feat(scanner): read Audiobookshelf metadata.json sidecars

Libraries managed by Audiobookshelf keep a metadata.json next to each book (title, authors, series+sequence, genres/tags, publisher, description, isbn/asin, language, published year/date) - and no metadata.opf. The scanner silently ignored those files: deleting them changed nothing, and their data never reached the database. Parse them as a first-class sidecar in extractMetadata, priority metadata.opf -> metadata.json -> embedded media. Only fields with a matching media_items column are mapped; narrators, subtitle, explicit, abridged, and chapters are deliberately skipped. Cover handling is unchanged: the existing findSidecarCover priority (cover.jpg / folder.jpg / {basename}.jpg) applies to the sidecar branch exactly as it does for Calibre.
2026-09-12 17:49:46 -04:00
parent 61681aac23
commit 44b98f3fc3
2 changed files with 177 additions and 1 deletions
@@ -958,6 +958,88 @@ func (s *MediaScanner) extractCalibreSidecar(path string) *MediaMetadata {
 	return metadata
 }

+// extractAudiobookshelfSidecar checks for and parses an Audiobookshelf-style
+// metadata.json sidecar next to the media file. Only fields with a matching
+// media_items column are mapped; narrators, subtitle, explicit, abridged and
+// chapters are deliberately skipped. Returns nil when no sidecar exists.
+func extractAudiobookshelfSidecar(path string) *MediaMetadata {
+	jsonPath := filepath.Join(filepath.Dir(path), "metadata.json")
+	if _, err := os.Stat(jsonPath); os.IsNotExist(err) {
+		return nil
+	}
+
+	data, err := os.ReadFile(jsonPath)
+	if err != nil {
+		fmt.Printf("Warning: failed to read metadata.json sidecar for %s: %v\n", path, err)
+		return nil
+	}
+
+	var sidecar struct {
+		Title   string   `json:"title"`
+		Authors []string `json:"authors"`
+		Series  []struct {
+			Series   string `json:"series"`
+			Sequence string `json:"sequence"`
+		} `json:"series"`
+		Genres        []string `json:"genres"`
+		Tags          []string `json:"tags"`
+		PublishedYear *int     `json:"publishedYear"`
+		PublishedDate *string  `json:"publishedDate"`
+		Publisher     *string  `json:"publisher"`
+		Description   *string  `json:"description"`
+		ISBN          *string  `json:"isbn"`
+		ASIN          *string  `json:"asin"`
+		Language      *string  `json:"language"`
+	}
+	if err := json.Unmarshal(data, &sidecar); err != nil {
+		fmt.Printf("Warning: failed to parse metadata.json sidecar for %s: %v\n", path, err)
+		return nil
+	}
+
+	metadata := &MediaMetadata{
+		Title: strings.TrimSpace(sidecar.Title),
+	}
+	if len(sidecar.Authors) > 0 {
+		metadata.Author = strings.TrimSpace(sidecar.Authors[0])
+	}
+	if len(sidecar.Series) > 0 {
+		metadata.Series = strings.TrimSpace(sidecar.Series[0].Series)
+		if index, err := strconv.ParseFloat(strings.TrimSpace(sidecar.Series[0].Sequence), 32); err == nil {
+			metadata.SeriesNumber = int32(index)
+		}
+	}
+	if tags := append(append([]string{}, sidecar.Genres...), sidecar.Tags...); len(tags) > 0 {
+		metadata.Tags = utils.NormalizeTags(tags)
+	}
+	if sidecar.PublishedDate != nil {
+		if date, err := time.Parse("2006-01-02", strings.TrimSpace(*sidecar.PublishedDate)); err == nil {
+			metadata.PublishDate = date
+		}
+	}
+	if metadata.PublishDate.IsZero() && sidecar.PublishedYear != nil && *sidecar.PublishedYear > 0 {
+		metadata.PublishDate = time.Date(*sidecar.PublishedYear, 1, 1, 0, 0, 0, 0, time.UTC)
+	}
+	if sidecar.Publisher != nil {
+		metadata.Publisher = strings.TrimSpace(*sidecar.Publisher)
+	}
+	if sidecar.Description != nil {
+		metadata.Description = strings.TrimSpace(*sidecar.Description)
+	}
+	if sidecar.ISBN != nil {
+		metadata.ISBN = utils.NormalizeISBNSafe(strings.TrimSpace(*sidecar.ISBN))
+	}
+	if sidecar.ASIN != nil {
+		metadata.ASIN = strings.TrimSpace(*sidecar.ASIN)
+	}
+	if sidecar.Language != nil {
+		metadata.Language = strings.TrimSpace(*sidecar.Language)
+	}
+
+	return metadata
+}
+
+// extractAudiobookshelfSidecar-TMP-END
+
 // mergeMetadata intelligently merges metadata from multiple sources
 // Priority: metadata.opf (Calibre) → embedded metadata → folder structure → filename
 // For comics: metadata.opf → ComicInfo.xml → folder structure → filename
@@ -1265,6 +1347,8 @@ func extractGenreTagsFromComicInfo(comicInfo *ComicInfo) []string {
 }

