Use google/go-containerregistry to parse OCI images in packaging tests

Author: swiatekm

dev-tools/packaging/testing/package_test.go

@@ -17,7 +17,6 @@ import (
 	"debug/buildinfo"
 	"debug/elf"
 	"encoding/hex"
-	"encoding/json"
 	"errors"
 	"flag"
 	"fmt"
@@ -34,6 +33,7 @@ import (
 
 	"github.com/blakesmith/ar"
 	"github.com/cavaliergopher/rpm"
+	"github.com/google/go-containerregistry/pkg/v1/tarball"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -1082,60 +1082,80 @@ func openZip(zipFile string) (*zip.ReadCloser, error) {
 func readDocker(t *testing.T, dockerFile string, filterWorkingDir bool) (*packageFile, *dockerInfo, error) {
 	t.Helper()
 
-	// Read the manifest file first so that the config file and layer
-	// names are known in advance.
-	manifest, err := getDockerManifest(dockerFile)
+	// Decompress the .tar.gz file, go-containerregistry wants uncompressed here
+	f, err := os.Open(dockerFile)
 	require.NoError(t, err)
 
-	file, err := os.Open(dockerFile)
+	gz, err := gzip.NewReader(f)
 	require.NoError(t, err)
-	defer file.Close()
 
-	var info *dockerInfo
+	tempDir := t.TempDir()
+	uncompressed, err := os.CreateTemp(tempDir, "docker")
+	require.NoError(t, err)
 
-	stat, err := file.Stat()
+	_, err = io.Copy(uncompressed, gz)
 	require.NoError(t, err)
+	require.NoError(t, uncompressed.Close())
 
-	layers := make(map[string]*packageFile)
+	opener := func() (io.ReadCloser, error) {
+		return os.Open(uncompressed.Name())
+	}
 
-	gzipReader, err := gzip.NewReader(file)
-	require.NoError(t, err)
-	defer gzipReader.Close()
+	// Load the Docker image tarball using go-containerregistry
+	img, err := tarball.Image(opener, nil)
+	require.NoError(t, err, "failed to load Docker image from %s", dockerFile)
 
-	tarReader := tar.NewReader(gzipReader)
-	for {
-		header, err := tarReader.Next()
-		if err != nil {
-			if errors.Is(err, io.EOF) {
-				break
-			}
-			require.NoError(t, err)
-		}
+	// Get the config file which contains entrypoint, labels, user, workingDir
+	configFile, err := img.ConfigFile()
+	require.NoError(t, err, "failed to get config file from image")
 
-		switch {
-		case header.Name == manifest.Config:
-			info, err = readDockerInfo(tarReader)
-			require.NoError(t, err)
-		case slices.Contains(manifest.Layers, header.Name):
-			layer, err := readTarContents(header.Name, tarReader)
-			require.NoError(t, err)
-			layers[header.Name] = layer
-		}
+	imgSize, err := img.Size()
+	require.NoError(t, err, "failed to get image size")
+	info := &dockerInfo{
+		Size: imgSize,
 	}
+	info.Config.Entrypoint = configFile.Config.Entrypoint
+	info.Config.Labels = configFile.Config.Labels
+	info.Config.User = configFile.Config.User
+	info.Config.WorkingDir = configFile.Config.WorkingDir
 
 	require.NotZero(t, len(info.Config.Entrypoint), "no entrypoint")
 	workingDir := info.Config.WorkingDir
 	entrypoint := info.Config.Entrypoint[0]
 
+	// Get all layers and read their contents
+	layers, err := img.Layers()
+	require.NoError(t, err, "failed to get layers from image")
+
 	// Read layers in order and for each file keep only the entry seen in the later layer
 	p := &packageFile{Name: filepath.Base(dockerFile), Contents: map[string]packageEntry{}}
-	for _, layer := range manifest.Layers {
-		layerFile, found := layers[layer]
-		require.True(t, found, fmt.Sprintf("layer not found: %s", layer))
-		for name, entry := range layerFile.Contents {
+	for _, layer := range layers {
+		rc, err := layer.Uncompressed()
+		require.NoError(t, err, "failed to get uncompressed layer")
+
+		tarReader := tar.NewReader(rc)
+		for {
+			header, err := tarReader.Next()
+			if err != nil {
+				if errors.Is(err, io.EOF) {
+					break
+				}
+				assert.NoError(t, rc.Close())
+				require.NoError(t, err)
+			}
+
+			name := header.Name
 			if excludedPathsPattern.MatchString(name) {
 				continue
 			}
+
+			entry := packageEntry{
+				File: name,
+				UID:  header.Uid,
+				GID:  header.Gid,
+				Mode: header.FileInfo().Mode(),
+			}
+
 			// Check only files in working dir and entrypoint
 			if !filterWorkingDir || strings.HasPrefix("/"+name, workingDir) || "/"+name == entrypoint {
 				p.Contents[name] = entry
@@ -1147,19 +1167,13 @@ func readDocker(t *testing.T, dockerFile string, filterWorkingDir bool) (*packag
 				}
 			}
 		}
+		assert.NoError(t, rc.Close())
 	}
 
