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
@@ -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)
+		}
+	})
+}