SBOM cataloger (#1029)

* SBOM cataloger

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* sbom-cataloger: turn off by default

and add integration test

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* SBOM cataloger

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* SBOM cataloger (optimize)

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* SBOM cataloger (fix)

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* SBOM cataloger (fix imports #1172)

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* SBOM cataloger (fix: support group attribute in CDX SBOMs)

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>

* port to generic cataloger and add relationship to original file

Signed-off-by: Alex Goodman <alex.goodman@anchore.com>

* generalize parser for all format globs

Signed-off-by: Alex Goodman <alex.goodman@anchore.com>

Signed-off-by: Patrik Beno <patrik.beno@greenhorn.sk>
Signed-off-by: Alex Goodman <alex.goodman@anchore.com>
Co-authored-by: Tom Fay <tomfay@microsoft.com>
Co-authored-by: Alex Goodman <alex.goodman@anchore.com>

cmd/syft/cli/options/format.go

@@ -1,28 +1,35 @@
 package options
 
 import (
-	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/formats/cyclonedxjson"
+	"github.com/anchore/syft/syft/formats/cyclonedxxml"
+	"github.com/anchore/syft/syft/formats/github"
+	"github.com/anchore/syft/syft/formats/spdx22json"
+	"github.com/anchore/syft/syft/formats/spdx22tagvalue"
+	"github.com/anchore/syft/syft/formats/syftjson"
+	"github.com/anchore/syft/syft/formats/table"
+	"github.com/anchore/syft/syft/formats/text"
 	"github.com/anchore/syft/syft/sbom"
 )
 
 func FormatAliases(ids ...sbom.FormatID) (aliases []string) {
 	for _, id := range ids {
 		switch id {
-		case syft.JSONFormatID:
+		case syftjson.ID:
 			aliases = append(aliases, "syft-json")
-		case syft.TextFormatID:
+		case text.ID:
 			aliases = append(aliases, "text")
-		case syft.TableFormatID:
+		case table.ID:
 			aliases = append(aliases, "table")
-		case syft.SPDXJSONFormatID:
+		case spdx22json.ID:
 			aliases = append(aliases, "spdx-json")
-		case syft.SPDXTagValueFormatID:
+		case spdx22tagvalue.ID:
 			aliases = append(aliases, "spdx-tag-value")
-		case syft.CycloneDxXMLFormatID:
+		case cyclonedxxml.ID:
 			aliases = append(aliases, "cyclonedx-xml")
-		case syft.CycloneDxJSONFormatID:
+		case cyclonedxjson.ID:
 			aliases = append(aliases, "cyclonedx-json")
-		case syft.GitHubID:
+		case github.ID:
 			aliases = append(aliases, "github", "github-json")
 		default:
 			aliases = append(aliases, string(id))

syft/artifact/relationship.go

@@ -12,6 +12,9 @@ const (
 
 	// DependencyOfRelationship is a proxy for the SPDX 2.2.1 DEPENDENCY_OF	relationship.
 	DependencyOfRelationship RelationshipType = "dependency-of"
+
+	// DescribedByRelationship is a proxy for the SPDX 2.2.2 DESCRIBED_BY relationship.
+	DescribedByRelationship RelationshipType = "described-by"
 )
 
 type RelationshipType string

syft/encode_decode.go

@@ -1,36 +1,18 @@
 package syft
 
 import (
-	"bytes"
-	"fmt"
 	"io"
 
+	"github.com/anchore/syft/syft/formats"
 	"github.com/anchore/syft/syft/sbom"
 )
 
-// Encode takes all SBOM elements and a format option and encodes an SBOM document.
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func Encode(s sbom.SBOM, f sbom.Format) ([]byte, error) {
-	buff := bytes.Buffer{}
+	return formats.Encode(s, f)
-
-	if err := f.Encode(&buff, s); err != nil {
-		return nil, fmt.Errorf("unable to encode sbom: %w", err)
 }
 
