Update GitHub format package_url and correlator (#961)

The Official CPE dictionary currently contains entries for springframework with three different vendors: springsource, vmware, and pivotal_software.  This appears to be because ownership has changed over time.

Signed-off-by: Weston Steimel <weston.steimel@anchore.com>

.github/scripts/apple-signing/setup-prod.sh

@@ -21,6 +21,14 @@ fi
 if [ -z "$DOCKER_PASSWORD" ]; then
   exit_with_error "DOCKER_PASSWORD not set"
 fi
+
+if [ -z "$GHCR_USERNAME" ]; then
+  exit_with_error "GHCR_USERNAME not set"
+fi
+
+if [ -z "$GHCR_PASSWORD" ]; then
+  exit_with_error "GHCR_PASSWORD not set"
+fi
 set -u
 
 # setup_signing
@@ -41,4 +49,5 @@ setup_signing() {
 
   commentary "log into docker -- required for publishing (since the default keychain has now been replaced)"
   echo "${DOCKER_PASSWORD}" | docker login docker.io -u "${DOCKER_USERNAME}"  --password-stdin
+  echo "${GHCR_PASSWORD}" | docker login ghcr.io -u "${GHCR_USERNAME}"  --password-stdin
 }

.github/workflows/release.yaml

@@ -94,6 +94,8 @@ jobs:
     needs: [quality-gate]
     # due to our code signing process, it's vital that we run our release steps on macOS
     runs-on: macos-latest
+    permissions:
+      packages: write
     steps:
       - uses: docker-practice/actions-setup-docker@v1
 
@@ -128,6 +130,8 @@ jobs:
       - name: Build & publish release artifacts
         run: make release
         env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GHCR_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
           DOCKER_USERNAME: ${{ secrets.TOOLBOX_DOCKER_USER }}
           DOCKER_PASSWORD: ${{ secrets.TOOLBOX_DOCKER_PASS }}
           # we use a different token than GITHUB_SECRETS to additionally allow updating the homebrew repos

.github/workflows/update-stereoscope-release.yml

@@ -0,0 +1,51 @@
+name: PR for latest Stereoscope release
+on:
+  schedule:
+    - cron: "0 8 * * *" # 3 AM EST
+
+  workflow_dispatch:
+
+env:
+  GO_VERSION: "1.18.x"
+  GO_STABLE_VERSION: true
+
+jobs:
+  upgrade-stereoscope:
+    runs-on: ubuntu-latest
+    if: github.repository == 'anchore/syft' # only run for main repo
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: actions/setup-go@v2
+        with:
+          go-version: ${{ env.GO_VERSION }}
+          stable: ${{ env.GO_STABLE_VERSION }}
+
+      - run: |
+          LATEST_VERSION=$(git ls-remote https://github.com/anchore/stereoscope main | head -n1 | awk '{print $1;}')
+
+          # update go.mod
+          go get github.com/anchore/stereoscope@$LATEST_VERSION
+          go mod tidy
+
+          # export the version for use with create-pull-request
+          echo "::set-output name=LATEST_VERSION::$LATEST_VERSION"
+        id: latest-version
+
+      - uses: tibdex/github-app-token@v1
+        id: generate-token
+        with:
+          app_id: ${{ secrets.TOKEN_APP_ID }}
+          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+
+      - uses: peter-evans/create-pull-request@v4
+        with:
+          signoff: true
+          delete-branch: true
+          branch: auto/latest
+          labels: dependencies
+          commit-message: "Update Stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}"
+          title: "Update Stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}"
+          body: |
+            Update Stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}
+          token: ${{ steps.generate-token.outputs.token }}

.goreleaser.yaml

@@ -99,6 +99,11 @@ dockers:
       - "anchore/syft:{{ .Tag }}-amd64"
       - "anchore/syft:v{{ .Major }}-amd64"
       - "anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64"
+      - "ghcr.io/anchore/syft:latest"
+      - "ghcr.io/anchore/syft:{{ .Tag }}-amd64"
+      - "ghcr.io/anchore/syft:v{{ .Major }}-amd64"
+      - "ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64"
+    goarch: amd64
     dockerfile: Dockerfile
     use: buildx
     build_flag_templates:
@@ -112,6 +117,9 @@ dockers:
       - "anchore/syft:{{ .Tag }}-arm64v8"
       - "anchore/syft:v{{ .Major }}-arm64v8"
       - "anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8"
+      - "ghcr.io/anchore/syft:{{ .Tag }}-arm64v8"
+      - "ghcr.io/anchore/syft:v{{ .Major }}-arm64v8"
+      - "ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8"
     goarch: arm64
     dockerfile: Dockerfile
     use: buildx
@@ -131,3 +139,11 @@ docker_manifests:
     image_templates:
       - anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64
       - anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8
+  - name_template: ghcr.io/anchore/syft:{{ .Tag }}
+    image_templates:
+      - ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64
+      - ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8
+  - name_template: ghcr.io/anchore/syft:latest
+    image_templates:
+      - ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64
+      - ghcr.io/anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8

README.md

@@ -156,9 +156,9 @@ syft <image> -o <format>
 Where the `formats` available are:
 - `json`: Use this to get as much information out of Syft as possible!
 - `text`: A row-oriented, human-and-machine-friendly output.
-- `cyclonedx`: A XML report conforming to the [CycloneDX 1.3 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.3 specification](https://cyclonedx.org/specification/overview/).
-- `spdx`: A tag-value formatted report conforming to the [SPDX 2.2 specification](https://spdx.github.io/spdx-spec/).
+- `cyclonedx-xml`: A XML report conforming to the [CycloneDX 1.4 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.4 specification](https://cyclonedx.org/specification/overview/).
+- `spdx-tag-value`: A tag-value formatted report conforming to the [SPDX 2.2 specification](https://spdx.github.io/spdx-spec/).
 - `spdx-json`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
 - `table`: A columnar summary (default).
 