 	require.NotZero(t, len(p.Contents), fmt.Sprintf("no files found in docker working directory (%s)", info.Config.WorkingDir))
-	info.Size = stat.Size()
 	return p, info, nil
 }
 
-type dockerManifest struct {
-	Config   string
-	RepoTags []string
-	Layers   []string
-}
-
 type dockerInfo struct {
 	Config struct {
 		Entrypoint []string
@@ -1170,78 +1184,6 @@ type dockerInfo struct {
 	Size int64
 }
 
-func readDockerInfo(r io.Reader) (*dockerInfo, error) {
-	data, err := io.ReadAll(r)
-	if err != nil {
-		return nil, err
-	}
-
-	var info dockerInfo
-	err = json.Unmarshal(data, &info)
-	if err != nil {
-		return nil, err
-	}
-
-	return &info, nil
-}
-
-// getDockerManifest opens a gzipped tar file to read the Docker manifest.json
-// that it is expected to contain.
-func getDockerManifest(file string) (*dockerManifest, error) {
-	f, err := os.Open(file)
-	if err != nil {
-		return nil, err
-	}
-	defer f.Close()
-
-	gzipReader, err := gzip.NewReader(f)
-	if err != nil {
-		return nil, err
-	}
-	defer gzipReader.Close()
-
-	var manifest *dockerManifest
-	tarReader := tar.NewReader(gzipReader)
-	for {
-		header, err := tarReader.Next()
-		if err != nil {
-			if errors.Is(err, io.EOF) {
-				break
-			}
-			return nil, err
-		}
-
-		if header.Name == "manifest.json" {
-			manifest, err = readDockerManifest(tarReader)
-			if err != nil {
-				return nil, err
-			}
-			break
-		}
-	}
-
-	return manifest, nil
-}
-
-func readDockerManifest(r io.Reader) (*dockerManifest, error) {
-	data, err := io.ReadAll(r)
-	if err != nil {
-		return nil, err
-	}
-
-	var manifests []*dockerManifest
-	err = json.Unmarshal(data, &manifests)
-	if err != nil {
-		return nil, err
-	}
-
-	if len(manifests) != 1 {
-		return nil, fmt.Errorf("one and only one manifest expected, %d found", len(manifests))
-	}
-
-	return manifests[0], nil
-}
-
 func checkSha512PackageHash(t *testing.T, packageFile string) {
 	t.Run("check hash file", func(t *testing.T) {
 		expectedHashFile := packageFile + ".sha512"

go.mod

@@ -33,6 +33,7 @@ require (
 	github.com/gofrs/flock v0.12.1
 	github.com/gofrs/uuid/v5 v5.4.0
 	github.com/google/go-cmp v0.7.0
+	github.com/google/go-containerregistry v0.20.3
 	github.com/google/pprof v0.0.0-20250923004556-9e5a51aed1e8
 	github.com/gorilla/mux v1.8.1
 	github.com/jaypipes/ghw v0.12.0
@@ -261,6 +262,7 @@ require (
 	github.com/containerd/errdefs/pkg v0.3.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
 	github.com/containerd/platforms v0.2.1 // indirect
+	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
 	github.com/coreos/go-systemd/v22 v22.6.0 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.6 // indirect
 	github.com/cyphar/filepath-securejoin v0.6.0 // indirect
@@ -634,6 +636,7 @@ require (
 	github.com/ugorji/go/codec v1.2.7 // indirect
 	github.com/urfave/cli/v2 v2.27.4 // indirect
 	github.com/valyala/fastjson v1.6.4 // indirect
+	github.com/vbatts/tar-split v0.11.6 // indirect
 	github.com/vmware/govmomi v0.52.0 // indirect
 	github.com/vultr/govultr/v2 v2.17.2 // indirect
 	github.com/x448/float16 v0.8.4 // indirect