-	return buff.Bytes(), nil
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
-}
-
-// Decode takes a reader for an SBOM and generates all internal SBOM elements.
 func Decode(reader io.Reader) (*sbom.SBOM, sbom.Format, error) {
-	by, err := io.ReadAll(reader)
+	return formats.Decode(reader)
-	if err != nil {
-		return nil, nil, fmt.Errorf("unable to read sbom: %w", err)
-	}
-
-	f := IdentifyFormat(by)
-	if f == nil {
-		return nil, nil, fmt.Errorf("unable to identify format")
-	}
-
-	s, err := f.Decode(bytes.NewReader(by))
-	return s, f, err
 }

syft/formats.go

@@ -1,9 +1,7 @@
 package syft
 
 import (
-	"bytes"
+	"github.com/anchore/syft/syft/formats"
-	"strings"
-
 	"github.com/anchore/syft/syft/formats/cyclonedxjson"
 	"github.com/anchore/syft/syft/formats/cyclonedxxml"
 	"github.com/anchore/syft/syft/formats/github"
@@ -17,94 +15,35 @@ import (
 )
 
 // these have been exported for the benefit of API users
+// TODO: deprecated: now that the formats package has been moved to syft/formats, will be removed in v1.0.0
 const (
 	JSONFormatID          = syftjson.ID
 	TextFormatID          = text.ID
 	TableFormatID         = table.ID
 	CycloneDxXMLFormatID  = cyclonedxxml.ID
 	CycloneDxJSONFormatID = cyclonedxjson.ID
-	GitHubID              = github.ID
+	GitHubFormatID        = github.ID
 	SPDXTagValueFormatID  = spdx22tagvalue.ID
 	SPDXJSONFormatID      = spdx22json.ID
 	TemplateFormatID      = template.ID
 )
 
-var formats []sbom.Format
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
-
-func init() {
-	formats = []sbom.Format{
-		syftjson.Format(),
-		cyclonedxxml.Format(),
-		cyclonedxjson.Format(),
-		github.Format(),
-		spdx22tagvalue.Format(),
-		spdx22json.Format(),
-		table.Format(),
-		text.Format(),
-		template.Format(),
-	}
-}
-
 func FormatIDs() (ids []sbom.FormatID) {
-	for _, f := range formats {
+	return formats.IDs()
-		ids = append(ids, f.ID())
-	}
-	return ids
 }
 
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func FormatByID(id sbom.FormatID) sbom.Format {
-	for _, f := range formats {
+	return formats.ByID(id)
-		if f.ID() == id {
-			return f
-		}
-	}
-	return nil
 }
 
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func FormatByName(name string) sbom.Format {
-	cleanName := cleanFormatName(name)
+	return formats.ByName(name)
-	for _, f := range formats {
-		if cleanFormatName(string(f.ID())) == cleanName {
-			return f
-		}
-	}
-
-	// handle any aliases for any supported format
-	switch cleanName {
-	case "json", "syftjson":
-		return FormatByID(syftjson.ID)
-	case "cyclonedx", "cyclone", "cyclonedxxml":
-		return FormatByID(cyclonedxxml.ID)
-	case "cyclonedxjson":
-		return FormatByID(cyclonedxjson.ID)
-	case "github", "githubjson":
-		return FormatByID(github.ID)
-	case "spdx", "spdxtv", "spdxtagvalue":
-		return FormatByID(spdx22tagvalue.ID)
-	case "spdxjson":
-		return FormatByID(spdx22json.ID)
-	case "table":
-		return FormatByID(table.ID)
-	case "text":
-		return FormatByID(text.ID)
-	case "template":
-		FormatByID(template.ID)
-	}
-
-	return nil
-}
-
-func cleanFormatName(name string) string {
-	r := strings.NewReplacer("-", "", "_", "")
-	return strings.ToLower(r.Replace(name))
 }
 
+// TODO: deprecated, moved to syft/formats/formats.go. will be removed in v1.0.0
 func IdentifyFormat(by []byte) sbom.Format {
-	for _, f := range formats {
+	return formats.Identify(by)
-		if err := f.Validate(bytes.NewReader(by)); err != nil {
-			continue
-		}
-		return f
-	}
-	return nil
 }

syft/formats/common/spdxhelpers/source_info.go

@@ -46,6 +46,9 @@ func SourceInfo(p pkg.Package) string {
 	default:
 		answer = "acquired package info from the following paths"
 	}
+	if p.FoundBy == "sbom-cataloger" {
+		answer = "acquired package info from SBOM"
+	}
 	var paths []string
 	for _, l := range p.Locations.ToSlice() {
 		paths = append(paths, l.RealPath)

