bookhoard/internal/services/media_scanner.go

package services

import (
	"archive/tar"
	"archive/zip"
	"bookhoard/internal/database"
	"bookhoard/internal/utils"
	"bytes"
	"compress/bzip2"
	"compress/gzip"
	"context"
	"crypto/sha256"
	"encoding/hex"
	"encoding/xml"
	"fmt"
	"image"
	_ "image/jpeg"
	_ "image/png"
	"io"
	"io/fs"
	"os"
	"path/filepath"
	"regexp"
	"strconv"
	"strings"
	"time"

	"bookhoard/internal/sevenzip"
	epub "github.com/ArcadiaLin/go-epub"
	"github.com/fsnotify/fsnotify"
	"github.com/jackc/pgx/v5"
	"github.com/jackc/pgx/v5/pgtype"
	"github.com/nwaples/rardecode"
	pdfcpuapi "github.com/pdfcpu/pdfcpu/pkg/api"
)

// MediaMetadata contains extracted metadata for media files (ebooks, comics, manga)
type MediaMetadata struct {
	Title        string
	Author       string
	Description  string
	Series       string
	SeriesNumber int32
	Publisher    string
	PublishDate  time.Time
	Contributors []string
	CoverPath    string
	ISBN         string
	ASIN         string
	Tags         []string

	FileHashInfo *HashInfo
	FileFormats  []*FormatInfo
}

type HashInfo struct {
	FileSHA256     string
	OPFIdentifier  string
	OPFUUID        string
	HashConfidence string
}

type FormatInfo struct {
	FormatType    string
	FilePath      string
	FileSHA256    string
	FileSizeBytes int64
	MimeType      string
}

// MediaScanner scans library folders for media files (ebooks, comics, manga)
type MediaScanner struct {
	db               *database.Queries
	watcher          *fsnotify.Watcher
	folders          []string
	adminID          pgtype.UUID
	defaultLibraryID pgtype.UUID
	libraryTypes     map[string][]string
	forceRescan      bool

	totalFiles int
	newItems   int
	errors     int
	job        *Job
}

// NewMediaScanner creates a new media scanner instance
func NewMediaScanner(db *database.Queries) *MediaScanner {
	watcher, err := fsnotify.NewWatcher()
	if err != nil {
		panic(fmt.Sprintf("Failed to create file watcher: %v", err))
	}

	return &MediaScanner{
		db:               db,
		watcher:          watcher,
		folders:          []string{},
		adminID:          pgtype.UUID{},
		defaultLibraryID: pgtype.UUID{Valid: false},
		libraryTypes:     make(map[string][]string),
	}
}

func (s *MediaScanner) SetAdminID(adminID pgtype.UUID) {
	s.adminID = adminID
}

func (s *MediaScanner) SetForce(force bool) {
	s.forceRescan = force
}

func (s *MediaScanner) GetStats() (int, int, int) {
	return s.totalFiles, s.newItems, s.errors
}

func (s *MediaScanner) SetFolders(folders []string) error {
	s.folders = folders

	// Remove old watch if exists
	if s.watcher != nil {
		s.watcher.Close()
	}

	// Create new watcher
	watcher, err := fsnotify.NewWatcher()
	if err != nil {
		return fmt.Errorf("failed to create watcher: %v", err)
	}
	s.watcher = watcher

	// Build cache of allowed extensions per folder
	s.libraryTypes = make(map[string][]string)
	ctx := context.Background()

	for _, folder := range folders {
		// Get library for this folder
		lib, err := s.db.GetLibraryByFolder(ctx, folder)
		if err != nil {
			fmt.Printf("Warning: failed to get library for folder %s: %v\n", folder, err)
			continue
		}

		// Get library type with allowed extensions
		libType, err := s.db.GetLibraryType(ctx, lib.LibraryTypeID)
		if err != nil {
			fmt.Printf("Warning: failed to get library type for %s: %v\n", folder, err)
			continue
		}

		// Cache allowed extensions for this folder
		s.libraryTypes[folder] = libType.AllowedExtensions
		fmt.Printf("Scanner: Folder %s (type: %s) allows extensions: %v\n",
			folder, libType.Name, libType.AllowedExtensions)
	}

	// Add all folders to watch
	for _, folder := range folders {
		if err := s.watcher.Add(folder); err != nil {
			fmt.Printf("Warning: failed to watch folder %s: %v\n", folder, err)
		}
	}

	return nil
}

func (s *MediaScanner) ScanFolders(ctx context.Context) error {
	if len(s.folders) == 0 {
		return fmt.Errorf("no folders set")
	}

	s.totalFiles = 0
	s.newItems = 0
	s.errors = 0

	for _, folder := range s.folders {
		filepath.WalkDir(folder, func(path string, d fs.DirEntry, err error) error {
			if !d.IsDir() && s.isScannableFile(path) {
				s.totalFiles++
			}
			return nil
		})
	}

	fmt.Printf("Starting scan of %d folders: %v (%d files to scan)\n", len(s.folders), s.folders, s.totalFiles)

	processedFiles := 0
	mediaFiles := 0

	for _, folder := range s.folders {
		fmt.Printf("Scanning folder: %s\n", folder)

		if _, err := os.Stat(folder); os.IsNotExist(err) {
			fmt.Printf("Folder does not exist: %s\n", folder)
			s.errors++
			continue
		}

		err := filepath.WalkDir(folder, func(path string, d fs.DirEntry, err error) error {
			if err != nil {
				fmt.Printf("Error accessing path %s: %v\n", path, err)
				s.errors++
				return err
			}

			if d.IsDir() {
				if err := s.watcher.Add(path); err != nil {
					fmt.Printf("Warning: failed to watch subdirectory %s: %v\n", path, err)
				}
				return nil
			}

			if s.isScannableFile(path) {
				mediaFiles++
				processedFiles++

				if processedFiles%10 == 0 && s.totalFiles > 0 {
					progress := float64(processedFiles) / float64(s.totalFiles)
					if s.job != nil {
						s.job.UpdateProgress(progress, processedFiles, s.newItems, s.errors)
					}
				}

				wasNew, err := s.processMediaFile(ctx, path)
				if err != nil {
					fmt.Printf("Error processing media file %s: %v\n", path, err)
					s.errors++
				} else if wasNew {
					fmt.Printf("Successfully processed media file: %s\n", path)
				} else {
					fmt.Printf("Successfully processed media file: %s\n", path)
				}
			}

			return nil
		})
		if err != nil {
			s.errors++
			return fmt.Errorf("failed to scan folder %s: %v", folder, err)
		}
	}

	fmt.Printf("Scan completed: %d total files scanned, %d media files found, %d new items, %d errors\n",
		processedFiles, mediaFiles, s.newItems, s.errors)

	if s.job != nil && s.totalFiles > 0 {
		s.job.UpdateProgress(1.0, processedFiles, s.newItems, s.errors)
	}

	return nil
}

func (s *MediaScanner) isScannableFile(path string) bool {
	ext := strings.ToLower(filepath.Ext(path))

