[wip] git-root config search concept

Signed-off-by: Alex Goodman <alex.goodman@anchore.com>

.bouncer.yaml

@@ -6,4 +6,17 @@ permit:
   - ISC
 ignore-packages:
   # packageurl-go is released under the MIT license located in the root of the repo at /mit.LICENSE
-  - github.com/package-url/packageurl-go
+  - github.com/anchore/packageurl-go
+
+  # from: https://github.com/spdx/tools-golang/blob/main/LICENSE.code
+  # The tools-golang source code is provided and may be used, at your option,
+  # under either:
+  # * Apache License, version 2.0 (Apache-2.0), OR
+  # * GNU General Public License, version 2.0 or later (GPL-2.0-or-later).
+  # (we choose Apache-2.0)
+  - github.com/spdx/tools-golang
+
+  # from: https://github.com/xi2/xz/blob/master/LICENSE
+  # All these files have been put into the public domain.
+  # You can do whatever you want with these files.
+  - github.com/xi2/xz

.github/ISSUE_TEMPLATE/config.yml

@@ -1,11 +1,6 @@
 contact_links:
 
-  - name: Help & Support Slack Channel ⛑️
-    # link to toolbox-help channel
-    url: https://anchorecommunity.slack.com/archives/C019BUXV7R6
-    about: Ask a questions and get answers
-
-  - name: Developer Slack Channel 💬
-    # link to toolbox-dev channel
-    url: https://anchorecommunity.slack.com/archives/C0190NF9TSM
-    about: Participate in design discussions and feature development
+  - name: Join the Slack community 💬
+    # link to our community Slack registration page
+    url: https://anchore.com/slack
+    about: 'Come chat with us! Ask for help, join our software development efforts, or just give us feedback!'

.github/scripts/go-mod-tidy-check.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+set -eu
+
+ORIGINAL_STATE_DIR=$(mktemp -d "TEMP-original-state-XXXXXXXXX")
+TIDY_STATE_DIR=$(mktemp -d "TEMP-tidy-state-XXXXXXXXX")
+
+trap "cp -v ${ORIGINAL_STATE_DIR}/* ./ && rm -fR ${ORIGINAL_STATE_DIR} ${TIDY_STATE_DIR}" EXIT
+
+echo "Capturing original state of files..."
+cp -v go.mod go.sum "${ORIGINAL_STATE_DIR}"
+
+echo "Capturing state of go.mod and go.sum after running go mod tidy..."
+go mod tidy
+cp -v go.mod go.sum "${TIDY_STATE_DIR}"
+echo ""
+
+set +e
+
+# Detect difference between the git HEAD state and the go mod tidy state
+DIFF_MOD=$(diff -u "${ORIGINAL_STATE_DIR}/go.mod" "${TIDY_STATE_DIR}/go.mod")
+DIFF_SUM=$(diff -u "${ORIGINAL_STATE_DIR}/go.sum" "${TIDY_STATE_DIR}/go.sum")
+
+if [[ -n "${DIFF_MOD}" || -n "${DIFF_SUM}" ]]; then
+    echo "go.mod diff:"
+    echo "${DIFF_MOD}"
+    echo "go.sum diff:"
+    echo "${DIFF_SUM}"
+    echo ""
+    printf "FAILED! go.mod and/or go.sum are NOT tidy; please run 'go mod tidy'.\n\n"
+    exit 1
+fi

.github/scripts/goreleaser-install.sh

@@ -0,0 +1,398 @@
+#!/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/workflows/codeql-analysis.yml

@@ -31,15 +31,6 @@ jobs:
     steps:
     - name: Checkout repository
       uses: actions/checkout@v2
-      with:
-        # We must fetch at least the immediate parents so that if this is
-        # a pull request then we can checkout the head.
-        fetch-depth: 2
-
-    # If this run was triggered by a pull request event, then checkout
-    # the head of the pull request instead of the merge commit.
-    - run: git checkout HEAD^2
-      if: ${{ github.event_name == 'pull_request' }}
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/release.yaml

@@ -96,10 +96,6 @@ jobs:
     steps:
       - uses: docker-practice/actions-setup-docker@v1
 
-      # note, it is important to always be auth'd into docker.io to prevent rate limiting issues
-      - name: Login to Docker Hub
-        run: echo ${{ secrets.TOOLBOX_DOCKER_PASS }} | docker login docker.io -u ${{ secrets.TOOLBOX_DOCKER_USER }} --password-stdin
-
       - uses: actions/setup-go@v2
         with:
           go-version: ${{ env.GO_VERSION }}
@@ -158,6 +154,10 @@ jobs:
           AC_USERNAME: ${{ secrets.ENG_CI_APPLE_ID }} # Used during macOS notarization.
           AC_PASSWORD: ${{ secrets.ENG_CI_APPLE_ID_PASS }} # Used during macOS notarization.
 
+      - uses: anchore/sbom-action@v0
+        with:
+          artifact-name: sbom.spdx.json
+
       - uses: 8398a7/action-slack@v3
         with:
           status: ${{ job.status }}

.github/workflows/validations.yaml

@@ -13,9 +13,6 @@ jobs:
     # 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
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/setup-go@v2
         with:
@@ -53,9 +50,6 @@ jobs:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Unit tests"
     runs-on: ubuntu-20.04
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/setup-go@v2
         with:
@@ -108,9 +102,6 @@ jobs:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Integration tests"
     runs-on: ubuntu-20.04
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/setup-go@v2
         with:
@@ -234,9 +225,6 @@ jobs:
   Build-Snapshot-Artifacts:
     name: "Build snapshot artifacts"
     runs-on: ubuntu-20.04
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/setup-go@v2
         with:
@@ -244,6 +232,9 @@ jobs:
 
       - uses: actions/checkout@v2
 
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+
       - name: Restore tool cache
         id: tool-cache
         uses: actions/cache@v2.1.3
@@ -277,9 +268,6 @@ jobs:
     name: "Acceptance tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/checkout@v2
 
@@ -296,9 +284,6 @@ jobs:
     name: "Acceptance tests (Mac)"
     needs: [Build-Snapshot-Artifacts]
     runs-on: macos-latest
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
       - uses: actions/checkout@v2
 
@@ -322,10 +307,11 @@ jobs:
     name: "CLI tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-20.04
-    # run only on push event (internal PRs) or on a pull_request event that is from a fork (external PR)
-    # skip if this is a pull_request event on an internal PR (which is already covered by push events)
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
     steps:
+      - uses: actions/setup-go@v2
+        with:
+          go-version: ${{ env.GO_VERSION }}
+
       - uses: actions/checkout@v2
 
       - name: Restore go cache

.golangci.yaml

@@ -15,6 +15,7 @@ linters:
     - dogsled
     - dupl
     - errcheck
+    - exportloopref
     - funlen
     - gocognit
     - goconst
@@ -22,7 +23,6 @@ linters:
     - gocyclo
     - gofmt
     - goimports
-    - golint
     - goprintffuncname
     - gosec
     - gosimple
@@ -31,8 +31,8 @@ linters:
     - misspell
     - nakedret
     - nolintlint
+    - revive
     - rowserrcheck
-    - scopelint
     - staticcheck
     - structcheck
     - stylecheck
@@ -49,11 +49,13 @@ linters:
 #    - godot
 #    - godox
 #    - goerr113
+#    - golint      # deprecated
 #    - gomnd       # this is too aggressive
 #    - interfacer  # this is a good idea, but is no longer supported and is prone to false positives
 #    - lll         # without a way to specify per-line exception cases, this is not usable
 #    - maligned    # this is an excellent linter, but tricky to optimize and we are not sensitive to memory layout optimizations
 #    - nestif
 #    - prealloc    # following this rule isn't consistently a good idea, as it sometimes forces unnecessary allocations that result in less idiomatic code
+#    - scopelint   # deprecated
 #    - testpackage
-#    - wsl
+#    - wsl         # this doens't have an auto-fixer yet and is pretty noisy (https://github.com/bombsimon/wsl/issues/90)

.goreleaser.yaml

@@ -12,9 +12,27 @@ builds:
     env:
       - CGO_ENABLED=0
     goos:
-      # windows not supported yet (due to jotframe)
-      # - windows
       - linux
+    goarch:
+      - amd64
+      - arm64
+    # Set the modified timestamp on the output binary to the git timestamp (to ensure a reproducible build)
+    mod_timestamp: '{{ .CommitTimestamp }}'
+    ldflags: |
+      -w
+      -s
+      -extldflags '-static'
+      -X github.com/anchore/syft/internal/version.version={{.Version}}
+      -X github.com/anchore/syft/internal/version.gitCommit={{.Commit}}
+      -X github.com/anchore/syft/internal/version.buildDate={{.Date}}
+      -X github.com/anchore/syft/internal/version.gitTreeState={{.Env.BUILD_GIT_TREE_STATE}}
+
+  - binary: syft
+    id: syft-win
+    env:
+      - CGO_ENABLED=0
+    goos:
+      - windows
     goarch:
       - amd64
     # Set the modified timestamp on the output binary to the git timestamp (to ensure a reproducible build)
@@ -27,7 +45,8 @@ builds:
       -X github.com/anchore/syft/internal/version.gitCommit={{.Commit}}
       -X github.com/anchore/syft/internal/version.buildDate={{.Date}}
       -X github.com/anchore/syft/internal/version.gitTreeState={{.Env.BUILD_GIT_TREE_STATE}}
-  # For more info on this macOS build, see: https://github.com/mitchellh/gon#usage-with-goreleaser
+
+    # For more info on this macOS build, see: https://github.com/mitchellh/gon#usage-with-goreleaser
   - binary: syft
     id: syft-macos
     env:
@@ -36,6 +55,7 @@ builds:
       - darwin
     goarch:
       - amd64
+      - arm64
     # Set the modified timestamp on the output binary to the git timestamp (to ensure a reproducible build)
     mod_timestamp: '{{ .CommitTimestamp }}'
     ldflags: |
@@ -51,10 +71,11 @@ archives:
   - format: tar.gz
     builds:
       - syft # i.e. Linux only
-  - format: zip # This is a hack! We don't actually intend to use _this_ ZIP file, we just need goreleaser to consider the ZIP file produced by gon (which will have the same file name) to be an artifact so we can use it downstream in publishing (e.g. to a homebrew tap)
+  - format: zip # This is a hack for syft-macos! We don't actually intend to use _this_ ZIP file, we just need goreleaser to consider the ZIP file produced by gon (which will have the same file name) to be an artifact so we can use it downstream in publishing (e.g. to a homebrew tap)
     id: syft-zip
     builds:
       - syft-macos
+      - syft-win
 
 signs:
   - artifacts: checksum
@@ -92,15 +113,48 @@ brews:
     description: *description
 
 dockers:
-  - dockerfile: Dockerfile
-    image_templates:
+  - image_templates:
       - "anchore/syft:latest"
-      - "anchore/syft:{{ .Tag }}"
-      - "anchore/syft:v{{ .Major }}"
-      - "anchore/syft:v{{ .Major }}.{{ .Minor }}"
+      - "anchore/syft:{{ .Tag }}-amd64"
+      - "anchore/syft:v{{ .Major }}-amd64"
+      - "anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64"
+    dockerfile: Dockerfile
+    use: buildx
     build_flag_templates:
+      - "--platform=linux/amd64"
       - "--build-arg=BUILD_DATE={{.Date}}"
       - "--build-arg=BUILD_VERSION={{.Version}}"
       - "--build-arg=VCS_REF={{.FullCommit}}"
       - "--build-arg=VCS_URL={{.GitURL}}"
-    use_buildx: true
+
+  - image_templates:
+      - "anchore/syft:{{ .Tag }}-arm64v8"
+      - "anchore/syft:v{{ .Major }}-arm64v8"
+      - "anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8"
+    goarch: arm64
+    dockerfile: Dockerfile
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/arm64/v8"
+      - "--build-arg=BUILD_DATE={{.Date}}"
+      - "--build-arg=BUILD_VERSION={{.Version}}"
+      - "--build-arg=VCS_REF={{.FullCommit}}"
+      - "--build-arg=VCS_URL={{.GitURL}}"
+
+docker_manifests:
+  - name_template: anchore/syft:{{ .Tag }}
+    image_templates:
+      - anchore/syft:{{ .Tag }}-amd64
+      - anchore/syft:v{{ .Major }}-amd64
+      - anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64
+      - anchore/syft:{{ .Tag }}-arm64v8
+      - anchore/syft:v{{ .Major }}-arm64v8
+      - anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8
+  - name_template: anchore/syft:latest
+    image_templates:
+      - anchore/syft:{{ .Tag }}-amd64
+      - anchore/syft:v{{ .Major }}-amd64
+      - anchore/syft:v{{ .Major }}.{{ .Minor }}-amd64
+      - anchore/syft:{{ .Tag }}-arm64v8
+      - anchore/syft:v{{ .Major }}-arm64v8
+      - anchore/syft:v{{ .Major }}.{{ .Minor }}-arm64v8

CONTRIBUTING.md

@@ -1,12 +1,12 @@
-# Contributing to `syft`
+# Contributing to Syft
 
-If you are looking to contribute to this project and want to open a Github pull request ("PR"), there are a few guidelines of what we are looking for in patches. Make sure you go through this document and ensure that your code proposal is aligned.
+If you are looking to contribute to this project and want to open a GitHub pull request ("PR"), there are a few guidelines of what we are looking for in patches. Make sure you go through this document and ensure that your code proposal is aligned.
 
-## Sign your work
+## Sign off your work
 
 The `sign-off` is an added line at the end of the explanation for the commit, certifying that you wrote it or otherwise have the right to submit it as an open-source patch. By submitting a contribution, you agree to be bound by the terms of the DCO Version 1.1 and Apache License Version 2.0.
 
-Signing a commit certifies the below Developer's Certificate of Origin (DCO):
+Signing off a commit certifies the below Developer's Certificate of Origin (DCO):
 
 ```text
 Developer's Certificate of Origin 1.1
@@ -51,13 +51,13 @@ $ git config --global user.name "John Doe"
 $ git config --global user.email "john.doe@example.com"
 ```
 
-Creating a signed commit is then possible with `-s`:
+Creating a signed-off commit is then possible with `-s` or `--signoff`:
 
 ```text
 $ git commit -s -m "this is a commit message"
 ```
 
-To double check if the commit was signed, look at the log output:
+To double-check that the commit was signed-off, look at the log output:
 
 ```text
 $ git log -1
@@ -82,6 +82,11 @@ Date:   Mon Aug 1 11:27:13 2020 -0400
 
 [//]: # (TODO: PR title and description)
 
+## Sign your commits
+
+To ensure the authenticity and integrity of code contributions, **we require that all commits are signed**. Signing commits proves that your commits were truly created by you, as the holder of a private key.
+
+Configuring git to sign your commits is a straightforward process. To get set up, see [GitHub's documentation on signing commits](https://docs.github.com/en/authentication/managing-commit-signature-verification/signing-commits).
 
 ## Test your changes
 

Makefile

@@ -15,10 +15,10 @@ RESET := $(shell tput -T linux sgr0)
 TITLE := $(BOLD)$(PURPLE)
 SUCCESS := $(BOLD)$(GREEN)
 # the quality gate lower threshold for unit test total % coverage (by function statements)
-COVERAGE_THRESHOLD := 70
+COVERAGE_THRESHOLD := 62
 # CI cache busting values; change these if you want CI to not use previous stored cache
 INTEGRATION_CACHE_BUSTER="88738d2f"
-CLI_CACHE_BUSTER="789bacdf"
+CLI_CACHE_BUSTER="9a2c03cf"
 BOOTSTRAP_CACHE="c7afb99ad"
 
 ## Build variables
@@ -37,10 +37,6 @@ ifeq "$(strip $(VERSION))" ""
  override VERSION = $(shell git describe --always --tags --dirty)
 endif
 
-# used to generate the changelog from the second to last tag to the current tag (used in the release pipeline when the release tag is in place)
-LAST_TAG := $(shell git describe --abbrev=0 --tags $(shell git rev-list --tags --max-count=1))
-SECOND_TO_LAST_TAG := $(shell git describe --abbrev=0 --tags $(shell git rev-list --tags --skip=1 --max-count=1))
-
 ## Variable assertions
 
 ifndef TEMPDIR
@@ -101,21 +97,21 @@ $(TEMPDIR):
 .PHONY: bootstrap-tools
 bootstrap-tools: $(TEMPDIR)
 	GO111MODULE=off GOBIN=$(shell realpath $(TEMPDIR)) go get -u golang.org/x/perf/cmd/benchstat
-	curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(TEMPDIR)/ v1.26.0
+	curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(TEMPDIR)/ v1.42.1
 	curl -sSfL https://raw.githubusercontent.com/wagoodman/go-bouncer/master/bouncer.sh | sh -s -- -b $(TEMPDIR)/ v0.2.0
-	curl -sfL https://install.goreleaser.com/github.com/goreleaser/goreleaser.sh | sh -s -- -b $(TEMPDIR)/ v0.160.0
+	curl -sSfL https://raw.githubusercontent.com/anchore/chronicle/main/install.sh | sh -s -- -b $(TEMPDIR)/ v0.3.0
+	.github/scripts/goreleaser-install.sh -b $(TEMPDIR)/ v0.177.0
 
 .PHONY: bootstrap-go
 bootstrap-go:
 	go mod download
-	go mod tidy # note: it is important that the go.sum is kept in a consistent state at all times (especially during release)
 
 .PHONY: bootstrap
 bootstrap: $(RESULTSDIR) bootstrap-go bootstrap-tools ## Download and install all go dependencies (+ prep tooling in the ./tmp dir)
 	$(call title,Bootstrapping dependencies)
 
 .PHONY: static-analysis
-static-analysis: lint check-licenses
+static-analysis: lint check-go-mod-tidy check-licenses
 
 .PHONY: lint
 lint: ## Run gofmt + golangci lint checks
@@ -136,11 +132,15 @@ lint-fix: ## Auto-format all source code + run golangci lint fixers
 	$(call title,Running lint fixers)
 	gofmt -w -s .
 	$(LINTCMD) --fix
+	go mod tidy
 
 .PHONY: check-licenses
-check-licenses:
+check-licenses: ## Ensure transitive dependencies are compliant with the current license policy
 	$(TEMPDIR)/bouncer check
 
+check-go-mod-tidy:
+	@ .github/scripts/go-mod-tidy-check.sh && echo "go.mod and go.sum are tidy!"
+
 .PHONY: validate-cyclonedx-schema
 validate-cyclonedx-schema:
 	cd schema/cyclonedx && make
@@ -190,6 +190,11 @@ fixtures:
 generate-json-schema:  ## Generate a new json schema
 	cd schema/json && go run generate.go
 
+.PHONY: generate-license-list
+generate-license-list: ## Generate an updated spdx license list
+	go generate ./internal/spdxlicense/...
+	gofmt -s -w ./internal/spdxlicense
+
 .PHONY: build
 build: $(SNAPSHOTDIR) ## Build release snapshot binaries and packages
 
@@ -200,7 +205,9 @@ $(SNAPSHOTDIR): ## Build snapshot release binaries and packages
 	cat .goreleaser.yaml >> $(TEMPDIR)/goreleaser.yaml
 
 	# build release snapshots
+	# DOCKER_CLI_EXPERIMENTAL needed to support multi architecture builds for goreleaser
 	BUILD_GIT_TREE_STATE=$(GITTREESTATE) \
+	DOCKER_CLI_EXPERIMENTAL=enabled \
 	$(TEMPDIR)/goreleaser release --skip-publish --skip-sign --rm-dist --snapshot --config $(TEMPDIR)/goreleaser.yaml
 
 # note: we cannot clean the snapshot directory since the pipeline builds the snapshot separately
@@ -246,44 +253,19 @@ cli: $(SNAPSHOTDIR) ## Run CLI tests
 	SYFT_BINARY_LOCATION='$(SNAPSHOT_CMD)' \
 		go test -count=1 -v ./test/cli
 
-.PHONY: changlog-release
-changelog-release:
-	@echo "Last tag: $(SECOND_TO_LAST_TAG)"
-	@docker run --rm \
-		-v "$(shell pwd)":/usr/local/src/your-app \
-		ferrarimarco/github-changelog-generator \
-		--user anchore \
-		--project $(BIN) \
-		-t ${GITHUB_TOKEN} \
-		--exclude-labels 'duplicate,question,invalid,wontfix,size:small,size:medium,size:large,size:x-large' \
-		--no-pr-wo-labels \
-		--no-issues-wo-labels \
-		--since-tag $(SECOND_TO_LAST_TAG)
-
-	@printf '\n$(BOLD)$(CYAN)Release $(VERSION) Changelog$(RESET)\n\n'
-	@cat CHANGELOG.md
-
-.PHONY: changelog-unreleased
-changelog-unreleased: ## show the current changelog that will be produced on the next release (note: requires GITHUB_TOKEN set)
-	@docker run -it --rm \
-		-v "$(shell pwd)":/usr/local/src/your-app \
-		ferrarimarco/github-changelog-generator \
-		--user anchore \
-		--project $(BIN) \
-		-t ${GITHUB_TOKEN} \
-		--exclude-labels 'duplicate,question,invalid,wontfix,size:small,size:medium,size:large,size:x-large' \
-		--since-tag $(LAST_TAG)
-
-	@printf '\n$(BOLD)$(CYAN)Unreleased Changes (closed PRs and issues will not be in the final changelog)$(RESET)\n'
-
+.PHONY: changelog
+changelog: clean-changelog CHANGELOG.md
 	@docker run -it --rm \
 		-v $(shell pwd)/CHANGELOG.md:/CHANGELOG.md \
 		rawkode/mdv \
 			-t 748.5989 \
 			/CHANGELOG.md
 
+CHANGELOG.md:
+	$(TEMPDIR)/chronicle -vv > CHANGELOG.md
+
 .PHONY: release
-release: clean-dist changelog-release ## Build and publish final binaries and packages. Intended to be run only on macOS.
+release: clean-dist CHANGELOG.md  ## Build and publish final binaries and packages. Intended to be run only on macOS.
 	$(call title,Publishing release artifacts)
 
 	# Prepare for macOS-specific signing process
@@ -298,9 +280,11 @@ release: clean-dist changelog-release ## Build and publish final binaries and pa
 	cat .goreleaser.yaml >> $(TEMPDIR)/goreleaser.yaml
 
 	# release (note the version transformation from v0.7.0 --> 0.7.0)
+	# DOCKER_CLI_EXPERIMENTAL needed to support multi architecture builds for goreleaser
 	bash -c "\
 		BUILD_GIT_TREE_STATE=$(GITTREESTATE) \
 		VERSION=$(VERSION:v%=%) \
+		DOCKER_CLI_EXPERIMENTAL=enabled \
 		$(TEMPDIR)/goreleaser \
 			--rm-dist \
 			--config $(TEMPDIR)/goreleaser.yaml \
@@ -322,9 +306,13 @@ clean-snapshot:
 	rm -rf $(SNAPSHOTDIR) $(TEMPDIR)/goreleaser.yaml
 
 .PHONY: clean-dist
-clean-dist:
+clean-dist: clean-changelog
 	rm -rf $(DISTDIR) $(TEMPDIR)/goreleaser.yaml
 
+.PHONY: clean-changelog
+clean-changelog:
+	rm -f CHANGELOG.md
+
 clean-test-image-cache: clean-test-image-tar-cache clean-test-image-docker-cache
 
 .PHONY: clear-test-image-tar-cache
@@ -346,4 +334,4 @@ show-test-image-cache: ## Show all docker and image tar cache
 .PHONY: show-test-snapshots
 show-test-snapshots: ## Show all test snapshots
 	$(call title,Test snapshots)
-	@find . -type f -wholename "**/test-fixtures/snapshot/*" | sort
+	@find . -type f -wholename "**/test-fixtures/snapshot/*" | sort

README.md

@@ -1,23 +1,59 @@
-# syft
+<p align="center">
+    <img src="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png" width="271" alt="Cute pink owl syft logo">
+</p>
 
 [![Validations](https://github.com/anchore/syft/actions/workflows/validations.yaml/badge.svg)](https://github.com/anchore/syft/actions/workflows/validations.yaml)
 [![Go Report Card](https://goreportcard.com/badge/github.com/anchore/syft)](https://goreportcard.com/report/github.com/anchore/syft)
 [![GitHub release](https://img.shields.io/github/release/anchore/syft.svg)](https://github.com/anchore/syft/releases/latest)
-[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/anchore/syft/blob/main/LICENSE)
 [![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/anchore/syft.svg)](https://github.com/anchore/syft)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/anchore/syft/blob/main/LICENSE)
+[![Slack Invite](https://img.shields.io/badge/Slack-Join-blue?logo=slack)](https://anchore.com/slack)
 
-A CLI tool and go library for generating a Software Bill of Materials (SBOM) from container images and filesystems.
+A CLI tool and Go library for generating a Software Bill of Materials (SBOM) from container images and filesystems. Exceptional for vulnerability detection when used with a scanner tool like [Grype](https://github.com/anchore/grype).
+
+### Join us at the virtual OSS meetup!
+
+When: December 1, 2021 @ 11am-noon PT (2-3pm ET)
+
+We’ve got security experts from VMware and Anchore who will share their tips, tricks, and lessons learned on securing containers using [Syft](https://github.com/anchore/syft), [Grype](https://github.com/anchore/grype), and [Cartographer](https://github.com/vmware-tanzu/cartographer).
+
+Register now: https://get.anchore.com/anchore-oss-meetup-dec-1-2021/
+
+---
 
 ![syft-demo](https://user-images.githubusercontent.com/590471/90277200-2a253000-de33-11ea-893f-32c219eea11a.gif)
 
-**Features**
+## Features
 - Catalog container images and filesystems to discover packages and libraries.
 - Supports packages and libraries from various ecosystems (APK, DEB, RPM, Ruby Bundles, Python Wheel/Egg/requirements.txt, JavaScript NPM/Yarn, Java JAR/EAR/WAR, Jenkins plugins JPI/HPI, Go modules)
 - Linux distribution identification (supports Alpine, BusyBox, CentOS/RedHat, Debian/Ubuntu flavored distributions)
 - Supports Docker and OCI image formats
+- Direct support for [Grype](https://github.com/anchore/grype), a fast and powerful vulnerability matcher.
+
 
 If you encounter an issue, please [let us know using the issue tracker](https://github.com/anchore/syft/issues).
 
+## Installation
+
+### Recommended
+```bash
+curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
+```
+
+...or, you can specify a release version and destination directory for the installation:
+
+```
+curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b <DESTINATION_DIR> <RELEASE_VERSION>
+```
+
+### Homebrew
+```bash
+brew tap anchore/syft
+brew install syft
+```
+
+**Note**: Currently, Syft is built only for macOS and Linux.
+
 ## Getting started
 
 To generate an SBOM for a Docker or OCI image:
@@ -37,7 +73,10 @@ To include software from all image layers in the SBOM, regardless of its presenc
 syft packages <image> --scope all-layers
 ```
 
+### Supported sources
+
 Syft can generate a SBOM from a variety of sources:
+
 ```
 # catalog a container image archive (from the result of `docker image save ...`, `podman save ...`, or `skopeo copy` commands)
 syft packages path/to/image.tar
@@ -47,42 +86,114 @@ syft packages path/to/dir
 ```
 
 Sources can be explicitly provided with a scheme:
+
 ```
 docker:yourrepo/yourimage:tag          use images from the Docker 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)
 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)
 ```
 
+### Output formats
+
 The output format for Syft is configurable as well:
+
 ```
 syft packages <image> -o <format>
 ```
 
-Where the `format`s available are:
+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.
-- `cyclonedx`: A XML report conforming to the [CycloneDX 1.2](https://cyclonedx.org/) specification.
+- `cyclonedx`: A XML report conforming to the [CycloneDX 1.2 specification](https://cyclonedx.org/specification/overview/).
+- `spdx`: A tag-value formatted report conforming to the [SPDX 2.2 specification](https://spdx.github.io/spdx-spec/).
+- `spdx-json`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
 - `table`: A columnar summary (default).
 
