Detect a fetched image's format from its bytes once (closes #319)

magic.DetectFormat returns an imagerequest.Format. ValidateMagicBytes
returns the format it checked against the upstream Content-Type. The
cache reads a cached source's format from its file's first bytes, as it
reads a variant's. The proxy hands the format to Process. Process
refuses a format that is not a source format, and input libvips would
load with another loader, such as an SVG passing as AVIF.
Format.MIMEType declares each MIME string once, and the fetcher, the
cache's variant read and the Accept matching use it. magic.MIMEType,
magic.ImageFormat, MIMEToImageFormat, magic's SVG detection,
detectFormat, formatFromString, FormatToMIME and Result.InputFormat are
gone.

Model: opus-5-5

internal/imgcache/source_content_internal_test.go

@@ -2,12 +2,17 @@ package imgcache
 
 import (
 	"bytes"
+	"errors"
+	"fmt"
+	"image/color"
 	"io"
 	"os"
 	"path/filepath"
 	"testing"
 
+	"sneak.berlin/go/pixa/internal/imageprocessor"
 	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/magic"
 )
 
 // TestPutSource_StoresIdenticalBytesOfTwoURLsTwice stores the same bytes
@@ -64,7 +69,7 @@ func TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed(t *testing.T) {
 	t.Parallel()
 
 	cache, _ := newEvictionTestCache(t, 1<<30)
-	content := bytes.Repeat([]byte{0x5B}, 400)
+	content := generateTestJPEG(t, 20, 20, color.RGBA{0x5B, 0x5B, 0x5B, 255})
 
 	evicted := storeEvictionTestSource(t, cache, testHostCDN, "/evicted.jpg", content)
 	storeEvictionTestSource(t, cache, testHostCDN, "/kept.jpg", content)
@@ -85,7 +90,7 @@ func TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed(t *testing.T) {
 		t.Errorf("the evicted source still has %d source_content rows", n)
 	}
 
-	reader, _, err := cache.Source(t.Context(),
+	reader, _, _, err := cache.Source(t.Context(),
 		imagerequest.Source{Host: testHostCDN, Path: "/kept.jpg"})
 	t.Logf("Source() of the kept source: error %v", err)
 
@@ -135,3 +140,99 @@ func TestPutSource_FailedRowWriteLeavesNoFile(t *testing.T) {
 		t.Error("the source's file is on disk although its row was not written")
 	}
 }
+
+// TestSource_FormatFromFirstBytes stores an image in each source format
+// under one source URL, in turn. After each store, Source must return that
+// image whole, with its format read from the file.
+func TestSource_FormatFromFirstBytes(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+	processor := imageprocessor.New(imageprocessor.Params{
+		MaxInputBytes:           50 << 20,
+		MaxConcurrentProcessing: 1,
+	})
+	jpegImage := generateTestJPEG(t, 40, 30, color.RGBA{200, 40, 40, 255})
+	src := imagerequest.Source{Host: testHostCDN, Path: testPathCat}
+
+	for _, format := range []imagerequest.Format{
+		imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
+		imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
+	} {
+		result, err := processor.Process(t.Context(), bytes.NewReader(jpegImage),
+			imagerequest.FormatJPEG, &imagerequest.Transform{Format: format})
+		if err != nil {
+			t.Fatalf("making a %s image: %v", format, err)
+		}
+
+		image, err := io.ReadAll(result.Content)
+		if err != nil {
+			t.Fatalf("reading the %s image: %v", format, err)
+		}
+
+		_, err = cache.PutSource(t.Context(), src, bytes.NewReader(image))
+		if err != nil {
+			t.Fatalf("PutSource(%s) error = %v", format, err)
+		}
+
+		reader, size, got, err := cache.Source(t.Context(), src)
+		if err != nil {
+			t.Fatalf("Source() of the %s image error = %v", format, err)
+		}
+
+		served, err := io.ReadAll(reader)
+		_ = reader.Close()
+
+		if err != nil {
+			t.Fatalf("reading the %s source: %v", format, err)
+		}
+
+		t.Logf("%s: %d bytes read as %s", format, size, got)
+
+		if got != format {
+			t.Errorf("Source() of the %s image format = %q, want %q",
+				format, got, format)
+		}
+
+		if size != int64(len(image)) || !bytes.Equal(served, image) {
+			t.Errorf("%s source read as %d bytes, size %d, want the %d bytes stored",
+				format, len(served), size, len(image))
+		}
+	}
+}
+
+// TestSource_RefusesFileOfNoSourceFormat checks that Source refuses a
+// cached source whose file's first bytes are not those of a source format,
+// with an error other than ErrNotFound.
+func TestSource_RefusesFileOfNoSourceFormat(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+	jpegImage := generateTestJPEG(t, 10, 10, color.RGBA{0, 0, 255, 255})
+
+	tests := []struct {
+		name    string
+		content []byte
+		wantErr error
+	}{
+		{"text", []byte("this is text, not an image"), magic.ErrUnknownFormat},
+		{"SVG", []byte(`<svg xmlns="http://www.w3.org/2000/svg"></svg>`),
+			magic.ErrUnknownFormat},
+		{"JPEG cut to 10 bytes", jpegImage[:10], io.EOF},
+		{"empty file", nil, io.EOF},
+	}
+
+	for i, tt := range tests {
+		path := fmt.Sprintf("/refused%d.jpg", i)
+		storeEvictionTestSource(t, cache, testHostCDN, path, tt.content)
+
+		reader, _, format, err := cache.Source(t.Context(),
+			imagerequest.Source{Host: testHostCDN, Path: path})
+		t.Logf("%s: Source() error = %v", tt.name, err)
+
+		if reader != nil || format != "" || !errors.Is(err, tt.wantErr) {
+			t.Errorf("%s: Source() = reader %v, format %q, error %v; "+
+				"want no reader and %v", tt.name, reader, format, err, tt.wantErr)
+		}
+	}
+}