fix: provide separate nonroot image (#3998)

Signed-off-by: Keith Zantow <kzantow@gmail.com>

.binny.yaml

@@ -2,7 +2,7 @@ tools:
   # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
   - name: binny
     version:
-      want: v0.8.0
+      want: v0.9.0
     method: github-release
     with:
       repo: anchore/binny
@@ -18,7 +18,7 @@ tools:
   # used to sign mac binaries at release
   - name: quill
     version:
-      want: v0.4.2
+      want: v0.5.1
     method: github-release
     with:
       repo: anchore/quill
@@ -26,7 +26,7 @@ tools:
   # used for linting
   - name: golangci-lint
     version:
-      want: v1.59.1
+      want: v2.1.6
     method: github-release
     with:
       repo: golangci/golangci-lint
@@ -34,7 +34,7 @@ tools:
   # used for showing the changelog at release
   - name: glow
     version:
-      want: v1.5.1
+      want: v2.1.1
     method: github-release
     with:
       repo: charmbracelet/glow
@@ -42,7 +42,7 @@ tools:
   # used for signing the checksums file at release
   - name: cosign
     version:
-      want: v2.3.0
+      want: v2.5.0
     method: github-release
     with:
       repo: sigstore/cosign
@@ -58,7 +58,7 @@ tools:
   # used to release all artifacts
   - name: goreleaser
     version:
-      want: v2.1.0
+      want: v2.10.2
     method: github-release
     with:
       repo: goreleaser/goreleaser
@@ -87,23 +87,10 @@ tools:
     with:
       repo: wagoodman/go-bouncer
 
-  # used for showing benchmark testing
-  - name: benchstat
-    version:
-      want: latest
-      method: go-proxy
-      with:
-        module: golang.org/x/perf
-        allow-unresolved-version: true
-    method: go-install
-    with:
-      entrypoint: cmd/benchstat
-      module: golang.org/x/perf
-
   # used for running all local and CI tasks
   - name: task
     version:
-      want: v3.38.0
+      want: v3.44.0
     method: github-release
     with:
       repo: go-task/task
@@ -111,7 +98,23 @@ tools:
   # used for triggering a release
   - name: gh
     version:
-      want: v2.54.0
+      want: v2.74.0
     method: github-release
     with:
       repo: cli/cli
+
+  # used to upload test fixture cache
+  - name: oras
+    version:
+      want: v1.2.3
+    method: github-release
+    with:
+      repo: oras-project/oras
+
+  # used to upload test fixture cache
+  - name: yq
+    version:
+      want: v4.45.4
+    method: github-release
+    with:
+      repo: mikefarah/yq

.github/ISSUE_TEMPLATE/config.yml

@@ -1,6 +1,6 @@
 contact_links:
 
-  - name: Join the Slack community 💬
-    # link to our community Slack registration page
-    url: https://anchore.com/slack
+  - name: Join our Discourse community 💬
+    # link to our community Discourse site
+    url: https://anchore.com/discourse
     about: 'Come chat with us! Ask for help, join our software development efforts, or just give us feedback!'

.github/actions/bootstrap/action.yaml

@@ -5,7 +5,7 @@ inputs:
   go-version:
     description: "Go version to install"
     required: true
-    default: "1.22.x"
+    default: ">= 1.24"
   go-dependencies:
     description: "Download go dependencies"
     required: true
@@ -13,34 +13,38 @@ inputs:
   cache-key-prefix:
     description: "Prefix all cache keys with this value"
     required: true
-    default: "1ac8281053"
-  compute-fingerprints:
-    description: "Compute test fixture fingerprints"
+    default: "181053ac82"
+  download-test-fixture-cache:
+    description: "Download test fixture cache from OCI and github actions"
     required: true
+    default: "false"
+  tools:
+    description: "whether to install tools"
     default: "true"
   bootstrap-apt-packages:
     description: "Space delimited list of tools to install via apt"
     default: "libxml2-utils"
 
-
 runs:
   using: "composite"
   steps:
     # note: go mod and build is automatically cached on default with v4+
-    - uses: actions/setup-go@cdcb36043654635271a94b9a6d1392de5bb323a7 # v5.0.1
+    - uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
       if: inputs.go-version != ''
       with:
         go-version: ${{ inputs.go-version }}
 
     - name: Restore tool cache
+      if: inputs.tools == 'true'
       id: tool-cache
-      uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 # v3.3.2
+      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
       with:
         path: ${{ github.workspace }}/.tool
         key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
 
     - name: Install project tools
       shell: bash
+      if: inputs.tools == 'true'
       run: make tools
 
     - name: Install go dependencies
@@ -54,8 +58,14 @@ runs:
       run: |
         DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y ${{ inputs.bootstrap-apt-packages }}
 
-    - name: Create all cache fingerprints
-      if: inputs.compute-fingerprints == 'true'
-      shell: bash
-      run: make fingerprints
+    - name: Restore ORAS cache from github actions
+      if: inputs.download-test-fixture-cache == 'true'
+      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      with:
+        path: ${{ github.workspace }}/.tmp/oras-cache
+        key: ${{ inputs.cache-key-prefix }}-oras-cache
 
+    - name: Download test fixture cache
+      if: inputs.download-test-fixture-cache == 'true'
+      shell: bash
+      run: make download-test-fixture-cache

.github/dependabot.yml

@@ -19,7 +19,7 @@ updates:
       - "dependencies"
 
   - package-ecosystem: "github-actions"
-    directory: "/.github/actions/boostrap"
+    directory: "/.github/actions/bootstrap"
     schedule:
       interval: "daily"
     open-pull-requests-limit: 10

.github/pull_request_template.md

@@ -0,0 +1,25 @@
+# Description
+
+Please include a summary of the changes along with any relevant motivation and context,
+or link to an issue where this is explained.
+
+<!-- If this completes an issue, please include: -->
+
+- Fixes
+
+## Type of change
+
+<!-- Delete any that are not relevant -->
+
+- [ ] Bug fix (non-breaking change which fixes an issue)
+- [ ] New feature (non-breaking change which adds functionality)
+- [ ] Breaking change (please discuss with the team first; Syft is 1.0 software and we won't accept breaking changes without going to 2.0)
+- [ ] Documentation (updates the documentation)
+- [ ] Chore (improve the developer experience, fix a test flake, etc, without changing the visible behavior of Syft)
+- [ ] Performance (make Syft run faster or use less memory, without changing visible behavior much)
+
+# Checklist:
+
+- [ ] I have added unit tests that cover changed behavior
+- [ ] I have tested my code in common scenarios and confirmed there are no regressions
+- [ ] I have added comments to my code, particularly in hard-to-understand sections

.github/scripts/find_cache_paths.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import os
+import glob
+import sys
+import json
+import hashlib
+
+
+IGNORED_PREFIXES = []
+
+
+def find_fingerprints_and_check_dirs(base_dir):
+    all_fingerprints = set(glob.glob(os.path.join(base_dir, '**', 'test*', '**', '*.fingerprint'), recursive=True))
+
+    all_fingerprints = {os.path.relpath(fp) for fp in all_fingerprints
+                        if not any(fp.startswith(prefix) for prefix in IGNORED_PREFIXES)}
+
+    if not all_fingerprints:
+        show("No .fingerprint files or cache directories found.")
+        exit(1)
+
+    missing_content = []
+    valid_paths = set()
+    fingerprint_contents = []
+
+    for fingerprint in all_fingerprints:
+        path = fingerprint.replace('.fingerprint', '')
+
+        if not os.path.exists(path):
+            missing_content.append(path)
+            continue
+
+        if not os.path.isdir(path):
+            valid_paths.add(path)
+            continue
+
+        if os.listdir(path):
+            valid_paths.add(path)
+        else:
+            missing_content.append(path)
+
+        with open(fingerprint, 'r') as f:
+            content = f.read().strip()
+            fingerprint_contents.append((fingerprint, content))
+
+    return sorted(valid_paths), missing_content, fingerprint_contents
+
+
+def parse_fingerprint_contents(fingerprint_content):
+    input_map = {}
+    for line in fingerprint_content.splitlines():
+        digest, path = line.split()
+        input_map[path] = digest
+    return input_map
+
+
+def calculate_sha256(fingerprint_contents):
+    sorted_fingerprint_contents = sorted(fingerprint_contents, key=lambda x: x[0])
+
+    concatenated_contents = ''.join(content for _, content in sorted_fingerprint_contents)
+
+    sha256_hash = hashlib.sha256(concatenated_contents.encode()).hexdigest()
+
+    return sha256_hash
+
+
+def calculate_file_sha256(file_path):
+    sha256_hash = hashlib.sha256()
+    with open(file_path, 'rb') as f:
+        for byte_block in iter(lambda: f.read(4096), b""):
+            sha256_hash.update(byte_block)
+    return sha256_hash.hexdigest()
+
+
+def show(*s: str):
+    print(*s, file=sys.stderr)
+
+
+def main(file_path: str | None):
+    base_dir = '.'
+    valid_paths, missing_content, fingerprint_contents = find_fingerprints_and_check_dirs(base_dir)
+
+    if missing_content:
+        show("The following paths are missing or have no content, but have corresponding .fingerprint files:")
+        for path in sorted(missing_content):
+            show(f"- {path}")
+        # when adding new cache directories there is a time where it is not possible to have this directory without
+        # running the tests first... but this step is a prerequisite for running the tests. We should not block on this.
+        # show("Please ensure these paths exist and have content if they are directories.")
+        # exit(1)
+
+    sha256_hash = calculate_sha256(fingerprint_contents)
+
+    paths_with_digests = []
+    for path in sorted(valid_paths):
+        fingerprint_file = f"{path}.fingerprint"
+        try:
+            if os.path.exists(fingerprint_file):
+                file_digest = calculate_file_sha256(fingerprint_file)
+
+                # Parse the fingerprint file to get the digest/path tuples
+                with open(fingerprint_file, 'r') as f:
+                    fingerprint_content = f.read().strip()
+                    input_map = parse_fingerprint_contents(fingerprint_content)
+
+                paths_with_digests.append({
+                    "path": path,
+                    "digest": file_digest,
+                    "input": input_map
+                })
+
+        except Exception as e:
+            show(f"Error processing {fingerprint_file}: {e}")
+            raise e
+
+
+    output = {
+        "digest": sha256_hash,
+        "paths": paths_with_digests
+    }
+
+    content = json.dumps(output, indent=2, sort_keys=True)
+
+    if file_path:
+        with open(file_path, 'w') as f:
+            f.write(content)
+
+    print(content)
+
+
+if __name__ == "__main__":
+    file_path = None
+    if len(sys.argv) > 1:
+        file_path = sys.argv[1]
+    main(file_path)

.github/scripts/fingerprint_docker_fixtures.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+
+import os
+import subprocess
+import hashlib
+
+BOLD = '\033[1m'
+YELLOW = '\033[0;33m'
+RESET = '\033[0m'
+
+
+def print_message(message):
+    print(f"{YELLOW}{message}{RESET}")
+
+
+def sha256sum(filepath):
+    h = hashlib.sha256()
+    with open(filepath, 'rb') as f:
+        for chunk in iter(lambda: f.read(4096), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def is_git_tracked_or_untracked(directory):
+    """Returns a sorted list of files in the directory that are tracked or not ignored by Git."""
+    result = subprocess.run(
+        ["git", "ls-files", "--cached", "--others", "--exclude-standard"],
+        cwd=directory,
+        stdout=subprocess.PIPE,
+        text=True
+    )
+    return sorted(result.stdout.strip().splitlines())
+
+
+def find_test_fixture_dirs_with_images(base_dir):
+    """Find directories that contain 'test-fixtures' and at least one 'image-*' directory."""
+    for root, dirs, files in os.walk(base_dir):
+        if 'test-fixtures' in root:
+            image_dirs = [d for d in dirs if d.startswith('image-')]
+            if image_dirs:
+                yield os.path.realpath(root)
+
+
+def generate_fingerprints():
+    print_message("creating fingerprint files for docker fixtures...")
+
+    for test_fixture_dir in find_test_fixture_dirs_with_images('.'):
+        cache_fingerprint_path = os.path.join(test_fixture_dir, 'cache.fingerprint')
+
+        with open(cache_fingerprint_path, 'w') as fingerprint_file:
+            for image_dir in find_image_dirs(test_fixture_dir):
+                for file in is_git_tracked_or_untracked(image_dir):
+                    file_path = os.path.join(image_dir, file)
+                    checksum = sha256sum(file_path)
+                    path_from_fixture_dir = os.path.relpath(file_path, test_fixture_dir)
+                    fingerprint_file.write(f"{checksum}  {path_from_fixture_dir}\n")
+
+
+def find_image_dirs(test_fixture_dir):
+    """Find all 'image-*' directories inside a given test-fixture directory."""
+    result = []
+    for root, dirs, files in os.walk(test_fixture_dir):
+        for dir_name in dirs:
+            if dir_name.startswith('image-'):
+                result.append(os.path.join(root, dir_name))
+    return sorted(result)
+
+
+if __name__ == "__main__":
+    generate_fingerprints()

.github/scripts/labeler.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 from __future__ import annotations
 
 import sys

.github/scripts/labeler_test.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 import unittest
 from unittest.mock import patch
 import subprocess

.github/workflows/benchmark-testing.yaml

@@ -1,62 +0,0 @@
-name: "Benchmark testing"
-
-on:
-  workflow_dispatch:
-  pull_request:
-
-permissions:
-  contents: read
-
-jobs:
-
-  Benchmark-Test:
-    name: "Benchmark tests"
-    runs-on: ubuntu-20.04
-    # note: we want benchmarks to run on pull_request events in order to publish results to a sticky comment, and
-    # we also want to run on push such that merges to main are recorded to the cache. For this reason we don't filter
-    # the job by event.
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - name: Restore base benchmark result
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: test/results/benchmark-main.txt
-          # use base sha for PR or new commit hash for main push in benchmark result key
-          key: ${{ runner.os }}-bench-${{ (github.event.pull_request.base.sha != github.event.after) && github.event.pull_request.base.sha || github.event.after }}
-
-      - name: Run benchmark tests
-        id: benchmark
-        run: |
-          REF_NAME=${GITHUB_REF##*/} make benchmark
-          OUTPUT=$(make show-benchstat)
-          OUTPUT="${OUTPUT//'%'/'%25'}"   # URL encode all '%' characters
-          OUTPUT="${OUTPUT//$'\n'/'%0A'}" # URL encode all '\n' characters
-          OUTPUT="${OUTPUT//$'\r'/'%0D'}" # URL encode all '\r' characters
-          echo "result=$OUTPUT" >> $GITHUB_OUTPUT
-
-      - uses: actions/upload-artifact@89ef406dd8d7e03cfd12d9e0a4a378f454709029 # v4.3.5
-        with:
-          name: benchmark-test-results
-          path: test/results/**/*
-
-      - name: Update PR benchmark results comment
-        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
-        continue-on-error: true
-        with:
-          header: benchmark
-          message: |
-            ### Benchmark Test Results
-
-            <details>
-              <summary>Benchmark results from the latest changes vs base branch</summary>
-
-            ```
-            ${{ steps.benchmark.outputs.result }}
-            ```
-
-            </details>

.github/workflows/codeql-analysis.yml

@@ -21,7 +21,7 @@ jobs:
   analyze:
     name: Analyze
     runs-on: ubuntu-22.04-4core-16gb
-
+    if: github.repository == 'anchore/syft' # only run for main repo
     permissions:
       security-events: write
 
@@ -36,16 +36,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
     - name: Install Go
-      uses: actions/setup-go@0a12ed9d6a96ab950c8f026ed9f722fe0da7ef32 #v5.0.2
+      uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 #v5.5.0
       with:
         go-version-file: go.mod
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@afb54ba388a7dca6ecae48f608c4ff05ff4cc77a #v3.25.15
+      uses: github/codeql-action/init@fca7ace96b7d713c7035871441bd52efbe39e27e #v3.28.19
       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@afb54ba388a7dca6ecae48f608c4ff05ff4cc77a #v3.25.15
+      uses: github/codeql-action/autobuild@fca7ace96b7d713c7035871441bd52efbe39e27e #v3.28.19
 
     # 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@afb54ba388a7dca6ecae48f608c4ff05ff4cc77a #v3.25.15
+      uses: github/codeql-action/analyze@fca7ace96b7d713c7035871441bd52efbe39e27e #v3.28.19

.github/workflows/detect-schema-changes.yaml

@@ -30,7 +30,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
 
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - run: python .github/scripts/labeler.py
         env:
@@ -40,7 +40,7 @@ jobs:
 
       - name: Delete existing comment
         if: ${{ hashFiles( env.CI_COMMENT_FILE ) == '' }}
-        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
+        uses: marocchino/sticky-pull-request-comment@67d0dec7b07ed060a405f9b2a64b8ab319fdd7db #v2.9.2
         with:
           header: ${{ env.COMMENT_HEADER }}
           hide: true
@@ -48,7 +48,7 @@ jobs:
 
       - name: Add comment
         if: ${{ hashFiles( env.CI_COMMENT_FILE ) != '' }}
-        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
+        uses: marocchino/sticky-pull-request-comment@67d0dec7b07ed060a405f9b2a64b8ab319fdd7db #v2.9.2
         with:
           header: ${{ env.COMMENT_HEADER }}
           path: ${{ env.CI_COMMENT_FILE }}

.github/workflows/release-version-file.yaml

@@ -1,4 +1,4 @@
-name: "Release"
+name: "Release: version file"
 
 on:
 
@@ -18,9 +18,9 @@ on:
 jobs:
 
   release:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Update version file
         run: make ci-release-version-file

.github/workflows/release.yaml

@@ -13,9 +13,9 @@ on:
 jobs:
   quality-gate:
     environment: release
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Check if running on main
         if: github.ref != 'refs/heads/main'
@@ -98,14 +98,14 @@ jobs:
 
   release:
     needs: [quality-gate]
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     permissions:
       contents: write
       packages: write
       # required for goreleaser signs section with cosign
       id-token: write
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
         with:
           fetch-depth: 0
 
@@ -113,13 +113,13 @@ jobs:
         uses: ./.github/actions/bootstrap
 
       - name: Login to Docker Hub
-        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567  #v3.3.0
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772  #v3.4.0
         with:
           username: ${{ secrets.ANCHOREOSSWRITE_DH_USERNAME }}
           password: ${{ secrets.ANCHOREOSSWRITE_DH_PAT }}
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567  #v3.3.0
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772  #v3.4.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -148,12 +148,13 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@d94f46e13c6c62f59525ac9a1e147a99dc0b9bf5 #v0.17.0
+      - uses: anchore/sbom-action@e11c554f704a0b820cbf8c51673f6945e0731532 #v0.20.0
         continue-on-error: true
         with:
+          file: go.mod
           artifact-name: sbom.spdx.json
 
-      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
+      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
         continue-on-error: true
         with:
           status: ${{ job.status }}

.github/workflows/remove-awaiting-response-label.yaml

@@ -0,0 +1,11 @@
+name: "Manage Awaiting Response Label"
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  run:
+    uses: "anchore/workflows/.github/workflows/remove-awaiting-response-label.yaml@main"
+    secrets:
+      token: ${{ secrets.OSS_PROJECT_GH_TOKEN }}

.github/workflows/test-fixture-cache-publish.yaml

@@ -0,0 +1,40 @@
+name: "Test fixture cache: publish"
+
+on:
+  workflow_dispatch:
+  schedule:
+    # run nightly at 4AM UTC
+    - cron: "0 4 * * *"
+
+permissions:
+  contents: read
+
+jobs:
+
+  Publish:
+    name: "Publish test fixture image cache"
+    # we use this runner to get enough storage space for docker images and fixture cache
+    runs-on: ubuntu-22.04-4core-16gb
+    if: github.repository == 'anchore/syft' # only run for main repo
+    permissions:
+      packages: write
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          # we want to rebuild the cache with no previous state
+          download-test-fixture-cache: false
+
+      - name: Run all tests
+        run: make test
+        env:
+          # we want to rebuild the cache with no previous state
+          DOWNLOAD_TEST_FIXTURE_CACHE: "false"
+
+      - name: Login to GitHub Container Registry (ORAS)
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | .tool/oras login ghcr.io -u ${{ github.actor }} --password-stdin
+
+      - name: Publish test fixture cache
+        run: make upload-test-fixture-cache

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

@@ -0,0 +1,49 @@
+name: PR to update Anchore dependencies
+on:
+  workflow_dispatch:
+    inputs:
+      repos:
+        description: "List of dependencies to update"
+        required: true
+        type: string
+
+permissions:
+  contents: read
+
+jobs:
+  update:
+    runs-on: ubuntu-latest
+    if: github.repository_owner == 'anchore' # only run for main repo (not forks)
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          tools: false
+          bootstrap-apt-packages: ""
+
+      - name: Update dependencies
+        id: update
+        uses: anchore/workflows/.github/actions/update-go-dependencies@main
+        with:
+          repos: ${{ github.event.inputs.repos }}
+
+      - 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
+          draft: ${{ steps.update.outputs.draft }}
+          # do not change this branch, as other workflows depend on it
+          branch: auto/integration
+          labels: dependencies,pre-release
+          commit-message: "chore(deps): update anchore dependencies"
+          title: "chore(deps): update anchore dependencies"
+          body: ${{ steps.update.outputs.summary }}
+          token: ${{ steps.generate-token.outputs.token }}

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

@@ -13,13 +13,12 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
         with:
           bootstrap-apt-packages: ""
-          compute-fingerprints: "false"
           go-dependencies: false
 
       - name: "Update tool versions"
@@ -50,7 +49,7 @@ jobs:
           app_id: ${{ secrets.TOKEN_APP_ID }}
           private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
-      - uses: peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c #v6.1.0
+      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:
           signoff: true
           delete-branch: true

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

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -33,7 +33,7 @@ jobs:
           app_id: ${{ secrets.TOKEN_APP_ID }}
           private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
-      - uses: peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c #v6.1.0
+      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:
           signoff: true
           delete-branch: true
@@ -45,7 +45,7 @@ jobs:
             Update CPE dictionary index based on the latest available CPE dictionary
           token: ${{ steps.generate-token.outputs.token }}
 
-      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
+      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
         with:
           status: ${{ job.status }}
           fields: workflow,eventName,job

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

@@ -1,57 +0,0 @@
-name: PR for latest Stereoscope release
-on:
-  schedule:
-    - cron: "0 8 * * *" # 3 AM EST
-
-  workflow_dispatch:
-
-env:
-  GO_VERSION: "1.21.x"
-  GO_STABLE_VERSION: true
-
-permissions:
-  contents: read
-
-jobs:
-  upgrade-stereoscope:
-    runs-on: ubuntu-latest
-    if: github.repository == 'anchore/syft' # only run for main repo
-    steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
-
-      - uses: actions/setup-go@0a12ed9d6a96ab950c8f026ed9f722fe0da7ef32 #v5.0.2
-        with:
-          go-version: ${{ env.GO_VERSION }}
-          stable: ${{ env.GO_STABLE_VERSION }}
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - run: |
-          LATEST_VERSION=$(git ls-remote https://github.com/anchore/stereoscope main | head -n1 | awk '{print $1;}')
-
-          # update go.mod
-          go get github.com/anchore/stereoscope@$LATEST_VERSION
-          go mod tidy
-
-          # export the version for use with create-pull-request
-          echo "LATEST_VERSION=$LATEST_VERSION" >> $GITHUB_OUTPUT
-        id: latest-version
-
-      - 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@c5a7806660adbe173f04e3e038b0ccdcd758773c #v6.1.0
-        with:
-          signoff: true
-          delete-branch: true
-          branch: auto/latest-stereoscope
-          labels: dependencies
-          commit-message: "chore(deps): update stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}"
-          title: "chore(deps): update stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}"
-          body: |
-            Update Stereoscope to ${{ steps.latest-version.outputs.LATEST_VERSION }}
-          token: ${{ steps.generate-token.outputs.token }}

