[wip] prototype binary relationships

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

.binny.yaml

@@ -0,0 +1,117 @@
+tools:
+  # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
+  - name: binny
+    version:
+      want: v0.6.3
+    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
+    method: github-release
+    with:
+      repo: anchore/quill
+
+  # used for linting
+  - name: golangci-lint
+    version:
+      want: v1.56.2
+    method: github-release
+    with:
+      repo: golangci/golangci-lint
+
+  # used for showing the changelog at release
+  - name: glow
+    version:
+      want: v1.5.1
+    method: github-release
+    with:
+      repo: charmbracelet/glow
+
+  # used for signing the checksums file at release
+  - name: cosign
+    version:
+      want: v2.2.3
+    method: github-release
+    with:
+      repo: sigstore/cosign
+
+  # used in integration tests to verify JSON schemas
+  - name: yajsv
+    version:
+      want: v1.4.1
+    method: github-release
+    with:
+      repo: neilpa/yajsv
+
+  # used to release all artifacts
+  - name: goreleaser
+    version:
+      want: v1.24.0
+    method: github-release
+    with:
+      repo: goreleaser/goreleaser
+
+  # used for organizing imports during static analysis
+  - name: gosimports
+    version:
+      want: v0.3.8
+    method: github-release
+    with:
+      repo: rinchsan/gosimports
+
+  # used at release to generate the changelog
+  - name: chronicle
+    version:
+      want: v0.8.0
+    method: github-release
+    with:
+      repo: anchore/chronicle
+
+  # used during static analysis for license compliance
+  - name: bouncer
+    version:
+      want: v0.4.0
+    method: github-release
+    with:
+      repo: wagoodman/go-bouncer
+
+  # used for showing benchmark testing
+  - name: benchstat
+    version:
+      want: latest
+      method: go-proxy
+      with:
+        module: golang.org/x/perf
+        allow-unresolved-version: true
+    method: go-install
+    with:
+      entrypoint: cmd/benchstat
+      module: golang.org/x/perf
+
+  # used for running all local and CI tasks
+  - name: task
+    version:
+      want: v3.35.1
+    method: github-release
+    with:
+      repo: go-task/task
+
+  # used for triggering a release
+  - name: gh
+    version:
+      want: v2.45.0
+    method: github-release
+    with:
+      repo: cli/cli

.chronicle.yaml

@@ -1,2 +1,78 @@
-enforce-v0: true # don't make breaking-change label bump major version before 1.0.
-title: ""
+enforce-v0: false
+title: ""
+
+github:
+  host: github.com
+  include-issue-pr-authors: true
+  include-issue-prs: true
+  include-issues-not-planned: false
+  include-prs: true
+  include-issues: true
+  include-unlabeled-issues: true
+  include-unlabeled-prs: true
+  issues-require-linked-prs: false
+  consider-pr-merge-commits: true
+
+  exclude-labels:
+    - duplicate
+    - question
+    - invalid
+    - wontfix
+    - wont-fix
+    - release-ignore
+    - changelog-ignore
+    - ignore
+
+  changes:
+
+    - name: security-fixes
+      title: Security Fixes
+      semver-field: patch
+      labels:
+        - security
+        - vulnerability
+
+    - name: added-feature
+      title: Added Features
+      semver-field: minor
+      labels:
+        - enhancement
+        - feature
+        - minor
+
+    - name: bug-fix
+      title: Bug Fixes
+      semver-field: patch
+      labels:
+        - bug
+        - fix
+        - bug-fix
+        - patch
+
+    - name: breaking-feature
+      title: Breaking Changes
+      semver-field: major
+      labels:
+        - breaking
+        - backwards-incompatible
+        - breaking-change
+        - breaking-feature
+        - major
+        - detected-breaking-change
+
+    - name: removed-feature
+      title: Removed Features
+      semver-field: major
+      labels:
+        - removed
+
+    - name: deprecated-feature
+      title: Deprecated Features
+      semver-field: minor
+      labels:
+        - deprecated
+
+    - name: unknown
+      title: Additional Changes
+      semver-field: ""
+      labels: []

.github/actions/bootstrap/action.yaml

@@ -6,23 +6,29 @@ inputs:
     description: "Go version to install"
     required: true
     default: "1.21.x"
+  go-dependencies:
+    description: "Download go dependencies"
+    required: true
+    default: "true"
   cache-key-prefix:
     description: "Prefix all cache keys with this value"
     required: true
-    default: "831180ac25"
-  build-cache-key-prefix:
-    description: "Prefix build cache key with this value"
+    default: "1ac8281053"
+  compute-fingerprints:
+    description: "Compute test fixture fingerprints"
     required: true
-    default: "f8b6d31dea"
+    default: "true"
   bootstrap-apt-packages:
     description: "Space delimited list of tools to install via apt"
     default: "libxml2-utils"
 
+
 runs:
   using: "composite"
   steps:
     # note: go mod and build is automatically cached on default with v4+
     - uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      if: inputs.go-version != ''
       with:
         go-version: ${{ inputs.go-version }}
 
@@ -30,17 +36,17 @@ runs:
       id: tool-cache
       uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
       with:
-        path: ${{ github.workspace }}/.tmp
-        key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('Makefile') }}
+        path: ${{ github.workspace }}/.tool
+        key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
 
-    - name: (cache-miss) Bootstrap project tools
+    - name: Install project tools
       shell: bash
-      if: steps.tool-cache.outputs.cache-hit != 'true'
-      run: make bootstrap-tools
+      run: make tools
 
-    - name: Bootstrap go dependencies
+    - name: Install go dependencies
+      if: inputs.go-dependencies == 'true'
       shell: bash
-      run: make bootstrap-go
+      run: make ci-bootstrap-go
 
     - name: Install apt packages
       if: inputs.bootstrap-apt-packages != ''
@@ -49,6 +55,7 @@ runs:
         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
 

.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/goreleaser-install.sh

@@ -1,398 +0,0 @@
-#!/bin/sh
-set -e
-# Code generated by godownloader on 2019-12-25T12:47:14Z. DO NOT EDIT.
-#
-
-usage() {
-	this=$1
-	cat <<EOF
-$this: download go binaries for goreleaser/goreleaser
-
-Usage: $this [-b] bindir [-d] [tag]
-  -b sets bindir or installation directory, Defaults to ./bin
-  -d turns on debug logging
-   [tag] is a tag from
-   https://github.com/goreleaser/goreleaser/releases
-   If tag is missing, then the latest will be used.
-
- Generated by godownloader
-  https://github.com/goreleaser/godownloader
-
-EOF
-	exit 2
-}
-
-parse_args() {
-	#BINDIR is ./bin unless set be ENV
-	# over-ridden by flag below
-
-	BINDIR=${BINDIR:-./bin}
-	while getopts "b:dh?x" arg; do
-		case "$arg" in
-		b) BINDIR="$OPTARG" ;;
-		d) log_set_priority 10 ;;
-		h | \?) usage "$0" ;;
-		x) set -x ;;
-		esac
-	done
-	shift $((OPTIND - 1))
-	TAG=$1
-}
-# this function wraps all the destructive operations
-# if a curl|bash cuts off the end of the script due to
-# network, either nothing will happen or will syntax error
-# out preventing half-done work
-execute() {
-	tmpdir=$(mktemp -d)
-	log_debug "downloading files into ${tmpdir}"
-	http_download "${tmpdir}/${TARBALL}" "${TARBALL_URL}"
-	http_download "${tmpdir}/${CHECKSUM}" "${CHECKSUM_URL}"
-	hash_sha256_verify "${tmpdir}/${TARBALL}" "${tmpdir}/${CHECKSUM}"
-	srcdir="${tmpdir}"
-	(cd "${tmpdir}" && untar "${TARBALL}")
-	test ! -d "${BINDIR}" && install -d "${BINDIR}"
-	for binexe in $BINARIES; do
-		if [ "$OS" = "windows" ]; then
-			binexe="${binexe}.exe"
-		fi
-		install "${srcdir}/${binexe}" "${BINDIR}/"
-		log_info "installed ${BINDIR}/${binexe}"
-	done
-	rm -rf "${tmpdir}"
-}
-get_binaries() {
-	case "$PLATFORM" in
-	darwin/386) BINARIES="goreleaser" ;;
-	darwin/amd64) BINARIES="goreleaser" ;;
-	darwin/arm64) BINARIES="goreleaser" ;;
-	darwin/armv6) BINARIES="goreleaser" ;;
-	linux/386) BINARIES="goreleaser" ;;
-	linux/amd64) BINARIES="goreleaser" ;;
-	linux/arm64) BINARIES="goreleaser" ;;
-	linux/armv6) BINARIES="goreleaser" ;;
-	windows/386) BINARIES="goreleaser" ;;
-	windows/amd64) BINARIES="goreleaser" ;;
-	windows/arm64) BINARIES="goreleaser" ;;
-	windows/armv6) BINARIES="goreleaser" ;;
-	*)
-		log_crit "platform $PLATFORM is not supported.  Make sure this script is up-to-date and file request at https://github.com/${PREFIX}/issues/new"
-		exit 1
-		;;
-	esac
-}
-tag_to_version() {
-	if [ -z "${TAG}" ]; then
-		log_info "checking GitHub for latest tag"
-	else
-		log_info "checking GitHub for tag '${TAG}'"
-	fi
-	REALTAG=$(github_release "$OWNER/$REPO" "${TAG}") && true
-	if test -z "$REALTAG"; then
-		log_crit "unable to find '${TAG}' - use 'latest' or see https://github.com/${PREFIX}/releases for details"
-		exit 1
-	fi
-	# if version starts with 'v', remove it
-	TAG="$REALTAG"
-	VERSION=${TAG#v}
-}
-adjust_format() {
-	# change format (tar.gz or zip) based on OS
-	case ${OS} in
-	windows) FORMAT=zip ;;
-	esac
-	true
-}
-adjust_os() {
-	# adjust archive name based on OS
-	case ${OS} in
-	386) OS=i386 ;;
-	amd64) OS=x86_64 ;;
-	darwin) OS=Darwin ;;
-	linux) OS=Linux ;;
-	windows) OS=Windows ;;
-	esac
-	true
-}
-adjust_arch() {
-	# adjust archive name based on ARCH
-	case ${ARCH} in
-	386) ARCH=i386 ;;
-	amd64) ARCH=x86_64 ;;
-	darwin) ARCH=Darwin ;;
-	linux) ARCH=Linux ;;
-	windows) ARCH=Windows ;;
-	esac
-	true
-}
-
-cat /dev/null <<EOF
-------------------------------------------------------------------------
-https://github.com/client9/shlib - portable posix shell functions
-Public domain - http://unlicense.org
-https://github.com/client9/shlib/blob/master/LICENSE.md
-but credit (and pull requests) appreciated.
-------------------------------------------------------------------------
-EOF
-is_command() {
-	command -v "$1" >/dev/null
-}
-echoerr() {
-	echo "$@" 1>&2
-}
-log_prefix() {
-	echo "$0"
-}
-_logp=6
-log_set_priority() {
-	_logp="$1"
-}
-log_priority() {
-	if test -z "$1"; then
-		echo "$_logp"
-		return
-	fi
-	[ "$1" -le "$_logp" ]
-}
-log_tag() {
-	case $1 in
-	0) echo "emerg" ;;
-	1) echo "alert" ;;
-	2) echo "crit" ;;
-	3) echo "err" ;;
-	4) echo "warning" ;;
-	5) echo "notice" ;;
-	6) echo "info" ;;
-	7) echo "debug" ;;
-	*) echo "$1" ;;
-	esac
-}
-log_debug() {
-	log_priority 7 || return 0
-	echoerr "$(log_prefix)" "$(log_tag 7)" "$@"
-}
-log_info() {
-	log_priority 6 || return 0
-	echoerr "$(log_prefix)" "$(log_tag 6)" "$@"
-}
-log_err() {
-	log_priority 3 || return 0
-	echoerr "$(log_prefix)" "$(log_tag 3)" "$@"
-}
-log_crit() {
-	log_priority 2 || return 0
-	echoerr "$(log_prefix)" "$(log_tag 2)" "$@"
-}
-uname_os() {
-	os=$(uname -s | tr '[:upper:]' '[:lower:]')
-	case "$os" in
-	cygwin_nt*) os="windows" ;;
-	mingw*) os="windows" ;;
-	msys_nt*) os="windows" ;;
-	esac
-	echo "$os"
-}
-uname_arch() {
-	arch=$(uname -m)
-	case $arch in
-	x86_64) arch="amd64" ;;
-	x86) arch="386" ;;
-	i686) arch="386" ;;
-	i386) arch="386" ;;
-	aarch64) arch="arm64" ;;
-	armv5*) arch="armv5" ;;
-	armv6*) arch="armv6" ;;
-	armv7*) arch="armv7" ;;
-	esac
-	echo ${arch}
-}
-uname_os_check() {
-	os=$(uname_os)
-	case "$os" in
-	darwin) return 0 ;;
-	dragonfly) return 0 ;;
-	freebsd) return 0 ;;
-	linux) return 0 ;;
-	android) return 0 ;;
-	nacl) return 0 ;;
-	netbsd) return 0 ;;
-	openbsd) return 0 ;;
-	plan9) return 0 ;;
-	solaris) return 0 ;;
-	windows) return 0 ;;
-	esac
-	log_crit "uname_os_check '$(uname -s)' got converted to '$os' which is not a GOOS value. Please file bug at https://github.com/client9/shlib"
-	return 1
-}
-uname_arch_check() {
-	arch=$(uname_arch)
-	case "$arch" in
-	386) return 0 ;;
-	amd64) return 0 ;;
-	arm64) return 0 ;;
-	armv5) return 0 ;;
-	armv6) return 0 ;;
-	armv7) return 0 ;;
-	ppc64) return 0 ;;
-	ppc64le) return 0 ;;
-	mips) return 0 ;;
-	mipsle) return 0 ;;
-	mips64) return 0 ;;
-	mips64le) return 0 ;;
-	s390x) return 0 ;;
-	amd64p32) return 0 ;;
-	esac
-	log_crit "uname_arch_check '$(uname -m)' got converted to '$arch' which is not a GOARCH value.  Please file bug report at https://github.com/client9/shlib"
-	return 1
-}
-untar() {
-	tarball=$1
-	case "${tarball}" in
-	*.tar.gz | *.tgz) tar --no-same-owner -xzf "${tarball}" ;;
-	*.tar) tar --no-same-owner -xf "${tarball}" ;;
-	*.zip) unzip "${tarball}" ;;
-	*)
-		log_err "untar unknown archive format for ${tarball}"
-		return 1
-		;;
-	esac
-}
-http_download_curl() {
-	local_file=$1
-	source_url=$2
-	header=$3
-	if [ -z "$header" ]; then
-		code=$(curl -w '%{http_code}' -sL -o "$local_file" "$source_url")
-	else
-		code=$(curl -w '%{http_code}' -sL -H "$header" -o "$local_file" "$source_url")
-	fi
-	if [ "$code" != "200" ]; then
-		log_debug "http_download_curl received HTTP status $code"
-		return 1
-	fi
-	return 0
-}
-http_download_wget() {
-	local_file=$1
-	source_url=$2
-	header=$3
-	if [ -z "$header" ]; then
-		wget -q -O "$local_file" "$source_url"
-	else
-		wget -q --header "$header" -O "$local_file" "$source_url"
-	fi
-}
-http_download() {
-	log_debug "http_download $2"
-	if is_command curl; then
-		http_download_curl "$@"
-		return
-	elif is_command wget; then
-		http_download_wget "$@"
-		return
-	fi
-	log_crit "http_download unable to find wget or curl"
-	return 1
-}
-http_copy() {
-	tmp=$(mktemp)
-	http_download "${tmp}" "$1" "$2" || return 1
-	body=$(cat "$tmp")
-	rm -f "${tmp}"
-	echo "$body"
-}
-github_release() {
-	owner_repo=$1
-	version=$2
-	test -z "$version" && version="latest"
-	giturl="https://github.com/${owner_repo}/releases/${version}"
-	json=$(http_copy "$giturl" "Accept:application/json")
-	test -z "$json" && return 1
-	version=$(echo "$json" | tr -s '\n' ' ' | sed 's/.*"tag_name":"//' | sed 's/".*//')
-	test -z "$version" && return 1
-	echo "$version"
-}
-hash_sha256() {
-	TARGET=${1:-/dev/stdin}
-	if is_command gsha256sum; then
-		hash=$(gsha256sum "$TARGET") || return 1
-		echo "$hash" | cut -d ' ' -f 1
-	elif is_command sha256sum; then
-		hash=$(sha256sum "$TARGET") || return 1
-		echo "$hash" | cut -d ' ' -f 1
-	elif is_command shasum; then
-		hash=$(shasum -a 256 "$TARGET" 2>/dev/null) || return 1
-		echo "$hash" | cut -d ' ' -f 1
-	elif is_command openssl; then
-		hash=$(openssl -dst openssl dgst -sha256 "$TARGET") || return 1
-		echo "$hash" | cut -d ' ' -f a
-	else
-		log_crit "hash_sha256 unable to find command to compute sha-256 hash"
-		return 1
-	fi
-}
-hash_sha256_verify() {
-	TARGET=$1
-	checksums=$2
-	if [ -z "$checksums" ]; then
-		log_err "hash_sha256_verify checksum file not specified in arg2"
-		return 1
-	fi
-	BASENAME=${TARGET##*/}
-	want=$(grep "${BASENAME}$" "${checksums}" 2>/dev/null | tr '\t' ' ' | cut -d ' ' -f 1)
-	if [ -z "$want" ]; then
-		log_err "hash_sha256_verify unable to find checksum for '${TARGET}' in '${checksums}'"
-		return 1
-	fi
-	got=$(hash_sha256 "$TARGET")
-	if [ "$want" != "$got" ]; then
-		log_err "hash_sha256_verify checksum for '$TARGET' did not verify ${want} vs $got"
-		return 1
-	fi
-}
-cat /dev/null <<EOF
-------------------------------------------------------------------------
-End of functions from https://github.com/client9/shlib
-------------------------------------------------------------------------
-EOF
-
-PROJECT_NAME="goreleaser"
-OWNER=goreleaser
-REPO="goreleaser"
-BINARY=goreleaser
-FORMAT=tar.gz
-OS=$(uname_os)
-ARCH=$(uname_arch)
-PREFIX="$OWNER/$REPO"
-
-# use in logging routines
-log_prefix() {
-	echo "$PREFIX"
-}
-PLATFORM="${OS}/${ARCH}"
-GITHUB_DOWNLOAD=https://github.com/${OWNER}/${REPO}/releases/download
-
-uname_os_check "$OS"
-uname_arch_check "$ARCH"
-
-parse_args "$@"
-
-get_binaries
-
-tag_to_version
-
-adjust_format
-
-adjust_os
-
-adjust_arch
-
-log_info "found version: ${VERSION} for ${TAG}/${OS}/${ARCH}"
-
-NAME=${PROJECT_NAME}_${OS}_${ARCH}
-TARBALL=${NAME}.${FORMAT}
-TARBALL_URL=${GITHUB_DOWNLOAD}/${TAG}/${TARBALL}
-CHECKSUM=checksums.txt
-CHECKSUM_URL=${GITHUB_DOWNLOAD}/${TAG}/${CHECKSUM}
-
-execute
-log_err "this script is deprecated, please do not use it anymore. check https://github.com/goreleaser/godownloader/issues/207"

