Support SVG sources (closes #68)

The fetcher accepts image/svg+xml again and internal/magic detects SVG.
A raster format renders the SVG at the least size that covers the
output, held to 8192 on a side, through libvips' thumbnail, which
renders at any scale, so an enlarged SVG stays sharp. An SVG's own size
is not limited; one with a side more than 8192 times the other is
ErrSVGTooThin, answered 415. orig of an SVG at the orig size is the SVG
unchanged, cached as a variant; at any other size it is
ErrSVGNotOriginalSize, answered 400. The cache reads up to 1024 first
bytes of a file to find its format. Render time and memory grow with
what the SVG draws; their bound is the owner's decision on #68. Tests that pinned SVG as refused now
expect it to be read.

Model: opus-5-5

internal/imageprocessor/imageprocessor.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"sync"
 	"time"
 
@@ -113,10 +114,21 @@ 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 its source
 // format, or as none. An SVG whose first bytes pass the first-bytes check for
-// AVIF is one example. A source format other than the six pixa reads is also
-// refused with it.
+// AVIF is one example. A source format other than the seven pixa reads is
+// also refused with it.
 var ErrUnsupportedInputFormat = errors.New("unsupported input format")
 
+// ErrSVGNotOriginalSize is returned when orig is asked of an SVG source at a
+// size other than orig. pixa returns an SVG only as it is; a raster format
+// gives it a size.
+var ErrSVGNotOriginalSize = errors.New(
+	"an SVG is returned as SVG only at the orig size")
+
+// ErrSVGTooThin is returned, before rendering, when an SVG source has one
+// side more than MaxInputDimension times the other. Rendered with its longer
+// side at most MaxInputDimension, its shorter side would be under 1 pixel.
+var ErrSVGTooThin = errors.New("SVG source too thin to render")
+
 // 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")
@@ -164,7 +176,9 @@ func New(params Params) *ImageProcessor {
 // encodes, it returns ctx's error and gives the slot back. govips gives pixa
 // no way to stop libvips once an encode has begun, so an encode keeps its
 // slot until it finishes. An AVIF output of more than MaxAVIFOutputPixels is
-// refused with ErrAVIFOutputTooLarge before anything is decoded.
+// refused with ErrAVIFOutputTooLarge before anything is decoded. orig of an
+// SVG source is the SVG as it is, since libvips cannot save SVG; any other
+// format renders it at the output size.
 func (p *ImageProcessor) Process(
 	ctx context.Context,
 	input io.Reader,
@@ -190,27 +204,17 @@ func (p *ImageProcessor) Process(
 		return nil, err
 	}
 
-	// Decode image
-	img, err := vips.NewImageFromBuffer(data)
+	img, err := loadImage(data, sourceFormat)
 	if err != nil {
-		return nil, fmt.Errorf("failed to decode image: %w", err)
+		return nil, err
 	}
 	defer img.Close()
 
-	// Turn the image upright now: encode strips the EXIF orientation tag,
-	// and sizes below must be worked out on the upright image.
-	err = img.AutoRotate()
-	if err != nil {
-		return nil, fmt.Errorf("failed to auto-rotate: %w", err)
-	}
+	origWidth, origHeight := img.Width(), img.Height()
+	outputFormat := resolveOutputFormat(transform.Format, sourceFormat)
 
-	// Get original dimensions
-	origWidth := img.Width()
-	origHeight := img.Height()
-
-	// Validate input dimensions to prevent DoS via decompression bombs
-	if origWidth > MaxInputDimension || origHeight > MaxInputDimension {
-		return nil, ErrInputTooLarge
+	if outputFormat == imagerequest.FormatSVG && sourceFormat == imagerequest.FormatSVG {
+		return svgAsItIs(data, transform.Size, origWidth, origHeight)
 	}
 
 	// Determine target dimensions; too large ones are refused before resizing
@@ -220,12 +224,6 @@ func (p *ImageProcessor) Process(
 		return nil, err
 	}
 
