fix: add green fixes before pr fixes

Signed-off-by: Christopher Phillips <32073428+spiffcs@users.noreply.github.com>

.binny.yaml

@@ -26,7 +26,7 @@ tools:
   # used for linting
   - name: golangci-lint
     version:
-      want: v2.5.0
+      want: v2.6.1
     method: github-release
     with:
       repo: golangci/golangci-lint
@@ -58,7 +58,7 @@ tools:
   # used to release all artifacts
   - name: goreleaser
     version:
-      want: v2.12.6
+      want: v2.12.7
     method: github-release
     with:
       repo: goreleaser/goreleaser
@@ -90,7 +90,7 @@ tools:
   # used for running all local and CI tasks
   - name: task
     version:
-      want: v3.45.4
+      want: v3.45.5
     method: github-release
     with:
       repo: go-task/task
@@ -98,7 +98,7 @@ tools:
   # used for triggering a release
   - name: gh
     version:
-      want: v2.82.1
+      want: v2.83.0
     method: github-release
     with:
       repo: cli/cli

.github/workflows/codeql-analysis.yml

@@ -47,7 +47,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@16140ae1a102900babc80a33c44059580f687047 #v3.29.5
+      uses: github/codeql-action/init@0499de31b99561a6d14a36a5f662c2a54f91beee #v3.29.5
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -58,7 +58,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@16140ae1a102900babc80a33c44059580f687047 #v3.29.5
+      uses: github/codeql-action/autobuild@0499de31b99561a6d14a36a5f662c2a54f91beee #v3.29.5
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -72,4 +72,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@16140ae1a102900babc80a33c44059580f687047 #v3.29.5
+      uses: github/codeql-action/analyze@0499de31b99561a6d14a36a5f662c2a54f91beee #v3.29.5

.github/workflows/release.yaml

@@ -19,6 +19,16 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - name: Validate Apple notarization credentials
+        run: .tool/quill submission list
+        env:
+          QUILL_NOTARY_ISSUER: ${{ secrets.APPLE_NOTARY_ISSUER }}
+          QUILL_NOTARY_KEY_ID: ${{ secrets.APPLE_NOTARY_KEY_ID }}
+          QUILL_NOTARY_KEY: ${{ secrets.APPLE_NOTARY_KEY }}
+
       - name: Check if running on main
         if: github.ref != 'refs/heads/main'
         # we are using the following flag when running `cosign blob-verify` for checksum signature verification:
@@ -161,7 +171,7 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@aa0e114b2e19480f157109b9922bda359bd98b90 #v0.20.8
+      - uses: anchore/sbom-action@8e94d75ddd33f69f691467e42275782e4bfefe84 #v0.20.9
         continue-on-error: true
         with:
           file: go.mod

.github/workflows/update-anchore-dependencies.yml

@@ -31,11 +31,11 @@ jobs:
         with:
           repos: ${{ github.event.inputs.repos }}
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-bootstrap-tools.yml

@@ -45,11 +45,11 @@ jobs:
             echo "\`\`\`"
           } >> $GITHUB_STEP_SUMMARY
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-cpe-dictionary-index.yml

@@ -14,6 +14,9 @@ env:
 jobs:
   upgrade-cpe-dictionary-index:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
       - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
@@ -22,18 +25,31 @@ jobs:
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        id: bootstrap
 
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
+      - name: Login to GitHub Container Registry
+        run: |
+          echo "${{ secrets.GITHUB_TOKEN }}" | ${{ steps.bootstrap.outputs.oras }} login ghcr.io -u ${{ github.actor }} --password-stdin
 
-      - run: |
-          make generate-cpe-dictionary-index
+      - name: Pull CPE cache from registry
+        run: make generate:cpe-index:cache:pull
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - name: Update CPE cache from NVD API
+        run: make generate:cpe-index:cache:update
+        env:
+          NVD_API_KEY: ${{ secrets.NVD_API_KEY }}
+
+      - name: Generate CPE dictionary index
+        run: make generate:cpe-index:build
+
+      - name: Push updated CPE cache to registry
+        run: make generate:cpe-index:cache:push
+
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-spdx-license-list.yaml

@@ -0,0 +1,54 @@
+name: PR to update SPDX license list
+on:
+  schedule:
+    - cron: "0 6 * * 1" # every monday at 6 AM UTC
+
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  SLACK_NOTIFICATIONS: true
+
+jobs:
+  upgrade-spdx-license-list:
+    runs-on: ubuntu-latest
+    if: github.repository == 'anchore/syft' # only run for main repo
+    steps:
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+        with:
+          persist-credentials: false
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - run: |
+          make generate-license-list
+
+      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+        id: generate-token
+        with:
+          app_id: ${{ secrets.TOKEN_APP_ID }}
+          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+
+      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
+        with:
+          signoff: true
+          delete-branch: true
+          branch: auto/latest-spdx-license-list
+          labels: dependencies
+          commit-message: "chore(deps): update SPDX license list"
+          title: "chore(deps): update SPDX license list"
+          body: |
+            Update SPDX license list based on the latest available list from spdx.org
+          token: ${{ steps.generate-token.outputs.token }}
+
+      - uses: 8398a7/action-slack@77eaa4f1c608a7d68b38af4e3f739dcd8cba273e #v3.19.0
+        with:
+          status: ${{ job.status }}
+          fields: workflow,eventName,job
+          text: Syft SPDX license list update failed
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
+        if: ${{ failure() && env.SLACK_NOTIFICATIONS == 'true' }}

.gitignore

@@ -73,3 +73,5 @@ cosign.pub
 __pycache__/
 *.py[cod]
 *$py.class
+
+

README.md

@@ -116,7 +116,7 @@ Where the `formats` available are:
 - `spdx-json@2.2`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
 - `github-json`: A JSON report conforming to GitHub's dependency snapshot format.
 - `syft-table`: A columnar summary (default).
-- `template`: Lets the user specify the output format. See ["Using templates"](#using-templates) below.
+- `template`: Lets the user specify the output format. See ["Using templates"](https://github.com/anchore/syft/wiki/using-templates) below.
 
 Note that flags using the @<version> can be used for earlier versions of each specification as well.
 
@@ -135,7 +135,7 @@ Note that flags using the @<version> can be used for earlier versions of each sp
 - Go (go.mod, Go binaries)
 - GitHub (workflows, actions)
 - Haskell (cabal, stack)
-- Java (jar, ear, war, par, sar, nar, native-image)
+- Java (jar, ear, war, par, sar, nar, rar, native-image)
 - JavaScript (npm, yarn)
 - Jenkins Plugins (jpi, hpi)
 - Linux kernel archives (vmlinz)

Taskfile.yaml

@@ -1,5 +1,9 @@
 
 version: "3"
+
+includes:
+  generate:cpe-index: ./task.d/generate/cpe-index.yaml
+
 vars:
   OWNER: anchore
   PROJECT: syft
@@ -511,10 +515,11 @@ tasks:
       - "gofmt -s -w ./internal/spdxlicense"
 
   generate-cpe-dictionary-index:
-    desc: Generate the CPE index based off of the latest available CPE dictionary
-    dir: "syft/pkg/cataloger/internal/cpegenerate/dictionary"
+    desc: Generate the CPE index from local cache
     cmds:
-      - "go generate"
+      - task: generate:cpe-index:cache:pull
+      - task: generate:cpe-index:cache:update
+      - task: generate:cpe-index:build
 
 
   ## Build-related targets #################################

cmd/syft/internal/commands/attest.go

@@ -253,7 +253,6 @@ func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opt
 	}
 
 	src, err := getSource(ctx, opts, userInput, stereoscope.RegistryTag)
-
 	if err != nil {
 		return nil, err
 	}

cmd/syft/internal/commands/cataloger_list.go

@@ -87,8 +87,8 @@ func runCatalogerList(opts *catalogerListOptions) error {
 }
 
 func catalogerListReport(opts *catalogerListOptions, allTaskGroups [][]task.Task) (string, error) {
-	defaultCatalogers := options.Flatten(opts.DefaultCatalogers)
-	selectCatalogers := options.Flatten(opts.SelectCatalogers)
+	defaultCatalogers := options.FlattenAndSort(opts.DefaultCatalogers)
+	selectCatalogers := options.FlattenAndSort(opts.SelectCatalogers)
 	selectedTaskGroups, selectionEvidence, err := task.SelectInGroups(
 		allTaskGroups,
 		cataloging.NewSelectionRequest().

cmd/syft/internal/commands/scan.go

@@ -185,7 +185,6 @@ func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, use
 	}
 
 	src, err := getSource(ctx, &opts.Catalog, userInput, sources...)
-
 	if err != nil {
 		return err
 	}

cmd/syft/internal/options/catalog.go

@@ -198,9 +198,10 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 		},
 		Nix: nix.DefaultConfig().
 			WithCaptureOwnedFiles(cfg.Nix.CaptureOwnedFiles),
-		Python: python.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
+		Python: python.DefaultCatalogerConfig().
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.SearchRemoteLicenses)).
+			WithPypiBaseURL(cfg.Python.PypiBaseURL).
+			WithGuessUnpinnedRequirements(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.GuessUnpinnedRequirements)),
 		JavaArchive: java.DefaultArchiveCatalogerConfig().
 			WithUseMavenLocalRepository(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseMavenLocalRepository)).
 			WithMavenLocalRepositoryDir(cfg.Java.MavenLocalRepositoryDir).
@@ -283,10 +284,10 @@ func (cfg *Catalog) PostLoad() error {
 
 	cfg.From = Flatten(cfg.From)
 
-	cfg.Catalogers = Flatten(cfg.Catalogers)
-	cfg.DefaultCatalogers = Flatten(cfg.DefaultCatalogers)
-	cfg.SelectCatalogers = Flatten(cfg.SelectCatalogers)
-	cfg.Enrich = Flatten(cfg.Enrich)
+	cfg.Catalogers = FlattenAndSort(cfg.Catalogers)
+	cfg.DefaultCatalogers = FlattenAndSort(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = FlattenAndSort(cfg.SelectCatalogers)
+	cfg.Enrich = FlattenAndSort(cfg.Enrich)
 
 	// for backwards compatibility
 	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
@@ -311,6 +312,11 @@ func Flatten(commaSeparatedEntries []string) []string {
 			out = append(out, strings.TrimSpace(s))
 		}
 	}
+	return out
+}
+
+func FlattenAndSort(commaSeparatedEntries []string) []string {
+	out := Flatten(commaSeparatedEntries)
 	sort.Strings(out)
 	return out
 }
@@ -320,6 +326,7 @@ var publicisedEnrichmentOptions = []string{
 	task.Golang,
 	task.Java,
 	task.JavaScript,
+	task.Python,
 }
 
 func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {

cmd/syft/internal/options/catalog_test.go

@@ -79,6 +79,98 @@ func TestCatalog_PostLoad(t *testing.T) {
 	}
 }
 
+func TestFlatten(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "preserves order of comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "preserves order across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "trims whitespace",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "preserves reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"zebra", "yankee", "xray"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Flatten(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+func TestFlattenAndSort(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "sorts comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "sorts across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "trims whitespace and sorts",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "sorts reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"xray", "yankee", "zebra"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := FlattenAndSort(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
 func Test_enrichmentEnabled(t *testing.T) {
 	tests := []struct {
 		directives string
@@ -139,7 +231,7 @@ func Test_enrichmentEnabled(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.directives, func(t *testing.T) {
-			got := enrichmentEnabled(Flatten([]string{test.directives}), test.test)
+			got := enrichmentEnabled(FlattenAndSort([]string{test.directives}), test.test)
 			assert.Equal(t, test.expected, got)
 		})
 	}

cmd/syft/internal/options/python.go

@@ -3,7 +3,9 @@ package options
 import "github.com/anchore/clio"
 
 type pythonConfig struct {
-	GuessUnpinnedRequirements bool `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
+	SearchRemoteLicenses      *bool  `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	PypiBaseURL               string `json:"pypi-base-url" yaml:"pypi-base-url" mapstructure:"pypi-base-url"`
+	GuessUnpinnedRequirements *bool  `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
 }
 
 var _ interface {
@@ -11,6 +13,8 @@ var _ interface {
 } = (*pythonConfig)(nil)
 
 func (o *pythonConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.SearchRemoteLicenses, `enables Syft to use the network to fill in more detailed license information`)
+	descriptions.Add(&o.PypiBaseURL, `base Pypi url to use`)
 	descriptions.Add(&o.GuessUnpinnedRequirements, `when running across entries in requirements.txt that do not specify a specific version 
 (e.g. "sqlalchemy >= 1.0.0, <= 2.0.0, != 3.0.0, <= 3.0.0"), attempt to guess what the version could
 be based on the version requirements specified (e.g. "1.0.0"). When enabled the lowest expressible version 

cmd/syft/internal/test/integration/catalog_packages_test.go

@@ -25,7 +25,6 @@ func BenchmarkImagePackageCatalogers(b *testing.B) {
 	// get the source object for the image
 	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(b, err)
-
 	b.Cleanup(func() {
 		require.NoError(b, theSource.Close())
 	})
@@ -88,6 +87,7 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedPkgs.Remove(string(pkg.TerraformPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // we have coverage for pear instead
 	definedPkgs.Remove(string(pkg.CondaPkg))
+	definedPkgs.Remove(string(pkg.ModelPkg))
 
 	var cases []testCase
 	cases = append(cases, commonTestCases...)
@@ -162,6 +162,7 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	definedPkgs.Remove(string(pkg.UnknownPkg))
 	definedPkgs.Remove(string(pkg.CondaPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // this is covered as pear packages
+	definedPkgs.Remove(string(pkg.ModelPkg))
 
 	// for directory scans we should not expect to see any of the following package types
 	definedPkgs.Remove(string(pkg.KbPkg))

cmd/syft/internal/test/integration/utils_test.go

@@ -38,11 +38,11 @@ func catalogFixtureImageWithConfig(t *testing.T, fixtureImageName string, cfg *s
 	// get the source to build an SBOM against
 	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(t, err)
-
 	t.Cleanup(func() {
 		require.NoError(t, theSource.Close())
 	})
 
+	// build the SBOM
 	s, err := syft.CreateSBOM(context.Background(), theSource, cfg)
 
 	require.NoError(t, err)
@@ -66,7 +66,7 @@ func catalogDirectory(t *testing.T, dir string, catalogerSelection ...string) (s
 func catalogDirectoryWithConfig(t *testing.T, dir string, cfg *syft.CreateSBOMConfig) (sbom.SBOM, source.Source) {
 	cfg.CatalogerSelection = cfg.CatalogerSelection.WithDefaults(pkgcataloging.DirectoryTag)
 
-	// get the source to build an sbom against
+	// get the source to build an SBOM against
 	theSource, err := syft.GetSource(context.Background(), dir, syft.DefaultGetSourceConfig().WithSources("dir"))
 	require.NoError(t, err)
 	t.Cleanup(func() {

examples/create_custom_sbom/main.go

@@ -23,6 +23,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// will catalog the given source and return a SBOM keeping in mind several configurable options
 	sbom := getSBOM(src)
@@ -46,7 +47,6 @@ func getSource(input string) source.Source {
 	fmt.Println("detecting source type for input:", input, "...")
 
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/create_simple_sbom/main.go

@@ -19,6 +19,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// catalog the given source and return a SBOM
 	sbom := getSBOM(src)
@@ -40,7 +41,6 @@ func imageReference() string {
 
 func getSource(input string) source.Source {
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/select_catalogers/main.go

@@ -19,6 +19,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// catalog the given source and return a SBOM
 	// let's explicitly use catalogers that are:
@@ -44,7 +45,6 @@ func imageReference() string {
 
 func getSource(input string) source.Source {
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/source_from_registry/main.go

@@ -15,6 +15,7 @@ func main() {
 	image := "alpine:3.19"
 
 	src, _ := syft.GetSource(context.Background(), image, syft.DefaultGetSourceConfig().WithSources("registry"))
+	defer src.Close()
 
 	sbom, _ := syft.CreateSBOM(context.Background(), src, syft.DefaultCreateSBOMConfig())
 

go.mod

@@ -24,7 +24,7 @@ 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 v0.1.1-0.20250220190351-d62adb6e1115
-	github.com/anchore/stereoscope v0.1.11
+	github.com/anchore/stereoscope v0.1.12
 	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
 	github.com/aquasecurity/go-pep440-version v0.0.1
 	github.com/bitnami/go-version v0.0.0-20250131085805-b1f57a8634ef
@@ -53,19 +53,19 @@ require (
 	github.com/google/uuid v1.6.0
 	github.com/gookit/color v1.6.0
 	github.com/hashicorp/go-cleanhttp v0.5.2
-	github.com/hashicorp/go-getter v1.8.2
+	github.com/hashicorp/go-getter v1.8.3
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/hashicorp/hcl/v2 v2.24.0
 	github.com/iancoleman/strcase v0.3.0
 	github.com/invopop/jsonschema v0.7.0
-	github.com/jedib0t/go-pretty/v6 v6.6.8
+	github.com/jedib0t/go-pretty/v6 v6.7.1
 	github.com/jinzhu/copier v0.4.0
 	github.com/kastenhq/goversion v0.0.0-20230811215019-93b2f8823953
 	github.com/magiconair/properties v1.8.10
 	github.com/mholt/archives v0.1.5
 	github.com/moby/sys/mountinfo v0.7.2
 	github.com/nix-community/go-nix v0.0.0-20250101154619-4bdde671e0a1
-	github.com/olekukonko/tablewriter v1.0.9
+	github.com/olekukonko/tablewriter v1.1.1
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/pelletier/go-toml v1.9.5
 	github.com/quasilyte/go-ruleguard/dsl v0.3.23
@@ -90,9 +90,9 @@ require (
 	go.uber.org/goleak v1.3.0
 	go.yaml.in/yaml/v3 v3.0.4
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b
-	golang.org/x/mod v0.29.0
+	golang.org/x/mod v0.30.0
 	golang.org/x/net v0.46.0
-	modernc.org/sqlite v1.39.1
+	modernc.org/sqlite v1.40.0
 )
 
 require (
@@ -131,7 +131,7 @@ require (
 	github.com/charmbracelet/x/term v0.2.1 // indirect
 	github.com/cloudflare/circl v1.6.1 // indirect
 	github.com/containerd/cgroups v1.1.0 // indirect
-	github.com/containerd/containerd v1.7.28 // indirect
+	github.com/containerd/containerd v1.7.29 // indirect
 	github.com/containerd/containerd/api v1.8.0 // indirect
 	github.com/containerd/continuity v0.4.4 // indirect
 	github.com/containerd/errdefs v1.0.0 // indirect
@@ -142,7 +142,7 @@ require (
 	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
 	github.com/containerd/ttrpc v1.2.7 // indirect
 	github.com/containerd/typeurl/v2 v2.2.0 // indirect
-	github.com/cyphar/filepath-securejoin v0.4.1 // indirect
+	github.com/cyphar/filepath-securejoin v0.6.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/docker/cli v28.5.1+incompatible // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
@@ -191,7 +191,7 @@ require (
 	github.com/mattn/go-colorable v0.1.14 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75 // indirect
-	github.com/mattn/go-runewidth v0.0.16 // indirect
+	github.com/mattn/go-runewidth v0.0.19 // indirect
 	github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d // indirect
 	github.com/mikelolasagasti/xz v1.0.1 // indirect
 	github.com/minio/minlz v1.0.1 // indirect
@@ -212,10 +212,10 @@ require (
 	github.com/nwaples/rardecode v1.1.3 // indirect
 	github.com/nwaples/rardecode/v2 v2.2.0 // indirect
 	github.com/olekukonko/errors v1.1.0 // indirect
-	github.com/olekukonko/ll v0.0.9 // indirect
+	github.com/olekukonko/ll v0.1.2 // indirect
 	github.com/opencontainers/image-spec v1.1.1 // indirect
 	github.com/opencontainers/runtime-spec v1.1.0 // indirect
-	github.com/opencontainers/selinux v1.11.0 // indirect
+	github.com/opencontainers/selinux v1.13.0 // indirect
 	github.com/pborman/indent v1.2.1 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.3 // indirect
 	github.com/pierrec/lz4/v4 v4.1.22 // indirect
@@ -270,7 +270,7 @@ require (
 	golang.org/x/sys v0.37.0 // indirect
 	golang.org/x/term v0.36.0 // indirect
 	golang.org/x/text v0.30.0 // indirect
-	golang.org/x/time v0.12.0 // indirect
+	golang.org/x/time v0.14.0
 	golang.org/x/tools v0.38.0
 	golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 // indirect
 	google.golang.org/api v0.203.0 // indirect
@@ -287,6 +287,12 @@ require (
 )
 
 require (
+	github.com/cespare/xxhash/v2 v2.3.0
+	github.com/gpustack/gguf-parser-go v0.22.1
+)
+
+require (
+	cyphar.com/go-pathrs v0.2.1 // indirect
 	github.com/aws/aws-sdk-go-v2 v1.36.5 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.10 // indirect
 	github.com/aws/aws-sdk-go-v2/config v1.29.17 // indirect
@@ -305,7 +311,17 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.30.3 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sts v1.34.0 // indirect
 	github.com/aws/smithy-go v1.22.4 // indirect
+	github.com/clipperhouse/displaywidth v0.3.1 // indirect
+	github.com/clipperhouse/stringish v0.1.1 // indirect
+	github.com/clipperhouse/uax29/v2 v2.2.0 // indirect
 	github.com/hashicorp/aws-sdk-go-base/v2 v2.0.0-beta.65 // indirect
+	github.com/henvic/httpretty v0.1.4 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6 // indirect
+	github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d // indirect
+	gonum.org/v1/gonum v0.15.1 // indirect
 )
 