-## Installation
+## Private Registry Authentication
 
-**Recommended (macOS and Linux)**
-```bash
-# install the latest version to /usr/local/bin
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b /usr/local/bin
+### Local Docker Credentials
+When a container runtime is not present, Syft can still utilize credentials configured in common credential sources (such as `~/.docker/config.json`). 
+It will pull images from private registries using these credentials. The config file is where your credentials are stored when authenticating with private registries via some command like `docker login`. 
+For more information see the `go-containerregistry` [documentation](https://github.com/google/go-containerregistry/tree/main/pkg/authn).
 
-# install a specific version into a specific dir
-curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sh -s -- -b <SOME_BIN_PATH> <RELEASE_VERSION>
+
+An example `config.json` looks something like this:
+```
+// config.json
+{
+	"auths": {
+		"registry.example.com": {
+			"username": "AzureDiamond",
+			"password": "hunter2"
+		}
+	}
+}
 ```
 
-**Homebrew (macOS)**
-```bash
-brew tap anchore/syft
-brew install syft
-```
+You can run the following command as an example. It details the mount/environment configuration a container needs to access a private registry:
+
+`docker run -v ./config.json:/config/config.json -e "DOCKER_CONFIG=/config" anchore/syft:latest  <private_image>`
+
+
+### Docker Credentials in Kubernetes
+The below section shows a simple workflow on how to mount this config file as a secret into a container on kubernetes.
+1. Create a secret. The value of `config.json` is important. It refers to the specification detailed [here](https://github.com/google/go-containerregistry/tree/main/pkg/authn#the-config-file). 
+Below this section is the `secret.yaml` file that the pod configuration will consume as a volume. 
+The key `config.json` is important. It will end up being the name of the file when mounted into the pod.
+    ```
+    # secret.yaml
+    
+    apiVersion: v1
+    kind: Secret
+    metadata:
+      name: registry-config
+      namespace: syft
+    data:
+      config.json: <base64 encoded config.json>
+    ```
+
+    `kubectl apply -f secret.yaml`
+
+
+2. Create your pod running syft. The env `DOCKER_CONFIG` is important because it advertises where to look for the credential file. 
+In the below example, setting `DOCKER_CONFIG=/config` informs syft that credentials can be found at `/config/config.json`. 
+This is why we used `config.json` as the key for our secret. When mounted into containers the secrets' key is used as the filename. 
+The `volumeMounts` section mounts our secret to `/config`. The `volumes` section names our volume and leverages the secret we created in step one.
+    ```
+    # pod.yaml
+    
+    apiVersion: v1
+    kind: Pod
+    spec:
+      containers:
+        - image: anchore/syft:latest
+          name: syft-private-registry-demo
+          env:
+            - name: DOCKER_CONFIG
+              value: /config
+          volumeMounts:
+          - mountPath: /config
+            name: registry-config
+            readOnly: true
+          args:
+            - <private_image>
+      volumes:
+      - name: registry-config
+        secret:
+          secretName: registry-config
+    ```
+
+    `kubectl apply -f pod.yaml`
+
+
+3. The user can now run `kubectl logs syft-private-registry-demo`. The logs should show the syft analysis for the `<private_image>` provided in the pod configuration.
+
+Using the above information, users should be able to configure private registry access without having to do so in the `grype` or `syft` configuration files.
+They will also not be dependent on a docker daemon, (or some other runtime software) for registry configuration and access.
 
 ## Configuration
 
@@ -90,6 +201,8 @@ Configuration search paths:
 
 - `.syft.yaml`
 - `.syft/config.yaml`
+- `<git repo root>/.syft.yaml`
+- `<git repo root>/.syft/config.yaml`
 - `~/.syft.yaml`
 - `<XDG_CONFIG_HOME>/syft/config.yaml`
 
@@ -104,6 +217,9 @@ output: "table"
 # same as -q ; SYFT_QUIET env var
 quiet: false
 
+# same as --file; write output report to a file (default is to write to stdout)
+file: ""
+
 # enable/disable checking for application updates on startup
 # same as SYFT_CHECK_FOR_APP_UPDATE env var
 check-for-app-update: true
@@ -114,7 +230,7 @@ package:
     # enable/disable cataloging of packages
     # SYFT_PACKAGE_CATALOGER_ENABLED env var
     enabled: true
-    
+
     # the search space to look for packages (options: all-layers, squashed)
     # same as -s ; SYFT_PACKAGE_CATALOGER_SCOPE env var
     scope: "squashed"
@@ -155,11 +271,11 @@ file-metadata:
     # 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: "sha256", "md5", "sha1")
   # SYFT_FILE_METADATA_DIGESTS env var
   digests: ["sha256"]
@@ -185,12 +301,12 @@ secrets:
 
   # 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 
+  # 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 
+  # 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: []
@@ -200,6 +316,9 @@ registry:
   # skip TLS verification when communicating with the registry
   # SYFT_REGISTRY_INSECURE_SKIP_TLS_VERIFY env var
   insecure-skip-tls-verify: false
+  # use http instead of https when connecting to the registry
+  # SYFT_REGISTRY_INSECURE_USE_HTTP env var
+  insecure-use-http: false
 
   # credentials for specific registries
   auth:
@@ -250,4 +369,4 @@ anchore:
   # same as -d ; SYFT_ANCHORE_DOCKERFILE env var
   dockerfile: ""
 
-```
+```

RELEASE.md

@@ -87,9 +87,12 @@ This release process itself should be as automated as possible, and have only a
 
 1. Tag the main branch with a full semantic-version, prefixed with a `v`. If there is a
    milestone with a partial version, the full version should be used for the git tag (e.g.
-   with a Milestone of `v0.1` the tag should be `v0.1.0`).
+   with a Milestone of `v0.1` the tag should be `v0.1.0`). You can determine the changes going
+   into a release by running `make changelog-unreleased`. Use this change list to determine the 
+   release increment. After determining the release increment (major, minor, patch), create the tag.
+   Given the above example the command to create the tag would be `git tag v0.1.0`.
 
-1. Push the tag.
+1. Push the tag. Given the above example the command to push the tag would be `git push origin v0.1.0`.
    
 1. A release admin must approve the release on the GitHub Actions release pipeline run page.
    Once approved, the release pipeline will generate all assets and draft a GitHub Release.

cmd/cmd.go

@@ -48,7 +48,13 @@ func initCmdAliasBindings() {
 		panic(err)
 	}
 
-	if activeCmd == packagesCmd || activeCmd == rootCmd {
+	// enable all cataloger by default if power-user command is run
+	if activeCmd == powerUserCmd {
+		config.PowerUserCatalogerEnabledDefault()
+	}
+
+	switch activeCmd {
+	case packagesCmd, rootCmd:
 		// note: we need to lazily bind config options since they are shared between both the root command
 		// and the packages command. Otherwise there will be global viper state that is in contention.
 		// See for more details: https://github.com/spf13/viper/issues/233 . Additionally, the bindings must occur BEFORE
@@ -58,7 +64,7 @@ func initCmdAliasBindings() {
 		if err = bindPackagesConfigOptions(activeCmd.Flags()); err != nil {
 			panic(err)
 		}
-	} else {
+	default:
 		// even though the root command or packages command is NOT being run, we still need default bindings
 		// such that application config parsing passes.
 		if err = bindPackagesConfigOptions(packagesCmd.Flags()); err != nil {

cmd/completion.go

@@ -14,9 +14,8 @@ import (
 
 // completionCmd represents the completion command
 var completionCmd = &cobra.Command{
-	Hidden: true,
-	Use:    "completion [bash|zsh|fish]",
-	Short:  "Generate a shell completion for Syft (listing local docker images)",
+	Use:   "completion [bash|zsh|fish]",
+	Short: "Generate a shell completion for Syft (listing local docker images)",
 	Long: `To load completions (docker image list):
 
 Bash:

cmd/event_loop.go

@@ -0,0 +1,98 @@
+package cmd
+
+import (
+	"errors"
+	"fmt"
+	"os"
+
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/ui"
+	"github.com/hashicorp/go-multierror"
+	"github.com/wagoodman/go-partybus"
+)
+
+// eventLoop listens to worker errors (from execution path), worker events (from a partybus subscription), and
+// signal interrupts. Is responsible for handling each event relative to a given UI an to coordinate eventing until
+// an eventual graceful exit.
+// nolint:funlen
+func eventLoop(workerErrs <-chan error, signals <-chan os.Signal, subscription *partybus.Subscription, cleanupFn func(), uxs ...ui.UI) error {
+	defer cleanupFn()
+	events := subscription.Events()
+	var err error
+	var ux ui.UI
+
+	if ux, err = setupUI(subscription.Unsubscribe, uxs...); err != nil {
+		return err
+	}
+
+	var retErr error
+	var forceTeardown bool
+
+	for {
+		if workerErrs == nil && events == nil {
+			break
+		}
+		select {
+		case err, isOpen := <-workerErrs:
+			if !isOpen {
+				workerErrs = nil
+				continue
+			}
+			if err != nil {
+				// capture the error from the worker and unsubscribe to complete a graceful shutdown
+				retErr = multierror.Append(retErr, err)
+				_ = subscription.Unsubscribe()
+				// the worker has exited, we may have been mid-handling events for the UI which should now be
+				// ignored, in which case forcing a teardown of the UI irregardless of the state is required.
+				forceTeardown = true
+			}
+		case e, isOpen := <-events:
+			if !isOpen {
+				events = nil
+				continue
+			}
+
+			if err := ux.Handle(e); err != nil {
+				if errors.Is(err, partybus.ErrUnsubscribe) {
+					events = nil
+				} else {
+					retErr = multierror.Append(retErr, err)
+					// TODO: should we unsubscribe? should we try to halt execution? or continue?
+				}
+			}
+		case <-signals:
+			// ignore further results from any event source and exit ASAP, but ensure that all cache is cleaned up.
+			// we ignore further errors since cleaning up the tmp directories will affect running catalogers that are
+			// reading/writing from/to their nested temp dirs. This is acceptable since we are bailing without result.
+
+			// TODO: potential future improvement would be to pass context into workers with a cancel function that is
+			// to the event loop. In this way we can have a more controlled shutdown even at the most nested levels
+			// of processing.
+			events = nil
+			workerErrs = nil
+			forceTeardown = true
+		}
+	}
+
+	if err := ux.Teardown(forceTeardown); err != nil {
+		retErr = multierror.Append(retErr, err)
+	}
+
+	return retErr
+}
+
+// setupUI takes one or more UIs that responds to events and takes a event bus unsubscribe function for use
+// during teardown. With the given UIs, the first UI which the ui.Setup() function does not return an error
+// will be utilized in execution. Providing a set of UIs allows for the caller to provide graceful fallbacks
+// when there are environmental problem (e.g. unable to setup a TUI with the current TTY).
+func setupUI(unsubscribe func() error, uis ...ui.UI) (ui.UI, error) {
+	for _, ux := range uis {
+		if err := ux.Setup(unsubscribe); err != nil {
+			log.Warnf("unable to setup given UI, falling back to alternative UI: %+v", err)
+			continue
+		}
+
+		return ux, nil
+	}
+	return nil, fmt.Errorf("unable to setup any UI")
+}

cmd/event_loop_test.go

@@ -0,0 +1,455 @@
+package cmd
+
+import (
+	"fmt"
+	"os"
+	"syscall"
+	"testing"
+	"time"
+
+	"github.com/anchore/syft/internal/ui"
+	"github.com/anchore/syft/syft/event"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/mock"
+	"github.com/wagoodman/go-partybus"
+)
+
+var _ ui.UI = (*uiMock)(nil)
+
+type uiMock struct {
+	t           *testing.T
+	finalEvent  partybus.Event
+	unsubscribe func() error
+	mock.Mock
+}
+
+func (u *uiMock) Setup(unsubscribe func() error) error {
+	u.t.Logf("UI Setup called")
+	u.unsubscribe = unsubscribe
+	return u.Called(unsubscribe).Error(0)
+}
+
+func (u *uiMock) Handle(event partybus.Event) error {
+	u.t.Logf("UI Handle called: %+v", event.Type)
+	if event == u.finalEvent {
+		assert.NoError(u.t, u.unsubscribe())
+	}
+	return u.Called(event).Error(0)
+}
+
+func (u *uiMock) Teardown(_ bool) error {
+	u.t.Logf("UI Teardown called")
+	return u.Called().Error(0)
+}
+
+func Test_eventLoop_gracefulExit(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		finalEvent := partybus.Event{
+			Type: event.PresenterReady,
+		}
+
+		worker := func() <-chan error {
+			ret := make(chan error)
+			go func() {
+				t.Log("worker running")
+				// send an empty item (which is ignored) ensuring we've entered the select statement,
+				// then close (a partial shutdown).
+				ret <- nil
+				t.Log("worker sent nothing")
+				close(ret)
+				t.Log("worker closed")
+				// do the other half of the shutdown
+				testBus.Publish(finalEvent)
+				t.Log("worker published final event")
+			}()
+			return ret
+		}
+
+		signaler := func() <-chan os.Signal {
+			return nil
+		}
+
+		ux := &uiMock{
+			t:          t,
+			finalEvent: finalEvent,
+		}
+
+		// ensure the mock sees at least the final event
+		ux.On("Handle", finalEvent).Return(nil)
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(nil)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		assert.NoError(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func Test_eventLoop_workerError(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		workerErr := fmt.Errorf("worker error")
+
+		worker := func() <-chan error {
+			ret := make(chan error)
+			go func() {
+				t.Log("worker running")
+				// send an empty item (which is ignored) ensuring we've entered the select statement,
+				// then close (a partial shutdown).
+				ret <- nil
+				t.Log("worker sent nothing")
+				ret <- workerErr
+				t.Log("worker sent error")
+				close(ret)
+				t.Log("worker closed")
+				// note: NO final event is fired
+			}()
+			return ret
+		}
+
+		signaler := func() <-chan os.Signal {
+			return nil
+		}
+
+		ux := &uiMock{
+			t: t,
+		}
+
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(nil)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		// ensure we see an error returned
+		assert.ErrorIs(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+			workerErr,
+			"should have seen a worker error, but did not",
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func Test_eventLoop_unsubscribeError(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		finalEvent := partybus.Event{
+			Type: event.PresenterReady,
+		}
+
+		worker := func() <-chan error {
+			ret := make(chan error)
+			go func() {
+				t.Log("worker running")
+				// send an empty item (which is ignored) ensuring we've entered the select statement,
+				// then close (a partial shutdown).
+				ret <- nil
+				t.Log("worker sent nothing")
+				close(ret)
+				t.Log("worker closed")
+				// do the other half of the shutdown
+				testBus.Publish(finalEvent)
+				t.Log("worker published final event")
+			}()
+			return ret
+		}
+
+		signaler := func() <-chan os.Signal {
+			return nil
+		}
+
+		ux := &uiMock{
+			t:          t,
+			finalEvent: finalEvent,
+		}
+
+		// ensure the mock sees at least the final event... note the unsubscribe error here
+		ux.On("Handle", finalEvent).Return(partybus.ErrUnsubscribe)
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(nil)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		// unsubscribe errors should be handled and ignored, not propagated. We are additionally asserting that
+		// this case is handled as a controlled shutdown (this test should not timeout)
+		assert.NoError(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func Test_eventLoop_handlerError(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		finalEvent := partybus.Event{
+			Type:  event.PresenterReady,
+			Error: fmt.Errorf("unable to create presenter"),
+		}
+
+		worker := func() <-chan error {
+			ret := make(chan error)
+			go func() {
+				t.Log("worker running")
+				// send an empty item (which is ignored) ensuring we've entered the select statement,
+				// then close (a partial shutdown).
+				ret <- nil
+				t.Log("worker sent nothing")
+				close(ret)
+				t.Log("worker closed")
+				// do the other half of the shutdown
+				testBus.Publish(finalEvent)
+				t.Log("worker published final event")
+			}()
+			return ret
+		}
+
+		signaler := func() <-chan os.Signal {
+			return nil
+		}
+
+		ux := &uiMock{
+			t:          t,
+			finalEvent: finalEvent,
+		}
+
+		// ensure the mock sees at least the final event... note the event error is propagated
+		ux.On("Handle", finalEvent).Return(finalEvent.Error)
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(nil)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		// handle errors SHOULD propagate the event loop. We are additionally asserting that this case is
+		// handled as a controlled shutdown (this test should not timeout)
+		assert.ErrorIs(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+			finalEvent.Error,
+			"should have seen a event error, but did not",
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func Test_eventLoop_signalsStopExecution(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		worker := func() <-chan error {
+			// the worker will never return work and the event loop will always be waiting...
+			return make(chan error)
+		}
+
+		signaler := func() <-chan os.Signal {
+			ret := make(chan os.Signal)
+			go func() {
+				ret <- syscall.SIGINT
+				// note: we do NOT close the channel to ensure the event loop does not depend on that behavior to exit
+			}()
+			return ret
+		}
+
+		ux := &uiMock{
+			t: t,
+		}
+
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(nil)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		assert.NoError(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func Test_eventLoop_uiTeardownError(t *testing.T) {
+	test := func(t *testing.T) {
+
+		testBus := partybus.NewBus()
+		subscription := testBus.Subscribe()
+		t.Cleanup(testBus.Close)
+
+		finalEvent := partybus.Event{
+			Type: event.PresenterReady,
+		}
+
+		worker := func() <-chan error {
+			ret := make(chan error)
+			go func() {
+				t.Log("worker running")
+				// send an empty item (which is ignored) ensuring we've entered the select statement,
+				// then close (a partial shutdown).
+				ret <- nil
+				t.Log("worker sent nothing")
+				close(ret)
+				t.Log("worker closed")
+				// do the other half of the shutdown
+				testBus.Publish(finalEvent)
+				t.Log("worker published final event")
+			}()
+			return ret
+		}
+
+		signaler := func() <-chan os.Signal {
+			return nil
+		}
+
+		ux := &uiMock{
+			t:          t,
+			finalEvent: finalEvent,
+		}
+
+		teardownError := fmt.Errorf("sorry, dave, the UI doesn't want to be torn down")
+
+		// ensure the mock sees at least the final event... note the event error is propagated
+		ux.On("Handle", finalEvent).Return(nil)
+		// ensure the mock sees basic setup/teardown events
+		ux.On("Setup", mock.AnythingOfType("func() error")).Return(nil)
+		ux.On("Teardown").Return(teardownError)
+
+		var cleanupCalled bool
+		cleanupFn := func() {
+			t.Log("cleanup called")
+			cleanupCalled = true
+		}
+
+		// ensure we see an error returned
+		assert.ErrorIs(t,
+			eventLoop(
+				worker(),
+				signaler(),
+				subscription,
+				cleanupFn,
+				ux,
+			),
+			teardownError,
+			"should have seen a UI teardown error, but did not",
+		)
+
+		assert.True(t, cleanupCalled, "cleanup function not called")
+		ux.AssertExpectations(t)
+	}
+
+	// if there is a bug, then there is a risk of the event loop never returning
+	testWithTimeout(t, 5*time.Second, test)
+}
+
+func testWithTimeout(t *testing.T, timeout time.Duration, test func(*testing.T)) {
+	done := make(chan bool)
+	go func() {
+		test(t)
+		done <- true
+	}()
+
+	select {
+	case <-time.After(timeout):
+		t.Fatal("test timed out")
+	case <-done:
+	}
+}

cmd/packages.go

@@ -6,34 +6,37 @@ import (
 	"io/ioutil"
 	"os"
 
-	"github.com/spf13/viper"
-
+	"github.com/anchore/stereoscope"
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/anchore"
 	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/formats"
 	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/internal/presenter/packages"
 	"github.com/anchore/syft/internal/ui"
-	"github.com/anchore/syft/syft"
-	"github.com/anchore/syft/syft/distro"
+	"github.com/anchore/syft/internal/version"
+	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/event"
-	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 	"github.com/pkg/profile"
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
+	"github.com/spf13/viper"
 	"github.com/wagoodman/go-partybus"
 )
 
 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 SBOM
+  {{.appName}} {{.command}} alpine:latest -o cyclonedx   show a CycloneDX formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx        show a SPDX 2.2 tag-value formatted SBOM
+  {{.appName}} {{.command}} alpine:latest -o spdx-json   show a SPDX 2.2 JSON formatted SBOM
   {{.appName}} {{.command}} alpine:latest -vv            show verbose debug information
 
   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, or generic filesystem directory 
+    {{.appName}} {{.command}} path/to/a/file/or/dir      a Docker tar, OCI tar, OCI directory, or generic filesystem directory
 
   You can also explicitly specify the scheme to use:
     {{.appName}} {{.command}} docker:yourrepo/yourimage:tag          explicitly use the Docker daemon
@@ -41,13 +44,13 @@ const (
     {{.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}} 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)
     {{.appName}} {{.command}} registry:yourrepo/yourimage:tag        pull image directly from a registry (no container runtime required)
 `
 )
 
 var (
-	packagesPresenterOpt packages.PresenterOption
-	packagesArgs         = cobra.MinimumNArgs(1)
+	packagesPresenterOpt format.Option
 	packagesCmd          = &cobra.Command{
 		Use:   "packages [SOURCE]",
 		Short: "Generate a package SBOM",
@@ -56,22 +59,13 @@ var (
 			"appName": internal.ApplicationName,
 			"command": "packages",
 		}),
-		Args:          packagesArgs,
+		Args:          validateInputArgs,
 		SilenceUsage:  true,
 		SilenceErrors: true,
 		PreRunE: func(cmd *cobra.Command, args []string) error {
-			if len(args) == 0 {
-				err := cmd.Help()
-				if err != nil {
-					return err
-				}
-				// silently exit
-				return fmt.Errorf("")
-			}
-
 			// set the presenter
-			presenterOption := packages.ParsePresenterOption(appConfig.Output)
-			if presenterOption == packages.UnknownPresenterOption {
+			presenterOption := format.ParseOption(appConfig.Output)
+			if presenterOption == format.UnknownFormatOption {
 				return fmt.Errorf("bad --output value '%s'", appConfig.Output)
 			}
 			packagesPresenterOpt = presenterOption
@@ -101,18 +95,23 @@ func init() {
 }
 
 func setPackageFlags(flags *pflag.FlagSet) {