.github/workflows/validations.yaml

@@ -15,9 +15,9 @@ jobs:
   Static-Analysis:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Static analysis"
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -29,54 +29,15 @@ jobs:
   Unit-Test:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Unit tests"
-    runs-on: ubuntu-20.04
+    # we need more storage than what's on the default runner
+    runs-on: ubuntu-22.04-4core-16gb
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore file executable test-fixture cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
-          path: syft/file/cataloger/executable/test-fixtures/elf/bin
-          key: ${{ runner.os }}-unit-file-executable-elf-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint' ) }}
-
-      - name: Restore file executable shared-info test-fixture cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: syft/file/cataloger/executable/test-fixtures/shared-info/bin
-          key: ${{ runner.os }}-unit-file-executable-shared-info-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint' ) }}
-
-      - name: Restore Java test-fixture cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        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@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        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@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        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@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        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@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: syft/pkg/cataloger/kernel/test-fixtures/cache
-          key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
+          download-test-fixture-cache: true
 
       - name: Run unit tests
         run: make unit
@@ -85,31 +46,27 @@ jobs:
   Integration-Test:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Integration tests"
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        with:
+          download-test-fixture-cache: true
 
       - name: Validate syft output against the CycloneDX schema
         run: make validate-cyclonedx-schema
 
-      - name: Restore integration test cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: ${{ github.workspace }}/cmd/syft/internal/test/integration/test-fixtures/cache
-          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('/cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint') }}
-
       - name: Run integration tests
         run: make integration
 
 
   Build-Snapshot-Artifacts:
     name: "Build snapshot artifacts"
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -119,10 +76,13 @@ jobs:
       - name: Build snapshot artifacts
         run: make snapshot
 
+      - name: Smoke test snapshot build
+        run: make snapshot-smoke-test
+
       # 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@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
+        uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         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
@@ -133,20 +93,77 @@ jobs:
           key: snapshot-build-${{ github.run_id }}
 
 
+  Upload-Snapshot-Artifacts:
+    # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
+    name: "Upload snapshot artifacts"
+    needs: [Build-Snapshot-Artifacts]
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          download-test-fixture-cache: true
+
+      - name: Download snapshot build
+        id: snapshot-cache
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
+        with:
+          path: |
+            snapshot
+            .task
+          fail-on-cache-miss: true
+          key: snapshot-build-${{ github.run_id }}
+
+      # workaround for https://github.com/actions/cache/issues/1265
+      - name: (cache-miss) Snapshot build missing
+        if: steps.snapshot-cache.outputs.cache-hit != 'true'
+        run: echo "unable to download snapshots from previous job" && false
+
+      - run: npm install @actions/artifact@2.2.2
+
+      - uses: actions/github-script@v7
+        with:
+          script: |
+            const { readdirSync } = require('fs')
+            const { DefaultArtifactClient } = require('@actions/artifact')
+            const artifact = new DefaultArtifactClient()
+            const ls = d => readdirSync(d, { withFileTypes: true })
+            const baseDir = "./snapshot"
+            const dirs = ls(baseDir).filter(f => f.isDirectory()).map(f => f.name)
+            const uploads = []
+            for (const dir of dirs) {
+              // uploadArtifact returns Promise<{id, size}>
+              uploads.push(artifact.uploadArtifact(
+                // name of the archive:
+                `${dir}`,
+                // array of all files to include:
+                ls(`${baseDir}/${dir}`).map(f => `${baseDir}/${dir}/${f.name}`),
+                // base directory to trim from entries:
+                `${baseDir}/${dir}`,
+                { retentionDays: 30 }
+              ))
+            }
+            // wait for all uploads to finish
+            Promise.all(uploads)
+
   Acceptance-Linux:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Acceptance tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        with:
+          download-test-fixture-cache: true
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             snapshot
@@ -162,13 +179,6 @@ jobs:
       - name: Run comparison tests (Linux)
         run: make compare-linux
 
-      - name: Restore install.sh test image cache
-        id: install-test-image-cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: ${{ github.workspace }}/test/install/cache
-          key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
-
       - name: Load test image cache
         if: steps.install-test-image-cache.outputs.cache-hit == 'true'
         run: make install-test-cache-load
@@ -188,20 +198,20 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Install Cosign
-        uses: sigstore/cosign-installer@v3.5.0
+        uses: sigstore/cosign-installer@v3.8.2
 
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
         with:
           bootstrap-apt-packages: ""
-          compute-fingerprints: "false"
           go-dependencies: false
+          download-test-fixture-cache: true
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             snapshot
@@ -214,13 +224,6 @@ jobs:
         if: steps.snapshot-cache.outputs.cache-hit != 'true'
         run: echo "unable to download snapshots from previous job" && false
 
-      - name: Restore docker image cache for compare testing
-        id: mac-compare-testing-cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
-        with:
-          path: image.tar
-          key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
-
       - name: Run comparison tests (Mac)
         run: make compare-mac
 
@@ -232,22 +235,18 @@ jobs:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "CLI tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore CLI test-fixture cache
-        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
-          path: ${{ github.workspace }}/test/cli/test-fixtures/cache
-          key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}
+          download-test-fixture-cache: true
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             snapshot
@@ -262,3 +261,23 @@ jobs:
 
       - name: Run CLI Tests (Linux)
         run: make cli
+
+
+  Cleanup-Cache:
+    name: "Cleanup snapshot cache"
+    if: github.event.pull_request.head.repo.full_name == github.repository
+    runs-on: ubuntu-24.04
+    permissions:
+      actions: write
+    needs:
+      - Acceptance-Linux
+      - Acceptance-Mac
+      - Cli-Linux
+      - Upload-Snapshot-Artifacts
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 #v4.2.2
+
+      - name: Delete snapshot cache
+        run: gh cache delete "snapshot-build-${{ github.run_id }}"
+        env:
+          GH_TOKEN: ${{ github.token }}

.golangci.yaml

@@ -1,66 +1,58 @@
-issues:
-  max-same-issues: 25
-
-  # TODO: enable this when we have coverage on docstring comments
-#  # The list of ids of default excludes to include or disable.
-#  include:
-#    - EXC0002 # disable excluding of issues about comments from golint
-
+version: "2"
+run:
+  tests: false
 linters:
-  # inverted configuration with `enable-all` and `disable` is not scalable during updates of golangci-lint
-  disable-all: true
+  default: none
   enable:
     - asciicheck
     - bodyclose
+    - copyloopvar
     - dogsled
     - dupl
     - errcheck
-    - exportloopref
     - funlen
     - gocognit
     - goconst
     - gocritic
     - gocyclo
-    - gofmt
-    - goimports
     - goprintffuncname
     - gosec
-    - gosimple
     - govet
     - ineffassign
     - misspell
     - nakedret
+    - nolintlint
     - revive
     - staticcheck
-    - stylecheck
-    - typecheck
     - unconvert
     - unparam
     - unused
     - whitespace
-
-linters-settings:
-  funlen:
-    # Checks the number of lines in a function.
-    # If lower than 0, disable the check.
-    # Default: 60
-    lines: 70
-    # Checks the number of statements in a function.
-    # If lower than 0, disable the check.
-    # Default: 40
-    statements: 50
-  gocritic:
-    enabled-checks:
-      - deferInLoop
-      - ruleguard
-    settings:
-      ruleguard:
-        rules: "test/rules/rules.go"
-output:
-  uniq-by-line: false
-run:
-  timeout: 10m
-  tests: false
+  settings:
+    funlen:
+      lines: 70
+      statements: 50
+    gocritic:
+      enabled-checks:
+        - deferInLoop
+        - ruleguard
+      settings:
+        ruleguard:
+          rules: test/rules/rules.go
+    gosec:
+      excludes:
+        - G115
+  exclusions:
+    generated: lax
+    presets:
+      - comments
+      - common-false-positives
+      - legacy
+      - std-error-handling
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
 
 # do not enable...
 #    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
@@ -80,7 +72,6 @@ run:
 #    - lll         # without a way to specify per-line exception cases, this is not usable
 #    - maligned    # this is an excellent linter, but tricky to optimize and we are not sensitive to memory layout optimizations
 #    - nestif
-#    - nolintlint   # as of go1.19 this conflicts with the behavior of gofmt, which is a deal-breaker (lint-fix will still fail when running lint)
 #    - prealloc     # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
 #    - rowserrcheck # not in a repo with sql, so this is not useful
 #    - scopelint    # deprecated
@@ -88,3 +79,23 @@ run:
 #    - testpackage
 #    - varcheck     # The owner seems to have abandoned the linter. Replaced by "unused".
 #    - wsl          # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)
+
+issues:
+  max-same-issues: 25
+  uniq-by-line: false
+
+# TODO: enable this when we have coverage on docstring comments
+#  # The list of ids of default excludes to include or disable.
+#  include:
+#    - EXC0002 # disable excluding of issues about comments from golint
+
+formatters:
+  enable:
+    - gofmt
+    - goimports
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$

.goreleaser.yaml

@@ -1,11 +1,11 @@
 version: 2
+project_name: syft
 
 release:
   prerelease: auto
   draft: false
 
 env:
-  # required to support multi architecture docker builds
   - DOCKER_CLI_EXPERIMENTAL=enabled
   - CGO_ENABLED=0
 
@@ -13,14 +13,8 @@ builds:
   - id: linux-build
     dir: ./cmd/syft
     binary: syft
-    goos:
-      - linux
-    goarch:
-      - amd64
-      - arm64
-      - ppc64le
-      - s390x
-    # set the modified timestamp on the output binary to the git timestamp to ensure a reproducible build
+    goos: [linux]
+    goarch: [amd64, arm64, ppc64le, s390x]
     mod_timestamp: &build-timestamp '{{ .CommitTimestamp }}'
     ldflags: &build-ldflags |
       -w
@@ -34,11 +28,8 @@ builds:
   - id: darwin-build
     dir: ./cmd/syft
     binary: syft
-    goos:
-      - darwin
-    goarch:
-      - amd64
-      - arm64
+    goos: [darwin]
+    goarch: [amd64, arm64]
     mod_timestamp: *build-timestamp
     ldflags: *build-ldflags
     hooks:
@@ -50,115 +41,42 @@ builds:
   - id: windows-build
     dir: ./cmd/syft
     binary: syft
-    goos:
-      - windows
-    goarch:
-      - amd64
+    goos: [windows]
+    goarch: [amd64]
     mod_timestamp: *build-timestamp
     ldflags: *build-ldflags
 
 archives:
   - id: linux-archives
-    builds:
-      - linux-build
-
-  # note: the signing process is depending on tar.gz archives. If this format changes then .github/scripts/apple-signing/*.sh will need to be adjusted
+    builds: [linux-build]
   - id: darwin-archives
-    builds:
-      - darwin-build
-
+    builds: [darwin-build]
   - id: windows-archives
     format: zip
-    builds:
-      - windows-build
+    builds: [windows-build]
 
 nfpms:
   - license: "Apache 2.0"
     maintainer: "Anchore, Inc"
     homepage: &website "https://github.com/anchore/syft"
     description: &description "A tool that generates a Software Bill Of Materials (SBOM) from container images and filesystems"
-    formats:
-      - rpm
-      - deb
+    formats: [rpm, deb]
 
 brews:
   - repository:
       owner: anchore
       name: homebrew-syft
       token: "{{.Env.GITHUB_BREW_TOKEN}}"
-    ids:
-      - darwin-archives
-      - linux-archives
+    ids: [darwin-archives, linux-archives]
     homepage: *website
     description: *description
     license: "Apache License 2.0"
 
 dockers:
+  # production images...
   - image_templates:
-      - anchore/syft:debug
-      - anchore/syft:{{.Tag}}-debug
-      - ghcr.io/anchore/syft:debug
-      - ghcr.io/anchore/syft:{{.Tag}}-debug
-    goarch: amd64
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/amd64"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:debug-arm64v8
-      - anchore/syft:{{.Tag}}-debug-arm64v8
-      - ghcr.io/anchore/syft:debug-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
-    goarch: arm64
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/arm64/v8"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:debug-ppc64le
-      - anchore/syft:{{.Tag}}-debug-ppc64le
-      - ghcr.io/anchore/syft:debug-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
-    goarch: ppc64le
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/ppc64le"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:debug-s390x
-      - anchore/syft:{{.Tag}}-debug-s390x
-      - ghcr.io/anchore/syft:debug-s390x
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
-    goarch: s390x
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/s390x"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:latest
-      - anchore/syft:{{.Tag}}
-      - ghcr.io/anchore/syft:latest
-      - ghcr.io/anchore/syft:{{.Tag}}
+      - anchore/syft:{{.Tag}}-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-amd64
     goarch: amd64
     dockerfile: Dockerfile
     use: buildx
@@ -208,51 +126,201 @@ dockers:
       - "--build-arg=VCS_REF={{.FullCommit}}"
       - "--build-arg=VCS_URL={{.GitURL}}"
 
+  # nonroot images...
+  - image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
+    goarch: amd64
+    dockerfile: Dockerfile.nonroot
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/amd64"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
+    goarch: arm64
+    dockerfile: Dockerfile.nonroot
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/arm64/v8"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
+    goarch: ppc64le
+    dockerfile: Dockerfile.nonroot
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/ppc64le"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-s390x
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
+    goarch: s390x
+    dockerfile: Dockerfile.nonroot
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/s390x"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  # debug images...
+  - image_templates:
+      - anchore/syft:{{.Tag}}-debug-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
+    goarch: amd64
+    dockerfile: Dockerfile.debug
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/amd64"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-debug-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
+    goarch: arm64
+    dockerfile: Dockerfile.debug
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/arm64/v8"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-debug-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
+    goarch: ppc64le
+    dockerfile: Dockerfile.debug
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/ppc64le"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+  - image_templates:
+      - anchore/syft:{{.Tag}}-debug-s390x
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
+    goarch: s390x
+    dockerfile: Dockerfile.debug
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/s390x"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
 docker_manifests:
   - name_template: anchore/syft:latest
     image_templates:
-      - anchore/syft:{{.Tag}}
-      - anchore/syft:{{.Tag}}-arm64v8
-      - anchore/syft:{{.Tag}}-ppc64le
-      - anchore/syft:{{.Tag}}-s390x
-
-  - name_template: anchore/syft:debug
-      - anchore/syft:{{.Tag}}-debug
-      - anchore/syft:{{.Tag}}-debug-arm64v8
-      - anchore/syft:{{.Tag}}-debug-ppc64le
-      - anchore/syft:{{.Tag}}-debug-s390x
-
-  - name_template: anchore/syft:{{.Tag}}
-    image_templates:
-      - anchore/syft:{{.Tag}}
+      - anchore/syft:{{.Tag}}-amd64
       - anchore/syft:{{.Tag}}-arm64v8
       - anchore/syft:{{.Tag}}-ppc64le
       - anchore/syft:{{.Tag}}-s390x
 
   - name_template: ghcr.io/anchore/syft:latest
     image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}
+      - ghcr.io/anchore/syft:{{.Tag}}-amd64
       - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
       - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
       - ghcr.io/anchore/syft:{{.Tag}}-s390x
 
+  - name_template: anchore/syft:{{.Tag}}
+    image_templates:
+      - anchore/syft:{{.Tag}}-amd64
+      - anchore/syft:{{.Tag}}-arm64v8
+      - anchore/syft:{{.Tag}}-ppc64le
+      - anchore/syft:{{.Tag}}-s390x
+
+  - name_template: ghcr.io/anchore/syft:{{.Tag}}
+    image_templates:
+      - ghcr.io/anchore/syft:{{.Tag}}-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-s390x
+
+  # nonroot images...
+  - name_template: anchore/syft:nonroot
+    image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-amd64
+      - anchore/syft:{{.Tag}}-nonroot-arm64v8
+      - anchore/syft:{{.Tag}}-nonroot-ppc64le
+      - anchore/syft:{{.Tag}}-nonroot-s390x
+
+  - name_template: ghcr.io/anchore/syft:nonroot
+    image_templates:
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
+
+  - name_template: anchore/syft:{{.Tag}}-nonroot
+    image_templates:
+      - anchore/syft:{{.Tag}}-nonroot-amd64
+      - anchore/syft:{{.Tag}}-nonroot-arm64v8
+      - anchore/syft:{{.Tag}}-nonroot-ppc64le
+      - anchore/syft:{{.Tag}}-nonroot-s390x
+
+  - name_template: ghcr.io/anchore/syft:{{.Tag}}-nonroot
+    image_templates:
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
+
+  # debug images...
+  - name_template: anchore/syft:debug
+    image_templates:
+      - anchore/syft:{{.Tag}}-debug-amd64
+      - anchore/syft:{{.Tag}}-debug-arm64v8
+      - anchore/syft:{{.Tag}}-debug-ppc64le
+      - anchore/syft:{{.Tag}}-debug-s390x
+
   - name_template: ghcr.io/anchore/syft:debug
     image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-debug
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
       - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
       - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
       - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
 
-  - name_template: ghcr.io/anchore/syft:{{.Tag}}
+  - name_template: anchore/syft:{{.Tag}}-debug
     image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}
-      - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-s390x
+      - anchore/syft:{{.Tag}}-debug-amd64
+      - anchore/syft:{{.Tag}}-debug-arm64v8
+      - anchore/syft:{{.Tag}}-debug-ppc64le
+      - anchore/syft:{{.Tag}}-debug-s390x
+
+  - name_template: ghcr.io/anchore/syft:{{.Tag}}-debug
+    image_templates:
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
+      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
 
 sboms:
   - artifacts: archive
-    # this is relative to the snapshot/dist directory, not the root of the repo
     cmd: ../.tool/syft
     documents:
       - "{{ .Binary }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}.sbom"

CONTRIBUTORS.md

@@ -8,4 +8,8 @@ A cataloger contributed by Oracle Corporation that extracts packages given withi
 
 ## Swift Package Manager
 
-A cataloger contributed by Axis Communications that catalogs packages resolved by Swift Package Manager.
+A cataloger contributed by Axis Communications that catalogs packages resolved by Swift Package Manager.
+
+## Bitnami Packages
+
+A cataloger contributed by Bitnami developer that catalogs packages described in Bitnami SBOMs.

DEVELOPING.md

@@ -83,7 +83,7 @@ Syft's core library is implemented in the `syft` package and subpackages, where
 - the `syft` package contains a single function that can take a `source.Source` object and catalog it, producing an `sbom.SBOM` object
 - the `syft/format` package contains the ability to encode and decode SBOMs to and from different SBOM formats (such as SPDX and CycloneDX)
 
-The `cmd` pacakge at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
+The `cmd` package at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
 ```mermaid
 sequenceDiagram
     participant main as cmd/syft/main
@@ -212,7 +212,7 @@ Finally, here is an example of where the package construction is done within the
 - [The APK package constructor itself](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/package.go#L12-L27)
 
 Interested in building a new cataloger? Checkout the [list of issues with the `new-cataloger` label](https://github.com/anchore/syft/issues?q=is%3Aopen+is%3Aissue+label%3Anew-cataloger+no%3Aassignee)!
-If you have questions about implementing a cataloger feel free to file an issue or reach out to us [on slack](https://anchore.com/slack)!
+If you have questions about implementing a cataloger feel free to file an issue or reach out to us [on discourse](https://anchore.com/discourse)!
 
 
 #### Searching for files
@@ -227,6 +227,16 @@ rough outline how that works:
 
 ## Testing
 
+### Testing commands
+
+* `make help` shows a list of available commands
+* `make unit`, `make integration`, `make cli`, and `make acceptance` run those test suites (see below)
+* `make test` runs all those tests (and is therefore pretty slow)
+* `make fixtures` clears and re-fetches all test fixtures.
+* `go test ./syft/pkg/` for example can test particular packages, assuming fixtures are already made
+* `make clean-cache` cleans all test cache. Note that subsequent test runs will be slower after this
+
+
 ### Levels of testing
 
 - `unit`: The default level of test which is distributed throughout the repo are unit tests. Any `_test.go` file that 
@@ -367,11 +377,11 @@ package under test and should always be updated by invoking `go test` on the spe
 update flag provided.
 
 Many of the `Format` tests make use of this approach, where the raw SBOM report is saved in the repo and the test 
-compares that SBOM with what is generated from the latest presenter code. For instance, at the time of this writing 
-the CycloneDX presenter snapshots can be updated by running:
+compares that SBOM with what is generated from the latest presenter code. The following command can be used to
+update the golden files for the various snapshot tests:
 
 ```bash
-go test ./internal/formats -update-cyclonedx
+make update-format-golden-files
 ```
 
 These flags are defined at the top of the test files that have tests that use the snapshot files.

Dockerfile

@@ -1,4 +1,4 @@
-FROM gcr.io/distroless/static-debian11:debug@sha256:a0a404776dec98be120089ae42bbdfbe48c177921d856937d124d48eb8c0b951 AS build
+FROM gcr.io/distroless/static-debian12:latest AS build
 
 FROM scratch
 # needed for version check HTTPS request

Dockerfile.debug

@@ -1,10 +1,12 @@
-FROM gcr.io/distroless/static-debian11:debug@sha256:a0a404776dec98be120089ae42bbdfbe48c177921d856937d124d48eb8c0b951
+FROM gcr.io/distroless/static-debian12:debug-nonroot
 
 # create the /tmp dir, which is needed for image content cache
 WORKDIR /tmp
 
 COPY syft /
 
+USER nonroot
+
 ARG BUILD_DATE
 ARG BUILD_VERSION
 ARG VCS_REF

Dockerfile.nonroot

@@ -0,0 +1,27 @@
+FROM gcr.io/distroless/static-debian12:nonroot
+
+# create the /tmp dir, which is needed for image content cache
+WORKDIR /tmp
+
+COPY syft /
+
+USER nonroot
+
+ARG BUILD_DATE
+ARG BUILD_VERSION
+ARG VCS_REF
+ARG VCS_URL
+
+LABEL org.opencontainers.image.created=$BUILD_DATE
+LABEL org.opencontainers.image.title="syft"
+LABEL org.opencontainers.image.description="CLI tool and library for generating a Software Bill of Materials from container images and filesystems"
+LABEL org.opencontainers.image.source=$VCS_URL
+LABEL org.opencontainers.image.revision=$VCS_REF
+LABEL org.opencontainers.image.vendor="Anchore, Inc."
+LABEL org.opencontainers.image.version=$BUILD_VERSION
+LABEL org.opencontainers.image.licenses="Apache-2.0"
+LABEL io.artifacthub.package.readme-url="https://raw.githubusercontent.com/anchore/syft/main/README.md"
+LABEL io.artifacthub.package.logo-url="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png"
+LABEL io.artifacthub.package.license="Apache-2.0"
+
+ENTRYPOINT ["/syft"]

Makefile

@@ -25,8 +25,8 @@ ci-bootstrap-go:
 
 # this is a bootstrapping catch-all, where if the target doesn't exist, we'll ensure the tools are installed and then try again
 %:
-	make $(TASK)
-	$(TASK) $@
+	@make --silent $(TASK)
+	@$(TASK) $@
 
 ## Shim targets #################################
 

README.md

@@ -12,7 +12,8 @@
  &nbsp;<a href="https://github.com/anchore/syft/releases/latest" target="_blank"><img alt="GitHub release" src="https://img.shields.io/github/release/anchore/syft.svg"></a>&nbsp;
  &nbsp;<a href="https://github.com/anchore/syft" target="_blank"><img alt="GitHub go.mod Go version" src="https://img.shields.io/github/go-mod/go-version/anchore/syft.svg"></a>&nbsp;
  &nbsp;<a href="" target="_blank"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"></a>&nbsp;
- &nbsp;<a href="https://anchore.com/slack" target="_blank"><img alt="Slack" src="https://img.shields.io/badge/Slack-Join-blue?logo=slack"></a>&nbsp;
+ &nbsp;<a href="https://anchore.com/discourse" target="_blank"><img alt="Join our Discourse" src="https://img.shields.io/badge/Discourse-Join-blue?logo=discourse"/></a>&nbsp;
+ &nbsp;<a rel="me" href="https://fosstodon.org/@syft"><img alt="Follow on Mastodon" src="https://img.shields.io/badge/Mastodon-Follow-blue?logoColor=white&logo=mastodon"/></a>&nbsp;
 </p>
 
 ![syft-demo](https://user-images.githubusercontent.com/590471/90277200-2a253000-de33-11ea-893f-32c219eea11a.gif)
@@ -66,7 +67,7 @@ choco install syft -y
 
 ### Nix
 
-**Note**: Nix packaging of Syft is [community maintained](https://github.com/NixOS/nixpkgs/blob/master/pkgs/tools/admin/syft/default.nix). Syft is available in the [stable channel](https://wiki.nixos.org/wiki/Nix_channels#The_official_channels) since NixOS `22.05`.
+**Note**: Nix packaging of Syft is [community maintained](https://github.com/NixOS/nixpkgs/blob/master/pkgs/by-name/sy/syft/package.nix). Syft is available in the [stable channel](https://wiki.nixos.org/wiki/Nix_channels#The_official_channels) since NixOS `22.05`.
 
