pixa/internal/imageprocessor/imageprocessor.go

// Package imageprocessor provides image format conversion and resizing using libvips.
package imageprocessor

import (
	"bytes"
	"context"
	"errors"
	"fmt"
	"io"
	"runtime"
	"sync"
	"time"

	"github.com/davidbyttow/govips/v2/vips"
)

// vipsOnce ensures vips is initialized exactly once.
//
//nolint:gochecknoglobals // package-level sync.Once for one-time vips init
var vipsOnce sync.Once

// initVips initializes libvips with quiet logging, one worker thread per
// image and no operation cache. Process already works on one image per CPU
// by default, so more threads per image would only compete for the CPUs.
// Each request decodes different source bytes, so the operation cache
// would rarely be hit and would hold memory outside MaxConcurrentProcessing;
// repeated requests are served from pixa's disk cache instead.
func initVips() {
	vipsOnce.Do(func() {
		vips.LoggingSettings(nil, vips.LogLevelError)
		vips.Startup(&vips.Config{
			ConcurrencyLevel: 1,
			MaxCacheSize:     0,
			MaxCacheMem:      0,
			MaxCacheFiles:    0,
		})
	})
}

// errNoJPEGXL is returned by CheckJPEGXLSupport.
var errNoJPEGXL = errors.New("libvips lacks JPEG XL support: install " +
	"vips-jxl on Alpine, or use a libvips built with libjxl")

// CheckJPEGXLSupport returns an error, naming the fix, when libvips
// cannot load and save JPEG XL.
func CheckJPEGXLSupport() error {
	initVips()

	// govips counts a format as supported when libvips has its loader;
	// libvips builds the JPEG XL loader and saver together.
	if !vips.IsTypeSupported(vips.ImageTypeJXL) {
		return errNoJPEGXL
	}

	return nil
}

// Format represents supported output image formats.
type Format string

// Supported image output formats.
const (
	FormatOriginal Format = "orig"
	FormatJPEG     Format = "jpeg"
	FormatPNG      Format = "png"
	FormatWebP     Format = "webp"
	FormatAVIF     Format = "avif"
	FormatJXL      Format = "jxl"
	FormatGIF      Format = "gif"
)

// FitMode represents how to fit an image into requested dimensions.
type FitMode string

// Supported image fit modes.
const (
	FitCover   FitMode = "cover"
	FitContain FitMode = "contain"
	FitFill    FitMode = "fill"
	FitInside  FitMode = "inside"
	FitOutside FitMode = "outside"
)

// ErrInvalidFitMode is returned when an invalid fit mode is provided.
var ErrInvalidFitMode = errors.New("invalid fit mode")

// Size represents requested image dimensions.
type Size struct {
	Width  int
	Height int
}

// Request holds the parameters for image processing.
type Request struct {
	Size    Size
	Format  Format
	Quality int
	FitMode FitMode
}

// Result contains the output of image processing.
type Result struct {
	// Content is the processed image data.
	Content io.ReadCloser
	// ContentLength is the size in bytes.
	ContentLength int64
	// ContentType is the MIME type of the output.
	ContentType string
	// Width is the output image width.
	Width int
	// Height is the output image height.
	Height int
	// InputWidth is the original image width before processing.
	InputWidth int
	// InputHeight is the original image height before processing.
	InputHeight int
	// InputFormat is the detected input format (e.g., "jpeg", "png").
	InputFormat string
}

// MaxInputDimension is the maximum allowed width or height for input images.
// Images larger than this are rejected to prevent DoS via decompression bombs.
const MaxInputDimension = 8192

// DefaultMaxInputBytes is the default maximum input size in bytes (50 MiB).
// This matches the default upstream fetcher limit.
const DefaultMaxInputBytes = 50 << 20

// ErrInputTooLarge is returned when input image dimensions exceed MaxInputDimension.
var ErrInputTooLarge = errors.New("input image dimensions exceed maximum")

// ErrInputDataTooLarge is returned when the raw input data exceeds the
// configured byte limit.
var ErrInputDataTooLarge = errors.New("input data exceeds maximum allowed size")

// ErrUnsupportedOutputFormat is returned when the requested output format is
// not supported.
var ErrUnsupportedOutputFormat = errors.New("unsupported output 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")