-	// orig is the source's own format; encode refuses an empty format
-	outputFormat := transform.Format
-	if outputFormat == imagerequest.FormatOriginal {
-		outputFormat = sourceFormat
-	}
-
 	// Determine output dimensions; too large ones are refused before
 	// resizing, which with FitCover already decodes the input
 	outputWidth, outputHeight, err := outputDimensions(origWidth, origHeight,
@@ -234,6 +232,19 @@ func (p *ImageProcessor) Process(
 		return nil, err
 	}
 
+	// An SVG is rendered again at about the output size, to stay sharp
+	if sourceFormat == imagerequest.FormatSVG {
+		rendered, err := renderSVG(data, origWidth, origHeight,
+			outputWidth, outputHeight)
+		if err != nil {
+			return nil, err
+		}
+
+		defer rendered.Close()
+
+		img = rendered
+	}
+
 	// Resize if needed
 	if targetWidth != origWidth || targetHeight != origHeight {
 		err := p.resize(img, outputWidth, outputHeight, transform.FitMode)
@@ -290,6 +301,110 @@ func targetDimensions(
 	return width, height, nil
 }
 
+// resolveOutputFormat returns the format of the output for the requested
+// format: sourceFormat for orig, and format itself for any other. encode
+// refuses an empty format.
+func resolveOutputFormat(
+	format, sourceFormat imagerequest.Format,
+) imagerequest.Format {
+	if format == imagerequest.FormatOriginal {
+		return sourceFormat
+	}
+
+	return format
+}
+
+// loadImage decodes data and turns the image upright: encode strips the EXIF
+// orientation tag, and sizes must be worked out on the upright image. An
+// image with a side above MaxInputDimension is ErrInputTooLarge, which guards
+// against decompression bombs. An SVG is not checked: only its header has
+// been read, and the output checks limit the size it is rendered at.
+func loadImage(
+	data []byte, sourceFormat imagerequest.Format,
+) (*vips.ImageRef, error) {
+	img, err := vips.NewImageFromBuffer(data)
+	if err != nil {
+		return nil, fmt.Errorf("failed to decode image: %w", err)
+	}
+
+	err = img.AutoRotate()
+	if err != nil {
+		img.Close()
+
+		return nil, fmt.Errorf("failed to auto-rotate: %w", err)
+	}
+
+	if sourceFormat != imagerequest.FormatSVG &&
+		(img.Width() > MaxInputDimension || img.Height() > MaxInputDimension) {
+		img.Close()
+
+		return nil, ErrInputTooLarge
+	}
+
+	return img, nil
+}
+
+// svgAsItIs returns the SVG data unchanged, which is orig of an SVG source
+// at the orig size. width x height is the SVG's own size. Any other size is
+// ErrSVGNotOriginalSize.
+func svgAsItIs(
+	data []byte, size imagerequest.Size, width, height int,
+) (*Result, error) {
+	if !size.OriginalSize() {
+		return nil, fmt.Errorf("%w: asked for %dx%d", ErrSVGNotOriginalSize,