go.mod

@@ -14,7 +14,7 @@ require (
 	github.com/anchore/go-testutils v0.0.0-20200925183923-d5f45b0d3c04
 	github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b
 	github.com/anchore/packageurl-go v0.1.1-0.20220314153042-1bcd40e5206b
-	github.com/anchore/stereoscope v0.0.0-20220330165332-7fc73ee7b0f0
+	github.com/anchore/stereoscope v0.0.0-20220406160859-c03a18a6b270
 	github.com/antihax/optional v1.0.0
 	github.com/bmatcuk/doublestar/v4 v4.0.2
 	github.com/dustin/go-humanize v1.0.0

go.sum

@@ -280,8 +280,8 @@ github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b h1:e1bmaoJfZV
 github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b/go.mod h1:Bkc+JYWjMCF8OyZ340IMSIi2Ebf3uwByOk6ho4wne1E=
 github.com/anchore/packageurl-go v0.1.1-0.20220314153042-1bcd40e5206b h1:YJWYt/6KQXR9JR46lLHrTTYi8rcye42tKcyjREA/hvA=
 github.com/anchore/packageurl-go v0.1.1-0.20220314153042-1bcd40e5206b/go.mod h1:Blo6OgJNiYF41ufcgHKkbCKF2MDOMlrqhXv/ij6ocR4=
-github.com/anchore/stereoscope v0.0.0-20220330165332-7fc73ee7b0f0 h1:mObz7bepZ6DtbIrsB2mxuOE9XEYmVtA/P/EDlKwfbjs=
-github.com/anchore/stereoscope v0.0.0-20220330165332-7fc73ee7b0f0/go.mod h1:yoCLUZY0k/pYLNIy0L80p2Ko0PKVNXm8rHtgxp4OiSc=
+github.com/anchore/stereoscope v0.0.0-20220406160859-c03a18a6b270 h1:NmxPDR6vo3xjwCL6o+tpF1vUad/BVo+WaVSwueB9W9w=
+github.com/anchore/stereoscope v0.0.0-20220406160859-c03a18a6b270/go.mod h1:yoCLUZY0k/pYLNIy0L80p2Ko0PKVNXm8rHtgxp4OiSc=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.0.0/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
 github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=

internal/formats/common/cyclonedxhelpers/component.go

@@ -5,6 +5,7 @@ import (
 
 	"github.com/CycloneDX/cyclonedx-go"
 
+	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/internal/formats/common"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
@@ -39,9 +40,23 @@ func encodeComponent(p pkg.Package) cyclonedx.Component {
 		Description:        encodeDescription(p),
 		ExternalReferences: encodeExternalReferences(p),
 		Properties:         properties,
+		BOMRef:             deriveBomRef(p),
 	}
 }
 
+func deriveBomRef(p pkg.Package) string {
+	// try and parse the PURL if possible and append syft id to it, to make
+	// the purl unique in the BOM.
+	// TODO: In the future we may want to dedupe by PURL and combine components with
+	// the same PURL while preserving their unique metadata.
+	if parsedPURL, err := packageurl.FromString(p.PURL); err == nil {
+		parsedPURL.Qualifiers = append(parsedPURL.Qualifiers, packageurl.Qualifier{Key: "syft-id", Value: string(p.ID())})
+		return parsedPURL.ToString()
+	}
+	// fallback is to use strictly the ID if there is no valid pURL
+	return string(p.ID())
+}
+
 func hasMetadata(p pkg.Package) bool {
 	return p.Metadata != nil
 }

internal/formats/common/cyclonedxhelpers/component_test.go

@@ -1,6 +1,7 @@
 package cyclonedxhelpers
 
 import (
+	"fmt"
 	"testing"
 
 	"github.com/CycloneDX/cyclonedx-go"
@@ -139,3 +140,54 @@ func Test_encodeComponentProperties(t *testing.T) {
 		})
 	}
 }
+
+func Test_deriveBomRef(t *testing.T) {
+	pkgWithPurl := pkg.Package{
+		Name:    "django",
+		Version: "1.11.1",
+		PURL:    "pkg:pypi/django@1.11.1",
+	}
+	pkgWithPurl.SetID()
+
+	pkgWithOutPurl := pkg.Package{
+		Name:    "django",
+		Version: "1.11.1",
+		PURL:    "",
+	}
+	pkgWithOutPurl.SetID()
+
+	pkgWithBadPurl := pkg.Package{
+		Name:    "django",
+		Version: "1.11.1",
+		PURL:    "pkg:pyjango@1.11.1",
+	}
+	pkgWithBadPurl.SetID()
+
+	tests := []struct {
+		name string
+		pkg  pkg.Package
+		want string
+	}{
+		{
+			name: "use pURL-id hybrid",
+			pkg:  pkgWithPurl,
+			want: fmt.Sprintf("pkg:pypi/django@1.11.1?syft-id=%s", pkgWithPurl.ID()),
+		},
+		{
+			name: "fallback to ID when pURL is invalid",
+			pkg:  pkgWithBadPurl,
+			want: string(pkgWithBadPurl.ID()),
+		},
+		{
+			name: "fallback to ID when pURL is missing",
+			pkg:  pkgWithOutPurl,
+			want: string(pkgWithOutPurl.ID()),
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			tt.pkg.ID()
+			assert.Equal(t, tt.want, deriveBomRef(tt.pkg))
+		})
+	}
+}

internal/formats/common/cyclonedxhelpers/external_references.go

@@ -4,12 +4,15 @@ import (
 	"fmt"
 	"strings"
 
+	syftFile "github.com/anchore/syft/syft/file"
+
 	"github.com/CycloneDX/cyclonedx-go"
 	"github.com/anchore/syft/syft/pkg"
 )
 
+//nolint:funlen, gocognit
 func encodeExternalReferences(p pkg.Package) *[]cyclonedx.ExternalReference {
-	refs := []cyclonedx.ExternalReference{}
+	var refs []cyclonedx.ExternalReference
 	if hasMetadata(p) {
 		switch metadata := p.Metadata.(type) {
 		case pkg.ApkMetadata:
@@ -46,6 +49,19 @@ func encodeExternalReferences(p pkg.Package) *[]cyclonedx.ExternalReference {
 					Type: cyclonedx.ERTypeWebsite,
 				})
 			}
+		case pkg.JavaMetadata:
+			if len(metadata.ArchiveDigests) > 0 {
+				for _, digest := range metadata.ArchiveDigests {
+					refs = append(refs, cyclonedx.ExternalReference{
+						URL:  "",
+						Type: cyclonedx.ERTypeBuildMeta,
+						Hashes: &[]cyclonedx.Hash{{
+							Algorithm: cyclonedx.HashAlgorithm(digest.Algorithm),
+							Value:     digest.Value,
+						}},
+					})
+				}
+			}
 		case pkg.PythonPackageMetadata:
 			if metadata.DirectURLOrigin != nil && metadata.DirectURLOrigin.URL != "" {
 				ref := cyclonedx.ExternalReference{
@@ -79,6 +95,20 @@ func decodeExternalReferences(c *cyclonedx.Component, metadata interface{}) {
 		meta.Homepage = refURL(c, cyclonedx.ERTypeWebsite)
 	case *pkg.GemMetadata:
 		meta.Homepage = refURL(c, cyclonedx.ERTypeWebsite)
+	case *pkg.JavaMetadata:
+		var digests []syftFile.Digest
+		if ref := findExternalRef(c, cyclonedx.ERTypeBuildMeta); ref != nil {
+			if ref.Hashes != nil {
+				for _, hash := range *ref.Hashes {
+					digests = append(digests, syftFile.Digest{
+						Algorithm: string(hash.Algorithm),
+						Value:     hash.Value,
+					})
+				}
+			}
+		}
+
+		meta.ArchiveDigests = digests
 	case *pkg.PythonPackageMetadata:
 		if meta.DirectURLOrigin == nil {
 			meta.DirectURLOrigin = &pkg.PythonDirectURLOriginInfo{}

