Deduplicate digests from user configuration (#2522)

* deduplicate digests from user configuration

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* backout pointer reciever change on imageSource

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

---------

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

.binny.yaml

@@ -90,7 +90,7 @@ tools:
 
   - name: gh
     version:
-      want: v2.42.0
+      want: v2.42.1
     method: github-release
     with:
       repo: cli/cli

.github/workflows/benchmark-testing.yaml

@@ -23,7 +23,7 @@ jobs:
         uses: ./.github/actions/bootstrap
 
       - name: Restore base benchmark result
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: test/results/benchmark-main.txt
           # use base sha for PR or new commit hash for main push in benchmark result key
@@ -39,7 +39,7 @@ jobs:
           OUTPUT="${OUTPUT//$'\r'/'%0D'}" # URL encode all '\r' characters
           echo "result=$OUTPUT" >> $GITHUB_OUTPUT
 
-      - uses: actions/upload-artifact@1eb3cb2b3e0f29609092a73eb033bb759a334595 # v4.1.0
+      - uses: actions/upload-artifact@694cdabd8bdb0f10b2cea11669e1bf5453eed0a6 # v4.2.0
         with:
           name: benchmark-test-results
           path: test/results/**/*

.github/workflows/codeql-analysis.yml

@@ -45,7 +45,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/init@0b21cf2492b6b02c465a3e5d7c473717ad7721ba #v3.23.1
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -56,7 +56,7 @@ 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@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/autobuild@0b21cf2492b6b02c465a3e5d7c473717ad7721ba #v3.23.1
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -70,4 +70,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@e5f05b81d5b6ff8cfa111c80c22c5fd02a384118 #v3.23.0
+      uses: github/codeql-action/analyze@0b21cf2492b6b02c465a3e5d7c473717ad7721ba #v3.23.1

.github/workflows/dependabot-automation.yaml

@@ -0,0 +1,10 @@
+name: Dependabot Automation
+on:
+  pull_request:
+
+permissions:
+  pull-requests: write
+
+jobs:
+  run:
+    uses: anchore/workflows/.github/workflows/dependabot-automation.yaml@main

.github/workflows/release.yaml

@@ -141,7 +141,7 @@ jobs:
           AWS_ACCESS_KEY_ID: ${{ secrets.TOOLBOX_AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.TOOLBOX_AWS_SECRET_ACCESS_KEY }}
 
-      - uses: anchore/sbom-action@c7f031d9249a826a082ea14c79d3b686a51d485a #v0.15.3
+      - uses: anchore/sbom-action@41f7a6c033dbcdf78917f23b652c8b8146298c85 #v0.15.4
         continue-on-error: true
         with:
           artifact-name: sbom.spdx.json

.github/workflows/validations.yaml

@@ -37,31 +37,31 @@ jobs:
         uses: ./.github/actions/bootstrap
 
       - name: Restore Java test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: syft/pkg/cataloger/java/test-fixtures/java-builds/packages
           key: ${{ runner.os }}-unit-java-cache-${{ hashFiles( 'syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint' ) }}
 
       - name: Restore RPM test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: syft/pkg/cataloger/redhat/test-fixtures/rpms
           key: ${{ runner.os }}-unit-rpm-cache-${{ hashFiles( 'syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint' ) }}
 
       - name: Restore go binary test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: syft/pkg/cataloger/golang/test-fixtures/archs/binaries
           key: ${{ runner.os }}-unit-go-binaries-cache-${{ hashFiles( 'syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint' ) }}
 
       - name: Restore binary cataloger test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: syft/pkg/cataloger/binary/test-fixtures/classifiers/bin
           key: ${{ runner.os }}-unit-binary-cataloger-cache-${{ hashFiles( 'syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint' ) }}
 
       - name: Restore Kernel test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: syft/pkg/cataloger/kernel/test-fixtures/cache
           key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
@@ -84,7 +84,7 @@ jobs:
         run: make validate-cyclonedx-schema
 
       - name: Restore integration test cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: ${{ github.workspace }}/test/integration/test-fixtures/cache
           key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('test/integration/test-fixtures/cache.fingerprint') }}
@@ -110,7 +110,7 @@ jobs:
       # why not use actions/upload-artifact? It is very slow (3 minutes to upload ~600MB of data, vs 10 seconds with this approach).
       # see https://github.com/actions/upload-artifact/issues/199 for more info
       - name: Upload snapshot artifacts
-        uses: actions/cache/save@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache/save@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           # we need to preserve the snapshot data itself as well as the task data that confirms if the
           # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
@@ -134,7 +134,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: |
             snapshot
@@ -152,7 +152,7 @@ jobs:
 
       - name: Restore install.sh test image cache
         id: install-test-image-cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: ${{ github.workspace }}/test/install/cache
           key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
@@ -187,7 +187,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: |
             snapshot
@@ -202,7 +202,7 @@ jobs:
 
       - name: Restore docker image cache for compare testing
         id: mac-compare-testing-cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: image.tar
           key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
@@ -226,14 +226,14 @@ jobs:
         uses: ./.github/actions/bootstrap
 
       - name: Restore CLI test-fixture cache
-        uses: actions/cache@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: ${{ github.workspace }}/test/cli/test-fixtures/cache
           key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@e12d46a63a90f2fae62d114769bbf2a179198b5c #v3.3.3
+        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
           path: |
             snapshot