.github/scripts/labeler.py

@@ -0,0 +1,232 @@
+from __future__ import annotations
+
+import sys
+import glob
+import subprocess
+import os
+import re
+
+DRY_RUN = False
+
+JSON_SCHEMA_LABEL = "json-schema"
+
+# note: we can't use "breaking-change" as the label since that might be applied manually by a user. This is a
+# distinct label that we can use to indicate that the label was applied (or removed) by automation.
+BREAKING_CHANGE_LABEL = "detected-breaking-change"
+
+
+def main(changed_files: str | None = None, merge_base_schema_files: str | None = None):
+    global DRY_RUN
+
+    pr_number = os.environ.get("GITHUB_PR_NUMBER")
+    comment_file_path = os.environ.get("CI_COMMENT_FILE")
+
+    if not comment_file_path:
+        print("CI_COMMENT_FILE not set")
+        sys.exit(1)
+
+    if not pr_number:
+        DRY_RUN = True
+
+    if changed_files:
+        DRY_RUN = True
+
+        # read lines from file... this is useful for local testing
+        with open(changed_files) as f:
+            pr_changed_files = f.read().splitlines()
+
+        with open(merge_base_schema_files) as f:
+            og_json_schema_files = sort_json_schema_files(f.read().splitlines())
+
+    else:
+        if not is_ci():
+            print("Not in CI")
+            sys.exit(1)
+
+        if not pr_number:
+            print("Not a PR")
+            sys.exit(1)
+
+        pr_changed_files = get_pr_changed_files(pr_number)
+        # since we are running this in the context of the pull_request_target, the checkout is the merge base..
+        # that is the main branch of the original repo, NOT the branch in the forked repo (or branch in the target 
+        # repo for non-forked PRs). This means we just need to list the current checkedout files to get a sense of
+        # the changes before a merge.
+        og_json_schema_files = list_json_schema_files()
+
+    pr_json_schema_files = filter_to_schema_files(pr_changed_files)
+
+    # print("schema files in pr:   ", summarize_schema_files(pr_json_schema_files))
+    # print("og schema files:      ", summarize_schema_files(og_json_schema_files))
+
+    if not og_json_schema_files:
+        print("No schema files found in merge base")
+        sys.exit(1)
+
+    # pr_json_schema_files = set of PR files are added, removed, and changed files
+    new_schema_files = set(pr_json_schema_files) - set(og_json_schema_files)
+    removed_or_modified_schema_files = set(pr_json_schema_files) - set(new_schema_files)
+
+    print("new schemas:                ", summarize_schema_files(new_schema_files))
+    print("removed or modified schemas:", summarize_schema_files(removed_or_modified_schema_files))
+
+    # if there is a new or modified schema, we should add the "json-schema" label to the PR...
+    if new_schema_files or removed_or_modified_schema_files:
+        print("\nAdding json-schema label...")
+        add_label(pr_number, JSON_SCHEMA_LABEL)
+
+    else:
+        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...
+    if is_breaking_change(new_schema_files, og_json_schema_files[-1]):
+        print("\nBreaking change detected...")
+        add_label(pr_number, BREAKING_CHANGE_LABEL)
+    else:
+        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...
+    if removed_or_modified_schema_files:
+        print("\nRemoved or modified schema detected...")
+        schemas = sort_json_schema_files(list(removed_or_modified_schema_files))
+        schemas_str = "\n".join([f" - {schema}" for schema in schemas])
+        add_comment(comment_file_path, f"Detected modification or removal of existing json schemas:\n{schemas_str}", warning=True)
+
+
+def add_comment(comment_file_path: str, comment: str, warning: bool = False, important: bool = False):
+    if warning or important:
+        comment_lines = comment.splitlines()
+        comment = "\n".join([f"> {line}" for line in comment_lines])
+
+    if warning:
+        comment = f"> [!WARNING]\n{comment}"    
+    elif important:
+        comment = f"> [!IMPORTANT]\n{comment}"
+
+    # create any parent directories if they don't exist
+    os.makedirs(os.path.dirname(comment_file_path), exist_ok=True)
+
+    with open(comment_file_path, "w") as f:
+        f.write(comment)
+
+    print(f"Comment file contents: {comment_file_path}")
+    print(comment)
+
+
+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(str(result.stderr))
+        sys.exit(1)
+
+
+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(str(result.stderr))
+        sys.exit(1)
+
+
+def major_version(semver: str) -> int:
+    return int(semver.split(".")[0])
+
+
+def is_breaking_change(new_schema_files: set[str], latest_schema_file: str) -> bool:
+    latest_major_version = major_version(get_semver(latest_schema_file))
+    for file in new_schema_files:
+        change_major_version = major_version(get_semver(file))
+        if change_major_version > latest_major_version:
+            return True
+    return False
+
+
+def summarize_schema_files(files: list[str]) -> list[str]:
+    return [get_semver(file) for file in files]
+
+
+def is_ci() -> bool:
+    return "CI" in os.environ
+
+
+def get_pr_changed_files(pr_number: str) -> list[str]:
+    result = run(f"gh pr view {pr_number} --json files --jq '.files.[].path'", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+    if result.returncode != 0:
+        print("Unable to get list of changed files in PR")
+        print(str(result.stderr))
+        sys.exit(1)
+    
+    list_of_files = result.stdout.splitlines()
+    return list_of_files
+
+
+def filter_to_schema_files(list_of_files: list[str]) -> list[str]:
+    # get files matching "schema/json/schema-*.json"
+    files = []
+    for file in list_of_files:
+        if re.match(r"^schema/json/schema-\d+\.\d+\.\d+\.json$", file):
+            files.append(file)
+    return sort_json_schema_files(files)
+
+
+def list_json_schema_files() -> list[str]:
+    # list files in "schema/json" directory matching the pattern of "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:
+    if DRY_RUN:
+        print(f"[DRY RUN] {command}")
+        return subprocess.CompletedProcess(args=[command], returncode=0)
+    print(f"[RUN] {command}")
+    return subprocess.run(command, **kwargs)
+
+
+def get_semver(input_file: str) -> str:
+    return input_file.split("-")[1].split(".json")[0]
+
+
+def sort_json_schema_files(files: list[str]) -> list[str]:
+    # sort files by schema version, where the input looks like "schema/json/schema-1.12.1.json"
+    # we should sort by the semantic version embedded within the basename, not the string
+    # 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('.') if "." in s])
+
+    return [f"schema/json/schema-{version}.json" for version in versions]
+
+
+# allow for test files that have line-by-line list of files:
+
+# .binny.yaml
+# .github/actions/bootstrap/action.yaml
+# .github/scripts/goreleaser-install.sh
+# .github/workflows/release.yaml
+# .github/workflows/update-bootstrap-tools.yml
+# .github/workflows/update-cpe-dictionary-index.yml
+# .github/workflows/update-stereoscope-release.yml
+# .github/workflows/validations.yaml
+# .gitignore
+# .goreleaser.yaml
+# Makefile
+# Taskfile.yaml
+# schema/cyclonedx/Makefile
+
+if __name__ == "__main__":
+    # these are variables for a single file name that contains a list of files (line separated)
+    changed_files = None
+    merge_base_schema_files = None
+
+    if len(sys.argv) > 2:
+        changed_files = sys.argv[1]
+        merge_base_schema_files = sys.argv[2]
+
+    main(changed_files, merge_base_schema_files)
+

.github/scripts/labeler_test.py

@@ -0,0 +1,70 @@
+import unittest
+from unittest.mock import patch
+import subprocess
+
+import labeler
+
+class Labeler(unittest.TestCase):
+
+    def test_major_version(self):
+        self.assertEqual(labeler.major_version("1.2.3"), 1)
+        self.assertEqual(labeler.major_version("2.0.0"), 2)
+
+    def test_is_breaking_change(self):
+        new_schema_files = ["schema/json/schema-2.0.0.json"]
+        latest_schema_file = "schema/json/schema-1.2.0.json"
+        self.assertTrue(labeler.is_breaking_change(new_schema_files, latest_schema_file))
+
+        new_schema_files = ["schema/json/schema-1.3.0.json"]
+        latest_schema_file = "schema/json/schema-1.2.0.json"
+        self.assertFalse(labeler.is_breaking_change(new_schema_files, latest_schema_file))
+
+    def test_summarize_schema_files(self):
+        files = ["schema/json/schema-1.0.0.json", "schema/json/schema-2.0.0.json"]
+        expected = ["1.0.0", "2.0.0"]
+        self.assertEqual(labeler.summarize_schema_files(files), expected)
+
+    def test_is_ci(self):
+        # Mock os.environ to simulate CI environment
+        with patch.dict("os.environ", {"CI": "true"}):
+            self.assertTrue(labeler.is_ci())
+
+    def test_get_pr_changed_files(self):
+        expected_command = "gh pr view 123 --json files --jq '.files.[].path'"
+        expected_output = "file1.json\nfile2.json\n"
+
+        subprocess.CompletedProcess.returncode = 0
+        subprocess.CompletedProcess.stdout = expected_output
+        with patch("labeler.run", return_value=subprocess.CompletedProcess) as mock_run:
+            result = labeler.get_pr_changed_files("123")
+            mock_run.assert_called_with(expected_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+            self.assertEqual(result, ["file1.json", "file2.json"])
+
+    def test_filter_to_schema_files(self):
+        input_files = ["schema/json/schema-1.0.0.json", "not_schema.txt", "schema/json/schema-2.0.0.json"]
+        expected_files = ["schema/json/schema-1.0.0.json", "schema/json/schema-2.0.0.json"]
+        self.assertEqual(labeler.filter_to_schema_files(input_files), expected_files)
+
+        # we should be strict about what files are allowed to be processed
+        input_files = ["schema/json/schema-1.0.0extracontent.json", "schema/json/schema-1.0.0.md", "schema/json/schema-1.0.0.json.extracontent"]
+        expected_files = []
+        self.assertEqual(labeler.filter_to_schema_files(input_files), expected_files)
+
+    def test_get_semver(self):
+        input_file = "schema/json/schema-1.0.0.json"
+        expected_semver = "1.0.0"
+        self.assertEqual(labeler.get_semver(input_file), expected_semver)
+
+    def test_sort_json_schema_files(self):
+        files = ["schema/json/schema-1.12.1.json", "schema/json/schema-1.2.1.json"]
+        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/workflows/benchmark-testing.yaml

@@ -17,13 +17,13 @@ jobs:
     # the job by event.
     steps:
       - name: Checkout code
-        uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 # v4.1.0
+        uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 # v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
       - name: Restore base benchmark result
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         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@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4.3.1
         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@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
     - name: Install Go
-      uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
       with:
         go-version-file: go.mod
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@fdcae64e1484d349b3366718cdfef3d404390e85 #v2.22.1
+      uses: github/codeql-action/init@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6
       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@fdcae64e1484d349b3366718cdfef3d404390e85 #v2.22.1
+      uses: github/codeql-action/autobuild@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6
 
     # 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@fdcae64e1484d349b3366718cdfef3d404390e85 #v2.22.1
+      uses: github/codeql-action/analyze@8a470fddafa5cbb6266ee11b37ef4d8aae19c571 #v3.24.6

.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

@@ -0,0 +1,54 @@
+name: "Detect schema changes"
+
+on:
+  # IMPORTANT! This workflow is triggered by the `pull_request_target` event
+  # which means that forked PRs will run with access secrets from the repo
+  # it's forked from (the "target" repo).
+  #
+  # For this reason we only NEVER checkout the code from the pull request
+  # (e.g. "ref: ${{ github.event.pull_request.head.sha }}") to prevent
+  # accidentally running potentially untrusted code.
+  #
+  # By default the checkout will be:
+  #   - GITHUB_SHA: Last commit on the PR base branch
+  #   - GITHUB_REF: PR base branch
+  #
+  # ...unlike a typical PR where:
+  #   - GITHUB_SHA: Last merge commit on the GITHUB_REF branch
+  #   - GITHUB_REF: PR merge branch refs/pull/:prNumber/merge
+  pull_request_target:
+
+env:
+  # note: this is used within hashFiles() so must be within the GITHUB_WORKSPACE path (or will silently fail)
+  CI_COMMENT_FILE: .tmp/labeler-comment.txt
+  # needs to be any string to uniquely identify the comment on a PR across multiple runs
+  COMMENT_HEADER: "label-commentary"
+
+jobs:
+  label:
+    name: "Label changes"
+    runs-on: ubuntu-22.04
+    steps:
+
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
+
+      - run: python .github/scripts/labeler.py
+        env:
+          # note: this token has write access to the repo
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_PR_NUMBER: ${{ github.event.number }}
+
+      - name: Delete existing comment
+        if: ${{ hashFiles( env.CI_COMMENT_FILE ) == '' }}
+        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 #v2.9.0
+        with:
+          header: ${{ env.COMMENT_HEADER }}
+          hide: true
+          hide_classify: "OUTDATED"
+
+      - name: Add comment
+        if: ${{ hashFiles( env.CI_COMMENT_FILE ) != '' }}
+        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

@@ -0,0 +1,48 @@
+name: "Release Homebrew"
+
+on:
+  workflow_dispatch:
+  release:
+    types:
+      - released
+
+jobs:
+  homebrew:
+    runs-on: ubuntu-20.04
+    steps:
+
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
+        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@baf2b60c51fc1f8453c884b0c61052668a71bd1d # v3.11.0
+        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@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
+        if: ${{ failure() }}
+        with:
+          status: ${{ job.status }}
+          fields: repo,workflow,action,eventName
+          text: "Post-release homebrew publish workflow has failed: https://github.com/anchore/syft/actions/workflows/release-homebrew.yaml"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}

.github/workflows/release.yaml

@@ -15,7 +15,7 @@ jobs:
     environment: release
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Check if tag already exists
         # note: this will fail if the tag already exists
@@ -94,16 +94,15 @@ jobs:
     permissions:
       contents: write
       packages: write
+      # required for goreleaser signs section with cosign
+      id-token: write
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
         with:
           fetch-depth: 0
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
-        with:
-          # use the same cache we used for building snapshots
-          build-cache-key-prefix: "snapshot"
 
       - name: Login to Docker Hub
         uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d  #v3.0.0
@@ -144,12 +143,12 @@ jobs:
           AWS_ACCESS_KEY_ID: ${{ secrets.TOOLBOX_AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.TOOLBOX_AWS_SECRET_ACCESS_KEY }}
 
-      - uses: anchore/sbom-action@78fc58e266e87a38d4194b2137a3d4e9bcaf7ca1 #v0.14.3
+      - uses: anchore/sbom-action@9fece9e20048ca9590af301449208b2b8861333b #v0.15.9
         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 }}

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

@@ -1,14 +1,10 @@
-name: PR for latest versions of bootstrap tools
+name: PR for latest versions of tools
 on:
   schedule:
     - cron: "0 8 * * *" # 3 AM EST
 
   workflow_dispatch:
 
-env:
-  GO_VERSION: "1.21.x"
-  GO_STABLE_VERSION: true
-
 permissions:
   contents: read
 
@@ -17,46 +13,36 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
-      - uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
         with:
-          go-version: ${{ env.GO_VERSION }}
-          stable: ${{ env.GO_STABLE_VERSION }}
+          bootstrap-apt-packages: ""
+          compute-fingerprints: "false"
+          go-dependencies: false
 
-      - run: |
-          GOLANGCILINT_LATEST_VERSION=$(go list -m -json github.com/golangci/golangci-lint@latest 2>/dev/null | jq -r '.Version')
-          BOUNCER_LATEST_VERSION=$(go list -m -json github.com/wagoodman/go-bouncer@latest 2>/dev/null | jq -r '.Version')
-          CHRONICLE_LATEST_VERSION=$(go list -m -json github.com/anchore/chronicle@latest 2>/dev/null | jq -r '.Version')
-          GORELEASER_LATEST_VERSION=$(go list -m -json github.com/goreleaser/goreleaser@latest 2>/dev/null | jq -r '.Version')
-          GOSIMPORTS_LATEST_VERSION=$(go list -m -json github.com/rinchsan/gosimports@latest 2>/dev/null | jq -r '.Version')
-          YAJSV_LATEST_VERSION=$(go list -m -json github.com/neilpa/yajsv@latest 2>/dev/null | jq -r '.Version')
-          COSIGN_LATEST_VERSION=$(go list -m -json github.com/sigstore/cosign/v2@latest 2>/dev/null | jq -r '.Version')
-          QUILL_LATEST_VERSION=$(go list -m -json github.com/anchore/quill@latest 2>/dev/null | jq -r '.Version')
-          GLOW_LATEST_VERSION=$(go list -m -json github.com/charmbracelet/glow@latest 2>/dev/null | jq -r '.Version')
-          
-          # update version variables in the Makefile
-          sed -r -i -e 's/^(GOLANGCILINT_VERSION := ).*/\1'${GOLANGCILINT_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(BOUNCER_VERSION := ).*/\1'${BOUNCER_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(CHRONICLE_VERSION := ).*/\1'${CHRONICLE_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(GORELEASER_VERSION := ).*/\1'${GORELEASER_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(GOSIMPORTS_VERSION := ).*/\1'${GOSIMPORTS_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(YAJSV_VERSION := ).*/\1'${YAJSV_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(COSIGN_VERSION := ).*/\1'${COSIGN_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(QUILL_VERSION := ).*/\1'${QUILL_LATEST_VERSION}'/' Makefile
-          sed -r -i -e 's/^(GLOW_VERSION := ).*/\1'${GLOW_LATEST_VERSION}'/' Makefile
-          
-          # export the versions for use with create-pull-request
-          echo "GOLANGCILINT=$GOLANGCILINT_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "BOUNCER=$BOUNCER_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "CHRONICLE=$CHRONICLE_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "GORELEASER=$GORELEASER_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "GOSIMPORTS=$GOSIMPORTS_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "YAJSV=$YAJSV_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "COSIGN=$COSIGN_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "QUILL=$QUILL_LATEST_VERSION" >> $GITHUB_OUTPUT
-          echo "GLOW=GLOW_LATEST_VERSION" >> $GITHUB_OUTPUT
+      - name: "Update tool versions"
         id: latest-versions
+        run: |
+          make update-tools
+          make list-tools
+          
+          export NO_COLOR=1
+          delimiter="$(openssl rand -hex 8)"
+          
+          {
+            echo "status<<${delimiter}"
+            make list-tool-updates
+            echo "${delimiter}"
+          } >> $GITHUB_OUTPUT
+          
+          {
+            echo "### Tool version status"
+            echo "\`\`\`"
+            make list-tool-updates
+            echo "\`\`\`"
+          } >> $GITHUB_STEP_SUMMARY
 
       - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
         id: generate-token
@@ -64,23 +50,17 @@ 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@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
         with:
           signoff: true
           delete-branch: true
-          branch: auto/latest-bootstrap-tools
+          branch: auto/latest-tools
           labels: dependencies
-          commit-message: 'chore(deps): update bootstrap tools to latest versions'
-          title: 'chore(deps): update bootstrap tools to latest versions'
+          commit-message: 'chore(deps): update tools to latest versions'
+          title: 'chore(deps): update tools to latest versions'
           body: |
-            - [golangci-lint ${{ steps.latest-versions.outputs.GOLANGCILINT }}](https://github.com/golangci/golangci-lint/releases/tag/${{ steps.latest-versions.outputs.GOLANGCILINT }})
-            - [bouncer ${{ steps.latest-versions.outputs.BOUNCER }}](https://github.com/wagoodman/go-bouncer/releases/tag/${{ steps.latest-versions.outputs.BOUNCER }})
-            - [chronicle ${{ steps.latest-versions.outputs.CHRONICLE }}](https://github.com/anchore/chronicle/releases/tag/${{ steps.latest-versions.outputs.CHRONICLE }})
-            - [goreleaser ${{ steps.latest-versions.outputs.GORELEASER }}](https://github.com/goreleaser/goreleaser/releases/tag/${{ steps.latest-versions.outputs.GORELEASER }})
-            - [gosimports ${{ steps.latest-versions.outputs.GOSIMPORTS }}](https://github.com/rinchsan/gosimports/releases/tag/${{ steps.latest-versions.outputs.GOSIMPORTS }})
-            - [yajsv ${{ steps.latest-versions.outputs.YAJSV }}](https://github.com/neilpa/yajsv/releases/tag/${{ steps.latest-versions.outputs.YAJSV }})
-            - [cosign ${{ steps.latest-versions.outputs.COSIGN }}](https://github.com/sigstore/cosign/releases/tag/${{ steps.latest-versions.outputs.COSIGN }})  
-            - [quill ${{ steps.latest-versions.outputs.QUILL }}](https://github.com/anchore/quill/releases/tag/${{ steps.latest-versions.outputs.QUILL }})  
-            - [glow ${{ steps.latest-versions.outputs.GLOW }}](https://github.com/charmbracelet/glow/releases/tag/${{ steps.latest-versions.outputs.GLOW }})  
-            This is an auto-generated pull request to update all of the bootstrap tools to the latest versions.
+            ```
+            ${{ steps.latest-versions.outputs.status }}
+            ```
+            This is an auto-generated pull request to update all of the tools to the latest versions.
           token: ${{ steps.generate-token.outputs.token }}

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

@@ -9,20 +9,20 @@ permissions:
   contents: read
 
 env:
-  GO_VERSION: "1.21.x"
-  GO_STABLE_VERSION: true
+  SLACK_NOTIFICATIONS: true
 
 jobs:
   upgrade-cpe-dictionary-index:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
-      - uses: actions/setup-go@3df4ab11eba7bda6032a0b82a6bb43b11571feac #v4.0.0
-        with:
-          go-version: ${{ env.GO_VERSION }}
-          stable: ${{ env.GO_STABLE_VERSION }}
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
 
       - run: |
           make generate-cpe-dictionary-index
@@ -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@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
         with:
           signoff: true
           delete-branch: true
@@ -44,3 +44,12 @@ jobs:
           body: |
             Update CPE dictionary index based on the latest available CPE dictionary
           token: ${{ steps.generate-token.outputs.token }}
+
+      - uses: 8398a7/action-slack@28ba43ae48961b90635b50953d216767a6bea486 #v3.16.2
+        with:
+          status: ${{ job.status }}
+          fields: workflow,eventName,job
+          text: Syft CPE dictionary index update failed
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
+        if: ${{ failure() && env.SLACK_NOTIFICATIONS == 'true' }}

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

@@ -17,13 +17,16 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
-      - uses: actions/setup-go@93397bea11091df50f3d7e59dc26a7711a8bcfbe #v4.1.0
+      - uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 #v5.0.0
         with:
           go-version: ${{ env.GO_VERSION }}
           stable: ${{ env.GO_STABLE_VERSION }}
 
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
       - run: |
           LATEST_VERSION=$(git ls-remote https://github.com/anchore/stereoscope main | head -n1 | awk '{print $1;}')
 
@@ -41,7 +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@70a41aba780001da0a30141984ae2a0c95d8704e #v6.0.2
         with:
           signoff: true
           delete-branch: true

.github/workflows/validations.yaml

@@ -11,12 +11,13 @@ permissions:
     contents: read
 
 jobs:
+
   Static-Analysis:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Static analysis"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -30,37 +31,49 @@ jobs:
     name: "Unit tests"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
+      - name: Restore file executable test-fixture cache
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
+        with:
+          path: syft/file/cataloger/executable/test-fixtures/elf/bin
+          key: ${{ runner.os }}-unit-file-executable-elf-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint' ) }}
+
+      - name: Restore file executable shared-info test-fixture cache
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
+        with:
+          path: syft/file/cataloger/executable/test-fixtures/shared-info/bin
+          key: ${{ runner.os }}-unit-file-executable-shared-info-cache-${{ hashFiles( 'syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint' ) }}
+
       - name: Restore Java test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         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
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: syft/pkg/cataloger/rpm/test-fixtures/rpms
-          key: ${{ runner.os }}-unit-rpm-cache-${{ hashFiles( 'syft/pkg/cataloger/rpm/test-fixtures/rpms.fingerprint' ) }}
+          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
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         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
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/dynamic
+          path: syft/pkg/cataloger/binary/test-fixtures/classifiers/bin
           key: ${{ runner.os }}-unit-binary-cataloger-cache-${{ hashFiles( 'syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint' ) }}
 