 retract (

go.sum

@@ -59,6 +59,8 @@ cloud.google.com/go/storage v1.8.0/go.mod h1:Wv1Oy7z6Yz3DshWRJFhqM/UCfaWIRTdp0RX
 cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9ullr3+Kg0=
 cloud.google.com/go/storage v1.43.0 h1:CcxnSohZwizt4LCzQHWvBf1/kvtHUn7gk9QERXPyXFs=
 cloud.google.com/go/storage v1.43.0/go.mod h1:ajvxEa7WmZS1PxvKRq4bq0tFT3vMd502JwstCcYv0Q0=
+cyphar.com/go-pathrs v0.2.1 h1:9nx1vOgwVvX1mNBWDu93+vaceedpbsDqo+XuBGL40b8=
+cyphar.com/go-pathrs v0.2.1/go.mod h1:y8f1EMG7r+hCuFf/rXsKqMJrJAUoADZGNh5/vZPKcGc=
 dario.cat/mergo v1.0.1 h1:Ra4+bf83h2ztPIQYNP99R6m+Y7KfnARDfID+a+vLl4s=
 dario.cat/mergo v1.0.1/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk=
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
@@ -138,8 +140,8 @@ 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 v0.1.1-0.20250220190351-d62adb6e1115 h1:ZyRCmiEjnoGJZ1+Ah0ZZ/mKKqNhGcUZBl0s7PTTDzvY=
 github.com/anchore/packageurl-go v0.1.1-0.20250220190351-d62adb6e1115/go.mod h1:KoYIv7tdP5+CC9VGkeZV4/vGCKsY55VvoG+5dadg4YI=
-github.com/anchore/stereoscope v0.1.11 h1:YP/XUNcJyMbOOPAWPkeZNCVlKKTRO2cnBTEeUW6I40Y=
-github.com/anchore/stereoscope v0.1.11/go.mod h1:G3PZlzPbxFhylj9pQwtqfVPaahuWmy/UCtv5FTIIMvg=
+github.com/anchore/stereoscope v0.1.12 h1:4T/10G7Nb98UoJBKVvAIhsAtrR63lZXxMJb/Qfw5inw=
+github.com/anchore/stereoscope v0.1.12/go.mod h1:G3PZlzPbxFhylj9pQwtqfVPaahuWmy/UCtv5FTIIMvg=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
 github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
@@ -227,7 +229,6 @@ github.com/cenkalti/backoff/v4 v4.2.1 h1:y4OZtCnogmCPw98Zjyt5a6+QwPLGkiQsYW5oUqy
 github.com/cenkalti/backoff/v4 v4.2.1/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/census-instrumentation/opencensus-proto v0.3.0/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
-github.com/cespare/xxhash v1.1.0 h1:a6HrQnmkObjyL+Gs60czilIUGqrzKutQD6XZog3p+ko=
 github.com/cespare/xxhash v1.1.0/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
 github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -263,6 +264,12 @@ github.com/chzyer/test v1.0.0/go.mod h1:2JlltgoNkt4TW/z9V/IzDdFaMTM2JPIi26O1pF38
 github.com/circonus-labs/circonus-gometrics v2.3.1+incompatible/go.mod h1:nmEj6Dob7S7YxXgwXpfOuvO54S+tGdZdw9fuRZt25Ag=
 github.com/circonus-labs/circonusllhist v0.1.3/go.mod h1:kMXHVDlOchFAehlya5ePtbp5jckzBHf4XRpQvBOLI+I=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
+github.com/clipperhouse/displaywidth v0.3.1 h1:k07iN9gD32177o1y4O1jQMzbLdCrsGJh+blirVYybsk=
+github.com/clipperhouse/displaywidth v0.3.1/go.mod h1:tgLJKKyaDOCadywag3agw4snxS5kYEuYR6Y9+qWDDYM=
+github.com/clipperhouse/stringish v0.1.1 h1:+NSqMOr3GR6k1FdRhhnXrLfztGzuG+VuFDfatpWHKCs=
+github.com/clipperhouse/stringish v0.1.1/go.mod h1:v/WhFtE1q0ovMta2+m+UbpZ+2/HEXNWYXQgCt4hdOzA=
+github.com/clipperhouse/uax29/v2 v2.2.0 h1:ChwIKnQN3kcZteTXMgb1wztSgaU+ZemkgWdohwgs8tY=
+github.com/clipperhouse/uax29/v2 v2.2.0/go.mod h1:EFJ2TJMRUaplDxHKj1qAEhCtQPW2tJSwu5BF98AuoVM=
 github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
 github.com/cloudflare/circl v1.6.1/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
@@ -277,8 +284,8 @@ github.com/cncf/xds/go v0.0.0-20211011173535-cb28da3451f1/go.mod h1:eXthEFrGJvWH
 github.com/cncf/xds/go v0.0.0-20211130200136-a8f946100490/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
 github.com/containerd/cgroups v1.1.0 h1:v8rEWFl6EoqHB+swVNjVoCJE8o3jX7e8nqBGPLaDFBM=
 github.com/containerd/cgroups v1.1.0/go.mod h1:6ppBcbh/NOOUU+dMKrykgaBnK9lCIBxHqJDGwsa1mIw=
-github.com/containerd/containerd v1.7.28 h1:Nsgm1AtcmEh4AHAJ4gGlNSaKgXiNccU270Dnf81FQ3c=
-github.com/containerd/containerd v1.7.28/go.mod h1:azUkWcOvHrWvaiUjSQH0fjzuHIwSPg1WL5PshGP4Szs=
+github.com/containerd/containerd v1.7.29 h1:90fWABQsaN9mJhGkoVnuzEY+o1XDPbg9BTC9QTAHnuE=
+github.com/containerd/containerd v1.7.29/go.mod h1:azUkWcOvHrWvaiUjSQH0fjzuHIwSPg1WL5PshGP4Szs=
 github.com/containerd/containerd/api v1.8.0 h1:hVTNJKR8fMc/2Tiw60ZRijntNMd1U+JVMyTRdsD2bS0=
 github.com/containerd/containerd/api v1.8.0/go.mod h1:dFv4lt6S20wTu/hMcP4350RL87qPWLVa/OHOwmmdnYc=
 github.com/containerd/continuity v0.4.4 h1:/fNVfTJ7wIl/YPMHjf+5H32uFhl63JucB34PlCpMKII=
@@ -304,8 +311,8 @@ github.com/coreos/go-systemd/v22 v22.3.2/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSV
 github.com/cpuguy83/go-md2man/v2 v2.0.1/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
-github.com/cyphar/filepath-securejoin v0.4.1 h1:JyxxyPEaktOD+GAnqIqTf9A8tHyAG22rowi7HkoSU1s=
-github.com/cyphar/filepath-securejoin v0.4.1/go.mod h1:Sdj7gXlvMcPZsbhwhQ33GguGLDGQL7h7bg04C/+u9jI=
+github.com/cyphar/filepath-securejoin v0.6.0 h1:BtGB77njd6SVO6VztOHfPxKitJvd/VPT+OFBFMOi1Is=
+github.com/cyphar/filepath-securejoin v0.6.0/go.mod h1:A8hd4EnAeyujCJRrICiOWqjS1AX0a9kM5XL+NwKoYSc=
 github.com/dave/jennifer v1.7.1 h1:B4jJJDHelWcDhlRQxWeo0Npa/pYKBLrirAQoTN45txo=
 github.com/dave/jennifer v1.7.1/go.mod h1:nXbxhEmQfOZhWml3D1cDK5M1FLnMSozpbFN/m3RmGZc=
 github.com/davecgh/go-spew v0.0.0-20161028175848-04cdfd42973b/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -541,6 +548,8 @@ github.com/gookit/assert v0.1.1/go.mod h1:jS5bmIVQZTIwk42uXl4lyj4iaaxx32tqH16CFj
 github.com/gookit/color v1.2.5/go.mod h1:AhIE+pS6D4Ql0SQWbBeXPHw7gY0/sjHoA4s/n1KB7xg=
 github.com/gookit/color v1.6.0 h1:JjJXBTk1ETNyqyilJhkTXJYYigHG24TM9Xa2M1xAhRA=
 github.com/gookit/color v1.6.0/go.mod h1:9ACFc7/1IpHGBW8RwuDm/0YEnhg3dwwXpoMsmtyHfjs=
+github.com/gpustack/gguf-parser-go v0.22.1 h1:FRnEDWqT0Rcplr/R9ctCRSN2+3DhVsf6dnR5/i9JA4E=
+github.com/gpustack/gguf-parser-go v0.22.1/go.mod h1:y4TwTtDqFWTK+xvprOjRUh+dowgU2TKCX37vRKvGiZ0=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.16.0 h1:YBftPWNWd4WwGqtY2yeZL2ef8rHAxPBD8KFhJpmcqms=
@@ -556,8 +565,8 @@ github.com/hashicorp/go-cleanhttp v0.5.0/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtng
 github.com/hashicorp/go-cleanhttp v0.5.1/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtngrth3wmdIIUrZ80=
 github.com/hashicorp/go-cleanhttp v0.5.2 h1:035FKYIWjmULyFRBKPs8TBQoi0x6d9G4xc9neXJWAZQ=
 github.com/hashicorp/go-cleanhttp v0.5.2/go.mod h1:kO/YDlP8L1346E6Sodw+PrpBSV4/SoxCXGY6BqNFT48=
-github.com/hashicorp/go-getter v1.8.2 h1:CGCK+bZQLl44PYiwJweVzfpjg7bBwtuXu3AGcLiod2o=
-github.com/hashicorp/go-getter v1.8.2/go.mod h1:CUTt9x2bCtJ/sV8ihgrITL3IUE+0BE1j/e4n5P/GIM4=
+github.com/hashicorp/go-getter v1.8.3 h1:gIS+oTNv3kyYAvlUVgMR46MiG0bM0KuSON/KZEvRoRg=
+github.com/hashicorp/go-getter v1.8.3/go.mod h1:CUTt9x2bCtJ/sV8ihgrITL3IUE+0BE1j/e4n5P/GIM4=
 github.com/hashicorp/go-hclog v0.12.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
 github.com/hashicorp/go-hclog v1.0.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
 github.com/hashicorp/go-immutable-radix v1.0.0/go.mod h1:0y9vanUI8NX6FsYoO3zeMjhV/C5i9g4Q3DwcSNZ4P60=
@@ -590,6 +599,8 @@ github.com/hashicorp/memberlist v0.2.2/go.mod h1:MS2lj3INKhZjWNqd3N0m3J+Jxf3DAOn
 github.com/hashicorp/memberlist v0.3.0/go.mod h1:MS2lj3INKhZjWNqd3N0m3J+Jxf3DAOnAH9VT3Sh9MUE=
 github.com/hashicorp/serf v0.9.5/go.mod h1:UWDWwZeL5cuWDJdl0C6wrvrUwEqtQ4ZKBKKENpqIUyk=
 github.com/hashicorp/serf v0.9.6/go.mod h1:TXZNMjZQijwlDvp+r0b63xZ45H7JmCmgg4gpTwn9UV4=
+github.com/henvic/httpretty v0.1.4 h1:Jo7uwIRWVFxkqOnErcoYfH90o3ddQyVrSANeS4cxYmU=
+github.com/henvic/httpretty v0.1.4/go.mod h1:Dn60sQTZfbt2dYsdUSNsCljyF4AfdqnuJFDLJA1I4AM=
 github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI=
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
 github.com/iancoleman/orderedmap v0.0.0-20190318233801-ac98e3ecb4b0/go.mod h1:N0Wam8K1arqPXNWjMo21EXnBPOPp36vB07FNRdD2geA=
@@ -609,14 +620,15 @@ github.com/invopop/jsonschema v0.7.0 h1:2vgQcBz1n256N+FpX3Jq7Y17AjYt46Ig3zIWyy77
 github.com/invopop/jsonschema v0.7.0/go.mod h1:O9uiLokuu0+MGFlyiaqtWxwqJm41/+8Nj0lD7A36YH0=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
-github.com/jedib0t/go-pretty/v6 v6.6.8 h1:JnnzQeRz2bACBobIaa/r+nqjvws4yEhcmaZ4n1QzsEc=
-github.com/jedib0t/go-pretty/v6 v6.6.8/go.mod h1:YwC5CE4fJ1HFUDeivSV1r//AmANFHyqczZk+U6BDALU=
+github.com/jedib0t/go-pretty/v6 v6.7.1 h1:bHDSsj93NuJ563hHuM7ohk/wpX7BmRFNIsVv1ssI2/M=
+github.com/jedib0t/go-pretty/v6 v6.7.1/go.mod h1:YwC5CE4fJ1HFUDeivSV1r//AmANFHyqczZk+U6BDALU=
 github.com/jinzhu/copier v0.4.0 h1:w3ciUoD19shMCRargcpm0cm91ytaBhDvuRpz1ODO/U8=
 github.com/jinzhu/copier v0.4.0/go.mod h1:DfbEm0FYsaqBcKcFuvmOZb218JkPGtvSHsKg8S8hyyg=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.11/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
 github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
@@ -676,8 +688,8 @@ github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWE
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75 h1:P8UmIzZMYDR+NGImiFvErt6VWfIRPuGM+vyjiEdkmIw=
 github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75/go.mod h1:8fBrzywKY7BI3czFoHkuzRoWE9C+EiG4R1k4Cjx5p88=
-github.com/mattn/go-runewidth v0.0.16 h1:E5ScNMtiwvlvB5paMFdw9p4kSQzbXFikJ5SQO6TULQc=
-github.com/mattn/go-runewidth v0.0.16/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
+github.com/mattn/go-runewidth v0.0.19 h1:v++JhqYnZuu5jSKrk9RbgF5v4CGUjqRfBm05byFGLdw=
+github.com/mattn/go-runewidth v0.0.19/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
 github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d h1:5PJl274Y63IEHC+7izoQE9x6ikvDFZS2mDVS3drnohI=
 github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d/go.mod h1:01TrycV0kFyexm33Z7vhZRXopbI8J3TDReVlkTgMUxE=
@@ -722,9 +734,11 @@ github.com/moby/sys/userns v0.1.0/go.mod h1:IHUYgu/kao6N8YZlp9Cf444ySSvCmDlmzUcY
 github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA=
 github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
 github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
@@ -745,12 +759,14 @@ github.com/nwaples/rardecode v1.1.3 h1:cWCaZwfM5H7nAD6PyEdcVnczzV8i/JtotnyW/dD9l
 github.com/nwaples/rardecode v1.1.3/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
 github.com/nwaples/rardecode/v2 v2.2.0 h1:4ufPGHiNe1rYJxYfehALLjup4Ls3ck42CWwjKiOqu0A=
 github.com/nwaples/rardecode/v2 v2.2.0/go.mod h1:7uz379lSxPe6j9nvzxUZ+n7mnJNgjsRNb6IbvGVHRmw=
+github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6 h1:zrbMGy9YXpIeTnGj4EljqMiZsIcE09mmF8XsD5AYOJc=
+github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6/go.mod h1:rEKTHC9roVVicUIfZK7DYrdIoM0EOr8mK1Hj5s3JjH0=
 github.com/olekukonko/errors v1.1.0 h1:RNuGIh15QdDenh+hNvKrJkmxxjV4hcS50Db478Ou5sM=
 github.com/olekukonko/errors v1.1.0/go.mod h1:ppzxA5jBKcO1vIpCXQ9ZqgDh8iwODz6OXIGKU8r5m4Y=
-github.com/olekukonko/ll v0.0.9 h1:Y+1YqDfVkqMWuEQMclsF9HUR5+a82+dxJuL1HHSRpxI=
-github.com/olekukonko/ll v0.0.9/go.mod h1:En+sEW0JNETl26+K8eZ6/W4UQ7CYSrrgg/EdIYT2H8g=
-github.com/olekukonko/tablewriter v1.0.9 h1:XGwRsYLC2bY7bNd93Dk51bcPZksWZmLYuaTHR0FqfL8=
-github.com/olekukonko/tablewriter v1.0.9/go.mod h1:5c+EBPeSqvXnLLgkm9isDdzR3wjfBkHR9Nhfp3NWrzo=
+github.com/olekukonko/ll v0.1.2 h1:lkg/k/9mlsy0SxO5aC+WEpbdT5K83ddnNhAepz7TQc0=
+github.com/olekukonko/ll v0.1.2/go.mod h1:b52bVQRRPObe+yyBl0TxNfhesL0nedD4Cht0/zx55Ew=
+github.com/olekukonko/tablewriter v1.1.1 h1:b3reP6GCfrHwmKkYwNRFh2rxidGHcT6cgxj/sHiDDx0=
+github.com/olekukonko/tablewriter v1.1.1/go.mod h1:De/bIcTF+gpBDB3Alv3fEsZA+9unTsSzAg/ZGADCtn4=
 github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
 github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
@@ -759,8 +775,8 @@ github.com/opencontainers/image-spec v1.1.1 h1:y0fUlFfIZhPF1W537XOLg0/fcx6zcHCJw
 github.com/opencontainers/image-spec v1.1.1/go.mod h1:qpqAh3Dmcf36wStyyWU+kCeDgrGnAve2nCC8+7h8Q0M=
 github.com/opencontainers/runtime-spec v1.1.0 h1:HHUyrt9mwHUjtasSbXSMvs4cyFxh+Bll4AjJ9odEGpg=
 github.com/opencontainers/runtime-spec v1.1.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU=
-github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
+github.com/opencontainers/selinux v1.13.0 h1:Zza88GWezyT7RLql12URvoxsbLfjFx988+LGaWfbL84=
+github.com/opencontainers/selinux v1.13.0/go.mod h1:XxWTed+A/s5NNq4GmYScVy+9jzXhGBVEOAyucdRUY8s=
 github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0=
 github.com/pascaldekloe/goe v0.0.0-20180627143212-57f6aae5913c/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
 github.com/pascaldekloe/goe v0.1.0/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
@@ -809,7 +825,6 @@ github.com/quasilyte/go-ruleguard/dsl v0.3.23 h1:lxjt5B6ZCiBeeNO8/oQsegE6fLeCzuM
 github.com/quasilyte/go-ruleguard/dsl v0.3.23/go.mod h1:KeCP03KrjuSO0H1kTuZQCWlQPulDV6YMIXmpQss17rU=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
-github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
 github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
@@ -851,6 +866,8 @@ github.com/sirupsen/logrus v1.9.4-0.20230606125235-dd1b4c2e81af h1:Sp5TG9f7K39yf
 github.com/sirupsen/logrus v1.9.4-0.20230606125235-dd1b4c2e81af/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
 github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
+github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d h1:3VwvTjiRPA7cqtgOWddEL+JrcijMlXUmj99c/6YyZoY=
+github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d/go.mod h1:tAG61zBM1DYRaGIPloumExGvScf08oHuo0kFoOqdbT0=
 github.com/sorairolake/lzip-go v0.3.8 h1:j5Q2313INdTA80ureWYRhX+1K78mUXfMoPZCw/ivWik=
 github.com/sorairolake/lzip-go v0.3.8/go.mod h1:JcBqGMV0frlxwrsE9sMWXDjqn3EeVf0/54YPsw66qkU=
 github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
@@ -1061,8 +1078,8 @@ golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.5.0/go.mod h1:5OXOZSfqPIIbmVBIIKWRFfZjPR0E5r58TLhUjH0a2Ro=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA=
-golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w=
+golang.org/x/mod v0.30.0 h1:fDEXFVZ/fmCKProc/yAXXUijritrDzahmwwefnjoPFk=
+golang.org/x/mod v0.30.0/go.mod h1:lAsf5O2EvJeSFMiBxXDki7sCgAxEUcZHXoXMKT4GJKc=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181023162649-9b4f9f5ad519/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -1239,8 +1256,8 @@ golang.org/x/text v0.30.0/go.mod h1:yDdHFIX9t+tORqspjENWgzaCVXgk0yYnYuSZ8UzzBVM=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
-golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
+golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
+golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -1304,6 +1321,8 @@ golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 h1:+cNy6SZtPcJQH3LJVLOSmiC7MMxXNOb3PU/VUEz+EhU=
 golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90=
+gonum.org/v1/gonum v0.15.1 h1:FNy7N6OUZVUaWG9pTiD+jlhdQ3lMP+/LcTpJ6+a8sQ0=
+gonum.org/v1/gonum v0.15.1/go.mod h1:eZTZuRFrzu5pcyjN5wJhcIhnUdNijYxX1T2IcrOGY0o=
 google.golang.org/api v0.4.0/go.mod h1:8k5glujaEP+g9n7WNsDg8QP6cUVNI86fCNMcbazEtwE=
 google.golang.org/api v0.7.0/go.mod h1:WtwebWUNSVBH/HAw79HIFXZNqEvBhG+Ra+ax0hx3E3M=
 google.golang.org/api v0.8.0/go.mod h1:o4eAsZoiT+ibD93RtjEohWalFOjRDx6CVaqeizhEnKg=
@@ -1509,8 +1528,8 @@ modernc.org/opt v0.1.4 h1:2kNGMRiUjrp4LcaPuLY2PzUfqM/w9N23quVwhKt5Qm8=
 modernc.org/opt v0.1.4/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
 modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
 modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
-modernc.org/sqlite v1.39.1 h1:H+/wGFzuSCIEVCvXYVHX5RQglwhMOvtHSv+VtidL2r4=
-modernc.org/sqlite v1.39.1/go.mod h1:9fjQZ0mB1LLP0GYrp39oOJXx/I2sxEnZtzCmEQIKvGE=
+modernc.org/sqlite v1.40.0 h1:bNWEDlYhNPAUdUdBzjAvn8icAs/2gaKlj4vM+tQ6KdQ=
+modernc.org/sqlite v1.40.0/go.mod h1:9fjQZ0mB1LLP0GYrp39oOJXx/I2sxEnZtzCmEQIKvGE=
 modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
 modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
 modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=

internal/capabilities/pkgtestobservation/model.go

@@ -0,0 +1,46 @@
+package pkgtestobservation
+
+import "time"
+
+// Observations represents capability observations during testing
+type Observations struct {
+	License       bool         `json:"license"`
+	Relationships Relationship `json:"relationships"`
+	FileListing   Count        `json:"file_listing"`
+	FileDigests   Count        `json:"file_digests"`
+	IntegrityHash Count        `json:"integrity_hash"`
+}
+
+// Relationship tracks dependency relationship observations
+type Relationship struct {
+	Found bool `json:"found"`
+	Count int  `json:"count"`
+}
+
+// Count tracks whether a capability was found and how many times
+type Count struct {
+	Found bool `json:"found"`
+	Count int  `json:"count"`
+}
+
+// Test is the root structure for test-observations.json
+type Test struct {
+	Package    string                `json:"package"`
+	UpdatedAt  time.Time             `json:"updated_at"`
+	Catalogers map[string]*Cataloger `json:"catalogers"`
+	Parsers    map[string]*Parser    `json:"parsers"`
+}
+
+// Parser captures all observations for a parser
+type Parser struct {
+	MetadataTypes []string     `json:"metadata_types"`
+	PackageTypes  []string     `json:"package_types"`
+	Observations  Observations `json:"observations"`
+}
+
+// Cataloger captures all observations for a cataloger
+type Cataloger struct {
+	MetadataTypes []string     `json:"metadata_types"`
+	PackageTypes  []string     `json:"package_types"`
+	Observations  Observations `json:"observations"`
+}

internal/constants.go

@@ -3,5 +3,5 @@ package internal
 const (
 	// JSONSchemaVersion is the current schema version output by the JSON encoder
 	// This is roughly following the "SchemaVer" guidelines for versioning the JSON schema. Please see schema/json/README.md for details on how to increment.
-	JSONSchemaVersion = "16.0.41"
+	JSONSchemaVersion = "16.0.43"
 )

internal/os/feature_detection_test.go

@@ -81,6 +81,10 @@ func Test_EnvironmentTask(t *testing.T) {
 			// get the source
 			theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 			require.NoError(t, err)
+			t.Cleanup(func() {
+				require.NoError(t, theSource.Close())
+			})
+
 			resolver, err := theSource.FileResolver(source.SquashedScope)
 			require.NoError(t, err)
 

internal/packagemetadata/generated.go

@@ -27,6 +27,7 @@ func AllTypes() []any {
 		pkg.ELFBinaryPackageNoteJSONPayload{},
 		pkg.ElixirMixLockEntry{},
 		pkg.ErlangRebarLockEntry{},
+		pkg.GGUFFileHeader{},
 		pkg.GitHubActionsUseStatement{},
 		pkg.GolangBinaryBuildinfoEntry{},
 		pkg.GolangModuleEntry{},
@@ -49,6 +50,7 @@ func AllTypes() []any {
 		pkg.PhpComposerLockEntry{},
 		pkg.PhpPearEntry{},
 		pkg.PhpPeclEntry{},
+		pkg.PnpmLockEntry{},
 		pkg.PortageEntry{},
 		pkg.PythonPackage{},
 		pkg.PythonPdmLockEntry{},

internal/packagemetadata/names.go

@@ -95,10 +95,11 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.NpmPackage{}, "javascript-npm-package", "NpmPackageJsonMetadata"),
 	jsonNames(pkg.NpmPackageLockEntry{}, "javascript-npm-package-lock-entry", "NpmPackageLockJsonMetadata"),
 	jsonNames(pkg.YarnLockEntry{}, "javascript-yarn-lock-entry", "YarnLockJsonMetadata"),
+	jsonNames(pkg.PnpmLockEntry{}, "javascript-pnpm-lock-entry"),
 	jsonNames(pkg.PEBinary{}, "pe-binary"),
 	jsonNames(pkg.PhpComposerLockEntry{}, "php-composer-lock-entry", "PhpComposerJsonMetadata"),
 	jsonNamesWithoutLookup(pkg.PhpComposerInstalledEntry{}, "php-composer-installed-entry", "PhpComposerJsonMetadata"), // the legacy value is split into two types, where the other is preferred
-	jsonNames(pkg.PhpPeclEntry{}, "php-pecl-entry", "PhpPeclMetadata"),
+	jsonNames(pkg.PhpPeclEntry{}, "php-pecl-entry", "PhpPeclMetadata"),                                                 //nolint:staticcheck
 	jsonNames(pkg.PhpPearEntry{}, "php-pear-entry"),
 	jsonNames(pkg.PortageEntry{}, "portage-db-entry", "PortageMetadata"),
 	jsonNames(pkg.PythonPackage{}, "python-package", "PythonPackageMetadata"),
@@ -123,6 +124,7 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.TerraformLockProviderEntry{}, "terraform-lock-provider-entry"),
 	jsonNames(pkg.DotnetPackagesLockEntry{}, "dotnet-packages-lock-entry"),
 	jsonNames(pkg.CondaMetaPackage{}, "conda-metadata-entry", "CondaPackageMetadata"),
+	jsonNames(pkg.GGUFFileHeader{}, "gguf-file-metadata"),
 )
 
 func expandLegacyNameVariants(names ...string) []string {

internal/spdxlicense/generate/generate_license_list.go

@@ -10,7 +10,6 @@ import (
 	"sort"
 	"strings"
 	"text/template"
-	"time"
 )
 
 // This program generates license_list.go.
@@ -20,8 +19,7 @@ const (
 )
 
 var tmp = template.Must(template.New("").Parse(`// Code generated by go generate; DO NOT EDIT.
-// This file was generated by robots at {{ .Timestamp }}
-// using data from {{ .URL }}
+// This file was generated using data from {{ .URL }}
 package spdxlicense
 
 const Version = {{ printf "%q" .Version }}
@@ -78,13 +76,11 @@ func run() error {
 	urlToLicense := buildURLToLicenseMap(result)
 
 	err = tmp.Execute(f, struct {
-		Timestamp    time.Time
 		URL          string
 		Version      string
 		LicenseIDs   map[string]string
 		URLToLicense map[string]string
 	}{
-		Timestamp:    time.Now(),
 		URL:          url,
 		Version:      result.Version,
 		LicenseIDs:   licenseIDs,

internal/task/package_tasks.go

@@ -3,6 +3,7 @@ package task
 import (
 	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/ai"
 	"github.com/anchore/syft/syft/pkg/cataloger/alpine"
 	"github.com/anchore/syft/syft/pkg/cataloger/arch"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
@@ -52,6 +53,9 @@ const (
 	JavaScript = "javascript"
 	Node       = "node"
 	NPM        = "npm"
+
+	// Python ecosystem labels
+	Python = "python"
 )
 
 //nolint:funlen
@@ -109,7 +113,7 @@ func DefaultPackageTaskFactories() Factories {
 			func(cfg CatalogingFactoryConfig) pkg.Cataloger {
 				return python.NewPackageCataloger(cfg.PackagesConfig.Python)
 			},
-			pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "python",
+			pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, Python,
 		),
 		newSimplePackageTaskFactory(ruby.NewGemFileLockCataloger, pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "ruby", "gem"),
 		newSimplePackageTaskFactory(ruby.NewGemSpecCataloger, pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "ruby", "gem", "gemspec"),
@@ -127,7 +131,7 @@ func DefaultPackageTaskFactories() Factories {
 			pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "dotnet", "c#",
 		),
 		newSimplePackageTaskFactory(dotnet.NewDotnetPackagesLockCataloger, pkgcataloging.DeclaredTag, pkgcataloging.ImageTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "dotnet", "c#"),
-		newSimplePackageTaskFactory(python.NewInstalledPackageCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.LanguageTag, "python"),
+		newSimplePackageTaskFactory(python.NewInstalledPackageCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.LanguageTag, Python),
 		newPackageTaskFactory(
 			func(cfg CatalogingFactoryConfig) pkg.Cataloger {
 				return golang.NewGoModuleBinaryCataloger(cfg.PackagesConfig.Golang)
@@ -175,12 +179,13 @@ func DefaultPackageTaskFactories() Factories {
 		newSimplePackageTaskFactory(homebrew.NewCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, "homebrew"),
 		newSimplePackageTaskFactory(conda.NewCondaMetaCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.PackageTag, "conda"),
 		newSimplePackageTaskFactory(snap.NewCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, "snap"),
+		newSimplePackageTaskFactory(ai.NewGGUFCataloger, pkgcataloging.DirectoryTag, pkgcataloging.ImageTag, "ai", "model", "gguf", "ml"),
 
 		// deprecated catalogers ////////////////////////////////////////
 		// these are catalogers that should not be selectable other than specific inclusion via name or "deprecated" tag (to remain backwards compatible)
-		newSimplePackageTaskFactory(dotnet.NewDotnetDepsCataloger, pkgcataloging.DeprecatedTag),               // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(dotnet.NewDotnetPortableExecutableCataloger, pkgcataloging.DeprecatedTag), // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(php.NewPeclCataloger, pkgcataloging.DeprecatedTag),                        // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(nix.NewStoreCataloger, pkgcataloging.DeprecatedTag),                       // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(dotnet.NewDotnetDepsCataloger, pkgcataloging.DeprecatedTag),               //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(dotnet.NewDotnetPortableExecutableCataloger, pkgcataloging.DeprecatedTag), //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(php.NewPeclCataloger, pkgcataloging.DeprecatedTag),                        //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(nix.NewStoreCataloger, pkgcataloging.DeprecatedTag),                       //nolint:staticcheck // TODO: remove in syft v2.0
 	}
 }