 ```bash
 nix-env -i syft
@@ -122,6 +123,7 @@ Note that flags using the @<version> can be used for earlier versions of each sp
 ### Supported Ecosystems
 
 - Alpine (apk)
+- Bitnami packages
 - C (conan)
 - C++ (conan)
 - Dart (pubs)
@@ -138,13 +140,14 @@ Note that flags using the @<version> can be used for earlier versions of each sp
 - Linux kernel archives (vmlinz)
 - Linux kernel modules (ko)
 - Nix (outputs in /nix/store)
-- PHP (composer)
+- PHP (composer, PECL, Pear)
 - Python (wheel, egg, poetry, requirements.txt)
 - Red Hat (rpm)
 - Ruby (gem)
-- Rust (cargo.lock)
+- Rust (cargo.lock, auditable binary)
 - Swift (cocoapods, swift-package-manager)
 - Wordpress plugins
+- Terraform providers (.terraform.lock.hcl)
 
 ## Documentation
 
@@ -178,3 +181,7 @@ The Syft Team hold regular community meetings online. All are welcome to join to
 - Check the [calendar](https://calendar.google.com/calendar/u/0/r?cid=Y182OTM4dGt0MjRtajI0NnNzOThiaGtnM29qNEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) for the next meeting date. 
 - Add items to the [agenda](https://docs.google.com/document/d/1ZtSAa6fj2a6KRWviTn3WoJm09edvrNUp4Iz_dOjjyY8/edit?usp=sharing) (join [this group](https://groups.google.com/g/anchore-oss-community) for write access to the [agenda](https://docs.google.com/document/d/1ZtSAa6fj2a6KRWviTn3WoJm09edvrNUp4Iz_dOjjyY8/edit?usp=sharing))
 - See you there!
+
+## Syft Logo
+
+<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/"><a property="dct:title" rel="cc:attributionURL" href="https://anchore.com/wp-content/uploads/2024/11/syft-logo.svg">Syft Logo</a> by <a rel="cc:attributionURL dct:creator" property="cc:attributionName" href="https://anchore.com/">Anchore</a> is licensed under <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC BY 4.0<img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg" alt=""></a></p>

RELEASE.md

@@ -1,5 +1,16 @@
 # Release
 
+A release of syft comprises:
+- a new semver git tag from the current tip of the main branch
+- a new [github release](https://github.com/anchore/syft/releases) with a changelog and archived binary assets
+- docker images published to `ghcr.io` and `dockerhub`, including multi architecture images + manifest
+- [`anchore/homebrew-syft`](https://github.com/anchore/homebrew-syft) tap updated to point to assets in the latest github release
+
+Ideally releasing should be done often with small increments when possible. Unless a
+breaking change is blocking the release, or no fixes/features have been merged, a good
+target release cadence is between every 1 or 2 weeks.
+
+
 ## Creating a release
 
 This release process itself should be as automated as possible, and has only a few steps:
@@ -9,16 +20,10 @@ This release process itself should be as automated as possible, and has only a f
   you can abort and adjust the labels on the PRs and issues to be included in the release and
   re-run the release trigger command.
 
-1. A release admin must approve the release on the GitHub Actions release pipeline run page.
+1. A release admin must approve the release on the GitHub Actions [release pipeline](https://github.com/anchore/syft/actions/workflows/release.yaml) run page.
    Once approved, the release pipeline will generate all assets and publish a GitHub Release.
 
-1. If there is a release Milestone, close it.
-
-Ideally releasing should be done often with small increments when possible. Unless a
-breaking change is blocking the release, or no fixes/features have been merged, a good
-target release cadence is between every 1 or 2 weeks.
-
-
+   
 ## Retracting a release
 
 If a release is found to be problematic, it can be retracted with the following steps:
@@ -32,81 +37,3 @@ If a release is found to be problematic, it can be retracted with the following
 in the go proxy, which will cause confusion when trying to reuse the tag later (the H1 hash will not match and there
 will be a warning when users try to pull the new release).
 
-
-## Background
-
-A good release process has the following qualities:
-
-1. There is a way to plan what should be in a release
-1. There is a way to see what is actually in a release
-1. Allow for different kinds of releases (major breaking vs backwards compatible enhancements vs patch updates)
-1. Specify a repeatable way to build and publish software artifacts
-
-
-### Planning a release
-
-To indicate a set of features to be released together add each issue to an in-repository
-Milestone named with major-minor version to be released (e.g. `v0.1`). It is OK for other
-features to be in the release that were not originally planned, and these issues and PRs
-do not need to be added to the Milestone in question. Only the set of features that, when
-completed, would allow the release to be considered complete. A Milestone is only used to:
-
-- Plan what is desired to be in a release
-- Track progress to indicate when we may be ready to cut a new release
-
-Not all releases need to be planned. For instance, patch releases for fixes should be
-released when they are ready and when releasing would not interfere with another current
-release (where some partial or breaking features have already been merged).
-
-Unless necessary, feature releases should be small and frequent, which may obviate the
-need for regular release planning under a Milestone.
-
-
-### What is in a release
-
-Milestones are specifically for planning a release, not necessarily tracking all changes
-that a release may bring (and more importantly, not all releases are necessarily planned
-either).
-
-This is one of the (many) reasons for a Changelog. A good Changelog lists changes grouped
-by the type of change (new, enhancement, deprecation, breaking, bug fix, security fix), in
-chronological order (within groups), linking the PR where the change was made in the
-Changelog line. Furthermore, there should be a place to see all released versions, the
-release date for each release, the semantic version of the release, and the set of changes
-for each release.
-
-**This project auto-generates the Changelog contents for each current release and posts the
-generated contents to the GitHub Release page**. Leveraging the GitHub Releases feature
-allows GitHub to manage the Changelog on each release outside of the git source tree while
-still being hosted with the released assets.
-
-The Changelog is generated from the metadata from in-repository issues and PRs, using
-labels to guide what kind of change each item is (e.g. breaking, new feature, bug fix,
-etx). Only issues/PRs with select labels are included in the Changelog, and only if the
-issue/PR was created after the last release. Additional labels are used to exclude items
-from the Changelog.
-
-The above suggestions imply that we should:
-
-- Ensure there is a sufficient title for each PR and issue title to be included in the
-  Changelog
-- The appropriate label is applied to PRs and/or issues to drive specific change type
-  sections (deprecated, breaking, security, bug, etc)
-
-**With this approach as we cultivate good organization of PRs and issues we automatically
-get an equally good Changelog.**
-
-
-### Major, minor, and patch releases
-
-The latest version of the tool is the only supported version, which implies that multiple
-parallel release branches will not be a regular process (if ever). Multiple releases can
-be planned in parallel, however, only one can be actively developed at a time. That is, if
-PRs attached to a release Milestone have been merged into the main branch, that release is
-now the "next" release. **This implies that the source of truth for release lies with the
-git log and Changelog, not with the release Milestones** (which are purely for planning and
-tracking).
-
-Semantic versioning should be used to indicate breaking changes, new features, and fixes.
-The exception to this is `< 1.0`, where the major version is not bumped for breaking changes,
-instead the minor version indicates both new features and breaking changes.

Taskfile.yaml

@@ -4,9 +4,19 @@ vars:
   OWNER: anchore
   PROJECT: syft
 
+  CACHE_IMAGE: ghcr.io/{{ .OWNER }}/{{ .PROJECT }}/test-fixture-cache:latest
+
   # static file dirs
   TOOL_DIR: .tool
   TMP_DIR: .tmp
+  ORAS_CACHE: "{{ .TMP_DIR }}/oras-cache"
+  CACHE_PATHS_FILE: "{{ .TMP_DIR }}/cache_paths.json"
+  LAST_CACHE_PULL_FILE: "{{ .TMP_DIR }}/last_cache_paths.json"
+
+  # TOOLS
+  ORAS: "{{ .TOOL_DIR }}/oras"
+  YQ: "{{ .TOOL_DIR }}/yq"
+  TASK: "{{ .TOOL_DIR }}/task"
 
   # used for changelog generation
   CHANGELOG: CHANGELOG.md
@@ -17,10 +27,12 @@ vars:
     sh: uname -s | tr '[:upper:]' '[:lower:]'
   ARCH:
     sh: |
-      [ "$(uname -m)" = "x86_64" ] && echo "amd64_v1" || echo $(uname -m)
+      [ "$(uname -m)" = "x86_64" ] && echo "amd64_v1" || { [ "$(uname -m)" = "aarch64" ] && echo "arm64_v8.0" || [ "$(uname -m)" = "arm64" ] && echo "arm64_v8.0" || echo $(uname -m); }
   PROJECT_ROOT:
     sh: echo $PWD
+
   # note: the snapshot dir must be a relative path starting with ./
+  # e.g. when installing snapshot debs from a local path, ./ forces the deb to be installed in the current working directory instead of referencing a package name
   SNAPSHOT_DIR: ./snapshot
   SNAPSHOT_BIN: "{{ .PROJECT_ROOT }}/{{ .SNAPSHOT_DIR }}/{{ .OS }}-build_{{ .OS }}_{{ .ARCH }}/{{ .PROJECT }}"
   SNAPSHOT_CMD: "{{ .TOOL_DIR }}/goreleaser release --config {{ .TMP_DIR }}/goreleaser.yaml --clean --snapshot --skip=publish --skip=sign"
@@ -33,6 +45,9 @@ vars:
   COMPARE_DIR: ./test/compare
   COMPARE_TEST_IMAGE: centos:8.2.2004
 
+env:
+  GNUMAKEFLAGS: '--no-print-directory'
+
 tasks:
 
   ## High-level tasks #################################
@@ -62,9 +77,9 @@ tasks:
       - task: unit
       - task: integration
       - task: validate-cyclonedx-schema
-      - task: benchmark
       - task: test-utils
       - task: cli
+      - task: check-docker-cache
 
   ## Bootstrap tasks #################################
 
@@ -177,6 +192,14 @@ tasks:
 
 
   ## Testing tasks #################################
+  update-format-golden-files:
+    desc: "Update golden (i.e. snapshot) files used by unit tests"
+    cmds:
+      - go test ./syft/format/spdxjson -update-spdx-json
+      - go test ./syft/format/spdxtagvalue -update-spdx-tv
+      - go test ./syft/format/cyclonedxxml -update-cyclonedx-xml
+      - go test ./syft/format/cyclonedxjson -update-cyclonedx-json
+      - go test ./syft/format/syftjson -update-json
 
   unit:
     desc: Run unit tests
@@ -199,28 +222,21 @@ tasks:
     cmds:
       - "go test -v ./cmd/syft/internal/test/integration"
       # exercise most of the CLI with the data race detector
-      - "go run -race cmd/syft/main.go alpine:latest"
+      # we use a larger image to ensure we're using multiple catalogers at a time
+      - "go run -race cmd/syft/main.go anchore/test_images:grype-quality-dotnet-69f15d2"
 
   validate-cyclonedx-schema:
-    desc: Run integration tests
+    desc: Validate that Syft produces valid CycloneDX documents
     cmds:
       - "cd schema/cyclonedx && make"
 
   cli:
     desc: Run CLI tests
-    # note: we don't want to regenerate the snapshot unless we have to. In CI it's probable
-    # that the cache being restored with the correct binary will be rebuilt since the timestamps
-    # and local checksums will not line up.
-    deps: [tools, snapshot]
-    sources:
-      - "{{ .SNAPSHOT_BIN }}"
-      - ./test/cli/**
-      - ./**/*.go
+    deps: [tools]
     cmds:
       - cmd: "echo 'testing binary: {{ .SNAPSHOT_BIN }}'"
         silent: true
-
-      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found' && false)"
+      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found for {{ .SNAPSHOT_BIN }}' && false)"
         silent: true
 
       - "go test -count=1 -timeout=15m -v ./test/cli"
@@ -229,90 +245,195 @@ tasks:
 
   test-utils:
     desc: Run tests for pipeline utils
-    sources:
-      - .github/scripts/labeler*.py
     cmds:
-      - cmd: python .github/scripts/labeler_test.py
-
-
-  ## Benchmark test targets #################################
-
-  benchmark:
-    deps: [tmpdir]
-    sources:
-      - ./**/*.go
-    generates:
-      - "{{ .TMP_DIR }}/benchmark-main.txt"
-    cmds:
-      - "go test -p 1 -run=^Benchmark -bench=. -count=7 -benchmem ./... | tee {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt"
-      - |
-        bash -c "(test -s {{ .TMP_DIR }}/benchmark-main.txt && \
-        {{ .TOOL_DIR }}/benchstat {{ .TMP_DIR }}/benchmark-main.txt {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt || \
-        {{ .TOOL_DIR }}/benchstat {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt) \
-        | tee {{ .TMP_DIR }}/benchstat.txt"
-
-  show-benchstat:
-    deps: [benchmark, tmpdir]
-    sources:
-      - "{{ .TMP_DIR }}/benchstat.txt"
-    cmds:
-      - cmd: "cat {{ .TMP_DIR }}/benchstat.txt"
-        silent: true
+      - cmd: .github/scripts/labeler_test.py
 
 
   ## Test-fixture-related targets #################################
 
   fingerprints:
-    desc: Generate test fixture fingerprints
+    desc: Generate fingerprints for all non-docker test fixture
+    silent: true
+    # this will look for `test-fixtures/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
     generates:
-      - cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint
-      - syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint
-      - syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint
-      - syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint
-      - syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint
-      - syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint
-      - syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint
-      - syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint
+      - '**/test-fixtures/**/*.fingerprint'
       - test/install/cache.fingerprint
-      - test/cli/test-fixtures/cache.fingerprint
     cmds:
-      # for EXECUTABLE unit test fixtures
-      - "cd syft/file/cataloger/executable/test-fixtures/elf && make cache.fingerprint"
-      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make cache.fingerprint"
-      # for IMAGE integration test fixtures
-      - "cd cmd/syft/internal/test/integration/test-fixtures && make cache.fingerprint"
-      # for BINARY unit test fixtures
-      - "cd syft/pkg/cataloger/binary/test-fixtures && make cache.fingerprint"
-      # for JAVA BUILD unit test fixtures
-      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make cache.fingerprint"
-      # for GO BINARY unit test fixtures
-      - "cd syft/pkg/cataloger/golang/test-fixtures/archs && make binaries.fingerprint"
-      # for RPM unit test fixtures
-      - "cd syft/pkg/cataloger/redhat/test-fixtures && make rpms.fingerprint"
-      # for Kernel unit test fixtures
-      - "cd syft/pkg/cataloger/kernel/test-fixtures && make cache.fingerprint"
-      # for INSTALL test fixtures
-      - "cd test/install && make cache.fingerprint"
-      # for CLI test fixtures
-      - "cd test/cli/test-fixtures && make cache.fingerprint"
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
 
-  fixtures:
-    desc: Generate test fixtures
+        echo -e "${YELLOW}creating fingerprint files for non-docker fixtures...${RESET}"        
+        for dir in $(find . -type d -name 'test-fixtures'); do
+          if [ -f "$dir/Makefile" ]; then
+            # for debugging...
+            #echo -e "${YELLOW}• calculating fingerprints in $dir... ${RESET}"
+            
+            (make -C "$dir" fingerprint)
+          fi
+        done
+
+        # for debugging...
+        # echo -e "generated all fixture fingerprints"
+
+      - .github/scripts/fingerprint_docker_fixtures.py
+      - |
+        # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then we don't need to calculate the fingerprint for the cache
+        if [ "$DOWNLOAD_TEST_FIXTURE_CACHE" = "false" ]; then
+          exit 0
+        fi
+        .github/scripts/find_cache_paths.py {{ .CACHE_PATHS_FILE }} > /dev/null
+
+
+  refresh-fixtures:
+    desc: Clear and fetch all test fixture cache
+    aliases:
+      - fixtures
+    silent: true
+    deps:
+      - tools
     cmds:
-      - "cd syft/file/cataloger/executable/test-fixtures/elf && make"
-      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make"
-      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make"
-      - "cd syft/pkg/cataloger/redhat/test-fixtures && make"
-      - "cd syft/pkg/cataloger/binary/test-fixtures && make"
+      - |
+        BOLD='\033[1m'
+        PURPLE='\033[0;35m'
+        RESET='\033[0m'
+        
+        # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then skip the cache download and always build
+        if [ "$DOWNLOAD_TEST_FIXTURE_CACHE" = "false" ]; then
+            echo -e "${BOLD}${PURPLE}skipping cache download, rebuilding cache...${RESET}"
+            {{ .TASK }} build-fixtures
+            exit 0
+        fi
+        
+        LATEST_FINGERPRINT=$(docker manifest inspect {{ .CACHE_IMAGE }} | {{ .YQ }} -r '.annotations.fingerprint')
+
+        echo "latest cache:      $LATEST_FINGERPRINT"
+        
+        if [ -f {{ .LAST_CACHE_PULL_FILE }} ]; then
+          LAST_PULL_FINGERPRINT=$(cat {{ .LAST_CACHE_PULL_FILE }} | {{ .YQ }} -r '.digest')
+        else
+          echo -e "${BOLD}${PURPLE}empty cache, downloading cache...${RESET}"
+          {{ .TASK }} download-test-fixture-cache
+          exit 0
+        fi
+        
+        {{ .TASK }} fingerprints
+
+        WANT_FINGERPRINT=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.digest')        
+
+        echo "desired cache:     $WANT_FINGERPRINT"
+        echo "last pulled cache: $LAST_PULL_FINGERPRINT"
+  
+        # if we already have the latest cache, skip the refresh
+        if [ "$LAST_PULL_FINGERPRINT" = "$WANT_FINGERPRINT" ]; then
+            echo -e "${BOLD}${PURPLE}already have the latest cache (skipping cache download)${RESET}"
+            exit 0
+        fi
+  
+        # at this point we only refresh the cache if we want the same cache that is currently available.
+        # we don't by default refresh the cache if the cache if it is simply different from what we have,
+        # because we may be working on a code change that doesn't require a cache refresh (but could trigger one,
+        # which would be annoying to deal with in a development workflow).
+  
+        if [ "$LATEST_FINGERPRINT" = "$WANT_FINGERPRINT" ]; then
+          echo -e "${BOLD}${PURPLE}found newer cache! downloading cache...${RESET}"
+          {{ .TASK }} download-test-fixture-cache
+        else
+          echo -e "${BOLD}${PURPLE}found different cache, but isn't clear if it's newer (skipping cache download and manually building)${RESET}"
+        
+          {{ .YQ }} eval '.paths[] | "\(.digest) \(.path)"' {{ .LAST_CACHE_PULL_FILE }} > .tmp/last_cache_lines
+          {{ .YQ }} eval '.paths[] | "\(.digest) \(.path)"' {{ .CACHE_PATHS_FILE }} > .tmp/cache_lines
+          diff .tmp/last_cache_lines .tmp/cache_lines || true
+        
+          echo -e "${BOLD}${PURPLE}diff with more context...${RESET}"
+        
+          diff -U10000 {{ .LAST_CACHE_PULL_FILE }} {{ .CACHE_PATHS_FILE }} || true
+        
+          echo -e "${BOLD}${PURPLE}detected changes to input material, manually building fixtures...${RESET}"
+        
+          {{ .TASK }} build-fixtures
+        fi
+
+  build-fixtures:
+    desc: Generate all non-docker test fixtures
+    silent: true
+    # this will look for `test-fixtures/Makefile` and invoke the `fixtures` target to generate any and all test fixtures
+    cmds:
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
+        
+        # Use a for loop with command substitution to avoid subshell issues
+        for dir in $(find . -type d -name 'test-fixtures'); do
+          if [ -f "$dir/Makefile" ]; then
+            echo -e "${YELLOW}${BOLD}generating fixtures in $dir${RESET}"
+            (make -C "$dir" fixtures)
+          fi
+        done
+        echo -e "${BOLD}generated all fixtures${RESET}"
+
+  download-test-fixture-cache:
+    desc: Download test fixture cache from ghcr.io
+    deps: [tools, clean-cache]
+    vars:
+      CACHE_DIGEST:
+        sh: docker manifest inspect {{ .CACHE_IMAGE }} | {{ .YQ }} -r '.annotations.fingerprint'
+    cmds:
+      - silent: true
+        cmd: |
+          # if oras cache is > 4 GB, delete it
+          if [ -d {{ .ORAS_CACHE }} ]; then
+            total_size=$(du -c {{ .ORAS_CACHE }} | grep total | awk '{print $1}')
+            if [ "$total_size" -gt 4194304 ]; then
+              echo 'deleting oras cache'
+              rm -rf {{ .ORAS_CACHE }}
+            fi
+          fi
+      - "ORAS_CACHE={{ .ORAS_CACHE }} {{ .ORAS }} pull {{ .CACHE_IMAGE }}"
+      - "cp {{ .CACHE_PATHS_FILE }} {{ .LAST_CACHE_PULL_FILE }}"
+
+  upload-test-fixture-cache:
+    desc: Upload the test fixture cache to ghcr.io
+    deps: [tools, fingerprints]
+    silent: true
+    cmd: |
+      set -eu
+      oras_command="{{ .ORAS }} push {{ .CACHE_IMAGE }}"
+
+      paths=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.paths[].path')      
+      for path in $paths; do
+        oras_command+=" $path"
+      done
+      oras_command+=" {{ .CACHE_PATHS_FILE }}"
+      
+      oras_command+=" --annotation org.opencontainers.image.source=https://github.com/{{ .OWNER }}/{{ .PROJECT }}"
+      oras_command+=" --annotation fingerprint=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.digest')"
+    
+      echo "Executing: $oras_command"
+      eval $oras_command
 
   show-test-image-cache:
     silent: true
     cmds:
-      - "echo '\nDocker daemon cache:'"
+      - "echo 'Docker daemon cache:'"
       - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}:{{`{{.Tag}}`}}' | grep stereoscope-fixture- | sort"
       - "echo '\nTar cache:'"
-      - 'find . -type f -wholename "**/test-fixtures/snapshot/*" | sort'
+      - 'find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" | sort'
 
+  check-docker-cache:
+    desc: Ensure docker caches aren't using too much disk space
+    silent: true
+    cmd: |
+      total_size=$(find . | grep cache | grep tar | xargs du -c | grep total | awk '{print $1}')
+      find . | grep cache | grep tar | xargs du
+      echo "total $total_size KB"
+
+      if [ "$total_size" -gt 5242880  ]; then
+        echo 'docker cache is larger than 5GB'
+        exit 1
+      fi
 
   ## install.sh testing targets #################################
 
@@ -430,6 +551,18 @@ tasks:
 
       - "{{ .SNAPSHOT_CMD }}"
 
+  snapshot-smoke-test:
+    desc: Run a smoke test on the snapshot builds + docker images
+    cmds:
+      - cmd: "echo 'testing snapshot binary: {{ .SNAPSHOT_BIN }}'"
+        silent: true
+      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found for {{ .SNAPSHOT_BIN }}' && false)"
+        silent: true
+      - "{{ .SNAPSHOT_BIN }} version"
+      - "{{ .SNAPSHOT_BIN }} scan alpine:latest"
+      - docker run --rm anchore/syft:latest version
+      - docker run --rm anchore/syft:latest scan alpine:latest
+
   changelog:
     desc: Generate a changelog
     deps: [tools]
@@ -438,7 +571,7 @@ tasks:
       - "{{ .NEXT_VERSION }}"
     cmds:
       - "{{ .TOOL_DIR }}/chronicle -vv -n --version-file {{ .NEXT_VERSION }} > {{ .CHANGELOG }}"
-      - "{{ .TOOL_DIR }}/glow {{ .CHANGELOG }}"
+      - "{{ .TOOL_DIR }}/glow -w 0 {{ .CHANGELOG }}"
 