       - name: Restore Kernel test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
           path: syft/pkg/cataloger/kernel/test-fixtures/cache
           key: ${{ runner.os }}-unit-kernel-cache-${{ hashFiles( 'syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint' ) }}
@@ -74,7 +87,7 @@ jobs:
     name: "Integration tests"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
@@ -83,10 +96,10 @@ jobs:
         run: make validate-cyclonedx-schema
 
       - name: Restore integration test cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: ${{ github.workspace }}/test/integration/test-fixtures/cache
-          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('test/integration/test-fixtures/cache.fingerprint') }}
+          path: ${{ github.workspace }}/cmd/syft/internal/test/integration/test-fixtures/cache
+          key: ${{ runner.os }}-integration-test-cache-${{ hashFiles('/cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint') }}
 
       - name: Run integration tests
         run: make integration
@@ -96,17 +109,11 @@ jobs:
     name: "Build snapshot artifacts"
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
         with:
-          # why have another build cache key? We don't want unit/integration/etc test build caches to replace
-          # the snapshot build cache, which includes builds for all OSs and architectures. As long as this key is
-          # unique from the build-cache-key-prefix in other CI jobs, we should be fine.
-          #
-          # note: ideally this value should match what is used in release (just to help with build times).
-          build-cache-key-prefix: "snapshot"
           bootstrap-apt-packages: ""
 
       - name: Build snapshot artifacts
@@ -115,9 +122,14 @@ 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@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: snapshot
+          # we need to preserve the snapshot data itself as well as the task data that confirms if the
+          # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
+          # even though it already exists.
+          path: |
+            snapshot
+            .task
           key: snapshot-build-${{ github.run_id }}
 
 
@@ -127,20 +139,32 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
 
       - name: Download snapshot build
-        uses: actions/cache/restore@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        id: snapshot-cache
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: snapshot
+          path: |
+            snapshot
+            .task
+          fail-on-cache-miss: true
           key: snapshot-build-${{ github.run_id }}
 
+      # workaround for https://github.com/actions/cache/issues/1265
+      - name: (cache-miss) Snapshot build missing
+        if: steps.snapshot-cache.outputs.cache-hit != 'true'
+        run: echo "unable to download snapshots from previous job" && false
+
       - 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
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
           path: ${{ github.workspace }}/test/install/cache
           key: ${{ runner.os }}-install-test-image-cache-${{ hashFiles('test/install/cache.fingerprint') }}
@@ -163,17 +187,34 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: macos-latest
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+        with:
+          bootstrap-apt-packages: ""
+          compute-fingerprints: "false"
+          go-dependencies: false
+          go-version: ""
 
       - name: Download snapshot build
-        uses: actions/cache/restore@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        id: snapshot-cache
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: snapshot
+          path: |
+            snapshot
+            .task
+          fail-on-cache-miss: true
           key: snapshot-build-${{ github.run_id }}
 
+      # workaround for https://github.com/actions/cache/issues/1265
+      - name: (cache-miss) Snapshot build missing
+        if: steps.snapshot-cache.outputs.cache-hit != 'true'
+        run: echo "unable to download snapshots from previous job" && false
+
       - name: Restore docker image cache for compare testing
         id: mac-compare-testing-cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
           path: image.tar
           key: ${{ runner.os }}-${{ hashFiles('test/compare/mac.sh') }}
@@ -191,22 +232,31 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@8ade135a41bc03ea155e62e844d188df1ea18608 #v4.1.0
+      - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 #v4.1.2
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
       - name: Restore CLI test-fixture cache
-        uses: actions/cache@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        uses: actions/cache@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
           path: ${{ github.workspace }}/test/cli/test-fixtures/cache
           key: ${{ runner.os }}-cli-test-cache-${{ hashFiles('test/cli/test-fixtures/cache.fingerprint') }}
 
       - name: Download snapshot build
-        uses: actions/cache/restore@704facf57e6136b1bc63b828d79edcd491f0ee84 #v3.3.2
+        id: snapshot-cache
+        uses: actions/cache/restore@ab5e6d0c87105b4c9c2047343972218f562e4319 #v4.0.1
         with:
-          path: snapshot
+          path: |
+            snapshot
+            .task
+          fail-on-cache-miss: true
           key: snapshot-build-${{ github.run_id }}
 
+      # workaround for https://github.com/actions/cache/issues/1265
+      - name: (cache-miss) Snapshot build missing
+        if: steps.snapshot-cache.outputs.cache-hit != 'true'
+        run: echo "unable to download snapshots from previous job" && false
+
       - name: Run CLI Tests (Linux)
         run: make cli

.gitignore

@@ -14,6 +14,8 @@ bin/
 /build
 /dist
 /snapshot
+/.tool
+/.task
 
 # changelog generation
 CHANGELOG.md
@@ -30,7 +32,6 @@ VERSION
 /test/results
 coverage.txt
 *.log
-test/integration/test-fixtures/**/go.sum
 
 # probable archives
 .images
@@ -64,3 +65,8 @@ test/integration/test-fixtures/**/go.sum
 # attestation
 cosign.key
 cosign.pub
+
+# Byte-compiled object files for python
+__pycache__/
+*.py[cod]
+*$py.class

.goreleaser.yaml

@@ -41,7 +41,7 @@ builds:
     ldflags: *build-ldflags
     hooks:
       post:
-        - cmd: .tmp/quill sign-and-notarize "{{ .Path }}" --dry-run={{ .IsSnapshot }} --ad-hoc={{ .IsSnapshot }} -vv
+        - cmd: .tool/quill sign-and-notarize "{{ .Path }}" --dry-run={{ .IsSnapshot }} --ad-hoc={{ .IsSnapshot }} -vv
           env:
             - QUILL_LOG_FILE=/tmp/quill-{{ .Target }}.log
 
@@ -247,3 +247,28 @@ 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

DEVELOPING.md

@@ -6,6 +6,7 @@ In order to test and develop in this repo you will need the following dependenci
 - Golang
 - docker
 - make
+- Python (>= 3.9)
 
 ### Docker settings for getting started
 Make sure you've updated your docker settings so the default docker socket path is available.
@@ -60,37 +61,29 @@ For more information on this setup and troubleshooting see [issue 1895](https://
 
 ## Architecture
 
-Syft is used to generate a Software Bill of Materials (SBOM) from different kinds of input.
-
-### Code organization for the cmd package
-
-Syft's entrypoint can be found in the `cmd` package at `cmd/syft/main.go`. `main.go` builds a new syft `cli` via `cli.New()` 
-and then executes the `cli` via `cli.Execute()`. The `cli` package is responsible for parsing command line arguments, 
-setting up the application context and configuration, and executing the application. Each of syft's commands 
-(e.g. `packages`, `attest`, `version`) are implemented as a `cobra.Command` in their respective `<command>.go` files. 
-They are registered in `syft/cli/commands/go`.
+At a high level, this is the package structure of syft:
 ```
-.
-└── syft/
-    ├── cli/
-    │   ├── attest/
-    │   ├── attest.go
-    │   ├── commands.go
-    │   ├── completion.go
-    │   ├── convert/
-    │   ├── convert.go
-    │   ├── eventloop/
-    │   ├── options/
-    │   ├── packages/
-    │   ├── packages.go
-    │   ├── poweruser/
-    │   ├── poweruser.go
-    │   └── version.go
-    └── main.go
+./cmd/syft/
+│   ├── cli/
+│   │   ├── cli.go          // where all commands are wired up
+│   │   ├── commands/       // all command implementations
+│   │   ├── options/        // all command flags and configuration options
+│   │   └── ui/             // all handlers for events that are shown on the UI
+│   └── main.go             // entrypoint for the application
+└── syft/                   // the "core" syft library
+    ├── format/             // contains code to encode or decode to and from SBOM formats
+    ├── pkg/                // contains code to catalog packages from a source
+    ├── sbom/               // contains the definition of an SBOM
+    └── source/             // contains code to create a source object for some input type (e.g. container image, directory, etc)
 ```
 
-#### Execution flow
+Syft's core library is implemented in the `syft` package and subpackages, where the major packages are:
 
+- the `syft/source` package produces a `source.Source` object that can be used to catalog a directory, container, and other source types.
+- the `syft` package contains a single function that can take a `source.Source` object and catalog it, producing an `sbom.SBOM` object
+- the `syft/format` package contains the ability to encode and decode SBOMs to and from different SBOM formats (such as SPDX and CycloneDX)
+
+The `cmd` pacakge at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
 ```mermaid
 sequenceDiagram
     participant main as cmd/syft/main
@@ -114,24 +107,7 @@ sequenceDiagram
     Note right of cmd: Execute SINGLE command from USER
 ```
 
-### Code organization for syft library
-
-Syft's core library (see, exported) functionality is implemented in the `syft` package. The `syft` package is responsible for organizing the core
-SBOM data model, it's translated output formats, and the core SBOM generation logic.
-
-- analysis creates a static SBOM which can be encoded and decoded
-- format objects, should strive to not add or enrich data in encoding that could otherwise be done during analysis
-- package catalogers and their organization can be viewed/added to the `syft/pkg/cataloger` package 
-- file catalogers and their organization can be viewed/added to the `syft/file` package
-- The source package provides an abstraction to allow a user to loosely define a data source that can be cataloged
-
-#### Code example of syft as a library
-
-Here is a gist of using syft as a library to generate a SBOM for a docker image: [link](https://gist.github.com/wagoodman/57ed59a6d57600c23913071b8470175b).
-The execution flow for the example is detailed below.
-
-#### Execution flow examples for the syft library
-
+The `packages` command uses the core library to generate an SBOM for the given user input:
 ```mermaid
 sequenceDiagram
     participant source as source.New(ubuntu:latest)
@@ -150,6 +126,42 @@ sequenceDiagram
     Note right of catalog: cataloger configuration is done based on src
 ```
 
+Additionally, here is a [gist of using syft as a library](https://gist.github.com/spiffcs/3027638b7ba904d07e482a712bc00d3d) to generate a SBOM for a docker image.
+
+
+### `pkg.Package` object
+
+The `pkg.Package` object is a core data structure that represents a software package. Fields like `name` and `version` probably don't need
+a detailed explanation, but some of the other fields are worth a quick overview:
+
+- `FoundBy`: the name of the cataloger that discovered this package (e.g. `python-pip-cataloger`).
+- `Locations`: these are the set of paths and layer ids that were parsed to discover this package (e.g. `python-pip-cataloger`).
+- `Language`: the language of the package (e.g. `python`).
+- `Type`: this is a high-level categorization of the ecosystem the package resides in. For instance, even if the package is a egg, wheel, or requirements.txt reference, it is still logically a "python" package. Not all package types align with a language (e.g. `rpm`) but it is common.
+- `Metadata`: specialized data for specific location(s) parsed. We should try and raise up as much raw information that seems useful. As a rule of thumb the object here should be as flat as possible and use the raw names and values from the underlying source material parsed.
+
+When `pkg.Package` is serialized an additional `MetadataType` is shown. This is a label that helps consumers understand the datashape of the `Metadata` field.
+
+By convention the `MetadataType` value should follow these rules of thumb:
+
+- Only use lowercase letters, numbers, and hyphens. Use hyphens to separate words.
+- **Try to anchor the name in the ecosystem, language, or packaging tooling it belongs to**. For a package manager for a language ecosystem the language, framework or runtime should be used as a prefix. For instance `pubspec-lock` is an OK name, but `dart-pubspec-lock` is better. For an OS package manager this is not necessary (e.g. `apk-db-entry` is a good name, but `alpine-apk-db-entry` is not since `alpine` and the `a` in `apk` is redundant).
+- **Be as specific as possible to what the data represents**. For instance `ruby-gem` is NOT a good `MetadataType` value, but `ruby-gemspec` is. Why? Ruby gem information can come from a gemspec file or a Gemfile.lock, which are very different. The latter name provides more context as to what to expect.
+- **Should describe WHAT the data is, NOT HOW it's used**. For instance `r-description-installed-file` is NOT a good `MetadataType` value since it's trying to convey that we use the DESCRIPTION file in the R ecosystem to detect installed packages. Instead simply describe what the DESCRIPTION file is itself without context of how it's used: `r-description`.
+- **Use the `lock` suffix** to distinct between manifest files that loosely describe package version requirements vs files that strongly specify one and only one version of a package ("lock" files). These should only be used with respect to package managers that have the guide and lock distinction, but would not be appropriate otherwise (e.g. `rpm` does not have a guide vs lock, so `lock` should NOT be used to describe a db entry).
+- **Use the `archive` suffix to indicate a package archive** (e.g. rpm file, apk file, etc) that describes the contents of the package. For example an RPM file that was cataloged would have a `rpm-archive` metadata type (not to be confused with an RPM DB record entry which would be `rpm-db-entry`).
+- **Use the `entry` suffix** to indicate information about a package that was found as a single entry within file that has multiple package entries. If the entry was found within a DB or a flat-file store for an OS package manager, you should use `db-entry`.
+- **Should NOT contain the phrase `package`**, though exceptions are allowed (say if the canonical name literally has the phrase package in it).
+- **Should NOT contain have a `file` suffix** unless the canonical name has the term "file", such as a `pipfile` or `gemfile`. An example of a bad name for this rule is`ruby-gemspec-file`; a better name would be `ruby-gemspec`.
+- **Should NOT contain the exact filename+extensions**. For instance `pipfile.lock` shouldn't really be in the name, instead try and describe what the file is: `python-pipfile-lock` (but shouldn't this be `python-pip-lock` you might ask? No, since the `pip` package manger is not related to the `pipfile` project).
+- **Should NOT contain the phrase `metadata`**, unless the canonical name has this term.
+- **Should represent a single use case**. For example, trying to describe Hackage metadata with a single `HackageMetadata` struct (and thus `MetadataType`) is not allowed since it represents 3 mutually exclusive use cases: representing a `stack.yaml`, `stack.lock`, or `cabal.project` file. Instead, each of these should have their own struct types and `MetadataType` values.
+
+There are other cases that are not covered by these rules... and that's ok! The goal is to provide a consistent naming scheme that is easy to understand and use when it's applicable. If the rules do not exactly apply in your situation then just use your best judgement (or amend these rules as needed whe new common cases come up).
+
+What if the underlying parsed data represents multiple files? There are two approaches to this:
+- use the primary file to represent all the data. For instance, though the `dpkg-cataloger` looks at multiple files to get all information about a package, it's the `status` file that gets represented.
+- nest each individual file's data under the `Metadata` field. For instance, the `java-archive-cataloger` may find information from on or all of the files: `pom.xml`, `pom.properties`, and `MANIFEST.MF`. However, the metadata is simply `java-metadata' with each possibility as a nested optional field.
 
 ### Syft Catalogers
 
@@ -168,6 +180,14 @@ From a high level catalogers have the following properties:
 - _Packages created by the cataloger should not be mutated after they are created_. There is one exception made for adding CPEs to a package after the cataloging phase, but that will most likely be moved back into the cataloger in the future.
 
 
+Cataloger names should be unique and named with the following rules of thumb in mind:
+
+- Must end with `-cataloger`
+- Use lowercase letters, numbers, and hyphens only
+- Use hyphens to separate words
+- Catalogers for language ecosystems should start with the language name (e.g. `python-` for a cataloger that raises up python packages)
+- Distinct between when the cataloger is searching for evidence of installed packages vs declared packages. For example, there are currently two different gemspec-based catalogers, the `ruby-gemspec-cataloger` and `ruby-installed-gemspec-cataloger`, where the latter requires that the gemspec is found within a `specifications` directory (which means it was installed, not just at the root of a source repo).
+
 #### Building a new Cataloger
 
 Catalogers must fulfill the [`pkg.Cataloger` interface](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger.go) in order to add packages to the SBOM.
@@ -214,7 +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

@@ -1,402 +1,46 @@
-BIN := syft
-TEMP_DIR := ./.tmp
+OWNER = anchore
+PROJECT = syft
 
-# Command templates #################################
-LINT_CMD := $(TEMP_DIR)/golangci-lint run --tests=false
-GOIMPORTS_CMD := $(TEMP_DIR)/gosimports -local github.com/anchore
-RELEASE_CMD := $(TEMP_DIR)/goreleaser release --clean
-SNAPSHOT_CMD := $(RELEASE_CMD) --skip-publish --skip-sign --snapshot
-CHRONICLE_CMD = $(TEMP_DIR)/chronicle
-GLOW_CMD = $(TEMP_DIR)/glow
-
-# Tool versions #################################
-GOLANGCILINT_VERSION := v1.54.2
-GOSIMPORTS_VERSION := v0.3.8
-BOUNCER_VERSION := v0.4.0
-CHRONICLE_VERSION := v0.8.0
-GORELEASER_VERSION := v1.21.2
-YAJSV_VERSION := v1.4.1
-COSIGN_VERSION := v2.2.0
-QUILL_VERSION := v0.4.1
-GLOW_VERSION := v1.5.1
-
-# Formatting variables #################################
-BOLD := $(shell tput -T linux bold)
-PURPLE := $(shell tput -T linux setaf 5)
-GREEN := $(shell tput -T linux setaf 2)
-CYAN := $(shell tput -T linux setaf 6)
-RED := $(shell tput -T linux setaf 1)
-RESET := $(shell tput -T linux sgr0)
-TITLE := $(BOLD)$(PURPLE)
-SUCCESS := $(BOLD)$(GREEN)
-
-# Test variables #################################
-COMPARE_DIR := ./test/compare
-COMPARE_TEST_IMAGE := centos:8.2.2004
-COVERAGE_THRESHOLD := 62  # the quality gate lower threshold for unit test total % coverage (by function statements)
-
-## Build variables #################################
-VERSION := $(shell git describe --dirty --always --tags)
-DIST_DIR := ./dist
-SNAPSHOT_DIR := ./snapshot
-CHANGELOG := CHANGELOG.md
-OS := $(shell uname | tr '[:upper:]' '[:lower:]')
-SNAPSHOT_BIN := $(realpath $(shell pwd)/$(SNAPSHOT_DIR)/$(OS)-build_$(OS)_amd64_v1/$(BIN))
-
-ifndef VERSION
-	$(error VERSION is not set)
-endif
-
-define title
-    @printf '$(TITLE)$(1)$(RESET)\n'
-endef
-
-define safe_rm_rf
-	bash -c 'test -z "$(1)" && false || rm -rf $(1)'
-endef
-
-define safe_rm_rf_children
-	bash -c 'test -z "$(1)" && false || rm -rf $(1)/*'
-endef
-
-.DEFAULT_GOAL:=help
-
-
-.PHONY: all
-all: static-analysis test ## Run all linux-based checks (linting, license check, unit, integration, and linux compare tests)
-	@printf '$(SUCCESS)All checks pass!$(RESET)\n'
-
-.PHONY: static-analysis
-static-analysis: check-go-mod-tidy lint check-licenses check-json-schema-drift  ## Run all static analysis checks
-
-.PHONY: test
-test: unit integration validate-cyclonedx-schema benchmark cli ## Run all tests (currently unit, integration, linux compare, and cli tests)
+TOOL_DIR = .tool
+BINNY = $(TOOL_DIR)/binny
+TASK = $(TOOL_DIR)/task
 
+.DEFAULT_GOAL := make-default
 
 ## Bootstrapping targets #################################
 
-.PHONY: bootstrap
-bootstrap: $(TEMP_DIR) bootstrap-go bootstrap-tools ## Download and install all tooling dependencies (+ prep tooling in the ./tmp dir)
-	$(call title,Bootstrapping dependencies)
+# note: we need to assume that binny and task have not already been installed
+$(BINNY):
+	@mkdir -p $(TOOL_DIR)
+	@curl -sSfL https://raw.githubusercontent.com/$(OWNER)/binny/main/install.sh | sh -s -- -b $(TOOL_DIR)
 
-.PHONY: bootstrap-tools
-bootstrap-tools: $(TEMP_DIR)
-	curl -sSfL https://raw.githubusercontent.com/anchore/quill/main/install.sh | sh -s -- -b $(TEMP_DIR)/ $(QUILL_VERSION)
-	GO111MODULE=off GOBIN=$(realpath $(TEMP_DIR)) go get -u golang.org/x/perf/cmd/benchstat
-	curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(TEMP_DIR)/ $(GOLANGCILINT_VERSION)
-	curl -sSfL https://raw.githubusercontent.com/wagoodman/go-bouncer/master/bouncer.sh | sh -s -- -b $(TEMP_DIR)/ $(BOUNCER_VERSION)
-	curl -sSfL https://raw.githubusercontent.com/anchore/chronicle/main/install.sh | sh -s -- -b $(TEMP_DIR)/ $(CHRONICLE_VERSION)
-	.github/scripts/goreleaser-install.sh -d -b $(TEMP_DIR)/ $(GORELEASER_VERSION)
-	# the only difference between goimports and gosimports is that gosimports removes extra whitespace between import blocks (see https://github.com/golang/go/issues/20818)
-	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/rinchsan/gosimports/cmd/gosimports@$(GOSIMPORTS_VERSION)
-	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/neilpa/yajsv@$(YAJSV_VERSION)
-	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/sigstore/cosign/v2/cmd/cosign@$(COSIGN_VERSION)
-	GOBIN="$(realpath $(TEMP_DIR))" go install github.com/charmbracelet/glow@$(GLOW_VERSION)
+# note: we need to assume that binny and task have not already been installed
+.PHONY: task
+$(TASK) task: $(BINNY)
+	@$(BINNY) install task -q
 