	// Find which folder this file belongs to
	var folder string
	for _, f := range s.folders {
		if strings.HasPrefix(path, f) {
			folder = f
			break
		}
	}

	// If no folder match, don't scan
	if folder == "" {
		return false
	}

	// Get allowed extensions for this folder's library
	allowed, ok := s.libraryTypes[folder]
	if !ok {
		// No library type info, skip file
		fmt.Printf("Warning: No library type info for folder %s, skipping %s\n", folder, path)
		return false
	}

	// Check if file extension is allowed for this library type
	for _, allowedExt := range allowed {
		if ext == strings.ToLower(allowedExt) {
			return true
		}
	}

	return false
}

// extractFolderStructureMetadata extracts metadata from folder paths, prioritizing Calibre structure
func (s *MediaScanner) extractFolderStructureMetadata(path, rootFolder string) *MediaMetadata {
	metadata := &MediaMetadata{}

	// Get the relative path from root folder
	relPath, err := filepath.Rel(rootFolder, path)
	if err != nil {
		return metadata
	}

	// Split into directory components
	dir := filepath.Dir(relPath)
	components := strings.Split(dir, string(filepath.Separator))

	if len(components) < 2 {
		return metadata // Not enough structure to extract
	}

	// Calibre structure detection
	// Pattern 1: Author Name/Book Title/
	// Pattern 2: Author Name/Series Name/Book Title/
	// Pattern 3: Author Name/Series Name, Book #1 - Book Title/

	author := strings.TrimSuffix(components[0], "_") // Remove trailing underscore if present
	metadata.Author = strings.ReplaceAll(author, "_", " ")

	if len(components) >= 3 {
		// This might be a series structure
		possibleSeries := components[1]
		possibleTitle := components[2]

		// Check for Calibre series format: "Series Name, Book #1 - Title"
		seriesMatch := regexp.MustCompile(`^(.*),\s+Book\s+#(\d+)\s*-\s*(.*)$`).FindStringSubmatch(possibleSeries)
		if len(seriesMatch) == 4 {
			metadata.Series = strings.ReplaceAll(seriesMatch[1], "_", " ")
			if seriesNum, err := strconv.ParseInt(seriesMatch[2], 10, 32); err == nil {
				metadata.SeriesNumber = int32(seriesNum)
			}
			metadata.Title = strings.ReplaceAll(possibleTitle, "_", " ")
		} else {
			// Simple series structure: Author/Series/Title
			metadata.Series = strings.ReplaceAll(possibleSeries, "_", " ")
			metadata.Title = strings.ReplaceAll(possibleTitle, "_", " ")

			// Try to extract series number from title
			titleNumMatch := regexp.MustCompile(`^(.*)\s+(\d+)$`).FindStringSubmatch(metadata.Title)
			if len(titleNumMatch) == 3 {
				metadata.Title = titleNumMatch[1]
				if seriesNum, err := strconv.ParseInt(titleNumMatch[2], 10, 32); err == nil {
					metadata.SeriesNumber = int32(seriesNum)
				}
			}
		}
	} else {
		// Simple structure: Author/Title
		metadata.Title = strings.ReplaceAll(components[1], "_", " ")
	}

	return metadata
}

func (s *MediaScanner) processMediaFile(ctx context.Context, path string) (bool, error) {
	fmt.Printf("Processing media file: %s\n", path)

	// Get file info
	info, err := os.Stat(path)
	if err != nil {
		fmt.Printf("Failed to get file info for %s: %v\n", path, err)
		return false, fmt.Errorf("failed to get file info: %v", err)
	}

	fmt.Printf("File info for %s: size=%d\n", path, info.Size())

	// Check if media item already exists in database
	existingItem, err := s.getMediaItemByFilePath(ctx, path)
	if err == nil {
		fmt.Printf("Media item already exists in database: %s (size: %d vs %d)\n", path, existingItem.FileSize.Int64, info.Size())

		// If force rescan is enabled, always re-process
		if s.forceRescan {
			fmt.Printf("Force rescan enabled, re-processing existing media item: %s\n", path)
			// Force update: delete existing and re-create
			if err := s.db.DeleteMediaItem(ctx, existingItem.ID); err != nil {
				fmt.Printf("Warning: failed to delete existing media item: %v\n", err)
			}
			// Continue to create new entry below
		} else {
			// Normal behavior: check if file has changed (by size)
			if existingItem.FileSize.Int64 != info.Size() {
				fmt.Printf("File size changed, updating media item: %s\n", path)
				_ = s.updateMediaItem(ctx, existingItem.ID, path, info)
				return false, nil
			}
			fmt.Printf("Media item already exists with same size, skipping: %s\n", path)
			return false, nil
		}
	} else if err != pgx.ErrNoRows {
		fmt.Printf("Database error checking media item existence: %v\n", err)
		return false, fmt.Errorf("failed to check if media item exists: %v", err)
	}
	fmt.Printf("Media item does not exist in database, creating new entry: %s\n", path)

	// Extract metadata from file first
	metadata, err := s.extractMetadata(path)
	if err != nil {
		fmt.Printf("Warning: failed to extract metadata from %s: %v\n", path, err)
		metadata = &MediaMetadata{}
	}

	// Extract hash information during metadata extraction
	hashInfo, formatInfo, err := s.extractHashInfo(path)
	if err != nil {
		fmt.Printf("Warning: failed to extract hash info from %s: %v\n", path, err)
		hashInfo = &HashInfo{}
		formatInfo = &FormatInfo{}
	} else {
		metadata.FileHashInfo = hashInfo
		metadata.FileFormats = []*FormatInfo{formatInfo}
		fmt.Printf("Hash info for %s: SHA256=%s, OPF_ID=%s, OPF_UUID=%s, Confidence=%s\n",
			path, hashInfo.FileSHA256, hashInfo.OPFIdentifier, hashInfo.OPFUUID, hashInfo.HashConfidence)
	}

	var comicInfo *ComicInfo
	var coverImage []byte

	ext := strings.ToLower(filepath.Ext(path))
	if ext == ".cbz" || ext == ".cbr" || ext == ".cb7" || ext == ".cbt" ||
		strings.HasSuffix(strings.ToLower(path), ".tar.gz") ||
		strings.HasSuffix(strings.ToLower(path), ".tar.bz2") ||
		strings.HasSuffix(strings.ToLower(path), ".tgz") ||
		strings.HasSuffix(strings.ToLower(path), ".tbz2") {
		info, cover, err := extractComicMetadata(path)
		if err != nil {
			fmt.Printf("Warning: failed to extract comic metadata from %s: %v\n", path, err)
		} else {
			comicInfo = info
			coverImage = cover
			if comicInfo.Title != "" && metadata.Title == "" {
				metadata.Title = comicInfo.Title
			}
			if comicInfo.Series != "" && metadata.Series == "" {
				metadata.Series = comicInfo.Series
			}
			if comicInfo.Number > 0 && metadata.SeriesNumber == 0 {
				metadata.SeriesNumber = int32(comicInfo.Number)
			}
			if comicInfo.Publisher != "" && metadata.Publisher == "" {
				metadata.Publisher = comicInfo.Publisher
			}
			if comicInfo.Writer != "" && metadata.Author == "" {
				metadata.Author = comicInfo.Writer
			}
			if len(coverImage) > 0 && metadata.CoverPath == "" {
				coverPath := path + ".cover.jpg"
				if err := os.WriteFile(coverPath, coverImage, 0644); err == nil {
					metadata.CoverPath = coverPath
				}
			}
			fmt.Printf("Extracted comic metadata from %s: title=%s, series=%s, issue=%d\n",
				path, comicInfo.Title, comicInfo.Series, comicInfo.Number)
		}
	}