syft/formats/formats.go

@@ -0,0 +1,124 @@
+package formats
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"strings"
+
+	"github.com/anchore/syft/syft/formats/cyclonedxjson"
+	"github.com/anchore/syft/syft/formats/cyclonedxxml"
+	"github.com/anchore/syft/syft/formats/github"
+	"github.com/anchore/syft/syft/formats/spdx22json"
+	"github.com/anchore/syft/syft/formats/spdx22tagvalue"
+	"github.com/anchore/syft/syft/formats/syftjson"
+	"github.com/anchore/syft/syft/formats/table"
+	"github.com/anchore/syft/syft/formats/template"
+	"github.com/anchore/syft/syft/formats/text"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+func Formats() []sbom.Format {
+	return []sbom.Format{
+		syftjson.Format(),
+		cyclonedxxml.Format(),
+		cyclonedxjson.Format(),
+		github.Format(),
+		spdx22tagvalue.Format(),
+		spdx22json.Format(),
+		table.Format(),
+		text.Format(),
+		template.Format(),
+	}
+}
+
+func Identify(by []byte) sbom.Format {
+	for _, f := range Formats() {
+		if err := f.Validate(bytes.NewReader(by)); err != nil {
+			continue
+		}
+		return f
+	}
+	return nil
+}
+
+func ByName(name string) sbom.Format {
+	cleanName := cleanFormatName(name)
+	for _, f := range Formats() {
+		if cleanFormatName(string(f.ID())) == cleanName {
+			return f
+		}
+	}
+
+	// handle any aliases for any supported format
+	switch cleanName {
+	case "json", "syftjson":
+		return ByID(syftjson.ID)
+	case "cyclonedx", "cyclone", "cyclonedxxml":
+		return ByID(cyclonedxxml.ID)
+	case "cyclonedxjson":
+		return ByID(cyclonedxjson.ID)
+	case "github", "githubjson":
+		return ByID(github.ID)
+	case "spdx", "spdxtv", "spdxtagvalue":
+		return ByID(spdx22tagvalue.ID)
+	case "spdxjson":
+		return ByID(spdx22json.ID)
+	case "table":
+		return ByID(table.ID)
+	case "text":
+		return ByID(text.ID)
+	case "template":
+		ByID(template.ID)
+	}
+
+	return nil
+}
+
+func IDs() (ids []sbom.FormatID) {
+	for _, f := range Formats() {
+		ids = append(ids, f.ID())
+	}
+	return ids
+}
+
+func ByID(id sbom.FormatID) sbom.Format {
+	for _, f := range Formats() {
+		if f.ID() == id {
+			return f
+		}
+	}
+	return nil
+}
+
+func cleanFormatName(name string) string {
+	r := strings.NewReplacer("-", "", "_", "")
+	return strings.ToLower(r.Replace(name))
+}
+
+// Encode takes all SBOM elements and a format option and encodes an SBOM document.
+func Encode(s sbom.SBOM, f sbom.Format) ([]byte, error) {
+	buff := bytes.Buffer{}
+
+	if err := f.Encode(&buff, s); err != nil {
+		return nil, fmt.Errorf("unable to encode sbom: %w", err)
+	}
+
+	return buff.Bytes(), nil
+}
+
+// Decode takes a reader for an SBOM and generates all internal SBOM elements.
+func Decode(reader io.Reader) (*sbom.SBOM, sbom.Format, error) {
+	by, err := io.ReadAll(reader)
+	if err != nil {
+		return nil, nil, fmt.Errorf("unable to read sbom: %w", err)
+	}
+
+	f := Identify(by)
+	if f == nil {
+		return nil, nil, fmt.Errorf("unable to identify format")
+	}
+
+	s, err := f.Decode(bytes.NewReader(by))
+	return s, f, err
+}

syft/formats/formats_test.go

@@ -1,4 +1,4 @@
-package syft
+package formats
 
 import (
 	"bytes"
@@ -37,7 +37,7 @@ func TestIdentify(t *testing.T) {
 			assert.NoError(t, err)
 			by, err := io.ReadAll(f)
 			assert.NoError(t, err)
-			frmt := IdentifyFormat(by)
+			frmt := Identify(by)
 			assert.NotNil(t, frmt)
 			assert.Equal(t, test.expected, frmt.ID())
 		})
@@ -45,7 +45,7 @@ func TestIdentify(t *testing.T) {
 }
 
 func TestFormats_EmptyInput(t *testing.T) {
-	for _, format := range formats {
+	for _, format := range Formats() {
 		t.Run(format.ID().String(), func(t *testing.T) {
 			t.Run("format.Decode", func(t *testing.T) {
 				input := bytes.NewReader(nil)
@@ -69,7 +69,7 @@ func TestFormats_EmptyInput(t *testing.T) {
 	}
 }
 