schema/json/schema-latest.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "anchore.io/schema/syft/json/16.0.41/document",
+  "$id": "anchore.io/schema/syft/json/16.0.43/document",
   "$ref": "#/$defs/Document",
   "$defs": {
     "AlpmDbEntry": {
@@ -130,7 +130,8 @@
           "description": "Digests contains file content hashes for integrity verification"
         }
       },
-      "type": "object"
+      "type": "object",
+      "description": "AlpmFileRecord represents a single file entry within an Arch Linux package with its associated metadata tracked by pacman."
     },
     "ApkDbEntry": {
       "properties": {
@@ -433,16 +434,19 @@
     "CPE": {
       "properties": {
         "cpe": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the CPE string identifier."
         },
         "source": {
-          "type": "string"
+          "type": "string",
+          "description": "Source is the source where this CPE was obtained or generated from."
         }
       },
       "type": "object",
       "required": [
         "cpe"
-      ]
+      ],
+      "description": "CPE represents a Common Platform Enumeration identifier used for matching packages to known vulnerabilities in security databases."
     },
     "ClassifierMatch": {
       "properties": {
@@ -747,19 +751,23 @@
     "Descriptor": {
       "properties": {
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the name of the tool that generated this SBOM (e.g., \"syft\")."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the version of the tool that generated this SBOM."
         },
-        "configuration": true
+        "configuration": {
+          "description": "Configuration contains the tool configuration used during SBOM generation."
+        }
       },
       "type": "object",
       "required": [
         "name",
         "version"
       ],
-      "description": "Descriptor describes what created the document as well as surrounding metadata"
+      "description": "Descriptor identifies the tool that generated this SBOM document, including its name, version, and configuration used during catalog generation."
     },
     "Digest": {
       "properties": {
@@ -1285,58 +1293,71 @@
     "File": {
       "properties": {
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is a unique identifier for this file within the SBOM."
         },
         "location": {
-          "$ref": "#/$defs/Coordinates"
+          "$ref": "#/$defs/Coordinates",
+          "description": "Location is the file path and layer information where this file was found."
         },
         "metadata": {
-          "$ref": "#/$defs/FileMetadataEntry"
+          "$ref": "#/$defs/FileMetadataEntry",
+          "description": "Metadata contains filesystem metadata such as permissions, ownership, and file type."
         },
         "contents": {
-          "type": "string"
+          "type": "string",
+          "description": "Contents is the file contents for small files."
         },
         "digests": {
           "items": {
             "$ref": "#/$defs/Digest"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Digests contains cryptographic hashes of the file contents."
         },
         "licenses": {
           "items": {
             "$ref": "#/$defs/FileLicense"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Licenses contains license information discovered within this file."
         },
         "executable": {
-          "$ref": "#/$defs/Executable"
+          "$ref": "#/$defs/Executable",
+          "description": "Executable contains executable metadata if this file is a binary."
         },
         "unknowns": {
           "items": {
             "type": "string"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Unknowns contains unknown fields for forward compatibility."
         }
       },
       "type": "object",
       "required": [
         "id",
         "location"
-      ]
+      ],
+      "description": "File represents a file discovered during cataloging with its metadata, content digests, licenses, and relationships to packages."
     },
     "FileLicense": {
       "properties": {
         "value": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the raw license identifier or text as found in the file."
         },
         "spdxExpression": {
-          "type": "string"
+          "type": "string",
+          "description": "SPDXExpression is the parsed SPDX license expression."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the license type classification (e.g., declared, concluded, discovered)."
         },
         "evidence": {
-          "$ref": "#/$defs/FileLicenseEvidence"
+          "$ref": "#/$defs/FileLicenseEvidence",
+          "description": "Evidence contains supporting evidence for this license detection."
         }
       },
       "type": "object",
@@ -1344,18 +1365,22 @@
         "value",
         "spdxExpression",
         "type"
-      ]
+      ],
+      "description": "FileLicense represents license information discovered within a file's contents or metadata, including the matched license text and SPDX expression."
     },
     "FileLicenseEvidence": {
       "properties": {
         "confidence": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Confidence is the confidence score for this license detection (0-100)."
         },
         "offset": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Offset is the byte offset where the license text starts in the file."
         },
         "extent": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Extent is the length of the license text in bytes."
         }
       },
       "type": "object",
@@ -1363,30 +1388,38 @@
         "confidence",
         "offset",
         "extent"
-      ]
+      ],
+      "description": "FileLicenseEvidence contains supporting evidence for a license detection in a file, including the byte offset, extent, and confidence level."
     },
     "FileMetadataEntry": {
       "properties": {
         "mode": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Mode is the Unix file permission mode in octal format."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the file type (e.g., \"RegularFile\", \"Directory\", \"SymbolicLink\")."
         },
         "linkDestination": {
-          "type": "string"
+          "type": "string",
+          "description": "LinkDestination is the target path for symbolic links."
         },
         "userID": {
-          "type": "integer"
+          "type": "integer",
+          "description": "UserID is the file owner user ID."
         },
         "groupID": {
-          "type": "integer"
+          "type": "integer",
+          "description": "GroupID is the file owner group ID."
         },
         "mimeType": {
-          "type": "string"
+          "type": "string",
+          "description": "MIMEType is the MIME type of the file contents."
         },
         "size": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Size is the file size in bytes."
         }
       },
       "type": "object",
@@ -1397,7 +1430,59 @@
         "groupID",
         "mimeType",
         "size"
-      ]
+      ],
+      "description": "FileMetadataEntry contains filesystem-level metadata attributes such as permissions, ownership, type, and size for a cataloged file."
+    },
+    "GgufFileMetadata": {
+      "properties": {
+        "ggufVersion": {
+          "type": "integer",
+          "description": "GGUFVersion is the GGUF format version (e.g., 3)"
+        },
+        "modelName": {
+          "type": "string",
+          "description": "ModelName is the name of the model (from general.name or filename)"
+        },
+        "fileSize": {
+          "type": "integer",
+          "description": "FileSize is the size of the GGUF file in bytes (best-effort if available from resolver)"
+        },
+        "license": {
+          "type": "string",
+          "description": "License is the license identifier (from general.license if present)"
+        },
+        "architecture": {
+          "type": "string",
+          "description": "Architecture is the model architecture (from general.architecture, e.g., \"qwen3moe\", \"llama\")"
+        },
+        "quantization": {
+          "type": "string",
+          "description": "Quantization is the quantization type (e.g., \"IQ4_NL\", \"Q4_K_M\")"
+        },
+        "parameters": {
+          "type": "integer",
+          "description": "Parameters is the number of model parameters (if present in header)"
+        },
+        "tensorCount": {
+          "type": "integer",
+          "description": "TensorCount is the number of tensors in the model"
+        },
+        "header": {
+          "type": "object",
+          "description": "Header contains the remaining key-value pairs from the GGUF header that are not already\nrepresented as typed fields above. This preserves additional metadata fields for reference\n(namespaced with general.*, llama.*, etc.) while avoiding duplication."
+        },
+        "metadataHash": {
+          "type": "string",
+          "description": "MetadataHash is a xx64 hash of all key-value pairs from the GGUF header metadata.\nThis hash is computed over the complete header metadata (including the fields extracted\ninto typed fields above) and provides a stable identifier for the model configuration\nacross different file locations or remotes. It allows matching identical models even\nwhen stored in different repositories or with different filenames."
+        }
+      },
+      "type": "object",
+      "required": [
+        "ggufVersion",
+        "modelName",
+        "tensorCount"
+      ],
+      "description": "GGUFFileHeader represents metadata extracted from a GGUF (GPT-Generated Unified Format) model file."
     },
     "GithubActionsUseStatement": {
       "properties": {
@@ -1545,7 +1630,8 @@
       "items": {
         "type": "string"
       },
-      "type": "array"
+      "type": "array",
+      "description": "IDLikes represents a list of distribution IDs that this Linux distribution is similar to or derived from, as defined in os-release ID_LIKE field."
     },
     "JavaArchive": {
       "properties": {
@@ -1876,15 +1962,48 @@
         "integrity": {
           "type": "string",
           "description": "Integrity is Subresource Integrity hash for verification using standard SRI format (sha512-... or sha1-...). npm changed from SHA-1 to SHA-512 in newer versions. For registry sources this is the integrity from registry, for remote tarballs it's SHA-512 of the file. npm verifies tarball matches this hash before unpacking, throwing EINTEGRITY error if mismatch detected."
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their version markers, i.e. \"lodash\": \"^1.0.0\""
         }
       },
       "type": "object",
       "required": [
         "resolved",
-        "integrity"
+        "integrity",
+        "dependencies"
       ],
       "description": "NpmPackageLockEntry represents a single entry within the \"packages\" section of a package-lock.json file."
     },
+    "JavascriptPnpmLockEntry": {
+      "properties": {
+        "resolution": {
+          "$ref": "#/$defs/PnpmLockResolution",
+          "description": "Resolution is the resolution information for the package"
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their versions"
+        }
+      },
+      "type": "object",
+      "required": [
+        "resolution",
+        "dependencies"
+      ],
+      "description": "PnpmLockEntry represents a single entry in the \"packages\" section of a pnpm-lock.yaml file."
+    },
     "JavascriptYarnLockEntry": {
       "properties": {
         "resolved": {
@@ -1894,12 +2013,22 @@
         "integrity": {
           "type": "string",
           "description": "Integrity is Subresource Integrity hash for verification (SRI format)"
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their versions"
         }
       },
       "type": "object",
       "required": [
         "resolved",
-        "integrity"
+        "integrity",
+        "dependencies"
       ],
       "description": "YarnLockEntry represents a single entry section of a yarn.lock file."
     },
@@ -1931,28 +2060,34 @@
     "License": {
       "properties": {
         "value": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the raw license identifier or expression as found."
         },
         "spdxExpression": {
-          "type": "string"
+          "type": "string",
+          "description": "SPDXExpression is the parsed SPDX license expression."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the license type classification (e.g., declared, concluded, discovered)."
         },
         "urls": {
           "items": {
             "type": "string"
           },
-          "type": "array"
+          "type": "array",
+          "description": "URLs are URLs where license text or information can be found."
         },
         "locations": {
           "items": {
             "$ref": "#/$defs/Location"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Locations are file locations where this license was discovered."
         },
         "contents": {
-          "type": "string"
+          "type": "string",
+          "description": "Contents is the full license text content."
         }
       },
       "type": "object",
@@ -1962,7 +2097,8 @@
         "type",
         "urls",
         "locations"
-      ]
+      ],
+      "description": "License represents software license information discovered for a package, including SPDX expressions and supporting evidence locations."
     },
     "LinuxKernelArchive": {
       "properties": {
@@ -2087,64 +2223,84 @@
     "LinuxRelease": {
       "properties": {
         "prettyName": {
-          "type": "string"
+          "type": "string",
+          "description": "PrettyName is a human-readable operating system name with version."
         },
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the operating system name without version information."
         },
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is the lower-case operating system identifier (e.g., \"ubuntu\", \"rhel\")."
         },
         "idLike": {
-          "$ref": "#/$defs/IDLikes"
+          "$ref": "#/$defs/IDLikes",
+          "description": "IDLike is a list of operating system IDs this distribution is similar to or derived from."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the operating system version including codename if available."
         },
         "versionID": {
-          "type": "string"
+          "type": "string",
+          "description": "VersionID is the operating system version number or identifier."
         },
         "versionCodename": {
-          "type": "string"
+          "type": "string",
+          "description": "VersionCodename is the operating system release codename (e.g., \"jammy\", \"bullseye\")."
         },
         "buildID": {
-          "type": "string"
+          "type": "string",
+          "description": "BuildID is a build identifier for the operating system."
         },
         "imageID": {
-          "type": "string"
+          "type": "string",
+          "description": "ImageID is an identifier for container or cloud images."
         },
         "imageVersion": {
-          "type": "string"
+          "type": "string",
+          "description": "ImageVersion is the version for container or cloud images."
         },
         "variant": {
-          "type": "string"
+          "type": "string",
+          "description": "Variant is the operating system variant name (e.g., \"Server\", \"Workstation\")."
         },
         "variantID": {
-          "type": "string"
+          "type": "string",
+          "description": "VariantID is the lower-case operating system variant identifier."
         },
         "homeURL": {
-          "type": "string"
+          "type": "string",
+          "description": "HomeURL is the homepage URL for the operating system."
         },
         "supportURL": {
-          "type": "string"
+          "type": "string",
+          "description": "SupportURL is the support or help URL for the operating system."
         },
         "bugReportURL": {
-          "type": "string"
+          "type": "string",
+          "description": "BugReportURL is the bug reporting URL for the operating system."
         },
         "privacyPolicyURL": {
-          "type": "string"
+          "type": "string",
+          "description": "PrivacyPolicyURL is the privacy policy URL for the operating system."
         },
         "cpeName": {
-          "type": "string"
+          "type": "string",
+          "description": "CPEName is the Common Platform Enumeration name for the operating system."
         },
         "supportEnd": {
-          "type": "string"
+          "type": "string",
+          "description": "SupportEnd is the end of support date or version identifier."
         },
         "extendedSupport": {
-          "type": "boolean"
+          "type": "boolean",
+          "description": "ExtendedSupport indicates whether extended security or support is available."
         }
       },
-      "type": "object"
+      "type": "object",
+      "description": "LinuxRelease contains Linux distribution identification and version information extracted from /etc/os-release or similar system files."
     },
     "Location": {
       "properties": {
@@ -2240,7 +2396,7 @@
         "product_id",
         "kb"
       ],
-      "description": "MicrosoftKbPatch is slightly odd in how it is expected to map onto data."
+      "description": "MicrosoftKbPatch represents a Windows Knowledge Base patch identifier associated with a specific Microsoft product from the MSRC (Microsoft Security Response Center)."
     },
     "NixDerivation": {
       "properties": {
@@ -2474,6 +2630,9 @@
             {
               "$ref": "#/$defs/ErlangRebarLockEntry"
             },
+            {
+              "$ref": "#/$defs/GgufFileMetadata"
+            },
             {
               "$ref": "#/$defs/GithubActionsUseStatement"
             },
@@ -2507,6 +2666,9 @@
             {
               "$ref": "#/$defs/JavascriptNpmPackageLockEntry"
             },
+            {
+              "$ref": "#/$defs/JavascriptPnpmLockEntry"
+            },
             {
               "$ref": "#/$defs/JavascriptYarnLockEntry"
             },
@@ -2958,6 +3120,19 @@
       ],
       "description": "PhpPeclEntry represents a single package entry found within php pecl metadata files."
     },
+    "PnpmLockResolution": {
+      "properties": {
+        "integrity": {
+          "type": "string",
+          "description": "Integrity is Subresource Integrity hash for verification (SRI format)"
+        }
+      },
+      "type": "object",
+      "required": [
+        "integrity"
+      ],
+      "description": "PnpmLockResolution contains package resolution metadata from pnpm lockfiles, including the integrity hash used for verification."
+    },
     "PortageDbEntry": {
       "properties": {
         "installedSize": {
@@ -3443,22 +3618,28 @@
     "Relationship": {
       "properties": {
         "parent": {
-          "type": "string"
+          "type": "string",
+          "description": "Parent is the ID of the parent artifact in this relationship."
         },
         "child": {
-          "type": "string"
+          "type": "string",
+          "description": "Child is the ID of the child artifact in this relationship."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the relationship type (e.g., \"contains\", \"dependency-of\", \"ancestor-of\")."
         },
-        "metadata": true
+        "metadata": {
+          "description": "Metadata contains additional relationship-specific metadata."
+        }
       },
       "type": "object",
       "required": [
         "parent",
         "child",
         "type"
-      ]
+      ],
+      "description": "Relationship represents a directed relationship between two artifacts in the SBOM, such as package-contains-file or package-depends-on-package."
     },
     "RpmArchive": {
       "properties": {
@@ -3805,17 +3986,20 @@
     "Schema": {
       "properties": {
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the JSON schema version for this document format."
         },
         "url": {
-          "type": "string"
+          "type": "string",
+          "description": "URL is the URL to the JSON schema definition document."
         }
       },
       "type": "object",
       "required": [
         "version",
         "url"
-      ]
+      ],
+      "description": "Schema specifies the JSON schema version and URL reference that defines the structure and validation rules for this document format."
     },
     "SnapEntry": {
       "properties": {
@@ -3853,21 +4037,28 @@
     "Source": {
       "properties": {
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is a unique identifier for the analyzed source artifact."
         },
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the name of the analyzed artifact (e.g., image name, directory path)."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the version of the analyzed artifact (e.g., image tag)."
         },
         "supplier": {
-          "type": "string"
+          "type": "string",
+          "description": "Supplier is supplier information, which can be user-provided for NTIA minimum elements compliance."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the source type (e.g., \"image\", \"directory\", \"file\")."
         },
-        "metadata": true
+        "metadata": {
+          "description": "Metadata contains additional source-specific metadata."
+        }
       },
       "type": "object",
       "required": [
@@ -3877,7 +4068,7 @@
         "type",
         "metadata"
       ],
-      "description": "Instead, the Supplier can be determined by the user of syft and passed as a config or flag to help fulfill the NTIA minimum elements."
+      "description": "Source represents the artifact that was analyzed to generate this SBOM, such as a container image, directory, or file archive."
     },
     "SwiftPackageManagerLockEntry": {
       "properties": {

syft/create_sbom_config.go

@@ -15,6 +15,7 @@ import (
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
+	"github.com/anchore/syft/syft/source/ocimodelsource"
 )
 
 // CreateSBOMConfig specifies all parameters needed for creating an SBOM.
@@ -483,6 +484,9 @@ func findDefaultTags(src source.Description) ([]string, error) {
 		return []string{pkgcataloging.DirectoryTag, filecataloging.FileTag}, nil
 	case source.SnapMetadata:
 		return []string{pkgcataloging.InstalledTag, filecataloging.FileTag}, nil
+	case *ocimodelsource.OCIModelMetadata:
+		// OCI model artifacts should use image-like catalogers since they provide files to scan
+		return []string{pkgcataloging.ImageTag, filecataloging.FileTag}, nil
 	default:
 		return nil, fmt.Errorf("unable to determine default cataloger tag for source type=%T", m)
 	}

syft/format/cpes/decoder.go

@@ -0,0 +1,95 @@
+package cpes
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"io"
+	"strings"
+
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/cpe"
+	"github.com/anchore/syft/syft/format/internal"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+const ID sbom.FormatID = "cpes"
+const version = "1"
+
+var _ sbom.FormatDecoder = (*decoder)(nil)
+
+type decoder struct{}
+
+func NewFormatDecoder() sbom.FormatDecoder {
+	return decoder{}
+}
+
+func (d decoder) Decode(r io.Reader) (*sbom.SBOM, sbom.FormatID, string, error) {
+	if r == nil {
+		return nil, "", "", fmt.Errorf("no reader provided")
+	}
+	s, err := toSyftModel(r)
+	return s, ID, version, err
+}
+
+func (d decoder) Identify(r io.Reader) (sbom.FormatID, string) {
+	if r == nil {
+		return "", ""
+	}
+
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if line == "" {
+			// skip whitespace only lines
+			continue
+		}
+
+		err := cpe.ValidateString(line)
+		if err != nil {
+			return "", ""
+		}
+
+		return ID, version
+	}
+
+	return "", ""
+}
+
+func toSyftModel(r io.Reader) (*sbom.SBOM, error) {
+	var errs []error
+	pkgs := pkg.NewCollection()
+
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+
+		if line == "" {
+			continue
+		}
+
+		// skip invalid CPEs
+		c, err := cpe.New(line, "")
+		if err != nil {
+			log.WithFields("error", err, "line", line).Debug("unable to parse cpe")
+			continue
+		}
+
+		p := pkg.Package{
+			Name:    c.Attributes.Product,
+			Version: c.Attributes.Version,
+			CPEs:    []cpe.CPE{c},
+		}
+
+		internal.Backfill(&p)
+		p.SetID()
+		pkgs.Add(p)
+	}
+
+	return &sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			Packages: pkgs,
+		},
+	}, errors.Join(errs...)
+}

syft/format/cpes/decoder_test.go

@@ -0,0 +1,171 @@
+package cpes
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/syft/cpe"
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+func Test_CPEProvider(t *testing.T) {
+	tests := []struct {
+		name      string
+		userInput string
+		sbom      *sbom.SBOM
+	}{
+		{
+			name:      "takes a single cpe",
+			userInput: "cpe:/a:apache:log4j:2.14.1",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name:    "log4j",
+						Version: "2.14.1",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:/a:apache:log4j:2.14.1", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name: "takes multiple cpes",
+			userInput: `cpe:/a:apache:log4j:2.14.1
+						cpe:2.3:a:f5:nginx:*:*:*:*:*:*:*:*;
+						cpe:2.3:a:f5:nginx:0.5.2:*:*:*:*:*:*:*;
+						cpe:2.3:a:f5:nginx:0.5.3:*:*:*:*:*:*:*;`,
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(
+						pkg.Package{
+							Name:    "log4j",
+							Version: "2.14.1",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:/a:apache:log4j:2.14.1", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:*:*:*:*:*:*:*:*;", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "0.5.2",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:0.5.2:*:*:*:*:*:*:*;", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "0.5.3",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:0.5.3:*:*:*:*:*:*:*;", ""),
+							},
+						},
+					),
+				},
+			},
+		},
+		{
+			name:      "takes cpe with no version",
+			userInput: "cpe:/a:apache:log4j",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "log4j",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:/a:apache:log4j", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "takes CPE 2.3 format",
+			userInput: "cpe:2.3:a:apache:log4j:2.14.1:*:*:*:*:*:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name:    "log4j",
+						Version: "2.14.1",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:apache:log4j:2.14.1:*:*:*:*:*:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "deduces target SW from CPE - known target_sw",
+			userInput: "cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "opensearch",
+						Type: pkg.GemPkg,
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "handles unknown target_sw CPE field",
+			userInput: "cpe:2.3:a:amazon:opensearch:*:*:*:*:*:loremipsum:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "opensearch",
+						Type: "",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:loremipsum:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "invalid prefix",
+			userInput: "dir:test-fixtures/cpe",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(),
+				},
+			},
+		},
+	}
+
+	syftPkgOpts := []cmp.Option{
+		cmpopts.IgnoreFields(pkg.Package{}, "id", "Language"),
+		cmpopts.IgnoreUnexported(pkg.Package{}, file.LocationSet{}, pkg.LicenseSet{}),
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			dec := NewFormatDecoder()
+
+			decodedSBOM, _, _, err := dec.Decode(strings.NewReader(tc.userInput))
+			require.NoError(t, err)
+
+			gotSyftPkgs := decodedSBOM.Artifacts.Packages.Sorted()
+			wantSyftPkgs := tc.sbom.Artifacts.Packages.Sorted()
+			require.Equal(t, len(gotSyftPkgs), len(wantSyftPkgs))
+			for idx, wantPkg := range wantSyftPkgs {
+				if d := cmp.Diff(wantPkg, gotSyftPkgs[idx], syftPkgOpts...); d != "" {
+					t.Errorf("unexpected Syft Package (-want +got):\n%s", d)
+				}
+			}
+		})
+	}
+}

syft/format/decoders.go

@@ -3,6 +3,7 @@ package format
 import (
 	"io"
 
+	"github.com/anchore/syft/syft/format/cpes"
 	"github.com/anchore/syft/syft/format/cyclonedxjson"
 	"github.com/anchore/syft/syft/format/cyclonedxxml"
 	"github.com/anchore/syft/syft/format/purls"
@@ -26,6 +27,7 @@ func Decoders() []sbom.FormatDecoder {
 		spdxtagvalue.NewFormatDecoder(),
 		spdxjson.NewFormatDecoder(),
 		purls.NewFormatDecoder(),
+		cpes.NewFormatDecoder(),
 	}
 }
 

syft/format/github/internal/model/model.go

@@ -87,6 +87,9 @@ func toGithubManifests(s *sbom.SBOM) Manifests {
 		}
 
 		name := dependencyName(p)
+		if name == "" || p.PURL == "" {
+			continue
+		}
 		manifest.Resolved[name] = DependencyNode{
 			PackageURL:   p.PURL,
 			Metadata:     toDependencyMetadata(p),

syft/format/github/test-fixtures/snapshot/TestGithubDirectoryEncoder.golden

@@ -16,11 +16,6 @@
         "source_location": "redacted/some/path/some/path/pkg1"
       },
       "resolved": {
-        "": {
-          "package_url": "a-purl-2",
-          "relationship": "direct",
-          "scope": "runtime"
-        },
         "pkg:deb/debian/package-2@2.0.1": {
           "package_url": "pkg:deb/debian/package-2@2.0.1",
           "relationship": "direct",

syft/format/github/test-fixtures/snapshot/TestGithubImageEncoder.golden

@@ -17,13 +17,6 @@
       },
       "metadata": {
         "syft:filesystem":"redacted"
-      },
-      "resolved": {
-        "": {
-          "package_url": "a-purl-1",
-          "relationship": "direct",
-          "scope": "runtime"
-        }
       }
     },
     "user-image-input:/somefile-2.txt": {

syft/format/internal/backfill.go

@@ -10,13 +10,31 @@ import (
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/pkg"
+	cataloger "github.com/anchore/syft/syft/pkg/cataloger/common/cpe"
 )
 
 // Backfill takes all information present in the package and attempts to fill in any missing information
-// from any available sources, such as the Metadata and PURL.
+// from any available sources, such as the Metadata, PURL, or CPEs.
 //
 // Backfill does not call p.SetID(), but this needs to be called later to ensure it's up to date
 func Backfill(p *pkg.Package) {
+	backfillFromPurl(p)
+	backfillFromCPE(p)
+}
+
+func backfillFromCPE(p *pkg.Package) {
+	if len(p.CPEs) == 0 {
+		return
+	}
+
+	c := p.CPEs[0]
+
+	if p.Type == "" {
+		p.Type = cataloger.TargetSoftwareToPackageType(c.Attributes.TargetSW)
+	}
+}
+
+func backfillFromPurl(p *pkg.Package) {
 	if p.PURL == "" {
 		return
 	}
@@ -29,6 +47,7 @@ func Backfill(p *pkg.Package) {
 
 	var cpes []cpe.CPE
 	epoch := ""
+	rpmmod := ""
 
 	for _, qualifier := range purl.Qualifiers {
 		switch qualifier.Key {
@@ -44,6 +63,8 @@ func Backfill(p *pkg.Package) {
 			}
 		case pkg.PURLQualifierEpoch:
 			epoch = qualifier.Value
+		case pkg.PURLQualifierRpmModularity:
+			rpmmod = qualifier.Value
 		}
 	}
 
@@ -63,6 +84,10 @@ func Backfill(p *pkg.Package) {
 		setJavaMetadataFromPurl(p, purl)
 	}
 
+	if p.Type == pkg.RpmPkg {
+		setRpmMetadataFromPurl(p, rpmmod)
+	}
+
 	for _, c := range cpes {
 		if slices.Contains(p.CPEs, c) {
 			continue
@@ -82,6 +107,35 @@ func setJavaMetadataFromPurl(p *pkg.Package, _ packageurl.PackageURL) {
 	}
 }
 
+func setRpmMetadataFromPurl(p *pkg.Package, rpmmod string) {
+	if p.Type != pkg.RpmPkg {
+		return
+	}
+	if rpmmod == "" {
+		return
+	}
+
+	if p.Metadata == nil {
+		p.Metadata = pkg.RpmDBEntry{
+			ModularityLabel: &rpmmod,
+		}
+		return
+	}
+
+	switch m := p.Metadata.(type) {
+	case pkg.RpmDBEntry:
+		if m.ModularityLabel == nil {
+			m.ModularityLabel = &rpmmod
+			p.Metadata = m
+		}
+	case pkg.RpmArchive:
+		if m.ModularityLabel == nil {
+			m.ModularityLabel = &rpmmod
+			p.Metadata = m
+		}
+	}
+}
+
 func setVersionFromPurl(p *pkg.Package, purl packageurl.PackageURL, epoch string) {
 	if p.Version == "" {
 		p.Version = purl.Version

syft/format/internal/backfill_test.go

@@ -53,6 +53,21 @@ func Test_Backfill(t *testing.T) {
 				Version: "1:1.12.8-26.el8",
 			},
 		},
+		{
+			name: "rpm with rpmmod",
+			in: pkg.Package{
+				PURL: "pkg:rpm/redhat/httpd@2.4.37-51?arch=x86_64&distro=rhel-8.7&rpmmod=httpd:2.4",
+			},
+			expected: pkg.Package{
+				PURL:    "pkg:rpm/redhat/httpd@2.4.37-51?arch=x86_64&distro=rhel-8.7&rpmmod=httpd:2.4",
+				Type:    pkg.RpmPkg,
+				Name:    "httpd",
+				Version: "2.4.37-51",
+				Metadata: pkg.RpmDBEntry{
+					ModularityLabel: strRef("httpd:2.4"),
+				},
+			},
+		},
 		{
 			name: "bad cpe",
 			in: pkg.Package{
@@ -106,6 +121,20 @@ func Test_Backfill(t *testing.T) {
 				Metadata: pkg.JavaArchive{},
 			},
 		},
+		{
+			name: "target-sw from CPE",
+			in: pkg.Package{
+				CPEs: []cpe.CPE{
+					cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+				},
+			},
+			expected: pkg.Package{
+				CPEs: []cpe.CPE{
+					cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+				},
+				Type: pkg.GemPkg,
+			},
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -171,3 +200,7 @@ func Test_nameFromPurl(t *testing.T) {
 		})
 	}
 }
+
+func strRef(s string) *string {
+	return &s
+}

syft/format/internal/cyclonedxutil/helpers/component.go

@@ -40,8 +40,11 @@ func EncodeComponent(p pkg.Package, supplier string, locationSorter func(a, b fi
 	}
 
 	componentType := cyclonedx.ComponentTypeLibrary
-	if p.Type == pkg.BinaryPkg {
+	switch p.Type {
+	case pkg.BinaryPkg:
 		componentType = cyclonedx.ComponentTypeApplication
+	case pkg.ModelPkg:
+		componentType = cyclonedx.ComponentTypeMachineLearningModel
 	}
 
 	return cyclonedx.Component{

syft/format/internal/cyclonedxutil/helpers/decoder.go

@@ -62,7 +62,7 @@ func collectPackages(component *cyclonedx.Component, s *sbom.SBOM, idMap map[str
 	switch component.Type {
 	case cyclonedx.ComponentTypeOS:
 	case cyclonedx.ComponentTypeContainer:
-	case cyclonedx.ComponentTypeApplication, cyclonedx.ComponentTypeFramework, cyclonedx.ComponentTypeLibrary:
+	case cyclonedx.ComponentTypeApplication, cyclonedx.ComponentTypeFramework, cyclonedx.ComponentTypeLibrary, cyclonedx.ComponentTypeMachineLearningModel:
 		p := decodeComponent(component)
 		idMap[component.BOMRef] = p
 		if component.BOMRef != "" {

syft/format/internal/spdxutil/helpers/originator_supplier_test.go

@@ -40,6 +40,7 @@ func Test_OriginatorSupplier(t *testing.T) {
 		pkg.PhpComposerInstalledEntry{},
 		pkg.PhpPearEntry{},
 		pkg.PhpPeclEntry{},
+		pkg.PnpmLockEntry{},
 		pkg.PortageEntry{},
 		pkg.PythonPipfileLockEntry{},
 		pkg.PythonPdmLockEntry{},
@@ -54,6 +55,7 @@ func Test_OriginatorSupplier(t *testing.T) {
 		pkg.OpamPackage{},
 		pkg.YarnLockEntry{},
 		pkg.TerraformLockProviderEntry{},
+		pkg.GGUFFileHeader{},
 	)
 	tests := []struct {
 		name       string

syft/format/internal/spdxutil/helpers/source_info.go

@@ -82,6 +82,8 @@ func SourceInfo(p pkg.Package) string {
 		answer = "acquired package info from Homebrew formula"
 	case pkg.TerraformPkg:
 		answer = "acquired package info from Terraform dependency lock file"
+	case pkg.ModelPkg:
+		answer = "acquired package info from AI artifact (e.g. GGUF File)"
 	default:
 		answer = "acquired package info from the following paths"
 	}

syft/format/internal/spdxutil/helpers/source_info_test.go

@@ -351,6 +351,14 @@ func Test_SourceInfo(t *testing.T) {
 				"acquired package info from Terraform dependency lock file",
 			},
 		},
+		{
+			input: pkg.Package{
+				Type: pkg.ModelPkg,
+			},
+			expected: []string{
+				"",
+			},
+		},
 	}
 	var pkgTypes []pkg.Type
 	for _, test := range tests {

syft/format/syftjson/model/document.go

@@ -35,14 +35,23 @@ func (d *Document) UnmarshalJSON(data []byte) error {
 	return nil
 }
 
