remove workflows that update the code

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.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: v0.6.3
+      want: v0.12.0
     method: github-release
     with:
       repo: anchore/binny
@@ -18,7 +18,7 @@ tools:
   # used to sign mac binaries at release
   - name: quill
     version:
-      want: v0.4.1
+      want: v0.7.1
     method: github-release
     with:
       repo: anchore/quill
@@ -26,7 +26,7 @@ tools:
   # used for linting
   - name: golangci-lint
     version:
-      want: v1.55.2
+      want: v2.11.4
     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: v2.2.3
+      want: v3.0.5
     method: github-release
     with:
       repo: sigstore/cosign
@@ -58,7 +58,7 @@ tools:
   # used to release all artifacts
   - name: goreleaser
     version:
-      want: v1.23.0
+      want: v2.14.3
     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: v3.34.1
+      want: v3.49.1
     method: github-release
     with:
       repo: go-task/task
@@ -111,7 +98,23 @@ tools:
   # used for triggering a release
   - name: gh
     version:
-      want: v2.43.1
+      want: v2.88.1
     method: github-release
     with:
       repo: cli/cli
+
+  # used to upload test fixture cache
+  - name: oras
+    version:
+      want: v1.3.1
+    method: github-release
+    with:
+      repo: oras-project/oras
+
+  # used to upload test fixture cache
+  - name: yq
+    version:
+      want: v4.52.4
+    method: github-release
+    with:
+      repo: mikefarah/yq

.bouncer.yaml

@@ -6,8 +6,12 @@ permit:
   - MPL.*
   - ISC
   - WTFPL
+  - Unlicense
 
 ignore-packages:
+  # https://github.com/sorairolake/lzip-go/blob/34a2615d2abf740175c6b0a835baa08364e09430/go.sum.license#L3
+  # has `SPDX-License-Identifier: Apache-2.0 OR MIT`, both of which are acceptable
+  - github.com/sorairolake/lzip-go
   # packageurl-go is released under the MIT license located in the root of the repo at /mit.LICENSE
   - github.com/anchore/packageurl-go
 

.chronicle.yaml

@@ -1,4 +1,4 @@
-enforce-v0: true # don't make breaking-change label bump major version before 1.0.
+enforce-v0: false
 title: ""
 
 github:

.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: "1.21.x"
+    default: "1.26.x"
   go-dependencies:
     description: "Download go dependencies"
     required: true
@@ -13,35 +13,43 @@ inputs:
   cache-key-prefix:
     description: "Prefix all cache keys with this value"
     required: true
-    default: "1ac8281053"
-  compute-fingerprints:
-    description: "Compute test fixture fingerprints"
+    default: "53ac821810"
+  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@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+    - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
       if: inputs.go-version != ''
       with:
         go-version: ${{ inputs.go-version }}
+        check-latest: true
 
     - name: Restore tool cache
+      if: inputs.tools == 'true'
       id: tool-cache
-      uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+      uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
       with:
         path: ${{ github.workspace }}/.tool
         key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
 
     - name: Install project tools
       shell: bash
-      run: make tools
+      if: inputs.tools == 'true'
+      run: |
+        make tools
+        .tool/binny list
+        .tool/binny check
 
     - name: Install go dependencies
       if: inputs.go-dependencies == 'true'
@@ -51,11 +59,20 @@ runs:
     - name: Install apt packages
       if: inputs.bootstrap-apt-packages != ''
       shell: bash
+      env:
+        APT_PACKAGES: ${{ inputs.bootstrap-apt-packages }}
       run: |
-        DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y ${{ inputs.bootstrap-apt-packages }}
+        IFS=' ' read -ra packages <<< "$APT_PACKAGES"
+        DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y "${packages[@]}"
 
-    - name: Create all cache fingerprints
-      if: inputs.compute-fingerprints == 'true'
+    - name: Restore ORAS cache from github actions
+      if: inputs.download-test-fixture-cache == 'true'
+      uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+      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 fingerprints
-
+      run: make download-test-fixture-cache

.github/dependabot.yml

@@ -1,12 +1,59 @@
+# Dependabot configuration
+#
+# Grouping behavior (see inline comments for details):
+#   - Minor + patch updates: grouped into a single PR per ecosystem
+#   - Major version bumps: individual PR per dependency
+#   - Security updates: individual PR per dependency
+#
+# Note: "patch" refers to semver version bumps (1.2.3 -> 1.2.4), not security fixes.
+# Security updates are identified separately via GitHub's Advisory Database and
+# can be any version bump (patch, minor, or major) that fixes a known CVE.
+
 version: 2
+
 updates:
+
   - package-ecosystem: gomod
     directory: "/"
+    cooldown:
+      default-days: 7
     schedule:
-      interval: "daily"
+      interval: "weekly"
+      day: "friday"
     open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+    ignore:
+      - dependency-name: "github.com/aquasecurity/go-pep440-version"
+      - dependency-name: "github.com/aquasecurity/go-version"
+      - dependency-name: "github.com/knqyf263/go-apk-version"
+      - dependency-name: "github.com/knqyf263/go-deb-version"
+    groups:
+      go-minor-patch:
+        applies-to: version-updates  # security updates get individual PRs
+        patterns:
+          - "*"
+        update-types:  # major omitted, gets individual PRs
+          - "minor"
+          - "patch"
+
   - package-ecosystem: "github-actions"
-    directory: "/"
+    directories:
+      - "/"
+      - "/.github/actions/bootstrap"
+    cooldown:
+      default-days: 7
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
+      interval: "weekly"
+      day: "friday"
+    open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+    groups:
+      actions-minor-patch:
+        applies-to: version-updates  # security updates get individual PRs
+        patterns:
+          - "*"
+        update-types:  # major omitted, gets individual PRs
+          - "minor"
+          - "patch"

.github/pull_request_template.md

@@ -0,0 +1,28 @@
+## Description
+
+<!-- Please include a summary of the changes along with any relevant motivation and context -->
+
+<!-- If CLI output changed, show an example (before/after if helpful) -->
+
+<!-- If this changes application or API configuration, describe new/changed/removed options -->
+
+## 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
+
+## Issue references
+
+<!-- If this fixes an issue, include "Fixes #<issue-number>" or otherwise list the issue references -->

.github/scripts/capability-drift-check.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+set -u
+
+if [ "$(git status --porcelain | wc -l)" -ne "0" ]; then
+  echo "  🔴 there are uncommitted changes, please commit them before running this check"
+  exit 1
+fi
+
+if ! make generate-capabilities REFRESH=false; then
+  echo "Generating capability descriptions failed"
+  exit 1
+fi
+
+if [ "$(git status --porcelain | wc -l)" -ne "0" ]; then
+  echo "  🔴 there is drift in capability descriptions! Please run 'make generate-capabilities' and commit the changes."
+  exit 1
+fi

.github/scripts/check_binary_fixture_size.sh

@@ -24,7 +24,7 @@ while IFS= read -r -d '' file; do
     echo "File $file is greater than ${size} bytes."
     found_large_files=1
   fi
-done < <(find "$directory" -type f -print0)
+done < <(git ls-files -z "$directory")
 
 if [ "$found_large_files" -eq 1 ]; then
   echo "Script failed: Some files are greater than ${size} bytes."

.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 'testdata' and at least one 'image-*' directory."""
+    for root, dirs, files in os.walk(base_dir):
+        if 'testdata' 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/json-schema-drift-check.sh

@@ -12,6 +12,6 @@ if ! make generate-json-schema; then
 fi
 
 if [ "$(git status --porcelain | wc -l)" -ne "0" ]; then
-  echo "  🔴 there are uncommitted changes, please commit them before running this check"
+  echo "  🔴 there is drift in json schema! Please run 'make generate-json-schema' and commit the changes."
   exit 1
 fi

.github/scripts/labeler.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 from __future__ import annotations
 
 import sys
@@ -56,6 +58,8 @@ def main(changed_files: str | None = None, merge_base_schema_files: str | None =
 
     pr_json_schema_files = filter_to_schema_files(pr_changed_files)
 
+    pr_labels = get_pr_labels(pr_number)
+
     # print("schema files in pr:   ", summarize_schema_files(pr_json_schema_files))
     # print("og schema files:      ", summarize_schema_files(og_json_schema_files))
 
@@ -76,7 +80,8 @@ def main(changed_files: str | None = None, merge_base_schema_files: str | None =
         add_label(pr_number, JSON_SCHEMA_LABEL)
 
     else:
-        remove_label(pr_number, JSON_SCHEMA_LABEL)
+        if JSON_SCHEMA_LABEL in pr_labels:
+            remove_label(pr_number, JSON_SCHEMA_LABEL)
 
     # new schema files should be scrutinized, comparing the latest and added versions to see if it's a breaking
     # change (major version bump). Warn about it on the PR via adding a breaking-change label...
@@ -84,7 +89,8 @@ def main(changed_files: str | None = None, merge_base_schema_files: str | None =
         print("\nBreaking change detected...")
         add_label(pr_number, BREAKING_CHANGE_LABEL)
     else:
-        remove_label(pr_number, BREAKING_CHANGE_LABEL)
+        if BREAKING_CHANGE_LABEL in pr_labels:        
+            remove_label(pr_number, BREAKING_CHANGE_LABEL)
 
     # modifying an existing schema could be a breaking change, we should warn about it on the PR via a comment...
     # removing schema files should never be allowed, we should warn about it on the PR via a comment...
@@ -119,7 +125,7 @@ def add_label(pr_number: str, label: str):
     # run "gh pr edit --add-label <label>"
     result = run(f"gh pr edit {pr_number} --add-label {label}", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     if result.returncode != 0:
-        print(f"Unable to add  {label!r} label to PR with")
+        print(f"Unable to add '{label!r}' label to PR, error:")
         print(str(result.stderr))
         sys.exit(1)
 
@@ -128,7 +134,7 @@ def remove_label(pr_number: str, label: str):
     # run "gh pr edit --remove-label <label>"
     result = run(f"gh pr edit {pr_number} --remove-label {label}", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     if result.returncode != 0:
-        print(f"Unable to label PR with {label!r}")
+        print(f"Unable to remove '{label!r}' label from PR, error:")
         print(str(result.stderr))
         sys.exit(1)
 
@@ -165,6 +171,17 @@ def get_pr_changed_files(pr_number: str) -> list[str]:
     return list_of_files
 
 
+def get_pr_labels(pr_number: str) -> list[str]:
+    result = run(f"gh pr view {pr_number} --json labels --jq '.labels[].name'", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+    if result.returncode != 0:
+        print("Unable to get list of labels on PR")
+        print(str(result.stderr))
+        sys.exit(1)
+    
+    list_of_labels = result.stdout.splitlines()
+    return list_of_labels
+
+
 def filter_to_schema_files(list_of_files: list[str]) -> list[str]:
     # get files matching "schema/json/schema-*.json"
     files = []
@@ -176,7 +193,8 @@ def filter_to_schema_files(list_of_files: list[str]) -> list[str]:
 
 def list_json_schema_files() -> list[str]:
     # list files in "schema/json" directory matching the pattern of "schema-*.json"
-    return sort_json_schema_files(list(glob.glob("schema/json/schema-*.json")))
+    # special case: always ignore the "latest" schema file
+    return sort_json_schema_files([f for f in glob.glob("schema/json/schema-*.json") if "latest" not in f])
 
 
 def run(command: str,  **kwargs) -> subprocess.CompletedProcess:
@@ -197,7 +215,7 @@ def sort_json_schema_files(files: list[str]) -> list[str]:
     # so that "schema/json/schema-1.2.1.json" comes before "schema/json/schema-1.12.1.json".
     versions = [get_semver(file) for file in files if file]
     
-    versions = sorted(versions, key=lambda s: [int(u) for u in s.split('.')])
+    versions = sorted(versions, key=lambda s: [int(u) for u in s.split('.') if "." in s])
 
     return [f"schema/json/schema-{version}.json" for version in versions]
 

.github/scripts/labeler_test.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 import unittest
 from unittest.mock import patch
 import subprocess
@@ -60,6 +62,11 @@ class Labeler(unittest.TestCase):
         expected_sorted_files = ["schema/json/schema-1.2.1.json", "schema/json/schema-1.12.1.json"]
         self.assertEqual(labeler.sort_json_schema_files(files), expected_sorted_files)
 
+        # ensure that "latest" doesn't cause a problem and is ultimately ignored
+        files = ["schema/json/schema-1.12.1.json", "schema/json/schema-_bogus.json"]
+        expected_sorted_files = ["schema/json/schema-_bogus.json", "schema/json/schema-1.12.1.json"]
+        self.assertEqual(labeler.sort_json_schema_files(files), expected_sorted_files)
+
 
 if __name__ == "__main__":
     unittest.main()

.github/scripts/trigger-release.sh

@@ -4,12 +4,19 @@ set -eu
 bold=$(tput bold)
 normal=$(tput sgr0)
 
-if ! [ -x "$(command -v gh)" ]; then
-    echo "The GitHub CLI could not be found. To continue follow the instructions at https://github.com/cli/cli#installation"
+GH_CLI=.tool/gh
+
+if ! [ -x "$(command -v $GH_CLI)" ]; then
+    echo "The GitHub CLI could not be found. run: make bootstrap"
     exit 1
 fi
 
-gh auth status
+$GH_CLI auth status
+
+# set the default repo in cases where multiple remotes are defined
+$GH_CLI repo set-default anchore/syft
+
+export GITHUB_TOKEN="${GITHUB_TOKEN-"$($GH_CLI auth token)"}"
 
 # we need all of the git state to determine the next version. Since tagging is done by
 # the release pipeline it is possible to not have all of the tags from previous releases.
@@ -37,7 +44,7 @@ done
 
 echo "${bold}Kicking off release for ${NEXT_VERSION}${normal}..."
 echo
-gh workflow run release.yaml -f version=${NEXT_VERSION}
+$GH_CLI workflow run release.yaml -f version=${NEXT_VERSION}
 
 echo
 echo "${bold}Waiting for release to start...${normal}"
@@ -45,6 +52,6 @@ sleep 10
 
 set +e
 
-echo "${bold}Head to the release workflow to monitor the release:${normal} $(gh run list --workflow=release.yaml --limit=1 --json url --jq '.[].url')"
-id=$(gh run list --workflow=release.yaml --limit=1 --json databaseId --jq '.[].databaseId')
-gh run watch $id --exit-status || (echo ; echo "${bold}Logs of failed step:${normal}" && GH_PAGER="" gh run view $id --log-failed)
+echo "${bold}Head to the release workflow to monitor the release:${normal} $($GH_CLI run list --workflow=release.yaml --limit=1 --json url --jq '.[].url')"
+id=$($GH_CLI run list --workflow=release.yaml --limit=1 --json databaseId --jq '.[].databaseId')
+$GH_CLI run watch $id --exit-status || (echo ; echo "${bold}Logs of failed step:${normal}" && GH_PAGER="" $GH_CLI run view $id --log-failed)

.github/scripts/update-version-file.sh

@@ -1,23 +0,0 @@
-#!/usr/bin/env bash
-set -ue
-
-BIN="syft"
-DISTDIR=$1
-VERSION=$2
-
-# the source of truth as to whether we want to notify users of an update is if the release just created is NOT
-# flagged as a pre-release on github
-if [[ "$(curl -SsL https://api.github.com/repos/anchore/${BIN}/releases/tags/${VERSION} | jq .prerelease)" == "true" ]] ; then
-   echo "skipping publishing a version file (this is a pre-release: ${VERSION})"
-   exit 0
-fi
-
-echo "creating and publishing version file"
-
-# create a version file for version-update checks
-VERSION_FILE="${DISTDIR}/VERSION"
-echo "${VERSION}" | tee "${VERSION_FILE}"
-
-# upload the version file that supports the application version update check
-export AWS_DEFAULT_REGION=us-west-2
-aws s3 cp "${VERSION_FILE}" s3://toolbox-data.anchore.io/${BIN}/releases/latest/VERSION

.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@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - name: Restore base benchmark result
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: test/results/benchmark-main.txt
-          # use base sha for PR or new commit hash for main push in benchmark result key
-          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@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
-        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

@@ -20,8 +20,8 @@ permissions:
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-latest
-
+    runs-on: ubuntu-22.04-4core-16gb
+    if: github.repository == 'anchore/syft' # only run for main repo
     permissions:
       security-events: write
 
@@ -36,16 +36,19 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      with:
+        persist-credentials: false
 
     - name: Install Go
-      uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
+      uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 #v6.3.0
       with:
         go-version-file: go.mod
+        check-latest: true
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@b7bf0a3ed3ecfa44160715d7c442788f65f0f923 #v3.23.2
+      uses: github/codeql-action/init@0d579ffd059c29b07949a3cce3983f0780820c98 # v4.32.6
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -56,7 +59,7 @@ 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@b7bf0a3ed3ecfa44160715d7c442788f65f0f923 #v3.23.2
+      uses: github/codeql-action/autobuild@0d579ffd059c29b07949a3cce3983f0780820c98 # v4.32.6
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -70,4 +73,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@b7bf0a3ed3ecfa44160715d7c442788f65f0f923 #v3.23.2
+      uses: github/codeql-action/analyze@0d579ffd059c29b07949a3cce3983f0780820c98 # v4.32.6

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

@@ -28,9 +28,17 @@ jobs:
   label:
     name: "Label changes"
     runs-on: ubuntu-22.04
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
     steps:
 
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
+          repository: anchore/syft # IMPORTANT! An additional protection that this is checking out code from the expected repository 
+          ref: main # IMPORTANT!  It is CRITICAL that this only ever considers the code from main and NEVER EVER from a fork.
 
       - run: python .github/scripts/labeler.py
         env:
@@ -40,7 +48,7 @@ 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@773744901bac0e8cbb5a0dc842800d45e9b2b405 #v2.9.4
         with:
           header: ${{ env.COMMENT_HEADER }}
           hide: true
@@ -48,7 +56,7 @@ 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@773744901bac0e8cbb5a0dc842800d45e9b2b405 #v2.9.4
         with:
           header: ${{ env.COMMENT_HEADER }}
           path: ${{ env.CI_COMMENT_FILE }}

.github/workflows/release-homebrew.yaml

@@ -1,48 +0,0 @@
-name: "Release Homebrew"
-
-on:
-  workflow_dispatch:
-  release:
-    types:
-      - released
-
-jobs:
-  homebrew:
-    runs-on: ubuntu-20.04
-    steps:
-
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
-        with:
-          # we need to be able to get the commit for a tag
-          fetch-depth: 0
-
-      - name: Get release info
-        id: release_info
-        run: |
-          echo -n "tag_name=$(gh release view --json tagName --jq '.tagName')" | tee -a $GITHUB_OUTPUT
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Get commit info
-        id: git_info
-        run: |
-          git checkout ${{ steps.release_info.outputs.tag_name }}
-          echo -n "commit=$(git rev-parse HEAD)" | tee -a $GITHUB_OUTPUT
-
-      - name: Update Homebrew formula
-        uses: dawidd6/action-homebrew-bump-formula@75ed025ff3ad1d617862838b342b06d613a0ddf3 # v3.10.1
-        with:
-          token: ${{ secrets.HOMEBREW_TOKEN }}
-          org: anchore
-          formula: syft
-          tag: ${{ steps.release_info.outputs.tag_name }}
-          revision: ${{ steps.git_info.outputs.commit }}
-
-      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
-        if: ${{ failure() }}
-        with:
-          status: ${{ job.status }}
-          fields: repo,workflow,action,eventName
-          text: "Post-release homebrew publish workflow has failed: https://github.com/anchore/syft/actions/workflows/release-homebrew.yaml"
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}

.github/workflows/release.yaml

@@ -9,22 +9,53 @@ on:
       version:
         description: tag the latest commit on main with the given version (prefixed with v)
         required: true
+      phase:
+        description: the specific workflow phase to run or all
+        required: true
+        default: "all"
+        type: choice
+        options:
+          - "all"
+          - "install-script-only"
 
 jobs:
   quality-gate:
     environment: release
-    runs-on: ubuntu-20.04
+    if: ${{ github.event.inputs.phase == 'all' }}
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - name: Validate Apple notarization credentials
+        run: .tool/quill submission list
+        env:
+          QUILL_NOTARY_ISSUER: ${{ secrets.APPLE_NOTARY_ISSUER }}
+          QUILL_NOTARY_KEY_ID: ${{ secrets.APPLE_NOTARY_KEY_ID }}
+          QUILL_NOTARY_KEY: ${{ secrets.APPLE_NOTARY_KEY }}
+
+      - name: Check if running on main
+        if: github.ref != 'refs/heads/main'
+        # we are using the following flag when running `cosign blob-verify` for checksum signature verification:
+        #   --certificate-identity-regexp "https://github.com/anchore/.github/workflows/release.yaml@refs/heads/main"
+        # if we are not on the main branch, the signature will not be verifiable since the suffix requires the main branch
+        # at the time of when the OIDC token was issued on the Github Actions runner.
+        run: echo "This can only be run on the main branch otherwise releases produced will not be verifiable with cosign" && exit 1
 
       - name: Check if tag already exists
         # note: this will fail if the tag already exists
         run: |
-          [[ "${{ github.event.inputs.version }}" == v* ]] || (echo "version '${{ github.event.inputs.version }}' does not have a 'v' prefix" && exit 1)
-          git tag ${{ github.event.inputs.version }}
+          [[ "$VERSION" == v* ]] || (echo "version '$VERSION' does not have a 'v' prefix" && exit 1)
+          git tag "$VERSION"
+        env:
+          VERSION: ${{ github.event.inputs.version }}
 
       - name: Check static analysis results
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: static-analysis
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -33,7 +64,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Check unit test results
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: unit
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -42,7 +73,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Check integration test results
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: integration
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -51,7 +82,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Check acceptance test results (linux)
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: acceptance-linux
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -60,7 +91,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Check acceptance test results (mac)
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: acceptance-mac
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -69,7 +100,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Check cli test results (linux)
-        uses: fountainhead/action-wait-for-check@297be350cf8393728ea4d4b39435c7d7ae167c93 # v1.1.0
+        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
         id: cli-linux
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
@@ -79,39 +110,53 @@ jobs:
 
       - name: Quality gate
         if: steps.static-analysis.outputs.conclusion != 'success' || steps.unit.outputs.conclusion != 'success' || steps.integration.outputs.conclusion != 'success' || steps.cli-linux.outputs.conclusion != 'success' || steps.acceptance-linux.outputs.conclusion != 'success' || steps.acceptance-mac.outputs.conclusion != 'success'
+        env:
+          STATIC_ANALYSIS_STATUS: ${{ steps.static-analysis.conclusion }}
+          UNIT_TEST_STATUS: ${{ steps.unit.outputs.conclusion }}
+          INTEGRATION_TEST_STATUS: ${{ steps.integration.outputs.conclusion }}
+          ACCEPTANCE_LINUX_STATUS: ${{ steps.acceptance-linux.outputs.conclusion }}
+          ACCEPTANCE_MAC_STATUS: ${{ steps.acceptance-mac.outputs.conclusion }}
+          CLI_LINUX_STATUS: ${{ steps.cli-linux.outputs.conclusion }}
         run: |
-          echo "Static Analysis Status: ${{ steps.static-analysis.conclusion }}"
-          echo "Unit Test Status: ${{ steps.unit.outputs.conclusion }}"
-          echo "Integration Test Status: ${{ steps.integration.outputs.conclusion }}"
-          echo "Acceptance Test (Linux) Status: ${{ steps.acceptance-linux.outputs.conclusion }}"
-          echo "Acceptance Test (Mac) Status: ${{ steps.acceptance-mac.outputs.conclusion }}"
-          echo "CLI Test (Linux) Status: ${{ steps.cli-linux.outputs.conclusion }}"
+          echo "Static Analysis Status: $STATIC_ANALYSIS_STATUS"
+          echo "Unit Test Status: $UNIT_TEST_STATUS"
+          echo "Integration Test Status: $INTEGRATION_TEST_STATUS"
+          echo "Acceptance Test (Linux) Status: $ACCEPTANCE_LINUX_STATUS"
+          echo "Acceptance Test (Mac) Status: $ACCEPTANCE_MAC_STATUS"
+          echo "CLI Test (Linux) Status: $CLI_LINUX_STATUS"
           false
 
   release:
-    needs: [quality-gate]
-    runs-on: ubuntu-20.04
+    needs: [ quality-gate ]
+    if: ${{ github.event.inputs.phase == 'all' }}
+    # runs-on.com: compute instances for parallel builds
+    #   spot disabled: reliability for build workflows (used for releases too)
+    #   goreleaser uses parallelism of 12, so we need more CPUs
+    #   s3-cache: faster actions cache
+    #   tmpfs: faster io-intensive workflows
+    runs-on: runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/extras=s3-cache+tmpfs
     permissions:
       contents: write
       packages: write
       # required for goreleaser signs section with cosign
       id-token: write
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
         with:
           fetch-depth: 0
+          persist-credentials: true
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
       - name: Login to Docker Hub
-        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d  #v3.0.0
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2  #v4.0.0
         with:
-          username: ${{ secrets.TOOLBOX_DOCKER_USER }}
-          password: ${{ secrets.TOOLBOX_DOCKER_PASS }}
+          username: ${{ secrets.ANCHOREOSSWRITE_DH_USERNAME }}
+          password: ${{ secrets.ANCHOREOSSWRITE_DH_PAT }}
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d  #v3.0.0
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2  #v4.0.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -121,10 +166,11 @@ jobs:
         run: |
           git config --global user.name "anchoreci"
           git config --global user.email "anchoreci@users.noreply.github.com"
-          git tag -a ${{ github.event.inputs.version }} -m "Release ${{ github.event.inputs.version }}"
+          git tag -a "$VERSION" -m "Release $VERSION"
           git push origin --tags
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VERSION: ${{ github.event.inputs.version }}
 
       - name: Build & publish release artifacts
         run: make ci-release
@@ -138,22 +184,45 @@ jobs:
           # for creating the release (requires write access to packages and content)
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           # for updating brew formula in anchore/homebrew-syft
-          GITHUB_BREW_TOKEN: ${{ secrets.ANCHORE_GIT_READ_TOKEN }}
-          # for updating the VERSION file in S3...
-          AWS_ACCESS_KEY_ID: ${{ secrets.TOOLBOX_AWS_ACCESS_KEY_ID }}
-          AWS_SECRET_ACCESS_KEY: ${{ secrets.TOOLBOX_AWS_SECRET_ACCESS_KEY }}
+          GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@b6a39da80722a2cb0ef5d197531764a89b5d48c3 #v0.15.8
+      - uses: anchore/sbom-action@17ae1740179002c89186b61233e0f892c3118b11 #v0.23.0
         continue-on-error: true
         with:
+          file: go.mod
           artifact-name: sbom.spdx.json
 
