Merge pull request #3884 from opencloud-eu/fix/webdav-generator-passthrough

fix(webdav): stream announced types without a converter to the generator

services/webdav/pkg/preprocessor/preprocessor.go

@@ -393,9 +393,8 @@ func ForType(mimeType string, opts Options) FileConverter {
 	case "audio/ogg":
 		return AudioDecoder{}
 	default:
-		// webdav decodes no image: an image/* source is streamed to the
-		// generator untouched, so a type without a converter here is one
-		// nobody can make a preview of.
+		// webdav decodes no image: a type without a converter is streamed to
+		// the generator untouched, which answers whether it can read it.
 		return nil
 	}
 }

services/webdav/pkg/thumbnail/workflow/workflow.go

@@ -471,10 +471,9 @@ func (w *ThumbnailWorkflow) generate(ctx context.Context, ref *providerv1beta1.R
 	// imagor's default resize does.
 	genURL := generator.BuildURL(w.generatorURL, int32(box.Dx()), int32(box.Dy()), operation, outputFormat, noUpscale)
 
-	// Produce the source image to send to the generator, never decoding an image
-	// in webdav: real images (incl. gif) are streamed straight through undecoded;
-	// non-image sources are converted to image bytes here so the generator always
-	// receives an image.
+	// Produce the source to send to the generator, never decoding an image in
+	// webdav: anything without a converter is streamed straight through undecoded,
+	// the few types with one (text, audio, geogebra) are turned into image bytes here.
 	imgStream, srcType, cleanup, err := w.sourceImage(ctx, ref, auth, mimeType, tr.Filename, logger)
 	if err != nil {
 		logger.Error().Err(err).Msg("could not obtain source image for thumbnail")
@@ -505,17 +504,19 @@ func (w *ThumbnailWorkflow) generate(ctx context.Context, ref *providerv1beta1.R
 	return Thumbnail{Data: thumbBytes, ContentType: outputType}, nil
 }
 
-// sourceImage returns a reader over the source image to send to the generator,
-// plus a cleanup func to release any resources (download body, temp buffer). It
-// never decodes an image in webdav:
-//   - real images (image/*, incl. gif) are streamed straight through from storage
-//     undecoded; the generator handles decoding and multi-frame gifs itself.
+// sourceImage returns a reader over the source to send to the generator, plus a
+// cleanup func to release any resources (download body, temp buffer). It never
+// decodes an image in webdav:
+//   - a type without a converter (image/*, incl. gif, and whatever else the source
+//     types announce) is streamed straight through from storage undecoded; the
+//     generator decides whether it can read it.
 //   - text/plain is rendered to an image here (the only true conversion).
 //   - audio and geogebra sources have their embedded image extracted to bytes.
 func (w *ThumbnailWorkflow) sourceImage(ctx context.Context, ref *providerv1beta1.Reference, auth, mimeType, filename string, logger log.Logger) (io.Reader, string, func(), error) {
 	m, _, _ := mime.ParseMediaType(mimeType)
 
-	if strings.HasPrefix(m, "image/") {
+	converter := preprocessor.ForType(m, preprocessor.Options{FontMapFile: w.fontMapFile, MaxImageSize: w.maxInputSize})
+	if converter == nil {
 		body, err := w.fileDownloader.DownloadStream(ctx, ref, auth)
 		if err != nil {
 			return nil, "", nil, fmt.Errorf("download: %w", err)
@@ -534,12 +535,6 @@ func (w *ThumbnailWorkflow) sourceImage(ctx context.Context, ref *providerv1beta
 		return nil, "", nil, fmt.Errorf("read source: %w", err)
 	}
 
-	converter := preprocessor.ForType(mimeType, preprocessor.Options{FontMapFile: w.fontMapFile, MaxImageSize: w.maxInputSize})
-	if converter == nil {
-		logger.Debug().Str("mimetype", mimeType).Msg("no converter for this type")
-		return nil, "", nil, fmt.Errorf("%w: no converter for %s", ErrNotFound, mimeType)
-	}
-
 	img, err := converter.Convert(bytes.NewReader(fileBytes))
 	if err != nil || img == nil {
 		logger.Debug().Err(err).Msg("could not convert file to image")

services/webdav/pkg/thumbnail/workflow/workflow_test.go

@@ -217,6 +217,7 @@ func setupPreprocessTest(
 		if err := r.ParseMultipartForm(10 << 20); err == nil {
 			for _, fh := range r.MultipartForm.File["image"] {
 				captured.filename = filepath.Base(fh.Filename)
+				captured.contentType = fh.Header.Get("Content-Type")
 				file, ferr := fh.Open()
 				if ferr != nil {
 					continue
@@ -235,9 +236,10 @@ func setupPreprocessTest(
 }
 
 type capturedUpload struct {
-	path     string
-	filename string
-	data     []byte
+	path        string
+	filename    string
+	contentType string
+	data        []byte
 }
 
 var _ = Describe("ThumbnailWorkflow", func() {
@@ -789,6 +791,25 @@ var _ = Describe("ThumbnailWorkflow", func() {
 			Expect(captured.data).To(Equal(pngBytes))
 		})
 
+		It("streams an announced type without a converter through untouched", func() {
+			pdfBytes := []byte("%PDF-1.4 not really a pdf")
+
+			wf2, captured := setupPreprocessTest(GinkgoT(), gatewayClient, logger, testCache, "application/pdf", "doc.pdf", pdfBytes)
+			wf2.sourceTypes = thumbnail.NewSourceTypes([]string{"application/pdf"})
+
+			tr := &requests.ThumbnailRequest{
+				Ref:      spaceRef("storageid$spaceid!opaqueid", "doc.pdf"),
+				Filename: "doc.pdf",
+				Width:    64,
+				Height:   64,
+			}
+
+			_, err := wf2.Execute(context.Background(), tr, testToken, logger)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(captured.data).To(Equal(pdfBytes))
+			Expect(captured.contentType).To(Equal("application/pdf"), "the generator sees the file's own type, not a guess")
+		})
+
 		It("converts audio to cover art before posting", func() {
 			mp3Bytes, err := os.ReadFile(filepath.Join("..", "..", "preprocessor", "test_assets", "empty.mp3"))
 			Expect(err).ToNot(HaveOccurred())
@@ -997,6 +1018,13 @@ var _ = Describe("ThumbnailWorkflow", func() {
 				Height:   64,
 			}
 
+			untouched := httptest.NewServer(http.HandlerFunc(func(http.ResponseWriter, *http.Request) {
+				defer GinkgoRecover()
+				Fail("a type outside the source types must never reach the generator")
+			}))
+			defer untouched.Close()
+			wf.generatorURL = untouched.URL
+
 			_, err := wf.Execute(context.Background(), tr, testToken, logger)
 			Expect(err).To(HaveOccurred())
 			Expect(errors.Is(err, ErrUnsupportedFileType)).To(BeTrue())