go.sum

@@ -396,6 +396,8 @@ github.com/containerd/log v0.1.0 h1:TCJt7ioM2cr/tfR8GPbGf9/VRAX8D2B4PjzCpfX540I=
 github.com/containerd/log v0.1.0/go.mod h1:VRRf09a7mHDIRezVKTRCrOq78v577GXq3bSa3EhrzVo=
 github.com/containerd/platforms v0.2.1 h1:zvwtM3rz2YHPQsF2CHYM8+KtB5dvhISiXh5ZpSBQv6A=
 github.com/containerd/platforms v0.2.1/go.mod h1:XHCb+2/hzowdiut9rkudds9bE5yJ7npe7dG/wG+uFPw=
+github.com/containerd/stargz-snapshotter/estargz v0.16.3 h1:7evrXtoh1mSbGj/pfRccTampEyKpjpOnS3CyiV1Ebr8=
+github.com/containerd/stargz-snapshotter/estargz v0.16.3/go.mod h1:uyr4BfYfOj3G9WBVE8cOlQmXAbPN9VEQpBBeJIuOipU=
 github.com/coreos/go-systemd/v22 v22.3.3-0.20220203105225-a9a7ef127534/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/coreos/go-systemd/v22 v22.6.0 h1:aGVa/v8B7hpb0TKl0MWoAavPDmHvobFe5R5zn0bCJWo=
 github.com/coreos/go-systemd/v22 v22.6.0/go.mod h1:iG+pp635Fo7ZmV/j14KUcmEyWF+0X7Lua8rrTWzYgWU=
@@ -772,6 +774,8 @@ github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
+github.com/google/go-containerregistry v0.20.3 h1:oNx7IdTI936V8CQRveCjaxOiegWwvM7kqkbXTpyiovI=
+github.com/google/go-containerregistry v0.20.3/go.mod h1:w00pIgBRDVUDFM6bq+Qx8lwNWK+cxgCuX1vd3PIBDNI=
 github.com/google/go-querystring v1.1.0 h1:AnCroh3fv4ZBgVIf1Iwtovgjaw/GiKJo8M8yD/fhyJ8=
 github.com/google/go-querystring v1.1.0/go.mod h1:Kcdr2DB4koayq7X8pmAG4sNG59So17icRSOU623lUBU=
 github.com/google/go-tpm v0.9.7 h1:u89J4tUUeDTlH8xxC3CTW7OHZjbjKoHdQ9W7gCUhtxA=
@@ -1581,6 +1585,8 @@ github.com/urfave/cli/v2 v2.27.4 h1:o1owoI+02Eb+K107p27wEX9Bb8eqIoZCfLXloLUSWJ8=
 github.com/urfave/cli/v2 v2.27.4/go.mod h1:m4QzxcD2qpra4z7WhzEGn74WZLViBnMpb1ToCAKdGRQ=
 github.com/valyala/fastjson v1.6.4 h1:uAUNq9Z6ymTgGhcm0UynUAB6tlbakBrz6CQFax3BXVQ=
 github.com/valyala/fastjson v1.6.4/go.mod h1:CLCAqky6SMuOcxStkYQvblddUtoRxhYMGLrsQns1aXY=
+github.com/vbatts/tar-split v0.11.6 h1:4SjTW5+PU11n6fZenf2IPoV8/tz3AaYHMWjf23envGs=
+github.com/vbatts/tar-split v0.11.6/go.mod h1:dqKNtesIOr2j2Qv3W/cHjnvk9I8+G7oAkFDFN6TCBEI=
 github.com/vladimirvivien/gexe v0.2.0 h1:nbdAQ6vbZ+ZNsolCgSVb9Fno60kzSuvtzVh6Ytqi/xY=
 github.com/vladimirvivien/gexe v0.2.0/go.mod h1:LHQL00w/7gDUKIak24n801ABp8C+ni6eBht9vGVst8w=
 github.com/vmware/govmomi v0.52.0 h1:JyxQ1IQdllrY7PJbv2am9mRsv3p9xWlIQ66bv+XnyLw=