	// Try to get metadata from folder structure as fallback/enhancement
	// Use the root folder that contains this file
	var rootFolder string
	for _, folder := range s.folders {
		if strings.HasPrefix(path, folder) {
			rootFolder = folder
			break
		}
	}

	if rootFolder != "" {
		folderMetadata := s.extractFolderStructureMetadata(path, rootFolder)

		// Use folder metadata as fallback for missing information
		if metadata.Title == "" && folderMetadata.Title != "" {
			metadata.Title = folderMetadata.Title
		}
		if metadata.Author == "" && folderMetadata.Author != "" {
			metadata.Author = folderMetadata.Author
		}
		if metadata.Series == "" && folderMetadata.Series != "" {
			metadata.Series = folderMetadata.Series
		}
		if metadata.SeriesNumber == 0 && folderMetadata.SeriesNumber > 0 {
			metadata.SeriesNumber = folderMetadata.SeriesNumber
		}
	}

	// Final fallback if still missing essential metadata
	if metadata.Title == "" {
		metadata.Title = strings.TrimSuffix(filepath.Base(path), filepath.Ext(path))
	}
	if metadata.Author == "" {
		metadata.Author = "Unknown"
	}

	// Find library for this folder
	var libraryID pgtype.UUID
	for _, folder := range s.folders {
		if strings.HasPrefix(path, folder) {
			lib, err := s.db.GetLibraryByFolder(ctx, folder)
			if err != nil {
				return false, fmt.Errorf("failed to find library for folder %s: %v", folder, err)
			}
			libraryID = lib.LibraryID
			break
		}
	}

	if !libraryID.Valid {
		return false, fmt.Errorf("no library found for file path: %s", path)
	}

	// Normalize metadata fields for display
	metadata.Contributors = utils.NormalizeContributors(metadata.Contributors)
	metadata.Tags = utils.NormalizeTags(metadata.Tags)

	// Normalize search fields
	contributorsSearch := utils.NormalizeContributorsSearch(metadata.Contributors)
	tagsSearch := utils.NormalizeTagsSearch(metadata.Tags)

	// Create media item in database
	createdItem, err := s.db.CreateMediaItem(ctx, database.CreateMediaItemParams{
		LibraryID:          libraryID,
		Title:              metadata.Title,
		Author:             pgtype.Text{String: metadata.Author, Valid: metadata.Author != ""},
		Isbn:               pgtype.Text{String: utils.NormalizeISBNSafe(metadata.ISBN), Valid: metadata.ISBN != ""},
		Asin:               pgtype.Text{String: metadata.ASIN, Valid: metadata.ASIN != ""},
		Description:        pgtype.Text{String: metadata.Description, Valid: metadata.Description != ""},
		FilePath:           path,
		FileSize:           pgtype.Int8{Int64: info.Size(), Valid: true},
		MimeType:           pgtype.Text{String: s.getMimeType(path), Valid: true},
		CoverImagePath:     pgtype.Text{String: metadata.CoverPath, Valid: metadata.CoverPath != ""},
		Series:             pgtype.Text{String: metadata.Series, Valid: metadata.Series != ""},
		SeriesNumber:       pgtype.Int4{Int32: metadata.SeriesNumber, Valid: metadata.SeriesNumber > 0},
		Publisher:          pgtype.Text{String: metadata.Publisher, Valid: metadata.Publisher != ""},
		DatePublished:      pgtype.Date{Time: metadata.PublishDate, Valid: !metadata.PublishDate.IsZero()},
		Contributors:       metadata.Contributors,
		ContributorsSearch: contributorsSearch,
		Tags:               metadata.Tags,
		TagsSearch:         tagsSearch,
		AddedByAdminID:     s.adminID,
	})
	if err != nil {
		return false, fmt.Errorf("failed to create media item: %v", err)
	}

	// Update hash information before database storage
	if metadata.FileHashInfo != nil && metadata.FileHashInfo.FileSHA256 != "" {
		_, err = s.db.UpdateMediaItemIdentifiers(ctx, database.UpdateMediaItemIdentifiersParams{
			ID:             createdItem.ID,
			FileSha256:     pgtype.Text{String: metadata.FileHashInfo.FileSHA256, Valid: true},
			OpfIdentifier:  pgtype.Text{String: metadata.FileHashInfo.OPFIdentifier, Valid: metadata.FileHashInfo.OPFIdentifier != ""},
			OpfUuid:        pgtype.Text{String: metadata.FileHashInfo.OPFUUID, Valid: metadata.FileHashInfo.OPFUUID != ""},
			HashConfidence: pgtype.Text{String: metadata.FileHashInfo.HashConfidence, Valid: true},
		})
		if err != nil {
			fmt.Printf("Warning: failed to update hash identifiers for %s: %v\n", path, err)
		}
	}

	// Store format information in the database
	for _, format := range metadata.FileFormats {
		_, err = s.db.CreateMediaItemFormat(ctx, database.CreateMediaItemFormatParams{
			MediaItemID:   createdItem.ID,
			FormatType:    format.FormatType,
			FilePath:      pgtype.Text{String: format.FilePath, Valid: true},
			FileSha256:    pgtype.Text{String: format.FileSHA256, Valid: true},
			FileSizeBytes: pgtype.Int8{Int64: format.FileSizeBytes, Valid: true},
			MimeType:      pgtype.Text{String: format.MimeType, Valid: true},
		})
		if err != nil {
			fmt.Printf("Warning: failed to create format entry for %s: %v\n", path, err)
		}
	}

	s.newItems++
	return true, nil
}

func (s *MediaScanner) extractMetadata(path string) (*MediaMetadata, error) {
	ext := strings.ToLower(filepath.Ext(path))

	switch ext {
	case ".epub":
		metadata, err := s.extractEPUBMetadata(path)
		if err != nil {
			return metadata, err
		}
		// Try to extract embedded cover
		coverPath, err := s.extractEPUBCover(path)
		if err != nil {
			fmt.Printf("Warning: failed to extract EPUB cover from %s: %v\n", path, err)
		} else if coverPath != "" {
			metadata.CoverPath = coverPath
		}
		// If no embedded cover, try sidecar
		if metadata.CoverPath == "" {
			sidecarCover := findSidecarCover(path)
			if sidecarCover != "" {
				metadata.CoverPath = sidecarCover
			}
		}
		return metadata, nil
	case ".pdf":
		return s.extractPDFMetadata(path)
	default:
		// For other formats, return basic metadata
		return &MediaMetadata{
			Title: strings.TrimSuffix(filepath.Base(path), ext),
		}, nil
	}
}

func (s *MediaScanner) extractEPUBMetadata(path string) (*MediaMetadata, error) {
	book, err := epub.ReadBook(path)
	if err != nil {
		return nil, fmt.Errorf("failed to open EPUB: %v", err)
	}

	metadata := &MediaMetadata{}

	// Title
	if title, err := book.Title(); err == nil && title != "" {
		metadata.Title = title
	}