-      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
+      - name: Notify Slack of new release
+        uses: slackapi/slack-github-action@91efab103c0de0a537f72a35f6b8cda0ee76bf0a #v2.1.1
         continue-on-error: true
         with:
-          status: ${{ job.status }}
-          fields: repo,workflow,action,eventName
-          text: "A new Syft release has been published: https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}"
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
+          webhook: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
+          webhook-type: incoming-webhook
+          payload: |
+            text: "A new Syft release has been published: https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}"
+            blocks:
+              - type: section
+                text:
+                  type: mrkdwn
+                  text: |
+                    *A new Syft release has been published* :rocket:
+                    • Release: <https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}|${{ github.event.inputs.version }}>
+                    • Repo: `${{ github.repository }}`
+                    • Workflow: `${{ github.workflow }}`
+                    • Event: `${{ github.event_name }}`
         if: ${{ success() }}
+
+  release-install-script:
+    needs: [ release ]
+    if: ${{ always() && (needs.release.result == 'success' || github.event.inputs.phase == 'install-script-only') }}
+    uses: "anchore/workflows/.github/workflows/release-install-script.yaml@main"
+    with:
+      tag: ${{ github.event.inputs.version }}
+    secrets:
+      # needed for r2...
+      R2_INSTALL_ACCESS_KEY_ID: ${{ secrets.OSS_R2_INSTALL_ACCESS_KEY_ID }}
+      R2_INSTALL_SECRET_ACCESS_KEY: ${{ secrets.OSS_R2_INSTALL_SECRET_ACCESS_KEY }}
+      R2_ENDPOINT: ${{ secrets.TOOLBOX_CLOUDFLARE_R2_ENDPOINT }}
+      # needed for s3...
+      S3_INSTALL_AWS_ACCESS_KEY_ID: ${{ secrets.TOOLBOX_AWS_ACCESS_KEY_ID }}
+      S3_INSTALL_AWS_SECRET_ACCESS_KEY: ${{ secrets.TOOLBOX_AWS_SECRET_ACCESS_KEY }}

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

@@ -0,0 +1,15 @@
+name: "Manage Awaiting Response Label"
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  run:
+    permissions:
+      contents: read
+      issues: write
+      pull-requests: write
+    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 +1,48 @@
+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"
+    # runs-on.com: general purpose instances for building test fixture cache
+    #   spot disabled: can run up to an hour, avoid interruptions
+    #   s3-cache: faster actions cache
+    #   family: note that m*d instances have local nvme storage which is beneficial for building large test fixture images
+    runs-on: "runs-on=${{ github.run_id }}/cpu=8+16/ram=32+64/family=m5d+m5ad+m5dn+m6gd+m6id+m6idn+m7gd+m8gd/spot=false/extras=s3-cache"
+    if: github.repository == 'anchore/syft' # only run for main repo
+    permissions:
+      packages: write
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          # we want to rebuild the cache with no previous state
+          download-test-fixture-cache: false
+
+      - name: Run all tests
+        run: |
+          make test
+        env:
+          # we want to rebuild the cache with no previous state
+          DOWNLOAD_TEST_FIXTURE_CACHE: "false"
+
+      - name: Login to GitHub Container Registry (ORAS)
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | .tool/oras login ghcr.io -u "$ACTOR" --password-stdin
+        env:
+          ACTOR: ${{ github.actor }}
+
+      - name: Publish test fixture cache
+        run: make upload-test-fixture-cache

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

@@ -1,66 +0,0 @@
-name: PR for latest versions of tools
-on:
-  schedule:
-    - cron: "0 8 * * *" # 3 AM EST
-
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  update-bootstrap-tools:
-    runs-on: ubuntu-latest
-    if: github.repository == 'anchore/syft' # only run for main repo
-    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-        with:
-          bootstrap-apt-packages: ""
-          compute-fingerprints: "false"
-          go-dependencies: false
-
-      - name: "Update tool versions"
-        id: latest-versions
-        run: |
-          make update-tools
-          make list-tools
-          
-          export NO_COLOR=1
-          delimiter="$(openssl rand -hex 8)"
-          
-          {
-            echo "status<<${delimiter}"
-            make list-tool-updates
-            echo "${delimiter}"
-          } >> $GITHUB_OUTPUT
-          
-          {
-            echo "### Tool version status"
-            echo "\`\`\`"
-            make list-tool-updates
-            echo "\`\`\`"
-          } >> $GITHUB_STEP_SUMMARY
-
-      - 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@b1ddad2c994a25fbc81a28b3ec0e368bb2021c50 #v6.0.0
-        with:
-          signoff: true
-          delete-branch: true
-          branch: auto/latest-tools
-          labels: dependencies
-          commit-message: 'chore(deps): update tools to latest versions'
-          title: 'chore(deps): update tools to latest versions'
-          body: |
-            ```
-            ${{ steps.latest-versions.outputs.status }}
-            ```
-            This is an auto-generated pull request to update all of the tools to the latest versions.
-          token: ${{ steps.generate-token.outputs.token }}

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

@@ -1,55 +0,0 @@
-name: PR to update CPE dictionary index
-on:
-  schedule:
-    - cron: "0 1 * * 1" # every monday at 1 AM
-
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-env:
-  SLACK_NOTIFICATIONS: true
-
-jobs:
-  upgrade-cpe-dictionary-index:
-    runs-on: ubuntu-latest
-    if: github.repository == 'anchore/syft' # only run for main repo
-    steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - run: |
-          make generate-cpe-dictionary-index
-
-      - 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@b1ddad2c994a25fbc81a28b3ec0e368bb2021c50 #v6.0.0
-        with:
-          signoff: true
-          delete-branch: true
-          branch: auto/latest-cpe-dictionary-index
-          labels: dependencies
-          commit-message: "chore(deps): update CPE dictionary index"
-          title: "chore(deps): update CPE dictionary index"
-          body: |
-            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
-        with:
-          status: ${{ job.status }}
-          fields: workflow,eventName,job
-          text: Syft CPE dictionary index update failed
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
-        if: ${{ failure() && env.SLACK_NOTIFICATIONS == 'true' }}

.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@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
-
-      - uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
-        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@b1ddad2c994a25fbc81a28b3ec0e368bb2021c50 #v6.0.0
-        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/validate-github-actions.yaml

@@ -0,0 +1,36 @@
+name: "Validate GitHub Actions"
+
+on:
+  pull_request:
+    paths:
+      - '.github/workflows/**'
+      - '.github/actions/**'
+  push:
+    branches:
+      - main
+    paths:
+      - '.github/workflows/**'
+      - '.github/actions/**'
+
+permissions:
+  contents: read
+
+jobs:
+  zizmor:
+    name: "Lint"
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      security-events: write  # for uploading SARIF results
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: "Run zizmor"
+        uses: zizmorcore/zizmor-action@0dce2577a4760a2749d8cfb7a84b7d5585ebcb7d # v0.5.0
+        with:
+          config: .github/zizmor.yml
+          # Disable SARIF upload so the step is a simple pass/fail gate
+          advanced-security: false
+          inputs: .github

.github/workflows/validations.yaml

@@ -1,5 +1,11 @@
 name: "Validations"
 
+# we should cancel any in-progress runs for the same workflow + PR/ref
+# so that we can avoid redundant work / save on CI minutes
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 on:
   workflow_dispatch:
   pull_request:
@@ -8,96 +14,88 @@ on:
       - main
 
 permissions:
-    contents: read
+  contents: read
 
 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.com: memory & general purpose instances for testing
+    #   spot enabled: ok to interrupt non-production workloads
+    #   s3-cache: faster actions cache
+    #   tmpfs: faster io-intensive workflows
+    runs-on: &test-runner "runs-on=${{ github.run_id }}/cpu=4+8/ram=32+128/family=r5+r6+r7+r8+m4+m5+m6+m7+m8/spot=price-capacity-optimized/extras=s3-cache+tmpfs"
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        with:
+          # the self-consistency tests for the output of the capabilities code generation depends on unit test
+          # output from  ./syft/pkg/... packages. Therefore we need to download the test fixture cache here
+          # so that running the few unit tests as part of static analysis works correctly.
+          download-test-fixture-cache: true
 
       - name: Run static analysis
         run: make static-analysis
 
-
   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
+    runs-on: *test-runner
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore Java test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
-          path: syft/pkg/cataloger/java/test-fixtures/java-builds/packages
-          key: ${{ runner.os }}-unit-java-cache-${{ hashFiles( 'syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint' ) }}
-
-      - name: Restore RPM test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: syft/pkg/cataloger/redhat/test-fixtures/rpms
-          key: ${{ runner.os }}-unit-rpm-cache-${{ hashFiles( 'syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint' ) }}
-
-      - name: Restore go binary test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: syft/pkg/cataloger/golang/test-fixtures/archs/binaries
-          key: ${{ runner.os }}-unit-go-binaries-cache-${{ hashFiles( 'syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint' ) }}
-
-      - name: Restore binary cataloger test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/bin
-          key: ${{ runner.os }}-unit-binary-cataloger-cache-${{ hashFiles( 'syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint' ) }}
-
-      - name: Restore Kernel test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: syft/pkg/cataloger/kernel/test-fixtures/cache
-          key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
+          download-test-fixture-cache: true
 
       - name: Run unit tests
         run: make unit
 
+      - name: Check for capability drift
+        run: make check-capability-drift
 
   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: *test-runner
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - 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@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        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.com: compute instances for parallel builds
+    #   spot disabled: reliability for build workflows (used for releases too)
+    #   goreleaser uses parallelism of 12, so we need more CPUs
+    #   s3-cache: faster actions cache
+    #   tmpfs: faster io-intensive workflows
+    runs-on: "runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/extras=s3-cache+tmpfs"
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -107,56 +105,46 @@ jobs:
       - name: Build snapshot artifacts
         run: make snapshot
 
-      # 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@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          # we need to preserve the snapshot data itself as well as the task data that confirms if the
-          # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
-          # even though it already exists.
-          path: |
-            snapshot
-            .task
-          key: snapshot-build-${{ github.run_id }}
+      - name: Smoke test snapshot build
+        run: make snapshot-smoke-test
 
+      - name: Upload snapshot artifacts
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f #v7.0.0
+        with:
+          name: snapshot
+          path: snapshot/
+          retention-days: 30
 
   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: *test-runner
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          download-test-fixture-cache: true
 
-      # 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
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 #v8.0.0
+        with:
+          name: snapshot
+          path: snapshot
+
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft snapshot/*/*.exe 2>/dev/null || true
 
       - name: Run comparison tests (Linux)
         run: make compare-linux
 
-      - name: Restore install.sh test image cache
-        id: install-test-image-cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: ${{ github.workspace }}/test/install/cache
-          key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
-
       - name: Load test image cache
         if: steps.install-test-image-cache.outputs.cache-hit == 'true'
         run: make install-test-cache-load
@@ -168,44 +156,35 @@ jobs:
         if: steps.install-test-image-cache.outputs.cache-hit != 'true'
         run: make install-test-cache-save
 
-
   Acceptance-Mac:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Acceptance tests (Mac)"
     needs: [Build-Snapshot-Artifacts]
+    # note: macos runners aren't supported yet for runs-on managed runners.
     runs-on: macos-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - name: Install Cosign
+        uses: sigstore/cosign-installer@faadad0cce49287aee09b3a48701e75088a2c6ad # v4.0.0
+
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
         with:
           bootstrap-apt-packages: ""
-          compute-fingerprints: "false"
           go-dependencies: false
-          go-version: ""
+          download-test-fixture-cache: true
 
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 #v8.0.0
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          name: snapshot
+          path: snapshot
 
-      # 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
-
-      - name: Restore docker image cache for compare testing
-        id: mac-compare-testing-cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
-        with:
-          path: image.tar
-          key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft 2>/dev/null || true
 
       - name: Run comparison tests (Mac)
         run: make compare-mac
@@ -213,38 +192,32 @@ jobs:
       - name: Run install.sh tests (Mac)
         run: make install-test-ci-mac
 
-
   Cli-Linux:
     # 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: *test-runner
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore CLI test-fixture cache
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
         with:
-          path: ${{ github.workspace }}/test/cli/test-fixtures/cache
-          key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}
+          download-test-fixture-cache: true
 
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 #v4.0.0
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 #v8.0.0
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          name: snapshot
+          path: snapshot
 
-      # 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
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft snapshot/*/*.exe 2>/dev/null || true
 
       - name: Run CLI Tests (Linux)
         run: make cli

.github/zizmor.yml

@@ -0,0 +1,11 @@
+rules:
+  unpinned-uses:
+    config:
+      policies:
+        # anchore/workflows is an internal repository; using @main is acceptable
+        anchore/*: any
+  dangerous-triggers:
+    ignore:
+      # Safe use of pull_request_target - only runs trusted scripts from base repo,
+      # never checks out PR code, needs secrets for labeling PRs from forks
+      - detect-schema-changes.yaml

.gitignore

@@ -2,6 +2,7 @@
 go.work
 go.work.sum
 .tool-versions
+.python-version
 
 # app configuration
 /.syft.yaml
@@ -16,6 +17,9 @@ bin/
 /snapshot
 /.tool
 /.task
+/generate
+/specs
+mise.toml
 
 # changelog generation
 CHANGELOG.md
@@ -32,6 +36,8 @@ VERSION
 /test/results
 coverage.txt
 *.log
+**/test-fixtures/test-observations.json
+**/testdata/test-observations.json
 
 # probable archives
 .images
@@ -70,3 +76,5 @@ cosign.pub
 __pycache__/
 *.py[cod]
 *$py.class
+
+

.golangci.yaml

@@ -1,58 +1,63 @@
-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
-output:
-  uniq-by-line: false
-run:
-  timeout: 10m
+  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
+    rules:
+      # we have multiple packages in syft that might overlap with the stblib; their names reflect their purpose
+      - linters:
+          - revive
+        text: "var-naming: avoid package names that conflict"
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
 
 # do not enable...
 #    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
@@ -72,7 +77,6 @@ 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
@@ -80,3 +84,23 @@ 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

@@ -1,9 +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
 
@@ -11,14 +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
@@ -32,11 +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:
@@ -48,115 +41,43 @@ builds:
   - id: windows-build
     dir: ./cmd/syft
     binary: syft
-    goos:
-      - windows
-    goarch:
-      - amd64
+    goos: [windows]
+    goarch: [amd64, arm64]
     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
+    ids: [linux-build]
   - id: darwin-archives
-    builds:
-      - darwin-build
-
+    ids: [darwin-build]
   - id: windows-archives
-    format: zip
-    builds:
-      - windows-build
+    formats:
+      - zip
+    ids: [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:
-  - tap:
+  - 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
@@ -206,51 +127,201 @@ 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"
@@ -266,6 +337,7 @@ signs:
     certificate: "${artifact}.pem"
     args:
       - "sign-blob"
+      - "--use-signing-config=false"
       - "--oidc-issuer=https://token.actions.githubusercontent.com"
       - "--output-certificate=${certificate}"
       - "--output-signature=${signature}"

CODE_OF_CONDUCT.md

@@ -0,0 +1,5 @@
+# Code of Conduct
+
+All contributors for any Anchore project must follow the [Contributor Covenant Code of Conduct](https://oss.anchore.com/docs/contributing/code-of-conduct/).
+
+**TLDR:** Be kind, be respectful, and assume good intentions. We're all here to build great software together.

CONTRIBUTING.md

@@ -1,154 +1,13 @@
-[#](#) Contributing to Syft
+# Contributing
 
-If you are looking to contribute to this project and want to open a GitHub pull request ("PR"), there are a few guidelines of what we are looking for in patches. Make sure you go through this document and ensure that your code proposal is aligned.
+Thank you for your interest in contributing to Syft!
 
-## Setting up your environment
+Please see the [contribution guide](https://oss.anchore.com/docs/contributing/syft/) for development requirements and helpful tips to get started developing in the repo. For a deeper dive, please see the [architecture docs](https://oss.anchore.com/docs/architecture/syft/).
 
-Before you can contribute to Syft, you need to configure your development environment.
+**Have a question or need help?** Check out our [issues and discussions guide](https://oss.anchore.com/docs/contributing/issues-and-discussions/) to find the right place to start a conversation.
 
-### Debian setup
+**Ready to submit code?** Our [pull request guide](https://oss.anchore.com/docs/contributing/pull-requests/) covers everything from title conventions to the review process. Don't forget that ***all commits require a [sign-off](https://oss.anchore.com/docs/contributing/sign-off/)***.
 
-You will need to install Go. The version on https://go.dev works best, using the system golang doesn't always work the way you might expect.
+**Found a security issue?** Please do **not** open a public issue. Instead, see our [security policy](https://oss.anchore.com/docs/contributing/security/) for how to report vulnerabilities responsibly.
 
-Refer to the go.mod file in the root of this repo for the recommended version of Go to install.
-
-You will also need Docker. There's no reason the system packages shouldn't work, but we used the official Docker package. You can find instructions for installing Docker in Debian [here](https://docs.docker.com/engine/install/debian/).
-
-You also need to install some Debian packages
-
-```sh
-sudo apt-get install build-essential zip bc libxml2-utils git
-```
-
-## Configuring Git
-
-You will need to configure your git client with your name and email address. This is easily done from the command line.
-
-```text
-$ git config --global user.name "John Doe"
-$ git config --global user.email "john.doe@example.com"
-```
-
-This username and email address will matter later in this guide.
-
-## Fork the repo
-
-You should fork the Syft repo using the "Fork" button at the top right of the Syft GitHub [site](https://github.com/anchore/syft/). You will be doing your development in your fork, then submit a pull request to Syft. There are many resources how to use GitHub effectively, we will not cover those here.
-
-## Adding a feature or fix
-
-If you look at the Syft [Issue](https://github.com/anchore/syft/issues) there are plenty of bugs and feature requests. Maybe look at the [good first issue](https://github.com/anchore/syft/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) list if you're not sure where to start.
-
-## Commit guidelines
-
-In the Syft project we like commits and pull requests (PR) to be easy to understand and review. Open source thrives best when everything happening is over documented and small enough to be understood.
-
-### Granular commits
-
-Please try to make every commit as simple as possible, but no simpler. The idea is that each commit should be a logical unit of code. Try not to commit too many tiny changes, for example every line changed in a file as a separate commit. And also try not to make a commit enormous, for example committing all your work at the end of the day.
-
-Rather than try to follow a strict guide on what is or is not best, we try to be flexible and simple in this space. Do what makes the most sense for the changes you are trying to include.
-
-### Commit title and description
-
-Remember that the message you leave for a commit is for the reviewer in the present, and for someone (maybe you) changing something in the future. Please make sure the title and description used is easy to understand and explains what was done. Jokes and clever comments generally don't age well in commit messages. Just the facts please.
-
-## Sign off your work
-
-The `sign-off` is an added line at the end of the explanation for the commit, certifying that you wrote it or otherwise have the right to submit it as an open-source patch. By submitting a contribution, you agree to be bound by the terms of the DCO Version 1.1 and Apache License Version 2.0.
-
-Signing off a commit certifies the below Developer's Certificate of Origin (DCO):
-
-```text
-Developer's Certificate of Origin 1.1
-
-By making a contribution to this project, I certify that:
-
-   (a) The contribution was created in whole or in part by me and I
-       have the right to submit it under the open source license
-       indicated in the file; or
-
-   (b) The contribution is based upon previous work that, to the best
-       of my knowledge, is covered under an appropriate open source
-       license and I have the right under that license to submit that
-       work with modifications, whether created in whole or in part
-       by me, under the same open source license (unless I am
-       permitted to submit under a different license), as indicated
-       in the file; or
-
-   (c) The contribution was provided directly to me by some other
-       person who certified (a), (b) or (c) and I have not modified
-       it.
-
-   (d) I understand and agree that this project and the contribution
-       are public and that a record of the contribution (including all
-       personal information I submit with it, including my sign-off) is
-       maintained indefinitely and may be redistributed consistent with
-       this project or the open source license(s) involved.
-```
-
-All contributions to this project are licensed under the [Apache License Version 2.0, January 2004](http://www.apache.org/licenses/).
-
-When committing your change, you can add the required line manually so that it looks like this:
-
-```text
-Signed-off-by: John Doe <john.doe@example.com>
-```
-
-Creating a signed-off commit is then possible with `-s` or `--signoff`:
-
-```text
-$ git commit -s -m "this is a commit message"
-```
-
-To double-check that the commit was signed-off, look at the log output:
-
-```text
-$ git log -1
-commit 37ceh170e4hb283bb73d958f2036ee5k07e7fde7 (HEAD -> issue-35, origin/main, main)
-Author: John Doe <john.doe@example.com>
-Date:   Mon Aug 1 11:27:13 2020 -0400
-
-    this is a commit message
-
-    Signed-off-by: John Doe <john.doe@example.com>
-```
-
-## Test your changes
-
-This project has a `Makefile` which includes many helpers running both unit and integration tests. You can run `make help` to see all the options. Although PRs will have automatic checks for these, it is useful to run them locally, ensuring they pass before submitting changes. Ensure you've bootstrapped once before running tests:
-
-```text
-$ make bootstrap
-```
-
-You only need to bootstrap once. After the bootstrap process, you can run the tests as many times as needed:
-
-```text
-$ make unit
-$ make integration
-```
-
-You can also run `make all` to run a more extensive test suite, but there is additional configuration that will be needed for those tests to run correctly. We will not cover the extra steps here.
-
-## Pull Request
-
-If you made it this far and all the tests are passing, it's time to submit a Pull Request (PR) for Syft. Submitting a PR is always a scary moment as what happens next can be an unknown. The Syft project strives to be easy to work with, we appreciate all contributions. Nobody is going to yell at you or try to make you feel bad. We love contributions and know how scary that first PR can be.
-
-### PR Title and Description
-
-Just like the commit title and description mentioned above, the PR title and description is very important for letting others know what's happening. Please include any details you think a reviewer will need to more properly review your PR.
-
-A PR that is very large or poorly described has a higher likelihood of being pushed to the end of the list. Reviewers like PRs they can understand and quickly review.
-
-### What to expect next
-
-Please be patient with the project. We try to review PRs in a timely manner, but this is highly dependent on all the other tasks we have going on. It's OK to ask for a status update every week or two, it's not OK to ask for a status update every day.
-
-It's very likely the reviewer will have questions and suggestions for changes to your PR. If your changes don't match the current style and flow of the other code, expect a request to change what you've done.
-
-## Document your changes
-
-And lastly, when proposed changes are modifying user-facing functionality or output, it is expected the PR will include updates to the documentation as well. Syft is not a project that is heavy on documentation. This will mostly be updating the README and help for the tool.
-
-If nobody knows new features exist, they can't use them!
+**Want to help improve the docs?** Check out the [anchore/oss-docs](https://github.com/anchore/oss-docs) repository.

