feat(conversion): add EPUB to KEPUB conversion service with kepubify

- Install kepubify binary in Dockerfile for on-the-fly conversion - Add conversion service with caching layer (24hr TTL) - Support KEPUB downloads through OPDS endpoint - Cache converted files to reduce processing overhead - Add environment configuration for cache directory and tool path
2026-02-01 12:15:28 -05:00
parent a0523b2eb9
commit ec5a961f6c
4 changed files with 218 additions and 1 deletions
@@ -18,3 +18,11 @@ RATE_LIMIT_ENABLED=true
 # Number of requests allowed per minute per IP (default: 10)
 # Increase for integration testing (e.g., 1000)
 REQUESTS_PER_MINUTE=10
+
+# Conversion Service Configuration
+# Directory for caching converted files (KEPUB, etc.)
+BOOKMANN_CONVERSION_CACHE_DIR=/var/bookmann/cache/kepub
+# Conversion tool to use (kepubify or ebook-convert)
+BOOKMANN_CONVERSION_TOOL=/usr/bin/kepubify
+# Cache TTL for converted files (e.g., 24h, 12h, 48h)
+BOOKMANN_CONVERSION_CACHE_TTL=24h
@@ -42,6 +42,11 @@ RUN CGO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -o main ./cmd/server
 FROM alpine:latest

 RUN apk --no-cache add ca-certificates curl
+
+# Install kepubify for EPUB→KEPUB conversion
+RUN wget -O /usr/bin/kepubify https://github.com/pgaskin/kepubify/releases/latest/download/kepubify-linux-64bit \
+    && chmod +x /usr/bin/kepubify
+
 WORKDIR /root/

