Add SPDX JSON format object (#584)

* remove existing spdxjson presenter + helpers

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

* add new spdx22json format

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

* add common sdpxhelpers (migrated)

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

* use new common spdx helpers

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

* wire up new spdx22json format object

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

* remove lossless syft-specific property bags

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

* remove spdxjson decoder and validator

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

* add nil checks in spdx test helpers

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

* remove empty default case

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

* use explicit golden snapshot

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

internal/formats/common/spdxhelpers/description.go

@@ -0,0 +1,23 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func Description(p *pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return metadata.Description
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Description
+		}
+	}
+	return ""
+}
+
+func packageExists(p *pkg.Package) bool {
+	return p != nil
+}
+
+func hasMetadata(p *pkg.Package) bool {
+	return packageExists(p) && p.Metadata != nil
+}

internal/formats/common/spdxhelpers/description_test.go

@@ -0,0 +1,56 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Description(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					Description: "a description!",
+				},
+			},
+			expected: "a description!",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Description: "a description!",
+				},
+			},
+			expected: "a description!",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Description(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/download_location.go

@@ -0,0 +1,23 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func DownloadLocation(p *pkg.Package) string {
+	// 3.7: Package Download Location
+	// Cardinality: mandatory, one
+	// NONE if there is no download location whatsoever.
+	// NOASSERTION if:
+	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
+	//   (ii) the SPDX file creator has made no attempt to determine this field; or
+	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
+
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return NoneIfEmpty(metadata.URL)
+		case pkg.NpmPackageJSONMetadata:
+			return NoneIfEmpty(metadata.URL)
+		}
+	}
+	return "NOASSERTION"
+}

internal/formats/common/spdxhelpers/download_location_test.go

@@ -0,0 +1,54 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_DownloadLocation(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "NOASSERTION",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					URL: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					URL: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					URL: "",
+				},
+			},
+			expected: "NONE",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, DownloadLocation(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/external_refs.go

@@ -0,0 +1,55 @@
+package spdxhelpers
+
+import (
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func ExternalRefs(p *pkg.Package) (externalRefs []model.ExternalRef) {
+	externalRefs = make([]model.ExternalRef, 0)
+
+	if !packageExists(p) {
+		return externalRefs
+	}
+
+	for _, c := range p.CPEs {
+		externalRefs = append(externalRefs, model.ExternalRef{
+			ReferenceCategory: model.SecurityReferenceCategory,
+			ReferenceLocator:  c.BindToFmtString(),
+			ReferenceType:     model.Cpe23ExternalRefType,
+		})
+	}
+
+	if p.PURL != "" {
+		externalRefs = append(externalRefs, model.ExternalRef{
+			ReferenceCategory: model.PackageManagerReferenceCategory,
+			ReferenceLocator:  p.PURL,
+			ReferenceType:     model.PurlExternalRefType,
+		})
+	}
+	return externalRefs
+}
+
+func ExtractPURL(refs []model.ExternalRef) string {
+	for _, r := range refs {
+		if r.ReferenceType == model.PurlExternalRefType {
+			return r.ReferenceLocator
+		}
+	}
+	return ""
+}
+
+func ExtractCPEs(refs []model.ExternalRef) (cpes []pkg.CPE) {
+	for _, r := range refs {
+		if r.ReferenceType == model.Cpe23ExternalRefType {
+			cpe, err := pkg.NewCPE(r.ReferenceLocator)
+			if err != nil {
+				log.Warnf("unable to extract SPDX CPE=%q: %+v", r.ReferenceLocator, err)
+				continue
+			}
+			cpes = append(cpes, cpe)
+		}
+	}
+	return cpes
+}

internal/formats/common/spdxhelpers/external_refs_test.go

@@ -0,0 +1,45 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_ExternalRefs(t *testing.T) {
+	testCPE := pkg.MustCPE("cpe:2.3:a:name:name:3.2:*:*:*:*:*:*:*")
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected []model.ExternalRef
+	}{
+		{
+			name: "cpe + purl",
+			input: pkg.Package{
+				CPEs: []pkg.CPE{
+					testCPE,
+				},
+				PURL: "a-purl",
+			},
+			expected: []model.ExternalRef{
+				{
+					ReferenceCategory: model.SecurityReferenceCategory,
+					ReferenceLocator:  testCPE.BindToFmtString(),
+					ReferenceType:     model.Cpe23ExternalRefType,
+				},
+				{
+					ReferenceCategory: model.PackageManagerReferenceCategory,
+					ReferenceLocator:  "a-purl",
+					ReferenceType:     model.PurlExternalRefType,
+				},
+			},
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.ElementsMatch(t, test.expected, ExternalRefs(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/files.go

@@ -0,0 +1,51 @@
+package spdxhelpers
+
+import (
+	"crypto/sha256"
+	"fmt"
+	"path/filepath"
+
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func Files(packageSpdxID string, p *pkg.Package) (files []model.File, fileIDs []string, relationships []model.Relationship) {
+	files = make([]model.File, 0)
+	fileIDs = make([]string, 0)
+	relationships = make([]model.Relationship, 0)
+
+	if !hasMetadata(p) {
+		return files, fileIDs, relationships
+	}
+
+	pkgFileOwner, ok := p.Metadata.(pkg.FileOwner)
+	if !ok {
+		return files, fileIDs, relationships
+	}
+
+	for _, ownedFilePath := range pkgFileOwner.OwnedFiles() {
+		baseFileName := filepath.Base(ownedFilePath)
+		pathHash := sha256.Sum256([]byte(ownedFilePath))
+		fileSpdxID := model.ElementID(fmt.Sprintf("File-%s-%x", p.Name, pathHash)).String()
+
+		fileIDs = append(fileIDs, fileSpdxID)
+
+		files = append(files, model.File{
+			FileName: ownedFilePath,
+			Item: model.Item{
+				Element: model.Element{
+					SPDXID: fileSpdxID,
+					Name:   baseFileName,
+				},
+			},
+		})
+
+		relationships = append(relationships, model.Relationship{
+			SpdxElementID:      packageSpdxID,
+			RelationshipType:   model.ContainsRelationship,
+			RelatedSpdxElement: fileSpdxID,
+		})
+	}
+
+	return files, fileIDs, relationships
+}

internal/formats/common/spdxhelpers/homepage.go

@@ -0,0 +1,15 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func Homepage(p *pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.GemMetadata:
+			return metadata.Homepage
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Homepage
+		}
+	}
+	return ""
+}

internal/formats/common/spdxhelpers/homepage_test.go

@@ -0,0 +1,56 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Homepage(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from gem",
+			input: pkg.Package{
+				Metadata: pkg.GemMetadata{
+					Homepage: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Homepage(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/license.go

@@ -0,0 +1,37 @@
+package spdxhelpers
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/internal/spdxlicense"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func License(p *pkg.Package) string {
+	// source: https://spdx.github.io/spdx-spec/3-package-information/#313-concluded-license
+	// The options to populate this field are limited to:
+	// A valid SPDX License Expression as defined in Appendix IV;
+	// NONE, if the SPDX file creator concludes there is no license available for this package; or
+	// NOASSERTION if:
+	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
+	//   (ii) the SPDX file creator has made no attempt to determine this field; or
+	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
+
+	if !packageExists(p) || len(p.Licenses) == 0 {
+		return "NONE"
+	}
+
+	// take all licenses and assume an AND expression; for information about license expressions see https://spdx.github.io/spdx-spec/appendix-IV-SPDX-license-expressions/
+	var parsedLicenses []string
+	for _, l := range p.Licenses {
+		if value, exists := spdxlicense.ID(l); exists {
+			parsedLicenses = append(parsedLicenses, value)
+		}
+	}
+
+	if len(parsedLicenses) == 0 {
+		return "NOASSERTION"
+	}
+
+	return strings.Join(parsedLicenses, " AND ")
+}

internal/formats/common/spdxhelpers/license_test.go

@@ -0,0 +1,73 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_License(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			name:     "no licenses",
+			input:    pkg.Package{},
+			expected: "NONE",
+		},
+		{
+			name: "no SPDX licenses",
+			input: pkg.Package{
+				Licenses: []string{
+					"made-up",
+				},
+			},
+			expected: "NOASSERTION",
+		},
+		{
+			name: "with SPDX license",
+			input: pkg.Package{
+				Licenses: []string{
+					"MIT",
+				},
+			},
+			expected: "MIT",
+		},
+		{
+			name: "with SPDX license expression",
+			input: pkg.Package{
+				Licenses: []string{
+					"MIT",
+					"GPL-3.0",
+				},
+			},
+			expected: "MIT AND GPL-3.0",
+		},
+		{
+			name: "cap insensitive",
+			input: pkg.Package{
+				Licenses: []string{
+					"gpl-3.0",
+				},
+			},
+			expected: "GPL-3.0",
+		},
+		{
+			name: "debian to spdx conversion",
+			input: pkg.Package{
+				Licenses: []string{
+					"GPL-2",
+				},
+			},
+			expected: "GPL-2.0",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, License(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/none_if_empty.go

@@ -0,0 +1,12 @@
+package spdxhelpers
+
+import (
+	"strings"
+)
+
+func NoneIfEmpty(value string) string {
+	if strings.TrimSpace(value) == "" {
+		return "NONE"
+	}
+	return value
+}

internal/formats/common/spdxhelpers/none_if_empty_test.go

@@ -0,0 +1,41 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_noneIfEmpty(t *testing.T) {
+	tests := []struct {
+		name     string
+		value    string
+		expected string
+	}{
+		{
+			name:     "non-zero value",
+			value:    "something",
+			expected: "something",
+		},
+		{
+			name:     "empty",
+			value:    "",
+			expected: "NONE",
+		},
+		{
+			name:     "space",
+			value:    " ",
+			expected: "NONE",
+		},
+		{
+			name:     "tab",
+			value:    "\t",
+			expected: "NONE",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, NoneIfEmpty(test.value))
+		})
+	}
+}

internal/formats/common/spdxhelpers/originator_test.go

@@ -0,0 +1,114 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Originator(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from gem",
+			input: pkg.Package{
+				Metadata: pkg.GemMetadata{
+					Authors: []string{
+						"auth1",
+						"auth2",
+					},
+				},
+			},
+			expected: "auth1",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Author: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					Maintainer: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from python - just name",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					Author: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from python - just email",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					AuthorEmail: "auth@auth.gov",
+				},
+			},
+			expected: "auth@auth.gov",
+		},
+		{
+			name: "from python - both name and email",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					Author:      "auth",
+					AuthorEmail: "auth@auth.gov",
+				},
+			},
+			expected: "auth <auth@auth.gov>",
+		},
+		{
+			name: "from rpm",
+			input: pkg.Package{
+				Metadata: pkg.RpmdbMetadata{
+					Vendor: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from dpkg",
+			input: pkg.Package{
+				Metadata: pkg.DpkgMetadata{
+					Maintainer: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Author: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Originator(&test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/origintor.go

