Refuse SVG sources and never save an unknown input as JPEG (closes #68)

The upstream fetch no longer accepts image/svg+xml, and both image
routes answer 415, not 500, for any upstream Content-Type outside the
source formats. Before decoding, the image processor names the input's
format from govips' DetermineImageType and refuses, with 415, input
whose first bytes libvips reads as anything but the six source formats,
so an SVG passing the first-bytes check for AVIF never reaches librsvg.
orig of such an input is refused instead of being saved as JPEG.
README.md drops SVG from the source formats.

SVG detection stays in internal/magic, unused on the request path, for
#168. An AVIF image sequence
(brand avis) answers 415.

Model: opus-5-5

internal/handlers/image.go

@@ -247,6 +247,14 @@ func (s *Handlers) respondImageError(
 		return
 	}
 
+	if errors.Is(err, httpfetcher.ErrInvalidContentType) ||
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat) {
+		s.respondError(w, "unsupported source format",
+			http.StatusUnsupportedMediaType)
+
+		return
+	}
+
 	s.respondError(w, "internal error", http.StatusInternalServerError)
 }
 

internal/handlers/imageenc.go

@@ -161,6 +161,10 @@ func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
 		errors.Is(err, imageprocessor.ErrTooManyImages):
 		s.respondError(w, "server busy, try again later",
 			http.StatusServiceUnavailable)
+	case errors.Is(err, httpfetcher.ErrInvalidContentType),
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat):
+		s.respondError(w, "unsupported source format",
+			http.StatusUnsupportedMediaType)
 	default:
 		s.log.Error("image request failed", "error", err)
 		s.respondError(w, "internal error", http.StatusInternalServerError)

internal/handlers/unsupported_source_internal_test.go

@@ -0,0 +1,54 @@
+package handlers
+
+import (
+	"fmt"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"sneak.berlin/go/pixa/internal/httpfetcher"
+	"sneak.berlin/go/pixa/internal/imageprocessor"
+	"sneak.berlin/go/pixa/internal/imgcache"
+)
+
+// TestUnsupportedSourceFormatAnswers415 checks that both image routes answer
+// 415 with a clear error when the upstream answers with a content type pixa
+// does not accept, such as SVG, and when orig is asked of a source in a
+// format the processor cannot name, wrapped as the service wraps them.
+func TestUnsupportedSourceFormatAnswers415(t *testing.T) {
+	t.Parallel()
+
+	h := &Handlers{log: slog.New(slog.DiscardHandler)}
+	req := &imgcache.ImageRequest{SourceHost: "img.example.com", SourcePath: "/a.svg"}
+
+	for _, err := range []error{
+		fmt.Errorf("upstream fetch failed: %w: image/svg+xml",
+			httpfetcher.ErrInvalidContentType),
+		fmt.Errorf("image processing failed: %w: unknown",
+			imageprocessor.ErrUnsupportedInputFormat),
+	} {
+		plain := httptest.NewRecorder()
+		h.respondImageError(plain, req, err)
+
+		encrypted := httptest.NewRecorder()
+		h.handleImageError(encrypted, err)
+
+		for route, rec := range map[string]*httptest.ResponseRecorder{
+			"HandleImage": plain, "HandleImageEnc": encrypted,
+		} {
+			t.Logf("%s for %v: %d %s", route, err, rec.Code, rec.Body.String())
+
+			if rec.Code != http.StatusUnsupportedMediaType {
+				t.Errorf("%s for %v: status = %d, want %d",
+					route, err, rec.Code, http.StatusUnsupportedMediaType)
+			}
+
+			if !strings.Contains(rec.Body.String(), "unsupported source format") {
+				t.Errorf("%s for %v: body = %q, want the unsupported source format error",
+					route, err, rec.Body.String())
+			}
+		}
+	}
+}

internal/httpfetcher/httpfetcher.go

@@ -158,7 +158,6 @@ func DefaultConfig() *Config {
 			contentTypeWebP,
 			contentTypeAVIF,
 			contentTypeJXL,
-			contentTypeSVG,
 		},
 		AllowHTTP:             false,
 		MaxConnectionsPerHost: DefaultMaxConnectionsPerHost,

internal/imageprocessor/imageprocessor.go

@@ -137,6 +137,12 @@ var ErrInputDataTooLarge = errors.New("input data exceeds maximum allowed size")
 // not supported.
 var ErrUnsupportedOutputFormat = errors.New("unsupported output format")
 