 
   ## Release targets #################################
@@ -489,8 +622,31 @@ tasks:
       - "rm -rf {{ .SNAPSHOT_DIR }}"
       - "rm -rf {{ .TMP_DIR }}/goreleaser.yaml"
 
-  clean-cache:
-    desc: Remove all docker cache and local image tar cache
+  clean-docker-cache:
+    desc: Remove all docker cache tars and images from the daemon
     cmds:
-      - 'find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" -delete'
-      - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}' | grep stereoscope-fixture- | awk '{print $$1}' | uniq | xargs -r docker rmi --force"
+      - find . -type d -wholename "**/test-fixtures/cache" | xargs rm -rf
+      - docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}' | grep stereoscope-fixture- | awk '{print $1}' | uniq | xargs -r docker rmi --force
+
+  clean-oras-cache:
+    desc: Remove all cache for oras commands
+    cmd: rm -rf {{ .ORAS_CACHE }}
+
+  clean-cache:
+    desc: Remove all image docker tar cache, images from the docker daemon, and ephemeral test fixtures
+    cmds:
+      - task: clean-docker-cache
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
+        
+        # Use a for loop with command substitution to avoid subshell issues
+        for dir in $(find . -type d -name 'test-fixtures'); do
+        if [ -f "$dir/Makefile" ]; then
+          echo -e "${YELLOW}${BOLD}deleting ephemeral test fixtures in $dir${RESET}"
+          (make -C "$dir" clean)
+        fi
+        done
+        echo -e "${BOLD}Deleted all ephemeral test fixtures${RESET}"
+      - rm -f {{ .LAST_CACHE_PULL_FILE }} {{ .CACHE_PATHS_FILE }}

cmd/syft/cli/cli.go

@@ -10,6 +10,7 @@ import (
 	"github.com/anchore/clio"
 	"github.com/anchore/syft/cmd/syft/internal"
 	"github.com/anchore/syft/cmd/syft/internal/commands"
+	constants "github.com/anchore/syft/internal"
 )
 
 // Application constructs the `syft packages` command and aliases the root command to `syft packages`.
@@ -47,7 +48,7 @@ func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Com
 		commands.Cataloger(app),
 		commands.Attest(app),
 		commands.Convert(app),
-		clio.VersionCommand(id),
+		clio.VersionCommand(id, schemaVersion),
 		clio.ConfigCommand(app, nil),
 		cranecmd.NewCmdAuthLogin(id.Name), // syft login uses the same command as crane
 	)
@@ -59,3 +60,7 @@ func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Com
 
 	return app, rootCmd
 }
+
+func schemaVersion() (string, any) {
+	return "SchemaVersion", constants.JSONSchemaVersion
+}

cmd/syft/cli/ui/__snapshots__/handle_attestation_test.snap

@@ -1,6 +1,6 @@
 
 [TestHandler_handleAttestationStarted/attesting_in_progress/task_line - 1]
- ⠋ Creating a thing                                                                running a thing
+ ⠋ Creating a thing                                                               running a thing 
 ---
 
 [TestHandler_handleAttestationStarted/attesting_in_progress/log - 1]
@@ -11,7 +11,7 @@
 ---
 
 [TestHandler_handleAttestationStarted/attesting_complete/task_line - 1]
- ✔ Created a thing                                                                 running a thing
+ ✔ Created a thing                                                                running a thing 
 ---
 
 [TestHandler_handleAttestationStarted/attesting_complete/log - 1]

cmd/syft/cli/ui/__snapshots__/handle_fetch_image_test.snap

@@ -1,8 +1,8 @@
 
 [TestHandler_handleFetchImage/fetch_image_in_progress - 1]
- ⠋ Loading image                   ━━━━━━━━━━━━━━━━━━━━  [current]                       the-image
+ ⠋ Loading image                   ━━━━━━━━━━━━━━━━━━━━  [current]                      the-image 
 ---
 
 [TestHandler_handleFetchImage/fetch_image_complete - 1]
- ✔ Loaded image                                                                          the-image
+ ✔ Loaded image                                                                         the-image 
 ---

cmd/syft/cli/ui/__snapshots__/handle_file_indexing_test.snap

@@ -1,8 +1,8 @@
 
 [TestHandler_handleFileIndexingStarted/cataloging_in_progress - 1]
- ⠋ Indexing file system            ━━━━━━━━━━━━━━━━━━━━  [current]                      /some/path
+ ⠋ Indexing file system            ━━━━━━━━━━━━━━━━━━━━  [current]                     /some/path 
 ---
 
 [TestHandler_handleFileIndexingStarted/cataloging_complete - 1]
- ✔ Indexed file system                                                                  /some/path
+ ✔ Indexed file system                                                                 /some/path 
 ---

cmd/syft/cli/ui/__snapshots__/handle_read_image_test.snap

@@ -1,8 +1,8 @@
 
 [TestHandler_handleReadImage/read_image_in_progress - 1]
- ⠋ Parsing image                   ━━━━━━━━━━━━━━━━━━━━                                         id
+ ⠋ Parsing image                   ━━━━━━━━━━━━━━━━━━━━                                        id 
 ---
 
 [TestHandler_handleReadImage/read_image_complete - 1]
- ✔ Parsed image                                                                                 id
+ ✔ Parsed image                                                                                id 
 ---

cmd/syft/cli/ui/handle_attestation.go

@@ -61,7 +61,7 @@ type backgroundLineReader struct {
 func (m *Handler) handleAttestationStarted(e partybus.Event) []tea.Model {
 	reader, prog, taskInfo, err := syftEventParsers.ParseAttestationStartedEvent(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/cli/ui/handle_cataloger_task.go

@@ -89,7 +89,7 @@ func (cts catalogerTaskModel) View() string {
 func (m *Handler) handleCatalogerTaskStarted(e partybus.Event) ([]tea.Model, tea.Cmd) {
 	mon, info, err := syftEventParsers.ParseCatalogerTaskStarted(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil, nil
 	}
 

cmd/syft/cli/ui/handle_fetch_image.go

@@ -12,7 +12,7 @@ import (
 func (m *Handler) handleFetchImage(e partybus.Event) []tea.Model {
 	imgName, prog, err := stereoEventParsers.ParseFetchImage(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/cli/ui/handle_file_indexing.go

@@ -12,7 +12,7 @@ import (
 func (m *Handler) handleFileIndexingStarted(e partybus.Event) []tea.Model {
 	path, prog, err := syftEventParsers.ParseFileIndexingStarted(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/cli/ui/handle_pull_containerd_image.go

@@ -43,7 +43,7 @@ type containerdPullStatusFormatter struct {
 func (m *Handler) handlePullContainerdImage(e partybus.Event) []tea.Model {
 	_, pullStatus, err := stereoscopeParsers.ParsePullContainerdImage(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/cli/ui/handle_pull_docker_image.go

@@ -44,7 +44,7 @@ type dockerPullStatusFormatter struct {
 func (m *Handler) handlePullDockerImage(e partybus.Event) []tea.Model {
 	_, pullStatus, err := stereoscopeParsers.ParsePullDockerImage(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/cli/ui/handle_read_image.go

@@ -12,7 +12,7 @@ import (
 func (m *Handler) handleReadImage(e partybus.Event) []tea.Model {
 	imgMetadata, prog, err := stereoEventParsers.ParseReadImage(e)
 	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
+		log.WithFields("error", err).Debug("unable to parse event")
 		return nil
 	}
 

cmd/syft/internal/clio_setup_config.go

@@ -6,7 +6,7 @@ import (
 
 	"github.com/anchore/clio"
 	"github.com/anchore/stereoscope"
-	ui2 "github.com/anchore/syft/cmd/syft/cli/ui"
+	handler "github.com/anchore/syft/cmd/syft/cli/ui"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
@@ -20,18 +20,18 @@ func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig
 		WithConfigInRootHelp().   // --help on the root command renders the full application config in the help text
 		WithUIConstructor(
 			// select a UI based on the logging configuration and state of stdin (if stdin is a tty)
-			func(cfg clio.Config) ([]clio.UI, error) {
+			func(cfg clio.Config) (*clio.UICollection, error) {
 				noUI := ui.None(out, cfg.Log.Quiet)
 				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
-					return []clio.UI{noUI}, nil
+					return clio.NewUICollection(noUI), nil
 				}
 
-				return []clio.UI{
+				return clio.NewUICollection(
 					ui.New(out, cfg.Log.Quiet,
-						ui2.New(ui2.DefaultHandlerConfig()),
+						handler.New(handler.DefaultHandlerConfig()),
 					),
 					noUI,
-				}, nil
+				), nil
 			},
 		).
 		WithInitializers(

cmd/syft/internal/commands/attest.go

@@ -52,7 +52,7 @@ func Attest(app clio.Application) *cobra.Command {
 	opts := defaultAttestOptions()
 
 	// template format explicitly not allowed
-	opts.Format.Template.Enabled = false
+	opts.Template.Enabled = false
 
 	return app.SetupCommand(&cobra.Command{
 		Use:   "attest --output [FORMAT] <IMAGE>",
@@ -93,14 +93,13 @@ func defaultAttestOutputOptions() options.Output {
 			string(spdxtagvalue.ID),
 		},
 		Outputs: []string{syftjson.ID.String()},
-		OutputFile: options.OutputFile{ // nolint:staticcheck
+		OutputFile: options.OutputFile{ //nolint:staticcheck
 			Enabled: false, // explicitly not allowed
 		},
 		Format: options.DefaultFormat(),
 	}
 }
 
-//nolint:funlen
 func runAttest(ctx context.Context, id clio.Identification, opts *attestOptions, userInput string) error {
 	// TODO: what other validation here besides binary name?
 	if !commandExists(cosignBinName) {
@@ -137,7 +136,7 @@ func writeSBOMToFormattedFile(s *sbom.SBOM, sbomFile io.Writer, opts *attestOpti
 		return fmt.Errorf("no output file provided")
 	}
 
-	encs, err := opts.Format.Encoders()
+	encs, err := opts.Encoders()
 	if err != nil {
 		return fmt.Errorf("unable to create encoders: %w", err)
 	}

cmd/syft/internal/commands/cataloger_list.go

@@ -3,6 +3,7 @@ package commands
 import (
 	"encoding/json"
 	"fmt"
+	"os"
 	"sort"
 	"strings"
 
@@ -12,9 +13,18 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/task"
-	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
+	"github.com/anchore/syft/syft/cataloging"
+)
+
+var (
+	activelyAddedStyle     = lipgloss.NewStyle().Foreground(lipgloss.Color("10")) // hi green
+	deselectedStyle        = lipgloss.NewStyle().Foreground(lipgloss.Color("8"))  // dark grey
+	activelyRemovedStyle   = lipgloss.NewStyle().Foreground(lipgloss.Color("9"))  // high red
+	defaultStyle           = lipgloss.NewStyle().Underline(true)
+	deselectedDefaultStyle = lipgloss.NewStyle().Inherit(deselectedStyle).Underline(true)
 )
 
 type catalogerListOptions struct {
@@ -44,8 +54,9 @@ func CatalogerList(app clio.Application) *cobra.Command {
 	opts := defaultCatalogerListOptions()
 
 	return app.SetupCommand(&cobra.Command{
-		Use:   "list [OPTIONS]",
-		Short: "List available catalogers",
+		Use:     "list [OPTIONS]",
+		Short:   "List available catalogers",
+		PreRunE: disableUI(app, os.Stdout),
 		RunE: func(_ *cobra.Command, _ []string) error {
 			return runCatalogerList(opts)
 		},
@@ -53,13 +64,19 @@ func CatalogerList(app clio.Application) *cobra.Command {
 }
 
 func runCatalogerList(opts *catalogerListOptions) error {
-	factories := task.DefaultPackageTaskFactories()
-	allTasks, err := factories.Tasks(task.DefaultCatalogingFactoryConfig())
+	pkgTaskFactories := task.DefaultPackageTaskFactories()
+	fileTaskFactories := task.DefaultFileTaskFactories()
+	allPkgTasks, err := pkgTaskFactories.Tasks(task.DefaultCatalogingFactoryConfig())
 	if err != nil {
-		return fmt.Errorf("unable to create cataloger tasks: %w", err)
+		return fmt.Errorf("unable to create pkg cataloger tasks: %w", err)
 	}
 
-	report, err := catalogerListReport(opts, allTasks)
+	allFileTasks, err := fileTaskFactories.Tasks(task.DefaultCatalogingFactoryConfig())
+	if err != nil {
+		return fmt.Errorf("unable to create file cataloger tasks: %w", err)
+	}
+
+	report, err := catalogerListReport(opts, [][]task.Task{allPkgTasks, allFileTasks})
 	if err != nil {
 		return fmt.Errorf("unable to generate cataloger list report: %w", err)
 	}
@@ -69,11 +86,14 @@ func runCatalogerList(opts *catalogerListOptions) error {
 	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...),
+func catalogerListReport(opts *catalogerListOptions, allTaskGroups [][]task.Task) (string, error) {
+	defaultCatalogers := options.Flatten(opts.DefaultCatalogers)
+	selectCatalogers := options.Flatten(opts.SelectCatalogers)
+	selectedTaskGroups, selectionEvidence, err := task.SelectInGroups(
+		allTaskGroups,
+		cataloging.NewSelectionRequest().
+			WithDefaults(defaultCatalogers...).
+			WithExpression(selectCatalogers...),
 	)
 	if err != nil {
 		return "", fmt.Errorf("unable to select catalogers: %w", err)
@@ -82,12 +102,12 @@ func catalogerListReport(opts *catalogerListOptions, allTasks []task.Task) (stri
 
 	switch opts.Output {
 	case "json":
-		report, err = renderCatalogerListJSON(selectedTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+		report, err = renderCatalogerListJSON(flattenTaskGroups(selectedTaskGroups), selectionEvidence, defaultCatalogers, selectCatalogers)
 	case "table", "":
 		if opts.ShowHidden {
-			report = renderCatalogerListTable(allTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+			report = renderCatalogerListTables(allTaskGroups, selectionEvidence)
 		} else {
-			report = renderCatalogerListTable(selectedTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+			report = renderCatalogerListTables(selectedTaskGroups, selectionEvidence)
 		}
 	}
 
@@ -98,6 +118,14 @@ func catalogerListReport(opts *catalogerListOptions, allTasks []task.Task) (stri
 	return report, nil
 }
 
+func flattenTaskGroups(taskGroups [][]task.Task) []task.Task {
+	var allTasks []task.Task
+	for _, tasks := range taskGroups {
+		allTasks = append(allTasks, tasks...)
+	}
+	return allTasks
+}
+
 func renderCatalogerListJSON(tasks []task.Task, selection task.Selection, defaultSelections, selections []string) (string, error) {
 	type node struct {
 		Name string   `json:"name"`
@@ -109,7 +137,12 @@ func renderCatalogerListJSON(tasks []task.Task, selection task.Selection, defaul
 	nodesByName := make(map[string]node)
 
 	for name := range tagsByName {
-		tagsSelected := selection.TokensByTask[name].SelectedOn.List()
+		tokensByTask, ok := selection.TokensByTask[name]
+
+		var tagsSelected []string
+		if ok {
+			tagsSelected = tokensByTask.SelectedOn.List()
+		}
 
 		if len(tagsSelected) == 1 && tagsSelected[0] == "all" {
 			tagsSelected = tagsByName[name]
@@ -153,10 +186,56 @@ func renderCatalogerListJSON(tasks []task.Task, selection task.Selection, defaul
 	return string(by), err
 }
 
-func renderCatalogerListTable(tasks []task.Task, selection task.Selection, defaultSelections, selections []string) string {
+func renderCatalogerListTables(taskGroups [][]task.Task, selection task.Selection) string {
+	pkgCatalogerTable := renderCatalogerListTable(taskGroups[0], selection, "Package Cataloger")
+	fileCatalogerTable := renderCatalogerListTable(taskGroups[1], selection, "File Cataloger")
+
+	report := fileCatalogerTable + "\n" + pkgCatalogerTable + "\n"
+
+	hasAdditions := len(selection.Request.AddNames) > 0
+	hasDefaults := len(selection.Request.DefaultNamesOrTags) > 0
+	hasRemovals := len(selection.Request.RemoveNamesOrTags) > 0
+	hasSubSelections := len(selection.Request.SubSelectTags) > 0
+	expressions := len(selection.Request.SubSelectTags) + len(selection.Request.AddNames) + len(selection.Request.RemoveNamesOrTags)
+
+	var header string
+
+	header += fmt.Sprintf("Default selections: %d\n", len(selection.Request.DefaultNamesOrTags))
+	if hasDefaults {
+		for _, expr := range selection.Request.DefaultNamesOrTags {
+			header += fmt.Sprintf("  • '%s'\n", expr)
+		}
+	}
+
+	header += fmt.Sprintf("Selection expressions: %d\n", expressions)
+
+	if hasSubSelections {
+		for _, n := range selection.Request.SubSelectTags {
+			header += fmt.Sprintf("  • '%s' (intersect)\n", n)
+		}
+	}
+	if hasRemovals {
+		for _, n := range selection.Request.RemoveNamesOrTags {
+			header += fmt.Sprintf("  • '-%s' (remove)\n", n)
+		}
+	}
+	if hasAdditions {
+		for _, n := range selection.Request.AddNames {
+			header += fmt.Sprintf("  • '+%s' (add)\n", n)
+		}
+	}
+
+	return header + report
+}
+
+func renderCatalogerListTable(tasks []task.Task, selection task.Selection, kindTitle string) string {
+	if len(tasks) == 0 {
+		return activelyRemovedStyle.Render(fmt.Sprintf("No %ss selected", strings.ToLower(kindTitle)))
+	}
+
 	t := table.NewWriter()
 	t.SetStyle(table.StyleLight)
-	t.AppendHeader(table.Row{"Cataloger", "Tags"})
+	t.AppendHeader(table.Row{kindTitle, "Tags"})
 
 	names, tagsByName := extractTaskInfo(tasks)
 
@@ -172,27 +251,12 @@ func renderCatalogerListTable(tasks []task.Task, selection task.Selection, defau
 
 	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)
+	defaults := strset.New(selection.Request.DefaultNamesOrTags...)
 	var selections *task.TokenSelection
 	if s, exists := selection.TokensByTask[name]; exists {
 		selections = &s
@@ -200,35 +264,32 @@ func formatRow(name string, tags []string, selection task.Selection) table.Row {
 
 	var formattedTags []string
 	for _, tag := range tags {
-		formattedTags = append(formattedTags, formatToken(tag, selections, isIncluded))
+		formattedTags = append(formattedTags, formatToken(tag, selections, isIncluded, defaults))
 	}
 
 	var tagStr string
 	if isIncluded {
 		tagStr = strings.Join(formattedTags, ", ")
 	} else {
-		tagStr = strings.Join(formattedTags, grey.Render(", "))
+		tagStr = strings.Join(formattedTags, deselectedStyle.Render(", "))
 	}
 
 	// TODO: selection should keep warnings (non-selections) in struct
 
 	return table.Row{
-		formatToken(name, selections, isIncluded),
+		formatToken(name, selections, isIncluded, defaults),
 		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 {
+func formatToken(token string, selection *task.TokenSelection, included bool, defaults *strset.Set) string {
 	if included && selection != nil {
 		// format all tokens in selection in green
 		if selection.SelectedOn.Has(token) {
-			return green.Render(token)
+			if defaults.Has(token) {
+				return defaultStyle.Render(token)
+			}
+			return activelyAddedStyle.Render(token)
 		}
 
 		return token
@@ -236,10 +297,12 @@ func formatToken(token string, selection *task.TokenSelection, included bool) st
 
 	// format all tokens in selection in red, all others in grey
 	if selection != nil && selection.DeselectedOn.Has(token) {
-		return red.Render(token)
+		return activelyRemovedStyle.Render(token)
 	}
-
-	return grey.Render(token)
+	if defaults.Has(token) {
+		return deselectedDefaultStyle.Render(token)
+	}
+	return deselectedStyle.Render(token)
 }
 
 func extractTaskInfo(tasks []task.Task) ([]string, map[string][]string) {

cmd/syft/internal/commands/cataloger_list_test.go

@@ -40,23 +40,35 @@ func (d dummyTask) Execute(_ context.Context, _ file.Resolver, _ sbomsync.Builde
 	panic("implement me")
 }
 
-func testTasks() []task.Task {
-	return []task.Task{
-		dummyTask{
-			name:      "task1",
-			selectors: []string{"image", "a", "b", "1"},
+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"},
+			},
 		},
-		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"},
+		{
+			dummyTask{
+				name:      "file-task1",
+				selectors: []string{"file", "ft", "ft-1-b"},
+			},
+			dummyTask{
+				name:      "file-task2",
+				selectors: []string{"file", "ft", "ft-2-b"},
+			},
 		},
 	}
 }
@@ -76,16 +88,23 @@ func Test_catalogerListReport(t *testing.T) {
 				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 │
-└───────────┴────────────────────┘
+Default selections: 1
+  • 'all'
+Selection expressions: 0
+┌────────────────┬──────────────────┐
+│ FILE CATALOGER │ TAGS             │
+├────────────────┼──────────────────┤
+│ file-task1     │ file, ft, ft-1-b │
+│ file-task2     │ file, ft, ft-2-b │
+└────────────────┴──────────────────┘
+┌───────────────────┬────────────────────┐
+│ PACKAGE CATALOGER │ TAGS               │
+├───────────────────┼────────────────────┤
+│ task1             │ 1, a, b, image     │
+│ task2             │ 2, b, c, image     │
+│ task3             │ 3, c, d, directory │
+│ task4             │ 4, d, directory, e │
+└───────────────────┴────────────────────┘
 `,
 		},
 		{
@@ -96,7 +115,7 @@ Default selections:
 				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"]}]}
+{"default":["all"],"selection":[],"catalogers":[{"name":"file-task1","tags":["file","ft","ft-1-b"]},{"name":"file-task2","tags":["file","ft","ft-2-b"]},{"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"]}]}
 `,
 		},
 		{
@@ -105,19 +124,27 @@ Default selections:
 				c := defaultCatalogerListOptions()
 				c.Output = "table"
 				c.DefaultCatalogers = []string{
-					"image",
+					"image", // note: for backwards compatibility file will automatically be added
 				}
 				return c
 			}(),
 			want: `
-Default selections:
-  - "image"
-┌───────────┬────────────────┐
-│ CATALOGER │ TAGS           │
-├───────────┼────────────────┤
-│ task1     │ 1, a, b, image │
-│ task2     │ 2, b, c, image │
-└───────────┴────────────────┘
+Default selections: 2
+  • 'image'
+  • 'file'
+Selection expressions: 0
+┌────────────────┬──────────────────┐
+│ FILE CATALOGER │ TAGS             │
+├────────────────┼──────────────────┤
+│ file-task1     │ file, ft, ft-1-b │
+│ file-task2     │ file, ft, ft-2-b │
+└────────────────┴──────────────────┘
+┌───────────────────┬────────────────┐
+│ PACKAGE CATALOGER │ TAGS           │
+├───────────────────┼────────────────┤
+│ task1             │ 1, a, b, image │
+│ task2             │ 2, b, c, image │
+└───────────────────┴────────────────┘
 `,
 		},
 		{
@@ -131,7 +158,7 @@ Default selections:
 				return c
 			}(),
 			want: `
-{"default":["image"],"selection":[],"catalogers":[{"name":"task1","tags":["image"]},{"name":"task2","tags":["image"]}]}
+{"default":["image"],"selection":[],"catalogers":[{"name":"file-task1","tags":["file"]},{"name":"file-task2","tags":["file"]},{"name":"task1","tags":["image"]},{"name":"task2","tags":["image"]}]}
 `,
 		},
 		{
@@ -147,23 +174,69 @@ Default selections:
 					"+task3",
 					"-c",
 					"b",
+					"-file",
+					"+file-task1",
 				}
 				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 │
-└───────────┴────────────────────┘
+Default selections: 1
+  • 'image'
+Selection expressions: 6
+  • 'b' (intersect)
+  • '-c' (remove)
+  • '-directory' (remove)
+  • '-file' (remove)
+  • '+file-task1' (add)
+  • '+task3' (add)
+┌────────────────┬──────────────────┐
+│ FILE CATALOGER │ TAGS             │
+├────────────────┼──────────────────┤
+│ file-task1     │ file, ft, ft-1-b │
+└────────────────┴──────────────────┘
+┌───────────────────┬────────────────────┐
+│ PACKAGE CATALOGER │ TAGS               │
+├───────────────────┼────────────────────┤
+│ task1             │ 1, a, b, image     │
+│ task3             │ 3, c, d, directory │
+└───────────────────┴────────────────────┘
+`,
+		},
+		{
+			name: "with comma separated expressions, table",
+			options: func() *catalogerListOptions {
+				c := defaultCatalogerListOptions()
+				c.Output = "table"
+				c.DefaultCatalogers = []string{
+					"image,task3,file-task1",
+				}
+				c.SelectCatalogers = []string{
+					"-task2,c,b",
+				}
+				return c
+			}(),
+			want: `
+Default selections: 4
+  • 'file-task1'
+  • 'image'
+  • 'task3'
+  • 'file'
+Selection expressions: 3
+  • 'b' (intersect)
+  • 'c' (intersect)
+  • '-task2' (remove)
+┌────────────────┬──────────────────┐
+│ FILE CATALOGER │ TAGS             │
+├────────────────┼──────────────────┤
+│ file-task1     │ file, ft, ft-1-b │
+│ file-task2     │ file, ft, ft-2-b │
+└────────────────┴──────────────────┘
+┌───────────────────┬────────────────────┐
+│ PACKAGE CATALOGER │ TAGS               │
+├───────────────────┼────────────────────┤
+│ task1             │ 1, a, b, image     │
+│ task3             │ 3, c, d, directory │
+└───────────────────┴────────────────────┘
 `,
 		},
 		{
@@ -183,7 +256,7 @@ Selected by expressions:
 				return c
 			}(),
 			want: `
-{"default":["image"],"selection":["-directory","+task3","-c","b"],"catalogers":[{"name":"task1","tags":["b","image"]},{"name":"task3","tags":["task3"]}]}
+{"default":["image"],"selection":["+task3","-c","-directory","b"],"catalogers":[{"name":"file-task1","tags":["file"]},{"name":"file-task2","tags":["file"]},{"name":"task1","tags":["b","image"]},{"name":"task3","tags":["task3"]}]}
 `,
 		},
 	}

cmd/syft/internal/commands/convert.go

@@ -17,7 +17,7 @@ import (
 
 const (
 	convertExample = `  {{.appName}} {{.command}} img.syft.json -o spdx-json                      convert a syft SBOM to spdx-json, output goes to stdout
-  {{.appName}} {{.command}} img.syft.json -o cyclonedx-json=img.cdx.json    convert a syft SBOM to CycloneDX, output is written to the file "img.cdx.json""
+  {{.appName}} {{.command}} img.syft.json -o cyclonedx-json=img.cdx.json    convert a syft SBOM to CycloneDX, output is written to the file "img.cdx.json"
   {{.appName}} {{.command}} - -o spdx-json                                  convert an SBOM from STDIN to spdx-json
 `
 )
@@ -28,7 +28,6 @@ type ConvertOptions struct {
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 }
 