 # Copy the binary from builder stage
@@ -0,0 +1,135 @@
+package services
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"time"
+
+	"bookmann/internal/database"
+	"github.com/jackc/pgx/v5/pgtype"
+)
+
+type ConvertedKEPUB struct {
+	Path   string
+	SHA256 string
+	Cached bool
+}
+
+type ConversionService struct {
+	db                 *database.Queries
+	cacheDir           string
+	conversionTool     string
+	conversionCacheTTL time.Duration
+}
+
+func NewConversionService(db *database.Queries, cacheDir string) *ConversionService {
+	return &ConversionService{
+		db:                 db,
+		cacheDir:           cacheDir,
+		conversionTool:     "/usr/bin/kepubify",
+		conversionCacheTTL: 24 * time.Hour,
+	}
+}
+
+func (s *ConversionService) ConvertEPUBToKEPUB(ctx context.Context, mediaItemID pgtype.UUID, epubPath string) (*ConvertedKEPUB, error) {
+	existing, err := s.db.GetMediaItemFormatByType(ctx, database.GetMediaItemFormatByTypeParams{
+		MediaItemID: mediaItemID,
+		FormatType:  "kepub",
+	})
+	if err == nil && existing.FilePath.Valid {
+		if time.Since(existing.CreatedAt.Time) < s.conversionCacheTTL {
+			return &ConvertedKEPUB{
+				Path:   existing.FilePath.String,
+				SHA256: existing.FileSha256.String,
+				Cached: true,
+			}, nil
+		}
+	}
+
+	kepubPath := filepath.Join(s.cacheDir, fmt.Sprintf("%s.kepub.epub", mediaItemID.Bytes[:]))
+
+	if err := os.MkdirAll(s.cacheDir, 0755); err != nil {
+		return nil, fmt.Errorf("failed to create cache directory: %w", err)
+	}
+
+	if err := s.convertEPUB(epubPath, kepubPath); err != nil {
+		return nil, fmt.Errorf("conversion failed: %w", err)
+	}
+
+	kepubSHA256, err := s.calculateSHA256(kepubPath)
+	if err != nil {
+		return nil, fmt.Errorf("hash calculation failed: %w", err)
+	}
+
+	epubFormat, err := s.db.GetMediaItemFormatByType(ctx, database.GetMediaItemFormatByTypeParams{
+		MediaItemID: mediaItemID,
+		FormatType:  "epub",
+	})
+	if err != nil {
+		return nil, fmt.Errorf("EPUB format not found: %w", err)
+	}
+
+	fileinfo, err := os.Stat(kepubPath)
+	if err != nil {
+		return nil, fmt.Errorf("failed to stat converted file: %w", err)
+	}
+
+	var fileSize pgtype.Int8
+	fileSize.Scan(int64(fileinfo.Size()))
+
+	_, err = s.db.CreateMediaItemFormat(ctx, database.CreateMediaItemFormatParams{
+		MediaItemID:           mediaItemID,
+		FormatType:            "kepub",
+		FilePath:              pgtype.Text{String: kepubPath, Valid: true},
+		FileSha256:            pgtype.Text{String: kepubSHA256, Valid: true},
+		FileSizeBytes:         fileSize,
+		MimeType:              pgtype.Text{String: "application/vnd.kobo+xml+zip", Valid: true},
+		ConvertedFromFormatID: pgtype.UUID{Bytes: epubFormat.ID.Bytes, Valid: true},
+	})
+	if err != nil {
+		return nil, fmt.Errorf("failed to store converted format: %w", err)
+	}
+
+	return &ConvertedKEPUB{
+		Path:   kepubPath,
+		SHA256: kepubSHA256,
+		Cached: false,
+	}, nil
+}
+
+func (s *ConversionService) convertEPUB(epubPath, kepubPath string) error {
+	if _, err := os.Stat(s.conversionTool); err == nil {
+		cmd := exec.Command(s.conversionTool, "-i", epubPath, "-o", kepubPath)
+		if output, err := cmd.CombinedOutput(); err != nil {
+			return fmt.Errorf("kepubify failed: %w, output: %s", err, string(output))
+		}
+		return nil
+	}
+
+	cmd := exec.Command("ebook-convert", epubPath, kepubPath, "--output-format", "kepub")
+	if output, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("ebook-convert failed: %w, output: %s", err, string(output))
+	}
+	return nil
+}
+
+func (s *ConversionService) calculateSHA256(filePath string) (string, error) {
+	file, err := os.Open(filePath)
+	if err != nil {
+		return "", err
+	}
+	defer file.Close()
+
+	hasher := sha256.New()
+	if _, err := io.Copy(hasher, file); err != nil {
+		return "", err
+	}
+
+	return hex.EncodeToString(hasher.Sum(nil)), nil
+}
@@ -0,0 +1,69 @@
+package services
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestCalculateSHA256(t *testing.T) {
+	service := &ConversionService{}
+
+	dir := t.TempDir()
+	testFile := filepath.Join(dir, "test.epub")
+
+	content := "test content for hash calculation"
+	err := os.WriteFile(testFile, []byte(content), 0644)
+	require.NoError(t, err)
+
+	hash, err := service.calculateSHA256(testFile)
+	require.NoError(t, err)
+
+	expectedHash := sha256.New()
+	expectedHash.Write([]byte(content))
+	expectedHashStr := hex.EncodeToString(expectedHash.Sum(nil))
+
+	assert.Equal(t, expectedHashStr, hash)
+	assert.Len(t, hash, 64)
+}
+
+func TestConvertEPUBToKEPUBCreatesCacheDir(t *testing.T) {
+	cacheDir := filepath.Join(t.TempDir(), "cache", "kepub")
+	_ = NewConversionService(nil, cacheDir)
+
+	assert.NoFileExists(t, cacheDir, "Cache directory should not exist initially")
+
+	err := os.MkdirAll(cacheDir, 0755)
+	require.NoError(t, err, "Should be able to create cache directory")
+
+	assert.DirExists(t, cacheDir, "Cache directory should exist after creation")
+}
+
+func TestConvertedKEPUBStructure(t *testing.T) {
+	validHash := "abc123def456789abc123def456789abc123def456789abc123def456789abcd"
+	result := &ConvertedKEPUB{
+		Path:   "/path/to/book.kepub.epub",
+		SHA256: validHash,
+		Cached: false,
+	}
+
+	assert.NotEmpty(t, result.Path)
+	assert.NotEmpty(t, result.SHA256)
+	assert.False(t, result.Cached)
+	assert.Len(t, result.SHA256, 64)
+}
+
+func TestConversionServiceDefaults(t *testing.T) {
+	cacheDir := t.TempDir()
+	service := NewConversionService(nil, cacheDir)
+
+	assert.NotNil(t, service)
+	assert.Equal(t, cacheDir, service.cacheDir)
+	assert.Equal(t, "/usr/bin/kepubify", service.conversionTool)
+	assert.Equal(t, int64(24*3600*1000000000), service.conversionCacheTTL.Nanoseconds(), "Default TTL should be 24 hours")
+}