@@ -0,0 +1,37 @@
+package spdxhelpers
+
+import (
+	"fmt"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func Originator(p *pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return metadata.Maintainer
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Author
+		case pkg.PythonPackageMetadata:
+			author := metadata.Author
+			if author == "" {
+				return metadata.AuthorEmail
+			}
+			if metadata.AuthorEmail != "" {
+				author += fmt.Sprintf(" <%s>", metadata.AuthorEmail)
+			}
+			return author
+		case pkg.GemMetadata:
+			if len(metadata.Authors) > 0 {
+				return metadata.Authors[0]
+			}
+			return ""
+		case pkg.RpmdbMetadata:
+			return metadata.Vendor
+		case pkg.DpkgMetadata:
+			return metadata.Maintainer
+		}
+	}
+	return ""
+}

internal/formats/common/spdxhelpers/source_info.go

@@ -0,0 +1,43 @@
+package spdxhelpers
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func SourceInfo(p *pkg.Package) string {
+	if !packageExists(p) {
+		return ""
+	}
+
+	answer := ""
+	switch p.Type {
+	case pkg.RpmPkg:
+		answer = "acquired package info from RPM DB"
+	case pkg.ApkPkg:
+		answer = "acquired package info from APK DB"
+	case pkg.DebPkg:
+		answer = "acquired package info from DPKG DB"
+	case pkg.NpmPkg:
+		answer = "acquired package info from installed node module manifest file"
+	case pkg.PythonPkg:
+		answer = "acquired package info from installed python package manifest file"
+	case pkg.JavaPkg, pkg.JenkinsPluginPkg:
+		answer = "acquired package info from installed java archive"
+	case pkg.GemPkg:
+		answer = "acquired package info from installed gem metadata file"
+	case pkg.GoModulePkg:
+		answer = "acquired package info from go module information"
+	case pkg.RustPkg:
+		answer = "acquired package info from rust cargo manifest"
+	default:
+		answer = "acquired package info from the following paths"
+	}
+	var paths []string
+	for _, l := range p.Locations {
+		paths = append(paths, l.RealPath)
+	}
+
+	return answer + ": " + strings.Join(paths, ", ")
+}

internal/formats/common/spdxhelpers/source_info_test.go

@@ -0,0 +1,141 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_SourceInfo(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected []string
+	}{
+		{
+			name: "locations are captured",
+			input: pkg.Package{
+				// note: no type given
+				Locations: []source.Location{
+					{
+						RealPath:    "/a-place",
+						VirtualPath: "/b-place",
+					},
+					{
+						RealPath:    "/c-place",
+						VirtualPath: "/d-place",
+					},
+				},
+			},
+			expected: []string{
+				"from the following paths",
+				"/a-place",
+				"/c-place",
+			},
+		},
+		{
+			// note: no specific support for this
+			input: pkg.Package{
+				Type: pkg.KbPkg,
+			},
+			expected: []string{
+				"from the following paths",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.RpmPkg,
+			},
+			expected: []string{
+				"from RPM DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.ApkPkg,
+			},
+			expected: []string{
+				"from APK DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.DebPkg,
+			},
+			expected: []string{
+				"from DPKG DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.NpmPkg,
+			},
+			expected: []string{
+				"from installed node module manifest file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.PythonPkg,
+			},
+			expected: []string{
+				"from installed python package manifest file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.JavaPkg,
+			},
+			expected: []string{
+				"from installed java archive",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.JenkinsPluginPkg,
+			},
+			expected: []string{
+				"from installed java archive",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.GemPkg,
+			},
+			expected: []string{
+				"from installed gem metadata file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.GoModulePkg,
+			},
+			expected: []string{
+				"from go module information",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.RustPkg,
+			},
+			expected: []string{
+				"from rust cargo manifest",
+			},
+		},
+	}
+	var pkgTypes []pkg.Type
+	for _, test := range tests {
+		t.Run(test.name+" "+string(test.input.Type), func(t *testing.T) {
+			if test.input.Type != "" {
+				pkgTypes = append(pkgTypes, test.input.Type)
+			}
+			actual := SourceInfo(&test.input)
+			for _, expected := range test.expected {
+				assert.Contains(t, actual, expected)
+			}
+		})
+	}
+	assert.ElementsMatch(t, pkg.AllPkgs, pkgTypes, "missing one or more package types to test against (maybe a package type was added?)")
+}

internal/formats/formats.go

@@ -4,10 +4,9 @@ import (
 	"bytes"
 
 	"github.com/anchore/syft/internal/formats/cyclonedx12xml"
-
-	"github.com/anchore/syft/internal/formats/table"
-
+	"github.com/anchore/syft/internal/formats/spdx22json"
 	"github.com/anchore/syft/internal/formats/syftjson"
+	"github.com/anchore/syft/internal/formats/table"
 	"github.com/anchore/syft/syft/format"
 )
 
@@ -17,6 +16,7 @@ func All() []format.Format {
 		syftjson.Format(),
 		table.Format(),
 		cyclonedx12xml.Format(),
+		spdx22json.Format(),
 	}
 }
 

internal/formats/spdx22json/encoder.go

@@ -0,0 +1,24 @@
+package spdx22json
+
+import (
+	"encoding/json"
+	"io"
+
+	"github.com/anchore/syft/syft/distro"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+)
+
+const anchoreNamespace = "https://anchore.com/syft"
+
+func encoder(output io.Writer, catalog *pkg.Catalog, srcMetadata *source.Metadata, d *distro.Distro, scope source.Scope) error {
+	doc := toFormatModel(catalog, srcMetadata, d, scope)
+
+	enc := json.NewEncoder(output)
+	// prevent > and < from being escaped in the payload
+	enc.SetEscapeHTML(false)
+	enc.SetIndent("", " ")
+
+	return enc.Encode(&doc)
+}

internal/formats/spdx22json/encoder_test.go

@@ -1,19 +1,22 @@
-package packages
+package spdx22json
 
 import (
 	"flag"
 	"regexp"
 	"testing"
 
+	"github.com/anchore/syft/syft/source"
+
 	"github.com/anchore/syft/internal/formats/common/testutils"
+	"github.com/anchore/syft/syft/format"
 )
 
 var updateSpdxJson = flag.Bool("update-spdx-json", false, "update the *.golden files for spdx-json presenters")
 
 func TestSPDXJSONDirectoryPresenter(t *testing.T) {
-	catalog, metadata, _ := testutils.DirectoryInput(t)
+	catalog, metadata, distro := testutils.DirectoryInput(t)
 	testutils.AssertPresenterAgainstGoldenSnapshot(t,
-		NewSPDXJSONPresenter(catalog, metadata),
+		format.NewPresenter(encoder, catalog, &metadata, distro, source.UnknownScope),
 		*updateSpdxJson,
 		spdxJsonRedactor,
 	)
@@ -21,9 +24,9 @@ func TestSPDXJSONDirectoryPresenter(t *testing.T) {
 
 func TestSPDXJSONImagePresenter(t *testing.T) {
 	testImage := "image-simple"
-	catalog, metadata, _ := testutils.ImageInput(t, testImage)
+	catalog, metadata, distro := testutils.ImageInput(t, testImage, testutils.FromSnapshot())
 	testutils.AssertPresenterAgainstGoldenImageSnapshot(t,
-		NewSPDXJSONPresenter(catalog, metadata),
+		format.NewPresenter(encoder, catalog, &metadata, distro, source.SquashedScope),
 		testImage,
 		*updateSpdxJson,
 		spdxJsonRedactor,

internal/formats/spdx22json/format.go

@@ -0,0 +1,13 @@
+package spdx22json
+
+import "github.com/anchore/syft/syft/format"
+
+// note: this format is LOSSY relative to the syftjson formation, which means that decoding and validation is not supported at this time
+func Format() format.Format {
+	return format.NewFormat(
+		format.SPDXJSONOption,
+		encoder,
+		nil,
+		nil,
+	)
+}

internal/formats/spdx22json/model/annotation.go

@@ -0,0 +1,21 @@
+package model
+
+import "time"
+
+type AnnotationType string
+
+const (
+	ReviewerAnnotationType AnnotationType = "REVIEWER"
+	OtherAnnotationType    AnnotationType = "OTHER"
+)
+
+type Annotation struct {
+	// Identify when the comment was made. This is to be specified according to the combined date and time in the
+	// UTC format, as specified in the ISO 8601 standard.
+	AnnotationDate time.Time `json:"annotationDate"`
+	// Type of the annotation
+	AnnotationType AnnotationType `json:"annotationType"`
+	// This field identifies the person, organization or tool that has commented on a file, package, or the entire document.
+	Annotator string `json:"annotator"`
+	Comment   string `json:"comment"`
+}

internal/formats/spdx22json/model/checksum.go

@@ -0,0 +1,7 @@
+package model
+
+type Checksum struct {
+	// Identifies the algorithm used to produce the subject Checksum. One of: "SHA256", "SHA1", "SHA384", "MD2", "MD4", "SHA512", "MD6", "MD5", "SHA224"
+	Algorithm     string `json:"algorithm"`
+	ChecksumValue string `json:"checksumValue"`
+}

internal/formats/spdx22json/model/creation_info.go

@@ -0,0 +1,19 @@
+package model
+
+import "time"
+
+type CreationInfo struct {
+	Comment string `json:"comment,omitempty"`
+	// Identify when the SPDX file was originally created. The date is to be specified according to combined date and
+	// time in UTC format as specified in ISO 8601 standard. This field is distinct from the fields in section 8,
+	// which involves the addition of information during a subsequent review.
+	Created time.Time `json:"created"`
+	// Identify who (or what, in the case of a tool) created the SPDX file. If the SPDX file was created by an
+	// individual, indicate the person's name. If the SPDX file was created on behalf of a company or organization,
+	// indicate the entity name. If the SPDX file was created using a software tool, indicate the name and version
+	// for that tool. If multiple participants or tools were involved, use multiple instances of this field. Person
+	// name or organization name may be designated as “anonymous” if appropriate.
+	Creators []string `json:"creators"`
+	// An optional field for creators of the SPDX file to provide the version of the SPDX License List used when the SPDX file was created.
+	LicenseListVersion string `json:"licenseListVersion"`
+}