-//nolint:dupl
 func Convert(app clio.Application) *cobra.Command {
 	id := app.ID()
 
@@ -40,7 +39,7 @@ func Convert(app clio.Application) *cobra.Command {
 	return app.SetupCommand(&cobra.Command{
 		Use:   "convert [SOURCE-SBOM] -o [FORMAT]",
 		Short: "Convert between SBOM formats",
-		Long:  "[Experimental] Convert SBOM files to, and from, SPDX, CycloneDX and Syft's format. For more info about data loss between formats see https://github.com/anchore/syft#format-conversion-experimental",
+		Long:  "[Experimental] Convert SBOM files to, and from, SPDX, CycloneDX and Syft's format. For more info about data loss between formats see https://github.com/anchore/syft/wiki/format-conversion",
 		Example: internal.Tprintf(convertExample, map[string]interface{}{
 			"appName": id.Name,
 			"command": "convert",

cmd/syft/internal/commands/scan.go

@@ -13,6 +13,7 @@ import (
 	"gopkg.in/yaml.v3"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/fangs"
 	"github.com/anchore/go-collections"
 	"github.com/anchore/stereoscope"
 	"github.com/anchore/stereoscope/pkg/image"
@@ -80,7 +81,6 @@ func defaultScanOptions() *scanOptions {
 	}
 }
 
-//nolint:dupl
 func Scan(app clio.Application) *cobra.Command {
 	id := app.ID()
 
@@ -110,7 +110,7 @@ func (o *scanOptions) PostLoad() error {
 }
 
 func (o *scanOptions) validateLegacyOptionsNotUsed() error {
-	if o.Config.ConfigFile == "" {
+	if len(fangs.Flatten(o.ConfigFile)) == 0 {
 		return nil
 	}
 
@@ -122,32 +122,33 @@ func (o *scanOptions) validateLegacyOptionsNotUsed() error {
 		File                            any     `yaml:"file" json:"file" mapstructure:"file"`
 	}
 
-	by, err := os.ReadFile(o.Config.ConfigFile)
-	if err != nil {
-		return fmt.Errorf("unable to read config file during validations %q: %w", o.Config.ConfigFile, err)
-	}
+	for _, f := range fangs.Flatten(o.ConfigFile) {
+		by, err := os.ReadFile(f)
+		if err != nil {
+			return fmt.Errorf("unable to read config file during validations %q: %w", f, err)
+		}
 
-	var legacy legacyConfig
-	if err := yaml.Unmarshal(by, &legacy); err != nil {
-		return fmt.Errorf("unable to parse config file during validations %q: %w", o.Config.ConfigFile, err)
-	}
+		var legacy legacyConfig
+		if err := yaml.Unmarshal(by, &legacy); err != nil {
+			return fmt.Errorf("unable to parse config file during validations %q: %w", f, err)
+		}
 
-	if legacy.DefaultImagePullSource != nil {
-		return fmt.Errorf("the config file option 'default-image-pull-source' has been removed, please use 'source.image.default-pull-source' instead")
-	}
+		if legacy.DefaultImagePullSource != nil {
+			return fmt.Errorf("the config file option 'default-image-pull-source' has been removed, please use 'source.image.default-pull-source' instead")
+		}
 
-	if legacy.ExcludeBinaryOverlapByOwnership != nil {
-		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.ExcludeBinaryOverlapByOwnership != nil {
+			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 {
-		return fmt.Errorf("the config file option 'base-path' has been removed, please use 'source.base-path' instead")
-	}
+		if legacy.BasePath != nil {
+			return fmt.Errorf("the config file option 'base-path' has been removed, please use 'source.base-path' instead")
+		}
 
-	if legacy.File != nil && reflect.TypeOf(legacy.File).Kind() == reflect.String {
-		return fmt.Errorf("the config file option 'file' has been removed, please use 'outputs' instead")
+		if legacy.File != nil && reflect.TypeOf(legacy.File).Kind() == reflect.String {
+			return fmt.Errorf("the config file option 'file' has been removed, please use 'outputs' instead")
+		}
 	}
-
 	return nil
 }
 
@@ -155,13 +156,13 @@ func validateScanArgs(cmd *cobra.Command, args []string) error {
 	return validateArgs(cmd, args, "an image/directory argument is required")
 }
 
-func validateArgs(cmd *cobra.Command, args []string, error string) error {
+func validateArgs(cmd *cobra.Command, args []string, err string) error {
 	if len(args) == 0 {
 		// in the case that no arguments are given we want to show the help text and return with a non-0 return code.
 		if err := cmd.Help(); err != nil {
 			return fmt.Errorf("unable to display help: %w", err)
 		}
-		return fmt.Errorf(error)
+		return fmt.Errorf("%v", err)
 	}
 
 	return cobra.MaximumNArgs(1)(cmd, args)
@@ -396,13 +397,13 @@ func getExplanation(expErr task.ErrInvalidExpression) string {
 
 	if errors.Is(err, task.ErrNamesNotAllowed) {
 		if expErr.Operation == task.SubSelectOperation {
-			return "However, " + err.Error() + ".\nIt seems like you are intending to add a cataloger in addition to the default set." // nolint:goconst
+			return "However, " + err.Error() + ".\nIt seems like you are intending to add a cataloger in addition to the default set."
 		}
-		return "However, " + err.Error() + "." // nolint:goconst
+		return "However, " + err.Error() + "."
 	}
 
 	if errors.Is(err, task.ErrTagsNotAllowed) {
-		return "However, " + err.Error() + ".\nAdding groups of catalogers may result in surprising behavior (create inaccurate SBOMs)." // nolint:goconst
+		return "However, " + err.Error() + ".\nAdding groups of catalogers may result in surprising behavior (create inaccurate SBOMs)."
 	}
 
 	if errors.Is(err, task.ErrAllNotAllowed) {

cmd/syft/internal/commands/utils.go

@@ -0,0 +1,23 @@
+package commands
+
+import (
+	"io"
+
+	"github.com/spf13/cobra"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/cmd/syft/internal/ui"
+)
+
+func disableUI(app clio.Application, out io.Writer) func(*cobra.Command, []string) error {
+	return func(_ *cobra.Command, _ []string) error {
+		type Stater interface {
+			State() *clio.State
+		}
+
+		state := app.(Stater).State()
+		state.UI = clio.NewUICollection(ui.None(out, state.Config.Log.Quiet))
+
+		return nil
+	}
+}

cmd/syft/internal/options/cache.go

@@ -10,9 +10,9 @@ import (
 	"time"
 
 	"github.com/adrg/xdg"
-	"github.com/mitchellh/go-homedir"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/internal/cache"
 	"github.com/anchore/syft/internal/log"
 )

cmd/syft/internal/options/cache_test.go

@@ -9,9 +9,9 @@ import (
 	"time"
 
 	"github.com/adrg/xdg"
-	"github.com/mitchellh/go-homedir"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/cache"
 )
@@ -57,35 +57,13 @@ func Test_defaultDir(t *testing.T) {
 		env[k] = os.Getenv(k)
 	}
 
-	unsetEnv := func(t *testing.T) {
-		for k := range env {
-			t.Setenv(k, "")
-		}
-	}
-
-	resetEnv := func() {
-		for k, v := range env {
-			if v == "" {
-				_ = os.Unsetenv(k)
-			} else {
-				_ = os.Setenv(k, v)
-			}
-		}
-		homedir.Reset()
-		xdg.Reload()
-	}
-
-	t.Cleanup(resetEnv)
-
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
-			defer resetEnv()
+			restoreCache(t)
 
-			unsetEnv(t)
 			for k, v := range test.env {
-				t.Setenv(k, v)
+				patchEnv(t, k, v)
 			}
-			homedir.Reset()
 			xdg.Reload()
 
 			got := defaultDir()
@@ -311,3 +289,35 @@ func Test_durationToString(t *testing.T) {
 		})
 	}
 }
+
+// restoreCache ensures cache settings are restored after test
+func restoreCache(t testing.TB) {
+	t.Helper()
+	origEnabled := homedir.CacheEnabled()
+
+	t.Cleanup(func() {
+		homedir.SetCacheEnable(origEnabled)
+		homedir.Reset()
+	})
+}
+
+// patchEnv modifies an environment variable for the duration of the test
+func patchEnv(t testing.TB, key, value string) {
+	t.Helper()
+	original := os.Getenv(key)
+
+	if value != "" {
+		os.Setenv(key, value)
+	} else {
+		os.Unsetenv(key)
+	}
+
+	t.Cleanup(func() {
+		if original != "" {
+			os.Setenv(key, original)
+		} else {
+			os.Unsetenv(key)
+		}
+		xdg.Reload()
+	})
+}

cmd/syft/internal/options/catalog.go

@@ -11,6 +11,7 @@ import (
 	"github.com/anchore/fangs"
 	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/task"
 	"github.com/anchore/syft/syft"
 	"github.com/anchore/syft/syft/cataloging"
 	"github.com/anchore/syft/syft/cataloging/filecataloging"
@@ -18,10 +19,12 @@ import (
 	"github.com/anchore/syft/syft/file/cataloger/executable"
 	"github.com/anchore/syft/syft/file/cataloger/filecontent"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
+	"github.com/anchore/syft/syft/pkg/cataloger/dotnet"
 	"github.com/anchore/syft/syft/pkg/cataloger/golang"
 	"github.com/anchore/syft/syft/pkg/cataloger/java"
 	"github.com/anchore/syft/syft/pkg/cataloger/javascript"
 	"github.com/anchore/syft/syft/pkg/cataloger/kernel"
+	"github.com/anchore/syft/syft/pkg/cataloger/nix"
 	"github.com/anchore/syft/syft/pkg/cataloger/python"
 	"github.com/anchore/syft/syft/source"
 )
@@ -32,16 +35,21 @@ type Catalog struct {
 	DefaultCatalogers []string            `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
 	SelectCatalogers  []string            `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
 	Package           packageConfig       `yaml:"package" json:"package" mapstructure:"package"`
+	License           licenseConfig       `yaml:"license" json:"license" mapstructure:"license"`
 	File              fileConfig          `yaml:"file" json:"file" mapstructure:"file"`
 	Scope             string              `yaml:"scope" json:"scope" mapstructure:"scope"`
 	Parallelism       int                 `yaml:"parallelism" json:"parallelism" mapstructure:"parallelism"` // the number of catalog workers to run in parallel
 	Relationships     relationshipsConfig `yaml:"relationships" json:"relationships" mapstructure:"relationships"`
+	Compliance        complianceConfig    `yaml:"compliance" json:"compliance" mapstructure:"compliance"`
+	Enrich            []string            `yaml:"enrich" json:"enrich" mapstructure:"enrich"`
 
 	// ecosystem-specific cataloger configuration
+	Dotnet      dotnetConfig      `yaml:"dotnet" json:"dotnet" mapstructure:"dotnet"`
 	Golang      golangConfig      `yaml:"golang" json:"golang" mapstructure:"golang"`
 	Java        javaConfig        `yaml:"java" json:"java" mapstructure:"java"`
 	JavaScript  javaScriptConfig  `yaml:"javascript" json:"javascript" mapstructure:"javascript"`
 	LinuxKernel linuxKernelConfig `yaml:"linux-kernel" json:"linux-kernel" mapstructure:"linux-kernel"`
+	Nix         nixConfig         `yaml:"nix" json:"nix" mapstructure:"nix"`
 	Python      pythonConfig      `yaml:"python" json:"python" mapstructure:"python"`
 
 	// configuration for the source (the subject being analyzed)
@@ -50,25 +58,34 @@ type Catalog struct {
 	Platform   string         `yaml:"platform" json:"platform" mapstructure:"platform"`
 	Source     sourceConfig   `yaml:"source" json:"source" mapstructure:"source"`
 	Exclusions []string       `yaml:"exclude" json:"exclude" mapstructure:"exclude"`
+
+	// configuration for inclusion of unknown information within elements
+	Unknowns unknownsConfig `yaml:"unknowns" mapstructure:"unknowns"`
 }
 
 var _ interface {
 	clio.FlagAdder
 	clio.PostLoader
-	fangs.FieldDescriber
+	clio.FieldDescriber
 } = (*Catalog)(nil)
 
 func DefaultCatalog() Catalog {
+	cfg := syft.DefaultCreateSBOMConfig()
 	return Catalog{
+		Compliance:    defaultComplianceConfig(),
 		Scope:         source.SquashedScope.String(),
 		Package:       defaultPackageConfig(),
+		License:       defaultLicenseConfig(),
 		LinuxKernel:   defaultLinuxKernelConfig(),
+		Nix:           defaultNixConfig(),
+		Dotnet:        defaultDotnetConfig(),
 		Golang:        defaultGolangConfig(),
 		Java:          defaultJavaConfig(),
 		File:          defaultFileConfig(),
 		Relationships: defaultRelationshipsConfig(),
+		Unknowns:      defaultUnknowns(),
 		Source:        defaultSourceConfig(),
-		Parallelism:   1,
+		Parallelism:   cfg.Parallelism,
 	}
 }
 
@@ -77,11 +94,14 @@ func (cfg Catalog) ToSBOMConfig(id clio.Identification) *syft.CreateSBOMConfig {
 		WithTool(id.Name, id.Version).
 		WithParallelism(cfg.Parallelism).
 		WithRelationshipsConfig(cfg.ToRelationshipsConfig()).
+		WithComplianceConfig(cfg.ToComplianceConfig()).
+		WithUnknownsConfig(cfg.ToUnknownsConfig()).
 		WithSearchConfig(cfg.ToSearchConfig()).
 		WithPackagesConfig(cfg.ToPackagesConfig()).
+		WithLicenseConfig(cfg.ToLicenseConfig()).
 		WithFilesConfig(cfg.ToFilesConfig()).
 		WithCatalogerSelection(
-			pkgcataloging.NewSelectionRequest().
+			cataloging.NewSelectionRequest().
 				WithDefaults(cfg.DefaultCatalogers...).
 				WithExpression(cfg.SelectCatalogers...),
 		)
@@ -102,6 +122,20 @@ func (cfg Catalog) ToRelationshipsConfig() cataloging.RelationshipsConfig {
 	}
 }
 
+func (cfg Catalog) ToComplianceConfig() cataloging.ComplianceConfig {
+	return cataloging.ComplianceConfig{
+		MissingName:    cfg.Compliance.MissingName,
+		MissingVersion: cfg.Compliance.MissingVersion,
+	}
+}
+
+func (cfg Catalog) ToUnknownsConfig() cataloging.UnknownsConfig {
+	return cataloging.UnknownsConfig{
+		IncludeExecutablesWithoutPackages: cfg.Unknowns.ExecutablesWithoutPackages,
+		IncludeUnexpandedArchives:         cfg.Unknowns.UnexpandedArchives,
+	}
+}
+
 func (cfg Catalog) ToFilesConfig() filecataloging.Config {
 	hashers, err := intFile.Hashers(cfg.File.Metadata.Digests...)
 	if err != nil {
@@ -122,6 +156,13 @@ func (cfg Catalog) ToFilesConfig() filecataloging.Config {
 	}
 }
 
+func (cfg Catalog) ToLicenseConfig() cataloging.LicenseConfig {
+	return cataloging.LicenseConfig{
+		IncludeContent: cfg.License.Content,
+		Coverage:       cfg.License.Coverage,
+	}
+}
+
 func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 	archiveSearch := cataloging.ArchiveSearchConfig{
 		IncludeIndexedArchives:   cfg.Package.SearchIndexedArchives,
@@ -129,10 +170,17 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 	}
 	return pkgcataloging.Config{
 		Binary: binary.DefaultClassifierCatalogerConfig(),
+		Dotnet: dotnet.DefaultCatalogerConfig().
+			WithDepPackagesMustHaveDLL(cfg.Dotnet.DepPackagesMustHaveDLL).
+			WithDepPackagesMustClaimDLL(cfg.Dotnet.DepPackagesMustClaimDLL).
+			WithPropagateDLLClaimsToParents(cfg.Dotnet.PropagateDLLClaimsToParents).
+			WithRelaxDLLClaimsWhenBundlingDetected(cfg.Dotnet.RelaxDLLClaimsWhenBundlingDetected),
 		Golang: golang.DefaultCatalogerConfig().
-			WithSearchLocalModCacheLicenses(cfg.Golang.SearchLocalModCacheLicenses).
+			WithSearchLocalModCacheLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchLocalModCacheLicenses)).
 			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
-			WithSearchRemoteLicenses(cfg.Golang.SearchRemoteLicenses).
+			WithSearchLocalVendorLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchLocalVendorLicenses)).
+			WithLocalVendorDir(cfg.Golang.LocalVendorDir).
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchRemoteLicenses)).
 			WithProxy(cfg.Golang.Proxy).
 			WithNoProxy(cfg.Golang.NoProxy).
 			WithMainModuleVersion(
@@ -142,20 +190,24 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
 			),
 		JavaScript: javascript.DefaultCatalogerConfig().
-			WithSearchRemoteLicenses(cfg.JavaScript.SearchRemoteLicenses).
+			WithIncludeDevDependencies(*multiLevelOption(false, cfg.JavaScript.IncludeDevDependencies)).
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.JavaScript, task.Node, task.NPM), cfg.JavaScript.SearchRemoteLicenses)).
 			WithNpmBaseURL(cfg.JavaScript.NpmBaseURL),
 		LinuxKernel: kernel.LinuxKernelCatalogerConfig{
 			CatalogModules: cfg.LinuxKernel.CatalogModules,
 		},
+		Nix: nix.DefaultConfig().
+			WithCaptureOwnedFiles(cfg.Nix.CaptureOwnedFiles),
 		Python: python.CatalogerConfig{
 			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
 		},
 		JavaArchive: java.DefaultArchiveCatalogerConfig().
-			WithUseMavenLocalRepository(cfg.Java.UseMavenLocalRepository).
+			WithUseMavenLocalRepository(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseMavenLocalRepository)).
 			WithMavenLocalRepositoryDir(cfg.Java.MavenLocalRepositoryDir).
-			WithUseNetwork(cfg.Java.UseNetwork).
+			WithUseNetwork(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseNetwork)).
 			WithMavenBaseURL(cfg.Java.MavenURL).
-			WithArchiveTraversal(archiveSearch, cfg.Java.MaxParentRecursiveDepth),
+			WithArchiveTraversal(archiveSearch, cfg.Java.MaxParentRecursiveDepth).
+			WithResolveTransitiveDependencies(cfg.Java.ResolveTransitiveDependencies),
 	}
 }
 
@@ -179,6 +231,9 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringArrayVarP(&cfg.Catalogers, "catalogers", "",
 		"enable one or more package catalogers")
 
+	flags.IntVarP(&cfg.Parallelism, "parallelism", "",
+		"number of cataloger workers to run in parallel")
+
 	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
 		if err := pfp.PFlagSet().MarkDeprecated("catalogers", "use: override-default-catalogers and select-catalogers"); err != nil {
 			panic(err)
@@ -193,6 +248,9 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringArrayVarP(&cfg.SelectCatalogers, "select-catalogers", "",
 		"add, remove, and filter the catalogers to be used")
 
+	flags.StringArrayVarP(&cfg.Enrich, "enrich", "",
+		fmt.Sprintf("enable package data enrichment from local and online sources (options: %s)", strings.Join(publicisedEnrichmentOptions, ", ")))
+
 	flags.StringVarP(&cfg.Source.Name, "source-name", "",
 		"set the name of the target being analyzed")
 
@@ -204,7 +262,12 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 }
 
 func (cfg *Catalog) DescribeFields(descriptions fangs.FieldDescriptionSet) {
-	descriptions.Add(&cfg.Parallelism, "number of cataloger workers to run in parallel")
+	descriptions.Add(&cfg.Parallelism, `number of cataloger workers to run in parallel
+by default, when set to 0: this will be based on runtime.NumCPU * 4, if set to less than 0 it will be unbounded`)
+
+	descriptions.Add(&cfg.Enrich, fmt.Sprintf(`Enable data enrichment operations, which can utilize services such as Maven Central and NPM.
+By default all enrichment is disabled, use: all to enable everything.
+Available options are: %s`, strings.Join(publicisedEnrichmentOptions, ", ")))
 }
 
 func (cfg *Catalog) PostLoad() error {
@@ -215,23 +278,12 @@ func (cfg *Catalog) PostLoad() error {
 		return fmt.Errorf("cannot use both 'catalogers' and 'select-catalogers'/'default-catalogers' flags")
 	}
 
-	flatten := func(l []string) []string {
-		var out []string
-		for _, v := range l {
-			for _, s := range strings.Split(v, ",") {
-				out = append(out, strings.TrimSpace(s))
-			}
-		}
-		sort.Strings(out)
+	cfg.From = Flatten(cfg.From)
 
-		return out
-	}
-
-	cfg.From = flatten(cfg.From)
-
-	cfg.Catalogers = flatten(cfg.Catalogers)
-	cfg.DefaultCatalogers = flatten(cfg.DefaultCatalogers)
-	cfg.SelectCatalogers = flatten(cfg.SelectCatalogers)
+	cfg.Catalogers = Flatten(cfg.Catalogers)
+	cfg.DefaultCatalogers = Flatten(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = Flatten(cfg.SelectCatalogers)
+	cfg.Enrich = Flatten(cfg.Enrich)
 