-// Descriptor describes what created the document as well as surrounding metadata
+// Descriptor identifies the tool that generated this SBOM document, including its name, version, and configuration used during catalog generation.
 type Descriptor struct {
+	// Name is the name of the tool that generated this SBOM (e.g., "syft").
 	Name string `json:"name"`
+
+	// Version is the version of the tool that generated this SBOM.
 	Version string `json:"version"`
+
+	// Configuration contains the tool configuration used during SBOM generation.
 	Configuration interface{} `json:"configuration,omitempty"`
 }
 
+// Schema specifies the JSON schema version and URL reference that defines the structure and validation rules for this document format.
 type Schema struct {
+	// Version is the JSON schema version for this document format.
 	Version string `json:"version"`
+
+	// URL is the URL to the JSON schema definition document.
 	URL string `json:"url"`
 }

syft/format/syftjson/model/file.go

@@ -10,24 +10,54 @@ import (
 	"github.com/anchore/syft/syft/license"
 )
 
+// File represents a file discovered during cataloging with its metadata, content digests, licenses, and relationships to packages.
 type File struct {
+	// ID is a unique identifier for this file within the SBOM.
 	ID string `json:"id"`
+
+	// Location is the file path and layer information where this file was found.
 	Location file.Coordinates `json:"location"`
+
+	// Metadata contains filesystem metadata such as permissions, ownership, and file type.
 	Metadata *FileMetadataEntry `json:"metadata,omitempty"`
+
+	// Contents is the file contents for small files.
 	Contents string `json:"contents,omitempty"`
+
+	// Digests contains cryptographic hashes of the file contents.
 	Digests []file.Digest `json:"digests,omitempty"`
+
+	// Licenses contains license information discovered within this file.
 	Licenses []FileLicense `json:"licenses,omitempty"`
+
+	// Executable contains executable metadata if this file is a binary.
 	Executable *file.Executable `json:"executable,omitempty"`
+
+	// Unknowns contains unknown fields for forward compatibility.
 	Unknowns []string `json:"unknowns,omitempty"`
 }
 
+// FileMetadataEntry contains filesystem-level metadata attributes such as permissions, ownership, type, and size for a cataloged file.
 type FileMetadataEntry struct {
+	// Mode is the Unix file permission mode in octal format.
 	Mode int `json:"mode"`
+
+	// Type is the file type (e.g., "RegularFile", "Directory", "SymbolicLink").
 	Type string `json:"type"`
+
+	// LinkDestination is the target path for symbolic links.
 	LinkDestination string `json:"linkDestination,omitempty"`
+
+	// UserID is the file owner user ID.
 	UserID int `json:"userID"`
+
+	// GroupID is the file owner group ID.
 	GroupID int `json:"groupID"`
+
+	// MIMEType is the MIME type of the file contents.
 	MIMEType string `json:"mimeType"`
+
+	// Size is the file size in bytes.
 	Size int64 `json:"size"`
 }
 
@@ -82,16 +112,30 @@ type sbomImportLegacyFileMetadataEntry struct {
 	Size            int64               `json:"Size"`
 }
 
+// FileLicense represents license information discovered within a file's contents or metadata, including the matched license text and SPDX expression.
 type FileLicense struct {
+	// Value is the raw license identifier or text as found in the file.
 	Value string `json:"value"`
+
+	// SPDXExpression is the parsed SPDX license expression.
 	SPDXExpression string `json:"spdxExpression"`
+
+	// Type is the license type classification (e.g., declared, concluded, discovered).
 	Type license.Type `json:"type"`
+
+	// Evidence contains supporting evidence for this license detection.
 	Evidence *FileLicenseEvidence `json:"evidence,omitempty"`
 }
 
+// FileLicenseEvidence contains supporting evidence for a license detection in a file, including the byte offset, extent, and confidence level.
 type FileLicenseEvidence struct {
+	// Confidence is the confidence score for this license detection (0-100).
 	Confidence int `json:"confidence"`
+
+	// Offset is the byte offset where the license text starts in the file.
 	Offset int `json:"offset"`
+
+	// Extent is the length of the license text in bytes.
 	Extent int `json:"extent"`
 }
 

syft/format/syftjson/model/linux_release.go

@@ -4,27 +4,66 @@ import (
 	"encoding/json"
 )
 
+// IDLikes represents a list of distribution IDs that this Linux distribution is similar to or derived from, as defined in os-release ID_LIKE field.
 type IDLikes []string
 
+// LinuxRelease contains Linux distribution identification and version information extracted from /etc/os-release or similar system files.
 type LinuxRelease struct {
+	// PrettyName is a human-readable operating system name with version.
 	PrettyName string `json:"prettyName,omitempty"`
+
+	// Name is the operating system name without version information.
 	Name string `json:"name,omitempty"`
+
+	// ID is the lower-case operating system identifier (e.g., "ubuntu", "rhel").
 	ID string `json:"id,omitempty"`
+
+	// IDLike is a list of operating system IDs this distribution is similar to or derived from.
 	IDLike IDLikes `json:"idLike,omitempty"`
+
+	// Version is the operating system version including codename if available.
 	Version string `json:"version,omitempty"`
+
+	// VersionID is the operating system version number or identifier.
 	VersionID string `json:"versionID,omitempty"`
+
+	// VersionCodename is the operating system release codename (e.g., "jammy", "bullseye").
 	VersionCodename string `json:"versionCodename,omitempty"`
+
+	// BuildID is a build identifier for the operating system.
 	BuildID string `json:"buildID,omitempty"`
+
+	// ImageID is an identifier for container or cloud images.
 	ImageID string `json:"imageID,omitempty"`
+
+	// ImageVersion is the version for container or cloud images.
 	ImageVersion string `json:"imageVersion,omitempty"`
+
+	// Variant is the operating system variant name (e.g., "Server", "Workstation").
 	Variant string `json:"variant,omitempty"`
+
+	// VariantID is the lower-case operating system variant identifier.
 	VariantID string `json:"variantID,omitempty"`
+
+	// HomeURL is the homepage URL for the operating system.
 	HomeURL string `json:"homeURL,omitempty"`
+
+	// SupportURL is the support or help URL for the operating system.
 	SupportURL string `json:"supportURL,omitempty"`
+
+	// BugReportURL is the bug reporting URL for the operating system.
 	BugReportURL string `json:"bugReportURL,omitempty"`
+
+	// PrivacyPolicyURL is the privacy policy URL for the operating system.
 	PrivacyPolicyURL string `json:"privacyPolicyURL,omitempty"`
+
+	// CPEName is the Common Platform Enumeration name for the operating system.
 	CPEName string `json:"cpeName,omitempty"`
+
+	// SupportEnd is the end of support date or version identifier.
 	SupportEnd string `json:"supportEnd,omitempty"`
+
+	// ExtendedSupport indicates whether extended security or support is available.
 	ExtendedSupport bool `json:"extendedSupport,omitempty"`
 }
 

syft/format/syftjson/model/package.go

@@ -36,21 +36,39 @@ type PackageBasicData struct {
 	PURL      string          `json:"purl"`
 }
 
+// cpes is a collection of Common Platform Enumeration identifiers for a package.
 type cpes []CPE
 
+// CPE represents a Common Platform Enumeration identifier used for matching packages to known vulnerabilities in security databases.
 type CPE struct {
+	// Value is the CPE string identifier.
 	Value string `json:"cpe"`
+
+	// Source is the source where this CPE was obtained or generated from.
 	Source string `json:"source,omitempty"`
 }
 
+// licenses is a collection of license findings associated with a package.
 type licenses []License
 
+// License represents software license information discovered for a package, including SPDX expressions and supporting evidence locations.
 type License struct {
+	// Value is the raw license identifier or expression as found.
 	Value string `json:"value"`
+
+	// SPDXExpression is the parsed SPDX license expression.
 	SPDXExpression string `json:"spdxExpression"`
+
+	// Type is the license type classification (e.g., declared, concluded, discovered).
 	Type license.Type `json:"type"`
+
+	// URLs are URLs where license text or information can be found.
 	URLs []string `json:"urls"`
+
+	// Locations are file locations where this license was discovered.
 	Locations []file.Location `json:"locations"`
+
+	// Contents is the full license text content.
 	Contents string `json:"contents,omitempty"`
 }
 

syft/format/syftjson/model/relationship.go

@@ -1,8 +1,16 @@
 package model
 
+// Relationship represents a directed relationship between two artifacts in the SBOM, such as package-contains-file or package-depends-on-package.
 type Relationship struct {
+	// Parent is the ID of the parent artifact in this relationship.
 	Parent string `json:"parent"`
+
+	// Child is the ID of the child artifact in this relationship.
 	Child string `json:"child"`
+
+	// Type is the relationship type (e.g., "contains", "dependency-of", "ancestor-of").
 	Type string `json:"type"`
+
+	// Metadata contains additional relationship-specific metadata.
 	Metadata interface{} `json:"metadata,omitempty"`
 }

syft/format/syftjson/model/source.go

@@ -11,18 +11,25 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
-// Source object represents the thing that was cataloged
-// Note: syft currently makes no claims or runs any logic to determine the Supplier field below
-
-// Instead, the Supplier can be determined by the user of syft and passed as a config or flag to help fulfill
-// the NTIA minimum elements. For mor information see the NTIA framing document below
-// https://www.ntia.gov/files/ntia/publications/framingsbom_20191112.pdf
+// Source represents the artifact that was analyzed to generate this SBOM, such as a container image, directory, or file archive.
+// The Supplier field can be provided by users to fulfill NTIA minimum elements requirements.
 type Source struct {
+	// ID is a unique identifier for the analyzed source artifact.
 	ID string `json:"id"`
+
+	// Name is the name of the analyzed artifact (e.g., image name, directory path).
 	Name string `json:"name"`
+
+	// Version is the version of the analyzed artifact (e.g., image tag).
 	Version string `json:"version"`
+
+	// Supplier is supplier information, which can be user-provided for NTIA minimum elements compliance.
 	Supplier string `json:"supplier,omitempty"`
+
+	// Type is the source type (e.g., "image", "directory", "file").
 	Type string `json:"type"`
+
+	// Metadata contains additional source-specific metadata.
 	Metadata interface{} `json:"metadata"`
 }
 

syft/internal/fileresolver/directory.go

@@ -19,16 +19,16 @@ type Directory struct {
 	indexer *directoryIndexer
 }
 
-func NewFromDirectory(root string, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
-	r, err := newFromDirectoryWithoutIndex(root, base, pathFilters...)
+func NewFromDirectory(root, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
+	resolver, err := newFromDirectoryWithoutIndex(root, base, pathFilters...)
 	if err != nil {
 		return nil, err
 	}
 
-	return r, r.buildIndex()
+	return resolver, resolver.buildIndex()
 }
 
-func newFromDirectoryWithoutIndex(root string, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
+func newFromDirectoryWithoutIndex(root, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
 	chroot, err := NewChrootContextFromCWD(root, base)
 	if err != nil {
 		return nil, fmt.Errorf("unable to interpret chroot context: %w", err)
@@ -66,6 +66,6 @@ func (r *Directory) buildIndex() error {
 }
 
 // Stringer to represent a directory path data source
-func (r Directory) String() string {
+func (r *Directory) String() string {
 	return fmt.Sprintf("dir:%s", r.path)
 }

syft/internal/fileresolver/file.go

@@ -17,17 +17,31 @@ type File struct {
 	indexer *fileIndexer
 }
 
-// parent should be the symlink free absolute path to the parent directory
+// NewFromFile single file analyser
 // path is the filepath of the file we're creating content access for
-func NewFromFile(parent, path string, pathFilters ...PathIndexVisitor) (*File, error) {
-	chroot, err := NewChrootContextFromCWD(parent, parent)
+func NewFromFile(path string, pathFilters ...PathIndexVisitor) (*File, error) {
+	resolver, err := newFromFileWithoutIndex(path, pathFilters...)
+	if err != nil {
+		return nil, err
+	}
+
+	return resolver, resolver.buildIndex()
+}
+
+func newFromFileWithoutIndex(path string, pathFilters ...PathIndexVisitor) (*File, error) {
+	absParentDir, err := absoluteSymlinkFreePathToParent(path)
+	if err != nil {
+		return nil, err
+	}
+
+	chroot, err := NewChrootContextFromCWD(absParentDir, absParentDir)
 	if err != nil {
 		return nil, fmt.Errorf("unable to interpret chroot context: %w", err)
 	}
 
 	cleanBase := chroot.Base()
 
-	file := &File{
+	return &File{
 		path: path,
 		FiletreeResolver: FiletreeResolver{
 			Chroot: *chroot,
@@ -36,9 +50,7 @@ func NewFromFile(parent, path string, pathFilters ...PathIndexVisitor) (*File, e
 			Opener: nativeOSFileOpener,
 		},
 		indexer: newFileIndexer(path, cleanBase, pathFilters...),
-	}
-
-	return file, file.buildIndex()
+	}, nil
 }
 
 func (r *File) buildIndex() error {
@@ -58,6 +70,6 @@ func (r *File) buildIndex() error {
 }
 
 // Stringer to represent a file path data source
-func (r File) String() string {
+func (r *File) String() string {
 	return fmt.Sprintf("file:%s", r.path)
 }

syft/internal/fileresolver/filetree_resolver_test.go

@@ -1384,9 +1384,10 @@ func TestFileResolver_FilesByPath(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, tt.filePath)
+			resolver, err := NewFromFile(tt.filePath)
 			require.NoError(t, err)
 			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 			refs, err := resolver.FilesByPath(tt.fileByPathInput)
 			require.NoError(t, err)
@@ -1431,8 +1432,11 @@ func TestFileResolver_MultipleFilesByPath(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, filePath)
+			resolver, err := NewFromFile(filePath)
 			assert.NoError(t, err)
+			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 			refs, err := resolver.FilesByPath(tt.input...)
 			assert.NoError(t, err)
 
@@ -1449,8 +1453,11 @@ func TestFileResolver_FilesByGlob(t *testing.T) {
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
 
-	resolver, err := NewFromFile(parentPath, filePath)
+	resolver, err := NewFromFile(filePath)
 	assert.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 	refs, err := resolver.FilesByGlob("**/*.txt")
 	assert.NoError(t, err)
 
@@ -1476,8 +1483,11 @@ func Test_fileResolver_FilesByMIMEType(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, filePath)
+			resolver, err := NewFromFile(filePath)
 			assert.NoError(t, err)
+			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 			locations, err := resolver.FilesByMIMEType(test.mimeType)
 			assert.NoError(t, err)
 			assert.Equal(t, test.expectedPaths.Size(), len(locations))
@@ -1497,10 +1507,12 @@ func Test_fileResolver_FileContentsByLocation(t *testing.T) {
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
 
-	r, err := NewFromFile(parentPath, filePath)
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
-	exists, existingPath, err := r.Tree.File(stereoscopeFile.Path(filepath.Join(cwd, "test-fixtures/image-simple/file-1.txt")))
+	exists, existingPath, err := resolver.Tree.File(stereoscopeFile.Path(filepath.Join(cwd, "test-fixtures/image-simple/file-1.txt")))
 	require.True(t, exists)
 	require.NoError(t, err)
 	require.True(t, existingPath.HasReference())
@@ -1525,7 +1537,7 @@ func Test_fileResolver_FileContentsByLocation(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 
-			actual, err := r.FileContentsByLocation(test.location)
+			actual, err := resolver.FileContentsByLocation(test.location)
 			if test.err {
 				require.Error(t, err)
 				return
@@ -1546,8 +1558,11 @@ func TestFileResolver_AllLocations_errorOnDirRequest(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	var dirLoc *file.Location
 	ctx, cancel := context.WithCancel(context.Background())
@@ -1575,8 +1590,11 @@ func TestFileResolver_AllLocations(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	paths := strset.New()
 	for loc := range resolver.AllLocations(context.Background()) {
@@ -1600,8 +1618,11 @@ func Test_FileResolver_AllLocationsDoesNotLeakGoRoutine(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	require.NoError(t, err)
 	ctx, cancel := context.WithCancel(context.Background())

syft/internal/fileresolver/metadata_test.go

@@ -4,9 +4,10 @@ import (
 	"os"
 	"testing"
 
-	"github.com/anchore/stereoscope/pkg/file"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/stereoscope/pkg/file"
 )
 
 func TestFileMetadataFromPath(t *testing.T) {

syft/pkg/alpm.go

@@ -58,6 +58,7 @@ type AlpmDBEntry struct {
 	Depends []string `mapstructure:"depends" json:"depends,omitempty"`
 }
 
+// AlpmFileRecord represents a single file entry within an Arch Linux package with its associated metadata tracked by pacman.
 type AlpmFileRecord struct {
 	// Path is the file path relative to the filesystem root
 	Path string `mapstruture:"path" json:"path,omitempty"`

syft/pkg/cataloger/.gitignore

@@ -0,0 +1,2 @@
+# these are generated by pkgtest helpers, no need to check them in
+**/test-fixtures/test-observations.json

syft/pkg/cataloger/ai/cataloger.go

@@ -0,0 +1,16 @@
+/*
+Package ai provides concrete Cataloger implementations for AI artifacts and machine learning models,
+including support for GGUF (GPT-Generated Unified Format) model files.
+*/
+package ai
+
+import (
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+)
+
+// NewGGUFCataloger returns a new cataloger instance for GGUF model files.
+func NewGGUFCataloger() pkg.Cataloger {
+	return generic.NewCataloger("gguf-cataloger").
+		WithParserByGlobs(parseGGUFModel, "**/*.gguf")
+}

syft/pkg/cataloger/ai/cataloger_test.go

@@ -0,0 +1,107 @@
+package ai
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/google/go-cmp/cmp/cmpopts"
+
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/pkgtest"
+)
+
+func TestGGUFCataloger_Globs(t *testing.T) {
+	tests := []struct {
+		name     string
+		fixture  string
+		expected []string
+	}{
+		{
+			name:    "obtain gguf files",
+			fixture: "test-fixtures/glob-paths",
+			expected: []string{
+				"models/model.gguf",
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, test.fixture).
+				ExpectsResolverContentQueries(test.expected).
+				TestCataloger(t, NewGGUFCataloger())
+		})
+	}
+}
+
+func TestGGUFCataloger_Integration(t *testing.T) {
+	tests := []struct {
+		name                  string
+		setup                 func(t *testing.T) string
+		expectedPackages      []pkg.Package
+		expectedRelationships []artifact.Relationship
+	}{
+		{
+			name: "catalog single GGUF file",
+			setup: func(t *testing.T) string {
+				dir := t.TempDir()
+				data := newTestGGUFBuilder().
+					withVersion(3).
+					withStringKV("general.architecture", "llama").
+					withStringKV("general.name", "llama3-8b").
+					withStringKV("general.version", "3.0").
+					withStringKV("general.license", "Apache-2.0").
+					withStringKV("general.quantization", "Q4_K_M").
+					withUint64KV("general.parameter_count", 8030000000).
+					build()
+
+				path := filepath.Join(dir, "llama3-8b.gguf")
+				os.WriteFile(path, data, 0644)
+				return dir
+			},
+			expectedPackages: []pkg.Package{
+				{
+					Name:    "llama3-8b",
+					Version: "3.0",
+					Type:    pkg.ModelPkg,
+					Licenses: pkg.NewLicenseSet(
+						pkg.NewLicenseFromFields("Apache-2.0", "", nil),
+					),
+					Metadata: pkg.GGUFFileHeader{
+						ModelName:    "llama3-8b",
+						License:      "Apache-2.0",
+						Architecture: "llama",
+						Quantization: "Unknown",
+						Parameters:   0,
+						GGUFVersion:  3,
+						TensorCount:  0,
+						Header:       map[string]interface{}{},
+					},
+				},
+			},
+			expectedRelationships: nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			fixtureDir := tt.setup(t)
+
+			// Use pkgtest to catalog and compare
+			tester := pkgtest.NewCatalogTester().
+				FromDirectory(t, fixtureDir).
+				Expects(tt.expectedPackages, tt.expectedRelationships).
+				IgnoreLocationLayer().
+				IgnorePackageFields("FoundBy", "Locations"). // These are set by the cataloger
+				WithCompareOptions(
+					// Ignore MetadataHash as it's computed dynamically
+					cmpopts.IgnoreFields(pkg.GGUFFileHeader{}, "MetadataHash"),
+				)
+
+			tester.TestCataloger(t, NewGGUFCataloger())
+		})
+	}
+}

syft/pkg/cataloger/ai/package.go

@@ -0,0 +1,28 @@
+package ai
+
+import (
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func newGGUFPackage(metadata *pkg.GGUFFileHeader, version string, locations ...file.Location) pkg.Package {
+	p := pkg.Package{
+		Name:      metadata.ModelName,
+		Version:   version,
+		Locations: file.NewLocationSet(locations...),
+		Type:      pkg.ModelPkg,
+		Licenses:  pkg.NewLicenseSet(),
+		Metadata:  *metadata,
+		// NOTE: PURL is intentionally not set as the package-url spec
+		// has not yet finalized support for ML model packages
+	}
+
+	// Add license to the package if present in metadata
+	if metadata.License != "" {
+		p.Licenses.Add(pkg.NewLicenseFromFields(metadata.License, "", nil))
+	}
+
+	p.SetID()
+
+	return p
+}

syft/pkg/cataloger/ai/package_test.go

@@ -0,0 +1,123 @@
+package ai
+
+import (
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func TestNewGGUFPackage(t *testing.T) {
+	tests := []struct {
+		name      string
+		metadata  *pkg.GGUFFileHeader
+		version   string
+		locations []file.Location
+		checkFunc func(t *testing.T, p pkg.Package)
+	}{
+		{
+			name:    "complete GGUF package with all fields",
+			version: "3.0",
+			metadata: &pkg.GGUFFileHeader{
+				ModelName:    "llama3-8b-instruct",
+				License:      "Apache-2.0",
+				Architecture: "llama",
+				Quantization: "Q4_K_M",
+				Parameters:   8030000000,
+				GGUFVersion:  3,
+				TensorCount:  291,
+				Header:       map[string]any{},
+			},
+			locations: []file.Location{file.NewLocation("/models/llama3-8b.gguf")},
+			checkFunc: func(t *testing.T, p pkg.Package) {
+				if d := cmp.Diff("llama3-8b-instruct", p.Name); d != "" {
+					t.Errorf("Name mismatch (-want +got):\n%s", d)
+				}
+				if d := cmp.Diff("3.0", p.Version); d != "" {
+					t.Errorf("Version mismatch (-want +got):\n%s", d)
+				}
+				if d := cmp.Diff(pkg.ModelPkg, p.Type); d != "" {
+					t.Errorf("Type mismatch (-want +got):\n%s", d)
+				}
+				assert.Empty(t, p.PURL, "PURL should not be set for model packages")
+				assert.Len(t, p.Licenses.ToSlice(), 1)
+				if d := cmp.Diff("Apache-2.0", p.Licenses.ToSlice()[0].Value); d != "" {
+					t.Errorf("License value mismatch (-want +got):\n%s", d)
+				}
+				assert.NotEmpty(t, p.ID())
+			},
+		},
+		{
+			name:    "minimal GGUF package",
+			version: "1.0",
+			metadata: &pkg.GGUFFileHeader{
+				ModelName:    "simple-model",
+				Architecture: "gpt2",
+				GGUFVersion:  3,
+				TensorCount:  50,
+			},
+			locations: []file.Location{file.NewLocation("/models/simple.gguf")},
+			checkFunc: func(t *testing.T, p pkg.Package) {
+				if d := cmp.Diff("simple-model", p.Name); d != "" {
+					t.Errorf("Name mismatch (-want +got):\n%s", d)
+				}
+				if d := cmp.Diff("1.0", p.Version); d != "" {
+					t.Errorf("Version mismatch (-want +got):\n%s", d)
+				}
+				if d := cmp.Diff(pkg.ModelPkg, p.Type); d != "" {
+					t.Errorf("Type mismatch (-want +got):\n%s", d)
+				}
+				assert.Empty(t, p.PURL, "PURL should not be set for model packages")
+				assert.Empty(t, p.Licenses.ToSlice())
+			},
+		},
+		{
+			name:    "GGUF package with multiple locations",
+			version: "1.5",
+			metadata: &pkg.GGUFFileHeader{
+				ModelName:    "multi-location-model",
+				Architecture: "llama",
+				GGUFVersion:  3,
+				TensorCount:  150,
+			},
+			locations: []file.Location{
+				file.NewLocation("/models/model1.gguf"),
+				file.NewLocation("/models/model2.gguf"),
+			},
+			checkFunc: func(t *testing.T, p pkg.Package) {
+				assert.Len(t, p.Locations.ToSlice(), 2)
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			p := newGGUFPackage(tt.metadata, tt.version, tt.locations...)
+
+			if d := cmp.Diff(tt.metadata.ModelName, p.Name); d != "" {
+				t.Errorf("Name mismatch (-want +got):\n%s", d)
+			}
+			if d := cmp.Diff(tt.version, p.Version); d != "" {
+				t.Errorf("Version mismatch (-want +got):\n%s", d)
+			}
+			if d := cmp.Diff(pkg.ModelPkg, p.Type); d != "" {
+				t.Errorf("Type mismatch (-want +got):\n%s", d)
+			}
+
+			// Verify metadata is attached
+			metadata, ok := p.Metadata.(pkg.GGUFFileHeader)
+			require.True(t, ok, "metadata should be GGUFFileHeader")
+			if d := cmp.Diff(*tt.metadata, metadata); d != "" {
+				t.Errorf("Metadata mismatch (-want +got):\n%s", d)
+			}
+
+			if tt.checkFunc != nil {
+				tt.checkFunc(t, p)
+			}
+		})
+	}
+}