internal/formats/spdx22json/model/document.go

@@ -0,0 +1,49 @@
+package model
+
+import "github.com/anchore/syft/syft/source"
+
+// derived from:
+// - https://spdx.github.io/spdx-spec/appendix-III-RDF-data-model-implementation-and-identifier-syntax/
+// - https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json
+// - https://github.com/spdx/spdx-spec/tree/v2.2/ontology
+
+type Document struct {
+	Element
+	SPDXVersion string `json:"spdxVersion"`
+	// One instance is required for each SPDX file produced. It provides the necessary information for forward
+	// and backward compatibility for processing tools.
+	CreationInfo CreationInfo `json:"creationInfo"`
+	// SyftSourceData contains information about what is being described in this SPDX document (e.g. a container image, a directory, etc)
+	SyftSourceData *source.Metadata `json:"syftSourceData,omitempty"`
+	// 2.2: Data License; should be "CC0-1.0"
+	// Cardinality: mandatory, one
+	// License expression for dataLicense.  Compliance with the SPDX specification includes populating the SPDX
+	// fields therein with data related to such fields (\"SPDX-Metadata\"). The SPDX specification contains numerous
+	// fields where an SPDX document creator may provide relevant explanatory text in SPDX-Metadata. Without
+	// opining on the lawfulness of \"database rights\" (in jurisdictions where applicable), such explanatory text
+	// is copyrightable subject matter in most Berne Convention countries. By using the SPDX specification, or any
+	// portion hereof, you hereby agree that any copyright rights (as determined by your jurisdiction) in any
+	// SPDX-Metadata, including without limitation explanatory text, shall be subject to the terms of the Creative
+	// Commons CC0 1.0 Universal license. For SPDX-Metadata not containing any copyright rights, you hereby agree
+	// and acknowledge that the SPDX-Metadata is provided to you \"as-is\" and without any representations or
+	// warranties of any kind concerning the SPDX-Metadata, express, implied, statutory or otherwise, including
+	// without limitation warranties of title, merchantability, fitness for a particular purpose, non-infringement,
+	// or the absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not
+	// discoverable, all to the greatest extent permissible under applicable law.
+	DataLicense string `json:"dataLicense"`
+	// Information about an external SPDX document reference including the checksum. This allows for verification of the external references.
+	ExternalDocumentRefs []ExternalDocumentRef `json:"externalDocumentRefs,omitempty"`
+	// Indicates that a particular ExtractedLicensingInfo was defined in the subject SpdxDocument.
+	HasExtractedLicensingInfos []HasExtractedLicensingInfo `json:"hasExtractedLicensingInfos,omitempty"`
+	// note: found in example documents from SPDX, but not in the JSON schema. See https://spdx.github.io/spdx-spec/2-document-creation-information/#25-spdx-document-namespace
+	DocumentNamespace string `json:"documentNamespace"`
+	// note: found in example documents from SPDX, but not in the JSON schema
+	// DocumentDescribes []string  `json:"documentDescribes"`
+	Packages []Package `json:"packages"`
+	// Files referenced in the SPDX document
+	Files []File `json:"files,omitempty"`
+	// Snippets referenced in the SPDX document
+	Snippets []Snippet `json:"snippets,omitempty"`
+	// Relationships referenced in the SPDX document
+	Relationships []Relationship `json:"relationships,omitempty"`
+}

internal/formats/spdx22json/model/element.go

@@ -0,0 +1,12 @@
+package model
+
+type Element struct {
+	SPDXID string `json:"SPDXID"`
+	// Identify name of this SpdxElement.
+	Name string `json:"name"`
+	// Relationships referenced in the SPDX document
+	Relationships []Relationship `json:"relationships,omitempty"`
+	// Provide additional information about an SpdxElement.
+	Annotations []Annotation `json:"annotations,omitempty"`
+	Comment     string       `json:"comment,omitempty"`
+}

internal/formats/spdx22json/model/element_id.go

@@ -0,0 +1,37 @@
+package model
+
+// ElementID represents the identifier string portion of an SPDX element
+// identifier. DocElementID should be used for any attributes which can
+// contain identifiers defined in a different SPDX document.
+// ElementIDs should NOT contain the mandatory 'SPDXRef-' portion.
+type ElementID string
+
+func (e ElementID) String() string {
+	return "SPDXRef-" + string(e)
+}
+
+// DocElementID represents an SPDX element identifier that could be defined
+// in a different SPDX document, and therefore could have a "DocumentRef-"
+// portion, such as Relationship and Annotations.
+// ElementID is used for attributes in which a "DocumentRef-" portion cannot
+// appear, such as a Package or File definition (since it is necessarily
+// being defined in the present document).
+// DocumentRefID will be the empty string for elements defined in the
+// present document.
+// DocElementIDs should NOT contain the mandatory 'DocumentRef-' or
+// 'SPDXRef-' portions.
+type DocElementID struct {
+	DocumentRefID string
+	ElementRefID  ElementID
+}
+
+// RenderDocElementID takes a DocElementID and returns the string equivalent,
+// with the SPDXRef- prefix (and, if applicable, the DocumentRef- prefix)
+// reinserted.
+func (d DocElementID) String() string {
+	prefix := ""
+	if d.DocumentRefID != "" {
+		prefix = "DocumentRef-" + d.DocumentRefID + ":"
+	}
+	return prefix + d.ElementRefID.String()
+}

internal/formats/spdx22json/model/external_document_ref.go

@@ -0,0 +1,9 @@
+package model
+
+type ExternalDocumentRef struct {
+	// externalDocumentId is a string containing letters, numbers, ., - and/or + which uniquely identifies an external document within this document.
+	ExternalDocumentID string   `json:"externalDocumentId"`
+	Checksum           Checksum `json:"checksum"`
+	// SPDX ID for SpdxDocument.  A propoerty containing an SPDX document.
+	SpdxDocument string `json:"spdxDocument"`
+}

internal/formats/spdx22json/model/external_ref.go

@@ -0,0 +1,43 @@
+package model
+
+type ReferenceCategory string
+
+const (
+	SecurityReferenceCategory       ReferenceCategory = "SECURITY"
+	PackageManagerReferenceCategory ReferenceCategory = "PACKAGE_MANAGER"
+	OtherReferenceCategory          ReferenceCategory = "OTHER"
+)
+
+// source: https://spdx.github.io/spdx-spec/appendix-VI-external-repository-identifiers/
+
+type ExternalRefType string
+
+const (
+	// see https://nvd.nist.gov/cpe
+	Cpe22ExternalRefType ExternalRefType = "cpe22Type"
+	// see https://nvd.nist.gov/cpe
+	Cpe23ExternalRefType ExternalRefType = "cpe23Type"
+	// see http://repo1.maven.org/maven2/
+	MavenCentralExternalRefType ExternalRefType = "maven-central"
+	// see https://www.npmjs.com/
+	NpmExternalRefType ExternalRefType = "npm"
+	// see https://www.nuget.org/
+	NugetExternalRefType ExternalRefType = "nuget"
+	// see http://bower.io/
+	BowerExternalRefType ExternalRefType = "bower"
+	// see https://github.com/package-url/purl-spec
+	PurlExternalRefType ExternalRefType = "purl"
+	// These point to objects present in the Software Heritage archive by the means of SoftWare Heritage persistent Identifiers (SWHID)
+	SwhExternalRefType ExternalRefType = "swh"
+)
+
+type ExternalRef struct {
+	Comment string `json:"comment,omitempty"`
+	// Category for the external reference.
+	ReferenceCategory ReferenceCategory `json:"referenceCategory"`
+	// The unique string with no spaces necessary to access the package-specific information, metadata, or content
+	// within the target location. The format of the locator is subject to constraints defined by the <type>.
+	ReferenceLocator string `json:"referenceLocator"`
+	// Type of the external reference. These are defined in an appendix in the SPDX specification.
+	ReferenceType ExternalRefType `json:"referenceType"`
+}

internal/formats/spdx22json/model/file.go

@@ -0,0 +1,41 @@
+package model
+
+type FileType string
+
+const (
+	DocumentationFileType FileType = "DOCUMENTATION"
+	ImageFileType         FileType = "IMAGE"
+	VideoFileType         FileType = "VIDEO"
+	ArchiveFileType       FileType = "ARCHIVE"
+	SpdxFileType          FileType = "SPDX"
+	ApplicationFileType   FileType = "APPLICATION"
+	SourceFileType        FileType = "SOURCE"
+	BinaryFileType        FileType = "BINARY"
+	TextFileType          FileType = "TEXT"
+	AudioFileType         FileType = "AUDIO"
+	OtherFileType         FileType = "OTHER"
+)
+
+type File struct {
+	Item
+	// (At least one is required.) The checksum property provides a mechanism that can be used to verify that the
+	// contents of a File or Package have not changed.
+	Checksums []Checksum `json:"checksums,omitempty"`
+	// This field provides a place for the SPDX file creator to record file contributors. Contributors could include
+	// names of copyright holders and/or authors who may not be copyright holders yet contributed to the file content.
+	FileContributors []string `json:"fileContributors,omitempty"`
+	// Each element is a SPDX ID for a File.
+	FileDependencies []string `json:"fileDependencies,omitempty"`
+	// The name of the file relative to the root of the package.
+	FileName string `json:"fileName"`
+	// The type of the file
+	FileTypes []string `json:"fileTypes,omitempty"`
+	// This field provides a place for the SPDX file creator to record potential legal notices found in the file.
+	// This may or may not include copyright statements.
+	NoticeText string `json:"noticeText,omitempty"`
+	// Indicates the project in which the SpdxElement originated. Tools must preserve doap:homepage and doap:name
+	// properties and the URI (if one is known) of doap:Project resources that are values of this property. All other
+	// properties of doap:Projects are not directly supported by SPDX and may be dropped when translating to or
+	// from some SPDX formats(deprecated).
+	ArtifactOf []string `json:"artifactOf,omitempty"`
+}

internal/formats/spdx22json/model/has_extracted_licensing_info.go

@@ -0,0 +1,14 @@
+package model
+
+type HasExtractedLicensingInfo struct {
+	// Verbatim license or licensing notice text that was discovered.
+	ExtractedText string `json:"extractedText"`
+	// A human readable short form license identifier for a license. The license ID is iether on the standard license
+	// oist or the form \"LicenseRef-\"[idString] where [idString] is a unique string containing letters,
+	// numbers, \".\", \"-\" or \"+\".
+	LicenseID string `json:"licenseId"`
+	Comment   string `json:"comment,omitempty"`
+	// Identify name of this SpdxElement.
+	Name     string   `json:"name,omitempty"`
+	SeeAlsos []string `json:"seeAlsos,omitempty"`
+}

internal/formats/spdx22json/model/item.go

@@ -0,0 +1,22 @@
+package model
+
+type Item struct {
+	Element
+	// The licenseComments property allows the preparer of the SPDX document to describe why the licensing in
+	// spdx:licenseConcluded was chosen.
+	LicenseComments  string `json:"licenseComments,omitempty"`
+	LicenseConcluded string `json:"licenseConcluded"`
+	// The licensing information that was discovered directly within the package. There will be an instance of this
+	// property for each distinct value of alllicenseInfoInFile properties of all files contained in the package.
+	LicenseInfoFromFiles []string `json:"licenseInfoFromFiles,omitempty"`
+	// Licensing information that was discovered directly in the subject file. This is also considered a declared license for the file.
+	LicenseInfoInFiles []string `json:"licenseInfoInFiles,omitempty"`
+	// The text of copyright declarations recited in the Package or File.
+	CopyrightText string `json:"copyrightText,omitempty"`
+	// This field provides a place for the SPDX data creator to record acknowledgements that may be required to be
+	// communicated in some contexts. This is not meant to include the actual complete license text (see
+	// licenseConculded and licenseDeclared), and may or may not include copyright notices (see also copyrightText).
+	// The SPDX data creator may use this field to record other acknowledgements, such as particular clauses from
+	// license texts, which may be necessary or desirable to reproduce.
+	AttributionTexts []string `json:"attributionTexts,omitempty"`
+}