+// ErrUnsupportedInputFormat is returned, before the input is decoded, when
+// libvips reads the input's first bytes as another format than the source
+// formats, or as none: for example an SVG whose first bytes pass the
+// first-bytes check for AVIF.
+var ErrUnsupportedInputFormat = errors.New("unsupported input format")
+
 // ErrTooManyImages is returned when MaxConcurrentProcessing images are being
 // processed and none finishes within ProcessingWaitTimeout.
 var ErrTooManyImages = errors.New("too many images being processed at once")
@@ -219,6 +225,17 @@ func (p *ImageProcessor) Process(
 		return nil, ErrInputDataTooLarge
 	}
 
+	// govips picks the libvips loader from the input's first bytes with
+	// DetermineImageType. Input whose first bytes it reads as no source
+	// format, such as SVG, which librsvg would render, is refused before
+	// libvips reads it.
+	inputFormat := p.detectFormat(vips.DetermineImageType(data))
+
+	sourceFormat, err := p.formatFromString(inputFormat)
+	if err != nil {
+		return nil, err
+	}
+
 	// Decode image
 	img, err := vips.NewImageFromBuffer(data)
 	if err != nil {
@@ -237,9 +254,6 @@ func (p *ImageProcessor) Process(
 	origWidth := img.Width()
 	origHeight := img.Height()
 
-	// Detect input format
-	inputFormat := p.detectFormat(img)
-
 	// Validate input dimensions to prevent DoS via decompression bombs
 	if origWidth > MaxInputDimension || origHeight > MaxInputDimension {
 		return nil, ErrInputTooLarge
@@ -259,7 +273,7 @@ func (p *ImageProcessor) Process(
 	// orig is the source's own format; encode refuses an empty format
 	outputFormat := req.Format
 	if outputFormat == FormatOriginal {
-		outputFormat = p.formatFromString(inputFormat)
+		outputFormat = sourceFormat
 	}
 
 	// Encode to target format
@@ -403,10 +417,9 @@ func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
 	}
 }
 
-// detectFormat returns the format string from a vips image.
-func (p *ImageProcessor) detectFormat(img *vips.ImageRef) string {
-	format := img.Format()
-	switch format {
+// detectFormat returns the format string for a govips image type.
+func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
+	switch imageType {
 	case vips.ImageTypeJPEG:
 		return "jpeg"
 	case vips.ImageTypePNG:
@@ -687,22 +700,23 @@ func jxlDistance(quality int) float64 {
 	return 53.0/3000.0*q*q - 23.0/20.0*q + 25.0
 }
 
-// formatFromString converts a format string to Format.
-func (p *ImageProcessor) formatFromString(format string) Format {
+// formatFromString converts a format string from detectFormat to Format. A
+// format detectFormat could not name is ErrUnsupportedInputFormat.
+func (p *ImageProcessor) formatFromString(format string) (Format, error) {
 	switch format {
 	case "jpeg":
-		return FormatJPEG
+		return FormatJPEG, nil
 	case "png":
-		return FormatPNG
+		return FormatPNG, nil
 	case "gif":
-		return FormatGIF
+		return FormatGIF, nil
 	case "webp":
-		return FormatWebP
+		return FormatWebP, nil
 	case string(FormatAVIF):
-		return FormatAVIF
+		return FormatAVIF, nil
 	case string(FormatJXL):
-		return FormatJXL
+		return FormatJXL, nil
 	default:
-		return FormatJPEG
+		return "", fmt.Errorf("%w: %s", ErrUnsupportedInputFormat, format)
 	}
 }