syft/pkg/cataloger/ai/parse_gguf.go

@@ -0,0 +1,74 @@
+package ai
+
+import (
+	"encoding/binary"
+	"fmt"
+	"io"
+
+	gguf_parser "github.com/gpustack/gguf-parser-go"
+)
+
+// GGUF file format constants
+const (
+	ggufMagicNumber = 0x46554747       // "GGUF" in little-endian
+	maxHeaderSize   = 50 * 1024 * 1024 // 50MB for large tokenizer vocabularies
+)
+
+// readHeader reads only the GGUF header (metadata) without reading tensor data
+// This is much more efficient than reading the entire file
+// The reader should be wrapped with io.LimitedReader to prevent OOM issues
+func readHeader(r io.Reader) ([]byte, error) {
+	// Read initial chunk to determine header size
+	// GGUF format: magic(4) + version(4) + tensor_count(8) + metadata_kv_count(8) + metadata_kvs + tensors_info
+	initialBuf := make([]byte, 24) // Enough for magic, version, tensor count, and kv count
+	if _, err := io.ReadFull(r, initialBuf); err != nil {
+		return nil, fmt.Errorf("failed to read GGUF header prefix: %w", err)
+	}
+
+	// Verify magic number
+	magic := binary.LittleEndian.Uint32(initialBuf[0:4])
+	if magic != ggufMagicNumber {
+		return nil, fmt.Errorf("invalid GGUF magic number: 0x%08X", magic)
+	}
+
+	// We need to read the metadata KV pairs to know the full header size
+	// The io.LimitedReader wrapping this reader ensures we don't read more than maxHeaderSize
+	headerData := make([]byte, 0, 1024*1024) // Start with 1MB capacity
+	headerData = append(headerData, initialBuf...)
+
+	// Read the rest of the header in larger chunks for efficiency
+	// The LimitedReader will return EOF once maxHeaderSize is reached
+	buf := make([]byte, 64*1024) // 64KB chunks
+	for {
+		n, err := r.Read(buf)
+		if n > 0 {
+			headerData = append(headerData, buf[:n]...)
+		}
+		if err == io.EOF {
+			// Reached end of file or limit, we have all available data
+			break
+		}
+		if err != nil {
+			return nil, fmt.Errorf("failed to read GGUF header: %w", err)
+		}
+	}
+
+	return headerData, nil
+}
+
+// Helper to convert gguf_parser metadata to simpler types
+func convertGGUFMetadataKVs(kvs gguf_parser.GGUFMetadataKVs) map[string]interface{} {
+	result := make(map[string]interface{})
+
+	for _, kv := range kvs {
+		// Skip standard fields that are extracted separately
+		switch kv.Key {
+		case "general.architecture", "general.name", "general.license",
+			"general.version", "general.parameter_count", "general.quantization":
+			continue
+		}
+		result[kv.Key] = kv.Value
+	}
+
+	return result
+}

syft/pkg/cataloger/ai/parse_gguf_model.go

@@ -0,0 +1,141 @@
+package ai
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	"github.com/cespare/xxhash/v2"
+	gguf_parser "github.com/gpustack/gguf-parser-go"
+
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/unknown"
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+)
+
+// parseGGUFModel parses a GGUF model file and returns the discovered package.
+// This implementation only reads the header portion of the file, not the entire model.
+func parseGGUFModel(_ context.Context, _ file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+	defer internal.CloseAndLogError(reader, reader.Path())
+
+	// Read and validate the GGUF file header using LimitedReader to prevent OOM
+	// We use LimitedReader to cap reads at maxHeaderSize (50MB)
+	limitedReader := &io.LimitedReader{R: reader, N: maxHeaderSize}
+	headerData, err := readHeader(limitedReader)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to read GGUF header: %w", err)
+	}
+
+	// Create a temporary file for the library to parse
+	// The library requires a file path, so we create a temp file
+	tempFile, err := os.CreateTemp("", "syft-gguf-*.gguf")
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to create temp file: %w", err)
+	}
+	tempPath := tempFile.Name()
+	defer os.Remove(tempPath)
+
+	// Write the validated header data to temp file
+	if _, err := tempFile.Write(headerData); err != nil {
+		tempFile.Close()
+		return nil, nil, fmt.Errorf("failed to write to temp file: %w", err)
+	}
+	tempFile.Close()
+
+	// Parse using gguf-parser-go with options to skip unnecessary data
+	ggufFile, err := gguf_parser.ParseGGUFFile(tempPath,
+		gguf_parser.SkipLargeMetadata(),
+	)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to parse GGUF file: %w", err)
+	}
+
+	// Extract metadata
+	metadata := ggufFile.Metadata()
+
+	// Extract version separately (will be set on Package.Version)
+	modelVersion := extractVersion(ggufFile.Header.MetadataKV)
+
+	// Convert to syft metadata structure
+	syftMetadata := &pkg.GGUFFileHeader{
+		ModelName:    metadata.Name,
+		License:      metadata.License,
+		Architecture: metadata.Architecture,
+		Quantization: metadata.FileTypeDescriptor,
+		Parameters:   uint64(metadata.Parameters),
+		GGUFVersion:  uint32(ggufFile.Header.Version),
+		TensorCount:  ggufFile.Header.TensorCount,
+		Header:       convertGGUFMetadataKVs(ggufFile.Header.MetadataKV),
+		MetadataHash: computeKVMetadataHash(ggufFile.Header.MetadataKV),
+	}
+
+	// If model name is not in metadata, use filename
+	if syftMetadata.ModelName == "" {
+		syftMetadata.ModelName = extractModelNameFromPath(reader.Path())
+	}
+
+	// Create package from metadata
+	p := newGGUFPackage(
+		syftMetadata,
+		modelVersion,
+		reader.WithAnnotation(pkg.EvidenceAnnotationKey, pkg.PrimaryEvidenceAnnotation),
+	)
+
+	return []pkg.Package{p}, nil, unknown.IfEmptyf([]pkg.Package{p}, "unable to parse GGUF file")
+}
+
+// computeKVMetadataHash computes a stable hash of the KV metadata for use as a global identifier
+func computeKVMetadataHash(metadata gguf_parser.GGUFMetadataKVs) string {
+	// Sort the KV pairs by key for stable hashing
+	sortedKVs := make([]gguf_parser.GGUFMetadataKV, len(metadata))
+	copy(sortedKVs, metadata)
+	sort.Slice(sortedKVs, func(i, j int) bool {
+		return sortedKVs[i].Key < sortedKVs[j].Key
+	})
+
+	// Marshal sorted KVs to JSON for stable hashing
+	jsonBytes, err := json.Marshal(sortedKVs)
+	if err != nil {
+		log.Debugf("failed to marshal metadata for hashing: %v", err)
+		return ""
+	}
+
+	// Compute xxhash
+	hash := xxhash.Sum64(jsonBytes)
+	return fmt.Sprintf("%016x", hash) // 16 hex chars (64 bits)
+}
+
+// extractVersion attempts to extract version from metadata KV pairs
+func extractVersion(kvs gguf_parser.GGUFMetadataKVs) string {
+	for _, kv := range kvs {
+		if kv.Key == "general.version" {
+			if v, ok := kv.Value.(string); ok && v != "" {
+				return v
+			}
+		}
+	}
+	return ""
+}
+
+// extractModelNameFromPath extracts the model name from the file path
+func extractModelNameFromPath(path string) string {
+	// Get the base filename
+	base := filepath.Base(path)
+
+	// Remove .gguf extension
+	name := strings.TrimSuffix(base, ".gguf")
+
+	return name
+}
+
+// integrity check
+var _ generic.Parser = parseGGUFModel

syft/pkg/cataloger/ai/test_builder_test.go

@@ -0,0 +1,41 @@
+package ai
+
+import (
+	"fmt"
+	"os"
+
+	gguf_parser "github.com/gpustack/gguf-parser-go"
+)
+
+func main() {
+	// Create a test GGUF file
+	data := newTestGGUFBuilder().
+		withVersion(3).
+		withStringKV("general.architecture", "llama").
+		withStringKV("general.name", "test-model").
+		build()
+
+	// Write to temp file
+	tempFile, err := os.CreateTemp("", "test-*.gguf")
+	if err != nil {
+		panic(err)
+	}
+	defer os.Remove(tempFile.Name())
+
+	if _, err := tempFile.Write(data); err != nil {
+		panic(err)
+	}
+	tempFile.Close()
+
+	fmt.Printf("Wrote %d bytes to %s\n", len(data), tempFile.Name())
+
+	// Try to parse it
+	fmt.Println("Attempting to parse...")
+	gf, err := gguf_parser.ParseGGUFFile(tempFile.Name(), gguf_parser.SkipLargeMetadata())
+	if err != nil {
+		fmt.Printf("Parse error: %v\n", err)
+		return
+	}
+
+	fmt.Printf("Success! Model: %s\n", gf.Metadata().Name)
+}

syft/pkg/cataloger/ai/test_helpers_test.go

@@ -0,0 +1,127 @@
+package ai
+
+import (
+	"bytes"
+	"encoding/binary"
+)
+
+// GGUF type constants for test builder
+const (
+	ggufMagic       = 0x46554747 // "GGUF" in little-endian
+	ggufTypeUint8   = 0
+	ggufTypeInt8    = 1
+	ggufTypeUint16  = 2
+	ggufTypeInt16   = 3
+	ggufTypeUint32  = 4
+	ggufTypeInt32   = 5
+	ggufTypeFloat32 = 6
+	ggufTypeBool    = 7
+	ggufTypeString  = 8
+	ggufTypeArray   = 9
+	ggufTypeUint64  = 10
+	ggufTypeInt64   = 11
+	ggufTypeFloat64 = 12
+)
+
+// testGGUFBuilder helps build GGUF files for testing
+type testGGUFBuilder struct {
+	buf         *bytes.Buffer
+	version     uint32
+	tensorCount uint64
+	kvPairs     []testKVPair
+}
+
+type testKVPair struct {
+	key       string
+	valueType uint32
+	value     interface{}
+}
+
+func newTestGGUFBuilder() *testGGUFBuilder {
+	return &testGGUFBuilder{
+		buf:         new(bytes.Buffer),
+		version:     3,
+		tensorCount: 0,
+		kvPairs:     []testKVPair{},
+	}
+}
+
+func (b *testGGUFBuilder) withVersion(v uint32) *testGGUFBuilder {
+	b.version = v
+	return b
+}
+
+func (b *testGGUFBuilder) withTensorCount(count uint64) *testGGUFBuilder {
+	b.tensorCount = count
+	return b
+}
+
+func (b *testGGUFBuilder) withStringKV(key, value string) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeString, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) withUint64KV(key string, value uint64) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeUint64, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) withUint32KV(key string, value uint32) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeUint32, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) writeString(s string) {
+	binary.Write(b.buf, binary.LittleEndian, uint64(len(s)))
+	b.buf.WriteString(s)
+}
+
+func (b *testGGUFBuilder) build() []byte {
+	// Write magic number "GGUF"
+	binary.Write(b.buf, binary.LittleEndian, uint32(ggufMagic))
+
+	// Write version
+	binary.Write(b.buf, binary.LittleEndian, b.version)
+
+	// Write tensor count
+	binary.Write(b.buf, binary.LittleEndian, b.tensorCount)
+
+	// Write KV count
+	binary.Write(b.buf, binary.LittleEndian, uint64(len(b.kvPairs)))
+
+	// Write KV pairs
+	for _, kv := range b.kvPairs {
+		// Write key
+		b.writeString(kv.key)
+		// Write value type
+		binary.Write(b.buf, binary.LittleEndian, kv.valueType)
+		// Write value based on type
+		switch kv.valueType {
+		case ggufTypeString:
+			b.writeString(kv.value.(string))
+		case ggufTypeUint32:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint32))
+		case ggufTypeUint64:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint64))
+		case ggufTypeUint8:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint8))
+		case ggufTypeInt32:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(int32))
+		case ggufTypeBool:
+			var v uint8
+			if kv.value.(bool) {
+				v = 1
+			}
+			binary.Write(b.buf, binary.LittleEndian, v)
+		}
+	}
+
+	return b.buf.Bytes()
+}
+
+// buildInvalidMagic creates a file with invalid magic number
+func (b *testGGUFBuilder) buildInvalidMagic() []byte {
+	buf := new(bytes.Buffer)
+	binary.Write(buf, binary.LittleEndian, uint32(0x12345678))
+	return buf.Bytes()
+}

syft/pkg/cataloger/binary/classifier_cataloger_test.go

@@ -1403,6 +1403,22 @@ func Test_Cataloger_PositiveCases(t *testing.T) {
 				Metadata:  metadata("ffmpeg-library"),
 			},
 		},
+		{
+			logicalFixture: "elixir/1.19.1/linux-amd64",
+			expected: pkg.Package{
+				Name:      "elixir",
+				Version:   "1.19.1",
+				Type:      "binary",
+				PURL:      "pkg:generic/elixir@1.19.1",
+				Locations: locations("elixir", "lib/elixir/ebin/elixir.app"),
+				Metadata: pkg.BinarySignature{
+					Matches: []pkg.ClassifierMatch{
+						match("elixir-binary", "elixir"),
+						match("elixir-library", "lib/elixir/ebin/elixir.app"),
+					},
+				},
+			},
+		},
 	}
 
 	for _, test := range tests {

syft/pkg/cataloger/binary/classifiers.go

@@ -663,6 +663,26 @@ func DefaultClassifiers() []binutils.Classifier {
 			PURL:    mustPURL("pkg:generic/ffmpeg@version"),
 			CPEs:    singleCPE("cpe:2.3:a:ffmpeg:ffmpeg:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
 		},
+		{
+			Class:    "elixir-binary",
+			FileGlob: "**/elixir",
+			EvidenceMatcher: m.FileContentsVersionMatcher(
+				`(?m)ELIXIR_VERSION=(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
+			Package: "elixir",
+			PURL:    mustPURL("pkg:generic/elixir@version"),
+			CPEs: []cpe.CPE{
+				cpe.Must("cpe:2.3:a:elixir-lang:elixir:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+			},
+		},
+		{
+			Class:    "elixir-library",
+			FileGlob: "**/elixir/ebin/elixir.app",
+			EvidenceMatcher: m.FileContentsVersionMatcher(
+				`(?m)\{vsn,"(?P<version>[0-9]+\.[0-9]+\.[0-9]+(-[a-z0-9]+)?)"\}`),
+			Package: "elixir",
+			PURL:    mustPURL("pkg:generic/elixir@version"),
+			CPEs:    singleCPE("cpe:2.3:a:elixir-lang:elixir:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+		},
 	}
 
 	return append(classifiers, defaultJavaClassifiers()...)

syft/pkg/cataloger/binary/pe_package.go

@@ -6,6 +6,7 @@ import (
 	"sort"
 	"strings"
 
+	packageurl "github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
 )
@@ -32,6 +33,19 @@ func newPEPackage(versionResources map[string]string, f file.Location) pkg.Packa
 		Metadata:  newPEBinaryVersionResourcesFromMap(versionResources),
 	}
 
+	// If this appears to be Ghostscript, emit a canonical generic purl
+	// Example expected: pkg:generic/ghostscript@<version>
+	prod := strings.ToLower(spaceNormalize(versionResources["ProductName"]))
+	if prod == "" {
+		// fall back to FileDescription if ProductName is missing
+		prod = strings.ToLower(spaceNormalize(versionResources["FileDescription"]))
+	}
+	if p.Version != "" && strings.Contains(prod, "ghostscript") {
+		// build a generic PURL for ghostscript
+		purl := packageurl.NewPackageURL(packageurl.TypeGeneric, "", "ghostscript", p.Version, nil, "").ToString()
+		p.PURL = purl
+	}
+
 	p.SetID()
 
 	return p

syft/pkg/cataloger/binary/pe_package_test.go

@@ -0,0 +1,24 @@
+package binary
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/file"
+)
+
+func TestGhostscriptPEGeneratesGenericPURL(t *testing.T) {
+	vr := map[string]string{
+		"CompanyName":     "Artifex Software, Inc.",
+		"ProductName":     "GPL Ghostscript",
+		"FileDescription": "Ghostscript Interpreter",
+		"ProductVersion":  "9.54.0",
+	}
+
+	loc := file.NewLocation("/usr/bin/gswin64c.exe")
+	p := newPEPackage(vr, loc)
+
+	expected := "pkg:generic/ghostscript@9.54.0"
+	if p.PURL != expected {
+		t.Fatalf("expected purl %q, got %q", expected, p.PURL)
+	}
+}

syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets/elixir/1.19.1/linux-amd64/elixir

@@ -0,0 +1,20 @@
+#!/bin/sh
+
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: 2021 The Elixir Team
+# SPDX-FileCopyrightText: 2012 Plataformatec
+
+set -e
+
+ELIXIR_VERSION=1.19.1
+
+if [ $# -eq 0 ] || { [ $# -eq 1 ] && { [ "$1" = "--help" ] || [ "$1" = "-h" ]; }; }; then
+  cat <<USAGE >&2
+Usage: $(basename "$0") [options] [.exs file] [data]
+
+## General options
+
+  -e "COMMAND"                 Evaluates the given command (*)
+  -h, --help                   Prints this message (standalone)
+  -r "FILE"                    Requires the given files/patterns (*)
+  -S SCRIPT                    Finds and executes the given script in \$PATH

syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets/elixir/1.19.1/linux-amd64/lib/elixir/ebin/elixir.app

@@ -0,0 +1,19 @@
+{application,elixir,
+    [{description,"elixir"},
+     {vsn,"1.19.1"},
+     {modules,
+         ['Elixir.Access','Elixir.Agent.Server','Elixir.Agent',
+          'Elixir.Application','Elixir.ArgumentError',
+          elixir_overridable,elixir_parser,elixir_quote,elixir_rewrite,
+          elixir_sup,elixir_tokenizer,elixir_utils,iex]},
+     {registered,[elixir_sup,elixir_config,elixir_code_server]},
+     {applications,[kernel,stdlib,compiler]},
+     {mod,{elixir,[]}},
+     {env,
+         [{ansi_syntax_colors,
+              [{atom,cyan},
+               {binary,default_color},
+               {operator,default_color}]},
+          {check_endianness,true},
+          {dbg_callback,{'Elixir.Macro',dbg,[]}},
+          {time_zone_database,'Elixir.Calendar.UTCOnlyTimeZoneDatabase'}]}]}.

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

@@ -0,0 +1,58 @@
+package cpe
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+// TargetSoftwareToPackageType is derived from looking at target_software attributes in the NVD dataset
+// TODO: ideally this would be driven from the store, where we can resolve ecosystem aliases directly
+func TargetSoftwareToPackageType(tsw string) pkg.Type {
+	tsw = strings.NewReplacer("-", "_", " ", "_").Replace(strings.ToLower(tsw))
+	switch tsw {
+	case "alpine", "apk":
+		return pkg.ApkPkg
+	case "debian", "dpkg":
+		return pkg.DebPkg
+	case "java", "maven", "ant", "gradle", "jenkins", "jenkins_ci", "kafka", "logstash", "mule", "nifi", "solr", "spark", "storm", "struts", "tomcat", "zookeeper", "log4j":
+		return pkg.JavaPkg
+	case "javascript", "node", "nodejs", "node.js", "npm", "yarn", "apache", "jquery", "next.js", "prismjs":
+		return pkg.NpmPkg
+	case "c", "c++", "c/c++", "conan", "gnu_c++", "qt":
+		return pkg.ConanPkg
+	case "dart":
+		return pkg.DartPubPkg
+	case "redhat", "rpm", "redhat_enterprise_linux", "rhel", "suse", "suse_linux", "opensuse", "opensuse_linux", "fedora", "centos", "oracle_linux", "ol":
+		return pkg.RpmPkg
+	case "elixir", "hex":
+		return pkg.HexPkg
+	case "erlang":
+		return pkg.ErlangOTPPkg
+	case ".net", ".net_framework", "asp", "asp.net", "dotnet", "dotnet_framework", "c#", "csharp", "nuget":
+		return pkg.DotnetPkg
+	case "ruby", "gem", "nokogiri", "ruby_on_rails":
+		return pkg.GemPkg
+	case "rust", "cargo", "crates":
+		return pkg.RustPkg
+	case "python", "pip", "pypi", "flask":
+		return pkg.PythonPkg
+	case "kb", "knowledgebase", "msrc", "mskb", "microsoft":
+		return pkg.KbPkg
+	case "portage", "gentoo":
+		return pkg.PortagePkg
+	case "go", "golang", "gomodule":
+		return pkg.GoModulePkg
+	case "linux_kernel", "linux", "z/linux":
+		return pkg.LinuxKernelPkg
+	case "php":
+		return pkg.PhpComposerPkg
+	case "swift":
+		return pkg.SwiftPkg
+	case "wordpress", "wordpress_plugin", "wordpress_":
+		return pkg.WordpressPluginPkg
+	case "lua", "luarocks":
+		return pkg.LuaRocksPkg
+	}
+	return ""
+}

syft/pkg/cataloger/dart/package.go

@@ -1,9 +1,12 @@
 package dart
 
 import (
+	"context"
+
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/licenses"
 )
 
 func newPubspecLockPackage(name string, raw pubspecLockPackage, locations ...file.Location) pkg.Package {
@@ -29,7 +32,7 @@ func newPubspecLockPackage(name string, raw pubspecLockPackage, locations ...fil
 	return p
 }
 
-func newPubspecPackage(raw pubspecPackage, locations ...file.Location) pkg.Package {
+func newPubspecPackage(ctx context.Context, resolver file.Resolver, raw pubspecPackage, locations ...file.Location) pkg.Package {
 	var env *pkg.DartPubspecEnvironment
 	if raw.Environment.SDK != "" || raw.Environment.Flutter != "" {
 		// this is required only after pubspec v2, but might have been optional before this
@@ -58,6 +61,8 @@ func newPubspecPackage(raw pubspecPackage, locations ...file.Location) pkg.Packa
 
 	p.SetID()
 
+	p = licenses.RelativeToPackage(ctx, resolver, p)
+
 	return p
 }
 

syft/pkg/cataloger/dart/parse_pubspec.go

@@ -29,7 +29,7 @@ type dartPubspecEnvironment struct {
 	Flutter string `mapstructure:"flutter" yaml:"flutter"`
 }
 
-func parsePubspec(_ context.Context, _ file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+func parsePubspec(ctx context.Context, resolver file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
 	var pkgs []pkg.Package
 
 	dec := yaml.NewDecoder(reader)
@@ -41,6 +41,8 @@ func parsePubspec(_ context.Context, _ file.Resolver, _ *generic.Environment, re
 
 	pkgs = append(pkgs,
 		newPubspecPackage(
+			ctx,
+			resolver,
 			p,
 			reader.WithAnnotation(pkg.EvidenceAnnotationKey, pkg.PrimaryEvidenceAnnotation),
 		),

syft/pkg/cataloger/debian/parse_dpkg_db.go

@@ -24,6 +24,10 @@ import (
 	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 )
 
+const (
+	deinstallStatus string = "deinstall"
+)
+
 var (
 	errEndOfPackages = fmt.Errorf("no more packages to read")
 	sourceRegexp     = regexp.MustCompile(`(?P<name>\S+)( \((?P<version>.*)\))?`)
@@ -112,6 +116,7 @@ type dpkgExtractedMetadata struct {
 	Provides      string `mapstructure:"Provides"`
 	Depends       string `mapstructure:"Depends"`
 	PreDepends    string `mapstructure:"PreDepends"` // note: original doc is Pre-Depends
+	Status        string `mapstructure:"Status"`
 }
 
 // parseDpkgStatusEntry returns an individual Dpkg entry, or returns errEndOfPackages if there are no more packages to parse from the reader.
@@ -134,6 +139,11 @@ func parseDpkgStatusEntry(reader *bufio.Reader) (*pkg.DpkgDBEntry, error) {
 		return nil, err
 	}
 
+	// Skip entries which have been removed but not purged, e.g. "rc" status in dpkg -l
+	if strings.Contains(raw.Status, deinstallStatus) {
+		return nil, nil
+	}
+
 	sourceName, sourceVersion := extractSourceVersion(raw.Source)
 	if sourceVersion != "" {
 		raw.SourceVersion = sourceVersion

syft/pkg/cataloger/debian/parse_dpkg_db_test.go

@@ -237,6 +237,37 @@ func Test_parseDpkgStatus(t *testing.T) {
 				},
 			},
 		},
+		{
+			name:        "deinstall status packages are ignored",
+			fixturePath: "test-fixtures/var/lib/dpkg/status.d/deinstall",
+			expected: []pkg.DpkgDBEntry{
+				{
+					Package:       "linux-image-6.14.0-1012-aws",
+					Source:        "linux-signed-aws-6.14",
+					Version:       "6.14.0-1012.12~24.04.1",
+					Architecture:  "amd64",
+					InstalledSize: 15221,
+					Maintainer:    "Canonical Kernel Team <kernel-team@lists.ubuntu.com>",
+					Description: `Signed kernel image aws
+ A kernel image for aws.  This version of it is signed with
+ Canonical's signing key.`,
+					Provides: []string{"fuse-module",
+						"linux-image",
+						"spl-dkms",
+						"spl-modules",
+						"v4l2loopback-dkms",
+						"v4l2loopback-modules",
+						"zfs-dkms",
+						"zfs-modules"},
+					Depends: []string{
+						"kmod",
+						"linux-base (>= 4.5ubuntu1~16.04.1)",
+						"linux-modules-6.14.0-1012-aws",
+					},
+					Files: []pkg.DpkgFileRecord{},
+				},
+			},
+		},
 	}
 
 	for _, test := range tests {

syft/pkg/cataloger/debian/test-fixtures/var/lib/dpkg/status.d/deinstall

@@ -0,0 +1,38 @@
+Package: linux-image-6.14.0-1012-aws
+Status: install ok installed
+Priority: optional
+Section: kernel
+Installed-Size: 15221
+Maintainer: Canonical Kernel Team <kernel-team@lists.ubuntu.com>
+Architecture: amd64
+Source: linux-signed-aws-6.14
+Version: 6.14.0-1012.12~24.04.1
+Provides: fuse-module, linux-image, spl-dkms, spl-modules, v4l2loopback-dkms, v4l2loopback-modules, zfs-dkms, zfs-modules
+Depends: kmod, linux-base (>= 4.5ubuntu1~16.04.1), linux-modules-6.14.0-1012-aws
+Recommends: grub-pc | grub-efi-amd64 | grub-efi-ia32 | grub | lilo, initramfs-tools | linux-initramfs-tool
+Suggests: bpftool, linux-perf, linux-aws-6.14-doc-6.14.0 | linux-aws-6.14-source-6.14.0, linux-aws-6.14-tools, linux-headers-6.14.0-1012-aws
+Conflicts: linux-image-unsigned-6.14.0-1012-aws
+Description: Signed kernel image aws
+ A kernel image for aws.  This version of it is signed with
+ Canonical's signing key.
+Built-Using: linux-aws-6.14 (= 6.14.0-1012.12~24.04.1)
+
+Package: linux-image-6.8.0-1029-aws
+Status: deinstall ok config-files
+Priority: optional
+Section: kernel
+Installed-Size: 14591
+Maintainer: Canonical Kernel Team <kernel-team@lists.ubuntu.com>
+Architecture: amd64
+Source: linux-signed-aws
+Version: 6.8.0-1029.31
+Config-Version: 6.8.0-1029.31
+Provides: fuse-module, linux-image, spl-dkms, spl-modules, v4l2loopback-dkms, v4l2loopback-modules, zfs-dkms, zfs-modules
+Depends: kmod, linux-base (>= 4.5ubuntu1~16.04.1), linux-modules-6.8.0-1029-aws
+Recommends: grub-pc | grub-efi-amd64 | grub-efi-ia32 | grub | lilo, initramfs-tools | linux-initramfs-tool
+Suggests: fdutils, linux-aws-doc-6.8.0 | linux-aws-source-6.8.0, linux-aws-tools, linux-headers-6.8.0-1029-aws
+Conflicts: linux-image-unsigned-6.8.0-1029-aws
+Description: Signed kernel image aws
+ A kernel image for aws.  This version of it is signed with
+ Canonical's signing key.
+Built-Using: linux-aws (= 6.8.0-1029.31)

syft/pkg/cataloger/dotnet/binary_cataloger.go

@@ -12,6 +12,7 @@ import (
 // binary cataloger will search for .dll and .exe files and create packages based off of the version resources embedded
 // as a resource directory within the executable. If there is no evidence of a .NET runtime (a CLR header) then no
 // package will be created.
+//
 // Deprecated: use depsBinaryCataloger instead which combines the PE and deps.json data which yields more accurate results (will be removed in syft v2.0).
 type binaryCataloger struct {
 }

syft/pkg/cataloger/dotnet/cataloger.go

@@ -13,12 +13,14 @@ func NewDotnetDepsBinaryCataloger(config CatalogerConfig) pkg.Cataloger {
 }
 
 // NewDotnetDepsCataloger returns a cataloger based on deps.json file contents.
+//
 // Deprecated: use NewDotnetDepsBinaryCataloger instead which combines the PE and deps.json data which yields more accurate results (will be removed in syft v2.0).
 func NewDotnetDepsCataloger() pkg.Cataloger {
 	return &depsCataloger{}
 }
 
 // NewDotnetPortableExecutableCataloger returns a cataloger based on PE file contents.
+//
 // Deprecated: use NewDotnetDepsBinaryCataloger instead which combines the PE and deps.json data which yields more accurate results (will be removed in syft v2.0).
 func NewDotnetPortableExecutableCataloger() pkg.Cataloger {
 	return &binaryCataloger{}

syft/pkg/cataloger/dotnet/deps_cataloger.go

@@ -9,6 +9,7 @@ import (
 )
 