README.md

@@ -502,19 +502,20 @@ Configuration options (example values are the default):
 
 ```yaml
 # the output format(s) of the SBOM report (options: syft-table, syft-text, syft-json, spdx-json, ...)
-# same as -o, --output, and SYFT_OUTPUT env var
 # to specify multiple output files in differing formats, use a list:
 # output:
 #   - "syft-json=<syft-json-output-file>"
 #   - "spdx-json=<spdx-json-output-file>"
-output: "syft-table"
+# SYFT_OUTPUT env var / -o, --output flags
+output: 
+  - "syft-table"
 
 # suppress all output (except for the SBOM report)
-# same as -q ; SYFT_QUIET env var
+# SYFT_QUIET env var / -q flag
 quiet: false
 
 # enable/disable checking for application updates on startup
-# same as SYFT_CHECK_FOR_APP_UPDATE env var
+# SYFT_CHECK_FOR_APP_UPDATE env var 
 check-for-app-update: true
 
 # maximum number of workers used to process the list of package catalogers in parallel
@@ -524,15 +525,11 @@ parallelism: 1
 # exclude:
 #   - "/etc/**"
 #   - "./out/**/*.json"
-# same as --exclude ; SYFT_EXCLUDE env var
+# SYFT_EXCLUDE env var / --exclude flag
 exclude: []
 
-# allows users to exclude synthetic binary packages from the sbom
-# these packages are removed if an overlap with a non-synthetic package is found
-exclude-binary-overlap-by-ownership: true
-
 # os and/or architecture to use when referencing container images (e.g. "windows/armv6" or "arm64")
-# same as --platform; SYFT_PLATFORM env var
+# SYFT_PLATFORM env var / --platform flag
 platform: ""
 
 # the search space to look for file and package data (options: all-layers, squashed)
@@ -541,44 +538,19 @@ scope: "squashed"
 
 # set the list of package catalogers to use when generating the SBOM
 # default = empty (cataloger set determined automatically by the source type [image or file/directory])
-# catalogers:
-#   - alpm-db-cataloger
-#   - apkdb-cataloger
-#   - binary-cataloger
-#   - cargo-auditable-binary-cataloger
-#   - cocoapods-cataloger
-#   - conan-cataloger
-#   - dartlang-lock-cataloger
-#   - dotnet-deps-cataloger
-#   - dotnet-portable-executable-cataloger
-#   - dpkg-db-cataloger
-#   - elixir-mix-lock-cataloger
-#   - erlang-rebar-lock-cataloger
-#   - go-module-file-cataloger
-#   - go-module-binary-cataloger
-#   - graalvm-native-image-cataloger
-#   - haskell-cataloger
-#   - java-cataloger
-#   - java-gradle-lockfile-cataloger
-#   - java-pom-cataloger
-#   - javascript-lock-cataloger
-#   - javascript-package-cataloger
-#   - linux-kernel-cataloger
-#   - nix-store-cataloger
-#   - php-composer-installed-cataloger
-#   - php-composer-lock-cataloger
-#   - portage-cataloger
-#   - python-package-cataloger
-#   - python-installed-package-cataloger
-#   - rpm-db-cataloger
-#   - rpm-archive-cataloger
-#   - ruby-gemfile-cataloger
-#   - ruby-installed-gemspec-cataloger
-#   - rust-cargo-lock-cataloger
-#   - sbom-cataloger
-#   - spm-cataloger
+# Use `syft cataloger list` for a list of catalogers you can specify
+# DEPRECATED: please use default-catalogers and select-catalogers configuration options instead
+# SYFT_CATALOGERS env var / --catalogers flag
 catalogers:
 
+# set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)
+# SYFT_DEFAULT_CATALOGERS env var / --override-default-catalogers flag
+default-catalogers: []
+
+# add, remove, and filter the catalogers to be used
+# SYFT_SELECT_CATALOGERS env var / --select-cataloger flag;
+select-catalogers: []
+
 # all format configuration
 format:
  
@@ -606,7 +578,7 @@ format:
   template:
     # path to the template file to use when rendering the output with the `template` output format. 
     # Note that all template paths are based on the current syft-json schema.
-    # same as -t ; SYFT_TEMPLATE_PATH env var
+    # SYFT_TEMPLATE_PATH env var / -t flag 
     path: ""
 
   # all spdx-json format options
@@ -636,16 +608,17 @@ file:
    metadata: 
       # select which files should be captured by the file-metadata cataloger and included in the SBOM. 
       # Options include:
-      #  - "all-files": capture all files from the search space
-      #  - "owned-files": capture only files owned by packages
-      #  - "unowned-files": capture only files not owned by packages
-      #  - "no-files", "": do not capture any files
+      #  - "all": capture all files from the search space
+      #  - "owned-by-package": capture only files owned by packages
+      #  - "none", "": do not capture any files
       # SYFT_FILE_METADATA_SELECTION env var
-      selection: "owned-files"
+      selection: "owned-by-package"
 
       # the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
       # SYFT_FILE_METADATA_DIGESTS env var
-      digests: ["sha256"]
+      digests:
+      - "sha256"
+      - "sha1"
 
    # capture the contents of select files in the SBOM
    content:
@@ -674,6 +647,7 @@ package:
 
   # allows users to exclude synthetic binary packages from the sbom
   # these packages are removed if an overlap with a non-synthetic package is found
+  # SYFT_PACKAGE_EXCLUDE_BINARY_OVERLAP_BY_OWNERSHIP env var
   exclude-binary-overlap-by-ownership: true
 
 
@@ -732,17 +706,23 @@ javascript:
 # configuration for the source that the SBOM is generated from (e.g. a file, directory, or container image)
 source:
   # alias name for the source
-  # SYFT_SOURCE_NAME env var; --source-name flag
+  # SYFT_SOURCE_NAME env var / --source-name flag
   name: ""
    
   # alias version for the source
-  # SYFT_SOURCE_VERSION env var; --source-version flag
+  # SYFT_SOURCE_VERSION env var / --source-version flag
   version: ""
-   
-  # options affecting the file source type
+
+  # base directory for scanning, no links will be followed above this directory, and all paths will be 
+  # reported relative to this directory
+  # SYFT_SOURCE_BASE_PATH env var
+  base-path: ''
+
+   # options affecting the file source type
   file:
     # the file digest algorithms to use on the scanned file (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-    digests: ["sha256"]
+    digests: 
+     - "sha256"
 
   image:
      
@@ -804,15 +784,15 @@ attest:
 
 log:
   # use structured logging
-  # same as SYFT_LOG_STRUCTURED env var
+  # SYFT_LOG_STRUCTURED env var
   structured: false
 
   # the log level; note: detailed logging suppress the ETUI
-  # same as SYFT_LOG_LEVEL env var
+  # SYFT_LOG_LEVEL env var
   level: "error"
 
   # location to write the log file (default is not to have a log file)
-  # same as SYFT_LOG_FILE env var
+  # SYFT_LOG_FILE env var
   file: ""
 ```
 

cmd/syft/cli/cli.go

@@ -86,6 +86,7 @@ func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Com
 	rootCmd.AddCommand(
 		scanCmd,
 		commands.Packages(app, scanCmd), // this is currently an alias for the scan command
+		commands.Cataloger(app),
 		commands.Attest(app),
 		commands.Convert(app),
 		clio.VersionCommand(id),

cmd/syft/cli/commands/attest.go

@@ -30,7 +30,7 @@ import (
 )
 
 const (
-	attestExample = `  {{.appName}} {{.command}} --output [FORMAT] alpine:latest defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry
+	attestExample = `  {{.appName}} {{.command}} --output [FORMAT] alpine:latest            defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry
 `
 	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
 	attestHelp       = attestExample + attestSchemeHelp
@@ -232,7 +232,7 @@ func attestCommand(sbomFilepath string, opts *attestOptions, userInput string) (
 }
 
 func predicateType(outputName string) string {
-	// Select Cosign predicate type based on defined output type
+	// select the Cosign predicate type based on defined output type
 	// As orientation, check: https://github.com/sigstore/cosign/blob/main/pkg/cosign/attestation/attestation.go
 	switch strings.ToLower(outputName) {
 	case "cyclonedx-json":

cmd/syft/cli/commands/cataloger.go

@@ -0,0 +1,20 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+
+	"github.com/anchore/clio"
+)
+
+func Cataloger(app clio.Application) *cobra.Command {
+	cmd := &cobra.Command{
+		Use:   "cataloger",
+		Short: "Show available catalogers and configuration",
+	}
+
+	cmd.AddCommand(
+		CatalogerList(app),
+	)
+
+	return cmd
+}