internal/formats/spdx22json/model/package.go

@@ -0,0 +1,50 @@
+package model
+
+type Package struct {
+	Item
+	// The checksum property provides a mechanism that can be used to verify that the contents of a File or
+	// Package have not changed.
+	Checksums []Checksum `json:"checksums,omitempty"`
+	// Provides a detailed description of the package.
+	Description string `json:"description,omitempty"`
+	// The URI at which this package is available for download. Private (i.e., not publicly reachable) URIs are
+	// acceptable as values of this property. The values http://spdx.org/rdf/terms#none and http://spdx.org/rdf/terms#noassertion
+	// may be used to specify that the package is not downloadable or that no attempt was made to determine its
+	// download location, respectively.
+	DownloadLocation string `json:"downloadLocation,omitempty"`
+	// An External Reference allows a Package to reference an external source of additional information, metadata,
+	// enumerations, asset identifiers, or downloadable content believed to be relevant to the Package.
+	ExternalRefs []ExternalRef `json:"externalRefs,omitempty"`
+	// Indicates whether the file content of this package has been available for or subjected to analysis when
+	// creating the SPDX document. If false indicates packages that represent metadata or URI references to a
+	// project, product, artifact, distribution or a component. If set to false, the package must not contain any files
+	FilesAnalyzed bool `json:"filesAnalyzed"`
+	// Indicates that a particular file belongs to a package (elements are SPDX ID for a File).
+	HasFiles []string `json:"hasFiles,omitempty"`
+	// Provide a place for the SPDX file creator to record a web site that serves as the package's home page.
+	// This link can also be used to reference further information about the package referenced by the SPDX file creator.
+	Homepage string `json:"homepage,omitempty"`
+	// List the licenses that have been declared by the authors of the package. Any license information that does not
+	// originate from the package authors, e.g. license information from a third party repository, should not be included in this field.
+	LicenseDeclared string `json:"licenseDeclared"`
+	// The name and, optionally, contact information of the person or organization that originally created the package.
+	// Values of this property must conform to the agent and tool syntax.
+	Originator string `json:"originator,omitempty"`
+	// The base name of the package file name. For example, zlib-1.2.5.tar.gz.
+	PackageFileName string `json:"packageFileName,omitempty"`
+	// A manifest based verification code (the algorithm is defined in section 4.7 of the full specification) of the
+	// SPDX Item. This allows consumers of this data and/or database to determine if an SPDX item they have in hand
+	// is identical to the SPDX item from which the data was produced. This algorithm works even if the SPDX document
+	// is included in the SPDX item.
+	PackageVerificationCode *PackageVerificationCode `json:"packageVerificationCode,omitempty"`
+	// Allows the producer(s) of the SPDX document to describe how the package was acquired and/or changed from the original source.
+	SourceInfo string `json:"sourceInfo,omitempty"`
+	// Provides a short description of the package.
+	Summary string `json:"summary,omitempty"`
+	// The name and, optionally, contact information of the person or organization who was the immediate supplier
+	// of this package to the recipient. The supplier may be different than originator when the software has been
+	// repackaged. Values of this property must conform to the agent and tool syntax.
+	Supplier string `json:"supplier,omitempty"`
+	// Provides an indication of the version of the package that is described by this SpdxDocument.
+	VersionInfo string `json:"versionInfo,omitempty"`
+}

internal/formats/spdx22json/model/package_verification_code.go

@@ -0,0 +1,23 @@
+package model
+
+// Why are there two package identifier fields Package Checksum and Package Verification?
+// Although the values of the two fields Package Checksum and Package Verification are similar, they each serve a
+// different purpose. The Package Checksum provides a unique identifier of a software package which is computed by
+// taking the SHA1 of the entire software package file. This enables one to quickly determine if two different copies
+// of a package are the same. One disadvantage of this approach is that one cannot add an SPDX data file into the
+// original package without changing the Package Checksum value. Alternatively, the Package Verification field enables
+// the inclusion of an SPDX file. It enables one to quickly verify if one or more of the original package files has
+// changed. The Package Verification field is a unique identifier that is based on SHAing only the original package
+// files (e.g., excluding the SPDX file). This allows one to add an SPDX file to the original package without changing
+// this unique identifier.
+// source: https://wiki.spdx.org/view/SPDX_FAQ
+type PackageVerificationCode struct {
+	// "A file that was excluded when calculating the package verification code. This is usually a file containing
+	// SPDX data regarding the package. If a package contains more than one SPDX file all SPDX files must be excluded
+	// from the package verification code. If this is not done it would be impossible to correctly calculate the
+	// verification codes in both files.
+	PackageVerificationCodeExcludedFiles []string `json:"packageVerificationCodeExcludedFiles"`
+
+	// The actual package verification code as a hex encoded value.
+	PackageVerificationCodeValue string `json:"packageVerificationCodeValue"`
+}

internal/formats/spdx22json/model/relationship.go

@@ -0,0 +1,183 @@
+package model
+
+type Relationship struct {
+	// Id to which the SPDX element is related
+	SpdxElementID string `json:"spdxElementId"`
+	// Describes the type of relationship between two SPDX elements.
+	RelationshipType RelationshipType `json:"relationshipType"`
+	// SPDX ID for SpdxElement.  A related SpdxElement.
+	RelatedSpdxElement string `json:"relatedSpdxElement"`
+	Comment            string `json:"comment,omitempty"`
+}
+
+// source: https://spdx.github.io/spdx-spec/7-relationships-between-SPDX-elements/
+type RelationshipType string
+
+const (
+	// DescribedByRelationship is to be used when SPDXRef-A is described by SPDXREF-Document.
+	// Example: The package 'WildFly' is described by SPDX document WildFly.spdx.
+	DescribedByRelationship RelationshipType = "DESCRIBED_BY"
+
+	// ContainsRelationship is to be used when SPDXRef-A contains SPDXRef-B.
+	// Example: An ARCHIVE file bar.tgz contains a SOURCE file foo.c.
+	ContainsRelationship RelationshipType = "CONTAINS"
+
+	// ContainedByRelationship is to be used when SPDXRef-A is contained by SPDXRef-B.
+	// Example: A SOURCE file foo.c is contained by ARCHIVE file bar.tgz
+	ContainedByRelationship RelationshipType = "CONTAINED_BY"
+
+	// DependsOnRelationship is to be used when SPDXRef-A depends on SPDXRef-B.
+	// Example: Package A depends on the presence of package B in order to build and run
+	DependsOnRelationship RelationshipType = "DEPENDS_ON"
+
+	// DependencyOfRelationship is to be used when SPDXRef-A is dependency of SPDXRef-B.
+	// Example: A is explicitly stated as a dependency of B in a machine-readable file. Use when a package manager does not define scopes.
+	DependencyOfRelationship RelationshipType = "DEPENDENCY_OF"
+
+	// DependencyManifestOfRelationship is to be used when SPDXRef-A is a manifest file that lists a set of dependencies for SPDXRef-B.
+	// Example: A file package.json is the dependency manifest of a package foo. Note that only one manifest should be used to define the same dependency graph.
+	DependencyManifestOfRelationship RelationshipType = "DEPENDENCY_MANIFEST_OF"
+
+	// BuildDependencyOfRelationship is to be used when SPDXRef-A is a build dependency of SPDXRef-B.
+	// Example: A is in the compile scope of B in a Maven project.
+	BuildDependencyOfRelationship RelationshipType = "BUILD_DEPENDENCY_OF"
+
+	// DevDependencyOfRelationship is to be used when SPDXRef-A is a development dependency of SPDXRef-B.
+	// Example: A is in the devDependencies scope of B in a Maven project.
+	DevDependencyOfRelationship RelationshipType = "DEV_DEPENDENCY_OF"
+
+	// OptionalDependencyOfRelationship is to be used when SPDXRef-A is an optional dependency of SPDXRef-B.
+	// Example: Use when building the code will proceed even if a dependency cannot be found, fails to install, or is only installed on a specific platform. For example, A is in the optionalDependencies scope of npm project B.
+	OptionalDependencyOfRelationship RelationshipType = "OPTIONAL_DEPENDENCY_OF"
+
+	// ProvidedDependencyOfRelationship is to be used when SPDXRef-A is a to be provided dependency of SPDXRef-B.
+	// Example: A is in the provided scope of B in a Maven project, indicating that the project expects it to be provided, for instance, by the container or JDK.
+	ProvidedDependencyOfRelationship RelationshipType = "PROVIDED_DEPENDENCY_OF"
+
+	// TestDependencyOfRelationship is to be used when SPDXRef-A is a test dependency of SPDXRef-B.
+	// Example: A is in the test scope of B in a Maven project.
+	TestDependencyOfRelationship RelationshipType = "TEST_DEPENDENCY_OF"
+
+	// RuntimeDependencyOfRelationship is to be used when SPDXRef-A is a dependency required for the execution of SPDXRef-B.
+	// Example: A is in the runtime scope of B in a Maven project.
+	RuntimeDependencyOfRelationship RelationshipType = "RUNTIME_DEPENDENCY_OF"
+
+	// ExampleOfRelationship is to be used when SPDXRef-A is an example of SPDXRef-B.
+	// Example: The file or snippet that illustrates how to use an application or library.
+	ExampleOfRelationship RelationshipType = "EXAMPLE_OF"
+
+	// GeneratesRelationship is to be used when SPDXRef-A generates SPDXRef-B.
+	// Example: A SOURCE file makefile.mk generates a BINARY file a.out
+	GeneratesRelationship RelationshipType = "GENERATES"
+
+	// GeneratedFromRelationship is to be used when SPDXRef-A was generated from SPDXRef-B.
+	// Example: A BINARY file a.out has been generated from a SOURCE file makefile.mk. A BINARY file foolib.a is generated from a SOURCE file bar.c.
+	GeneratedFromRelationship RelationshipType = "GENERATED_FROM"
+
+	// AncestorOfRelationship is to be used when SPDXRef-A is an ancestor (same lineage but pre-dates) SPDXRef-B.
+	// Example: A SOURCE file makefile.mk is a version of the original ancestor SOURCE file 'makefile2.mk'
+	AncestorOfRelationship RelationshipType = "ANCESTOR_OF"
+
+	// DescendantOfRelationship is to be used when SPDXRef-A is a descendant of (same lineage but postdates) SPDXRef-B.
+	// Example: A SOURCE file makefile2.mk is a descendant of the original SOURCE file 'makefile.mk'
+	DescendantOfRelationship RelationshipType = "DESCENDANT_OF"
+
+	// VariantOfRelationship is to be used when SPDXRef-A is a variant of (same lineage but not clear which came first) SPDXRef-B.
+	// Example: A SOURCE file makefile2.mk is a variant of SOURCE file makefile.mk if they differ by some edit, but there is no way to tell which came first (no reliable date information).
+	VariantOfRelationship RelationshipType = "VARIANT_OF"
+
+	// DistributionArtifactRelationship is to be used when distributing SPDXRef-A requires that SPDXRef-B also be distributed.
+	// Example: A BINARY file foo.o requires that the ARCHIVE file bar-sources.tgz be made available on distribution.
+	DistributionArtifactRelationship RelationshipType = "DISTRIBUTION_ARTIFACT"
+
+	// PatchForRelationship is to be used when SPDXRef-A is a patch file for (to be applied to) SPDXRef-B.
+	// Example: A SOURCE file foo.diff is a patch file for SOURCE file foo.c.
+	PatchForRelationship RelationshipType = "PATCH_FOR"
+
+	// PatchAppliedRelationship is to be used when SPDXRef-A is a patch file that has been applied to SPDXRef-B.
+	// Example: A SOURCE file foo.diff is a patch file that has been applied to SOURCE file 'foo-patched.c'.
+	PatchAppliedRelationship RelationshipType = "PATCH_APPLIED"
+
+	// CopyOfRelationship is to be used when SPDXRef-A is an exact copy of SPDXRef-B.
+	// Example: A BINARY file alib.a is an exact copy of BINARY file a2lib.a.
+	CopyOfRelationship RelationshipType = "COPY_OF"
+
+	// FileAddedRelationship is to be used when SPDXRef-A is a file that was added to SPDXRef-B.
+	// Example: A SOURCE file foo.c has been added to package ARCHIVE bar.tgz.
+	FileAddedRelationship RelationshipType = "FILE_ADDED"
+
+	// FileDeletedRelationship is to be used when SPDXRef-A is a file that was deleted from SPDXRef-B.
+	// Example: A SOURCE file foo.diff has been deleted from package ARCHIVE bar.tgz.
+	FileDeletedRelationship RelationshipType = "FILE_DELETED"
+
+	// FileModifiedRelationship is to be used when SPDXRef-A is a file that was modified from SPDXRef-B.
+	// Example: A SOURCE file foo.c has been modified from SOURCE file foo.orig.c.
+	FileModifiedRelationship RelationshipType = "FILE_MODIFIED"
+
+	// ExpandedFromArchiveRelationship is to be used when SPDXRef-A is expanded from the archive SPDXRef-B.
+	// Example: A SOURCE file foo.c, has been expanded from the archive ARCHIVE file xyz.tgz.
+	ExpandedFromArchiveRelationship RelationshipType = "EXPANDED_FROM_ARCHIVE"
+
+	// DynamicLinkRelationship is to be used when SPDXRef-A dynamically links to SPDXRef-B.
+	// Example: An APPLICATION file 'myapp' dynamically links to BINARY file zlib.so.
+	DynamicLinkRelationship RelationshipType = "DYNAMIC_LINK"
+
+	// StaticLinkRelationship is to be used when SPDXRef-A statically links to SPDXRef-B.
+	// Example: An APPLICATION file 'myapp' statically links to BINARY zlib.a.
+	StaticLinkRelationship RelationshipType = "STATIC_LINK"
+
+	// DataFileOfRelationship is to be used when SPDXRef-A is a data file used in SPDXRef-B.
+	// Example: An IMAGE file 'kitty.jpg' is a data file of an APPLICATION 'hellokitty'.
+	DataFileOfRelationship RelationshipType = "DATA_FILE_OF"
+
+	// TestCaseOfRelationship is to be used when SPDXRef-A is a test case used in testing SPDXRef-B.
+	// Example: A SOURCE file testMyCode.java is a unit test file used to test an APPLICATION MyPackage.
+	TestCaseOfRelationship RelationshipType = "TEST_CASE_OF"
+
+	// BuildToolOfRelationship is to be used when SPDXRef-A is used to build SPDXRef-B.
+	// Example: A SOURCE file makefile.mk is used to build an APPLICATION 'zlib'.
+	BuildToolOfRelationship RelationshipType = "BUILD_TOOL_OF"
+
+	// DevToolOfRelationship is to be used when SPDXRef-A is used as a development tool for SPDXRef-B.
+	// Example: Any tool used for development such as a code debugger.
+	DevToolOfRelationship RelationshipType = "DEV_TOOL_OF"
+
+	// TestOfRelationship is to be used when SPDXRef-A is used for testing SPDXRef-B.
+	// Example: Generic relationship for cases where it's clear that something is used for testing but unclear whether it's TEST_CASE_OF or TEST_TOOL_OF.
+	TestOfRelationship RelationshipType = "TEST_OF"
+
+	// TestToolOfRelationship is to be used when SPDXRef-A is used as a test tool for SPDXRef-B.
+	// Example: Any tool used to test the code such as ESlint.
+	TestToolOfRelationship RelationshipType = "TEST_TOOL_OF"
+
+	// DocumentationOfRelationship is to be used when SPDXRef-A provides documentation of SPDXRef-B.
+	// Example: A DOCUMENTATION file readme.txt documents the APPLICATION 'zlib'.
+	DocumentationOfRelationship RelationshipType = "DOCUMENTATION_OF"
+
+	// OptionalComponentOfRelationship is to be used when SPDXRef-A is an optional component of SPDXRef-B.
+	// Example: A SOURCE file fool.c (which is in the contributors directory) may or may not be included in the build of APPLICATION 'atthebar'.
+	OptionalComponentOfRelationship RelationshipType = "OPTIONAL_COMPONENT_OF"
+
+	// MetafileOfRelationship is to be used when SPDXRef-A is a metafile of SPDXRef-B.
+	// Example: A SOURCE file pom.xml is a metafile of the APPLICATION 'Apache Xerces'.
+	MetafileOfRelationship RelationshipType = "METAFILE_OF"
+
+	// PackageOfRelationship is to be used when SPDXRef-A is used as a package as part of SPDXRef-B.
+	// Example: A Linux distribution contains an APPLICATION package gawk as part of the distribution MyLinuxDistro.
+	PackageOfRelationship RelationshipType = "PACKAGE_OF"
+
+	// AmendsRelationship is to be used when (current) SPDXRef-DOCUMENT amends the SPDX information in SPDXRef-B.
+	// Example: (Current) SPDX document A version 2 contains a correction to a previous version of the SPDX document A version 1. Note the reserved identifier SPDXRef-DOCUMENT for the current document is required.
+	AmendsRelationship RelationshipType = "AMENDS"
+
+	// PrerequisiteForRelationship is to be used when SPDXRef-A is a prerequisite for SPDXRef-B.
+	// Example: A library bar.dll is a prerequisite or dependency for APPLICATION foo.exe
+	PrerequisiteForRelationship RelationshipType = "PREREQUISITE_FOR"
+
+	// HasPrerequisiteRelationship is to be used when SPDXRef-A has as a prerequisite SPDXRef-B.
+	// Example: An APPLICATION foo.exe has prerequisite or dependency on bar.dll
+	HasPrerequisiteRelationship RelationshipType = "HAS_PREREQUISITE"
+
+	// OtherRelationship is to be used for a relationship which has not been defined in the formal SPDX specification. A description of the relationship should be included in the Relationship comments field.
+	OtherRelationship RelationshipType = "OTHER"
+)