 	// for backwards compatibility
 	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
@@ -241,5 +293,75 @@ func (cfg *Catalog) PostLoad() error {
 		return fmt.Errorf("bad scope value %q", cfg.Scope)
 	}
 
+	// the binary package exclusion code depends on the file overlap relationships being created upstream in processing
+	if !cfg.Relationships.PackageFileOwnershipOverlap && cfg.Package.ExcludeBinaryOverlapByOwnership {
+		return fmt.Errorf("cannot enable exclude-binary-overlap-by-ownership without enabling package-file-ownership-overlap")
+	}
+
 	return nil
 }
+
+func Flatten(commaSeparatedEntries []string) []string {
+	var out []string
+	for _, v := range commaSeparatedEntries {
+		for _, s := range strings.Split(v, ",") {
+			out = append(out, strings.TrimSpace(s))
+		}
+	}
+	sort.Strings(out)
+	return out
+}
+
+var publicisedEnrichmentOptions = []string{
+	"all",
+	task.Golang,
+	task.Java,
+	task.JavaScript,
+}
+
+func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {
+	if len(enrichDirectives) == 0 {
+		return nil
+	}
+
+	enabled := func(features ...string) *bool {
+		for _, directive := range enrichDirectives {
+			enable := true
+			directive = strings.TrimPrefix(directive, "+") // +java and java are equivalent
+			if strings.HasPrefix(directive, "-") {
+				directive = directive[1:]
+				enable = false
+			}
+			for _, feature := range features {
+				if directive == feature {
+					return &enable
+				}
+			}
+		}
+		return nil
+	}
+
+	enableAll := enabled("all")
+	disableAll := enabled("none")
+
+	if disableAll != nil && *disableAll {
+		if enableAll != nil {
+			log.Warn("you have specified to both enable and disable all enrichment functionality, defaulting to disabled")
+		}
+		enableAll = ptr(false)
+	}
+
+	// check for explicit enable/disable of feature names
+	for _, feat := range features {
+		enableFeature := enabled(feat)
+		if enableFeature != nil {
+			return enableFeature
+		}
+	}
+
+	return enableAll
+}
+
+func ptr[T any](val T) *T {
+	return &val
+}

cmd/syft/internal/options/catalog_test.go

@@ -57,6 +57,14 @@ func TestCatalog_PostLoad(t *testing.T) {
 				assert.Empty(t, options.Catalogers)
 			},
 		},
+		{
+			name: "must have package overlap flag when pruning binaries by overlap",
+			options: Catalog{
+				Package:       packageConfig{ExcludeBinaryOverlapByOwnership: true},
+				Relationships: relationshipsConfig{PackageFileOwnershipOverlap: false},
+			},
+			wantErr: assert.Error,
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -70,3 +78,69 @@ func TestCatalog_PostLoad(t *testing.T) {
 		})
 	}
 }
+
+func Test_enrichmentEnabled(t *testing.T) {
+	tests := []struct {
+		directives string
+		test       string
+		expected   *bool
+	}{
+		{
+			directives: "",
+			test:       "java",
+			expected:   nil,
+		},
+		{
+			directives: "none",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "none,+java",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "all,none",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "all",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "golang,js",
+			test:       "java",
+			expected:   nil,
+		},
+		{
+			directives: "golang,-js,java",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "golang,js,-java",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "all",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "all,-java",
+			test:       "java",
+			expected:   ptr(false),
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.directives, func(t *testing.T) {
+			got := enrichmentEnabled(Flatten([]string{test.directives}), test.test)
+			assert.Equal(t, test.expected, got)
+		})
+	}
+}

cmd/syft/internal/options/compliance.go

@@ -0,0 +1,35 @@
+package options
+
+import (
+	"github.com/anchore/fangs"
+	"github.com/anchore/syft/syft/cataloging"
+)
+
+var (
+	_ fangs.FieldDescriber = (*complianceConfig)(nil)
+	_ fangs.PostLoader     = (*complianceConfig)(nil)
+)
+
+type complianceConfig struct {
+	MissingName    cataloging.ComplianceAction `mapstructure:"missing-name" json:"missing-name" yaml:"missing-name"`
+	MissingVersion cataloging.ComplianceAction `mapstructure:"missing-version" json:"missing-version" yaml:"missing-version"`
+}
+
+func defaultComplianceConfig() complianceConfig {
+	def := cataloging.DefaultComplianceConfig()
+	return complianceConfig{
+		MissingName:    def.MissingName,
+		MissingVersion: def.MissingVersion,
+	}
+}
+
+func (r *complianceConfig) DescribeFields(descriptions fangs.FieldDescriptionSet) {
+	descriptions.Add(&r.MissingName, "action to take when a package is missing a name")
+	descriptions.Add(&r.MissingVersion, "action to take when a package is missing a version")
+}
+
+func (r *complianceConfig) PostLoad() error {
+	r.MissingName = r.MissingName.Parse()
+	r.MissingVersion = r.MissingVersion.Parse()
+	return nil
+}

cmd/syft/internal/options/config.go

@@ -2,11 +2,11 @@ package options
 
 import "github.com/anchore/fangs"
 
-// Config holds a reference to the specific config file that was used to load application configuration
+// Config holds a reference to the specific config file(s) that were used to load application configuration
 type Config struct {
 	ConfigFile string `yaml:"config" json:"config" mapstructure:"config"`
 }
 
 func (cfg *Config) DescribeFields(descriptions fangs.FieldDescriptionSet) {
-	descriptions.Add(&cfg.ConfigFile, "the configuration file that was used to load application configuration")
+	descriptions.Add(&cfg.ConfigFile, "the configuration file(s) used to load application configuration")
 }

cmd/syft/internal/options/dotnet.go

@@ -0,0 +1,37 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/dotnet"
+)
+
+type dotnetConfig struct {
+	DepPackagesMustHaveDLL bool `mapstructure:"dep-packages-must-have-dll" json:"dep-packages-must-have-dll" yaml:"dep-packages-must-have-dll"`
+
+	DepPackagesMustClaimDLL bool `mapstructure:"dep-packages-must-claim-dll" json:"dep-packages-must-claim-dll" yaml:"dep-packages-must-claim-dll"`
+
+	PropagateDLLClaimsToParents bool `mapstructure:"propagate-dll-claims-to-parents" json:"propagate-dll-claims-to-parents" yaml:"propagate-dll-claims-to-parents"`
+
+	RelaxDLLClaimsWhenBundlingDetected bool `mapstructure:"relax-dll-claims-when-bundling-detected" json:"relax-dll-claims-when-bundling-detected" yaml:"relax-dll-claims-when-bundling-detected"`
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*dotnetConfig)(nil)
+
+func (o *dotnetConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.DepPackagesMustHaveDLL, `only keep dep.json packages which an executable on disk is found. The package is also included if a DLL is found for any child package, even if the package itself does not have a DLL.`)
+	descriptions.Add(&o.DepPackagesMustClaimDLL, `only keep dep.json packages which have a runtime/resource DLL claimed in the deps.json targets section (but not necessarily found on disk). The package is also included if any child package claims a DLL, even if the package itself does not claim a DLL.`)
+	descriptions.Add(&o.PropagateDLLClaimsToParents, `treat DLL claims or on-disk evidence for child packages as DLL claims or on-disk evidence for any parent package`)
+	descriptions.Add(&o.RelaxDLLClaimsWhenBundlingDetected, `show all packages from the deps.json if bundling tooling is present as a dependency (e.g. ILRepack)`)
+}
+
+func defaultDotnetConfig() dotnetConfig {
+	def := dotnet.DefaultCatalogerConfig()
+	return dotnetConfig{
+		DepPackagesMustHaveDLL:             def.DepPackagesMustHaveDLL,
+		DepPackagesMustClaimDLL:            def.DepPackagesMustClaimDLL,
+		PropagateDLLClaimsToParents:        def.PropagateDLLClaimsToParents,
+		RelaxDLLClaimsWhenBundlingDetected: def.RelaxDLLClaimsWhenBundlingDetected,
+	}
+}

cmd/syft/internal/options/format.go

@@ -50,7 +50,7 @@ if false, uses the syft-json output for templating (which follows the syft JSON
 
 Note: long term support for this option is not guaranteed (it may change or break at any time)`)
 
-	prettyDescription := `include space indention and newlines
+	prettyDescription := `include space indentation and newlines
 note: inherits default value from 'format.pretty' or 'false' if parent is unset`
 	descriptions.Add(&o.SyftJSON.Pretty, prettyDescription)
 	descriptions.Add(&o.SPDXJSON.Pretty, prettyDescription)

cmd/syft/internal/options/golang.go

@@ -8,9 +8,11 @@ import (
 )
 
 type golangConfig struct {
-	SearchLocalModCacheLicenses bool                          `json:"search-local-mod-cache-licenses" yaml:"search-local-mod-cache-licenses" mapstructure:"search-local-mod-cache-licenses"`
+	SearchLocalModCacheLicenses *bool                         `json:"search-local-mod-cache-licenses" yaml:"search-local-mod-cache-licenses" mapstructure:"search-local-mod-cache-licenses"`
 	LocalModCacheDir            string                        `json:"local-mod-cache-dir" yaml:"local-mod-cache-dir" mapstructure:"local-mod-cache-dir"`
-	SearchRemoteLicenses        bool                          `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	SearchLocalVendorLicenses   *bool                         `json:"search-local-vendor-licenses" yaml:"search-local-vendor-licenses" mapstructure:"search-local-vendor-licenses"`
+	LocalVendorDir              string                        `json:"local-vendor-dir" yaml:"local-vendor-dir" mapstructure:"local-vendor-dir"`
+	SearchRemoteLicenses        *bool                         `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
 	Proxy                       string                        `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
 	NoProxy                     string                        `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
 	MainModuleVersion           golangMainModuleVersionConfig `json:"main-module-version" yaml:"main-module-version" mapstructure:"main-module-version"`
@@ -24,6 +26,9 @@ func (o *golangConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
 	descriptions.Add(&o.SearchLocalModCacheLicenses, `search for go package licences in the GOPATH of the system running Syft, note that this is outside the
 container filesystem and potentially outside the root of a local directory scan`)
 	descriptions.Add(&o.LocalModCacheDir, `specify an explicit go mod cache directory, if unset this defaults to $GOPATH/pkg/mod or $HOME/go/pkg/mod`)
+	descriptions.Add(&o.SearchLocalVendorLicenses, `search for go package licences in the vendor folder on the system running Syft, note that this is outside the
+container filesystem and potentially outside the root of a local directory scan`)
+	descriptions.Add(&o.LocalVendorDir, `specify an explicit go vendor directory, if unset this defaults to ./vendor`)
 	descriptions.Add(&o.SearchRemoteLicenses, `search for go package licences by retrieving the package from a network proxy`)
 	descriptions.Add(&o.Proxy, `remote proxy to use when retrieving go packages from the network,
 if unset this defaults to $GOPROXY followed by https://proxy.golang.org`)
@@ -47,9 +52,11 @@ type golangMainModuleVersionConfig struct {
 func defaultGolangConfig() golangConfig {
 	def := golang.DefaultCatalogerConfig()
 	return golangConfig{
-		SearchLocalModCacheLicenses: def.SearchLocalModCacheLicenses,
+		SearchLocalModCacheLicenses: nil, // this defaults to false, which is the API default
 		LocalModCacheDir:            def.LocalModCacheDir,
-		SearchRemoteLicenses:        def.SearchRemoteLicenses,
+		SearchLocalVendorLicenses:   nil, // this defaults to false, which is the API default
+		LocalVendorDir:              def.LocalVendorDir,
+		SearchRemoteLicenses:        nil, // this defaults to false, which is the API default
 		Proxy:                       strings.Join(def.Proxies, ","),
 		NoProxy:                     strings.Join(def.NoProxy, ","),
 		MainModuleVersion: golangMainModuleVersionConfig{

cmd/syft/internal/options/java.go

@@ -6,22 +6,24 @@ import (
 )
 
 type javaConfig struct {
-	UseNetwork              bool   `yaml:"use-network" json:"use-network" mapstructure:"use-network"`
-	UseMavenLocalRepository bool   `yaml:"use-maven-local-repository" json:"use-maven-local-repository" mapstructure:"use-maven-local-repository"`
-	MavenLocalRepositoryDir string `yaml:"maven-local-repository-dir" json:"maven-local-repository-dir" mapstructure:"maven-local-repository-dir"`
-	MavenURL                string `yaml:"maven-url" json:"maven-url" mapstructure:"maven-url"`
-	MaxParentRecursiveDepth int    `yaml:"max-parent-recursive-depth" json:"max-parent-recursive-depth" mapstructure:"max-parent-recursive-depth"`
+	UseNetwork                    *bool  `yaml:"use-network" json:"use-network" mapstructure:"use-network"`
+	UseMavenLocalRepository       *bool  `yaml:"use-maven-local-repository" json:"use-maven-local-repository" mapstructure:"use-maven-local-repository"`
+	MavenLocalRepositoryDir       string `yaml:"maven-local-repository-dir" json:"maven-local-repository-dir" mapstructure:"maven-local-repository-dir"`
+	MavenURL                      string `yaml:"maven-url" json:"maven-url" mapstructure:"maven-url"`
+	MaxParentRecursiveDepth       int    `yaml:"max-parent-recursive-depth" json:"max-parent-recursive-depth" mapstructure:"max-parent-recursive-depth"`
+	ResolveTransitiveDependencies bool   `yaml:"resolve-transitive-dependencies" json:"resolve-transitive-dependencies" mapstructure:"resolve-transitive-dependencies"`
 }
 
 func defaultJavaConfig() javaConfig {
 	def := java.DefaultArchiveCatalogerConfig()
 
 	return javaConfig{
-		UseNetwork:              def.UseNetwork,
-		MaxParentRecursiveDepth: def.MaxParentRecursiveDepth,
-		UseMavenLocalRepository: def.UseMavenLocalRepository,
-		MavenLocalRepositoryDir: def.MavenLocalRepositoryDir,
-		MavenURL:                def.MavenBaseURL,
+		UseNetwork:                    nil, // this defaults to false, which is the API default
+		MaxParentRecursiveDepth:       def.MaxParentRecursiveDepth,
+		UseMavenLocalRepository:       nil, // this defaults to false, which is the API default
+		MavenLocalRepositoryDir:       def.MavenLocalRepositoryDir,
+		MavenURL:                      def.MavenBaseURL,
+		ResolveTransitiveDependencies: def.ResolveTransitiveDependencies,
 	}
 }
 
@@ -43,4 +45,5 @@ TIP: If you want to download all required pom files to the local repository with
 build, run 'mvn help:effective-pom' before performing the scan with syft.`)
 	descriptions.Add(&o.MavenLocalRepositoryDir, `override the default location of the local Maven repository. 
 the default is the subdirectory '.m2/repository' in your home directory`)
+	descriptions.Add(&o.ResolveTransitiveDependencies, `resolve transient dependencies such as those defined in a dependency's POM on Maven central`)
 }

cmd/syft/internal/options/javascript.go

@@ -3,8 +3,9 @@ package options
 import "github.com/anchore/clio"
 
 type javaScriptConfig struct {
-	SearchRemoteLicenses bool   `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
-	NpmBaseURL           string `json:"npm-base-url" yaml:"npm-base-url" mapstructure:"npm-base-url"`
+	SearchRemoteLicenses   *bool  `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	NpmBaseURL             string `json:"npm-base-url" yaml:"npm-base-url" mapstructure:"npm-base-url"`
+	IncludeDevDependencies *bool  `json:"include-dev-dependencies" yaml:"include-dev-dependencies" mapstructure:"include-dev-dependencies"`
 }
 
 var _ interface {
@@ -14,4 +15,5 @@ var _ interface {
 func (o *javaScriptConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
 	descriptions.Add(&o.SearchRemoteLicenses, `enables Syft to use the network to fill in more detailed license information`)
 	descriptions.Add(&o.NpmBaseURL, `base NPM url to use`)
+	descriptions.Add(&o.IncludeDevDependencies, `include development-scoped dependencies`)
 }

cmd/syft/internal/options/license.go

@@ -0,0 +1,47 @@
+package options
+
+import (
+	"fmt"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/syft/cataloging"
+)
+
+type licenseConfig struct {
+	Content                 cataloging.LicenseContent   `yaml:"content" json:"content" mapstructure:"content"`
+	Coverage                float64                     `yaml:"coverage" json:"coverage" mapstructure:"coverage"`
+	AvailableLicenseContent []cataloging.LicenseContent `yaml:"-" json:"-" mapstructure:"-"`
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*licenseConfig)(nil)
+
+func (o *licenseConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.Content, fmt.Sprintf("include the content of licenses in the SBOM for a given syft scan; valid values are: %s", o.AvailableLicenseContent))
+
+	descriptions.Add(&o.Coverage, `adjust the percent as a fraction of the total text, in normalized words, that
+matches any valid license for the given inputs, expressed as a percentage across all of the licenses matched.`)
+}
+
+func (o *licenseConfig) PostLoad() error {
+	validContent := internal.NewSet(o.AvailableLicenseContent...)
+	if !validContent.Contains(o.Content) {
+		return fmt.Errorf("could not use %q as license content option; valid values are: %v", o.Content, validContent.ToSlice())
+	}
+	return nil
+}
+
+func defaultLicenseConfig() licenseConfig {
+	cfg := cataloging.DefaultLicenseConfig()
+	return licenseConfig{
+		Content:  cfg.IncludeContent,
+		Coverage: cfg.Coverage,
+		AvailableLicenseContent: []cataloging.LicenseContent{
+			cataloging.LicenseContentIncludeAll,
+			cataloging.LicenseContentIncludeUnknown,
+			cataloging.LicenseContentExcludeAll,
+		},
+	}
+}

cmd/syft/internal/options/nix.go

@@ -0,0 +1,25 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/nix"
+)
+
+type nixConfig struct {
+	CaptureOwnedFiles bool `json:"capture-owned-files" yaml:"capture-owned-files" mapstructure:"capture-owned-files"`
+}
+
+func defaultNixConfig() nixConfig {
+	def := nix.DefaultConfig()
+	return nixConfig{
+		def.CaptureOwnedFiles,
+	}
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*nixConfig)(nil)
+
+func (o *nixConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.CaptureOwnedFiles, `enumerate all files owned by packages found within Nix store paths`)
+}

cmd/syft/internal/options/output.go

@@ -12,6 +12,7 @@ import (
 	"github.com/anchore/syft/syft/format/cyclonedxjson"
 	"github.com/anchore/syft/syft/format/cyclonedxxml"
 	"github.com/anchore/syft/syft/format/github"
+	"github.com/anchore/syft/syft/format/purls"
 	"github.com/anchore/syft/syft/format/spdxjson"
 	"github.com/anchore/syft/syft/format/spdxtagvalue"
 	"github.com/anchore/syft/syft/format/syftjson"
@@ -89,7 +90,7 @@ func (o Output) SBOMWriter() (sbom.Writer, error) {
 
 	usesTemplateOutput := names.Has(string(template.ID))
 
-	if usesTemplateOutput && o.Format.Template.Path == "" {
+	if usesTemplateOutput && o.Template.Path == "" {
 		return nil, fmt.Errorf(`must specify path to template file when using "template" output format`)
 	}
 
@@ -127,6 +128,7 @@ func supportedIDs() []sbom.FormatID {
 		table.ID,
 		text.ID,
 		template.ID,
+		purls.ID,
 
 		// encoders that support multiple versions
 		cyclonedxxml.ID,

cmd/syft/internal/options/output_file.go

@@ -3,10 +3,9 @@ package options
 import (
 	"fmt"
 
-	"github.com/mitchellh/go-homedir"
-
 	"github.com/anchore/clio"
 	"github.com/anchore/fangs"
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/syft/sbom"
 )
 
@@ -28,7 +27,7 @@ func (o *OutputFile) AddFlags(flags clio.FlagSet) {
 
 		if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
 			flagSet := pfp.PFlagSet()
-			flagSet.Lookup("file").Deprecated = "use: output"
+			flagSet.Lookup("file").Deprecated = "use: --output FORMAT=PATH"
 		}
 	}
 }

cmd/syft/internal/options/pkg.go

@@ -16,9 +16,9 @@ var _ interface {
 } = (*packageConfig)(nil)
 
 func (o *packageConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
-	descriptions.Add(&o.SearchUnindexedArchives, `search within archives that do contain a file index to search against (zip)
+	descriptions.Add(&o.SearchIndexedArchives, `search within archives that do contain a file index to search against (zip)
 note: for now this only applies to the java package cataloger`)
-	descriptions.Add(&o.SearchIndexedArchives, `search within archives that do not contain a file index to search against (tar, tar.gz, tar.bz2, etc)
+	descriptions.Add(&o.SearchUnindexedArchives, `search within archives that do not contain a file index to search against (tar, tar.gz, tar.bz2, etc)
 note: enabling this may result in a performance impact since all discovered compressed tars will be decompressed
 note: for now this only applies to the java package cataloger`)
 	descriptions.Add(&o.ExcludeBinaryOverlapByOwnership, `allows users to exclude synthetic binary packages from the sbom

cmd/syft/internal/options/source.go

@@ -5,9 +5,11 @@ import (
 	"sort"
 	"strings"
 
+	"github.com/dustin/go-humanize"
 	"github.com/scylladb/go-set/strset"
 
 	"github.com/anchore/clio"
+	stereoscopeFile "github.com/anchore/stereoscope/pkg/file"
 	"github.com/anchore/syft/syft/source/sourceproviders"
 )
 
@@ -27,6 +29,8 @@ var _ interface {
 	clio.FieldDescriber
 } = (*sourceConfig)(nil)
 
+var _ clio.PostLoader = (*imageSource)(nil)
+
 func (o *sourceConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
 	descriptions.Add(&o.File.Digests, `the file digest algorithms to use on the scanned file (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")`)
 	descriptions.Add(&o.Image.DefaultPullSource, `allows users to specify which image source should be used to generate the sbom
@@ -35,6 +39,7 @@ valid values are: registry, docker, podman`)
 
 type imageSource struct {
 	DefaultPullSource string `json:"default-pull-source" yaml:"default-pull-source" mapstructure:"default-pull-source"`
+	MaxLayerSize      string `json:"max-layer-size" yaml:"max-layer-size" mapstructure:"max-layer-size"`
 }
 
 func defaultSourceConfig() sourceConfig {
@@ -56,7 +61,14 @@ func (c *fileSource) PostLoad() error {
 	return nil
 }
 
-func (c imageSource) PostLoad() error {
+func (c *imageSource) PostLoad() error {
+	if c.MaxLayerSize != "" {
+		perFileReadLimit, err := humanize.ParseBytes(c.MaxLayerSize)
+		if err != nil {
+			return err
+		}
+		stereoscopeFile.SetPerFileReadLimit(int64(perFileReadLimit))
+	}
 	return checkDefaultSourceValues(c.DefaultPullSource)
 }
 

cmd/syft/internal/options/unknowns.go

@@ -0,0 +1,31 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/cataloging"
+)
+
+type unknownsConfig struct {
+	RemoveWhenPackagesDefined  bool `json:"remove-when-packages-defined" yaml:"remove-when-packages-defined" mapstructure:"remove-when-packages-defined"`
+	ExecutablesWithoutPackages bool `json:"executables-without-packages" yaml:"executables-without-packages" mapstructure:"executables-without-packages"`
+	UnexpandedArchives         bool `json:"unexpanded-archives" yaml:"unexpanded-archives" mapstructure:"unexpanded-archives"`
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*unknownsConfig)(nil)
+
+func (o *unknownsConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.RemoveWhenPackagesDefined, `remove unknown errors on files with discovered packages`)
+	descriptions.Add(&o.ExecutablesWithoutPackages, `include executables without any identified packages`)
+	descriptions.Add(&o.UnexpandedArchives, `include archives which were not expanded and searched`)
+}
+
+func defaultUnknowns() unknownsConfig {
+	def := cataloging.DefaultUnknownsConfig()
+	return unknownsConfig{
+		RemoveWhenPackagesDefined:  def.RemoveWhenPackagesDefined,
+		ExecutablesWithoutPackages: def.IncludeExecutablesWithoutPackages,
+		UnexpandedArchives:         def.IncludeUnexpandedArchives,
+	}
+}

cmd/syft/internal/options/writer.go

@@ -10,9 +10,9 @@ import (
 	"strings"
 