cmd/syft/cli/commands/cataloger_list.go

@@ -0,0 +1,267 @@
+package commands
+
+import (
+	"encoding/json"
+	"fmt"
+	"sort"
+	"strings"
+
+	"github.com/charmbracelet/lipgloss"
+	"github.com/jedib0t/go-pretty/v6/table"
+	"github.com/scylladb/go-set/strset"
+	"github.com/spf13/cobra"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/task"
+	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
+)
+
+type catalogerListOptions struct {
+	Output            string   `yaml:"output" json:"output" mapstructure:"output"`
+	DefaultCatalogers []string `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
+	SelectCatalogers  []string `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
+	ShowHidden        bool     `yaml:"show-hidden" json:"show-hidden" mapstructure:"show-hidden"`
+}
+
+func (o *catalogerListOptions) AddFlags(flags clio.FlagSet) {
+	flags.StringVarP(&o.Output, "output", "o", "format to output the cataloger list (available: table, json)")
+
+	flags.StringArrayVarP(&o.DefaultCatalogers, "override-default-catalogers", "", "override the default catalogers with an expression")
+
+	flags.StringArrayVarP(&o.SelectCatalogers, "select-catalogers", "", "select catalogers with an expression")
+
+	flags.BoolVarP(&o.ShowHidden, "show-hidden", "s", "show catalogers that have been de-selected")
+}
+
+func defaultCatalogerListOptions() *catalogerListOptions {
+	return &catalogerListOptions{
+		DefaultCatalogers: []string{"all"},
+	}
+}
+
+func CatalogerList(app clio.Application) *cobra.Command {
+	opts := defaultCatalogerListOptions()
+
+	return app.SetupCommand(&cobra.Command{
+		Use:   "list [OPTIONS]",
+		Short: "List available catalogers",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			return runCatalogerList(opts)
+		},
+	}, opts)
+}
+
+func runCatalogerList(opts *catalogerListOptions) error {
+	factories := task.DefaultPackageTaskFactories()
+	allTasks, err := factories.Tasks(task.DefaultCatalogingFactoryConfig())
+	if err != nil {
+		return fmt.Errorf("unable to create cataloger tasks: %w", err)
+	}
+
+	report, err := catalogerListReport(opts, allTasks)
+	if err != nil {
+		return fmt.Errorf("unable to generate cataloger list report: %w", err)
+	}
+
+	bus.Report(report)
+
+	return nil
+}
+
+func catalogerListReport(opts *catalogerListOptions, allTasks []task.Task) (string, error) {
+	selectedTasks, selectionEvidence, err := task.Select(allTasks,
+		pkgcataloging.NewSelectionRequest().
+			WithDefaults(opts.DefaultCatalogers...).
+			WithExpression(opts.SelectCatalogers...),
+	)
+	if err != nil {
+		return "", fmt.Errorf("unable to select catalogers: %w", err)
+	}
+	var report string
+
+	switch opts.Output {
+	case "json":
+		report, err = renderCatalogerListJSON(selectedTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+	case "table", "":
+		if opts.ShowHidden {
+			report = renderCatalogerListTable(allTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+		} else {
+			report = renderCatalogerListTable(selectedTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+		}
+	}
+
+	if err != nil {
+		return "", fmt.Errorf("unable to render cataloger list: %w", err)
+	}
+
+	return report, nil
+}
+
+func renderCatalogerListJSON(tasks []task.Task, selection task.Selection, defaultSelections, selections []string) (string, error) {
+	type node struct {
+		Name string   `json:"name"`
+		Tags []string `json:"tags"`
+	}
+
+	names, tagsByName := extractTaskInfo(tasks)
+
+	nodesByName := make(map[string]node)
+
+	for name := range tagsByName {
+		tagsSelected := selection.TokensByTask[name].SelectedOn.List()
+
+		if len(tagsSelected) == 1 && tagsSelected[0] == "all" {
+			tagsSelected = tagsByName[name]
+		}
+
+		sort.Strings(tagsSelected)
+
+		if tagsSelected == nil {
+			// ensure collections are not null
+			tagsSelected = []string{}
+		}
+
+		nodesByName[name] = node{
+			Name: name,
+			Tags: tagsSelected,
+		}
+	}
+
+	type document struct {
+		DefaultSelection []string `json:"default"`
+		Selection        []string `json:"selection"`
+		Catalogers       []node   `json:"catalogers"`
+	}
+
+	if selections == nil {
+		// ensure collections are not null
+		selections = []string{}
+	}
+
+	doc := document{
+		DefaultSelection: defaultSelections,
+		Selection:        selections,
+	}
+
+	for _, name := range names {
+		doc.Catalogers = append(doc.Catalogers, nodesByName[name])
+	}
+
+	by, err := json.Marshal(doc)
+
+	return string(by), err
+}
+
+func renderCatalogerListTable(tasks []task.Task, selection task.Selection, defaultSelections, selections []string) string {
+	t := table.NewWriter()
+	t.SetStyle(table.StyleLight)
+	t.AppendHeader(table.Row{"Cataloger", "Tags"})
+
+	names, tagsByName := extractTaskInfo(tasks)
+
+	rowsByName := make(map[string]table.Row)
+
+	for name, tags := range tagsByName {
+		rowsByName[name] = formatRow(name, tags, selection)
+	}
+
+	for _, name := range names {
+		t.AppendRow(rowsByName[name])
+	}
+
+	report := t.Render()
+
+	if len(selections) > 0 {
+		header := "Selected by expressions:\n"
+		for _, expr := range selections {
+			header += fmt.Sprintf("  - %q\n", expr)
+		}
+		report = header + report
+	}
+
+	if len(defaultSelections) > 0 {
+		header := "Default selections:\n"
+		for _, expr := range defaultSelections {
+			header += fmt.Sprintf("  - %q\n", expr)
+		}
+		report = header + report
+	}
+
+	return report
+}
+
+func formatRow(name string, tags []string, selection task.Selection) table.Row {
+	isIncluded := selection.Result.Has(name)
+	var selections *task.TokenSelection
+	if s, exists := selection.TokensByTask[name]; exists {
+		selections = &s
+	}
+
+	var formattedTags []string
+	for _, tag := range tags {
+		formattedTags = append(formattedTags, formatToken(tag, selections, isIncluded))
+	}
+
+	var tagStr string
+	if isIncluded {
+		tagStr = strings.Join(formattedTags, ", ")
+	} else {
+		tagStr = strings.Join(formattedTags, grey.Render(", "))
+	}
+
+	// TODO: selection should keep warnings (non-selections) in struct
+
+	return table.Row{
+		formatToken(name, selections, isIncluded),
+		tagStr,
+	}
+}
+
+var (
+	green = lipgloss.NewStyle().Foreground(lipgloss.Color("10")) // hi green
+	grey  = lipgloss.NewStyle().Foreground(lipgloss.Color("8"))  // dark grey
+	red   = lipgloss.NewStyle().Foreground(lipgloss.Color("9"))  // high red
+)
+
+func formatToken(token string, selection *task.TokenSelection, included bool) string {
+	if included && selection != nil {
+		// format all tokens in selection in green
+		if selection.SelectedOn.Has(token) {
+			return green.Render(token)
+		}
+
+		return token
+	}
+
+	// format all tokens in selection in red, all others in grey
+	if selection != nil && selection.DeselectedOn.Has(token) {
+		return red.Render(token)
+	}
+
+	return grey.Render(token)
+}
+
+func extractTaskInfo(tasks []task.Task) ([]string, map[string][]string) {
+	tagsByName := make(map[string][]string)
+	var names []string
+
+	for _, tsk := range tasks {
+		var tags []string
+		name := tsk.Name()
+
+		if s, ok := tsk.(task.Selector); ok {
+			set := strset.New(s.Selectors()...)
+			set.Remove(name)
+			tags = set.List()
+			sort.Strings(tags)
+		}
+
+		tagsByName[name] = tags
+		names = append(names, name)
+	}
+
+	sort.Strings(names)
+
+	return names, tagsByName
+}

