pixa/internal/imgcache/source_content_internal_test.go

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
// for two source URLs and checks that each URL has a source_content row of
// its own and a file of its own, named by its source key under
// cache/sources/<ab>/<cd>/.
func TestPutSource_StoresIdenticalBytesOfTwoURLsTwice(t *testing.T) {
	t.Parallel()

	cache, stateDir := newEvictionTestCache(t, 1<<30)
	content := bytes.Repeat([]byte{0x5A}, 400)

	keys := map[string]imagerequest.SourceKey{
		"/a.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/a.jpg", content),
		"/b.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/b.jpg", content),
	}
	t.Logf("source keys: %v", keys)

	if keys["/a.jpg"] == keys["/b.jpg"] {
		t.Fatalf("both source URLs got the key %s", keys["/a.jpg"])
	}

	for sourcePath, key := range keys {
		rows := countRows(t, cache,
			`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key))
		if rows != 1 {
			t.Errorf("%s has %d source_content rows, want 1", sourcePath, rows)
		}

		name := string(key)
		file := filepath.Join(stateDir, "cache", "sources", name[0:2], name[2:4], name)

		stored, err := os.ReadFile(file) //nolint:gosec // path in the test's state dir
		if err != nil || !bytes.Equal(stored, content) {
			t.Errorf("file of %s at %s holds %d bytes (error %v), want the %d stored",
				sourcePath, file, len(stored), err, len(content))
		}
	}

	usage, err := cache.UsageBytes(t.Context())
	if err != nil {
		t.Fatalf("UsageBytes() error = %v", err)
	}

	if usage != 800 {
		t.Errorf("UsageBytes() = %d, want 800, the 400 bytes once for each URL", usage)
	}
}

// TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed stores the same
// bytes for two source URLs and evicts the first. Its row and file must be
// gone, and the second must still be found and read from the cache.
func TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed(t *testing.T) {
	t.Parallel()

	cache, _ := newEvictionTestCache(t, 1<<30)
	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)

	err := cache.evictSourceBlob(t.Context(), evicted)
	if err != nil {
		t.Fatalf("evictSourceBlob() error = %v", err)
	}

	_, err = os.Stat(cache.srcContent.keyToPath(string(evicted)))
	if err == nil {
		t.Error("the evicted source's file is still on disk")
	}

	if n := countRows(t, cache,
		`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(evicted),
	); n != 0 {
		t.Errorf("the evicted source still has %d source_content rows", n)
	}

	reader, _, _, err := cache.Source(t.Context(),
		imagerequest.Source{Host: testHostCDN, Path: "/kept.jpg"})
	t.Logf("Source() of the kept source: error %v", err)

	if err != nil {
		t.Fatalf("Source() of the kept source error = %v; want it cached", err)
	}

	defer func() { _ = reader.Close() }()

	served, err := io.ReadAll(reader)
	if err != nil {
		t.Fatalf("reading the kept source: %v", err)
	}

	if !bytes.Equal(served, content) {
		t.Errorf("the kept source reads as %d bytes, want the %d stored",
			len(served), len(content))
	}
}

// TestPutSource_FailedRowWriteLeavesNoFile drops source_content, so that
// PutSource cannot write the source's row, and checks that the store fails
// and leaves no file under the source's key.
func TestPutSource_FailedRowWriteLeavesNoFile(t *testing.T) {
	t.Parallel()

	cache, _ := newEvictionTestCache(t, 1<<30)

	_, err := cache.db.ExecContext(t.Context(), `DROP TABLE source_content`)
	if err != nil {
		t.Fatalf("failed to drop source_content: %v", err)
	}

	req := &imagerequest.Request{
		Source: imagerequest.Source{Host: testHostCDN, Path: testPathCat},
	}
	key, err := cache.PutSource(t.Context(), req.Source,
		bytes.NewReader([]byte("source bytes")), SourceInfo{})
	t.Logf("PutSource() = %q, error = %v", key, err)

	if err == nil {
		t.Error("PutSource() error = nil, want the failed row write")
	}

	_, err = os.Stat(cache.srcContent.keyToPath(string(req.Source.Key())))
	if err == nil {
		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), SourceInfo{})
		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)
		}
	}
}