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

@@ -1,382 +0,0 @@
-# Developing
-
-## Getting started
-
-In order to test and develop in this repo you will need the following dependencies installed:
-- Golang
-- docker
-- make
-- Python (>= 3.9)
-
-### Docker settings for getting started
-Make sure you've updated your docker settings so the default docker socket path is available.
-
-Go to:
-
-docker -> settings -> advanced
-
-Make sure:
-
-```
-Allow the default Docker socket to be used
-```
-
-is checked.
-
-Also double check that the docker context being used is the default context. If it is not, run:
-
-`docker context use default`
-
-After cloning the following step can help you get setup:
-1. run `make bootstrap` to download go mod dependencies, create the `/.tmp` dir, and download helper utilities.
-2. run `make` to view the selection of developer commands in the Makefile
-3. run `make build` to build the release snapshot binaries and packages
-4. for an even quicker start you can run `go run cmd/syft/main.go` to print the syft help.
-	- this command `go run cmd/syft/main.go alpine:latest` will compile and run syft against `alpine:latest`
-5. view the README or syft help output for more output options
-
-The main make tasks for common static analysis and testing are `lint`, `format`, `lint-fix`, `unit`, `integration`, and `cli`.
-
-See `make help` for all the current make tasks.
-
-### Internal Artifactory Settings
-
-**Not always applicable**
-
-Some companies have Artifactory setup internally as a solution for sourcing secure dependencies.
-If you're seeing an issue where the unit tests won't run because of the below error then this section might be relevant for your use case.
-
-```
-[ERROR] [ERROR] Some problems were encountered while processing the POMs
-```
-
-If you're dealing with an issue where the unit tests will not pull/build certain java fixtures check some of these settings:
-
-- a `settings.xml` file should be available to help you communicate with your internal artifactory deployment
-- this can be moved to `syft/pkg/cataloger/java/test-fixtures/java-builds/example-jenkins-plugin/` to help build the unit test-fixtures
-- you'll also want to modify the `build-example-jenkins-plugin.sh` to use `settings.xml`
-
-For more information on this setup and troubleshooting see [issue 1895](https://github.com/anchore/syft/issues/1895#issuecomment-1610085319)
-
-
-## Architecture
-
-At a high level, this is the package structure of syft:
-```
-./cmd/syft/
-│   ├── cli/
-│   │   ├── cli.go          // where all commands are wired up
-│   │   ├── commands/       // all command implementations
-│   │   ├── options/        // all command flags and configuration options
-│   │   └── ui/             // all handlers for events that are shown on the UI
-│   └── main.go             // entrypoint for the application
-└── syft/                   // the "core" syft library
-    ├── format/             // contains code to encode or decode to and from SBOM formats
-    ├── pkg/                // contains code to catalog packages from a source
-    ├── sbom/               // contains the definition of an SBOM
-    └── source/             // contains code to create a source object for some input type (e.g. container image, directory, etc)
-```
-
-Syft's core library is implemented in the `syft` package and subpackages, where the major packages are:
-
-- the `syft/source` package produces a `source.Source` object that can be used to catalog a directory, container, and other source types.
-- 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:
-```mermaid
-sequenceDiagram
-    participant main as cmd/syft/main
-    participant cli as cli.New()
-    participant root as root.Execute()
-    participant cmd as <command>.Execute()
-
-    main->>+cli: 
-
-    Note right of cli: wire ALL CLI commands
-    Note right of cli: add flags for ALL commands
-
-    cli-->>-main:  root command 
-
-    main->>+root: 
-    root->>+cmd: 
-    cmd-->>-root: (error)  
-
-    root-->>-main: (error) 
-
-    Note right of cmd: Execute SINGLE command from USER
-```
-
-The `packages` command uses the core library to generate an SBOM for the given user input:
-```mermaid
-sequenceDiagram
-    participant source as source.New(ubuntu:latest)
-    participant sbom as sbom.SBOM
-    participant catalog as syft.CatalogPackages(src)
-    participant encoder as syft.Encode(sbom, format)
-
-    Note right of source: use "ubuntu:latest" as SBOM input
-
-    source-->>+sbom: add source to SBOM struct
-    source-->>+catalog: pass src to generate catalog
-    catalog-->-sbom: add cataloging results onto SBOM
-    sbom-->>encoder: pass SBOM and format desiered to syft encoder
-    encoder-->>source: return bytes that are the SBOM of the original input 
-
-    Note right of catalog: cataloger configuration is done based on src
-```
-
-Additionally, here is a [gist of using syft as a library](https://gist.github.com/spiffcs/3027638b7ba904d07e482a712bc00d3d) to generate a SBOM for a docker image.
-
-
-### `pkg.Package` object
-
-The `pkg.Package` object is a core data structure that represents a software package. Fields like `name` and `version` probably don't need
-a detailed explanation, but some of the other fields are worth a quick overview:
-
-- `FoundBy`: the name of the cataloger that discovered this package (e.g. `python-pip-cataloger`).
-- `Locations`: these are the set of paths and layer ids that were parsed to discover this package (e.g. `python-pip-cataloger`).
-- `Language`: the language of the package (e.g. `python`).
-- `Type`: this is a high-level categorization of the ecosystem the package resides in. For instance, even if the package is a egg, wheel, or requirements.txt reference, it is still logically a "python" package. Not all package types align with a language (e.g. `rpm`) but it is common.
-- `Metadata`: specialized data for specific location(s) parsed. We should try and raise up as much raw information that seems useful. As a rule of thumb the object here should be as flat as possible and use the raw names and values from the underlying source material parsed.
-
-When `pkg.Package` is serialized an additional `MetadataType` is shown. This is a label that helps consumers understand the datashape of the `Metadata` field.
-
-By convention the `MetadataType` value should follow these rules of thumb:
-
-- Only use lowercase letters, numbers, and hyphens. Use hyphens to separate words.
-- **Try to anchor the name in the ecosystem, language, or packaging tooling it belongs to**. For a package manager for a language ecosystem the language, framework or runtime should be used as a prefix. For instance `pubspec-lock` is an OK name, but `dart-pubspec-lock` is better. For an OS package manager this is not necessary (e.g. `apk-db-entry` is a good name, but `alpine-apk-db-entry` is not since `alpine` and the `a` in `apk` is redundant).
-- **Be as specific as possible to what the data represents**. For instance `ruby-gem` is NOT a good `MetadataType` value, but `ruby-gemspec` is. Why? Ruby gem information can come from a gemspec file or a Gemfile.lock, which are very different. The latter name provides more context as to what to expect.
-- **Should describe WHAT the data is, NOT HOW it's used**. For instance `r-description-installed-file` is NOT a good `MetadataType` value since it's trying to convey that we use the DESCRIPTION file in the R ecosystem to detect installed packages. Instead simply describe what the DESCRIPTION file is itself without context of how it's used: `r-description`.
-- **Use the `lock` suffix** to distinct between manifest files that loosely describe package version requirements vs files that strongly specify one and only one version of a package ("lock" files). These should only be used with respect to package managers that have the guide and lock distinction, but would not be appropriate otherwise (e.g. `rpm` does not have a guide vs lock, so `lock` should NOT be used to describe a db entry).
-- **Use the `archive` suffix to indicate a package archive** (e.g. rpm file, apk file, etc) that describes the contents of the package. For example an RPM file that was cataloged would have a `rpm-archive` metadata type (not to be confused with an RPM DB record entry which would be `rpm-db-entry`).
-- **Use the `entry` suffix** to indicate information about a package that was found as a single entry within file that has multiple package entries. If the entry was found within a DB or a flat-file store for an OS package manager, you should use `db-entry`.
-- **Should NOT contain the phrase `package`**, though exceptions are allowed (say if the canonical name literally has the phrase package in it).
-- **Should NOT contain have a `file` suffix** unless the canonical name has the term "file", such as a `pipfile` or `gemfile`. An example of a bad name for this rule is`ruby-gemspec-file`; a better name would be `ruby-gemspec`.
-- **Should NOT contain the exact filename+extensions**. For instance `pipfile.lock` shouldn't really be in the name, instead try and describe what the file is: `python-pipfile-lock` (but shouldn't this be `python-pip-lock` you might ask? No, since the `pip` package manger is not related to the `pipfile` project).
-- **Should NOT contain the phrase `metadata`**, unless the canonical name has this term.
-- **Should represent a single use case**. For example, trying to describe Hackage metadata with a single `HackageMetadata` struct (and thus `MetadataType`) is not allowed since it represents 3 mutually exclusive use cases: representing a `stack.yaml`, `stack.lock`, or `cabal.project` file. Instead, each of these should have their own struct types and `MetadataType` values.
-
-There are other cases that are not covered by these rules... and that's ok! The goal is to provide a consistent naming scheme that is easy to understand and use when it's applicable. If the rules do not exactly apply in your situation then just use your best judgement (or amend these rules as needed whe new common cases come up).
-
-What if the underlying parsed data represents multiple files? There are two approaches to this:
-- use the primary file to represent all the data. For instance, though the `dpkg-cataloger` looks at multiple files to get all information about a package, it's the `status` file that gets represented.
-- nest each individual file's data under the `Metadata` field. For instance, the `java-archive-cataloger` may find information from on or all of the files: `pom.xml`, `pom.properties`, and `MANIFEST.MF`. However, the metadata is simply `java-metadata' with each possibility as a nested optional field.
-
-### Syft Catalogers
-
-Catalogers are the way in which syft is able to identify and construct packages given a set a targeted list of files.
-For example, a cataloger can ask syft for all `package-lock.json` files in order to parse and raise up javascript packages 
-(see [how file globs](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) and
-[file parser functions](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) are used 
-for a quick example).
-
-From a high level catalogers have the following properties:
-
-- _They are independent from one another_. The java cataloger has no idea of the processes, assumptions, or results of the python cataloger, for example.
-
-- _They do not know what source is being analyzed_. Are we analyzing a local directory? an image? if so, the squashed representation or all layers? The catalogers do not know the answers to these questions. Only that there is an interface to query for file paths and contents from an underlying "source" being scanned.
-
-- _Packages created by the cataloger should not be mutated after they are created_. There is one exception made for adding CPEs to a package after the cataloging phase, but that will most likely be moved back into the cataloger in the future.
-
-
-Cataloger names should be unique and named with the following rules of thumb in mind:
-
-- Must end with `-cataloger`
-- Use lowercase letters, numbers, and hyphens only
-- Use hyphens to separate words
-- Catalogers for language ecosystems should start with the language name (e.g. `python-` for a cataloger that raises up python packages)
-- Distinct between when the cataloger is searching for evidence of installed packages vs declared packages. For example, there are currently two different gemspec-based catalogers, the `ruby-gemspec-cataloger` and `ruby-installed-gemspec-cataloger`, where the latter requires that the gemspec is found within a `specifications` directory (which means it was installed, not just at the root of a source repo).
-
-#### Building a new Cataloger
-
-Catalogers must fulfill the [`pkg.Cataloger` interface](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger.go) in order to add packages to the SBOM.
-All catalogers should be added to:
-- the [global list of catalogers](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/cataloger/cataloger.go#L92-L125)
-- at least one source-specific list, today the two lists are [directory catalogers and image catalogers](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/cataloger/cataloger.go#L39-L89)
-
-For reference, catalogers are [invoked within syft](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/catalog.go#L41-L100) one after the other, and can be invoked in parallel.
-
-`generic.NewCataloger` is an abstraction syft used to make writing common components easier (see the [apkdb cataloger](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/cataloger.go) for example usage). 
-It takes the following information as input:
-- A `catalogerName` to identify the cataloger uniquely among all other catalogers.
-- Pairs of file globs as well as parser functions to parse those files. These parser functions return a slice of [`pkg.Package`](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/package.go#L19) as well as a slice of [`artifact.Relationship`](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/artifact/relationship.go#L31) to describe how the returned packages are related. See this [the apkdb cataloger parser function](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102) as an example.
-
-Identified packages share a common `pkg.Package` struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/package.go#L16-L31).
-If you want to return more information than what is available on the `pkg.Package` struct then you can do so in the `pkg.Package.Metadata` section of the struct, which is unique for each [`pkg.Type`](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/type.go).
-See [the `pkg` package](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg) for examples of the different metadata types that are supported today. 
-These are plugged into the `MetadataType` and `Metadata` fields in the above struct. `MetadataType` informs which type is being used. `Metadata` is an interface converted to that type.
-
-Finally, here is an example of where the package construction is done within the apk cataloger:
-- [Calling the APK package constructor from the parser function](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L106)
-- [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)!
-
-
-#### Searching for files
-
-All catalogers are provided an instance of the [`file.Resolver`](https://github.com/anchore/syft/blob/v0.70.0/syft/source/file_resolver.go#L8) to interface with the image and search for files. The implementations for these 
-abstractions leverage [`stereoscope`](https://github.com/anchore/stereoscope) in order to perform searching. Here is a 
-rough outline how that works:
-
-1. a stereoscope `file.Index` is searched based on the input given (a path, glob, or MIME type). The index is relatively fast to search, but requires results to be filtered down to the files that exist in the specific layer(s) of interest. This is done automatically by the `filetree.Searcher` abstraction. This abstraction will fallback to searching directly against the raw `filetree.FileTree` if the index does not contain the file(s) of interest. Note: the `filetree.Searcher` is used by the `file.Resolver` abstraction.
-2. Once the set of files are returned from the `filetree.Searcher` the results are filtered down further to return the most unique file results. For example, you may have requested for files by a glob that returns multiple results. These results are filtered down to deduplicate by real files, so if a result contains two references to the same file, say one accessed via symlink and one accessed via the real path, then the real path reference is returned and the symlink reference is filtered out. If both were accessed by symlink then the first (by lexical order) is returned. This is done automatically by the `file.Resolver` abstraction.
-3. By the time results reach the `pkg.Cataloger` you are guaranteed to have a set of unique files that exist in the layer(s) of interest (relative to what the resolver supports).
-
-## Testing
-
-### Levels of testing
-
-- `unit`: The default level of test which is distributed throughout the repo are unit tests. Any `_test.go` file that 
-  does not reside somewhere within the `/test` directory is a unit test. Other forms of testing should be organized in 
-  the `/test` directory. These tests should focus on correctness of functionality in depth. % test coverage metrics 
-  only considers unit tests and no other forms of testing.
-
-- `integration`: located within `cmd/syft/internal/test/integration`, these tests focus on the behavior surfaced by the common library 
-  entrypoints from the `syft` package and make light assertions about the results surfaced. Additionally, these tests
-  tend to make diversity assertions for enum-like objects, ensuring that as enum values are added to a definition
-  that integration tests will automatically fail if no test attempts to use that enum value. For more details see 
-  the "Data diversity and freshness assertions" section below.
-
-- `cli`: located with in `test/cli`, these are tests that test the correctness of application behavior from a 
-  snapshot build. This should be used in cases where a unit or integration test will not do or if you are looking
-  for in-depth testing of code in the `cmd/` package (such as testing the proper behavior of application configuration,
-  CLI switches, and glue code before syft library calls).
-
-- `acceptance`: located within `test/compare` and `test/install`, these are smoke-like tests that ensure that application  
-  packaging and installation works as expected. For example, during release we provide RPM packages as a download 
-  artifact. We also have an accompanying RPM acceptance test that installs the RPM from a snapshot build and ensures the 
-  output of a syft invocation matches canned expected output. New acceptance tests should be added for each release artifact
-  and architecture supported (when possible).
-
-### Data diversity and freshness assertions
-
-It is important that tests against the codebase are flexible enough to begin failing when they do not cover "enough"
-of the objects under test. "Cover" in this case does not mean that some percentage of the code has been executed 
-during testing, but instead that there is enough diversity of data input reflected in testing relative to the
-definitions available.
-
-For instance, consider an enum-like value like so:
-```go
-type Language string
-
-const (
-  Java            Language = "java"
-  JavaScript      Language = "javascript"
-  Python          Language = "python"
-  Ruby            Language = "ruby"
-  Go              Language = "go"
-)
-```
-
-Say we have a test that exercises all the languages defined today:
-
-```go
-func TestCatalogPackages(t *testing.T) {
-  testTable := []struct {
-    // ... the set of test cases that test all languages
-  }
-  for _, test := range cases {
-    t.Run(test.name, func (t *testing.T) {
-      // use inputFixturePath and assert that syft.CatalogPackages() returns the set of expected Package objects
-      // ...
-    })
-  }
-}
-```
-
-Where each test case has a `inputFixturePath` that would result with packages from each language. This test is
-brittle since it does not assert that all languages were exercised directly and future modifications (such as 
-adding a new language) won't be covered by any test cases.
-
-To address this the enum-like object should have a definition of all objects that can be used in testing:
-
-```go
-type Language string
-
-// const( Java Language = ..., ... )
-
-var AllLanguages = []Language{
-	Java,
-	JavaScript,
-	Python,
-	Ruby,
-	Go,
-	Rust,
-}
-```
-
-Allowing testing to automatically fail when adding a new language:
-
-```go
-func TestCatalogPackages(t *testing.T) {
-  testTable := []struct {
-  	// ... the set of test cases that (hopefully) covers all languages
-  }
-
-  // new stuff...
-  observedLanguages := strset.New()
-  
-  for _, test := range cases {
-    t.Run(test.name, func (t *testing.T) {
-      // use inputFixturePath and assert that syft.CatalogPackages() returns the set of expected Package objects
-    	// ...
-    	
-    	// new stuff...
-    	for _, actualPkg := range actual {
-        observedLanguages.Add(string(actualPkg.Language))
-    	}
-    	
-    })
-  }
-
-   // new stuff...
-  for _, expectedLanguage := range pkg.AllLanguages {
-    if 	!observedLanguages.Contains(expectedLanguage) {
-      t.Errorf("failed to test language=%q", expectedLanguage)	
-    }
-  }
-}
-```
-
-This is a better test since it will fail when someone adds a new language but fails to write a test case that should
-exercise that new language. This method is ideal for integration-level testing, where testing correctness in depth 
-is not needed (that is what unit tests are for) but instead testing in breadth to ensure that units are well integrated.
-
-A similar case can be made for data freshness; if the quality of the results will be diminished if the input data
-is not kept up to date then a test should be written (when possible) to assert any input data is not stale.
-
-An example of this is the static list of licenses that is stored in `internal/spdxlicense` for use by the SPDX 
-presenters. This list is updated and published periodically by an external group and syft can grab and update this
-list by running `go generate ./...` from the root of the repo.
-
-An integration test has been written to grabs the latest license list version externally and compares that version
-with the version generated in the codebase. If they differ, the test fails, indicating to someone that there is an
-action needed to update it.
-
-**_The key takeaway is to try and write tests that fail when data assumptions change and not just when code changes.**_
-
-### Snapshot tests
-
-The format objects make a lot of use of "snapshot" testing, where you save the expected output bytes from a call into the
-git repository and during testing make a comparison of the actual bytes from the subject under test with the golden
-copy saved in the repo. The "golden" files are stored in the `test-fixtures/snapshot` directory relative to the go 
-package under test and should always be updated by invoking `go test` on the specific test file with a specific CLI 
-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:
-
-```bash
-go test ./internal/formats -update-cyclonedx
-```
-
-These flags are defined at the top of the test files that have tests that use the snapshot files.
-
-Snapshot testing is only as good as the manual verification of the golden snapshot file saved to the repo! Be careful 
-and diligent when updating these 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

@@ -12,7 +12,7 @@ TASK = $(TOOL_DIR)/task
 # note: we need to assume that binny and task have not already been installed
 $(BINNY):
 	@mkdir -p $(TOOL_DIR)
-	@curl -sSfL https://raw.githubusercontent.com/$(OWNER)/binny/main/install.sh | sh -s -- -b $(TOOL_DIR)
+	@curl -sSfL https://get.anchore.io/binny | sh -s -- -b $(TOOL_DIR)
 
 # note: we need to assume that binny and task have not already been installed
 .PHONY: task
@@ -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 #################################
 
@@ -36,7 +36,7 @@ make-default: $(TASK)
 	@$(TASK)
 
 # for those of us that can't seem to kick the habit of typing `make ...` lets wrap the superior `task` tool
-TASKS := $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep '^\* ' | cut -d' ' -f2 | tr -d ':' | tr '\n' ' '" ) $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep 'aliases:' | cut -d ':' -f 3 | tr '\n' ' ' | tr -d ','")
+TASKS := $(shell bash -c "test -f $(TASK) && NO_COLOR=1 $(TASK) -l | grep '^\* ' | cut -d' ' -f2 | tr -d ':' | tr '\n' ' '" ) $(shell bash -c "test -f $(TASK) && NO_COLOR=1 $(TASK) -l | grep 'aliases:' | cut -d ':' -f 3 | tr '\n' ' ' | tr -d ','")
 
 .PHONY: $(TASKS)
 $(TASKS): $(TASK)

README.md

@@ -2,849 +2,90 @@
     <img src="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png" width="271" alt="Cute pink owl syft logo">
 </p>
 
-[![Validations](https://github.com/anchore/syft/actions/workflows/validations.yaml/badge.svg)](https://github.com/anchore/syft/actions/workflows/validations.yaml)
-[![Go Report Card](https://goreportcard.com/badge/github.com/anchore/syft)](https://goreportcard.com/report/github.com/anchore/syft)
-[![GitHub release](https://img.shields.io/github/release/anchore/syft.svg)](https://github.com/anchore/syft/releases/latest)
-[![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/anchore/syft.svg)](https://github.com/anchore/syft)
-[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/anchore/syft/blob/main/LICENSE)
-[![Slack Invite](https://img.shields.io/badge/Slack-Join-blue?logo=slack)](https://anchore.com/slack)
+# Syft
 
-A CLI tool and Go library for generating a Software Bill of Materials (SBOM) from container images and filesystems. Exceptional for vulnerability detection when used with a scanner like [Grype](https://github.com/anchore/grype).
+**A CLI tool and Go library for generating a Software Bill of Materials (SBOM) from container images and filesystems. Exceptional for vulnerability detection when used with a scanner like [Grype](https://github.com/anchore/grype).**
 
-### Join our community meetings!
-
-- Calendar: https://calendar.google.com/calendar/u/0/r?cid=Y182OTM4dGt0MjRtajI0NnNzOThiaGtnM29qNEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t
-- 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)
-- All are welcome!
-
-For commercial support options with Syft or Grype, please [contact Anchore](https://get.anchore.com/contact/)
+<p align="center">
+ &nbsp;<a href="https://github.com/anchore/syft/actions/workflows/validations.yaml" target="_blank"><img alt="Validations" src="https://github.com/anchore/syft/actions/workflows/validations.yaml/badge.svg"></a>&nbsp;
+ &nbsp;<a href="https://goreportcard.com/report/github.com/anchore/syft" target="_blank"><img alt="Go Report Card" src="https://goreportcard.com/badge/github.com/anchore/syft"></a>&nbsp;
+ &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/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)
 
 ## Features
-- Generates SBOMs for container images, filesystems, archives, and more to discover packages and libraries
-- Supports OCI, Docker and [Singularity](https://github.com/sylabs/singularity) image formats
-- Linux distribution identification
-- Works seamlessly with [Grype](https://github.com/anchore/grype) (a fast, modern vulnerability scanner)
-- Able to create signed SBOM attestations using the [in-toto specification](https://github.com/in-toto/attestation/blob/main/spec/README.md)
-- Convert between SBOM formats, such as CycloneDX, SPDX, and Syft's own format.
 
-### Supported Ecosystems
+- Generates SBOMs for **container images**, **filesystems**, **archives** (see the docs for a full list of [supported scan targets](https://oss.anchore.com/docs/guides/sbom/scan-targets/))
+- Supports dozens of packaging ecosystems (e.g. Alpine (apk), Debian (dpkg), RPM, Go, Python, Java, JavaScript, Ruby, Rust, PHP, .NET, and [many more](https://oss.anchore.com/docs/capabilities/all-packages/))
+- Supports OCI, Docker, [Singularity](https://github.com/sylabs/singularity), and [more image formats](https://oss.anchore.com/docs/guides/sbom/scan-targets/)
+- Works seamlessly with [Grype](https://github.com/anchore/grype) for vulnerability scanning
+- Multiple output formats (**CycloneDX**, **SPDX**, **Syft JSON**, and [more](https://oss.anchore.com/docs/guides/sbom/formats/)) including the ability to [convert between SBOM formats](https://oss.anchore.com/docs/guides/sbom/conversion/)
+- Create signed SBOM attestations using the [in-toto specification](https://github.com/in-toto/attestation/blob/main/spec/README.md)
 
-- Alpine (apk)
-- C (conan)
-- C++ (conan)
-- Dart (pubs)
-- Debian (dpkg)
-- Dotnet (deps.json)
-- Objective-C (cocoapods)
-- Elixir (mix)
-- Erlang (rebar3)
-- Go (go.mod, Go binaries)
-- Haskell (cabal, stack)
-- Java (jar, ear, war, par, sar, nar, native-image)
-- JavaScript (npm, yarn)
-- Jenkins Plugins (jpi, hpi)
-- Linux kernel archives (vmlinz)
-- Linux kernel modules (ko)
-- Nix (outputs in /nix/store)
-- PHP (composer)
-- Python (wheel, egg, poetry, requirements.txt)
-- Red Hat (rpm)
-- Ruby (gem)
-- Rust (cargo.lock)
-- Swift (cocoapods, swift-package-manager)
+> [!TIP]
+> **New to Syft? Check out the [Getting Started guide](https://oss.anchore.com/docs/guides/sbom/getting-started/) for a walkthrough!**
 
 ## Installation
 
-**Note**: Currently, Syft is built only for Linux, macOS and Windows.
-
-### Recommended
+The quickest way to get up and going:
 ```bash
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
+curl -sSfL https://get.anchore.io/syft | sudo sh -s -- -b /usr/local/bin
 ```
 
-... or, you can specify a release version and destination directory for the installation:
+> [!TIP]
+> **See [Installation docs](https://oss.anchore.com/docs/installation/syft/) for more ways to get Syft, including Homebrew, Docker, Scoop, Chocolatey, Nix, and more!**
 
-```
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b <DESTINATION_DIR> <RELEASE_VERSION>
-```
+## The basics
 
-### Chocolatey
-
-The chocolatey distribution of syft is community maintained and not distributed by the anchore team
-
-```powershell
-choco install syft -y
-```
-
-### Scoop
-
-```powershell
-scoop install syft
-```
-
-### Homebrew
-```bash
-brew install syft
-```
-
-### 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://nixos.wiki/wiki/Nix_channels#The_official_channels) since NixOS `22.05`.
+See the packages within a container image or directory:
 
 ```bash
-nix-env -i syft
+# container image
+syft alpine:latest
+
+# directory
+syft ./my-project
 ```
 
-... or, just try it out in an ephemeral nix shell:
+To get an SBOM, specify one or more output formats:
 
 ```bash
-nix-shell -p syft
-```
+# SBOM to stdout
+syft <image> -o cyclonedx-json
 
-## Getting started
-
-### SBOM
-
-To generate an SBOM for a container image:
-
-```bash
-syft <image>
-```
-
-The above output includes only software that is visible in the container (i.e., the squashed representation of the image). To include software from all image layers in the SBOM, regardless of its presence in the final image, provide `--scope all-layers`:
-
-```bash
-syft <image> --scope all-layers
-```
-
-### Supported sources
-
-Syft can generate an SBOM from a variety of sources:
-
-```bash
-# catalog a container image archive (from the result of `docker image save ...`, `podman save ...`, or `skopeo copy` commands)
-syft path/to/image.tar
-
-# catalog a Singularity Image Format (SIF) container
-syft path/to/image.sif
-
-# catalog a directory
-syft path/to/dir
-```
-
-Sources can be explicitly provided with a scheme:
-
-```
-docker:yourrepo/yourimage:tag            use images from the Docker daemon
-podman:yourrepo/yourimage:tag            use images from the Podman daemon
-containerd:yourrepo/yourimage:tag        use images from the Containerd daemon
-docker-archive:path/to/yourimage.tar     use a tarball from disk for archives created from "docker save"
-oci-archive:path/to/yourimage.tar        use a tarball from disk for OCI archives (from Skopeo or otherwise)
-oci-dir:path/to/yourimage                read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
-singularity:path/to/yourimage.sif        read directly from a Singularity Image Format (SIF) container on disk
-dir:path/to/yourproject                  read directly from a path on disk (any directory)
-file:path/to/yourproject/file            read directly from a path on disk (any single file)
-registry:yourrepo/yourimage:tag          pull image directly from a registry (no container runtime required)
-```
-
-If an image source is not provided and cannot be detected from the given reference it is assumed the image should be pulled from the Docker daemon.
-If docker is not present, then the Podman daemon is attempted next, followed by reaching out directly to the image registry last.
-
-
-This default behavior can be overridden with the `default-image-pull-source` configuration option (See [Configuration](https://github.com/anchore/syft#configuration) for more details).
-
-
-### File selection
-
-By default, Syft will catalog file details and digests for files that are owned by discovered packages. You can change this behavior by using the `SYFT_FILE_METADATA_SELECTION` environment variable or the `file.metadata.selection` configuration option. The options are:
-
-- `all`: capture all files from the search space
-- `owned-by-package`: capture only files owned by packages (default)
-- `none`: disable capturing any file information
-
-
-### Package cataloger selection
-
-#### Concepts
-
-> [!IMPORTANT]  
-> Syft uses a different set of catalogers by default when scanning files directly than it does when scanning images
-
-The catalogers for an image scan assumes that package installation steps have already been completed. For example, Syft will identify Python packages that have egg or wheel metadata files under a `site-packages` directory, since this is how the canonical tooling `pip` installs python packages.
-
-The catalogers for a directory scan will look for installed software as well as declared dependencies that are not necessarily installed. For example, dependencies listed in a Python `requirements.txt`.
-
-This default set of catalogers being dynamic is critical as this allows Syft to be used in a variety of contexts while still generating accurate SBOMs.
-Overriding the set of default catalogers is not recommended for most purposes, however, is possible if needed.
-
-Catalogers can be referenced in two different ways:
-- *by name*: the exact cataloger name (e.g. `java-pom-cataloger` or `java-archive-cataloger`)
-- *by tag*: a tag that is associated with a cataloger (e.g. `java`)
-
-Syft can take lists of references on the CLI or in the application configuration to define which catalogers to use.
-
-You can **set** the list of catalogers explicitly to use with the `--override-default-catalogers` CLI flag, accepting a comma-separated list of cataloger names or tags.
-
-You can also **add** to, **remove** from, or **sub-select** catalogers to use within the default set of catalogers by using the `--select-catalogers` CLI flag.
-  - To **sub-select** catalogers simply provide a tag (e.g. `--select-catalogers TAG`). Catalogers will always be selected from the default set of catalogers (e.g. `--select-catalogers java,go` will select all the `java` catalogers in the default set and all the `go` catalogers in the default set).
-  - To **add** a cataloger prefix the cataloger name with `+` (e.g. `--select-catalogers +NAME`). Added catalogers will _always be added_ regardless of removals, filtering, or other defaults.
-  - To **remove** a cataloger prefix the cataloger name or tag with `-` (e.g. `--select-catalogers -NAME_OR_TAG`). Catalogers are removed from the set of default catalogers after processing any sub-selections.
-
-These rules and the dynamic default cataloger sets approximates to the following logic:
-
-```
-image_catalogers = all_catalogers AND catalogers_tagged("image")
-
-directory_catalogers = all_catalogers AND catalogers_tagged("directory")
-
-default_catalogers = image_catalogers OR directory_catalogers
-
-sub_selected_catalogers = default_catalogers INTERSECT catalogers_tagged(TAG) [ UNION sub_selected_catalogers ... ]
-
-base_catalogers = default_catalogers OR sub_selected_catalogers
-
-final_set = (base_catalogers SUBTRACT removed_catalogers) UNION added_catalogers
+# Multiple SBOMs to files
+syft <image> -o spdx-json=./spdx.json -o cyclonedx-json=./cdx.json
 ```
 
 
-#### Examples
+> [!TIP]
+> **Check out the [Getting Started guide](https://oss.anchore.com/docs/guides/sbom/getting-started/)** to explore all of the capabilities and features.
+>
+> **Want to know all of the ins-and-outs of Syft?** Check out the [CLI docs](https://oss.anchore.com/docs/reference/syft/cli/),  [configuration docs](https://oss.anchore.com/docs/reference/syft/configuration/), and [JSON schema](https://oss.anchore.com/docs/reference/syft/json/latest/).
 