cmd/syft/cli/commands/cataloger_list_test.go

@@ -0,0 +1,201 @@
+package commands
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"github.com/scylladb/go-set/strset"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/internal/sbomsync"
+	"github.com/anchore/syft/internal/task"
+	"github.com/anchore/syft/syft/file"
+)
+
+var _ interface {
+	task.Task
+	task.Selector
+} = (*dummyTask)(nil)
+
+type dummyTask struct {
+	name      string
+	selectors []string
+}
+
+func (d dummyTask) HasAllSelectors(s ...string) bool {
+	return strset.New(d.selectors...).Has(s...)
+}
+
+func (d dummyTask) Selectors() []string {
+	return d.selectors
+}
+
+func (d dummyTask) Name() string {
+	return d.name
+}
+
+func (d dummyTask) Execute(_ context.Context, _ file.Resolver, _ sbomsync.Builder) error {
+	panic("implement me")
+}
+
+func testTasks() []task.Task {
+	return []task.Task{
+		dummyTask{
+			name:      "task1",
+			selectors: []string{"image", "a", "b", "1"},
+		},
+		dummyTask{
+			name:      "task2",
+			selectors: []string{"image", "b", "c", "2"},
+		},
+		dummyTask{
+			name:      "task3",
+			selectors: []string{"directory", "c", "d", "3"},
+		},
+		dummyTask{
+			name:      "task4",
+			selectors: []string{"directory", "d", "e", "4"},
+		},
+	}
+}
+
+func Test_catalogerListReport(t *testing.T) {
+	tests := []struct {
+		name    string
+		options *catalogerListOptions
+		want    string
+		wantErr require.ErrorAssertionFunc
+	}{
+		{
+			name: "no expressions, table",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "table"
+				return c
+			}(),
+			want: `
+Default selections:
+  - "all"
+┌───────────┬────────────────────┐
+│ CATALOGER │ TAGS               │
+├───────────┼────────────────────┤
+│ task1     │ 1, a, b, image     │
+│ task2     │ 2, b, c, image     │
+│ task3     │ 3, c, d, directory │
+│ task4     │ 4, d, directory, e │
+└───────────┴────────────────────┘
+`,
+		},
+		{
+			name: "no expressions, json",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "json"
+				return c
+			}(),
+			want: `
+{"default":["all"],"selection":[],"catalogers":[{"name":"task1","tags":["1","a","b","image"]},{"name":"task2","tags":["2","b","c","image"]},{"name":"task3","tags":["3","c","d","directory"]},{"name":"task4","tags":["4","d","directory","e"]}]}
+`,
+		},
+		{
+			name: "no expressions, default selection, table",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "table"
+				c.DefaultCatalogers = []string{
+					"image",
+				}
+				return c
+			}(),
+			want: `
+Default selections:
+  - "image"
+┌───────────┬────────────────┐
+│ CATALOGER │ TAGS           │
+├───────────┼────────────────┤
+│ task1     │ 1, a, b, image │
+│ task2     │ 2, b, c, image │
+└───────────┴────────────────┘
+`,
+		},
+		{
+			name: "no expressions, default selection, json",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "json"
+				c.DefaultCatalogers = []string{
+					"image",
+				}
+				return c
+			}(),
+			want: `
+{"default":["image"],"selection":[],"catalogers":[{"name":"task1","tags":["image"]},{"name":"task2","tags":["image"]}]}
+`,
+		},
+		{
+			name: "with expressions, default selection, table",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "table"
+				c.DefaultCatalogers = []string{
+					"image",
+				}
+				c.SelectCatalogers = []string{
+					"-directory",
+					"+task3",
+					"-c",
+					"b",
+				}
+				return c
+			}(),
+			want: `
+Default selections:
+  - "image"
+Selected by expressions:
+  - "-directory"
+  - "+task3"
+  - "-c"
+  - "b"
+┌───────────┬────────────────────┐
+│ CATALOGER │ TAGS               │
+├───────────┼────────────────────┤
+│ task1     │ 1, a, b, image     │
+│ task3     │ 3, c, d, directory │
+└───────────┴────────────────────┘
+`,
+		},
+		{
+			name: "with expressions, default selection, json",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "json"
+				c.DefaultCatalogers = []string{
+					"image",
+				}
+				c.SelectCatalogers = []string{
+					"-directory",
+					"+task3",
+					"-c",
+					"b",
+				}
+				return c
+			}(),
+			want: `
+{"default":["image"],"selection":["-directory","+task3","-c","b"],"catalogers":[{"name":"task1","tags":["b","image"]},{"name":"task3","tags":["task3"]}]}
+`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = require.NoError
+			}
+
+			got, err := catalogerListReport(tt.options, testTasks())
+			tt.wantErr(t, err)
+			assert.Equal(t, strings.TrimSpace(tt.want), strings.TrimSpace(got))
+		})
+	}
+}

cmd/syft/cli/commands/packages.go

@@ -5,6 +5,7 @@ import (
 
 	"github.com/anchore/clio"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
+	"github.com/anchore/syft/internal"
 )
 
 func Packages(app clio.Application, scanCmd *cobra.Command) *cobra.Command {
@@ -13,11 +14,14 @@ func Packages(app clio.Application, scanCmd *cobra.Command) *cobra.Command {
 	opts := defaultScanOptions()
 
 	cmd := app.SetupCommand(&cobra.Command{
-		Use:     "packages [SOURCE]",
-		Short:   scanCmd.Short,
-		Long:    scanCmd.Long,
-		Args:    scanCmd.Args,
-		Example: scanCmd.Example,
+		Use:   "packages [SOURCE]",
+		Short: scanCmd.Short,
+		Long:  scanCmd.Long,
+		Args:  scanCmd.Args,
+		Example: internal.Tprintf(scanHelp, map[string]interface{}{
+			"appName": id.Name,
+			"command": "packages",
+		}),
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
 		RunE: func(cmd *cobra.Command, args []string) error {
 			restoreStdout := ui.CaptureStdoutToTraceLog()

cmd/syft/cli/commands/scan.go

@@ -132,7 +132,7 @@ func (o *scanOptions) validateLegacyOptionsNotUsed() error {
 	}
 
 	if legacy.ExcludeBinaryOverlapByOwnership != nil {
-		return fmt.Errorf("the config file option 'exclude-binary-overlap-by-ownership' has been removed, please use 'relationships.exclude-binary-packages-with-file-ownership-overlap' instead")
+		return fmt.Errorf("the config file option 'exclude-binary-overlap-by-ownership' has been removed, please use 'package.exclude-binary-overlap-by-ownership' instead")
 	}
 
 	if legacy.BasePath != nil {

cmd/syft/cli/commands/scan_test.go

@@ -29,7 +29,7 @@ func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
 		{
 			name:    "config file with exclude-binary-overlap-by-ownership legacy option",
 			cfg:     "test-fixtures/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
-			wantErr: assertErrorContains("relationships.exclude-binary-packages-with-file-ownership-overlap"),
+			wantErr: assertErrorContains("package.exclude-binary-overlap-by-ownership"),
 		},
 		{
 			name:    "config file with file string legacy option",

cmd/syft/cli/options/file.go

@@ -2,6 +2,9 @@ package options
 
 import (
 	"fmt"
+	"sort"
+
+	"github.com/scylladb/go-set/strset"
 
 	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/syft/file"
@@ -35,6 +38,10 @@ func defaultFileConfig() fileConfig {
 }
 
 func (c *fileConfig) PostLoad() error {
+	digests := strset.New(c.Metadata.Digests...).List()
+	sort.Strings(digests)
+	c.Metadata.Digests = digests
+
 	switch c.Metadata.Selection {
 	case file.NoFilesSelection, file.FilesOwnedByPackageSelection, file.AllFilesSelection:
 		return nil

cmd/syft/cli/options/file_test.go

@@ -0,0 +1,56 @@
+package options
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/anchore/syft/syft/file"
+)
+
+func Test_fileConfig_PostLoad(t *testing.T) {
+	tests := []struct {
+		name    string
+		cfg     fileConfig
+		assert  func(t *testing.T, cfg fileConfig)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "deduplicate digests",
+			cfg: fileConfig{
+				Metadata: fileMetadata{
+					Selection: file.NoFilesSelection,
+					Digests:   []string{"sha1", "sha1"},
+				},
+			},
+			assert: func(t *testing.T, cfg fileConfig) {
+				assert.Equal(t, []string{"sha1"}, cfg.Metadata.Digests)
+			},
+		},
+		{
+			name: "error on invalid selection",
+			cfg: fileConfig{
+				Metadata: fileMetadata{
+					Selection: file.Selection("invalid"),
+				},
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name:    "error on empty selection",
+			cfg:     fileConfig{},
+			wantErr: assert.Error,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.cfg.PostLoad())
+			if tt.assert != nil {
+				tt.assert(t, tt.cfg)
+			}
+		})
+	}
+}

cmd/syft/cli/options/source.go

@@ -2,6 +2,7 @@ package options
 
 import (
 	"fmt"
+	"sort"
 	"strings"
 