	// Author
	if authors, err := book.MetadataByKey("creator"); err == nil && len(authors) > 0 {
		metadata.Author = authors[0]
	}

	// Description
	if descriptions, err := book.MetadataByKey("description"); err == nil && len(descriptions) > 0 {
		metadata.Description = descriptions[0]
	}

	// Publisher
	if publishers, err := book.MetadataByKey("publisher"); err == nil && len(publishers) > 0 {
		metadata.Publisher = publishers[0]
	}

	// Series and series number (Calibre specific metadata)
	if series, err := book.MetadataByKey("calibre:series"); err == nil && len(series) > 0 {
		metadata.Series = series[0]
	}
	if seriesIndex, err := book.MetadataByKey("calibre:series_index"); err == nil && len(seriesIndex) > 0 {
		if index, err := strconv.ParseFloat(seriesIndex[0], 32); err == nil {
			metadata.SeriesNumber = int32(index)
		}
	}

	// Publish date
	if dates, err := book.MetadataByKey("date"); err == nil && len(dates) > 0 {
		if date, err := time.Parse("2006-01-02", dates[0]); err == nil {
			metadata.PublishDate = date
		} else {
			// Try alternative date formats
			if date, err := time.Parse("2006", dates[0]); err == nil {
				metadata.PublishDate = date
			}
		}
	}

	// Contributors
	if contributors, err := book.MetadataByKey("contributor"); err == nil && len(contributors) > 0 {
		// Normalize contributors for display
		metadata.Contributors = utils.NormalizeContributors(contributors)
	}

	// ISBN
	if isbns, err := book.MetadataByKey("identifier"); err == nil && len(isbns) > 0 {
		for _, isbn := range isbns {
			if strings.Contains(strings.ToLower(isbn), "isbn") {
				// Extract ISBN number from identifier like "isbn:978-3-16-148410-0"
				isbnParts := strings.SplitN(isbn, ":", 2)
				if len(isbnParts) == 2 {
					metadata.ISBN = isbnParts[1]
					break
				}
			}
			if strings.Contains(strings.ToLower(isbn), "asin") {
				// Extract ASIN from identifier like "asin:B08XXXXX"
				asinParts := strings.SplitN(isbn, ":", 2)
				if len(asinParts) == 2 {
					metadata.ASIN = asinParts[1]
				}
			}
		}
	}

	// Tags
	if tags, err := book.MetadataByKey("subject"); err == nil && len(tags) > 0 {
		// Normalize tags for display
		metadata.Tags = utils.NormalizeTags(tags)
	}

	return metadata, nil
}

// extractEPUBCover extracts the cover image from an EPUB file.
// It looks for:
// 1. An item with properties="cover-image" in the manifest
// 2. A meta tag with name="cover" pointing to an image
// 3. Common cover image paths like cover.jpg, cover.jpeg, cover.png
// Returns the path to the saved cover image, or empty string if no cover found.
func (s *MediaScanner) extractEPUBCover(epubPath string) (string, error) {
	// Open the EPUB as a zip file to extract images
	r, err := zip.OpenReader(epubPath)
	if err != nil {
		return "", fmt.Errorf("failed to open EPUB as zip: %v", err)
	}
	defer r.Close()

	// Try to find cover image from OPF metadata
	coverImageName := ""

	// Attempt to read the OPF file to find cover reference
	// First, find container.xml to locate the OPF
	var opfPath string
	for _, f := range r.File {
		if f.Name == "META-INF/container.xml" {
			rc, err := f.Open()
			if err != nil {
				continue
			}
			content, err := io.ReadAll(rc)
			rc.Close()
			if err != nil {
				continue
			}
			// Parse container.xml to find OPF path
			// Simple string search since we just need the path
			opfStart := bytes.Index(content, []byte("<rootfile "))
			if opfStart == -1 {
				continue
			}
			opfStartAttr := bytes.Index(content[opfStart:], []byte("full-path="))
			if opfStartAttr == -1 {
				continue
			}
			opfStartAttr += len("full-path=")
			quote := content[opfStart+opfStartAttr]
			opfStartQuote := opfStart + opfStartAttr + 1
			opfEndQuote := bytes.Index(content[opfStartQuote:], []byte{byte(quote)})
			if opfEndQuote == -1 {
				continue
			}
			opfPath = string(content[opfStartQuote : opfStartQuote+opfEndQuote])
			break
		}
	}

	if opfPath == "" {
		// No OPF found, try common cover image paths
		coverImageName = findCoverImageInZip(r.File)
	} else {
		// Read OPF to find cover reference
		opfContent, err := readFileFromZip(r.File, opfPath)
		if err != nil {
			// Fall back to common paths
			coverImageName = findCoverImageInZip(r.File)
		} else {
			coverImageName = findCoverInOPF(opfContent, r.File, opfPath)
		}
	}

	if coverImageName == "" {
		return "", nil // No cover found
	}

	// Extract the cover image
	coverImage, err := extractImageFromZip(r.File, coverImageName, opfPath)
	if err != nil {
		return "", fmt.Errorf("failed to extract cover image: %v", err)
	}
	if len(coverImage) == 0 {
		return "", nil
	}

	// Save cover to disk (same pattern as comics: {book_path}.cover.jpg)
	coverPath := epubPath + ".cover.jpg"
	if err := os.WriteFile(coverPath, coverImage, 0644); err != nil {
		return "", fmt.Errorf("failed to write cover file: %v", err)
	}

	return coverPath, nil
}

// findCoverImageInZip searches for common cover image filenames in the zip
func findCoverImageInZip(files []*zip.File) string {
	coverNames := []string{"cover.jpg", "cover.jpeg", "cover.png", "cover.webp",
		"Cover.jpg", "Cover.jpeg", "Cover.png", "Cover.webp",
		"images/cover.jpg", "Images/cover.jpg", "OEBPS/images/cover.jpg"}

	for _, name := range coverNames {
		for _, f := range files {
			if strings.ToLower(f.Name) == strings.ToLower(name) {
				return f.Name
			}
		}
	}
	return ""
}