internal/formats/spdx22json/model/snippet.go

@@ -0,0 +1,32 @@
+package model
+
+type StartPointer struct {
+	Offset     int `json:"offset,omitempty"`
+	LineNumber int `json:"lineNumber,omitempty"`
+	// SPDX ID for File
+	Reference string `json:"reference"`
+}
+
+type EndPointer struct {
+	Offset     int `json:"offset,omitempty"`
+	LineNumber int `json:"lineNumber,omitempty"`
+	// SPDX ID for File
+	Reference string `json:"reference"`
+}
+
+type Range struct {
+	StartPointer StartPointer `json:"startPointer"`
+	EndPointer   EndPointer   `json:"endPointer"`
+}
+
+type Snippet struct {
+	Item
+	// Licensing information that was discovered directly in the subject snippet. This is also considered a declared
+	// license for the snippet. (elements are license expressions)
+	LicenseInfoInSnippets []string `json:"licenseInfoInSnippets"`
+	// SPDX ID for File. File containing the SPDX element (e.g. the file contaning a snippet).
+	SnippetFromFile string `json:"snippetFromFile"`
+	// (At least 1 range is required). This field defines the byte range in the original host file (in X.2) that the
+	// snippet information applies to.
+	Ranges []Range `json:"ranges"`
+}

internal/formats/spdx22json/model/version.go

@@ -0,0 +1,3 @@
+package model
+
+const Version = "SPDX-2.2"

internal/formats/spdx22json/test-fixtures/image-simple/Dockerfile

@@ -0,0 +1,4 @@
+# Note: changes to this file will result in updating several test values. Consider making a new image fixture instead of editing this one.
+FROM scratch
+ADD file-1.txt /somefile-1.txt
+ADD file-2.txt /somefile-2.txt

internal/formats/spdx22json/test-fixtures/image-simple/file-1.txt

@@ -0,0 +1 @@
+this file has contents

internal/formats/spdx22json/test-fixtures/image-simple/file-2.txt

@@ -0,0 +1 @@
+file-2 contents!

internal/formats/spdx22json/test-fixtures/snapshot/TestSPDXJSONDirectoryPresenter.golden

@@ -0,0 +1,95 @@
+{
+ "SPDXID": "SPDXRef-DOCUMENT",
+ "name": "/some/path",
+ "spdxVersion": "SPDX-2.2",
+ "creationInfo": {
+  "created": "2021-10-22T19:25:38.33537Z",
+  "creators": [
+   "Organization: Anchore, Inc",
+   "Tool: syft-[not provided]"
+  ],
+  "licenseListVersion": "3.14"
+ },
+ "syftSourceData": {
+  "Scheme": "DirectoryScheme",
+  "ImageMetadata": {
+   "userInput": "",
+   "imageID": "",
+   "manifestDigest": "",
+   "mediaType": "",
+   "tags": null,
+   "imageSize": 0,
+   "layers": null,
+   "manifest": null,
+   "config": null,
+   "repoDigests": null
+  },
+  "Path": "/some/path"
+ },
+ "dataLicense": "CC0-1.0",
+ "documentNamespace": "https:/anchore.com/syft/dir/some/path-a868c45f-e62b-473f-9dd3-b72994be6294",
+ "packages": [
+  {
+   "SPDXID": "SPDXRef-Package-python-package-1-1.0.1",
+   "name": "package-1",
+   "licenseConcluded": "MIT",
+   "downloadLocation": "NOASSERTION",
+   "externalRefs": [
+    {
+     "referenceCategory": "SECURITY",
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
+     "referenceType": "cpe23Type"
+    },
+    {
+     "referenceCategory": "PACKAGE_MANAGER",
+     "referenceLocator": "a-purl-2",
+     "referenceType": "purl"
+    }
+   ],
+   "filesAnalyzed": false,
+   "hasFiles": [
+    "SPDXRef-File-package-1-efae7fecc76ca25da40f79d7ef5b8933510434914835832c7976f3e866aa756a"
+   ],
+   "licenseDeclared": "MIT",
+   "sourceInfo": "acquired package info from installed python package manifest file: /some/path/pkg1",
+   "versionInfo": "1.0.1"
+  },
+  {
+   "SPDXID": "SPDXRef-Package-deb-package-2-2.0.1",
+   "name": "package-2",
+   "licenseConcluded": "NONE",
+   "downloadLocation": "NOASSERTION",
+   "externalRefs": [
+    {
+     "referenceCategory": "SECURITY",
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
+     "referenceType": "cpe23Type"
+    },
+    {
+     "referenceCategory": "PACKAGE_MANAGER",
+     "referenceLocator": "a-purl-2",
+     "referenceType": "purl"
+    }
+   ],
+   "filesAnalyzed": false,
+   "licenseDeclared": "NONE",
+   "sourceInfo": "acquired package info from DPKG DB: /some/path/pkg1",
+   "versionInfo": "2.0.1"
+  }
+ ],
+ "files": [
+  {
+   "SPDXID": "SPDXRef-File-package-1-efae7fecc76ca25da40f79d7ef5b8933510434914835832c7976f3e866aa756a",
+   "name": "foo",
+   "licenseConcluded": "",
+   "fileName": "/some/path/pkg1/dependencies/foo"
+  }
+ ],
+ "relationships": [
+  {
+   "spdxElementId": "SPDXRef-Package-python-package-1-1.0.1",
+   "relationshipType": "CONTAINS",
+   "relatedSpdxElement": "SPDXRef-File-package-1-efae7fecc76ca25da40f79d7ef5b8933510434914835832c7976f3e866aa756a"
+  }
+ ]
+}

internal/formats/spdx22json/test-fixtures/snapshot/TestSPDXJSONImagePresenter.golden