 	"github.com/scylladb/go-set/strset"
@@ -34,6 +35,13 @@ func defaultSourceConfig() sourceConfig {
 	}
 }
 
+func (c *fileSource) PostLoad() error {
+	digests := strset.New(c.Digests...).List()
+	sort.Strings(digests)
+	c.Digests = digests
+	return nil
+}
+
 func (c imageSource) PostLoad() error {
 	return checkDefaultSourceValues(c.DefaultPullSource)
 }

cmd/syft/cli/options/source_test.go

@@ -0,0 +1,37 @@
+package options
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_fileSource_PostLoad(t *testing.T) {
+	tests := []struct {
+		name    string
+		cfg     fileSource
+		assert  func(t *testing.T, cfg fileSource)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "deduplicate digests",
+			cfg: fileSource{
+				Digests: []string{"sha1", "sha1"},
+			},
+			assert: func(t *testing.T, cfg fileSource) {
+				assert.Equal(t, []string{"sha1"}, cfg.Digests)
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.cfg.PostLoad())
+			if tt.assert != nil {
+				tt.assert(t, tt.cfg)
+			}
+		})
+	}
+}

go.mod

@@ -16,17 +16,19 @@ 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 v0.1.1-0.20230104203445-02e0a6721501
-	github.com/anchore/stereoscope v0.0.0-20231220161148-590920dabc54
+	github.com/anchore/stereoscope v0.0.0-20240118133533-eb656fc71793
+	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
 	// we are hinting brotli to latest due to warning when installing archiver v3:
 	// go: warning: github.com/andybalholm/brotli@v1.0.1: retracted by module author: occasional panics and data corruption
 	github.com/aquasecurity/go-pep440-version v0.0.0-20210121094942-22b2f8951d46
 	github.com/bmatcuk/doublestar/v4 v4.6.1
+	github.com/charmbracelet/bubbles v0.17.1
 	github.com/charmbracelet/bubbletea v0.25.0
 	github.com/charmbracelet/lipgloss v0.9.1
 	github.com/dave/jennifer v1.7.0
 	github.com/deitch/magic v0.0.0-20230404182410-1ff89d7342da
 	github.com/distribution/reference v0.5.0
-	github.com/docker/docker v24.0.7+incompatible
+	github.com/docker/docker v25.0.0+incompatible
 	github.com/dustin/go-humanize v1.0.1
 	github.com/facebookincubator/nvdtools v0.1.5
 	github.com/github/go-spdx/v2 v2.2.0
@@ -35,13 +37,14 @@ require (
 	github.com/go-git/go-git/v5 v5.11.0
 	github.com/go-test/deep v1.1.0
 	github.com/google/go-cmp v0.6.0
-	github.com/google/go-containerregistry v0.17.0
+	github.com/google/go-containerregistry v0.18.0
 	github.com/google/licensecheck v0.3.1
 	github.com/google/uuid v1.5.0
 	github.com/gookit/color v1.5.4
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/iancoleman/strcase v0.3.0
 	github.com/invopop/jsonschema v0.7.0
+	github.com/jedib0t/go-pretty/v6 v6.5.3
 	github.com/jinzhu/copier v0.4.0
 	github.com/kastenhq/goversion v0.0.0-20230811215019-93b2f8823953
 	github.com/knqyf263/go-rpmdb v0.0.0-20230301153543-ba94b245509b
@@ -76,12 +79,6 @@ require (
 	modernc.org/sqlite v1.28.0
 )
 
-require (
-	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
-	github.com/charmbracelet/bubbles v0.17.1
-	github.com/jedib0t/go-pretty/v6 v6.5.3
-)
-
 require (
 	dario.cat/mergo v1.0.0 // indirect
 	github.com/AdaLogics/go-fuzz-headers v0.0.0-20230811130428-ced1acdcaa24 // indirect
@@ -101,7 +98,7 @@ require (
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/becheran/wildmatch-go v1.0.0 // indirect
 	github.com/charmbracelet/harmonica v0.2.0 // indirect
-	github.com/cloudflare/circl v1.3.3 // indirect
+	github.com/cloudflare/circl v1.3.7 // indirect
 	github.com/containerd/cgroups v1.1.0 // indirect
 	github.com/containerd/console v1.0.4-0.20230313162750-1ae8d489ac81 // indirect
 	github.com/containerd/containerd v1.7.11 // indirect