internal/formats/common/spdxhelpers/external_refs.go

@@ -22,5 +22,6 @@ func ExternalRefs(p pkg.Package) (externalRefs []ExternalRef) {
 			ReferenceType:     PurlExternalRefType,
 		})
 	}
+
 	return externalRefs
 }

internal/formats/common/spdxhelpers/spdxid.go

@@ -0,0 +1,13 @@
+package spdxhelpers
+
+import (
+	"regexp"
+)
+
+var expr = regexp.MustCompile("[^a-zA-Z0-9.-]")
+
+// SPDX spec says SPDXID must be:
+// "SPDXRef-"[idstring] where [idstring] is a unique string containing letters, numbers, ., and/or -
+func SanitizeElementID(id string) string {
+	return expr.ReplaceAllString(id, "-")
+}

internal/formats/common/spdxhelpers/spdxid_test.go

@@ -0,0 +1,39 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_SanitizeElementID(t *testing.T) {
+	tests := []struct {
+		input    string
+		expected string
+	}{
+		{
+			input:    "letters",
+			expected: "letters",
+		},
+		{
+			input:    "ssl-client",
+			expected: "ssl-client",
+		},
+		{
+			input:    "ssl_client",
+			expected: "ssl-client",
+		},
+		{
+			input:    "go-module-sigs.k8s.io/structured-merge-diff/v3",
+			expected: "go-module-sigs.k8s.io-structured-merge-diff-v3",
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.input, func(t *testing.T) {
+			actual := SanitizeElementID(test.input)
+
+			assert.Equal(t, test.expected, actual)
+		})
+	}
+}

internal/formats/common/spdxhelpers/to_syft_model.go

@@ -309,6 +309,14 @@ func extractMetadata(p *spdx.Package2_2, info pkgInfo) (pkg.MetadataType, interf
 			Architecture:  arch,
 			Maintainer:    p.PackageOriginatorPerson,
 		}
+	case pkg.JavaPkg:
+		var digests []file.Digest
+		for algorithm, value := range p.PackageChecksums {
+			digests = append(digests, file.Digest{Algorithm: string(algorithm), Value: value.Value})
+		}
+		return pkg.JavaMetadataType, pkg.JavaMetadata{
+			ArchiveDigests: digests,
+		}
 	}
 	return pkg.UnknownMetadataType, nil
 }

internal/formats/common/testutils/utils.go

@@ -169,7 +169,7 @@ func populateImageCatalog(catalog *pkg.Catalog, img *image.Image) {
 			Name:    "package-1",
 			Version: "1.0.1",
 		},
-		PURL: "a-purl-1",
+		PURL: "a-purl-1", // intentionally a bad pURL for test fixtures
 		CPEs: []pkg.CPE{
 			pkg.MustCPE("cpe:2.3:*:some:package:1:*:*:*:*:*:*:*"),
 		},
@@ -187,7 +187,7 @@ func populateImageCatalog(catalog *pkg.Catalog, img *image.Image) {
 			Package: "package-2",
 			Version: "2.0.1",
 		},
-		PURL: "a-purl-2",
+		PURL: "pkg:deb/debian/package-2@2.0.1",
 		CPEs: []pkg.CPE{
 			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
 		},
@@ -249,7 +249,7 @@ func newDirectoryCatalog() *pkg.Catalog {
 				},
 			},
 		},
-		PURL: "a-purl-2",
+		PURL: "a-purl-2", // intentionally a bad pURL for test fixtures
 		CPEs: []pkg.CPE{
 			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
 		},
@@ -267,7 +267,7 @@ func newDirectoryCatalog() *pkg.Catalog {
 			Package: "package-2",
 			Version: "2.0.1",
 		},
-		PURL: "a-purl-2",
+		PURL: "pkg:deb/debian/package-2@2.0.1",
 		CPEs: []pkg.CPE{
 			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
 		},

internal/formats/cyclonedxjson/test-fixtures/snapshot/TestCycloneDxDirectoryEncoder.golden

@@ -1,10 +1,10 @@
 {
   "bomFormat": "CycloneDX",
   "specVersion": "1.4",
-  "serialNumber": "urn:uuid:498e659b-0758-4a7f-816e-91bee18df634",
+  "serialNumber": "urn:uuid:dec3f6b4-8458-48bb-b60d-dfd312f6ec4e",
   "version": 1,
   "metadata": {
-    "timestamp": "2022-03-08T12:30:39Z",
+    "timestamp": "2022-04-01T11:48:04-04:00",
     "tools": [
       {
         "vendor": "anchore",
@@ -20,6 +20,7 @@
   },
   "components": [
     {
+      "bom-ref": "b85dbb4e6ece5082",
       "type": "library",
       "name": "package-1",
       "version": "1.0.1",
@@ -56,11 +57,12 @@
       ]
     },
     {
+      "bom-ref": "pkg:deb/debian/package-2@2.0.1?syft-id=ceda99598967ae8d",
       "type": "library",
       "name": "package-2",
       "version": "2.0.1",
       "cpe": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-      "purl": "a-purl-2",
+      "purl": "pkg:deb/debian/package-2@2.0.1",
       "properties": [
         {
           "name": "syft:package:foundBy",

internal/formats/cyclonedxjson/test-fixtures/snapshot/TestCycloneDxImageEncoder.golden

@@ -1,10 +1,10 @@
 {
   "bomFormat": "CycloneDX",
   "specVersion": "1.4",
-  "serialNumber": "urn:uuid:342c3d2c-d26e-47b6-94d6-92fbf41da945",
+  "serialNumber": "urn:uuid:054d973e-fe99-4762-92e4-eaf01997ae41",
   "version": 1,
   "metadata": {
-    "timestamp": "2022-03-08T12:30:39Z",
+    "timestamp": "2022-04-01T11:48:04-04:00",
     "tools": [
       {
         "vendor": "anchore",
@@ -13,7 +13,7 @@
       }
     ],
     "component": {
-      "bom-ref": "711095b1cdf90cce",
+      "bom-ref": "e777314b02b362e4",
       "type": "container",
       "name": "user-image-input",
       "version": "sha256:2731251dc34951c0e50fcc643b4c5f74922dad1a5d98f302b504cf46cd5d9368"
@@ -21,6 +21,7 @@
   },
   "components": [
     {
+      "bom-ref": "2a46171f91c8d4bc",
       "type": "library",
       "name": "package-1",
       "version": "1.0.1",
@@ -52,7 +53,7 @@
         },
         {
           "name": "syft:location:0:layerID",
-          "value": "sha256:16e64541f2ddf59a90391ce7bb8af90313f7d373f2105d88f3d3267b72e0ebab"
+          "value": "sha256:fb6beecb75b39f4bb813dbf177e501edd5ddb3e69bb45cedeb78c676ee1b7a59"
         },
         {
           "name": "syft:location:0:path",
@@ -61,11 +62,12 @@
       ]
     },
     {
+      "bom-ref": "pkg:deb/debian/package-2@2.0.1?syft-id=ae77680e9b1d087e",
       "type": "library",
       "name": "package-2",
       "version": "2.0.1",
       "cpe": "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*",
-      "purl": "a-purl-2",
+      "purl": "pkg:deb/debian/package-2@2.0.1",
       "properties": [
         {
           "name": "syft:package:foundBy",
@@ -81,7 +83,7 @@
         },
         {
           "name": "syft:location:0:layerID",
-          "value": "sha256:de6c235f76ea24c8503ec08891445b5d6a8bdf8249117ed8d8b0b6fb3ebe4f67"
+          "value": "sha256:319b588ce64253a87b533c8ed01cf0025e0eac98e7b516e12532957e1244fdec"
         },
         {
           "name": "syft:location:0:path",

