanner.dirtyDirs = make(map[string]time.Time)
scanner.dirtyDirsMu.Unlock()
scanner.checkDirectoryMtimes()
scanner.dirtyDirsMu.RLock()
count := len(scanner.dirtyDirs)
scanner.dirtyDirsMu.RUnlock()
assert.Equal(t, 0, count, "Unchanged directories should not be marked dirty")
}
func TestCheckDirectoryMtimes_DetectsModifiedDirectory(t *testing.T) {
db := setupTestDB(t)
scanner := NewMediaScanner(db)
tmpDir := t.TempDir()
subDir := filepath.Join(tmpDir, "author")
require.NoError(t, os.Mkdir(subDir, 0755))
scanner.folders = []string{tmpDir}
scanner.seedDirectoryMtimes()
time.Sleep(10 * time.Millisecond)
require.NoError(t, os.WriteFile(filepath.Join(subDir, "new_book.epub"), []byte("test"), 0644))
scanner.checkDirectoryMtimes()
scanner.dirtyDirsMu.RLock()
_, dirty := scanner.dirtyDirs[subDir]
scanner.dirtyDirsMu.RUnlock()
assert.True(t, dirty, "Modified directory should be marked dirty")
}