go.sum

@@ -107,8 +107,8 @@ 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 v0.1.1-0.20230104203445-02e0a6721501 h1:AV7qjwMcM4r8wFhJq3jLRztew3ywIyPTRapl2T1s9o8=
 github.com/anchore/packageurl-go v0.1.1-0.20230104203445-02e0a6721501/go.mod h1:Blo6OgJNiYF41ufcgHKkbCKF2MDOMlrqhXv/ij6ocR4=
-github.com/anchore/stereoscope v0.0.0-20231220161148-590920dabc54 h1:i2YK5QEs9H2YB3B2zv+AGR44ves0nmAGOD07lMphH14=
-github.com/anchore/stereoscope v0.0.0-20231220161148-590920dabc54/go.mod h1:IylG7ofLoUKHwS1XDF6rPhOmaE3GgpAgsMdvvYfooTU=
+github.com/anchore/stereoscope v0.0.0-20240118133533-eb656fc71793 h1:wji+qdjsV7ooolBwb3faVZnEK3WtY/kcT5473kxVZS4=
+github.com/anchore/stereoscope v0.0.0-20240118133533-eb656fc71793/go.mod h1:IylG7ofLoUKHwS1XDF6rPhOmaE3GgpAgsMdvvYfooTU=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu3qAvBg8x/Y=
 github.com/andybalholm/brotli v1.0.4 h1:V7DdXeJtZscaqfNuAdSRuRFzuiKlHSC/Zh3zl9qY3JY=
@@ -142,6 +142,8 @@ github.com/bmatcuk/doublestar/v4 v4.6.1/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTS
 github.com/bradleyjkemp/cupaloy/v2 v2.8.0 h1:any4BmKE+jGIaMpnU8YgH/I2LPiLBufr6oMMlVBbn9M=
 github.com/bradleyjkemp/cupaloy/v2 v2.8.0/go.mod h1:bm7JXdkRd4BHJk9HpwqAI8BoAY1lps46Enkdqw6aRX0=
 github.com/bwesterb/go-ristretto v1.2.3/go.mod h1:fUIoIZaG73pV5biE2Blr2xEzDoMj7NFEuV9ekS419A0=
+github.com/cenkalti/backoff/v4 v4.2.1 h1:y4OZtCnogmCPw98Zjyt5a6+QwPLGkiQsYW5oUqylYbM=
+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/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
@@ -163,8 +165,9 @@ github.com/cilium/ebpf v0.7.0/go.mod h1:/oI2+1shJiTGAMgl6/RgJr36Eo1jzrRcAWbcXO2u
 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/cloudflare/circl v1.3.3 h1:fE/Qz0QdIGqeWfnwq0RE0R7MI51s0M2E4Ga9kq5AEMs=
 github.com/cloudflare/circl v1.3.3/go.mod h1:5XYMA4rFBvNIrhs50XuiBJ15vF2pZn4nnUKZrLbUZFA=
+github.com/cloudflare/circl v1.3.7 h1:qlCDlTPz2n9fu58M0Nh1J/JzcFpfgkFHHX3O35r5vcU=
+github.com/cloudflare/circl v1.3.7/go.mod h1:sRTcRWXGLrKw6yIGJ+l7amYJFfAXbZG0kBSc8r4zxgA=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
 github.com/cncf/udpa/go v0.0.0-20200629203442-efcf912fb354/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
 github.com/cncf/udpa/go v0.0.0-20201120205902-5459f2c99403/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
@@ -220,8 +223,8 @@ github.com/docker/cli v24.0.0+incompatible h1:0+1VshNwBQzQAx9lOl+OYCTCEAD8fKs/qe
 github.com/docker/cli v24.0.0+incompatible/go.mod h1:JLrzqnKDaYBop7H2jaqPtU4hHvMKP+vjCwu2uszcLI8=
 github.com/docker/distribution v2.8.3+incompatible h1:AtKxIZ36LoNK51+Z6RpzLpddBirtxJnzDrHLEKxTAYk=
 github.com/docker/distribution v2.8.3+incompatible/go.mod h1:J2gT2udsDAN96Uj4KfcMRqY0/ypR+oyYUYmja8H+y+w=
-github.com/docker/docker v24.0.7+incompatible h1:Wo6l37AuwP3JaMnZa226lzVXGA3F9Ig1seQen0cKYlM=
-github.com/docker/docker v24.0.7+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
+github.com/docker/docker v25.0.0+incompatible h1:g9b6wZTblhMgzOT2tspESstfw6ySZ9kdm94BLDKaZac=
+github.com/docker/docker v25.0.0+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
 github.com/docker/docker-credential-helpers v0.7.0 h1:xtCHsjxogADNZcdv1pKUHXryefjlVRqWqIhk/uXJp0A=
 github.com/docker/docker-credential-helpers v0.7.0/go.mod h1:rETQfLdHNT3foU5kuNkFR1R1V12OJRRO5lzt2D1b5X0=
 github.com/docker/go-connections v0.4.0 h1:El9xVISelRB7BuFusrZozjnkIM5YnzCViNKohAFqRJQ=
@@ -372,8 +375,8 @@ github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
-github.com/google/go-containerregistry v0.17.0 h1:5p+zYs/R4VGHkhyvgWurWrpJ2hW4Vv9fQI+GzdcwXLk=
-github.com/google/go-containerregistry v0.17.0/go.mod h1:u0qB2l7mvtWVR5kNcbFIhFY1hLbf8eeGapA+vbFDCtQ=
+github.com/google/go-containerregistry v0.18.0 h1:ShE7erKNPqRh5ue6Z9DUOlk04WsnFWPO6YGr3OxnfoQ=
+github.com/google/go-containerregistry v0.18.0/go.mod h1:u0qB2l7mvtWVR5kNcbFIhFY1hLbf8eeGapA+vbFDCtQ=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/licensecheck v0.3.1 h1:QoxgoDkaeC4nFrtGN1jV7IPmDCHFNIVh54e5hSt6sPs=
 github.com/google/licensecheck v0.3.1/go.mod h1:ORkR35t/JjW+emNKtfJDII0zlciG9JgbT7SmsohlHmY=
@@ -410,7 +413,10 @@ github.com/googleapis/gax-go/v2 v2.1.1/go.mod h1:hddJymUZASv3XPyGkUpKj8pPO47Rmb0
 github.com/gookit/color v1.2.5/go.mod h1:AhIE+pS6D4Ql0SQWbBeXPHw7gY0/sjHoA4s/n1KB7xg=
 github.com/gookit/color v1.5.4 h1:FZmqs7XOyGgCAxmWyPslpiok1k05wmY3SJTytgvYFs0=
 github.com/gookit/color v1.5.4/go.mod h1:pZJOeOS8DM43rXbp4AZo1n9zCU2qjpcRko0b6/QJi9w=
+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=
+github.com/grpc-ecosystem/grpc-gateway/v2 v2.16.0/go.mod h1:YN5jB8ie0yfIUg6VvR9Kz84aCaG7AsGZnLjhHbUqwPg=
 github.com/hashicorp/consul/api v1.11.0/go.mod h1:XjsvQN+RJGWI2TWy1/kqaE16HrR2J/FWgkYjdZQsX9M=
 github.com/hashicorp/consul/sdk v0.8.0/go.mod h1:GBvyrGALthsZObzUGsfgHZQDXjg4lOjagTIwIR1vPms=
 github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
@@ -831,11 +837,19 @@ go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.45.0 h1:x8Z78aZ
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.45.0/go.mod h1:62CPTSry9QZtOaSsE3tOzhx6LzDhHnXJ6xHeMNNiM6Q=
 go.opentelemetry.io/otel v1.19.0 h1:MuS/TNf4/j4IXsZuJegVzI1cwut7Qc00344rgH7p8bs=
 go.opentelemetry.io/otel v1.19.0/go.mod h1:i0QyjOq3UPoTzff0PJB2N66fb4S0+rSbSB15/oyH9fY=
+go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.19.0 h1:Mne5On7VWdx7omSrSSZvM4Kw7cS7NQkOOmLcgscI51U=
+go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.19.0/go.mod h1:IPtUMKL4O3tH5y+iXVyAXqpAwMuzC1IrxVS81rummfE=
+go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.19.0 h1:IeMeyr1aBvBiPVYihXIaeIZba6b8E1bYp7lbdxK8CQg=
+go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.19.0/go.mod h1:oVdCUtjq9MK9BlS7TtucsQwUcXcymNiEDjgDD2jMtZU=
 go.opentelemetry.io/otel/metric v1.19.0 h1:aTzpGtV0ar9wlV4Sna9sdJyII5jTVJEvKETPiOKwvpE=
 go.opentelemetry.io/otel/metric v1.19.0/go.mod h1:L5rUsV9kM1IxCj1MmSdS+JQAcVm319EUrDVLrt7jqt8=
+go.opentelemetry.io/otel/sdk v1.19.0 h1:6USY6zH+L8uMH8L3t1enZPR3WFEmSTADlqldyHtJi3o=
+go.opentelemetry.io/otel/sdk v1.19.0/go.mod h1:NedEbbS4w3C6zElbLdPJKOpJQOrGUJ+GfzpjUvI0v1A=
 go.opentelemetry.io/otel/trace v1.19.0 h1:DFVQmlVbfVeOuBRrwdtaehRrWiL1JoVs9CPIQ1Dzxpg=
 go.opentelemetry.io/otel/trace v1.19.0/go.mod h1:mfaSyvGyEJEI0nyV2I4qhNQnbBOUUmYZpYojqMnX2vo=
 go.opentelemetry.io/proto/otlp v0.7.0/go.mod h1:PqfVotwruBrMGOCsRd/89rSnXhoiJIqeYNgFYFoEGnI=
+go.opentelemetry.io/proto/otlp v1.0.0 h1:T0TX0tmXU8a3CbNXzEKGeU5mIVOdf0oykP+u2lIVU/I=
+go.opentelemetry.io/proto/otlp v1.0.0/go.mod h1:Sy6pihPLfYHkr3NkUbEhGHFhINUSI/v80hjKIs5JXpM=
 go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
 go.uber.org/atomic v1.9.0 h1:ECmE8Bn/WFTYwEW/bpKD3M8VtR/zQVbavAoalC1PYyE=
 go.uber.org/atomic v1.9.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
@@ -1269,6 +1283,8 @@ google.golang.org/genproto v0.0.0-20211206160659-862468c7d6e0/go.mod h1:5CzLGKJ6
 google.golang.org/genproto v0.0.0-20211208223120-3a66f561d7aa/go.mod h1:5CzLGKJ67TSI2B9POpiiyGha0AjJvZIUgRMt1dSmuhc=
 google.golang.org/genproto v0.0.0-20231106174013-bbf56f31fb17 h1:wpZ8pe2x1Q3f2KyT5f8oP/fa9rHAKgFPr/HZdNuS+PQ=
 google.golang.org/genproto v0.0.0-20231106174013-bbf56f31fb17/go.mod h1:J7XzRzVy1+IPwWHZUzoD0IccYZIrXILAQpc+Qy9CMhY=
+google.golang.org/genproto/googleapis/api v0.0.0-20231106174013-bbf56f31fb17 h1:JpwMPBpFN3uKhdaekDpiNlImDdkUAyiJ6ez/uxGaUSo=
+google.golang.org/genproto/googleapis/api v0.0.0-20231106174013-bbf56f31fb17/go.mod h1:0xJLfVdJqpAPl8tDg1ujOCGzx6LFLttXT5NhllGOXY4=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20231120223509-83a465c0220f h1:ultW7fxlIvee4HYrtnaRPon9HpEgFk5zYpmfMgtKB5I=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20231120223509-83a465c0220f/go.mod h1:L9KNLi232K1/xB6f7AlSX692koaRnKaWSR0stBki0Yc=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=