-	///////// Formatting & Input options //////////////////////////////////////////////
+	// Formatting & Input options //////////////////////////////////////////////
 
 	flags.StringP(
 		"scope", "s", source.SquashedScope.String(),
 		fmt.Sprintf("selection of layers to catalog, options=%v", source.AllScopes))
 
 	flags.StringP(
-		"output", "o", string(packages.TablePresenterOption),
-		fmt.Sprintf("report output formatter, options=%v", packages.AllPresenters),
+		"output", "o", string(format.TableOption),
+		fmt.Sprintf("report output formatter, options=%v", format.AllOptions),
 	)
 
-	///////// Upload options //////////////////////////////////////////////////////////
+	flags.StringP(
+		"file", "", "",
+		"file to write the report output to (default is STDOUT)",
+	)
+
+	// Upload options //////////////////////////////////////////////////////////
 	flags.StringP(
 		"host", "H", "",
 		"the hostname or URL of the Anchore Enterprise instance to upload to",
@@ -137,10 +136,15 @@ func setPackageFlags(flags *pflag.FlagSet) {
 		"overwrite-existing-image", false,
 		"overwrite an existing image during the upload to Anchore Enterprise",
 	)
+
+	flags.Uint(
+		"import-timeout", 30,
+		"set a timeout duration (in seconds) for the upload to Anchore Enterprise",
+	)
 }
 
 func bindPackagesConfigOptions(flags *pflag.FlagSet) error {
-	///////// Formatting & Input options //////////////////////////////////////////////
+	// Formatting & Input options //////////////////////////////////////////////
 
 	if err := viper.BindPFlag("package.cataloger.scope", flags.Lookup("scope")); err != nil {
 		return err
@@ -150,7 +154,11 @@ func bindPackagesConfigOptions(flags *pflag.FlagSet) error {
 		return err
 	}
 
-	///////// Upload options //////////////////////////////////////////////////////////
+	if err := viper.BindPFlag("file", flags.Lookup("file")); err != nil {
+		return err
+	}
+
+	// Upload options //////////////////////////////////////////////////////////
 
 	if err := viper.BindPFlag("anchore.host", flags.Lookup("host")); err != nil {
 		return err
@@ -172,13 +180,58 @@ func bindPackagesConfigOptions(flags *pflag.FlagSet) error {
 		return err
 	}
 
+	if err := viper.BindPFlag("anchore.import-timeout", flags.Lookup("import-timeout")); err != nil {
+		return err
+	}
+
 	return nil
 }
 
+func validateInputArgs(cmd *cobra.Command, args []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("an image/directory argument is required")
+	}
+
+	return cobra.MaximumNArgs(1)(cmd, args)
+}
+
 func packagesExec(_ *cobra.Command, args []string) error {
-	errs := packagesExecWorker(args[0])
-	ux := ui.Select(appConfig.CliOptions.Verbosity > 0, appConfig.Quiet)
-	return ux(errs, eventSubscription)
+	// could be an image or a directory, with or without a scheme
+	userInput := args[0]
+
+	reporter, closer, err := reportWriter()
+	defer func() {
+		if err := closer(); err != nil {
+			log.Warnf("unable to write to report destination: %+v", err)
+		}
+	}()
+
+	if err != nil {
+		return err
+	}
+
+	return eventLoop(
+		packagesExecWorker(userInput),
+		setupSignals(),
+		eventSubscription,
+		stereoscope.Cleanup,
+		ui.Select(isVerbose(), appConfig.Quiet, reporter)...,
+	)
+}
+
+func isVerbose() (result bool) {
+	isPipedInput, err := internal.IsPipedInput()
+	if err != nil {
+		// since we can't tell if there was piped input we assume that there could be to disable the ETUI
+		log.Warnf("unable to determine if there is piped input: %+v", err)
+		return true
+	}
+	// verbosity should consider if there is piped input (in which case we should not show the ETUI)
+	return appConfig.CliOptions.Verbosity > 0 || isPipedInput
 }
 
 func packagesExecWorker(userInput string) <-chan error {
@@ -186,42 +239,73 @@ func packagesExecWorker(userInput string) <-chan error {
 	go func() {
 		defer close(errs)
 
+		tasks, err := tasks()
+		if err != nil {
+			errs <- err
+			return
+		}
+
+		f := formats.ByOption(packagesPresenterOpt)
+		if f == nil {
+			errs <- fmt.Errorf("unknown format: %s", packagesPresenterOpt)
+			return
+		}
+
 		checkForApplicationUpdate()
 
 		src, cleanup, err := source.New(userInput, appConfig.Registry.ToOptions())
 		if err != nil {
-			errs <- fmt.Errorf("failed to determine image source: %+v", err)
+			errs <- fmt.Errorf("failed to determine image source: %w", err)
 			return
 		}
-		defer cleanup()
+		if cleanup != nil {
+			defer cleanup()
+		}
 
-		catalog, d, err := syft.CatalogPackages(src, appConfig.Package.Cataloger.ScopeOpt)
-		if err != nil {
-			errs <- fmt.Errorf("failed to catalog input: %+v", err)
-			return
+		s := sbom.SBOM{
+			Source: src.Metadata,
+			Descriptor: sbom.Descriptor{
+				Name:          internal.ApplicationName,
+				Version:       version.FromBuild().Version,
+				Configuration: appConfig,
+			},
 		}
 
+		var relationships []<-chan artifact.Relationship
+		for _, task := range tasks {
+			c := make(chan artifact.Relationship)
+			relationships = append(relationships, c)
+
+			go runTask(task, &s.Artifacts, src, c, errs)
+		}
+		s.Relationships = append(s.Relationships, mergeRelationships(relationships...)...)
+
 		if appConfig.Anchore.Host != "" {
-			if err := runPackageSbomUpload(src, src.Metadata, catalog, d, appConfig.Package.Cataloger.ScopeOpt); err != nil {
+			if err := runPackageSbomUpload(src, s); err != nil {
 				errs <- err
 				return
 			}
 		}
 
 		bus.Publish(partybus.Event{
-			Type: event.PresenterReady,
-			Value: packages.Presenter(packagesPresenterOpt, packages.PresenterConfig{
-				SourceMetadata: src.Metadata,
-				Catalog:        catalog,
-				Distro:         d,
-				Scope:          appConfig.Package.Cataloger.ScopeOpt,
-			}),
+			Type:  event.PresenterReady,
+			Value: f.Presenter(s),
 		})
 	}()
 	return errs
 }
 
-func runPackageSbomUpload(src source.Source, s source.Metadata, catalog *pkg.Catalog, d *distro.Distro, scope source.Scope) error {
+func mergeRelationships(cs ...<-chan artifact.Relationship) (relationships []artifact.Relationship) {
+	for _, c := range cs {
+		for n := range c {
+			relationships = append(relationships, n)
+		}
+	}
+
+	return relationships
+}
+
+func runPackageSbomUpload(src *source.Source, s sbom.SBOM) error {
 	log.Infof("uploading results to %s", appConfig.Anchore.Host)
 
 	if src.Metadata.Scheme != source.ImageScheme {
@@ -251,21 +335,20 @@ func runPackageSbomUpload(src source.Source, s source.Metadata, catalog *pkg.Cat
 		Password: appConfig.Anchore.Password,
 	})
 	if err != nil {
-		return fmt.Errorf("failed to create anchore client: %+v", err)
+		return fmt.Errorf("failed to create anchore client: %w", err)
 	}
 
 	importCfg := anchore.ImportConfig{
 		ImageMetadata:           src.Image.Metadata,
-		SourceMetadata:          s,
-		Catalog:                 catalog,
-		Distro:                  d,
+		SBOM:                    s,
 		Dockerfile:              dockerfileContents,
 		OverwriteExistingUpload: appConfig.Anchore.OverwriteExistingImage,
-		Scope:                   scope,
+		Timeout:                 appConfig.Anchore.ImportTimeout,
 	}
 
 	if err := c.Import(context.Background(), importCfg); err != nil {
 		return fmt.Errorf("failed to upload results to host=%s: %+v", appConfig.Anchore.Host, err)
 	}
+
 	return nil
 }

cmd/power_user.go

@@ -2,15 +2,20 @@ package cmd
 
 import (
 	"fmt"
-	"sync"
+	"os"
 
+	"github.com/anchore/stereoscope"
 	"github.com/anchore/syft/internal"
-
 	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/internal/presenter/poweruser"
+	"github.com/anchore/syft/internal/formats/syftjson"
+	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/internal/ui"
+	"github.com/anchore/syft/internal/version"
+	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
+	"github.com/gookit/color"
 	"github.com/pkg/profile"
 	"github.com/spf13/cobra"
 	"github.com/wagoodman/go-partybus"
@@ -18,6 +23,8 @@ import (
 
 const powerUserExample = `  {{.appName}} {{.command}} <image>
 
+  DEPRECATED - THIS COMMAND WILL BE REMOVED in v1.0.0
+
   Only image sources are supported (e.g. docker: , docker-archive: , oci: , etc.), the directory source (dir:) is not supported.
 
   All behavior is controlled via application configuration and environment variables (see https://github.com/anchore/syft#configuration)
@@ -34,7 +41,7 @@ var powerUserCmd = &cobra.Command{
 		"appName": internal.ApplicationName,
 		"command": "power-user",
 	}),
-	Args:          cobra.ExactArgs(1),
+	Args:          validateInputArgs,
 	Hidden:        true,
 	SilenceUsage:  true,
 	SilenceErrors: true,
@@ -63,17 +70,42 @@ func init() {
 }
 
 func powerUserExec(_ *cobra.Command, args []string) error {
-	errs := powerUserExecWorker(args[0])
-	ux := ui.Select(appConfig.CliOptions.Verbosity > 0, appConfig.Quiet)
-	return ux(errs, eventSubscription)
-}
+	// could be an image or a directory, with or without a scheme
+	userInput := args[0]
 
+	reporter, closer, err := reportWriter()
+	defer func() {
+		if err := closer(); err != nil {
+			log.Warnf("unable to write to report destination: %+v", err)
+		}
+
+		// 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)
+	}()
+
+	if err != nil {
+		return err
+	}
+
+	return eventLoop(
+		powerUserExecWorker(userInput),
+		setupSignals(),
+		eventSubscription,
+		stereoscope.Cleanup,
+		ui.Select(isVerbose(), appConfig.Quiet, reporter)...,
+	)
+}
 func powerUserExecWorker(userInput string) <-chan error {
 	errs := make(chan error)
 	go func() {
 		defer close(errs)
 
-		tasks, err := powerUserTasks()
+		appConfig.Secrets.Cataloger.Enabled = true
+		appConfig.FileMetadata.Cataloger.Enabled = true
+		appConfig.FileContents.Cataloger.Enabled = true
+		appConfig.FileClassification.Cataloger.Enabled = true
+		tasks, err := tasks()
 		if err != nil {
 			errs <- err
 			return
@@ -86,36 +118,34 @@ func powerUserExecWorker(userInput string) <-chan error {
 			errs <- err
 			return
 		}
-		defer cleanup()
-
-		if src.Metadata.Scheme != source.ImageScheme {
-			errs <- fmt.Errorf("the power-user subcommand only allows for 'image' schemes, given %q", src.Metadata.Scheme)
-			return
+		if cleanup != nil {
+			defer cleanup()
 		}
 
-		analysisResults := poweruser.JSONDocumentConfig{
-			SourceMetadata:    src.Metadata,
-			ApplicationConfig: *appConfig,
+		s := sbom.SBOM{
+			Source: src.Metadata,
+			Descriptor: sbom.Descriptor{
+				Name:          internal.ApplicationName,
+				Version:       version.FromBuild().Version,
+				Configuration: appConfig,
+			},
 		}
 
-		wg := &sync.WaitGroup{}
+		var relationships []<-chan artifact.Relationship
 		for _, task := range tasks {
-			wg.Add(1)
-			go func(task powerUserTask) {
-				defer wg.Done()
-				if err = task(&analysisResults, src); err != nil {
-					errs <- err
-					return
-				}
-			}(task)
+			c := make(chan artifact.Relationship)
+			relationships = append(relationships, c)
+
+			go runTask(task, &s.Artifacts, src, c, errs)
 		}
 
-		wg.Wait()
+		s.Relationships = append(s.Relationships, mergeRelationships(relationships...)...)
 
 		bus.Publish(partybus.Event{
 			Type:  event.PresenterReady,
-			Value: poweruser.NewJSONPresenter(analysisResults),
+			Value: syftjson.Format().Presenter(s),
 		})
 	}()
+
 	return errs
 }

cmd/report_writer.go

@@ -0,0 +1,33 @@
+package cmd
+
+import (
+	"fmt"
+	"io"
+	"os"
+	"strings"
+
+	"github.com/anchore/syft/internal/log"
+)
+
+func reportWriter() (io.Writer, func() error, error) {
+	nop := func() error { return nil }
+	path := strings.TrimSpace(appConfig.File)
+
+	switch len(path) {
+	case 0:
+		return os.Stdout, nop, nil
+
+	default:
+		reportFile, err := os.OpenFile(path, os.O_RDWR|os.O_CREATE|os.O_TRUNC, 0644)
+
+		if err != nil {
+			return nil, nop, fmt.Errorf("unable to create report file: %w", err)
+		}
+
+		return reportFile, func() error {
+			log.Infof("report written to file=%q", path)
+
+			return reportFile.Close()
+		}, nil
+	}
+}

cmd/root.go

@@ -33,6 +33,7 @@ func init() {
 		flag, "q", false,
 		"suppress all logging output",
 	)
+
 	if err := viper.BindPFlag(flag, rootCmd.PersistentFlags().Lookup(flag)); err != nil {
 		fmt.Printf("unable to bind flag '%s': %+v", flag, err)
 		os.Exit(1)

cmd/signals.go

@@ -0,0 +1,20 @@
+package cmd
+
+import (
+	"os"
+	"os/signal"
+	"syscall"
+)
+
+func setupSignals() <-chan os.Signal {
+	c := make(chan os.Signal, 1) // Note: A buffered channel is recommended for this; see https://golang.org/pkg/os/signal/#Notify
+
+	interruptions := []os.Signal{
+		syscall.SIGINT,
+		syscall.SIGTERM,
+	}
+
+	signal.Notify(c, interruptions...)
+
+	return c
+}

cmd/tasks.go

@@ -4,24 +4,25 @@ import (
 	"crypto"
 	"fmt"
 
-	"github.com/anchore/syft/internal/presenter/poweruser"
 	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
 
-type powerUserTask func(*poweruser.JSONDocumentConfig, source.Source) error
+type task func(*sbom.Artifacts, *source.Source) ([]artifact.Relationship, error)
 
-func powerUserTasks() ([]powerUserTask, error) {
-	var tasks []powerUserTask
+func tasks() ([]task, error) {
+	var tasks []task
 
-	generators := []func() (powerUserTask, error){
-		catalogPackagesTask,
-		catalogFileMetadataTask,
-		catalogFileDigestsTask,
-		catalogSecretsTask,
-		catalogFileClassificationsTask,
-		catalogContentsTask,
+	generators := []func() (task, error){
+		generateCatalogPackagesTask,
+		generateCatalogFileMetadataTask,
+		generateCatalogFileDigestsTask,
+		generateCatalogSecretsTask,
+		generateCatalogFileClassificationsTask,
+		generateCatalogContentsTask,
 	}
 
 	for _, generator := range generators {
@@ -29,6 +30,7 @@ func powerUserTasks() ([]powerUserTask, error) {
 		if err != nil {
 			return nil, err
 		}
+
 		if task != nil {
 			tasks = append(tasks, task)
 		}
@@ -37,51 +39,51 @@ func powerUserTasks() ([]powerUserTask, error) {
 	return tasks, nil
 }
 
-func catalogPackagesTask() (powerUserTask, error) {
+func generateCatalogPackagesTask() (task, error) {
 	if !appConfig.Package.Cataloger.Enabled {
 		return nil, nil
 	}
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
-		packageCatalog, theDistro, err := syft.CatalogPackages(src, appConfig.Package.Cataloger.ScopeOpt)
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
+		packageCatalog, relationships, theDistro, err := syft.CatalogPackages(src, appConfig.Package.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		results.PackageCatalog = packageCatalog
 		results.Distro = theDistro
 
-		return nil
+		return relationships, nil
 	}
 
 	return task, nil
 }
 
-func catalogFileMetadataTask() (powerUserTask, error) {
+func generateCatalogFileMetadataTask() (task, error) {
 	if !appConfig.FileMetadata.Cataloger.Enabled {
 		return nil, nil
 	}
 
 	metadataCataloger := file.NewMetadataCataloger()
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(appConfig.FileMetadata.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		result, err := metadataCataloger.Catalog(resolver)
 		if err != nil {
-			return err
+			return nil, err
 		}
 		results.FileMetadata = result
-		return nil
+		return nil, nil
 	}
 
 	return task, nil
 }
 
-func catalogFileDigestsTask() (powerUserTask, error) {
+func generateCatalogFileDigestsTask() (task, error) {
 	if !appConfig.FileMetadata.Cataloger.Enabled {
 		return nil, nil
 	}
@@ -110,24 +112,24 @@ func catalogFileDigestsTask() (powerUserTask, error) {
 		return nil, err
 	}
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(appConfig.FileMetadata.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		result, err := digestsCataloger.Catalog(resolver)
 		if err != nil {
-			return err
+			return nil, err
 		}
 		results.FileDigests = result
-		return nil
+		return nil, nil
 	}
 
 	return task, nil
 }
 
-func catalogSecretsTask() (powerUserTask, error) {
+func generateCatalogSecretsTask() (task, error) {
 	if !appConfig.Secrets.Cataloger.Enabled {
 		return nil, nil
 	}
@@ -142,24 +144,24 @@ func catalogSecretsTask() (powerUserTask, error) {
 		return nil, err
 	}
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(appConfig.Secrets.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		result, err := secretsCataloger.Catalog(resolver)
 		if err != nil {
-			return err
+			return nil, err
 		}
 		results.Secrets = result
-		return nil
+		return nil, nil
 	}
 
 	return task, nil
 }
 
-func catalogFileClassificationsTask() (powerUserTask, error) {
+func generateCatalogFileClassificationsTask() (task, error) {
 	if !appConfig.FileClassification.Cataloger.Enabled {
 		return nil, nil
 	}
@@ -170,24 +172,24 @@ func catalogFileClassificationsTask() (powerUserTask, error) {
 		return nil, err
 	}
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(appConfig.FileClassification.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		result, err := classifierCataloger.Catalog(resolver)
 		if err != nil {
-			return err
+			return nil, err
 		}
 		results.FileClassifications = result
-		return nil
+		return nil, nil
 	}
 
 	return task, nil
 }
 
-func catalogContentsTask() (powerUserTask, error) {
+func generateCatalogContentsTask() (task, error) {
 	if !appConfig.FileContents.Cataloger.Enabled {
 		return nil, nil
 	}
@@ -197,19 +199,33 @@ func catalogContentsTask() (powerUserTask, error) {
 		return nil, err
 	}
 
-	task := func(results *poweruser.JSONDocumentConfig, src source.Source) error {
+	task := func(results *sbom.Artifacts, src *source.Source) ([]artifact.Relationship, error) {
 		resolver, err := src.FileResolver(appConfig.FileContents.Cataloger.ScopeOpt)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
 		result, err := contentsCataloger.Catalog(resolver)
 		if err != nil {
-			return err
+			return nil, err
 		}
 		results.FileContents = result
-		return nil
+		return nil, nil
 	}
 
 	return task, nil
 }
+
+func runTask(t task, a *sbom.Artifacts, src *source.Source, c chan<- artifact.Relationship, errs chan<- error) {
+	defer close(c)
+
+	relationships, err := t(a, src)
+	if err != nil {
+		errs <- err
+		return
+	}
+
+	for _, relationship := range relationships {
+		c <- relationship
+	}
+}

go.mod

@@ -7,40 +7,52 @@ require (
 	github.com/adrg/xdg v0.2.1
 	github.com/alecthomas/jsonschema v0.0.0-20210301060011-54c507b6f074
 	github.com/anchore/client-go v0.0.0-20210222170800-9c70f9b80bcf
-	github.com/anchore/go-rpmdb v0.0.0-20210415132930-2460011e83c6
+	github.com/anchore/go-presenter v0.0.0-20211102174526-0dbf20f6c7fa
+	github.com/anchore/go-rpmdb v0.0.0-20210914181456-a9c52348da63
 	github.com/anchore/go-testutils v0.0.0-20200925183923-d5f45b0d3c04
 	github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b
-	github.com/anchore/stereoscope v0.0.0-20210413221244-d577f30b19e6
+	github.com/anchore/packageurl-go v0.0.0-20210922164639-b3fa992ebd29
+	github.com/anchore/stereoscope v0.0.0-20211116152349-7e4e1b56a15d
+	// we are hinting brotli to latest due to warning when installing archiver v3:
+	// go: warning: github.com/andybalholm/brotli@v1.0.1: retracted by module author: occasional panics and data corruption
+	github.com/andybalholm/brotli v1.0.4 // indirect
 	github.com/antihax/optional v1.0.0
 	github.com/bmatcuk/doublestar/v2 v2.0.4
-	github.com/docker/docker v17.12.0-ce-rc1.0.20200309214505-aa6a9891b09c+incompatible
+	github.com/docker/docker v20.10.10+incompatible
 	github.com/dustin/go-humanize v1.0.0
 	github.com/facebookincubator/nvdtools v0.1.4
 	github.com/go-test/deep v1.0.7
-	github.com/google/uuid v1.1.1
+	github.com/google/go-cmp v0.5.6
+	github.com/google/uuid v1.2.0
 	github.com/gookit/color v1.2.7
 	github.com/hashicorp/go-multierror v1.1.0
 	github.com/hashicorp/go-version v1.2.0
+	github.com/jinzhu/copier v0.3.2
+	github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d // indirect
+	github.com/mholt/archiver/v3 v3.5.1
 	github.com/mitchellh/go-homedir v1.1.0
-	github.com/mitchellh/mapstructure v1.3.1
+	github.com/mitchellh/hashstructure/v2 v2.0.2
+	github.com/mitchellh/mapstructure v1.4.1
 	github.com/olekukonko/tablewriter v0.0.4
-	github.com/package-url/packageurl-go v0.1.0
-	github.com/pelletier/go-toml v1.8.0
+	github.com/pelletier/go-toml v1.9.3
 	github.com/pkg/profile v1.5.0
 	github.com/scylladb/go-set v1.0.2
 	github.com/sergi/go-diff v1.1.0
-	github.com/sirupsen/logrus v1.6.0
-	github.com/spf13/afero v1.2.2
-	github.com/spf13/cobra v1.0.1-0.20200909172742-8a63648dd905
+	github.com/sirupsen/logrus v1.8.1
+	github.com/spdx/tools-golang v0.1.0
+	github.com/spf13/afero v1.6.0
+	github.com/spf13/cobra v1.2.1
 	github.com/spf13/pflag v1.0.5
-	github.com/spf13/viper v1.7.0
-	github.com/stretchr/testify v1.6.0
-	github.com/wagoodman/go-partybus v0.0.0-20200526224238-eb215533f07d
+	github.com/spf13/viper v1.8.1
+	github.com/stretchr/testify v1.7.0
+	github.com/vifraa/gopom v0.1.0
+	github.com/wagoodman/go-partybus v0.0.0-20210627031916-db1f5573bbc5
 	github.com/wagoodman/go-progress v0.0.0-20200731105512-1020f39e6240
-	github.com/wagoodman/jotframe v0.0.0-20200730190914-3517092dd163
+	github.com/wagoodman/jotframe v0.0.0-20211129225309-56b0d0a4aebb
 	github.com/x-cray/logrus-prefixed-formatter v0.5.2
 	github.com/xeipuuv/gojsonschema v1.2.0
-	golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9
-	golang.org/x/mod v0.3.0
-	gopkg.in/yaml.v2 v2.3.0
+	golang.org/x/mod v0.4.2
+	golang.org/x/net v0.0.0-20211111160137-58aab5ef257a
+	golang.org/x/term v0.0.0-20210615171337-6886f2dfbf5b
+	gopkg.in/yaml.v2 v2.4.0
 )

internal/anchore/import.go

@@ -6,27 +6,22 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/antihax/optional"
-
 	"github.com/anchore/client-go/pkg/external"
 	"github.com/anchore/stereoscope/pkg/image"
 	"github.com/anchore/syft/internal/bus"
-	"github.com/anchore/syft/syft/distro"
 	"github.com/anchore/syft/syft/event"
-	"github.com/anchore/syft/syft/pkg"
-	"github.com/anchore/syft/syft/source"
+	"github.com/anchore/syft/syft/sbom"
+	"github.com/antihax/optional"
 	"github.com/wagoodman/go-partybus"
 	"github.com/wagoodman/go-progress"
 )
 
 type ImportConfig struct {
 	ImageMetadata           image.Metadata
-	SourceMetadata          source.Metadata
-	Catalog                 *pkg.Catalog
-	Distro                  *distro.Distro
+	SBOM                    sbom.SBOM
 	Dockerfile              []byte
 	OverwriteExistingUpload bool
-	Scope                   source.Scope
+	Timeout                 uint
 }
 
 func importProgress(source string) (*progress.Stage, *progress.Manual) {
@@ -54,7 +49,8 @@ func importProgress(source string) (*progress.Stage, *progress.Manual) {
 func (c *Client) Import(ctx context.Context, cfg ImportConfig) error {
 	stage, prog := importProgress(c.config.BaseURL)
 
-	ctxWithTimeout, cancel := context.WithTimeout(ctx, time.Second*30)
+	timeout := time.Duration(cfg.Timeout) * time.Second
+	ctxWithTimeout, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()
 
 	authedCtx := c.newRequestContext(ctxWithTimeout)
@@ -72,19 +68,19 @@ func (c *Client) Import(ctx context.Context, cfg ImportConfig) error {
 	prog.N++
 	sessionID := startOperation.Uuid
 
-	packageDigest, err := importPackageSBOM(authedCtx, c.client.ImportsApi, sessionID, cfg.SourceMetadata, cfg.Catalog, cfg.Distro, cfg.Scope, stage)
+	packageDigest, err := importPackageSBOM(authedCtx, c.client.ImportsApi, sessionID, cfg.SBOM, stage)
