Support SVG sources (closes #68)

The fetcher accepts image/svg+xml; internal/magic detects SVG. orig of
an SVG at the orig size is the SVG unchanged, cached, with a
Content-Security-Policy allowing only its styles and data: images; at
another size, ErrSVGNotOriginalSize (400). Any other format renders it
at the least size covering the output, at most 8192 on a side.
Rendering refuses an SVG with a side over 8192 times the other
(ErrSVGTooThin, 415), and the orig size of one above 8192 on a side
(ErrSVGTooLargeForOrigSize, 400). Child processes of pixad read an
SVG's size and render it, killed after 20 seconds and limited to 1 GiB;
any failure there is ErrSVGRenderFailed (415). Tests pinning the SVG
refusal now expect SVG.

Model: opus-5-5

internal/imageprocessor/imageprocessor.go

@@ -1,4 +1,7 @@
 // Package imageprocessor provides image format conversion and resizing using libvips.
+// It reads the size of an SVG source and renders it in child processes, each
+// the running program started again (see RunAsSVGChildProcess). pixa kills
+// them after SVGRenderTimeout, and each may use at most MaxSVGRenderMemory.
 package imageprocessor
 
 import (
@@ -7,6 +10,8 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
+	"strconv"
 	"sync"
 	"time"
 
@@ -113,10 +118,43 @@ 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")
+
+// ErrSVGTooLargeForOrigSize is returned, before rendering, when a format other
+// than orig asks for an SVG source at the orig size and the SVG has a side
+// above MaxOutputDimension.
+var ErrSVGTooLargeForOrigSize = errors.New(
+	"SVG source too large to render at its own size")
+
+// SVGRenderTimeout is how long the child processes that read the size of one
+// SVG source and render it may run, counted from the start of the first,
+// before pixa kills them.
+const SVGRenderTimeout = 20 * time.Second
+
+// MaxSVGRenderMemory is the most memory, in bytes, that each child process
+// reading the size of an SVG source or rendering it may use. It is the
+// child's RLIMIT_DATA, which limits its heap and its other private writable
+// memory.
+const MaxSVGRenderMemory = 1 << 30 // 1 GiB
+
+// ErrSVGRenderFailed is returned when a child process fails to read the size
+// of an SVG source or to render it: librsvg cannot read the SVG, or the
+// child takes more than SVGRenderTimeout or MaxSVGRenderMemory.
+var ErrSVGRenderFailed = errors.New("SVG source could not be rendered")
+
 // 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")
@@ -134,6 +172,10 @@ type ImageProcessor struct {
 	processingSemaphore chan struct{}
 	// processingWaitTimeout is ProcessingWaitTimeout; tests shorten it.
 	processingWaitTimeout time.Duration
+	// svgRenderTimeout is SVGRenderTimeout; tests shorten it.
+	svgRenderTimeout time.Duration
+	// maxSVGRenderMemory is MaxSVGRenderMemory; tests lower it.
+	maxSVGRenderMemory int
 }
 
 // Params holds configuration for creating an ImageProcessor. Both fields
@@ -153,6 +195,8 @@ func New(params Params) *ImageProcessor {
 		maxInputBytes:         params.MaxInputBytes,
 		processingSemaphore:   make(chan struct{}, params.MaxConcurrentProcessing),
 		processingWaitTimeout: ProcessingWaitTimeout,
+		svgRenderTimeout:      SVGRenderTimeout,
+		maxSVGRenderMemory:    MaxSVGRenderMemory,
 	}
 }
 
@@ -164,7 +208,10 @@ 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. Child processes read an SVG's size
+// and render it, as processSVG describes.
 func (p *ImageProcessor) Process(
 	ctx context.Context,
 	input io.Reader,
@@ -183,35 +230,18 @@ func (p *ImageProcessor) Process(
 		return nil, err
 	}
 
-	// Input libvips would not load as sourceFormat is refused before it is
-	// decoded
-	err = checkInputFormat(data, sourceFormat)
+	if sourceFormat == imagerequest.FormatSVG {
+		return p.processSVG(ctx, data, transform)
+	}
+
+	img, err := loadImage(data, sourceFormat)
 	if err != nil {
 		return nil, err
 	}
-
-	// Decode image
-	img, err := vips.NewImageFromBuffer(data)
-	if err != nil {
-		return nil, fmt.Errorf("failed to decode image: %w", 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)
-	}
-
-	// 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
-	}
+	origWidth, origHeight := img.Width(), img.Height()
+	outputFormat := resolveOutputFormat(transform.Format, sourceFormat)
 
 	// Determine target dimensions; too large ones are refused before resizing
 	targetWidth, targetHeight, err := targetDimensions(transform.Size,
@@ -220,12 +250,6 @@ 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,
@@ -242,8 +266,104 @@ func (p *ImageProcessor) Process(
 		}
 	}
 