@@ -0,0 +1,90 @@
+{
+ "SPDXID": "SPDXRef-DOCUMENT",
+ "name": "user-image-input",
+ "spdxVersion": "SPDX-2.2",
+ "creationInfo": {
+  "created": "2021-10-22T19:25:38.341582Z",
+  "creators": [
+   "Organization: Anchore, Inc",
+   "Tool: syft-[not provided]"
+  ],
+  "licenseListVersion": "3.14"
+ },
+ "syftSourceData": {
+  "Scheme": "ImageScheme",
+  "ImageMetadata": {
+   "userInput": "user-image-input",
+   "imageID": "sha256:2480160b55bec40c44d3b145c7b2c1c47160db8575c3dcae086d76b9370ae7ca",
+   "manifestDigest": "sha256:2731251dc34951c0e50fcc643b4c5f74922dad1a5d98f302b504cf46cd5d9368",
+   "mediaType": "application/vnd.docker.distribution.manifest.v2+json",
+   "tags": [
+    "stereoscope-fixture-image-simple:85066c51088bdd274f7a89e99e00490f666c49e72ffc955707cd6e18f0e22c5b"
+   ],
+   "imageSize": 38,
+   "layers": [
+    {
+     "mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
+     "digest": "sha256:fb6beecb75b39f4bb813dbf177e501edd5ddb3e69bb45cedeb78c676ee1b7a59",
+     "size": 22
+    },
+    {
+     "mediaType": "application/vnd.docker.image.rootfs.diff.tar.gzip",
+     "digest": "sha256:319b588ce64253a87b533c8ed01cf0025e0eac98e7b516e12532957e1244fdec",
+     "size": 16
+    }
+   ],
+   "manifest": "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",
+   "config": "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",
+   "repoDigests": []
+  },
+  "Path": ""
+ },
+ "dataLicense": "CC0-1.0",
+ "documentNamespace": "https:/anchore.com/syft/image/user-image-input-7c996682-9cdf-45cd-b70b-e771d740c9ed",
+ "packages": [
+  {
+   "SPDXID": "SPDXRef-Package-python-package-1-1.0.1",
+   "name": "package-1",
+   "licenseConcluded": "MIT",
+   "downloadLocation": "NOASSERTION",
+   "externalRefs": [
+    {
+     "referenceCategory": "SECURITY",
+     "referenceLocator": "cpe:2.3:*:some:package:1:*:*:*:*:*:*:*",
+     "referenceType": "cpe23Type"
+    },
+    {
+     "referenceCategory": "PACKAGE_MANAGER",
+     "referenceLocator": "a-purl-1",
+     "referenceType": "purl"
+    }
+   ],
+   "filesAnalyzed": false,
+   "licenseDeclared": "MIT",
+   "sourceInfo": "acquired package info from installed python package manifest file: /somefile-1.txt",
+   "versionInfo": "1.0.1"
+  },
+  {
+   "SPDXID": "SPDXRef-Package-deb-package-2-2.0.1",
+   "name": "package-2",
+   "licenseConcluded": "NONE",
+   "downloadLocation": "NOASSERTION",
+   "externalRefs": [
+    {
+     "referenceCategory": "SECURITY",
+     "referenceLocator": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
+     "referenceType": "cpe23Type"
+    },
+    {
+     "referenceCategory": "PACKAGE_MANAGER",
+     "referenceLocator": "a-purl-2",
+     "referenceType": "purl"
+    }
+   ],
+   "filesAnalyzed": false,
+   "licenseDeclared": "NONE",
+   "sourceInfo": "acquired package info from DPKG DB: /somefile-2.txt",
+   "versionInfo": "2.0.1"
+  }
+ ]
+}

internal/formats/spdx22json/to_format_model.go

@@ -0,0 +1,133 @@
+package spdx22json
+
+import (
+	"fmt"
+	"path"
+	"strings"
+	"time"
+
+	"github.com/anchore/syft/syft/distro"
+
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/formats/common/spdxhelpers"
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/internal/spdxlicense"
+	"github.com/anchore/syft/internal/version"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+	"github.com/google/uuid"
+)
+
+// toFormatModel creates and populates a new JSON document struct that follows the SPDX 2.2 spec from the given cataloging results.
+func toFormatModel(catalog *pkg.Catalog, srcMetadata *source.Metadata, _ *distro.Distro, _ source.Scope) model.Document {
+	name := documentName(srcMetadata)
+	packages, files, relationships := extractFromCatalog(catalog)
+
+	return model.Document{
+		Element: model.Element{
+			SPDXID: model.ElementID("DOCUMENT").String(),
+			Name:   name,
+		},
+		SPDXVersion: model.Version,
+		CreationInfo: model.CreationInfo{
+			Created: time.Now().UTC(),
+			Creators: []string{
+				// note: key-value format derived from the JSON example document examples: https://github.com/spdx/spdx-spec/blob/v2.2/examples/SPDXJSONExample-v2.2.spdx.json
+				"Organization: Anchore, Inc",
+				"Tool: " + internal.ApplicationName + "-" + version.FromBuild().Version,
+			},
+			LicenseListVersion: spdxlicense.Version,
+		},
+		DataLicense:       "CC0-1.0",
+		DocumentNamespace: documentNamespace(name, srcMetadata),
+		Packages:          packages,
+		Files:             files,
+		Relationships:     relationships,
+		// TODO: add scope
+		SyftSourceData: srcMetadata,
+	}
+}
+
+func documentName(srcMetadata *source.Metadata) string {
+	if srcMetadata != nil {
+		switch srcMetadata.Scheme {
+		case source.ImageScheme:
+			return cleanSPDXName(srcMetadata.ImageMetadata.UserInput)
+		case source.DirectoryScheme:
+			return cleanSPDXName(srcMetadata.Path)
+		}
+	}
+	// TODO: is this alright?
+	return uuid.Must(uuid.NewRandom()).String()
+}
+
+func documentNamespace(name string, srcMetadata *source.Metadata) string {
+	input := "unknown-source-type"
+	if srcMetadata != nil {
+		switch srcMetadata.Scheme {
+		case source.ImageScheme:
+			input = "image"
+		case source.DirectoryScheme:
+			input = "dir"
+		}
+	}
+
+	uniqueID := uuid.Must(uuid.NewRandom())
+	identifier := path.Join(input, uniqueID.String())
+	if name != "." {
+		identifier = path.Join(input, fmt.Sprintf("%s-%s", name, uniqueID.String()))
+	}
+
+	return path.Join(anchoreNamespace, identifier)
+}
+
+func extractFromCatalog(catalog *pkg.Catalog) ([]model.Package, []model.File, []model.Relationship) {
+	packages := make([]model.Package, 0)
+	relationships := make([]model.Relationship, 0)
+	files := make([]model.File, 0)
+
+	for _, p := range catalog.Sorted() {
+		license := spdxhelpers.License(p)
+		packageSpdxID := model.ElementID(fmt.Sprintf("Package-%+v-%s-%s", p.Type, p.Name, p.Version)).String()
+
+		packageFiles, fileIDs, packageFileRelationships := spdxhelpers.Files(packageSpdxID, p)
+		files = append(files, packageFiles...)
+
+		relationships = append(relationships, packageFileRelationships...)
+
+		// note: the license concluded and declared should be the same since we are collecting license information
+		// from the project data itself (the installed package files).
+		packages = append(packages, model.Package{
+			Description:      spdxhelpers.Description(p),
+			DownloadLocation: spdxhelpers.DownloadLocation(p),
+			ExternalRefs:     spdxhelpers.ExternalRefs(p),
+			FilesAnalyzed:    false,
+			HasFiles:         fileIDs,
+			Homepage:         spdxhelpers.Homepage(p),
+			LicenseDeclared:  license, // The Declared License is what the authors of a project believe govern the package
+			Originator:       spdxhelpers.Originator(p),
+			SourceInfo:       spdxhelpers.SourceInfo(p),
+			VersionInfo:      p.Version,
+			Item: model.Item{
+				LicenseConcluded: license, // The Concluded License field is the license the SPDX file creator believes governs the package
+				Element: model.Element{
+					SPDXID: packageSpdxID,
+					Name:   p.Name,
+				},
+			},
+		})
+	}
+
+	return packages, files, relationships
+}
+
+func cleanSPDXName(name string) string {
+	// remove # according to specification
+	name = strings.ReplaceAll(name, "#", "-")
+
+	// remove : for url construction
+	name = strings.ReplaceAll(name, ":", "-")
+
+	// clean relative pathing
+	return path.Clean(name)
+}