-func TestFormatByName(t *testing.T) {
+func TestByName(t *testing.T) {
 
 	tests := []struct {
 		name string
@@ -190,7 +190,7 @@ func TestFormatByName(t *testing.T) {
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			f := FormatByName(tt.name)
+			f := ByName(tt.name)
 			if tt.want == "" {
 				require.Nil(t, f)
 				return

syft/pkg/cataloger/cataloger.go

@@ -26,6 +26,7 @@ import (
 	"github.com/anchore/syft/syft/pkg/cataloger/rpm"
 	"github.com/anchore/syft/syft/pkg/cataloger/ruby"
 	"github.com/anchore/syft/syft/pkg/cataloger/rust"
+	"github.com/anchore/syft/syft/pkg/cataloger/sbom"
 	"github.com/anchore/syft/syft/pkg/cataloger/swift"
 )
 
@@ -47,6 +48,7 @@ func ImageCatalogers(cfg Config) []pkg.Cataloger {
 		golang.NewGoModuleBinaryCataloger(),
 		dotnet.NewDotnetDepsCataloger(),
 		portage.NewPortageCataloger(),
+		sbom.NewSBOMCataloger(),
 	}, cfg.Catalogers)
 }
 
@@ -75,6 +77,7 @@ func DirectoryCatalogers(cfg Config) []pkg.Cataloger {
 		cpp.NewConanCataloger(),
 		portage.NewPortageCataloger(),
 		haskell.NewHackageCataloger(),
+		sbom.NewSBOMCataloger(),
 	}, cfg.Catalogers)
 }
 
@@ -107,6 +110,7 @@ func AllCatalogers(cfg Config) []pkg.Cataloger {
 		cpp.NewConanCataloger(),
 		portage.NewPortageCataloger(),
 		haskell.NewHackageCataloger(),
+		sbom.NewSBOMCataloger(),
 	}, cfg.Catalogers)
 }
 

syft/pkg/cataloger/internal/pkgtest/test_generic_parser.go

@@ -124,6 +124,11 @@ func (p *CatalogTester) IgnoreLocationLayer() *CatalogTester {
 	return p
 }
 
+func (p *CatalogTester) IgnorePackageFields(fields ...string) *CatalogTester {
+	p.compareOptions = append(p.compareOptions, cmpopts.IgnoreFields(pkg.Package{}, fields...))
+	return p
+}
+
 func (p *CatalogTester) Expects(pkgs []pkg.Package, relationships []artifact.Relationship) *CatalogTester {
 	p.expectedPkgs = pkgs
 	p.expectedRelationships = relationships

syft/pkg/cataloger/sbom/cataloger.go

@@ -0,0 +1,62 @@
+package sbom
+
+import (
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/formats"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+	"github.com/anchore/syft/syft/source"
+)
+
+const catalogerName = "sbom-cataloger"
+
+// NewSBOMCataloger returns a new SBOM cataloger object loaded from saved SBOM JSON.
+func NewSBOMCataloger() *generic.Cataloger {
+	return generic.NewCataloger(catalogerName).
+		WithParserByGlobs(parseSBOM,
+			"**/*.syft.json",
+			"**/*.bom.*",
+			"**/*.bom",
+			"**/bom",
+			"**/*.sbom.*",
+			"**/*.sbom",
+			"**/sbom",
+			"**/*.cdx.*",
+			"**/*.cdx",
+			"**/*.spdx.*",
+			"**/*.spdx",
+		)
+}
+
+func parseSBOM(_ source.FileResolver, _ *generic.Environment, reader source.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+	s, _, err := formats.Decode(reader)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	if s == nil {
+		log.WithFields("path", reader.Location.RealPath).Trace("file is not an SBOM")
+		return nil, nil, nil
+	}
+
+	var pkgs []pkg.Package
+	var relationships []artifact.Relationship
+	for _, p := range s.Artifacts.PackageCatalog.Sorted() {
+		// replace all locations on the package with the location of the SBOM file.
+		// Why not keep the original list of locations? Since the "locations" field is meant to capture
+		// where there is evidence of this file, and the catalogers have not run against any file other than,
+		// the SBOM, this is the only location that is relevant for this cataloger.
+		p.Locations = source.NewLocationSet(reader.Location)
+		p.FoundBy = catalogerName
+
+		pkgs = append(pkgs, p)
+		relationships = append(relationships, artifact.Relationship{
+			From: p,
+			To:   reader.Location.Coordinates,
+			Type: artifact.DescribedByRelationship,
+		})
+	}
+
+	return pkgs, relationships, nil
+}