// ProcessingWaitTimeout is how long Process waits for a free slot when
// MaxConcurrentProcessing images are already being processed.
const ProcessingWaitTimeout = 10 * time.Second

// ImageProcessor implements image transformation using libvips via govips.
type ImageProcessor struct {
	maxInputBytes int64
	// processingSemaphore has one slot per image that may be processed at
	// once. Process holds a slot from before it reads its input until it
	// returns, so the input, the decoded image and the output all count.
	processingSemaphore chan struct{}
	// processingWaitTimeout is ProcessingWaitTimeout; tests shorten it.
	processingWaitTimeout time.Duration
}

// Params holds configuration for creating an ImageProcessor.
// Zero values use sensible defaults (MaxInputBytes defaults to DefaultMaxInputBytes).
type Params struct {
	// MaxInputBytes is the maximum allowed input size in bytes.
	// If <= 0, DefaultMaxInputBytes is used.
	MaxInputBytes int64
	// MaxConcurrentProcessing is the most images processed at once.
	// If <= 0, the number of CPUs Go uses (runtime.GOMAXPROCS(0)) is used.
	MaxConcurrentProcessing int
}

// New creates a new image processor with the given parameters.
// A zero-value Params{} uses sensible defaults.
func New(params Params) *ImageProcessor {
	initVips()

	maxInputBytes := params.MaxInputBytes
	if maxInputBytes <= 0 {
		maxInputBytes = DefaultMaxInputBytes
	}

	maxConcurrentProcessing := params.MaxConcurrentProcessing
	if maxConcurrentProcessing <= 0 {
		maxConcurrentProcessing = runtime.GOMAXPROCS(0)
	}

	return &ImageProcessor{
		maxInputBytes:         maxInputBytes,
		processingSemaphore:   make(chan struct{}, maxConcurrentProcessing),
		processingWaitTimeout: ProcessingWaitTimeout,
	}
}

// Process transforms an image according to the request. When
// MaxConcurrentProcessing images are already being processed, it waits up
// to ProcessingWaitTimeout for one to finish, then fails with
// ErrTooManyImages.
func (p *ImageProcessor) Process(
	ctx context.Context,
	input io.Reader,
	req *Request,
) (*Result, error) {
	release, err := p.acquireSlot(ctx)
	if err != nil {
		return nil, err
	}

	defer release()

	// Read input with a size limit to prevent unbounded memory consumption.
	// We read at most maxInputBytes+1 so we can detect if the input exceeds
	// the limit without consuming additional memory.
	limited := io.LimitReader(input, p.maxInputBytes+1)

	data, err := io.ReadAll(limited)
	if err != nil {
		return nil, fmt.Errorf("failed to read input: %w", err)
	}

	if int64(len(data)) > p.maxInputBytes {
		return nil, ErrInputDataTooLarge
	}

	// 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()

	// Detect input format
	inputFormat := p.detectFormat(img)

	// Validate input dimensions to prevent DoS via decompression bombs
	if origWidth > MaxInputDimension || origHeight > MaxInputDimension {
		return nil, ErrInputTooLarge
	}

	// Determine target dimensions
	targetWidth, targetHeight := targetDimensions(req.Size, origWidth, origHeight)

	// Resize if needed
	if targetWidth != origWidth || targetHeight != origHeight {
		err := p.resize(img, targetWidth, targetHeight, req.FitMode)
		if err != nil {
			return nil, fmt.Errorf("failed to resize: %w", err)
		}
	}

	// orig is the source's own format; encode refuses an empty format
	outputFormat := req.Format
	if outputFormat == FormatOriginal {
		outputFormat = p.formatFromString(inputFormat)
	}

	// Encode to target format
	output, err := p.encode(img, outputFormat, req.Quality)
	if err != nil {
		return nil, fmt.Errorf("failed to encode: %w", err)
	}

	return &Result{
		Content:       io.NopCloser(bytes.NewReader(output)),
		ContentLength: int64(len(output)),
		ContentType:   FormatToMIME(outputFormat),
		Width:         img.Width(),
		Height:        img.Height(),
		InputWidth:    origWidth,
		InputHeight:   origHeight,
		InputFormat:   inputFormat,
	}, nil
}