-Only scan for python related packages with catalogers appropriate for the source type (image or directory):
-```bash
-syft <some container image> --select-catalogers "python"
-# results in the following catalogers being used:
-# - python-installed-package-cataloger
-```
 
-Same command, but the set of catalogers changes based on what is being analyzed (in this case a directory):
-```bash
-syft <a directory> --select-catalogers "python"
-# results in the following catalogers being used:
-# - python-installed-package-cataloger
-# - python-package-cataloger
-```
+## Contributing
 
-Use the default set of catalogers and add a cataloger to the set:
-```bash
-syft ... --catalogers "+sbom-cataloger"
-```
+We encourage users to help make these tools better by [submitting issues](https://github.com/anchore/syft/issues) when you find a bug or want a new feature. 
+Check out our [contributing overview](https://oss.anchore.com/docs/contributing/) and [developer-specific documentation](https://oss.anchore.com/docs/contributing/syft/) if you are interested in providing code contributions.
 
-Use the default set of catalogers but remove any catalogers that deal with RPMs:
-```bash
-syft ... --catalogers "-rpm"
-```
 
-Only scan with catalogers that:
-- are tagged with "go"
-- always use the sbom-cataloger
-- are appropriate for the source type (image or directory)
 
-```bash
-syft <some container image> --select-catalogers "go,+sbom-cataloger"
-# results in the following catalogers being used:
-# - go-module-binary-cataloger
-# - sbom-cataloger
-```
+<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/">
+  Syft development is sponsored by <a href="https://anchore.com/">Anchore</a>, and is released under the <a href="https://github.com/anchore/syft?tab=Apache-2.0-1-ov-file">Apache-2.0 License</a>.
+  The <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>
 
-Scan with all catalogers that deal with binary analysis, regardless of the source type:
-```bash
-syft ... --override-default-catalogers "binary"
-# results in the following catalogers being used:
-# - binary-cataloger
-# - cargo-auditable-binary-cataloger
-# - dotnet-portable-executable-cataloger
-# - go-module-binary-cataloger
-```
+For commercial support options with Syft or Grype, please [contact Anchore](https://get.anchore.com/contact/).
 
-Only scan with the specific `go-module-binary-cataloger` and `go-module-file-cataloger` catalogers:
-```bash
-syft ... --override-default-catalogers "go-module-binary-cataloger,go-module-file-cataloger"
-```
+## Come talk to us!
 
-
-### Excluding file paths
-
-Syft can exclude files and paths from being scanned within a source by using glob expressions
-with one or more `--exclude` parameters:
-```
-syft <source> --exclude './out/**/*.json' --exclude /etc
-```
-**Note:** in the case of _image scanning_, since the entire filesystem is scanned it is
-possible to use absolute paths like `/etc` or `/usr/**/*.txt` whereas _directory scans_
-exclude files _relative to the specified directory_. For example: scanning `/usr/foo` with
-`--exclude ./package.json` would exclude `/usr/foo/package.json` and `--exclude '**/package.json'`
-would exclude all `package.json` files under `/usr/foo`. For _directory scans_,
-it is required to begin path expressions with `./`, `*/`, or `**/`, all of which
-will be resolved _relative to the specified scan directory_. Keep in mind, your shell
-may attempt to expand wildcards, so put those parameters in single quotes, like:
-`'**/*.json'`.
-
-### Output formats
-
-The output format for Syft is configurable as well using the
-`-o` (or `--output`) option:
-
-```
-syft <image> -o <format>
-```
-
-Where the `formats` available are:
-- `syft-json`: Use this to get as much information out of Syft as possible!
-- `syft-text`: A row-oriented, human-and-machine-friendly output.
-- `cyclonedx-xml`: A XML report conforming to the [CycloneDX 1.4 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.4 specification](https://cyclonedx.org/specification/overview/).
-- `spdx-tag-value`: A tag-value formatted report conforming to the [SPDX 2.3 specification](https://spdx.github.io/spdx-spec/v2.3/).
-- `spdx-tag-value@2.2`: A tag-value formatted report conforming to the [SPDX 2.2 specification](https://spdx.github.io/spdx-spec/v2.2.2/).
-- `spdx-json`: A JSON report conforming to the [SPDX 2.3 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.3/schemas/spdx-schema.json).
-- `spdx-json@2.2`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
-- `github-json`: A JSON report conforming to GitHub's dependency snapshot format.
-- `syft-table`: A columnar summary (default).
-- `template`: Lets the user specify the output format. See ["Using templates"](#using-templates) below.
-
-## Using templates
-
-Syft lets you define custom output formats, using [Go templates](https://pkg.go.dev/text/template). Here's how it works:
-
-- Define your format as a Go template, and save this template as a file.
-
-- Set the output format to "template" (`-o template`).
-
-- Specify the path to the template file (`-t ./path/to/custom.template`).
-
-- Syft's template processing uses the same data models as the `syft-json` output format — so if you're wondering what data is available as you author a template, you can use the output from `syft <image> -o syft-json` as a reference.
-
-**Example:** You could make Syft output data in CSV format by writing a Go template that renders CSV data and then running `syft <image> -o template -t ~/path/to/csv.tmpl`.
-
-Here's what the `csv.tmpl` file might look like:
-```gotemplate
-"Package","Version Installed","Found by"
-{{- range .Artifacts}}
-"{{.Name}}","{{.Version}}","{{.FoundBy}}"
-{{- end}}
-```
-
-Which would produce output like:
-```text
-"Package","Version Installed","Found by"
-"alpine-baselayout","3.2.0-r20","apkdb-cataloger"
-"alpine-baselayout-data","3.2.0-r20","apkdb-cataloger"
-"alpine-keys","2.4-r1","apkdb-cataloger"
-...
-```
-
-Syft also includes a vast array of utility templating functions from [sprig](http://masterminds.github.io/sprig/) apart from the default Golang [text/template](https://pkg.go.dev/text/template#hdr-Functions) to allow users to customize the output format.
-
-Lastly, Syft has custom templating functions defined in `./syft/format/template/encoder.go` to help parse the passed-in JSON structs.
-
-## Multiple outputs
-
-Syft can also output _multiple_ files in differing formats by appending
-`=<file>` to the option, for example to output Syft JSON and SPDX JSON:
-
-```shell
-syft <image> -o syft-json=sbom.syft.json -o spdx-json=sbom.spdx.json
-```
-
-## Private Registry Authentication
-
-### Local Docker Credentials
-When a container runtime is not present, Syft can still utilize credentials configured in common credential sources (such as `~/.docker/config.json`). It will pull images from private registries using these credentials. The config file is where your credentials are stored when authenticating with private registries via some command like `docker login`. For more information see the `go-containerregistry` [documentation](https://github.com/google/go-containerregistry/tree/main/pkg/authn).
-
-An example `config.json` looks something like this:
-```json
-{
-	"auths": {
-		"registry.example.com": {
-			"username": "AzureDiamond",
-			"password": "hunter2"
-		}
-	}
-}
-```
-
-You can run the following command as an example. It details the mount/environment configuration a container needs to access a private registry:
-
-```
-docker run -v ./config.json:/config/config.json -e "DOCKER_CONFIG=/config" anchore/syft:latest  <private_image>
-```
-
-### Docker Credentials in Kubernetes
-
-Here's a simple workflow to mount this config file as a secret into a container on Kubernetes.
-
-1. Create a secret. The value of `config.json` is important. It refers to the specification detailed [here](https://github.com/google/go-containerregistry/tree/main/pkg/authn#the-config-file). Below this section is the `secret.yaml` file that the pod configuration will consume as a volume. The key `config.json` is important. It will end up being the name of the file when mounted into the pod.
-
-    ```yaml
-    # secret.yaml
-
-    apiVersion: v1
-    kind: Secret
-    metadata:
-      name: registry-config
-      namespace: syft
-    data:
-      config.json: <base64 encoded config.json>
-    ```
-
-   `kubectl apply -f secret.yaml`
-
-
-2. Create your pod running syft. The env `DOCKER_CONFIG` is important because it advertises where to look for the credential file. In the below example, setting `DOCKER_CONFIG=/config` informs syft that credentials can be found at `/config/config.json`. This is why we used `config.json` as the key for our secret. When mounted into containers the secrets' key is used as the filename. The `volumeMounts` section mounts our secret to `/config`. The `volumes` section names our volume and leverages the secret we created in step one.
-
-    ```yaml
-    # pod.yaml
-
-    apiVersion: v1
-    kind: Pod
-    metadata:
-      name: syft-k8s-usage
-    spec:
-      containers:
-        - image: anchore/syft:latest
-          name: syft-private-registry-demo
-          env:
-            - name: DOCKER_CONFIG
-              value: /config
-          volumeMounts:
-          - mountPath: /config
-            name: registry-config
-            readOnly: true
-          args:
-            - <private_image>
-      volumes:
-      - name: registry-config
-        secret:
-          secretName: registry-config
-    ```
-
-   `kubectl apply -f pod.yaml`
-
-
-3. The user can now run `kubectl logs syft-private-registry-demo`. The logs should show the Syft analysis for the `<private_image>` provided in the pod configuration.
-
-Using the above information, users should be able to configure private registry access without having to do so in the `grype` or `syft` configuration files.  They will also not be dependent on a Docker daemon, (or some other runtime software) for registry configuration and access.
-
-## Format conversion (experimental)
-
-The ability to convert existing SBOMs means you can create SBOMs in different formats quickly, without the need to regenerate the SBOM from scratch, which may take significantly more time.
-
-```
-syft convert <ORIGINAL-SBOM-FILE> -o <NEW-SBOM-FORMAT>[=<NEW-SBOM-FILE>]
-```
-
-This feature is experimental and data might be lost when converting formats. Packages are the main SBOM component easily transferable across formats, whereas files and relationships, as well as other information Syft doesn't support, are more likely to be lost.
-
-We support formats with wide community usage AND good encode/decode support by Syft. The supported formats are:
-- Syft JSON (```-o syft-json```)
-- SPDX 2.2 JSON (```-o spdx-json```)
-- SPDX 2.2 tag-value (```-o spdx-tag-value```)
-- CycloneDX 1.4 JSON (```-o cyclonedx-json```)
-- CycloneDX 1.4 XML (```-o cyclonedx-xml```)
-
-Conversion example:
-```sh
-syft alpine:latest -o syft-json=sbom.syft.json # generate a syft SBOM
-syft convert sbom.syft.json -o cyclonedx-json=sbom.cdx.json  # convert it to CycloneDX
-```
-
-## Attestation (experimental)
-### Keyless support
-Syft supports generating attestations using cosign's [keyless](https://github.com/sigstore/cosign/blob/main/KEYLESS.md) signatures.
-
-Note: users need to have >= v1.12.0 of cosign installed for this command to function
-
-To use this feature with a format like CycloneDX json simply run:
-```
-syft attest --output cyclonedx-json <IMAGE WITH OCI WRITE ACCESS>
-```
-This command will open a web browser and allow the user to authenticate their OIDC identity as the root of trust for the attestation (Github, Google, Microsoft).
-
-After authenticating, Syft will upload the attestation to the OCI registry specified by the image that the user has write access to.
-
-You will need to make sure your credentials are configured for the OCI registry you are uploading to so that the attestation can write successfully.
-
-Users can then verify the attestation(or any image with attestations) by running:
-```
-COSIGN_EXPERIMENTAL=1 cosign verify-attestation <IMAGE_WITH_ATTESTATIONS>
-```
-
-Users should see that the uploaded attestation claims are validated, the claims exist within the transparency log, and certificates on the attestations were verified against [fulcio](https://github.com/SigStore/fulcio).
-There will also be a printout of the certificates subject `<user identity>` and the certificate issuer URL: `<provider of user identity (Github, Google, Microsoft)>`:
-```
-Certificate subject:  test.email@testdomain.com
-Certificate issuer URL:  https://accounts.google.com
-```
-
-### Local private key support
-
-To generate an SBOM attestation for a container image using a local private key:
-```
-syft attest --output [FORMAT] --key [KEY] [SOURCE] [flags]
-```
-
-The above output is in the form of the [DSSE envelope](https://github.com/secure-systems-lab/dsse/blob/master/envelope.md#dsse-envelope).
-The payload is a base64 encoded `in-toto` statement with the generated SBOM as the predicate. For details on workflows using this command see [here](#adding-an-sbom-to-an-image-as-an-attestation-using-syft).
-
-
-
-## Configuration
-
-Configuration search paths:
-
-- `.syft.yaml`
-- `.syft/config.yaml`
-- `~/.syft.yaml`
-- `<XDG_CONFIG_HOME>/syft/config.yaml`
-
-Configuration options (example values are the default):
-
-```yaml
-# the output format(s) of the SBOM report (options: syft-table, syft-text, syft-json, spdx-json, ...)
-# to specify multiple output files in differing formats, use a list:
-# output:
-#   - "syft-json=<syft-json-output-file>"
-#   - "spdx-json=<spdx-json-output-file>"
-# SYFT_OUTPUT env var / -o, --output flags
-output: 
-  - "syft-table"
-
-# suppress all output (except for the SBOM report)
-# SYFT_QUIET env var / -q flag
-quiet: false
-
-# enable/disable checking for application updates on startup
-# SYFT_CHECK_FOR_APP_UPDATE env var 
-check-for-app-update: true
-
-# maximum number of workers used to process the list of package catalogers in parallel
-parallelism: 1
-
-# a list of globs to exclude from scanning, for example:
-# exclude:
-#   - "/etc/**"
-#   - "./out/**/*.json"
-# SYFT_EXCLUDE env var / --exclude flag
-exclude: []
-
-# os and/or architecture to use when referencing container images (e.g. "windows/armv6" or "arm64")
-# SYFT_PLATFORM env var / --platform flag
-platform: ""
-
-# the search space to look for file and package data (options: all-layers, squashed)
-# SYFT_SCOPE env var
-scope: "squashed"
-
-# set the list of package catalogers to use when generating the SBOM
-# default = empty (cataloger set determined automatically by the source type [image or file/directory])
-# Use `syft cataloger list` for a list of catalogers you can specify
-# DEPRECATED: please use default-catalogers and select-catalogers configuration options instead
-# SYFT_CATALOGERS env var / --catalogers flag
-catalogers:
-
-# set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)
-# SYFT_DEFAULT_CATALOGERS env var / --override-default-catalogers flag
-default-catalogers: []
-
-# add, remove, and filter the catalogers to be used
-# SYFT_SELECT_CATALOGERS env var / --select-catalogers flag;
-select-catalogers: []
-
-# all format configuration
-format:
- 
-  # default value for all formats that support the "pretty" option (default is unset)
-  # SYFT_FORMAT_PRETTY env var
-  pretty: 
-
-  # all syft-json format options
-  json:
-
-    # include space indention and newlines (inherits default value from 'format.pretty' or 'false' if parent is unset)
-    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
-    # SYFT_FORMAT_JSON_PRETTY env var
-    pretty: false
-    
-    # transform any syft-json output to conform to an approximation of the v11.0.1 schema. This includes:
-    # - using the package metadata type names from before v12 of the JSON schema (changed in https://github.com/anchore/syft/pull/1983)
-    #
-    # Note: this will still include package types and fields that were added at or after json schema v12. This means
-    # that output might not strictly be json schema v11 compliant, however, for consumers that require time to port
-    # over to the final syft 1.0 json output this option can be used to ease the transition.
-    #
-    # Note: long term support for this option is not guaranteed (it may change or break at any time).
-    # SYFT_FORMAT_JSON_LEGACY env var
-    legacy: false
-
-  # all template format options
-  template:
-    # path to the template file to use when rendering the output with the `template` output format. 
-    # Note that all template paths are based on the current syft-json schema.
-    # SYFT_FORMAT_TEMPLATE_PATH env var / -t flag 
-    path: ""
-    
-    # if true, uses the go structs for the syft-json format for templating. 
-    # if false, uses the syft-json output for templating (which follows the syft JSON schema exactly).
-    #
-    # Note: long term support for this option is not guaranteed (it may change or break at any time).
-    # SYFT_FORMAT_TEMPLATE_LEGACY env var
-    legacy: false
-
-  # all spdx-json format options
-  spdx-json:
-
-    # include space indention and newlines
-    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
-    # SYFT_FORMAT_SPDX_JSON_PRETTY env var
-    pretty: false
-
-  # all cyclonedx-json format options
-  cyclonedx-json:
-
-     # include space indention and newlines
-     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
-     # SYFT_FORMAT_CYCLONEDX_JSON_PRETTY env var
-     pretty: false
-
-  # all cyclonedx-xml format options
-  cyclonedx-xml:
-
-     # include space indention
-     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
-     # SYFT_FORMAT_CYCLONEDX_XML_PRETTY env var
-     pretty: false
-
-
-file:
-
-   metadata: 
-      # select which files should be captured by the file-metadata cataloger and included in the SBOM. 
-      # Options include:
-      #  - "all": capture all files from the search space
-      #  - "owned-by-package": capture only files owned by packages
-      #  - "none", "": do not capture any files
-      # SYFT_FILE_METADATA_SELECTION env var
-      selection: "owned-by-package"
-
-      # the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-      # SYFT_FILE_METADATA_DIGESTS env var
-      digests:
-      - "sha256"
-      - "sha1"
-
-   # capture the contents of select files in the SBOM
-   content:
-      # skip searching a file entirely if it is above the given size (default = 1MB; unit = bytes)
-      # SYFT_FILE_CONTENT_SKIP_FILES_ABOVE_SIZE env var
-      skip-files-above-size: 1048576
-   
-      # file globs for the cataloger to match on
-      # SYFT_FILE_CONTENT_GLOBS env var
-      globs: []
-
-
-# cataloging packages is exposed through the packages and power-user subcommands
-package:
-   
-  # search within archives that do contain a file index to search against (zip)
-  # note: for now this only applies to the java package cataloger
-  # SYFT_PACKAGE_SEARCH_INDEXED_ARCHIVES env var
-  search-indexed-archives: true
-
-  # 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
-  # SYFT_PACKAGE_SEARCH_UNINDEXED_ARCHIVES env var
-  search-unindexed-archives: false
-
-  # allows users to exclude synthetic binary packages from the sbom
-  # these packages are removed if an overlap with a non-synthetic package is found
-  # SYFT_PACKAGE_EXCLUDE_BINARY_OVERLAP_BY_OWNERSHIP env var
-  exclude-binary-overlap-by-ownership: true
-
-
-golang:
-   # 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
-   # SYFT_GOLANG_SEARCH_LOCAL_MOD_CACHE_LICENSES env var
-   search-local-mod-cache-licenses: false
-   
-   # specify an explicit go mod cache directory, if unset this defaults to $GOPATH/pkg/mod or $HOME/go/pkg/mod
-   # SYFT_GOLANG_LOCAL_MOD_CACHE_DIR env var
-   local-mod-cache-dir: ""
-
-   # search for go package licences by retrieving the package from a network proxy
-   # SYFT_GOLANG_SEARCH_REMOTE_LICENSES env var
-   search-remote-licenses: false
-
-   # remote proxy to use when retrieving go packages from the network,
-   # if unset this defaults to $GOPROXY followed by https://proxy.golang.org
-   # SYFT_GOLANG_PROXY env var
-   proxy: ""
-
-   # specifies packages which should not be fetched by proxy
-   # if unset this defaults to $GONOPROXY
-   # SYFT_GOLANG_NOPROXY env var
-   no-proxy: ""
-  
-java:
-   maven-url: "https://repo1.maven.org/maven2"
-   max-parent-recursive-depth: 5
-   # enables Syft to use the network to fill in more detailed information about artifacts
-   # currently this enables searching maven-url for license data
-   # when running across pom.xml files that could have more information, syft will
-   # explicitly search maven for license information by querying the online pom when this is true
-   # this option is helpful for when the parent pom has more data,
-   # that is not accessible from within the final built artifact
-   use-network: false
-
-linux-kernel:
-   # whether to catalog linux kernel modules found within lib/modules/** directories
-   # SYFT_LINUX_KERNEL_CATALOG_MODULES env var
-   catalog-modules: true
-
-python:
-   # when running across entries in requirements.txt that do not specify a specific version 
-   # (e.g. "sqlalchemy >= 1.0.0, <= 2.0.0, != 3.0.0, <= 3.0.0"), attempt to guess what the version could
-   # be based on the version requirements specified (e.g. "1.0.0"). When enabled the lowest expressible version 
-   # when given an arbitrary constraint will be used (even if that version may not be available/published).
-   guess-unpinned-requirements: false
-
-javascript:
-  search-remote-licenses: false
-  npm-base-url: "https://registry.npmjs.org"
-
-
-# configuration for the source that the SBOM is generated from (e.g. a file, directory, or container image)
-source:
-  # alias name for the source
-  # SYFT_SOURCE_NAME env var / --source-name flag
-  name: ""
-   
-  # alias version for the source
-  # SYFT_SOURCE_VERSION env var / --source-version flag
-  version: ""
-
-  # base directory for scanning, no links will be followed above this directory, and all paths will be 
-  # reported relative to this directory
-  # SYFT_SOURCE_BASE_PATH env var
-  base-path: ''
-
-   # options affecting the file source type
-  file:
-    # the file digest algorithms to use on the scanned file (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-    digests: 
-     - "sha256"
-
-  image:
-     
-    # allows users to specify which image source should be used to generate the sbom
-    # valid values are: registry, docker, podman
-    # SYFT_SOURCE_IMAGE_DEFAULT_PULL_SOURCE env var
-    default-pull-source: ""
-
-
-# options when pulling directly from a registry via the "registry:" or "containerd:" scheme
-registry:
-  # skip TLS verification when communicating with the registry
-  # SYFT_REGISTRY_INSECURE_SKIP_TLS_VERIFY env var
-  insecure-skip-tls-verify: false
-
-  # use http instead of https when connecting to the registry
-  # SYFT_REGISTRY_INSECURE_USE_HTTP env var
-  insecure-use-http: false
-
-  # filepath to a CA certificate (or directory containing *.crt, *.cert, *.pem) used to generate the client certificate
-  # SYFT_REGISTRY_CA_CERT env var
-  ca-cert: ""
-
-  # credentials for specific registries
-  auth:
-      # the URL to the registry (e.g. "docker.io", "localhost:5000", etc.)
-      # SYFT_REGISTRY_AUTH_AUTHORITY env var
-    - authority: ""
-
-      # SYFT_REGISTRY_AUTH_USERNAME env var
-      username: ""
-
-      # SYFT_REGISTRY_AUTH_PASSWORD env var
-      password: ""
-
-      # note: token and username/password are mutually exclusive
-      # SYFT_REGISTRY_AUTH_TOKEN env var
-      token: ""
-
-      # filepath to the client certificate used for TLS authentication to the registry
-      # SYFT_REGISTRY_AUTH_TLS_CERT env var
-      tls-cert: ""
-
-      # filepath to the client key used for TLS authentication to the registry
-      # SYFT_REGISTRY_AUTH_TLS_KEY env var
-      tls-key: ""
-    
-    # - ... # note, more credentials can be provided via config file only (not env vars)
-
-# generate an attested SBOM
-attest:
-  # path to the private key file to use for attestation
-  # SYFT_ATTEST_KEY env var
-  key: "cosign.key"
-
-  # password to decrypt to given private key
-  # SYFT_ATTEST_PASSWORD env var, additionally responds to COSIGN_PASSWORD
-  password: ""
-
-log:
-  # use structured logging
-  # SYFT_LOG_STRUCTURED env var
-  structured: false
-
-  # the log level; note: detailed logging suppress the ETUI
-  # SYFT_LOG_LEVEL env var
-  level: "error"
-
-  # location to write the log file (default is not to have a log file)
-  # SYFT_LOG_FILE env var
-  file: ""
-```
-
-### Adding an SBOM to an image as an attestation using Syft
-
-`syft attest --output [FORMAT] --key [KEY] [SOURCE] [flags]`
-
-SBOMs themselves can serve as input to different analysis tools. [Grype](https://github.com/anchore/grype), a vulnerability scanner CLI tool from Anchore, is one such tool. Publishers of container images can use attestations to enable their consumers to trust Syft-generated SBOM descriptions of those container images. To create and provide these attestations, image publishers can run `syft attest` in conjunction with the [cosign](https://github.com/sigstore/cosign) tool to attach SBOM attestations to their images.
-
-#### Example attestation
-Note for the following example replace `docker.io/image:latest` with an image you own. You should also have push access to
-its remote reference. Replace `$MY_PRIVATE_KEY` with a private key you own or have generated with cosign.
-
-```bash
-syft attest --key $MY_PRIVATE_KEY -o spdx-json docker.io/image:latest > image_latest_sbom_attestation.json
-cosign attach attestation --attestation image_latest_sbom_attestation.json docker.io/image:latest
-```
-
-Verify the new attestation exists on your image.
-
-```bash
-cosign verify-attestation --key $MY_PUBLIC_KEY --type spdxjson docker.io/image:latest | jq '.payload | @base64d | .payload | fromjson | .predicate'
-```
-
-You should see this output along with the attached SBOM:
-
-```
-Verification for docker.io/image:latest --
-The following checks were performed on each of these signatures:
-  - The cosign claims were validated
-  - The signatures were verified against the specified public key
-  - Any certificates were verified against the Fulcio roots.
-```
-
-Consumers of your image can now trust that the SBOM associated with your image is correct and from a trusted source.
-
-The SBOM can be piped to Grype:
-
-
-```bash
-cosign verify-attestation --key $MY_PUBLIC_KEY --type spdxjson docker.io/image:latest | jq '.payload | @base64d | .payload | fromjson | .predicate' | grype
-```
+The Syft Team holds regular community meetings online. All are welcome to join to bring topics for discussion.
+- 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!