 // depsCataloger will search for deps.json file contents.
+//
 // Deprecated: use depsBinaryCataloger instead which combines the PE and deps.json data which yields more accurate results (will be removed in syft v2.0).
 type depsCataloger struct {
 }

syft/pkg/cataloger/golang/license_finder.go

@@ -4,18 +4,20 @@ import (
 	"context"
 	"fmt"
 	"path/filepath"
-	"regexp"
 	"strings"
 
 	"github.com/spf13/afero"
 
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/licenses"
 )
 
 // resolveModuleLicenses finds and parses license files for Go modules
-func resolveModuleLicenses(ctx context.Context, pkgInfos []pkgInfo, fs afero.Fs) pkg.LicenseSet {
-	licenses := pkg.NewLicenseSet()
+func resolveModuleLicenses(ctx context.Context, scanRoot string, pkgInfos []pkgInfo, fs afero.Fs) pkg.LicenseSet {
+	out := pkg.NewLicenseSet()
 
 	for _, info := range pkgInfos {
 		modDir, pkgDir, err := getAbsolutePkgPaths(info)
@@ -23,22 +25,32 @@ func resolveModuleLicenses(ctx context.Context, pkgInfos []pkgInfo, fs afero.Fs)
 			continue
 		}
 
-		licenseFiles, err := findAllLicenseCandidatesUpwards(pkgDir, licenseRegexp, modDir, fs)
+		licenseFiles, err := findAllLicenseCandidatesUpwards(pkgDir, modDir, fs)
 		if err != nil {
 			continue
 		}
 
 		for _, f := range licenseFiles {
-			contents, err := fs.Open(f)
-			if err != nil {
-				continue
-			}
-			licenses.Add(pkg.NewLicensesFromReadCloserWithContext(ctx, file.NewLocationReadCloser(file.Location{}, contents))...)
-			_ = contents.Close()
+			out.Add(readLicenses(ctx, scanRoot, fs, f)...)
 		}
 	}
 
-	return licenses
+	return out
+}
+
+func readLicenses(ctx context.Context, scanRoot string, fs afero.Fs, f string) []pkg.License {
+	contents, err := fs.Open(f)
+	if err != nil {
+		log.WithFields("file", f, "error", err).Debug("unable to read license file")
+		return nil
+	}
+	defer internal.CloseAndLogError(contents, f)
+	location := file.Location{}
+	if scanRoot != "" && strings.HasPrefix(f, scanRoot) {
+		// include location when licenses are found within the scan target
+		location = file.NewLocation(strings.TrimPrefix(f, scanRoot))
+	}
+	return pkg.NewLicensesFromReadCloserWithContext(ctx, file.NewLocationReadCloser(location, contents))
 }
 
 /*
@@ -60,7 +72,7 @@ When we should consider redesign tip to stem:
 - We need to consider the case here where nested modules are visited by accident and licenses
 are erroneously associated to a 'parent module'; bubble up currently prevents this
 */
-func findAllLicenseCandidatesUpwards(dir string, r *regexp.Regexp, stopAt string, fs afero.Fs) ([]string, error) {
+func findAllLicenseCandidatesUpwards(dir string, stopAt string, fs afero.Fs) ([]string, error) {
 	// Validate that both paths are absolute
 	if !filepath.IsAbs(dir) {
 		return nil, fmt.Errorf("dir must be an absolute path, got: %s", dir)
@@ -69,25 +81,16 @@ func findAllLicenseCandidatesUpwards(dir string, r *regexp.Regexp, stopAt string
 		return nil, fmt.Errorf("stopAt must be an absolute path, got: %s", stopAt)
 	}
 
-	licenses, err := findLicenseCandidates(dir, r, stopAt, fs)
-	if err != nil {
-		return nil, err
+	return findLicenseCandidates(dir, stopAt, fs)
 }
 
-	// Ensure we return an empty slice rather than nil for consistency
-	if licenses == nil {
-		return []string{}, nil
-	}
-	return licenses, nil
-}
-
-func findLicenseCandidates(dir string, r *regexp.Regexp, stopAt string, fs afero.Fs) ([]string, error) {
+func findLicenseCandidates(dir string, stopAt string, fs afero.Fs) ([]string, error) {
 	// stop if we've gone outside the stopAt directory
 	if !strings.HasPrefix(dir, stopAt) {
 		return []string{}, nil
 	}
 
-	licenses, err := findLicensesInDir(dir, r, fs)
+	out, err := findLicensesInDir(dir, fs)
 	if err != nil {
 		return nil, err
 	}
@@ -95,17 +98,17 @@ func findLicenseCandidates(dir string, r *regexp.Regexp, stopAt string, fs afero
 	parent := filepath.Dir(dir)
 	// can't go any higher up the directory tree: "/" case
 	if parent == dir {
-		return licenses, nil
+		return out, nil
 	}
 
 	// search parent directory and combine results
-	parentLicenses, err := findLicenseCandidates(parent, r, stopAt, fs)
+	parentLicenses, err := findLicenseCandidates(parent, stopAt, fs)
 	if err != nil {
 		return nil, err
 	}
 
 	// Combine current directory licenses with parent directory licenses
-	return append(licenses, parentLicenses...), nil
+	return append(out, parentLicenses...), nil
 }
 
 func getAbsolutePkgPaths(info pkgInfo) (modDir string, pkgDir string, err error) {
@@ -126,8 +129,8 @@ func getAbsolutePkgPaths(info pkgInfo) (modDir string, pkgDir string, err error)
 	return modDir, pkgDir, nil
 }
 
-func findLicensesInDir(dir string, r *regexp.Regexp, fs afero.Fs) ([]string, error) {
-	var licenses []string
+func findLicensesInDir(dir string, fs afero.Fs) ([]string, error) {
+	var out []string
 
 	dirContents, err := afero.ReadDir(fs, dir)
 	if err != nil {
@@ -139,11 +142,11 @@ func findLicensesInDir(dir string, r *regexp.Regexp, fs afero.Fs) ([]string, err
 			continue
 		}
 
-		if r.MatchString(f.Name()) {
+		if licenses.IsLicenseFile(f.Name()) {
 			path := filepath.Join(dir, f.Name())
-			licenses = append(licenses, path)
+			out = append(out, path)
 		}
 	}
 
-	return licenses, nil
+	return out, nil
 }

syft/pkg/cataloger/golang/license_finder_test.go

@@ -70,8 +70,8 @@ func TestFindAllLicenseCandidatesUpwards(t *testing.T) {
 				fs.MkdirAll("/empty/dir/tree", 0755)
 				// No license files
 			},
-			expectedFiles: []string{},
-			description:   "Should return empty slice when no license files found",
+			expectedFiles: nil,
+			description:   "Should return nil when no license files found",
 		},
 		{
 			name:     "handles directory at filesystem root",
@@ -205,7 +205,7 @@ func TestFindAllLicenseCandidatesUpwards(t *testing.T) {
 			tt.setupFS(fs)
 
 			// Run the function
-			result, err := findAllLicenseCandidatesUpwards(tt.startDir, licenseRegexp, tt.stopAt, fs)
+			result, err := findAllLicenseCandidatesUpwards(tt.startDir, tt.stopAt, fs)
 
 			// Check error expectation
 			if tt.expectedError {

syft/pkg/cataloger/golang/licenses.go

@@ -19,14 +19,13 @@ import (
 	"github.com/go-git/go-git/v5"
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/storage/memory"
-	"github.com/scylladb/go-set/strset"
 
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/cache"
-	"github.com/anchore/syft/internal/licenses"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/licenses"
 )
 
 type goLicenseResolver struct {
@@ -35,7 +34,6 @@ type goLicenseResolver struct {
 	localModCacheDir fs.FS
 	localVendorDir   fs.FS
 	licenseCache     cache.Resolver[[]pkg.License]
-	lowerLicenseFileNames *strset.Set
 }
 
 func newGoLicenseResolver(catalogerName string, opts CatalogerConfig) goLicenseResolver {
@@ -64,18 +62,9 @@ func newGoLicenseResolver(catalogerName string, opts CatalogerConfig) goLicenseR
 		localModCacheDir: localModCacheDir,
 		localVendorDir:   localVendorDir,
 		licenseCache:     cache.GetResolverCachingErrors[[]pkg.License]("golang", "v2"),
-		lowerLicenseFileNames: strset.New(lowercaseLicenseFiles()...),
 	}
 }
 
-func lowercaseLicenseFiles() []string {
-	fileNames := licenses.FileNames()
-	for i := range fileNames {
-		fileNames[i] = strings.ToLower(fileNames[i])
-	}
-	return fileNames
-}
-
 func remotesForModule(proxies []string, noProxy []string, module string) []string {
 	for _, pattern := range noProxy {
 		if matched, err := path.Match(pattern, module); err == nil && matched {
@@ -194,7 +183,7 @@ func (c *goLicenseResolver) findLicensesInFS(ctx context.Context, urlPrefix stri
 			log.Debugf("nil entry for %s#%s", urlPrefix, filePath)
 			return nil
 		}
-		if !c.lowerLicenseFileNames.Has(strings.ToLower(d.Name())) {
+		if !licenses.IsLicenseFile(d.Name()) {
 			return nil
 		}
 		rdr, err := fsys.Open(filePath)
@@ -203,11 +192,11 @@ func (c *goLicenseResolver) findLicensesInFS(ctx context.Context, urlPrefix stri
 			return nil
 		}
 		defer internal.CloseAndLogError(rdr, filePath)
-		licenses := pkg.NewLicensesFromReadCloserWithContext(ctx, file.NewLocationReadCloser(file.NewLocation(filePath), rdr))
+		foundLicenses := pkg.NewLicensesFromReadCloserWithContext(ctx, file.NewLocationReadCloser(file.NewLocation(filePath), rdr))
 		// since these licenses are found in an external fs.FS, not in the scanned source,
 		// get rid of the locations but keep information about the where the license was found
 		// by prepending the urlPrefix to the internal path for an accurate representation
-		for _, l := range licenses {
+		for _, l := range foundLicenses {
 			l.URLs = []string{urlPrefix + filePath}
 			l.Locations = file.NewLocationSet()
 			out = append(out, l)
@@ -246,7 +235,7 @@ func (c *goLicenseResolver) findLicensesInSource(ctx context.Context, resolver f
 func (c *goLicenseResolver) parseLicenseFromLocation(ctx context.Context, l file.Location, resolver file.Resolver) ([]pkg.License, error) {
 	var out []pkg.License
 	fileName := path.Base(l.RealPath)
-	if c.lowerLicenseFileNames.Has(strings.ToLower(fileName)) {
+	if licenses.IsLicenseFile(fileName) {
 		contents, err := resolver.FileContentsByLocation(l)
 		if err != nil {
 			return nil, err

syft/pkg/cataloger/golang/package.go

@@ -10,7 +10,14 @@ import (
 )
 
 func (c *goBinaryCataloger) newGoBinaryPackage(dep *debug.Module, m pkg.GolangBinaryBuildinfoEntry, licenses []pkg.License, locations ...file.Location) pkg.Package {
+	// Similar to syft/pkg/cataloger/golang/parse_go_mod.go logic - use original path for relative replacements
+	finalPath := dep.Path
 	if dep.Replace != nil {
+		if strings.HasPrefix(dep.Replace.Path, ".") || strings.HasPrefix(dep.Replace.Path, "/") {
+			finalPath = dep.Path
+		} else {
+			finalPath = dep.Replace.Path
+		}
 		dep = dep.Replace
 	}
 
@@ -23,10 +30,10 @@ func (c *goBinaryCataloger) newGoBinaryPackage(dep *debug.Module, m pkg.GolangBi
 	}
 
 	p := pkg.Package{
-		Name:      dep.Path,
+		Name:      finalPath,
 		Version:   version,
 		Licenses:  pkg.NewLicenseSet(licenses...),
-		PURL:      packageURL(dep.Path, version),
+		PURL:      packageURL(finalPath, version),
 		Language:  pkg.Go,
 		Type:      pkg.GoModulePkg,
 		Locations: file.NewLocationSet(locations...),

syft/pkg/cataloger/golang/package_test.go

@@ -1,6 +1,7 @@
 package golang
 
 import (
+	"runtime/debug"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -54,3 +55,67 @@ func Test_packageURL(t *testing.T) {
 		})
 	}
 }
+
+func Test_newGoBinaryPackage_relativeReplace(t *testing.T) {
+	tests := []struct {
+		name         string
+		dep          *debug.Module
+		expectedName string
+	}{
+		{
+			name: "relative replace with ../",
+			dep: &debug.Module{
+				Path:    "github.com/aws/aws-sdk-go-v2",
+				Version: "(devel)",
+				Replace: &debug.Module{
+					Path:    "../../",
+					Version: "(devel)",
+				},
+			},
+			expectedName: "github.com/aws/aws-sdk-go-v2", // should use original path, not relative
+		},
+		{
+			name: "relative replace with ./",
+			dep: &debug.Module{
+				Path:    "github.com/example/module",
+				Version: "v1.0.0",
+				Replace: &debug.Module{
+					Path:    "./local",
+					Version: "v0.0.0",
+				},
+			},
+			expectedName: "github.com/example/module", // should use original path
+		},
+		{
+			name: "absolute replace",
+			dep: &debug.Module{
+				Path:    "github.com/old/module",
+				Version: "v1.0.0",
+				Replace: &debug.Module{
+					Path:    "github.com/new/module",
+					Version: "v2.0.0",
+				},
+			},
+			expectedName: "github.com/new/module", // should use replacement path
+		},
+		{
+			name: "no replace",
+			dep: &debug.Module{
+				Path:    "github.com/normal/module",
+				Version: "v1.0.0",
+			},
+			expectedName: "github.com/normal/module", // should use original path
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			cataloger := &goBinaryCataloger{}
+			result := cataloger.newGoBinaryPackage(test.dep, pkg.GolangBinaryBuildinfoEntry{}, nil)
+
+			assert.Equal(t, test.expectedName, result.Name)
+			assert.Equal(t, pkg.Go, result.Language)
+			assert.Equal(t, pkg.GoModulePkg, result.Type)
+		})
+	}
+}

syft/pkg/cataloger/golang/parse_go_mod.go

@@ -7,7 +7,7 @@ import (
 	"go/build"
 	"io"
 	"path/filepath"
-	"regexp"
+	"slices"
 	"sort"
 	"strings"
 
@@ -20,14 +20,11 @@ import (
 	"github.com/anchore/syft/internal/unknown"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/internal/fileresolver"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/generic"
 )
 
-var (
-	licenseRegexp = regexp.MustCompile(`^(?i)((UN)?LICEN(S|C)E|COPYING|NOTICE).*$`)
-)
-
 type goModCataloger struct {
 	licenseResolver goLicenseResolver
 }
@@ -46,9 +43,14 @@ func (c *goModCataloger) parseGoModFile(ctx context.Context, resolver file.Resol
 		log.Debugf("unable to get go.sum: %v", err)
 	}
 
+	scanRoot := ""
+	if dir, ok := resolver.(*fileresolver.Directory); ok && dir != nil {
+		scanRoot = dir.Chroot.Base()
+	}
+
 	// source analysis using go toolchain if available
 	syftSourcePackages, sourceModules, sourceDependencies, unknownErr := c.loadPackages(modDir, reader.Location)
-	catalogedModules, sourceModuleToPkg := c.catalogModules(ctx, syftSourcePackages, sourceModules, reader, digests)
+	catalogedModules, sourceModuleToPkg := c.catalogModules(ctx, scanRoot, syftSourcePackages, sourceModules, reader, digests)
 	relationships := buildModuleRelationships(catalogedModules, sourceDependencies, sourceModuleToPkg)
 
 	// base case go.mod file parsing
@@ -208,12 +210,16 @@ func (c *goModCataloger) visitPackages(
 				}
 			}
 		}
-		pkgs[module.Path] = append(pkgs[module.Path], pkgInfo{
+
+		info := pkgInfo{
 			pkgPath:    p.PkgPath,
 			modulePath: module.Path,
 			pkgDir:     pkgDir,
 			moduleDir:  module.Dir,
-		})
+		}
+		if !slices.Contains(pkgs[module.Path], info) { // avoid duplicates
+			pkgs[module.Path] = append(pkgs[module.Path], info)
+		}
 		modules[p.Module.Path] = module
 
 		return true
@@ -224,6 +230,7 @@ func (c *goModCataloger) visitPackages(
 // create syft packages from Go modules found by the go toolchain
 func (c *goModCataloger) catalogModules(
 	ctx context.Context,
+	scanRoot string,
 	pkgs map[string][]pkgInfo,
 	modules map[string]*packages.Module,
 	reader file.LocationReadCloser,
@@ -243,7 +250,7 @@ func (c *goModCataloger) catalogModules(
 		}
 
 		pkgInfos := pkgs[m.Path]
-		moduleLicenses := resolveModuleLicenses(ctx, pkgInfos, afero.NewOsFs())
+		moduleLicenses := resolveModuleLicenses(ctx, scanRoot, pkgInfos, afero.NewOsFs())
 		// we do out of source lookups for module parsing
 		// locations are NOT included in the SBOM because of this
 		goModulePkg := pkg.Package{

syft/pkg/cataloger/homebrew/package.go

@@ -1,15 +1,22 @@
 package homebrew
 
 import (
+	"context"
+	"path"
+
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/licenses"
 )
 
-func newHomebrewPackage(pd parsedHomebrewData, formulaLocation file.Location) pkg.Package {
-	var licenses []string
+func newHomebrewPackage(ctx context.Context, resolver file.Resolver, pd parsedHomebrewData, formulaLocation file.Location) pkg.Package {
+	var lics []pkg.License
 	if pd.License != "" {
-		licenses = append(licenses, pd.License)
+		lics = append(lics, pkg.NewLicensesFromValues(pd.License)...)
+	} else {
+		// sometimes licenses are included in the parent directory
+		lics = licenses.FindInDirs(ctx, resolver, path.Dir(formulaLocation.Path()))
 	}
 
 	p := pkg.Package{
@@ -17,7 +24,7 @@ func newHomebrewPackage(pd parsedHomebrewData, formulaLocation file.Location) pk
 		Version:   pd.Version,
 		Type:      pkg.HomebrewPkg,
 		Locations: file.NewLocationSet(formulaLocation.WithAnnotation(pkg.EvidenceAnnotationKey, pkg.PrimaryEvidenceAnnotation)),
-		Licenses:  pkg.NewLicenseSet(pkg.NewLicensesFromValues(licenses...)...),
+		Licenses:  pkg.NewLicenseSet(lics...),
 		FoundBy:   "homebrew-cataloger",
 		PURL:      packageURL(pd.Name, pd.Version),
 		Metadata: pkg.HomebrewFormula{

syft/pkg/cataloger/homebrew/parse_homebrew_formula.go

@@ -22,7 +22,7 @@ type parsedHomebrewData struct {
 	License  string
 }
 
-func parseHomebrewFormula(_ context.Context, _ file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+func parseHomebrewFormula(ctx context.Context, resolver file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
 	pd, err := parseFormulaFile(reader)
 	if err != nil {
 		log.WithFields("path", reader.RealPath).Trace("failed to parse formula")
@@ -35,6 +35,8 @@ func parseHomebrewFormula(_ context.Context, _ file.Resolver, _ *generic.Environ
 
 	return []pkg.Package{
 		newHomebrewPackage(
+			ctx,
+			resolver,
 			*pd,
 			reader.Location,
 		),

syft/pkg/cataloger/internal/cpegenerate/README.md

@@ -0,0 +1,167 @@
+# CPE Generation
+
+This package generates Common Platform Enumeration (CPE) identifiers for software packages discovered by Syft.
+CPEs are standardized identifiers that enable vulnerability matching by linking packages to known vulnerabilities in databases like the National Vulnerability Database (NVD).
+
+## Overview
+
+CPE generation in Syft uses a **two-tier approach** to balance accuracy and coverage:
+
+1. **Dictionary Lookups** (Authoritative): Pre-validated CPEs from the official NIST CPE dictionary
+2. **Heuristic Generation** (Fallback): Intelligent generation based on package metadata and ecosystem-specific patterns
+
+This dual approach ensures:
+- **High accuracy** for packages in the NIST dictionary (no false positives)
+- **Broad coverage** for packages not yet in the dictionary (maximizes vulnerability detection)
+- **Fast performance** with an embedded, indexed CPE dictionary (~814KB)
+
+## Why It Matters
+
+CPEs link discovered packages to security vulnerabilities (CVEs) in tools like Grype. Without accurate CPE generation, vulnerability scanning misses security issues.
+
+## How It Works
+
+### Architecture
+
+```
+┌─────────────────────────────────────────────────────────┐
+│  Syft Package Discovery                                 │
+└──────────────────┬──────────────────────────────────────┘
+                   │
+                   ▼
+         ┌─────────────────────┐
+         │  CPE Generation     │
+         │  (this package)     │
+         └──────────┬──────────┘
+                    │
+        ┌───────────┴────────────┐
+        │                        │
+        ▼                        ▼
+┌──────────────────┐    ┌─────────────────────┐
+│ Dictionary       │    │ Heuristic           │
+│ Lookup           │    │ Generation          │
+│                  │    │                     │
+│ • Embedded index │    │ • Ecosystem rules   │
+│ • ~22K entries   │    │ • Vendor/product    │
+│ • 11 ecosystems  │    │   candidates        │
+└──────────────────┘    │ • Curated mappings  │
+                        │ • Smart filters     │
+                        └─────────────────────┘
+```
+
+### Dictionary Generation Process
+
+The dictionary is generated offline and embedded into the Syft binary for fast, offline lookups.
+
+**Location**: `dictionary/index-generator/`
+
+**Process**:
+1. **Fetch**: Retrieves CPE data from NVD Products API using incremental updates
+2. **Cache**: Stores raw API responses in ORAS registry for reuse (`.cpe-cache/`)
+3. **Filter**:
+   - Removes CPEs without reference URLs
+   - Excludes hardware (`h`) and OS (`o`) CPEs (keeps only applications `a`)
+4. **Index by Ecosystem**:
+   - Extracts package names from reference URLs (npm, pypi, rubygems, etc.)
+   - Creates index: `ecosystem → package_name → [CPE strings]`
+5. **Embed**: Generates `data/cpe-index.json` embedded via `go:embed` directive
+
+### Runtime CPE Lookup/Generation
+
+**Entry Point**: `generate.go`
+
+When Syft discovers a package:
+
+1. **Check for Declared CPEs**: If package metadata already contains CPEs (from SBOM imports), skip generation
+2. **Try Dictionary Lookup** (`FromDictionaryFind`):
+   - Loads embedded CPE index (singleton, loaded once)
+   - Looks up by ecosystem + package name
+   - Returns pre-validated CPEs if found
+   - Marks source as `NVDDictionaryLookupSource`
+3. **Fallback to Heuristic Generation** (`FromPackageAttributes`):
+   - Generates vendor/product/targetSW candidates using ecosystem-specific logic
+   - Creates CPE permutations from candidates
+   - Applies filters to remove known false positives
+   - Marks source as `GeneratedSource`
+
+### Supported Ecosystems
+
+**Dictionary Lookups** (11 ecosystems):
+npm, RubyGems, PyPI, Jenkins Plugins, crates.io, PHP, Go Modules, WordPress Plugins/Themes
+
+**Heuristic Generation** (all package types):
+All dictionary ecosystems plus Java, .NET/NuGet, Alpine APK, Debian/RPM, and any other package type Syft discovers
+
+### Ecosystem-Specific Intelligence
+
+The heuristic generator uses per-ecosystem strategies:
+
+- **Java**: Extracts vendor from groupId, product from artifactId
+- **Python**: Parses author fields, adds `_project` suffix variants
+- **Go**: Extracts org/repo from module paths (`github.com/org/repo`)
+- **JavaScript**: Handles npm scope patterns (`@scope/package`)
+
+### Curated Mappings & Filters
+
+- **500+ curated mappings**: `curl` → `haxx`, `spring-boot` → `pivotal`, etc.
+- **Filters**: Prevent false positives (Jenkins plugins vs. core, Jira client vs. server)
+- **Validation**: Ensures CPE syntax correctness before returning
+
+## Implementation Details
+
+### Embedded Index Format
+
+```json
+{
+  "ecosystems": {
+    "npm": {
+      "lodash": ["cpe:2.3:a:lodash:lodash:*:*:*:*:*:node.js:*:*"]
+    },
+    "pypi": {
+      "Django": ["cpe:2.3:a:djangoproject:django:*:*:*:*:*:python:*:*"]
+    }
+  }
+}
+```
+
+The dictionary generator maps packages to ecosystems using reference URL patterns (npmjs.com, pypi.org, rubygems.org, etc.).
+
+## Maintenance
+
+### Updating the CPE Dictionary
+
+The CPE dictionary should be updated periodically to include new packages:
+
+```bash
+# Full workflow: pull cache → update from NVD → build index
+make generate:cpe-index
+
+# Or run individual steps:
+make generate:cpe-index:cache:pull     # Pull cached CPE data from ORAS
+make generate:cpe-index:cache:update   # Fetch updates from NVD Products API
+make generate:cpe-index:build          # Generate cpe-index.json from cache
+```
+
+**Optional**: Set `NVD_API_KEY` for faster updates (50 req/30s vs 5 req/30s)
+
+This workflow:
+1. Pulls existing cache from ORAS registry (avoids re-fetching all ~1.5M CPEs)
+2. Fetches only products modified since last update from NVD Products API
+3. Builds indexed dictionary (~814KB, ~22K entries)
+4. Pushes updated cache for team reuse
+
+### Extending CPE Generation
+
+**Add dictionary support for a new ecosystem:**
+1. Add URL pattern in `index-generator/generate.go`
+2. Regenerate index with `make generate:cpe-index`
+
+**Improve heuristic generation:**
+1. Modify ecosystem-specific file (e.g., `java.go`, `python.go`)
+2. Add curated mappings to `candidate_by_package_type.go`
+
+**Key files:**
+- `generate.go` - Main generation logic
+- `dictionary/` - Dictionary generator and embedded index
+- `candidate_by_package_type.go` - Ecosystem-specific candidates
+- `filter.go` - Filtering rules

syft/pkg/cataloger/internal/cpegenerate/candidate_for_pe.go

@@ -0,0 +1,63 @@
+package cpegenerate
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+// candidateVendorsForPE returns vendor candidates for PE (BinaryPkg) packages based on common metadata hints.
+// Specifically, normalize Ghostscript binaries to vendor "artifex" when detected.
+func candidateVendorsForPE(p pkg.Package) fieldCandidateSet {
+	candidates := newFieldCandidateSet()
+
+	meta, ok := p.Metadata.(pkg.PEBinary)
+	if !ok {
+		return candidates
+	}
+
+	var company, product, fileDesc string
+	for _, kv := range meta.VersionResources {
+		switch strings.ToLower(kv.Key) {
+		case "companyname":
+			company = strings.ToLower(kv.Value)
+		case "productname":
+			product = strings.ToLower(kv.Value)
+		case "filedescription":
+			fileDesc = strings.ToLower(kv.Value)
+		}
+	}
+
+	if strings.Contains(product, "ghostscript") || strings.Contains(fileDesc, "ghostscript") || strings.Contains(company, "artifex") {
+		candidates.addValue("artifex")
+	}
+
+	return candidates
+}
+
+// candidateProductsForPE returns product candidates for PE (BinaryPkg) packages based on common metadata hints.
+// Specifically, normalize Ghostscript binaries to product "ghostscript" when detected.
+func candidateProductsForPE(p pkg.Package) fieldCandidateSet {
+	candidates := newFieldCandidateSet()
+
+	meta, ok := p.Metadata.(pkg.PEBinary)
+	if !ok {
+		return candidates
+	}
+
+	var product, fileDesc string
+	for _, kv := range meta.VersionResources {
+		switch strings.ToLower(kv.Key) {
+		case "productname":
+			product = strings.ToLower(kv.Value)
+		case "filedescription":
+			fileDesc = strings.ToLower(kv.Value)
+		}
+	}
+
+	if strings.Contains(product, "ghostscript") || strings.Contains(fileDesc, "ghostscript") {
+		candidates.addValue("ghostscript")
+	}
+
+	return candidates
+}