internal/file/digest.go

@@ -22,6 +22,7 @@ func supportedHashAlgorithms() []crypto.Hash {
 }
 
 func NewDigestsFromFile(closer io.ReadCloser, hashes []crypto.Hash) ([]file.Digest, error) {
+	hashes = NormalizeHashes(hashes)
 	// create a set of hasher objects tied together with a single writer to feed content into
 	hashers := make([]hash.Hash, len(hashes))
 	writers := make([]io.Writer, len(hashes))
@@ -67,7 +68,7 @@ func Hashers(names ...string) ([]crypto.Hash, error) {
 		}
 		hashers = append(hashers, hashObj)
 	}
-	return hashers, nil
+	return NormalizeHashes(hashers), nil
 }
 
 func CleanDigestAlgorithmName(name string) string {

internal/file/normalize_hashes.go

@@ -0,0 +1,24 @@
+package file
+
+import (
+	"crypto"
+	"sort"
+
+	"github.com/scylladb/go-set/uset"
+)
+
+func NormalizeHashes(hashes []crypto.Hash) []crypto.Hash {
+	set := uset.New()
+	for _, h := range hashes {
+		set.Add(uint(h))
+	}
+	list := set.List()
+	sort.Slice(list, func(i, j int) bool {
+		return list[i] < list[j]
+	})
+	result := make([]crypto.Hash, len(list))
+	for i, v := range list {
+		result[i] = crypto.Hash(v)
+	}
+	return result
+}

internal/file/normalize_hashes_test.go

@@ -0,0 +1,44 @@
+package file
+
+import (
+	"crypto"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestNormalizeHashes(t *testing.T) {
+
+	tests := []struct {
+		name  string
+		input []crypto.Hash
+		want  []crypto.Hash
+	}{
+		{
+			name: "deduplicate hashes",
+			input: []crypto.Hash{
+				crypto.SHA1,
+				crypto.SHA1,
+			},
+			want: []crypto.Hash{
+				crypto.SHA1,
+			},
+		},
+		{
+			name: "sort hashes",
+			input: []crypto.Hash{
+				crypto.SHA512,
+				crypto.SHA1,
+			},
+			want: []crypto.Hash{
+				crypto.SHA1,
+				crypto.SHA512,
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, NormalizeHashes(tt.input))
+		})
+	}
+}

syft/cataloging/filecataloging/config.go

@@ -73,6 +73,6 @@ func (cfg Config) WithSelection(selection file.Selection) Config {
 }
 
 func (cfg Config) WithHashers(hashers []crypto.Hash) Config {
-	cfg.Hashers = hashers
+	cfg.Hashers = intFile.NormalizeHashes(hashers)
 	return cfg
 }

syft/cataloging/pkgcataloging/config.go

@@ -20,6 +20,7 @@ type Config struct {
 
 func DefaultConfig() Config {
 	return Config{
+		Binary:      binary.DefaultCatalogerConfig(),
 		Golang:      golang.DefaultCatalogerConfig(),
 		LinuxKernel: kernel.DefaultLinuxCatalogerConfig(),
 		Python:      python.DefaultCatalogerConfig(),

syft/create_sbom.go

@@ -11,7 +11,6 @@ import (
 	"github.com/wagoodman/go-progress"
 
 	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/internal/relationship"
 	"github.com/anchore/syft/internal/sbomsync"
 	"github.com/anchore/syft/internal/task"
 	"github.com/anchore/syft/syft/artifact"
@@ -78,8 +77,6 @@ func CreateSBOM(ctx context.Context, src source.Source, cfg *CreateSBOMConfig) (
 	packageCatalogingProgress.SetCompleted()
 	catalogingProgress.SetCompleted()
 
-	relationship.Finalize(builder, cfg.Relationships, src)
-
 	return &s, nil
 }
 

syft/file/cataloger/filedigest/cataloger.go

@@ -25,7 +25,7 @@ type Cataloger struct {
 
 func NewCataloger(hashes []crypto.Hash) *Cataloger {
 	return &Cataloger{
-		hashes: hashes,
+		hashes: intFile.NormalizeHashes(hashes),
 	}
 }
 

syft/pkg/cataloger/binary/cataloger.go

@@ -4,6 +4,8 @@ Package binary provides a concrete Cataloger implementations for surfacing possi
 package binary
 
 import (
+	"encoding/json"
+
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
@@ -28,6 +30,15 @@ func NewCataloger(cfg CatalogerConfig) pkg.Cataloger {
 	}
 }
 
+func (cfg CatalogerConfig) MarshalJSON() ([]byte, error) {
+	// only keep the class names
+	var names []string
+	for _, cls := range cfg.Classifiers {
+		names = append(names, cls.Class)
+	}
+	return json.Marshal(names)
+}
+
 // Cataloger is the cataloger responsible for surfacing evidence of a very limited set of binary files,
 // which have been identified by the classifiers. The Cataloger is _NOT_ a place to catalog any and every
 // binary, but rather the specific set that has been curated to be important, predominantly related to toolchain-

syft/pkg/cataloger/binary/cataloger_test.go

@@ -13,7 +13,9 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/packageurl-go"
 	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary/test-fixtures/manager/testutil"
@@ -870,6 +872,17 @@ func Test_Cataloger_PositiveCases(t *testing.T) {
 				Metadata:  metadata("gcc-binary"),
 			},
 		},
+		{
+			logicalFixture: "wp/2.9.0/linux-amd64",
+			expected: pkg.Package{
+				Name:      "wp-cli",
+				Version:   "2.9.0",
+				Type:      "binary",
+				PURL:      "pkg:generic/wp-cli@2.9.0",
+				Locations: locations("wp"),
+				Metadata:  metadata("wordpress-cli-binary"),
+			},
+		},
 	}
 