// findCoverInOPF parses OPF content to find cover image reference
func findCoverInOPF(opfContent []byte, files []*zip.File, opfDir string) string {
	contentStr := string(opfContent)

	// Look for item with properties="cover-image"
	coverImageRE := regexp.MustCompile(`<item[^>]*properties="[^"]*cover-image[^"]*"[^>]*id="([^"]+)"`)
	matches := coverImageRE.FindStringSubmatch(contentStr)
	if len(matches) > 1 {
		coverID := matches[1]
		// Find the href for this ID
		hrefRE := regexp.MustCompile(fmt.Sprintf(`<item[^>]*id="%s"[^>]*href="([^"]+)"`, coverID))
		hrefMatches := hrefRE.FindStringSubmatch(contentStr)
		if len(hrefMatches) > 1 {
			return resolveOPFPath(opfDir, hrefMatches[1])
		}
	}

	// Look for meta name="cover"
	metaCoverRE := regexp.MustCompile(`<meta[^>]*name="cover"[^>]*content="([^"]+)"`)
	metaMatches := metaCoverRE.FindStringSubmatch(contentStr)
	if len(metaMatches) > 1 {
		coverContent := metaMatches[1]
		// Could be "image-id" format
		if strings.HasPrefix(coverContent, "image-") {
			coverID := strings.TrimPrefix(coverContent, "image-")
			hrefRE := regexp.MustCompile(fmt.Sprintf(`<item[^>]*id="%s"[^>]*href="([^"]+)"`, coverID))
			hrefMatches := hrefRE.FindStringSubmatch(contentStr)
			if len(hrefMatches) > 1 {
				return resolveOPFPath(opfDir, hrefMatches[1])
			}
		}
	}

	// Fall back to searching common paths
	return findCoverImageInZip(files)
}

// resolveOPFPath resolves a relative path against the OPF directory
func resolveOPFPath(opfDir, href string) string {
	if opfDir == "" {
		return href
	}
	// Handle ../ in href
	if strings.HasPrefix(href, "../") {
		// Simple case: just use the href as-is for now
		return href
	}
	// Join the directory with the href
	return filepath.Join(filepath.Dir(opfDir), href)
}

// readFileFromZip reads a file from the zip by name
func readFileFromZip(files []*zip.File, name string) ([]byte, error) {
	// Normalize the name for comparison
	name = filepath.ToSlash(name)
	for _, f := range files {
		fName := filepath.ToSlash(f.Name)
		if fName == name {
			rc, err := f.Open()
			if err != nil {
				return nil, err
			}
			defer rc.Close()
			return io.ReadAll(rc)
		}
	}
	return nil, fmt.Errorf("file not found: %s", name)
}

// extractImageFromZip extracts an image file and returns its contents
func extractImageFromZip(files []*zip.File, imagePath, opfDir string) ([]byte, error) {
	// Try direct match first
	for _, f := range files {
		if strings.ToLower(f.Name) == strings.ToLower(imagePath) {
			rc, err := f.Open()
			if err != nil {
				return nil, err
			}
			defer rc.Close()
			return io.ReadAll(rc)
		}
	}

	// Try resolved path
	resolvedPath := resolveOPFPath(opfDir, imagePath)
	for _, f := range files {
		if strings.ToLower(f.Name) == strings.ToLower(resolvedPath) {
			rc, err := f.Open()
			if err != nil {
				return nil, err
			}
			defer rc.Close()
			return io.ReadAll(rc)
		}
	}

	return nil, fmt.Errorf("image not found: %s", imagePath)
}

// findSidecarCover looks for cover images in the same directory as the media file.
// It checks for common cover filename patterns in priority order:
// 1. cover.jpg, cover.jpeg, cover.png, cover.webp
// 2. folder.jpg, folder.jpeg, folder.png, folder.webp
// 3. {basename}.jpg, {basename}.jpeg, etc. (same name as media file)
// 4. .folder.jpg (hidden file)
// Returns the full path to the cover file, or empty string if not found.
func findSidecarCover(mediaPath string) string {
	dir := filepath.Dir(mediaPath)
	baseName := strings.TrimSuffix(filepath.Base(mediaPath), filepath.Ext(mediaPath))

	// Priority order for cover filenames
	coverPatterns := []string{
		"cover.jpg",
		"cover.jpeg",
		"cover.png",
		"cover.webp",
		"folder.jpg",
		"folder.jpeg",
		"folder.png",
		"folder.webp",
		".folder.jpg",
		".folder.jpeg",
		".folder.png",
	}

	// First, check exact match cover/folder names
	for _, coverName := range coverPatterns {
		coverPath := filepath.Join(dir, coverName)
		if _, err := os.Stat(coverPath); err == nil {
			return coverPath
		}
	}

	// Second, check for {basename}.{ext} pattern
	extensions := []string{".jpg", ".jpeg", ".png", ".webp"}
	for _, ext := range extensions {
		coverPath := filepath.Join(dir, baseName+ext)
		if _, err := os.Stat(coverPath); err == nil {
			return coverPath
		}
		// Also check uppercase extension
		coverPathUpper := filepath.Join(dir, baseName+strings.ToUpper(ext))
		if _, err := os.Stat(coverPathUpper); err == nil {
			return coverPathUpper
		}
	}

	return ""
}

func (s *MediaScanner) extractPDFMetadata(path string) (*MediaMetadata, error) {
	metadata := &MediaMetadata{}

	// Open PDF file for reading metadata
	f, err := os.Open(path)
	if err != nil {
		fmt.Printf("Warning: failed to open PDF file %s: %v\n", path, err)
		metadata.Title = strings.TrimSuffix(filepath.Base(path), ".pdf")
		return metadata, nil
	}
	defer f.Close()

	// Use pdfcpu API to read PDF metadata
	// Configuration: nil = default (lenient mode)
	pdfInfo, err := pdfcpuapi.PDFInfo(f, filepath.Base(path), nil, nil)
	if err != nil {
		fmt.Printf("Warning: failed to read PDF info from %s: %v\n", path, err)
		// Fall back to filename as title
		metadata.Title = strings.TrimSuffix(filepath.Base(path), ".pdf")
		return metadata, nil
	}

	// Extract title
	if pdfInfo.Title != "" {
		metadata.Title = pdfInfo.Title
	} else {
		metadata.Title = strings.TrimSuffix(filepath.Base(path), ".pdf")
	}

	// Extract author
	if pdfInfo.Author != "" {
		metadata.Author = pdfInfo.Author
	}

	// Extract subject (use as description)
	if pdfInfo.Subject != "" {
		metadata.Description = pdfInfo.Subject
	}

	// Extract creator (use as author fallback)
	if pdfInfo.Creator != "" && metadata.Author == "" {
		metadata.Author = pdfInfo.Creator
	}

	// Extract producer (use as publisher)
	if pdfInfo.Producer != "" {
		metadata.Publisher = pdfInfo.Producer
	}