syft/pkg/cataloger/sbom/cataloger_test.go

@@ -0,0 +1,291 @@
+package sbom
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/formats/syftjson"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/pkgtest"
+	"github.com/anchore/syft/syft/sbom"
+	"github.com/anchore/syft/syft/source"
+)
+
+func mustCPEs(s ...string) (c []pkg.CPE) {
+	for _, i := range s {
+		c = append(c, mustCPE(i))
+	}
+	return
+}
+
+func mustCPE(c string) pkg.CPE {
+	return must(pkg.NewCPE(c))
+}
+func must(c pkg.CPE, e error) pkg.CPE {
+	if e != nil {
+		panic(e)
+	}
+	return c
+}
+
+func Test_parseSBOM(t *testing.T) {
+
+	expectedPkgs := []pkg.Package{
+		{
+			Name:      "alpine-baselayout",
+			Version:   "3.2.0-r23",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/alpine-baselayout@3.2.0-r23?arch=x86_64&upstream=alpine-baselayout&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:alpine-baselayout:alpine-baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine-baselayout:alpine_baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout:alpine-baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout:alpine_baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine-baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine_baselayout:3.2.0-r23:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "alpine-baselayout-data",
+			Version:   "3.2.0-r23",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/alpine-baselayout-data@3.2.0-r23?arch=x86_64&upstream=alpine-baselayout&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:alpine-baselayout-data:alpine-baselayout-data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine-baselayout-data:alpine_baselayout_data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout_data:alpine-baselayout-data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout_data:alpine_baselayout_data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine-baselayout:alpine-baselayout-data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine-baselayout:alpine_baselayout_data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout:alpine-baselayout-data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_baselayout:alpine_baselayout_data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine-baselayout-data:3.2.0-r23:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine_baselayout_data:3.2.0-r23:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "alpine-keys",
+			Version:   "2.4-r1",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"MIT"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/alpine-keys@2.4-r1?arch=x86_64&upstream=alpine-keys&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:alpine-keys:alpine-keys:2.4-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine-keys:alpine_keys:2.4-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_keys:alpine-keys:2.4-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine_keys:alpine_keys:2.4-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine-keys:2.4-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:alpine:alpine_keys:2.4-r1:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "apk-tools",
+			Version:   "2.12.9-r3",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/apk-tools@2.12.9-r3?arch=x86_64&upstream=apk-tools&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:apk-tools:apk-tools:2.12.9-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:apk-tools:apk_tools:2.12.9-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:apk_tools:apk-tools:2.12.9-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:apk_tools:apk_tools:2.12.9-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:apk:apk-tools:2.12.9-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:apk:apk_tools:2.12.9-r3:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "busybox",
+			Version:   "1.35.0-r17",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/busybox@1.35.0-r17?arch=x86_64&upstream=busybox&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:busybox:busybox:1.35.0-r17:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "ca-certificates-bundle",
+			Version:   "20220614-r0",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"MPL-2.0", "AND", "MIT"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/ca-certificates-bundle@20220614-r0?arch=x86_64&upstream=ca-certificates&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:ca-certificates-bundle:ca-certificates-bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca-certificates-bundle:ca_certificates_bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca_certificates_bundle:ca-certificates-bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca_certificates_bundle:ca_certificates_bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca-certificates:ca-certificates-bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca-certificates:ca_certificates_bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca_certificates:ca-certificates-bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca_certificates:ca_certificates_bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca:ca-certificates-bundle:20220614-r0:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ca:ca_certificates_bundle:20220614-r0:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "libc-utils",