+			size.Width, size.Height)
+	}
+
+	return &Result{
+		Content:       io.NopCloser(bytes.NewReader(data)),
+		ContentLength: int64(len(data)),
+		ContentType:   imagerequest.FormatSVG.MIMEType(),
+		Width:         width,
+		Height:        height,
+		InputWidth:    width,
+		InputHeight:   height,
+	}, nil
+}
+
+// svgRenderSize returns the least size in the proportions of width x height,
+// an SVG's own size, that covers outputWidth x outputHeight, so that resize
+// hardly changes it. Neither side is above MaxInputDimension.
+func svgRenderSize(width, height, outputWidth, outputHeight int) (int, int) {
+	scale := min(
+		max(float64(outputWidth)/float64(width),
+			float64(outputHeight)/float64(height)),
+		float64(MaxInputDimension)/float64(max(width, height)))
+
+	return int(math.Round(float64(width) * scale)),
+		int(math.Round(float64(height) * scale))
+}
+
+// renderSVG renders the SVG data, whose own size is width x height, at
+// svgRenderSize for outputWidth x outputHeight. An SVG with one side more
+// than MaxInputDimension times the other is ErrSVGTooThin. libvips'
+// thumbnail has librsvg render the SVG at that size directly, at any scale:
+// govips takes a density only in whole dots per inch, which cannot render
+// an SVG below 1/72 of its own size. Given the SVG as bytes with no file
+// name, librsvg loads no file or URL the SVG refers to.
+func renderSVG(
+	data []byte, width, height, outputWidth, outputHeight int,
+) (*vips.ImageRef, error) {
+	if max(width, height) > MaxInputDimension*min(width, height) {
+		return nil, fmt.Errorf("%w: %dx%d", ErrSVGTooThin, width, height)
+	}
+
+	renderWidth, renderHeight := svgRenderSize(width, height,
+		outputWidth, outputHeight)
+
+	img, err := vips.NewThumbnailWithSizeFromBuffer(data,
+		renderWidth, renderHeight, vips.InterestingNone, vips.SizeBoth)
+	if err != nil {
+		return nil, fmt.Errorf("failed to render SVG: %w", err)
+	}
+
+	return img, nil
+}
+
 // WaitForProcessing waits until no image is being processed, or until ctx
 // ends, and returns how many images were still being processed then. It
 // waits by taking each slot in processingSemaphore as it frees up until it
@@ -397,6 +512,8 @@ func vipsImageType(format imagerequest.Format) vips.ImageType {
 		return vips.ImageTypeAVIF
 	case imagerequest.FormatJXL:
 		return vips.ImageTypeJXL
+	case imagerequest.FormatSVG:
+		return vips.ImageTypeSVG
 	case imagerequest.FormatOriginal, imagerequest.FormatAuto:
 		return vips.ImageTypeUnknown
 	default:
@@ -575,7 +692,9 @@ func (p *ImageProcessor) encode(
 	case imagerequest.FormatJXL:
 		return exportJXL(img, quality)
 