internal/imageprocessor/orig_format_internal_test.go

@@ -0,0 +1,39 @@
+package imageprocessor
+
+import (
+	"bytes"
+	"errors"
+	"testing"
+
+	"github.com/davidbyttow/govips/v2/vips"
+)
+
+// TestImageProcessor_OrigOfUnnamedFormatRefused verifies that orig of a TIFF
+// input, which is not a source format, is refused with
+// ErrUnsupportedInputFormat before it is decoded, and not saved as JPEG.
+func TestImageProcessor_OrigOfUnnamedFormatRefused(t *testing.T) {
+	t.Parallel()
+
+	img, err := vips.NewImageFromBuffer(createTestPNG(t, 20, 20))
+	if err != nil {
+		t.Fatalf("failed to decode test PNG: %v", err)
+	}
+
+	t.Cleanup(img.Close)
+
+	tiff, _, err := img.ExportTiff(vips.NewTiffExportParams())
+	if err != nil {
+		t.Fatalf("failed to save test TIFF: %v", err)
+	}
+
+	result, err := New(Params{}).Process(
+		t.Context(), bytes.NewReader(tiff), &Request{Format: FormatOriginal},
+	)
+	if result != nil {
+		t.Logf("Process() returned %s", result.ContentType)
+	}
+
+	if !errors.Is(err, ErrUnsupportedInputFormat) {
+		t.Errorf("Process() error = %v, want %v", err, ErrUnsupportedInputFormat)
+	}
+}

internal/imageprocessor/source_formats_internal_test.go

@@ -0,0 +1,46 @@
+package imageprocessor
+
+import (
+	"bytes"
+	"io"
+	"testing"
+)
+
+// TestImageProcessor_LoadsEachSourceFormat verifies that an image in each of
+// the six source formats, saved by the processor itself, is loaded and saved
+// again in its own format (orig).
+func TestImageProcessor_LoadsEachSourceFormat(t *testing.T) {
+	t.Parallel()
+
+	proc := New(Params{})
+
+	for _, format := range []Format{
+		FormatJPEG, FormatPNG, FormatGIF, FormatWebP, FormatAVIF, FormatJXL,
+	} {
+		saved, err := proc.Process(t.Context(),
+			bytes.NewReader(createTestPNG(t, 20, 20)), &Request{Format: format})
+		if err != nil {
+			t.Fatalf("saving the test image as %s: %v", format, err)
+		}
+
+		source, err := io.ReadAll(saved.Content)
+		if err != nil {
+			t.Fatalf("reading the %s image: %v", format, err)
+		}
+
+		result, err := proc.Process(t.Context(), bytes.NewReader(source),
+			&Request{Format: FormatOriginal})
+		if err != nil {
+			t.Errorf("orig of the %s image: %v", format, err)
+
+			continue
+		}
+
+		t.Logf("orig of the %s image: %s", format, result.ContentType)
+
+		if result.ContentType != FormatToMIME(format) {
+			t.Errorf("orig of the %s image is %s, want %s",
+				format, result.ContentType, FormatToMIME(format))
+		}
+	}
+}