-.PHONY: bootstrap-go
-bootstrap-go:
+.PHONY: ci-bootstrap-go
+ci-bootstrap-go:
 	go mod download
 
-$(TEMP_DIR):
-	mkdir -p $(TEMP_DIR)
+# 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) $@
 
+## Shim targets #################################
 
-## Static analysis targets #################################
+.PHONY: make-default
+make-default: $(TASK)
+	@# run the default task in the taskfile
+	@$(TASK)
 
-.PHONY: lint
-lint:  ## Run gofmt + golangci lint checks
-	$(call title,Running linters)
-	# ensure there are no go fmt differences
-	@printf "files with gofmt issues: [$(shell gofmt -l -s .)]\n"
-	@test -z "$(shell gofmt -l -s .)"
+# for those of us that can't seem to kick the habit of typing `make ...` lets wrap the superior `task` tool
+TASKS := $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep '^\* ' | cut -d' ' -f2 | tr -d ':' | tr '\n' ' '" ) $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep 'aliases:' | cut -d ':' -f 3 | tr '\n' ' ' | tr -d ','")
 
-	# run all golangci-lint rules
-	$(LINT_CMD)
-	@[ -z "$(shell $(GOIMPORTS_CMD) -d .)" ] || (echo "goimports needs to be fixed" && false)
+.PHONY: $(TASKS)
+$(TASKS): $(TASK)
+	@$(TASK) $@
 
-	# go tooling does not play well with certain filename characters, ensure the common cases don't result in future "go get" failures
-	$(eval MALFORMED_FILENAMES := $(shell find . | grep -e ':'))
-	@bash -c "[[ '$(MALFORMED_FILENAMES)' == '' ]] || (printf '\nfound unsupported filename characters:\n$(MALFORMED_FILENAMES)\n\n' && false)"
-
-.PHONY: format
-format:  ## Auto-format all source code
-	$(call title,Running formatters)
-	gofmt -w -s .
-	$(GOIMPORTS_CMD) -w .
-	go mod tidy
-
-.PHONY: lint-fix
-lint-fix: format  ## Auto-format all source code + run golangci lint fixers
-	$(call title,Running lint fixers)
-	$(LINT_CMD) --fix
-
-.PHONY: check-licenses
-check-licenses:  ## Ensure transitive dependencies are compliant with the current license policy
-	$(call title,Checking for license compliance)
-	$(TEMP_DIR)/bouncer check ./...
-
-check-go-mod-tidy:
-	@ .github/scripts/go-mod-tidy-check.sh && echo "go.mod and go.sum are tidy!"
-
-check-json-schema-drift:
-	$(call title,Ensure there is no drift between the JSON schema and the code)
-	@.github/scripts/json-schema-drift-check.sh
-
-## Testing targets #################################
-
-.PHONY: unit
-unit: $(TEMP_DIR) fixtures  ## Run unit tests (with coverage)
-	$(call title,Running unit tests)
-	go test -race -coverprofile $(TEMP_DIR)/unit-coverage-details.txt $(shell go list ./... | grep -v anchore/syft/test)
-	@.github/scripts/coverage.py $(COVERAGE_THRESHOLD) $(TEMP_DIR)/unit-coverage-details.txt
-
-.PHONY: integration
-integration:  ## Run integration tests
-	$(call title,Running integration tests)
-	go test -v ./test/integration
-	go run -race cmd/syft/main.go alpine:latest
-
-.PHONY: validate-cyclonedx-schema
-validate-cyclonedx-schema:
-	cd schema/cyclonedx && make
-
-.PHONY: cli
-cli: $(SNAPSHOT_DIR)  ## Run CLI tests
-	chmod 755 "$(SNAPSHOT_BIN)"
-	$(SNAPSHOT_BIN) version
-	SYFT_BINARY_LOCATION='$(SNAPSHOT_BIN)' \
-		go test -count=1 -timeout=15m -v ./test/cli
-
-
-## Benchmark test targets #################################
-
-.PHONY: benchmark
-benchmark: $(TEMP_DIR)  ## Run benchmark tests and compare against the baseline (if available)
-	$(call title,Running benchmark tests)
-	go test -p 1 -run=^Benchmark -bench=. -count=7 -benchmem ./... | tee $(TEMP_DIR)/benchmark-$(VERSION).txt
-	(test -s $(TEMP_DIR)/benchmark-main.txt && \
-		$(TEMP_DIR)/benchstat $(TEMP_DIR)/benchmark-main.txt $(TEMP_DIR)/benchmark-$(VERSION).txt || \
-		$(TEMP_DIR)/benchstat $(TEMP_DIR)/benchmark-$(VERSION).txt) \
-			| tee $(TEMP_DIR)/benchstat.txt
-
-.PHONY: show-benchstat
-show-benchstat:
-	@cat $(TEMP_DIR)/benchstat.txt
-
-
-## Test-fixture-related targets #################################
-
-# note: this is used by CI to determine if various test fixture cache should be restored or recreated
-fingerprints:
-	$(call title,Creating all test cache input fingerprints)
-
-	# 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/rpm/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
-
-.PHONY: fixtures
-fixtures:
-	$(call title,Generating test fixtures)
-	cd syft/pkg/cataloger/java/test-fixtures/java-builds && make
-	cd syft/pkg/cataloger/rpm/test-fixtures && make
-	cd syft/pkg/cataloger/binary/test-fixtures && make
-
-.PHONY: show-test-image-cache
-show-test-image-cache:  ## Show all docker and image tar cache
-	$(call title,Docker daemon cache)
-	@docker images --format '{{.ID}} {{.Repository}}:{{.Tag}}' | grep stereoscope-fixture- | sort
-
-	$(call title,Tar cache)
-	@find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" | sort
-
-.PHONY: show-test-snapshots
-show-test-snapshots:  ## Show all test snapshots
-	$(call title,Test snapshots)
-	@find . -type f -wholename "**/test-fixtures/snapshot/*" | sort
-
-
-## install.sh testing targets #################################
-
-install-test: $(SNAPSHOT_DIR)
-	cd test/install && \
-		make
-
-install-test-cache-save: $(SNAPSHOT_DIR)
-	cd test/install && \
-		make save
-
-install-test-cache-load: $(SNAPSHOT_DIR)
-	cd test/install && \
-		make load
-
-install-test-ci-mac: $(SNAPSHOT_DIR)
-	cd test/install && \
-		make ci-test-mac
-
-.PHONY: generate-compare-file
-generate-compare-file:
-	$(call title,Generating compare test file)
-	go run ./cmd/syft $(COMPARE_TEST_IMAGE) -o json > $(COMPARE_DIR)/test-fixtures/acceptance-centos-8.2.2004.json
-
-# note: we cannot clean the snapshot directory since the pipeline builds the snapshot separately
-.PHONY: compare-mac
-compare-mac: $(TEMP_DIR) $(SNAPSHOT_DIR)  ## Run compare tests on build snapshot binaries and packages (Mac)
-	$(call title,Running compare test: Run on Mac)
-	$(COMPARE_DIR)/mac.sh \
-			$(SNAPSHOT_DIR) \
-			$(COMPARE_DIR) \
-			$(COMPARE_TEST_IMAGE) \
-			$(TEMP_DIR)
-
-# note: we cannot clean the snapshot directory since the pipeline builds the snapshot separately
-.PHONY: compare-linux
-compare-linux: compare-test-deb-package-install compare-test-rpm-package-install  ## Run compare tests on build snapshot binaries and packages (Linux)
-
-.PHONY: compare-test-deb-package-install
-compare-test-deb-package-install: $(TEMP_DIR) $(SNAPSHOT_DIR)
-	$(call title,Running compare test: DEB install)
-	$(COMPARE_DIR)/deb.sh \
-			$(SNAPSHOT_DIR) \
-			$(COMPARE_DIR) \
-			$(COMPARE_TEST_IMAGE) \
-			$(TEMP_DIR)
-
-.PHONY: compare-test-rpm-package-install
-compare-test-rpm-package-install: $(TEMP_DIR) $(SNAPSHOT_DIR)
-	$(call title,Running compare test: RPM install)
-	$(COMPARE_DIR)/rpm.sh \
-			$(SNAPSHOT_DIR) \
-			$(COMPARE_DIR) \
-			$(COMPARE_TEST_IMAGE) \
-			$(TEMP_DIR)
-
-
-## Code and data generation targets #################################
-
-.PHONY: generate-json-schema
-generate-json-schema:  ## Generate a new json schema
-	cd syft/internal && go generate . && cd jsonschema && go run .
-
-.PHONY: generate-license-list
-generate-license-list:  ## Generate an updated spdx license list
-	go generate ./internal/spdxlicense/...
-	gofmt -s -w ./internal/spdxlicense
-
-.PHONY: generate-cpe-dictionary-index
-generate-cpe-dictionary-index:  ## Build the CPE index based off of the latest available CPE dictionary
-	$(call title,Building CPE index)
-	go generate ./syft/pkg/cataloger/common/cpe/dictionary
-
-
-## Build-related targets #################################
-
-.PHONY: build
-build:
-	CGO_ENABLED=0 go build -trimpath -ldflags "$(LDFLAGS)" -o $@ ./cmd/syft
-
-$(SNAPSHOT_DIR):  ## Build snapshot release binaries and packages
-	$(call title,Building snapshot artifacts)
-
-	# create a config with the dist dir overridden
-	echo "dist: $(SNAPSHOT_DIR)" > $(TEMP_DIR)/goreleaser.yaml
-	cat .goreleaser.yaml >> $(TEMP_DIR)/goreleaser.yaml
-
-	# build release snapshots
-	$(SNAPSHOT_CMD) --config $(TEMP_DIR)/goreleaser.yaml
-
-.PHONY: changelog
-changelog: clean-changelog  ## Generate and show the changelog for the current unreleased version
-	$(CHRONICLE_CMD) -vvv -n --version-file VERSION > $(CHANGELOG)
-	@$(GLOW_CMD) $(CHANGELOG)
-
-$(CHANGELOG):
-	$(CHRONICLE_CMD) -vvv > $(CHANGELOG)
-
-.PHONY: release
-release:
-	@.github/scripts/trigger-release.sh
-
-.PHONY: ci-release
-ci-release: ci-check clean-dist $(CHANGELOG)
-	$(call title,Publishing release artifacts)
-
-	# create a config with the dist dir overridden
-	echo "dist: $(DIST_DIR)" > $(TEMP_DIR)/goreleaser.yaml
-	cat .goreleaser.yaml >> $(TEMP_DIR)/goreleaser.yaml
-
-	bash -c "\
-		$(RELEASE_CMD) \
-			--config $(TEMP_DIR)/goreleaser.yaml \
-			--release-notes <(cat $(CHANGELOG)) \
-				 || (cat /tmp/quill-*.log && false)"
-
-	# upload the version file that supports the application version update check (excluding pre-releases)
-	.github/scripts/update-version-file.sh "$(DIST_DIR)" "$(VERSION)"
-
-.PHONY: ci-check
-ci-check:
-	@.github/scripts/ci-check.sh
-
-## Cleanup targets #################################
-
-.PHONY: clean
-clean: clean-dist clean-snapshot clean-test-image-cache  ## Remove previous builds, result reports, and test cache
-	$(call safe_rm_rf_children,$(TEMP_DIR))
-
-.PHONY: clean-snapshot
-clean-snapshot:
-	$(call safe_rm_rf,$(SNAPSHOT_DIR))
-	rm -f $(TEMP_DIR)/goreleaser.yaml
-
-.PHONY: clean-dist
-clean-dist: clean-changelog
-	$(call safe_rm_rf,$(DIST_DIR))
-	rm -f $(TEMP_DIR)/goreleaser.yaml
-
-.PHONY: clean-changelog
-clean-changelog:
-	rm -f $(CHANGELOG) VERSION
-
-clean-test-image-cache: clean-test-image-tar-cache clean-test-image-docker-cache ## Clean test image cache
-
-.PHONY: clear-test-image-tar-cache
-clean-test-image-tar-cache:  ## Delete all test cache (built docker image tars)
-	find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" -delete
-
-.PHONY: clear-test-image-docker-cache
-clean-test-image-docker-cache:	## Purge all test docker images
-	docker images --format '{{.ID}} {{.Repository}}' | grep stereoscope-fixture- | awk '{print $$1}' | uniq | xargs -r docker rmi --force
-
-## Halp! #################################
-
-.PHONY: help
-help:  ## Display this help
-	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "$(BOLD)$(CYAN)%-25s$(RESET)%s\n", $$1, $$2}'
+help: $(TASK)
+	@$(TASK) -l

README.md

@@ -54,6 +54,7 @@ For commercial support options with Syft or Grype, please [contact Anchore](http
 - Ruby (gem)
 - Rust (cargo.lock)
 - Swift (cocoapods, swift-package-manager)
+- Wordpress plugins
 
 ## Installation
 
@@ -109,21 +110,22 @@ nix-shell -p syft
 
 To generate an SBOM for a container image:
 
-```
+```bash
 syft <image>
 ```
 
 The above output includes only software that is visible in the container (i.e., the squashed representation of the image). To include software from all image layers in the SBOM, regardless of its presence in the final image, provide `--scope all-layers`:
 
-```
+```bash
 syft <image> --scope all-layers
 ```
 
 ### Supported sources
 
-Syft can generate a SBOM from a variety of sources:
+Syft can generate an SBOM from a variety of sources including images, files, directories, and archives. Syft will attempt to
+determine the type of source based on provided input, for example:
 
-```
+```bash
 # catalog a container image archive (from the result of `docker image save ...`, `podman save ...`, or `skopeo copy` commands)
 syft path/to/image.tar
 
@@ -134,88 +136,133 @@ syft path/to/image.sif
 syft path/to/dir
 ```
 
-Sources can be explicitly provided with a scheme:
+To explicitly specify the source behavior, use the `--from` flag. Allowable options are:
 
 ```
-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)
+docker             use images from the Docker daemon
+podman             use images from the Podman daemon
+containerd         use images from the Containerd daemon
+docker-archive     use a tarball from disk for archives created from "docker save"
+oci-archive        use a tarball from disk for OCI archives (from Skopeo or otherwise)
+oci-dir            read directly from a path on disk for OCI layout directories (from Skopeo or otherwise)
+singularity        read directly from a Singularity Image Format (SIF) container on disk
+dir                read directly from a path on disk (any directory)
+file               read directly from a path on disk (any single file)
+registry           pull image directly from a registry (no container runtime required)
+```
+If a source is not provided and Syft identifies the input as a potential image reference, Syft will attempt to resolve it using:
+the Docker, Podman, and Containerd daemons followed by direct registry access, in that order.
+
+This default behavior can be overridden with the `default-image-pull-source` configuration option (See [Configuration](#configuration) for more details).
+
+
+### File selection
+
+By default, Syft will catalog file details and digests for files that are owned by discovered packages. You can change this behavior by using the `SYFT_FILE_METADATA_SELECTION` environment variable or the `file.metadata.selection` configuration option. The options are:
+
+- `all`: capture all files from the search space
+- `owned-by-package`: capture only files owned by packages (default)
+- `none`: disable capturing any file information
+
+
+### Package cataloger selection
+
+#### Concepts
+
+> [!IMPORTANT]  
+> Syft uses a different set of catalogers by default when scanning files directly than it does when scanning images
+
+The catalogers for an image scan assumes that package installation steps have already been completed. For example, Syft will identify Python packages that have egg or wheel metadata files under a `site-packages` directory, since this is how the canonical tooling `pip` installs python packages.
+
+The catalogers for a directory scan will look for installed software as well as declared dependencies that are not necessarily installed. For example, dependencies listed in a Python `requirements.txt`.
+
+This default set of catalogers being dynamic is critical as this allows Syft to be used in a variety of contexts while still generating accurate SBOMs.
+Overriding the set of default catalogers is not recommended for most purposes, however, is possible if needed.
+
+Catalogers can be referenced in two different ways:
+- *by name*: the exact cataloger name (e.g. `java-pom-cataloger` or `java-archive-cataloger`)
+- *by tag*: a tag that is associated with a cataloger (e.g. `java`)
+
+Syft can take lists of references on the CLI or in the application configuration to define which catalogers to use.
+
+You can **set** the list of catalogers explicitly to use with the `--override-default-catalogers` CLI flag, accepting a comma-separated list of cataloger names or tags.
+
+You can also **add** to, **remove** from, or **sub-select** catalogers to use within the default set of catalogers by using the `--select-catalogers` CLI flag.
+  - To **sub-select** catalogers simply provide a tag (e.g. `--select-catalogers TAG`). Catalogers will always be selected from the default set of catalogers (e.g. `--select-catalogers java,go` will select all the `java` catalogers in the default set and all the `go` catalogers in the default set).
+  - To **add** a cataloger prefix the cataloger name with `+` (e.g. `--select-catalogers +NAME`). Added catalogers will _always be added_ regardless of removals, filtering, or other defaults.
+  - To **remove** a cataloger prefix the cataloger name or tag with `-` (e.g. `--select-catalogers -NAME_OR_TAG`). Catalogers are removed from the set of default catalogers after processing any sub-selections.
+
+These rules and the dynamic default cataloger sets approximates to the following logic:
+
+```
+image_catalogers = all_catalogers AND catalogers_tagged("image")
+
+directory_catalogers = all_catalogers AND catalogers_tagged("directory")
+
+default_catalogers = image_catalogers OR directory_catalogers
+
+sub_selected_catalogers = default_catalogers INTERSECT catalogers_tagged(TAG) [ UNION sub_selected_catalogers ... ]
+
+base_catalogers = default_catalogers OR sub_selected_catalogers
+
+final_set = (base_catalogers SUBTRACT removed_catalogers) UNION added_catalogers
 ```
 
-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.
 
+#### Examples
 
-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).
+Only scan for python related packages with catalogers appropriate for the source type (image or directory):
+```bash
+syft <some container image> --select-catalogers "python"
+# results in the following catalogers being used:
+# - python-installed-package-cataloger
+```
 
-### Default Cataloger Configuration by scan type
+Same command, but the set of catalogers changes based on what is being analyzed (in this case a directory):
+```bash
+syft <a directory> --select-catalogers "python"
+# results in the following catalogers being used:
+# - python-installed-package-cataloger
+# - python-package-cataloger
+```
 
-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.
+Use the default set of catalogers and add a cataloger to the set:
+```bash
+syft ... --select-catalogers "+sbom-cataloger"
+```
 
-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.
+Use the default set of catalogers but remove any catalogers that deal with RPMs:
+```bash
+syft ... --select-catalogers "-rpm"
+```
 
-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).
+Only scan with catalogers that:
+- are tagged with "go"
+- always use the sbom-cataloger
+- are appropriate for the source type (image or directory)
 
-##### Image Scanning:
-- alpmdb
-- apkdb
-- binary
-- dotnet-deps
-- 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
+```bash
+syft <some container image> --select-catalogers "go,+sbom-cataloger"
+# results in the following catalogers being used:
+# - go-module-binary-cataloger
+# - sbom-cataloger
+```
 
-##### Directory Scanning:
-- alpmdb
-- apkdb
-- binary
-- cocoapods
-- conan
-- dartlang-lock
-- dotnet-deps
-- 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
+Scan with all catalogers that deal with binary analysis, regardless of the source type:
+```bash
+syft ... --override-default-catalogers "binary"
+# results in the following catalogers being used:
+# - binary-cataloger
+# - cargo-auditable-binary-cataloger
+# - dotnet-portable-executable-cataloger
+# - go-module-binary-cataloger
+```
+
+Only scan with the specific `go-module-binary-cataloger` and `go-module-file-cataloger` catalogers:
+```bash
+syft ... --override-default-catalogers "go-module-binary-cataloger,go-module-file-cataloger"
+```
 
-##### Non Default:
-- cargo-auditable-binary
 
 ### Excluding file paths
 
@@ -244,21 +291,21 @@ syft <image> -o <format>
 ```
 
 Where the `formats` available are:
-- `json`: Use this to get as much information out of Syft as possible!
-- `text`: A row-oriented, human-and-machine-friendly output.
+- `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`: A JSON report conforming to GitHub's dependency snapshot format.
-- `table`: A columnar summary (default).
+- `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:
+Syft lets you define custom output formats, using [Go templates](https://pkg.go.dev/text/template) relative to the Syft JSON output. Here's how it works:
 
 - Define your format as a Go template, and save this template as a file.
 
@@ -266,15 +313,15 @@ Syft lets you define custom output formats, using [Go templates](https://pkg.go.
 
 - Specify the path to the template file (`-t ./path/to/custom.template`).
 