internal/presenter/packages/spdx_helpers.go

@@ -1,207 +0,0 @@
-package packages
-
-import (
-	"crypto/sha256"
-	"fmt"
-	"path/filepath"
-	"strings"
-
-	"github.com/anchore/syft/internal/presenter/packages/model/spdx22"
-	"github.com/anchore/syft/internal/spdxlicense"
-	"github.com/anchore/syft/syft/pkg"
-)
-
-func getSPDXExternalRefs(p *pkg.Package) (externalRefs []spdx22.ExternalRef) {
-	externalRefs = make([]spdx22.ExternalRef, 0)
-	for _, c := range p.CPEs {
-		externalRefs = append(externalRefs, spdx22.ExternalRef{
-			ReferenceCategory: spdx22.SecurityReferenceCategory,
-			ReferenceLocator:  c.BindToFmtString(),
-			ReferenceType:     spdx22.Cpe23ExternalRefType,
-		})
-	}
-
-	if p.PURL != "" {
-		externalRefs = append(externalRefs, spdx22.ExternalRef{
-			ReferenceCategory: spdx22.PackageManagerReferenceCategory,
-			ReferenceLocator:  p.PURL,
-			ReferenceType:     spdx22.PurlExternalRefType,
-		})
-	}
-	return externalRefs
-}
-
-func getSPDXFiles(packageSpdxID string, p *pkg.Package) (files []spdx22.File, fileIDs []string, relationships []spdx22.Relationship) {
-	files = make([]spdx22.File, 0)
-	fileIDs = make([]string, 0)
-	relationships = make([]spdx22.Relationship, 0)
-
-	pkgFileOwner, ok := p.Metadata.(pkg.FileOwner)
-	if !ok {
-		return files, fileIDs, relationships
-	}
-
-	for _, ownedFilePath := range pkgFileOwner.OwnedFiles() {
-		baseFileName := filepath.Base(ownedFilePath)
-		pathHash := sha256.Sum256([]byte(ownedFilePath))
-		fileSpdxID := spdx22.ElementID(fmt.Sprintf("File-%s-%x", p.Name, pathHash)).String()
-
-		fileIDs = append(fileIDs, fileSpdxID)
-
-		files = append(files, spdx22.File{
-			FileName: ownedFilePath,
-			Item: spdx22.Item{
-				Element: spdx22.Element{
-					SPDXID: fileSpdxID,
-					Name:   baseFileName,
-				},
-			},
-		})
-
-		relationships = append(relationships, spdx22.Relationship{
-			SpdxElementID:      packageSpdxID,
-			RelationshipType:   spdx22.ContainsRelationship,
-			RelatedSpdxElement: fileSpdxID,
-		})
-	}
-
-	return files, fileIDs, relationships
-}
-
-func getSPDXLicense(p *pkg.Package) string {
-	// source: https://spdx.github.io/spdx-spec/3-package-information/#313-concluded-license
-	// The options to populate this field are limited to:
-	// A valid SPDX License Expression as defined in Appendix IV;
-	// NONE, if the SPDX file creator concludes there is no license available for this package; or
-	// NOASSERTION if:
-	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
-	//   (ii) the SPDX file creator has made no attempt to determine this field; or
-	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
-
-	if len(p.Licenses) == 0 {
-		return "NONE"
-	}
-
-	// take all licenses and assume an AND expression; for information about license expressions see https://spdx.github.io/spdx-spec/appendix-IV-SPDX-license-expressions/
-	var parsedLicenses []string
-	for _, l := range p.Licenses {
-		if value, exists := spdxlicense.ID(l); exists {
-			parsedLicenses = append(parsedLicenses, value)
-		}
-	}
-
-	if len(parsedLicenses) == 0 {
-		return "NOASSERTION"
-	}
-
-	return strings.Join(parsedLicenses, " AND ")
-}
-
-func noneIfEmpty(value string) string {
-	if strings.TrimSpace(value) == "" {
-		return "NONE"
-	}
-	return value
-}
-
-func getSPDXDownloadLocation(p *pkg.Package) string {
-	// 3.7: Package Download Location
-	// Cardinality: mandatory, one
-	// NONE if there is no download location whatsoever.
-	// NOASSERTION if:
-	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
-	//   (ii) the SPDX file creator has made no attempt to determine this field; or
-	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
-
-	switch metadata := p.Metadata.(type) {
-	case pkg.ApkMetadata:
-		return noneIfEmpty(metadata.URL)
-	case pkg.NpmPackageJSONMetadata:
-		return noneIfEmpty(metadata.URL)
-	default:
-		return "NOASSERTION"
-	}
-}
-
-func getSPDXHomepage(p *pkg.Package) string {
-	switch metadata := p.Metadata.(type) {
-	case pkg.GemMetadata:
-		return metadata.Homepage
-	case pkg.NpmPackageJSONMetadata:
-		return metadata.Homepage
-	default:
-		return ""
-	}
-}
-
-func getSPDXSourceInfo(p *pkg.Package) string {
-	answer := ""
-	switch p.Type {
-	case pkg.RpmPkg:
-		answer = "acquired package info from RPM DB"
-	case pkg.ApkPkg:
-		answer = "acquired package info from APK DB"
-	case pkg.DebPkg:
-		answer = "acquired package info from DPKG DB"
-	case pkg.NpmPkg:
-		answer = "acquired package info from installed node module manifest file"
-	case pkg.PythonPkg:
-		answer = "acquired package info from installed python package manifest file"
-	case pkg.JavaPkg, pkg.JenkinsPluginPkg:
-		answer = "acquired package info from installed java archive"
-	case pkg.GemPkg:
-		answer = "acquired package info from installed gem metadata file"
-	case pkg.GoModulePkg:
-		answer = "acquired package info from go module information"
-	case pkg.RustPkg:
-		answer = "acquired package info from rust cargo manifest"
-	default:
-		answer = "acquired package info from the following paths"
-	}
-	var paths []string
-	for _, l := range p.Locations {
-		paths = append(paths, l.RealPath)
-	}
-
-	return answer + ": " + strings.Join(paths, ", ")
-}
-
-func getSPDXOriginator(p *pkg.Package) string {
-	switch metadata := p.Metadata.(type) {
-	case pkg.ApkMetadata:
-		return metadata.Maintainer
-	case pkg.NpmPackageJSONMetadata:
-		return metadata.Author
-	case pkg.PythonPackageMetadata:
-		author := metadata.Author
-		if author == "" {
-			return metadata.AuthorEmail
-		}
-		if metadata.AuthorEmail != "" {
-			author += fmt.Sprintf(" <%s>", metadata.AuthorEmail)
-		}
-		return author
-	case pkg.GemMetadata:
-		if len(metadata.Authors) > 0 {
-			return metadata.Authors[0]
-		}
-		return ""
-	case pkg.RpmdbMetadata:
-		return metadata.Vendor
-	case pkg.DpkgMetadata:
-		return metadata.Maintainer
-	default:
-		return ""
-	}
-}
-
-func getSPDXDescription(p *pkg.Package) string {
-	switch metadata := p.Metadata.(type) {
-	case pkg.ApkMetadata:
-		return metadata.Description
-	case pkg.NpmPackageJSONMetadata:
-		return metadata.Description
-	default:
-		return ""
-	}
-}

internal/presenter/packages/spdx_helpers_test.go

@@ -1,527 +0,0 @@
-package packages
-
-import (
-	"testing"
-
-	"github.com/anchore/syft/syft/source"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/anchore/syft/internal/presenter/packages/model/spdx22"
-	"github.com/anchore/syft/syft/pkg"
-)
-
-func Test_getSPDXExternalRefs(t *testing.T) {
-	testCPE := pkg.MustCPE("cpe:2.3:a:name:name:3.2:*:*:*:*:*:*:*")
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected []spdx22.ExternalRef
-	}{
-		{
-			name: "cpe + purl",
-			input: pkg.Package{
-				CPEs: []pkg.CPE{
-					testCPE,
-				},
-				PURL: "a-purl",
-			},
-			expected: []spdx22.ExternalRef{
-				{
-					ReferenceCategory: spdx22.SecurityReferenceCategory,
-					ReferenceLocator:  testCPE.BindToFmtString(),
-					ReferenceType:     spdx22.Cpe23ExternalRefType,
-				},
-				{
-					ReferenceCategory: spdx22.PackageManagerReferenceCategory,
-					ReferenceLocator:  "a-purl",
-					ReferenceType:     spdx22.PurlExternalRefType,
-				},
-			},
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.ElementsMatch(t, test.expected, getSPDXExternalRefs(&test.input))
-		})
-	}
-}
-
-func Test_getSPDXLicense(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected string
-	}{
-		{
-			name:     "no licenses",
-			input:    pkg.Package{},
-			expected: "NONE",
-		},
-		{
-			name: "no SPDX licenses",
-			input: pkg.Package{
-				Licenses: []string{
-					"made-up",
-				},
-			},
-			expected: "NOASSERTION",
-		},
-		{
-			name: "with SPDX license",
-			input: pkg.Package{
-				Licenses: []string{
-					"MIT",
-				},
-			},
-			expected: "MIT",
-		},
-		{
-			name: "with SPDX license expression",
-			input: pkg.Package{
-				Licenses: []string{
-					"MIT",
-					"GPL-3.0",
-				},
-			},
-			expected: "MIT AND GPL-3.0",
-		},
-		{
-			name: "cap insensitive",
-			input: pkg.Package{
-				Licenses: []string{
-					"gpl-3.0",
-				},
-			},
-			expected: "GPL-3.0",
-		},
-		{
-			name: "debian to spdx conversion",
-			input: pkg.Package{
-				Licenses: []string{
-					"GPL-2",
-				},
-			},
-			expected: "GPL-2.0",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, getSPDXLicense(&test.input))
-		})
-	}
-}
-
-func Test_noneIfEmpty(t *testing.T) {
-	tests := []struct {
-		name     string
-		value    string
-		expected string
-	}{
-		{
-			name:     "non-zero value",
-			value:    "something",
-			expected: "something",
-		},
-		{
-			name:     "empty",
-			value:    "",
-			expected: "NONE",
-		},
-		{
-			name:     "space",
-			value:    " ",
-			expected: "NONE",
-		},
-		{
-			name:     "tab",
-			value:    "\t",
-			expected: "NONE",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, noneIfEmpty(test.value))
-		})
-	}
-}
-
-func Test_getSPDXDownloadLocation(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected string
-	}{
-		{
-			name:     "no metadata",
-			input:    pkg.Package{},
-			expected: "NOASSERTION",
-		},
-		{
-			name: "from apk",
-			input: pkg.Package{
-				Metadata: pkg.ApkMetadata{
-					URL: "http://a-place.gov",
-				},
-			},
-			expected: "http://a-place.gov",
-		},
-		{
-			name: "from npm",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					URL: "http://a-place.gov",
-				},
-			},
-			expected: "http://a-place.gov",
-		},
-		{
-			name: "empty",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					URL: "",
-				},
-			},
-			expected: "NONE",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, getSPDXDownloadLocation(&test.input))
-		})
-	}
-}
-
-func Test_getSPDXHomepage(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected string
-	}{
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name:     "no metadata",
-			input:    pkg.Package{},
-			expected: "",
-		},
-		{
-			name: "from gem",
-			input: pkg.Package{
-				Metadata: pkg.GemMetadata{
-					Homepage: "http://a-place.gov",
-				},
-			},
-			expected: "http://a-place.gov",
-		},
-		{
-			name: "from npm",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Homepage: "http://a-place.gov",
-				},
-			},
-			expected: "http://a-place.gov",
-		},
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name: "empty",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Homepage: "",
-				},
-			},
-			expected: "",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, getSPDXHomepage(&test.input))
-		})
-	}
-}
-
-func Test_getSPDXSourceInfo(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected []string
-	}{
-		{
-			name: "locations are captured",
-			input: pkg.Package{
-				// note: no type given
-				Locations: []source.Location{
-					{
-						RealPath:    "/a-place",
-						VirtualPath: "/b-place",
-					},
-					{
-						RealPath:    "/c-place",
-						VirtualPath: "/d-place",
-					},
-				},
-			},
-			expected: []string{
-				"from the following paths",
-				"/a-place",
-				"/c-place",
-			},
-		},
-		{
-			// note: no specific support for this
-			input: pkg.Package{
-				Type: pkg.KbPkg,
-			},
-			expected: []string{
-				"from the following paths",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.RpmPkg,
-			},
-			expected: []string{
-				"from RPM DB",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.ApkPkg,
-			},
-			expected: []string{
-				"from APK DB",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.DebPkg,
-			},
-			expected: []string{
-				"from DPKG DB",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.NpmPkg,
-			},
-			expected: []string{
-				"from installed node module manifest file",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.PythonPkg,
-			},
-			expected: []string{
-				"from installed python package manifest file",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.JavaPkg,
-			},
-			expected: []string{
-				"from installed java archive",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.JenkinsPluginPkg,
-			},
-			expected: []string{
-				"from installed java archive",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.GemPkg,
-			},
-			expected: []string{
-				"from installed gem metadata file",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.GoModulePkg,
-			},
-			expected: []string{
-				"from go module information",
-			},
-		},
-		{
-			input: pkg.Package{
-				Type: pkg.RustPkg,
-			},
-			expected: []string{
-				"from rust cargo manifest",
-			},
-		},
-	}
-	var pkgTypes []pkg.Type
-	for _, test := range tests {
-		t.Run(test.name+" "+string(test.input.Type), func(t *testing.T) {
-			if test.input.Type != "" {
-				pkgTypes = append(pkgTypes, test.input.Type)
-			}
-			actual := getSPDXSourceInfo(&test.input)
-			for _, expected := range test.expected {
-				assert.Contains(t, actual, expected)
-			}
-		})
-	}
-	assert.ElementsMatch(t, pkg.AllPkgs, pkgTypes, "missing one or more package types to test against (maybe a package type was added?)")
-}
-
-func Test_getSPDXOriginator(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected string
-	}{
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name:     "no metadata",
-			input:    pkg.Package{},
-			expected: "",
-		},
-		{
-			name: "from gem",
-			input: pkg.Package{
-				Metadata: pkg.GemMetadata{
-					Authors: []string{
-						"auth1",
-						"auth2",
-					},
-				},
-			},
-			expected: "auth1",
-		},
-		{
-			name: "from npm",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Author: "auth",
-				},
-			},
-			expected: "auth",
-		},
-		{
-			name: "from apk",
-			input: pkg.Package{
-				Metadata: pkg.ApkMetadata{
-					Maintainer: "auth",
-				},
-			},
-			expected: "auth",
-		},
-		{
-			name: "from python - just name",
-			input: pkg.Package{
-				Metadata: pkg.PythonPackageMetadata{
-					Author: "auth",
-				},
-			},
-			expected: "auth",
-		},
-		{
-			name: "from python - just email",
-			input: pkg.Package{
-				Metadata: pkg.PythonPackageMetadata{
-					AuthorEmail: "auth@auth.gov",
-				},
-			},
-			expected: "auth@auth.gov",
-		},
-		{
-			name: "from python - both name and email",
-			input: pkg.Package{
-				Metadata: pkg.PythonPackageMetadata{
-					Author:      "auth",
-					AuthorEmail: "auth@auth.gov",
-				},
-			},
-			expected: "auth <auth@auth.gov>",
-		},
-		{
-			name: "from rpm",
-			input: pkg.Package{
-				Metadata: pkg.RpmdbMetadata{
-					Vendor: "auth",
-				},
-			},
-			expected: "auth",
-		},
-		{
-			name: "from dpkg",
-			input: pkg.Package{
-				Metadata: pkg.DpkgMetadata{
-					Maintainer: "auth",
-				},
-			},
-			expected: "auth",
-		},
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name: "empty",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Author: "",
-				},
-			},
-			expected: "",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, getSPDXOriginator(&test.input))
-		})
-	}
-}
-
-func Test_getSPDXDescription(t *testing.T) {
-	tests := []struct {
-		name     string
-		input    pkg.Package
-		expected string
-	}{
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name:     "no metadata",
-			input:    pkg.Package{},
-			expected: "",
-		},
-		{
-			name: "from apk",
-			input: pkg.Package{
-				Metadata: pkg.ApkMetadata{
-					Description: "a description!",
-				},
-			},
-			expected: "a description!",
-		},
-		{
-			name: "from npm",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Description: "a description!",
-				},
-			},
-			expected: "a description!",
-		},
-		{
-			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
-			name: "empty",
-			input: pkg.Package{
-				Metadata: pkg.NpmPackageJSONMetadata{
-					Homepage: "",
-				},
-			},
-			expected: "",
-		},
-	}
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			assert.Equal(t, test.expected, getSPDXDescription(&test.input))
-		})
-	}
-}