 func (s *MediaScanner) extractMetadata(path string) (*MediaMetadata, error) {
+	// Metadata sidecar priority: Calibre metadata.opf, then Audiobookshelf
+	// metadata.json, then the media file's own embedded metadata.
 	// Try Calibre sidecar first
 	calibreMetadata := s.extractCalibreSidecar(path)
 	if calibreMetadata != nil {
@@ -1279,7 +1363,21 @@ func (s *MediaScanner) extractMetadata(path string) (*MediaMetadata, error) {
 		return s.mergeMetadata(path, calibreMetadata)
 	}

-	// EXISTING: Fallback to embedded metadata
+	// Audiobookshelf-style metadata.json sidecar (fields without a DB column
+	// - narrators, subtitle, explicit, abridged, chapters - are skipped)
+	abMetadata := extractAudiobookshelfSidecar(path)
+	if abMetadata != nil {
+		fmt.Printf("Using metadata.json sidecar for %s\n", path)
+
+		coverPath := findSidecarCover(path)
+		if coverPath != "" {
+			abMetadata.CoverPath = s.getRelativePath(coverPath)
+		}
+
+		return s.mergeMetadata(path, abMetadata)
+	}
+
+	// Fallback to embedded metadata
 	ext := strings.ToLower(filepath.Ext(path))

 	switch ext {
@@ -152,3 +152,81 @@ func TestParseOPFContentCalibreSeries(t *testing.T) {
 		t.Errorf("Tags = %v, want 2 subjects", metadata.Tags)
 	}
 }
+
+func TestExtractAudiobookshelfSidecar(t *testing.T) {
+	tests := []struct {
+		name     string
+		json     string
+		validate func(t *testing.T, m *MediaMetadata)
+	}{
+		{
+			name: "full sidecar",
+			json: `{
+				"title": "An Book",
+				"authors": ["Author One", "Author Two"],
+				"series": [{"series": "The Series", "sequence": "4.5"}],
+				"genres": ["Fantasy"],
+				"tags": ["tag1"],
+				"publishedYear": 2019,
+				"publisher": "ACME Books",
+				"description": "A very good book.",
+				"isbn": "978-3-16-148410-0",
+				"asin": "B08XYZ",
+				"language": "en"
+			}`,
+			validate: func(t *testing.T, m *MediaMetadata) {
+				if m.Title != "An Book" || m.Author != "Author One" {
+					t.Errorf("Title/Author = %q/%q", m.Title, m.Author)
+				}
+				if m.Series != "The Series" || m.SeriesNumber != 4 {
+					t.Errorf("Series = %q/%d, want The Series/4", m.Series, m.SeriesNumber)
+				}
+				if len(m.Tags) != 2 {
+					t.Errorf("Tags = %v, want genres+tags merged", m.Tags)
+				}
+				if m.PublishDate.Year() != 2019 {
+					t.Errorf("PublishDate year = %d, want 2019", m.PublishDate.Year())
+				}
+				if m.Publisher != "ACME Books" || m.Description != "A very good book." {
+					t.Errorf("Publisher/Description = %q/%q", m.Publisher, m.Description)
+				}
+				if m.ISBN == "" || m.ASIN != "B08XYZ" || m.Language != "en" {
+					t.Errorf("ISBN/ASIN/Language = %q/%q/%q", m.ISBN, m.ASIN, m.Language)
+				}
+			},
+		},
+		{
+			name: "sparse sidecar (real-world Audiobookshelf export)",
+			json: `{"title": "Sparse (1234)", "authors": ["X"], "tags": [], "description": null}`,
+			validate: func(t *testing.T, m *MediaMetadata) {
+				if m.Title != "Sparse (1234)" || m.Author != "X" {
+					t.Errorf("Title/Author = %q/%q", m.Title, m.Author)
+				}
+				if m.Description != "" || m.Tags != nil {
+					t.Error("null/empty sidecar fields must stay unset")
+				}
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			dir := t.TempDir()
+			if err := os.WriteFile(filepath.Join(dir, "metadata.json"), []byte(tt.json), 0644); err != nil {
+				t.Fatal(err)
+			}
+			m := extractAudiobookshelfSidecar(filepath.Join(dir, "book.epub"))
+			if m == nil {
+				t.Fatal("extractAudiobookshelfSidecar() = nil, want metadata")
+			}
+			tt.validate(t, m)
+		})
+	}
+
+	t.Run("no sidecar returns nil", func(t *testing.T) {
+		dir := t.TempDir()
+		if m := extractAudiobookshelfSidecar(filepath.Join(dir, "book.epub")); m != nil {
+			t.Errorf("extractAudiobookshelfSidecar() = %v, want nil", m)
+		}
+	})
+}