	// Try to extract cover image
	coverPath, err := s.extractPDFCover(path)
	if err != nil {
		fmt.Printf("Warning: failed to extract PDF cover from %s: %v\n", path, err)
	} else if coverPath != "" {
		metadata.CoverPath = coverPath
	}

	// If no embedded cover, try sidecar
	if metadata.CoverPath == "" {
		sidecarCover := findSidecarCover(path)
		if sidecarCover != "" {
			metadata.CoverPath = sidecarCover
		}
	}

	return metadata, nil
}

// extractPDFCover extracts a cover image from a PDF file.
// It uses pdfcpu API to extract images from the first page.
// Returns the path to the saved cover, or empty string if no cover found.
func (s *MediaScanner) extractPDFCover(pdfPath string) (string, error) {
	// Create a temporary directory for extracted images
	tmpDir, err := os.MkdirTemp("", "pdf-cover-")
	if err != nil {
		return "", fmt.Errorf("failed to create temp dir: %v", err)
	}
	defer os.RemoveAll(tmpDir)

	// Use pdfcpu API to extract images from first page
	// ExtractImagesFile(inFile, outDir string, selectedPages []string, conf *model.Configuration) error
	err = pdfcpuapi.ExtractImagesFile(pdfPath, tmpDir, []string{"1"}, nil)
	if err != nil {
		// No images found or extraction failed - this is OK, just return empty
		return "", nil
	}

	// Check for extracted images in the temp directory
	entries, err := os.ReadDir(tmpDir)
	if err != nil || len(entries) == 0 {
		return "", nil
	}

	// Find the largest image (likely the cover)
	var largestImage string
	var largestSize int64

	for _, entry := range entries {
		if entry.IsDir() {
			continue
		}
		info, err := entry.Info()
		if err != nil {
			continue
		}
		// Skip very small files (likely thumbnails or icons)
		if info.Size() < 1000 {
			continue
		}
		if info.Size() > largestSize {
			largestImage = filepath.Join(tmpDir, entry.Name())
			largestSize = info.Size()
		}
	}

	if largestImage == "" {
		return "", nil
	}

	// Read the image
	imageData, err := os.ReadFile(largestImage)
	if err != nil || len(imageData) == 0 {
		return "", nil
	}

	// Save cover to disk (same pattern as comics: {pdf_path}.cover.jpg)
	coverPath := pdfPath + ".cover.jpg"
	if err := os.WriteFile(coverPath, imageData, 0644); err != nil {
		return "", fmt.Errorf("failed to write cover file: %v", err)
	}

	return coverPath, nil
}

// ComicInfo represents metadata from ComicInfo.xml
type ComicInfo struct {
	XMLName     xml.Name `xml:"ComicInfo"`
	Title       string   `xml:"Title"`
	Series      string   `xml:"Series"`
	Number      int      `xml:"Number"`
	Volume      int      `xml:"Volume"`
	Publisher   string   `xml:"Publisher"`
	Year        int      `xml:"Year"`
	Month       int      `xml:"Month"`
	Day         int      `xml:"Day"`
	Writer      string   `xml:"Writer"`
	Penciller   string   `xml:"Penciller"`
	Inker       string   `xml:"Inker"`
	Colorist    string   `xml:"Colorist"`
	Letterer    string   `xml:"Letterer"`
	CoverArtist string   `xml:"CoverArtist"`
	Genre       string   `xml:"Genre"`
	Tags        string   `xml:"Tags"`
	Web         string   `xml:"Web"`
	Notes       string   `xml:"Notes"`
}

// extractComicMetadata extracts metadata from comic archive (supports .cbz, .cbr, .cb7, .cbt)
func extractComicMetadata(filePath string) (*ComicInfo, []byte, error) {
	ext := strings.ToLower(filepath.Ext(filePath))

	switch ext {
	case ".cbz":
		return extractZipMetadata(filePath)
	case ".cbr":
		return extractRarMetadata(filePath)
	case ".cb7":
		return extract7ZipMetadata(filePath)
	case ".cbt":
		return extractTarMetadata(filePath)
	default:
		return nil, nil, fmt.Errorf("unsupported comic format: %s", ext)
	}
}

// archiveFile represents a file in an archive for uniform handling
type archiveFile interface {
	Name() string
	Open() (io.ReadCloser, error)
}

// extractMetadataFromArchive extracts ComicInfo.xml and cover image from any archive format
func extractMetadataFromArchive(files []archiveFile) (*ComicInfo, []byte, error) {
	var comicInfo *ComicInfo
	var coverImage []byte

	for _, f := range files {
		if f.Name() == "ComicInfo.xml" {
			rc, err := f.Open()
			if err != nil {
				return nil, nil, fmt.Errorf("failed to open ComicInfo.xml: %w", err)
			}

			data, err := io.ReadAll(rc)
			rc.Close()
			if err != nil {
				return nil, nil, fmt.Errorf("failed to read ComicInfo.xml: %w", err)
			}

			comicInfo = &ComicInfo{}
			if err := xml.Unmarshal(data, comicInfo); err != nil {
				return nil, nil, fmt.Errorf("failed to parse ComicInfo.xml: %w", err)
			}
		}

		if coverImage == nil && isImageFile(f.Name()) {
			if !strings.Contains(filepath.Dir(f.Name()), string(filepath.Separator)) ||
				filepath.Dir(f.Name()) == "." {
				rc, err := f.Open()
				if err != nil {
					continue
				}

				coverImage, err = io.ReadAll(rc)
				rc.Close()
				if err == nil {
					_, _, err = image.Decode(bytes.NewReader(coverImage))
					if err != nil {
						coverImage = nil
					}
				}
			}
		}
	}

	if comicInfo == nil {
		comicInfo = &ComicInfo{}
	}

	return comicInfo, coverImage, nil
}

// extractZipMetadata extracts metadata from ZIP archives (.cbz)
func extractZipMetadata(filePath string) (*ComicInfo, []byte, error) {
	r, err := zip.OpenReader(filePath)
	if err != nil {
		return nil, nil, fmt.Errorf("failed to open ZIP archive: %w", err)
	}
	defer r.Close()

	files := make([]archiveFile, 0, len(r.File))
	for _, f := range r.File {
		files = append(files, &zipFileAdapter{f})
	}

	comicInfo, coverImage, err := extractMetadataFromArchive(files)
	if err != nil {
		return nil, nil, err
	}

	if comicInfo.Title == "" {
		basename := filepath.Base(filePath)
		comicInfo.Title = strings.TrimSuffix(basename, filepath.Ext(basename))
	}

	return comicInfo, coverImage, nil
}

// zipFileAdapter adapts zip.File to archiveFile interface
type zipFileAdapter struct {
	*zip.File
}