internal/formats/cyclonedxxml/test-fixtures/snapshot/TestCycloneDxDirectoryEncoder.golden

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<bom xmlns="http://cyclonedx.org/schema/bom/1.4" serialNumber="urn:uuid:892f8304-0142-45b1-b411-cade3c53057f" version="1">
+<bom xmlns="http://cyclonedx.org/schema/bom/1.4" serialNumber="urn:uuid:554fd820-210b-40c8-8c0b-75690274e21c" version="1">
   <metadata>
-    <timestamp>2022-03-08T12:30:33Z</timestamp>
+    <timestamp>2022-04-01T11:57:46-04:00</timestamp>
     <tools>
       <tool>
         <vendor>anchore</vendor>
@@ -14,7 +14,7 @@
     </component>
   </metadata>
   <components>
-    <component type="library">
+    <component bom-ref="b85dbb4e6ece5082" type="library">
       <name>package-1</name>
       <version>1.0.1</version>
       <licenses>
@@ -32,11 +32,11 @@
         <property name="syft:location:0:path">/some/path/pkg1</property>
       </properties>
     </component>
-    <component type="library">
+    <component bom-ref="pkg:deb/debian/package-2@2.0.1?syft-id=ceda99598967ae8d" type="library">
       <name>package-2</name>
       <version>2.0.1</version>
       <cpe>cpe:2.3:*:some:package:2:*:*:*:*:*:*:*</cpe>
-      <purl>a-purl-2</purl>
+      <purl>pkg:deb/debian/package-2@2.0.1</purl>
       <properties>
         <property name="syft:package:foundBy">the-cataloger-2</property>
         <property name="syft:package:metadataType">DpkgMetadata</property>

internal/formats/cyclonedxxml/test-fixtures/snapshot/TestCycloneDxImageEncoder.golden

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<bom xmlns="http://cyclonedx.org/schema/bom/1.4" serialNumber="urn:uuid:5fa94827-eb85-4f32-a62d-76fb6e89a2dd" version="1">
+<bom xmlns="http://cyclonedx.org/schema/bom/1.4" serialNumber="urn:uuid:1535f940-172f-4d97-8280-d5a5764d1557" version="1">
   <metadata>
-    <timestamp>2022-03-08T12:30:33Z</timestamp>
+    <timestamp>2022-04-01T11:57:46-04:00</timestamp>
     <tools>
       <tool>
         <vendor>anchore</vendor>
@@ -9,13 +9,13 @@
         <version>[not provided]</version>
       </tool>
     </tools>
-    <component bom-ref="711095b1cdf90cce" type="container">
+    <component bom-ref="e777314b02b362e4" type="container">
       <name>user-image-input</name>
       <version>sha256:2731251dc34951c0e50fcc643b4c5f74922dad1a5d98f302b504cf46cd5d9368</version>
     </component>
   </metadata>
   <components>
-    <component type="library">
+    <component bom-ref="2a46171f91c8d4bc" type="library">
       <name>package-1</name>
       <version>1.0.1</version>
       <licenses>
@@ -30,20 +30,20 @@
         <property name="syft:package:language">python</property>
         <property name="syft:package:metadataType">PythonPackageMetadata</property>
         <property name="syft:package:type">python</property>
-        <property name="syft:location:0:layerID">sha256:16e64541f2ddf59a90391ce7bb8af90313f7d373f2105d88f3d3267b72e0ebab</property>
+        <property name="syft:location:0:layerID">sha256:fb6beecb75b39f4bb813dbf177e501edd5ddb3e69bb45cedeb78c676ee1b7a59</property>
         <property name="syft:location:0:path">/somefile-1.txt</property>
       </properties>
     </component>
-    <component type="library">
+    <component bom-ref="pkg:deb/debian/package-2@2.0.1?syft-id=ae77680e9b1d087e" type="library">
       <name>package-2</name>
       <version>2.0.1</version>
       <cpe>cpe:2.3:*:some:package:2:*:*:*:*:*:*:*</cpe>
-      <purl>a-purl-2</purl>
+      <purl>pkg:deb/debian/package-2@2.0.1</purl>
       <properties>
         <property name="syft:package:foundBy">the-cataloger-2</property>
         <property name="syft:package:metadataType">DpkgMetadata</property>
         <property name="syft:package:type">deb</property>
-        <property name="syft:location:0:layerID">sha256:de6c235f76ea24c8503ec08891445b5d6a8bdf8249117ed8d8b0b6fb3ebe4f67</property>
+        <property name="syft:location:0:layerID">sha256:319b588ce64253a87b533c8ed01cf0025e0eac98e7b516e12532957e1244fdec</property>
         <property name="syft:location:0:path">/somefile-2.txt</property>
         <property name="syft:metadata:installedSize">0</property>
       </properties>

internal/formats/github/encoder.go

@@ -130,7 +130,7 @@ func toGithubManifests(s *sbom.SBOM) Manifests {
 
 		name := dependencyName(p)
 		manifest.Resolved[name] = DependencyNode{
-			Purl:         p.PURL,
+			PackageURL:   p.PURL,
 			Metadata:     toDependencyMetadata(p),
 			Relationship: toDependencyRelationshipType(p),
 			Scope:        toDependencyScope(p),

internal/formats/github/encoder_test.go

@@ -104,12 +104,12 @@ func Test_toGithubModel(t *testing.T) {
 				},
 				Resolved: DependencyGraph{
 					"pkg:generic/pkg-1@1.0.1": DependencyNode{
-						Purl:         "pkg:generic/pkg-1@1.0.1",
+						PackageURL:   "pkg:generic/pkg-1@1.0.1",
 						Scope:        DependencyScopeRuntime,
 						Relationship: DependencyRelationshipDirect,
 					},
 					"pkg:generic/pkg-2@2.0.2": DependencyNode{
-						Purl:         "pkg:generic/pkg-2@2.0.2",
+						PackageURL:   "pkg:generic/pkg-2@2.0.2",
 						Scope:        DependencyScopeRuntime,
 						Relationship: DependencyRelationshipDirect,
 					},
@@ -125,7 +125,7 @@ func Test_toGithubModel(t *testing.T) {
 				},
 				Resolved: DependencyGraph{
 					"pkg:generic/pkg-3@3.0.3": DependencyNode{
-						Purl:         "pkg:generic/pkg-3@3.0.3",
+						PackageURL:   "pkg:generic/pkg-3@3.0.3",
 						Scope:        DependencyScopeRuntime,
 						Relationship: DependencyRelationshipDirect,
 					},