 	if err != nil {
 		return fmt.Errorf("failed to import Package SBOM: %w", err)
 	}
 	prog.N++
 
-	manifestDigest, err := importManifest(authedCtx, c.client.ImportsApi, sessionID, cfg.ImageMetadata.RawManifest, stage)
+	manifestDigest, err := importManifest(authedCtx, c.client.ImportsApi, sessionID, cfg.SBOM.Source.ImageMetadata.RawManifest, stage)
 	if err != nil {
 		return fmt.Errorf("failed to import Manifest: %w", err)
 	}
 	prog.N++
 
-	configDigest, err := importConfig(authedCtx, c.client.ImportsApi, sessionID, cfg.ImageMetadata.RawConfig, stage)
+	configDigest, err := importConfig(authedCtx, c.client.ImportsApi, sessionID, cfg.SBOM.Source.ImageMetadata.RawConfig, stage)
 	if err != nil {
 		return fmt.Errorf("failed to import Config: %w", err)
 	}

internal/anchore/import_package_sbom.go

@@ -8,26 +8,24 @@ import (
 	"fmt"
 	"net/http"
 
-	"github.com/anchore/syft/internal/presenter/packages"
+	"github.com/anchore/syft/syft/sbom"
+
+	"github.com/anchore/syft/internal/formats/syftjson"
 
 	"github.com/wagoodman/go-progress"
 
-	"github.com/anchore/syft/syft/distro"
-	"github.com/anchore/syft/syft/source"
-
 	"github.com/anchore/client-go/pkg/external"
 	"github.com/anchore/syft/internal/log"
-	"github.com/anchore/syft/syft/pkg"
 )
 
 type packageSBOMImportAPI interface {
 	ImportImagePackages(context.Context, string, external.ImagePackageManifest) (external.ImageImportContentResponse, *http.Response, error)
 }
 
-func packageSbomModel(s source.Metadata, catalog *pkg.Catalog, d *distro.Distro, scope source.Scope) (*external.ImagePackageManifest, error) {
+func packageSbomModel(s sbom.SBOM) (*external.ImagePackageManifest, error) {
 	var buf bytes.Buffer
-	pres := packages.NewJSONPresenter(catalog, s, d, scope)
-	err := pres.Present(&buf)
+
+	err := syftjson.Format().Presenter(s).Present(&buf)
 	if err != nil {
 		return nil, fmt.Errorf("unable to serialize results: %w", err)
 	}
@@ -41,11 +39,11 @@ func packageSbomModel(s source.Metadata, catalog *pkg.Catalog, d *distro.Distro,
 	return &model, nil
 }
 
-func importPackageSBOM(ctx context.Context, api packageSBOMImportAPI, sessionID string, s source.Metadata, catalog *pkg.Catalog, d *distro.Distro, scope source.Scope, stage *progress.Stage) (string, error) {
+func importPackageSBOM(ctx context.Context, api packageSBOMImportAPI, sessionID string, s sbom.SBOM, stage *progress.Stage) (string, error) {
 	log.Debug("importing package SBOM")
 	stage.Current = "package SBOM"
 
-	model, err := packageSbomModel(s, catalog, d, scope)
+	model, err := packageSbomModel(s)
 	if err != nil {
 		return "", fmt.Errorf("unable to create PackageSBOM model: %w", err)
 	}

internal/anchore/import_package_sbom_test.go

@@ -9,18 +9,17 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/anchore/syft/internal/presenter/packages"
-
-	"github.com/wagoodman/go-progress"
-
-	"github.com/anchore/syft/syft/distro"
-
-	"github.com/docker/docker/pkg/ioutils"
+	"github.com/anchore/syft/syft/sbom"
 
 	"github.com/anchore/client-go/pkg/external"
+	"github.com/anchore/syft/internal/formats/syftjson"
+	syftjsonModel "github.com/anchore/syft/internal/formats/syftjson/model"
+	"github.com/anchore/syft/syft/distro"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/source"
+	"github.com/docker/docker/pkg/ioutils"
 	"github.com/go-test/deep"
+	"github.com/wagoodman/go-progress"
 )
 
 func must(c pkg.CPE, e error) pkg.CPE {
@@ -60,8 +59,10 @@ func TestPackageSbomToModel(t *testing.T) {
 		FoundBy: "foundBy",
 		Locations: []source.Location{
 			{
-				RealPath:     "path",
-				FileSystemID: "layerID",
+				Coordinates: source.Coordinates{
+					RealPath:     "path",
+					FileSystemID: "layerID",
+				},
 			},
 		},
 		Licenses: []string{"license"},
@@ -75,7 +76,15 @@ func TestPackageSbomToModel(t *testing.T) {
 
 	c := pkg.NewCatalog(p)
 
-	model, err := packageSbomModel(m, c, &d, source.AllLayersScope)
+	sbomResult := sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			PackageCatalog: c,
+			Distro:         &d,
+		},
+		Source: m,
+	}
+
+	model, err := packageSbomModel(sbomResult)
 	if err != nil {
 		t.Fatalf("unable to generate model from source material: %+v", err)
 	}
@@ -87,20 +96,28 @@ func TestPackageSbomToModel(t *testing.T) {
 		t.Fatalf("unable to marshal model: %+v", err)
 	}
 
+	s := sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			PackageCatalog: c,
+			Distro:         &d,
+		},
+		Source: m,
+	}
+
 	var buf bytes.Buffer
-	pres := packages.NewJSONPresenter(c, m, &d, source.AllLayersScope)
+	pres := syftjson.Format().Presenter(s)
 	if err := pres.Present(&buf); err != nil {
 		t.Fatalf("unable to get expected json: %+v", err)
 	}
 
 	// unmarshal expected result
-	var expectedDoc packages.JSONDocument
+	var expectedDoc syftjsonModel.Document
 	if err := json.Unmarshal(buf.Bytes(), &expectedDoc); err != nil {
 		t.Fatalf("unable to parse json doc: %+v", err)
 	}
 
 	// unmarshal actual result
-	var actualDoc packages.JSONDocument
+	var actualDoc syftjsonModel.Document
 	if err := json.Unmarshal(modelJSON, &actualDoc); err != nil {
 		t.Fatalf("unable to parse json doc: %+v", err)
 	}
@@ -142,8 +159,10 @@ func TestPackageSbomImport(t *testing.T) {
 		FoundBy: "foundBy",
 		Locations: []source.Location{
 			{
-				RealPath:     "path",
-				FileSystemID: "layerID",
+				Coordinates: source.Coordinates{
+					RealPath:     "path",
+					FileSystemID: "layerID",
+				},
 			},
 		},
 		Licenses: []string{"license"},
@@ -190,7 +209,15 @@ func TestPackageSbomImport(t *testing.T) {
 
 	d, _ := distro.NewDistro(distro.CentOS, "8.0", "")
 
-	theModel, err := packageSbomModel(m, catalog, &d, source.AllLayersScope)
+	sbomResult := sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			PackageCatalog: catalog,
+			Distro:         &d,
+		},
+		Source: m,
+	}
+
+	theModel, err := packageSbomModel(sbomResult)
 	if err != nil {
 		t.Fatalf("could not get sbom model: %+v", err)
 	}
@@ -229,7 +256,7 @@ func TestPackageSbomImport(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 
-			digest, err := importPackageSBOM(context.TODO(), test.api, sessionID, m, catalog, &d, source.AllLayersScope, &progress.Stage{})
+			digest, err := importPackageSBOM(context.TODO(), test.api, sessionID, sbomResult, &progress.Stage{})
 
 			// validate error handling
 			if err != nil && !test.expectsError {

internal/config/anchore.go

@@ -12,6 +12,8 @@ type anchore struct {
 	Password               string `yaml:"-" json:"-" mapstructure:"password"`                                                               // -p , password to authenticate upload
 	Dockerfile             string `yaml:"dockerfile" json:"dockerfile" mapstructure:"dockerfile"`                                           // -d , dockerfile to attach for upload
 	OverwriteExistingImage bool   `yaml:"overwrite-existing-image" json:"overwrite-existing-image" mapstructure:"overwrite-existing-image"` // --overwrite-existing-image , if any of the SBOM components have already been uploaded this flag will ensure they are overwritten with the current upload
+	ImportTimeout          uint   `yaml:"import-timeout" json:"import-timeout" mapstructure:"import-timeout"`                               // --import-timeout
+	// , customize the number of seconds within which the SBOM import must be completed or canceled
 }
 
 func (cfg anchore) loadDefaultValues(v *viper.Viper) {

internal/config/application.go

@@ -3,7 +3,10 @@ package config
 import (
 	"errors"
 	"fmt"
+	"os"
+	"os/exec"
 	"path"
+	"path/filepath"
 	"reflect"
 	"strings"
 
@@ -17,6 +20,8 @@ import (
 
 var ErrApplicationConfigNotFound = fmt.Errorf("application config not found")
 
+var catalogerEnabledDefault = false
+
 type defaultValueLoader interface {
 	loadDefaultValues(*viper.Viper)
 }
@@ -29,6 +34,7 @@ type parser interface {
 type Application struct {
 	ConfigPath         string             `yaml:",omitempty" json:"configPath"`                                                         // the location where the application config was read from (either from -c or discovered while loading)
 	Output             string             `yaml:"output" json:"output" mapstructure:"output"`                                           // -o, the Presenter hint string to use for report formatting
+	File               string             `yaml:"file" json:"file" mapstructure:"file"`                                                 // --file, the file to write report output to
 	Quiet              bool               `yaml:"quiet" json:"quiet" mapstructure:"quiet"`                                              // -q, indicates to not show any status output to stderr (ETUI or logging UI)
 	CheckForAppUpdate  bool               `yaml:"check-for-app-update" json:"check-for-app-update" mapstructure:"check-for-app-update"` // whether to check for an application update on start up or not
 	Anchore            anchore            `yaml:"anchore" json:"anchore" mapstructure:"anchore"`                                        // options for interacting with Anchore Engine/Enterprise
@@ -43,6 +49,11 @@ type Application struct {
 	Registry           registry           `yaml:"registry" json:"registry" mapstructure:"registry"`
 }
 
+// PowerUserCatalogerEnabledDefault switches all catalogers to be enabled when running power-user command
+func PowerUserCatalogerEnabledDefault() {
+	catalogerEnabledDefault = true
+}
+
 func newApplicationConfig(v *viper.Viper, cliOpts CliOnlyOptions) *Application {
 	config := &Application{
 		CliOptions: cliOpts,
@@ -88,42 +99,18 @@ func (cfg Application) loadDefaultValues(v *viper.Viper) {
 	}
 }
 
-// build inflates simple config values into syft native objects (or other complex objects) after the config is fully read in.
 func (cfg *Application) parseConfigValues() error {
-	if cfg.Quiet {
-		// TODO: this is bad: quiet option trumps all other logging options
-		// we should be able to quiet the console logging and leave file logging alone...
-		// ... this will be an enhancement for later
-		cfg.Log.LevelOpt = logrus.PanicLevel
-	} else {
-		if cfg.Log.Level != "" {
-			if cfg.CliOptions.Verbosity > 0 {
-				return fmt.Errorf("cannot explicitly set log level (cfg file or env var) and use -v flag together")
-			}
-
-			lvl, err := logrus.ParseLevel(strings.ToLower(cfg.Log.Level))
-			if err != nil {
-				return fmt.Errorf("bad log level configured (%q): %w", cfg.Log.Level, err)
-			}
-			// set the log level explicitly
-			cfg.Log.LevelOpt = lvl
-		} else {
-			// set the log level implicitly
-			switch v := cfg.CliOptions.Verbosity; {
-			case v == 1:
-				cfg.Log.LevelOpt = logrus.InfoLevel
-			case v >= 2:
-				cfg.Log.LevelOpt = logrus.DebugLevel
-			default:
-				cfg.Log.LevelOpt = logrus.WarnLevel
-			}
+	// parse application config options
+	for _, optionFn := range []func() error{
+		cfg.parseUploadOptions,
+		cfg.parseLogLevelOption,
+	} {
+		if err := optionFn(); err != nil {
+			return err
 		}
 	}
 
-	if cfg.Anchore.Host == "" && cfg.Anchore.Dockerfile != "" {
-		return fmt.Errorf("cannot provide dockerfile option without enabling upload")
-	}
-
+	// parse nested config options
 	// for each field in the configuration struct, see if the field implements the parser interface
 	// note: the app config is a pointer, so we need to grab the elements explicitly (to traverse the address)
 	value := reflect.ValueOf(cfg).Elem()
@@ -136,6 +123,52 @@ func (cfg *Application) parseConfigValues() error {
 			}
 		}
 	}
+	return nil
+}
+
+func (cfg *Application) parseUploadOptions() error {
+	if cfg.Anchore.Host == "" && cfg.Anchore.Dockerfile != "" {
+		return fmt.Errorf("cannot provide dockerfile option without enabling upload")
+	}
+	return nil
+}
+
+func (cfg *Application) parseLogLevelOption() error {
+	switch {
+	case cfg.Quiet:
+		// TODO: this is bad: quiet option trumps all other logging options (such as to a file on disk)
+		// we should be able to quiet the console logging and leave file logging alone...
+		// ... this will be an enhancement for later
+		cfg.Log.LevelOpt = logrus.PanicLevel
+	case cfg.Log.Level != "":
+		if cfg.CliOptions.Verbosity > 0 {
+			return fmt.Errorf("cannot explicitly set log level (cfg file or env var) and use -v flag together")
+		}
+
+		lvl, err := logrus.ParseLevel(strings.ToLower(cfg.Log.Level))
+		if err != nil {
+			return fmt.Errorf("bad log level configured (%q): %w", cfg.Log.Level, err)
+		}
+
+		cfg.Log.LevelOpt = lvl
+		if cfg.Log.LevelOpt >= logrus.InfoLevel {
+			cfg.CliOptions.Verbosity = 1
+		}
+	default:
+
+		switch v := cfg.CliOptions.Verbosity; {
+		case v == 1:
+			cfg.Log.LevelOpt = logrus.InfoLevel
+		case v >= 2:
+			cfg.Log.LevelOpt = logrus.DebugLevel
+		default:
+			cfg.Log.LevelOpt = logrus.ErrorLevel
+		}
+	}
+
+	if cfg.Log.Level == "" {
+		cfg.Log.Level = cfg.Log.LevelOpt.String()
+	}
 
 	return nil
 }
@@ -176,44 +209,80 @@ func readConfig(v *viper.Viper, configPath string) error {
 	// 1. look for .<appname>.yaml (in the current directory)
 	v.AddConfigPath(".")
 	v.SetConfigName("." + internal.ApplicationName)
-	if err = v.ReadInConfig(); err == nil {
-		return nil
-	} else if !errors.As(err, &viper.ConfigFileNotFoundError{}) {
-		return fmt.Errorf("unable to parse config=%q: %w", v.ConfigFileUsed(), err)
+	if exists, err := readViperConfig(v); exists || err != nil {
+		return err
 	}
 
 	// 2. look for .<appname>/config.yaml (in the current directory)
 	v.AddConfigPath("." + internal.ApplicationName)
 	v.SetConfigName("config")
-	if err = v.ReadInConfig(); err == nil {
-		return nil
-	} else if !errors.As(err, &viper.ConfigFileNotFoundError{}) {
-		return fmt.Errorf("unable to parse config=%q: %w", v.ConfigFileUsed(), err)
+	if exists, err := readViperConfig(v); exists || err != nil {
+		return err
 	}
 
-	// 3. look for ~/.<appname>.yaml
+	if root := gitRepoRoot(); root != "" {
+		// 3. look for <git repo root>/.<appname>.yaml, where the repo root is defined by "git rev-parse --show-toplevel"
+		v.AddConfigPath(root)
+		v.SetConfigName("." + internal.ApplicationName)
+		if exists, err := readViperConfig(v); exists {
+			if err != nil {
+				return err
+			}
+			return os.Chdir(root)
+		}
+
+		// 4. look for <git repo root>/.<appname>/config.yaml, where the repo root is defined by "git rev-parse --show-toplevel"
+		v.AddConfigPath(filepath.Join(root, "."+internal.ApplicationName))
+		v.SetConfigName("config")
+		if exists, err := readViperConfig(v); exists {
+			if err != nil {
+				return err
+			}
+			return os.Chdir(root)
+		}
+	}
+
+	// 5. look for ~/.<appname>.yaml
 	home, err := homedir.Dir()
 	if err == nil {
 		v.AddConfigPath(home)
 		v.SetConfigName("." + internal.ApplicationName)
-		if err = v.ReadInConfig(); err == nil {
-			return nil
-		} else if !errors.As(err, &viper.ConfigFileNotFoundError{}) {
-			return fmt.Errorf("unable to parse config=%q: %w", v.ConfigFileUsed(), err)
+		if exists, err := readViperConfig(v); exists || err != nil {
+			return err
 		}
 	}
 
-	// 4. look for <appname>/config.yaml in xdg locations (starting with xdg home config dir, then moving upwards)
+	// 6. look for <appname>/config.yaml in xdg locations (starting with xdg home config dir, then moving upwards)
 	v.AddConfigPath(path.Join(xdg.ConfigHome, internal.ApplicationName))
 	for _, dir := range xdg.ConfigDirs {
 		v.AddConfigPath(path.Join(dir, internal.ApplicationName))
 	}
 	v.SetConfigName("config")
-	if err = v.ReadInConfig(); err == nil {
-		return nil
-	} else if !errors.As(err, &viper.ConfigFileNotFoundError{}) {
-		return fmt.Errorf("unable to parse config=%q: %w", v.ConfigFileUsed(), err)
+	if exists, err := readViperConfig(v); exists || err != nil {
+		return err
 	}
 
 	return ErrApplicationConfigNotFound
 }
+
+func readViperConfig(v *viper.Viper) (bool, error) {
+	err := v.ReadInConfig()
+	if err == nil {
+		return true, nil
+	} else if errors.As(err, &viper.ConfigFileNotFoundError{}) {
+		return false, nil
+	}
+	return true, fmt.Errorf("unable to parse config=%q: %w", v.ConfigFileUsed(), err)
+}
+
+func gitRepoRoot() string {
+	root, err := exec.Command("git", "rev-parse", "--show-toplevel").Output()
+	if err != nil {
+		return ""
+	}
+	absRepoRoot, err := filepath.Abs(strings.TrimSpace(string(root)))
+	if err != nil {
+		return ""
+	}
+	return absRepoRoot
+}

internal/config/file_classification.go

@@ -10,7 +10,7 @@ type fileClassification struct {
 }
 
 func (cfg fileClassification) loadDefaultValues(v *viper.Viper) {
-	v.SetDefault("file-classification.cataloger.enabled", true)
+	v.SetDefault("file-classification.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("file-classification.cataloger.scope", source.SquashedScope)
 }
 

internal/config/file_contents.go

@@ -13,7 +13,7 @@ type fileContents struct {
 }
 
 func (cfg fileContents) loadDefaultValues(v *viper.Viper) {
-	v.SetDefault("file-contents.cataloger.enabled", true)
+	v.SetDefault("file-contents.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("file-contents.cataloger.scope", source.SquashedScope)
 	v.SetDefault("file-contents.skip-files-above-size", 1*file.MB)
 	v.SetDefault("file-contents.globs", []string{})

internal/config/file_metadata.go

@@ -11,7 +11,7 @@ type FileMetadata struct {
 }
 
 func (cfg FileMetadata) loadDefaultValues(v *viper.Viper) {
-	v.SetDefault("file-metadata.cataloger.enabled", true)
+	v.SetDefault("file-metadata.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("file-metadata.cataloger.scope", source.SquashedScope)
 	v.SetDefault("file-metadata.digests", []string{"sha256"})
 }

internal/config/registry.go

@@ -20,11 +20,13 @@ type RegistryCredentials struct {
 
 type registry struct {
 	InsecureSkipTLSVerify bool                  `yaml:"insecure-skip-tls-verify" json:"insecure-skip-tls-verify" mapstructure:"insecure-skip-tls-verify"`
+	InsecureUseHTTP       bool                  `yaml:"insecure-use-http" json:"insecure-use-http" mapstructure:"insecure-use-http"`
 	Auth                  []RegistryCredentials `yaml:"auth" json:"auth" mapstructure:"auth"`
 }
 
 func (cfg registry) loadDefaultValues(v *viper.Viper) {
 	v.SetDefault("registry.insecure-skip-tls-verify", false)
+	v.SetDefault("registry.insecure-use-http", false)
 	v.SetDefault("registry.auth", []RegistryCredentials{})
 }
 
@@ -37,7 +39,7 @@ func (cfg *registry) parseConfigValues() error {
 		os.Getenv("SYFT_REGISTRY_AUTH_PASSWORD"),
 		os.Getenv("SYFT_REGISTRY_AUTH_TOKEN")
 
-	if hasNonEmptyCredentials(authority, username, password, token) {
+	if hasNonEmptyCredentials(username, password, token) {
 		// note: we prepend the credentials such that the environment variables take precedence over on-disk configuration.
 		cfg.Auth = append([]RegistryCredentials{
 			{
@@ -51,8 +53,8 @@ func (cfg *registry) parseConfigValues() error {
 	return nil
 }
 
-func hasNonEmptyCredentials(authority, username, password, token string) bool {
-	return authority != "" && password != "" && username != "" || authority != "" && token != ""
+func hasNonEmptyCredentials(username, password, token string) bool {
+	return password != "" && username != "" || token != ""
 }
 
 func (cfg *registry) ToOptions() *image.RegistryOptions {
@@ -67,6 +69,7 @@ func (cfg *registry) ToOptions() *image.RegistryOptions {
 	}
 	return &image.RegistryOptions{
 		InsecureSkipTLSVerify: cfg.InsecureSkipTLSVerify,
+		InsecureUseHTTP:       cfg.InsecureUseHTTP,
 		Credentials:           auth,
 	}
 }

internal/config/registry_test.go

@@ -2,6 +2,7 @@ package config
 
 import (
 	"fmt"
+	"github.com/anchore/stereoscope/pkg/image"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -9,51 +10,102 @@ import (
 
 func TestHasNonEmptyCredentials(t *testing.T) {
 	tests := []struct {
-		auth, username, password, token string
-		expected                        bool
+		username, password, token string
+		expected                  bool
 	}{
+
 		{
-			"", "", "", "",
+			"", "", "",
 			false,
 		},
 		{
-			"auth", "", "", "",
+			"user", "", "",
 			false,
 		},
 		{
-			"auth", "user", "", "",
+			"", "pass", "",
 			false,
 		},
 		{
-			"auth", "", "pass", "",
-			false,
-		},
-		{
-			"auth", "", "pass", "tok",
+			"", "pass", "tok",
 			true,
 		},
 		{
-			"auth", "user", "", "tok",
+			"user", "", "tok",
 			true,
 		},
 		{
-			"auth", "", "", "tok",
+			"", "", "tok",
 			true,
 		},
 		{
-			"auth", "user", "pass", "tok",
+			"user", "pass", "tok",
 			true,
 		},
 
 		{
-			"auth", "user", "pass", "",
+			"user", "pass", "",
 			true,
 		},
 	}
 
 	for _, test := range tests {
 		t.Run(fmt.Sprintf("%+v", test), func(t *testing.T) {
-			assert.Equal(t, test.expected, hasNonEmptyCredentials(test.auth, test.username, test.password, test.token))
+			assert.Equal(t, test.expected, hasNonEmptyCredentials(test.username, test.password, test.token))
+		})
+	}
+}
+
+func Test_registry_ToOptions(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    registry
+		expected image.RegistryOptions
+	}{
+		{
+			name:  "no registry options",
+			input: registry{},
+			expected: image.RegistryOptions{
+				Credentials: []image.RegistryCredentials{},
+			},
+		},
+		{
+			name: "set InsecureSkipTLSVerify",
+			input: registry{
+				InsecureSkipTLSVerify: true,
+			},
+			expected: image.RegistryOptions{
+				InsecureSkipTLSVerify: true,
+				Credentials:           []image.RegistryCredentials{},
+			},
+		},
+		{
+			name: "set InsecureUseHTTP",
+			input: registry{
+				InsecureUseHTTP: true,
+			},
+			expected: image.RegistryOptions{
+				InsecureUseHTTP: true,
+				Credentials:     []image.RegistryCredentials{},
+			},
+		},
+		{
+			name: "set all bool options",
+			input: registry{
+				InsecureSkipTLSVerify: true,
+				InsecureUseHTTP:       true,
+			},
+			expected: image.RegistryOptions{
+				InsecureSkipTLSVerify: true,
+				InsecureUseHTTP:       true,
+				Credentials:           []image.RegistryCredentials{},
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, &test.expected, test.input.ToOptions())
 		})
 	}
 }

internal/config/secrets.go

@@ -15,7 +15,7 @@ type secrets struct {
 }
 
 func (cfg secrets) loadDefaultValues(v *viper.Viper) {
-	v.SetDefault("secrets.cataloger.enabled", true)
+	v.SetDefault("secrets.cataloger.enabled", catalogerEnabledDefault)
 	v.SetDefault("secrets.cataloger.scope", source.AllLayersScope)
 	v.SetDefault("secrets.reveal-values", false)
 	v.SetDefault("secrets.skip-files-above-size", 1*file.MB)

internal/constants.go

@@ -6,5 +6,5 @@ const (
 
 	// JSONSchemaVersion is the current schema version output by the JSON presenter
 	// This is roughly following the "SchemaVer" guidelines for versioning the JSON schema. Please see schema/json/README.md for details on how to increment.
-	JSONSchemaVersion = "1.1.0"
+	JSONSchemaVersion = "2.0.0"
 )

internal/err_helper.go

@@ -0,0 +1,38 @@
+package internal
+
+import (
+	"fmt"
+	"io"
+	"os"
+
+	"github.com/anchore/syft/internal/log"
+)
+
+// CloseAndLogError closes the given io.Closer and reports any errors found as a warning in the log
+func CloseAndLogError(closer io.Closer, location string) {
+	if err := closer.Close(); err != nil {