func (z *zipFileAdapter) Name() string {
	return z.File.Name
}

func (z *zipFileAdapter) Open() (io.ReadCloser, error) {
	return z.File.Open()
}

// extractRarMetadata extracts metadata from RAR archives (.cbr)
func extractRarMetadata(filePath string) (*ComicInfo, []byte, error) {
	r, err := rardecode.OpenReader(filePath, "")
	if err != nil {
		return nil, nil, fmt.Errorf("failed to open RAR archive: %w", err)
	}
	defer r.Close()

	files := make([]archiveFile, 0, 100)
	for {
		header, err := r.Next()
		if err == io.EOF {
			break
		}
		if err != nil {
			return nil, nil, fmt.Errorf("failed to read RAR entry: %w", err)
		}

		data, err := io.ReadAll(r)
		if err != nil {
			continue
		}
		files = append(files, &rarFileAdapter{
			name: header.Name,
			data: data,
		})
	}

	comicInfo, coverImage, err := extractMetadataFromArchive(files)
	if err != nil {
		return nil, nil, err
	}

	if comicInfo.Title == "" {
		basename := filepath.Base(filePath)
		comicInfo.Title = strings.TrimSuffix(basename, filepath.Ext(basename))
	}

	return comicInfo, coverImage, nil
}

// rarFileAdapter stores RAR file data in memory
type rarFileAdapter struct {
	name string
	data []byte
}

func (r *rarFileAdapter) Name() string {
	return r.name
}

func (r *rarFileAdapter) Open() (io.ReadCloser, error) {
	return io.NopCloser(bytes.NewReader(r.data)), nil
}

// extract7ZipMetadata extracts metadata from 7-Zip archives (.cb7)
func extract7ZipMetadata(filePath string) (*ComicInfo, []byte, error) {
	r, err := sevenzip.OpenReader(filePath)
	if err != nil {
		return nil, nil, fmt.Errorf("failed to open 7-Zip archive: %w", err)
	}
	defer r.Close()

	files := make([]archiveFile, 0, len(r.File))
	for _, f := range r.File {
		files = append(files, &sevenZipFileAdapter{file: f})
	}

	comicInfo, coverImage, err := extractMetadataFromArchive(files)
	if err != nil {
		return nil, nil, err
	}

	if comicInfo.Title == "" {
		basename := filepath.Base(filePath)
		comicInfo.Title = strings.TrimSuffix(basename, filepath.Ext(basename))
	}

	return comicInfo, coverImage, nil
}

// sevenZipFileAdapter adapts sevenzip.File to archiveFile interface
type sevenZipFileAdapter struct {
	file *sevenzip.File
}

func (s *sevenZipFileAdapter) Name() string {
	return s.file.Name
}

func (s *sevenZipFileAdapter) Open() (io.ReadCloser, error) {
	return s.file.Open()
}

// extractTarMetadata extracts metadata from TAR archives (.cbt)
func extractTarMetadata(filePath string) (*ComicInfo, []byte, error) {
	f, err := os.Open(filePath)
	if err != nil {
		return nil, nil, fmt.Errorf("failed to open TAR archive: %w", err)
	}
	defer f.Close()

	var tarReader *tar.Reader
	if strings.HasSuffix(strings.ToLower(filePath), ".tar.gz") ||
		strings.HasSuffix(strings.ToLower(filePath), ".tgz") {
		gzReader, err := gzip.NewReader(f)
		if err != nil {
			return nil, nil, fmt.Errorf("failed to create gzip reader: %w", err)
		}
		defer gzReader.Close()
		tarReader = tar.NewReader(gzReader)
	} else if strings.HasSuffix(strings.ToLower(filePath), ".tar.bz2") ||
		strings.HasSuffix(strings.ToLower(filePath), ".tbz2") {
		bz2Reader := bzip2.NewReader(f)
		tarReader = tar.NewReader(bz2Reader)
	} else {
		tarReader = tar.NewReader(f)
	}

	files := make([]archiveFile, 0, 100)
	for {
		header, err := tarReader.Next()
		if err == io.EOF {
			break
		}
		if err != nil {
			return nil, nil, fmt.Errorf("failed to read TAR entry: %w", err)
		}

		if header.Typeflag == tar.TypeReg {
			data, err := io.ReadAll(tarReader)
			if err != nil {
				continue
			}
			files = append(files, &tarFileAdapter{
				name: header.Name,
				data: data,
			})
		}
	}

	comicInfo, coverImage, err := extractMetadataFromArchive(files)
	if err != nil {
		return nil, nil, err
	}

	if comicInfo.Title == "" {
		basename := filepath.Base(filePath)
		comicInfo.Title = strings.TrimSuffix(basename, filepath.Ext(basename))
	}

	return comicInfo, coverImage, nil
}

// tarFileAdapter stores TAR file data in memory
type tarFileAdapter struct {
	name string
	data []byte
}

func (t *tarFileAdapter) Name() string {
	return t.name
}

func (t *tarFileAdapter) Open() (io.ReadCloser, error) {
	return io.NopCloser(bytes.NewReader(t.data)), nil
}

// isImageFile checks if a file is an image based on extension
func isImageFile(filename string) bool {
	ext := strings.ToLower(filepath.Ext(filename))
	return ext == ".jpg" || ext == ".jpeg" || ext == ".png" || ext == ".gif"
}

func (s *MediaScanner) updateMediaItem(ctx context.Context, mediaItemID pgtype.UUID, filePath string, info os.FileInfo) error {
	// Update disabled - scanner creates items but doesn't update
	return nil
}

func (s *MediaScanner) getMediaItemByFilePath(ctx context.Context, filePath string) (database.MediaItems, error) {
	return s.db.GetMediaItemByFilePath(ctx, filePath)
}

func (s *MediaScanner) getMimeType(path string) string {
	ext := strings.ToLower(filepath.Ext(path))
	switch ext {
	case ".epub":
		return "application/epub+zip"
	case ".pdf":
		return "application/pdf"
	case ".mobi":
		return "application/x-mobipocket-ebook"
	case ".azw3":
		return "application/vnd.amazon.ebook"
	case ".fb2":
		return "application/x-fictionbook+xml"
	case ".txt":
		return "text/plain"
	case ".cbz":
		return "application/vnd.comicbook+zip"
	case ".cbr":
		return "application/vnd.comicbook-rar"
	case ".cb7":
		return "application/x-7z-compressed"
	case ".cbt":
		return "application/x-tar"
	default:
		return "application/octet-stream"
	}
}

func (s *MediaScanner) WatchChanges(ctx context.Context) {
	go func() {
		for {
			select {
			case event, ok := <-s.watcher.Events:
				if !ok {
					return
				}

				// Handle new directories - add them to the watcher
				if event.Has(fsnotify.Create) {
					info, err := os.Stat(event.Name)
					if err == nil && info.IsDir() {
						// Add the new directory to the watcher
						if err := s.watcher.Add(event.Name); err != nil {
							fmt.Printf("Warning: failed to watch new directory %s: %v\n", event.Name, err)
						} else {
							fmt.Printf("Now watching new directory: %s\n", event.Name)
						}
					}
				}