// targetDimensions calculates the output dimensions for a requested size,
// scaling proportionally when only one dimension is given and keeping the
// original dimensions when both are zero.
func targetDimensions(size Size, origWidth, origHeight int) (int, int) {
	switch {
	case size.Width == 0 && size.Height == 0:
		// Both are 0: keep original size
		return origWidth, origHeight
	case size.Width == 0:
		// Only height specified: calculate width proportionally
		return origWidth * size.Height / origHeight, size.Height
	case size.Height == 0:
		// Only width specified: calculate height proportionally
		return size.Width, origHeight * size.Width / origWidth
	default:
		return size.Width, size.Height
	}
}

// MIME types for the supported image formats.
const (
	mimeJPEG = "image/jpeg"
	mimePNG  = "image/png"
	mimeGIF  = "image/gif"
	mimeWebP = "image/webp"
	mimeAVIF = "image/avif"
	mimeJXL  = "image/jxl"
)

// SupportedInputFormats returns MIME types this processor can read.
func (p *ImageProcessor) SupportedInputFormats() []string {
	return []string{
		mimeJPEG,
		mimePNG,
		mimeGIF,
		mimeWebP,
		mimeAVIF,
		mimeJXL,
	}
}

// SupportedOutputFormats returns formats this processor can write.
func (p *ImageProcessor) SupportedOutputFormats() []Format {
	return []Format{
		FormatJPEG,
		FormatPNG,
		FormatGIF,
		FormatWebP,
		FormatAVIF,
		FormatJXL,
	}
}

// FormatToMIME converts a Format to its MIME type string.
func FormatToMIME(format Format) string {
	switch format {
	case FormatJPEG:
		return mimeJPEG
	case FormatPNG:
		return mimePNG
	case FormatWebP:
		return mimeWebP
	case FormatGIF:
		return mimeGIF
	case FormatAVIF:
		return mimeAVIF
	case FormatJXL:
		return mimeJXL
	case FormatOriginal:
		return "application/octet-stream"
	default:
		return "application/octet-stream"
	}
}

// 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
}

// acquireSlot takes a slot in processingSemaphore, waiting at most
// processingWaitTimeout for one to free up, and returns the func that gives
// it back. A free slot is taken even when ctx has ended; only the wait for
// one stops when ctx ends, as the rest of Process does not check ctx.
func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
	release := func() { <-p.processingSemaphore }

	select {
	case p.processingSemaphore <- struct{}{}:
		return release, nil
	default:
	}

	select {
	case p.processingSemaphore <- struct{}{}:
		return release, nil
	case <-time.After(p.processingWaitTimeout):
		return nil, ErrTooManyImages
	case <-ctx.Done():
		return nil, ctx.Err()
	}
}

// detectFormat returns the format string from a vips image.
func (p *ImageProcessor) detectFormat(img *vips.ImageRef) string {
	format := img.Format()
	switch format {
	case vips.ImageTypeJPEG:
		return "jpeg"
	case vips.ImageTypePNG:
		return "png"
	case vips.ImageTypeGIF:
		return "gif"
	case vips.ImageTypeWEBP:
		return "webp"
	case vips.ImageTypeAVIF, vips.ImageTypeHEIF:
		return string(FormatAVIF)
	case vips.ImageTypeJXL:
		return string(FormatJXL)
	case vips.ImageTypeUnknown, vips.ImageTypeMagick, vips.ImageTypePDF,
		vips.ImageTypeSVG, vips.ImageTypeTIFF, vips.ImageTypeBMP,
		vips.ImageTypeJP2K:
		return "unknown"
	default:
		return "unknown"
	}
}