-- Syft's template processing uses the same data models as the `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 json` as a reference.
+- 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}}"
+"Package","Version Installed", "Found by"
+{{- range .artifacts}}
+"{{.name}}","{{.version}}","{{.foundBy}}"
 {{- end}}
 ```
 
@@ -291,13 +338,16 @@ Syft also includes a vast array of utility templating functions from [sprig](htt
 
 Lastly, Syft has custom templating functions defined in `./syft/format/template/encoder.go` to help parse the passed-in JSON structs.
 
+> [!NOTE]
+> If you have templates being used before Syft v0.102.0 that are no longer working. This is because templating keys were relative to the internal go structs before this version whereas now the keys are relative to the Syft JSON output. To get the legacy behavior back you can set the `format.template.legacy` option to `true` in your configuration.
+
 ## 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 json=sbom.syft.json -o spdx-json=sbom.spdx.json
+syft <image> -o syft-json=sbom.syft.json -o spdx-json=sbom.spdx.json
 ```
 
 ## Private Registry Authentication
@@ -454,85 +504,152 @@ Configuration search paths:
 Configuration options (example values are the default):
 
 ```yaml
-# the output format(s) of the SBOM report (options: table, text, json, spdx, ...)
-# same as -o, --output, and SYFT_OUTPUT env var
+# the output format(s) of the SBOM report (options: syft-table, syft-text, syft-json, spdx-json, ...)
 # to specify multiple output files in differing formats, use a list:
 # output:
-#   - "json=<syft-json-output-file>"
+#   - "syft-json=<syft-json-output-file>"
 #   - "spdx-json=<spdx-json-output-file>"
-output: "table"
+# SYFT_OUTPUT env var / -o, --output flags
+output: 
+  - "syft-table"
 
 # suppress all output (except for the SBOM report)
-# same as -q ; SYFT_QUIET env var
+# SYFT_QUIET env var / -q flag
 quiet: false
 
-# 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
+# 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: ""
+# maximum number of workers used to process the list of package catalogers in parallel
+parallelism: 1
 
-# a list of globs to exclude from scanning. same as --exclude ; for example:
+# a list of globs to exclude from scanning, for example:
 # exclude:
 #   - "/etc/**"
 #   - "./out/**/*.json"
+# SYFT_EXCLUDE env var / --exclude flag
 exclude: []
 
-# allows users to exclude synthetic binary packages from the sbom
-# these packages are removed if an overlap with a non-synthetic package is found
-exclude-binary-overlap-by-ownership: true
-
 # os and/or architecture to use when referencing container images (e.g. "windows/armv6" or "arm64")
-# same as --platform; SYFT_PLATFORM env var
+# SYFT_PLATFORM env var / --platform flag
 platform: ""
 
+# the search space to look for file and package data (options: all-layers, squashed)
+# SYFT_SCOPE env var
+scope: "squashed"
+
 # set the list of package catalogers to use when generating the SBOM
 # default = empty (cataloger set determined automatically by the source type [image or file/directory])
-# catalogers:
-#   - alpmdb-cataloger
-#   - apkdb-cataloger
-#   - binary-cataloger
-#   - cargo-auditable-binary-cataloger
-#   - cocoapods-cataloger
-#   - conan-cataloger
-#   - dartlang-lock-cataloger
-#   - dotnet-deps-cataloger
-#   - dpkgdb-cataloger
-#   - elixir-mix-lock-cataloger
-#   - erlang-rebar-lock-cataloger
-#   - go-mod-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-index-cataloger
-#   - python-package-cataloger
-#   - rpm-db-cataloger
-#   - rpm-file-cataloger
-#   - ruby-gemfile-cataloger
-#   - ruby-gemspec-cataloger
-#   - rust-cargo-lock-cataloger
-#   - sbom-cataloger
-#   - spm-cataloger
+# Use `syft cataloger list` for a list of catalogers you can specify
+# DEPRECATED: please use default-catalogers and select-catalogers configuration options instead
+# SYFT_CATALOGERS env var / --catalogers flag
 catalogers:
 
+# set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)
+# SYFT_DEFAULT_CATALOGERS env var / --override-default-catalogers flag
+default-catalogers: []
+
+# add, remove, and filter the catalogers to be used
+# SYFT_SELECT_CATALOGERS env var / --select-catalogers flag;
+select-catalogers: []
+
+# all format configuration
+format:
+ 
+  # default value for all formats that support the "pretty" option (default is unset)
+  # SYFT_FORMAT_PRETTY env var
+  pretty: 
+
+  # all syft-json format options
+  json:
+
+    # include space indention and newlines (inherits default value from 'format.pretty' or 'false' if parent is unset)
+    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+    # SYFT_FORMAT_JSON_PRETTY env var
+    pretty: false
+    
+    # transform any syft-json output to conform to an approximation of the v11.0.1 schema. This includes:
+    # - using the package metadata type names from before v12 of the JSON schema (changed in https://github.com/anchore/syft/pull/1983)
+    #
+    # Note: this will still include package types and fields that were added at or after json schema v12. This means
+    # that output might not strictly be json schema v11 compliant, however, for consumers that require time to port
+    # over to the final syft 1.0 json output this option can be used to ease the transition.
+    #
+    # Note: long term support for this option is not guaranteed (it may change or break at any time).
+    # SYFT_FORMAT_JSON_LEGACY env var
+    legacy: false
+
+  # all template format options
+  template:
+    # path to the template file to use when rendering the output with the `template` output format. 
+    # Note that all template paths are based on the current syft-json schema.
+    # SYFT_FORMAT_TEMPLATE_PATH env var / -t flag 
+    path: ""
+    
+    # if true, uses the go structs for the syft-json format for templating. 
+    # if false, uses the syft-json output for templating (which follows the syft JSON schema exactly).
+    #
+    # Note: long term support for this option is not guaranteed (it may change or break at any time).
+    # SYFT_FORMAT_TEMPLATE_LEGACY env var
+    legacy: false
+
+  # all spdx-json format options
+  spdx-json:
+
+    # include space indention and newlines
+    # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+    # SYFT_FORMAT_SPDX_JSON_PRETTY env var
+    pretty: false
+
+  # all cyclonedx-json format options
+  cyclonedx-json:
+
+     # include space indention and newlines
+     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+     # SYFT_FORMAT_CYCLONEDX_JSON_PRETTY env var
+     pretty: false
+
+  # all cyclonedx-xml format options
+  cyclonedx-xml:
+
+     # include space indention
+     # note: inherits default value from 'format.pretty' or 'false' if parent is unset
+     # SYFT_FORMAT_CYCLONEDX_XML_PRETTY env var
+     pretty: false
+
+
+file:
+
+   metadata: 
+      # select which files should be captured by the file-metadata cataloger and included in the SBOM. 
+      # Options include:
+      #  - "all": capture all files from the search space
+      #  - "owned-by-package": capture only files owned by packages
+      #  - "none", "": do not capture any files
+      # SYFT_FILE_METADATA_SELECTION env var
+      selection: "owned-by-package"
+
+      # the file digest algorithms to use when cataloging files (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
+      # SYFT_FILE_METADATA_DIGESTS env var
+      digests:
+      - "sha256"
+      - "sha1"
+
+   # capture the contents of select files in the SBOM
+   content:
+      # skip searching a file entirely if it is above the given size (default = 1MB; unit = bytes)
+      # SYFT_FILE_CONTENT_SKIP_FILES_ABOVE_SIZE env var
+      skip-files-above-size: 1048576
+   
+      # file globs for the cataloger to match on
+      # SYFT_FILE_CONTENT_GLOBS env var
+      globs: []
+
+
 # cataloging packages is exposed through the packages and power-user subcommands
 package:
-
+   
   # search within archives that do contain a file index to search against (zip)
   # note: for now this only applies to the java package cataloger
   # SYFT_PACKAGE_SEARCH_INDEXED_ARCHIVES env var
@@ -544,14 +661,11 @@ package:
   # 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
+  # allows users to exclude synthetic binary packages from the sbom
+  # these packages are removed if an overlap with a non-synthetic package is found
+  # SYFT_PACKAGE_EXCLUDE_BINARY_OVERLAP_BY_OWNERSHIP env var
+  exclude-binary-overlap-by-ownership: true
 
-    # 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
@@ -576,6 +690,35 @@ golang:
    # if unset this defaults to $GONOPROXY
    # SYFT_GOLANG_NOPROXY env var
    no-proxy: ""
+  
+   # the go main module version discovered from binaries built with the go compiler will
+   # always show (devel) as the version. Use these options to control heuristics to guess
+   # a more accurate version from the binary.
+   main-module-version:
+      
+      # look for LD flags that appear to be setting a version (e.g. -X main.version=1.0.0)
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_LD_FLAGS env var
+      from-ld-flags: true
+      
+      # use the build settings (e.g. vcs.version & vcs.time) to craft a v0 pseudo version 
+      # (e.g. v0.0.0-20220308212642-53e6d0aaf6fb) when a more accurate version cannot be found otherwise.
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_BUILD_SETTINGS env var
+      from-build-settings: true
+      
+      # search for semver-like strings in the binary contents.
+      # SYFT_GOLANG_MAIN_MODULE_VERSION_FROM_CONTENTS env var
+      from-contents: true
+  
+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
@@ -589,88 +732,39 @@ python:
    # when given an arbitrary constraint will be used (even if that version may not be available/published).
    guess-unpinned-requirements: false
 
-# cataloging file contents is exposed through the power-user subcommand
-file-contents:
-  cataloger:
-    # enable/disable cataloging of secrets
-    # SYFT_FILE_CONTENTS_CATALOGER_ENABLED env var
-    enabled: true
+javascript:
+  search-remote-licenses: false
+  npm-base-url: "https://registry.npmjs.org"
 
-    # the search space to look for secrets (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: []
-
-# cataloging file metadata is exposed through the power-user subcommand
-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
-
-# cataloging secrets is exposed through the power-user subcommand
-secrets:
-  cataloger:
-    # enable/disable cataloging of secrets
-    # SYFT_SECRETS_CATALOGER_ENABLED env var
-    enabled: true
-
-    # the search space to look for secrets (options: all-layers, squashed)
-    # SYFT_SECRETS_CATALOGER_SCOPE env var
-    scope: "all-layers"
-
-  # show extracted secret values in the final JSON report
-  # SYFT_SECRETS_REVEAL_VALUES env var
-  reveal-values: false
-
-  # skip searching a file entirely if it is above the given size (default = 1MB; unit = bytes)
-  # SYFT_SECRETS_SKIP_FILES_ABOVE_SIZE env var
-  skip-files-above-size: 1048576
-
-  # name-regex pairs to consider when searching files for secrets. Note: the regex must match single line patterns
-  # but may also have OPTIONAL multiline capture groups. Regexes with a named capture group of "value" will
-  # use the entire regex to match, but the secret value will be assumed to be entirely contained within the
-  # "value" named capture group.
-  additional-patterns: {}
-
-  # names to exclude from the secrets search, valid values are: "aws-access-key", "aws-secret-key", "pem-private-key",
-  # "docker-config-auth", and "generic-api-key". Note: this does not consider any names introduced in the
-  # "secrets.additional-patterns" config option.
-  # SYFT_SECRETS_EXCLUDE_PATTERN_NAMES env var
-  exclude-pattern-names: []
-
-# options that apply to all scan sources
+# configuration for the source that the SBOM is generated from (e.g. a file, directory, or container image)
 source:
   # alias name for the source
-  # SYFT_SOURCE_NAME env var; --source-name flag
+  # SYFT_SOURCE_NAME env var / --source-name flag
   name: ""
    
   # alias version for the source
-  # SYFT_SOURCE_VERSION env var; --source-version flag
+  # SYFT_SOURCE_VERSION env var / --source-version flag
   version: ""
-   
-  # options affecting the file source type
+
+  # base directory for scanning, no links will be followed above this directory, and all paths will be 
+  # reported relative to this directory
+  # SYFT_SOURCE_BASE_PATH env var
+  base-path: ''
+
+   # options affecting the file source type
   file:
     # the file digest algorithms to use on the scanned file (options: "md5", "sha1", "sha224", "sha256", "sha384", "sha512")
-    digests: ["sha256"]
+    digests: 
+     - "sha256"
+
+  image:
+     
+    # allows users to specify which image source should be used to generate the sbom
+    # valid values are: registry, docker, podman
+    # SYFT_SOURCE_IMAGE_DEFAULT_PULL_SOURCE env var
+    default-pull-source: ""
+
 
 # options when pulling directly from a registry via the "registry:" or "containerd:" scheme
 registry:
@@ -724,15 +818,15 @@ attest:
 
 log:
   # use structured logging
-  # same as SYFT_LOG_STRUCTURED env var
+  # SYFT_LOG_STRUCTURED env var
   structured: false
 
   # the log level; note: detailed logging suppress the ETUI
-  # same as SYFT_LOG_LEVEL env var
+  # SYFT_LOG_LEVEL env var
   level: "error"
 
   # location to write the log file (default is not to have a log file)
-  # same as SYFT_LOG_FILE env var
+  # SYFT_LOG_FILE env var
   file: ""
 ```
 

Taskfile.yaml

@@ -0,0 +1,486 @@
+
+version: "3"
+vars:
+  OWNER: anchore
+  PROJECT: syft
+
+  # static file dirs
+  TOOL_DIR: .tool
+  TMP_DIR: .tmp
+
+  # used for changelog generation
+  CHANGELOG: CHANGELOG.md
+  NEXT_VERSION: VERSION
+
+  # used for snapshot builds
+  OS:
+    sh: uname -s | tr '[:upper:]' '[:lower:]'
+  ARCH:
+    sh: |
+      [ "$(uname -m)" = "x86_64" ] && echo "amd64_v1" || echo $(uname -m)
+  PROJECT_ROOT:
+    sh: echo $PWD
+  # note: the snapshot dir must be a relative path starting with ./
+  SNAPSHOT_DIR: ./snapshot
+  SNAPSHOT_BIN: "{{ .PROJECT_ROOT }}/{{ .SNAPSHOT_DIR }}/{{ .OS }}-build_{{ .OS }}_{{ .ARCH }}/{{ .PROJECT }}"
+  SNAPSHOT_CMD: "{{ .TOOL_DIR }}/goreleaser release --config {{ .TMP_DIR }}/goreleaser.yaml --clean --snapshot --skip=publish --skip=sign"
+  BUILD_CMD:    "{{ .TOOL_DIR }}/goreleaser build   --config {{ .TMP_DIR }}/goreleaser.yaml --clean --snapshot --single-target"
+  RELEASE_CMD:  "{{ .TOOL_DIR }}/goreleaser release --clean --release-notes {{ .CHANGELOG }}"
+  VERSION:
+    sh: git describe --dirty --always --tags
+
+  # used for install and acceptance testing
+  COMPARE_DIR: ./test/compare
+  COMPARE_TEST_IMAGE: centos:8.2.2004
+
+tasks:
+
+  ## High-level tasks #################################
+
+  default:
+    desc: Run all validation tasks
+    aliases:
+      - pr-validations
+      - validations
+    cmds:
+      - task: static-analysis
+      - task: test
+      - task: install-test
+
+  static-analysis:
+    desc: Run all static analysis tasks
+    cmds:
+      - task: check-go-mod-tidy
+      - task: check-licenses
+      - task: lint
+      - task: check-json-schema-drift
+      - task: check-binary-fixture-size
+
+  test:
+    desc: Run all levels of test
+    cmds:
+      - task: unit
+      - task: integration
+      - task: validate-cyclonedx-schema
+      - task: benchmark
+      - task: test-utils
+      - task: cli
+
+  ## Bootstrap tasks #################################
+
+  binny:
+    internal: true
+    # desc: Get the binny tool
+    generates:
+      - "{{ .TOOL_DIR }}/binny"
+    status:
+      - "test -f {{ .TOOL_DIR }}/binny"
+    cmd: "curl -sSfL https://raw.githubusercontent.com/anchore/binny/main/install.sh | sh -s -- -b .tool"
+    silent: true
+
+  tools:
+    desc: Install all tools needed for CI and local development
+    deps: [binny]
+    aliases:
+      - bootstrap
+    generates:
+      - ".binny.yaml"
+      - "{{ .TOOL_DIR }}/*"
+    status:
+      - "{{ .TOOL_DIR }}/binny check -v"
+    cmd: "{{ .TOOL_DIR }}/binny install -v"
+    silent: true
+
+  update-tools:
+    desc: Update pinned versions of all tools to their latest available versions
+    deps: [binny]
+    generates:
+      - ".binny.yaml"
+      - "{{ .TOOL_DIR }}/*"
+    cmd: "{{ .TOOL_DIR }}/binny update -v"
+    silent: true
+
+  list-tools:
+    desc: List all tools needed for CI and local development
+    deps: [binny]
+    cmd: "{{ .TOOL_DIR }}/binny list"
+    silent: true
+
+  list-tool-updates:
+    desc: List all tools that are not up to date relative to the binny config
+    deps: [binny]
+    cmd: "{{ .TOOL_DIR }}/binny list --updates"
+    silent: true
+
+  tmpdir:
+    silent: true
+    generates:
+      - "{{ .TMP_DIR }}"
+    cmd: "mkdir -p {{ .TMP_DIR }}"
+
+  ## Static analysis tasks #################################
+
+  format:
+    desc: Auto-format all source code
+    deps: [tools]
+    cmds:
+      - gofmt -w -s .
+      - "{{ .TOOL_DIR }}/gosimports -local github.com/anchore -w ."
+      - go mod tidy
+
+  lint-fix:
+    desc: Auto-format all source code + run golangci lint fixers
+    deps: [tools]
+    cmds:
+      - task: format
+      - "{{ .TOOL_DIR }}/golangci-lint run --tests=false --fix"
+
+  lint:
+    desc: Run gofmt + golangci lint checks
+    vars:
+      BAD_FMT_FILES:
+        sh: gofmt -l -s .
+      BAD_FILE_NAMES:
+        sh: "find . | grep -e ':' || true"
+    deps: [tools]
+    cmds:
+      # ensure there are no go fmt differences
+      - cmd: 'test -z "{{ .BAD_FMT_FILES }}" || (echo "files with gofmt issues: [{{ .BAD_FMT_FILES }}]"; exit 1)'
+        silent: true
+      # ensure there are no files with ":" in it (a known back case in the go ecosystem)
+      - cmd: 'test -z "{{ .BAD_FILE_NAMES }}" || (echo "files with bad names: [{{ .BAD_FILE_NAMES }}]"; exit 1)'
+        silent: true
+      # run linting
+      - "{{ .TOOL_DIR }}/golangci-lint run --tests=false"
+
+
+  check-licenses:
+    # desc: Ensure transitive dependencies are compliant with the current license policy
+    deps: [tools]
+    cmd: "{{ .TOOL_DIR }}/bouncer check ./..."
+
+  check-go-mod-tidy:
+    # desc: Ensure go.mod and go.sum are up to date
+    cmds:
+      - cmd: .github/scripts/go-mod-tidy-check.sh && echo "go.mod and go.sum are tidy!"
+        silent: true
+
+  check-json-schema-drift:
+    desc: Ensure there is no drift between the JSON schema and the code
+    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 #################################
+
+  unit:
+    desc: Run unit tests
+    deps:
+      - tmpdir
+      - fixtures
+    vars:
+      TEST_PKGS:
+        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
+    cmds:
+      - "go test -coverprofile {{ .TMP_DIR }}/unit-coverage-details.txt {{ .TEST_PKGS }}"
+      - cmd: ".github/scripts/coverage.py {{ .COVERAGE_THRESHOLD }} {{ .TMP_DIR }}/unit-coverage-details.txt"
+        silent: true
+
+  integration:
+    desc: Run integration tests
+    cmds:
+      - "go test -v ./cmd/syft/internal/test/integration"
+      # exercise most of the CLI with the data race detector
+      - "go run -race cmd/syft/main.go alpine:latest"
+
+  validate-cyclonedx-schema:
+    desc: Run integration tests
+    cmds:
+      - "cd schema/cyclonedx && make"
+
+  cli:
+    desc: Run CLI tests
+    # note: we don't want to regenerate the snapshot unless we have to. In CI it's probable
+    # that the cache being restored with the correct binary will be rebuilt since the timestamps
+    # and local checksums will not line up.
+    deps: [tools, snapshot]
+    sources:
+      - "{{ .SNAPSHOT_BIN }}"
+      - ./test/cli/**
+      - ./**/*.go
+    cmds:
+      - cmd: "echo 'testing binary: {{ .SNAPSHOT_BIN }}'"
+        silent: true
+
+      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found' && false)"
+        silent: true
+
+      - "go test -count=1 -timeout=15m -v ./test/cli"
+    env:
+      SYFT_BINARY_LOCATION: "{{ .SNAPSHOT_BIN }}"
+
+  test-utils:
+    desc: Run tests for pipeline utils
+    sources:
+      - .github/scripts/labeler*.py
+    cmds:
+      - cmd: python .github/scripts/labeler_test.py
+
+
+  ## Benchmark test targets #################################
+
+  benchmark:
+    deps: [tmpdir]
+    sources:
+      - ./**/*.go
+    generates:
+      - "{{ .TMP_DIR }}/benchmark-main.txt"
+    cmds:
+      - "go test -p 1 -run=^Benchmark -bench=. -count=7 -benchmem ./... | tee {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt"
+      - |
+        bash -c "(test -s {{ .TMP_DIR }}/benchmark-main.txt && \
+        {{ .TOOL_DIR }}/benchstat {{ .TMP_DIR }}/benchmark-main.txt {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt || \
+        {{ .TOOL_DIR }}/benchstat {{ .TMP_DIR }}/benchmark-{{ .VERSION }}.txt) \
+        | tee {{ .TMP_DIR }}/benchstat.txt"
+
+  show-benchstat:
+    deps: [benchmark, tmpdir]
+    sources:
+      - "{{ .TMP_DIR }}/benchstat.txt"
+    cmds:
+      - cmd: "cat {{ .TMP_DIR }}/benchstat.txt"
+        silent: true
+
+
+  ## Test-fixture-related targets #################################
+
+  fingerprints:
+    desc: Generate test fixture fingerprints
+    generates:
+      - cmd/syft/internal/test/integration/test-fixtures/cache.fingerprint
+      - syft/file/cataloger/executable/test-fixtures/elf/cache.fingerprint
+      - syft/file/cataloger/executable/test-fixtures/shared-info/cache.fingerprint
+      - syft/pkg/cataloger/binary/test-fixtures/cache.fingerprint
+      - syft/pkg/cataloger/java/test-fixtures/java-builds/cache.fingerprint
+      - syft/pkg/cataloger/golang/test-fixtures/archs/binaries.fingerprint
+      - syft/pkg/cataloger/redhat/test-fixtures/rpms.fingerprint
+      - syft/pkg/cataloger/kernel/test-fixtures/cache.fingerprint
+      - test/install/cache.fingerprint
+      - test/cli/test-fixtures/cache.fingerprint
+    cmds:
+      # for EXECUTABLE unit test fixtures
+      - "cd syft/file/cataloger/executable/test-fixtures/elf && make cache.fingerprint"
+      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make cache.fingerprint"
+      # for IMAGE integration test fixtures
+      - "cd cmd/syft/internal/test/integration/test-fixtures && make cache.fingerprint"
+      # for BINARY unit test fixtures
+      - "cd syft/pkg/cataloger/binary/test-fixtures && make cache.fingerprint"
+      # for JAVA BUILD unit test fixtures
+      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make cache.fingerprint"
+      # for GO BINARY unit test fixtures
+      - "cd syft/pkg/cataloger/golang/test-fixtures/archs && make binaries.fingerprint"
+      # for RPM unit test fixtures
+      - "cd syft/pkg/cataloger/redhat/test-fixtures && make rpms.fingerprint"
+      # for Kernel unit test fixtures
+      - "cd syft/pkg/cataloger/kernel/test-fixtures && make cache.fingerprint"
+      # for INSTALL test fixtures
+      - "cd test/install && make cache.fingerprint"
+      # for CLI test fixtures
+      - "cd test/cli/test-fixtures && make cache.fingerprint"
+
+  fixtures:
+    desc: Generate test fixtures
+    cmds:
+      - "cd syft/file/cataloger/executable/test-fixtures/elf && make"
+      - "cd syft/file/cataloger/executable/test-fixtures/shared-info && make"
+      - "cd syft/pkg/cataloger/java/test-fixtures/java-builds && make"
+      - "cd syft/pkg/cataloger/redhat/test-fixtures && make"
+      - "cd syft/pkg/cataloger/binary/test-fixtures && make"
+
+  show-test-image-cache:
+    silent: true
+    cmds:
+      - "echo '\nDocker daemon cache:'"
+      - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}:{{`{{.Tag}}`}}' | grep stereoscope-fixture- | sort"
+      - "echo '\nTar cache:'"
+      - 'find . -type f -wholename "**/test-fixtures/snapshot/*" | sort'
+
+
+  ## install.sh testing targets #################################
+
+  install-test:
+    cmds:
+      - "cd test/install && make"
+
+  install-test-cache-save:
+    cmds:
+      - "cd test/install && make save"
+
+  install-test-cache-load:
+    cmds:
+      - "cd test/install && make load"
+
+  install-test-ci-mac:
+    cmds:
+      - "cd test/install && make ci-test-mac"
+
+  generate-compare-file:
+    cmd: "go run ./cmd/syft {{ .COMPARE_TEST_IMAGE }} -o json > {{ .COMPARE_DIR }}/test-fixtures/acceptance-{{ .COMPARE_TEST_IMAGE }}.json"
+
+  compare-mac:
+    deps: [tmpdir]
+    cmd: |
+      {{ .COMPARE_DIR }}/mac.sh \
+        {{ .SNAPSHOT_DIR }} \
+        {{ .COMPARE_DIR }} \
+        {{ .COMPARE_TEST_IMAGE }} \
+        {{ .TMP_DIR }}
+
+  compare-linux:
+    cmds:
+      - task: compare-test-deb-package-install
+      - task: compare-test-rpm-package-install
+
+  compare-test-deb-package-install:
+    deps: [tmpdir]
+    cmd: |
+      {{ .COMPARE_DIR }}/deb.sh \
+        {{ .SNAPSHOT_DIR }} \
+        {{ .COMPARE_DIR }} \
+        {{ .COMPARE_TEST_IMAGE }} \
+        {{ .TMP_DIR }}
+
+  compare-test-rpm-package-install:
+    deps: [tmpdir]
+    cmd: |
+      {{ .COMPARE_DIR }}/rpm.sh \
+        {{ .SNAPSHOT_DIR }} \
+        {{ .COMPARE_DIR }} \
+        {{ .COMPARE_TEST_IMAGE }} \
+        {{ .TMP_DIR }}
+
+
+  ## Code and data generation targets #################################
+
+  generate:
+    desc: Add data generation tasks
+    cmds:
+      - task: generate-json-schema
+      - task: generate-license-list
+      - task: generate-cpe-dictionary-index
+
+  generate-json-schema:
+    desc: Generate a new JSON schema
+    cmds:
+      - "cd syft/internal && go generate . && cd jsonschema && go run . && go fmt ../..."
+
+  generate-license-list:
+    desc: Generate an updated license processing code off of the latest available SPDX license list
+    cmds:
+      - "go generate ./internal/spdxlicense/..."
+      - "gofmt -s -w ./internal/spdxlicense"
+
+  generate-cpe-dictionary-index:
+    desc: Generate the CPE index based off of the latest available CPE dictionary
+    dir: "syft/pkg/cataloger/common/cpe/dictionary"
+    cmds:
+      - "go generate"
+
+
+  ## Build-related targets #################################
+
+  build:
+    desc: Build the project
+    deps: [tools, tmpdir]
+    generates:
+      - "{{ .PROJECT }}"
+    cmds:
+      - silent: true
+        cmd: |
+          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
+          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
+
+      - "{{ .BUILD_CMD }}"
+
+  snapshot:
+    desc: Create a snapshot release
+    aliases:
+      - build
+    deps: [tools, tmpdir]
+    sources:
+      - cmd/**/*.go
+      - syft/**/*.go
+      - internal/**/*.go
+    method: checksum
+    generates:
+      - "{{ .SNAPSHOT_BIN }}"
+    cmds:
+      - silent: true
+        cmd: |
+          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
+          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
+
+      - "{{ .SNAPSHOT_CMD }}"
+
+  changelog:
+    desc: Generate a changelog
+    deps: [tools]
+    generates:
+      - "{{ .CHANGELOG }}"
+      - "{{ .NEXT_VERSION }}"
+    cmds:
+      - "{{ .TOOL_DIR }}/chronicle -vv -n --version-file {{ .NEXT_VERSION }} > {{ .CHANGELOG }}"
+      - "{{ .TOOL_DIR }}/glow {{ .CHANGELOG }}"
+
+
+  ## Release targets #################################
+
+  release:
+    desc: Create a release
+    interactive: true
+    deps: [tools]
+    cmds:
+      - cmd: .github/scripts/trigger-release.sh
+        silent: true
+
+
+  ## CI-only targets #################################
+
+  ci-check:
+    # desc: "[CI only] Are you in CI?"
+    cmds:
+      - cmd: .github/scripts/ci-check.sh
+        silent: true
+
+  ci-release:
+    # desc: "[CI only] Create a release"
+    deps: [tools]
+    cmds:
+      - task: ci-check
+      - "{{ .TOOL_DIR }}/chronicle -vvv > CHANGELOG.md"
+      - cmd: "cat CHANGELOG.md"
+        silent: true
+      - "{{ .RELEASE_CMD }}"
+
+
+  ## Cleanup targets #################################
+
+  clean-snapshot:
+    desc: Remove any snapshot builds
+    cmds:
+      - "rm -rf {{ .SNAPSHOT_DIR }}"
+      - "rm -rf {{ .TMP_DIR }}/goreleaser.yaml"
+
+  clean-cache:
+    desc: Remove all docker cache and local image tar cache
+    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"