 	"github.com/hashicorp/go-multierror"
-	"github.com/mitchellh/go-homedir"
 	"github.com/scylladb/go-set/strset"
 
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/format"

cmd/syft/internal/options/writer_test.go

@@ -6,10 +6,10 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/docker/docker/pkg/homedir"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/syft/sbom"
 )
 
@@ -228,6 +228,8 @@ func Test_newSBOMMultiWriter(t *testing.T) {
 }
 
 func Test_newSBOMWriterDescription(t *testing.T) {
+	h, err := homedir.Dir()
+	require.NoError(t, err)
 	tests := []struct {
 		name     string
 		path     string
@@ -236,7 +238,7 @@ func Test_newSBOMWriterDescription(t *testing.T) {
 		{
 			name:     "expand home dir",
 			path:     "~/place.txt",
-			expected: filepath.Join(homedir.Get(), "place.txt"),
+			expected: filepath.Join(h, "place.txt"),
 		},
 		{
 			name:     "passthrough other paths",

cmd/syft/internal/test/integration/.gitignore

@@ -0,0 +1 @@
+results

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

@@ -7,7 +7,7 @@ import (
 )
 
 func Test_AllLayersIncludesSquashed(t *testing.T) {
-	// This is a verification test for issue #894 (https://github.com/anchore/syft/issues/894)
+	// This is a verification test for issue grype/#894 (https://github.com/anchore/grype/issues/894)
 	allLayers, _ := catalogFixtureImage(t, "image-suse-all-layers", source.AllLayersScope)
 	squashed, _ := catalogFixtureImage(t, "image-suse-all-layers", source.SquashedScope)
 

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

@@ -78,11 +78,27 @@ var imageOnlyTestCases = []testCase{
 		},
 	},
 	{
-		name:        "find dot net executable",
+		name:        "find .NET packages (deps.json + .dlls)",
 		pkgType:     pkg.DotnetPkg,
 		pkgLanguage: pkg.Dotnet,
 		pkgInfo: map[string]string{
+			// executable
 			"DocuSign.eSign": "6.8.0.0",
+			// deps.json
+			"AWSSDK.Core": "3.7.10.6",
+			"Microsoft.Extensions.DependencyInjection":              "6.0.0",
+			"Microsoft.Extensions.DependencyInjection.Abstractions": "6.0.0",
+			"Microsoft.Extensions.Logging":                          "6.0.0",
+			"Microsoft.Extensions.Logging.Abstractions":             "6.0.0",
+			"Microsoft.Extensions.Options":                          "6.0.0",
+			"Microsoft.Extensions.Primitives":                       "6.0.0",
+			"Newtonsoft.Json":                                       "13.0.1",
+			"Serilog":                                               "2.10.0",
+			"Serilog.Sinks.Console":                                 "4.0.1",
+			//"System.Diagnostics.DiagnosticSource":                   "6.0.0", // no dll claims in deps.json targets section
+			//"System.Runtime.CompilerServices.Unsafe":                "6.0.0", // no dll claims in deps.json targets section
+			"TestCommon":  "1.0.0",
+			"TestLibrary": "1.0.0",
 		},
 	},
 }
@@ -241,10 +257,11 @@ var dirOnlyTestCases = []testCase{
 		},
 	},
 	{
-		name:        "find dotnet packages",
+		name:        "find dotnet packages (.deps.json)",
 		pkgType:     pkg.DotnetPkg,
 		pkgLanguage: pkg.Dotnet,
 		pkgInfo: map[string]string{
+			// all from deps.json
 			"AWSSDK.Core": "3.7.10.6",
 			"Microsoft.Extensions.DependencyInjection":              "6.0.0",
 			"Microsoft.Extensions.DependencyInjection.Abstractions": "6.0.0",
@@ -255,17 +272,17 @@ var dirOnlyTestCases = []testCase{
 			"Newtonsoft.Json":                                       "13.0.1",
 			"Serilog":                                               "2.10.0",
 			"Serilog.Sinks.Console":                                 "4.0.1",
-			"System.Diagnostics.DiagnosticSource":                   "6.0.0",
-			"System.Runtime.CompilerServices.Unsafe":                "6.0.0",
-			"TestCommon":                                            "1.0.0",
-			"TestLibrary":                                           "1.0.0",
+			//"System.Diagnostics.DiagnosticSource":                   "6.0.0", // no dll claims in deps.json targets section
+			//"System.Runtime.CompilerServices.Unsafe":                "6.0.0", // no dll claims in deps.json targets section
+			"TestCommon":  "1.0.0",
+			"TestLibrary": "1.0.0",
 		},
 	},
 	{
 		name:        "find java packages including pom.xml", // directory scans can include packages that have yet to be installed
 		pkgType:     pkg.JavaPkg,
 		pkgLanguage: pkg.Java,
-		duplicates:  1, // joda-time is included in both pom.xml AND the .jar collection
+		duplicates:  2, // joda-time and example-java-app-maven are included in both pom.xml AND the .jar collection
 		pkgInfo: map[string]string{
 			"example-java-app-maven": "0.1.0",
 			"joda-time":              "2.9.2",
@@ -410,6 +427,22 @@ var dirOnlyTestCases = []testCase{
 			"octo-org/this-repo/.github/workflows/workflow-1.yml": "172239021f7ba04fe7327647b213799853a9eb89",
 		},
 	},
+	{
+		name:        "find opam package",
+		pkgType:     pkg.OpamPkg,
+		pkgLanguage: pkg.OCaml,
+		pkgInfo: map[string]string{
+			"ocaml-base-compiler": "4.14.0",
+		},
+	},
+	{
+		name:        "find terraform packages",
+		pkgType:     pkg.TerraformPkg,
+		pkgLanguage: pkg.Go,
+		pkgInfo: map[string]string{
+			"registry.terraform.io/hashicorp/aws": "5.72.1",
+		},
+	},
 }
 
 var commonTestCases = []testCase{
@@ -469,8 +502,15 @@ var commonTestCases = []testCase{
 		},
 	},
 	{
-		name:        "find php pecl package",
-		pkgType:     pkg.PhpPeclPkg,
+		name:    "find homebrew",
+		pkgType: pkg.HomebrewPkg,
+		pkgInfo: map[string]string{
+			"afflib": "1.2.3",
+		},
+	},
+	{
+		name:        "find php pear/pecl package",
+		pkgType:     pkg.PhpPearPkg,
 		pkgLanguage: pkg.PHP,
 		pkgInfo: map[string]string{
 			"memcached": "3.2.0",

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

@@ -12,6 +12,7 @@ import (
 	"github.com/anchore/stereoscope/pkg/imagetest"
 	"github.com/anchore/syft/syft"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
 
@@ -52,6 +53,7 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedLanguages.Remove(pkg.Dart.String())
 	definedLanguages.Remove(pkg.Swift.String())
 	definedLanguages.Remove(pkg.Swipl.String())
+	definedLanguages.Remove(pkg.OCaml.String())
 	definedLanguages.Remove(pkg.CPP.String())
 	definedLanguages.Remove(pkg.Haskell.String())
 	definedLanguages.Remove(pkg.Elixir.String())
@@ -73,13 +75,18 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedPkgs.Remove(string(pkg.ConanPkg))
 	definedPkgs.Remove(string(pkg.HackagePkg))
 	definedPkgs.Remove(string(pkg.BinaryPkg))
+	definedPkgs.Remove(string(pkg.BitnamiPkg))
+	definedPkgs.Remove(string(pkg.GraalVMNativeImagePkg))
 	definedPkgs.Remove(string(pkg.HexPkg))
 	definedPkgs.Remove(string(pkg.LinuxKernelPkg))
 	definedPkgs.Remove(string(pkg.LinuxKernelModulePkg))
 	definedPkgs.Remove(string(pkg.SwiftPkg))
 	definedPkgs.Remove(string(pkg.SwiplPackPkg))
+	definedPkgs.Remove(string(pkg.OpamPkg))
 	definedPkgs.Remove(string(pkg.GithubActionPkg))
 	definedPkgs.Remove(string(pkg.GithubActionWorkflowPkg))
+	definedPkgs.Remove(string(pkg.TerraformPkg))
+	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // we have coverage for pear instead
 
 	var cases []testCase
 	cases = append(cases, commonTestCases...)
@@ -87,40 +94,7 @@ func TestPkgCoverageImage(t *testing.T) {
 
 	for _, c := range cases {
 		t.Run(c.name, func(t *testing.T) {
-			pkgCount := 0
-
-			for a := range sbom.Artifacts.Packages.Enumerate(c.pkgType) {
-				if a.Language.String() != "" {
-					observedLanguages.Add(a.Language.String())
-				}
-
-				observedPkgs.Add(string(a.Type))
-				expectedVersion, ok := c.pkgInfo[a.Name]
-				if !ok {
-					t.Errorf("unexpected package found: %s", a.Name)
-				}
-
-				if expectedVersion != a.Version {
-					t.Errorf("unexpected package version (pkg=%s): %s, expected: %s", a.Name, a.Version, expectedVersion)
-				}
-
-				if a.Language != c.pkgLanguage {
-					t.Errorf("bad language (pkg=%+v): %+v", a.Name, a.Language)
-				}
-
-				if a.Type != c.pkgType {
-					t.Errorf("bad package type (pkg=%+v): %+v", a.Name, a.Type)
-				}
-				pkgCount++
-			}
-
-			if pkgCount != len(c.pkgInfo)+c.duplicates {
-				t.Logf("Discovered packages of type %+v", c.pkgType)
-				for a := range sbom.Artifacts.Packages.Enumerate(c.pkgType) {
-					t.Log("   ", a)
-				}
-				t.Fatalf("unexpected package count: %d!=%d", pkgCount, len(c.pkgInfo))
-			}
+			assertPackages(t, sbom, c, observedLanguages, observedPkgs)
 		})
 	}
 
@@ -170,44 +144,7 @@ func TestPkgCoverageDirectory(t *testing.T) {
 
 	for _, test := range cases {
 		t.Run(test.name, func(t *testing.T) {
-			actualPkgCount := 0
-
-			for actualPkg := range sbom.Artifacts.Packages.Enumerate(test.pkgType) {
-				observedLanguages.Add(actualPkg.Language.String())
-				observedPkgs.Add(string(actualPkg.Type))
-
-				expectedVersion, ok := test.pkgInfo[actualPkg.Name]
-				if !ok {
-					t.Errorf("unexpected package found: %s", actualPkg.Name)
-				}
-
-				if expectedVersion != actualPkg.Version {
-					t.Errorf("unexpected package version (pkg=%s): %s", actualPkg.Name, actualPkg.Version)
-				}
-
-				var foundLang bool
-				for _, lang := range strings.Split(test.pkgLanguage.String(), ",") {
-					if actualPkg.Language.String() == lang {
-						foundLang = true
-						break
-					}
-				}
-				if !foundLang {
-					t.Errorf("bad language (pkg=%+v): %+v", actualPkg.Name, actualPkg.Language)
-				}
-
-				if actualPkg.Type != test.pkgType {
-					t.Errorf("bad package type (pkg=%+v): %+v", actualPkg.Name, actualPkg.Type)
-				}
-				actualPkgCount++
-			}
-
-			if actualPkgCount != len(test.pkgInfo)+test.duplicates {
-				for actualPkg := range sbom.Artifacts.Packages.Enumerate(test.pkgType) {
-					t.Log("   ", actualPkg)
-				}
-				t.Fatalf("unexpected package count: %d!=%d", actualPkgCount, len(test.pkgInfo))
-			}
+			assertPackages(t, sbom, test, observedLanguages, observedPkgs)
 		})
 	}
 
@@ -216,10 +153,13 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	definedLanguages.Remove(pkg.R.String())
 	observedPkgs.Remove(string(pkg.UnknownPkg))
 	definedPkgs.Remove(string(pkg.BinaryPkg))
+	definedPkgs.Remove(string(pkg.BitnamiPkg))
+	definedPkgs.Remove(string(pkg.GraalVMNativeImagePkg))
 	definedPkgs.Remove(string(pkg.LinuxKernelPkg))
 	definedPkgs.Remove(string(pkg.LinuxKernelModulePkg))
 	definedPkgs.Remove(string(pkg.Rpkg))
 	definedPkgs.Remove(string(pkg.UnknownPkg))
+	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // this is covered as pear packages
 
 	// for directory scans we should not expect to see any of the following package types
 	definedPkgs.Remove(string(pkg.KbPkg))
@@ -234,6 +174,61 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	}
 }
 
+func assertPackages(t *testing.T, sbom sbom.SBOM, test testCase, observedLanguages *strset.Set, observedPkgs *strset.Set) {
+	actualPkgCount := 0
+
+	for actualPkg := range sbom.Artifacts.Packages.Enumerate(test.pkgType) {
+		observedLanguages.Add(actualPkg.Language.String())
+		observedPkgs.Add(string(actualPkg.Type))
+
+		expectedVersion, ok := test.pkgInfo[actualPkg.Name]
+		if !ok {
+			t.Errorf("unexpected package found: %s", actualPkg.Name)
+		}
+
+		if expectedVersion != actualPkg.Version {
+			t.Errorf("unexpected package version (pkg=%s): %s", actualPkg.Name, actualPkg.Version)
+		}
+
+		var foundLang bool
+		for _, lang := range strings.Split(test.pkgLanguage.String(), ",") {
+			if actualPkg.Language.String() == lang {
+				foundLang = true
+				break
+			}
+		}
+		if !foundLang {
+			t.Errorf("bad language (pkg=%+v): %+v", actualPkg.Name, actualPkg.Language)
+		}
+
+		if actualPkg.Type != test.pkgType {
+			t.Errorf("bad package type (pkg=%+v): %+v", actualPkg.Name, actualPkg.Type)
+		}
+		actualPkgCount++
+
+		// all packages should have at least one location associated with it, and of those locations at least one should be primary evidence
+		locs := actualPkg.Locations.ToSlice()
+		assert.NotEmpty(t, locs, "package %q has no locations (type=%q)", actualPkg.Name, actualPkg.Type)
+		var primaryEvidenceFound bool
+		for _, l := range locs {
+			if _, exists := l.Annotations[pkg.EvidenceAnnotationKey]; !exists {
+				t.Errorf("missing evidence annotation (pkg=%s type=%s)", actualPkg.Name, actualPkg.Type)
+			}
+			if l.Annotations[pkg.EvidenceAnnotationKey] == pkg.PrimaryEvidenceAnnotation {
+				primaryEvidenceFound = true
+			}
+		}
+		assert.True(t, primaryEvidenceFound, "no primary evidence found for package %q", actualPkg.Name)
+	}
+
+	if actualPkgCount != len(test.pkgInfo)+test.duplicates {
+		for actualPkg := range sbom.Artifacts.Packages.Enumerate(test.pkgType) {
+			t.Log("   ", actualPkg)
+		}
+		t.Fatalf("unexpected package count: %d!=%d", actualPkgCount, len(test.pkgInfo))
+	}
+}
+
 func TestPkgCoverageImage_HasEvidence(t *testing.T) {
 	sbom, _ := catalogFixtureImage(t, "image-pkg-coverage", source.SquashedScope)
 

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

@@ -2,7 +2,9 @@ package integration
 
 import (
 	"bytes"
-	"regexp"
+	"os"
+	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/google/go-cmp/cmp"
@@ -12,8 +14,6 @@ import (
 
 	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/syft/format"
-	"github.com/anchore/syft/syft/format/cyclonedxjson"
-	"github.com/anchore/syft/syft/format/cyclonedxxml"
 	"github.com/anchore/syft/syft/format/syftjson"
 	"github.com/anchore/syft/syft/source"
 )
@@ -43,26 +43,27 @@ func TestEncodeDecodeEncodeCycleComparison(t *testing.T) {
 			},
 			json: true,
 		},
-		{
-			name: cyclonedxjson.ID.String(),
-			redactor: func(in []byte) []byte {
-				// unstable values
-				in = regexp.MustCompile(`"(timestamp|serialNumber|bom-ref|ref)":\s*"(\n|[^"])+"`).ReplaceAll(in, []byte(`"$1": "redacted"`))
-				in = regexp.MustCompile(`"(dependsOn)":\s*\[(?:\s|[^]])+]`).ReplaceAll(in, []byte(`"$1": []`))
-				return in
-			},
-			json: true,
-		},
-		{
-			name: cyclonedxxml.ID.String(),
-			redactor: func(in []byte) []byte {
-				// unstable values
-				in = regexp.MustCompile(`(serialNumber|bom-ref|ref)="[^"]+"`).ReplaceAll(in, []byte{})
-				in = regexp.MustCompile(`<timestamp>[^<]+</timestamp>`).ReplaceAll(in, []byte{})
-
-				return in
-			},
-		},
+		// TODO: ignoring the `ref` field though does create stable results to compare, but the SBOM is fundamentally gutted and not worth comparing (find a better redaction or compare method)
+		//{
+		//	name: cyclonedxjson.ID.String(),
+		//	redactor: func(in []byte) []byte {
+		//		// unstable values
+		//		in = regexp.MustCompile(`"(timestamp|serialNumber|bom-ref|ref)":\s*"(\n|[^"])+"`).ReplaceAll(in, []byte(`"$1": "redacted"`))
+		//		in = regexp.MustCompile(`"(dependsOn)":\s*\[(?:\s|[^]])+]`).ReplaceAll(in, []byte(`"$1": []`))
+		//		return in
+		//	},
+		//	json: true,
+		//},
+		//{
+		//	name: cyclonedxxml.ID.String(),
+		//	redactor: func(in []byte) []byte {
+		//		// unstable values
+		//		in = regexp.MustCompile(`(serialNumber|bom-ref|ref)="[^"]+"`).ReplaceAll(in, []byte{})
+		//		in = regexp.MustCompile(`<timestamp>[^<]+</timestamp>`).ReplaceAll(in, []byte{})
+		//
+		//		return in
+		//	},
+		//},
 	}
 
 	opts := options.DefaultOutput()
@@ -112,6 +113,21 @@ func TestEncodeDecodeEncodeCycleComparison(t *testing.T) {
 					diffs := dmp.DiffMain(string(by1), string(by2), true)
 					t.Errorf("diff: %s", dmp.DiffPrettyText(diffs))
 				}
+
+				// write raw IMAGE@NAME-start and IMAGE@NAME-finish to files within the results dir
+				// ... this is helpful for debugging
+				require.NoError(t, os.MkdirAll("results", 0700))
+
+				suffix := "sbom"
+				switch {
+				case strings.Contains(test.name, "json"):
+					suffix = "json"
+				case strings.Contains(test.name, "xml"):
+					suffix = "xml"
+				}
+
+				require.NoError(t, os.WriteFile(filepath.Join("results", image+"@"+test.name+"-start."+suffix), by1, 0600))
+				require.NoError(t, os.WriteFile(filepath.Join("results", image+"@"+test.name+"-finish."+suffix), by2, 0600))
 			}
 		})
 	}

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

@@ -35,8 +35,8 @@ func TestGolangCompilerDetection(t *testing.T) {
 			for _, pkg := range packages {
 				foundCompilerVersions[pkg.Version] = struct{}{}
 				foundPURL[pkg.PURL] = struct{}{}
-				for _, cpe := range pkg.CPEs {
-					foundCPE[cpe] = struct{}{}
+				for _, c := range pkg.CPEs {
+					foundCPE[c] = struct{}{}
 				}
 			}
 

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

@@ -1,37 +0,0 @@
-package integration
-
-import (
-	"encoding/json"
-	"net/http"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/anchore/syft/internal/spdxlicense"
-)
-
-func TestSPDXLicenseListIsTheLatest(t *testing.T) {
-	resp, err := http.Get("https://spdx.org/licenses/licenses.json")
-	if err != nil {
-		t.Fatalf("unable to get licenses list: %+v", err)
-	}
-
-	type licenseList struct {
-		Version  string `json:"licenseListVersion"`
-		Licenses []struct {
-			ID          string   `json:"licenseId"`
-			Name        string   `json:"name"`
-			Text        string   `json:"licenseText"`
-			Deprecated  bool     `json:"isDeprecatedLicenseId"`
-			OSIApproved bool     `json:"isOsiApproved"`
-			SeeAlso     []string `json:"seeAlso"`
-		} `json:"licenses"`
-	}
-
-	var latest licenseList
-	if err = json.NewDecoder(resp.Body).Decode(&latest); err != nil {
-		t.Fatalf("unable to decode license list: %+v", err)
-	}
-
-	assert.Equal(t, latest.Version, spdxlicense.Version)
-}

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

@@ -25,7 +25,7 @@ func TestNpmPackageLockDirectory(t *testing.T) {
 	}
 
 	// ensure that integration test commonTestCases stay in sync with the available catalogers
-	const expectedPackageCount = 6
+	const expectedPackageCount = 2
 	if foundPackages.Size() != expectedPackageCount {
 		t.Errorf("found the wrong set of npm package-lock.json packages (expected: %d, actual: %d)", expectedPackageCount, foundPackages.Size())
 	}

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

@@ -52,8 +52,18 @@ func TestAllPackageCatalogersReachableInTasks(t *testing.T) {
 
 	assert.Equal(t, len(taskTagsByName), constructorCount, "mismatch in number of cataloger constructors and task names")
 
+	exceptions := strset.New(
+		// not reachable since they are deprecated
+		"dotnet-portable-executable-cataloger",
+		"dotnet-deps-cataloger",
+		"nix-store-cataloger",
+		"php-pecl-serialized-cataloger",
+		// not reachable by design
+		"sbom-cataloger",
+	)
+
 	for taskName, tags := range taskTagsByName {
-		if taskName == "sbom-cataloger" {
+		if exceptions.Has(taskName) {
 			continue // this is a special case
 		}
 		if !strset.New(tags...).HasAny(pkgcataloging.ImageTag, pkgcataloging.DirectoryTag) {

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

@@ -1,5 +1,3 @@
-//go:build !arm64
-
 package integration
 
 import (
@@ -7,7 +5,6 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
 
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
@@ -22,41 +19,39 @@ func TestPackageDeduplication(t *testing.T) {
 	}{
 		{
 			scope:        source.AllLayersScope,
-			packageCount: 172, // without deduplication this would be 618
+			packageCount: 175, // without deduplication this would be ~600
 			instanceCount: map[string]int{
-				"basesystem": 1,
-				"wget":       1,
-				"curl":       2, // upgraded in the image
-				"vsftpd":     1,
-				"httpd":      1, // rpm, - we exclude binary
+				"basesystem":   1,
+				"wget":         1,
+				"curl-minimal": 2, // upgraded in the image
+				"vsftpd":       1,
+				"httpd":        1, // rpm, - we exclude binary
 			},
 			locationCount: map[string]int{
-				"basesystem-10.0-7.el7.centos": 4,
-				"curl-7.29.0-59.el7":           1, // from base image
-				"curl-7.29.0-59.el7_9.1":       3, // upgrade
-				"wget-1.14-18.el7_6.1":         3,
-				"vsftpd-3.0.2-29.el7_9":        2,
-				"httpd-2.4.6-97.el7.centos.5":  1,
-				// "httpd-2.4.6":                  1, // binary
+				"basesystem-11-13.el9":               5, // in all layers
+				"curl-minimal-7.76.1-26.el9_3.2.0.1": 2, // base + wget layer
+				"curl-minimal-7.76.1-31.el9":         3, // curl upgrade layer + all above layers
+				"wget-1.21.1-8.el9_4":                4, // wget + all above layers
+				"vsftpd-3.0.5-6.el9":                 2, // vsftpd + all above layers
+				"httpd-2.4.62-1.el9_5.2":             1, // last layer
 			},
 		},
 		{
 			scope:        source.SquashedScope,
-			packageCount: 170,
+			packageCount: 169,
 			instanceCount: map[string]int{
-				"basesystem": 1,
-				"wget":       1,
-				"curl":       1, // upgraded, but the most recent
-				"vsftpd":     1,
-				"httpd":      1, // rpm, binary is now excluded by overlap
+				"basesystem":   1,
+				"wget":         1,
+				"curl-minimal": 1, // upgraded, but the most recent
+				"vsftpd":       1,
+				"httpd":        1, // rpm, binary is now excluded by overlap
 			},
 			locationCount: map[string]int{
-				"basesystem-10.0-7.el7.centos": 1,
-				"curl-7.29.0-59.el7_9.1":       1, // upgrade
-				"wget-1.14-18.el7_6.1":         1,
-				"vsftpd-3.0.2-29.el7_9":        1,
-				"httpd-2.4.6-97.el7.centos.5":  1,
-				// "httpd-2.4.6":                  1, // binary (excluded)
+				"basesystem-11-13.el9":       1,
+				"curl-minimal-7.76.1-31.el9": 1, // upgrade
+				"wget-1.21.1-8.el9_4":        1,
+				"vsftpd-3.0.5-6.el9":         1,
+				"httpd-2.4.62-1.el9_5.2":     1,
 			},
 		},
 	}
@@ -75,20 +70,21 @@ func TestPackageDeduplication(t *testing.T) {
 				pkgs := sbom.Artifacts.Packages.PackagesByName(name)
 
