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/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))
+		}
+	}
+}