 	for _, test := range tests {
@@ -1242,3 +1255,49 @@ func Test_Cataloger_ResilientToErrors(t *testing.T) {
 	assert.NoError(t, err)
 	assert.True(t, resolver.searchCalled)
 }
+
+func TestCatalogerConfig_MarshalJSON(t *testing.T) {
+
+	tests := []struct {
+		name    string
+		cfg     CatalogerConfig
+		want    string
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "only show names of classes",
+			cfg: CatalogerConfig{
+				Classifiers: []Classifier{
+					{
+						Class:           "class",
+						FileGlob:        "glob",
+						EvidenceMatcher: FileContentsVersionMatcher(".thing"),
+						Package:         "pkg",
+						PURL: packageurl.PackageURL{
+							Type:       "type",
+							Namespace:  "namespace",
+							Name:       "name",
+							Version:    "version",
+							Qualifiers: nil,
+							Subpath:    "subpath",
+						},
+						CPEs: []cpe.CPE{cpe.Must("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*")},
+					},
+				},
+			},
+			want: `["class"]`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			got, err := tt.cfg.MarshalJSON()
+			if !tt.wantErr(t, err) {
+				return
+			}
+			assert.Equal(t, tt.want, string(got))
+		})
+	}
+}

syft/pkg/cataloger/binary/classifier.go

@@ -5,6 +5,7 @@ import (
 	"debug/elf"
 	"debug/macho"
 	"debug/pe"
+	"encoding/json"
 	"fmt"
 	"io"
 	"regexp"
@@ -44,6 +45,31 @@ type Classifier struct {
 	CPEs []cpe.CPE `json:"cpes"`
 }
 
+func (cfg Classifier) MarshalJSON() ([]byte, error) {
+	type marshalled struct {
+		Class    string   `json:"class"`
+		FileGlob string   `json:"fileGlob"`
+		Package  string   `json:"package"`
+		PURL     string   `json:"purl"`
+		CPEs     []string `json:"cpes"`
+	}
+
+	var marshalledCPEs []string
+	for _, c := range cfg.CPEs {
+		marshalledCPEs = append(marshalledCPEs, c.BindToFmtString())
+	}
+
+	m := marshalled{
+		Class:    cfg.Class,
+		FileGlob: cfg.FileGlob,
+		Package:  cfg.Package,
+		PURL:     cfg.PURL.String(),
+		CPEs:     marshalledCPEs,
+	}
+
+	return json.Marshal(m)
+}
+
 // EvidenceMatcher is a function called to catalog Packages that match some sort of evidence
 type EvidenceMatcher func(resolver file.Resolver, classifier Classifier, location file.Location) ([]pkg.Package, error)
 

syft/pkg/cataloger/binary/classifier_test.go

@@ -3,8 +3,10 @@ package binary
 import (
 	"testing"
 
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/file"
 )
@@ -83,3 +85,46 @@ func Test_ClassifierCPEs(t *testing.T) {
 		})
 	}
 }
+
+func TestClassifier_MarshalJSON(t *testing.T) {
+
+	tests := []struct {
+		name       string
+		classifier Classifier
+		want       string
+		wantErr    assert.ErrorAssertionFunc
+	}{
+		{
+			name: "go case",
+			classifier: Classifier{
+				Class:           "class",
+				FileGlob:        "glob",
+				EvidenceMatcher: FileContentsVersionMatcher(".thing"),
+				Package:         "pkg",
+				PURL: packageurl.PackageURL{
+					Type:       "type",
+					Namespace:  "namespace",
+					Name:       "name",
+					Version:    "version",
+					Qualifiers: nil,
+					Subpath:    "subpath",
+				},
+				CPEs: []cpe.CPE{cpe.Must("cpe:2.3:a:some:app:*:*:*:*:*:*:*:*")},
+			},
+			want: `{"class":"class","fileGlob":"glob","package":"pkg","purl":"pkg:type/namespace/name@version#subpath","cpes":["cpe:2.3:a:some:app:*:*:*:*:*:*:*:*"]}`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			cfg := tt.classifier
+			got, err := cfg.MarshalJSON()
+			if !tt.wantErr(t, err) {
+				return
+			}
+			assert.Equal(t, tt.want, string(got))
+		})
+	}
+}

syft/pkg/cataloger/binary/default_classifiers.go

@@ -403,6 +403,17 @@ func DefaultClassifiers() []Classifier {
 			PURL:    mustPURL("pkg:generic/gcc@version"),
 			CPEs:    singleCPE("cpe:2.3:a:gnu:gcc:*:*:*:*:*:*:*:*"),
 		},
+		{
+			Class:    "wordpress-cli-binary",
+			FileGlob: "**/wp",
+			EvidenceMatcher: FileContentsVersionMatcher(
+				// wp-cli/wp-cli 2.9.0'
+				`(?m)wp-cli/wp-cli (?P<version>[0-9]+\.[0-9]+\.[0-9]+)`,
+			),
+			Package: "wp-cli",
+			PURL:    mustPURL("pkg:generic/wp-cli@version"),
+			CPEs:    singleCPE("cpe:2.3:a:wp-cli:wp-cli:*:*:*:*:*:*:*:*"),
+		},
 	}
 }
 

syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets/wp/2.9.0/linux-amd64/wp

@@ -0,0 +1,10 @@
+name: wp
+offset: 6967657
+length: 120
+snippetSha256: fe7afa7db1b4efc55b3099b5b1fb46a34e34b147c708be0a74d1dd9fce2b5cac
+fileSha256: af6b7ccc21ed0907cb504db5a059f0e120117905a6017bfdd4375cee3c93d864
+
+### byte snippet to follow ###
+ND CERTIFICATE-----
+wp-cli/wp-cli 2.9.0 2023-10-25T09:10:40+00:00
+composer/ca-bundle 1.3.7 76e46335014860eec1aa5a724799a

syft/pkg/cataloger/binary/test-fixtures/config.yaml

@@ -315,6 +315,13 @@ from-images:
     paths:
       - /usr/local/bin/redis-server
 
+  - version: 2.9.0
+    images:
+      - ref: wordpress:cli-2.9.0-php8.3@sha256:3a008aafccc6a8d2d7ec2b069722cb43b3569b61cd833f9f2f13d74a9284746e
+        platform: linux/amd64
+    paths:
+      - /usr/local/bin/wp
+
   - version: 1.9.3p551
     images:
       - ref: ruby:1.9.3-p551@sha256:56b4a74e4fc2492b3b857bc94454dfa910f61e823a4bfab275d279bfa218eb05

test/integration/regression_sbom_duplicate_relationships_test.go

@@ -0,0 +1,26 @@
+package integration
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/scylladb/go-set/strset"
+
+	"github.com/anchore/syft/syft/source"
+)
+
+func TestRelationshipsUnique(t *testing.T) {
+	// This test is to ensure that the relationships are deduplicated in the final SBOM.
+	// It is not a test of the relationships themselves.
+	// This test is a regression test for #syft/2509
+	sbom, _ := catalogFixtureImage(t, "image-pkg-coverage", source.SquashedScope)
+	observedRelationships := strset.New()
+
+	for _, rel := range sbom.Relationships {
+		unique := fmt.Sprintf("%s:%s:%s", rel.From.ID(), rel.To.ID(), rel.Type)
+		if observedRelationships.Has(unique) {
+			t.Errorf("duplicate relationship found: %s", unique)
+		}
+		observedRelationships.Add(unique)
+	}
+}