-	case imagerequest.FormatOriginal, imagerequest.FormatAuto:
+	// libvips cannot save SVG; Process returns an SVG source as it is
+	case imagerequest.FormatSVG, imagerequest.FormatOriginal,
+		imagerequest.FormatAuto:
 		return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
 
 	default:

internal/imageprocessor/source_formats_internal_test.go

@@ -51,7 +51,7 @@ func TestImageProcessor_LoadsEachSourceFormat(t *testing.T) {
 }
 
 // TestImageProcessor_NotASourceFormatRefused verifies that a source format
-// other than the six, such as orig, auto or none, is refused with
+// other than the seven, such as orig, auto or none, is refused with
 // ErrUnsupportedInputFormat. The input is text, which libvips reads as no
 // format.
 func TestImageProcessor_NotASourceFormatRefused(t *testing.T) {

internal/imageprocessor/svg_internal_test.go

@@ -0,0 +1,293 @@
+package imageprocessor
+
+import (
+	"bytes"
+	"errors"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+
+	"github.com/davidbyttow/govips/v2/vips"
+	"sneak.berlin/go/pixa/internal/imagerequest"
+)
+
+// testSVG is a 16x12 SVG, black on its left half and white on its right.
+const testSVG = `<svg xmlns="http://www.w3.org/2000/svg" width="16" height="12">` +
+	`<rect width="16" height="12" fill="white"/>` +
+	`<rect width="8" height="12" fill="black"/></svg>`
+
+// newSVGTestProcessor returns a processor for the SVG tests.
+func newSVGTestProcessor() *ImageProcessor {
+	return New(Params{MaxInputBytes: 1 << 20, MaxConcurrentProcessing: 1})
+}
+
+// processSVG processes svg, as an SVG source, with transform.
+func processSVG(
+	t *testing.T, svg string, transform imagerequest.Transform,
+) (*Result, []byte, error) {
+	t.Helper()
+
+	result, err := newSVGTestProcessor().Process(t.Context(),
+		bytes.NewReader([]byte(svg)), imagerequest.FormatSVG, &transform)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	output, err := io.ReadAll(result.Content)
+	if err != nil {
+		t.Fatalf("reading the output: %v", err)
+	}
+
+	return result, output, nil
+}
+
+// TestImageProcessor_SVGOrigIsTheSVG checks that orig of an SVG at the orig
+// size is the SVG itself, never another format, and that orig at another
+// size is ErrSVGNotOriginalSize.
+func TestImageProcessor_SVGOrigIsTheSVG(t *testing.T) {
+	t.Parallel()
+
+	result, output, err := processSVG(t, testSVG,
+		imagerequest.Transform{Format: imagerequest.FormatOriginal})
+	if err != nil {
+		t.Fatalf("orig of the SVG: %v", err)
+	}
+
+	t.Logf("orig of the SVG: %s, %dx%d", result.ContentType, result.Width,
+		result.Height)
+
+	if result.ContentType != "image/svg+xml" || string(output) != testSVG {
+		t.Errorf("orig of the SVG = %s %q, want image/svg+xml %q",
+			result.ContentType, output, testSVG)
+	}
+
+	_, _, err = processSVG(t, testSVG, imagerequest.Transform{
+		Size:   imagerequest.Size{Width: 32, Height: 24},
+		Format: imagerequest.FormatOriginal,
+	})
+	if !errors.Is(err, ErrSVGNotOriginalSize) {
+		t.Errorf("orig of the SVG at 32x24: error = %v, want %v", err,
+			ErrSVGNotOriginalSize)
+	}
+}
+
+// TestImageProcessor_RendersSVGToEachRasterFormat checks that an SVG is
+// rendered to each raster format at the requested size.
+func TestImageProcessor_RendersSVGToEachRasterFormat(t *testing.T) {
+	t.Parallel()
+
+	for _, format := range []imagerequest.Format{
+		imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
+		imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
+	} {
+		result, output, err := processSVG(t, testSVG, imagerequest.Transform{
+			Size:   imagerequest.Size{Width: 40, Height: 30},
+			Format: format,
+		})
+		if err != nil {
+			t.Errorf("SVG as %s: %v", format, err)