// resize resizes the image according to the fit mode.
func (p *ImageProcessor) resize(
	img *vips.ImageRef, width, height int, fit FitMode,
) error {
	switch fit {
	case FitCover, "":
		// Resize and crop to fill exact dimensions (default)
		return img.Thumbnail(width, height, vips.InterestingCentre)

	case FitContain:
		// Resize to fit within dimensions, maintaining aspect ratio
		imgW, imgH := img.Width(), img.Height()
		scaleW := float64(width) / float64(imgW)
		scaleH := float64(height) / float64(imgH)
		scale := min(scaleW, scaleH)
		newW := int(float64(imgW) * scale)
		newH := int(float64(imgH) * scale)

		return img.Thumbnail(newW, newH, vips.InterestingNone)

	case FitFill:
		// Resize to exact dimensions (may distort)
		return img.ThumbnailWithSize(width, height, vips.InterestingNone, vips.SizeForce)

	case FitInside:
		// Same as contain, but only shrink
		if img.Width() <= width && img.Height() <= height {
			return nil // Already fits
		}

		imgW, imgH := img.Width(), img.Height()
		scaleW := float64(width) / float64(imgW)
		scaleH := float64(height) / float64(imgH)
		scale := min(scaleW, scaleH)
		newW := int(float64(imgW) * scale)
		newH := int(float64(imgH) * scale)

		return img.Thumbnail(newW, newH, vips.InterestingNone)

	case FitOutside:
		// Resize so smallest dimension fits, may exceed target on other dimension
		imgW, imgH := img.Width(), img.Height()
		scaleW := float64(width) / float64(imgW)
		scaleH := float64(height) / float64(imgH)
		scale := max(scaleW, scaleH)
		newW := int(float64(imgW) * scale)
		newH := int(float64(imgH) * scale)

		return img.Thumbnail(newW, newH, vips.InterestingNone)

	default:
		return fmt.Errorf("%w: %s", ErrInvalidFitMode, fit)
	}
}

const defaultQuality = 85

// encode encodes an image to the specified format.
func (p *ImageProcessor) encode(
	img *vips.ImageRef, format Format, quality int,
) ([]byte, error) {
	if quality <= 0 {
		quality = defaultQuality
	}

	// Stripping drops the ICC profile as well, and clients show an image
	// with no profile as sRGB, so convert to sRGB first. "srgb" names
	// libvips' built-in profile; govips' own sRGB path variable is set on
	// first use but read without a lock, so concurrent requests race on it.
	if img.HasICCProfile() {
		err := img.TransformICCProfileWithFallback("srgb", "srgb")
		if err != nil {
			return nil, fmt.Errorf("failed to convert to sRGB: %w", err)
		}
	}

	switch format {
	case FormatJPEG:
		return exportJPEG(img, quality)

	case FormatPNG:
		return exportPNG(img)

	case FormatGIF:
		return exportGIF(img)

	case FormatWebP:
		return exportWebP(img, quality)

	case FormatAVIF:
		return exportAVIF(img, quality)

	case FormatJXL:
		return exportJXL(img, quality)

	case FormatOriginal:
		return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)

	default:
		return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
	}
}

// govips sends libvips Go's zero value for some settings an export leaves
// out, such as no compression at all for PNG, so each export below sets
// every setting whose zero value is not what pixa wants. Stripping metadata
// drops EXIF, XMP, IPTC and the ICC profile.

// exportJPEG encodes img as JPEG at quality, without metadata. The settings
// it leaves out are at libvips' defaults.
func exportJPEG(img *vips.ImageRef, quality int) ([]byte, error) {
	output, _, err := img.ExportJpeg(&vips.JpegExportParams{
		StripMetadata: true,
		Quality:       quality,
	})

	return output, err
}

// pngCompression is libvips' default PNG compression, from 0 (none) to 9.
const pngCompression = 6

// exportPNG encodes img as PNG at libvips' default compression and row
// filter, without metadata.
func exportPNG(img *vips.ImageRef) ([]byte, error) {
	output, _, err := img.ExportPng(&vips.PngExportParams{
		StripMetadata: true,
		Compression:   pngCompression,
		Filter:        vips.PngFilterNone,
	})

	return output, err
}

// gifEffort is libvips' default GIF effort, from 1 to 10.
const gifEffort = 7

// exportGIF encodes img as GIF at libvips' default effort. govips cannot
// have libvips strip metadata from GIF, which carries none.
func exportGIF(img *vips.ImageRef) ([]byte, error) {
	output, _, err := img.ExportGIF(&vips.GifExportParams{Effort: gifEffort})

	return output, err
}

// webpEffort is libvips' default WebP effort, from 0 (fastest) to 6.
const webpEffort = 4