+		log.Warnf("unable to close file for location=%q: %+v", location, err)
+	}
+}
+
+type ErrPath struct {
+	Path string
+	Err  error
+}
+
+func (e ErrPath) Error() string {
+	return fmt.Sprintf("unable to observe contents of %+v: %v", e.Path, e.Err)
+}
+
+func IsErrPath(err error) bool {
+	_, ok := err.(ErrPath)
+	return ok
+}
+
+func IsErrPathPermission(err error) bool {
+	pathErr, ok := err.(ErrPath)
+	if ok {
+		return os.IsPermission(pathErr.Err)
+	}
+	return ok
+}

internal/file/zip_file_helpers_test.go

@@ -1,7 +1,6 @@
 package file
 
 import (
-	"fmt"
 	"io/ioutil"
 	"os"
 	"os/exec"
@@ -9,6 +8,8 @@ import (
 	"path/filepath"
 	"syscall"
 	"testing"
+
+	"github.com/stretchr/testify/assert"
 )
 
 var expectedZipArchiveEntries = []string{
@@ -18,35 +19,21 @@ var expectedZipArchiveEntries = []string{
 	"nested.zip",
 }
 
-// fatalIfError calls the supplied function. If the function returns a non-nil error, t.Fatal(err) is called.
-func fatalIfError(t *testing.T, fn func() error) {
-	t.Helper()
-
-	if fn == nil {
-		return
-	}
-
-	err := fn()
-	if err != nil {
-		t.Fatal(err)
-	}
-}
-
 // createZipArchive creates a new ZIP archive file at destinationArchivePath based on the directory found at
 // sourceDirPath.
-func createZipArchive(t *testing.T, sourceDirPath, destinationArchivePath string) error {
+func createZipArchive(t testing.TB, sourceDirPath, destinationArchivePath string) {
 	t.Helper()
 
 	cwd, err := os.Getwd()
 	if err != nil {
-		return fmt.Errorf("unable to get cwd: %+v", err)
+		t.Fatalf("unable to get cwd: %+v", err)
 	}
 
-	cmd := exec.Command("./generate-zip-fixture.sh", destinationArchivePath, path.Base(sourceDirPath))
+	cmd := exec.Command("./generate-zip-fixture-from-source-dir.sh", destinationArchivePath, path.Base(sourceDirPath))
 	cmd.Dir = filepath.Join(cwd, "test-fixtures")
 
 	if err := cmd.Start(); err != nil {
-		return fmt.Errorf("unable to start generate zip fixture script: %+v", err)
+		t.Fatalf("unable to start generate zip fixture script: %+v", err)
 	}
 
 	if err := cmd.Wait(); err != nil {
@@ -59,61 +46,62 @@ func createZipArchive(t *testing.T, sourceDirPath, destinationArchivePath string
 			// an ExitStatus() method with the same signature.
 			if status, ok := exiterr.Sys().(syscall.WaitStatus); ok {
 				if status.ExitStatus() != 0 {
-					return fmt.Errorf("failed to generate fixture: rc=%d", status.ExitStatus())
+					t.Fatalf("failed to generate fixture: rc=%d", status.ExitStatus())
 				}
 			}
 		} else {
-			return fmt.Errorf("unable to get generate fixture script result: %+v", err)
+			t.Fatalf("unable to get generate fixture script result: %+v", err)
 		}
 	}
 
-	return nil
+}
+
+func assertNoError(t testing.TB, fn func() error) func() {
+	return func() {
+		assert.NoError(t, fn())
+	}
 }
 
 // setupZipFileTest encapsulates common test setup work for zip file tests. It returns a cleanup function,
 // which should be called (typically deferred) by the caller, the path of the created zip archive, and an error,
 // which should trigger a fatal test failure in the consuming test. The returned cleanup function will never be nil
 // (even if there's an error), and it should always be called.
-func setupZipFileTest(t *testing.T, sourceDirPath string) (func() error, string, error) {
+func setupZipFileTest(t testing.TB, sourceDirPath string) string {
 	t.Helper()
 
-	// Keep track of any needed cleanup work as we go
-	var cleanupFns []func() error
-	cleanup := func(fns []func() error) func() error {
-		return func() error {
-			for _, fn := range fns {
-				err := fn()
-				if err != nil {
-					return err
-				}
-			}
-
-			return nil
-		}
-	}
-
 	archivePrefix, err := ioutil.TempFile("", "syft-ziputil-archive-TEST-")
 	if err != nil {
-		return cleanup(cleanupFns), "", fmt.Errorf("unable to create tempfile: %+v", err)
+		t.Fatalf("unable to create tempfile: %+v", err)
 	}
-	cleanupFns = append(cleanupFns, func() error { return os.Remove(archivePrefix.Name()) })
+
+	t.Cleanup(
+		assertNoError(t,
+			func() error {
+				return os.Remove(archivePrefix.Name())
+			},
+		),
+	)
 
 	destinationArchiveFilePath := archivePrefix.Name() + ".zip"
 	t.Logf("archive path: %s", destinationArchiveFilePath)
-	err = createZipArchive(t, sourceDirPath, destinationArchiveFilePath)
-	cleanupFns = append(cleanupFns, func() error { return os.Remove(destinationArchiveFilePath) })
-	if err != nil {
-		return cleanup(cleanupFns), "", err
-	}
+	createZipArchive(t, sourceDirPath, destinationArchiveFilePath)
+
+	t.Cleanup(
+		assertNoError(t,
+			func() error {
+				return os.Remove(destinationArchiveFilePath)
+			},
+		),
+	)
 
 	cwd, err := os.Getwd()
 	if err != nil {
-		return cleanup(cleanupFns), "", fmt.Errorf("unable to get cwd: %+v", err)
+		t.Fatalf("unable to get cwd: %+v", err)
 	}
 
 	t.Logf("running from: %s", cwd)
 
-	return cleanup(cleanupFns), destinationArchiveFilePath, nil
+	return destinationArchiveFilePath
 }
 
 // TODO: Consider moving any non-git asset generation to a task (e.g. make) that's run ahead of running go tests.
@@ -121,11 +109,7 @@ func ensureNestedZipExists(t *testing.T, sourceDirPath string) error {
 	t.Helper()
 
 	nestedArchiveFilePath := path.Join(sourceDirPath, "nested.zip")
-	err := createZipArchive(t, sourceDirPath, nestedArchiveFilePath)
-
-	if err != nil {
-		return fmt.Errorf("unable to create nested archive for test fixture: %+v", err)
-	}
+	createZipArchive(t, sourceDirPath, nestedArchiveFilePath)
 
 	return nil
 }

internal/file/zip_file_manifest.go

@@ -1,23 +1,36 @@
 package file
 
 import (
-	"archive/zip"
 	"fmt"
 	"os"
 	"sort"
 	"strings"
 
 	"github.com/anchore/syft/internal"
-
 	"github.com/anchore/syft/internal/log"
 )
 
 // ZipFileManifest is a collection of paths and their file metadata.
 type ZipFileManifest map[string]os.FileInfo
 
-// newZipManifest creates an empty ZipFileManifest.
-func newZipManifest() ZipFileManifest {
-	return make(ZipFileManifest)
+// NewZipFileManifest creates and returns a new ZipFileManifest populated with path and metadata from the given zip archive path.
+func NewZipFileManifest(archivePath string) (ZipFileManifest, error) {
+	zipReader, err := OpenZip(archivePath)
+	manifest := make(ZipFileManifest)
+	if err != nil {
+		return manifest, fmt.Errorf("unable to open zip archive (%s): %w", archivePath, err)
+	}
+	defer func() {
+		err = zipReader.Close()
+		if err != nil {
+			log.Warnf("unable to close zip archive (%s): %+v", archivePath, err)
+		}
+	}()
+
+	for _, file := range zipReader.Reader.File {
+		manifest.Add(file.Name, file.FileInfo())
+	}
+	return manifest, nil
 }
 
 // Add a new path and it's file metadata to the collection.
@@ -47,26 +60,6 @@ func (z ZipFileManifest) GlobMatch(patterns ...string) []string {
 	return results
 }
 
-// NewZipFileManifest creates and returns a new ZipFileManifest populated with path and metadata from the given zip archive path.
-func NewZipFileManifest(archivePath string) (ZipFileManifest, error) {
-	zipReader, err := zip.OpenReader(archivePath)
-	manifest := newZipManifest()
-	if err != nil {
-		return manifest, fmt.Errorf("unable to open zip archive (%s): %w", archivePath, err)
-	}
-	defer func() {
-		err = zipReader.Close()
-		if err != nil {
-			log.Errorf("unable to close zip archive (%s): %+v", archivePath, err)
-		}
-	}()
-
-	for _, file := range zipReader.Reader.File {
-		manifest.Add(file.Name, file.FileInfo())
-	}
-	return manifest, nil
-}
-
 // normalizeZipEntryName takes the given path entry and ensures it is prefixed with "/".
 func normalizeZipEntryName(entry string) string {
 	if !strings.HasPrefix(entry, "/") {

internal/file/zip_file_manifest_test.go

@@ -19,11 +19,7 @@ func TestNewZipFileManifest(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	cleanup, archiveFilePath, err := setupZipFileTest(t, sourceDirPath)
-	defer fatalIfError(t, cleanup)
-	if err != nil {
-		t.Fatal(err)
-	}
+	archiveFilePath := setupZipFileTest(t, sourceDirPath)
 
 	actual, err := NewZipFileManifest(archiveFilePath)
 	if err != nil {
@@ -63,12 +59,7 @@ func TestZipFileManifest_GlobMatch(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	cleanup, archiveFilePath, err := setupZipFileTest(t, sourceDirPath)
-	//goland:noinspection GoNilness
-	defer fatalIfError(t, cleanup)
-	if err != nil {
-		t.Fatal(err)
-	}
+	archiveFilePath := setupZipFileTest(t, sourceDirPath)
 
 	z, err := NewZipFileManifest(archiveFilePath)
 	if err != nil {

internal/file/zip_file_traversal.go

@@ -47,7 +47,7 @@ func newZipTraverseRequest(paths ...string) zipTraversalRequest {
 func TraverseFilesInZip(archivePath string, visitor func(*zip.File) error, paths ...string) error {
 	request := newZipTraverseRequest(paths...)
 
-	zipReader, err := zip.OpenReader(archivePath)
+	zipReader, err := OpenZip(archivePath)
 	if err != nil {
 		return fmt.Errorf("unable to open zip archive (%s): %w", archivePath, err)
 	}

internal/file/zip_file_traversal_test.go

@@ -44,14 +44,12 @@ func TestUnzipToDir(t *testing.T) {
 
 	goldenRootDir := filepath.Join(cwd, "test-fixtures")
 	sourceDirPath := path.Join(goldenRootDir, "zip-source")
-	cleanup, archiveFilePath, err := setupZipFileTest(t, sourceDirPath)
-	defer fatalIfError(t, cleanup)
-	if err != nil {
-		t.Fatal(err)
-	}
+	archiveFilePath := setupZipFileTest(t, sourceDirPath)
 
 	unzipDestinationDir, err := ioutil.TempDir("", "syft-ziputil-contents-TEST-")
-	defer os.RemoveAll(unzipDestinationDir)
+	t.Cleanup(assertNoError(t, func() error {
+		return os.RemoveAll(unzipDestinationDir)
+	}))
 	if err != nil {
 		t.Fatalf("unable to create tempdir: %+v", err)
 	}
@@ -127,41 +125,119 @@ func TestUnzipToDir(t *testing.T) {
 }
 
 func TestContentsFromZip(t *testing.T) {
-	archivePrefix, err := ioutil.TempFile("", "syft-ziputil-archive-TEST-")
+	tests := []struct {
+		name        string
+		archivePrep func(tb testing.TB) string
+	}{
+		{
+			name:        "standard, non-nested zip",
+			archivePrep: prepZipSourceFixture,
+		},
+		{
+			name:        "zip with prepended bytes",
+			archivePrep: prependZipSourceFixtureWithString(t, "junk at the beginning of the file..."),
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			archivePath := test.archivePrep(t)
+			expected := zipSourceFixtureExpectedContents()
+
+			var paths []string
+			for p := range expected {
+				paths = append(paths, p)
+			}
+
+			actual, err := ContentsFromZip(archivePath, paths...)
+			if err != nil {
+				t.Fatalf("unable to extract from unzip archive: %+v", err)
+			}
+
+			assertZipSourceFixtureContents(t, actual, expected)
+		})
+	}
+}
+
+func prependZipSourceFixtureWithString(tb testing.TB, value string) func(tb testing.TB) string {
+	if len(value) == 0 {
+		tb.Fatalf("no bytes given to prefix")
+	}
+	return func(t testing.TB) string {
+		archivePath := prepZipSourceFixture(t)
+
+		// create a temp file
+		tmpFile, err := ioutil.TempFile("", "syft-ziputil-prependZipSourceFixtureWithString-")
+		if err != nil {
+			t.Fatalf("unable to create tempfile: %+v", err)
+		}
+		defer tmpFile.Close()
+
+		// write value to the temp file
+		if _, err := tmpFile.WriteString(value); err != nil {
+			t.Fatalf("unable to write to tempfile: %+v", err)
+		}
+
+		// open the original archive
+		sourceFile, err := os.Open(archivePath)
+		if err != nil {
+			t.Fatalf("unable to read source file: %+v", err)
+		}
+
+		// copy all contents from the archive to the temp file
+		if _, err := io.Copy(tmpFile, sourceFile); err != nil {
+			t.Fatalf("unable to copy source to dest: %+v", err)
+		}
+
+		sourceFile.Close()
+
+		// remove the original archive and replace it with the temp file
+		if err := os.Remove(archivePath); err != nil {
+			t.Fatalf("unable to remove original source archive (%q): %+v", archivePath, err)
+		}
+
+		if err := os.Rename(tmpFile.Name(), archivePath); err != nil {
+			t.Fatalf("unable to move new archive to old path (%q): %+v", tmpFile.Name(), err)
+		}
+
+		return archivePath
+	}
+}
+
+func prepZipSourceFixture(t testing.TB) string {
+	t.Helper()
+	archivePrefix, err := ioutil.TempFile("", "syft-ziputil-prepZipSourceFixture-")
 	if err != nil {
 		t.Fatalf("unable to create tempfile: %+v", err)
 	}
-	defer os.Remove(archivePrefix.Name())
+
+	t.Cleanup(func() {
+		assert.NoError(t, os.Remove(archivePrefix.Name()))
+	})
+
 	// the zip utility will add ".zip" to the end of the given name
 	archivePath := archivePrefix.Name() + ".zip"
-	defer os.Remove(archivePath)
+
+	t.Cleanup(func() {
+		assert.NoError(t, os.Remove(archivePath))
+	})
+
 	t.Logf("archive path: %s", archivePath)
 
-	err = createZipArchive(t, "zip-source", archivePrefix.Name())
-	if err != nil {
-		t.Fatal(err)
-	}
+	createZipArchive(t, "zip-source", archivePrefix.Name())
 
-	cwd, err := os.Getwd()
-	if err != nil {
-		t.Errorf("unable to get cwd: %+v", err)
-	}
+	return archivePath
+}
 
-	t.Logf("running from: %s", cwd)
-
-	aFilePath := filepath.Join("some-dir", "a-file.txt")
-	bFilePath := filepath.Join("b-file.txt")
-
-	expected := map[string]string{
-		aFilePath: "A file! nice!",
-		bFilePath: "B file...",
-	}
-
-	actual, err := ContentsFromZip(archivePath, aFilePath, bFilePath)
-	if err != nil {
-		t.Fatalf("unable to extract from unzip archive: %+v", err)
+func zipSourceFixtureExpectedContents() map[string]string {
+	return map[string]string{
+		filepath.Join("some-dir", "a-file.txt"): "A file! nice!",
+		filepath.Join("b-file.txt"):             "B file...",
 	}
+}
 
+func assertZipSourceFixtureContents(t testing.TB, actual map[string]string, expected map[string]string) {
+	t.Helper()
 	diffs := deep.Equal(actual, expected)
 	if len(diffs) > 0 {
 		for _, d := range diffs {

internal/file/zip_read_closer.go

@@ -0,0 +1,149 @@
+package file
+
+import (
+	"archive/zip"
+	"encoding/binary"
+	"fmt"
+	"io"
+	"os"
+)
+
+// directoryEndLen, readByf, directoryEnd, and findSignatureInBlock were copied from the golang stdlib, specifically:
+// - https://github.com/golang/go/blob/go1.16.4/src/archive/zip/struct.go
+// - https://github.com/golang/go/blob/go1.16.4/src/archive/zip/reader.go
+// findArchiveStartOffset is derived from the same stdlib utils, specifically the readDirectoryEnd function.
+
+const directoryEndLen = 22
+
+// ZipReadCloser is a drop-in replacement for zip.ReadCloser (from zip.OpenReader) that additionally considers zips
+// that have bytes prefixed to the front of the archive (common with self-extracting jars).
+type ZipReadCloser struct {
+	*zip.Reader
+	io.Closer
+}
+
+// OpenZip provides a ZipReadCloser for the given filepath.
+func OpenZip(filepath string) (*ZipReadCloser, error) {
+	f, err := os.Open(filepath)
+	if err != nil {
+		return nil, err
+	}
+	fi, err := f.Stat()
+	if err != nil {
+		f.Close()
+		return nil, err
+	}
+
+	// some archives may have bytes prepended to the front of the archive, such as with self executing JARs. We first
+	// need to find the start of the archive and keep track of this offset.
+	offset, err := findArchiveStartOffset(f, fi.Size())
+	if err != nil {
+		return nil, fmt.Errorf("cannot find beginning of zip archive=%q : %w", filepath, err)
+	}
+
+	if _, err := f.Seek(0, io.SeekStart); err != nil {
+		return nil, fmt.Errorf("unable to seek to beginning of archive: %w", err)
+	}
+
+	size := fi.Size() - int64(offset)
+
+	r, err := zip.NewReader(io.NewSectionReader(f, int64(offset), size), size)
+	if err != nil {
+		return nil, fmt.Errorf("unable to open ZipReadCloser @ %q: %w", filepath, err)
+	}
+
+	return &ZipReadCloser{
+		Reader: r,
+		Closer: f,
+	}, nil
+}
+
+type readBuf []byte
+
+func (b *readBuf) uint16() uint16 {
+	v := binary.LittleEndian.Uint16(*b)
+	*b = (*b)[2:]
+	return v
+}
+
+func (b *readBuf) uint32() uint32 {
+	v := binary.LittleEndian.Uint32(*b)
+	*b = (*b)[4:]
+	return v
+}
+
+type directoryEnd struct {
+	diskNbr            uint32 // unused
+	dirDiskNbr         uint32 // unused
+	dirRecordsThisDisk uint64 // unused
+	directoryRecords   uint64
+	directorySize      uint64
+	directoryOffset    uint64 // relative to file
+}
+
+// note: this is derived from readDirectoryEnd within the archive/zip package
+func findArchiveStartOffset(r io.ReaderAt, size int64) (startOfArchive uint64, err error) {
+	// look for directoryEndSignature in the last 1k, then in the last 65k
+	var buf []byte
+	var directoryEndOffset int64
+	for i, bLen := range []int64{1024, 65 * 1024} {
+		if bLen > size {
+			bLen = size
+		}
+		buf = make([]byte, int(bLen))
+		if _, err := r.ReadAt(buf, size-bLen); err != nil && err != io.EOF {
+			return 0, err
+		}
+		if p := findSignatureInBlock(buf); p >= 0 {
+			buf = buf[p:]
+			directoryEndOffset = size - bLen + int64(p)
+			break
+		}
+		if i == 1 || bLen == size {
+			return 0, zip.ErrFormat
+		}
+	}
+
+	if buf == nil {
+		// we were unable to find the directoryEndSignature block
+		return 0, zip.ErrFormat
+	}
+
+	// read header into struct
+	b := readBuf(buf[4:]) // skip signature
+	d := &directoryEnd{
+		diskNbr:            uint32(b.uint16()),
+		dirDiskNbr:         uint32(b.uint16()),
+		dirRecordsThisDisk: uint64(b.uint16()),
+		directoryRecords:   uint64(b.uint16()),
+		directorySize:      uint64(b.uint32()),
+		directoryOffset:    uint64(b.uint32()),
+	}
+	// Calculate where the zip data actually begins
+	startOfArchive = uint64(directoryEndOffset) - d.directorySize - d.directoryOffset
+
+	// These values mean that the file can be a zip64 file
+	if d.directoryRecords == 0xffff || d.directorySize == 0xffff || d.directoryOffset == 0xffffffff {
+		startOfArchive = 0 // Prefixed data not supported
+	}
+
+	// Make sure directoryOffset points to somewhere in our file.
+	if o := int64(d.directoryOffset); o < 0 || o >= size {
+		return 0, zip.ErrFormat
+	}
+	return startOfArchive, nil
+}
+
+func findSignatureInBlock(b []byte) int {
+	for i := len(b) - directoryEndLen; i >= 0; i-- {
+		// defined from directoryEndSignature
+		if b[i] == 'P' && b[i+1] == 'K' && b[i+2] == 0x05 && b[i+3] == 0x06 {
+			// n is length of comment
+			n := int(b[i+directoryEndLen-2]) | int(b[i+directoryEndLen-1])<<8
+			if n+directoryEndLen+i <= len(b) {
+				return i
+			}
+		}
+	}
+	return -1
+}

internal/file/zip_read_closer_test.go

@@ -0,0 +1,47 @@
+package file
+
+import (
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFindArchiveStartOffset(t *testing.T) {
+	tests := []struct {
+		name        string
+		archivePrep func(tb testing.TB) string
+		expected    uint64
+	}{
+		{
+			name:        "standard, non-nested zip",
+			archivePrep: prepZipSourceFixture,
+			expected:    0,
+		},
+		{
+			name:        "zip with prepended bytes",
+			archivePrep: prependZipSourceFixtureWithString(t, "junk at the beginning of the file..."),
+			expected:    36,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			archivePath := test.archivePrep(t)
+			f, err := os.Open(archivePath)
+			if err != nil {
+				t.Fatalf("could not open archive %q: %+v", archivePath, err)
+			}
+			fi, err := os.Stat(f.Name())
+			if err != nil {
+				t.Fatalf("unable to stat archive: %+v", err)
+			}
+
+			actual, err := findArchiveStartOffset(f, fi.Size())
+			if err != nil {
+				t.Fatalf("unable to find offset: %+v", err)
+			}
+			assert.Equal(t, test.expected, actual)
+		})
+	}
+}

internal/formats/common/spdxhelpers/description.go

@@ -0,0 +1,19 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func Description(p pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return metadata.Description
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Description
+		}
+	}
+	return ""
+}
+
+func hasMetadata(p pkg.Package) bool {
+	return p.Metadata != nil
+}

internal/formats/common/spdxhelpers/description_test.go

@@ -0,0 +1,56 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Description(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					Description: "a description!",
+				},
+			},
+			expected: "a description!",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Description: "a description!",
+				},
+			},
+			expected: "a description!",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Description(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/download_location.go

@@ -0,0 +1,23 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func DownloadLocation(p pkg.Package) string {
+	// 3.7: Package Download Location
+	// Cardinality: mandatory, one
+	// NONE if there is no download location whatsoever.
+	// NOASSERTION if:
+	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
+	//   (ii) the SPDX file creator has made no attempt to determine this field; or
+	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
+
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return NoneIfEmpty(metadata.URL)
+		case pkg.NpmPackageJSONMetadata:
+			return NoneIfEmpty(metadata.URL)
+		}
+	}
+	return "NOASSERTION"
+}

internal/formats/common/spdxhelpers/download_location_test.go

@@ -0,0 +1,54 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_DownloadLocation(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "NOASSERTION",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					URL: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					URL: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					URL: "",
+				},
+			},
+			expected: "NONE",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, DownloadLocation(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/external_refs.go

@@ -0,0 +1,51 @@
+package spdxhelpers
+
+import (
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func ExternalRefs(p pkg.Package) (externalRefs []model.ExternalRef) {
+	externalRefs = make([]model.ExternalRef, 0)
+
+	for _, c := range p.CPEs {
+		externalRefs = append(externalRefs, model.ExternalRef{
+			ReferenceCategory: model.SecurityReferenceCategory,
+			ReferenceLocator:  c.BindToFmtString(),
+			ReferenceType:     model.Cpe23ExternalRefType,
+		})
+	}
+
+	if p.PURL != "" {
+		externalRefs = append(externalRefs, model.ExternalRef{
+			ReferenceCategory: model.PackageManagerReferenceCategory,
+			ReferenceLocator:  p.PURL,
+			ReferenceType:     model.PurlExternalRefType,
+		})
+	}
+	return externalRefs
+}
+
+func ExtractPURL(refs []model.ExternalRef) string {
+	for _, r := range refs {
+		if r.ReferenceType == model.PurlExternalRefType {
+			return r.ReferenceLocator
+		}
+	}
+	return ""
+}
+
+func ExtractCPEs(refs []model.ExternalRef) (cpes []pkg.CPE) {
+	for _, r := range refs {
+		if r.ReferenceType == model.Cpe23ExternalRefType {
+			cpe, err := pkg.NewCPE(r.ReferenceLocator)
+			if err != nil {
+				log.Warnf("unable to extract SPDX CPE=%q: %+v", r.ReferenceLocator, err)
+				continue
+			}
+			cpes = append(cpes, cpe)
+		}
+	}
+	return cpes
+}

internal/formats/common/spdxhelpers/external_refs_test.go

@@ -0,0 +1,45 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/internal/formats/spdx22json/model"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_ExternalRefs(t *testing.T) {
+	testCPE := pkg.MustCPE("cpe:2.3:a:name:name:3.2:*:*:*:*:*:*:*")
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected []model.ExternalRef
+	}{
+		{
+			name: "cpe + purl",
+			input: pkg.Package{
+				CPEs: []pkg.CPE{
+					testCPE,
+				},