syft/pkg/cataloger/internal/cpegenerate/dictionary/data/cpe-index.json

@@ -653,6 +653,9 @@
       "dbCharts": [
         "cpe:2.3:a:jenkins:dbcharts:*:*:*:*:*:jenkins:*:*"
       ],
+      "deadmanssnitch": [
+        "cpe:2.3:a:jenkins:dead_man\\'s_snitch:*:*:*:*:*:jenkins:*:*"
+      ],
       "debian-package-builder": [
         "cpe:2.3:a:jenkins:debian_package_builder:*:*:*:*:*:jenkins:*:*"
       ],
@@ -1360,6 +1363,9 @@
       "oic-auth": [
         "cpe:2.3:a:jenkins:openid_connect_authentication:*:*:*:*:*:jenkins:*:*"
       ],
+      "oidc-provider": [
+        "cpe:2.3:a:jenkins:openid_connect_provider:*:*:*:*:*:jenkins:*:*"
+      ],
       "ontrack": [
         "cpe:2.3:a:jenkins:ontrack:*:*:*:*:*:jenkins:*:*"
       ],
@@ -1531,6 +1537,9 @@
       "qualys-pc": [
         "cpe:2.3:a:qualys:policy_compliance:*:*:*:*:*:jenkins:*:*"
       ],
+      "qualys-was": [
+        "cpe:2.3:a:qualys:web_application_screening:*:*:*:*:*:jenkins:*:*"
+      ],
       "quayio-trigger": [
         "cpe:2.3:a:jenkins:quay.io_trigger:*:*:*:*:*:jenkins:*:*"
       ],
@@ -2164,6 +2173,9 @@
       "@azure/ms-rest-nodeauth": [
         "cpe:2.3:a:microsoft:ms-rest-nodeauth:*:*:*:*:*:node.js:*:*"
       ],
+      "@backstage/backend-common": [
+        "cpe:2.3:a:linuxfoundation:backstage_backend-common:*:*:*:*:*:node.js:*:*"
+      ],
       "@backstage/plugin-auth-backend": [
         "cpe:2.3:a:linuxfoundation:auth_backend:*:*:*:*:*:node.js:*:*"
       ],
@@ -3035,6 +3047,9 @@
       "electron-packager": [
         "cpe:2.3:a:electron-packager_project:electron-packager:*:*:*:*:*:node.js:*:*"
       ],
+      "electron-pdf": [
+        "cpe:2.3:a:fraserxu:electron-pdf:*:*:*:*:*:node.js:*:*"
+      ],
       "elliptic": [
         "cpe:2.3:a:indutny:elliptic:*:*:*:*:*:node.js:*:*"
       ],
@@ -5284,6 +5299,9 @@
       "ts-process-promises": [
         "cpe:2.3:a:ts-process-promises_project:ts-process-promises:*:*:*:*:*:node.js:*:*"
       ],
+      "tsup": [
+        "cpe:2.3:a:egoist:tsup:*:*:*:*:*:node.js:*:*"
+      ],
       "ua-parser": [
         "cpe:2.3:a:ua-parser_project:ua-parser:*:*:*:*:*:node.js:*:*"
       ],
@@ -5552,6 +5570,9 @@
       "alfnru/password_recovery": [
         "cpe:2.3:a:password_recovery_project:password_recovery:*:*:*:*:*:roundcube:*:*"
       ],
+      "couleurcitron/tarteaucitron-wp": [
+        "cpe:2.3:a:couleurcitron:tarteaucitron-wp:*:*:*:*:*:wordpress:*:*"
+      ],
       "dev-lancer/minecraft-motd-parser": [
         "cpe:2.3:a:jgniecki:minecraft_motd_parser:*:*:*:*:*:*:*:*"
       ],
@@ -7259,6 +7280,9 @@
       "ab-press-optimizer-lite": [
         "cpe:2.3:a:abpressoptimizer:ab_press_optimizer:*:*:*:*:*:wordpress:*:*"
       ],
+      "abitgone-commentsafe": [
+        "cpe:2.3:a:abitgone:abitgone_commentsafe:*:*:*:*:*:wordpress:*:*"
+      ],
       "about-me": [
         "cpe:2.3:a:about-me_project:about-me:*:*:*:*:*:wordpress:*:*"
       ],
@@ -7605,6 +7629,9 @@
       "advanced-backgrounds": [
         "cpe:2.3:a:wpbackgrounds:advanced_wordpress_backgrounds:*:*:*:*:*:wordpress:*:*"
       ],
+      "advanced-blocks-pro": [
+        "cpe:2.3:a:essamamdani:advanced_blocks_pro:*:*:*:*:*:wordpress:*:*"
+      ],
       "advanced-booking-calendar": [
         "cpe:2.3:a:elbtide:advanced_booking_calendar:*:*:*:*:*:wordpress:*:*"
       ],
@@ -7702,6 +7729,9 @@
       "affiliatebooster-blocks": [
         "cpe:2.3:a:affiliatebooster:affiliate_booster:*:*:*:*:*:wordpress:*:*"
       ],
+      "affiliateimportereb": [
+        "cpe:2.3:a:cr1000:affiliateimportereb:*:*:*:*:*:wordpress:*:*"
+      ],
       "affiliates-manager": [
         "cpe:2.3:a:wpaffiliatemanager:affiliates_manager:*:*:*:*:*:wordpress:*:*"
       ],
@@ -8408,6 +8438,9 @@
         "cpe:2.3:a:dotstore:woocommerce_category_banner_management:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:multidots:banner_management_for_woocommerce:*:*:*:*:*:wordpress:*:*"
       ],
+      "bannerlid": [
+        "cpe:2.3:a:web_lid:bannerlid:*:*:*:*:*:wordpress:*:*"
+      ],
       "barcode-scanner-lite-pos-to-manage-products-inventory-and-orders": [
         "cpe:2.3:a:ukrsolution:barcode_scanner_and_inventory_manager:*:*:*:*:*:wordpress:*:*"
       ],
@@ -8516,6 +8549,9 @@
       "better-elementor-addons": [
         "cpe:2.3:a:kitforest:better_elementor_addons:*:*:*:*:*:wordpress:*:*"
       ],
+      "better-follow-button-for-jetpack": [
+        "cpe:2.3:a:antonpug:better_flow_button_for_jetpack:*:*:*:*:*:wordpress:*:*"
+      ],
       "better-font-awesome": [
         "cpe:2.3:a:better_font_awesome_project:better_font_awesome:*:*:*:*:*:wordpress:*:*"
       ],
@@ -8770,6 +8806,9 @@
       "bp-cover": [
         "cpe:2.3:a:buddypress_cover_project:buddypress_cover:*:*:*:*:*:wordpress:*:*"
       ],
+      "bp-email-assign-templates": [
+        "cpe:2.3:a:shanebp:bp_email_assign_templates:*:*:*:*:*:wordpress:*:*"
+      ],
       "bp-profile-search": [
         "cpe:2.3:a:dontdream:bp_profile_search:*:*:*:*:*:wordpress:*:*"
       ],
@@ -9240,6 +9279,9 @@
       "chained-quiz": [
         "cpe:2.3:a:kibokolabs:chained_quiz:*:*:*:*:*:wordpress:*:*"
       ],
+      "chalet-montagne-com-tools": [
+        "cpe:2.3:a:alpium:chalet-montagne.com_tools:*:*:*:*:*:wordpress:*:*"
+      ],
       "chamber-dashboard-business-directory": [
         "cpe:2.3:a:chamber_dashboard_business_directory_project:chamber_dashboard_business_directory:*:*:*:*:*:wordpress:*:*"
       ],
@@ -9252,6 +9294,9 @@
       "change-memory-limit": [
         "cpe:2.3:a:simon99:change_memory_limit:*:*:*:*:*:wordpress:*:*"
       ],
+      "change-table-prefix": [
+        "cpe:2.3:a:youngtechleads:change_table_prefix:*:*:*:*:*:wordpress:*:*"
+      ],
       "change-uploaded-file-permissions": [
         "cpe:2.3:a:change_uploaded_file_permissions_project:change_uploaded_file_permissions:*:*:*:*:*:wordpress:*:*"
       ],
@@ -9550,6 +9595,9 @@
       "commenttweets": [
         "cpe:2.3:a:theresehansen:commenttweets:*:*:*:*:*:wordpress:*:*"
       ],
+      "common-tools-for-site": [
+        "cpe:2.3:a:chetanvaghela:common_tools_for_site:*:*:*:*:*:wordpress:*:*"
+      ],
       "commonsbooking": [
         "cpe:2.3:a:wielebenwir:commonsbooking:*:*:*:*:*:wordpress:*:*"
       ],
@@ -10041,6 +10089,9 @@
       "csv-importer": [
         "cpe:2.3:a:deniskobozev:csv_importer:*:*:*:*:*:wordpress:*:*"
       ],
+      "csv-mass-importer": [
+        "cpe:2.3:a:aleapp:csv_mass_importer:*:*:*:*:*:wordpress:*:*"
+      ],
       "ct-commerce": [
         "cpe:2.3:a:ujwolbastakoti:ct_commerce:*:*:*:*:*:wordpress:*:*"
       ],
@@ -10798,6 +10849,9 @@
       "easy-svg": [
         "cpe:2.3:a:benjaminzekavica:easy_svg_support:*:*:*:*:*:wordpress:*:*"
       ],
+      "easy-svg-upload": [
+        "cpe:2.3:a:delowerhossain:easy_svg_upload:*:*:*:*:*:wordpress:*:*"
+      ],
       "easy-table": [
         "cpe:2.3:a:easy_table_project:easy_table:*:*:*:*:*:wordpress:*:*"
       ],
@@ -11286,6 +11340,9 @@
       "exit-intent-popups-by-optimonk": [
         "cpe:2.3:a:optimonk:optimonk\\:popups\\,_personalization_\\\u0026_a\\/b_testing:*:*:*:*:*:wordpress:*:*"
       ],
+      "exit-notifier": [
+        "cpe:2.3:a:cvstech:exit_notifier:*:*:*:*:*:wordpress:*:*"
+      ],
       "exmage-wp-image-links": [
         "cpe:2.3:a:villatheme:exmage:*:*:*:*:*:wordpress:*:*"
       ],
@@ -11325,6 +11382,9 @@
       "exquisite-paypal-donation": [
         "cpe:2.3:a:exquisite_paypal_donation_project:exquisite_paypal_donation:*:*:*:*:*:wordpress:*:*"
       ],
+      "extended-search-plugin": [
+        "cpe:2.3:a:jakesnyder:enhanced_search_box:*:*:*:*:*:wordpress:*:*"
+      ],
       "extensions-for-cf7": [
         "cpe:2.3:a:hasthemes:extensions_for_cf7:*:*:*:*:*:wordpress:*:*"
       ],
@@ -11571,6 +11631,7 @@
         "cpe:2.3:a:five_minute_webshop_project:five_minute_webshop:*:*:*:*:*:wordpress:*:*"
       ],
       "fl3r-feelbox": [
+        "cpe:2.3:a:armandofiore:fl3r_feelbox:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:fl3r-feelbox_project:fl3r-feelbox:*:*:*:*:*:wordpress:*:*"
       ],
       "flash-album-gallery": [
@@ -12235,6 +12296,9 @@
       "google-sitemap-plugin": [
         "cpe:2.3:a:bestwebsoft:google_sitemap:*:*:*:*:*:wordpress:*:*"
       ],
+      "google-website-translator": [
+        "cpe:2.3:a:prisna:google_website_translator:*:*:*:*:*:wordpress:*:*"
+      ],
       "googleanalytics": [
         "cpe:2.3:a:sharethis:dashboard_for_google_analytics:*:*:*:*:*:wordpress:*:*"
       ],
@@ -12634,6 +12698,9 @@
       "hunk-companion": [
         "cpe:2.3:a:themehunk:hunk_companion:*:*:*:*:*:wordpress:*:*"
       ],
+      "hurrytimer": [
+        "cpe:2.3:a:nabillemsieh:hurrytimer:*:*:*:*:*:wordpress:*:*"
+      ],
       "hyphenator": [
         "cpe:2.3:a:benedictb\\/maciejgryniuk:hyphenator:*:*:*:*:*:wordpress:*:*"
       ],
@@ -12907,6 +12974,9 @@
         "cpe:2.3:a:cm-wp:woody_code_snippets:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:webcraftic:woody_ad_snippets:*:*:*:*:*:wordpress:*:*"
       ],
+      "insert-php-code-snippet": [
+        "cpe:2.3:a:f1logic:insert_php_code_snippet:*:*:*:*:*:wordpress:*:*"
+      ],
       "insight-core": [
         "cpe:2.3:a:thememove:insight_core:*:*:*:*:*:wordpress:*:*"
       ],
@@ -13011,6 +13081,9 @@
       "ip-blacklist-cloud": [
         "cpe:2.3:a:ip_blacklist_cloud_project:ip_blacklist_cloud:*:*:*:*:*:wordpress:*:*"
       ],
+      "ip-vault-wp-firewall": [
+        "cpe:2.3:a:youtag:two-factor_authentication:*:*:*:*:*:wordpress:*:*"
+      ],
       "ip2location-country-blocker": [
         "cpe:2.3:a:ip2location:country_blocker:*:*:*:*:*:wordpress:*:*"
       ],
@@ -13557,6 +13630,9 @@
       "list-category-posts": [
         "cpe:2.3:a:fernandobriano:list_category_posts:*:*:*:*:*:wordpress:*:*"
       ],
+      "list-children": [
+        "cpe:2.3:a:sizeable:list_children:*:*:*:*:*:wordpress:*:*"
+      ],
       "list-last-changes": [
         "cpe:2.3:a:rolandbaer:list_last_changes:*:*:*:*:*:wordpress:*:*"
       ],
@@ -13854,6 +13930,9 @@
       "manual-image-crop": [
         "cpe:2.3:a:manual_image_crop_project:manual_image_crop:*:*:*:*:*:wordpress:*:*"
       ],
+      "mapfig-studio": [
+        "cpe:2.3:a:acugis:mapfig_studio:*:*:*:*:*:wordpress:*:*"
+      ],
       "mapping-multiple-urls-redirect-same-page": [
         "cpe:2.3:a:mapping_multiple_urls_redirect_same_page_project:mapping_multiple_urls_redirect_same_page:*:*:*:*:*:wordpress:*:*"
       ],
@@ -14237,6 +14316,9 @@
       "monetize": [
         "cpe:2.3:a:monetize_project:monetize:*:*:*:*:*:wordpress:*:*"
       ],
+      "monitor-chat": [
+        "cpe:2.3:a:edwardstoever:monitor.chat:*:*:*:*:*:wordpress:*:*"
+      ],
       "month-name-translation-benaceur": [
         "cpe:2.3:a:benaceur-php:month_name_translation_benaceur:*:*:*:*:*:wordpress:*:*"
       ],
@@ -14306,6 +14388,9 @@
       "mq-woocommerce-products-price-bulk-edit": [
         "cpe:2.3:a:mq-woocommerce-products-price-bulk-edit_project:mq-woocommerce-products-price-bulk-edit:*:*:*:*:*:wordpress:*:*"
       ],
+      "ms-registration": [
+        "cpe:2.3:a:alphaefficiencyteam:custom_login_and_registration:*:*:*:*:*:wordpress:*:*"
+      ],
       "ms-reviews": [
         "cpe:2.3:a:ms-reviews_project:ms-reviews:*:*:*:*:*:wordpress:*:*"
       ],
@@ -14438,7 +14523,7 @@
         "cpe:2.3:a:stormhillmedia:mybook_table_bookstore:*:*:*:*:*:wordpress:*:*"
       ],
       "mycred": [
-        "cpe:2.3:a:mycred:mycred:*:*:*:*:*:wordpress:*:*"
+        "cpe:2.3:a:wpexperts:mycred:*:*:*:*:*:wordpress:*:*"
       ],
       "mycryptocheckout": [
         "cpe:2.3:a:plainviewplugins:mycryptocheckout:*:*:*:*:*:wordpress:*:*"
@@ -14625,12 +14710,18 @@
       "ninjafirewall": [
         "cpe:2.3:a:nintechnet:ninjafirewall:*:*:*:*:*:wordpress:*:*"
       ],
+      "ninjateam-telegram": [
+        "cpe:2.3:a:ninjateam:chat_for_telegram:*:*:*:*:*:wordpress:*:*"
+      ],
       "nirweb-support": [
         "cpe:2.3:a:nirweb:nirweb_support:*:*:*:*:*:wordpress:*:*"
       ],
       "nitropack": [
         "cpe:2.3:a:nitropack:nitropack:*:*:*:*:*:wordpress:*:*"
       ],
+      "nix-anti-spam-light": [
+        "cpe:2.3:a:nixsolutions:nix_anti-spam_light:*:*:*:*:*:wordpress:*:*"
+      ],
       "nktagcloud": [
         "cpe:2.3:a:better_tag_cloud_project:better_tag_cloud:*:*:*:*:*:wordpress:*:*"
       ],
@@ -15186,6 +15277,9 @@
         "cpe:2.3:a:greentreelabs:gallery_photoblocks:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:wpchill:gallery_photoblocks:*:*:*:*:*:wordpress:*:*"
       ],
+      "photokit": [
+        "cpe:2.3:a:jackzhu:photokit:*:*:*:*:*:wordpress:*:*"
+      ],
       "photoshow": [
         "cpe:2.3:a:codepeople:smart_image_gallery:*:*:*:*:*:wordpress:*:*"
       ],
@@ -15511,6 +15605,9 @@
       "postman-smtp": [
         "cpe:2.3:a:postman-smtp_project:postman-smtp:*:*:*:*:*:wordpress:*:*"
       ],
+      "postmash": [
+        "cpe:2.3:a:jmash:postmash:*:*:*:*:*:wordpress:*:*"
+      ],
       "postmatic": [
         "cpe:2.3:a:gopostmatic:replyable:*:*:*:*:*:wordpress:*:*"
       ],
@@ -15761,6 +15858,9 @@
       "pure-chat": [
         "cpe:2.3:a:purechat:pure_chat:*:*:*:*:*:*:*:*"
       ],
+      "pure-css-circle-progress-bar": [
+        "cpe:2.3:a:shafayat:pure_css_circle_progress_bar:*:*:*:*:*:wordpress:*:*"
+      ],
       "purple-xmls-google-product-feed-for-woocommerce": [
         "cpe:2.3:a:dpl:product_feed_on_woocommerce_for_google\\,_awin\\,_shareasale\\,_bing\\,_and_more:*:*:*:*:*:wordpress:*:*"
       ],
@@ -15964,6 +16064,9 @@
       "react-webcam": [
         "cpe:2.3:a:react_webcam_project:react_webcam:*:*:*:*:*:wordpress:*:*"
       ],
+      "reaction-buttons": [
+        "cpe:2.3:a:jakob42:reaction_buttons:*:*:*:*:*:wordpress:*:*"
+      ],
       "read-and-understood": [
         "cpe:2.3:a:read_and_understood_project:read_and_understood:*:*:*:*:*:wordpress:*:*"
       ],
@@ -16124,6 +16227,9 @@
       "reservation-studio-widget": [
         "cpe:2.3:a:pvmg:reservation.studio:*:*:*:*:*:wordpress:*:*"
       ],
+      "reset": [
+        "cpe:2.3:a:smartzminds:reset:*:*:*:*:*:wordpress:*:*"
+      ],
       "resize-at-upload-plus": [
         "cpe:2.3:a:resize_at_upload_plus_project:resize_at_upload_plus:*:*:*:*:*:wordpress:*:*"
       ],
@@ -16527,6 +16633,9 @@
       "sellkit": [
         "cpe:2.3:a:artbees:sellkit:*:*:*:*:*:wordpress:*:*"
       ],
+      "send-email-only-on-reply-to-my-comment": [
+        "cpe:2.3:a:yasirwazir:send_email_only_on_reply_to_my_comment:*:*:*:*:*:wordpress:*:*"
+      ],
       "send-emails-with-mandrill": [
         "cpe:2.3:a:millermedia:mandrill:*:*:*:*:*:wordpress:*:*"
       ],
@@ -17092,6 +17201,9 @@
       "site-editor": [
         "cpe:2.3:a:siteeditor:site_editor:*:*:*:*:*:wordpress:*:*"
       ],
+      "site-mailer": [
+        "cpe:2.3:a:elementor:site_mailer:*:*:*:*:*:wordpress:*:*"
+      ],
       "site-offline": [
         "cpe:2.3:a:freehtmldesigns:site_offline:*:*:*:*:*:wordpress:*:*"
       ],
@@ -17780,6 +17892,9 @@
       "svg-support": [
         "cpe:2.3:a:benbodhi:svg_support:*:*:*:*:*:wordpress:*:*"
       ],
+      "svg-uploads-support": [
+        "cpe:2.3:a:ablyperu:svg_uploads_support:*:*:*:*:*:wordpress:*:*"
+      ],
       "svg-vector-icon-plugin": [
         "cpe:2.3:a:wp_svg_icons_project:wp_svg_icons:*:*:*:*:*:wordpress:*:*"
       ],
@@ -17859,6 +17974,7 @@
         "cpe:2.3:a:tainacan:tainacan:*:*:*:*:*:wordpress:*:*"
       ],
       "tarteaucitronjs": [
+        "cpe:2.3:a:amauri:tarteaucitron.io:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:tarteaucitron.js_-_cookies_legislation_\\\u0026_gdpr_project:tarteaucitron.js_-_cookies_legislation_\\\u0026_gdpr:*:*:*:*:*:wordpress:*:*"
       ],
       "taskbuilder": [
@@ -18106,6 +18222,9 @@
       "timeline-widget-addon-for-elementor": [
         "cpe:2.3:a:coolplugins:timeline_widget_for_elementor:*:*:*:*:*:wordpress:*:*"
       ],
+      "timer-countdown": [
+        "cpe:2.3:a:yaidier:countdown_timer:*:*:*:*:*:wordpress:*:*"
+      ],
       "timesheet": [
         "cpe:2.3:a:bestwebsoft:timesheet:*:*:*:*:*:wordpress:*:*"
       ],
@@ -18249,9 +18368,15 @@
       "tripetto": [
         "cpe:2.3:a:tripetto:tripetto:*:*:*:*:*:wordpress:*:*"
       ],
+      "tripplan": [
+        "cpe:2.3:a:checklist:trip_plan:*:*:*:*:*:wordpress:*:*"
+      ],
       "truebooker-appointment-booking": [
         "cpe:2.3:a:themetechmount:truebooker:*:*:*:*:*:wordpress:*:*"
       ],
+      "trx_addons": [
+        "cpe:2.3:a:themerex:addons:*:*:*:*:*:wordpress:*:*"
+      ],
       "ts-webfonts-for-conoha": [
         "cpe:2.3:a:gmo:typesquare_webfonts_for_conoha:*:*:*:*:*:wordpress:*:*"
       ],
@@ -18457,9 +18582,15 @@
       "ultimate-weather-plugin": [
         "cpe:2.3:a:ultimate-weather_project:ultimate-weather:*:*:*:*:*:wordpress:*:*"
       ],
+      "ultimate-woocommerce-auction-pro": [
+        "cpe:2.3:a:auctionplugin:ultimate_wordpress_auction_plugin:*:*:*:*:pro:wordpress:*:*"
+      ],
       "ultimate-wp-query-search-filter": [
         "cpe:2.3:a:ultimate_wp_query_search_filter_project:ultimate_wp_query_search_filter:*:*:*:*:*:wordpress:*:*"
       ],
+      "ultimate-youtube-video-player": [
+        "cpe:2.3:a:codelizar:ultimate_youtube_video_\\\u0026_shorts_player_with_vimeo:*:*:*:*:*:wordpress:*:*"
+      ],
       "ultra-companion": [
         "cpe:2.3:a:wpoperation:ultra_companion:*:*:*:*:*:wordpress:*:*"
       ],
@@ -19198,6 +19329,9 @@
       "woo-esto": [
         "cpe:2.3:a:rebing:woocommerce_esto:*:*:*:*:*:wordpress:*:*"
       ],
+      "woo-exfood": [
+        "cpe:2.3:a:exthemes:woocommerce_food:*:*:*:*:*:wordpress:*:*"
+      ],
       "woo-floating-cart-lite": [
         "cpe:2.3:a:xplodedthemes:xt_floating_cart_for_woocommerce:*:*:*:*:*:wordpress:*:*"
       ],
@@ -19267,6 +19401,9 @@
       "woo-shipping-dpd-baltic": [
         "cpe:2.3:a:dpdgroup:woocommerce_shipping:*:*:*:*:*:wordpress:*:*"
       ],
+      "woo-slider-pro-drag-drop-slider-builder-for-woocommerce": [
+        "cpe:2.3:a:binarycarpenter:woo_slider_pro:*:*:*:*:*:wordpress:*:*"
+      ],
       "woo-smart-compare": [
         "cpe:2.3:a:wpclever:wpc_smart_compare_for_woocommerce:*:*:*:*:*:wordpress:*:*"
       ],
@@ -19820,6 +19957,9 @@
         "cpe:2.3:a:kigurumi:csv_exporter:*:*:*:*:*:wordpress:*:*",
         "cpe:2.3:a:wp_csv_exporter_project:wp_csv_exporter:*:*:*:*:*:wordpress:*:*"
       ],
+      "wp-curriculo-vitae": [
+        "cpe:2.3:a:williamluis:wp-curriculo_vitae_free:*:*:*:*:*:wordpress:*:*"
+      ],
       "wp-custom-admin-interface": [
         "cpe:2.3:a:wp_custom_admin_interface_project:wp_custom_admin_interface:*:*:*:*:*:*:*:*"
       ],
@@ -19891,7 +20031,8 @@
         "cpe:2.3:a:display_users_project:display_users:*:*:*:*:*:wordpress:*:*"
       ],
       "wp-docs": [
-        "cpe:2.3:a:androidbubble:wp_docs:*:*:*:*:*:wordpress:*:*"
+        "cpe:2.3:a:androidbubble:wp_docs:*:*:*:*:*:wordpress:*:*",
+        "cpe:2.3:a:fahadmahmood:wp_docs:*:*:*:*:*:wordpress:*:*"
       ],
       "wp-domain-redirect": [
         "cpe:2.3:a:wp_domain_redirect_project:wp_domain_redirect:*:*:*:*:*:wordpress:*:*"
@@ -20795,6 +20936,9 @@
       "wp-table-builder": [
         "cpe:2.3:a:dotcamp:wp_table_builder:*:*:*:*:*:wordpress:*:*"
       ],
+      "wp-table-manager": [
+        "cpe:2.3:a:joomunited:wp_table_manager:*:*:*:*:*:wordpress:*:*"
+      ],
       "wp-table-reloaded": [
         "cpe:2.3:a:wp-table_reloaded_project:wp-table_reloaded:*:*:*:*:*:wordpress:*:*"
       ],
@@ -21139,6 +21283,9 @@
       "wppizza": [
         "cpe:2.3:a:wp-pizza:wppizza:*:*:*:*:*:wordpress:*:*"
       ],
+      "wpquiz": [
+        "cpe:2.3:a:bauc:wpquiz:*:*:*:*:*:wordpress:*:*"
+      ],
       "wprequal": [
         "cpe:2.3:a:kevinbrent:wprequal:*:*:*:*:*:wordpress:*:*"
       ],
@@ -21169,6 +21316,9 @@
       "wpsolr-search-engine": [
         "cpe:2.3:a:wpsolr:wpsolr-search-engine:*:*:*:*:*:wordpress:*:*"
       ],
+      "wpstickybar-sticky-bar-sticky-header": [
+        "cpe:2.3:a:a17lab:wpstickybar:*:*:*:*:*:wordpress:*:*"
+      ],
       "wpstream": [
         "cpe:2.3:a:wpstream:wpstream:*:*:*:*:*:wordpress:*:*"
       ],
@@ -21276,6 +21426,9 @@
       "xtremelocator": [
         "cpe:2.3:a:xtremelocator:xtremelocator:*:*:*:*:*:wordpress:*:*"
       ],
+      "xv-random-quotes": [
+        "cpe:2.3:a:xavivars:xv_random_quotes:*:*:*:*:*:wordpress:*:*"
+      ],
       "yabp": [
         "cpe:2.3:a:tromit:yabp:*:*:*:*:*:wordpress:*:*"
       ],
@@ -21362,6 +21515,9 @@
       "yotpo-social-reviews-for-woocommerce": [
         "cpe:2.3:a:yotpo:yotpo:*:*:*:*:*:wordpress:*:*"
       ],
+      "yotuwp-easy-youtube-embed": [
+        "cpe:2.3:a:yotuwp:video_gallery:*:*:*:*:*:wordpress:*:*"
+      ],
       "yourchannel": [
         "cpe:2.3:a:plugin:yourchannel:*:*:*:*:*:wordpress:*:*"
       ],
@@ -21782,6 +21938,9 @@
       "pressmart": [
         "cpe:2.3:a:presslayouts:pressmart:*:*:*:*:*:wordpress:*:*"
       ],
+      "puzzles": [
+        "cpe:2.3:a:themerex:puzzles:*:*:*:*:*:wordpress:*:*"
+      ],
       "regina-lite": [
         "cpe:2.3:a:machothemes:regina_lite:*:*:*:*:*:wordpress:*:*"
       ],

syft/pkg/cataloger/internal/cpegenerate/dictionary/generate_index.go

@@ -1,3 +0,0 @@
-package dictionary
-
-//go:generate go run ./index-generator/ -o data/cpe-index.json

syft/pkg/cataloger/internal/cpegenerate/dictionary/index-generator/.gitignore

@@ -0,0 +1,6 @@
+# ORAS cache directory - raw CPE data from NVD API
+.cpe-cache/
+
+# Build artifacts
+index-generator
+.tmp-*

syft/pkg/cataloger/internal/cpegenerate/dictionary/index-generator/cache_manager.go