cmd/syft/cli/cli.go

@@ -1,96 +1,60 @@
 package cli
 
 import (
+	"io"
 	"os"
 
 	cranecmd "github.com/google/go-containerregistry/cmd/crane/cmd"
 	"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, aliases the root command to `syft packages`,
-// and constructs the `syft power-user` command. It is also responsible for
-// organizing flag usage and injecting the application config for each command.
+// Application constructs the `syft packages` command and aliases the root command to `syft packages`.
+// It is also responsible for organizing flag usage and injecting the application config for each command.
 // It also constructs the syft attest command and the syft version command.
 // `RunE` is the earliest that the complete application configuration can be loaded.
 func Application(id clio.Identification) clio.Application {
-	app, _ := create(id)
+	app, _ := create(id, os.Stdout)
 	return app
 }
 
 // Command returns the root command for the syft CLI application. This is useful for embedding the entire syft CLI
 // into an existing application.
 func Command(id clio.Identification) *cobra.Command {
-	_, cmd := create(id)
+	_, cmd := create(id, os.Stdout)
 	return cmd
 }
 
-func create(id clio.Identification) (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(cfg.Log.Quiet)
-				if !cfg.Log.AllowUI(os.Stdin) || cfg.Log.Quiet {
-					return []clio.UI{noUI}, nil
-				}
-
-				return []clio.UI{
-					ui.New(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()
-		})
+func create(id clio.Identification, out io.Writer) (clio.Application, *cobra.Command) {
+	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,
-		commands.PowerUser(app),
+		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),
 		cranecmd.NewCmdAuthLogin(id.Name), // syft login uses the same command as crane
 	)
 
+	// 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/attest.go

@@ -1,258 +0,0 @@
-package commands
-
-import (
-	"fmt"
-	"os"
-	"os/exec"
-	"strings"
-
-	"github.com/spf13/cobra"
-	"github.com/wagoodman/go-partybus"
-	"github.com/wagoodman/go-progress"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/stereoscope/pkg/image"
-	"github.com/anchore/syft/cmd/syft/cli/options"
-	"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/event"
-	"github.com/anchore/syft/syft/event/monitor"
-	"github.com/anchore/syft/syft/formats"
-	"github.com/anchore/syft/syft/formats/github"
-	"github.com/anchore/syft/syft/formats/syftjson"
-	"github.com/anchore/syft/syft/formats/table"
-	"github.com/anchore/syft/syft/formats/template"
-	"github.com/anchore/syft/syft/formats/text"
-	"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
-`
-	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
-	attestHelp       = attestExample + attestSchemeHelp
-)
-
-type attestOptions struct {
-	options.Config       `yaml:",inline" mapstructure:",squash"`
-	options.SingleOutput `yaml:",inline" mapstructure:",squash"`
-	options.UpdateCheck  `yaml:",inline" mapstructure:",squash"`
-	options.Catalog      `yaml:",inline" mapstructure:",squash"`
-	options.Attest       `yaml:",inline" mapstructure:",squash"`
-}
-
-func Attest(app clio.Application) *cobra.Command {
-	id := app.ID()
-
-	var allowableOutputs []string
-	for _, f := range formats.AllIDs() {
-		switch f {
-		case table.ID, text.ID, github.ID, template.ID:
-			continue
-		}
-		allowableOutputs = append(allowableOutputs, f.String())
-	}
-
-	opts := &attestOptions{
-		UpdateCheck: options.DefaultUpdateCheck(),
-		SingleOutput: options.SingleOutput{
-			AllowableOptions: allowableOutputs,
-			Output:           syftjson.ID.String(),
-		},
-		Catalog: options.DefaultCatalog(),
-	}
-
-	return app.SetupCommand(&cobra.Command{
-		Use:   "attest --output [FORMAT] <IMAGE>",
-		Short: "Generate an SBOM as an attestation for the given [SOURCE] container image",
-		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from a container image as the predicate of an in-toto attestation that will be uploaded to the image registry",
-		Example: internal.Tprintf(attestHelp, map[string]interface{}{
-			"appName": id.Name,
-			"command": "attest",
-		}),
-		Args:    validatePackagesArgs,
-		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(cmd *cobra.Command, args []string) error {
-			return runAttest(id, opts, args[0])
-		},
-	}, opts)
-}
-
-//nolint:funlen
-func runAttest(id clio.Identification, opts *attestOptions, userInput string) error {
-	_, err := exec.LookPath("cosign")
-	if err != nil {
-		// when cosign is not installed the error will be rendered like so:
-		// 2023/06/30 08:31:52 error during command execution: 'syft attest' requires cosign to be installed: exec: "cosign": executable file not found in $PATH
-		return fmt.Errorf("'syft attest' requires cosign to be installed: %w", err)
-	}
-
-	s, err := buildSBOM(id, &opts.Catalog, userInput)
-	if err != nil {
-		return fmt.Errorf("unable to build SBOM: %w", err)
-	}
-
-	o := opts.Output
-
-	f, err := os.CreateTemp("", o)
-	if err != nil {
-		return fmt.Errorf("unable to create temp file: %w", err)
-	}
-	defer os.Remove(f.Name())
-
-	writer, err := opts.SBOMWriter(f.Name())
-	if err != nil {
-		return fmt.Errorf("unable to create SBOM writer: %w", err)
-	}
-
-	if err := writer.Write(*s); err != nil {
-		return fmt.Errorf("unable to write SBOM to temp file: %w", err)
-	}
-
-	// TODO: what other validation here besides binary name?
-	cmd := "cosign"
-	if !commandExists(cmd) {
-		return fmt.Errorf("unable to find cosign in PATH; make sure you have it installed")
-	}
-
-	// Select Cosign predicate type based on defined output type
-	// As orientation, check: https://github.com/sigstore/cosign/blob/main/pkg/cosign/attestation/attestation.go
-	var predicateType string
-	switch strings.ToLower(o) {
-	case "cyclonedx-json":
-		predicateType = "cyclonedx"
-	case "spdx-tag-value", "spdx-tv":
-		predicateType = "spdx"
-	case "spdx-json", "json":
-		predicateType = "spdxjson"
-	default:
-		predicateType = "custom"
-	}
-
-	args := []string{"attest", userInput, "--predicate", f.Name(), "--type", predicateType}
-	if opts.Attest.Key != "" {
-		args = append(args, "--key", opts.Attest.Key.String())
-	}
-
-	execCmd := exec.Command(cmd, args...)
-	execCmd.Env = os.Environ()
-	if opts.Attest.Key != "" {
-		execCmd.Env = append(execCmd.Env, fmt.Sprintf("COSIGN_PASSWORD=%s", opts.Attest.Password))
-	} else {
-		// no key provided, use cosign's keyless mode
-		execCmd.Env = append(execCmd.Env, "COSIGN_EXPERIMENTAL=1")
-	}
-
-	log.WithFields("cmd", strings.Join(execCmd.Args, " ")).Trace("creating attestation")
-
-	// bus adapter for ui to hook into stdout via an os pipe
-	r, w, err := os.Pipe()
-	if err != nil {
-		return fmt.Errorf("unable to create os pipe: %w", err)
-	}
-	defer w.Close()
-
-	mon := progress.NewManual(-1)
-
-	bus.Publish(
-		partybus.Event{
-			Type: event.AttestationStarted,
-			Source: monitor.GenericTask{
-				Title: monitor.Title{
-					Default:      "Create attestation",
-					WhileRunning: "Creating attestation",
-					OnSuccess:    "Created attestation",
-				},
-				Context: "cosign",
-			},
-			Value: &monitor.ShellProgress{
-				Reader:       r,
-				Progressable: mon,
-			},
-		},
-	)
-
-	execCmd.Stdout = w
-	execCmd.Stderr = w
-
-	// attest the SBOM
-	err = execCmd.Run()
-	if err != nil {
-		mon.SetError(err)
-		return fmt.Errorf("unable to attest SBOM: %w", err)
-	}
-
-	mon.SetCompleted()
-
-	return nil
-}
-
-func buildSBOM(id clio.Identification, opts *options.Catalog, userInput string) (*sbom.SBOM, error) {
-	cfg := source.DetectConfig{
-		DefaultImageSource: opts.DefaultImagePullSource,
-	}
-	detection, err := source.Detect(userInput, cfg)
-	if err != nil {
-		return nil, fmt.Errorf("could not deteremine source: %w", err)
-	}
-
-	if detection.IsContainerImage() {
-		return nil, fmt.Errorf("attestations are only supported for oci images at this time")
-	}
-
-	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 src != nil {
-		defer src.Close()
-	}
-	if err != nil {
-		return nil, fmt.Errorf("failed to construct source from user input %q: %w", userInput, err)
-	}
-
-	s, err := generateSBOM(id, src, opts)
-	if err != nil {
-		return nil, err
-	}
-
-	if s == nil {
-		return nil, fmt.Errorf("no SBOM produced for %q", userInput)
-	}
-
-	return s, nil
-}
-
-func commandExists(cmd string) bool {
-	_, err := exec.LookPath(cmd)
-	return err == nil
-}

cmd/syft/cli/commands/packages.go

@@ -1,253 +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/internal"
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/formats/template"
-	"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.MultiOutput `yaml:",inline" mapstructure:",squash"`
-	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
-	options.Catalog     `yaml:",inline" mapstructure:",squash"`
-}
-
-func defaultPackagesOptions() *packagesOptions {
-	return &packagesOptions{
-		MultiOutput: 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 {
-			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 {
-	err := validatePackageOutputOptions(&opts.MultiOutput)
-	if err != nil {
-		return err
-	}
-
-	writer, err := opts.SBOMWriter()
-	if err != nil {
-		return err
-	}
-
-	detection, err := source.Detect(
-		userInput,
-		source.DetectConfig{
-			DefaultImageSource: opts.DefaultImagePullSource,
-		},
-	)
-	if err != nil {
-		return fmt.Errorf("could not deteremine source: %w", err)
-	}
-
-	var platform *image.Platform
-
-	if opts.Platform != "" {
-		platform, err = image.NewPlatform(opts.Platform)
-		if err != nil {
-			return fmt.Errorf("invalid platform: %w", err)
-		}
-	}
-
-	hashers, err := file.Hashers(opts.Source.File.Digests...)
-	if err != nil {
-		return 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 {
-		return fmt.Errorf("failed to construct source from user input %q: %w", userInput, 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 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
-}
-
-func validatePackageOutputOptions(cfg *options.MultiOutput) error {
-	var usesTemplateOutput bool
-	for _, o := range cfg.Outputs {
-		if o == template.ID.String() {
-			usesTemplateOutput = true
-			break
-		}
-	}
-
-	if usesTemplateOutput && cfg.OutputTemplatePath == "" {
-		return fmt.Errorf(`must specify path to template file when using "template" output format`)
-	}
-
-	return nil
-}

cmd/syft/cli/commands/poweruser.go

@@ -1,154 +0,0 @@
-package commands
-
-import (
-	"fmt"
-	"os"
-
-	"github.com/gookit/color"
-	"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/internal"
-	"github.com/anchore/syft/syft/artifact"
-	"github.com/anchore/syft/syft/formats/syftjson"
-	"github.com/anchore/syft/syft/sbom"
-	"github.com/anchore/syft/syft/source"
-)
-
-const powerUserExample = `  {{.appName}} {{.command}} <image>
-  DEPRECATED - THIS COMMAND WILL BE REMOVED in v1.0.0
-  Template outputs are not supported.
-  All behavior is controlled via application configuration and environment variables (see https://github.com/anchore/syft#configuration)
-`
-
-type powerUserOptions struct {
-	options.Config      `yaml:",inline" mapstructure:",squash"`
-	options.OutputFile  `yaml:",inline" mapstructure:",squash"`
-	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
-	options.Catalog     `yaml:",inline" mapstructure:",squash"`
-}
-
-func PowerUser(app clio.Application) *cobra.Command {
-	id := app.ID()
-
-	pkgs := options.DefaultCatalog()
-	pkgs.Secrets.Cataloger.Enabled = true
-	pkgs.FileMetadata.Cataloger.Enabled = true
-	pkgs.FileContents.Cataloger.Enabled = true
-	pkgs.FileClassification.Cataloger.Enabled = true
-	opts := &powerUserOptions{
-		Catalog: pkgs,
-	}
-
-	return app.SetupCommand(&cobra.Command{
-		Use:   "power-user [IMAGE]",
-		Short: "Run bulk operations on container images",
-		Example: internal.Tprintf(powerUserExample, map[string]interface{}{
-			"appName": id.Name,
-			"command": "power-user",
-		}),
-		Args:    validatePackagesArgs,
-		Hidden:  true,
-		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(cmd *cobra.Command, args []string) error {
-			return runPowerUser(id, opts, args[0])
-		},
-	}, opts)
-}
-
-//nolint:funlen
-func runPowerUser(id clio.Identification, opts *powerUserOptions, userInput string) error {
-	writer, err := opts.SBOMWriter(syftjson.Format())
-	if err != nil {
-		return err
-	}
-	defer func() {
-		// inform user at end of run that command will be removed
-		deprecated := color.Style{color.Red, color.OpBold}.Sprint("DEPRECATED: This command will be removed in v1.0.0")
-		fmt.Fprintln(os.Stderr, deprecated)
-	}()
-
-	tasks, err := eventloop.Tasks(&opts.Catalog)
-	if err != nil {
-		return err
-	}
-
-	detection, err := source.Detect(
-		userInput,
-		source.DetectConfig{
-			DefaultImageSource: opts.DefaultImagePullSource,
-		},
-	)
-	if err != nil {
-		return fmt.Errorf("could not deteremine source: %w", err)
-	}
-
-	var platform *image.Platform
-
-	if opts.Platform != "" {
-		platform, err = image.NewPlatform(opts.Platform)
-		if err != nil {
-			return fmt.Errorf("invalid platform: %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: nil,
-			BasePath:         opts.BasePath,
-		},
-	)
-
-	if src != nil {
-		defer src.Close()
-	}
-	if err != nil {
-		return fmt.Errorf("failed to construct source from user input %q: %w", userInput, err)
-	}
-
-	s := sbom.SBOM{
-		Source: src.Describe(),
-		Descriptor: sbom.Descriptor{
-			Name:          id.Name,
-			Version:       id.Version,
-			Configuration: opts,
-		},
-	}
-
-	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)
-			errs = multierror.Append(errs, err)
-		}(task)
-	}
-
-	if errs != nil {
-		return errs
-	}
-
-	s.Relationships = append(s.Relationships, mergeRelationships(relationships...)...)
-
-	if err := writer.Write(s); err != nil {
-		return fmt.Errorf("failed to write sbom: %w", err)
-	}
-
-	return nil
-}

cmd/syft/cli/eventloop/tasks.go

@@ -1,185 +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/file/cataloger/secrets"
-	"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,
-		generateCatalogSecretsTask,
-		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 generateCatalogSecretsTask(opts *options.Catalog) (Task, error) {
-	if !opts.Secrets.Cataloger.Enabled {
-		return nil, nil
-	}
-
-	patterns, err := secrets.GenerateSearchPatterns(secrets.DefaultSecretsPatterns, opts.Secrets.AdditionalPatterns, opts.Secrets.ExcludePatternNames)
-	if err != nil {
-		return nil, err
-	}
-
-	secretsCataloger, err := secrets.NewCataloger(patterns, opts.Secrets.RevealValues, opts.Secrets.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.Secrets.Cataloger.GetScope())
-		if err != nil {
-			return nil, err
-		}
-
-		result, err := secretsCataloger.Catalog(resolver)
-		if err != nil {
-			return nil, err
-		}
-		results.Secrets = 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