+				PURL: "a-purl",
+			},
+			expected: []model.ExternalRef{
+				{
+					ReferenceCategory: model.SecurityReferenceCategory,
+					ReferenceLocator:  testCPE.BindToFmtString(),
+					ReferenceType:     model.Cpe23ExternalRefType,
+				},
+				{
+					ReferenceCategory: model.PackageManagerReferenceCategory,
+					ReferenceLocator:  "a-purl",
+					ReferenceType:     model.PurlExternalRefType,
+				},
+			},
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.ElementsMatch(t, test.expected, ExternalRefs(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/homepage.go

@@ -0,0 +1,15 @@
+package spdxhelpers
+
+import "github.com/anchore/syft/syft/pkg"
+
+func Homepage(p pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.GemMetadata:
+			return metadata.Homepage
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Homepage
+		}
+	}
+	return ""
+}

internal/formats/common/spdxhelpers/homepage_test.go

@@ -0,0 +1,56 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Homepage(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from gem",
+			input: pkg.Package{
+				Metadata: pkg.GemMetadata{
+					Homepage: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "http://a-place.gov",
+				},
+			},
+			expected: "http://a-place.gov",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Homepage: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Homepage(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/license.go

@@ -0,0 +1,37 @@
+package spdxhelpers
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/internal/spdxlicense"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func License(p pkg.Package) string {
+	// source: https://spdx.github.io/spdx-spec/3-package-information/#313-concluded-license
+	// The options to populate this field are limited to:
+	// A valid SPDX License Expression as defined in Appendix IV;
+	// NONE, if the SPDX file creator concludes there is no license available for this package; or
+	// NOASSERTION if:
+	//   (i) the SPDX file creator has attempted to but cannot reach a reasonable objective determination;
+	//   (ii) the SPDX file creator has made no attempt to determine this field; or
+	//   (iii) the SPDX file creator has intentionally provided no information (no meaning should be implied by doing so).
+
+	if len(p.Licenses) == 0 {
+		return "NONE"
+	}
+
+	// take all licenses and assume an AND expression; for information about license expressions see https://spdx.github.io/spdx-spec/appendix-IV-SPDX-license-expressions/
+	var parsedLicenses []string
+	for _, l := range p.Licenses {
+		if value, exists := spdxlicense.ID(l); exists {
+			parsedLicenses = append(parsedLicenses, value)
+		}
+	}
+
+	if len(parsedLicenses) == 0 {
+		return "NOASSERTION"
+	}
+
+	return strings.Join(parsedLicenses, " AND ")
+}

internal/formats/common/spdxhelpers/license_test.go

@@ -0,0 +1,73 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_License(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			name:     "no licenses",
+			input:    pkg.Package{},
+			expected: "NONE",
+		},
+		{
+			name: "no SPDX licenses",
+			input: pkg.Package{
+				Licenses: []string{
+					"made-up",
+				},
+			},
+			expected: "NOASSERTION",
+		},
+		{
+			name: "with SPDX license",
+			input: pkg.Package{
+				Licenses: []string{
+					"MIT",
+				},
+			},
+			expected: "MIT",
+		},
+		{
+			name: "with SPDX license expression",
+			input: pkg.Package{
+				Licenses: []string{
+					"MIT",
+					"GPL-3.0",
+				},
+			},
+			expected: "MIT AND GPL-3.0",
+		},
+		{
+			name: "cap insensitive",
+			input: pkg.Package{
+				Licenses: []string{
+					"gpl-3.0",
+				},
+			},
+			expected: "GPL-3.0",
+		},
+		{
+			name: "debian to spdx conversion",
+			input: pkg.Package{
+				Licenses: []string{
+					"GPL-2",
+				},
+			},
+			expected: "GPL-2.0",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, License(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/none_if_empty.go

@@ -0,0 +1,12 @@
+package spdxhelpers
+
+import (
+	"strings"
+)
+
+func NoneIfEmpty(value string) string {
+	if strings.TrimSpace(value) == "" {
+		return "NONE"
+	}
+	return value
+}

internal/formats/common/spdxhelpers/none_if_empty_test.go

@@ -0,0 +1,41 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_noneIfEmpty(t *testing.T) {
+	tests := []struct {
+		name     string
+		value    string
+		expected string
+	}{
+		{
+			name:     "non-zero value",
+			value:    "something",
+			expected: "something",
+		},
+		{
+			name:     "empty",
+			value:    "",
+			expected: "NONE",
+		},
+		{
+			name:     "space",
+			value:    " ",
+			expected: "NONE",
+		},
+		{
+			name:     "tab",
+			value:    "\t",
+			expected: "NONE",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, NoneIfEmpty(test.value))
+		})
+	}
+}

internal/formats/common/spdxhelpers/originator_test.go

@@ -0,0 +1,114 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_Originator(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected string
+	}{
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name:     "no metadata",
+			input:    pkg.Package{},
+			expected: "",
+		},
+		{
+			name: "from gem",
+			input: pkg.Package{
+				Metadata: pkg.GemMetadata{
+					Authors: []string{
+						"auth1",
+						"auth2",
+					},
+				},
+			},
+			expected: "auth1",
+		},
+		{
+			name: "from npm",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Author: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from apk",
+			input: pkg.Package{
+				Metadata: pkg.ApkMetadata{
+					Maintainer: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from python - just name",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					Author: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from python - just email",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					AuthorEmail: "auth@auth.gov",
+				},
+			},
+			expected: "auth@auth.gov",
+		},
+		{
+			name: "from python - both name and email",
+			input: pkg.Package{
+				Metadata: pkg.PythonPackageMetadata{
+					Author:      "auth",
+					AuthorEmail: "auth@auth.gov",
+				},
+			},
+			expected: "auth <auth@auth.gov>",
+		},
+		{
+			name: "from rpm",
+			input: pkg.Package{
+				Metadata: pkg.RpmdbMetadata{
+					Vendor: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			name: "from dpkg",
+			input: pkg.Package{
+				Metadata: pkg.DpkgMetadata{
+					Maintainer: "auth",
+				},
+			},
+			expected: "auth",
+		},
+		{
+			// note: since this is an optional field, no value is preferred over NONE or NOASSERTION
+			name: "empty",
+			input: pkg.Package{
+				Metadata: pkg.NpmPackageJSONMetadata{
+					Author: "",
+				},
+			},
+			expected: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			assert.Equal(t, test.expected, Originator(test.input))
+		})
+	}
+}

internal/formats/common/spdxhelpers/origintor.go

@@ -0,0 +1,37 @@
+package spdxhelpers
+
+import (
+	"fmt"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func Originator(p pkg.Package) string {
+	if hasMetadata(p) {
+		switch metadata := p.Metadata.(type) {
+		case pkg.ApkMetadata:
+			return metadata.Maintainer
+		case pkg.NpmPackageJSONMetadata:
+			return metadata.Author
+		case pkg.PythonPackageMetadata:
+			author := metadata.Author
+			if author == "" {
+				return metadata.AuthorEmail
+			}
+			if metadata.AuthorEmail != "" {
+				author += fmt.Sprintf(" <%s>", metadata.AuthorEmail)
+			}
+			return author
+		case pkg.GemMetadata:
+			if len(metadata.Authors) > 0 {
+				return metadata.Authors[0]
+			}
+			return ""
+		case pkg.RpmdbMetadata:
+			return metadata.Vendor
+		case pkg.DpkgMetadata:
+			return metadata.Maintainer
+		}
+	}
+	return ""
+}

internal/formats/common/spdxhelpers/source_info.go

@@ -0,0 +1,41 @@
+package spdxhelpers
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func SourceInfo(p pkg.Package) string {
+	answer := ""
+	switch p.Type {
+	case pkg.RpmPkg:
+		answer = "acquired package info from RPM DB"
+	case pkg.ApkPkg:
+		answer = "acquired package info from APK DB"
+	case pkg.DebPkg:
+		answer = "acquired package info from DPKG DB"
+	case pkg.NpmPkg:
+		answer = "acquired package info from installed node module manifest file"
+	case pkg.PythonPkg:
+		answer = "acquired package info from installed python package manifest file"
+	case pkg.JavaPkg, pkg.JenkinsPluginPkg:
+		answer = "acquired package info from installed java archive"
+	case pkg.GemPkg:
+		answer = "acquired package info from installed gem metadata file"
+	case pkg.GoModulePkg:
+		answer = "acquired package info from go module information"
+	case pkg.RustPkg:
+		answer = "acquired package info from rust cargo manifest"
+	case pkg.PhpComposerPkg:
+		answer = "acquired package info from PHP composer manifest"
+	default:
+		answer = "acquired package info from the following paths"
+	}
+	var paths []string
+	for _, l := range p.Locations {
+		paths = append(paths, l.RealPath)
+	}
+
+	return answer + ": " + strings.Join(paths, ", ")
+}

internal/formats/common/spdxhelpers/source_info_test.go

@@ -0,0 +1,143 @@
+package spdxhelpers
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_SourceInfo(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    pkg.Package
+		expected []string
+	}{
+		{
+			name: "locations are captured",
+			input: pkg.Package{
+				// note: no type given
+				Locations: []source.Location{
+					source.NewVirtualLocation("/a-place", "/b-place"),
+					source.NewVirtualLocation("/c-place", "/d-place"),
+				},
+			},
+			expected: []string{
+				"from the following paths",
+				"/a-place",
+				"/c-place",
+			},
+		},
+		{
+			// note: no specific support for this
+			input: pkg.Package{
+				Type: pkg.KbPkg,
+			},
+			expected: []string{
+				"from the following paths",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.RpmPkg,
+			},
+			expected: []string{
+				"from RPM DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.ApkPkg,
+			},
+			expected: []string{
+				"from APK DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.DebPkg,
+			},
+			expected: []string{
+				"from DPKG DB",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.NpmPkg,
+			},
+			expected: []string{
+				"from installed node module manifest file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.PythonPkg,
+			},
+			expected: []string{
+				"from installed python package manifest file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.JavaPkg,
+			},
+			expected: []string{
+				"from installed java archive",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.JenkinsPluginPkg,
+			},
+			expected: []string{
+				"from installed java archive",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.GemPkg,
+			},
+			expected: []string{
+				"from installed gem metadata file",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.GoModulePkg,
+			},
+			expected: []string{
+				"from go module information",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.RustPkg,
+			},
+			expected: []string{
+				"from rust cargo manifest",
+			},
+		},
+		{
+			input: pkg.Package{
+				Type: pkg.PhpComposerPkg,
+			},
+			expected: []string{
+				"from PHP composer manifest",
+			},
+		},
+	}
+	var pkgTypes []pkg.Type
+	for _, test := range tests {
+		t.Run(test.name+" "+string(test.input.Type), func(t *testing.T) {
+			if test.input.Type != "" {
+				pkgTypes = append(pkgTypes, test.input.Type)
+			}
+			actual := SourceInfo(test.input)
+			for _, expected := range test.expected {
+				assert.Contains(t, actual, expected)
+			}
+		})
+	}
+	assert.ElementsMatch(t, pkg.AllPkgs, pkgTypes, "missing one or more package types to test against (maybe a package type was added?)")
+}

internal/formats/common/testutils/utils.go

@@ -0,0 +1,260 @@
+package testutils
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/anchore/go-presenter"
+	"github.com/anchore/go-testutils"
+	"github.com/anchore/stereoscope/pkg/filetree"
+	"github.com/anchore/stereoscope/pkg/image"
+	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft/distro"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+	"github.com/anchore/syft/syft/source"
+	"github.com/sergi/go-diff/diffmatchpatch"
+	"github.com/stretchr/testify/assert"
+)
+
+type redactor func(s []byte) []byte
+
+type imageCfg struct {
+	fromSnapshot bool
+}
+
+type ImageOption func(cfg *imageCfg)
+
+func FromSnapshot() ImageOption {
+	return func(cfg *imageCfg) {
+		cfg.fromSnapshot = true
+	}
+}
+
+func AssertPresenterAgainstGoldenImageSnapshot(t *testing.T, pres presenter.Presenter, testImage string, updateSnapshot bool, redactors ...redactor) {
+	var buffer bytes.Buffer
+
+	// grab the latest image contents and persist
+	if updateSnapshot {
+		imagetest.UpdateGoldenFixtureImage(t, testImage)
+	}
+
+	err := pres.Present(&buffer)
+	assert.NoError(t, err)
+	actual := buffer.Bytes()
+
+	// replace the expected snapshot contents with the current presenter contents
+	if updateSnapshot {
+		testutils.UpdateGoldenFileContents(t, actual)
+	}
+
+	var expected = testutils.GetGoldenFileContents(t)
+
+	// remove dynamic values, which should be tested independently
+	for _, r := range redactors {
+		actual = r(actual)
+		expected = r(expected)
+	}
+
+	// assert that the golden file snapshot matches the actual contents
+	if !bytes.Equal(expected, actual) {
+		dmp := diffmatchpatch.New()
+		diffs := dmp.DiffMain(string(expected), string(actual), true)
+		t.Errorf("mismatched output:\n%s", dmp.DiffPrettyText(diffs))
+	}
+}
+
+func AssertPresenterAgainstGoldenSnapshot(t *testing.T, pres presenter.Presenter, updateSnapshot bool, redactors ...redactor) {
+	var buffer bytes.Buffer
+
+	err := pres.Present(&buffer)
+	assert.NoError(t, err)
+	actual := buffer.Bytes()
+
+	// replace the expected snapshot contents with the current presenter contents
+	if updateSnapshot {
+		testutils.UpdateGoldenFileContents(t, actual)
+	}
+
+	var expected = testutils.GetGoldenFileContents(t)
+
+	// remove dynamic values, which should be tested independently
+	for _, r := range redactors {
+		actual = r(actual)
+		expected = r(expected)
+	}
+
+	if !bytes.Equal(expected, actual) {
+		dmp := diffmatchpatch.New()
+		diffs := dmp.DiffMain(string(expected), string(actual), true)
+		t.Errorf("mismatched output:\n%s", dmp.DiffPrettyText(diffs))
+	}
+}
+
+func ImageInput(t testing.TB, testImage string, options ...ImageOption) sbom.SBOM {
+	t.Helper()
+	catalog := pkg.NewCatalog()
+	var cfg imageCfg
+	var img *image.Image
+	for _, opt := range options {
+		opt(&cfg)
+	}
+
+	switch cfg.fromSnapshot {
+	case true:
+		img = imagetest.GetGoldenFixtureImage(t, testImage)
+	default:
+		img = imagetest.GetFixtureImage(t, "docker-archive", testImage)
+	}
+
+	populateImageCatalog(catalog, img)
+
+	// this is a hard coded value that is not given by the fixture helper and must be provided manually
+	img.Metadata.ManifestDigest = "sha256:2731251dc34951c0e50fcc643b4c5f74922dad1a5d98f302b504cf46cd5d9368"
+
+	src, err := source.NewFromImage(img, "user-image-input")
+	assert.NoError(t, err)
+
+	dist, err := distro.NewDistro(distro.Debian, "1.2.3", "like!")
+	assert.NoError(t, err)
+
+	return sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			PackageCatalog: catalog,
+			Distro:         &dist,
+		},
+		Source: src.Metadata,
+		Descriptor: sbom.Descriptor{
+			Name:    "syft",
+			Version: "v0.42.0-bogus",
+			// the application configuration should be persisted here, however, we do not want to import
+			// the application configuration in this package (it's reserved only for ingestion by the cmd package)
+			Configuration: map[string]string{
+				"config-key": "config-value",
+			},
+		},
+	}
+}
+
+func populateImageCatalog(catalog *pkg.Catalog, img *image.Image) {
+	_, ref1, _ := img.SquashedTree().File("/somefile-1.txt", filetree.FollowBasenameLinks)
+	_, ref2, _ := img.SquashedTree().File("/somefile-2.txt", filetree.FollowBasenameLinks)
+
+	// populate catalog with test data
+	catalog.Add(pkg.Package{
+		Name:    "package-1",
+		Version: "1.0.1",
+		Locations: []source.Location{
+			source.NewLocationFromImage(string(ref1.RealPath), *ref1, img),
+		},
+		Type:         pkg.PythonPkg,
+		FoundBy:      "the-cataloger-1",
+		Language:     pkg.Python,
+		MetadataType: pkg.PythonPackageMetadataType,
+		Licenses:     []string{"MIT"},
+		Metadata: pkg.PythonPackageMetadata{
+			Name:    "package-1",
+			Version: "1.0.1",
+		},
+		PURL: "a-purl-1",
+		CPEs: []pkg.CPE{
+			pkg.MustCPE("cpe:2.3:*:some:package:1:*:*:*:*:*:*:*"),
+		},
+	})
+	catalog.Add(pkg.Package{
+		Name:    "package-2",
+		Version: "2.0.1",
+		Locations: []source.Location{
+			source.NewLocationFromImage(string(ref2.RealPath), *ref2, img),
+		},
+		Type:         pkg.DebPkg,
+		FoundBy:      "the-cataloger-2",
+		MetadataType: pkg.DpkgMetadataType,
+		Metadata: pkg.DpkgMetadata{
+			Package: "package-2",
+			Version: "2.0.1",
+		},
+		PURL: "a-purl-2",
+		CPEs: []pkg.CPE{
+			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
+		},
+	})
+}
+
+func DirectoryInput(t testing.TB) sbom.SBOM {
+	catalog := newDirectoryCatalog()
+
+	dist, err := distro.NewDistro(distro.Debian, "1.2.3", "like!")
+	assert.NoError(t, err)
+
+	src, err := source.NewFromDirectory("/some/path")
+	assert.NoError(t, err)
+
+	return sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			PackageCatalog: catalog,
+			Distro:         &dist,
+		},
+		Source: src.Metadata,
+		Descriptor: sbom.Descriptor{
+			Name:    "syft",
+			Version: "v0.42.0-bogus",
+			// the application configuration should be persisted here, however, we do not want to import
+			// the application configuration in this package (it's reserved only for ingestion by the cmd package)
+			Configuration: map[string]string{
+				"config-key": "config-value",
+			},
+		},
+	}
+}
+
+func newDirectoryCatalog() *pkg.Catalog {
+	catalog := pkg.NewCatalog()
+
+	// populate catalog with test data
+	catalog.Add(pkg.Package{
+		Name:    "package-1",
+		Version: "1.0.1",
+		Type:    pkg.PythonPkg,
+		FoundBy: "the-cataloger-1",
+		Locations: []source.Location{
+			source.NewLocation("/some/path/pkg1"),
+		},
+		Language:     pkg.Python,
+		MetadataType: pkg.PythonPackageMetadataType,
+		Licenses:     []string{"MIT"},
+		Metadata: pkg.PythonPackageMetadata{
+			Name:    "package-1",
+			Version: "1.0.1",
+			Files: []pkg.PythonFileRecord{
+				{
+					Path: "/some/path/pkg1/dependencies/foo",
+				},
+			},
+		},
+		PURL: "a-purl-2",
+		CPEs: []pkg.CPE{
+			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
+		},
+	})
+	catalog.Add(pkg.Package{
+		Name:    "package-2",
+		Version: "2.0.1",
+		Type:    pkg.DebPkg,
+		FoundBy: "the-cataloger-2",
+		Locations: []source.Location{
+			source.NewLocation("/some/path/pkg1"),
+		},
+		MetadataType: pkg.DpkgMetadataType,
+		Metadata: pkg.DpkgMetadata{
+			Package: "package-2",
+			Version: "2.0.1",
+		},
+		PURL: "a-purl-2",
+		CPEs: []pkg.CPE{
+			pkg.MustCPE("cpe:2.3:*:some:package:2:*:*:*:*:*:*:*"),
+		},
+	})
+
+	return catalog
+}

internal/formats/cyclonedx12xml/encoder.go

@@ -0,0 +1,26 @@
+package cyclonedx12xml
+
+import (
+	"encoding/xml"
+	"io"
+
+	"github.com/anchore/syft/syft/sbom"
+)
+
+func encoder(output io.Writer, s sbom.SBOM) error {
+	enc := xml.NewEncoder(output)
+	enc.Indent("", "  ")
+
+	_, err := output.Write([]byte(xml.Header))
+	if err != nil {
+		return err
+	}
+
+	err = enc.Encode(toFormatModel(s))
+	if err != nil {
+		return err
+	}
+
+	_, err = output.Write([]byte("\n"))
+	return err
+}

internal/formats/cyclonedx12xml/encoder_test.go

@@ -0,0 +1,39 @@
+package cyclonedx12xml
+
+import (
+	"flag"
+	"regexp"
+	"testing"
+
+	"github.com/anchore/syft/internal/formats/common/testutils"
+)
+
+var updateCycloneDx = flag.Bool("update-cyclonedx", false, "update the *.golden files for cyclone-dx presenters")
+
+func TestCycloneDxDirectoryPresenter(t *testing.T) {
+	testutils.AssertPresenterAgainstGoldenSnapshot(t,
+		Format().Presenter(testutils.DirectoryInput(t)),
+		*updateCycloneDx,
+		cycloneDxRedactor,
+	)
+}
+
+func TestCycloneDxImagePresenter(t *testing.T) {
+	testImage := "image-simple"
+	testutils.AssertPresenterAgainstGoldenImageSnapshot(t,
+		Format().Presenter(testutils.ImageInput(t, testImage)),
+		testImage,
+		*updateCycloneDx,
+		cycloneDxRedactor,
+	)
+}
+
+func cycloneDxRedactor(s []byte) []byte {
+	serialPattern := regexp.MustCompile(`serialNumber="[a-zA-Z0-9\-:]+"`)
+	rfc3339Pattern := regexp.MustCompile(`([0-9]+)-(0[1-9]|1[012])-(0[1-9]|[12][0-9]|3[01])[Tt]([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9]|60)(\.[0-9]+)?(([Zz])|([\+|\-]([01][0-9]|2[0-3]):[0-5][0-9]))`)
+
+	for _, pattern := range []*regexp.Regexp{serialPattern, rfc3339Pattern} {
+		s = pattern.ReplaceAll(s, []byte("redacted"))
+	}
+	return s
+}

internal/formats/cyclonedx12xml/format.go

@@ -0,0 +1,12 @@
+package cyclonedx12xml
+
+import "github.com/anchore/syft/syft/format"
+
+func Format() format.Format {
+	return format.NewFormat(
+		format.CycloneDxOption,
+		encoder,
+		nil,
+		nil,
+	)
+}

internal/formats/cyclonedx12xml/model/bom_descriptor.go

@@ -0,0 +1,31 @@
+package model
+
+import (
+	"encoding/xml"
+)
+
+// Source: https://cyclonedx.org/ext/bom-descriptor/
+
+// BomDescriptor represents all metadata surrounding the BOM report (such as when the BOM was made, with which tool, and the item being cataloged).
+type BomDescriptor struct {
+	XMLName   xml.Name                `xml:"metadata"`
+	Timestamp string                  `xml:"timestamp,omitempty"` // The date and time (timestamp) when the document was created
+	Tools     []BomDescriptorTool     `xml:"tools>tool"`          // The tool used to create the BOM.
+	Component *BomDescriptorComponent `xml:"component"`           // The component that the BOM describes.
+}
+
+// BomDescriptorTool represents the tool that created the BOM report.
+type BomDescriptorTool struct {
+	XMLName xml.Name `xml:"tool"`
+	Vendor  string   `xml:"vendor,omitempty"`  // The vendor of the tool used to create the BOM.
+	Name    string   `xml:"name,omitempty"`    // The name of the tool used to create the BOM.
+	Version string   `xml:"version,omitempty"` // The version of the tool used to create the BOM.
+	// TODO: hashes, author, manufacture, supplier
+	// TODO: add user-defined fields for the remaining build/version parameters
+}
+
+// BomDescriptorComponent represents the software/package being cataloged.
+type BomDescriptorComponent struct {
+	XMLName xml.Name `xml:"component"`
+	Component
+}

internal/formats/cyclonedx12xml/model/component.go

@@ -0,0 +1,20 @@
+package model
+
+import "encoding/xml"
+
+// Component represents a single element in the CycloneDX BOM
+type Component struct {
+	XMLName     xml.Name   `xml:"component"`
+	Type        string     `xml:"type,attr"`             // Required; Describes if the component is a library, framework, application, container, operating system, firmware, hardware device, or file
+	Supplier    string     `xml:"supplier,omitempty"`    // The organization that supplied the component. The supplier may often be the manufacture, but may also be a distributor or repackager.