internal/formats/github/github_dependency_api.go

@@ -14,9 +14,9 @@ type DependencySnapshot struct {
 }
 
 type Job struct {
-	Name    string `json:"name,omitempty"` // !omitempty
-	ID      string `json:"id,omitempty"`   // !omitempty
-	HTMLURL string `json:"html_url,omitempty"`
+	Correlator string `json:"correlator,omitempty"` // !omitempty
+	ID         string `json:"id,omitempty"`         // !omitempty
+	HTMLURL    string `json:"html_url,omitempty"`
 }
 
 type DetectorMetadata struct {
@@ -62,7 +62,7 @@ const (
 )
 
 type DependencyNode struct {
-	Purl         string                 `json:"purl,omitempty"`
+	PackageURL   string                 `json:"package_url,omitempty"`
 	Metadata     Metadata               `json:"metadata,omitempty"`
 	Relationship DependencyRelationship `json:"relationship,omitempty"`
 	Scope        DependencyScope        `json:"scope,omitempty"`

internal/formats/spdx22json/model/element_id.go

@@ -1,5 +1,7 @@
 package model
 
+import "github.com/anchore/syft/internal/formats/common/spdxhelpers"
+
 // 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.
@@ -7,31 +9,5 @@ package model
 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()
+	return "SPDXRef-" + spdxhelpers.SanitizeElementID(string(e))
 }

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

@@ -3,7 +3,7 @@
  "name": "/some/path",
  "spdxVersion": "SPDX-2.2",
  "creationInfo": {
-  "created": "2022-03-30T21:48:28.297464Z",
+  "created": "2022-04-01T15:48:39.459232Z",
   "creators": [
    "Organization: Anchore, Inc",
    "Tool: syft-[not provided]"
@@ -11,7 +11,7 @@
   "licenseListVersion": "3.16"
  },
  "dataLicense": "CC0-1.0",
- "documentNamespace": "https://anchore.com/syft/dir/some/path-e188d59b-76f6-4c7f-a9f2-1ae7d0577781",
+ "documentNamespace": "https://anchore.com/syft/dir/some/path-8d335d81-29c9-4236-84f1-2292ea92aaf5",
  "packages": [
   {
    "SPDXID": "SPDXRef-b85dbb4e6ece5082",
@@ -48,7 +48,7 @@
     },
     {
      "referenceCategory": "PACKAGE_MANAGER",
-     "referenceLocator": "a-purl-2",
+     "referenceLocator": "pkg:deb/debian/package-2@2.0.1",
      "referenceType": "purl"
     }
    ],

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

@@ -3,7 +3,7 @@
  "name": "user-image-input",
  "spdxVersion": "SPDX-2.2",
  "creationInfo": {
-  "created": "2022-03-30T21:48:28.303986Z",
+  "created": "2022-04-01T15:48:39.465643Z",
   "creators": [
    "Organization: Anchore, Inc",
    "Tool: syft-[not provided]"
@@ -11,7 +11,7 @@
   "licenseListVersion": "3.16"
  },
  "dataLicense": "CC0-1.0",
- "documentNamespace": "https://anchore.com/syft/image/user-image-input-9e4f4190-c5ae-4e31-a852-d1ab71357516",
+ "documentNamespace": "https://anchore.com/syft/image/user-image-input-e64e0be8-5031-4eec-842d-e59fb6deb518",
  "packages": [
   {
    "SPDXID": "SPDXRef-2a46171f91c8d4bc",
@@ -48,7 +48,7 @@
     },
     {
      "referenceCategory": "PACKAGE_MANAGER",
-     "referenceLocator": "a-purl-2",
+     "referenceLocator": "pkg:deb/debian/package-2@2.0.1",
      "referenceType": "purl"
     }
    ],

internal/formats/spdx22json/to_format_model.go

@@ -55,14 +55,32 @@ func toPackages(catalog *pkg.Catalog, relationships []artifact.Relationship) []m
 	for _, p := range catalog.Sorted() {
 		license := spdxhelpers.License(p)
 		packageSpdxID := model.ElementID(p.ID()).String()
+		filesAnalyzed := false
 
+		// we generate digest for some Java packages
+		// see page 33 of the spdx specification for 2.2
+		// spdx.github.io/spdx-spec/package-information/#710-package-checksum-field
+		var checksums []model.Checksum
+		if p.MetadataType == pkg.JavaMetadataType {
+			javaMetadata := p.Metadata.(pkg.JavaMetadata)
+			if len(javaMetadata.ArchiveDigests) > 0 {
+				filesAnalyzed = true
+				for _, digest := range javaMetadata.ArchiveDigests {
+					checksums = append(checksums, model.Checksum{
+						Algorithm:     strings.ToUpper(digest.Algorithm),
+						ChecksumValue: digest.Value,
+					})
+				}
+			}
+		}
 		// 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{
+			Checksums:        checksums,
 			Description:      spdxhelpers.Description(p),
 			DownloadLocation: spdxhelpers.DownloadLocation(p),
 			ExternalRefs:     spdxhelpers.ExternalRefs(p),
-			FilesAnalyzed:    false,
+			FilesAnalyzed:    filesAnalyzed,
 			HasFiles:         fileIDsForPackage(packageSpdxID, relationships),
 			Homepage:         spdxhelpers.Homepage(p),
 			// The Declared License is what the authors of a project believe govern the package

internal/formats/spdx22tagvalue/encoder_test.go

@@ -6,6 +6,9 @@ import (
 	"testing"
 
 	"github.com/anchore/syft/internal/formats/common/testutils"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+	"github.com/anchore/syft/syft/source"
 )
 
 var updateSpdxTagValue = flag.Bool("update-spdx-tv", false, "update the *.golden files for spdx-tv encoders")
@@ -31,6 +34,32 @@ func TestSPDXTagValueImageEncoder(t *testing.T) {
 	)
 }
 