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.

SECURITY.md

@@ -0,0 +1,16 @@
+# Security Policy
+
+## Supported Versions
+
+Security updates are applied only to the most recent release, try to always be up to date.
+
+## Reporting a Vulnerability
+
+To report a security issue, please email
+[security@anchore.com](mailto:security@anchore.com)
+with a description of the issue, the steps you took to create the issue,
+affected versions, and, if known, mitigations for the issue.
+
+All support will be made on a best effort basis, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.
+
+For more details, see our [security policy documentation](https://oss.anchore.com/docs/contributing/security/).

Taskfile.yaml

@@ -1,12 +1,28 @@
 
 version: "3"
+
+includes:
+  generate:cpe-index: ./task.d/generate/cpe-index.yaml
+
 vars:
   OWNER: anchore
   PROJECT: syft
 
+  # v1: when fixtures were located at test-fixtures dirs
+  # v2: migration to testdata dirs
+  CACHE_IMAGE: ghcr.io/{{ .OWNER }}/{{ .PROJECT }}/test-fixture-cache:v2
+
   # 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 +33,12 @@ 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 +51,9 @@ vars:
   COMPARE_DIR: ./test/compare
   COMPARE_TEST_IMAGE: centos:8.2.2004
 
+env:
+  GNUMAKEFLAGS: '--no-print-directory'
+
 tasks:
 
   ## High-level tasks #################################
@@ -62,9 +83,10 @@ tasks:
       - task: unit
       - task: integration
       - task: validate-cyclonedx-schema
-      - task: benchmark
       - task: test-utils
+      - task: snapshot
       - task: cli
+      - task: check-docker-cache
 
   ## Bootstrap tasks #################################
 
@@ -75,7 +97,7 @@ tasks:
       - "{{ .TOOL_DIR }}/binny"
     status:
       - "test -f {{ .TOOL_DIR }}/binny"
-    cmd: "curl -sSfL https://raw.githubusercontent.com/anchore/binny/main/install.sh | sh -s -- -b .tool"
+    cmd: "curl -sSfL https://get.anchore.io/binny | sh -s -- -b .tool"
     silent: true
 
   tools:
@@ -170,13 +192,26 @@ tasks:
     cmds:
       - .github/scripts/json-schema-drift-check.sh
 
+  check-capability-drift:
+    desc: Ensure there is no drift between the capabilities data and the code
+    cmds:
+      - .github/scripts/capability-drift-check.sh
+
   check-binary-fixture-size:
     desc: Ensure that the binary test fixtures are not too large
     cmds:
-      - .github/scripts/check_binary_fixture_size.sh syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets
+      - .github/scripts/check_binary_fixture_size.sh syft/pkg/cataloger/binary/testdata/classifiers/snippets
 
 
   ## 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
@@ -190,6 +225,7 @@ tasks:
       # unit test coverage threshold (in % coverage)
       COVERAGE_THRESHOLD: 62
     cmds:
+      - task: clean-test-observations
       - "go test -coverprofile {{ .TMP_DIR }}/unit-coverage-details.txt {{ .TEST_PKGS }}"
       - cmd: ".github/scripts/coverage.py {{ .COVERAGE_THRESHOLD }} {{ .TMP_DIR }}/unit-coverage-details.txt"
         silent: true
@@ -199,28 +235,21 @@ 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"
@@ -229,83 +258,198 @@ 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 `testdata/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
     generates:
-      - cmd/syft/internal/test/integration/test-fixtures/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
+      - '**/testdata/**/*.fingerprint'
       - test/install/cache.fingerprint
-      - test/cli/test-fixtures/cache.fingerprint
     cmds:
-      # for IMAGE integration test fixtures
-      - "cd cmd/syft/internal/test/integration/test-fixtures && make cache.fingerprint"
-      # for BINARY test fixtures
-      - "cd syft/pkg/cataloger/binary/test-fixtures && make cache.fingerprint"
-      # for JAVA BUILD test fixtures
-      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make cache.fingerprint"
-      # for GO BINARY test fixtures
-      - "cd syft/pkg/cataloger/golang/test-fixtures/archs && make binaries.fingerprint"
-      # for RPM test fixtures
-      - "cd syft/pkg/cataloger/redhat/test-fixtures && make rpms.fingerprint"
-      # for Kernel 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 $(find . -type d -name 'testdata'); do
+          if [ -f "$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 [ "$DOWNLOAD_TEST_FIXTURE_CACHE" = "false" ]; then
+          exit 0
+        fi
+        .github/scripts/find_cache_paths.py {{ .CACHE_PATHS_FILE }} > /dev/null
+
+
+  refresh-fixtures:
+    desc: Clear and fetch all test fixture cache
+    aliases:
+      - fixtures
+    silent: true
+    deps:
+      - tools
     cmds:
-      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make"
-      - "cd syft/pkg/cataloger/redhat/test-fixtures && make"
-      - "cd syft/pkg/cataloger/binary/test-fixtures && make"
+      - |
+        BOLD='\033[1m'
+        PURPLE='\033[0;35m'
+        RESET='\033[0m'
+
+        # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then skip the cache download and always build
+        if [ "$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 `testdata/Makefile` and invoke the `fixtures` target to generate any and all test fixtures
+    cmds:
+      - |
+        # we want to stop on the first build error
+        set -e
+
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
+
+        # Use a for loop with command substitution to avoid subshell issues
+        for dir in $(find . -type d -name 'testdata'); do
+          if [ -f "$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 "**/testdata/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 #################################
 
@@ -326,7 +470,7 @@ tasks:
       - "cd test/install && make ci-test-mac"
 
   generate-compare-file:
-    cmd: "go run ./cmd/syft {{ .COMPARE_TEST_IMAGE }} -o json > {{ .COMPARE_DIR }}/test-fixtures/acceptance-{{ .COMPARE_TEST_IMAGE }}.json"
+    cmd: "go run ./cmd/syft {{ .COMPARE_TEST_IMAGE }} -o json > {{ .COMPARE_DIR }}/testdata/acceptance-{{ .COMPARE_TEST_IMAGE }}.json"
 
   compare-mac:
     deps: [tmpdir]
@@ -367,13 +511,14 @@ tasks:
     desc: Add data generation tasks
     cmds:
       - task: generate-json-schema
+      - task: generate-capabilities
       - task: generate-license-list
       - task: generate-cpe-dictionary-index
 
   generate-json-schema:
     desc: Generate a new JSON schema
     cmds:
-      - "cd syft/internal && go generate . && cd jsonschema && go run . && go fmt ../..."
+      - "cd ./internal && go generate . && cd ./jsonschema && go run . && go fmt ../..."
 
   generate-license-list:
     desc: Generate an updated license processing code off of the latest available SPDX license list
@@ -382,10 +527,32 @@ tasks:
       - "gofmt -s -w ./internal/spdxlicense"
 
   generate-cpe-dictionary-index:
-    desc: Generate the CPE index based off of the latest available CPE dictionary
-    dir: "syft/pkg/cataloger/common/cpe/dictionary"
+    desc: Generate the CPE index from local cache
     cmds:
-      - "go generate"
+      - task: generate:cpe-index:cache:pull
+      - task: generate:cpe-index:cache:update
+      - task: generate:cpe-index:build
+
+  generate-capabilities:
+    desc: Generate the capabilities data file
+    deps:
+      - tmpdir
+      - fixtures
+    vars:
+      # set REFRESH=true to run package tests first and refresh test observations (default: true)
+      REFRESH: '{{ .REFRESH | default "true" }}'
+    cmds:
+      # remove all test observations prior to regenerating
+      - task: clean-test-observations
+        if: '{{ eq .REFRESH "true" }}'
+      # this is required to update test observations; such evidence is used to update the packages/*.yaml
+      - cmd: "go test ./syft/pkg/... -count=1"
+        if: '{{ eq .REFRESH "true" }}'
+      - "go generate ./internal/capabilities/..."
+      - "gofmt -s -w ./internal/capabilities"
+      # now that we have the latest capabilities, run completeness tests to ensure this is self-consistent
+      # note: -p 1 forces sequential package execution to avoid race between generate (writes) and internal (reads)
+      - "SYFT_ENABLE_COMPLETENESS_TESTS=true go test -p 1 ./internal/capabilities/... -count=1"
 
 
   ## Build-related targets #################################
@@ -423,6 +590,18 @@ 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]
@@ -431,7 +610,7 @@ 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 #################################
@@ -466,14 +645,51 @@ tasks:
 
   ## Cleanup targets #################################
 
+  clean:
+    desc: Remove all cache files and old builds
+    cmds:
+      - task: clean-snapshot
+      - task: clean-cache
+      - task: clean-test-observations
+      - task: clean-docker-cache
+      - task: clean-oras-cache
+
   clean-snapshot:
     desc: Remove any snapshot builds
     cmds:
       - "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 "**/testdata/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 $(find . -type d -name 'testdata'); do
+        if [ -f "$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 }}
+
+  clean-test-observations:
+    desc: Remove all test observations (i.e. testdata/test-observations.json)
+    cmds:
+      - find . -type f -wholename "**/testdata/test-observations.json" | xargs rm -f

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 +48,8 @@ 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
 	)
 
@@ -58,3 +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_pull_source_test.snap

@@ -0,0 +1,8 @@
+
+[TestHandler_handlePullSourceStarted/snap_download_in_progress - 1]
+ ⠋ Downloading snap file...        ━━━━━━━━━━━━━━━━━━━━                example-app_1.0_amd64.snap 
+---
+
+[TestHandler_handlePullSourceStarted/snap_download_complete - 1]
+ ✔ Snap downloaded successfully                                        example-app_1.0_amd64.snap 
+---

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
 	}
 
@@ -219,7 +219,7 @@ func (l attestLogFrame) View() string {
 	sb := strings.Builder{}
 
 	for _, line := range l.lines {
-		sb.WriteString(fmt.Sprintf("     %s %s\n", l.borderStype.Render("░░"), line))
+		fmt.Fprintf(&sb, "     %s %s\n", l.borderStype.Render("░░"), line)
 	}
 
 	return sb.String()

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_cataloger_task_test.go

@@ -26,7 +26,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging task in progress",
 			eventFn: func(t *testing.T) partybus.Event {
-				value := &monitor.CatalogerTaskProgress{
+				value := &monitor.TaskProgress{
 					AtomicStage: progress.NewAtomicStage("some stage"),
 					Manual:      progress.NewManual(100),
 				}
@@ -48,7 +48,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging sub task in progress",
 			eventFn: func(t *testing.T) partybus.Event {
-				value := &monitor.CatalogerTaskProgress{
+				value := &monitor.TaskProgress{
 					AtomicStage: progress.NewAtomicStage("some stage"),
 					Manual:      progress.NewManual(100),
 				}
@@ -71,7 +71,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging sub task complete",
 			eventFn: func(t *testing.T) partybus.Event {
-				value := &monitor.CatalogerTaskProgress{
+				value := &monitor.TaskProgress{
 					AtomicStage: progress.NewAtomicStage("some stage"),
 					Manual:      progress.NewManual(100),
 				}
@@ -94,7 +94,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging sub task complete -- hide stage",
 			eventFn: func(t *testing.T) partybus.Event {
-				value := &monitor.CatalogerTaskProgress{
+				value := &monitor.TaskProgress{
 					AtomicStage: progress.NewAtomicStage("some stage"),
 					Manual:      progress.NewManual(100),
 				}
@@ -117,7 +117,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging sub task complete with removal",
 			eventFn: func(t *testing.T) partybus.Event {
-				value := &monitor.CatalogerTaskProgress{
+				value := &monitor.TaskProgress{
 					AtomicStage: progress.NewAtomicStage("some stage"),
 					Manual:      progress.NewManual(100),
 				}
@@ -162,7 +162,7 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 			}
 
 			// note: this line / event is not under test, only needed to show a sub status
-			kickoffEvent := &monitor.CatalogerTaskProgress{
+			kickoffEvent := &monitor.TaskProgress{
 				AtomicStage: progress.NewAtomicStage(""),
 				Manual:      progress.NewManual(-1),
 			}

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_pull_source.go

@@ -0,0 +1,37 @@
+package ui
+
+import (
+	tea "github.com/charmbracelet/bubbletea"
+	"github.com/wagoodman/go-partybus"
+
+	"github.com/anchore/bubbly/bubbles/taskprogress"
+	"github.com/anchore/syft/internal/log"
+	syftEventParsers "github.com/anchore/syft/syft/event/parsers"
+)
+
+func (m *Handler) handlePullSourceStarted(e partybus.Event) []tea.Model {
+	prog, info, err := syftEventParsers.ParsePullSourceStarted(e)
+	if err != nil {
+		log.WithFields("error", err).Debug("unable to parse event")
+		return nil
+	}
+
+	tsk := m.newTaskProgress(
+		taskprogress.Title{
+			Default: info.Title.Default,
+			Running: info.Title.WhileRunning,
+			Success: info.Title.OnSuccess,
+		},
+		taskprogress.WithStagedProgressable(prog),
+	)
+
+	tsk.HideOnSuccess = info.HideOnSuccess
+	tsk.HideStageOnSuccess = info.HideStageOnSuccess
+	tsk.HideProgressOnSuccess = true
+
+	if info.Context != "" {
+		tsk.Context = []string{info.Context}
+	}
+
+	return []tea.Model{tsk}
+}

cmd/syft/cli/ui/handle_pull_source_test.go

@@ -0,0 +1,121 @@
+package ui
+
+import (
+	"testing"
+	"time"
+
+	tea "github.com/charmbracelet/bubbletea"
+	"github.com/gkampitakis/go-snaps/snaps"
+	"github.com/stretchr/testify/require"
+	"github.com/wagoodman/go-partybus"
+	"github.com/wagoodman/go-progress"
+
+	"github.com/anchore/bubbly/bubbles/taskprogress"
+	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/event/monitor"
+)
+
+func TestHandler_handlePullSourceStarted(t *testing.T) {
+
+	tests := []struct {
+		name       string
+		eventFn    func(*testing.T) partybus.Event
+		iterations int
+	}{
+		{
+			name: "snap download in progress",
+			eventFn: func(t *testing.T) partybus.Event {
+				stage := progress.NewAtomicStage("")
+				manual := progress.NewManual(0)
+				manual.SetTotal(1000000) // 1MB file
+				manual.Set(250000)       // 25% downloaded
+
+				taskProg := &monitor.TaskProgress{
+					AtomicStage: stage,
+					Manual:      manual,
+				}
+
+				genericTask := monitor.GenericTask{
+					Title: monitor.Title{
+						Default:      "Downloading snap",
+						WhileRunning: "Downloading snap file...",
+						OnSuccess:    "Snap downloaded",
+					},
+					Context:            "example-app_1.0_amd64.snap",
+					HideOnSuccess:      false,
+					HideStageOnSuccess: true,
+					ID:                 "snap-download-123",
+				}
+
+				return partybus.Event{
+					Type:   event.PullSourceStarted,
+					Source: genericTask,
+					Value:  taskProg,
+				}
+			},
+			iterations: 5,
+		},
+		{
+			name: "snap download complete",
+			eventFn: func(t *testing.T) partybus.Event {
+				stage := progress.NewAtomicStage("")
+				manual := progress.NewManual(0)
+				manual.SetTotal(1000000) // 1MB file
+				manual.Set(1000000)      // 100% downloaded
+				manual.SetCompleted()
+
+				taskProg := &monitor.TaskProgress{
+					AtomicStage: stage,
+					Manual:      manual,
+				}
+
+				genericTask := monitor.GenericTask{
+					Title: monitor.Title{
+						Default:      "Downloading snap",
+						WhileRunning: "Downloading snap file...",
+						OnSuccess:    "Snap downloaded successfully",
+					},
+					Context:            "example-app_1.0_amd64.snap",
+					HideOnSuccess:      false,
+					HideStageOnSuccess: true,
+					ID:                 "snap-download-123",
+				}
+
+				return partybus.Event{
+					Type:   event.PullSourceStarted,
+					Source: genericTask,
+					Value:  taskProg,
+				}
+			},
+			iterations: 3,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			event := tt.eventFn(t)
+			handler := New(DefaultHandlerConfig())
+			handler.WindowSize = tea.WindowSizeMsg{
+				Width:  100,
+				Height: 80,
+			}
+
+			models := handler.handlePullSourceStarted(event)
+			require.Len(t, models, 1)
+			model := models[0]
+
+			tsk, ok := model.(taskprogress.Model)
+			require.True(t, ok)
+
+			gotModel := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
+				Time:     time.Now(),
+				Sequence: tsk.Sequence(),
+				ID:       tsk.ID(),
+			})
+
+			got := gotModel.View()
+
+			t.Log(got)
+			snaps.MatchSnapshot(t, got)
+		})
+	}
+}

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/cli/ui/handler.go

@@ -57,6 +57,7 @@ func New(cfg HandlerConfig) *Handler {
 		stereoscopeEvent.FetchImage:          simpleHandler(h.handleFetchImage),
 		syftEvent.FileIndexingStarted:        simpleHandler(h.handleFileIndexingStarted),
 		syftEvent.AttestationStarted:         simpleHandler(h.handleAttestationStarted),
+		syftEvent.PullSourceStarted:          simpleHandler(h.handlePullSourceStarted),
 		syftEvent.CatalogerTaskStarted:       h.handleCatalogerTaskStarted,
 	})
 

cmd/syft/internal/clio_setup_config.go

@@ -5,10 +5,8 @@ import (
 	"os"
 
 	"github.com/anchore/clio"
-	"github.com/anchore/go-logger"
-	gologgerredact "github.com/anchore/go-logger/adapter/redact"
 	"github.com/anchore/stereoscope"
-	handlers "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"
@@ -20,31 +18,20 @@ func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig
 		WithGlobalConfigFlag().   // add persistent -c <path> for reading an application config from
 		WithGlobalLoggingFlags(). // add persistent -v and -q flags tied to the logging config
 		WithConfigInRootHelp().   // --help on the root command renders the full application config in the help text
-		WithLoggerConstructor(
-			func(cfg clio.Config, store gologgerredact.Store) (logger.Logger, error) {
-				if !cfg.Log.AllowUI(os.Stdin) && !cfg.Log.Quiet {
-					// this is a special case where the user has not explicitly disabled the UI, but the UI is not allowed
-					// due to the lack of a tty. In this case, we should default to info level.
-					cfg.Log.Level = logger.InfoLevel
-					cfg.Log.Verbosity = 1
-				}
-				return clio.DefaultLogger(cfg, store)
-			},
-		).
 		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,
-						handlers.New(handlers.DefaultHandlerConfig()),
+						handler.New(handler.DefaultHandlerConfig()),
 					),
 					noUI,
-				}, nil
+				), nil
 			},
 		).
 		WithInitializers(
@@ -57,12 +44,12 @@ func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig
 				redact.Set(state.RedactStore)
 
 				log.Set(state.Logger)
-				stereoscope.SetLogger(state.Logger)
+				stereoscope.SetLogger(state.Logger.Nested("from", "stereoscope"))
 				return nil
 			},
 		).
-		WithPostRuns(func(state *clio.State, err error) {
-			stereoscope.Cleanup()
+		WithPostRuns(func(_ *clio.State, _ error) {
+			stereoscope.Cleanup() //nolint:staticcheck // we don't have access to the image object here
 		})
 	return clioCfg
 }

cmd/syft/internal/commands/attest.go

@@ -13,6 +13,7 @@ import (
 	"github.com/wagoodman/go-progress"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/stereoscope"
 	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
@@ -26,7 +27,6 @@ import (
 	"github.com/anchore/syft/syft/format/spdxtagvalue"
 	"github.com/anchore/syft/syft/format/syftjson"
 	"github.com/anchore/syft/syft/sbom"
-	"github.com/anchore/syft/syft/source"
 )
 
 const (
@@ -35,6 +35,7 @@ const (
 	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
 	attestHelp       = attestExample + attestSchemeHelp
 	cosignBinName    = "cosign"
+	jsonFormat       = "json"
 )
 
 type attestOptions struct {
@@ -43,6 +44,7 @@ type attestOptions struct {
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 	options.Catalog     `yaml:",inline" mapstructure:",squash"`
 	Attest              options.Attest `yaml:"attest" mapstructure:"attest"`
+	Cache               options.Cache  `json:"-" yaml:"cache" mapstructure:"cache"`
 }
 
 func Attest(app clio.Application) *cobra.Command {
@@ -51,7 +53,7 @@ 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>",
@@ -77,6 +79,7 @@ func defaultAttestOptions() attestOptions {
 		Output:      defaultAttestOutputOptions(),
 		UpdateCheck: options.DefaultUpdateCheck(),
 		Catalog:     options.DefaultCatalog(),
+		Cache:       options.DefaultCache(),
 	}
 }
 
@@ -91,14 +94,11 @@ func defaultAttestOutputOptions() options.Output {
 			string(spdxtagvalue.ID),
 		},
 		Outputs: []string{syftjson.ID.String()},
-		OutputFile: options.OutputFile{ // nolint:staticcheck
-			Enabled: false, // explicitly not allowed
-		},
+		// OutputFile is omitted (defaults to Enabled: false, explicitly not allowed for attestation)
 		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) {
@@ -135,7 +135,7 @@ 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)
 	}
@@ -239,7 +239,7 @@ func predicateType(outputName string) string {
 		return "cyclonedx"
 	case "spdx-tag-value", "spdx-tv":
 		return "spdx"
-	case "spdx-json", "json":
+	case "spdx-json", jsonFormat:
 		return "spdxjson"
 	default:
 		return "custom"
@@ -247,8 +247,11 @@ func predicateType(outputName string) string {
 }
 
 func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opts *options.Catalog, userInput string) (*sbom.SBOM, error) {
-	src, err := getSource(opts, userInput, onlyContainerImages)
+	if len(opts.From) > 1 || (len(opts.From) == 1 && opts.From[0] != stereoscope.RegistryTag) {
+		return nil, fmt.Errorf("attest requires use of an OCI registry directly, one or more of the specified sources is unsupported: %v", opts.From)
+	}
 
+	src, err := getSource(ctx, opts, userInput, stereoscope.RegistryTag)
 	if err != nil {
 		return nil, err
 	}
@@ -273,13 +276,6 @@ func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opt
 	return s, nil
 }
 
-func onlyContainerImages(d *source.Detection) error {
-	if !d.IsContainerImage() {
-		return fmt.Errorf("attestations are only supported for oci images at this time")
-	}
-	return nil
-}
-
 func commandExists(cmd string) bool {
 	_, err := exec.LookPath(cmd)
 	return err == nil

cmd/syft/internal/commands/cataloger.go

@@ -1,6 +1,8 @@
 package commands
 
 import (
+	"os"
+
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
@@ -16,5 +18,14 @@ func Cataloger(app clio.Application) *cobra.Command {
 		CatalogerList(app),
 	)
 