+	Author      string     `xml:"author,omitempty"`      // The person(s) or organization(s) that authored the component
+	Publisher   string     `xml:"publisher,omitempty"`   // The person(s) or organization(s) that published the component
+	Group       string     `xml:"group,omitempty"`       // The high-level classification that a project self-describes as. This will often be a shortened, single name of the company or project that produced the component, or the source package or domain name.
+	Name        string     `xml:"name"`                  // Required; The name of the component as defined by the project
+	Version     string     `xml:"version"`               // Required; The version of the component as defined by the project
+	Description string     `xml:"description,omitempty"` // A description of the component
+	Licenses    *[]License `xml:"licenses>license"`      // A node describing zero or more license names, SPDX license IDs or expressions
+	PackageURL  string     `xml:"purl,omitempty"`        // Specifies the package-url (PackageURL). The purl, if specified, must be valid and conform to the specification defined at: https://github.com/package-url/purl-spec
+	// TODO: source, hashes, copyright, cpe, purl, swid, modified, pedigree, externalReferences
+	// TODO: add user-defined parameters for syft-specific values (image layer index, cataloger, location path, etc.)
+}

internal/formats/cyclonedx12xml/model/document.go

@@ -0,0 +1,17 @@
+package model
+
+import (
+	"encoding/xml"
+)
+
+// Source: https://github.com/CycloneDX/specification
+
+// Document represents a CycloneDX BOM Document.
+type Document struct {
+	XMLName       xml.Name       `xml:"bom"`
+	XMLNs         string         `xml:"xmlns,attr"`
+	Version       int            `xml:"version,attr"`
+	SerialNumber  string         `xml:"serialNumber,attr"`
+	BomDescriptor *BomDescriptor `xml:"metadata"`             // The BOM descriptor extension
+	Components    []Component    `xml:"components>component"` // The BOM contents
+}

internal/formats/cyclonedx12xml/model/license.go

@@ -0,0 +1,10 @@
+package model
+
+import "encoding/xml"
+
+// License represents a single software license for a Component
+type License struct {
+	XMLName xml.Name `xml:"license"`
+	ID      string   `xml:"id,omitempty"`   // A valid SPDX license ID
+	Name    string   `xml:"name,omitempty"` // If SPDX does not define the license used, this field may be used to provide the license name
+}

internal/formats/cyclonedx12xml/test-fixtures/snapshot/TestCycloneDxDirectoryPresenter.golden

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<bom xmlns="http://cyclonedx.org/schema/bom/1.2" version="1" serialNumber="urn:uuid:544b9f08-b39d-4d0c-8723-32609567e8ed">
+<bom xmlns="http://cyclonedx.org/schema/bom/1.2" version="1" serialNumber="urn:uuid:5404937f-72d6-44a2-8e9b-954305ecb4f6">
   <metadata>
-    <timestamp>2020-12-28T13:56:29-05:00</timestamp>
+    <timestamp>2021-06-23T13:40:33-04:00</timestamp>
     <tools>
       <tool>
         <vendor>anchore</vendor>
@@ -16,20 +16,19 @@
   </metadata>
   <components>
     <component type="library">
-      <name>package1</name>
+      <name>package-1</name>
       <version>1.0.1</version>
-    </component>
-    <component type="library">
-      <name>package2</name>
-      <version>2.0.1</version>
       <licenses>
         <license>
           <name>MIT</name>
         </license>
-        <license>
-          <name>Apache-v2</name>
-        </license>
       </licenses>
+      <purl>a-purl-2</purl>
+    </component>
+    <component type="library">
+      <name>package-2</name>
+      <version>2.0.1</version>
+      <purl>a-purl-2</purl>
     </component>
   </components>
 </bom>

internal/formats/cyclonedx12xml/test-fixtures/snapshot/TestCycloneDxImagePresenter.golden

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<bom xmlns="http://cyclonedx.org/schema/bom/1.2" version="1" serialNumber="urn:uuid:e1515688-2fd6-422a-acb2-97405a44cdfe">
+<bom xmlns="http://cyclonedx.org/schema/bom/1.2" version="1" serialNumber="urn:uuid:e34bad2e-cd27-483c-86dc-f4e26d6103b0">
   <metadata>
-    <timestamp>2020-12-28T13:56:29-05:00</timestamp>
+    <timestamp>2021-06-23T13:40:33-04:00</timestamp>
     <tools>
       <tool>
         <vendor>anchore</vendor>
@@ -16,22 +16,19 @@
   </metadata>
   <components>
     <component type="library">
-      <name>package1</name>
+      <name>package-1</name>
       <version>1.0.1</version>
-      <purl>the-purl-1</purl>
-    </component>
-    <component type="library">
-      <name>package2</name>
-      <version>2.0.1</version>
       <licenses>
         <license>
           <name>MIT</name>
         </license>
-        <license>
-          <name>Apache-v2</name>
-        </license>
       </licenses>
-      <purl>the-purl-2</purl>
+      <purl>a-purl-1</purl>
+    </component>
+    <component type="library">
+      <name>package-2</name>
+      <version>2.0.1</version>
+      <purl>a-purl-2</purl>
     </component>
   </components>
 </bom>

internal/formats/cyclonedx12xml/to_format_model.go

@@ -0,0 +1,95 @@
+package cyclonedx12xml
+
+import (
+	"encoding/xml"
+	"time"
+
+	"github.com/anchore/syft/syft/sbom"
+
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/formats/cyclonedx12xml/model"
+	"github.com/anchore/syft/internal/version"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/source"
+	"github.com/google/uuid"
+)
+
+// toFormatModel creates and populates a new in-memory representation of a CycloneDX 1.2 document
+func toFormatModel(s sbom.SBOM) model.Document {
+	versionInfo := version.FromBuild()
+
+	doc := model.Document{
+		XMLNs:         "http://cyclonedx.org/schema/bom/1.2",
+		Version:       1,
+		SerialNumber:  uuid.New().URN(),
+		BomDescriptor: toBomDescriptor(internal.ApplicationName, versionInfo.Version, s.Source),
+	}
+
+	// attach components
+	for _, p := range s.Artifacts.PackageCatalog.Sorted() {
+		doc.Components = append(doc.Components, toComponent(p))
+	}
+
+	return doc
+}
+
+func toComponent(p pkg.Package) model.Component {
+	return model.Component{
+		Type:       "library", // TODO: this is not accurate
+		Name:       p.Name,
+		Version:    p.Version,
+		PackageURL: p.PURL,
+		Licenses:   toLicenses(p.Licenses),
+	}
+}
+
+// NewBomDescriptor returns a new BomDescriptor tailored for the current time and "syft" tool details.
+func toBomDescriptor(name, version string, srcMetadata source.Metadata) *model.BomDescriptor {
+	return &model.BomDescriptor{
+		XMLName:   xml.Name{},
+		Timestamp: time.Now().Format(time.RFC3339),
+		Tools: []model.BomDescriptorTool{
+			{
+				Vendor:  "anchore",
+				Name:    name,
+				Version: version,
+			},
+		},
+		Component: toBomDescriptorComponent(srcMetadata),
+	}
+}
+
+func toBomDescriptorComponent(srcMetadata source.Metadata) *model.BomDescriptorComponent {
+	switch srcMetadata.Scheme {
+	case source.ImageScheme:
+		return &model.BomDescriptorComponent{
+			Component: model.Component{
+				Type:    "container",
+				Name:    srcMetadata.ImageMetadata.UserInput,
+				Version: srcMetadata.ImageMetadata.ManifestDigest,
+			},
+		}
+	case source.DirectoryScheme:
+		return &model.BomDescriptorComponent{
+			Component: model.Component{
+				Type: "file",
+				Name: srcMetadata.Path,
+			},
+		}
+	}
+	return nil
+}
+
+func toLicenses(licenses []string) *[]model.License {
+	if len(licenses) == 0 {
+		return nil
+	}
+
+	var result []model.License
+	for _, licenseName := range licenses {
+		result = append(result, model.License{
+			Name: licenseName,
+		})
+	}
+	return &result
+}

internal/formats/formats.go

@@ -0,0 +1,44 @@
+package formats
+
+import (
+	"bytes"
+
+	"github.com/anchore/syft/internal/formats/cyclonedx12xml"
+	"github.com/anchore/syft/internal/formats/spdx22json"
+	"github.com/anchore/syft/internal/formats/spdx22tagvalue"
+	"github.com/anchore/syft/internal/formats/syftjson"
+	"github.com/anchore/syft/internal/formats/table"
+	"github.com/anchore/syft/internal/formats/text"
+	"github.com/anchore/syft/syft/format"
+)
+
+// TODO: eventually this is the source of truth for all formatters
+func All() []format.Format {
+	return []format.Format{
+		syftjson.Format(),
+		table.Format(),
+		cyclonedx12xml.Format(),
+		spdx22json.Format(),
+		spdx22tagvalue.Format(),
+		text.Format(),
+	}
+}
+
+func Identify(by []byte) (*format.Format, error) {
+	for _, f := range All() {
+		if err := f.Validate(bytes.NewReader(by)); err != nil {
+			continue
+		}
+		return &f, nil
+	}
+	return nil, nil
+}
+
+func ByOption(option format.Option) *format.Format {
+	for _, f := range All() {
+		if f.Option == option {
+			return &f
+		}
+	}
+	return nil
+}

internal/formats/formats_test.go

@@ -0,0 +1,34 @@
+package formats
+
+import (
+	"io"
+	"os"
+	"testing"
+
+	"github.com/anchore/syft/syft/format"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestIdentify(t *testing.T) {
+	tests := []struct {
+		fixture  string
+		expected format.Option
+	}{
+		{
+			fixture:  "test-fixtures/alpine-syft.json",
+			expected: format.JSONOption,
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.fixture, func(t *testing.T) {
+			f, err := os.Open(test.fixture)
+			assert.NoError(t, err)
+			by, err := io.ReadAll(f)
+			assert.NoError(t, err)
+			frmt, err := Identify(by)
+			assert.NoError(t, err)
+			assert.NotNil(t, frmt)
+			assert.Equal(t, test.expected, frmt.Option)
+		})
+	}
+}

internal/formats/spdx22json/encoder.go

@@ -0,0 +1,21 @@
+package spdx22json
+
+import (
+	"encoding/json"
+	"io"
+
+	"github.com/anchore/syft/syft/sbom"
+)
+
+const anchoreNamespace = "https://anchore.com/syft"
+
+func encoder(output io.Writer, s sbom.SBOM) error {
+	doc := toFormatModel(s)
+
+	enc := json.NewEncoder(output)
+	// prevent > and < from being escaped in the payload
+	enc.SetEscapeHTML(false)
+	enc.SetIndent("", " ")
+
+	return enc.Encode(&doc)
+}

internal/formats/spdx22json/encoder_test.go

@@ -0,0 +1,40 @@
+package spdx22json
+
+import (
+	"flag"
+	"regexp"
+	"testing"
+
+	"github.com/anchore/syft/internal/formats/common/testutils"
+)
+
+var updateSpdxJson = flag.Bool("update-spdx-json", false, "update the *.golden files for spdx-json presenters")
+
+func TestSPDXJSONDirectoryPresenter(t *testing.T) {
+	testutils.AssertPresenterAgainstGoldenSnapshot(t,
+		Format().Presenter(testutils.DirectoryInput(t)),
+		*updateSpdxJson,
+		spdxJsonRedactor,
+	)
+}
+
+func TestSPDXJSONImagePresenter(t *testing.T) {
+	testImage := "image-simple"
+	testutils.AssertPresenterAgainstGoldenImageSnapshot(t,
+		Format().Presenter(testutils.ImageInput(t, testImage, testutils.FromSnapshot())),
+		testImage,
+		*updateSpdxJson,
+		spdxJsonRedactor,
+	)
+}
+
+func spdxJsonRedactor(s []byte) []byte {
+	// each SBOM reports the time it was generated, which is not useful during snapshot testing
+	s = regexp.MustCompile(`"created": .*`).ReplaceAll(s, []byte("redacted"))
+
+	// each SBOM reports a unique documentNamespace when generated, this is not useful for snapshot testing
+	s = regexp.MustCompile(`"documentNamespace": .*`).ReplaceAll(s, []byte("redacted"))
+
+	// the license list will be updated periodically, the value here should not be directly tested in snapshot tests
+	return regexp.MustCompile(`"licenseListVersion": .*`).ReplaceAll(s, []byte("redacted"))
+}

internal/formats/spdx22json/format.go

@@ -0,0 +1,13 @@
+package spdx22json
+
+import "github.com/anchore/syft/syft/format"
+
+// note: this format is LOSSY relative to the syftjson formation, which means that decoding and validation is not supported at this time
+func Format() format.Format {
+	return format.NewFormat(
+		format.SPDXJSONOption,
+		encoder,
+		nil,
+		nil,
+	)
+}

internal/formats/spdx22json/model/annotation.go

@@ -0,0 +1,21 @@
+package model
+
+import "time"
+
+type AnnotationType string
+
+const (
+	ReviewerAnnotationType AnnotationType = "REVIEWER"
+	OtherAnnotationType    AnnotationType = "OTHER"
+)
+
+type Annotation struct {
+	// Identify when the comment was made. This is to be specified according to the combined date and time in the
+	// UTC format, as specified in the ISO 8601 standard.
+	AnnotationDate time.Time `json:"annotationDate"`
+	// Type of the annotation
+	AnnotationType AnnotationType `json:"annotationType"`
+	// This field identifies the person, organization or tool that has commented on a file, package, or the entire document.
+	Annotator string `json:"annotator"`
+	Comment   string `json:"comment"`
+}

internal/formats/spdx22json/model/checksum.go

@@ -0,0 +1,7 @@
+package model
+
+type Checksum struct {
+	// Identifies the algorithm used to produce the subject Checksum. One of: "SHA256", "SHA1", "SHA384", "MD2", "MD4", "SHA512", "MD6", "MD5", "SHA224"
+	Algorithm     string `json:"algorithm"`
+	ChecksumValue string `json:"checksumValue"`
+}

internal/formats/spdx22json/model/creation_info.go

@@ -0,0 +1,19 @@
+package model
+
+import "time"
+
+type CreationInfo struct {
+	Comment string `json:"comment,omitempty"`
+	// Identify when the SPDX file was originally created. The date is to be specified according to combined date and
+	// time in UTC format as specified in ISO 8601 standard. This field is distinct from the fields in section 8,
+	// which involves the addition of information during a subsequent review.
+	Created time.Time `json:"created"`
+	// Identify who (or what, in the case of a tool) created the SPDX file. If the SPDX file was created by an
+	// individual, indicate the person's name. If the SPDX file was created on behalf of a company or organization,
+	// indicate the entity name. If the SPDX file was created using a software tool, indicate the name and version
+	// for that tool. If multiple participants or tools were involved, use multiple instances of this field. Person
+	// name or organization name may be designated as “anonymous” if appropriate.
+	Creators []string `json:"creators"`
+	// An optional field for creators of the SPDX file to provide the version of the SPDX License List used when the SPDX file was created.
+	LicenseListVersion string `json:"licenseListVersion"`
+}

internal/formats/spdx22json/model/document.go

@@ -0,0 +1,45 @@
+package model
+
+// derived from:
+// - https://spdx.github.io/spdx-spec/appendix-III-RDF-data-model-implementation-and-identifier-syntax/
+// - https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json
+// - https://github.com/spdx/spdx-spec/tree/v2.2/ontology
+
+type Document struct {
+	Element
+	SPDXVersion string `json:"spdxVersion"`
+	// One instance is required for each SPDX file produced. It provides the necessary information for forward
+	// and backward compatibility for processing tools.
+	CreationInfo CreationInfo `json:"creationInfo"`
+	// 2.2: Data License; should be "CC0-1.0"
+	// Cardinality: mandatory, one
+	// License expression for dataLicense.  Compliance with the SPDX specification includes populating the SPDX
+	// fields therein with data related to such fields (\"SPDX-Metadata\"). The SPDX specification contains numerous
+	// fields where an SPDX document creator may provide relevant explanatory text in SPDX-Metadata. Without
+	// opining on the lawfulness of \"database rights\" (in jurisdictions where applicable), such explanatory text
+	// is copyrightable subject matter in most Berne Convention countries. By using the SPDX specification, or any
+	// portion hereof, you hereby agree that any copyright rights (as determined by your jurisdiction) in any
+	// SPDX-Metadata, including without limitation explanatory text, shall be subject to the terms of the Creative
+	// Commons CC0 1.0 Universal license. For SPDX-Metadata not containing any copyright rights, you hereby agree
+	// and acknowledge that the SPDX-Metadata is provided to you \"as-is\" and without any representations or
+	// warranties of any kind concerning the SPDX-Metadata, express, implied, statutory or otherwise, including
+	// without limitation warranties of title, merchantability, fitness for a particular purpose, non-infringement,
+	// or the absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not
+	// discoverable, all to the greatest extent permissible under applicable law.
+	DataLicense string `json:"dataLicense"`
+	// Information about an external SPDX document reference including the checksum. This allows for verification of the external references.
+	ExternalDocumentRefs []ExternalDocumentRef `json:"externalDocumentRefs,omitempty"`
+	// Indicates that a particular ExtractedLicensingInfo was defined in the subject SpdxDocument.
+	HasExtractedLicensingInfos []HasExtractedLicensingInfo `json:"hasExtractedLicensingInfos,omitempty"`
+	// note: found in example documents from SPDX, but not in the JSON schema. See https://spdx.github.io/spdx-spec/2-document-creation-information/#25-spdx-document-namespace
+	DocumentNamespace string `json:"documentNamespace"`
+	// note: found in example documents from SPDX, but not in the JSON schema
+	// DocumentDescribes []string  `json:"documentDescribes"`
+	Packages []Package `json:"packages"`
+	// Files referenced in the SPDX document
+	Files []File `json:"files,omitempty"`
+	// Snippets referenced in the SPDX document
+	Snippets []Snippet `json:"snippets,omitempty"`
+	// Relationships referenced in the SPDX document
+	Relationships []Relationship `json:"relationships,omitempty"`
+}

internal/formats/spdx22json/model/element.go

@@ -0,0 +1,12 @@
+package model
+
+type Element struct {
+	SPDXID string `json:"SPDXID"`
+	// Identify name of this SpdxElement.
+	Name string `json:"name"`
+	// Relationships referenced in the SPDX document
+	Relationships []Relationship `json:"relationships,omitempty"`
+	// Provide additional information about an SpdxElement.
+	Annotations []Annotation `json:"annotations,omitempty"`
+	Comment     string       `json:"comment,omitempty"`
+}

internal/formats/spdx22json/model/element_id.go

@@ -0,0 +1,37 @@
+package model
+
+// ElementID represents the identifier string portion of an SPDX element
+// identifier. DocElementID should be used for any attributes which can
+// contain identifiers defined in a different SPDX document.
+// ElementIDs should NOT contain the mandatory 'SPDXRef-' portion.
+type ElementID string
+
+func (e ElementID) String() string {
+	return "SPDXRef-" + string(e)
+}
+
+// DocElementID represents an SPDX element identifier that could be defined
+// in a different SPDX document, and therefore could have a "DocumentRef-"
+// portion, such as Relationship and Annotations.
+// ElementID is used for attributes in which a "DocumentRef-" portion cannot
+// appear, such as a Package or File definition (since it is necessarily
+// being defined in the present document).
+// DocumentRefID will be the empty string for elements defined in the
+// present document.
+// DocElementIDs should NOT contain the mandatory 'DocumentRef-' or
+// 'SPDXRef-' portions.
+type DocElementID struct {
+	DocumentRefID string
+	ElementRefID  ElementID
+}
+
+// RenderDocElementID takes a DocElementID and returns the string equivalent,
+// with the SPDXRef- prefix (and, if applicable, the DocumentRef- prefix)
+// reinserted.
+func (d DocElementID) String() string {
+	prefix := ""
+	if d.DocumentRefID != "" {
+		prefix = "DocumentRef-" + d.DocumentRefID + ":"
+	}
+	return prefix + d.ElementRefID.String()
+}

internal/formats/spdx22json/model/external_document_ref.go

@@ -0,0 +1,9 @@
+package model
+
+type ExternalDocumentRef struct {
+	// externalDocumentId is a string containing letters, numbers, ., - and/or + which uniquely identifies an external document within this document.
+	ExternalDocumentID string   `json:"externalDocumentId"`
+	Checksum           Checksum `json:"checksum"`
+	// SPDX ID for SpdxDocument.  A propoerty containing an SPDX document.
+	SpdxDocument string `json:"spdxDocument"`
+}

internal/formats/spdx22json/model/external_ref.go

@@ -0,0 +1,43 @@
+package model
+
+type ReferenceCategory string
+
+const (
+	SecurityReferenceCategory       ReferenceCategory = "SECURITY"
+	PackageManagerReferenceCategory ReferenceCategory = "PACKAGE_MANAGER"
+	OtherReferenceCategory          ReferenceCategory = "OTHER"
+)
+
+// source: https://spdx.github.io/spdx-spec/appendix-VI-external-repository-identifiers/
+
+type ExternalRefType string
+
+const (
+	// see https://nvd.nist.gov/cpe
+	Cpe22ExternalRefType ExternalRefType = "cpe22Type"
+	// see https://nvd.nist.gov/cpe
+	Cpe23ExternalRefType ExternalRefType = "cpe23Type"
+	// see http://repo1.maven.org/maven2/
+	MavenCentralExternalRefType ExternalRefType = "maven-central"
+	// see https://www.npmjs.com/
+	NpmExternalRefType ExternalRefType = "npm"
+	// see https://www.nuget.org/
+	NugetExternalRefType ExternalRefType = "nuget"
+	// see http://bower.io/
+	BowerExternalRefType ExternalRefType = "bower"
+	// see https://github.com/package-url/purl-spec
+	PurlExternalRefType ExternalRefType = "purl"
+	// These point to objects present in the Software Heritage archive by the means of SoftWare Heritage persistent Identifiers (SWHID)
+	SwhExternalRefType ExternalRefType = "swh"
+)
+
+type ExternalRef struct {
+	Comment string `json:"comment,omitempty"`
+	// Category for the external reference.
+	ReferenceCategory ReferenceCategory `json:"referenceCategory"`
+	// The unique string with no spaces necessary to access the package-specific information, metadata, or content
+	// within the target location. The format of the locator is subject to constraints defined by the <type>.
+	ReferenceLocator string `json:"referenceLocator"`
+	// Type of the external reference. These are defined in an appendix in the SPDX specification.
+	ReferenceType ExternalRefType `json:"referenceType"`
+}

internal/formats/spdx22json/model/file.go

@@ -0,0 +1,41 @@
+package model
+
+type FileType string
+
+const (
+	DocumentationFileType FileType = "DOCUMENTATION" // if the file serves as documentation
+	ImageFileType         FileType = "IMAGE"         // if the file is associated with a picture image file (MIME type of image/*, e.g., .jpg, .gif)
+	VideoFileType         FileType = "VIDEO"         // if the file is associated with a video file type (MIME type of video/*)
+	ArchiveFileType       FileType = "ARCHIVE"       // if the file represents an archive (.tar, .jar, etc.)
+	SpdxFileType          FileType = "SPDX"          // if the file is an SPDX document
+	ApplicationFileType   FileType = "APPLICATION"   // if the file is associated with a specific application type (MIME type of application/*)
+	SourceFileType        FileType = "SOURCE"        // if the file is human readable source code (.c, .html, etc.)
+	BinaryFileType        FileType = "BINARY"        // if the file is a compiled object, target image or binary executable (.o, .a, etc.)
+	TextFileType          FileType = "TEXT"          // if the file is human readable text file (MIME type of text/*)
+	AudioFileType         FileType = "AUDIO"         // if the file is associated with an audio file (MIME type of audio/* , e.g. .mp3)
+	OtherFileType         FileType = "OTHER"         // if the file doesn't fit into the above categories (generated artifacts, data files, etc.)