				// Handle file modifications and creations
				if (event.Has(fsnotify.Create) || event.Has(fsnotify.Write)) && s.isScannableFile(event.Name) {
					fmt.Printf("New/modified media file detected: %s\n", event.Name)
					if _, err := s.processMediaFile(ctx, event.Name); err != nil {
						fmt.Printf("Error processing modified media file %s: %v\n", event.Name, err)
					}
				}

			case err, ok := <-s.watcher.Errors:
				if !ok {
					return
				}
				fmt.Printf("Watcher error: %v\n", err)
			case <-ctx.Done():
				return
			}
		}
	}()
}

func (s *MediaScanner) Close() error {
	if s.watcher != nil {
		return s.watcher.Close()
	}
	return nil
}

// ============================================
// SCANNER ENHANCEMENTS
// ============================================

// calculateFileSHA256 calculates SHA-256 hash using streaming to avoid loading entire file into memory
func (s *MediaScanner) calculateFileSHA256(filePath string) (string, error) {
	file, err := os.Open(filePath)
	if err != nil {
		return "", fmt.Errorf("failed to open file: %v", err)
	}
	defer file.Close()

	hasher := sha256.New()
	if _, err := io.Copy(hasher, file); err != nil {
		return "", fmt.Errorf("failed to calculate hash: %v", err)
	}

	return hex.EncodeToString(hasher.Sum(nil)), nil
}

// OPFIdentifier represents an identifier from OPF metadata
type OPFIdentifier struct {
	XMLName xml.Name `xml:"identifier"`
	ID      string   `xml:"id,attr"`
	Scheme  string   `xml:"scheme,attr"`
	Content string   `xml:",chardata"`
}

// OPFMetadata represents parsed OPF metadata
type OPFMetadata struct {
	XMLName     xml.Name        `xml:"package"`
	Version     string          `xml:"version,attr"`
	Identifiers []OPFIdentifier `xml:"metadata>identifier"`
}

// extractOPFIdentifiers extracts identifiers from EPUB OPF file
func (s *MediaScanner) extractOPFIdentifiers(epubPath string) (opfIdentifier, opfUUID string, confidence string, err error) {
	book, err := epub.ReadBook(epubPath)
	if err != nil {
		return "", "", "", fmt.Errorf("failed to open EPUB: %v", err)
	}

	// Extract OPF identifiers using go-epub library
	identifiers, err := book.MetadataByKey("identifier")
	if err != nil || len(identifiers) == 0 {
		return "", "", "low", nil
	}

	var identifier, uuid string
	for _, id := range identifiers {
		id = strings.TrimSpace(id)

		// Check for UUID format (urn:uuid:)
		if strings.HasPrefix(strings.ToLower(id), "urn:uuid:") {
			uuid = strings.TrimPrefix(strings.ToLower(id), "urn:uuid:")
			continue
		}

		// Check if it's a plain UUID (8-4-4-4-12 format)
		if isValidUUID(id) {
			uuid = id
			continue
		}

		// Check for ISBN
		if strings.Contains(strings.ToLower(id), "isbn") {
			isbn := s.extractISBNFromIdentifier(id)
			if isbn != "" {
				identifier = isbn
				continue
			}
		}

		// Use first identifier as fallback
		if identifier == "" && id != "" {
			identifier = id
		}
	}

	confidence = s.determineHashConfidence(uuid, identifier)

	return identifier, uuid, confidence, nil
}

// isValidUUID checks if string is a valid UUID (8-4-4-4-12 format)
func isValidUUID(idStr string) bool {
	uuidRegex := regexp.MustCompile(`^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}$`)
	return uuidRegex.MatchString(idStr)
}

// extractISBNFromIdentifier extracts ISBN from identifier string
func (s *MediaScanner) extractISBNFromIdentifier(id string) string {
	id = strings.TrimSpace(id)

	// Remove "isbn:" prefix if present
	if strings.HasPrefix(strings.ToLower(id), "isbn:") {
		id = strings.TrimPrefix(strings.ToLower(id), "isbn:")
	}

	// Remove hyphens and spaces
	isbn := regexp.MustCompile(`[\s-]`).ReplaceAllString(id, "")

	// Check if it's a valid ISBN-10 or ISBN-13
	if len(isbn) == 10 || len(isbn) == 13 {
		return isbn
	}

	return ""
}

// determineHashConfidence determines confidence level based on available identifiers
func (s *MediaScanner) determineHashConfidence(uuid, identifier string) string {
	if uuid != "" && isValidUUID(uuid) {
		return "high"
	}
	if identifier != "" && (strings.Contains(strings.ToLower(identifier), "isbn") || len(identifier) >= 10) {
		return "medium"
	}
	return "low"
}

// detectFormatType detects the format type based on file extension and content
func (s *MediaScanner) detectFormatType(filePath string) string {
	base := strings.ToLower(filepath.Base(filePath))

	// Check for compound extensions first (like .kepub.epub)
	if strings.HasSuffix(base, ".kepub.epub") {
		return "kepub"
	}

	ext := strings.ToLower(filepath.Ext(filePath))

	switch ext {
	case ".epub":
		return "epub"
	case ".kepub":
		return "kepub"
	case ".pdf":
		return "pdf"
	case ".cbz", ".cbr", ".cb7", ".cbt":
		return "comic_archive"
	case ".mobi":
		return "mobi"
	case ".azw", ".azw3":
		return "kfx"
	case ".txt":
		return "txt"
	case ".fb2":
		return "fb2"
	default:
		return "unknown"
	}
}

// extractHashInfo calculates hash and extracts OPF identifiers for a file
func (s *MediaScanner) extractHashInfo(filePath string) (*HashInfo, *FormatInfo, error) {
	// Calculate SHA-256
	fileSHA256, err := s.calculateFileSHA256(filePath)
	if err != nil {
		return nil, nil, fmt.Errorf("failed to calculate SHA-256: %v", err)
	}

	// Get file info
	info, err := os.Stat(filePath)
	if err != nil {
		return nil, nil, fmt.Errorf("failed to get file info: %v", err)
	}

	// Extract OPF identifiers for EPUB files
	var opfIdentifier, opfUUID, confidence string
	if strings.HasSuffix(strings.ToLower(filePath), ".epub") {
		opfIdentifier, opfUUID, confidence, err = s.extractOPFIdentifiers(filePath)
		if err != nil {
			// Non-fatal error, continue with low confidence
			confidence = "low"
		}
	}

	hashInfo := &HashInfo{
		FileSHA256:     fileSHA256,
		OPFIdentifier:  opfIdentifier,
		OPFUUID:        opfUUID,
		HashConfidence: confidence,
	}

	formatInfo := &FormatInfo{
		FormatType:    s.detectFormatType(filePath),
		FilePath:      filePath,
		FileSHA256:    fileSHA256,
		FileSizeBytes: info.Size(),
		MimeType:      s.getMimeType(filePath),
	}

	return hashInfo, formatInfo, nil
}