+	// only add cataloger info command if experimental capabilities feature is enabled
+	if isCapabilitiesExperimentEnabled() {
+		cmd.AddCommand(CatalogerCaps(app))
+	}
+
 	return cmd
 }
+
+func isCapabilitiesExperimentEnabled() bool {
+	return os.Getenv("SYFT_EXP_CAPABILITIES") == "true"
+}

cmd/syft/internal/commands/cataloger_info.go

@@ -0,0 +1,589 @@
+package commands
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"os"
+	"sort"
+	"strings"
+
+	"github.com/charmbracelet/lipgloss"
+	"github.com/olekukonko/tablewriter"
+	"github.com/olekukonko/tablewriter/renderer"
+	"github.com/olekukonko/tablewriter/tw"
+	"github.com/scylladb/go-set/strset"
+	"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/capabilities"
+	"github.com/anchore/syft/internal/task"
+	"github.com/anchore/syft/syft/cataloging"
+	_ "github.com/anchore/syft/syft/pkg/cataloger" // register all cataloger capabilities, otherwise the info command will not function
+)
+
+var (
+	yesStyle       = lipgloss.NewStyle().Foreground(lipgloss.Color("10")) // hi green
+	noStyle        = lipgloss.NewStyle().Foreground(lipgloss.Color("8"))  // dark grey
+	criteriaWidth  = 60
+	criteriaMargin = 10
+)
+
+// types for JSON cataloger info output
+type (
+	configFieldInfo struct {
+		Key         string `json:"key"`
+		Description string `json:"description"`
+		AppKey      string `json:"app_key,omitempty"`
+	}
+
+	configInfo struct {
+		Type   string            `json:"type"`
+		Fields []configFieldInfo `json:"fields,omitempty"`
+	}
+
+	detectorPackageInfo struct {
+		Class string   `json:"class"`
+		Name  string   `json:"name"`
+		PURL  string   `json:"purl"`
+		CPEs  []string `json:"cpes"`
+		Type  string   `json:"type"`
+	}
+
+	patternInfo struct {
+		Method          string                           `json:"method"`
+		Criteria        []string                         `json:"criteria"`
+		Conditions      []capabilities.DetectorCondition `json:"conditions,omitempty"`
+		Packages        []detectorPackageInfo            `json:"packages,omitempty"`
+		Comment         string                           `json:"comment,omitempty"`
+		PackageTypes    []string                         `json:"package_types,omitempty"`
+		JSONSchemaTypes []string                         `json:"json_schema_types,omitempty"`
+		Capabilities    capabilities.CapabilitySet       `json:"capabilities,omitempty"`
+	}
+
+	catalogerInfo struct {
+		Ecosystem    string                     `json:"ecosystem,omitempty"`
+		Name         string                     `json:"name"`
+		Type         string                     `json:"type"`
+		Selectors    []string                   `json:"selectors,omitempty"`
+		Deprecated   bool                       `json:"deprecated,omitempty"`
+		Patterns     []patternInfo              `json:"patterns,omitempty"`
+		Capabilities capabilities.CapabilitySet `json:"capabilities,omitempty"`
+		Config       *configInfo                `json:"config,omitempty"`
+	}
+)
+
+type catalogerInfoOptions struct {
+	Output                     string `yaml:"output" json:"output" mapstructure:"output"`
+	options.CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+	Names                      []string // cataloger names from args
+}
+
+func (o *catalogerInfoOptions) setNames(args []string) error {
+	o.Names = args
+
+	usingLegacyCatalogers := len(o.Catalogers) > 0
+	usingNewCatalogers := len(o.DefaultCatalogers) > 0 || len(o.SelectCatalogers) > 0
+	usingSelection := usingNewCatalogers || usingLegacyCatalogers
+
+	if usingSelection && len(o.Names) > 0 {
+		return fmt.Errorf("cannot use both cataloger name arguments and '--catalogers'/'--select-catalogers'/'--default-catalogers' flags")
+	}
+
+	if usingSelection {
+		// get all available package cataloger tasks
+		pkgTaskFactories := task.DefaultPackageTaskFactories()
+		allPkgTasks, err := pkgTaskFactories.Tasks(task.DefaultCatalogingFactoryConfig())
+		if err != nil {
+			return fmt.Errorf("unable to create pkg cataloger tasks: %w", err)
+		}
+
+		// make the selection based on user input
+		defaultCatalogers := options.FlattenAndSort(o.DefaultCatalogers)
+		selectCatalogers := options.FlattenAndSort(o.SelectCatalogers)
+		selectedTaskGroups, _, err := task.SelectInGroups(
+			[][]task.Task{allPkgTasks},
+			cataloging.NewSelectionRequest().
+				WithDefaults(defaultCatalogers...).
+				WithExpression(selectCatalogers...),
+		)
+
+		if err != nil {
+			return fmt.Errorf("unable to select catalogers: %w", err)
+		}
+
+		// build the list of cataloger names based on the selection
+		for _, g := range selectedTaskGroups {
+			for _, t := range g {
+				o.Names = append(o.Names, t.Name())
+			}
+		}
+	}
+	return nil
+}
+
+func (o *catalogerInfoOptions) AddFlags(flags clio.FlagSet) {
+	flags.StringVarP(&o.Output, "output", "o", "format to output the cataloger info (available: table, json)")
+}
+
+func defaultCatalogerCapsOptions() *catalogerInfoOptions {
+	return &catalogerInfoOptions{
+		CatalogerSelection: options.CatalogerSelection{
+			// this is different than the default behavior where a scan will automatically detect the default set
+			DefaultCatalogers: []string{"all"},
+		},
+	}
+}
+
+func CatalogerCaps(app clio.Application) *cobra.Command {
+	opts := defaultCatalogerCapsOptions()
+
+	return app.SetupCommand(&cobra.Command{
+		Use:     "info [OPTIONS] [CATALOGER_NAMES...]",
+		Short:   "Show detailed capabilities of catalogers",
+		Args:    cobra.ArbitraryArgs,
+		PreRunE: disableUI(app, os.Stdout),
+		RunE: func(_ *cobra.Command, args []string) error {
+			if err := opts.setNames(args); err != nil {
+				return err
+			}
+
+			return runCatalogerInfo(opts)
+		},
+	}, opts)
+}
+
+func runCatalogerInfo(opts *catalogerInfoOptions) error {
+	doc, err := capabilities.LoadDocument()
+	if err != nil {
+		return fmt.Errorf("unable to load cataloger capabilities: %w", err)
+	}
+
+	// filter by cataloger names if provided
+	catalogers := doc.Catalogers
+	if len(opts.Names) > 0 {
+		catalogers = filterCatalogersByName(catalogers, opts.Names)
+	}
+
+	report, err := catalogerInfoReport(opts, doc, catalogers)
+	if err != nil {
+		return fmt.Errorf("unable to generate cataloger info report: %w", err)
+	}
+
+	bus.Report(report)
+	bus.Notify("Note: the `cataloger info` command is experimental and may change or be removed without notice. Do not depend on its output in production systems.")
+
+	return nil
+}
+
+func filterCatalogersByName(catalogers []capabilities.CatalogerEntry, names []string) []capabilities.CatalogerEntry {
+	nameSet := make(map[string]bool)
+	for _, name := range names {
+		nameSet[name] = true
+	}
+
+	var filtered []capabilities.CatalogerEntry
+	for _, cat := range catalogers {
+		if nameSet[cat.Name] {
+			filtered = append(filtered, cat)
+		}
+	}
+	return filtered
+}
+
+func catalogerInfoReport(opts *catalogerInfoOptions, doc *capabilities.Document, catalogers []capabilities.CatalogerEntry) (string, error) {
+	switch opts.Output {
+	case jsonFormat:
+		return renderCatalogerInfoJSON(doc, catalogers)
+	case "table", "":
+		return renderCatalogerInfoTable(doc, catalogers), nil
+	default:
+		return "", fmt.Errorf("invalid output format %q, must be one of: table, json", opts.Output)
+	}
+}
+
+func renderCatalogerInfoJSON(doc *capabilities.Document, catalogers []capabilities.CatalogerEntry) (string, error) {
+	type document struct {
+		Catalogers []catalogerInfo `json:"catalogers"`
+	}
+
+	docOut := document{}
+
+	// sort catalogers by ecosystem then name
+	sort.Slice(catalogers, func(i, j int) bool {
+		if catalogers[i].Ecosystem != catalogers[j].Ecosystem {
+			return catalogers[i].Ecosystem < catalogers[j].Ecosystem
+		}
+		return catalogers[i].Name < catalogers[j].Name
+	})
+
+	for _, cat := range catalogers {
+		info := catalogerInfo{
+			Ecosystem:  cat.Ecosystem,
+			Name:       cat.Name,
+			Type:       cat.Type,
+			Selectors:  cat.Selectors,
+			Deprecated: isDeprecatedCataloger(cat.Selectors),
+		}
+
+		// convert parsers to patterns if available
+		info.Patterns = convertParsersToPatterns(cat.Parsers)
+
+		// if no parsers, use detectors instead
+		if len(info.Patterns) == 0 {
+			info.Capabilities = cat.Capabilities
+			info.Patterns = convertDetectorsToPatterns(cat.Detectors, cat.PackageTypes, cat.JSONSchemaTypes)
+		}
+
+		info.Config = getConfigInfoFromDocument(doc, cat.Config)
+
+		docOut.Catalogers = append(docOut.Catalogers, info)
+	}
+
+	by, err := json.Marshal(docOut)
+	return string(by), err
+}
+
+// isDeprecatedCataloger checks if a cataloger is deprecated based on its selectors
+func isDeprecatedCataloger(selectors []string) bool {
+	for _, selector := range selectors {
+		if selector == "deprecated" {
+			return true
+		}
+	}
+	return false
+}
+
+// convertDetectorPackages converts detector package info to the JSON output format
+func convertDetectorPackages(pkgs []capabilities.DetectorPackageInfo) []detectorPackageInfo {
+	var result []detectorPackageInfo
+	for _, pkg := range pkgs {
+		result = append(result, detectorPackageInfo{
+			Class: pkg.Class,
+			Name:  pkg.Name,
+			PURL:  pkg.PURL,
+			CPEs:  pkg.CPEs,
+			Type:  pkg.Type,
+		})
+	}
+	return result
+}
+
+// convertParsersToPatterns converts parser entries to pattern info for JSON output
+func convertParsersToPatterns(parsers []capabilities.Parser) []patternInfo {
+	var patterns []patternInfo
+	for _, parser := range parsers {
+		patterns = append(patterns, patternInfo{
+			Method:          string(parser.Detector.Method),
+			Criteria:        parser.Detector.Criteria,
+			Conditions:      parser.Detector.Conditions,
+			Packages:        convertDetectorPackages(parser.Detector.Packages),
+			Comment:         parser.Detector.Comment,
+			PackageTypes:    parser.PackageTypes,
+			JSONSchemaTypes: parser.JSONSchemaTypes,
+			Capabilities:    parser.Capabilities,
+		})
+	}
+	return patterns
+}
+
+// convertDetectorsToPatterns converts detector entries to pattern info for JSON output (for non-parser catalogers)
+func convertDetectorsToPatterns(detectors []capabilities.Detector, packageTypes, jsonSchemaTypes []string) []patternInfo {
+	var patterns []patternInfo
+	for _, det := range detectors {
+		patterns = append(patterns, patternInfo{
+			Method:          string(det.Method),
+			Criteria:        det.Criteria,
+			Conditions:      det.Conditions,
+			Packages:        convertDetectorPackages(det.Packages),
+			Comment:         det.Comment,
+			PackageTypes:    packageTypes,
+			JSONSchemaTypes: jsonSchemaTypes,
+		})
+	}
+	return patterns
+}
+
+// getConfigInfoFromDocument retrieves config info from the capabilities document
+func getConfigInfoFromDocument(doc *capabilities.Document, configType string) *configInfo {
+	if configType == "" {
+		return nil
+	}
+	configEntry, ok := doc.Configs[configType]
+	if !ok {
+		return nil
+	}
+	cfg := &configInfo{
+		Type: configType,
+	}
+	for _, field := range configEntry.Fields {
+		cfg.Fields = append(cfg.Fields, configFieldInfo{
+			Key:         field.Key,
+			Description: field.Description,
+			AppKey:      field.AppKey,
+		})
+	}
+	return cfg
+}
+
+func renderCatalogerInfoTable(_ *capabilities.Document, catalogers []capabilities.CatalogerEntry) string {
+	if len(catalogers) == 0 {
+		return noStyle.Render("No catalogers found")
+	}
+
+	// sort catalogers by ecosystem then name
+	sort.Slice(catalogers, func(i, j int) bool {
+		if catalogers[i].Ecosystem != catalogers[j].Ecosystem {
+			return catalogers[i].Ecosystem < catalogers[j].Ecosystem
+		}
+		return catalogers[i].Name < catalogers[j].Name
+	})
+
+	var buf bytes.Buffer
+
+	// create table with hierarchical merging
+	table := tablewriter.NewTable(&buf,
+		tablewriter.WithRenderer(renderer.NewBlueprint(tw.Rendition{
+			Settings: tw.Settings{Separators: tw.Separators{BetweenRows: tw.On}},
+		})),
+		tablewriter.WithConfig(tablewriter.Config{
+			Row: tw.CellConfig{
+				Formatting: tw.CellFormatting{MergeMode: tw.MergeHierarchical},
+				Alignment:  tw.CellAlignment{Global: tw.AlignLeft},
+			},
+		}),
+	)
+
+	// set headers
+	table.Header("ECOSYSTEM", "CATALOGER", "CRITERIA", "LICENSE", "NODES", "EDGES", "KINDS", "LISTING", "DIGESTS", "HASH")
+
+	// build rows for each cataloger
+	var data [][]string
+	for _, cat := range catalogers {
+		ecosystem := cat.Ecosystem
+		if ecosystem == "" {
+			ecosystem = "other"
+		}
+
+		if cat.Type == "generic" {
+			// generic catalogers: one row per parser
+			for _, parser := range cat.Parsers {
+				criteria := formatCriteria([]capabilities.Detector{parser.Detector})
+				row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, parser.Capabilities)
+				data = append(data, row)
+			}
+		} else {
+			// custom catalogers: one row with all detectors
+			criteria := formatCriteria(cat.Detectors)
+			row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, cat.Capabilities)
+			data = append(data, row)
+		}
+	}
+
+	// add all rows at once for better merging
+	_ = table.Bulk(data)
+	_ = table.Render()
+	return buf.String()
+}
+
+// buildTableRowFromCapabilities builds a table row from capability values
+func buildTableRowFromCapabilities(ecosystem, name, criteria string, caps capabilities.CapabilitySet) []string {
+	// extract capability default values
+	license := extractBoolCapability(caps, "license")
+	nodes := extractNodesCapability(caps)
+	edges := extractStringCapability(caps, "dependency.edges")
+	kinds := extractArrayCapability(caps, "dependency.kinds")
+	listing := extractBoolCapability(caps, "package_manager.files.listing")
+	digests := extractBoolCapability(caps, "package_manager.files.digests")
+	hash := extractBoolCapability(caps, "package_manager.package_integrity_hash")
+
+	return []string{
+		ecosystem,
+		name,
+		criteria,
+		license,
+		nodes,
+		edges,
+		kinds,
+		listing,
+		digests,
+		hash,
+	}
+}
+
+// extractBoolCapability extracts a boolean capability value and formats it
+func extractBoolCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			if b, ok := cap.Default.(bool); ok {
+				if b {
+					return yesStyle.Render("✔")
+				}
+				return noStyle.Render("·")
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractStringCapability extracts a string capability value
+func extractStringCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			if s, ok := cap.Default.(string); ok && s != "" {
+				return s
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractArrayCapability extracts an array capability value and formats it as comma-separated
+func extractArrayCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			// handle various array types
+			switch v := cap.Default.(type) {
+			case []string:
+				if len(v) > 0 {
+					return strings.Join(v, ", ")
+				}
+			case []interface{}:
+				if len(v) > 0 {
+					strs := make([]string, 0, len(v))
+					for _, item := range v {
+						strs = append(strs, fmt.Sprintf("%v", item))
+					}
+					return strings.Join(strs, ", ")
+				}
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractNodesCapability extracts dependency.depth and formats it
+// maps ["direct", "indirect"] to "transitive"
+func extractNodesCapability(caps capabilities.CapabilitySet) string {
+	for _, cap := range caps {
+		if cap.Name == "dependency.depth" {
+			switch v := cap.Default.(type) {
+			case []string:
+				return formatDepthStringArray(v)
+			case []interface{}:
+				return formatDepthInterfaceArray(v)
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// formatDepthStringArray formats a []string dependency depth value
+func formatDepthStringArray(v []string) string {
+	if len(v) == 0 {
+		return noStyle.Render("·")
+	}
+	if hasBothDirectAndIndirect(v) {
+		return "transitive"
+	}
+	return strings.Join(v, ", ")
+}
+
+// formatDepthInterfaceArray formats a []interface{} dependency depth value
+func formatDepthInterfaceArray(v []interface{}) string {
+	if len(v) == 0 {
+		return noStyle.Render("·")
+	}
+	strs := make([]string, 0, len(v))
+	for _, item := range v {
+		strs = append(strs, fmt.Sprintf("%v", item))
+	}
+	if hasBothDirectAndIndirect(strs) {
+		return "transitive"
+	}
+	return strings.Join(strs, ", ")
+}
+
+// hasBothDirectAndIndirect checks if a slice contains both "direct" and "indirect" strings
+func hasBothDirectAndIndirect(items []string) bool {
+	hasDirect := false
+	hasIndirect := false
+	for _, item := range items {
+		if item == "direct" {
+			hasDirect = true
+		}
+		if item == "indirect" {
+			hasIndirect = true
+		}
+	}
+	return hasDirect && hasIndirect
+}
+
+func formatCriteria(detectors []capabilities.Detector) string {
+	var allCriteria []string
+	methods := strset.New()
+
+	for _, det := range detectors {
+		allCriteria = append(allCriteria, det.Criteria...)
+		methods.Add(string(det.Method))
+	}
+
+	// smart word wrapping: wrap by word (criterion) up to criteriaWidth,
+	// allow up to criteriaWidth+criteriaMargin before forcing a new line
+	var lines []string
+	var currentLine []string
+	currentLength := 0
+
+	for _, criterion := range allCriteria {
+		// calculate length including the criterion plus ", " separator (except for first item)
+		itemLength := len(criterion)
+		if len(currentLine) > 0 {
+			itemLength += 2 // for ", "
+		}
+
+		newLength := currentLength + itemLength
+
+		if len(currentLine) > 0 && newLength > criteriaWidth {
+			// check if it's within margin
+			if newLength <= criteriaWidth+criteriaMargin {
+				// close enough, add it anyway
+				currentLine = append(currentLine, criterion)
+				currentLength = newLength
+			} else {
+				// too long, finalize current line and start new one
+				lines = append(lines, strings.Join(currentLine, ", "))
+				currentLine = []string{criterion}
+				currentLength = len(criterion)
+			}
+		} else {
+			// fits within width or first item
+			currentLine = append(currentLine, criterion)
+			currentLength = newLength
+		}
+	}
+
+	// add final line
+	if len(currentLine) > 0 {
+		lines = append(lines, strings.Join(currentLine, ", "))
+	}
+
+	methodsList := methods.List()
+	sort.Strings(methodsList)
+	method := strings.Join(methodsList, ", ")
+
+	if len(lines) == 0 {
+		return ""
+	}
+
+	joined := strings.Join(lines, "\n")
+	if method != string(capabilities.GlobDetection) {
+		return fmt.Sprintf("%s (%s)", joined, method)
+	}
+	return joined
+}

cmd/syft/internal/commands/cataloger_info_test.go

@@ -0,0 +1,373 @@
+package commands
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/internal/capabilities"
+)
+
+func Test_isDeprecatedCataloger(t *testing.T) {
+	tests := []struct {
+		name      string
+		selectors []string
+		want      bool
+	}{
+		{
+			name:      "empty selectors",
+			selectors: nil,
+			want:      false,
+		},
+		{
+			name:      "no deprecated selector",
+			selectors: []string{"python", "pip", "package"},
+			want:      false,
+		},
+		{
+			name:      "has deprecated selector",
+			selectors: []string{"python", "deprecated", "package"},
+			want:      true,
+		},
+		{
+			name:      "only deprecated selector",
+			selectors: []string{"deprecated"},
+			want:      true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := isDeprecatedCataloger(tt.selectors)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func Test_hasBothDirectAndIndirect(t *testing.T) {
+	tests := []struct {
+		name  string
+		items []string
+		want  bool
+	}{
+		{
+			name:  "empty slice",
+			items: nil,
+			want:  false,
+		},
+		{
+			name:  "only direct",
+			items: []string{"direct"},
+			want:  false,
+		},
+		{
+			name:  "only indirect",
+			items: []string{"indirect"},
+			want:  false,
+		},
+		{
+			name:  "both direct and indirect",
+			items: []string{"direct", "indirect"},
+			want:  true,
+		},
+		{
+			name:  "both with other items",
+			items: []string{"other", "direct", "more", "indirect", "stuff"},
+			want:  true,
+		},
+		{
+			name:  "unrelated items",
+			items: []string{"foo", "bar", "baz"},
+			want:  false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := hasBothDirectAndIndirect(tt.items)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func Test_filterCatalogersByName(t *testing.T) {
+	catalogers := []capabilities.CatalogerEntry{
+		{Name: "python-cataloger", Ecosystem: "python"},
+		{Name: "java-cataloger", Ecosystem: "java"},
+		{Name: "go-cataloger", Ecosystem: "golang"},
+		{Name: "npm-cataloger", Ecosystem: "javascript"},
+	}
+
+	tests := []struct {
+		name       string
+		catalogers []capabilities.CatalogerEntry
+		names      []string
+		want       []capabilities.CatalogerEntry
+	}{
+		{
+			name:       "empty names returns empty",
+			catalogers: catalogers,
+			names:      nil,
+			want:       nil,
+		},
+		{
+			name:       "single match",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+			},
+		},
+		{
+			name:       "multiple matches",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger", "java-cataloger"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+				{Name: "java-cataloger", Ecosystem: "java"},
+			},
+		},
+		{
+			name:       "no matches",
+			catalogers: catalogers,
+			names:      []string{"nonexistent"},
+			want:       nil,
+		},
+		{
+			name:       "partial matches",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger", "nonexistent"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := filterCatalogersByName(tt.catalogers, tt.names)
+			if diff := cmp.Diff(tt.want, got); diff != "" {
+				t.Errorf("filterCatalogersByName() mismatch (-want +got):\n%s", diff)
+			}
+		})
+	}
+}
+
+func Test_formatCriteria(t *testing.T) {
+	tests := []struct {
+		name      string
+		detectors []capabilities.Detector
+		want      string
+	}{
+		{
+			name:      "empty detectors",
+			detectors: nil,
+			want:      "",
+		},
+		{
+			name: "single glob detector",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py"},
+				},
+			},
+			want: "**/*.py",
+		},
+		{
+			name: "multiple criteria single detector",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py", "**/*.pyc", "**/requirements.txt"},
+				},
+			},
+			want: "**/*.py, **/*.pyc, **/requirements.txt",
+		},
+		{
+			name: "path detection shows method",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.PathDetection,
+					Criteria: []string{"/usr/bin/python"},
+				},
+			},
+			want: "/usr/bin/python (path)",
+		},
+		{
+			name: "mimetype detection shows method",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.MIMETypeDetection,
+					Criteria: []string{"application/x-python"},
+				},
+			},
+			want: "application/x-python (mimetype)",
+		},
+		{
+			name: "multiple detectors combine criteria",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py"},
+				},
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.pyc"},
+				},
+			},
+			want: "**/*.py, **/*.pyc",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := formatCriteria(tt.detectors)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func testDocument() *capabilities.Document {
+	return &capabilities.Document{
+		Configs: map[string]capabilities.CatalogerConfigEntry{
+			"test-config": {
+				Fields: []capabilities.CatalogerConfigFieldEntry{
+					{Key: "field1", Description: "test field"},
+				},
+			},
+		},
+	}
+}
+
+func Test_catalogerInfoReport(t *testing.T) {
+	tests := []struct {
+		name       string
+		opts       *catalogerInfoOptions
+		doc        *capabilities.Document
+		catalogers []capabilities.CatalogerEntry
+		wantErr    require.ErrorAssertionFunc
+		assertions func(t *testing.T, got string)
+	}{
+		{
+			name: "empty catalogers table",
+			opts: &catalogerInfoOptions{Output: "table"},
+			doc:  testDocument(),
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, "No catalogers found")
+			},
+		},
+		{
+			name: "empty catalogers json",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"catalogers":null`)
+			},
+		},
+		{
+			name: "single cataloger table output",
+			opts: &catalogerInfoOptions{Output: "table"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "test-cataloger",
+					Ecosystem: "test",
+					Type:      "custom",
+					Detectors: []capabilities.Detector{
+						{Method: capabilities.GlobDetection, Criteria: []string{"**/*.test"}},
+					},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, "test-cataloger")
+				assert.Contains(t, got, "ECOSYSTEM")
+				assert.Contains(t, got, "CATALOGER")
+			},
+		},
+		{
+			name: "single cataloger json output",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "test-cataloger",
+					Ecosystem: "test",
+					Type:      "custom",
+					Selectors: []string{"test", "custom"},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"name":"test-cataloger"`)
+				assert.Contains(t, got, `"ecosystem":"test"`)
+				assert.Contains(t, got, `"type":"custom"`)
+			},
+		},
+		{
+			name: "deprecated cataloger json output",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "old-cataloger",
+					Ecosystem: "legacy",
+					Type:      "custom",
+					Selectors: []string{"legacy", "deprecated"},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"deprecated":true`)
+			},
+		},
+		{
+			name:    "invalid output format",
+			opts:    &catalogerInfoOptions{Output: "invalid"},
+			doc:     testDocument(),
+			wantErr: require.Error,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = require.NoError
+			}
+
+			got, err := catalogerInfoReport(tt.opts, tt.doc, tt.catalogers)
+			tt.wantErr(t, err)
+
+			if err != nil {
+				return
+			}
+
+			if tt.assertions != nil {
+				tt.assertions(t, got)
+			}
+		})
+	}
+}
+
+func Test_formatCriteria_wordWrapping(t *testing.T) {
+	// test word wrapping behavior with long criteria lists
+	longCriteria := make([]string, 20)
+	for i := range longCriteria {
+		longCriteria[i] = "**/file" + strings.Repeat("x", 10)
+	}
+
+	detector := capabilities.Detector{
+		Method:   capabilities.GlobDetection,
+		Criteria: longCriteria,
+	}
+
+	got := formatCriteria([]capabilities.Detector{detector})
+
+	// should contain newlines for wrapping
+	assert.Contains(t, got, "\n")
+	// should contain all criteria (joined with ", " and possibly split across lines)
+	for _, c := range longCriteria {
+		assert.Contains(t, got, c)
+	}
+}

cmd/syft/internal/commands/cataloger_list.go

@@ -3,6 +3,7 @@ package commands
 import (
 	"encoding/json"
 	"fmt"
+	"os"
 	"sort"
 	"strings"
 
@@ -12,31 +13,39 @@ 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/capabilities"
 	"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 {
-	Output            string   `yaml:"output" json:"output" mapstructure:"output"`
-	DefaultCatalogers []string `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
-	SelectCatalogers  []string `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
-	ShowHidden        bool     `yaml:"show-hidden" json:"show-hidden" mapstructure:"show-hidden"`
+	Output                     string `yaml:"output" json:"output" mapstructure:"output"`
+	options.CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+	ShowHidden                 bool `yaml:"show-hidden" json:"show-hidden" mapstructure:"show-hidden"`
 }
 
 func (o *catalogerListOptions) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP(&o.Output, "output", "o", "format to output the cataloger list (available: table, json)")
 