+
+			continue
+		}
+
+		t.Logf("SVG as %s: %s, %dx%d, %d bytes", format, result.ContentType,
+			result.Width, result.Height, len(output))
+
+		if result.ContentType != format.MIMEType() ||
+			vips.DetermineImageType(output) != vipsImageType(format) ||
+			result.Width != 40 || result.Height != 30 {
+			t.Errorf("SVG as %s = %s, %dx%d; want %s, 40x30", format,
+				result.ContentType, result.Width, result.Height, format.MIMEType())
+		}
+	}
+}
+
+// TestImageProcessor_RendersSVGSharpWhenEnlarged checks that a 16x12 SVG
+// asked for at 1600x1200 is rendered at that size, not rendered at 16x12 and
+// enlarged: 10 pixels either side of the edge between its black and white
+// halves are black and white, where an enlarged image is grey there.
+func TestImageProcessor_RendersSVGSharpWhenEnlarged(t *testing.T) {
+	t.Parallel()
+
+	_, output, err := processSVG(t, testSVG, imagerequest.Transform{
+		Size:   imagerequest.Size{Width: 1600, Height: 1200},
+		Format: imagerequest.FormatPNG,
+	})
+	if err != nil {
+		t.Fatalf("SVG as PNG at 1600x1200: %v", err)
+	}
+
+	img, err := vips.NewImageFromBuffer(output)
+	if err != nil {
+		t.Fatalf("decoding the PNG: %v", err)
+	}
+
+	t.Cleanup(img.Close)
+
+	for x, want := range map[int]float64{790: 0, 810: 255} {
+		point, err := img.GetPoint(x, 600)
+		if err != nil {
+			t.Fatalf("GetPoint(%d, 600): %v", x, err)
+		}
+
+		t.Logf("pixel at %d,600: %v", x, point)
+
+		if point[0] != want {
+			t.Errorf("pixel at %d,600 = %v, want %v", x, point[0], want)
+		}
+	}
+}
+
+// TestImageProcessor_SVGFetchesNothing checks that rendering an SVG that
+// refers to an image and an external entity on a local server makes no
+// request to that server.
+func TestImageProcessor_SVGFetchesNothing(t *testing.T) {
+	t.Parallel()
+
+	var requests atomic.Int64
+
+	png := createTestPNG(t, 4, 4)
+
+	server := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			requests.Add(1)
+			t.Logf("request for %s", r.URL)
+			w.Header().Set("Content-Type", "image/png")
+			_, _ = w.Write(png)
+		}))
+	t.Cleanup(server.Close)
+
+	svg := `<?xml version="1.0"?>` +
+		`<!DOCTYPE svg [<!ENTITY outside SYSTEM "` + server.URL + `/entity">]>` +
+		`<svg xmlns="http://www.w3.org/2000/svg" ` +
+		`xmlns:xlink="http://www.w3.org/1999/xlink" width="16" height="12">` +
+		`<image href="` + server.URL + `/image.png" width="16" height="12"/>` +
+		`<image xlink:href="` + server.URL + `/xlink.png" width="16" height="12"/>` +
+		`<text y="10">&outside;</text></svg>`
+
+	_, _, err := processSVG(t, svg, imagerequest.Transform{
+		Format: imagerequest.FormatPNG,
+	})
+	t.Logf("SVG as PNG: error = %v", err)
+
+	if requests.Load() != 0 {
+		t.Errorf("rendering the SVG made %d requests, want none", requests.Load())
+	}
+}
+
+// TestImageProcessor_RendersSVGLargerThanMaxInputDimension checks that an
+// SVG whose own size is above MaxInputDimension is limited only by the
+// output checks: it is rendered at a raster size, orig of it is the SVG
+// itself, and a raster format at its own size is ErrOutputTooLarge. The
+// 1000000x1000000 one is rendered at a ten-thousandth of its own size.
+func TestImageProcessor_RendersSVGLargerThanMaxInputDimension(t *testing.T) {
+	t.Parallel()
+
+	for _, svg := range []string{
+		`<svg xmlns="http://www.w3.org/2000/svg" width="10000" height="10">` +
+			`<rect width="10000" height="10"/></svg>`,
+		`<svg xmlns="http://www.w3.org/2000/svg" width="1000000" ` +
+			`height="1000000"><rect width="1000000" height="1000000"/></svg>`,
+	} {
+		result, _, err := processSVG(t, svg, imagerequest.Transform{
+			Size:   imagerequest.Size{Width: 100, Height: 100},
+			Format: imagerequest.FormatPNG,
