Add Calibre metadata.opf sidecar file support to media scanner

Implement sidecar-first metadata extraction approach that prioritizes Calibre metadata.opf files over embedded metadata when available. Key Features: - Sidecar-first approach: Check for metadata.opf before extracting embedded - Full Dublin Core namespace support: Use complete namespace URLs - Calibre-specific meta tags: Extract series, series_index from <meta> tags - Graceful degradation: Fall back to embedded metadata on parse failure - Identifier extraction: Support ISBN and ASIN from Dublin Core identifiers - Date parsing: Handle ISO 8601 timestamps and simple date formats Implementation Details: - Added extractCalibreSidecar() to check for and parse metadata.opf - Added parseCalibreMetadataOPF() with full Dublin Core namespace handling - Modified extractMetadata() to try sidecar first, fallback to embedded - Added CalibreOPFMetadata struct for intermediate parsing - Cover image support: findSidecarCover() for sidecar metadata Tests: - Unit tests for parseCalibreMetadataOPF() with real Calibre file examples - Integration tests for Calibre library scanning This allows users with Calibre-managed libraries to import their curated metadata (series, tags, custom covers) into Bookhoard. Fixes: #calibre-opf-support
2026-03-26 14:38:20 -04:00
parent 902e878341
commit a900c78faf
3 changed files with 496 additions and 0 deletions
@@ -0,0 +1,149 @@
+package services
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestParseCalibreMetadataOPF(t *testing.T) {
+	tests := []struct {
+		name       string
+		opfContent string
+		wantTitle  string
+		wantAuthor string
+		wantSeries string
+		wantTags   int
+		wantErr    bool
+	}{
+		{
+			name: "Complete metadata.opf",
+			opfContent: `<?xml version='1.0' encoding='utf-8'?>
+<package xmlns="http://www.idpf.org/2007/opf" version="2.0">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>Test Book</dc:title>
+    <dc:creator>Test Author</dc:creator>
+    <dc:subject>Fantasy</dc:subject>
+    <dc:subject>Adventure</dc:subject>
+    <dc:description>Test description</dc:description>
+    <dc:publisher>Test Publisher</dc:publisher>
+    <dc:date>2024-01-15</dc:date>
+    <dc:language>en</dc:language>
+    <dc:identifier opf:scheme="ISBN">978-0-123456-78-9</dc:identifier>
+    <dc:contributor>Contributor Name</dc:contributor>
+    <meta name="calibre:series" content="Test Series"/>
+    <meta name="calibre:series_index" content="1"/>
+  </metadata>
+</package>`,
+			wantTitle:  "Test Book",
+			wantAuthor: "Test Author",
+			wantSeries: "Test Series",
+			wantTags:   2,
+			wantErr:    false,
+		},
+		{
+			name: "Minimal metadata.opf",
+			opfContent: `<?xml version='1.0' encoding='utf-8'?>
+<package xmlns="http://www.idpf.org/2007/opf" version="2.0">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>Minimal Book</dc:title>
+  </metadata>
+</package>`,
+			wantTitle:  "Minimal Book",
+			wantAuthor: "",
+			wantSeries: "",
+			wantTags:   0,
+			wantErr:    false,
+		},
+		{
+			name: "Malformed XML",
+			opfContent: `<?xml version='1.0' encoding='utf-8'?>
+<package xmlns="http://www.idpf.org/2007/opf" version="2.0">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>Test`,
+			wantTitle:  "",
+			wantAuthor: "",
+			wantSeries: "",
+			wantTags:   0,
+			wantErr:    true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Create temporary OPF file
+			tmpDir := t.TempDir()
+			opfPath := filepath.Join(tmpDir, "metadata.opf")
+			if err := os.WriteFile(opfPath, []byte(tt.opfContent), 0644); err != nil {
+				t.Fatalf("Failed to create test OPF: %v", err)
+			}
+
+			// Parse
+			scanner := &MediaScanner{}
+			got, err := scanner.parseCalibreMetadataOPF(opfPath)
+
+			if (err != nil) != tt.wantErr {
+				t.Errorf("parseCalibreMetadataOPF() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+
+			if !tt.wantErr && got.Title != tt.wantTitle {
+				t.Errorf("Title = %v, want %v", got.Title, tt.wantTitle)
+			}
+			if !tt.wantErr && got.Author != tt.wantAuthor {
+				t.Errorf("Author = %v, want %v", got.Author, tt.wantAuthor)
+			}
+			if !tt.wantErr && got.Series != tt.wantSeries {
+				t.Errorf("Series = %v, want %v", got.Series, tt.wantSeries)
+			}
+			if !tt.wantErr && len(got.Tags) != tt.wantTags {
+				t.Errorf("Tags length = %v, want %v", len(got.Tags), tt.wantTags)
+			}
+		})
+	}
+}
+
+func TestExtractCalibreSidecar(t *testing.T) {
+	t.Run("Sidecar exists", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		opfPath := filepath.Join(tmpDir, "metadata.opf")
+		bookPath := filepath.Join(tmpDir, "book.epub")
+
+		// Create OPF file
+		opfContent := `<?xml version='1.0' encoding='utf-8'?>
+<package xmlns="http://www.idpf.org/2007/opf" version="2.0">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>Sidecar Test</dc:title>
+    <dc:creator>Test Author</dc:creator>
+  </metadata>
+</package>`
+		if err := os.WriteFile(opfPath, []byte(opfContent), 0644); err != nil {
+			t.Fatal(err)
+		}
+
+		// Test extraction
+		scanner := &MediaScanner{}
+		metadata := scanner.extractCalibreSidecar(bookPath)
+
+		if metadata == nil {
+			t.Error("Expected metadata, got nil")
+			return
+		}
+
+		if metadata.Title != "Sidecar Test" {
+			t.Errorf("Title = %v, want 'Sidecar Test'", metadata.Title)
+		}
+	})
+
+	t.Run("No sidecar", func(t *testing.T) {
+		tmpDir := t.TempDir()
+		bookPath := filepath.Join(tmpDir, "book.epub")
+
+		scanner := &MediaScanner{}
+		metadata := scanner.extractCalibreSidecar(bookPath)
+
+		if metadata != nil {
+			t.Error("Expected nil, got metadata")
+		}
+	})
+}