-	flags.StringArrayVarP(&o.DefaultCatalogers, "override-default-catalogers", "", "override the default catalogers with an expression")
-
-	flags.StringArrayVarP(&o.SelectCatalogers, "select-catalogers", "", "select catalogers with an expression")
-
 	flags.BoolVarP(&o.ShowHidden, "show-hidden", "s", "show catalogers that have been de-selected")
 }
 
 func defaultCatalogerListOptions() *catalogerListOptions {
 	return &catalogerListOptions{
-		DefaultCatalogers: []string{"all"},
+		CatalogerSelection: options.CatalogerSelection{
+			// this is different than the default behavior where a scan will automatically detect the default set
+			DefaultCatalogers: []string{"all"},
+		},
 	}
 }
 
@@ -44,22 +53,29 @@ func CatalogerList(app clio.Application) *cobra.Command {
 	opts := defaultCatalogerListOptions()
 
 	return app.SetupCommand(&cobra.Command{
-		Use:   "list [OPTIONS]",
-		Short: "List available catalogers",
-		RunE: func(cmd *cobra.Command, args []string) error {
+		Use:     "list [OPTIONS]",
+		Short:   "List available catalogers",
+		PreRunE: disableUI(app, os.Stdout),
+		RunE: func(_ *cobra.Command, _ []string) error {
 			return runCatalogerList(opts)
 		},
 	}, opts)
 }
 
 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 +85,14 @@ 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.FlattenAndSort(opts.DefaultCatalogers)
+	selectCatalogers := options.FlattenAndSort(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)
@@ -81,13 +100,13 @@ func catalogerListReport(opts *catalogerListOptions, allTasks []task.Task) (stri
 	var report string
 
 	switch opts.Output {
-	case "json":
-		report, err = renderCatalogerListJSON(selectedTasks, selectionEvidence, opts.DefaultCatalogers, opts.SelectCatalogers)
+	case jsonFormat:
+		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 +117,14 @@ 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 +136,12 @@ 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 +185,56 @@ 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 +250,12 @@ 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 +263,32 @@ 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
@@ -236,29 +296,23 @@ 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) {
+	infos := capabilities.ExtractCatalogerInfo(tasks)
+
 	tagsByName := make(map[string][]string)
 	var names []string
 
-	for _, tsk := range tasks {
-		var tags []string
-		name := tsk.Name()
-
-		if s, ok := tsk.(task.Selector); ok {
-			set := strset.New(s.Selectors()...)
-			set.Remove(name)
-			tags = set.List()
-			sort.Strings(tags)
-		}
-
-		tagsByName[name] = tags
-		names = append(names, name)
+	for _, info := range infos {
+		tagsByName[info.Name] = info.Selectors
+		names = append(names, info.Name)
 	}
 
 	sort.Strings(names)

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()
 
@@ -40,14 +39,14 @@ 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",
 		}),
 		Args:    validateConvertArgs,
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(cmd *cobra.Command, args []string) error {
+		RunE: func(_ *cobra.Command, args []string) error {
 			restoreStdout := ui.CaptureStdoutToTraceLog()
 			defer restoreStdout()
 

cmd/syft/internal/commands/scan.go

@@ -10,9 +10,12 @@ import (
 
 	"github.com/hashicorp/go-multierror"
 	"github.com/spf13/cobra"
-	"gopkg.in/yaml.v3"
+	"go.yaml.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"
 	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
@@ -24,6 +27,7 @@ import (
 	"github.com/anchore/syft/syft"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
+	"github.com/anchore/syft/syft/source/sourceproviders"
 )
 
 const (
@@ -55,7 +59,9 @@ const (
 	nonImageSchemeHelp = `    {{.appName}} {{.command}} dir:path/to/yourproject                  read directly from a path on disk (any directory)
     {{.appName}} {{.command}} file:path/to/yourproject/file            read directly from a path on disk (any single file)
 `
-	scanSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp + nonImageSchemeHelp
+	modelSchemeHelp = `    {{.appName}} {{.command}} oci-model-registry:ai/llama3.2           scan an OCI model artifact from a registry (e.g. Docker Hub AI models)
+`
+	scanSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp + modelSchemeHelp + nonImageSchemeHelp
 
 	scanHelp = scanExample + scanSchemeHelp
 )
@@ -65,6 +71,7 @@ type scanOptions struct {
 	options.Output      `yaml:",inline" mapstructure:",squash"`
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 	options.Catalog     `yaml:",inline" mapstructure:",squash"`
+	Cache               options.Cache `json:"-" yaml:"cache" mapstructure:"cache"`
 }
 
 func defaultScanOptions() *scanOptions {
@@ -72,10 +79,10 @@ func defaultScanOptions() *scanOptions {
 		Output:      options.DefaultOutput(),
 		UpdateCheck: options.DefaultUpdateCheck(),
 		Catalog:     options.DefaultCatalog(),
+		Cache:       options.DefaultCache(),
 	}
 }
 
-//nolint:dupl
 func Scan(app clio.Application) *cobra.Command {
 	id := app.ID()
 
@@ -105,7 +112,7 @@ func (o *scanOptions) PostLoad() error {
 }
 
 func (o *scanOptions) validateLegacyOptionsNotUsed() error {
-	if o.Config.ConfigFile == "" {
+	if len(fangs.Flatten(o.ConfigFile)) == 0 {
 		return nil
 	}
 
@@ -117,32 +124,33 @@ 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
 }
 
@@ -150,27 +158,35 @@ 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)
 }
 
-// nolint:funlen
 func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, userInput string) error {
 	writer, err := opts.SBOMWriter()
 	if err != nil {
 		return err
 	}
 
-	src, err := getSource(&opts.Catalog, userInput)
+	sources := opts.From
+	if len(sources) == 0 {
+		// extract a scheme if it matches any provider tag; this is a holdover for compatibility, using the --from flag is recommended
+		explicitSource, newUserInput := stereoscope.ExtractSchemeSource(userInput, allSourceProviderTags()...)
+		if explicitSource != "" {
+			sources = append(sources, explicitSource)
+			userInput = newUserInput
+		}
+	}
 
+	src, err := getSource(ctx, &opts.Catalog, userInput, sources...)
 	if err != nil {
 		return err
 	}
@@ -199,23 +215,22 @@ func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, use
 	return nil
 }
 
-func getSource(opts *options.Catalog, userInput string, filters ...func(*source.Detection) error) (source.Source, error) {
-	detection, err := source.Detect(
-		userInput,
-		source.DetectConfig{
-			DefaultImageSource: opts.Source.Image.DefaultPullSource,
-		},
-	)
-	if err != nil {
-		return nil, fmt.Errorf("could not deteremine source: %w", err)
-	}
-
-	for _, filter := range filters {
-		if err := filter(detection); err != nil {
-			return nil, err
-		}
-	}
+func getSource(ctx context.Context, opts *options.Catalog, userInput string, sources ...string) (source.Source, error) {
+	cfg := syft.DefaultGetSourceConfig().
+		WithRegistryOptions(opts.Registry.ToOptions()).
+		WithAlias(source.Alias{
+			Name:     opts.Source.Name,
+			Version:  opts.Source.Version,
+			Supplier: opts.Source.Supplier,
+		}).
+		WithExcludeConfig(source.ExcludeConfig{
+			Paths: opts.Exclusions,
+		}).
+		WithBasePath(opts.Source.BasePath).
+		WithSources(sources...).
+		WithDefaultImagePullSource(opts.Source.Image.DefaultPullSource)
 
+	var err error
 	var platform *image.Platform
 
 	if opts.Platform != "" {
@@ -223,34 +238,20 @@ func getSource(opts *options.Catalog, userInput string, filters ...func(*source.
 		if err != nil {
 			return nil, fmt.Errorf("invalid platform: %w", err)
 		}
+		cfg = cfg.WithPlatform(platform)
 	}
 
-	hashers, err := file.Hashers(opts.Source.File.Digests...)
-	if err != nil {
-		return nil, fmt.Errorf("invalid hash algorithm: %w", err)
-	}
-
-	src, err := detection.NewSource(
-		source.DetectionSourceConfig{
-			Alias: source.Alias{
-				Name:    opts.Source.Name,
-				Version: opts.Source.Version,
-			},
-			RegistryOptions: opts.Registry.ToOptions(),
-			Platform:        platform,
-			Exclude: source.ExcludeConfig{
-				Paths: opts.Exclusions,
-			},
-			DigestAlgorithms: hashers,
-			BasePath:         opts.Source.BasePath,
-		},
-	)
-
-	if err != nil {
-		if userInput == "power-user" {
-			bus.Notify("Note: the 'power-user' command has been removed.")
+	if opts.Source.File.Digests != nil {
+		hashers, err := file.Hashers(opts.Source.File.Digests...)
+		if err != nil {
+			return nil, fmt.Errorf("invalid hash algorithm: %w", err)
 		}
-		return nil, fmt.Errorf("failed to construct source from user input %q: %w", userInput, err)
+		cfg = cfg.WithDigestAlgorithms(hashers...)
+	}
+
+	src, err := syft.GetSource(ctx, userInput, cfg)
+	if err != nil {
+		return nil, fmt.Errorf("could not determine source: %w", err)
 	}
 
 	return src, nil
@@ -398,13 +399,13 @@ 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) {
@@ -445,3 +446,7 @@ func getHintPhrase(expErr task.ErrInvalidExpression) string {
 func trimOperation(x string) string {
 	return strings.TrimLeft(x, "+-")
 }
+
+func allSourceProviderTags() []string {
+	return collections.TaggedValueSet[source.Provider]{}.Join(sourceproviders.All("", nil)...).Tags()
+}

cmd/syft/internal/commands/scan_test.go

@@ -19,30 +19,30 @@ func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
 		},
 		{
 			name: "config file with no legacy options",
-			cfg:  "test-fixtures/scan-configs/no-legacy-options.yaml",
+			cfg:  "testdata/scan-configs/no-legacy-options.yaml",
 		},
 		{
 			name:    "config file with default image pull source legacy option",
-			cfg:     "test-fixtures/scan-configs/with-default-pull-source.yaml",
+			cfg:     "testdata/scan-configs/with-default-pull-source.yaml",
 			wantErr: assertErrorContains("source.image.default-pull-source"),
 		},
 		{
 			name:    "config file with exclude-binary-overlap-by-ownership legacy option",
-			cfg:     "test-fixtures/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
+			cfg:     "testdata/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
 			wantErr: assertErrorContains("package.exclude-binary-overlap-by-ownership"),
 		},
 		{
 			name:    "config file with file string legacy option",
-			cfg:     "test-fixtures/scan-configs/with-file-string.yaml",
+			cfg:     "testdata/scan-configs/with-file-string.yaml",
 			wantErr: assertErrorContains("outputs"),
 		},
 		{
 			name: "config file with file section",
-			cfg:  "test-fixtures/scan-configs/with-file-section.yaml",
+			cfg:  "testdata/scan-configs/with-file-section.yaml",
 		},
 		{
 			name:    "config file with base-path legacy option",
-			cfg:     "test-fixtures/scan-configs/with-base-path.yaml",
+			cfg:     "testdata/scan-configs/with-base-path.yaml",
 			wantErr: assertErrorContains("source.base-path"),
 		},
 	}

cmd/syft/internal/commands/update.go

@@ -28,7 +28,7 @@ var latestAppVersionURL = struct {
 }
 
 func applicationUpdateCheck(id clio.Identification, check *options.UpdateCheck) func(cmd *cobra.Command, args []string) error {
-	return func(cmd *cobra.Command, args []string) error {
+	return func(_ *cobra.Command, _ []string) error {
 		if check.CheckForAppUpdate {
 			checkForApplicationUpdate(id)
 		}
@@ -107,7 +107,7 @@ func fetchLatestApplicationVersion(id clio.Identification) (*hashiVersion.Versio
 		return nil, fmt.Errorf("HTTP %d on fetching latest version: %s", resp.StatusCode, resp.Status)
 	}
 
-	versionBytes, err := io.ReadAll(resp.Body)
+	versionBytes, err := io.ReadAll(io.LimitReader(resp.Body, 500))
 	if err != nil {
 		return nil, fmt.Errorf("failed to read latest version: %w", err)
 	}

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/attest.go

@@ -12,8 +12,16 @@ type Attest struct {
 	Password secret `yaml:"password" json:"password" mapstructure:"password"`
 }
 
-var _ clio.FlagAdder = (*Attest)(nil)
+var _ interface {
+	clio.FlagAdder
+	clio.FieldDescriber
+} = (*Attest)(nil)
 
 func (o *Attest) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP((*string)(&o.Key), "key", "k", "the key to use for the attestation")
 }
+
+func (o *Attest) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.Password, `password to decrypt to given private key
+additionally responds to COSIGN_PASSWORD env var`)
+}

cmd/syft/internal/options/cache.go

@@ -0,0 +1,131 @@
+package options
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/adrg/xdg"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/go-homedir"
+	"github.com/anchore/syft/internal/cache"
+	"github.com/anchore/syft/internal/log"
+)
+
+// Cache provides configuration for the Syft caching behavior
+type Cache struct {
+	Dir string `yaml:"dir" mapstructure:"dir"`
+	TTL string `yaml:"ttl" mapstructure:"ttl"`
+}
+
+func (c *Cache) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&c.Dir, "root directory to cache any downloaded content; empty string will use an in-memory cache")
+	descriptions.Add(&c.TTL, "time to live for cached data; setting this to 0 will disable caching entirely")
+}
+
+func (c *Cache) PostLoad() error {
+	ttl, err := parseDuration(c.TTL)
+	if err != nil {
+		log.Warnf("unable to parse duration '%v', using default (%s) due to: %v", c.TTL, durationToString(defaultTTL()), err)
+		ttl = defaultTTL()
+	}
+	// if TTL is <= 0, disable caching entirely
+	if ttl <= 0 {
+		cache.SetManager(nil)
+		return nil
+	}
+	// if dir == "" but we have a TTL, use an in-memory cache
+	if c.Dir == "" {
+		cache.SetManager(cache.NewInMemory(ttl))
+		return nil
+	}
+	dir, err := homedir.Expand(c.Dir)
+	if err != nil {
+		log.Warnf("unable to expand cache directory %s: %v", c.Dir, err)
+		cache.SetManager(cache.NewInMemory(ttl))
+	} else {
+		m, err := cache.NewFromDir(dir, ttl)
+		if err != nil {
+			log.Warnf("unable to get filesystem cache at %s: %v", c.Dir, err)
+			cache.SetManager(cache.NewInMemory(ttl))
+		} else {
+			cache.SetManager(m)
+		}
+	}
+	return nil
+}
+
+var _ interface {
+	clio.PostLoader
+	clio.FieldDescriber
+} = (*Cache)(nil)
+
+func DefaultCache() Cache {
+	return Cache{
+		Dir: defaultDir(),
+		TTL: durationToString(defaultTTL()),
+	}
+}
+
+func defaultTTL() time.Duration {
+	return 7 * 24 * time.Hour
+}
+
+func defaultDir() string {
+	var err error
+	cacheRoot := xdg.CacheHome
+	if cacheRoot == "" {
+		cacheRoot, err = homedir.Dir()
+		if err != nil {
+			cacheRoot = os.TempDir()
+			log.Debugf("unable to get stable cache directory due to: %v, defaulting cache to temp dir: %s", err, cacheRoot)
+		} else {
+			cacheRoot = filepath.Join(cacheRoot, ".cache")
+		}
+	}
+
+	return filepath.Join(cacheRoot, "syft")
+}
+
+func durationToString(duration time.Duration) string {
+	days := int64(duration / (24 * time.Hour))
+	remain := duration % (24 * time.Hour)
+	out := ""
+	if days > 0 {
+		out = fmt.Sprintf("%vd", days)
+	}
+	if remain != 0 {
+		out += remain.String()
+	}
+	if out == "" {
+		return "0"
+	}
+	return out
+}
+
+func parseDuration(duration string) (time.Duration, error) {
+	whitespace := regexp.MustCompile(`\s+`)
+	duration = strings.ToLower(whitespace.ReplaceAllString(duration, ""))
+	parts := strings.SplitN(duration, "d", 2)
+	var days time.Duration
+	var remain time.Duration
+	var err error
+	if len(parts) > 1 {
+		numDays, daysErr := strconv.Atoi(parts[0])
+		if daysErr != nil {
+			return 0, daysErr
+		}
+		days = time.Duration(numDays) * 24 * time.Hour
+		if len(parts[1]) > 0 {
+			remain, err = time.ParseDuration(parts[1])
+		}
+	} else {
+		remain, err = time.ParseDuration(duration)
+	}
+	return days + remain, err
+}

cmd/syft/internal/options/cache_test.go

@@ -0,0 +1,323 @@
+package options
+
+import (
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/adrg/xdg"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/go-homedir"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/cache"
+)
+
+func Test_defaultDir(t *testing.T) {
+	tmpDir := filepath.Join(t.TempDir(), "cache-temp")
+	xdgCacheDir := filepath.Join(tmpDir, "fake-xdg-cache")
+	homeDir := filepath.Join(tmpDir, "fake-home")
+
+	tests := []struct {
+		name     string
+		env      map[string]string
+		expected string
+	}{
+		{
+			name: "no-xdg",
+			env: map[string]string{
+				"HOME": homeDir,
+			},
+			expected: homeDir,
+		},
+		{
+			name: "xdg-cache",
+			env: map[string]string{
+				"XDG_CACHE_HOME": xdgCacheDir,
+			},
+			expected: xdgCacheDir,
+		},
+	}
+
+	// capture all the initial environment variables to reset them before we reset library caches
+	env := map[string]string{
+		"HOME":            "",
+		"XDG_DATA_HOME":   "",
+		"XDG_DATA_DIRS":   "",
+		"XDG_CONFIG_HOME": "",
+		"XDG_CONFIG_DIRS": "",
+		"XDG_STATE_HOME":  "",
+		"XDG_CACHE_HOME":  "",
+		"XDG_RUNTIME_DIR": "",
+	}
+	for k := range env {
+		env[k] = os.Getenv(k)
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			restoreCache(t)
+
+			for k, v := range test.env {
+				patchEnv(t, k, v)
+			}
+			xdg.Reload()
+
+			got := defaultDir()
+
+			require.True(t, strings.HasPrefix(got, test.expected))
+		})
+	}
+}
+
+func Test_cacheOptions(t *testing.T) {
+	tmp := t.TempDir()
+	tests := []struct {
+		name string
+		opts Cache
+		test func(t *testing.T)
+	}{
+		{
+			name: "disable-1",
+			opts: Cache{
+				Dir: "some-dir",
+				TTL: "0",
+			},
+			test: func(t *testing.T) {
+				c := cache.GetManager().GetCache("test-disable-1", "v-disable-1")
+				err := c.Write("key-disable-1", strings.NewReader("some-value-disable-1"))
+				require.NoError(t, err)
+				rdr, err := c.Read("key-disable-1")
+				require.Nil(t, rdr)
+				require.Error(t, err)
+			},
+		},
+		{
+			name: "disable-2",
+			opts: Cache{
+				Dir: "some-dir",
+				TTL: "0s",
+			},
+			test: func(t *testing.T) {
+				c := cache.GetManager().GetCache("test-disable-2", "v-disable-2")
+				err := c.Write("key-disable-2", strings.NewReader("some-value-disable-2"))
+				require.NoError(t, err)
+				rdr, err := c.Read("key-disable-2")
+				require.Nil(t, rdr)
+				require.Error(t, err)
+			},
+		},
+
+		{
+			name: "disable-3",
+			opts: Cache{
+				Dir: "some-dir",
+				TTL: "0d",
+			},
+			test: func(t *testing.T) {
+				c := cache.GetManager().GetCache("test-disable-3", "v-disable-3")
+				err := c.Write("key-disable-3", strings.NewReader("some-value-disable-3"))
+				require.NoError(t, err)
+				rdr, err := c.Read("key-disable-3")
+				require.Nil(t, rdr)
+				require.Error(t, err)
+			},
+		},
+		{
+			name: "in-memory",
+			opts: Cache{
+				Dir: "",
+				TTL: "10m",
+			},
+			test: func(t *testing.T) {
+				c := cache.GetManager().GetCache("test-mem", "v-mem")
+				err := c.Write("key-mem", strings.NewReader("some-value-mem"))
+				require.NoError(t, err)
+				rdr, err := c.Read("key-mem")
+				require.NotNil(t, rdr)
+				defer internal.CloseAndLogError(rdr, "")
+				require.NoError(t, err)
+				data, err := io.ReadAll(rdr)
+				require.NoError(t, err)
+				require.Equal(t, "some-value-mem", string(data))
+				require.NoDirExists(t, filepath.Join("test-mem", "v-mem"))
+			},
+		},
+		{
+			name: "on disk",
+			opts: Cache{
+				Dir: tmp,
+				TTL: "10m",
+			},
+			test: func(t *testing.T) {
+				c := cache.GetManager().GetCache("test-disk", "v-disk")
+				err := c.Write("key-disk", strings.NewReader("some-value-disk"))
+				require.NoError(t, err)
+				rdr, err := c.Read("key-disk")
+				require.NotNil(t, rdr)
+				defer internal.CloseAndLogError(rdr, "")
+				require.NoError(t, err)
+				data, err := io.ReadAll(rdr)
+				require.NoError(t, err)
+				require.Equal(t, "some-value-disk", string(data))
+				require.DirExists(t, filepath.Join(tmp, "test-disk", "v-disk"))
+			},
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			original := cache.GetManager()
+			defer cache.SetManager(original)
+
+			err := test.opts.PostLoad()
+			require.NoError(t, err)
+
+			test.test(t)
+		})
+	}
+}
+
+func Test_parseDuration(t *testing.T) {
+	tests := []struct {
+		duration string
+		expect   time.Duration
+		err      require.ErrorAssertionFunc
+	}{
+		{
+			duration: "0d",
+			expect:   0,
+		},
+		{
+			duration: "0m",
+			expect:   0,
+		},
+		{
+			duration: "0s",
+			expect:   0,
+		},
+		{
+			duration: "0",
+			expect:   0,
+		},
+		{
+			duration: "1d",
+			expect:   24 * time.Hour,
+		},
+		{
+			duration: "7d",
+			expect:   7 * 24 * time.Hour,
+		},
+		{
+			duration: "365D",
+			expect:   365 * 24 * time.Hour,
+		},
+		{
+			duration: "7d1h1m1s",
+			expect:   7*24*time.Hour + time.Hour + time.Minute + time.Second,
+		},
+		{
+			duration: "7d  1h 1m 1s",
+			expect:   7*24*time.Hour + time.Hour + time.Minute + time.Second,
+		},
+		{
+			duration: "2h",
+			expect:   2 * time.Hour,
+		},
+		{
+			duration: "2h5m",
+			expect:   2*time.Hour + 5*time.Minute,
+		},
+		{
+			duration: "2h 5m",
+			expect:   2*time.Hour + 5*time.Minute,
+		},
+		{
+			duration: "d24h",
+			err:      require.Error,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.duration, func(t *testing.T) {
+			got, err := parseDuration(test.duration)
+			if test.err != nil {
+				test.err(t, err)
+				return
+			} else {
+				require.NoError(t, err)
+			}
+			require.Equal(t, test.expect, got)
+		})
+	}
+}
+
+func Test_durationToString(t *testing.T) {
+	tests := []struct {
+		duration time.Duration
+		expect   string
+		err      require.ErrorAssertionFunc
+	}{
+		{
+			expect:   "1d",
+			duration: 24 * time.Hour,
+		},
+		{
+			expect:   "7d",
+			duration: 7 * 24 * time.Hour,
+		},
+		{
+			expect:   "7d1h1m1s",
+			duration: 7*24*time.Hour + time.Hour + time.Minute + time.Second,
+		},
+		{
+			expect:   "2h0m0s",
+			duration: 2 * time.Hour,
+		},
+		{
+			expect:   "2h5m0s",
+			duration: 2*time.Hour + 5*time.Minute,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.expect, func(t *testing.T) {
+			got := durationToString(test.duration)
+			require.Equal(t, test.expect, got)
+		})
+	}
+}
+
+// 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

@@ -11,60 +11,82 @@ 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"
 	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
+	"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"
 )
 
 type Catalog struct {
 	// high-level cataloger configuration
-	Catalogers        []string            `yaml:"-" json:"catalogers" mapstructure:"catalogers"` // deprecated and not shown in yaml output
-	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"`
-	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"`
+	CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+
+	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)
 	Registry   registryConfig `yaml:"registry" json:"registry" mapstructure:"registry"`
+	From       []string       `yaml:"from" json:"from" mapstructure:"from"`
 	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(),
+		JavaScript:    defaultJavaScriptConfig(),
+		Python:        defaultPythonConfig(),
+		Nix:           defaultNixConfig(),
+		Dotnet:        defaultDotnetConfig(),
+		Golang:        defaultGolangConfig(),
+		Java:          defaultJavaConfig(),
 		File:          defaultFileConfig(),
 		Relationships: defaultRelationshipsConfig(),
+		Unknowns:      defaultUnknowns(),
 		Source:        defaultSourceConfig(),
-		Parallelism:   1,
+		Parallelism:   cfg.Parallelism,
 	}
 }
 
@@ -73,11 +95,14 @@ 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...),
 		)
@@ -98,6 +123,20 @@ 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 {
@@ -111,6 +150,17 @@ func (cfg Catalog) ToFilesConfig() filecataloging.Config {
 			Globs:              cfg.File.Content.Globs,
 			SkipFilesAboveSize: cfg.File.Content.SkipFilesAboveSize,
 		},
+		Executable: executable.Config{
+			MIMETypes: executable.DefaultConfig().MIMETypes,
+			Globs:     cfg.File.Executable.Globs,
+		},
+	}
+}
+
+func (cfg Catalog) ToLicenseConfig() cataloging.LicenseConfig {
+	return cataloging.LicenseConfig{
+		IncludeContent: cfg.License.Content,
+		Coverage:       cfg.License.Coverage,
 	}
 }
 
@@ -120,26 +170,47 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 		IncludeUnindexedArchives: cfg.Package.SearchUnindexedArchives,
 	}
 	return pkgcataloging.Config{
-		Binary: binary.DefaultCatalogerConfig(),
+		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),
+			WithNoProxy(cfg.Golang.NoProxy).
+			WithMainModuleVersion(
+				golang.DefaultMainModuleVersionConfig().
+					WithFromContents(cfg.Golang.MainModuleVersion.FromContents).
+					WithFromBuildSettings(cfg.Golang.MainModuleVersion.FromBuildSettings).
+					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
+			).
+			WithUsePackagesLib(*multiLevelOption(true, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.UsePackagesLib)),
 		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,
 		},
-		Python: python.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
+		Nix: nix.DefaultConfig().
+			WithCaptureOwnedFiles(cfg.Nix.CaptureOwnedFiles),
+		Python: python.DefaultCatalogerConfig().
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.SearchRemoteLicenses)).
+			WithPypiBaseURL(cfg.Python.PypiBaseURL).
+			WithGuessUnpinnedRequirements(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.GuessUnpinnedRequirements)),
 		JavaArchive: java.DefaultArchiveCatalogerConfig().
-			WithUseNetwork(cfg.Java.UseNetwork).
+			WithUseMavenLocalRepository(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseMavenLocalRepository)).
+			WithMavenLocalRepositoryDir(cfg.Java.MavenLocalRepositoryDir).
+			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),
 	}
 }
 
@@ -151,28 +222,20 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP(&cfg.Scope, "scope", "s",
 		fmt.Sprintf("selection of layers to catalog, options=%v", validScopeValues))
 
+	flags.StringArrayVarP(&cfg.From, "from", "",
+		"specify the source behavior to use (e.g. docker, registry, oci-dir, ...)")
+
 	flags.StringVarP(&cfg.Platform, "platform", "",
 		"an optional platform specifier for container image sources (e.g. 'linux/arm64', 'linux/arm64/v8', 'arm64', 'linux')")
 
 	flags.StringArrayVarP(&cfg.Exclusions, "exclude", "",
 		"exclude paths from being scanned using a glob expression")
 
-	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)
-		}
-	} else {
-		panic("unable to mark flags as deprecated")
-	}
-
-	flags.StringArrayVarP(&cfg.DefaultCatalogers, "override-default-catalogers", "",
-		"set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)")
-
-	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")
@@ -182,43 +245,104 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 
 	flags.StringVarP(&cfg.Source.BasePath, "base-path", "",
 		"base directory for scanning, no links will be followed above this directory, and all paths will be reported relative to this directory")
+
+	flags.StringVarP(&cfg.Source.Supplier, "source-supplier", "",
+		"the organization that supplied the component, which often may be the manufacturer, distributor, or repackager")
 }
 
 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 {
-	usingLegacyCatalogers := len(cfg.Catalogers) > 0
-	usingNewCatalogers := len(cfg.DefaultCatalogers) > 0 || len(cfg.SelectCatalogers) > 0
-
-	if usingLegacyCatalogers && usingNewCatalogers {
-		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)
-
-		return out
-	}
-
-	cfg.Catalogers = flatten(cfg.Catalogers)
-	cfg.DefaultCatalogers = flatten(cfg.DefaultCatalogers)
-	cfg.SelectCatalogers = flatten(cfg.SelectCatalogers)
-
-	// for backwards compatibility
-	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
+	cfg.From = Flatten(cfg.From)
+	cfg.Enrich = FlattenAndSort(cfg.Enrich)
 
 	s := source.ParseScope(cfg.Scope)
 	if s == source.UnknownScope {
 		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))
+		}
+	}
+	return out
+}
+
+func FlattenAndSort(commaSeparatedEntries []string) []string {
+	out := Flatten(commaSeparatedEntries)
+	sort.Strings(out)
+	return out
+}
+
+var publicisedEnrichmentOptions = []string{
+	"all",
+	task.Golang,
+	task.Java,
+	task.JavaScript,
+	task.Python,
+}
+
+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

@@ -8,7 +8,6 @@ import (
 )
 
 func TestCatalog_PostLoad(t *testing.T) {
-
 	tests := []struct {
 		name    string
 		options Catalog
@@ -16,47 +15,13 @@ func TestCatalog_PostLoad(t *testing.T) {
 		wantErr assert.ErrorAssertionFunc
 	}{
 		{
-			name: "mutually exclusive cataloger flags (cat / def-cat)",
+			name: "must have package overlap flag when pruning binaries by overlap",
 			options: Catalog{
-				Catalogers:        []string{"foo,bar", "42"},
-				DefaultCatalogers: []string{"some,thing"},
-				Scope:             "squashed",
+				Package:       packageConfig{ExcludeBinaryOverlapByOwnership: true},
+				Relationships: relationshipsConfig{PackageFileOwnershipOverlap: false},
 			},
 			wantErr: assert.Error,
 		},
-		{
-			name: "mutually exclusive cataloger flags (cat / sel-cat)",
-			options: Catalog{
-				Catalogers:       []string{"foo,bar", "42"},
-				SelectCatalogers: []string{"some,thing"},
-				Scope:            "squashed",
-			},
-			wantErr: assert.Error,
-		},
-		{
-			name: "allow old cataloger flags",
-			options: Catalog{
-				Catalogers: []string{"foo,bar"},
-				Scope:      "squashed",
-			},
-			assert: func(t *testing.T, options Catalog) {
-				assert.Equal(t, []string{"bar", "foo"}, options.DefaultCatalogers) // note: sorted order
-				assert.Equal(t, []string{"bar", "foo"}, options.Catalogers)        // note: sorted order
-			},
-		},
-		{
-			name: "allow new cataloger flags",
-			options: Catalog{
-				SelectCatalogers:  []string{"foo,bar", "42"},
-				DefaultCatalogers: []string{"some,thing"},
-				Scope:             "squashed",
-			},
-			assert: func(t *testing.T, options Catalog) {
-				assert.Equal(t, []string{"42", "bar", "foo"}, options.SelectCatalogers) // note: sorted order
-				assert.Equal(t, []string{"some", "thing"}, options.DefaultCatalogers)   // note: sorted order
-				assert.Empty(t, options.Catalogers)
-			},
-		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -70,3 +35,161 @@ func TestCatalog_PostLoad(t *testing.T) {
 		})
 	}
 }
+
+func TestFlatten(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "preserves order of comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "preserves order across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "trims whitespace",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "preserves reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"zebra", "yankee", "xray"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Flatten(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+func TestFlattenAndSort(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "sorts comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "sorts across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "trims whitespace and sorts",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "sorts reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"xray", "yankee", "zebra"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := FlattenAndSort(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+func Test_enrichmentEnabled(t *testing.T) {
+	tests := []struct {
+		directives string
+		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(FlattenAndSort([]string{test.directives}), test.test)
+			assert.Equal(t, test.expected, got)
+		})
+	}
+}

cmd/syft/internal/options/cataloger_selection.go

@@ -0,0 +1,57 @@
+package options
+
+import (
+	"fmt"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/fangs"
+)
+
+type CatalogerSelection struct {
+	// high-level cataloger configuration
+	Catalogers        []string `yaml:"-" json:"catalogers" mapstructure:"catalogers"` // deprecated and not shown in yaml output
+	DefaultCatalogers []string `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
+	SelectCatalogers  []string `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
+}
+
+var _ interface {
+	clio.FlagAdder
+	clio.PostLoader
+} = (*CatalogerSelection)(nil)
+
+func (cfg *CatalogerSelection) AddFlags(flags clio.FlagSet) {
+	flags.StringArrayVarP(&cfg.Catalogers, "catalogers", "",
+		"enable one or more package catalogers")
+
+	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
+		if err := pfp.PFlagSet().MarkDeprecated("catalogers", "use: override-default-catalogers and select-catalogers"); err != nil {
+			panic(err)
+		}
+	} else {
+		panic("unable to mark flags as deprecated")
+	}
+
+	flags.StringArrayVarP(&cfg.DefaultCatalogers, "override-default-catalogers", "",
+		"set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)")
+
+	flags.StringArrayVarP(&cfg.SelectCatalogers, "select-catalogers", "",
+		"add, remove, and filter the catalogers to be used")
+}
+
+func (cfg *CatalogerSelection) PostLoad() error {
+	usingLegacyCatalogers := len(cfg.Catalogers) > 0
+	usingNewCatalogers := len(cfg.DefaultCatalogers) > 0 || len(cfg.SelectCatalogers) > 0
+
+	if usingLegacyCatalogers && usingNewCatalogers {
+		return fmt.Errorf("cannot use both 'catalogers' and 'select-catalogers'/'default-catalogers' flags %q | %q %q", cfg.Catalogers, cfg.SelectCatalogers, cfg.DefaultCatalogers)
+	}
+
+	cfg.Catalogers = FlattenAndSort(cfg.Catalogers)
+	cfg.DefaultCatalogers = FlattenAndSort(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = FlattenAndSort(cfg.SelectCatalogers)
+
+	// for backwards compatibility
+	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
+
+	return nil
+}

cmd/syft/internal/options/cataloger_selection_test.go

@@ -0,0 +1,68 @@
+package options
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCatalogerSelection_PostLoad(t *testing.T) {
+
+	tests := []struct {
+		name    string
+		options CatalogerSelection
+		assert  func(t *testing.T, options CatalogerSelection)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "mutually exclusive cataloger flags (cat / def-cat)",
+			options: CatalogerSelection{
+				Catalogers:        []string{"foo,bar", "42"},
+				DefaultCatalogers: []string{"some,thing"},
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "mutually exclusive cataloger flags (cat / sel-cat)",
+			options: CatalogerSelection{
+				Catalogers:       []string{"foo,bar", "42"},
+				SelectCatalogers: []string{"some,thing"},
+			},
+			wantErr: assert.Error,
+		},
+		{
+			name: "allow old cataloger flags",
+			options: CatalogerSelection{
+				Catalogers: []string{"foo,bar"},
+			},
+			assert: func(t *testing.T, options CatalogerSelection) {
+				assert.Equal(t, []string{"bar", "foo"}, options.DefaultCatalogers) // note: sorted order
+				assert.Equal(t, []string{"bar", "foo"}, options.Catalogers)        // note: sorted order
+			},
+		},
+		{
+			name: "allow new cataloger flags",
+			options: CatalogerSelection{
+				SelectCatalogers:  []string{"foo,bar", "42"},
+				DefaultCatalogers: []string{"some,thing"},
+			},
+			assert: func(t *testing.T, options CatalogerSelection) {
+				assert.Equal(t, []string{"42", "bar", "foo"}, options.SelectCatalogers) // note: sorted order
+				assert.Equal(t, []string{"some", "thing"}, options.DefaultCatalogers)   // note: sorted order
+				assert.Empty(t, options.Catalogers)
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.options.PostLoad(), fmt.Sprintf("PostLoad()"))
+			if tt.assert != nil {
+				tt.assert(t, tt.options)
+			}
+		})
+	}
+}

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 +1,41 @@
+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"`
+
+	ExcludeProjectReferences bool `mapstructure:"exclude-project-references" json:"exclude-project-references" yaml:"exclude-project-references"`
+}
+
+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)`)
+	descriptions.Add(&o.ExcludeProjectReferences, `exclude packages with type "project" from deps.json output (these are internal project references, not NuGet packages)`)
+}
+
+func defaultDotnetConfig() dotnetConfig {
+	def := dotnet.DefaultCatalogerConfig()
+	return dotnetConfig{
+		DepPackagesMustHaveDLL:             def.DepPackagesMustHaveDLL,
+		DepPackagesMustClaimDLL:            def.DepPackagesMustClaimDLL,
+		PropagateDLLClaimsToParents:        def.PropagateDLLClaimsToParents,
+		RelaxDLLClaimsWhenBundlingDetected: def.RelaxDLLClaimsWhenBundlingDetected,
+		ExcludeProjectReferences:           def.ExcludeProjectReferences,
+	}
+}

cmd/syft/internal/options/file.go

@@ -6,13 +6,15 @@ import (
 
 	"github.com/scylladb/go-set/strset"
 
+	"github.com/anchore/clio"
 	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/syft/file"
 )
 
 type fileConfig struct {
-	Metadata fileMetadata `yaml:"metadata" json:"metadata" mapstructure:"metadata"`
-	Content  fileContent  `yaml:"content" json:"content" mapstructure:"content"`
+	Metadata   fileMetadata   `yaml:"metadata" json:"metadata" mapstructure:"metadata"`
+	Content    fileContent    `yaml:"content" json:"content" mapstructure:"content"`
+	Executable fileExecutable `yaml:"executable" json:"executable" mapstructure:"executable"`
 }
 
 type fileMetadata struct {
@@ -25,6 +27,10 @@ type fileContent struct {
 	Globs              []string `yaml:"globs" json:"globs" mapstructure:"globs"`
 }
 
+type fileExecutable struct {
+	Globs []string `yaml:"globs" json:"globs" mapstructure:"globs"`
+}
+
 func defaultFileConfig() fileConfig {
 	return fileConfig{
 		Metadata: fileMetadata{
@@ -34,9 +40,17 @@ func defaultFileConfig() fileConfig {
 		Content: fileContent{
 			SkipFilesAboveSize: 250 * intFile.KB,
 		},
+		Executable: fileExecutable{
+			Globs: nil,
+		},
 	}
 }
 
+var _ interface {
+	clio.PostLoader
+	clio.FieldDescriber
+} = (*fileConfig)(nil)
+
 func (c *fileConfig) PostLoad() error {
 	digests := strset.New(c.Metadata.Digests...).List()
 	sort.Strings(digests)
@@ -48,3 +62,17 @@ func (c *fileConfig) PostLoad() error {
 	}
 	return fmt.Errorf("invalid file metadata selection: %q", c.Metadata.Selection)
 }
+
+func (c *fileConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&c.Metadata.Selection, `select which files should be captured by the file-metadata cataloger and included in the SBOM. 
+Options include:
+ - "all": capture all files from the search space
+ - "owned-by-package": capture only files owned by packages
+ - "none", "": do not capture any files`)
+	descriptions.Add(&c.Metadata.Digests, `the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")`)
+
+	descriptions.Add(&c.Content.SkipFilesAboveSize, `skip searching a file entirely if it is above the given size (default = 1MB; unit = bytes)`)
+	descriptions.Add(&c.Content.Globs, `file globs for the cataloger to match on`)
+
+	descriptions.Add(&c.Executable.Globs, `file globs for the cataloger to match on`)
+}

cmd/syft/internal/options/format.go

@@ -3,19 +3,23 @@ package options
 import (
 	"github.com/anchore/clio"
 	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/spdxtagvalue"
 	"github.com/anchore/syft/syft/sbom"
 )
 
-var _ clio.PostLoader = (*Format)(nil)
+var _ interface {
+	clio.PostLoader
+	clio.FieldDescriber
+} = (*Format)(nil)
 
 // Format contains all user configuration for output formatting.
 type Format struct {
 	Pretty        *bool               `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-	Template      FormatTemplate      `yaml:"template" json:"template" mapstructure:"template"`
-	SyftJSON      FormatSyftJSON      `yaml:"json" json:"json" mapstructure:"json"`
-	SPDXJSON      FormatSPDXJSON      `yaml:"spdx-json" json:"spdx-json" mapstructure:"spdx-json"`
-	CyclonedxJSON FormatCyclonedxJSON `yaml:"cyclonedx-json" json:"cyclonedx-json" mapstructure:"cyclonedx-json"`
-	CyclonedxXML  FormatCyclonedxXML  `yaml:"cyclonedx-xml" json:"cyclonedx-xml" mapstructure:"cyclonedx-xml"`
+	Template      FormatTemplate      `yaml:"template" json:"template" mapstructure:"template" description:"all template format options"`
+	SyftJSON      FormatSyftJSON      `yaml:"json" json:"json" mapstructure:"json" description:"all syft-json format options"`
+	SPDXJSON      FormatSPDXJSON      `yaml:"spdx-json" json:"spdx-json" mapstructure:"spdx-json" description:"all spdx-json format options"`
+	CyclonedxJSON FormatCyclonedxJSON `yaml:"cyclonedx-json" json:"cyclonedx-json" mapstructure:"cyclonedx-json" description:"all cyclonedx-json format options"`
+	CyclonedxXML  FormatCyclonedxXML  `yaml:"cyclonedx-xml" json:"cyclonedx-xml" mapstructure:"cyclonedx-xml" description:"all cyclonedx-xml format options"`
 }
 
 func (o *Format) PostLoad() error {
@@ -27,6 +31,33 @@ func (o *Format) PostLoad() error {
 	return nil
 }
 
+func (o *Format) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.Pretty, `default value for all formats that support the "pretty" option (default is unset)`)
+	descriptions.Add(&o.SyftJSON, `all syft-json format options`)
+	descriptions.Add(&o.SyftJSON.Legacy, `transform any syft-json output to conform to an approximation of the v11.0.1 schema. This includes:
+- using the package metadata type names from before v12 of the JSON schema (changed in https://github.com/anchore/syft/pull/1983)
+
+Note: this will still include package types and fields that were added at or after json schema v12. This means
+that output might not strictly be json schema v11 compliant, however, for consumers that require time to port
+over to the final syft 1.0 json output this option can be used to ease the transition.
+
+Note: long term support for this option is not guaranteed (it may change or break at any time)`)
+
+	descriptions.Add(&o.Template.Path, `path to the template file to use when rendering the output with the template output format.
+Note that all template paths are based on the current syft-json schema`)
+	descriptions.Add(&o.Template.Legacy, `if true, uses the go structs for the syft-json format for templating.
+if false, uses the syft-json output for templating (which follows the syft JSON schema exactly).
+
+Note: long term support for this option is not guaranteed (it may change or break at any time)`)
+
+	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)
+	descriptions.Add(&o.CyclonedxJSON.Pretty, prettyDescription)
+	descriptions.Add(&o.CyclonedxXML.Pretty, prettyDescription)
+}
+
 func DefaultFormat() Format {
 	return Format{
 		Template:      DefaultFormatTemplate(),
@@ -41,9 +72,10 @@ func (o Format) Encoders() ([]sbom.FormatEncoder, error) {
 	return format.EncodersConfig{
 		Template:      o.Template.config(),
 		SyftJSON:      o.SyftJSON.config(),
-		SPDXJSON:      o.SPDXJSON.config(format.AllVersions),      // we support multiple versions, not just a single version
-		CyclonedxJSON: o.CyclonedxJSON.config(format.AllVersions), // we support multiple versions, not just a single version
-		CyclonedxXML:  o.CyclonedxXML.config(format.AllVersions),  // we support multiple versions, not just a single version
+		SPDXJSON:      o.SPDXJSON.config(format.AllVersions),                   // we support multiple versions, not just a single version
+		SPDXTagValue:  spdxtagvalue.EncoderConfig{Version: format.AllVersions}, // we support multiple versions, not just a single version
+		CyclonedxJSON: o.CyclonedxJSON.config(format.AllVersions),              // we support multiple versions, not just a single version
+		CyclonedxXML:  o.CyclonedxXML.config(format.AllVersions),               // we support multiple versions, not just a single version
 	}.Encoders()
 }
 

cmd/syft/internal/options/golang.go

@@ -1,9 +1,71 @@
 package options
 
+import (
+	"strings"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/golang"
+)
+
 type golangConfig struct {
-	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"`
-	Proxy                       string `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
-	NoProxy                     string `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
+	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"`
+	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"`
+	UsePackagesLib              *bool                         `json:"use-packages-lib" yaml:"use-packages-lib" mapstructure:"use-packages-lib"`
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*golangConfig)(nil)
+
+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`)
+	descriptions.Add(&o.NoProxy, `specifies packages which should not be fetched by proxy
+if unset this defaults to $GONOPROXY`)
+	descriptions.Add(&o.MainModuleVersion, `the go main module version discovered from binaries built with the go compiler will
+always show (devel) as the version. Use these options to control heuristics to guess
+a more accurate version from the binary.`)
+	descriptions.Add(&o.UsePackagesLib, `use the golang.org/x/tools/go/packages library, which executes golang tooling found on the path in addition to potential network access to get the most accurate results`)
+	descriptions.Add(&o.MainModuleVersion.FromLDFlags, `look for LD flags that appear to be setting a version (e.g. -X main.version=1.0.0)`)
+	descriptions.Add(&o.MainModuleVersion.FromBuildSettings, `use the build settings (e.g. vcs.version & vcs.time) to craft a v0 pseudo version 
+(e.g. v0.0.0-20220308212642-53e6d0aaf6fb) when a more accurate version cannot be found otherwise`)
+	descriptions.Add(&o.MainModuleVersion.FromContents, `search for semver-like strings in the binary contents`)
+}
+
+type golangMainModuleVersionConfig struct {
+	FromLDFlags       bool `json:"from-ld-flags" yaml:"from-ld-flags" mapstructure:"from-ld-flags"`
+	FromContents      bool `json:"from-contents" yaml:"from-contents" mapstructure:"from-contents"`
+	FromBuildSettings bool `json:"from-build-settings" yaml:"from-build-settings" mapstructure:"from-build-settings"`
+}
+
+func defaultGolangConfig() golangConfig {
+	def := golang.DefaultCatalogerConfig()
+	return golangConfig{
+		SearchLocalModCacheLicenses: nil, // this defaults to false, which is the API default
+		LocalModCacheDir:            def.LocalModCacheDir,
+		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{
+			FromLDFlags:       def.MainModuleVersion.FromLDFlags,
+			FromContents:      def.MainModuleVersion.FromContents,
+			FromBuildSettings: def.MainModuleVersion.FromBuildSettings,
+		},
+		UsePackagesLib: nil, // this defaults to true, which is the API default
+	}
 }

cmd/syft/internal/options/java.go

@@ -1,7 +1,49 @@
 package options
 
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/java"
+)
+
 type javaConfig struct {
-	UseNetwork              bool   `yaml:"use-network" json:"use-network" mapstructure:"use-network"`
-	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:                    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,
+	}
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*javaConfig)(nil)
+
+func (o *javaConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.UseNetwork, `enables Syft to use the network to fetch version and license information for packages when
+a parent or imported pom file is not found in the local maven repository.
+the pom files are downloaded from the remote Maven repository at 'maven-url'`)
+	descriptions.Add(&o.MavenURL, `maven repository to use, defaults to Maven central`)
+	descriptions.Add(&o.MaxParentRecursiveDepth, `depth to recursively resolve parent POMs, no limit if <= 0`)
+	descriptions.Add(&o.UseMavenLocalRepository, `use the local Maven repository to retrieve pom files. When Maven is installed and was previously used
+for building the software that is being scanned, then most pom files will be available in this
+repository on the local file system. this greatly speeds up scans. when all pom files are available
+in the local repository, then 'use-network' is not needed.
+TIP: If you want to download all required pom files to the local repository without running a full
+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

@@ -1,6 +1,40 @@
 package options
 
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/javascript"
+)
+
 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 {
+	clio.FieldDescriber
+} = (*javaScriptConfig)(nil)
+
+func defaultJavaScriptConfig() javaScriptConfig {
+	def := javascript.DefaultCatalogerConfig()
+	var includeDevDependencies *bool
+	if def.IncludeDevDependencies {
+		includeDevDependencies = &def.IncludeDevDependencies
+	}
+
+	var searchRemoteLicenses *bool
+	if def.SearchRemoteLicenses {
+		searchRemoteLicenses = &def.SearchRemoteLicenses
+	}
+	return javaScriptConfig{
+		NpmBaseURL:             def.NPMBaseURL,
+		SearchRemoteLicenses:   searchRemoteLicenses,
+		IncludeDevDependencies: includeDevDependencies,
+	}
+}
+
+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/linux_kernel.go

@@ -1,11 +1,25 @@
 package options
 
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/kernel"
+)
+
 type linuxKernelConfig struct {
 	CatalogModules bool `json:"catalog-modules" yaml:"catalog-modules" mapstructure:"catalog-modules"`
 }
 
 func defaultLinuxKernelConfig() linuxKernelConfig {
+	def := kernel.DefaultLinuxKernelCatalogerConfig()
 	return linuxKernelConfig{
-		CatalogModules: true,
+		CatalogModules: def.CatalogModules,
 	}
 }
+
+var _ interface {
+	clio.FieldDescriber
+} = (*linuxKernelConfig)(nil)
+
+func (o *linuxKernelConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.CatalogModules, `whether to catalog linux kernel modules found within lib/modules/** directories`)
+}

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"
@@ -24,6 +25,7 @@ import (
 var _ interface {
 	clio.FlagAdder
 	clio.PostLoader
+	clio.FieldDescriber
 } = (*Output)(nil)
 
 // Output has the standard output options syft accepts: multiple -o, --file, --template
@@ -70,6 +72,15 @@ func (o *Output) AddFlags(flags clio.FlagSet) {
 		fmt.Sprintf("report output format (<format>=<file> to output to a file), formats=%v", names))
 }
 
+func (o *Output) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.Outputs, `the output format(s) of the SBOM report (options: syft-table, syft-text, syft-json, spdx-json, ...)
+to specify multiple output files in differing formats, use a list:
+output:
+  - "syft-json=<syft-json-output-file>"
+  - "spdx-json=<spdx-json-output-file>"
+`)
+}
+
 func (o Output) SBOMWriter() (sbom.Writer, error) {
 	names := o.OutputNameSet()
 
@@ -79,7 +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`)
 	}
 
@@ -117,6 +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

@@ -1,6 +1,9 @@
 package options
 
-import "github.com/anchore/syft/syft/cataloging"
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/cataloging"
+)
 
 type packageConfig struct {
 	SearchUnindexedArchives         bool `yaml:"search-unindexed-archives" json:"search-unindexed-archives" mapstructure:"search-unindexed-archives"`
@@ -8,6 +11,20 @@ type packageConfig struct {
 	ExcludeBinaryOverlapByOwnership bool `yaml:"exclude-binary-overlap-by-ownership" json:"exclude-binary-overlap-by-ownership" mapstructure:"exclude-binary-overlap-by-ownership"` // exclude synthetic binary packages owned by os package files
 }
 
+var _ interface {
+	clio.FieldDescriber
+} = (*packageConfig)(nil)
+
+func (o *packageConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	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.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
+these packages are removed if an overlap with a non-synthetic package is found`)
+}
+
 func defaultPackageConfig() packageConfig {
 	c := cataloging.DefaultArchiveSearchConfig()
 	return packageConfig{