+func TestSPDXJSONSPDXIDs(t *testing.T) {
+	var pkgs []pkg.Package
+	for _, name := range []string{"some/slashes", "@at-sign", "under_scores"} {
+		p := pkg.Package{
+			Name: name,
+		}
+		p.SetID()
+		pkgs = append(pkgs, p)
+	}
+	testutils.AssertEncoderAgainstGoldenSnapshot(t,
+		Format(),
+		sbom.SBOM{
+			Artifacts: sbom.Artifacts{
+				PackageCatalog: pkg.NewCatalog(pkgs...),
+			},
+			Relationships: nil,
+			Source: source.Metadata{
+				Scheme: source.DirectoryScheme,
+			},
+			Descriptor: sbom.Descriptor{},
+		},
+		true,
+		spdxTagValueRedactor,
+	)
+}
+
 func spdxTagValueRedactor(s []byte) []byte {
 	// each SBOM reports the time it was generated, which is not useful during snapshot testing
 	s = regexp.MustCompile(`Created: .*`).ReplaceAll(s, []byte("redacted"))

internal/formats/spdx22tagvalue/test-fixtures/snapshot/TestSPDXJSONSPDXIDs.golden

@@ -0,0 +1,40 @@
+SPDXVersion: SPDX-2.2
+DataLicense: CC0-1.0
+SPDXID: SPDXRef-DOCUMENT
+DocumentName: .
+DocumentNamespace: https://anchore.com/syft/dir/e69056a9-935e-4f00-b85f-9467f5d99a92
+LicenseListVersion: 3.16
+Creator: Organization: Anchore, Inc
+Creator: Tool: syft-[not provided]
+Created: 2022-04-13T16:38:03Z
+
+##### Package: @at-sign
+
+PackageName: @at-sign
+SPDXID: SPDXRef-Package---at-sign-739e4f0d93fb8298
+PackageDownloadLocation: NOASSERTION
+FilesAnalyzed: false
+PackageLicenseConcluded: NONE
+PackageLicenseDeclared: NONE
+PackageCopyrightText: NOASSERTION
+
+##### Package: some/slashes
+
+PackageName: some/slashes
+SPDXID: SPDXRef-Package--some-slashes-26db06648b24bff9
+PackageDownloadLocation: NOASSERTION
+FilesAnalyzed: false
+PackageLicenseConcluded: NONE
+PackageLicenseDeclared: NONE
+PackageCopyrightText: NOASSERTION
+
+##### Package: under_scores
+
+PackageName: under_scores
+SPDXID: SPDXRef-Package--under-scores-250cbfefcdea318b
+PackageDownloadLocation: NOASSERTION
+FilesAnalyzed: false
+PackageLicenseConcluded: NONE
+PackageLicenseDeclared: NONE
+PackageCopyrightText: NOASSERTION
+

internal/formats/spdx22tagvalue/test-fixtures/snapshot/TestSPDXTagValueDirectoryEncoder.golden

@@ -2,11 +2,11 @@ SPDXVersion: SPDX-2.2
 DataLicense: CC0-1.0
 SPDXID: SPDXRef-DOCUMENT
 DocumentName: /some/path
-DocumentNamespace: https://anchore.com/syft/dir/some/path-71aa3553-1a73-405f-9f1f-6347d6d4593b
+DocumentNamespace: https://anchore.com/syft/dir/some/path-d227b0f2-4ee8-4e10-ac43-019db86d16ff
 LicenseListVersion: 3.16
 Creator: Organization: Anchore, Inc
 Creator: Tool: syft-[not provided]
-Created: 2022-03-30T21:48:22Z
+Created: 2022-04-01T15:48:44Z
 
 ##### Package: package-2
 
@@ -19,7 +19,7 @@ PackageLicenseConcluded: NONE
 PackageLicenseDeclared: NONE
 PackageCopyrightText: NOASSERTION
 ExternalRef: SECURITY cpe23Type cpe:2.3:*:some:package:2:*:*:*:*:*:*:*
-ExternalRef: PACKAGE_MANAGER purl a-purl-2
+ExternalRef: PACKAGE_MANAGER purl pkg:deb/debian/package-2@2.0.1
 
 ##### Package: package-1
 

internal/formats/spdx22tagvalue/test-fixtures/snapshot/TestSPDXTagValueImageEncoder.golden

@@ -2,11 +2,11 @@ SPDXVersion: SPDX-2.2
 DataLicense: CC0-1.0
 SPDXID: SPDXRef-DOCUMENT
 DocumentName: user-image-input
-DocumentNamespace: https://anchore.com/syft/image/user-image-input-e46e20f4-43a4-40e7-9f82-fd55b8a89e5f
+DocumentNamespace: https://anchore.com/syft/image/user-image-input-49f98c61-3418-4427-9e00-8b1c735e9799
 LicenseListVersion: 3.16
 Creator: Organization: Anchore, Inc
 Creator: Tool: syft-[not provided]
-Created: 2022-03-30T21:48:22Z
+Created: 2022-04-01T15:48:44Z
 
 ##### Package: package-2
 
@@ -19,7 +19,7 @@ PackageLicenseConcluded: NONE
 PackageLicenseDeclared: NONE
 PackageCopyrightText: NOASSERTION
 ExternalRef: SECURITY cpe23Type cpe:2.3:*:some:package:2:*:*:*:*:*:*:*
-ExternalRef: PACKAGE_MANAGER purl a-purl-2
+ExternalRef: PACKAGE_MANAGER purl pkg:deb/debian/package-2@2.0.1
 
 ##### Package: package-1
 

internal/formats/spdx22tagvalue/to_format_model.go

@@ -96,13 +96,31 @@ func toFormatPackages(catalog *pkg.Catalog) map[spdx.ElementID]*spdx.Package2_2
 
 	for _, p := range catalog.Sorted() {
 		// name should be guaranteed to be unique, but semantically useful and stable
-		id := fmt.Sprintf("Package-%+v-%s-%s", p.Type, p.Name, p.ID())
+		id := spdxhelpers.SanitizeElementID(fmt.Sprintf("Package-%+v-%s-%s", p.Type, p.Name, p.ID()))
 
 		// 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 := spdxhelpers.License(p)
 
+		filesAnalyzed := false
+		checksums := make(map[spdx.ChecksumAlgorithm]spdx.Checksum)
+
+		// If the pkg type is Java we have attempted to generated a digest
+		// FilesAnalyzed should be true in this case
+		if p.MetadataType == pkg.JavaMetadataType {
+			javaMetadata := p.Metadata.(pkg.JavaMetadata)
+			if len(javaMetadata.ArchiveDigests) > 0 {
+				filesAnalyzed = true
+				for _, digest := range javaMetadata.ArchiveDigests {
+					checksums[spdx.ChecksumAlgorithm(digest.Algorithm)] = spdx.Checksum{
+						Algorithm: spdx.ChecksumAlgorithm(digest.Algorithm),
+						Value:     digest.Value,
+					}
+				}
+			}
+		}
+
 		results[spdx.ElementID(id)] = &spdx.Package2_2{
 
 			// NOT PART OF SPEC
@@ -159,7 +177,7 @@ func toFormatPackages(catalog *pkg.Catalog) map[spdx.ElementID]*spdx.Package2_2
 