@@ -1,168 +0,0 @@
-package options
-
-import (
-	"fmt"
-	"sort"
-	"strings"
-
-	"github.com/iancoleman/strcase"
-	"github.com/mitchellh/go-homedir"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/fangs"
-	"github.com/anchore/syft/internal"
-	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/pkg/cataloger"
-	golangCataloger "github.com/anchore/syft/syft/pkg/cataloger/golang"
-	"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"`
-	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"`
-	FileClassification              fileClassification `yaml:"file-classification" json:"file-classification" mapstructure:"file-classification"`
-	FileContents                    fileContents       `yaml:"file-contents" json:"file-contents" mapstructure:"file-contents"`
-	Secrets                         secrets            `yaml:"secrets" json:"secrets" mapstructure:"secrets"`
-	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(),
-		FileClassification:              defaultFileClassification(),
-		FileContents:                    defaultFileContents(),
-		Secrets:                         defaultSecrets(),
-		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.NewGoCatalogerOpts().
-			WithSearchLocalModCacheLicenses(cfg.Golang.SearchLocalModCacheLicenses).
-			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
-			WithSearchRemoteLicenses(cfg.Golang.SearchRemoteLicenses).
-			WithProxy(cfg.Golang.Proxy).
-			WithNoProxy(cfg.Golang.NoProxy),
-		LinuxKernel: kernel.LinuxCatalogerConfig{
-			CatalogModules: cfg.LinuxKernel.CatalogModules,
-		},
-		Python: pythonCataloger.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
-		ExcludeBinaryOverlapByOwnership: cfg.ExcludeBinaryOverlapByOwnership,
-	}
-}
-
-var validDefaultSourceValues = []string{"registry", "docker", "podman", ""}
-
-func checkDefaultSourceValues(source string) error {
-	validValues := internal.NewStringSet(validDefaultSourceValues...)
-	if !validValues.Contains(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_classification.go

@@ -1,17 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/syft/source"
-)
-
-type fileClassification struct {
-	Cataloger scope `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
-}
-
-func defaultFileClassification() fileClassification {
-	return fileClassification{
-		Cataloger: scope{
-			Scope: source.SquashedScope.String(),
-		},
-	}
-}

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/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/output.go

@@ -1,100 +0,0 @@
-package options
-
-import (
-	"fmt"
-	"slices"
-
-	"github.com/anchore/clio"
-	"github.com/anchore/fangs"
-	"github.com/anchore/syft/syft/formats"
-	"github.com/anchore/syft/syft/formats/table"
-	"github.com/anchore/syft/syft/formats/template"
-	"github.com/anchore/syft/syft/sbom"
-)
-
-// MultiOutput has the standard output options syft accepts: multiple -o, --file, --template
-type MultiOutput struct {
-	Outputs            []string `yaml:"output" json:"output" mapstructure:"output"` // -o, the format to use for output
-	OutputFile         `yaml:",inline" json:"" mapstructure:",squash"`
-	OutputTemplatePath string `yaml:"output-template-path" json:"output-template-path" mapstructure:"output-template-path"` // -t template file to use for output
-}
-
-var _ interface {
-	clio.FlagAdder
-} = (*MultiOutput)(nil)
-
-func DefaultOutput() MultiOutput {
-	return MultiOutput{
-		Outputs: []string{string(table.ID)},
-	}
-}
-
-func (o *MultiOutput) AddFlags(flags clio.FlagSet) {
-	flags.StringArrayVarP(&o.Outputs, "output", "o",
-		fmt.Sprintf("report output format (<format>=<file> to output to a file), formats=%v", formats.AllIDs()))
-
-	flags.StringVarP(&o.OutputTemplatePath, "template", "t",
-		"specify the path to a Go template file")
-}
-
-func (o *MultiOutput) SBOMWriter() (sbom.Writer, error) {
-	return makeSBOMWriter(o.Outputs, o.File, o.OutputTemplatePath)
-}
-
-// SingleOutput allows only 1 output to be specified, with a user able to set what options are allowed by setting AllowableOptions
-type SingleOutput struct {
-	AllowableOptions   []string `yaml:"-" json:"-" mapstructure:"-"`
-	Output             string   `yaml:"output" json:"output" mapstructure:"output"`
-	OutputTemplatePath string   `yaml:"output-template-path" json:"output-template-path" mapstructure:"output-template-path"` // -t template file to use for output
-}
-
-var _ clio.FlagAdder = (*SingleOutput)(nil)
-
-func (o *SingleOutput) AddFlags(flags clio.FlagSet) {
-	flags.StringVarP(&o.Output, "output", "o",
-		fmt.Sprintf("report output format, options=%v", o.AllowableOptions))
-
-	if slices.Contains(o.AllowableOptions, template.ID.String()) {
-		flags.StringVarP(&o.OutputTemplatePath, "template", "t",
-			"specify the path to a Go template file")
-	}
-}
-
-func (o *SingleOutput) SBOMWriter(file string) (sbom.Writer, error) {
-	return makeSBOMWriter([]string{o.Output}, file, o.OutputTemplatePath)
-}
-
-// Deprecated: OutputFile is only the --file argument
-type OutputFile struct {
-	File string `yaml:"file" json:"file" mapstructure:"file"` // --file, the file to write report output to
-}
-
-var _ interface {
-	clio.FlagAdder
-	clio.PostLoader
-} = (*OutputFile)(nil)
-
-func (o *OutputFile) AddFlags(flags clio.FlagSet) {
-	flags.StringVarP(&o.File, "file", "",
-		"file to write the default report output to (default is STDOUT)")
-
-	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
-		flagSet := pfp.PFlagSet()
-		flagSet.Lookup("file").Deprecated = "use: output"
-	}
-}
-
-func (o *OutputFile) PostLoad() error {
-	if o.File != "" {
-		file, err := expandFilePath(o.File)
-		if err != nil {
-			return err
-		}
-		o.File = file
-	}
-	return nil
-}
-
-func (o *OutputFile) SBOMWriter(f sbom.Format) (sbom.Writer, error) {
-	return makeSBOMWriterForFormat(f, o.File)
-}

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/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/secrets.go

@@ -1,23 +0,0 @@
-package options
-
-import (
-	"github.com/anchore/syft/internal/file"
-	"github.com/anchore/syft/syft/source"
-)
-
-type secrets struct {
-	Cataloger           scope             `yaml:"cataloger" json:"cataloger" mapstructure:"cataloger"`
-	AdditionalPatterns  map[string]string `yaml:"additional-patterns" json:"additional-patterns" mapstructure:"additional-patterns"`
-	ExcludePatternNames []string          `yaml:"exclude-pattern-names" json:"exclude-pattern-names" mapstructure:"exclude-pattern-names"`
-	RevealValues        bool              `yaml:"reveal-values" json:"reveal-values" mapstructure:"reveal-values"`
-	SkipFilesAboveSize  int64             `yaml:"skip-files-above-size" json:"skip-files-above-size" mapstructure:"skip-files-above-size"`
-}
-
-func defaultSecrets() secrets {
-	return secrets{
-		Cataloger: scope{
-			Scope: source.AllLayersScope.String(),
-		},
-		SkipFilesAboveSize: 1 * file.MB,
-	}
-}

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/handle_secrets_cataloger.go

@@ -1,57 +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/file/cataloger/secrets"
-)
-
-var _ progress.StagedProgressable = (*secretsCatalogerProgressAdapter)(nil)
-
-// Deprecated: will be removed in syft 1.0
-type secretsCatalogerProgressAdapter struct {
-	*secrets.Monitor
-}
-
-// Deprecated: will be removed in syft 1.0
-func newSecretsCatalogerProgressAdapter(monitor *secrets.Monitor) secretsCatalogerProgressAdapter {
-	return secretsCatalogerProgressAdapter{
-		Monitor: monitor,
-	}
-}
-
-func (s secretsCatalogerProgressAdapter) Stage() string {
-	return fmt.Sprintf("%d secrets", s.Monitor.SecretsDiscovered.Current())
-}
-
-// Deprecated: will be removed in syft 1.0
-func (m *Handler) handleSecretsCatalogerStarted(e partybus.Event) []tea.Model {
-	mon, err := syftEventParsers.ParseSecretsCatalogingStarted(e)
-	if err != nil {
-		log.WithFields("error", err).Warn("unable to parse event")
-		return nil
-	}
-
-	tsk := m.newTaskProgress(
-		taskprogress.Title{
-			Default: "Catalog secrets",
-			Running: "Cataloging secrets",
-			Success: "Cataloged secrets",
-		},
-
-		taskprogress.WithStagedProgressable(
-			newSecretsCatalogerProgressAdapter(mon),
-		),
-	)
-
-	tsk.HideStageOnSuccess = false
-
-	return []tea.Model{tsk}
-}

cmd/syft/cli/ui/handle_secrets_cataloger_test.go

@@ -1,96 +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/file/cataloger/secrets"
-)
-
-func TestHandler_handleSecretsCatalogerStarted(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 {
-				stage := &progress.Stage{
-					Current: "current",
-				}
-				secretsDiscovered := progress.NewManual(-1)
-				secretsDiscovered.Set(64)
-				prog := progress.NewManual(72)
-				prog.Set(50)
-
-				return partybus.Event{
-					Type:   syftEvent.SecretsCatalogerStarted,
-					Source: secretsDiscovered,
-					Value: secrets.Monitor{
-						Stager:            progress.Stager(stage),
-						SecretsDiscovered: secretsDiscovered,
-						Progressable:      prog,
-					},
-				}
-			},
-		},
-		{
-			name: "cataloging complete",
-			eventFn: func(t *testing.T) partybus.Event {
-				stage := &progress.Stage{
-					Current: "current",
-				}
-				secretsDiscovered := progress.NewManual(-1)
-				secretsDiscovered.Set(64)
-				prog := progress.NewManual(72)
-				prog.Set(72)
-				prog.SetCompleted()
-
-				return partybus.Event{
-					Type:   syftEvent.SecretsCatalogerStarted,
-					Source: secretsDiscovered,
-					Value: secrets.Monitor{
-						Stager:            progress.Stager(stage),
-						SecretsDiscovered: secretsDiscovered,
-						Progressable:      prog,
-					},
-				}
-			},
-		},
-	}
-	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/handler.go

@@ -29,6 +29,8 @@ type Handler struct {
 	Config     HandlerConfig
 
 	bubbly.EventHandler
+
+	onNewCatalogerTask *sync.Once
 }
 
 func DefaultHandlerConfig() HandlerConfig {
@@ -41,31 +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,
-
-		// deprecated
-		syftEvent.SecretsCatalogerStarted: h.handleSecretsCatalogerStarted,
+		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

@@ -0,0 +1,283 @@
+package commands
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"strings"
+
+	"github.com/spf13/cobra"
+	"github.com/wagoodman/go-partybus"
+	"github.com/wagoodman/go-progress"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/stereoscope"
+	"github.com/anchore/syft/cmd/syft/internal/options"
+	"github.com/anchore/syft/cmd/syft/internal/ui"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/event/monitor"
+	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/cyclonedxjson"
+	"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/sbom"
+)
+
+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
+`
+	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
+	attestHelp       = attestExample + attestSchemeHelp
+	cosignBinName    = "cosign"
+)
+
+type attestOptions 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"`
+	Attest              options.Attest `yaml:"attest" mapstructure:"attest"`
+}
+
+func Attest(app clio.Application) *cobra.Command {
+	id := app.ID()
+
+	opts := defaultAttestOptions()
+
+	// template format explicitly not allowed
+	opts.Format.Template.Enabled = false
+
+	return app.SetupCommand(&cobra.Command{
+		Use:   "attest --output [FORMAT] <IMAGE>",
+		Short: "Generate an SBOM as an attestation for the given [SOURCE] container image",
+		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from a container image as the predicate of an in-toto attestation that will be uploaded to the image registry",
+		Example: internal.Tprintf(attestHelp, map[string]interface{}{
+			"appName": id.Name,
+			"command": "attest",
+		}),
+		Args:    validateScanArgs,
+		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
+		RunE: func(cmd *cobra.Command, args []string) error {
+			restoreStdout := ui.CaptureStdoutToTraceLog()
+			defer restoreStdout()
+
+			return runAttest(cmd.Context(), id, &opts, args[0])
+		},
+	}, &opts)
+}
+
+func defaultAttestOptions() attestOptions {
+	return attestOptions{
+		Output:      defaultAttestOutputOptions(),
+		UpdateCheck: options.DefaultUpdateCheck(),
+		Catalog:     options.DefaultCatalog(),
+	}
+}
+
+func defaultAttestOutputOptions() options.Output {
+	return options.Output{
+		AllowMultipleOutputs: false,
+		AllowToFile:          false,
+		AllowableOptions: []string{
+			string(syftjson.ID),
+			string(cyclonedxjson.ID),
+			string(spdxjson.ID),
+			string(spdxtagvalue.ID),
+		},
+		Outputs: []string{syftjson.ID.String()},
+		OutputFile: options.OutputFile{ // nolint:staticcheck
+			Enabled: false, // explicitly not allowed
+		},
+		Format: options.DefaultFormat(),
+	}
+}
+
+//nolint:funlen
+func runAttest(ctx context.Context, id clio.Identification, opts *attestOptions, userInput string) error {
+	// TODO: what other validation here besides binary name?
+	if !commandExists(cosignBinName) {
+		return fmt.Errorf("'syft attest' requires cosign to be installed, however it does not appear to be on PATH")
+	}
+
+	// this is the file that will contain the SBOM being attested
+	f, err := os.CreateTemp("", "syft-attest-")
+	if err != nil {
+		return fmt.Errorf("unable to create temp file: %w", err)
+	}
+	defer os.Remove(f.Name())
+
+	s, err := generateSBOMForAttestation(ctx, id, &opts.Catalog, userInput)
+	if err != nil {
+		return fmt.Errorf("unable to build SBOM: %w", err)
+	}
+
+	if err = writeSBOMToFormattedFile(s, f, opts); err != nil {
+		return fmt.Errorf("unable to write SBOM to file: %w", err)
+	}
+
+	if err = createAttestation(f.Name(), opts, userInput); err != nil {
+		return err
+	}
+
+	bus.Notify("Attestation has been created, please check your registry for the output or use the cosign command:")
+	bus.Notify(fmt.Sprintf("cosign download attestation %s", userInput))
+	return nil
+}
+
+func writeSBOMToFormattedFile(s *sbom.SBOM, sbomFile io.Writer, opts *attestOptions) error {
+	if sbomFile == nil {
+		return fmt.Errorf("no output file provided")
+	}
+
+	encs, err := opts.Format.Encoders()
+	if err != nil {
+		return fmt.Errorf("unable to create encoders: %w", err)
+	}
+
+	encoders := format.NewEncoderCollection(encs...)
+	encoder := encoders.GetByString(opts.Outputs[0])
+	if encoder == nil {
+		return fmt.Errorf("unable to find encoder for %q", opts.Outputs[0])
+	}
+
+	if err = encoder.Encode(sbomFile, *s); err != nil {
+		return fmt.Errorf("unable to encode SBOM: %w", err)
+	}
+
+	return nil
+}
+
+func createAttestation(sbomFilepath string, opts *attestOptions, userInput string) error {
+	execCmd, err := attestCommand(sbomFilepath, opts, userInput)
+	if err != nil {
+		return fmt.Errorf("unable to craft attest command: %w", err)
+	}
+
+	log.WithFields("cmd", strings.Join(execCmd.Args, " ")).Trace("creating attestation")
+
+	// bus adapter for ui to hook into stdout via an os pipe
+	r, w, err := os.Pipe()
+	if err != nil {
+		return fmt.Errorf("unable to create os pipe: %w", err)
+	}
+	defer w.Close()
+
+	mon := progress.NewManual(-1)
+
+	bus.Publish(
+		partybus.Event{
+			Type: event.AttestationStarted,
+			Source: monitor.GenericTask{
+				Title: monitor.Title{
+					Default:      "Create attestation",
+					WhileRunning: "Creating attestation",
+					OnSuccess:    "Created attestation",
+				},
+				Context: "cosign",
+			},
+			Value: &monitor.ShellProgress{
+				Reader:       r,
+				Progressable: mon,
+			},
+		},
+	)
+
+	execCmd.Stdout = w
+	execCmd.Stderr = w
+
+	// attest the SBOM
+	err = execCmd.Run()
+	if err != nil {
+		mon.SetError(err)
+		return fmt.Errorf("unable to attest SBOM: %w", err)
+	}
+
+	mon.SetCompleted()
+	return nil
+}
+
+func attestCommand(sbomFilepath string, opts *attestOptions, userInput string) (*exec.Cmd, error) {
+	outputNames := opts.OutputNameSet()
+	var outputName string
+	switch outputNames.Size() {
+	case 0:
+		return nil, fmt.Errorf("no output format specified")
+	case 1:
+		outputName = outputNames.List()[0]
+	default:
+		return nil, fmt.Errorf("multiple output formats specified: %s", strings.Join(outputNames.List(), ", "))
+	}
+
+	args := []string{"attest", userInput, "--predicate", sbomFilepath, "--type", predicateType(outputName), "-y"}
+	if opts.Attest.Key != "" {
+		args = append(args, "--key", opts.Attest.Key.String())
+	}
+
+	execCmd := exec.Command(cosignBinName, args...)
+	execCmd.Env = os.Environ()
+	if opts.Attest.Key != "" {
+		execCmd.Env = append(execCmd.Env, fmt.Sprintf("COSIGN_PASSWORD=%s", opts.Attest.Password))
+	} else {
+		// no key provided, use cosign's keyless mode
+		execCmd.Env = append(execCmd.Env, "COSIGN_EXPERIMENTAL=1")
+	}
+
+	return execCmd, nil
+}
+
+func predicateType(outputName string) string {
+	// 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":
+		return "cyclonedx"
+	case "spdx-tag-value", "spdx-tv":
+		return "spdx"
+	case "spdx-json", "json":
+		return "spdxjson"
+	default:
+		return "custom"
+	}
+}
+
+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
+	}
+
+	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)
+	if err != nil {
+		return nil, err
+	}
+
+	if s == nil {
+		return nil, fmt.Errorf("no SBOM produced for %q", userInput)
+	}
+
+	return s, nil
+}
+
+func commandExists(cmd string) bool {
+	_, err := exec.LookPath(cmd)
+	return err == nil
+}