+		})
+		if err != nil {
+			t.Errorf("%s as PNG at 100x100: %v", svg, err)
+		} else {
+			t.Logf("%s as PNG at 100x100: %dx%d", svg, result.Width, result.Height)
+
+			if result.Width != 100 || result.Height != 100 {
+				t.Errorf("%s as PNG at 100x100 = %dx%d, want 100x100", svg,
+					result.Width, result.Height)
+			}
+		}
+
+		result, output, err := processSVG(t, svg,
+			imagerequest.Transform{Format: imagerequest.FormatOriginal})
+		if err != nil || result.ContentType != imagerequest.FormatSVG.MIMEType() ||
+			string(output) != svg {
+			t.Errorf("orig of %s: error = %v, want the SVG itself", svg, err)
+		}
+
+		_, _, err = processSVG(t, svg,
+			imagerequest.Transform{Format: imagerequest.FormatPNG})
+		if !errors.Is(err, ErrOutputTooLarge) {
+			t.Errorf("%s as PNG at its own size: error = %v, want %v", svg,
+				err, ErrOutputTooLarge)
+		}
+	}
+}
+
+// TestImageProcessor_RefusesSVGTooThin checks that an SVG with one side more
+// than MaxInputDimension times the other is ErrSVGTooThin at a raster size,
+// that one at exactly that proportion is rendered, and that orig of either
+// is the SVG itself.
+func TestImageProcessor_RefusesSVGTooThin(t *testing.T) {
+	t.Parallel()
+
+	tooThin := `<svg xmlns="http://www.w3.org/2000/svg" width="81930" ` +
+		`height="10"><rect width="81930" height="10"/></svg>`
+	atTheLimit := `<svg xmlns="http://www.w3.org/2000/svg" width="81920" ` +
+		`height="10"><rect width="81920" height="10"/></svg>`
+	size := imagerequest.Size{Width: 100, Height: 100}
+
+	_, _, err := processSVG(t, tooThin,
+		imagerequest.Transform{Size: size, Format: imagerequest.FormatPNG})
+	if !errors.Is(err, ErrSVGTooThin) {
+		t.Errorf("81930x10 SVG as PNG at 100x100: error = %v, want %v", err,
+			ErrSVGTooThin)
+	}
+
+	result, _, err := processSVG(t, atTheLimit,
+		imagerequest.Transform{Size: size, Format: imagerequest.FormatPNG})
+	if err != nil {
+		t.Errorf("81920x10 SVG as PNG at 100x100: %v", err)
+	} else if result.Width != 100 || result.Height != 100 {
+		t.Errorf("81920x10 SVG as PNG at 100x100 = %dx%d, want 100x100",
+			result.Width, result.Height)
+	}
+
+	for _, svg := range []string{tooThin, atTheLimit} {
+		result, output, err := processSVG(t, svg,
+			imagerequest.Transform{Format: imagerequest.FormatOriginal})
+		if err != nil || result.ContentType != imagerequest.FormatSVG.MIMEType() ||
+			string(output) != svg {
+			t.Errorf("orig of %s: error = %v, want the SVG itself", svg, err)
+		}
+	}
+}
+
+// TestSVGRenderSize checks the size at which an SVG is rendered to cover an
+// output size, and that it is held to MaxInputDimension.
+func TestSVGRenderSize(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name                      string
+		width, height             int
+		outputWidth, outputHeight int
+		wantWidth, wantHeight     int
+	}{
+		{"own size", 16, 12, 16, 12, 16, 12},
+		{"100 times larger", 16, 12, 1600, 1200, 1600, 1200},
+		{"wider than the SVG's proportions", 16, 12, 160, 12, 160, 120},
+		{"10 times smaller", 100, 100, 10, 10, 10, 10},
+		{"held to MaxInputDimension", 8192, 1, 8192, 8192, 8192, 1},
+		{"held to MaxInputDimension when enlarged", 1024, 1, 8192, 8192, 8192, 8},
+		{"far above MaxInputDimension", 1000000, 1000000, 100, 100, 100, 100},
+	}
+
+	for _, tt := range tests {
+		gotWidth, gotHeight := svgRenderSize(tt.width, tt.height,
+			tt.outputWidth, tt.outputHeight)
+		if gotWidth != tt.wantWidth || gotHeight != tt.wantHeight {
+			t.Errorf("%s: svgRenderSize(%d, %d, %d, %d) = %dx%d, want %dx%d",
+				tt.name, tt.width, tt.height, tt.outputWidth, tt.outputHeight,
+				gotWidth, gotHeight, tt.wantWidth, tt.wantHeight)
+		}
+	}
+}