+			Version:   "0.7.2-r3",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"BSD-2-Clause", "AND", "BSD-3-Clause"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/libc-utils@0.7.2-r3?arch=x86_64&upstream=libc-dev&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:libc-utils:libc-utils:0.7.2-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:libc-utils:libc_utils:0.7.2-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:libc_utils:libc-utils:0.7.2-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:libc_utils:libc_utils:0.7.2-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:libc:libc-utils:0.7.2-r3:*:*:*:*:*:*:*",
+				"cpe:2.3:a:libc:libc_utils:0.7.2-r3:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "libcrypto1.1",
+			Version:   "1.1.1s-r0",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"OpenSSL"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/libcrypto1.1@1.1.1s-r0?arch=x86_64&upstream=openssl&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:libcrypto1.1:libcrypto1.1:1.1.1s-r0:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "libssl1.1",
+			Version:   "1.1.1s-r0",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"OpenSSL"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/libssl1.1@1.1.1s-r0?arch=x86_64&upstream=openssl&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:libssl1.1:libssl1.1:1.1.1s-r0:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "musl",
+			Version:   "1.2.3-r1",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"MIT"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/musl@1.2.3-r1?arch=x86_64&upstream=musl&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:musl:musl:1.2.3-r1:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "musl-utils",
+			Version:   "1.2.3-r1",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"MIT", "BSD", "GPL2+"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/musl-utils@1.2.3-r1?arch=x86_64&upstream=musl&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:musl-utils:musl-utils:1.2.3-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:musl-utils:musl_utils:1.2.3-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:musl_utils:musl-utils:1.2.3-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:musl_utils:musl_utils:1.2.3-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:musl:musl-utils:1.2.3-r1:*:*:*:*:*:*:*",
+				"cpe:2.3:a:musl:musl_utils:1.2.3-r1:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "scanelf",
+			Version:   "1.3.4-r0",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/scanelf@1.3.4-r0?arch=x86_64&upstream=pax-utils&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:scanelf:scanelf:1.3.4-r0:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "ssl_client",
+			Version:   "1.35.0-r17",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"GPL-2.0-only"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/ssl_client@1.35.0-r17?arch=x86_64&upstream=busybox&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:ssl-client:ssl-client:1.35.0-r17:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ssl-client:ssl_client:1.35.0-r17:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ssl_client:ssl-client:1.35.0-r17:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ssl_client:ssl_client:1.35.0-r17:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ssl:ssl-client:1.35.0-r17:*:*:*:*:*:*:*",
+				"cpe:2.3:a:ssl:ssl_client:1.35.0-r17:*:*:*:*:*:*:*",
+			),
+		},
+		{
+			Name:      "zlib",
+			Version:   "1.2.12-r3",
+			Type:      "apk",
+			Locations: source.NewLocationSet(source.NewLocation("sbom.syft.json")),
+			Licenses:  []string{"Zlib"},
+			FoundBy:   "sbom-cataloger",
+			PURL:      "pkg:alpine/zlib@1.2.12-r3?arch=x86_64&upstream=zlib&distro=alpine-3.16.3",
+			CPEs: mustCPEs(
+				"cpe:2.3:a:zlib:zlib:1.2.12-r3:*:*:*:*:*:*:*",
+			),
+		},
+	}
+
+	var expectedRelationships []artifact.Relationship
+
+	for _, p := range expectedPkgs {
+		expectedRelationships = append(expectedRelationships, artifact.Relationship{
+			From: p,
+			To: source.Coordinates{
+				RealPath: "sbom.syft.json",
+			},
+			Type: artifact.DescribedByRelationship,
+		})
+	}
+
+	tests := []struct {
+		name              string
+		format            sbom.Format
+		fixture           string
+		wantPkgs          []pkg.Package
+		wantRelationships []artifact.Relationship
+		wantErr           require.ErrorAssertionFunc
+	}{
+		{
+			name:              "parse syft JSON",
+			format:            syftjson.Format(),
+			fixture:           "test-fixtures/alpine/syft-json",
+			wantPkgs:          expectedPkgs,
+			wantRelationships: expectedRelationships,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, tt.fixture).
+				IgnorePackageFields("Metadata", "MetadataType").
+				Expects(tt.wantPkgs, tt.wantRelationships).
+				TestCataloger(t, NewSBOMCataloger())
+		})
+	}
+}