@@ -0,0 +1,370 @@
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"time"
+)
+
+const cacheDir = ".cpe-cache"
+
+// IncrementMetadata tracks a single fetch increment for a monthly batch
+type IncrementMetadata struct {
+	FetchedAt        time.Time `json:"fetchedAt"`
+	LastModStartDate time.Time `json:"lastModStartDate"`
+	LastModEndDate   time.Time `json:"lastModEndDate"`
+	Products         int       `json:"products"`
+	StartIndex       int       `json:"startIndex"` // API pagination start index
+	EndIndex         int       `json:"endIndex"`   // API pagination end index (last fetched)
+}
+
+// MonthlyBatchMetadata tracks all increments for a specific month
+type MonthlyBatchMetadata struct {
+	Complete      bool                `json:"complete"`
+	TotalProducts int                 `json:"totalProducts"`
+	Increments    []IncrementMetadata `json:"increments"`
+}
+
+// CacheMetadata tracks the state of the CPE cache using monthly time-based organization
+type CacheMetadata struct {
+	LastFullRefresh time.Time                        `json:"lastFullRefresh"`
+	LastStartIndex  int                              `json:"lastStartIndex"` // last successfully processed startIndex for resume
+	TotalProducts   int                              `json:"totalProducts"`
+	MonthlyBatches  map[string]*MonthlyBatchMetadata `json:"monthlyBatches"` // key is "YYYY-MM"
+}
+
+// CacheManager handles local caching of CPE data
+type CacheManager struct {
+	cacheDir string
+}
+
+// NewCacheManager creates a new cache manager
+func NewCacheManager() *CacheManager {
+	return &CacheManager{
+		cacheDir: cacheDir,
+	}
+}
+
+// EnsureCacheDir ensures the cache directory exists
+func (m *CacheManager) EnsureCacheDir() error {
+	if err := os.MkdirAll(m.cacheDir, 0755); err != nil {
+		return fmt.Errorf("failed to create cache directory: %w", err)
+	}
+	return nil
+}
+
+// LoadMetadata loads the cache metadata
+func (m *CacheManager) LoadMetadata() (*CacheMetadata, error) {
+	metadataPath := filepath.Join(m.cacheDir, "metadata.json")
+
+	// check if metadata file exists
+	if _, err := os.Stat(metadataPath); os.IsNotExist(err) {
+		// return empty metadata for first run
+		return &CacheMetadata{
+			LastFullRefresh: time.Time{},
+			TotalProducts:   0,
+			MonthlyBatches:  make(map[string]*MonthlyBatchMetadata),
+		}, nil
+	}
+
+	data, err := os.ReadFile(metadataPath)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read metadata: %w", err)
+	}
+
+	var metadata CacheMetadata
+	if err := json.Unmarshal(data, &metadata); err != nil {
+		return nil, fmt.Errorf("failed to unmarshal metadata: %w", err)
+	}
+
+	// ensure MonthlyBatches map is initialized
+	if metadata.MonthlyBatches == nil {
+		metadata.MonthlyBatches = make(map[string]*MonthlyBatchMetadata)
+	}
+
+	return &metadata, nil
+}
+
+// SaveMetadata saves the cache metadata
+func (m *CacheManager) SaveMetadata(metadata *CacheMetadata) error {
+	if err := m.EnsureCacheDir(); err != nil {
+		return err
+	}
+
+	metadataPath := filepath.Join(m.cacheDir, "metadata.json")
+
+	data, err := json.MarshalIndent(metadata, "", "  ")
+	if err != nil {
+		return fmt.Errorf("failed to marshal metadata: %w", err)
+	}
+
+	if err := os.WriteFile(metadataPath, data, 0600); err != nil {
+		return fmt.Errorf("failed to write metadata: %w", err)
+	}
+
+	return nil
+}
+
+// SaveProductsToMonthlyFile saves products to a monthly file (initial.json or YYYY-MM.json)
+// uses atomic write pattern with temp file + rename for safety
+func (m *CacheManager) SaveProductsToMonthlyFile(filename string, products []NVDProduct) error {
+	if err := m.EnsureCacheDir(); err != nil {
+		return err
+	}
+
+	filePath := filepath.Join(m.cacheDir, filename)
+	tempPath := filePath + ".tmp"
+
+	// marshal products to JSON
+	data, err := json.MarshalIndent(products, "", "  ")
+	if err != nil {
+		return fmt.Errorf("failed to marshal products: %w", err)
+	}
+
+	// write to temp file first
+	if err := os.WriteFile(tempPath, data, 0600); err != nil {
+		return fmt.Errorf("failed to write temp file: %w", err)
+	}
+
+	// atomic rename
+	if err := os.Rename(tempPath, filePath); err != nil {
+		// cleanup temp file on error
+		_ = os.Remove(tempPath)
+		return fmt.Errorf("failed to rename temp file: %w", err)
+	}
+
+	return nil
+}
+
+// LoadMonthlyFile loads products from a monthly file
+func (m *CacheManager) LoadMonthlyFile(filename string) ([]NVDProduct, error) {
+	filePath := filepath.Join(m.cacheDir, filename)
+
+	data, err := os.ReadFile(filePath)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return []NVDProduct{}, nil
+		}
+		return nil, fmt.Errorf("failed to read %s: %w", filename, err)
+	}
+
+	var products []NVDProduct
+	if err := json.Unmarshal(data, &products); err != nil {
+		return nil, fmt.Errorf("failed to unmarshal %s: %w", filename, err)
+	}
+
+	return products, nil
+}
+
+// GetMonthKey returns the "YYYY-MM" key for a given time
+func GetMonthKey(t time.Time) string {
+	return t.Format("2006-01")
+}
+
+// SaveProducts saves products grouped by modification month
+// this is called after fetching from the API to organize products into monthly files
+func (m *CacheManager) SaveProducts(products []NVDProduct, isFullRefresh bool, metadata *CacheMetadata, increment IncrementMetadata) error {
+	if len(products) == 0 {
+		return nil
+	}
+
+	if isFullRefresh {
+		return m.saveFullRefresh(products, metadata)
+	}
+
+	return m.saveIncrementalUpdate(products, metadata, increment)
+}
+
+// saveFullRefresh saves all products to initial.json
+func (m *CacheManager) saveFullRefresh(products []NVDProduct, metadata *CacheMetadata) error {
+	if err := m.SaveProductsToMonthlyFile("initial.json", products); err != nil {
+		return fmt.Errorf("failed to save initial.json: %w", err)
+	}
+
+	metadata.LastFullRefresh = time.Now()
+	metadata.TotalProducts = len(products)
+	metadata.LastStartIndex = 0 // reset on full refresh
+	metadata.MonthlyBatches = make(map[string]*MonthlyBatchMetadata)
+
+	return nil
+}
+
+// saveIncrementalUpdate saves products grouped by modification month to monthly files
+func (m *CacheManager) saveIncrementalUpdate(products []NVDProduct, metadata *CacheMetadata, increment IncrementMetadata) error {
+	productsByMonth, err := groupProductsByMonth(products)
+	if err != nil {
+		return err
+	}
+
+	for monthKey, monthProducts := range productsByMonth {
+		if err := m.saveMonthlyBatch(monthKey, monthProducts, metadata, increment); err != nil {
+			return err
+		}
+	}
+
+	// update last processed index for resume capability
+	metadata.LastStartIndex = increment.EndIndex
+
+	return nil
+}
+
+// groupProductsByMonth groups products by their lastModified month
+func groupProductsByMonth(products []NVDProduct) (map[string][]NVDProduct, error) {
+	productsByMonth := make(map[string][]NVDProduct)
+
+	for _, product := range products {
+		lastMod, err := time.Parse(time.RFC3339, product.CPE.LastModified)
+		if err != nil {
+			return nil, fmt.Errorf("failed to parse lastModified for %s: %w", product.CPE.CPENameID, err)
+		}
+
+		monthKey := GetMonthKey(lastMod)
+		productsByMonth[monthKey] = append(productsByMonth[monthKey], product)
+	}
+
+	return productsByMonth, nil
+}
+
+// saveMonthlyBatch saves products for a specific month, merging with existing data
+func (m *CacheManager) saveMonthlyBatch(monthKey string, monthProducts []NVDProduct, metadata *CacheMetadata, increment IncrementMetadata) error {
+	filename := monthKey + ".json"
+
+	// load existing products for this month
+	existing, err := m.LoadMonthlyFile(filename)
+	if err != nil {
+		return fmt.Errorf("failed to load existing %s: %w", filename, err)
+	}
+
+	// merge products (newer wins)
+	merged := mergeProducts(existing, monthProducts)
+
+	// atomically save merged products
+	if err := m.SaveProductsToMonthlyFile(filename, merged); err != nil {
+		return fmt.Errorf("failed to save %s: %w", filename, err)
+	}
+
+	// update metadata
+	updateMonthlyBatchMetadata(metadata, monthKey, monthProducts, merged, increment)
+
+	return nil
+}
+
+// mergeProducts deduplicates products by CPENameID, with newer products overwriting older ones
+func mergeProducts(existing, updated []NVDProduct) []NVDProduct {
+	productMap := make(map[string]NVDProduct)
+
+	for _, p := range existing {
+		productMap[p.CPE.CPENameID] = p
+	}
+	for _, p := range updated {
+		productMap[p.CPE.CPENameID] = p
+	}
+
+	merged := make([]NVDProduct, 0, len(productMap))
+	for _, p := range productMap {
+		merged = append(merged, p)
+	}
+
+	return merged
+}
+
+// updateMonthlyBatchMetadata updates the metadata for a monthly batch
+func updateMonthlyBatchMetadata(metadata *CacheMetadata, monthKey string, newProducts, allProducts []NVDProduct, increment IncrementMetadata) {
+	if metadata.MonthlyBatches[monthKey] == nil {
+		metadata.MonthlyBatches[monthKey] = &MonthlyBatchMetadata{
+			Complete:   false,
+			Increments: []IncrementMetadata{},
+		}
+	}
+
+	batchMeta := metadata.MonthlyBatches[monthKey]
+	batchMeta.Increments = append(batchMeta.Increments, IncrementMetadata{
+		FetchedAt:        increment.FetchedAt,
+		LastModStartDate: increment.LastModStartDate,
+		LastModEndDate:   increment.LastModEndDate,
+		Products:         len(newProducts),
+		StartIndex:       increment.StartIndex,
+		EndIndex:         increment.EndIndex,
+	})
+	batchMeta.TotalProducts = len(allProducts)
+}
+
+// LoadAllProducts loads and merges all cached products from monthly files
+// returns a deduplicated slice of products (newer products override older ones by CPENameID)
+func (m *CacheManager) LoadAllProducts() ([]NVDProduct, error) {
+	// check if cache directory exists
+	if _, err := os.Stat(m.cacheDir); os.IsNotExist(err) {
+		return []NVDProduct{}, nil
+	}
+
+	productMap := make(map[string]NVDProduct)
+
+	// load initial.json first (if it exists)
+	initial, err := m.LoadMonthlyFile("initial.json")
+	if err != nil {
+		return nil, fmt.Errorf("failed to load initial.json: %w", err)
+	}
+
+	for _, p := range initial {
+		productMap[p.CPE.CPENameID] = p
+	}
+
+	// load all monthly files (YYYY-MM.json)
+	entries, err := os.ReadDir(m.cacheDir)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read cache directory: %w", err)
+	}
+
+	for _, entry := range entries {
+		if entry.IsDir() || filepath.Ext(entry.Name()) != ".json" {
+			continue
+		}
+
+		// skip metadata.json and initial.json
+		if entry.Name() == "metadata.json" || entry.Name() == "initial.json" {
+			continue
+		}
+
+		// load monthly file
+		products, err := m.LoadMonthlyFile(entry.Name())
+		if err != nil {
+			return nil, fmt.Errorf("failed to load %s: %w", entry.Name(), err)
+		}
+
+		// merge products (newer wins based on lastModified)
+		for _, p := range products {
+			existing, exists := productMap[p.CPE.CPENameID]
+			if !exists {
+				productMap[p.CPE.CPENameID] = p
+				continue
+			}
+
+			// compare lastModified timestamps to keep the newer one
+			newMod, _ := time.Parse(time.RFC3339, p.CPE.LastModified)
+			existingMod, _ := time.Parse(time.RFC3339, existing.CPE.LastModified)
+
+			if newMod.After(existingMod) {
+				productMap[p.CPE.CPENameID] = p
+			}
+		}
+	}
+
+	// convert map to slice
+	allProducts := make([]NVDProduct, 0, len(productMap))
+	for _, p := range productMap {
+		allProducts = append(allProducts, p)
+	}
+
+	return allProducts, nil
+}
+
+// CleanCache removes the local cache directory
+func (m *CacheManager) CleanCache() error {
+	if err := os.RemoveAll(m.cacheDir); err != nil {
+		return fmt.Errorf("failed to clean cache: %w", err)
+	}
+	fmt.Println("Cache cleaned successfully")
+	return nil
+}

syft/pkg/cataloger/internal/cpegenerate/dictionary/index-generator/cache_manager_test.go

@@ -0,0 +1,319 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestCacheManager_MonthlyFileOperations(t *testing.T) {
+	tmpDir := t.TempDir()
+	cacheManager := &CacheManager{cacheDir: tmpDir}
+
+	testProducts := []NVDProduct{
+		{
+			CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product1:1.0:*:*:*:*:*:*:*",
+				CPENameID:    "product1-id",
+				LastModified: "2024-11-15T10:00:00.000Z",
+				Titles:       []NVDTitle{{Title: "Test Product 1", Lang: "en"}},
+			},
+		},
+		{
+			CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product2:2.0:*:*:*:*:*:*:*",
+				CPENameID:    "product2-id",
+				LastModified: "2024-11-20T10:00:00.000Z",
+				Titles:       []NVDTitle{{Title: "Test Product 2", Lang: "en"}},
+			},
+		},
+	}
+
+	t.Run("save and load monthly file", func(t *testing.T) {
+		err := cacheManager.SaveProductsToMonthlyFile("2024-11.json", testProducts)
+		require.NoError(t, err)
+
+		expectedPath := filepath.Join(tmpDir, "2024-11.json")
+		require.FileExists(t, expectedPath)
+
+		loaded, err := cacheManager.LoadMonthlyFile("2024-11.json")
+		require.NoError(t, err)
+		require.Len(t, loaded, 2)
+		assert.Equal(t, testProducts[0].CPE.CPEName, loaded[0].CPE.CPEName)
+		assert.Equal(t, testProducts[1].CPE.CPEName, loaded[1].CPE.CPEName)
+	})
+
+	t.Run("atomic save with temp file", func(t *testing.T) {
+		err := cacheManager.SaveProductsToMonthlyFile("2024-12.json", testProducts)
+		require.NoError(t, err)
+
+		// temp file should not exist after successful save
+		tempPath := filepath.Join(tmpDir, "2024-12.json.tmp")
+		require.NoFileExists(t, tempPath)
+
+		// actual file should exist
+		finalPath := filepath.Join(tmpDir, "2024-12.json")
+		require.FileExists(t, finalPath)
+	})
+
+	t.Run("load non-existent file returns empty", func(t *testing.T) {
+		loaded, err := cacheManager.LoadMonthlyFile("2025-01.json")
+		require.NoError(t, err)
+		assert.Empty(t, loaded)
+	})
+}
+
+func TestCacheManager_Metadata(t *testing.T) {
+	tmpDir := t.TempDir()
+	cacheManager := &CacheManager{cacheDir: tmpDir}
+
+	t.Run("load metadata on first run", func(t *testing.T) {
+		metadata, err := cacheManager.LoadMetadata()
+		require.NoError(t, err)
+		require.NotNil(t, metadata)
+
+		assert.NotNil(t, metadata.MonthlyBatches)
+		assert.True(t, metadata.LastFullRefresh.IsZero())
+		assert.Equal(t, 0, metadata.LastStartIndex)
+		assert.Equal(t, 0, metadata.TotalProducts)
+	})
+
+	t.Run("save and load metadata with monthly batches", func(t *testing.T) {
+		now := time.Now()
+		metadata := &CacheMetadata{
+			LastFullRefresh: now,
+			LastStartIndex:  4000,
+			TotalProducts:   1500,
+			MonthlyBatches: map[string]*MonthlyBatchMetadata{
+				"2024-11": {
+					Complete:      true,
+					TotalProducts: 1000,
+					Increments: []IncrementMetadata{
+						{
+							FetchedAt:        now,
+							LastModStartDate: now.Add(-24 * time.Hour),
+							LastModEndDate:   now,
+							Products:         1000,
+							StartIndex:       0,
+							EndIndex:         2000,
+						},
+					},
+				},
+				"2024-12": {
+					Complete:      false,
+					TotalProducts: 500,
+					Increments: []IncrementMetadata{
+						{
+							FetchedAt:        now,
+							LastModStartDate: now.Add(-12 * time.Hour),
+							LastModEndDate:   now,
+							Products:         500,
+							StartIndex:       0,
+							EndIndex:         1000,
+						},
+					},
+				},
+			},
+		}
+
+		err := cacheManager.SaveMetadata(metadata)
+		require.NoError(t, err)
+
+		loadedMetadata, err := cacheManager.LoadMetadata()
+		require.NoError(t, err)
+
+		assert.Equal(t, metadata.TotalProducts, loadedMetadata.TotalProducts)
+		assert.Equal(t, metadata.LastStartIndex, loadedMetadata.LastStartIndex)
+		assert.Equal(t, 2, len(loadedMetadata.MonthlyBatches))
+		assert.True(t, loadedMetadata.MonthlyBatches["2024-11"].Complete)
+		assert.False(t, loadedMetadata.MonthlyBatches["2024-12"].Complete)
+		assert.Equal(t, 1000, loadedMetadata.MonthlyBatches["2024-11"].TotalProducts)
+		assert.Len(t, loadedMetadata.MonthlyBatches["2024-11"].Increments, 1)
+	})
+}
+
+func TestCacheManager_LoadAllProducts(t *testing.T) {
+	tmpDir := t.TempDir()
+	cacheManager := &CacheManager{cacheDir: tmpDir}
+
+	t.Run("load and merge monthly files", func(t *testing.T) {
+		// save initial.json with base products
+		initialProducts := []NVDProduct{
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product1:*:*:*:*:*:*:*:*",
+				CPENameID:    "product1-id",
+				LastModified: "2024-10-01T10:00:00.000Z",
+			}},
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product2:*:*:*:*:*:*:*:*",
+				CPENameID:    "product2-id",
+				LastModified: "2024-10-15T10:00:00.000Z",
+			}},
+		}
+		err := cacheManager.SaveProductsToMonthlyFile("initial.json", initialProducts)
+		require.NoError(t, err)
+
+		// save 2024-11.json with updated product2 and new product3
+		novemberProducts := []NVDProduct{
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product2:*:*:*:*:*:*:*:*",
+				CPENameID:    "product2-id",
+				LastModified: "2024-11-05T10:00:00.000Z", // newer version
+			}},
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product3:*:*:*:*:*:*:*:*",
+				CPENameID:    "product3-id",
+				LastModified: "2024-11-10T10:00:00.000Z",
+			}},
+		}
+		err = cacheManager.SaveProductsToMonthlyFile("2024-11.json", novemberProducts)
+		require.NoError(t, err)
+
+		// load all products
+		allProducts, err := cacheManager.LoadAllProducts()
+		require.NoError(t, err)
+
+		// should have 3 unique products (product2 from Nov overwrites Oct version)
+		require.Len(t, allProducts, 3)
+
+		// verify we got all products
+		cpeNames := make(map[string]string) // CPENameID -> LastModified
+		for _, product := range allProducts {
+			cpeNames[product.CPE.CPENameID] = product.CPE.LastModified
+		}
+
+		assert.Contains(t, cpeNames, "product1-id")
+		assert.Contains(t, cpeNames, "product2-id")
+		assert.Contains(t, cpeNames, "product3-id")
+
+		// product2 should be the newer version from November
+		assert.Equal(t, "2024-11-05T10:00:00.000Z", cpeNames["product2-id"])
+	})
+
+	t.Run("empty directory", func(t *testing.T) {
+		emptyDir := t.TempDir()
+		emptyCache := &CacheManager{cacheDir: emptyDir}
+
+		allProducts, err := emptyCache.LoadAllProducts()
+		require.NoError(t, err)
+		assert.Empty(t, allProducts)
+	})
+}
+
+func TestCacheManager_CleanCache(t *testing.T) {
+	tmpDir := t.TempDir()
+	cacheManager := &CacheManager{cacheDir: tmpDir}
+
+	// create some cache files
+	testProducts := []NVDProduct{
+		{CPE: NVDProductDetails{
+			CPEName:      "cpe:2.3:a:vendor:product:*:*:*:*:*:*:*:*",
+			CPENameID:    "test-id",
+			LastModified: "2024-11-01T10:00:00.000Z",
+		}},
+	}
+	err := cacheManager.SaveProductsToMonthlyFile("initial.json", testProducts)
+	require.NoError(t, err)
+
+	// verify cache exists
+	require.DirExists(t, tmpDir)
+
+	// clean cache
+	err = cacheManager.CleanCache()
+	require.NoError(t, err)
+
+	// verify cache is removed
+	_, err = os.Stat(tmpDir)
+	assert.True(t, os.IsNotExist(err))
+}
+
+func TestCacheManager_SaveProducts(t *testing.T) {
+	tmpDir := t.TempDir()
+	cacheManager := &CacheManager{cacheDir: tmpDir}
+
+	t.Run("full refresh saves to initial.json", func(t *testing.T) {
+		metadata := &CacheMetadata{
+			MonthlyBatches: make(map[string]*MonthlyBatchMetadata),
+		}
+
+		products := []NVDProduct{
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product1:*:*:*:*:*:*:*:*",
+				CPENameID:    "p1",
+				LastModified: "2024-10-01T10:00:00.000Z",
+			}},
+		}
+
+		increment := IncrementMetadata{
+			FetchedAt: time.Now(),
+			Products:  1,
+		}
+
+		err := cacheManager.SaveProducts(products, true, metadata, increment)
+		require.NoError(t, err)
+
+		// verify initial.json exists
+		initialPath := filepath.Join(tmpDir, "initial.json")
+		require.FileExists(t, initialPath)
+
+		// verify metadata updated
+		assert.NotZero(t, metadata.LastFullRefresh)
+		assert.Equal(t, 1, metadata.TotalProducts)
+		assert.Empty(t, metadata.MonthlyBatches)
+	})
+
+	t.Run("incremental update groups by month", func(t *testing.T) {
+		metadata := &CacheMetadata{
+			LastFullRefresh: time.Now().Add(-30 * 24 * time.Hour),
+			MonthlyBatches:  make(map[string]*MonthlyBatchMetadata),
+		}
+
+		products := []NVDProduct{
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product1:*:*:*:*:*:*:*:*",
+				CPENameID:    "p1",
+				LastModified: "2024-11-05T10:00:00.000Z",
+			}},
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product2:*:*:*:*:*:*:*:*",
+				CPENameID:    "p2",
+				LastModified: "2024-11-15T10:00:00.000Z",
+			}},
+			{CPE: NVDProductDetails{
+				CPEName:      "cpe:2.3:a:vendor:product3:*:*:*:*:*:*:*:*",
+				CPENameID:    "p3",
+				LastModified: "2024-12-01T10:00:00.000Z",
+			}},
+		}
+
+		increment := IncrementMetadata{
+			FetchedAt: time.Now(),
+			Products:  3,
+		}
+
+		err := cacheManager.SaveProducts(products, false, metadata, increment)
+		require.NoError(t, err)
+
+		// verify monthly files exist
+		nov2024Path := filepath.Join(tmpDir, "2024-11.json")
+		dec2024Path := filepath.Join(tmpDir, "2024-12.json")
+		require.FileExists(t, nov2024Path)
+		require.FileExists(t, dec2024Path)
+
+		// verify metadata has monthly batches
+		assert.Len(t, metadata.MonthlyBatches, 2)
+		assert.Contains(t, metadata.MonthlyBatches, "2024-11")
+		assert.Contains(t, metadata.MonthlyBatches, "2024-12")
+
+		// verify 2024-11 has 2 products
+		assert.Equal(t, 2, metadata.MonthlyBatches["2024-11"].TotalProducts)
+		assert.Len(t, metadata.MonthlyBatches["2024-11"].Increments, 1)
+
+		// verify 2024-12 has 1 product
+		assert.Equal(t, 1, metadata.MonthlyBatches["2024-12"].TotalProducts)
+	})
+}

syft/pkg/cataloger/internal/cpegenerate/dictionary/index-generator/generate.go

@@ -1,11 +1,6 @@
 package main
 
 import (
-	"compress/gzip"
-	"encoding/json"
-	"encoding/xml"
-	"fmt"
-	"io"
 	"log"
 	"slices"
 	"strings"
@@ -15,39 +10,6 @@ import (
 	"github.com/anchore/syft/syft/pkg/cataloger/internal/cpegenerate/dictionary"
 )
 
-func generateIndexedDictionaryJSON(rawGzipData io.Reader) ([]byte, error) {
-	gzipReader, err := gzip.NewReader(rawGzipData)
-	if err != nil {
-		return nil, fmt.Errorf("unable to decompress CPE dictionary: %w", err)
-	}
-	defer gzipReader.Close()
-
-	// Read XML data
-	data, err := io.ReadAll(gzipReader)
-	if err != nil {
-		return nil, fmt.Errorf("unable to read CPE dictionary: %w", err)
-	}
-
-	// Unmarshal XML
-	var cpeList CpeList
-	if err := xml.Unmarshal(data, &cpeList); err != nil {
-		return nil, fmt.Errorf("unable to unmarshal CPE dictionary XML: %w", err)
-	}
-
-	// Filter out data that's not applicable here
-	cpeList = filterCpeList(cpeList)
-
-	// Create indexed dictionary to help with looking up CPEs
-	indexedDictionary := indexCPEList(cpeList)
-
-	// Convert to JSON
-	jsonData, err := json.MarshalIndent(indexedDictionary, "", "  ")
-	if err != nil {
-		return nil, fmt.Errorf("unable to marshal CPE dictionary to JSON: %w", err)
-	}
-	return jsonData, nil
-}
-
 // filterCpeList removes CPE items that are not applicable to software packages.
 func filterCpeList(cpeList CpeList) CpeList {
 	var processedCpeList CpeList