+)
+
+type File struct {
+	Item
+	// (At least one is required.) The checksum property provides a mechanism that can be used to verify that the
+	// contents of a File or Package have not changed.
+	Checksums []Checksum `json:"checksums,omitempty"`
+	// This field provides a place for the SPDX file creator to record file contributors. Contributors could include
+	// names of copyright holders and/or authors who may not be copyright holders yet contributed to the file content.
+	FileContributors []string `json:"fileContributors,omitempty"`
+	// Each element is a SPDX ID for a File.
+	FileDependencies []string `json:"fileDependencies,omitempty"`
+	// The name of the file relative to the root of the package.
+	FileName string `json:"fileName"`
+	// The type of the file
+	FileTypes []string `json:"fileTypes,omitempty"`
+	// This field provides a place for the SPDX file creator to record potential legal notices found in the file.
+	// This may or may not include copyright statements.
+	NoticeText string `json:"noticeText,omitempty"`
+	// Indicates the project in which the SpdxElement originated. Tools must preserve doap:homepage and doap:name
+	// properties and the URI (if one is known) of doap:Project resources that are values of this property. All other
+	// properties of doap:Projects are not directly supported by SPDX and may be dropped when translating to or
+	// from some SPDX formats (deprecated).
+	ArtifactOf []string `json:"artifactOf,omitempty"`
+}

internal/formats/spdx22json/model/has_extracted_licensing_info.go

@@ -0,0 +1,14 @@
+package model
+
+type HasExtractedLicensingInfo struct {
+	// Verbatim license or licensing notice text that was discovered.
+	ExtractedText string `json:"extractedText"`
+	// A human readable short form license identifier for a license. The license ID is iether on the standard license
+	// oist or the form \"LicenseRef-\"[idString] where [idString] is a unique string containing letters,
+	// numbers, \".\", \"-\" or \"+\".
+	LicenseID string `json:"licenseId"`
+	Comment   string `json:"comment,omitempty"`
+	// Identify name of this SpdxElement.
+	Name     string   `json:"name,omitempty"`
+	SeeAlsos []string `json:"seeAlsos,omitempty"`
+}

internal/formats/spdx22json/model/item.go

@@ -0,0 +1,22 @@
+package model
+
+type Item struct {
+	Element
+	// The licenseComments property allows the preparer of the SPDX document to describe why the licensing in
+	// spdx:licenseConcluded was chosen.
+	LicenseComments  string `json:"licenseComments,omitempty"`
+	LicenseConcluded string `json:"licenseConcluded"`
+	// The licensing information that was discovered directly within the package. There will be an instance of this
+	// property for each distinct value of alllicenseInfoInFile properties of all files contained in the package.
+	LicenseInfoFromFiles []string `json:"licenseInfoFromFiles,omitempty"`
+	// Licensing information that was discovered directly in the subject file. This is also considered a declared license for the file.
+	LicenseInfoInFiles []string `json:"licenseInfoInFiles,omitempty"`
+	// The text of copyright declarations recited in the Package or File.
+	CopyrightText string `json:"copyrightText,omitempty"`
+	// This field provides a place for the SPDX data creator to record acknowledgements that may be required to be
+	// communicated in some contexts. This is not meant to include the actual complete license text (see
+	// licenseConculded and licenseDeclared), and may or may not include copyright notices (see also copyrightText).
+	// The SPDX data creator may use this field to record other acknowledgements, such as particular clauses from
+	// license texts, which may be necessary or desirable to reproduce.
+	AttributionTexts []string `json:"attributionTexts,omitempty"`
+}

internal/formats/spdx22json/model/package.go

@@ -0,0 +1,50 @@
+package model
+
+type Package struct {
+	Item
+	// The checksum property provides a mechanism that can be used to verify that the contents of a File or
+	// Package have not changed.
+	Checksums []Checksum `json:"checksums,omitempty"`
+	// Provides a detailed description of the package.
+	Description string `json:"description,omitempty"`
+	// The URI at which this package is available for download. Private (i.e., not publicly reachable) URIs are
+	// acceptable as values of this property. The values http://spdx.org/rdf/terms#none and http://spdx.org/rdf/terms#noassertion
+	// may be used to specify that the package is not downloadable or that no attempt was made to determine its
+	// download location, respectively.
+	DownloadLocation string `json:"downloadLocation,omitempty"`
+	// An External Reference allows a Package to reference an external source of additional information, metadata,
+	// enumerations, asset identifiers, or downloadable content believed to be relevant to the Package.
+	ExternalRefs []ExternalRef `json:"externalRefs,omitempty"`
+	// Indicates whether the file content of this package has been available for or subjected to analysis when
+	// creating the SPDX document. If false indicates packages that represent metadata or URI references to a
+	// project, product, artifact, distribution or a component. If set to false, the package must not contain any files
+	FilesAnalyzed bool `json:"filesAnalyzed"`
+	// Indicates that a particular file belongs to a package (elements are SPDX ID for a File).
+	HasFiles []string `json:"hasFiles,omitempty"`
+	// Provide a place for the SPDX file creator to record a web site that serves as the package's home page.
+	// This link can also be used to reference further information about the package referenced by the SPDX file creator.
+	Homepage string `json:"homepage,omitempty"`
+	// List the licenses that have been declared by the authors of the package. Any license information that does not
+	// originate from the package authors, e.g. license information from a third party repository, should not be included in this field.
+	LicenseDeclared string `json:"licenseDeclared"`
+	// The name and, optionally, contact information of the person or organization that originally created the package.
+	// Values of this property must conform to the agent and tool syntax.
+	Originator string `json:"originator,omitempty"`
+	// The base name of the package file name. For example, zlib-1.2.5.tar.gz.
+	PackageFileName string `json:"packageFileName,omitempty"`
+	// A manifest based verification code (the algorithm is defined in section 4.7 of the full specification) of the
+	// SPDX Item. This allows consumers of this data and/or database to determine if an SPDX item they have in hand
+	// is identical to the SPDX item from which the data was produced. This algorithm works even if the SPDX document
+	// is included in the SPDX item.
+	PackageVerificationCode *PackageVerificationCode `json:"packageVerificationCode,omitempty"`
+	// Allows the producer(s) of the SPDX document to describe how the package was acquired and/or changed from the original source.
+	SourceInfo string `json:"sourceInfo,omitempty"`
+	// Provides a short description of the package.
+	Summary string `json:"summary,omitempty"`
+	// The name and, optionally, contact information of the person or organization who was the immediate supplier
+	// of this package to the recipient. The supplier may be different than originator when the software has been
+	// repackaged. Values of this property must conform to the agent and tool syntax.
+	Supplier string `json:"supplier,omitempty"`
+	// Provides an indication of the version of the package that is described by this SpdxDocument.
+	VersionInfo string `json:"versionInfo,omitempty"`
+}

internal/formats/spdx22json/model/package_verification_code.go

@@ -0,0 +1,23 @@
+package model
+
+// Why are there two package identifier fields Package Checksum and Package Verification?
+// Although the values of the two fields Package Checksum and Package Verification are similar, they each serve a
+// different purpose. The Package Checksum provides a unique identifier of a software package which is computed by
+// taking the SHA1 of the entire software package file. This enables one to quickly determine if two different copies
+// of a package are the same. One disadvantage of this approach is that one cannot add an SPDX data file into the
+// original package without changing the Package Checksum value. Alternatively, the Package Verification field enables
+// the inclusion of an SPDX file. It enables one to quickly verify if one or more of the original package files has
+// changed. The Package Verification field is a unique identifier that is based on SHAing only the original package
+// files (e.g., excluding the SPDX file). This allows one to add an SPDX file to the original package without changing
+// this unique identifier.
+// source: https://wiki.spdx.org/view/SPDX_FAQ
+type PackageVerificationCode struct {
+	// "A file that was excluded when calculating the package verification code. This is usually a file containing
+	// SPDX data regarding the package. If a package contains more than one SPDX file all SPDX files must be excluded
+	// from the package verification code. If this is not done it would be impossible to correctly calculate the
+	// verification codes in both files.
+	PackageVerificationCodeExcludedFiles []string `json:"packageVerificationCodeExcludedFiles"`
+
+	// The actual package verification code as a hex encoded value.
+	PackageVerificationCodeValue string `json:"packageVerificationCodeValue"`
+}

internal/formats/spdx22json/model/relationship.go

@@ -0,0 +1,183 @@
+package model
+
+type Relationship struct {
+	// Id to which the SPDX element is related
+	SpdxElementID string `json:"spdxElementId"`
+	// Describes the type of relationship between two SPDX elements.
+	RelationshipType RelationshipType `json:"relationshipType"`
+	// SPDX ID for SpdxElement.  A related SpdxElement.
+	RelatedSpdxElement string `json:"relatedSpdxElement"`
+	Comment            string `json:"comment,omitempty"`
+}
+
+// source: https://spdx.github.io/spdx-spec/7-relationships-between-SPDX-elements/
+type RelationshipType string
+
+const (
+	// DescribedByRelationship is to be used when SPDXRef-A is described by SPDXREF-Document.
+	// Example: The package 'WildFly' is described by SPDX document WildFly.spdx.
+	DescribedByRelationship RelationshipType = "DESCRIBED_BY"
+
+	// ContainsRelationship is to be used when SPDXRef-A contains SPDXRef-B.
+	// Example: An ARCHIVE file bar.tgz contains a SOURCE file foo.c.
+	ContainsRelationship RelationshipType = "CONTAINS"
+
+	// ContainedByRelationship is to be used when SPDXRef-A is contained by SPDXRef-B.
+	// Example: A SOURCE file foo.c is contained by ARCHIVE file bar.tgz
+	ContainedByRelationship RelationshipType = "CONTAINED_BY"
+
+	// DependsOnRelationship is to be used when SPDXRef-A depends on SPDXRef-B.
+	// Example: Package A depends on the presence of package B in order to build and run
+	DependsOnRelationship RelationshipType = "DEPENDS_ON"
+
+	// DependencyOfRelationship is to be used when SPDXRef-A is dependency of SPDXRef-B.
+	// Example: A is explicitly stated as a dependency of B in a machine-readable file. Use when a package manager does not define scopes.
+	DependencyOfRelationship RelationshipType = "DEPENDENCY_OF"
+
+	// DependencyManifestOfRelationship is to be used when SPDXRef-A is a manifest file that lists a set of dependencies for SPDXRef-B.
+	// Example: A file package.json is the dependency manifest of a package foo. Note that only one manifest should be used to define the same dependency graph.
+	DependencyManifestOfRelationship RelationshipType = "DEPENDENCY_MANIFEST_OF"
+
+	// BuildDependencyOfRelationship is to be used when SPDXRef-A is a build dependency of SPDXRef-B.
+	// Example: A is in the compile scope of B in a Maven project.
+	BuildDependencyOfRelationship RelationshipType = "BUILD_DEPENDENCY_OF"
+
+	// DevDependencyOfRelationship is to be used when SPDXRef-A is a development dependency of SPDXRef-B.
+	// Example: A is in the devDependencies scope of B in a Maven project.
+	DevDependencyOfRelationship RelationshipType = "DEV_DEPENDENCY_OF"
+
+	// OptionalDependencyOfRelationship is to be used when SPDXRef-A is an optional dependency of SPDXRef-B.
+	// Example: Use when building the code will proceed even if a dependency cannot be found, fails to install, or is only installed on a specific platform. For example, A is in the optionalDependencies scope of npm project B.
+	OptionalDependencyOfRelationship RelationshipType = "OPTIONAL_DEPENDENCY_OF"
+
+	// ProvidedDependencyOfRelationship is to be used when SPDXRef-A is a to be provided dependency of SPDXRef-B.
+	// Example: A is in the provided scope of B in a Maven project, indicating that the project expects it to be provided, for instance, by the container or JDK.
+	ProvidedDependencyOfRelationship RelationshipType = "PROVIDED_DEPENDENCY_OF"
+
+	// TestDependencyOfRelationship is to be used when SPDXRef-A is a test dependency of SPDXRef-B.
+	// Example: A is in the test scope of B in a Maven project.
+	TestDependencyOfRelationship RelationshipType = "TEST_DEPENDENCY_OF"
+
+	// RuntimeDependencyOfRelationship is to be used when SPDXRef-A is a dependency required for the execution of SPDXRef-B.
+	// Example: A is in the runtime scope of B in a Maven project.
+	RuntimeDependencyOfRelationship RelationshipType = "RUNTIME_DEPENDENCY_OF"
+
+	// ExampleOfRelationship is to be used when SPDXRef-A is an example of SPDXRef-B.
+	// Example: The file or snippet that illustrates how to use an application or library.
+	ExampleOfRelationship RelationshipType = "EXAMPLE_OF"
+
+	// GeneratesRelationship is to be used when SPDXRef-A generates SPDXRef-B.
+	// Example: A SOURCE file makefile.mk generates a BINARY file a.out
+	GeneratesRelationship RelationshipType = "GENERATES"
+
+	// GeneratedFromRelationship is to be used when SPDXRef-A was generated from SPDXRef-B.
+	// Example: A BINARY file a.out has been generated from a SOURCE file makefile.mk. A BINARY file foolib.a is generated from a SOURCE file bar.c.
+	GeneratedFromRelationship RelationshipType = "GENERATED_FROM"
+
+	// AncestorOfRelationship is to be used when SPDXRef-A is an ancestor (same lineage but pre-dates) SPDXRef-B.
+	// Example: A SOURCE file makefile.mk is a version of the original ancestor SOURCE file 'makefile2.mk'
+	AncestorOfRelationship RelationshipType = "ANCESTOR_OF"
+
+	// DescendantOfRelationship is to be used when SPDXRef-A is a descendant of (same lineage but postdates) SPDXRef-B.
+	// Example: A SOURCE file makefile2.mk is a descendant of the original SOURCE file 'makefile.mk'
+	DescendantOfRelationship RelationshipType = "DESCENDANT_OF"
+
+	// VariantOfRelationship is to be used when SPDXRef-A is a variant of (same lineage but not clear which came first) SPDXRef-B.
+	// Example: A SOURCE file makefile2.mk is a variant of SOURCE file makefile.mk if they differ by some edit, but there is no way to tell which came first (no reliable date information).
+	VariantOfRelationship RelationshipType = "VARIANT_OF"
+
+	// DistributionArtifactRelationship is to be used when distributing SPDXRef-A requires that SPDXRef-B also be distributed.
+	// Example: A BINARY file foo.o requires that the ARCHIVE file bar-sources.tgz be made available on distribution.
+	DistributionArtifactRelationship RelationshipType = "DISTRIBUTION_ARTIFACT"
+
+	// PatchForRelationship is to be used when SPDXRef-A is a patch file for (to be applied to) SPDXRef-B.
+	// Example: A SOURCE file foo.diff is a patch file for SOURCE file foo.c.
+	PatchForRelationship RelationshipType = "PATCH_FOR"
+
+	// PatchAppliedRelationship is to be used when SPDXRef-A is a patch file that has been applied to SPDXRef-B.
+	// Example: A SOURCE file foo.diff is a patch file that has been applied to SOURCE file 'foo-patched.c'.
+	PatchAppliedRelationship RelationshipType = "PATCH_APPLIED"
+
+	// CopyOfRelationship is to be used when SPDXRef-A is an exact copy of SPDXRef-B.
+	// Example: A BINARY file alib.a is an exact copy of BINARY file a2lib.a.
+	CopyOfRelationship RelationshipType = "COPY_OF"
+
+	// FileAddedRelationship is to be used when SPDXRef-A is a file that was added to SPDXRef-B.
+	// Example: A SOURCE file foo.c has been added to package ARCHIVE bar.tgz.
+	FileAddedRelationship RelationshipType = "FILE_ADDED"
+
+	// FileDeletedRelationship is to be used when SPDXRef-A is a file that was deleted from SPDXRef-B.
+	// Example: A SOURCE file foo.diff has been deleted from package ARCHIVE bar.tgz.
+	FileDeletedRelationship RelationshipType = "FILE_DELETED"
+
+	// FileModifiedRelationship is to be used when SPDXRef-A is a file that was modified from SPDXRef-B.
+	// Example: A SOURCE file foo.c has been modified from SOURCE file foo.orig.c.
+	FileModifiedRelationship RelationshipType = "FILE_MODIFIED"
+
+	// ExpandedFromArchiveRelationship is to be used when SPDXRef-A is expanded from the archive SPDXRef-B.
+	// Example: A SOURCE file foo.c, has been expanded from the archive ARCHIVE file xyz.tgz.
+	ExpandedFromArchiveRelationship RelationshipType = "EXPANDED_FROM_ARCHIVE"
+
+	// DynamicLinkRelationship is to be used when SPDXRef-A dynamically links to SPDXRef-B.
+	// Example: An APPLICATION file 'myapp' dynamically links to BINARY file zlib.so.
+	DynamicLinkRelationship RelationshipType = "DYNAMIC_LINK"
+
+	// StaticLinkRelationship is to be used when SPDXRef-A statically links to SPDXRef-B.
+	// Example: An APPLICATION file 'myapp' statically links to BINARY zlib.a.
+	StaticLinkRelationship RelationshipType = "STATIC_LINK"
+
+	// DataFileOfRelationship is to be used when SPDXRef-A is a data file used in SPDXRef-B.
+	// Example: An IMAGE file 'kitty.jpg' is a data file of an APPLICATION 'hellokitty'.
+	DataFileOfRelationship RelationshipType = "DATA_FILE_OF"
+
+	// TestCaseOfRelationship is to be used when SPDXRef-A is a test case used in testing SPDXRef-B.
+	// Example: A SOURCE file testMyCode.java is a unit test file used to test an APPLICATION MyPackage.
+	TestCaseOfRelationship RelationshipType = "TEST_CASE_OF"
+
+	// BuildToolOfRelationship is to be used when SPDXRef-A is used to build SPDXRef-B.
+	// Example: A SOURCE file makefile.mk is used to build an APPLICATION 'zlib'.
+	BuildToolOfRelationship RelationshipType = "BUILD_TOOL_OF"
+
+	// DevToolOfRelationship is to be used when SPDXRef-A is used as a development tool for SPDXRef-B.
+	// Example: Any tool used for development such as a code debugger.
+	DevToolOfRelationship RelationshipType = "DEV_TOOL_OF"
+
+	// TestOfRelationship is to be used when SPDXRef-A is used for testing SPDXRef-B.
+	// Example: Generic relationship for cases where it's clear that something is used for testing but unclear whether it's TEST_CASE_OF or TEST_TOOL_OF.
+	TestOfRelationship RelationshipType = "TEST_OF"
+
+	// TestToolOfRelationship is to be used when SPDXRef-A is used as a test tool for SPDXRef-B.
+	// Example: Any tool used to test the code such as ESlint.
+	TestToolOfRelationship RelationshipType = "TEST_TOOL_OF"
+
+	// DocumentationOfRelationship is to be used when SPDXRef-A provides documentation of SPDXRef-B.
+	// Example: A DOCUMENTATION file readme.txt documents the APPLICATION 'zlib'.
+	DocumentationOfRelationship RelationshipType = "DOCUMENTATION_OF"
+
+	// OptionalComponentOfRelationship is to be used when SPDXRef-A is an optional component of SPDXRef-B.
+	// Example: A SOURCE file fool.c (which is in the contributors directory) may or may not be included in the build of APPLICATION 'atthebar'.
+	OptionalComponentOfRelationship RelationshipType = "OPTIONAL_COMPONENT_OF"
+
+	// MetafileOfRelationship is to be used when SPDXRef-A is a metafile of SPDXRef-B.
+	// Example: A SOURCE file pom.xml is a metafile of the APPLICATION 'Apache Xerces'.
+	MetafileOfRelationship RelationshipType = "METAFILE_OF"
+
+	// PackageOfRelationship is to be used when SPDXRef-A is used as a package as part of SPDXRef-B.
+	// Example: A Linux distribution contains an APPLICATION package gawk as part of the distribution MyLinuxDistro.
+	PackageOfRelationship RelationshipType = "PACKAGE_OF"
+
+	// AmendsRelationship is to be used when (current) SPDXRef-DOCUMENT amends the SPDX information in SPDXRef-B.
+	// Example: (Current) SPDX document A version 2 contains a correction to a previous version of the SPDX document A version 1. Note the reserved identifier SPDXRef-DOCUMENT for the current document is required.
+	AmendsRelationship RelationshipType = "AMENDS"
+
+	// PrerequisiteForRelationship is to be used when SPDXRef-A is a prerequisite for SPDXRef-B.
+	// Example: A library bar.dll is a prerequisite or dependency for APPLICATION foo.exe
+	PrerequisiteForRelationship RelationshipType = "PREREQUISITE_FOR"
+
+	// HasPrerequisiteRelationship is to be used when SPDXRef-A has as a prerequisite SPDXRef-B.
+	// Example: An APPLICATION foo.exe has prerequisite or dependency on bar.dll
+	HasPrerequisiteRelationship RelationshipType = "HAS_PREREQUISITE"
+
+	// OtherRelationship is to be used for a relationship which has not been defined in the formal SPDX specification. A description of the relationship should be included in the Relationship comments field.
+	OtherRelationship RelationshipType = "OTHER"
+)

internal/formats/spdx22json/model/snippet.go

@@ -0,0 +1,32 @@
+package model
+
+type StartPointer struct {
+	Offset     int `json:"offset,omitempty"`
+	LineNumber int `json:"lineNumber,omitempty"`
+	// SPDX ID for File
+	Reference string `json:"reference"`
+}
+
+type EndPointer struct {
+	Offset     int `json:"offset,omitempty"`
+	LineNumber int `json:"lineNumber,omitempty"`
+	// SPDX ID for File
+	Reference string `json:"reference"`
+}
+
+type Range struct {
+	StartPointer StartPointer `json:"startPointer"`
+	EndPointer   EndPointer   `json:"endPointer"`
+}
+
+type Snippet struct {
+	Item
+	// Licensing information that was discovered directly in the subject snippet. This is also considered a declared
+	// license for the snippet. (elements are license expressions)
+	LicenseInfoInSnippets []string `json:"licenseInfoInSnippets"`
+	// SPDX ID for File. File containing the SPDX element (e.g. the file contaning a snippet).
+	SnippetFromFile string `json:"snippetFromFile"`
+	// (At least 1 range is required). This field defines the byte range in the original host file (in X.2) that the
+	// snippet information applies to.
+	Ranges []Range `json:"ranges"`
+}

internal/formats/spdx22json/model/version.go

@@ -0,0 +1,3 @@
+package model
+
+const Version = "SPDX-2.2"

internal/formats/spdx22json/test-fixtures/image-simple/Dockerfile

@@ -0,0 +1,4 @@
+# Note: changes to this file will result in updating several test values. Consider making a new image fixture instead of editing this one.
+FROM scratch
+ADD file-1.txt /somefile-1.txt
+ADD file-2.txt /somefile-2.txt

internal/formats/spdx22json/test-fixtures/image-simple/file-1.txt

@@ -0,0 +1 @@
+this file has contents

internal/formats/spdx22json/test-fixtures/image-simple/file-2.txt

@@ -0,0 +1 @@
+file-2 contents!