// exportWebP encodes img as lossy WebP at quality and libvips' default
// effort, without metadata.
func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
	output, _, err := img.ExportWebp(&vips.WebpExportParams{
		StripMetadata:   true,
		Quality:         quality,
		ReductionEffort: webpEffort,
	})

	return output, err
}

// avifEffort is the AVIF effort, from 0 (fastest) to 9; 1 is the lowest
// govips can set. With one thread, as pixad runs libvips, 1 takes about 51
// seconds to save an 8192x8192 image of random pixels, the worst case,
// against the default downstream_timeout of 60 seconds. On an image of
// milder noise, which 1 saves in about 12 seconds, 2 takes nearly a minute
// and libvips' default, 4, takes minutes.
const avifEffort = 1

// avifBitdepth is the AVIF bit depth, 8 bits per sample for every image.
// libvips would save a 16-bit image with 12, but at avifEffort that takes
// about 54 seconds for a 16-bit 8192x8192 image of milder noise, nearly all
// of the default downstream_timeout, and about 12 seconds with 8.
const avifBitdepth = 8

// exportAVIF encodes img as lossy AVIF at quality, avifEffort and
// avifBitdepth, without metadata.
func exportAVIF(img *vips.ImageRef, quality int) ([]byte, error) {
	output, _, err := img.ExportAvif(&vips.AvifExportParams{
		StripMetadata: true,
		Quality:       quality,
		Effort:        avifEffort,
		Bitdepth:      avifBitdepth,
	})

	return output, err
}

// jxlResolution is the resolution every JPEG XL image is saved with, in
// pixels per millimetre as libvips counts it: 72 dpi, what libvips gives a
// JPEG that names none.
const jxlResolution = 72 / 25.4

// exportJXL encodes img as JPEG XL at quality, with libvips' default effort
// and without metadata. govips sends libvips a distance, the JPEG XL
// encoder's own measure of quality, along with the quality, and libvips then
// uses the distance alone, so the quality is also given as a distance.
func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
	// libvips converts a CMYK image to sRGB before it saves WebP, AVIF or
	// PNG, but cannot save one as JPEG XL. encode has already converted
	// any image with an ICC profile to sRGB, so this is CMYK with none.
	if img.Interpretation() == vips.InterpretationCMYK {
		err := img.ToColorSpace(vips.InterpretationSRGB)
		if err != nil {
			return nil, fmt.Errorf("failed to convert CMYK to sRGB: %w", err)
		}
	}

	// govips cannot make libvips strip metadata from JPEG XL, so it is
	// removed from the image itself. RemoveMetadata removes EXIF, XMP and
	// IPTC but keeps the ICC profile.
	err := img.RemoveMetadata()
	if err != nil {
		return nil, err
	}

	err = img.RemoveICCProfile()
	if err != nil {
		return nil, err
	}

	// libvips 8.16 and later still write an EXIF block of their own, from
	// the image's size, orientation and resolution, and fixed values. The
	// image is upright, so its orientation is 1, but its resolution is still
	// the source's.
	toSave, err := img.CopyChangingResolution(jxlResolution, jxlResolution)
	if err != nil {
		return nil, err
	}

	defer toSave.Close()

	params := vips.NewJxlExportParams()
	params.Quality = quality
	params.Distance = jxlDistance(quality)

	output, _, err := toSave.ExportJxl(params)
	if err != nil {
		return nil, err
	}

	return output, nil
}

// jxlDistance turns a quality from 1 to 100 into the JPEG XL encoder's
// distance, with the formula libvips and libjxl use for their own quality
// setting, except that 100 stays lossy (distance 0.1) where libjxl makes it
// lossless.
//
//nolint:mnd // the constants of that formula
func jxlDistance(quality int) float64 {
	q := float64(quality)

	if quality >= 30 {
		return 0.1 + (100-q)*0.09
	}

	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 {
	switch format {
	case "jpeg":
		return FormatJPEG
	case "png":
		return FormatPNG
	case "gif":
		return FormatGIF
	case "webp":
		return FormatWebP
	case string(FormatAVIF):
		return FormatAVIF
	case string(FormatJXL):
		return FormatJXL
	default:
		return FormatJPEG
	}
}