internal/presenter/packages/spdx_json_presenter.go

@@ -1,142 +0,0 @@
-package packages
-
-import (
-	"encoding/json"
-	"fmt"
-	"io"
-	"path"
-	"strings"
-	"time"
-
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/internal/presenter/packages/model/spdx22"
-	"github.com/anchore/syft/internal/spdxlicense"
-	"github.com/anchore/syft/internal/version"
-	"github.com/anchore/syft/syft/pkg"
-	"github.com/anchore/syft/syft/source"
-	"github.com/google/uuid"
-)
-
-const anchoreNamespace = "https://anchore.com/syft"
-
-// SPDXJsonPresenter is a SPDX presentation object for the syft results (see https://github.com/spdx/spdx-spec)
-type SPDXJsonPresenter struct {
-	catalog     *pkg.Catalog
-	srcMetadata source.Metadata
-}
-
-// NewSPDXJSONPresenter creates a new JSON presenter object for the given cataloging results.
-func NewSPDXJSONPresenter(catalog *pkg.Catalog, srcMetadata source.Metadata) *SPDXJsonPresenter {
-	return &SPDXJsonPresenter{
-		catalog:     catalog,
-		srcMetadata: srcMetadata,
-	}
-}
-
-// Present the catalog results to the given writer.
-func (pres *SPDXJsonPresenter) Present(output io.Writer) error {
-	doc := newSPDXJsonDocument(pres.catalog, pres.srcMetadata)
-
-	enc := json.NewEncoder(output)
-	// prevent > and < from being escaped in the payload
-	enc.SetEscapeHTML(false)
-	enc.SetIndent("", " ")
-	return enc.Encode(&doc)
-}
-
-// newSPDXJsonDocument creates and populates a new JSON document struct that follows the SPDX 2.2 spec from the given cataloging results.
-func newSPDXJsonDocument(catalog *pkg.Catalog, srcMetadata source.Metadata) spdx22.Document {
-	uniqueID := uuid.Must(uuid.NewRandom())
-
-	var name, input, identifier string
-	switch srcMetadata.Scheme {
-	case source.ImageScheme:
-		name = cleanSPDXName(srcMetadata.ImageMetadata.UserInput)
-		input = "image"
-	case source.DirectoryScheme:
-		name = cleanSPDXName(srcMetadata.Path)
-		input = "dir"
-	}
-
-	if name != "." {
-		identifier = path.Join(input, fmt.Sprintf("%s-%s", name, uniqueID.String()))
-	} else {
-		identifier = path.Join(input, uniqueID.String())
-	}
-
-	namespace := path.Join(anchoreNamespace, identifier)
-	packages, files, relationships := newSPDXJsonElements(catalog)
-
-	return spdx22.Document{
-		Element: spdx22.Element{
-			SPDXID: spdx22.ElementID("DOCUMENT").String(),
-			Name:   name,
-		},
-		SPDXVersion: spdx22.Version,
-		CreationInfo: spdx22.CreationInfo{
-			Created: time.Now().UTC(),
-			Creators: []string{
-				// note: key-value format derived from the JSON example document examples: https://github.com/spdx/spdx-spec/blob/v2.2/examples/SPDXJSONExample-v2.2.spdx.json
-				"Organization: Anchore, Inc",
-				"Tool: " + internal.ApplicationName + "-" + version.FromBuild().Version,
-			},
-			LicenseListVersion: spdxlicense.Version,
-		},
-		DataLicense:       "CC0-1.0",
-		DocumentNamespace: namespace,
-		Packages:          packages,
-		Files:             files,
-		Relationships:     relationships,
-	}
-}
-
-func newSPDXJsonElements(catalog *pkg.Catalog) ([]spdx22.Package, []spdx22.File, []spdx22.Relationship) {
-	packages := make([]spdx22.Package, 0)
-	relationships := make([]spdx22.Relationship, 0)
-	files := make([]spdx22.File, 0)
-
-	for _, p := range catalog.Sorted() {
-		license := getSPDXLicense(p)
-		packageSpdxID := spdx22.ElementID(fmt.Sprintf("Package-%+v-%s-%s", p.Type, p.Name, p.Version)).String()
-
-		packageFiles, fileIDs, packageFileRelationships := getSPDXFiles(packageSpdxID, p)
-		files = append(files, packageFiles...)
-
-		relationships = append(relationships, packageFileRelationships...)
-
-		// note: the license concluded and declared should be the same since we are collecting license information
-		// from the project data itself (the installed package files).
-		packages = append(packages, spdx22.Package{
-			Description:      getSPDXDescription(p),
-			DownloadLocation: getSPDXDownloadLocation(p),
-			ExternalRefs:     getSPDXExternalRefs(p),
-			FilesAnalyzed:    false,
-			HasFiles:         fileIDs,
-			Homepage:         getSPDXHomepage(p),
-			LicenseDeclared:  license, // The Declared License is what the authors of a project believe govern the package
-			Originator:       getSPDXOriginator(p),
-			SourceInfo:       getSPDXSourceInfo(p),
-			VersionInfo:      p.Version,
-			Item: spdx22.Item{
-				LicenseConcluded: license, // The Concluded License field is the license the SPDX file creator believes governs the package
-				Element: spdx22.Element{
-					SPDXID: packageSpdxID,
-					Name:   p.Name,
-				},
-			},
-		})
-	}
-
-	return packages, files, relationships
-}
-
-func cleanSPDXName(name string) string {
-	// remove # according to specification
-	name = strings.ReplaceAll(name, "#", "-")
-
-	// remove : for url construction
-	name = strings.ReplaceAll(name, ":", "-")
-
-	// clean relative pathing
-	return path.Clean(name)
-}

internal/presenter/packages/spdx_tag_value_presenter.go

@@ -5,6 +5,8 @@ import (
 	"io"
 	"time"
 
+	"github.com/anchore/syft/internal/formats/common/spdxhelpers"
+
 	"github.com/anchore/syft/internal/spdxlicense"
 
 	"github.com/anchore/syft/internal"
@@ -114,7 +116,7 @@ func (pres *SPDXTagValuePresenter) packages() map[spdx.ElementID]*spdx.Package2_
 		// If the Concluded License is not the same as the Declared License, a written explanation should be provided
 		// in the Comments on License field (section 3.16). With respect to NOASSERTION, a written explanation in
 		// the Comments on License field (section 3.16) is preferred.
-		license := getSPDXLicense(p)
+		license := spdxhelpers.License(p)
 
 		results[spdx.ElementID(id)] = &spdx.Package2_2{
 
@@ -274,7 +276,7 @@ func (pres *SPDXTagValuePresenter) packages() map[spdx.ElementID]*spdx.Package2_
 }
 
 func formatSPDXExternalRefs(p *pkg.Package) (refs []*spdx.PackageExternalReference2_2) {
-	for _, ref := range getSPDXExternalRefs(p) {
+	for _, ref := range spdxhelpers.ExternalRefs(p) {
 		refs = append(refs, &spdx.PackageExternalReference2_2{
 			Category:           string(ref.ReferenceCategory),
 			RefType:            string(ref.ReferenceType),

syft/presenter/packages/presenter.go

@@ -18,8 +18,6 @@ func Presenter(option format.Option, config PresenterConfig) presenter.Presenter
 		return packages.NewTextPresenter(config.Catalog, config.SourceMetadata)
 	case format.SPDXTagValueOption:
 		return packages.NewSPDXTagValuePresenter(config.Catalog, config.SourceMetadata)
-	case format.SPDXJSONOption:
-		return packages.NewSPDXJSONPresenter(config.Catalog, config.SourceMetadata)
 	default:
 		// TODO: the final state is that all other cases would be replaced by formats.ByOption (wed remove this function entirely)
 		f := formats.ByOption(option)