test/integration/sbom_cataloger_test.go

@@ -0,0 +1,34 @@
+package integration
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+)
+
+func TestSbomCataloger(t *testing.T) {
+	// The image contains a go.mod file with 2 dependencies and an spdx json sbom.
+	// The go.mod file contains 2 dependencies, and the sbom includes a go dependency
+	// that overlaps with the go.mod
+	sbom, _ := catalogFixtureImage(t, "image-sbom-cataloger", source.SquashedScope, []string{"all"})
+
+	expectedSbomCatalogerPkgs := 1
+	expectedGoModCatalogerPkgs := 2
+	actualSbomPkgs := 0
+	actualGoModPkgs := 0
+	for pkg := range sbom.Artifacts.PackageCatalog.Enumerate(pkg.GoModulePkg) {
+		if pkg.FoundBy == "go-mod-file-cataloger" {
+			actualGoModPkgs += 1
+		} else if pkg.FoundBy == "sbom-cataloger" {
+			actualSbomPkgs += 1
+		}
+	}
+
+	if actualGoModPkgs != expectedGoModCatalogerPkgs {
+		t.Errorf("unexpected number of packages from go mod cataloger: %d != %d", expectedGoModCatalogerPkgs, actualGoModPkgs)
+	}
+	if actualSbomPkgs != expectedSbomCatalogerPkgs {
+		t.Errorf("unexpected number of packages from sbom cataloger: %d != %d", expectedSbomCatalogerPkgs, actualSbomPkgs)
+	}
+}

test/integration/test-fixtures/image-sbom-cataloger/Dockerfile

@@ -0,0 +1,3 @@
+FROM scratch
+COPY go.mod /
+COPY test.spdx.json /

test/integration/test-fixtures/image-sbom-cataloger/go.mod

@@ -0,0 +1,8 @@
+module github.com/anchore/syft
+
+go 1.14
+
+require (
+	github.com/anchore/packageurl-go v0.1.1-0.20220428202044-a072fa3cb6d7
+	github.com/bmatcuk/doublestar v1.3.1
+)

test/integration/test-fixtures/image-sbom-cataloger/test.spdx.json

@@ -0,0 +1,39 @@
+{
+ "SPDXID": "SPDXRef-DOCUMENT",
+ "name": "test/integration/test-fixtures/image-sbom-cataloger",
+ "spdxVersion": "SPDX-2.2",
+ "creationInfo": {
+  "created": "2022-08-18T05:23:38.066146511Z",
+  "creators": [
+   "Organization: Anchore, Inc",
+   "Tool: syft-0.53.0"
+  ],
+  "licenseListVersion": "3.17"
+ },
+ "dataLicense": "CC0-1.0",
+ "documentNamespace": "https://anchore.com/syft/dir/test/integration/test-fixtures/image-sbom-cataloger-057e7aa2-332c-4b50-bbd1-a17dd62ddce4",
+ "packages": [
+  {
+   "SPDXID": "SPDXRef-45209ca0cdcbafa",
+   "name": "github.com/bmatcuk/doublestar",
+   "licenseConcluded": "NONE",
+   "downloadLocation": "NOASSERTION",
+   "externalRefs": [
+    {
+     "referenceCategory": "SECURITY",
+     "referenceLocator": "cpe:2.3:a:bmatcuk:doublestar:v1.3.1:*:*:*:*:*:*:*",
+     "referenceType": "cpe23Type"
+    },
+    {
+     "referenceCategory": "PACKAGE_MANAGER",
+     "referenceLocator": "pkg:golang/github.com/bmatcuk/doublestar@v1.3.1",
+     "referenceType": "purl"
+    }
+   ],
+   "filesAnalyzed": false,
+   "licenseDeclared": "NONE",
+   "sourceInfo": "acquired package info from go module information: go.mod",
+   "versionInfo": "v1.3.1"
+  }
+ ]
+}