-	// Encode to target format
-	output, err := p.encode(ctx, img, outputFormat, transform.Quality)
+	return p.encodeResult(ctx, img, outputFormat, transform.Quality,
+		origWidth, origHeight)
+}
+
+// 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
+// holds them all, or until ctx ends, then gives back the slots it took.
+func (p *ImageProcessor) WaitForProcessing(ctx context.Context) int {
+	taken := 0
+
+	defer func() {
+		for range taken {
+			<-p.processingSemaphore
+		}
+	}()
+
+	for taken < cap(p.processingSemaphore) {
+		select {
+		case p.processingSemaphore <- struct{}{}:
+			taken++
+		case <-ctx.Done():
+			return len(p.processingSemaphore) - taken
+		}
+	}
+
+	return 0
+}
+
+// processSVG is Process for an SVG source, data. Apart from the first-bytes
+// check, pixad hands the SVG to libvips only in child processes (see
+// runSVGChildProcess). One reads the SVG's size. For a raster format a second
+// renders it as PNG, which is then resized and encoded as any other image.
+// pixa kills them once svgRenderTimeout has passed since the first one
+// started.
+func (p *ImageProcessor) processSVG(
+	ctx context.Context, data []byte, transform *imagerequest.Transform,
+) (*Result, error) {
+	err := checkInputFormat(data, imagerequest.FormatSVG)
+	if err != nil {
+		return nil, err
+	}
+
+	deadline := time.Now().Add(p.svgRenderTimeout)
+
+	origWidth, origHeight, err := p.readSVGSize(ctx, deadline, data)
+	if err != nil {
+		return nil, err
+	}
+
+	outputFormat := resolveOutputFormat(transform.Format, imagerequest.FormatSVG)
+	if outputFormat == imagerequest.FormatSVG {
+		return svgAsItIs(data, transform.Size, origWidth, origHeight)
+	}
+
+	err = checkSVGOrigSize(transform.Size, origWidth, origHeight)
+	if err != nil {
+		return nil, err
+	}
+
+	targetWidth, targetHeight, err := targetDimensions(transform.Size,
+		origWidth, origHeight)
+	if err != nil {
+		return nil, err
+	}
+
+	outputWidth, outputHeight, err := outputDimensions(origWidth, origHeight,
+		targetWidth, targetHeight, transform.FitMode, outputFormat)
+	if err != nil {
+		return nil, err
+	}
+
+	// The SVG is rendered at about the output size, to stay sharp
+	img, err := p.renderSVG(ctx, deadline, data, origWidth, origHeight,
+		outputWidth, outputHeight)
+	if err != nil {
+		return nil, err
+	}
+	defer img.Close()
+
+	if targetWidth != origWidth || targetHeight != origHeight {
+		err := p.resize(img, outputWidth, outputHeight, transform.FitMode)
+		if err != nil {
+			return nil, fmt.Errorf("failed to resize: %w", err)
+		}
+	}
+
+	return p.encodeResult(ctx, img, outputFormat, transform.Quality,
+		origWidth, origHeight)
+}
+
+// encodeResult encodes img as format at quality and returns it as the result
+// for a source of origWidth x origHeight.
+func (p *ImageProcessor) encodeResult(
+	ctx context.Context, img *vips.ImageRef, format imagerequest.Format,
+	quality, origWidth, origHeight int,
+) (*Result, error) {
+	output, err := p.encode(ctx, img, format, quality)
 	if err != nil {
 		return nil, fmt.Errorf("failed to encode: %w", err)
 	}
@@ -251,7 +371,7 @@ func (p *ImageProcessor) Process(
 	return &Result{
 		Content:       io.NopCloser(bytes.NewReader(output)),
 		ContentLength: int64(len(output)),
-		ContentType:   outputFormat.MIMEType(),
+		ContentType:   format.MIMEType(),
 		Width:         img.Width(),
 		Height:        img.Height(),
 		InputWidth:    origWidth,
@@ -290,29 +410,125 @@ func targetDimensions(
 	return width, height, 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
-// holds them all, or until ctx ends, then gives back the slots it took.
-func (p *ImageProcessor) WaitForProcessing(ctx context.Context) int {
-	taken := 0
-
-	defer func() {
-		for range taken {
-			<-p.processingSemaphore
-		}
-	}()
-
-	for taken < cap(p.processingSemaphore) {
-		select {
-		case p.processingSemaphore <- struct{}{}:
-			taken++
-		case <-ctx.Done():
-			return len(p.processingSemaphore) - taken
-		}
+// 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 0
+	return format
+}
+
+// loadImage refuses data that libvips would not load as sourceFormat, then
+// decodes it 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.
+func loadImage(
+	data []byte, sourceFormat imagerequest.Format,
+) (*vips.ImageRef, error) {
+	err := checkInputFormat(data, sourceFormat)
+	if err != nil {
+		return nil, err
+	}
+
+	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 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
+}
+
+// checkSVGOrigSize returns ErrSVGTooLargeForOrigSize when size is the orig
+// size and the SVG source, of width x height, has a side above
+// MaxOutputDimension. processSVG calls it after returning orig of the SVG, so
+// the SVG would be rendered at its own size.
+func checkSVGOrigSize(size imagerequest.Size, width, height int) error {
+	if size.OriginalSize() && max(width, height) > MaxOutputDimension {
+		return fmt.Errorf("%w: %dx%d is above %d", ErrSVGTooLargeForOrigSize,
+			width, height, MaxOutputDimension)
+	}
+
+	return 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, in a child process that pixa
+// kills at deadline (see runSVGChildProcess). It returns the rendered image,
+// read from the child's PNG. An SVG with one side more than
+// MaxInputDimension times the other is ErrSVGTooThin.
+func (p *ImageProcessor) renderSVG(
+	ctx context.Context, deadline time.Time, 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)
+
+	png, err := p.runSVGChildProcess(ctx, deadline, data,
+		renderSVGAsPNGArgument, strconv.Itoa(renderWidth),
+		strconv.Itoa(renderHeight))
+	if err != nil {
+		return nil, err
+	}
+
+	return loadImage(png, imagerequest.FormatPNG)
 }
 
 // acquireSlot takes a slot in processingSemaphore, waiting at most
@@ -397,6 +613,8 @@ 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 +793,9 @@ 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: