rename testing license scanner

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

.binny.yaml

@@ -1,39 +1,53 @@
 tools:
+  # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
   - name: binny
     version:
-      want: v0.6.2
+      want: v0.8.0
     method: github-release
     with:
       repo: anchore/binny
 
+  # used to produce SBOMs during release
+  - name: syft
+    version:
+      want: latest
+    method: github-release
+    with:
+      repo: anchore/syft
+
+  # used to sign mac binaries at release
   - name: quill
     version:
-      want: v0.4.1
+      want: v0.4.2
     method: github-release
     with:
       repo: anchore/quill
 
+  # used for linting
   - name: golangci-lint
     version:
-      want: v1.55.2
+      want: v1.61.0
     method: github-release
     with:
       repo: golangci/golangci-lint
 
+  # used for showing the changelog at release
   - name: glow
     version:
-      want: v1.5.1
+      want: v2.0.0
     method: github-release
     with:
       repo: charmbracelet/glow
 
+  # used for signing the checksums file at release
   - name: cosign
     version:
-      want: v2.2.1
+      want: v2.4.0
     method: github-release
     with:
       repo: sigstore/cosign
 
+  # used in integration tests to verify JSON schemas
   - name: yajsv
     version:
       want: v1.4.1
@@ -41,13 +55,15 @@ tools:
     with:
       repo: neilpa/yajsv
 
+  # used to release all artifacts
   - name: goreleaser
     version:
-      want: v1.22.1
+      want: v2.3.2
     method: github-release
     with:
       repo: goreleaser/goreleaser
 
+  # used for organizing imports during static analysis
   - name: gosimports
     version:
       want: v0.3.8
@@ -55,6 +71,7 @@ tools:
     with:
       repo: rinchsan/gosimports
 
+  # used at release to generate the changelog
   - name: chronicle
     version:
       want: v0.8.0
@@ -62,6 +79,7 @@ tools:
     with:
       repo: anchore/chronicle
 
+  # used during static analysis for license compliance
   - name: bouncer
     version:
       want: v0.4.0
@@ -69,6 +87,7 @@ tools:
     with:
       repo: wagoodman/go-bouncer
 
+  # used for showing benchmark testing
   - name: benchstat
     version:
       want: latest
@@ -81,16 +100,34 @@ tools:
       entrypoint: cmd/benchstat
       module: golang.org/x/perf
 
+  # used for running all local and CI tasks
   - name: task
     version:
-      want: v3.31.0
+      want: v3.39.2
     method: github-release
     with:
       repo: go-task/task
 
+  # used for triggering a release
   - name: gh
     version:
-      want: v2.39.2
+      want: v2.57.0
     method: github-release
     with:
       repo: cli/cli
+
+  # used to upload test fixture cache
+  - name: oras
+    version:
+      want: v1.2.0
+    method: github-release
+    with:
+      repo: oras-project/oras
+
+  # used to upload test fixture cache
+  - name: yq
+    version:
+      want: v4.44.3
+    method: github-release
+    with:
+      repo: mikefarah/yq

.bouncer.yaml

@@ -6,6 +6,7 @@ permit:
   - MPL.*
   - ISC
   - WTFPL
+  - Unlicense
 
 ignore-packages:
   # packageurl-go is released under the MIT license located in the root of the repo at /mit.LICENSE

.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: "1.22.x"
   go-dependencies:
     description: "Download go dependencies"
     required: true
@@ -13,28 +13,27 @@ inputs:
   cache-key-prefix:
     description: "Prefix all cache keys with this value"
     required: true
-    default: "1ac8281053"
-  compute-fingerprints:
-    description: "Compute test fixture fingerprints"
+    default: "181053ac82"
+  download-test-fixture-cache:
+    description: "Download test fixture cache from OCI and github actions"
     required: true
-    default: "true"
+    default: "false"
   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@cdcb36043654635271a94b9a6d1392de5bb323a7 # v5.0.1
       if: inputs.go-version != ''
       with:
         go-version: ${{ inputs.go-version }}
 
     - name: Restore tool cache
       id: tool-cache
-      uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+      uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 # v3.3.2
       with:
         path: ${{ github.workspace }}/.tool
         key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
@@ -54,8 +53,14 @@ runs:
       run: |
         DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y ${{ inputs.bootstrap-apt-packages }}
 
-    - name: Create all cache fingerprints
-      if: inputs.compute-fingerprints == 'true'
-      shell: bash
-      run: make fingerprints
+    - name: Restore ORAS cache from github actions
+      if: inputs.download-test-fixture-cache == 'true'
+      uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 # v3.3.2
+      with:
+        path: ${{ github.workspace }}/.tmp/oras-cache
+        key: ${{ inputs.cache-key-prefix }}-oras-cache
 
+    - name: Download test fixture cache
+      if: inputs.download-test-fixture-cache == 'true'
+      shell: bash
+      run: make download-test-fixture-cache

.github/dependabot.yml

@@ -1,12 +1,27 @@
 version: 2
+
 updates:
+
   - package-ecosystem: gomod
     directory: "/"
     schedule:
       interval: "daily"
     open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
       interval: "daily"
-    open-pull-requests-limit: 10
+    open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+
+  - package-ecosystem: "github-actions"
+    directory: "/.github/actions/boostrap"
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 10
+    labels:
+      - "dependencies"

.github/scripts/check_binary_fixture_size.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+# current limit for fixture size
+size=1000
+
+if [ $# -eq 0 ]; then
+  echo "Usage: $0 <directory>"
+  exit 1
+fi
+
+directory="$1"
+
+# Remove trailing slash using parameter expansion
+directory="${directory%/}"
+
+if [ ! -d "$directory" ]; then
+  echo "Directory not found: $directory"
+  exit 1
+fi
+
+found_large_files=0
+while IFS= read -r -d '' file; do
+  if [ $(wc -c < "$file") -gt $size ]; then
+    echo "File $file is greater than ${size} bytes."
+    found_large_files=1
+  fi
+done < <(find "$directory" -type f -print0)
+
+if [ "$found_large_files" -eq 1 ]; then
+  echo "Script failed: Some files are greater than ${size} bytes."
+  exit 1
+else
+  echo "All files in $directory and its subdirectories are ${size} bytes or smaller. Check passed."
+  exit 0
+fi
+

.github/scripts/find_cache_paths.py

@@ -0,0 +1,135 @@
+#!/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}")
+        show("Please ensure these paths exist and have content if they are directories.")
+        exit(1)
+
+    sha256_hash = calculate_sha256(fingerprint_contents)
+
+    paths_with_digests = []
+    for path in sorted(valid_paths):
+        fingerprint_file = f"{path}.fingerprint"
+        try:
+            if os.path.exists(fingerprint_file):
+                file_digest = calculate_file_sha256(fingerprint_file)
+
+                # Parse the fingerprint file to get the digest/path tuples
+                with open(fingerprint_file, 'r') as f:
+                    fingerprint_content = f.read().strip()
+                    input_map = parse_fingerprint_contents(fingerprint_content)
+
+                paths_with_digests.append({
+                    "path": path,
+                    "digest": file_digest,
+                    "input": input_map
+                })
+
+        except Exception as e:
+            show(f"Error processing {fingerprint_file}: {e}")
+            raise e
+
+
+    output = {
+        "digest": sha256_hash,
+        "paths": paths_with_digests
+    }
+
+    content = json.dumps(output, indent=2, sort_keys=True)
+
+    if file_path:
+        with open(file_path, 'w') as f:
+            f.write(content)
+
+    print(content)
+
+
+if __name__ == "__main__":
+    file_path = None
+    if len(sys.argv) > 1:
+        file_path = sys.argv[1]
+    main(file_path)

.github/scripts/fingerprint_docker_fixtures.py

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

.github/scripts/labeler.py

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

@@ -2,8 +2,8 @@
 set -ue
 
 BIN="syft"
-DISTDIR=$1
-VERSION=$2
+VERSION_FILE="VERSION"
+VERSION=$1
 
 # 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
@@ -12,10 +12,9 @@ if [[ "$(curl -SsL https://api.github.com/repos/anchore/${BIN}/releases/tags/${V
    exit 0
 fi
 
-echo "creating and publishing version file"
+echo "creating and publishing version file (${VERSION})"
 
 # 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

.github/workflows/benchmark-testing.yaml

@@ -17,13 +17,13 @@ jobs:
     # the job by event.
     steps:
       - name: Checkout code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
       - name: Restore base benchmark result
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
           path: test/results/benchmark-main.txt
           # use base sha for PR or new commit hash for main push in benchmark result key
@@ -39,13 +39,13 @@ jobs:
           OUTPUT="${OUTPUT//$'\r'/'%0D'}" # URL encode all '\r' characters
           echo "result=$OUTPUT" >> $GITHUB_OUTPUT
 
-      - uses: actions/upload-artifact@a8a3f3ad30e3422c9c7b888a15615d19a852ae32 # v3.1.3
+      - uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874 # v4.4.0
         with:
           name: benchmark-test-results
           path: test/results/**/*
 
       - name: Update PR benchmark results comment
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
         continue-on-error: true
         with:
           header: benchmark

.github/workflows/codeql-analysis.yml

@@ -20,7 +20,7 @@ permissions:
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04-4core-16gb
 
     permissions:
       security-events: write
@@ -36,16 +36,16 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
     - name: Install Go
-      uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      uses: actions/setup-go@0a12ed9d6a96ab950c8f026ed9f722fe0da7ef32 #v5.0.2
       with:
         go-version-file: go.mod
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@407ffafae6a767df3e0230c3df91b6443ae8df75 #v2.22.8
+      uses: github/codeql-action/init@294a9d92911152fe08befb9ec03e240add280cb3 #v3.26.8
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -56,7 +56,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@407ffafae6a767df3e0230c3df91b6443ae8df75 #v2.22.8
+      uses: github/codeql-action/autobuild@294a9d92911152fe08befb9ec03e240add280cb3 #v3.26.8
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -70,4 +70,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@407ffafae6a767df3e0230c3df91b6443ae8df75 #v2.22.8
+      uses: github/codeql-action/analyze@294a9d92911152fe08befb9ec03e240add280cb3 #v3.26.8

.github/workflows/dependabot-automation.yaml

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

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

@@ -30,7 +30,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
 
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - run: python .github/scripts/labeler.py
         env:
@@ -40,7 +40,7 @@ jobs:
 
       - name: Delete existing comment
         if: ${{ hashFiles( env.CI_COMMENT_FILE ) == '' }}
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
         with:
           header: ${{ env.COMMENT_HEADER }}
           hide: true
@@ -48,7 +48,7 @@ jobs:
 
       - name: Add comment
         if: ${{ hashFiles( env.CI_COMMENT_FILE ) != '' }}
-        uses: marocchino/sticky-pull-request-comment@efaaab3fd41a9c3de579aba759d2552635e590fd #v2.8.0
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
         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@d3667e5ae14df19579e4414897498e3e88f2f458 # v3.10.0
-        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@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
-        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-version-file.yaml

@@ -0,0 +1,31 @@
+name: "Release: version file"
+
+on:
+
+  workflow_dispatch:
+    inputs:
+      version:
+        description: release version to update the version file with (prefixed with v)
+        required: true
+
+  workflow_call:
+    inputs:
+      version:
+        type: string
+        description: release version to update the version file with (prefixed with v)
+        required: true
+
+jobs:
+
+  release:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+
+      - name: Update version file
+        run: make ci-release-version-file
+        env:
+          RELEASE_VERSION: ${{ github.event.inputs.version }}
+          # 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/workflows/release.yaml

@@ -15,7 +15,15 @@ jobs:
     environment: release
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+
+      - 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
@@ -24,7 +32,7 @@ jobs:
           git tag ${{ 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 +41,7 @@ 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 +50,7 @@ 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 +59,7 @@ 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 +68,7 @@ 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 +77,7 @@ 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 }}
@@ -94,8 +102,10 @@ jobs:
     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@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
         with:
           fetch-depth: 0
 
@@ -103,13 +113,13 @@ jobs:
         uses: ./.github/actions/bootstrap
 
       - name: Login to Docker Hub
-        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d  #v3.0.0
+        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567  #v3.3.0
         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@9780b0c442fbb1117ed29e0efdff1e18412f7567  #v3.3.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -136,17 +146,14 @@ 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@fd74a6fb98a204a1ad35bbfae0122c1a302ff88b #v0.15.0
+      - uses: anchore/sbom-action@61119d458adab75f756bc0b9e4bde25725f86a7a #v0.17.2
         continue-on-error: true
         with:
           artifact-name: sbom.spdx.json
 
-      - uses: 8398a7/action-slack@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
         continue-on-error: true
         with:
           status: ${{ job.status }}
@@ -155,3 +162,10 @@ jobs:
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
         if: ${{ success() }}
+
+  release-version-file:
+    needs: [release]
+    uses: ./.github/workflows/release-version-file.yaml
+    with:
+      version: ${{ github.event.inputs.version }}
+    secrets: inherit

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

@@ -0,0 +1,39 @@
+name: "Test fixture cache: publish"
+
+on:
+  workflow_dispatch:
+  schedule:
+    # run nightly at 4AM UTC
+    - cron: "0 4 * * *"
+
+permissions:
+  contents: read
+
+jobs:
+
+  Publish:
+    name: "Publish test fixture image cache"
+    # we use this runner to get enough storage space for docker images and fixture cache
+    runs-on: ubuntu-22.04-4core-16gb
+    permissions:
+      packages: write
+    steps:
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          # we want to rebuild the cache with no previous state
+          download-test-fixture-cache: false
+
+      - name: Run all tests
+        run: make test
+        env:
+          # we want to rebuild the cache with no previous state
+          DOWNLOAD_TEST_FIXTURE_CACHE: "false"
+
+      - name: Login to GitHub Container Registry (ORAS)
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | .tool/oras login ghcr.io -u ${{ github.actor }} --password-stdin
+
+      - name: Publish test fixture cache
+        run: make upload-test-fixture-cache

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

@@ -13,13 +13,12 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
         with:
           bootstrap-apt-packages: ""
-          compute-fingerprints: "false"
           go-dependencies: false
 
       - name: "Update tool versions"
@@ -50,7 +49,7 @@ jobs:
           app_id: ${{ secrets.TOKEN_APP_ID }}
           private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@5e914681df9dc83aa4e4905692ca88beb2f9e91f #v7.0.5
         with:
           signoff: true
           delete-branch: true

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

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -33,7 +33,7 @@ jobs:
           app_id: ${{ secrets.TOKEN_APP_ID }}
           private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@5e914681df9dc83aa4e4905692ca88beb2f9e91f #v7.0.5
         with:
           signoff: true
           delete-branch: true
@@ -45,7 +45,7 @@ jobs:
             Update CPE dictionary index based on the latest available CPE dictionary
           token: ${{ steps.generate-token.outputs.token }}
 
-      - uses: 8398a7/action-slack@fbd6aa58ba854a740e11a35d0df80cb5d12101d8 #v3.15.1
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
         with:
           status: ${{ job.status }}
           fields: workflow,eventName,job

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

@@ -17,9 +17,9 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
-      - uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      - uses: actions/setup-go@0a12ed9d6a96ab950c8f026ed9f722fe0da7ef32 #v5.0.2
         with:
           go-version: ${{ env.GO_VERSION }}
           stable: ${{ env.GO_STABLE_VERSION }}
@@ -44,7 +44,7 @@ jobs:
           app_id: ${{ secrets.TOKEN_APP_ID }}
           private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
-      - uses: peter-evans/create-pull-request@153407881ec5c347639a548ade7d8ad1d6740e38 #v5.0.2
+      - uses: peter-evans/create-pull-request@5e914681df9dc83aa4e4905692ca88beb2f9e91f #v7.0.5
         with:
           signoff: true
           delete-branch: true

.github/workflows/validations.yaml

@@ -17,7 +17,7 @@ jobs:
     name: "Static analysis"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -31,40 +31,12 @@ jobs:
     name: "Unit tests"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore Java test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
         with:
-          path: syft/pkg/cataloger/java/test-fixtures/java-builds/packages
-          key: ${{ runner.os }}-unit-java-cache-${{ hashFiles( 'syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint' ) }}
-
-      - name: Restore RPM test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: syft/pkg/cataloger/redhat/test-fixtures/rpms
-          key: ${{ runner.os }}-unit-rpm-cache-${{ hashFiles( 'syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint' ) }}
-
-      - name: Restore go binary test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: syft/pkg/cataloger/golang/test-fixtures/archs/binaries
-          key: ${{ runner.os }}-unit-go-binaries-cache-${{ hashFiles( 'syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint' ) }}
-
-      - name: Restore binary cataloger test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/dynamic
-          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@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: syft/pkg/cataloger/kernel/test-fixtures/cache
-          key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
+          download-test-fixture-cache: true
 
       - name: Run unit tests
         run: make unit
@@ -75,20 +47,16 @@ jobs:
     name: "Integration tests"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - 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@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: ${{ github.workspace }}/test/integration/test-fixtures/cache
-          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('test/integration/test-fixtures/cache.fingerprint') }}
-
       - name: Run integration tests
         run: make integration
 
@@ -97,7 +65,7 @@ jobs:
     name: "Build snapshot artifacts"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -110,7 +78,7 @@ jobs:
       # why not use actions/upload-artifact? It is very slow (3 minutes to upload ~600MB of data, vs 10 seconds with this approach).
       # see https://github.com/actions/upload-artifact/issues/199 for more info
       - name: Upload snapshot artifacts
-        uses: actions/cache/save@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache/save@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         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
@@ -127,14 +95,16 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        with:
+          download-test-fixture-cache: true
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
           path: |
             snapshot
@@ -150,13 +120,6 @@ jobs:
       - name: Run comparison tests (Linux)
         run: make compare-linux
 
-      - name: Restore install.sh test image cache
-        id: install-test-image-cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: ${{ github.workspace }}/test/install/cache
-          key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
-
       - name: Load test image cache
         if: steps.install-test-image-cache.outputs.cache-hit == 'true'
         run: make install-test-cache-load
@@ -175,19 +138,21 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: macos-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - name: Install Cosign
+        uses: sigstore/cosign-installer@v3.6.0
+
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - 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@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
           path: |
             snapshot
@@ -200,13 +165,6 @@ jobs:
         if: steps.snapshot-cache.outputs.cache-hit != 'true'
         run: echo "unable to download snapshots from previous job" && false
 
-      - name: Restore docker image cache for compare testing
-        id: mac-compare-testing-cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
-        with:
-          path: image.tar
-          key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
-
       - name: Run comparison tests (Mac)
         run: make compare-mac
 
@@ -220,20 +178,16 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 #v4.1.1
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-
-      - name: Restore CLI test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
         with:
-          path: ${{ github.workspace }}/test/cli/test-fixtures/cache
-          key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}
+          download-test-fixture-cache: true
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 #v4.0.2
         with:
           path: |
             snapshot
@@ -248,3 +202,22 @@ jobs:
 
       - name: Run CLI Tests (Linux)
         run: make cli
+
+
+  Cleanup-Cache:
+    name: "Cleanup snapshot cache"
+    if: github.event.pull_request.head.repo.full_name == github.repository
+    runs-on: ubuntu-20.04
+    permissions:
+      actions: write
+    needs:
+      - Acceptance-Linux
+      - Acceptance-Mac
+      - Cli-Linux
+    steps:
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 #v4.1.7
+
+      - name: Delete snapshot cache
+        run: gh cache delete "snapshot-build-${{ github.run_id }}"
+        env:
+          GH_TOKEN: ${{ github.token }}

.gitignore

@@ -32,7 +32,6 @@ VERSION
 /test/results
 coverage.txt
 *.log
-test/integration/test-fixtures/**/go.sum
 
 # probable archives
 .images

.golangci.yaml

@@ -12,10 +12,10 @@ linters:
   enable:
     - asciicheck
     - bodyclose
+    - copyloopvar
     - dogsled
     - dupl
     - errcheck
-    - exportloopref
     - funlen
     - gocognit
     - goconst
@@ -30,6 +30,7 @@ linters:
     - ineffassign
     - misspell
     - nakedret
+    - nolintlint
     - revive
     - staticcheck
     - stylecheck
@@ -49,10 +50,21 @@ linters-settings:
     # If lower than 0, disable the check.
     # Default: 40
     statements: 50
+  gocritic:
+    enabled-checks:
+      - deferInLoop
+      - ruleguard
+    settings:
+      ruleguard:
+        rules: "test/rules/rules.go"
+  gosec:
+    excludes:
+      - G115
 output:
   uniq-by-line: false
 run:
   timeout: 10m
+  tests: false
 
 # do not enable...
 #    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
@@ -72,7 +84,6 @@ 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

.goreleaser.yaml

@@ -1,3 +1,5 @@
+version: 2
+
 release:
   prerelease: auto
   draft: false
@@ -80,7 +82,7 @@ nfpms:
       - deb
 
 brews:
-  - tap:
+  - repository:
       owner: anchore
       name: homebrew-syft
       token: "{{.Env.GITHUB_BREW_TOKEN}}"
@@ -247,3 +249,28 @@ docker_manifests:
       - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
       - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
       - ghcr.io/anchore/syft:{{.Tag}}-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"
+    args:
+      - "scan"
+      - "$artifact"
+      - "--output"
+      - "json=$document"
+
+signs:
+  - cmd: .tool/cosign
+    signature: "${artifact}.sig"
+    certificate: "${artifact}.pem"
+    args:
+      - "sign-blob"
+      - "--oidc-issuer=https://token.actions.githubusercontent.com"
+      - "--output-certificate=${certificate}"
+      - "--output-signature=${signature}"
+      - "${artifact}"
+      - "--yes"
+    artifacts: checksum

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[opensource@anchore.com](mailto:opensource@anchore.com).
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

DEVELOPING.md

@@ -83,7 +83,7 @@ Syft's core library is implemented in the `syft` package and subpackages, where
 - the `syft` package contains a single function that can take a `source.Source` object and catalog it, producing an `sbom.SBOM` object
 - the `syft/format` package contains the ability to encode and decode SBOMs to and from different SBOM formats (such as SPDX and CycloneDX)
 
-The `cmd` pacakge at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
+The `cmd` package at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
 ```mermaid
 sequenceDiagram
     participant main as cmd/syft/main
@@ -212,7 +212,7 @@ Finally, here is an example of where the package construction is done within the
 - [The APK package constructor itself](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/package.go#L12-L27)
 
 Interested in building a new cataloger? Checkout the [list of issues with the `new-cataloger` label](https://github.com/anchore/syft/issues?q=is%3Aopen+is%3Aissue+label%3Anew-cataloger+no%3Aassignee)!
-If you have questions about implementing a cataloger feel free to file an issue or reach out to us [on slack](https://anchore.com/slack)!
+If you have questions about implementing a cataloger feel free to file an issue or reach out to us [on discourse](https://anchore.com/discourse)!
 
 
 #### Searching for files
@@ -234,7 +234,7 @@ rough outline how that works:
   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 `test/integration`, these tests focus on the behavior surfaced by the common library 
+- `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 

Makefile

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

README.md

@@ -2,25 +2,27 @@
     <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;
+</p>
 
 ![syft-demo](https://user-images.githubusercontent.com/590471/90277200-2a253000-de33-11ea-893f-32c219eea11a.gif)
 
+## Introduction
+
+Syft is a powerful and easy-to-use open-source tool for generating Software Bill of Materials (SBOMs) for container images and filesystems. It provides detailed visibility into the packages and dependencies in your software, helping you manage vulnerabilities, license compliance, and software supply chain security.
+
+Syft development is sponsored by [Anchore](https://anchore.com/), and is released under the [Apache-2.0 License](https://github.com/anchore/syft?tab=Apache-2.0-1-ov-file). For commercial support options with Syft or Grype, please [contact Anchore](https://get.anchore.com/contact/).
+
 ## 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
@@ -29,6 +31,94 @@ For commercial support options with Syft or Grype, please [contact Anchore](http
 - 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.
 
+## Installation
+
+Syft binaries are provided for Linux, macOS and Windows.
+
+### Recommended
+> ```bash 
+> curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
+> ```
+
+Install script options:
+-	`-b`: Specify a custom installation directory (defaults to `./bin`)
+-	`-d`: More verbose logging levels (`-d` for debug, `-dd` for trace)
+-	`-v`: Verify the signature of the downloaded artifact before installation (requires [`cosign`](https://github.com/sigstore/cosign) to be installed)
+
+### Homebrew
+```bash
+brew install syft
+```
+
+### Scoop
+
+```powershell
+scoop install syft
+```
+
+### Chocolatey
+
+The chocolatey distribution of Syft is community-maintained and not distributed by the Anchore team
+
+```powershell
+choco install syft -y
+```
+
+### Nix
+
+**Note**: Nix packaging of Syft is [community maintained](https://github.com/NixOS/nixpkgs/blob/master/pkgs/tools/admin/syft/default.nix). Syft is available in the [stable channel](https://wiki.nixos.org/wiki/Nix_channels#The_official_channels) since NixOS `22.05`.
+
+```bash
+nix-env -i syft
+```
+
+... or, just try it out in an ephemeral nix shell:
+
+```bash
+nix-shell -p syft
+```
+
+## 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
+```
+
+### 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 1.6 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-xml@1.5`: A XML report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-json@1.5`: A JSON report conforming to the [CycloneDX 1.5 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.
+
+Note that flags using the @<version> can be used for earlier versions of each specification as well.
+
 ### Supported Ecosystems
 
 - Alpine (apk)
@@ -54,758 +144,37 @@ For commercial support options with Syft or Grype, please [contact Anchore](http
 - Ruby (gem)
 - Rust (cargo.lock)
 - Swift (cocoapods, swift-package-manager)
-
-## Installation
-
-**Note**: Currently, Syft is built only for Linux, macOS and Windows.
-
-### Recommended
-```bash
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
-```
-
-... or, you can specify a release version and destination directory for the installation:
-
-```
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b <DESTINATION_DIR> <RELEASE_VERSION>
-```
-
-### 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`.
-
-```bash
-nix-env -i syft
-```
-
-... or, just try it out in an ephemeral nix shell:
-
-```bash
-nix-shell -p syft
-```
-
-## Getting started
-
-### SBOM
-
-To generate an SBOM for a container image:
-
-```
-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`:
-
-```
-syft <image> --scope all-layers
-```
-
-### Supported sources
-
-Syft can generate a SBOM from a variety of sources:
-
-```
-# 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).
-
-### Default Cataloger Configuration by scan type
-
-Syft uses different default sets of catalogers depending on what it is scanning: a container image or a directory on disk. The default 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 indicates software actually installed on an image.
-
-However, if you are scanning a directory, Syft doesn't assume that all relevant software is installed, and will use catalogers that can identify declared dependencies that may not yet be installed on the final system: for example, dependencies listed in a Python requirements.txt.
-
-You can override the list of enabled/disabled catalogers by using the "catalogers" keyword in the [Syft configuration file](https://github.com/anchore/syft#configuration).
-
-##### Image Scanning:
-- alpmdb
-- apkdb
-- binary
-- dotnet-deps
-- dotnet-portable-executable
-- dpkgdb
-- go-module-binary
-- graalvm-native-image
-- java
-- javascript-package
-- linux-kernel
-- nix-store
-- php-composer-installed
-- portage
-- python-package
-- rpm-db
-- ruby-gemspec
-- sbom
-
-##### Directory Scanning:
-- alpmdb
-- apkdb
-- binary
-- cocoapods
-- conan
-- dartlang-lock
-- dotnet-deps
-- dotnet-portable-executable
-- dpkgdb
-- elixir-mix-lock
-- erlang-rebar-lock
-- go-mod-file
-- go-module-binary
-- graalvm-native-image
-- haskell
-- java
-- java-gradle-lockfile
-- java-pom
-- javascript-lock
-- linux-kernel
-- nix-store
-- php-composer-lock
-- portage
-- python-index
-- python-package
-- rpm-db
-- rpm-file
-- ruby-gemfile
-- rust-cargo-lock
-- sbom
-- swift-package-manager
-
-##### Non Default:
-- cargo-auditable-binary
-
-### 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, ...)
-# same as -o, --output, and SYFT_OUTPUT env var
-# to specify multiple output files in differing formats, use a list:
-# output:
-#   - "syft-json=<syft-json-output-file>"
-#   - "spdx-json=<spdx-json-output-file>"
-output: "syft-table"
-
-# suppress all output (except for the SBOM report)
-# same as -q ; SYFT_QUIET env var
-quiet: false
-
-# same as --file; write output report to a file (default is to write to stdout)
-file: ""
-
-# enable/disable checking for application updates on startup
-# same as SYFT_CHECK_FOR_APP_UPDATE env var
-check-for-app-update: true
-
-# allows users to specify which image source should be used to generate the sbom
-# valid values are: registry, docker, podman
-default-image-pull-source: ""
-
-# a list of globs to exclude from scanning. same as --exclude ; for example:
-# exclude:
-#   - "/etc/**"
-#   - "./out/**/*.json"
-exclude: []
-
-# allows users to exclude synthetic binary packages from the sbom
-# these packages are removed if an overlap with a non-synthetic package is found
-exclude-binary-overlap-by-ownership: true
-
-# os and/or architecture to use when referencing container images (e.g. "windows/armv6" or "arm64")
-# same as --platform; SYFT_PLATFORM env var
-platform: ""
-
-# set the list of package catalogers to use when generating the SBOM
-# default = empty (cataloger set determined automatically by the source type [image or file/directory])
-# catalogers:
-#   - alpm-db-cataloger
-#   - apkdb-cataloger
-#   - binary-cataloger
-#   - cargo-auditable-binary-cataloger
-#   - cocoapods-cataloger
-#   - conan-cataloger
-#   - dartlang-lock-cataloger
-#   - dotnet-deps-cataloger
-#   - dotnet-portable-executable-cataloger
-#   - dpkg-db-cataloger
-#   - elixir-mix-lock-cataloger
-#   - erlang-rebar-lock-cataloger
-#   - go-module-file-cataloger
-#   - go-module-binary-cataloger
-#   - graalvm-native-image-cataloger
-#   - haskell-cataloger
-#   - java-cataloger
-#   - java-gradle-lockfile-cataloger
-#   - java-pom-cataloger
-#   - javascript-lock-cataloger
-#   - javascript-package-cataloger
-#   - linux-kernel-cataloger
-#   - nix-store-cataloger
-#   - php-composer-installed-cataloger
-#   - php-composer-lock-cataloger
-#   - portage-cataloger
-#   - python-package-cataloger
-#   - python-installed-package-cataloger
-#   - rpm-db-cataloger
-#   - rpm-archive-cataloger
-#   - ruby-gemfile-cataloger
-#   - ruby-installed-gemspec-cataloger
-#   - rust-cargo-lock-cataloger
-#   - sbom-cataloger
-#   - spm-cataloger
-catalogers:
-
-
-# all format configuration
-format:
- 
-  # default value for all formats that support the "pretty" option (default is unset)
-  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
-    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.
-    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.
-    # same as -t ; SYFT_TEMPLATE_PATH env var
-    path: ""
-
-  # 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
-    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
-     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
-     pretty: false
-
-
-# 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
-
-  cataloger:
-    # enable/disable cataloging of packages
-    # SYFT_PACKAGE_CATALOGER_ENABLED env var
-    enabled: true
-
-    # the search space to look for packages (options: all-layers, squashed)
-    # same as -s ; SYFT_PACKAGE_CATALOGER_SCOPE env var
-    scope: "squashed"
-
-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
-
-file-contents:
-  cataloger:
-    # enable/disable cataloging of file contents
-    # SYFT_FILE_CONTENTS_CATALOGER_ENABLED env var
-    enabled: true
-
-    # the search space to look for file contents (options: all-layers, squashed)
-    # SYFT_FILE_CONTENTS_CATALOGER_SCOPE env var
-    scope: "squashed"
-
-  # skip searching a file entirely if it is above the given size (default = 1MB; unit = bytes)
-  # SYFT_FILE_CONTENTS_SKIP_FILES_ABOVE_SIZE env var
-  skip-files-above-size: 1048576
-
-  # file globs for the cataloger to match on
-  # SYFT_FILE_CONTENTS_GLOBS env var
-  globs: []
-
-file-metadata:
-  cataloger:
-    # enable/disable cataloging of file metadata
-    # SYFT_FILE_METADATA_CATALOGER_ENABLED env var
-    enabled: true
-
-    # the search space to look for file metadata (options: all-layers, squashed)
-    # SYFT_FILE_METADATA_CATALOGER_SCOPE env var
-    scope: "squashed"
-
-  # the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-  # SYFT_FILE_METADATA_DIGESTS env var
-  digests: ["sha256"]
-
-# maximum number of workers used to process the list of package catalogers in parallel
-parallelism: 1
-
-# options that apply to all scan sources
-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: ""
-   
-  # 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"]
-
-# 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
-  # same as SYFT_LOG_STRUCTURED env var
-  structured: false
-
-  # the log level; note: detailed logging suppress the ETUI
-  # same as SYFT_LOG_LEVEL env var
-  level: "error"
-
-  # location to write the log file (default is not to have a log file)
-  # same as SYFT_LOG_FILE env var
-  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
-```
+- Wordpress plugins
+
+## Documentation
+
+Our [wiki](https://github.com/anchore/syft/wiki) contains further details on the following topics:
+
+* [Supported Sources](https://github.com/anchore/syft/wiki/supported-sources)
+* [File Selection](https://github.com/anchore/syft/wiki/file-selection)
+* [Excluding file paths](https://github.com/anchore/syft/wiki/excluding-file-paths)
+* [Output formats](https://github.com/anchore/syft/wiki/output-formats)
+* [Package Cataloger Selection](https://github.com/anchore/syft/wiki/package-cataloger-selection) 
+  * [Concepts](https://github.com/anchore/syft/wiki/package-cataloger-selection#concepts)
+  * [Examples](https://github.com/anchore/syft/wiki/package-cataloger-selection#examples)
+* [Using templates](https://github.com/anchore/syft/wiki/using-templates)
+* [Multiple outputs](https://github.com/anchore/syft/wiki/multiple-outputs)
+* [Private Registry Authentication](https://github.com/anchore/syft/wiki/private-registry-authentication)
+  * [Local Docker Credentials](https://github.com/anchore/syft/wiki/private-registry-authentication#local-docker)
+  * [Docker Credentials in Kubernetes](https://github.com/anchore/syft/wiki/private-registry-authentication#docker-credentials-in-kubernetes)
+* [Attestation (experimental)](https://github.com/anchore/syft/wiki/attestation)
+  * [Keyless Support](https://github.com/anchore/syft/wiki/attestation#keyless-support)
+  * [Local private key support](https://github.com/anchore/syft/wiki/attestation#local-private-key-support)
+  * [Adding an SBOM to an image as an attestation using Syft](https://github.com/anchore/syft/wiki/attestation#adding-an-sbom-to-an-image-as-an-attestation-using-syft)
+* [Configuration](https://github.com/anchore/syft/wiki/configuration)
+
+## Contributing
+
+Check out our [contributing](/CONTRIBUTING.md) guide and [developer](/DEVELOPING.md) docs.
+
+## Syft Team Meetings
+
+The Syft Team hold 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!

SECURITY.md

@@ -0,0 +1,32 @@
+# Security Policy
+
+## Supported Versions
+
+<!-- Use this section to tell people about which versions of your project are
+currently being supported with security updates.
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 5.1.x   | :white_check_mark: |
+| 5.0.x   | :x:                |
+| 4.0.x   | :white_check_mark: |
+| < 4.0   | :x:                |
+
+-->
+
+Security updates are applied only to the most recent release, try to always be up to date.
+
+## Reporting a Vulnerability
+
+<!-- Use this section to tell people how to report a vulnerability.
+
+Tell them where to go, how often they can expect to get an update on a
+reported vulnerability, what to expect if the vulnerability is accepted or
+declined, etc. -->
+
+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 the best effort base, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.

Taskfile.yaml

@@ -4,9 +4,19 @@ vars:
   OWNER: anchore
   PROJECT: syft
 
+  CACHE_IMAGE: ghcr.io/{{ .OWNER }}/{{ .PROJECT }}/test-fixture-cache:latest
+
   # static file dirs
   TOOL_DIR: .tool
   TMP_DIR: .tmp
+  ORAS_CACHE: "{{ .TMP_DIR }}/oras-cache"
+  CACHE_PATHS_FILE: "{{ .TMP_DIR }}/cache_paths.json"
+  LAST_CACHE_PULL_FILE: "{{ .TMP_DIR }}/last_cache_paths.json"
+
+  # TOOLS
+  ORAS: "{{ .TOOL_DIR }}/oras"
+  YQ: "{{ .TOOL_DIR }}/yq"
+  TASK: "{{ .TOOL_DIR }}/task"
 
   # used for changelog generation
   CHANGELOG: CHANGELOG.md
@@ -33,6 +43,9 @@ vars:
   COMPARE_DIR: ./test/compare
   COMPARE_TEST_IMAGE: centos:8.2.2004
 
+env:
+  GNUMAKEFLAGS: '--no-print-directory'
+
 tasks:
 
   ## High-level tasks #################################
@@ -54,6 +67,7 @@ tasks:
       - task: check-licenses
       - task: lint
       - task: check-json-schema-drift
+      - task: check-binary-fixture-size
 
   test:
     desc: Run all levels of test
@@ -64,6 +78,7 @@ tasks:
       - task: benchmark
       - task: test-utils
       - task: cli
+      - task: check-docker-cache
 
   ## Bootstrap tasks #################################
 
@@ -169,6 +184,11 @@ tasks:
     cmds:
       - .github/scripts/json-schema-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
+
 
   ## Testing tasks #################################
 
@@ -179,7 +199,7 @@ tasks:
       - fixtures
     vars:
       TEST_PKGS:
-        sh: "go list ./... | grep -v {{ .OWNER }}/{{ .PROJECT }}/test | tr '\n' ' '"
+        sh: "go list ./... | grep -v {{ .OWNER }}/{{ .PROJECT }}/test | grep -v {{ .OWNER }}/{{ .PROJECT }}/cmd/syft/internal/test | tr '\n' ' '"
 
       # unit test coverage threshold (in % coverage)
       COVERAGE_THRESHOLD: 62
@@ -191,7 +211,7 @@ tasks:
   integration:
     desc: Run integration tests
     cmds:
-      - "go test -v ./test/integration"
+      - "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"
 
@@ -206,10 +226,6 @@ tasks:
     # 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
     cmds:
       - cmd: "echo 'testing binary: {{ .SNAPSHOT_BIN }}'"
         silent: true
@@ -223,18 +239,14 @@ tasks:
 
   test-utils:
     desc: Run tests for pipeline utils
-    sources:
-      - .github/scripts/labeler*.py
     cmds:
-      - cmd: python .github/scripts/labeler_test.py
+      - cmd: .github/scripts/labeler_test.py
 
 
   ## Benchmark test targets #################################
 
   benchmark:
     deps: [tmpdir]
-    sources:
-      - ./**/*.go
     generates:
       - "{{ .TMP_DIR }}/benchmark-main.txt"
     cmds:
@@ -247,8 +259,6 @@ tasks:
 
   show-benchstat:
     deps: [benchmark, tmpdir]
-    sources:
-      - "{{ .TMP_DIR }}/benchstat.txt"
     cmds:
       - cmd: "cat {{ .TMP_DIR }}/benchstat.txt"
         silent: true
@@ -257,49 +267,188 @@ tasks:
   ## Test-fixture-related targets #################################
 
   fingerprints:
-    desc: Generate test fixture fingerprints
+    desc: Generate fingerprints for all non-docker test fixture
+    silent: true
+    # this will look for `test-fixtures/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
     generates:
-      - 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
+      - '**/test-fixtures/**/*.fingerprint'
       - test/install/cache.fingerprint
-      - test/cli/test-fixtures/cache.fingerprint
     cmds:
-      # for IMAGE integration test fixtures
-      - "cd 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 integration test fixtures
-      - "cd test/install && make cache.fingerprint"
-      # for CLI test fixtures
-      - "cd test/cli/test-fixtures && make cache.fingerprint"
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
 
-  fixtures:
-    desc: Generate test fixtures
+        echo -e "${YELLOW}creating fingerprint files for non-docker fixtures...${RESET}"        
+        for dir in $(find . -type d -name 'test-fixtures'); do
+          if [ -f "$dir/Makefile" ]; then
+            # for debugging...
+            #echo -e "${YELLOW}• calculating fingerprints in $dir... ${RESET}"
+            
+            (make -C "$dir" fingerprint)
+          fi
+        done
+
+        # for debugging...
+        # echo -e "generated all fixture fingerprints"
+
+      - .github/scripts/fingerprint_docker_fixtures.py
+      - |
+        # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then we don't need to calculate the fingerprint for the cache
+        if [ "$DOWNLOAD_TEST_FIXTURE_CACHE" = "false" ]; then
+          exit 0
+        fi
+        .github/scripts/find_cache_paths.py {{ .CACHE_PATHS_FILE }} > /dev/null
+
+
+  refresh-fixtures:
+    desc: Clear and fetch all test fixture cache
+    aliases:
+      - fixtures
+    silent: true
+    deps:
+      - tools
     cmds:
-      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make"
-      - "cd syft/pkg/cataloger/redhat/test-fixtures && make"
-      - "cd syft/pkg/cataloger/binary/test-fixtures && make"
+      - |
+        BOLD='\033[1m'
+        PURPLE='\033[0;35m'
+        RESET='\033[0m'
+        
+        # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then skip the cache download and always build
+        if [ "$DOWNLOAD_TEST_FIXTURE_CACHE" = "false" ]; then
+            echo -e "${BOLD}${PURPLE}skipping cache download, rebuilding cache...${RESET}"
+            {{ .TASK }} build-fixtures
+            exit 0
+        fi
+        
+        LATEST_FINGERPRINT=$(docker manifest inspect {{ .CACHE_IMAGE }} | {{ .YQ }} -r '.annotations.fingerprint')
+
+        echo "latest cache:      $LATEST_FINGERPRINT"
+        
+        if [ -f {{ .LAST_CACHE_PULL_FILE }} ]; then
+          LAST_PULL_FINGERPRINT=$(cat {{ .LAST_CACHE_PULL_FILE }} | {{ .YQ }} -r '.digest')
+        else
+          echo -e "${BOLD}${PURPLE}empty cache, downloading cache...${RESET}"
+          {{ .TASK }} download-test-fixture-cache
+          exit 0
+        fi
+        
+        {{ .TASK }} fingerprints
+
+        WANT_FINGERPRINT=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.digest')        
+
+        echo "desired cache:     $WANT_FINGERPRINT"
+        echo "last pulled cache: $LAST_PULL_FINGERPRINT"
+  
+        # if we already have the latest cache, skip the refresh
+        if [ "$LAST_PULL_FINGERPRINT" = "$WANT_FINGERPRINT" ]; then
+            echo -e "${BOLD}${PURPLE}already have the latest cache (skipping cache download)${RESET}"
+            exit 0
+        fi
+  
+        # at this point we only refresh the cache if we want the same cache that is currently available.
+        # we don't by default refresh the cache if the cache if it is simply different from what we have,
+        # because we may be working on a code change that doesn't require a cache refresh (but could trigger one,
+        # which would be annoying to deal with in a development workflow).
+  
+        if [ "$LATEST_FINGERPRINT" = "$WANT_FINGERPRINT" ]; then
+          echo -e "${BOLD}${PURPLE}found newer cache! downloading cache...${RESET}"
+          {{ .TASK }} download-test-fixture-cache
+        else
+          echo -e "${BOLD}${PURPLE}found different cache, but isn't clear if it's newer (skipping cache download and manually building)${RESET}"
+        
+          {{ .YQ }} eval '.paths[] | "\(.digest) \(.path)"' {{ .LAST_CACHE_PULL_FILE }} > .tmp/last_cache_lines
+          {{ .YQ }} eval '.paths[] | "\(.digest) \(.path)"' {{ .CACHE_PATHS_FILE }} > .tmp/cache_lines
+          diff .tmp/last_cache_lines .tmp/cache_lines || true
+        
+          echo -e "${BOLD}${PURPLE}diff with more context...${RESET}"
+        
+          diff -U10000 {{ .LAST_CACHE_PULL_FILE }} {{ .CACHE_PATHS_FILE }} || true
+        
+          echo -e "${BOLD}${PURPLE}detected changes to input material, manually building fixtures...${RESET}"
+        
+          {{ .TASK }} build-fixtures
+        fi
+
+  build-fixtures:
+    desc: Generate all non-docker test fixtures
+    silent: true
+    # this will look for `test-fixtures/Makefile` and invoke the `fixtures` target to generate any and all test fixtures
+    cmds:
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
+        
+        # Use a for loop with command substitution to avoid subshell issues
+        for dir in $(find . -type d -name 'test-fixtures'); do
+          if [ -f "$dir/Makefile" ]; then
+            echo -e "${YELLOW}${BOLD}generating fixtures in $dir${RESET}"
+            (make -C "$dir" fixtures)
+          fi
+        done
+        echo -e "${BOLD}generated all fixtures${RESET}"
+
+  download-test-fixture-cache:
+    desc: Download test fixture cache from ghcr.io
+    deps: [tools, clean-cache]
+    vars:
+      CACHE_DIGEST:
+        sh: docker manifest inspect {{ .CACHE_IMAGE }} | {{ .YQ }} -r '.annotations.fingerprint'
+    cmds:
+      - silent: true
+        cmd: |
+          # if oras cache is > 4 GB, delete it
+          if [ -d {{ .ORAS_CACHE }} ]; then
+            total_size=$(du -c {{ .ORAS_CACHE }} | grep total | awk '{print $1}')
+            if [ "$total_size" -gt 4194304 ]; then
+              echo 'deleting oras cache'
+              rm -rf {{ .ORAS_CACHE }}
+            fi
+          fi
+      - "ORAS_CACHE={{ .ORAS_CACHE }} {{ .ORAS }} pull {{ .CACHE_IMAGE }}"
+      - "cp {{ .CACHE_PATHS_FILE }} {{ .LAST_CACHE_PULL_FILE }}"
+
+  upload-test-fixture-cache:
+    desc: Upload the test fixture cache to ghcr.io
+    deps: [tools, fingerprints]
+    silent: true
+    cmd: |
+      set -eu
+      oras_command="{{ .ORAS }} push {{ .CACHE_IMAGE }}"
+
+      paths=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.paths[].path')      
+      for path in $paths; do
+        oras_command+=" $path"
+      done
+      oras_command+=" {{ .CACHE_PATHS_FILE }}"
+      
+      oras_command+=" --annotation org.opencontainers.image.source=https://github.com/{{ .OWNER }}/{{ .PROJECT }}"
+      oras_command+=" --annotation fingerprint=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.digest')"
+    
+      echo "Executing: $oras_command"
+      eval $oras_command
 
   show-test-image-cache:
     silent: true
     cmds:
-      - "echo '\nDocker daemon cache:'"
+      - "echo 'Docker daemon cache:'"
       - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}:{{`{{.Tag}}`}}' | grep stereoscope-fixture- | sort"
       - "echo '\nTar cache:'"
-      - 'find . -type f -wholename "**/test-fixtures/snapshot/*" | sort'
+      - 'find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" | sort'
 
+  check-docker-cache:
+    desc: Ensure docker caches aren't using too much disk space
+    silent: true
+    cmd: |
+      total_size=$(find . | grep cache | grep tar | xargs du -c | grep total | awk '{print $1}')
+      find . | grep cache | grep tar | xargs du
+      echo "total $total_size KB"
+      
+      if [ "$total_size" -gt 1048576 ]; then
+        echo 'docker cache is larger than 1GB'
+        exit 1
+      fi
 
   ## install.sh testing targets #################################
 
@@ -377,7 +526,7 @@ tasks:
 
   generate-cpe-dictionary-index:
     desc: Generate the CPE index based off of the latest available CPE dictionary
-    dir: "syft/pkg/cataloger/common/cpe/dictionary"
+    dir: "syft/pkg/cataloger/internal/cpegenerate/dictionary"
     cmds:
       - "go generate"
 
@@ -457,6 +606,16 @@ tasks:
         silent: true
       - "{{ .RELEASE_CMD }}"
 
+  ci-release-version-file:
+    # desc: "[CI only] Update the version file"
+    deps: [tools]
+    cmds:
+      - task: ci-check
+      - ".github/scripts/update-version-file.sh {{ .RELEASE_VERSION }}"
+    requires:
+      vars:
+        - RELEASE_VERSION
+
 
   ## Cleanup targets #################################
 
@@ -466,8 +625,31 @@ tasks:
       - "rm -rf {{ .SNAPSHOT_DIR }}"
       - "rm -rf {{ .TMP_DIR }}/goreleaser.yaml"
 
-  clean-cache:
-    desc: Remove all docker cache and local image tar cache
+  clean-docker-cache:
+    desc: Remove all docker cache tars and images from the daemon
     cmds:
-      - 'find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" -delete'
-      - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}' | grep stereoscope-fixture- | awk '{print $$1}' | uniq | xargs -r docker rmi --force"
+      - find . -type d -wholename "**/test-fixtures/cache" | xargs rm -rf
+      - docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}' | grep stereoscope-fixture- | awk '{print $1}' | uniq | xargs -r docker rmi --force
+
+  clean-oras-cache:
+    desc: Remove all cache for oras commands
+    cmd: rm -rf {{ .ORAS_CACHE }}
+
+  clean-cache:
+    desc: Remove all image docker tar cache, images from the docker daemon, and ephemeral test fixtures
+    cmds:
+      - task: clean-docker-cache
+      - |
+        BOLD='\033[1m'
+        YELLOW='\033[0;33m'
+        RESET='\033[0m'
+        
+        # Use a for loop with command substitution to avoid subshell issues
+        for dir in $(find . -type d -name 'test-fixtures'); do
+        if [ -f "$dir/Makefile" ]; then
+          echo -e "${YELLOW}${BOLD}deleting ephemeral test fixtures in $dir${RESET}"
+          (make -C "$dir" clean)
+        fi
+        done
+        echo -e "${BOLD}Deleted all ephemeral test fixtures${RESET}"
+      - rm -f {{ .LAST_CACHE_PULL_FILE }} {{ .CACHE_PATHS_FILE }}

cmd/syft/cli/cli.go

@@ -8,13 +8,8 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
-	"github.com/anchore/stereoscope"
-	"github.com/anchore/syft/cmd/syft/cli/commands"
-	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"
-	"github.com/anchore/syft/internal/redact"
+	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/commands"
 )
 
 // Application constructs the `syft packages` command and aliases the root command to `syft packages`.
@@ -34,65 +29,33 @@ func Command(id clio.Identification) *cobra.Command {
 }
 
 func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Command) {
-	clioCfg := clio.NewSetupConfig(id).
-		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
-		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) {
-				noUI := ui.None(out, cfg.Log.Quiet)
-				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
-					return []clio.UI{noUI}, nil
-				}
-
-				return []clio.UI{
-					ui.New(out, cfg.Log.Quiet,
-						handler.New(handler.DefaultHandlerConfig()),
-					),
-					noUI,
-				}, nil
-			},
-		).
-		WithInitializers(
-			func(state *clio.State) error {
-				// clio is setting up and providing the bus, redact store, and logger to the application. Once loaded,
-				// we can hoist them into the internal packages for global use.
-				stereoscope.SetBus(state.Bus)
-				bus.Set(state.Bus)
-
-				redact.Set(state.RedactStore)
-
-				log.Set(state.Logger)
-				stereoscope.SetLogger(state.Logger)
-
-				return nil
-			},
-		).
-		WithPostRuns(func(state *clio.State, err error) {
-			stereoscope.Cleanup()
-		})
+	clioCfg := internal.AppClioSetupConfig(id, out)
 
 	app := clio.New(*clioCfg)
 
 	// since root is aliased as the packages cmd we need to construct this command first
 	// we also need the command to have information about the `root` options because of this alias
-	packagesCmd := commands.Packages(app)
+	scanCmd := commands.Scan(app)
 
-	// rootCmd is currently an alias for the packages command
-	rootCmd := commands.Root(app, packagesCmd)
+	// root is currently an alias for the scan command
+	rootCmd := commands.Root(app, scanCmd)
 
 	// add sub-commands
 	rootCmd.AddCommand(
-		packagesCmd,
+		scanCmd,
+		commands.Packages(app, scanCmd), // this is currently an alias for the scan command
+		commands.Cataloger(app),
 		commands.Attest(app),
 		commands.Convert(app),
 		clio.VersionCommand(id),
+		clio.ConfigCommand(app, nil),
 		cranecmd.NewCmdAuthLogin(id.Name), // syft login uses the same command as crane
 	)
 
-	// explicitly set Cobra output to the real stdout to write things like errors and help
-	rootCmd.SetOut(out)
+	// note: we would direct cobra to use our writer explicitly with rootCmd.SetOut(out) , however this causes
+	// deprecation warnings to be shown to stdout via the writer instead of stderr. This is unfortunate since this
+	// does not appear to be the correct behavior on cobra's part https://github.com/spf13/cobra/issues/1708 .
+	// In the future this functionality should be restored.
 
 	return app, rootCmd
 }

cmd/syft/cli/commands/packages.go

@@ -1,255 +0,0 @@
-package commands
-
-import (
-	"fmt"
-
-	"github.com/hashicorp/go-multierror"
-	"github.com/spf13/cobra"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/stereoscope/pkg/image"
-	"github.com/anchore/syft/cmd/syft/cli/eventloop"
-	"github.com/anchore/syft/cmd/syft/cli/options"
-	"github.com/anchore/syft/cmd/syft/internal/ui"
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/sbom"
-	"github.com/anchore/syft/syft/source"
-)
-
-const (
-	packagesExample = `  {{.appName}} {{.command}} alpine:latest                                a summary of discovered packages
-  {{.appName}} {{.command}} alpine:latest -o json                        show all possible cataloging details
-  {{.appName}} {{.command}} alpine:latest -o cyclonedx                   show a CycloneDX formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -o cyclonedx-json              show a CycloneDX JSON formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -o spdx                        show a SPDX 2.3 Tag-Value formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -o spdx@2.2                    show a SPDX 2.2 Tag-Value formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -o spdx-json                   show a SPDX 2.3 JSON formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -o spdx-json@2.2               show a SPDX 2.2 JSON formatted SBOM
-  {{.appName}} {{.command}} alpine:latest -vv                            show verbose debug information
-  {{.appName}} {{.command}} alpine:latest -o template -t my_format.tmpl  show a SBOM formatted according to given template file
-
-  Supports the following image sources:
-    {{.appName}} {{.command}} yourrepo/yourimage:tag     defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry.
-    {{.appName}} {{.command}} path/to/a/file/or/dir      a Docker tar, OCI tar, OCI directory, SIF container, or generic filesystem directory
-`
-
-	schemeHelpHeader = "You can also explicitly specify the scheme to use:"
-	imageSchemeHelp  = `    {{.appName}} {{.command}} docker:yourrepo/yourimage:tag            explicitly use the Docker daemon
-    {{.appName}} {{.command}} podman:yourrepo/yourimage:tag            explicitly use the Podman daemon
-    {{.appName}} {{.command}} registry:yourrepo/yourimage:tag          pull image directly from a registry (no container runtime required)
-    {{.appName}} {{.command}} docker-archive:path/to/yourimage.tar     use a tarball from disk for archives created from "docker save"
-    {{.appName}} {{.command}} oci-archive:path/to/yourimage.tar        use a tarball from disk for OCI archives (from Skopeo or otherwise)
-    {{.appName}} {{.command}} oci-dir:path/to/yourimage                read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
-    {{.appName}} {{.command}} singularity:path/to/yourimage.sif        read directly from a Singularity Image Format (SIF) container on disk
-`
-	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)
-`
-	packagesSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp + nonImageSchemeHelp
-
-	packagesHelp = packagesExample + packagesSchemeHelp
-)
-
-type packagesOptions struct {
-	options.Config      `yaml:",inline" mapstructure:",squash"`
-	options.Output      `yaml:",inline" mapstructure:",squash"`
-	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
-	options.Catalog     `yaml:",inline" mapstructure:",squash"`
-}
-
-func defaultPackagesOptions() *packagesOptions {
-	return &packagesOptions{
-		Output:      options.DefaultOutput(),
-		UpdateCheck: options.DefaultUpdateCheck(),
-		Catalog:     options.DefaultCatalog(),
-	}
-}
-
-//nolint:dupl
-func Packages(app clio.Application) *cobra.Command {
-	id := app.ID()
-
-	opts := defaultPackagesOptions()
-
-	return app.SetupCommand(&cobra.Command{
-		Use:   "packages [SOURCE]",
-		Short: "Generate a package SBOM",
-		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from container images and filesystems",
-		Example: internal.Tprintf(packagesHelp, map[string]interface{}{
-			"appName": id.Name,
-			"command": "packages",
-		}),
-		Args:    validatePackagesArgs,
-		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(cmd *cobra.Command, args []string) error {
-			restoreStdout := ui.CaptureStdoutToTraceLog()
-			defer restoreStdout()
-
-			return runPackages(id, opts, args[0])
-		},
-	}, opts)
-}
-
-func validatePackagesArgs(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 {
-	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 cobra.MaximumNArgs(1)(cmd, args)
-}
-
-// nolint:funlen
-func runPackages(id clio.Identification, opts *packagesOptions, userInput string) error {
-	writer, err := opts.SBOMWriter()
-	if err != nil {
-		return err
-	}
-
-	src, err := getSource(&opts.Catalog, userInput)
-
-	if err != nil {
-		return err
-	}
-
-	defer func() {
-		if src != nil {
-			if err := src.Close(); err != nil {
-				log.Tracef("unable to close source: %+v", err)
-			}
-		}
-	}()
-
-	s, err := generateSBOM(id, src, &opts.Catalog)
-	if err != nil {
-		return err
-	}
-
-	if s == nil {
-		return fmt.Errorf("no SBOM produced for %q", userInput)
-	}
-
-	if err := writer.Write(*s); err != nil {
-		return fmt.Errorf("failed to write SBOM: %w", err)
-	}
-
-	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.DefaultImagePullSource,
-		},
-	)
-	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
-		}
-	}
-
-	var platform *image.Platform
-
-	if opts.Platform != "" {
-		platform, err = image.NewPlatform(opts.Platform)
-		if err != nil {
-			return nil, fmt.Errorf("invalid platform: %w", err)
-		}
-	}
-
-	hashers, err := file.Hashers(opts.Source.File.Digests...)
-	if err != nil {
-		return nil, fmt.Errorf("invalid hash: %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.BasePath,
-		},
-	)
-
-	if err != nil {
-		if userInput == "power-user" {
-			bus.Notify("Note: the 'power-user' command has been removed.")
-		}
-		return nil, fmt.Errorf("failed to construct source from user input %q: %w", userInput, err)
-	}
-
-	return src, nil
-}
-
-func generateSBOM(id clio.Identification, src source.Source, opts *options.Catalog) (*sbom.SBOM, error) {
-	tasks, err := eventloop.Tasks(opts)
-	if err != nil {
-		return nil, err
-	}
-
-	s := sbom.SBOM{
-		Source: src.Describe(),
-		Descriptor: sbom.Descriptor{
-			Name:          id.Name,
-			Version:       id.Version,
-			Configuration: opts,
-		},
-	}
-
-	err = buildRelationships(&s, src, tasks)
-
-	return &s, err
-}
-
-func buildRelationships(s *sbom.SBOM, src source.Source, tasks []eventloop.Task) error {
-	var errs error
-
-	var relationships []<-chan artifact.Relationship
-	for _, task := range tasks {
-		c := make(chan artifact.Relationship)
-		relationships = append(relationships, c)
-		go func(task eventloop.Task) {
-			err := eventloop.RunTask(task, &s.Artifacts, src, c)
-			if err != nil {
-				errs = multierror.Append(errs, err)
-			}
-		}(task)
-	}
-
-	s.Relationships = append(s.Relationships, mergeRelationships(relationships...)...)
-
-	return errs
-}
-
-func mergeRelationships(cs ...<-chan artifact.Relationship) (relationships []artifact.Relationship) {
-	for _, c := range cs {
-		for n := range c {
-			relationships = append(relationships, n)
-		}
-	}
-
-	return relationships
-}

cmd/syft/cli/eventloop/tasks.go

@@ -1,151 +0,0 @@
-package eventloop
-
-import (
-	"github.com/anchore/syft/cmd/syft/cli/options"
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/syft"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/file/cataloger/filecontent"
-	"github.com/anchore/syft/syft/file/cataloger/filedigest"
-	"github.com/anchore/syft/syft/file/cataloger/filemetadata"
-	"github.com/anchore/syft/syft/sbom"
-	"github.com/anchore/syft/syft/source"
-)
-
-type Task func(*sbom.Artifacts, source.Source) ([]artifact.Relationship, error)
-
-func Tasks(opts *options.Catalog) ([]Task, error) {
-	var tasks []Task
-
-	generators := []func(opts *options.Catalog) (Task, error){
-		generateCatalogPackagesTask,
-		generateCatalogFileMetadataTask,
-		generateCatalogFileDigestsTask,
-		generateCatalogContentsTask,
-	}
-
-	for _, generator := range generators {
-		task, err := generator(opts)
-		if err != nil {
-			return nil, err
-		}
-
-		if task != nil {
-			tasks = append(tasks, task)
-		}
-	}
-
-	return tasks, nil
-}
-
-func generateCatalogPackagesTask(opts *options.Catalog) (Task, error) {
-	if !opts.Package.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	task := func(results *sbom.Artifacts, src source.Source) ([]artifact.Relationship, error) {
-		packageCatalog, relationships, theDistro, err := syft.CatalogPackages(src, opts.ToCatalogerConfig())
-
-		results.Packages = packageCatalog
-		results.LinuxDistribution = theDistro
-
-		return relationships, err
-	}
-
-	return task, nil
-}
-
-func generateCatalogFileMetadataTask(opts *options.Catalog) (Task, error) {
-	if !opts.FileMetadata.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	metadataCataloger := filemetadata.NewCataloger()
-
-	task := func(results *sbom.Artifacts, src source.Source) ([]artifact.Relationship, error) {
-		resolver, err := src.FileResolver(opts.FileMetadata.Cataloger.GetScope())
-		if err != nil {
-			return nil, err
-		}
-
-		result, err := metadataCataloger.Catalog(resolver)
-		if err != nil {
-			return nil, err
-		}
-		results.FileMetadata = result
-		return nil, nil
-	}
-
-	return task, nil
-}
-
-func generateCatalogFileDigestsTask(opts *options.Catalog) (Task, error) {
-	if !opts.FileMetadata.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	hashes, err := file.Hashers(opts.FileMetadata.Digests...)
-	if err != nil {
-		return nil, err
-	}
-
-	digestsCataloger := filedigest.NewCataloger(hashes)
-
-	task := func(results *sbom.Artifacts, src source.Source) ([]artifact.Relationship, error) {
-		resolver, err := src.FileResolver(opts.FileMetadata.Cataloger.GetScope())
-		if err != nil {
-			return nil, err
-		}
-
-		result, err := digestsCataloger.Catalog(resolver)
-		if err != nil {
-			return nil, err
-		}
-		results.FileDigests = result
-		return nil, nil
-	}
-
-	return task, nil
-}
-
-func generateCatalogContentsTask(opts *options.Catalog) (Task, error) {
-	if !opts.FileContents.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	contentsCataloger, err := filecontent.NewCataloger(opts.FileContents.Globs, opts.FileContents.SkipFilesAboveSize) //nolint:staticcheck
-	if err != nil {
-		return nil, err
-	}
-
-	task := func(results *sbom.Artifacts, src source.Source) ([]artifact.Relationship, error) {
-		resolver, err := src.FileResolver(opts.FileContents.Cataloger.GetScope())
-		if err != nil {
-			return nil, err
-		}
-
-		result, err := contentsCataloger.Catalog(resolver)
-		if err != nil {
-			return nil, err
-		}
-		results.FileContents = result
-		return nil, nil
-	}
-
-	return task, nil
-}
-
-func RunTask(t Task, a *sbom.Artifacts, src source.Source, c chan<- artifact.Relationship) error {
-	defer close(c)
-
-	relationships, err := t(a, src)
-	if err != nil {
-		return err
-	}
-
-	for _, relationship := range relationships {
-		c <- relationship
-	}
-
-	return nil
-}

cmd/syft/cli/options/catalog.go

@@ -1,176 +0,0 @@
-package options
-
-import (
-	"fmt"
-	"sort"
-	"strings"
-
-	"github.com/iancoleman/strcase"
-	"github.com/mitchellh/go-homedir"
-	"github.com/scylladb/go-set/strset"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/fangs"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/cataloging"
-	"github.com/anchore/syft/syft/pkg/cataloger"
-	golangCataloger "github.com/anchore/syft/syft/pkg/cataloger/golang"
-	javaCataloger "github.com/anchore/syft/syft/pkg/cataloger/java"
-	"github.com/anchore/syft/syft/pkg/cataloger/kernel"
-	pythonCataloger "github.com/anchore/syft/syft/pkg/cataloger/python"
-	"github.com/anchore/syft/syft/source"
-)
-
-type Catalog struct {
-	Catalogers                      []string     `yaml:"catalogers" json:"catalogers" mapstructure:"catalogers"`
-	Package                         pkg          `yaml:"package" json:"package" mapstructure:"package"`
-	Golang                          golang       `yaml:"golang" json:"golang" mapstructure:"golang"`
-	Java                            java         `yaml:"java" json:"java" mapstructure:"java"`
-	LinuxKernel                     linuxKernel  `yaml:"linux-kernel" json:"linux-kernel" mapstructure:"linux-kernel"`
-	Python                          python       `yaml:"python" json:"python" mapstructure:"python"`
-	FileMetadata                    fileMetadata `yaml:"file-metadata" json:"file-metadata" mapstructure:"file-metadata"`
-	FileContents                    fileContents `yaml:"file-contents" json:"file-contents" mapstructure:"file-contents"`
-	Registry                        registry     `yaml:"registry" json:"registry" mapstructure:"registry"`
-	Exclusions                      []string     `yaml:"exclude" json:"exclude" mapstructure:"exclude"`
-	Platform                        string       `yaml:"platform" json:"platform" mapstructure:"platform"`
-	Name                            string       `yaml:"name" json:"name" mapstructure:"name"`
-	Source                          sourceCfg    `yaml:"source" json:"source" mapstructure:"source"`
-	Parallelism                     int          `yaml:"parallelism" json:"parallelism" mapstructure:"parallelism"`                                                                         // the number of catalog workers to run in parallel
-	DefaultImagePullSource          string       `yaml:"default-image-pull-source" json:"default-image-pull-source" mapstructure:"default-image-pull-source"`                               // specify default image pull source
-	BasePath                        string       `yaml:"base-path" json:"base-path" mapstructure:"base-path"`                                                                               // specify base path for all file paths
-	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.FlagAdder
-	clio.PostLoader
-} = (*Catalog)(nil)
-
-func DefaultCatalog() Catalog {
-	return Catalog{
-		Package:                         defaultPkg(),
-		LinuxKernel:                     defaultLinuxKernel(),
-		FileMetadata:                    defaultFileMetadata(),
-		FileContents:                    defaultFileContents(),
-		Source:                          defaultSourceCfg(),
-		Parallelism:                     1,
-		ExcludeBinaryOverlapByOwnership: true,
-	}
-}
-
-func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
-	var validScopeValues []string
-	for _, scope := range source.AllScopes {
-		validScopeValues = append(validScopeValues, strcase.ToDelimited(string(scope), '-'))
-	}
-	flags.StringVarP(&cfg.Package.Cataloger.Scope, "scope", "s",
-		fmt.Sprintf("selection of layers to catalog, options=%v", validScopeValues))
-
-	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.StringVarP(&cfg.Source.Name, "name", "",
-		"set the name of the target being analyzed")
-
-	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
-		flagSet := pfp.PFlagSet()
-		flagSet.Lookup("name").Deprecated = "use: source-name"
-	}
-
-	flags.StringVarP(&cfg.Source.Name, "source-name", "",
-		"set the name of the target being analyzed")
-
-	flags.StringVarP(&cfg.Source.Version, "source-version", "",
-		"set the version of the target being analyzed")
-
-	flags.StringVarP(&cfg.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")
-}
-
-func (cfg *Catalog) PostLoad() error {
-	// parse options on this struct
-	var catalogers []string
-	for _, c := range cfg.Catalogers {
-		for _, f := range strings.Split(c, ",") {
-			catalogers = append(catalogers, strings.TrimSpace(f))
-		}
-	}
-	sort.Strings(catalogers)
-	cfg.Catalogers = catalogers
-
-	if err := checkDefaultSourceValues(cfg.DefaultImagePullSource); err != nil {
-		return err
-	}
-
-	if cfg.Name != "" {
-		log.Warnf("name parameter is deprecated. please use: source-name. name will be removed in a future version")
-		if cfg.Source.Name == "" {
-			cfg.Source.Name = cfg.Name
-		}
-	}
-
-	return nil
-}
-
-func (cfg Catalog) ToCatalogerConfig() cataloger.Config {
-	return cataloger.Config{
-		Search: cataloger.SearchConfig{
-			IncludeIndexedArchives:   cfg.Package.SearchIndexedArchives,
-			IncludeUnindexedArchives: cfg.Package.SearchUnindexedArchives,
-			Scope:                    cfg.Package.Cataloger.GetScope(),
-		},
-		Catalogers:  cfg.Catalogers,
-		Parallelism: cfg.Parallelism,
-		Golang: golangCataloger.DefaultCatalogerConfig().
-			WithSearchLocalModCacheLicenses(cfg.Golang.SearchLocalModCacheLicenses).
-			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
-			WithSearchRemoteLicenses(cfg.Golang.SearchRemoteLicenses).
-			WithProxy(cfg.Golang.Proxy).
-			WithNoProxy(cfg.Golang.NoProxy),
-		LinuxKernel: kernel.LinuxKernelCatalogerConfig{
-			CatalogModules: cfg.LinuxKernel.CatalogModules,
-		},
-		Java: javaCataloger.DefaultArchiveCatalogerConfig().
-			WithUseNetwork(cfg.Java.UseNetwork).
-			WithMavenBaseURL(cfg.Java.MavenURL).
-			WithArchiveTraversal(
-				cataloging.ArchiveSearchConfig{
-					IncludeIndexedArchives:   cfg.Package.SearchIndexedArchives,
-					IncludeUnindexedArchives: cfg.Package.SearchUnindexedArchives,
-				},
-				cfg.Java.MaxParentRecursiveDepth),
-		Python: pythonCataloger.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
-		ExcludeBinaryOverlapByOwnership: cfg.ExcludeBinaryOverlapByOwnership,
-	}
-}
-
-var validDefaultSourceValues = []string{"registry", "docker", "podman", ""}
-
-func checkDefaultSourceValues(source string) error {
-	validValues := strset.New(validDefaultSourceValues...)
-	if !validValues.Has(source) {
-		validValuesString := strings.Join(validDefaultSourceValues, ", ")
-		return fmt.Errorf("%s is not a valid default source; please use one of the following: %s''", source, validValuesString)
-	}
-
-	return nil
-}
-
-func expandFilePath(file string) (string, error) {
-	if file != "" {
-		expandedPath, err := homedir.Expand(file)
-		if err != nil {
-			return "", fmt.Errorf("unable to expand file path=%q: %w", file, err)
-		}
-		file = expandedPath
-	}
-	return file, nil
-}

cmd/syft/cli/options/config.go

@@ -1,6 +0,0 @@
-package options
-
-// Config holds a reference to the specific config file that was used to load application configuration
-type Config struct {
-	ConfigFile string `yaml:"config" json:"config" mapstructure:"config"`
-}

cmd/syft/cli/options/file_contents.go

@@ -1,21 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/syft/source"
-)
-
-type fileContents struct {
-	Cataloger          scope    `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
-	SkipFilesAboveSize int64    `yaml:"skip-files-above-size" json:"skip-files-above-size" mapstructure:"skip-files-above-size"`
-	Globs              []string `yaml:"globs" json:"globs" mapstructure:"globs"`
-}
-
-func defaultFileContents() fileContents {
-	return fileContents{
-		Cataloger: scope{
-			Scope: source.SquashedScope.String(),
-		},
-		SkipFilesAboveSize: 1 * file.MB,
-	}
-}

cmd/syft/cli/options/file_metadata.go

@@ -1,19 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/syft/source"
-)
-
-type fileMetadata struct {
-	Cataloger scope    `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
-	Digests   []string `yaml:"digests" json:"digests" mapstructure:"digests"`
-}
-
-func defaultFileMetadata() fileMetadata {
-	return fileMetadata{
-		Cataloger: scope{
-			Scope: source.SquashedScope.String(),
-		},
-		Digests: []string{"sha256"},
-	}
-}

cmd/syft/cli/options/format.go

@@ -1,129 +0,0 @@
-package options
-
-import (
-	"fmt"
-
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/clio"
-	"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/spdxjson"
-	"github.com/anchore/syft/syft/format/spdxtagvalue"
-	"github.com/anchore/syft/syft/format/syftjson"
-	"github.com/anchore/syft/syft/format/table"
-	"github.com/anchore/syft/syft/format/template"
-	"github.com/anchore/syft/syft/format/text"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-var _ clio.PostLoader = (*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"`
-}
-
-func (o *Format) PostLoad() error {
-	o.SyftJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SyftJSON.Pretty)
-	o.SPDXJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.SPDXJSON.Pretty)
-	o.CyclonedxJSON.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxJSON.Pretty)
-	o.CyclonedxXML.Pretty = multiLevelOption[bool](false, o.Pretty, o.CyclonedxXML.Pretty)
-
-	return nil
-}
-
-func DefaultFormat() Format {
-	return Format{
-		Template:      DefaultFormatTemplate(),
-		SyftJSON:      DefaultFormatJSON(),
-		SPDXJSON:      DefaultFormatSPDXJSON(),
-		CyclonedxJSON: DefaultFormatCyclonedxJSON(),
-		CyclonedxXML:  DefaultFormatCyclonedxXML(),
-	}
-}
-
-func (o *Format) Encoders() ([]sbom.FormatEncoder, error) {
-	// setup all encoders based on the configuration
-	var list encoderList
-
-	// in the future there will be application configuration options that can be used to set the default output format
-	list.addWithErr(template.ID)(o.Template.formatEncoders())
-	list.addWithErr(syftjson.ID)(o.SyftJSON.formatEncoders())
-	list.add(table.ID)(table.NewFormatEncoder())
-	list.add(text.ID)(text.NewFormatEncoder())
-	list.add(github.ID)(github.NewFormatEncoder())
-	list.addWithErr(cyclonedxxml.ID)(o.CyclonedxXML.formatEncoders())
-	list.addWithErr(cyclonedxjson.ID)(o.CyclonedxJSON.formatEncoders())
-	list.addWithErr(spdxjson.ID)(o.SPDXJSON.formatEncoders())
-	list.addWithErr(spdxtagvalue.ID)(spdxTagValueEncoders())
-
-	return list.encoders, list.err
-}
-
-// TODO: when application configuration is made for this format then this should be ported to the options object
-// that is created for that configuration (as done with the template output option)
-func spdxTagValueEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range spdxtagvalue.SupportedVersions() {
-		enc, err := spdxtagvalue.NewFormatEncoderWithConfig(spdxtagvalue.EncoderConfig{Version: v})
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-type encoderList struct {
-	encoders []sbom.FormatEncoder
-	err      error
-}
-
-func (l *encoderList) addWithErr(name sbom.FormatID) func([]sbom.FormatEncoder, error) {
-	return func(encs []sbom.FormatEncoder, err error) {
-		if err != nil {
-			l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: %w", name, err))
-			return
-		}
-		for _, enc := range encs {
-			if enc == nil {
-				l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: nil encoder returned", name))
-				continue
-			}
-			l.encoders = append(l.encoders, enc)
-		}
-	}
-}
-
-func (l *encoderList) add(name sbom.FormatID) func(...sbom.FormatEncoder) {
-	return func(encs ...sbom.FormatEncoder) {
-		for _, enc := range encs {
-			if enc == nil {
-				l.err = multierror.Append(l.err, fmt.Errorf("unable to configure %q format encoder: nil encoder returned", name))
-				continue
-			}
-			l.encoders = append(l.encoders, enc)
-		}
-	}
-}
-
-func multiLevelOption[T any](defaultValue T, option ...*T) *T {
-	result := defaultValue
-	for _, opt := range option {
-		if opt != nil {
-			result = *opt
-		}
-	}
-	return &result
-}

cmd/syft/cli/options/format_cyclonedx_json.go

@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/cyclonedxjson"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatCyclonedxJSON struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatCyclonedxJSON() FormatCyclonedxJSON {
-	return FormatCyclonedxJSON{}
-}
-
-func (o FormatCyclonedxJSON) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range cyclonedxjson.SupportedVersions() {
-		enc, err := cyclonedxjson.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatCyclonedxJSON) buildConfig(version string) cyclonedxjson.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return cyclonedxjson.EncoderConfig{
-		Version: version,
-		Pretty:  pretty,
-	}
-}

cmd/syft/cli/options/format_cyclonedx_xml.go

@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/cyclonedxxml"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatCyclonedxXML struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatCyclonedxXML() FormatCyclonedxXML {
-	return FormatCyclonedxXML{}
-}
-
-func (o FormatCyclonedxXML) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range cyclonedxxml.SupportedVersions() {
-		enc, err := cyclonedxxml.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatCyclonedxXML) buildConfig(version string) cyclonedxxml.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return cyclonedxxml.EncoderConfig{
-		Version: version,
-		Pretty:  pretty,
-	}
-}

cmd/syft/cli/options/format_spdx_json.go

@@ -1,43 +0,0 @@
-package options
-
-import (
-	"github.com/hashicorp/go-multierror"
-
-	"github.com/anchore/syft/syft/format/spdxjson"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-type FormatSPDXJSON struct {
-	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
-}
-
-func DefaultFormatSPDXJSON() FormatSPDXJSON {
-	return FormatSPDXJSON{}
-}
-
-func (o FormatSPDXJSON) formatEncoders() ([]sbom.FormatEncoder, error) {
-	var (
-		encs []sbom.FormatEncoder
-		errs error
-	)
-	for _, v := range spdxjson.SupportedVersions() {
-		enc, err := spdxjson.NewFormatEncoderWithConfig(o.buildConfig(v))
-		if err != nil {
-			errs = multierror.Append(errs, err)
-		} else {
-			encs = append(encs, enc)
-		}
-	}
-	return encs, errs
-}
-
-func (o FormatSPDXJSON) buildConfig(v string) spdxjson.EncoderConfig {
-	var pretty bool
-	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return spdxjson.EncoderConfig{
-		Version: v,
-		Pretty:  pretty,
-	}
-}

cmd/syft/cli/options/golang.go

@@ -1,9 +0,0 @@
-package options
-
-type golang 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"`
-}

cmd/syft/cli/options/java.go

@@ -1,7 +0,0 @@
-package options
-
-type java 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"`
-}

cmd/syft/cli/options/linux_kernel.go

@@ -1,11 +0,0 @@
-package options
-
-type linuxKernel struct {
-	CatalogModules bool `json:"catalog-modules" yaml:"catalog-modules" mapstructure:"catalog-modules"`
-}
-
-func defaultLinuxKernel() linuxKernel {
-	return linuxKernel{
-		CatalogModules: true,
-	}
-}

cmd/syft/cli/options/pkg.go

@@ -1,23 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/syft/pkg/cataloger"
-)
-
-type pkg struct {
-	Cataloger               scope `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
-	SearchUnindexedArchives bool  `yaml:"search-unindexed-archives" json:"search-unindexed-archives" mapstructure:"search-unindexed-archives"`
-	SearchIndexedArchives   bool  `yaml:"search-indexed-archives" json:"search-indexed-archives" mapstructure:"search-indexed-archives"`
-}
-
-func defaultPkg() pkg {
-	c := cataloger.DefaultSearchConfig()
-	return pkg{
-		SearchIndexedArchives:   c.IncludeIndexedArchives,
-		SearchUnindexedArchives: c.IncludeUnindexedArchives,
-		Cataloger: scope{
-			Enabled: true,
-			Scope:   c.Scope.String(),
-		},
-	}
-}

cmd/syft/cli/options/python.go

@@ -1,5 +0,0 @@
-package options
-
-type python struct {
-	GuessUnpinnedRequirements bool `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
-}

cmd/syft/cli/options/scope.go

@@ -1,27 +0,0 @@
-package options
-
-import (
-	"fmt"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/syft/syft/source"
-)
-
-type scope struct {
-	Enabled bool   `yaml:"enabled" json:"enabled" mapstructure:"enabled"`
-	Scope   string `yaml:"scope" json:"scope" mapstructure:"scope"`
-}
-
-var _ clio.PostLoader = (*scope)(nil)
-
-func (opt *scope) PostLoad() error {
-	s := opt.GetScope()
-	if s == source.UnknownScope {
-		return fmt.Errorf("bad scope value %v", opt.Scope)
-	}
-	return nil
-}
-
-func (opt scope) GetScope() source.Scope {
-	return source.ParseScope(opt.Scope)
-}

cmd/syft/cli/options/source.go

@@ -1,19 +0,0 @@
-package options
-
-type sourceCfg struct {
-	Name    string     `json:"name" yaml:"name" mapstructure:"name"`
-	Version string     `json:"version" yaml:"version" mapstructure:"version"`
-	File    fileSource `json:"file" yaml:"file" mapstructure:"file"`
-}
-
-type fileSource struct {
-	Digests []string `json:"digests" yaml:"digests" mapstructure:"digests"`
-}
-
-func defaultSourceCfg() sourceCfg {
-	return sourceCfg{
-		File: fileSource{
-			Digests: []string{"sha256"},
-		},
-	}
-}

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

@@ -1,16 +1,24 @@
 
 [TestHandler_handleCatalogerTaskStarted/cataloging_task_in_progress - 1]
-   some task title                 [some value]  
+ ⠙ Cataloging contents             
+ ⠙ some task title                 ━━━━━━━━━━━━━━━━━━━━  [some stage]  
 ---
 
 [TestHandler_handleCatalogerTaskStarted/cataloging_sub_task_in_progress - 1]
-   └── some task title             [some value]  
+ ⠙ Cataloging contents             
+   └── ⠙ some task title                 ━━━━━━━━━━━━━━━━━━━━  [some stage]  
 ---
 
 [TestHandler_handleCatalogerTaskStarted/cataloging_sub_task_complete - 1]
- ✔ └── some task done              [some value]  
+ ⠙ Cataloging contents             
+   └── ✔ some task done                  [some stage]  
+---
+
+[TestHandler_handleCatalogerTaskStarted/cataloging_sub_task_complete_--_hide_stage - 1]
+ ⠙ Cataloging contents             
+   └── ✔ some task done                  
 ---
 
 [TestHandler_handleCatalogerTaskStarted/cataloging_sub_task_complete_with_removal - 1]
-
+ ⠙ Cataloging contents             
 ---

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

@@ -1,8 +0,0 @@
-
-[TestHandler_handleFileDigestsCatalogerStarted/cataloging_in_progress - 1]
- ⠋ Cataloging file digests         ━━━━━━━━━━━━━━━━━━━━  [current]  
----
-
-[TestHandler_handleFileDigestsCatalogerStarted/cataloging_complete - 1]
- ✔ Cataloged file digests          
----

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

@@ -1,8 +0,0 @@
-
-[TestHandler_handleFileMetadataCatalogerStarted/cataloging_in_progress - 1]
- ⠋ Cataloging file metadata        ━━━━━━━━━━━━━━━━━━━━  [current]  
----
-
-[TestHandler_handleFileMetadataCatalogerStarted/cataloging_complete - 1]
- ✔ Cataloged file metadata         
----

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

@@ -1,16 +0,0 @@
-
-[TestHandler_handlePackageCatalogerStarted/cataloging_in_progress - 1]
- ⠋ Cataloging packages             [50 packages]  
----
-
-[TestHandler_handlePackageCatalogerStarted/cataloging_only_files_complete - 1]
- ⠋ Cataloging packages             [50 packages]  
----
-
-[TestHandler_handlePackageCatalogerStarted/cataloging_only_packages_complete - 1]
- ⠋ Cataloging packages             [100 packages]  
----
-
-[TestHandler_handlePackageCatalogerStarted/cataloging_complete - 1]
- ✔ Cataloged packages              [100 packages]  
----

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

@@ -1,8 +0,0 @@
-
-[TestHandler_handleSecretsCatalogerStarted/cataloging_in_progress - 1]
- ⠋ Cataloging secrets              ━━━━━━━━━━━━━━━━━━━━  [64 secrets]  
----
-
-[TestHandler_handleSecretsCatalogerStarted/cataloging_complete - 1]
- ✔ Cataloged secrets               [64 secrets]  
----

cmd/syft/cli/ui/handle_attestation_test.go

@@ -100,18 +100,21 @@ func TestHandler_handleAttestationStarted(t *testing.T) {
 				Height: 80,
 			}
 
-			models := handler.Handle(event)
+			models, _ := handler.Handle(event)
 			require.Len(t, models, 2)
 
 			t.Run("task line", func(t *testing.T) {
 				tsk, ok := models[0].(taskprogress.Model)
 				require.True(t, ok)
 
-				got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
+				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)
 			})
@@ -119,11 +122,15 @@ func TestHandler_handleAttestationStarted(t *testing.T) {
 			t.Run("log", func(t *testing.T) {
 				log, ok := models[1].(attestLogFrame)
 				require.True(t, ok)
-				got := runModel(t, log, tt.iterations, attestLogFrameTickMsg{
+
+				gotModel := runModel(t, log, tt.iterations, attestLogFrameTickMsg{
 					Time:     time.Now(),
 					Sequence: log.sequence,
 					ID:       log.id,
 				}, log.reader.running)
+
+				got := gotModel.View()
+
 				t.Log(got)
 				snaps.MatchSnapshot(t, got)
 			})

cmd/syft/cli/ui/handle_cataloger_task.go

@@ -3,70 +3,121 @@ package ui
 import (
 	tea "github.com/charmbracelet/bubbletea"
 	"github.com/charmbracelet/lipgloss"
+	"github.com/google/uuid"
 	"github.com/wagoodman/go-partybus"
 	"github.com/wagoodman/go-progress"
 
 	"github.com/anchore/bubbly/bubbles/taskprogress"
+	"github.com/anchore/bubbly/bubbles/tree"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/event/monitor"
 	syftEventParsers "github.com/anchore/syft/syft/event/parsers"
 )
 
-var _ progress.Stager = (*catalogerTaskStageAdapter)(nil)
+// we standardize how rows are instantiated to ensure consistency in the appearance across the UI
+type taskModelFactory func(title taskprogress.Title, opts ...taskprogress.Option) taskprogress.Model
 
-type catalogerTaskStageAdapter struct {
-	mon *monitor.CatalogerTask
+var _ tea.Model = (*catalogerTaskModel)(nil)
+
+type catalogerTaskModel struct {
+	model        tree.Model
+	modelFactory taskModelFactory
 }
 
-func newCatalogerTaskStageAdapter(mon *monitor.CatalogerTask) *catalogerTaskStageAdapter {
-	return &catalogerTaskStageAdapter{
-		mon: mon,
+func newCatalogerTaskTreeModel(f taskModelFactory) *catalogerTaskModel {
+	t := tree.NewModel()
+	t.Padding = "   "
+	t.RootsWithoutPrefix = true
+	return &catalogerTaskModel{
+		modelFactory: f,
+		model:        t,
 	}
 }
 
-func (c catalogerTaskStageAdapter) Stage() string {
-	return c.mon.GetValue()
+type newCatalogerTaskRowEvent struct {
+	info monitor.GenericTask
+	prog progress.StagedProgressable
 }
 
-func (m *Handler) handleCatalogerTaskStarted(e partybus.Event) []tea.Model {
-	mon, err := syftEventParsers.ParseCatalogerTaskStarted(e)
-	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
-		return nil
+func (cts catalogerTaskModel) Init() tea.Cmd {
+	return cts.model.Init()
+}
+
+func (cts catalogerTaskModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
+	event, ok := msg.(newCatalogerTaskRowEvent)
+	if !ok {
+		model, cmd := cts.model.Update(msg)
+		cts.model = model.(tree.Model)
+
+		return cts, cmd
 	}
 
-	var prefix string
-	if mon.SubStatus {
-		// TODO: support list of sub-statuses, not just a single leaf
-		prefix = "└── "
-	}
+	info, prog := event.info, event.prog
 
-	tsk := m.newTaskProgress(
+	tsk := cts.modelFactory(
 		taskprogress.Title{
-			// TODO: prefix should not be part of the title, but instead a separate field that is aware of the tree structure
-			Default: prefix + mon.Title,
-			Running: prefix + mon.Title,
-			Success: prefix + mon.TitleOnCompletion,
+			Default: info.Title.Default,
+			Running: info.Title.WhileRunning,
+			Success: info.Title.OnSuccess,
 		},
-		taskprogress.WithStagedProgressable(
-			struct {
-				progress.Stager
-				progress.Progressable
-			}{
-				Progressable: mon.GetMonitor(),
-				Stager:       newCatalogerTaskStageAdapter(mon),
-			},
-		),
+		taskprogress.WithStagedProgressable(prog),
 	)
 
-	// TODO: this isn't ideal since the model stays around after it is no longer needed, but it works for now
-	tsk.HideOnSuccess = mon.RemoveOnCompletion
-	tsk.HideStageOnSuccess = false
-	tsk.HideProgressOnSuccess = false
+	if info.Context != "" {
+		tsk.Context = []string{info.Context}
+	}
 
-	tsk.TitleStyle = lipgloss.NewStyle()
-	// TODO: this is a hack to get the spinner to not show up, but ideally the component would support making the spinner optional
-	tsk.Spinner.Spinner.Frames = []string{" "}
+	tsk.HideOnSuccess = info.HideOnSuccess
+	tsk.HideStageOnSuccess = info.HideStageOnSuccess
+	tsk.HideProgressOnSuccess = true
 
-	return []tea.Model{tsk}
+	if info.ParentID != "" {
+		tsk.TitleStyle = lipgloss.NewStyle()
+	}
+
+	if err := cts.model.Add(info.ParentID, info.ID, tsk); err != nil {
+		log.WithFields("error", err).Error("unable to add cataloger task to tree model")
+	}
+
+	return cts, tsk.Init()
+}
+
+func (cts catalogerTaskModel) View() string {
+	return cts.model.View()
+}
+
+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")
+		return nil, nil
+	}
+
+	var models []tea.Model
+
+	// only create the new cataloger task tree once to manage all cataloger task events
+	m.onNewCatalogerTask.Do(func() {
+		models = append(models, newCatalogerTaskTreeModel(m.newTaskProgress))
+	})
+
+	// we need to update the cataloger task model with a new row. We should never update the model outside of the
+	// bubbletea update-render event loop. Instead, we return a command that will be executed by the bubbletea runtime,
+	// producing a message that is passed to the cataloger task model. This is the prescribed way to update models
+	// in bubbletea.
+
+	if info.ID == "" {
+		// ID is optional from the consumer perspective, but required internally
+		info.ID = uuid.Must(uuid.NewRandom()).String()
+	}
+
+	cmd := func() tea.Msg {
+		// this message will cause the cataloger task model to add a new row to the output based on the given task
+		// information and progress data.
+		return newCatalogerTaskRowEvent{
+			info: *info,
+			prog: mon,
+		}
+	}
+
+	return models, cmd
 }

cmd/syft/cli/ui/handle_cataloger_task_test.go

@@ -2,19 +2,22 @@ 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"
 	syftEvent "github.com/anchore/syft/syft/event"
 	"github.com/anchore/syft/syft/event/monitor"
 )
 
 func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
+	title := monitor.Title{
+		Default:   "some task title",
+		OnSuccess: "some task done",
+	}
 	tests := []struct {
 		name       string
 		eventFn    func(*testing.T) partybus.Event
@@ -23,99 +26,171 @@ func TestHandler_handleCatalogerTaskStarted(t *testing.T) {
 		{
 			name: "cataloging task in progress",
 			eventFn: func(t *testing.T) partybus.Event {
-				src := &monitor.CatalogerTask{
-					SubStatus:          false,
-					RemoveOnCompletion: false,
-					Title:              "some task title",
-					TitleOnCompletion:  "some task done",
+				value := &monitor.CatalogerTaskProgress{
+					AtomicStage: progress.NewAtomicStage("some stage"),
+					Manual:      progress.NewManual(100),
 				}
 
-				src.SetValue("some value")
+				value.Manual.Add(50)
 
 				return partybus.Event{
-					Type:   syftEvent.CatalogerTaskStarted,
-					Source: src,
+					Type: syftEvent.CatalogerTaskStarted,
+					Source: monitor.GenericTask{
+						Title:              title,
+						HideOnSuccess:      false,
+						HideStageOnSuccess: false,
+						ID:                 "my-id",
+					},
+					Value: value,
 				}
 			},
 		},
 		{
 			name: "cataloging sub task in progress",
 			eventFn: func(t *testing.T) partybus.Event {
-				src := &monitor.CatalogerTask{
-					SubStatus:          true,
-					RemoveOnCompletion: false,
-					Title:              "some task title",
-					TitleOnCompletion:  "some task done",
+				value := &monitor.CatalogerTaskProgress{
+					AtomicStage: progress.NewAtomicStage("some stage"),
+					Manual:      progress.NewManual(100),
 				}
 
-				src.SetValue("some value")
+				value.Manual.Add(50)
 
 				return partybus.Event{
-					Type:   syftEvent.CatalogerTaskStarted,
-					Source: src,
+					Type: syftEvent.CatalogerTaskStarted,
+					Source: monitor.GenericTask{
+						Title:              title,
+						HideOnSuccess:      false,
+						HideStageOnSuccess: false,
+						ID:                 "my-id",
+						ParentID:           "top-level-task",
+					},
+					Value: value,
 				}
 			},
 		},
 		{
 			name: "cataloging sub task complete",
 			eventFn: func(t *testing.T) partybus.Event {
-				src := &monitor.CatalogerTask{
-					SubStatus:          true,
-					RemoveOnCompletion: false,
-					Title:              "some task title",
-					TitleOnCompletion:  "some task done",
+				value := &monitor.CatalogerTaskProgress{
+					AtomicStage: progress.NewAtomicStage("some stage"),
+					Manual:      progress.NewManual(100),
 				}
 
-				src.SetValue("some value")
-				src.SetCompleted()
+				value.SetCompleted()
 
 				return partybus.Event{
-					Type:   syftEvent.CatalogerTaskStarted,
-					Source: src,
+					Type: syftEvent.CatalogerTaskStarted,
+					Source: monitor.GenericTask{
+						Title:              title,
+						HideOnSuccess:      false,
+						HideStageOnSuccess: false,
+						ID:                 "my-id",
+						ParentID:           "top-level-task",
+					},
+					Value: value,
+				}
+			},
+		},
+		{
+			name: "cataloging sub task complete -- hide stage",
+			eventFn: func(t *testing.T) partybus.Event {
+				value := &monitor.CatalogerTaskProgress{
+					AtomicStage: progress.NewAtomicStage("some stage"),
+					Manual:      progress.NewManual(100),
+				}
+
+				value.SetCompleted()
+
+				return partybus.Event{
+					Type: syftEvent.CatalogerTaskStarted,
+					Source: monitor.GenericTask{
+						Title:              title,
+						HideOnSuccess:      false,
+						HideStageOnSuccess: true,
+						ID:                 "my-id",
+						ParentID:           "top-level-task",
+					},
+					Value: value,
 				}
 			},
 		},
 		{
 			name: "cataloging sub task complete with removal",
 			eventFn: func(t *testing.T) partybus.Event {
-				src := &monitor.CatalogerTask{
-					SubStatus:          true,
-					RemoveOnCompletion: true,
-					Title:              "some task title",
-					TitleOnCompletion:  "some task done",
+				value := &monitor.CatalogerTaskProgress{
+					AtomicStage: progress.NewAtomicStage("some stage"),
+					Manual:      progress.NewManual(100),
 				}
 
-				src.SetValue("some value")
-				src.SetCompleted()
+				value.SetCompleted()
 
 				return partybus.Event{
-					Type:   syftEvent.CatalogerTaskStarted,
-					Source: src,
+					Type: syftEvent.CatalogerTaskStarted,
+					Source: monitor.GenericTask{
+						Title:              title,
+						HideOnSuccess:      true,
+						HideStageOnSuccess: false,
+						ID:                 "my-id",
+						ParentID:           "top-level-task",
+					},
+					Value: value,
 				}
 			},
 		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			event := tt.eventFn(t)
+			// need to be able to get the initial newCatalogerTaskRowEvent + initialize the nested taskprogress model
+			if tt.iterations == 0 {
+				tt.iterations = 2
+			}
+
+			e := tt.eventFn(t)
 			handler := New(DefaultHandlerConfig())
 			handler.WindowSize = tea.WindowSizeMsg{
 				Width:  100,
 				Height: 80,
 			}
 
-			models := handler.Handle(event)
+			info := monitor.GenericTask{
+				Title: monitor.Title{
+					Default:      "Catalog contents",
+					WhileRunning: "Cataloging contents",
+					OnSuccess:    "Cataloged contents",
+				},
+				ID: "top-level-task",
+			}
+
+			// note: this line / event is not under test, only needed to show a sub status
+			kickoffEvent := &monitor.CatalogerTaskProgress{
+				AtomicStage: progress.NewAtomicStage(""),
+				Manual:      progress.NewManual(-1),
+			}
+
+			models, cmd := handler.Handle(
+				partybus.Event{
+					Type:   syftEvent.CatalogerTaskStarted,
+					Source: info,
+					Value:  progress.StagedProgressable(kickoffEvent),
+				},
+			)
 			require.Len(t, models, 1)
+			require.NotNil(t, cmd)
 			model := models[0]
 
-			tsk, ok := model.(taskprogress.Model)
+			tr, ok := model.(*catalogerTaskModel)
 			require.True(t, ok)
 
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
-				Time:     time.Now(),
-				Sequence: tsk.Sequence(),
-				ID:       tsk.ID(),
-			})
+			gotModel := runModel(t, tr, tt.iterations, cmd())
+
+			models, cmd = handler.Handle(e)
+			require.Len(t, models, 0)
+			require.NotNil(t, cmd)
+
+			gotModel = runModel(t, gotModel, tt.iterations, cmd())
+
+			got := gotModel.View()
+
 			t.Log(got)
 			snaps.MatchSnapshot(t, got)
 		})

cmd/syft/cli/ui/handle_fetch_image_test.go

@@ -80,18 +80,21 @@ func TestHandler_handleFetchImage(t *testing.T) {
 				Height: 80,
 			}
 
-			models := handler.Handle(event)
+			models, _ := handler.Handle(event)
 			require.Len(t, models, 1)
 			model := models[0]
 
 			tsk, ok := model.(taskprogress.Model)
 			require.True(t, ok)
 
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
+			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_file_digests_cataloger.go

@@ -1,28 +0,0 @@
-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) handleFileDigestsCatalogerStarted(e partybus.Event) []tea.Model {
-	prog, err := syftEventParsers.ParseFileDigestsCatalogingStarted(e)
-	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
-		return nil
-	}
-
-	tsk := m.newTaskProgress(
-		taskprogress.Title{
-			Default: "Catalog file digests",
-			Running: "Cataloging file digests",
-			Success: "Cataloged file digests",
-		}, taskprogress.WithStagedProgressable(prog),
-	)
-
-	return []tea.Model{tsk}
-}

cmd/syft/cli/ui/handle_file_digests_cataloger_test.go

@@ -1,97 +0,0 @@
-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"
-	syftEvent "github.com/anchore/syft/syft/event"
-)
-
-func TestHandler_handleFileDigestsCatalogerStarted(t *testing.T) {
-
-	tests := []struct {
-		name       string
-		eventFn    func(*testing.T) partybus.Event
-		iterations int
-	}{
-		{
-			name: "cataloging in progress",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(50)
-
-				mon := struct {
-					progress.Progressable
-					progress.Stager
-				}{
-					Progressable: prog,
-					Stager: &progress.Stage{
-						Current: "current",
-					},
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.FileDigestsCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-		{
-			name: "cataloging complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(100)
-				prog.SetCompleted()
-
-				mon := struct {
-					progress.Progressable
-					progress.Stager
-				}{
-					Progressable: prog,
-					Stager: &progress.Stage{
-						Current: "current",
-					},
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.FileDigestsCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-	}
-	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.Handle(event)
-			require.Len(t, models, 1)
-			model := models[0]
-
-			tsk, ok := model.(taskprogress.Model)
-			require.True(t, ok)
-
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
-				Time:     time.Now(),
-				Sequence: tsk.Sequence(),
-				ID:       tsk.ID(),
-			})
-			t.Log(got)
-			snaps.MatchSnapshot(t, got)
-		})
-	}
-}

cmd/syft/cli/ui/handle_file_indexing_test.go

@@ -80,18 +80,21 @@ func TestHandler_handleFileIndexingStarted(t *testing.T) {
 				Height: 80,
 			}
 
-			models := handler.Handle(event)
+			models, _ := handler.Handle(event)
 			require.Len(t, models, 1)
 			model := models[0]
 
 			tsk, ok := model.(taskprogress.Model)
 			require.True(t, ok)
 
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
+			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_file_metadata_cataloger.go

@@ -1,29 +0,0 @@
-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) handleFileMetadataCatalogerStarted(e partybus.Event) []tea.Model {
-	prog, err := syftEventParsers.ParseFileMetadataCatalogingStarted(e)
-	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
-		return nil
-	}
-
-	tsk := m.newTaskProgress(
-		taskprogress.Title{
-			Default: "Catalog file metadata",
-			Running: "Cataloging file metadata",
-			Success: "Cataloged file metadata",
-		},
-		taskprogress.WithStagedProgressable(prog),
-	)
-
-	return []tea.Model{tsk}
-}

cmd/syft/cli/ui/handle_file_metadata_cataloger_test.go

@@ -1,97 +0,0 @@
-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"
-	syftEvent "github.com/anchore/syft/syft/event"
-)
-
-func TestHandler_handleFileMetadataCatalogerStarted(t *testing.T) {
-
-	tests := []struct {
-		name       string
-		eventFn    func(*testing.T) partybus.Event
-		iterations int
-	}{
-		{
-			name: "cataloging in progress",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(50)
-
-				mon := struct {
-					progress.Progressable
-					progress.Stager
-				}{
-					Progressable: prog,
-					Stager: &progress.Stage{
-						Current: "current",
-					},
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.FileMetadataCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-		{
-			name: "cataloging complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(100)
-				prog.SetCompleted()
-
-				mon := struct {
-					progress.Progressable
-					progress.Stager
-				}{
-					Progressable: prog,
-					Stager: &progress.Stage{
-						Current: "current",
-					},
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.FileMetadataCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-	}
-	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.Handle(event)
-			require.Len(t, models, 1)
-			model := models[0]
-
-			tsk, ok := model.(taskprogress.Model)
-			require.True(t, ok)
-
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
-				Time:     time.Now(),
-				Sequence: tsk.Sequence(),
-				ID:       tsk.ID(),
-			})
-			t.Log(got)
-			snaps.MatchSnapshot(t, got)
-		})
-	}
-}

cmd/syft/cli/ui/handle_package_cataloger.go

@@ -1,87 +0,0 @@
-package ui
-
-import (
-	"fmt"
-
-	tea "github.com/charmbracelet/bubbletea"
-	"github.com/wagoodman/go-partybus"
-	"github.com/wagoodman/go-progress"
-
-	"github.com/anchore/bubbly/bubbles/taskprogress"
-	"github.com/anchore/syft/internal/log"
-	syftEventParsers "github.com/anchore/syft/syft/event/parsers"
-	"github.com/anchore/syft/syft/pkg/cataloger"
-)
-
-var _ progress.StagedProgressable = (*packageCatalogerProgressAdapter)(nil)
-
-type packageCatalogerProgressAdapter struct {
-	monitor  *cataloger.Monitor
-	monitors []progress.Monitorable
-}
-
-func newPackageCatalogerProgressAdapter(monitor *cataloger.Monitor) packageCatalogerProgressAdapter {
-	return packageCatalogerProgressAdapter{
-		monitor: monitor,
-		monitors: []progress.Monitorable{
-			monitor.FilesProcessed,
-			monitor.PackagesDiscovered,
-		},
-	}
-}
-
-func (p packageCatalogerProgressAdapter) Stage() string {
-	return fmt.Sprintf("%d packages", p.monitor.PackagesDiscovered.Current())
-}
-
-func (p packageCatalogerProgressAdapter) Current() int64 {
-	return p.monitor.PackagesDiscovered.Current()
-}
-
-func (p packageCatalogerProgressAdapter) Error() error {
-	completedMonitors := 0
-	for _, monitor := range p.monitors {
-		err := monitor.Error()
-		if err == nil {
-			continue
-		}
-		if progress.IsErrCompleted(err) {
-			completedMonitors++
-			continue
-		}
-		// something went wrong
-		return err
-	}
-	if completedMonitors == len(p.monitors) && len(p.monitors) > 0 {
-		return p.monitors[0].Error()
-	}
-	return nil
-}
-
-func (p packageCatalogerProgressAdapter) Size() int64 {
-	// this is an inherently unknown value (indeterminate total number of packages to discover)
-	return -1
-}
-
-func (m *Handler) handlePackageCatalogerStarted(e partybus.Event) []tea.Model {
-	monitor, err := syftEventParsers.ParsePackageCatalogerStarted(e)
-	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
-		return nil
-	}
-
-	tsk := m.newTaskProgress(
-		taskprogress.Title{
-			Default: "Catalog packages",
-			Running: "Cataloging packages",
-			Success: "Cataloged packages",
-		},
-		taskprogress.WithStagedProgressable(
-			newPackageCatalogerProgressAdapter(monitor),
-		),
-	)
-
-	tsk.HideStageOnSuccess = false
-
-	return []tea.Model{tsk}
-}

cmd/syft/cli/ui/handle_package_cataloger_test.go

@@ -1,133 +0,0 @@
-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"
-	syftEvent "github.com/anchore/syft/syft/event"
-	"github.com/anchore/syft/syft/pkg/cataloger"
-)
-
-func TestHandler_handlePackageCatalogerStarted(t *testing.T) {
-
-	tests := []struct {
-		name       string
-		eventFn    func(*testing.T) partybus.Event
-		iterations int
-	}{
-		{
-			name: "cataloging in progress",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(50)
-
-				mon := cataloger.Monitor{
-					FilesProcessed:     progress.NewManual(-1),
-					PackagesDiscovered: prog,
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.PackageCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-		{
-			name: "cataloging only files complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(50)
-
-				files := progress.NewManual(-1)
-				files.SetCompleted()
-
-				mon := cataloger.Monitor{
-					FilesProcessed:     files,
-					PackagesDiscovered: prog,
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.PackageCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-		{
-			name: "cataloging only packages complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(100)
-				prog.SetCompleted()
-
-				files := progress.NewManual(-1)
-
-				mon := cataloger.Monitor{
-					FilesProcessed:     files,
-					PackagesDiscovered: prog,
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.PackageCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-		{
-			name: "cataloging complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				prog := &progress.Manual{}
-				prog.SetTotal(100)
-				prog.Set(100)
-				prog.SetCompleted()
-
-				files := progress.NewManual(-1)
-				files.SetCompleted()
-
-				mon := cataloger.Monitor{
-					FilesProcessed:     files,
-					PackagesDiscovered: prog,
-				}
-
-				return partybus.Event{
-					Type:  syftEvent.PackageCatalogerStarted,
-					Value: mon,
-				}
-			},
-		},
-	}
-	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.Handle(event)
-			require.Len(t, models, 1)
-			model := models[0]
-
-			tsk, ok := model.(taskprogress.Model)
-			require.True(t, ok)
-
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
-				Time:     time.Now(),
-				Sequence: tsk.Sequence(),
-				ID:       tsk.ID(),
-			})
-			t.Log(got)
-			snaps.MatchSnapshot(t, got)
-		})
-	}
-}

cmd/syft/cli/ui/handle_read_image_test.go

@@ -98,18 +98,21 @@ func TestHandler_handleReadImage(t *testing.T) {
 				Height: 80,
 			}
 
-			models := handler.Handle(event)
+			models, _ := handler.Handle(event)
 			require.Len(t, models, 1)
 			model := models[0]
 
 			tsk, ok := model.(taskprogress.Model)
 			require.True(t, ok)
 
-			got := runModel(t, tsk, tt.iterations, taskprogress.TickMsg{
+			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/handler.go

@@ -29,6 +29,8 @@ type Handler struct {
 	Config     HandlerConfig
 
 	bubbly.EventHandler
+
+	onNewCatalogerTask *sync.Once
 }
 
 func DefaultHandlerConfig() HandlerConfig {
@@ -41,28 +43,32 @@ func New(cfg HandlerConfig) *Handler {
 	d := bubbly.NewEventDispatcher()
 
 	h := &Handler{
-		EventHandler: d,
-		Running:      &sync.WaitGroup{},
-		Config:       cfg,
+		EventHandler:       d,
+		Running:            &sync.WaitGroup{},
+		Config:             cfg,
+		onNewCatalogerTask: &sync.Once{},
 	}
 
 	// register all supported event types with the respective handler functions
 	d.AddHandlers(map[partybus.EventType]bubbly.EventHandlerFn{
-		stereoscopeEvent.PullDockerImage:       h.handlePullDockerImage,
-		stereoscopeEvent.PullContainerdImage:   h.handlePullContainerdImage,
-		stereoscopeEvent.ReadImage:             h.handleReadImage,
-		stereoscopeEvent.FetchImage:            h.handleFetchImage,
-		syftEvent.PackageCatalogerStarted:      h.handlePackageCatalogerStarted,
-		syftEvent.FileDigestsCatalogerStarted:  h.handleFileDigestsCatalogerStarted,
-		syftEvent.FileMetadataCatalogerStarted: h.handleFileMetadataCatalogerStarted,
-		syftEvent.FileIndexingStarted:          h.handleFileIndexingStarted,
-		syftEvent.AttestationStarted:           h.handleAttestationStarted,
-		syftEvent.CatalogerTaskStarted:         h.handleCatalogerTaskStarted,
+		stereoscopeEvent.PullDockerImage:     simpleHandler(h.handlePullDockerImage),
+		stereoscopeEvent.PullContainerdImage: simpleHandler(h.handlePullContainerdImage),
+		stereoscopeEvent.ReadImage:           simpleHandler(h.handleReadImage),
+		stereoscopeEvent.FetchImage:          simpleHandler(h.handleFetchImage),
+		syftEvent.FileIndexingStarted:        simpleHandler(h.handleFileIndexingStarted),
+		syftEvent.AttestationStarted:         simpleHandler(h.handleAttestationStarted),
+		syftEvent.CatalogerTaskStarted:       h.handleCatalogerTaskStarted,
 	})
 
 	return h
 }
 
+func simpleHandler(fn func(partybus.Event) []tea.Model) bubbly.EventHandlerFn {
+	return func(e partybus.Event) ([]tea.Model, tea.Cmd) {
+		return fn(e), nil
+	}
+}
+
 func (m *Handler) OnMessage(msg tea.Msg) {
 	if msg, ok := msg.(tea.WindowSizeMsg); ok {
 		m.WindowSize = msg

cmd/syft/cli/ui/util_test.go

@@ -4,12 +4,11 @@ import (
 	"reflect"
 	"sync"
 	"testing"
-	"unsafe"
 
 	tea "github.com/charmbracelet/bubbletea"
 )
 
-func runModel(t testing.TB, m tea.Model, iterations int, message tea.Msg, h ...*sync.WaitGroup) string {
+func runModel(t testing.TB, m tea.Model, iterations int, message tea.Msg, h ...*sync.WaitGroup) tea.Model {
 	t.Helper()
 	if iterations == 0 {
 		iterations = 1
@@ -37,34 +36,21 @@ func runModel(t testing.TB, m tea.Model, iterations int, message tea.Msg, h ...*
 		cmd = tea.Batch(nextCmds...)
 	}
 
-	return m.View()
+	return m
 }
 
-func flatten(p tea.Msg) (msgs []tea.Msg) {
-	if reflect.TypeOf(p).Name() == "batchMsg" {
-		partials := extractBatchMessages(p)
-		for _, m := range partials {
-			msgs = append(msgs, flatten(m)...)
+func flatten(ps ...tea.Msg) (msgs []tea.Msg) {
+	for _, p := range ps {
+		if bm, ok := p.(tea.BatchMsg); ok {
+			for _, m := range bm {
+				if m == nil {
+					continue
+				}
+				msgs = append(msgs, flatten(m())...)
+			}
+		} else {
+			msgs = []tea.Msg{p}
 		}
-	} else {
-		msgs = []tea.Msg{p}
 	}
 	return msgs
 }
-
-func extractBatchMessages(m tea.Msg) (ret []tea.Msg) {
-	sliceMsgType := reflect.SliceOf(reflect.TypeOf(tea.Cmd(nil)))
-	value := reflect.ValueOf(m) // note: this is technically unaddressable
-
-	// make our own instance that is addressable
-	valueCopy := reflect.New(value.Type()).Elem()
-	valueCopy.Set(value)
-
-	cmds := reflect.NewAt(sliceMsgType, unsafe.Pointer(valueCopy.UnsafeAddr())).Elem()
-	for i := 0; i < cmds.Len(); i++ {
-		item := cmds.Index(i)
-		r := item.Call(nil)
-		ret = append(ret, r[0].Interface().(tea.Msg))
-	}
-	return ret
-}

cmd/syft/internal/clio_setup_config.go

@@ -0,0 +1,55 @@
+package internal
+
+import (
+	"io"
+	"os"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/stereoscope"
+	ui2 "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"
+	"github.com/anchore/syft/internal/redact"
+)
+
+func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig {
+	clioCfg := clio.NewSetupConfig(id).
+		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
+		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) {
+				noUI := ui.None(out, cfg.Log.Quiet)
+				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
+					return []clio.UI{noUI}, nil
+				}
+
+				return []clio.UI{
+					ui.New(out, cfg.Log.Quiet,
+						ui2.New(ui2.DefaultHandlerConfig()),
+					),
+					noUI,
+				}, nil
+			},
+		).
+		WithInitializers(
+			func(state *clio.State) error {
+				// clio is setting up and providing the bus, redact store, and logger to the application. Once loaded,
+				// we can hoist them into the internal packages for global use.
+				stereoscope.SetBus(state.Bus)
+				bus.Set(state.Bus)
+
+				redact.Set(state.RedactStore)
+
+				log.Set(state.Logger)
+				stereoscope.SetLogger(state.Logger)
+				return nil
+			},
+		).
+		WithPostRuns(func(_ *clio.State, _ error) {
+			stereoscope.Cleanup()
+		})
+	return clioCfg
+}

cmd/syft/internal/commands/attest.go

@@ -1,6 +1,7 @@
 package commands
 
 import (
+	"context"
 	"fmt"
 	"io"
 	"os"
@@ -12,7 +13,8 @@ import (
 	"github.com/wagoodman/go-progress"
 
 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"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"
 	"github.com/anchore/syft/internal/bus"
@@ -25,11 +27,10 @@ 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 (
-	attestExample = `  {{.appName}} {{.command}} --output [FORMAT] alpine:latest defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry
+	attestExample = `  {{.appName}} {{.command}} --output [FORMAT] alpine:latest            defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry
 `
 	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
 	attestHelp       = attestExample + attestSchemeHelp
@@ -41,7 +42,8 @@ type attestOptions struct {
 	options.Output      `yaml:",inline" mapstructure:",squash"`
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 	options.Catalog     `yaml:",inline" mapstructure:",squash"`
-	options.Attest      `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 {
@@ -60,13 +62,13 @@ func Attest(app clio.Application) *cobra.Command {
 			"appName": id.Name,
 			"command": "attest",
 		}),
-		Args:    validatePackagesArgs,
+		Args:    validateScanArgs,
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
 		RunE: func(cmd *cobra.Command, args []string) error {
 			restoreStdout := ui.CaptureStdoutToTraceLog()
 			defer restoreStdout()
 
-			return runAttest(id, &opts, args[0])
+			return runAttest(cmd.Context(), id, &opts, args[0])
 		},
 	}, &opts)
 }
@@ -76,6 +78,7 @@ func defaultAttestOptions() attestOptions {
 		Output:      defaultAttestOutputOptions(),
 		UpdateCheck: options.DefaultUpdateCheck(),
 		Catalog:     options.DefaultCatalog(),
+		Cache:       options.DefaultCache(),
 	}
 }
 
@@ -90,15 +93,14 @@ func defaultAttestOutputOptions() options.Output {
 			string(spdxtagvalue.ID),
 		},
 		Outputs: []string{syftjson.ID.String()},
-		OutputFile: options.OutputFile{ // nolint:staticcheck
+		OutputFile: options.OutputFile{ //nolint:staticcheck
 			Enabled: false, // explicitly not allowed
 		},
 		Format: options.DefaultFormat(),
 	}
 }
 
-//nolint:funlen
-func runAttest(id clio.Identification, opts *attestOptions, userInput string) error {
+func runAttest(ctx context.Context, id clio.Identification, opts *attestOptions, userInput string) error {
 	// TODO: what other validation here besides binary name?
 	if !commandExists(cosignBinName) {
 		return fmt.Errorf("'syft attest' requires cosign to be installed, however it does not appear to be on PATH")
@@ -111,7 +113,7 @@ func runAttest(id clio.Identification, opts *attestOptions, userInput string) er
 	}
 	defer os.Remove(f.Name())
 
-	s, err := generateSBOMForAttestation(id, &opts.Catalog, userInput)
+	s, err := generateSBOMForAttestation(ctx, id, &opts.Catalog, userInput)
 	if err != nil {
 		return fmt.Errorf("unable to build SBOM: %w", err)
 	}
@@ -231,7 +233,7 @@ func attestCommand(sbomFilepath string, opts *attestOptions, userInput string) (
 }
 
 func predicateType(outputName string) string {
-	// Select Cosign predicate type based on defined output type
+	// select the Cosign predicate type based on defined output type
 	// As orientation, check: https://github.com/sigstore/cosign/blob/main/pkg/cosign/attestation/attestation.go
 	switch strings.ToLower(outputName) {
 	case "cyclonedx-json":
@@ -245,8 +247,12 @@ func predicateType(outputName string) string {
 	}
 }
 
-func generateSBOMForAttestation(id clio.Identification, opts *options.Catalog, userInput string) (*sbom.SBOM, error) {
-	src, err := getSource(opts, userInput, onlyContainerImages)
+func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opts *options.Catalog, userInput string) (*sbom.SBOM, error) {
+	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
@@ -260,7 +266,7 @@ func generateSBOMForAttestation(id clio.Identification, opts *options.Catalog, u
 		}
 	}()
 
-	s, err := generateSBOM(id, src, opts)
+	s, err := generateSBOM(ctx, id, src, opts)
 	if err != nil {
 		return nil, err
 	}
@@ -272,13 +278,6 @@ func generateSBOMForAttestation(id clio.Identification, opts *options.Catalog, u
 	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/attest_test.go

@@ -2,18 +2,24 @@ package commands
 
 import (
 	"bytes"
+	"context"
 	"fmt"
+	"io"
 	"os/exec"
 	"regexp"
 	"strings"
 	"testing"
 
+	"github.com/google/go-cmp/cmp"
 	"github.com/scylladb/go-set/strset"
+	"github.com/spf13/cobra"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/clio/cliotestutils"
+	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
@@ -258,7 +264,7 @@ func Test_buildSBOMForAttestation(t *testing.T) {
 			if tt.wantErr == nil {
 				tt.wantErr = require.NoError
 			}
-			_, err := generateSBOMForAttestation(tt.args.id, tt.args.opts, tt.args.userInput)
+			_, err := generateSBOMForAttestation(context.Background(), tt.args.id, tt.args.opts, tt.args.userInput)
 			tt.wantErr(t, err)
 			if err != nil {
 				return
@@ -266,3 +272,60 @@ func Test_buildSBOMForAttestation(t *testing.T) {
 		})
 	}
 }
+
+func Test_attestCLIWiring(t *testing.T) {
+	id := clio.Identification{
+		Name:    "syft",
+		Version: "testing",
+	}
+	cfg := internal.AppClioSetupConfig(id, io.Discard)
+	tests := []struct {
+		name          string
+		assertionFunc func(*testing.T, *cobra.Command, []string, ...any)
+		wantOpts      attestOptions
+		args          []string
+		env           map[string]string
+	}{
+		{
+			name:          "key flag is accepted",
+			args:          []string{"some-image:some-tag", "--key", "some-cosign-key.key"},
+			assertionFunc: hasAttestOpts(options.Attest{Key: "some-cosign-key.key"}),
+		},
+		{
+			name: "key password is read from env",
+			args: []string{"some-image:some-tag", "--key", "cosign.key"},
+			env: map[string]string{
+				"SYFT_ATTEST_PASSWORD": "some-password",
+			},
+			assertionFunc: hasAttestOpts(options.Attest{
+				Key:      "cosign.key",
+				Password: "some-password",
+			}),
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.env != nil {
+				for k, v := range tt.env {
+					t.Setenv(k, v)
+				}
+			}
+			app := cliotestutils.NewApplication(t, cfg, tt.assertionFunc)
+			cmd := Attest(app)
+			cmd.SetArgs(tt.args)
+			err := cmd.Execute()
+			assert.NoError(t, err)
+		})
+	}
+}
+
+func hasAttestOpts(wantOpts options.Attest) cliotestutils.AssertionFunc {
+	return func(t *testing.T, _ *cobra.Command, _ []string, cfgs ...any) {
+		assert.Equal(t, len(cfgs), 1)
+		attestOpts, ok := cfgs[0].(*attestOptions)
+		require.True(t, ok)
+		if d := cmp.Diff(wantOpts, attestOpts.Attest); d != "" {
+			t.Errorf("mismatched attest options (-want +got):\n%s", d)
+		}
+	}
+}

cmd/syft/internal/commands/cataloger.go

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

cmd/syft/internal/commands/cataloger_list.go

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

cmd/syft/internal/commands/cataloger_list_test.go

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

cmd/syft/internal/commands/commands_test.go

@@ -0,0 +1,20 @@
+package commands
+
+import (
+	"os"
+	"testing"
+
+	gologgerredact "github.com/anchore/go-logger/adapter/redact"
+	"github.com/anchore/syft/internal/redact"
+)
+
+func TestMain(m *testing.M) {
+	// Initialize global state needed to test clio/cobra commands directly
+	// Should be kept minimal.
+
+	// Initialize redact store once for all tests in the commands package
+	// Redact store must be wired up here because syft will panic unless
+	// a redact store is wired up exactly once
+	redact.Set(gologgerredact.NewStore())
+	os.Exit(m.Run())
+}

cmd/syft/internal/commands/convert.go

@@ -8,7 +8,7 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
-	"github.com/anchore/syft/cmd/syft/cli/options"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
@@ -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()
 
@@ -47,7 +46,7 @@ func Convert(app clio.Application) *cobra.Command {
 		}),
 		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/packages.go

@@ -0,0 +1,37 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/cmd/syft/internal/ui"
+	"github.com/anchore/syft/internal"
+)
+
+func Packages(app clio.Application, scanCmd *cobra.Command) *cobra.Command {
+	id := app.ID()
+
+	opts := defaultScanOptions()
+
+	cmd := app.SetupCommand(&cobra.Command{
+		Use:   "packages [SOURCE]",
+		Short: scanCmd.Short,
+		Long:  scanCmd.Long,
+		Args:  scanCmd.Args,
+		Example: internal.Tprintf(scanHelp, map[string]interface{}{
+			"appName": id.Name,
+			"command": "packages",
+		}),
+		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
+		RunE: func(cmd *cobra.Command, args []string) error {
+			restoreStdout := ui.CaptureStdoutToTraceLog()
+			defer restoreStdout()
+
+			return runScan(cmd.Context(), id, opts, args[0])
+		},
+	}, opts)
+
+	cmd.Deprecated = "use `syft scan` instead"
+
+	return cmd
+}

cmd/syft/internal/commands/packages_test.go

@@ -0,0 +1,300 @@
+package commands
+
+import (
+	"errors"
+	"fmt"
+	"testing"
+
+	"github.com/hashicorp/go-multierror"
+	"github.com/stretchr/testify/assert"
+
+	"github.com/anchore/syft/internal/task"
+)
+
+func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
+	tests := []struct {
+		name        string
+		err         error
+		wantExpErrs []task.ErrInvalidExpression
+		wantErr     assert.ErrorAssertionFunc
+		wantHelp    string
+	}{
+		{
+			name:        "no errors",
+			err:         nil,
+			wantExpErrs: nil,
+			wantErr:     assert.NoError,
+			wantHelp:    "",
+		},
+		{
+			name: "single non-expression error is retained",
+			err:  errors.New("foo"),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				return assert.Equal(t, "foo", err.Error())
+			},
+			wantHelp: "",
+		},
+		{
+			name: "multiple non-expression sibling errors are retained",
+			err: func() error {
+				var err error
+				err = multierror.Append(err, errors.New("foo"))
+				err = multierror.Append(err, errors.New("bar"))
+				return err
+			}(),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				// note: this is the default formatting from the hashicorp multierror object
+				expected := `2 errors occurred:
+	* foo
+	* bar
+
+`
+				return assert.Equal(t, expected, err.Error())
+			},
+			wantHelp: "",
+		},
+		{
+			name: "has multiple expression errors (with sibling errors)",
+			err: func() error {
+				var err error
+				err = multierror.Append(err, errors.New("foo"))
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed})
+				err = multierror.Append(err, errors.New("bar"))
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed})
+				err = multierror.Append(err, errors.New("last"))
+				return err
+			}(),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				expected := `5 errors occurred:
+	* foo
+	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
+	* bar
+	* invalid expression: "bar": names are not allowed with this operation (must use tags)
+	* last
+
+`
+				return assert.Equal(t, expected, err.Error())
+			},
+			wantExpErrs: []task.ErrInvalidExpression{
+				{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed},
+				{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed},
+			},
+			wantHelp: `Suggestions:
+
+ ❖ Given expression "--select-catalogers foo"
+   However, tags are not allowed with this operation (must use exact names).
+   Adding groups of catalogers may result in surprising behavior (create inaccurate SBOMs).
+   If you are certain this is what you want to do, use "--override-default-catalogers foo" instead.
+
+ ❖ Given expression "--select-catalogers bar"
+   However, names are not allowed with this operation (must use tags).
+   It seems like you are intending to add a cataloger in addition to the default set.
+   ... Did you mean "--select-catalogers +bar" instead?
+`,
+		},
+		{
+			name: "has multiple expression errors (with error chains and sibling errors)",
+			err: func() error {
+				var err error
+				err = multierror.Append(err, fmt.Errorf("foo: %w", fmt.Errorf("bar: %w", errors.New("last"))))
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed})
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed})
+				err = multierror.Append(err, errors.New("bottom"))
+
+				return fmt.Errorf("top: %w", fmt.Errorf("middle: %w", err))
+			}(),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				expected := `top: middle: 4 errors occurred:
+	* foo: bar: last
+	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
+	* invalid expression: "bar": names are not allowed with this operation (must use tags)
+	* bottom
+
+`
+				return assert.Equal(t, expected, err.Error())
+			},
+			wantExpErrs: []task.ErrInvalidExpression{
+				{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed},
+				{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed},
+			},
+			wantHelp: `Suggestions:
+
+ ❖ Given expression "--select-catalogers foo"
+   However, tags are not allowed with this operation (must use exact names).
+   Adding groups of catalogers may result in surprising behavior (create inaccurate SBOMs).
+   If you are certain this is what you want to do, use "--override-default-catalogers foo" instead.
+
+ ❖ Given expression "--select-catalogers bar"
+   However, names are not allowed with this operation (must use tags).
+   It seems like you are intending to add a cataloger in addition to the default set.
+   ... Did you mean "--select-catalogers +bar" instead?
+`,
+		},
+		{
+			name: "has multiple expression errors (with error chains and sibling errors)",
+			err: func() error {
+				var err error
+				err = multierror.Append(err, fmt.Errorf("foo: %w", fmt.Errorf("bar: %w", errors.New("last"))))
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed})
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed})
+				err = multierror.Append(err, errors.New("bottom"))
+
+				// note we wrap the top error in a chain
+				return fmt.Errorf("top: %w", fmt.Errorf("middle: %w", err))
+			}(),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				expected := `top: middle: 4 errors occurred:
+	* foo: bar: last
+	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
+	* invalid expression: "bar": names are not allowed with this operation (must use tags)
+	* bottom
+
+`
+				return assert.Equal(t, expected, err.Error())
+			},
+			wantExpErrs: []task.ErrInvalidExpression{
+				{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed},
+				{Expression: "bar", Operation: task.SubSelectOperation, Err: task.ErrNamesNotAllowed},
+			},
+			wantHelp: `Suggestions:
+
+ ❖ Given expression "--select-catalogers foo"
+   However, tags are not allowed with this operation (must use exact names).
+   Adding groups of catalogers may result in surprising behavior (create inaccurate SBOMs).
+   If you are certain this is what you want to do, use "--override-default-catalogers foo" instead.
+
+ ❖ Given expression "--select-catalogers bar"
+   However, names are not allowed with this operation (must use tags).
+   It seems like you are intending to add a cataloger in addition to the default set.
+   ... Did you mean "--select-catalogers +bar" instead?
+`,
+		},
+		{
+			name: "preserve for any errors within ErrInvalidExpression types",
+			err: func() error {
+				var err error
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed})
+				err = multierror.Append(err, task.ErrInvalidExpression{Expression: "bar", Operation: task.SubSelectOperation, Err: errors.New("explanation")}) // this is what makes this test different...
+
+				return err
+			}(),
+			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+				// note: the errors are removed and the help text shows the enriched error help
+				expected := `2 errors occurred:
+	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
+	* invalid expression: "bar": explanation
+
+`
+				return assert.Equal(t, expected, err.Error())
+			},
+			wantExpErrs: []task.ErrInvalidExpression{
+				{Expression: "foo", Operation: task.AddOperation, Err: task.ErrTagsNotAllowed},
+				{Expression: "bar", Operation: task.SubSelectOperation, Err: errors.New("explanation")},
+			},
+			wantHelp: `Suggestions:
+
+ ❖ Given expression "--select-catalogers foo"
+   However, tags are not allowed with this operation (must use exact names).
+   Adding groups of catalogers may result in surprising behavior (create inaccurate SBOMs).
+   If you are certain this is what you want to do, use "--override-default-catalogers foo" instead.
+
+`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			gotExpErrs := filterExpressionErrors(tt.err)
+			tt.wantErr(t, tt.err) // ensure the error still remains
+			assert.Equal(t, tt.wantExpErrs, gotExpErrs)
+
+			gotHelp := expressionErrorsHelp(gotExpErrs)
+			assert.Equal(t, tt.wantHelp, gotHelp)
+		})
+	}
+}
+
+func Test_expressionSuggestions(t *testing.T) {
+	tests := []struct {
+		name   string
+		expErr task.ErrInvalidExpression
+		want   string
+	}{
+		{
+			name: "no embedded error",
+			expErr: task.ErrInvalidExpression{
+				Expression: "example",
+			},
+			want: ``,
+		},
+		{
+			name: "general error",
+			expErr: task.ErrInvalidExpression{
+				Err:        errors.New("general error message"),
+				Expression: "example",
+			},
+			want: ``,
+		},
+		{
+			name: "ErrUnknownNameOrTag with add operation",
+			expErr: task.ErrInvalidExpression{
+				Err:        task.ErrUnknownNameOrTag,
+				Operation:  task.AddOperation,
+				Expression: "+example",
+			},
+			want: ``,
+		},
+		{
+			name: "ErrUnknownNameOrTag with subselect operation",
+			expErr: task.ErrInvalidExpression{
+				Err:        task.ErrUnknownNameOrTag,
+				Operation:  task.SubSelectOperation,
+				Expression: "example",
+			},
+			want: ``,
+		},
+		{
+			name: "ErrNamesNotAllowed with subselect operator",
+			expErr: task.ErrInvalidExpression{
+				Err:        task.ErrNamesNotAllowed,
+				Operation:  task.SubSelectOperation,
+				Expression: "example",
+			},
+			want: ` ❖ Given expression "--select-catalogers example"
+   However, names are not allowed with this operation (must use tags).
+   It seems like you are intending to add a cataloger in addition to the default set.
+   ... Did you mean "--select-catalogers +example" instead?
+`,
+		},
+		{
+			name: "ErrTagsNotAllowed with add operation",
+			expErr: task.ErrInvalidExpression{
+				Err:        task.ErrTagsNotAllowed,
+				Operation:  task.AddOperation,
+				Expression: "+example",
+			},
+			want: ` ❖ Given expression "--select-catalogers +example"
+   However, tags are not allowed with this operation (must use exact names).
+   Adding groups of catalogers may result in surprising behavior (create inaccurate SBOMs).
+   If you are certain this is what you want to do, use "--override-default-catalogers example" instead.
+`,
+		},
+		{
+			name: "ErrAllNotAllowed with subselect operation",
+			expErr: task.ErrInvalidExpression{
+				Err:        task.ErrAllNotAllowed,
+				Operation:  task.SubSelectOperation,
+				Expression: "example",
+			},
+			want: ` ❖ Given expression "--select-catalogers example"
+   However, you cannot use the 'all' operand in this context.
+   It seems like you are intending to use all catalogers (which is not recommended).
+   ... Did you mean "--override-default-catalogers example" instead?
+`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, expressionSuggetions(tt.expErr))
+		})
+	}
+}

cmd/syft/internal/commands/root.go

@@ -12,7 +12,7 @@ import (
 func Root(app clio.Application, packagesCmd *cobra.Command) *cobra.Command {
 	id := app.ID()
 
-	opts := defaultPackagesOptions()
+	opts := defaultScanOptions()
 
 	return app.SetupRootCommand(&cobra.Command{
 		Use:     fmt.Sprintf("%s [SOURCE]", app.ID().Name),
@@ -25,7 +25,7 @@ func Root(app clio.Application, packagesCmd *cobra.Command) *cobra.Command {
 			restoreStdout := ui.CaptureStdoutToTraceLog()
 			defer restoreStdout()
 
-			return runPackages(id, opts, args[0])
+			return runScan(cmd.Context(), id, opts, args[0])
 		},
 	}, opts)
 }

cmd/syft/internal/commands/scan.go

@@ -0,0 +1,448 @@
+package commands
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"reflect"
+	"strings"
+
+	"github.com/hashicorp/go-multierror"
+	"github.com/spf13/cobra"
+	"gopkg.in/yaml.v3"
+
+	"github.com/anchore/clio"
+	"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"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/bus"
+	"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/sbom"
+	"github.com/anchore/syft/syft/source"
+	"github.com/anchore/syft/syft/source/sourceproviders"
+)
+
+const (
+	scanExample = `  {{.appName}} {{.command}} alpine:latest                                a summary of discovered packages
+  {{.appName}} {{.command}} alpine:latest -o json                        show all possible cataloging details
+  {{.appName}} {{.command}} alpine:latest -o cyclonedx                   show a CycloneDX formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o cyclonedx-json              show a CycloneDX JSON formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx                        show a SPDX 2.3 Tag-Value formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx@2.2                    show a SPDX 2.2 Tag-Value formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx-json                   show a SPDX 2.3 JSON formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx-json@2.2               show a SPDX 2.2 JSON formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -vv                            show verbose debug information
+  {{.appName}} {{.command}} alpine:latest -o template -t my_format.tmpl  show a SBOM formatted according to given template file
+
+  Supports the following image sources:
+    {{.appName}} {{.command}} yourrepo/yourimage:tag     defaults to using images from a Docker daemon. If Docker is not present, the image is pulled directly from the registry.
+    {{.appName}} {{.command}} path/to/a/file/or/dir      a Docker tar, OCI tar, OCI directory, SIF container, or generic filesystem directory
+`
+
+	schemeHelpHeader = "You can also explicitly specify the scheme to use:"
+	imageSchemeHelp  = `    {{.appName}} {{.command}} docker:yourrepo/yourimage:tag            explicitly use the Docker daemon
+    {{.appName}} {{.command}} podman:yourrepo/yourimage:tag            explicitly use the Podman daemon
+    {{.appName}} {{.command}} registry:yourrepo/yourimage:tag          pull image directly from a registry (no container runtime required)
+    {{.appName}} {{.command}} docker-archive:path/to/yourimage.tar     use a tarball from disk for archives created from "docker save"
+    {{.appName}} {{.command}} oci-archive:path/to/yourimage.tar        use a tarball from disk for OCI archives (from Skopeo or otherwise)
+    {{.appName}} {{.command}} oci-dir:path/to/yourimage                read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
+    {{.appName}} {{.command}} singularity:path/to/yourimage.sif        read directly from a Singularity Image Format (SIF) container on disk
+`
+	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
+
+	scanHelp = scanExample + scanSchemeHelp
+)
+
+type scanOptions struct {
+	options.Config      `yaml:",inline" mapstructure:",squash"`
+	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 {
+	return &scanOptions{
+		Output:      options.DefaultOutput(),
+		UpdateCheck: options.DefaultUpdateCheck(),
+		Catalog:     options.DefaultCatalog(),
+		Cache:       options.DefaultCache(),
+	}
+}
+
+func Scan(app clio.Application) *cobra.Command {
+	id := app.ID()
+
+	opts := defaultScanOptions()
+
+	return app.SetupCommand(&cobra.Command{
+		Use:   "scan [SOURCE]",
+		Short: "Generate an SBOM",
+		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from container images and filesystems",
+		Example: internal.Tprintf(scanHelp, map[string]interface{}{
+			"appName": id.Name,
+			"command": "scan",
+		}),
+		Args:    validateScanArgs,
+		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
+		RunE: func(cmd *cobra.Command, args []string) error {
+			restoreStdout := ui.CaptureStdoutToTraceLog()
+			defer restoreStdout()
+
+			return runScan(cmd.Context(), id, opts, args[0])
+		},
+	}, opts)
+}
+
+func (o *scanOptions) PostLoad() error {
+	return o.validateLegacyOptionsNotUsed()
+}
+
+func (o *scanOptions) validateLegacyOptionsNotUsed() error {
+	if o.Config.ConfigFile == "" {
+		return nil
+	}
+
+	// check for legacy config file shapes that are no longer valid
+	type legacyConfig struct {
+		BasePath                        *string `yaml:"base-path" json:"base-path" mapstructure:"base-path"`
+		DefaultImagePullSource          *string `yaml:"default-image-pull-source" json:"default-image-pull-source" mapstructure:"default-image-pull-source"`
+		ExcludeBinaryOverlapByOwnership *bool   `yaml:"exclude-binary-overlap-by-ownership" json:"exclude-binary-overlap-by-ownership" mapstructure:"exclude-binary-overlap-by-ownership"`
+		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)
+	}
+
+	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)
+	}
+
+	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.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")
+	}
+
+	return nil
+}
+
+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 {
+	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("%v", error)
+	}
+
+	return cobra.MaximumNArgs(1)(cmd, args)
+}
+
+func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, userInput string) error {
+	writer, err := opts.SBOMWriter()
+	if err != nil {
+		return err
+	}
+
+	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
+	}
+
+	defer func() {
+		if src != nil {
+			if err := src.Close(); err != nil {
+				log.Tracef("unable to close source: %+v", err)
+			}
+		}
+	}()
+
+	s, err := generateSBOM(ctx, id, src, &opts.Catalog)
+	if err != nil {
+		return err
+	}
+
+	if s == nil {
+		return fmt.Errorf("no SBOM produced for %q", userInput)
+	}
+
+	if err := writer.Write(*s); err != nil {
+		return fmt.Errorf("failed to write SBOM: %w", err)
+	}
+
+	return nil
+}
+
+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,
+		}).
+		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 != "" {
+		platform, err = image.NewPlatform(opts.Platform)
+		if err != nil {
+			return nil, fmt.Errorf("invalid platform: %w", err)
+		}
+		cfg = cfg.WithPlatform(platform)
+	}
+
+	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)
+		}
+		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
+}
+
+func generateSBOM(ctx context.Context, id clio.Identification, src source.Source, opts *options.Catalog) (*sbom.SBOM, error) {
+	s, err := syft.CreateSBOM(ctx, src, opts.ToSBOMConfig(id))
+	if err != nil {
+		expErrs := filterExpressionErrors(err)
+		notifyExpressionErrors(expErrs)
+		return nil, err
+	}
+	return s, nil
+}
+
+func filterExpressionErrors(err error) []task.ErrInvalidExpression {
+	if err == nil {
+		return nil
+	}
+
+	expErrs := processErrors(err)
+
+	return expErrs
+}
+
+// processErrors traverses error chains and multierror lists and returns all ErrInvalidExpression errors found
+func processErrors(err error) []task.ErrInvalidExpression {
+	var result []task.ErrInvalidExpression
+
+	var processError func(...error)
+	processError = func(errs ...error) {
+		for _, e := range errs {
+			// note: using errors.As will result in surprising behavior (since that will traverse the error chain,
+			// potentially skipping over nodes in a list of errors)
+			if cerr, ok := e.(task.ErrInvalidExpression); ok {
+				result = append(result, cerr)
+				continue
+			}
+			var multiErr *multierror.Error
+			if errors.As(e, &multiErr) {
+				processError(multiErr.Errors...)
+			}
+		}
+	}
+
+	processError(err)
+
+	return result
+}
+
+func notifyExpressionErrors(expErrs []task.ErrInvalidExpression) {
+	helpText := expressionErrorsHelp(expErrs)
+	if helpText == "" {
+		return
+	}
+
+	bus.Notify(helpText)
+}
+
+func expressionErrorsHelp(expErrs []task.ErrInvalidExpression) string {
+	// enrich all errors found with CLI hints
+	if len(expErrs) == 0 {
+		return ""
+	}
+
+	sb := strings.Builder{}
+
+	sb.WriteString("Suggestions:\n\n")
+
+	found := false
+	for i, expErr := range expErrs {
+		help := expressionSuggetions(expErr)
+		if help == "" {
+			continue
+		}
+		found = true
+		sb.WriteString(help)
+		if i != len(expErrs)-1 {
+			sb.WriteString("\n")
+		}
+	}
+
+	if !found {
+		return ""
+	}
+
+	return sb.String()
+}
+
+const expressionHelpTemplate = " ❖ Given expression %q\n%s%s"
+
+func expressionSuggetions(expErr task.ErrInvalidExpression) string {
+	if expErr.Err == nil {
+		return ""
+	}
+
+	hint := getHintPhrase(expErr)
+	if hint == "" {
+		return ""
+	}
+
+	return fmt.Sprintf(expressionHelpTemplate,
+		getExpression(expErr),
+		indentMsg(getExplanation(expErr)),
+		indentMsg(hint),
+	)
+}
+
+func indentMsg(msg string) string {
+	if msg == "" {
+		return ""
+	}
+
+	lines := strings.Split(msg, "\n")
+	for i, line := range lines {
+		lines[i] = "   " + line
+	}
+
+	return strings.Join(lines, "\n") + "\n"
+}
+
+func getExpression(expErr task.ErrInvalidExpression) string {
+	flag := "--select-catalogers"
+	if expErr.Operation == task.SetOperation {
+		flag = "--override-default-catalogers"
+	}
+	return fmt.Sprintf("%s %s", flag, expErr.Expression)
+}
+
+func getExplanation(expErr task.ErrInvalidExpression) string {
+	err := expErr.Err
+	if errors.Is(err, task.ErrUnknownNameOrTag) {
+		noun := ""
+		switch expErr.Operation {
+		case task.AddOperation:
+			noun = "name"
+		case task.SubSelectOperation:
+			noun = "tag"
+		default:
+			noun = "name or tag"
+		}
+
+		return fmt.Sprintf("However, %q is not a recognized cataloger %s.", trimOperation(expErr.Expression), noun)
+	}
+
+	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."
+		}
+		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)."
+	}
+
+	if errors.Is(err, task.ErrAllNotAllowed) {
+		return "However, you " + err.Error() + ".\nIt seems like you are intending to use all catalogers (which is not recommended)."
+	}
+
+	if err != nil {
+		return "However, this is not valid: " + err.Error()
+	}
+
+	return ""
+}
+
+func getHintPhrase(expErr task.ErrInvalidExpression) string {
+	if errors.Is(expErr.Err, task.ErrUnknownNameOrTag) {
+		return ""
+	}
+
+	switch expErr.Operation {
+	case task.AddOperation:
+		if errors.Is(expErr.Err, task.ErrTagsNotAllowed) {
+			return fmt.Sprintf("If you are certain this is what you want to do, use %q instead.", "--override-default-catalogers "+trimOperation(expErr.Expression))
+		}
+
+	case task.SubSelectOperation:
+		didYouMean := "... Did you mean %q instead?"
+		if errors.Is(expErr.Err, task.ErrNamesNotAllowed) {
+			return fmt.Sprintf(didYouMean, "--select-catalogers +"+expErr.Expression)
+		}
+
+		if errors.Is(expErr.Err, task.ErrAllNotAllowed) {
+			return fmt.Sprintf(didYouMean, "--override-default-catalogers "+expErr.Expression)
+		}
+	}
+	return ""
+}
+
+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

@@ -0,0 +1,66 @@
+package commands
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/anchore/syft/cmd/syft/internal/options"
+)
+
+func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
+	tests := []struct {
+		name    string
+		cfg     string
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "no config file",
+		},
+		{
+			name: "config file with no legacy options",
+			cfg:  "test-fixtures/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",
+			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",
+			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",
+			wantErr: assertErrorContains("outputs"),
+		},
+		{
+			name: "config file with file section",
+			cfg:  "test-fixtures/scan-configs/with-file-section.yaml",
+		},
+		{
+			name:    "config file with base-path legacy option",
+			cfg:     "test-fixtures/scan-configs/with-base-path.yaml",
+			wantErr: assertErrorContains("source.base-path"),
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			o := &scanOptions{
+				Config: options.Config{ConfigFile: tt.cfg},
+			}
+			tt.wantErr(t, o.validateLegacyOptionsNotUsed())
+		})
+	}
+}
+
+func assertErrorContains(contains string) assert.ErrorAssertionFunc {
+	return func(t assert.TestingT, err error, i ...interface{}) bool {
+		return assert.ErrorContains(t, err, contains, i...)
+	}
+}

cmd/syft/internal/commands/test-fixtures/scan-configs/no-legacy-options.yaml

@@ -0,0 +1,2 @@
+# simple, valid syft config with no legacy fields used
+parallelism: 5

cmd/syft/internal/commands/test-fixtures/scan-configs/with-base-path.yaml

@@ -0,0 +1 @@
+base-path: "something"

cmd/syft/internal/commands/test-fixtures/scan-configs/with-default-pull-source.yaml

@@ -0,0 +1 @@
+default-image-pull-source: "something"

cmd/syft/internal/commands/test-fixtures/scan-configs/with-exclude-binary-overlap-by-ownership.yaml

@@ -0,0 +1 @@
+exclude-binary-overlap-by-ownership: true

cmd/syft/internal/commands/test-fixtures/scan-configs/with-file-section.yaml

@@ -0,0 +1,2 @@
+file:
+  selection: all

cmd/syft/internal/commands/test-fixtures/scan-configs/with-file-string.yaml

@@ -0,0 +1 @@
+file: path

cmd/syft/internal/commands/update.go

@@ -11,8 +11,8 @@ import (
 
 	"github.com/anchore/clio"
 	hashiVersion "github.com/anchore/go-version"
-	"github.com/anchore/syft/cmd/syft/cli/options"
 	"github.com/anchore/syft/cmd/syft/internal"
+	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/event"
@@ -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)
 		}

cmd/syft/internal/options/attest.go

@@ -4,14 +4,24 @@ import (
 	"github.com/anchore/clio"
 )
 
+var _ clio.FlagAdder = (*Attest)(nil)
+
 type Attest struct {
 	// IMPORTANT: do not show the attestation key/password in any YAML/JSON output (sensitive information)
 	Key      secret `yaml:"key" json:"key" mapstructure:"key"`
 	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) {
+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/mitchellh/go-homedir"
+
+	"github.com/anchore/clio"
+	"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 +1,313 @@
+package options
+
+import (
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/adrg/xdg"
+	"github.com/mitchellh/go-homedir"
+	"github.com/stretchr/testify/require"
+
+	"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)
+	}
+
+	unsetEnv := func(t *testing.T) {
+		for k := range env {
+			t.Setenv(k, "")
+		}
+	}
+
+	resetEnv := func() {
+		for k, v := range env {
+			if v == "" {
+				_ = os.Unsetenv(k)
+			} else {
+				_ = os.Setenv(k, v)
+			}
+		}
+		homedir.Reset()
+		xdg.Reload()
+	}
+
+	t.Cleanup(resetEnv)
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			defer resetEnv()
+
+			unsetEnv(t)
+			for k, v := range test.env {
+				t.Setenv(k, v)
+			}
+			homedir.Reset()
+			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)
+		})
+	}
+}

cmd/syft/internal/options/catalog.go

@@ -0,0 +1,323 @@
+package options
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+
+	"github.com/iancoleman/strcase"
+
+	"github.com/anchore/clio"
+	"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/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/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"`
+	Compliance        complianceConfig    `yaml:"compliance" json:"compliance" mapstructure:"compliance"`
+	Enrich            []string            `yaml:"enrich" json:"enrich" mapstructure:"enrich"`
+
+	// ecosystem-specific cataloger configuration
+	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"`
+	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"`
+}
+
+var _ interface {
+	clio.FlagAdder
+	clio.PostLoader
+	clio.FieldDescriber
+} = (*Catalog)(nil)
+
+func DefaultCatalog() Catalog {
+	return Catalog{
+		Compliance:    defaultComplianceConfig(),
+		Scope:         source.SquashedScope.String(),
+		Package:       defaultPackageConfig(),
+		LinuxKernel:   defaultLinuxKernelConfig(),
+		Golang:        defaultGolangConfig(),
+		Java:          defaultJavaConfig(),
+		File:          defaultFileConfig(),
+		Relationships: defaultRelationshipsConfig(),
+		Source:        defaultSourceConfig(),
+		Parallelism:   1,
+	}
+}
+
+func (cfg Catalog) ToSBOMConfig(id clio.Identification) *syft.CreateSBOMConfig {
+	return syft.DefaultCreateSBOMConfig().
+		WithTool(id.Name, id.Version).
+		WithParallelism(cfg.Parallelism).
+		WithRelationshipsConfig(cfg.ToRelationshipsConfig()).
+		WithComplianceConfig(cfg.ToComplianceConfig()).
+		WithSearchConfig(cfg.ToSearchConfig()).
+		WithPackagesConfig(cfg.ToPackagesConfig()).
+		WithFilesConfig(cfg.ToFilesConfig()).
+		WithCatalogerSelection(
+			pkgcataloging.NewSelectionRequest().
+				WithDefaults(cfg.DefaultCatalogers...).
+				WithExpression(cfg.SelectCatalogers...),
+		)
+}
+
+func (cfg Catalog) ToSearchConfig() cataloging.SearchConfig {
+	return cataloging.SearchConfig{
+		Scope: source.ParseScope(cfg.Scope),
+	}
+}
+
+func (cfg Catalog) ToRelationshipsConfig() cataloging.RelationshipsConfig {
+	return cataloging.RelationshipsConfig{
+		PackageFileOwnership:        cfg.Relationships.PackageFileOwnership,
+		PackageFileOwnershipOverlap: cfg.Relationships.PackageFileOwnershipOverlap,
+		// note: this option was surfaced in the syft application configuration before this relationships section was added
+		ExcludeBinaryPackagesWithFileOwnershipOverlap: cfg.Package.ExcludeBinaryOverlapByOwnership,
+	}
+}
+
+func (cfg Catalog) ToComplianceConfig() cataloging.ComplianceConfig {
+	return cataloging.ComplianceConfig{
+		MissingName:    cfg.Compliance.MissingName,
+		MissingVersion: cfg.Compliance.MissingVersion,
+	}
+}
+
+func (cfg Catalog) ToFilesConfig() filecataloging.Config {
+	hashers, err := intFile.Hashers(cfg.File.Metadata.Digests...)
+	if err != nil {
+		log.WithFields("error", err).Warn("unable to configure file hashers")
+	}
+
+	return filecataloging.Config{
+		Selection: cfg.File.Metadata.Selection,
+		Hashers:   hashers,
+		Content: filecontent.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) ToPackagesConfig() pkgcataloging.Config {
+	archiveSearch := cataloging.ArchiveSearchConfig{
+		IncludeIndexedArchives:   cfg.Package.SearchIndexedArchives,
+		IncludeUnindexedArchives: cfg.Package.SearchUnindexedArchives,
+	}
+	return pkgcataloging.Config{
+		Binary: binary.DefaultClassifierCatalogerConfig(),
+		Golang: golang.DefaultCatalogerConfig().
+			WithSearchLocalModCacheLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchLocalModCacheLicenses)).
+			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchRemoteLicenses)).
+			WithProxy(cfg.Golang.Proxy).
+			WithNoProxy(cfg.Golang.NoProxy).
+			WithMainModuleVersion(
+				golang.DefaultMainModuleVersionConfig().
+					WithFromContents(cfg.Golang.MainModuleVersion.FromContents).
+					WithFromBuildSettings(cfg.Golang.MainModuleVersion.FromBuildSettings).
+					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
+			),
+		JavaScript: javascript.DefaultCatalogerConfig().
+			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,
+		},
+		JavaArchive: java.DefaultArchiveCatalogerConfig().
+			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),
+	}
+}
+
+func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
+	var validScopeValues []string
+	for _, scope := range source.AllScopes {
+		validScopeValues = append(validScopeValues, strcase.ToDelimited(string(scope), '-'))
+	}
+	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")
+
+	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")
+
+	flags.StringVarP(&cfg.Source.Version, "source-version", "",
+		"set the version of the target being analyzed")
+
+	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")
+}
+
+func (cfg *Catalog) DescribeFields(descriptions fangs.FieldDescriptionSet) {
+	descriptions.Add(&cfg.Parallelism, "number of cataloger workers to run in parallel")
+
+	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")
+	}
+
+	cfg.From = flatten(cfg.From)
+
+	cfg.Catalogers = flatten(cfg.Catalogers)
+	cfg.DefaultCatalogers = flatten(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = flatten(cfg.SelectCatalogers)
+	cfg.Enrich = flatten(cfg.Enrich)
+
+	// for backwards compatibility
+	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
+
+	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))
+		}
+	}
+	sort.Strings(out)
+	return out
+}
+
+var publicisedEnrichmentOptions = []string{
+	"all",
+	task.Golang,
+	task.Java,
+	task.JavaScript,
+}
+
+func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {
+	if len(enrichDirectives) == 0 {
+		return nil
+	}
+
+	enabled := func(features ...string) *bool {
+		for _, directive := range enrichDirectives {
+			enable := true
+			directive = strings.TrimPrefix(directive, "+") // +java and java are equivalent
+			if strings.HasPrefix(directive, "-") {
+				directive = directive[1:]
+				enable = false
+			}
+			for _, feature := range features {
+				if directive == feature {
+					return &enable
+				}
+			}
+		}
+		return nil
+	}
+
+	enableAll := enabled("all")
+	disableAll := enabled("none")
+
+	if disableAll != nil && *disableAll {
+		if enableAll != nil {
+			log.Warn("you have specified to both enable and disable all enrichment functionality, defaulting to disabled")
+		}
+		enableAll = ptr(false)
+	}
+
+	// check for explicit enable/disable of feature names
+	for _, feat := range features {
+		enableFeature := enabled(feat)
+		if enableFeature != nil {
+			return enableFeature
+		}
+	}
+
+	return enableAll
+}
+
+func ptr[T any](val T) *T {
+	return &val
+}

cmd/syft/internal/options/catalog_test.go

@@ -0,0 +1,146 @@
+package options
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCatalog_PostLoad(t *testing.T) {
+
+	tests := []struct {
+		name    string
+		options Catalog
+		assert  func(t *testing.T, options Catalog)
+		wantErr assert.ErrorAssertionFunc
+	}{
+		{
+			name: "mutually exclusive cataloger flags (cat / def-cat)",
+			options: Catalog{
+				Catalogers:        []string{"foo,bar", "42"},
+				DefaultCatalogers: []string{"some,thing"},
+				Scope:             "squashed",
+			},
+			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)
+			},
+		},
+		{
+			name: "must have package overlap flag when pruning binaries by overlap",
+			options: Catalog{
+				Package:       packageConfig{ExcludeBinaryOverlapByOwnership: true},
+				Relationships: relationshipsConfig{PackageFileOwnershipOverlap: false},
+			},
+			wantErr: assert.Error,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			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)
+			}
+		})
+	}
+}
+
+func Test_enrichmentEnabled(t *testing.T) {
+	tests := []struct {
+		directives string
+		test       string
+		expected   *bool
+	}{
+		{
+			directives: "",
+			test:       "java",
+			expected:   nil,
+		},
+		{
+			directives: "none",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "none,+java",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "all,none",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "all",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "golang,js",
+			test:       "java",
+			expected:   nil,
+		},
+		{
+			directives: "golang,-js,java",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "golang,js,-java",
+			test:       "java",
+			expected:   ptr(false),
+		},
+		{
+			directives: "all",
+			test:       "java",
+			expected:   ptr(true),
+		},
+		{
+			directives: "all,-java",
+			test:       "java",
+			expected:   ptr(false),
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.directives, func(t *testing.T) {
+			got := enrichmentEnabled(flatten([]string{test.directives}), test.test)
+			assert.Equal(t, test.expected, got)
+		})
+	}
+}

cmd/syft/internal/options/compliance.go

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

cmd/syft/internal/options/config.go

@@ -0,0 +1,12 @@
+package options
+
+import "github.com/anchore/fangs"
+
+// Config holds a reference to the specific config file that was 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")
+}

cmd/syft/internal/options/file.go

@@ -0,0 +1,78 @@
+package options
+
+import (
+	"fmt"
+	"sort"
+
+	"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"`
+	Executable fileExecutable `yaml:"executable" json:"executable" mapstructure:"executable"`
+}
+
+type fileMetadata struct {
+	Selection file.Selection `yaml:"selection" json:"selection" mapstructure:"selection"`
+	Digests   []string       `yaml:"digests" json:"digests" mapstructure:"digests"`
+}
+
+type fileContent struct {
+	SkipFilesAboveSize int64    `yaml:"skip-files-above-size" json:"skip-files-above-size" mapstructure:"skip-files-above-size"`
+	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{
+			Selection: file.FilesOwnedByPackageSelection,
+			Digests:   []string{"sha1", "sha256"},
+		},
+		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)
+	c.Metadata.Digests = digests
+
+	switch c.Metadata.Selection {
+	case file.NoFilesSelection, file.FilesOwnedByPackageSelection, file.AllFilesSelection:
+		return nil
+	}
+	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`)
+}