 				// with multiple packages with the same name, something is wrong (or this is the wrong fixture)
-				require.Len(t, pkgs, expectedInstanceCount)
+				if assert.Len(t, pkgs, expectedInstanceCount, "unexpected package count for %s", name) {
+					for _, p := range pkgs {
+						nameVersion := fmt.Sprintf("%s-%s", name, p.Version)
+						expectedLocationCount, ok := tt.locationCount[nameVersion]
+						if !ok {
+							t.Errorf("missing name-version: %s", nameVersion)
+							continue
+						}
 
-				for _, p := range pkgs {
-					nameVersion := fmt.Sprintf("%s-%s", name, p.Version)
-					expectedLocationCount, ok := tt.locationCount[nameVersion]
-					if !ok {
-						t.Fatalf("missing name-version: %s", nameVersion)
+						// we should see merged locations (assumption, there was 1 location for each package)
+						assert.Len(t, p.Locations.ToSlice(), expectedLocationCount, "unexpected location count for %s", nameVersion)
+
+						// all paths should match
+						assert.Len(t, p.Locations.CoordinateSet().Paths(), 1, "unexpected location count for %s", nameVersion)
 					}
-
-					// we should see merged locations (assumption, there was 1 location for each package)
-					assert.Len(t, p.Locations.ToSlice(), expectedLocationCount)
-
-					// all paths should match
-					assert.Len(t, p.Locations.CoordinateSet().Paths(), 1)
 				}
 			}
 

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

@@ -3,18 +3,18 @@ package integration
 import (
 	"testing"
 
+	"github.com/stretchr/testify/assert"
+
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
 )
 
 func TestPhotonPackageRegression(t *testing.T) { // Regression: https://github.com/anchore/syft/pull/1997
 	sbom, _ := catalogFixtureImage(t, "image-photon-all-layers", source.AllLayersScope)
-	var packages []pkg.Package
-	for p := range sbom.Artifacts.Packages.Enumerate() {
-		packages = append(packages, p)
+	var count int
+	for range sbom.Artifacts.Packages.Enumerate(pkg.RpmPkg) {
+		count++
 	}
 
-	if len(packages) < 1 {
-		t.Errorf("failed to find packages for photon distro; wanted > 0 got 0")
-	}
+	assert.Greater(t, count, 0, "expected to find RPM packages in the SBOM (but did not)")
 }

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

@@ -0,0 +1,25 @@
+package integration
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+)
+
+func TestSbomMetadataComponent(t *testing.T) {
+	sbom, _ := catalogFixtureImage(t, "image-sbom-metadata-component", source.SquashedScope, "+sbom-cataloger")
+
+	expectedPkgs := []string{"first-subcomponent", "main-component"}
+	foundPkgs := []string{}
+
+	for sbomPkg := range sbom.Artifacts.Packages.Enumerate(pkg.JavaPkg) {
+		foundPkgs = append(foundPkgs, sbomPkg.Name)
+	}
+
+	// check if both the package in `.metadata.component` and the one in `.components` were found
+	if !reflect.DeepEqual(expectedPkgs, foundPkgs) {
+		t.Errorf("expected packages %v, got %v", expectedPkgs, foundPkgs)
+	}
+}

cmd/syft/internal/test/integration/test-fixtures/Makefile

@@ -1,6 +1,21 @@
-# change these if you want CI to not use previous stored cache
-INTEGRATION_CACHE_BUSTER := "894d8ca"
+FINGERPRINT_FILE := cache.fingerprint
 
-.PHONY: cache.fingerprint
-cache.fingerprint:
-	find image-* -type f -exec md5sum {} + | awk '{print $1}' | sort | tee /dev/stderr | md5sum | tee cache.fingerprint && echo "$(INTEGRATION_CACHE_BUSTER)" >> cache.fingerprint
+.DEFAULT_GOAL := fixtures
+
+# requirement 1: 'fixtures' goal to generate any and all test fixtures
+fixtures:
+	@echo "nothing to do"
+
+# requirement 2: 'fingerprint' goal to determine if the fixture input that indicates any existing cache should be busted
+fingerprint: $(FINGERPRINT_FILE)
+
+# requirement 3: we always need to recalculate the fingerprint based on source regardless of any existing fingerprint
+.PHONY: $(FINGERPRINT_FILE)
+$(FINGERPRINT_FILE):
+	@find image-* -type f -exec sha256sum {} \; | sort -k2 > $(FINGERPRINT_FILE)
+	@#cat $(FINGERPRINT_FILE) | sha256sum | awk '{print $$1}'
+
+# requirement 4: 'clean' goal to remove all generated test fixtures
+.PHONY: clean
+clean:
+	rm -f $(FINGERPRINT_FILE)

cmd/syft/internal/test/integration/test-fixtures/image-golang-compiler/Dockerfile

@@ -1 +1,6 @@
-FROM golang:1.18.10-alpine
+FROM --platform=linux/amd64 golang:1.18.10-alpine
+
+FROM scratch
+
+# we don't need the entire golang toolchain, just a single binary with the stdlib baked in
+COPY --from=0 /usr/local/go/bin/gofmt bin/gofmt

cmd/syft/internal/test/integration/test-fixtures/image-java-no-main-package/Dockerfile

@@ -1,4 +1,4 @@
-FROM jenkins/jenkins:2.346.3-slim-jdk17@sha256:028fbbd9112c60ed086f5197fcba71992317864d27644e5949cf9c52ff4b65f0
+FROM jenkins/jenkins:2.346.3-slim-jdk17@sha256:028fbbd9112c60ed086f5197fcba71992317864d27644e5949cf9c52ff4b65f0 AS base
 
 USER root
 
@@ -12,7 +12,7 @@ RUN apt-get update 2>&1 > /dev/null && apt-get install -y less zip 2>&1 > /dev/n
 
 RUN unzip ../jenkins.war 2>&1 > /dev/null
 
-RUN rm -f ./META-INF/MANIFEST.MF
+RUN rm -rf ./META-INF/MANIFEST.MF ./WEB-INF ./jsbundles ./scripts ./css
 
 WORKDIR /usr/share/jenkins
 
@@ -21,3 +21,7 @@ RUN rm -rf jenkins.war
 RUN cd ./tmp && zip -r ../jenkins.war . && cd ..
 
 RUN rm -rf ./tmp
+
+FROM scratch
+
+COPY --from=base /usr/share/jenkins/jenkins.war /jenkins.war

cmd/syft/internal/test/integration/test-fixtures/image-java-virtualpath-regression/Dockerfile

@@ -1,7 +1,15 @@
-FROM alpine:3.18.3@sha256:7144f7bab3d4c2648d7e59409f15ec52a18006a128c733fcff20d3a4a54ba44a
+FROM alpine:3.18.3@sha256:7144f7bab3d4c2648d7e59409f15ec52a18006a128c733fcff20d3a4a54ba44a AS base
 
 RUN wget https://repo1.maven.org/maven2/org/jvnet/hudson/main/hudson-war/2.2.1/hudson-war-2.2.1.war
 
 RUN mv hudson-war-2.2.1.war hudson.war
 
+# let's make this image a little smaller as to not take up so much disk space
+# we'll only keep the jar metadata files (pom data + manifest) and throw away the rest
+RUN apk add --no-cache python3 py3-pip
+COPY extract.py /extract.py
+RUN python extract.py
 
+FROM scratch
+
+COPY --from=base /slim /

cmd/syft/internal/test/integration/test-fixtures/image-java-virtualpath-regression/extract.py

@@ -0,0 +1,69 @@
+import os
+import zipfile
+import io
+
+ARCHIVE_EXTENSIONS = ('.jar', '.war', '.ear', '.hpi', '.war', '.sar', '.nar', '.par')
+METADATA_FILES = ('pom.xml', 'pom.properties', 'MANIFEST.MF')
+
+
+def slim_archive(archive, output_dir, base_path="", archive_name=""):
+    """
+    extracts metadata files from the archive and creates a slim JAR file
+    containing only these files. handles nested JARs by preserving them.
+    """
+    slim_buffer = io.BytesIO()
+    with zipfile.ZipFile(archive, 'r') as zip_file:
+        with zipfile.ZipFile(slim_buffer, 'w', zipfile.ZIP_DEFLATED) as slim_zip:
+            for file_name in zip_file.namelist():
+                # check for metadata files or nested JARs
+                if file_name.endswith(METADATA_FILES):
+                    # add metadata files directly to the slimmed archive
+                    file_data = zip_file.read(file_name)
+                    slim_zip.writestr(file_name, file_data)
+                elif file_name.endswith(ARCHIVE_EXTENSIONS):
+                    # if it's a nested archive, recursively slim it
+                    nested_archive = io.BytesIO(zip_file.read(file_name))
+                    nested_slim_buffer = io.BytesIO()
+                    slim_archive(
+                        nested_archive,
+                        nested_slim_buffer,
+                        base_path=os.path.join(base_path, os.path.dirname(file_name)),
+                        archive_name=os.path.basename(file_name)
+                    )
+                    # add the slimmed nested archive back to the parent archive
+                    nested_slim_buffer.seek(0)
+                    slim_zip.writestr(file_name, nested_slim_buffer.read())
+
+    # write out the slimmed JAR to the output directory if output_dir is a directory
+    if isinstance(output_dir, str):
+        output_path = os.path.join(output_dir, base_path, archive_name)
+        os.makedirs(os.path.dirname(output_path), exist_ok=True)
+        with open(output_path, 'wb') as f:
+            slim_buffer.seek(0)
+            f.write(slim_buffer.read())
+    else:
+        # if output_dir is a BytesIO buffer (for nested archives), just write to it
+        output_dir.seek(0)
+        output_dir.write(slim_buffer.getvalue())
+
+
+def walk_directory_and_slim_jars(base_dir, output_dir):
+    """
+    recursively walks through a directory tree looking for .jar, .war, .ear,
+    .hpi files and slims them down by keeping only metadata files.
+    """
+    for dirpath, _, filenames in os.walk(base_dir):
+        for filename in filenames:
+            if filename.endswith(ARCHIVE_EXTENSIONS):
+                archive_path = os.path.join(dirpath, filename)
+                print(f"Processing {archive_path}")
+                slim_archive(archive_path, output_dir, os.path.relpath(dirpath, base_dir), filename)
+
+
+# a helper script for slimming down JAR files by keeping only metadata files but still keeping the jar packaging,
+# including nested JARs! Useful for testing purposes.
+if __name__ == "__main__":
+    BASE_DIR = "."
+    OUTPUT_DIR = "./slim"
+    os.makedirs(OUTPUT_DIR, exist_ok=True)
+    walk_directory_and_slim_jars(BASE_DIR, OUTPUT_DIR)

cmd/syft/internal/test/integration/test-fixtures/image-large-apk-data/Dockerfile

@@ -1,4 +1,4 @@
-FROM alpine@sha256:d9a7354e3845ea8466bb00b22224d9116b183e594527fb5b6c3d30bc01a20378
+FROM alpine@sha256:d9a7354e3845ea8466bb00b22224d9116b183e594527fb5b6c3d30bc01a20378 AS base
 
 # we keep these unpinned so that if alpine
 # changes our integration tests can adapt
@@ -6,3 +6,8 @@ RUN apk add --no-cache \
             tzdata \
             vim \
             alpine-sdk
+
+# we don't need the installed bins for this test, only the APK installed metadata
+FROM scratch
+
+COPY --from=base /lib/apk/db/installed /lib/apk/db/installed

cmd/syft/internal/test/integration/test-fixtures/image-mariner-distroless/Dockerfile

@@ -1 +1,8 @@
-FROM mcr.microsoft.com/cbl-mariner/distroless/base:2.0.202205275@sha256:f550c5428df17b145851ad75983aca6d613ad4b51ca7983b2a83e67d0ac91a5d
+FROM mcr.microsoft.com/cbl-mariner/distroless/base:2.0.202205275@sha256:f550c5428df17b145851ad75983aca6d613ad4b51ca7983b2a83e67d0ac91a5d AS base
+
+# let's shoot for smaller test fixtures
+FROM scratch
+
+COPY --from=base /var/lib/rpmmanifest/container-manifest-2 /var/lib/rpmmanifest/container-manifest-2
+COPY --from=base /usr/bin/gencat /usr/bin/gencat
+COPY --from=base /usr/bin/openssl /usr/bin/openssl

cmd/syft/internal/test/integration/test-fixtures/image-owning-package/Dockerfile

@@ -1,3 +1,8 @@
-FROM ubuntu:20.04@sha256:33a5cc25d22c45900796a1aca487ad7a7cb09f09ea00b779e3b2026b4fc2faba
+FROM ubuntu:20.04@sha256:33a5cc25d22c45900796a1aca487ad7a7cb09f09ea00b779e3b2026b4fc2faba AS base
 # this covers rpm-python
 RUN apt-get update && apt-get install -y python-pil=6.2.1-3
+
+# let's save some space...
+FROM scratch
+
+COPY --from=base /var/lib/dpkg/status /var/lib/dpkg/status

cmd/syft/internal/test/integration/test-fixtures/image-photon-all-layers/Dockerfile

@@ -1 +1,5 @@
-FROM photon:5.0-20230729@sha256:4cf2a1ce0a3f4625f13a0becb6b9bccfdb014c565be6e9a2ec4c4aad1ff8a5d9
+FROM photon:5.0-20230729@sha256:4cf2a1ce0a3f4625f13a0becb6b9bccfdb014c565be6e9a2ec4c4aad1ff8a5d9 AS base
+
+FROM scratch
+
+COPY --from=base /usr/lib/sysimage/rpm /usr/lib/sysimage/rpm

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/pkgs/homebrew/Cellar/afflib/1.2.3/.brew/afflib.rb

@@ -0,0 +1,2 @@
+desc "Advanced Forensic Format"
+homepage "https://github.com/sshock/AFFLIBv3"

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/pkgs/opam/ocaml-base-compiler.4.14.0/opam

@@ -0,0 +1,93 @@
+opam-version: "2.0"
+synopsis: "Official release 4.14.0"
+maintainer: [
+  "David Allsopp <david@tarides.com>"
+  "Florian Angeletti <florian.angeletti@inria.fr>"
+]
+authors: "Xavier Leroy and many contributors"
+license: "LGPL-2.1-or-later WITH OCaml-LGPL-linking-exception"
+homepage: "https://ocaml.org"
+bug-reports: "https://github.com/ocaml/opam-repository/issues"
+depends: [
+  "ocaml" {= "4.14.0" & post}
+  "base-unix" {post}
+  "base-bigarray" {post}
+  "base-threads" {post}
+  "host-arch-arm32" {arch = "arm32" & post}
+  "host-arch-arm64" {arch = "arm64" & post}
+  "host-arch-ppc64" {arch = "ppc64" & post}
+  "host-arch-riscv64" {arch = "riscv64" & post}
+  "host-arch-s390x" {arch = "s390x" & post}
+  "host-arch-x86_32" {os != "win32" & arch = "x86_32" & post}
+  "host-arch-x86_64" {os != "win32" & arch = "x86_64" & post}
+  "host-arch-unknown"
+    {os != "win32" & arch != "arm32" & arch != "arm64" & arch != "ppc64" &
+     arch != "riscv64" &
+     arch != "s390x" &
+     arch != "x86_32" &
+     arch != "x86_64" &
+     post}
+  (("arch-x86_64" {os = "win32" & arch = "x86_64"} &
+    (("system-mingw" & "mingw-w64-shims" {os-distribution = "cygwin" & post}) |
+     "system-msvc")) |
+   ("arch-x86_32" {os = "win32"} &
+    (("system-mingw" & "mingw-w64-shims" {os-distribution = "cygwin" & post}) |
+     "system-msvc")) |
+   "host-system-other" {os != "win32" & post})
+  "ocaml-options-vanilla" {post}
+  "flexdll" {>= "0.36" & os = "win32"}
+]
+conflict-class: "ocaml-core-compiler"
+flags: compiler
+setenv: CAML_LD_LIBRARY_PATH = "%{lib}%/stublibs"
+build: [
+  [
+    "./configure"
+    "--host=x86_64-pc-windows"
+      {system-msvc:installed & arch-x86_64:installed}
+    "--host=x86_64-w64-mingw32"
+      {os-distribution = "cygwin" & system-mingw:installed &
+       arch-x86_64:installed}
+    "--host=i686-pc-windows" {system-msvc:installed & arch-x86_32:installed}
+    "--host=i686-w64-mingw32"
+      {os-distribution = "cygwin" & system-mingw:installed &
+       arch-x86_32:installed}
+    "--prefix=%{prefix}%"
+    "--docdir=%{doc}%/ocaml"
+    "--with-flexdll=%{flexdll:share}%" {os = "win32" & flexdll:installed}
+    "-C"
+    "CC=cc" {os = "openbsd" | os = "macos"}
+    "ASPP=cc -c" {os = "openbsd" | os = "macos"}
+  ]
+  [make "-j%{jobs}%"]
+]
+install: [make "install"]
+build-env: MSYS2_ARG_CONV_EXCL = "*"
+post-messages: [
+  """\
+A failure in the middle of the build may be caused by build parallelism
+   (enabled by default).
+   Please file a bug report at https://github.com/ocaml/opam-repository/issues"""
+    {failure & jobs > "1"}
+  """\
+You can try installing again including --jobs=1
+   to force a sequential build instead."""
+    {failure & jobs > "1" & opam-version >= "2.0.5"}
+]
+dev-repo: "git+https://github.com/ocaml/ocaml#4.14"
+url {
+  src: "https://github.com/ocaml/ocaml/archive/4.14.0.tar.gz"
+  checksum:
+    "sha256=39f44260382f28d1054c5f9d8bf4753cb7ad64027da792f7938344544da155e8"
+}
+extra-source "ocaml-base-compiler.install" {
+  src:
+    "https://raw.githubusercontent.com/ocaml/opam-source-archives/main/patches/ocaml-base-compiler/ocaml-base-compiler.install"
+  checksum: [
+    "sha256=79f2a1a5044a91350a0eb6ce12e261a72a2855c094c425cddf3860e58c486678"
+    "md5=3e969b841df1f51ca448e6e6295cb451"
+  ]
+}
+x-env-path-rewrite: [
+  [CAML_LD_LIBRARY_PATH (";" {os = "win32"} ":" {os != "win32"}) "target"]
+]

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/pkgs/php/.registry/.channel.pecl.php.net/memcached.reg

@@ -1 +1 @@
-a:5:{s:4:"name";s:9:"memcached";s:4:"date";s:10:"2022-01-11";s:4:"time";s:8:"15:23:47";s:7:"version";a:2:{s:7:"release";s:5:"3.2.0";s:3:"api";s:5:"3.2.0";}s:7:"license";a:2:{s:7:"attribs";a:1:{s:3:"uri";s:26:"http://www.php.net/license";}s:8:"_content";s:11:"PHP License";}}
+a:6:{s:4:"name";s:9:"memcached";s:7:"channel";s:12:"pecl.php.net";s:4:"date";s:10:"2022-01-11";s:4:"time";s:8:"15:23:47";s:7:"version";a:2:{s:7:"release";s:5:"3.2.0";s:3:"api";s:5:"3.2.0";}s:7:"license";a:2:{s:7:"attribs";a:1:{s:3:"uri";s:26:"http://www.php.net/license";}s:8:"_content";s:11:"PHP License";}}

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/pkgs/var/lib/rpm/generate-fixture.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 set -eux
 
-docker create --name generate-rpmdb-fixture centos:latest sh -c 'tail -f /dev/null'
+docker create --name generate-rpmdb-fixture rockylinux:9 sh -c 'tail -f /dev/null'
 
 function cleanup {
   docker kill generate-rpmdb-fixture

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/terraform/.terraform.lock.hcl

@@ -0,0 +1,25 @@
+# This file is maintained automatically by "terraform init".
+# Manual edits may be lost in future updates.
+
+provider "registry.terraform.io/hashicorp/aws" {
+  version     = "5.72.1"
+  constraints = ">= 5.72.0"
+  hashes = [
+    "h1:jhd5O5o0CfZCNEwwN0EiDAzb7ApuFrtxJqa6HXW4EKE=",
+    "zh:0dea6843836e926d33469b48b948744079023816d16a2ff7666bcfb6aa3522d4",
+    "zh:195fa9513f75800a0d62797ebec75ee73e9b8c28d713fe9b63d3b1d1eec129b3",
+    "zh:1ed92f3961715bf0e024bcde3c12dfbdc50b00c1f8a43cc00802cfc45a256208",
+    "zh:2ac687e3a52606466cae4a6813e81d923042488df88d2424e28d3f8530f091bb",
+    "zh:32e7ca75f9314557daada3c44628fe1f3bf964a4f833bfb4b2295d833fe64b6f",
+    "zh:374ee0e6b4327cc6ef666908ce5d6450a3a56e90cd2b785e83c2bcfc100021d2",
+    "zh:5500fd6fdac44f96411fcf9c6d01691159ec35455ed127eb4c3a498e1cc92a64",
+    "zh:723a2dc4b064c12e7ee62ad4fbfd72fa5e025206ea47b735994ef53f3c373152",
+    "zh:89d97b87605f1d734f27e642567cbecf785b521af8ea81dac55c77ccde876221",
+    "zh:951ee1e5731e8d65d521d71b95927e55055b3c4656eef6d46fa580a63328befc",
+    "zh:9b12af85486a96aedd8d7984b0ff811a4b42e3d88dad1a3fb4c0b580d04fa425",
+    "zh:9b2b362470b64ec227b2da64762ab8bc4111c6b80365fd9d82fc5e1e33f44038",
+    "zh:aa6e57d0cb974ff0da5dee5d43ad2745cbbc4a2b507d4c799839b9fa96daf688",
+    "zh:ba0d14c4a6b7aa844a830d47c0bf995b632e37f0795394b5b60c638b62b7fc03",
+    "zh:c9764065a9c5d324db0b02bd201b9e3a2118e49c4960884acdeea377173302e9",
+  ]
+}

cmd/syft/internal/test/integration/test-fixtures/image-sbom-metadata-component/Dockerfile

@@ -0,0 +1,2 @@
+FROM scratch
+COPY test.cdx.json /

cmd/syft/internal/test/integration/test-fixtures/image-sbom-metadata-component/test.cdx.json

@@ -0,0 +1,32 @@
+{
+  "bomFormat" : "CycloneDX",
+  "specVersion" : "1.5",
+  "serialNumber" : "urn:uuid:dc807d4b-0415-35ab-ba61-49b5d39bc2d9",
+  "version" : 1,
+  "metadata" : {
+    "component" : {
+      "name" : "main-component",
+      "version" : "1.2.3",
+      "purl" : "pkg:maven/org.example/main-component@1.2.3",
+      "type" : "library",
+      "bom-ref" : "pkg:maven/org.example/main-component@1.2.3"
+    }
+  },
+  "components" : [
+    {
+      "name" : "first-subcomponent",
+      "version" : "2.3.4",
+      "purl" : "pkg:maven/org.example/first-subcomponent@2.3.4",
+      "type" : "library",
+      "bom-ref" : "pkg:maven/org.example/first-subcomponent@2.3.4"
+    }
+  ],
+  "dependencies" : [
+    {
+      "ref" : "pkg:maven/org.example/main-component-assembly@1.2.3",
+      "dependsOn" : [
+        "pkg:maven/org.example/first-subcomponent@2.3.4"
+      ]
+    }
+  ]
+}