internal/server/svg_as_avif_internal_test.go

@@ -0,0 +1,71 @@
+package server
+
+import (
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"sneak.berlin/go/pixa/internal/encurl"
+	"sneak.berlin/go/pixa/internal/imgcache"
+)
+
+// svgServedAsAVIF is an SVG whose first bytes pass the first-bytes check for
+// AVIF: its XML comment puts "ftypavis" at bytes 4 to 11, where an AVIF file
+// has its ftyp box and brand. libvips would load it as SVG.
+const svgServedAsAVIF = `<!--ftypavis--><svg xmlns="http://www.w3.org/2000/svg" ` +
+	`width="64" height="48"><rect width="64" height="48"/></svg>`
+
+// TestImageProxyRefusesSVGServedAsAVIF requests svgServedAsAVIF, which the
+// upstream answers as image/avif, through both image routes, resized as PNG
+// and in its own format (orig). Each request is answered 415, as for an SVG
+// source, never with an image.
+func TestImageProxyRefusesSVGServedAsAVIF(t *testing.T) {
+	t.Parallel()
+
+	upstream := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.Header().Set("Content-Type", "image/avif")
+			_, _ = io.WriteString(w, svgServedAsAVIF)
+		}))
+	t.Cleanup(upstream.Close)
+
+	s, _, _ := startImageProxy(t, upstream)
+
+	generator, err := encurl.NewGenerator(testSigningKey)
+	if err != nil {
+		t.Fatalf("encurl.NewGenerator: %v", err)
+	}
+
+	encryptedURL := func(format imgcache.ImageFormat) string {
+		token, err := generator.Generate(&encurl.Payload{
+			SourceHost: upstreamHost, SourcePath: "/drawing.avif",
+			Width: 32, Height: 24, Format: format,
+		})
+		if err != nil {
+			t.Fatalf("encurl Generate: %v", err)
+		}
+
+		return "/v1/e/" + token + "/drawing." + string(format)
+	}
+
+	for _, target := range []string{
+		"/v1/image/" + upstreamHost + "/drawing.avif/32x24.png",
+		"/v1/image/" + upstreamHost + "/drawing.avif/64x48.orig",
+		encryptedURL(imgcache.FormatPNG),
+		encryptedURL(imgcache.FormatOriginal),
+	} {
+		rec := httptest.NewRecorder()
+		s.ServeHTTP(rec, httptest.NewRequestWithContext(
+			t.Context(), http.MethodGet, target, nil))
+		t.Logf("GET %s: %d, Content-Type %s, body %q",
+			target, rec.Code, rec.Header().Get("Content-Type"), rec.Body.String())
+
+		if rec.Code != http.StatusUnsupportedMediaType ||
+			!strings.Contains(rec.Body.String(), "unsupported source format") {
+			t.Errorf("GET %s: %d %q, want %d unsupported source format",
+				target, rec.Code, rec.Body.String(), http.StatusUnsupportedMediaType)
+		}
+	}
+}

internal/server/svg_internal_test.go

@@ -0,0 +1,41 @@
+package server
+
+import (
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+// TestImageProxyRefusesSVG requests an image the upstream answers as SVG,
+// in its own format (orig) and resized as PNG, through pixa's router,
+// upstream fetcher and image processor. pixa does not accept SVG as a
+// source, so each request is answered 415, never with an image.
+func TestImageProxyRefusesSVG(t *testing.T) {
+	t.Parallel()
+
+	upstream := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.Header().Set("Content-Type", "image/svg+xml")
+			_, _ = io.WriteString(w, `<svg xmlns="http://www.w3.org/2000/svg" `+
+				`width="64" height="48"><rect width="64" height="48"/></svg>`)
+		}))
+	t.Cleanup(upstream.Close)
+
+	s, _, _ := startImageProxy(t, upstream)
+
+	for _, sizeFormat := range []string{"64x48.orig", "32x24.png"} {
+		target := "/v1/image/" + upstreamHost + "/drawing.svg/" + sizeFormat
+
+		rec := httptest.NewRecorder()
+		s.ServeHTTP(rec, httptest.NewRequestWithContext(
+			t.Context(), http.MethodGet, target, nil))
+		t.Logf("GET %s: %d, Content-Type %s, body %s",
+			target, rec.Code, rec.Header().Get("Content-Type"), rec.Body.String())
+
+		if rec.Code != http.StatusUnsupportedMediaType {
+			t.Errorf("GET %s status = %d, want %d",
+				target, rec.Code, http.StatusUnsupportedMediaType)
+		}
+	}
+}