cmd/syft/internal/commands/attest_test.go

@@ -0,0 +1,331 @@
+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/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"
+)
+
+func Test_writeSBOMToFormattedFile(t *testing.T) {
+	type args struct {
+		s    *sbom.SBOM
+		opts *attestOptions
+	}
+	tests := []struct {
+		name         string
+		args         args
+		wantSbomFile string
+		wantErr      bool
+	}{
+		{
+			name: "go case",
+			args: args{
+				opts: &attestOptions{
+					Output: func() options.Output {
+						def := defaultAttestOutputOptions()
+						def.Outputs = []string{"syft-json"}
+						return def
+					}(),
+				},
+				s: &sbom.SBOM{
+					Artifacts:     sbom.Artifacts{},
+					Relationships: nil,
+					Source: source.Description{
+						ID:      "source-id",
+						Name:    "source-name",
+						Version: "source-version",
+					},
+					Descriptor: sbom.Descriptor{
+						Name:    "syft-test",
+						Version: "non-version",
+					},
+				},
+			},
+			wantSbomFile: `{
+ "artifacts": [],
+ "artifactRelationships": [],
+ "source": {
+  "id": "source-id",
+  "name": "source-name",
+  "version": "source-version",
+  "type": "",
+  "metadata": null
+ },
+ "distro": {},
+ "descriptor": {
+  "name": "syft-test",
+  "version": "non-version"
+ },
+ "schema": {}
+}`,
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			sbomFile := &bytes.Buffer{}
+
+			err := writeSBOMToFormattedFile(tt.args.s, sbomFile, tt.args.opts)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("writeSBOMToFormattedFile() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+
+			// redact the schema block
+			re := regexp.MustCompile(`(?s)"schema":\W*\{.*?},?`)
+			subject := re.ReplaceAllString(sbomFile.String(), `"schema":{}`)
+
+			assert.JSONEq(t, tt.wantSbomFile, subject)
+		})
+	}
+}
+
+func Test_attestCommand(t *testing.T) {
+	cmdPrefix := cosignBinName
+	lp, err := exec.LookPath(cosignBinName)
+	if err == nil {
+		cmdPrefix = lp
+	}
+
+	fullCmd := func(args string) string {
+		return fmt.Sprintf("%s %s", cmdPrefix, args)
+	}
+
+	type args struct {
+		sbomFilepath string
+		opts         attestOptions
+		userInput    string
+	}
+	tests := []struct {
+		name        string
+		args        args
+		wantCmd     string
+		wantEnvVars map[string]string
+		notEnvVars  []string
+		wantErr     require.ErrorAssertionFunc
+	}{
+		{
+			name: "with key and password",
+			args: args{
+				userInput:    "myimage",
+				sbomFilepath: "/tmp/sbom-filepath.json",
+				opts: func() attestOptions {
+					def := defaultAttestOptions()
+					def.Outputs = []string{"syft-json"}
+					def.Attest.Key = "key"
+					def.Attest.Password = "password"
+					return def
+				}(),
+			},
+			wantCmd: fullCmd("attest myimage --predicate /tmp/sbom-filepath.json --type custom -y --key key"),
+			wantEnvVars: map[string]string{
+				"COSIGN_PASSWORD": "password",
+			},
+			notEnvVars: []string{
+				"COSIGN_EXPERIMENTAL", // only for keyless
+			},
+		},
+		{
+			name: "keyless",
+			args: args{
+				userInput:    "myimage",
+				sbomFilepath: "/tmp/sbom-filepath.json",
+				opts: func() attestOptions {
+					def := defaultAttestOptions()
+					def.Outputs = []string{"syft-json"}
+					return def
+				}(),
+			},
+			wantCmd: fullCmd("attest myimage --predicate /tmp/sbom-filepath.json --type custom -y"),
+			wantEnvVars: map[string]string{
+				"COSIGN_EXPERIMENTAL": "1",
+			},
+			notEnvVars: []string{
+				"COSIGN_PASSWORD",
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = require.NoError
+			}
+
+			got, err := attestCommand(tt.args.sbomFilepath, &tt.args.opts, tt.args.userInput)
+			tt.wantErr(t, err)
+			if err != nil {
+				return
+			}
+
+			require.NotNil(t, got)
+			assert.Equal(t, tt.wantCmd, got.String())
+
+			gotEnv := strset.New(got.Env...)
+
+			for k, v := range tt.wantEnvVars {
+				assert.True(t, gotEnv.Has(fmt.Sprintf("%s=%s", k, v)))
+			}
+
+			for _, k := range tt.notEnvVars {
+				for _, env := range got.Env {
+					fields := strings.Split(env, "=")
+					if fields[0] == k {
+						t.Errorf("attestCommand() unexpected environment variable %s", k)
+					}
+				}
+			}
+		})
+	}
+}
+
+func Test_predicateType(t *testing.T) {
+	tests := []struct {
+		name string
+		want string
+	}{
+		{
+			name: "cyclonedx-json",
+			want: "cyclonedx",
+		},
+		{
+			name: "spdx-tag-value",
+			want: "spdx",
+		},
+		{
+			name: "spdx-tv",
+			want: "spdx",
+		},
+		{
+			name: "spdx-json",
+			want: "spdxjson",
+		},
+		{
+			name: "json",
+			want: "spdxjson",
+		},
+		{
+			name: "syft-json",
+			want: "custom",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equalf(t, tt.want, predicateType(tt.name), "predicateType(%v)", tt.name)
+		})
+	}
+}
+
+func Test_buildSBOMForAttestation(t *testing.T) {
+	// note: this test is only meant to test that the filter function is wired
+	// and not the correctness of the function in depth
+	type args struct {
+		id        clio.Identification
+		opts      *options.Catalog
+		userInput string
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    *sbom.SBOM
+		wantErr require.ErrorAssertionFunc
+	}{
+		{
+			name: "do not allow directory scans",
+			args: args{
+				opts: func() *options.Catalog {
+					def := defaultAttestOptions()
+					return &def.Catalog
+				}(),
+				userInput: "dir:/tmp/something",
+			},
+			wantErr: require.Error,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = require.NoError
+			}
+			_, err := generateSBOMForAttestation(context.Background(), tt.args.id, tt.args.opts, tt.args.userInput)
+			tt.wantErr(t, err)
+			if err != nil {
+				return
+			}
+		})
+	}
+}
+
+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

@@ -8,10 +8,11 @@ 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"
-	"github.com/anchore/syft/syft/formats"
+	"github.com/anchore/syft/syft/format"
 )
 
 const (
@@ -23,7 +24,7 @@ const (
 
 type ConvertOptions struct {
 	options.Config      `yaml:",inline" mapstructure:",squash"`
-	options.MultiOutput `yaml:",inline" mapstructure:",squash"`
+	options.Output      `yaml:",inline" mapstructure:",squash"`
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
 }
 
@@ -33,6 +34,7 @@ func Convert(app clio.Application) *cobra.Command {
 
 	opts := &ConvertOptions{
 		UpdateCheck: options.DefaultUpdateCheck(),
+		Output:      options.DefaultOutput(),
 	}
 
 	return app.SetupCommand(&cobra.Command{
@@ -45,7 +47,10 @@ 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()
+
 			return RunConvert(opts, args[0])
 		},
 	}, opts)
@@ -63,10 +68,13 @@ func RunConvert(opts *ConvertOptions, userInput string) error {
 		return err
 	}
 
-	var reader io.ReadCloser
+	var reader io.ReadSeekCloser
 
 	if userInput == "-" {
-		reader = os.Stdin
+		// though os.Stdin is an os.File, it does not support seeking
+		// you will get errors such as "seek /dev/stdin: illegal seek".
+		// We need to buffer what we read.
+		reader = internal.NewBufferedSeeker(os.Stdin)
 	} else {
 		f, err := os.Open(userInput)
 		if err != nil {
@@ -78,7 +86,7 @@ func RunConvert(opts *ConvertOptions, userInput string) error {
 		reader = f
 	}
 
-	s, _, err := formats.Decode(reader)
+	s, _, _, err := format.Decode(reader)
 	if err != nil {
 		return fmt.Errorf("failed to decode SBOM: %w", err)
 	}

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

@@ -6,12 +6,13 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/syft/cmd/syft/internal/ui"
 )
 
 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),
@@ -21,7 +22,10 @@ func Root(app clio.Application, packagesCmd *cobra.Command) *cobra.Command {
 		Example: packagesCmd.Example,
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
 		RunE: func(cmd *cobra.Command, args []string) error {
-			return runPackages(id, opts, args[0])
+			restoreStdout := ui.CaptureStdoutToTraceLog()
+			defer restoreStdout()
+
+			return runScan(cmd.Context(), id, opts, args[0])
 		},
 	}, opts)
 }

cmd/syft/internal/commands/scan.go

@@ -0,0 +1,454 @@
+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"`
+}
+
+func defaultScanOptions() *scanOptions {
+	return &scanOptions{
+		Output:      options.DefaultOutput(),
+		UpdateCheck: options.DefaultUpdateCheck(),
+		Catalog:     options.DefaultCatalog(),
+	}
+}
+
+//nolint:dupl
+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(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)
+	}
+
+	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(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." // nolint:goconst
+		}
+		return "However, " + err.Error() + "." // nolint:goconst
+	}
+
+	if errors.Is(err, task.ErrTagsNotAllowed) {
+		return "However, " + err.Error() + ".\nAdding groups of catalogers may result in surprising behavior (create inaccurate SBOMs)." // nolint:goconst
+	}
+
+	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

@@ -4,6 +4,8 @@ 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"`
@@ -12,6 +14,6 @@ type Attest struct {
 
 var _ clio.FlagAdder = (*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")
 }

cmd/syft/internal/options/catalog.go

@@ -0,0 +1,242 @@
+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/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"`
+
+	// 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
+	fangs.FieldDescriber
+} = (*Catalog)(nil)
+
+func DefaultCatalog() Catalog {
+	return Catalog{
+		Scope:         source.SquashedScope.String(),
+		Package:       defaultPackageConfig(),
+		LinuxKernel:   defaultLinuxKernelConfig(),
+		Golang:        defaultGolangConfig(),
+		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()).
+		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) 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(cfg.Golang.SearchLocalModCacheLicenses).
+			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
+			WithSearchRemoteLicenses(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(cfg.JavaScript.SearchRemoteLicenses).
+			WithNpmBaseURL(cfg.JavaScript.NpmBaseURL),
+		LinuxKernel: kernel.LinuxKernelCatalogerConfig{
+			CatalogModules: cfg.LinuxKernel.CatalogModules,
+		},
+		Python: python.CatalogerConfig{
+			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
+		},
+		JavaArchive: java.DefaultArchiveCatalogerConfig().
+			WithUseNetwork(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.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")
+}
+
+func (cfg *Catalog) PostLoad() error {
+	usingLegacyCatalogers := len(cfg.Catalogers) > 0
+	usingNewCatalogers := len(cfg.DefaultCatalogers) > 0 || len(cfg.SelectCatalogers) > 0
+
+	if usingLegacyCatalogers && usingNewCatalogers {
+		return fmt.Errorf("cannot use both 'catalogers' and 'select-catalogers'/'default-catalogers' flags")
+	}
+
+	flatten := func(l []string) []string {
+		var out []string
+		for _, v := range l {
+			for _, s := range strings.Split(v, ",") {
+				out = append(out, strings.TrimSpace(s))
+			}
+		}
+		sort.Strings(out)
+
+		return out
+	}
+
+	cfg.From = flatten(cfg.From)
+
+	cfg.Catalogers = flatten(cfg.Catalogers)
+	cfg.DefaultCatalogers = flatten(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = flatten(cfg.SelectCatalogers)
+
+	// for backwards compatibility
+	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
+
+	s := source.ParseScope(cfg.Scope)
+	if s == source.UnknownScope {
+		return fmt.Errorf("bad scope value %q", cfg.Scope)
+	}
+
+	return nil
+}

cmd/syft/internal/options/catalog_test.go

@@ -0,0 +1,72 @@
+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)
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			tt.wantErr(t, tt.options.PostLoad(), fmt.Sprintf("PostLoad()"))
+			if tt.assert != nil {
+				tt.assert(t, tt.options)
+			}
+		})
+	}
+}

cmd/syft/internal/options/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 +1,58 @@
+package options
+
+import (
+	"fmt"
+	"sort"
+
+	"github.com/scylladb/go-set/strset"
+
+	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,
+		},
+	}
+}
+
+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)
+}

cmd/syft/internal/options/file_test.go

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

cmd/syft/internal/options/format.go

@@ -0,0 +1,60 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/spdxtagvalue"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+var _ clio.PostLoader = (*Format)(nil)
+
+// 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) {
+	return format.EncodersConfig{
+		Template:      o.Template.config(),
+		SyftJSON:      o.SyftJSON.config(),
+		SPDXJSON:      o.SPDXJSON.config(format.AllVersions),                   // we support multiple versions, not just a single version
+		SPDXTagValue:  spdxtagvalue.EncoderConfig{Version: format.AllVersions}, // we support multiple versions, not just a single version
+		CyclonedxJSON: o.CyclonedxJSON.config(format.AllVersions),              // we support multiple versions, not just a single version
+		CyclonedxXML:  o.CyclonedxXML.config(format.AllVersions),               // we support multiple versions, not just a single version
+	}.Encoders()
+}
+
+func multiLevelOption[T any](defaultValue T, option ...*T) *T {
+	result := defaultValue
+	for _, opt := range option {
+		if opt != nil {
+			result = *opt
+		}
+	}
+	return &result
+}

cmd/syft/internal/options/format_cyclonedx_json.go

@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/cyclonedxjson"
+)
+
+type FormatCyclonedxJSON struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatCyclonedxJSON() FormatCyclonedxJSON {
+	return FormatCyclonedxJSON{}
+}
+
+func (o FormatCyclonedxJSON) config(version string) cyclonedxjson.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return cyclonedxjson.EncoderConfig{
+		Version: version,
+		Pretty:  pretty,
+	}
+}

cmd/syft/internal/options/format_cyclonedx_json_test.go

@@ -0,0 +1,67 @@
+package options
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFormatCyclonedxJSON_buildConfig(t *testing.T) {
+	// assert when building the config that we respond to all possible fields
+
+	ft := &FormatCyclonedxJSON{}
+	ft = setAllToNonZero(t, ft).(*FormatCyclonedxJSON)
+
+	subject := ft.config("Version")
+	assertExpectedValue(t, subject)
+}
+
+func setAllToNonZero(t testing.TB, structPtr any) any {
+	// set all fields on the struct to non-zero values
+	rt := reflect.TypeOf(structPtr)
+	if rt.Kind() != reflect.Ptr || rt.Elem().Kind() != reflect.Struct {
+		t.Fatal("expected a pointer to a struct")
+	}
+
+	rv := reflect.ValueOf(structPtr).Elem()
+	for i := 0; i < rt.Elem().NumField(); i++ {
+		val := getNonZeroExampleValue(t, rv.Field(i).Interface(), rt.Elem().Field(i).Name)
+		rv.Field(i).Set(reflect.ValueOf(val))
+	}
+	return structPtr
+}
+
+func getNonZeroExampleValue(t testing.TB, v any, name string) any {
+	switch v.(type) {
+	case bool:
+		return true
+	case *bool:
+		val := true
+		return &val
+	case string:
+		return name
+	}
+	t.Fatalf("unsupported type: %T", v)
+	return nil
+}
+
+func assertExpectedValue(t *testing.T, structTy any) {
+	rt := reflect.TypeOf(structTy)
+	rv := reflect.ValueOf(structTy)
+
+	for i := 0; i < rt.NumField(); i++ {
+		f := rt.Field(i)
+		fieldValue := rv.Field(i)
+
+		if fieldValue.Type().Kind() == reflect.String {
+			// use the field name as the expected value
+			assert.Equalf(t, f.Name, fieldValue.String(), "field %q value differs", f.Name)
+		} else {
+			// use the zero value for the type
+			if reflect.DeepEqual(fieldValue.Interface(), reflect.Zero(fieldValue.Type()).Interface()) {
+				t.Errorf("field '%s' is zero", f.Name)
+			}
+		}
+	}
+}

cmd/syft/internal/options/format_cyclonedx_xml.go

@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/cyclonedxxml"
+)
+
+type FormatCyclonedxXML struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatCyclonedxXML() FormatCyclonedxXML {
+	return FormatCyclonedxXML{}
+}
+
+func (o FormatCyclonedxXML) config(version string) cyclonedxxml.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return cyclonedxxml.EncoderConfig{
+		Version: version,
+		Pretty:  pretty,
+	}
+}

cmd/syft/internal/options/format_cyclonedx_xml_test.go

@@ -0,0 +1,15 @@
+package options
+
+import (
+	"testing"
+)
+
+func TestFormatCyclonedxXML_buildConfig(t *testing.T) {
+	// assert when building the config that we respond to all possible fields
+
+	ft := FormatCyclonedxXML{}
+	ftp := setAllToNonZero(t, &ft).(*FormatCyclonedxXML)
+
+	subject := ftp.config("Version")
+	assertExpectedValue(t, subject)
+}

cmd/syft/internal/options/format_spdx_json.go

@@ -0,0 +1,24 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/spdxjson"
+)
+
+type FormatSPDXJSON struct {
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatSPDXJSON() FormatSPDXJSON {
+	return FormatSPDXJSON{}
+}
+
+func (o FormatSPDXJSON) config(v string) spdxjson.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return spdxjson.EncoderConfig{
+		Version: v,
+		Pretty:  pretty,
+	}
+}

cmd/syft/internal/options/format_spdx_json_test.go

@@ -0,0 +1,15 @@
+package options
+
+import (
+	"testing"
+)
+
+func TestFormatSPDXJSON_buildConfig(t *testing.T) {
+	// assert when building the config that we respond to all possible fields
+
+	ft := &FormatSPDXJSON{}
+	ft = setAllToNonZero(t, ft).(*FormatSPDXJSON)
+
+	subject := ft.config("Version")
+	assertExpectedValue(t, subject)
+}

cmd/syft/internal/options/format_syft_json.go

@@ -0,0 +1,27 @@
+package options
+
+import (
+	"github.com/anchore/syft/syft/format/syftjson"
+)
+
+type FormatSyftJSON struct {
+	Legacy bool  `yaml:"legacy" json:"legacy" mapstructure:"legacy"`
+	Pretty *bool `yaml:"pretty" json:"pretty" mapstructure:"pretty"`
+}
+
+func DefaultFormatJSON() FormatSyftJSON {
+	return FormatSyftJSON{
+		Legacy: false,
+	}
+}
+
+func (o FormatSyftJSON) config() syftjson.EncoderConfig {
+	var pretty bool
+	if o.Pretty != nil {
+		pretty = *o.Pretty
+	}
+	return syftjson.EncoderConfig{
+		Legacy: o.Legacy,
+		Pretty: pretty,
+	}
+}

cmd/syft/internal/options/format_syft_json_test.go

@@ -0,0 +1,15 @@
+package options
+
+import (
+	"testing"
+)
+
+func TestFormatSyftJSON_buildConfig(t *testing.T) {
+	// assert when building the config that we respond to all possible fields
+
+	ft := &FormatSyftJSON{}
+	ft = setAllToNonZero(t, ft).(*FormatSyftJSON)
+
+	subject := ft.config()
+	assertExpectedValue(t, subject)
+}

cmd/syft/internal/options/format_template.go

@@ -0,0 +1,34 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/format/template"
+)
+
+var _ clio.FlagAdder = (*FormatTemplate)(nil)
+
+type FormatTemplate struct {
+	Enabled bool   `yaml:"-" json:"-" mapstructure:"-"`
+	Path    string `yaml:"path" json:"path" mapstructure:"path"` // -t template file to use for output
+	Legacy  bool   `yaml:"legacy" json:"legacy" mapstructure:"legacy"`
+}
+
+func DefaultFormatTemplate() FormatTemplate {
+	return FormatTemplate{
+		Enabled: true,
+	}
+}
+
+func (o *FormatTemplate) AddFlags(flags clio.FlagSet) {
+	if o.Enabled {
+		flags.StringVarP(&o.Path, "template", "t",
+			"specify the path to a Go template file")
+	}
+}
+
+func (o FormatTemplate) config() template.EncoderConfig {
+	return template.EncoderConfig{
+		TemplatePath: o.Path,
+		Legacy:       o.Legacy,
+	}
+}

cmd/syft/internal/options/golang.go

@@ -0,0 +1,38 @@
+package options
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg/cataloger/golang"
+)
+
+type golangConfig struct {
+	SearchLocalModCacheLicenses bool                          `json:"search-local-mod-cache-licenses" yaml:"search-local-mod-cache-licenses" mapstructure:"search-local-mod-cache-licenses"`
+	LocalModCacheDir            string                        `json:"local-mod-cache-dir" yaml:"local-mod-cache-dir" mapstructure:"local-mod-cache-dir"`
+	SearchRemoteLicenses        bool                          `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	Proxy                       string                        `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
+	NoProxy                     string                        `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
+	MainModuleVersion           golangMainModuleVersionConfig `json:"main-module-version" yaml:"main-module-version" mapstructure:"main-module-version"`
+}
+
+type golangMainModuleVersionConfig struct {
+	FromLDFlags       bool `json:"from-ld-flags" yaml:"from-ld-flags" mapstructure:"from-ld-flags"`
+	FromContents      bool `json:"from-contents" yaml:"from-contents" mapstructure:"from-contents"`
+	FromBuildSettings bool `json:"from-build-settings" yaml:"from-build-settings" mapstructure:"from-build-settings"`
+}
+
+func defaultGolangConfig() golangConfig {
+	def := golang.DefaultCatalogerConfig()
+	return golangConfig{
+		SearchLocalModCacheLicenses: def.SearchLocalModCacheLicenses,
+		LocalModCacheDir:            def.LocalModCacheDir,
+		SearchRemoteLicenses:        def.SearchRemoteLicenses,
+		Proxy:                       strings.Join(def.Proxies, ","),
+		NoProxy:                     strings.Join(def.NoProxy, ","),
+		MainModuleVersion: golangMainModuleVersionConfig{
+			FromLDFlags:       def.MainModuleVersion.FromLDFlags,
+			FromContents:      def.MainModuleVersion.FromContents,
+			FromBuildSettings: def.MainModuleVersion.FromBuildSettings,
+		},
+	}
+}

cmd/syft/internal/options/java.go

@@ -0,0 +1,7 @@
+package options
+
+type javaConfig struct {
+	UseNetwork              bool   `yaml:"use-network" json:"use-network" mapstructure:"use-network"`
+	MavenURL                string `yaml:"maven-url" json:"maven-url" mapstructure:"maven-url"`
+	MaxParentRecursiveDepth int    `yaml:"max-parent-recursive-depth" json:"max-parent-recursive-depth" mapstructure:"max-parent-recursive-depth"`
+}

cmd/syft/internal/options/javascript.go

@@ -0,0 +1,6 @@
+package options
+
+type javaScriptConfig struct {
+	SearchRemoteLicenses bool   `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	NpmBaseURL           string `json:"npm-base-url" yaml:"npm-base-url" mapstructure:"npm-base-url"`
+}