 			// Intent: A package can refer to a project, product, artifact, distribution or a component that is
 			// external to the SPDX document.
-			FilesAnalyzed: false,
+			FilesAnalyzed: filesAnalyzed,
 			// NOT PART OF SPEC: did FilesAnalyzed tag appear?
 			IsFilesAnalyzedTagPresent: true,
 
@@ -180,6 +198,7 @@ func toFormatPackages(catalog *pkg.Catalog) map[spdx.ElementID]*spdx.Package2_2
 			// to determine if any file in the original package has been changed. If the SPDX file is to be included
 			// in a package, this value should not be calculated. The SHA-1 algorithm will be used to provide the
 			// checksum by default.
+			PackageChecksums: checksums,
 
 			// note: based on the purpose above no discovered checksums should be provided, but instead, only
 			// tool-derived checksums.

internal/formats/syftjson/test-fixtures/snapshot/TestDirectoryEncoder.golden

@@ -51,7 +51,7 @@
    "cpes": [
     "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
    ],
-   "purl": "a-purl-2",
+   "purl": "pkg:deb/debian/package-2@2.0.1",
    "metadataType": "DpkgMetadata",
    "metadata": {
     "package": "package-2",

internal/formats/syftjson/test-fixtures/snapshot/TestImageEncoder.golden

@@ -48,7 +48,7 @@
    "cpes": [
     "cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"
    ],
-   "purl": "a-purl-2",
+   "purl": "pkg:deb/debian/package-2@2.0.1",
    "metadataType": "DpkgMetadata",
    "metadata": {
     "package": "package-2",

syft/file/digest_cataloger.go

@@ -77,30 +77,39 @@ func (i *DigestsCataloger) catalogLocation(resolver source.FileResolver, locatio
 	}
 	defer internal.CloseAndLogError(contentReader, location.VirtualPath)
 
+	digests, err := DigestsFromFile(contentReader, i.hashes)
+	if err != nil {
+		return nil, internal.ErrPath{Context: "digests-cataloger", Path: location.RealPath, Err: err}
+	}
+
+	return digests, nil
+}
+
+func DigestsFromFile(closer io.ReadCloser, hashes []crypto.Hash) ([]Digest, error) {
 	// create a set of hasher objects tied together with a single writer to feed content into
-	hashers := make([]hash.Hash, len(i.hashes))
-	writers := make([]io.Writer, len(i.hashes))
-	for idx, hashObj := range i.hashes {
+	hashers := make([]hash.Hash, len(hashes))
+	writers := make([]io.Writer, len(hashes))
+	for idx, hashObj := range hashes {
 		hashers[idx] = hashObj.New()
 		writers[idx] = hashers[idx]
 	}
 
-	size, err := io.Copy(io.MultiWriter(writers...), contentReader)
+	size, err := io.Copy(io.MultiWriter(writers...), closer)
 	if err != nil {
-		return nil, internal.ErrPath{Context: "digests-cataloger", Path: location.RealPath, Err: err}
+		return nil, err
 	}
 
 	if size == 0 {
 		return make([]Digest, 0), nil
 	}
 
-	result := make([]Digest, len(i.hashes))
+	result := make([]Digest, len(hashes))
 	// only capture digests when there is content. It is important to do this based on SIZE and not
 	// FILE TYPE. The reasoning is that it is possible for a tar to be crafted with a header-only
 	// file type but a body is still allowed.
 	for idx, hasher := range hashers {
 		result[idx] = Digest{
-			Algorithm: DigestAlgorithmName(i.hashes[idx]),
+			Algorithm: DigestAlgorithmName(hashes[idx]),
 			Value:     fmt.Sprintf("%+x", hasher.Sum(nil)),
 		}
 	}

syft/pkg/cataloger/common/cpe/candidate_by_package_type.go

@@ -19,12 +19,12 @@ var defaultCandidateAdditions = buildCandidateLookup(
 		{
 			pkg.JavaPkg,
 			candidateKey{PkgName: "springframework"},
-			candidateAddition{AdditionalProducts: []string{"spring_framework", "springsource_spring_framework"}},
+			candidateAddition{AdditionalProducts: []string{"spring_framework", "springsource_spring_framework"}, AdditionalVendors: []string{"pivotal_software", "springsource", "vmware"}},
 		},
 		{
 			pkg.JavaPkg,
 			candidateKey{PkgName: "spring-core"},
-			candidateAddition{AdditionalProducts: []string{"spring_framework", "springsource_spring_framework"}},
+			candidateAddition{AdditionalProducts: []string{"spring_framework", "springsource_spring_framework"}, AdditionalVendors: []string{"pivotal_software", "springsource", "vmware"}},
 		},
 		{
 			// example image: docker.io/nuxeo:latest

syft/pkg/cataloger/java/archive_parser.go

@@ -1,14 +1,17 @@
 package java
 
 import (
+	"crypto"
 	"fmt"
 	"io"
+	"os"
 	"path"
 	"strings"
 
 	"github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
+	syftFile "github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/common"
 )
@@ -34,6 +37,11 @@ var archiveFormatGlobs = []string{
 	// project that we can build in CI feel free to include it
 }
 
+// javaArchiveHashes are all the current hash algorithms used to calculate archive digests
+var javaArchiveHashes = []crypto.Hash{
+	crypto.SHA1,
+}
+
 type archiveParser struct {
 	fileManifest file.ZipFileManifest
 	virtualPath  string
@@ -101,6 +109,7 @@ func (j *archiveParser) parse() ([]*pkg.Package, []artifact.Relationship, error)
 	}
 
 	// find aux packages from pom.properties/pom.xml and potentially modify the existing parentPkg
+	// NOTE: we cannot generate sha1 digests from packages discovered via pom.properties/pom.xml
 	auxPkgs, err := j.discoverPkgsFromAllMavenFiles(parentPkg)
 	if err != nil {
 		return nil, nil, err
@@ -135,6 +144,7 @@ func (j *archiveParser) parse() ([]*pkg.Package, []artifact.Relationship, error)
 // discoverMainPackage parses the root Java manifest used as the parent package to all discovered nested packages.
 func (j *archiveParser) discoverMainPackage() (*pkg.Package, error) {
 	// search and parse java manifest files
+	// TODO: do we want to prefer or check for pom files over manifest here?
 	manifestMatches := j.fileManifest.GlobMatch(manifestGlob)
 	if len(manifestMatches) > 1 {
 		return nil, fmt.Errorf("found multiple manifests in the jar: %+v", manifestMatches)
@@ -157,6 +167,18 @@ func (j *archiveParser) discoverMainPackage() (*pkg.Package, error) {
 		return nil, nil
 	}
 
+	archiveCloser, err := os.Open(j.archivePath)
+	if err != nil {
+		return nil, fmt.Errorf("unable to open archive path (%s): %w", j.archivePath, err)
+	}
+	defer archiveCloser.Close()
+
+	// grab and assign digest for the entire archive
+	digests, err := syftFile.DigestsFromFile(archiveCloser, javaArchiveHashes)
+	if err != nil {
+		log.Warnf("failed to create digest for file=%q: %+v", j.archivePath, err)
+	}
+
 	return &pkg.Package{
 		Name:         selectName(manifest, j.fileInfo),
 		Version:      selectVersion(manifest, j.fileInfo),
@@ -164,8 +186,9 @@ func (j *archiveParser) discoverMainPackage() (*pkg.Package, error) {
 		Type:         j.fileInfo.pkgType(),
 		MetadataType: pkg.JavaMetadataType,
 		Metadata: pkg.JavaMetadata{
-			VirtualPath: j.virtualPath,
-			Manifest:    manifest,
+			VirtualPath:    j.virtualPath,
+			Manifest:       manifest,
+			ArchiveDigests: digests,
 		},
 	}, nil
 }
@@ -181,12 +204,14 @@ func (j *archiveParser) discoverPkgsFromAllMavenFiles(parentPkg *pkg.Package) ([
 
 	var pkgs []*pkg.Package
 
-	properties, err := pomPropertiesByParentPath(j.archivePath, j.fileManifest.GlobMatch(pomPropertiesGlob), j.virtualPath)
+	// pom.properties
+	properties, err := pomPropertiesByParentPath(j.archivePath, j.virtualPath, j.fileManifest.GlobMatch(pomPropertiesGlob))
 	if err != nil {
 		return nil, err
 	}
 
-	projects, err := pomProjectByParentPath(j.archivePath, j.fileManifest.GlobMatch(pomXMLGlob), j.virtualPath)
+	// pom.xml
+	projects, err := pomProjectByParentPath(j.archivePath, j.virtualPath, j.fileManifest.GlobMatch(pomXMLGlob))
 	if err != nil {
 		return nil, err
 	}
@@ -273,7 +298,7 @@ func discoverPkgsFromOpener(virtualPath, pathWithinArchive string, archiveOpener
 	return nestedPkgs, nestedRelationships, nil
 }
 
-func pomPropertiesByParentPath(archivePath string, extractPaths []string, virtualPath string) (map[string]pkg.PomProperties, error) {
+func pomPropertiesByParentPath(archivePath, virtualPath string, extractPaths []string) (map[string]pkg.PomProperties, error) {
 	contentsOfMavenPropertiesFiles, err := file.ContentsFromZip(archivePath, extractPaths...)
 	if err != nil {
 		return nil, fmt.Errorf("unable to extract maven files: %w", err)
@@ -298,10 +323,11 @@ func pomPropertiesByParentPath(archivePath string, extractPaths []string, virtua
 
 		propertiesByParentPath[path.Dir(filePath)] = *pomProperties
 	}
+
 	return propertiesByParentPath, nil
 }
 
-func pomProjectByParentPath(archivePath string, extractPaths []string, virtualPath string) (map[string]pkg.PomProject, error) {
+func pomProjectByParentPath(archivePath, virtualPath string, extractPaths []string) (map[string]pkg.PomProject, error) {
 	contentsOfMavenProjectFiles, err := file.ContentsFromZip(archivePath, extractPaths...)
 	if err != nil {
 		return nil, fmt.Errorf("unable to extract maven files: %w", err)

syft/pkg/cataloger/java/archive_parser_test.go

@@ -283,6 +283,11 @@ func TestParseJar(t *testing.T) {
 				metadata := a.Metadata.(pkg.JavaMetadata)
 				metadata.Parent = nil
 
+				// redact Digest which is computed differently between CI and local
+				if len(metadata.ArchiveDigests) > 0 {
+					metadata.ArchiveDigests = nil
+				}
+
 				// ignore select fields (only works for the main section)
 				for _, field := range test.ignoreExtras {
 					if metadata.Manifest != nil && metadata.Manifest.Main != nil {
@@ -567,7 +572,6 @@ func TestParseNestedJar(t *testing.T) {
 						}
 					}
 				}
-
 			}
 		})
 	}

syft/pkg/cataloger/java/save_archive_to_tmp.go

@@ -5,14 +5,13 @@ import (
 	"io"
 	"io/ioutil"
 	"os"
-	"path"
 	"path/filepath"
 
 	"github.com/anchore/syft/internal/log"
 )
 
 func saveArchiveToTmp(archiveVirtualPath string, reader io.Reader) (string, string, func(), error) {
-	name := path.Base(archiveVirtualPath)
+	name := filepath.Base(archiveVirtualPath)
 	tempDir, err := ioutil.TempDir("", "syft-archive-contents-")
 	if err != nil {
 		return "", "", func() {}, fmt.Errorf("unable to create tempdir for archive processing: %w", err)

syft/pkg/java_metadata.go

@@ -3,6 +3,7 @@ package pkg
 import (
 	"strings"
 
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/linux"
 
 	"github.com/anchore/syft/internal"
@@ -20,12 +21,13 @@ var jenkinsPluginPomPropertiesGroupIDs = []string{
 
 // JavaMetadata encapsulates all Java ecosystem metadata for a package as well as an (optional) parent relationship.
 type JavaMetadata struct {
-	VirtualPath   string         `json:"virtualPath" cyclonedx:"virtualPath"` // we need to include the virtual path in cyclonedx documents to prevent deduplication of jars within jars
-	Manifest      *JavaManifest  `mapstructure:"Manifest" json:"manifest,omitempty"`
-	PomProperties *PomProperties `mapstructure:"PomProperties" json:"pomProperties,omitempty" cyclonedx:"-"`
-	PomProject    *PomProject    `mapstructure:"PomProject" json:"pomProject,omitempty"`
-	PURL          string         `hash:"ignore" json:"-"` // pURLs and CPEs are ignored for package IDs
-	Parent        *Package       `hash:"ignore" json:"-"` // note: the parent cannot be included in the minimal definition of uniqueness since this field is not reproducible in an encode-decode cycle (is lossy).
+	VirtualPath    string         `json:"virtualPath" cyclonedx:"virtualPath"` // we need to include the virtual path in cyclonedx documents to prevent deduplication of jars within jars
+	Manifest       *JavaManifest  `mapstructure:"Manifest" json:"manifest,omitempty"`
+	PomProperties  *PomProperties `mapstructure:"PomProperties" json:"pomProperties,omitempty" cyclonedx:"-"`
+	PomProject     *PomProject    `mapstructure:"PomProject" json:"pomProject,omitempty"`
+	ArchiveDigests []file.Digest  `hash:"ignore" json:"digest,omitempty"`
+	PURL           string         `hash:"ignore" json:"-"` // pURLs and CPEs are ignored for package IDs
+	Parent         *Package       `hash:"ignore" json:"-"` // note: the parent cannot be included in the minimal definition of uniqueness since this field is not reproducible in an encode-decode cycle (is lossy).
 }
 
 // PomProperties represents the fields of interest extracted from a Java archive's pom.properties file.