limit source-distribution refs to deb and rpm

- apk origins and alpm pkgbases are build recipes, not published source packages, and their names are usually also real binary packages, so a `source-distribution` ref there would point at a binary package. They keep relying on the `upstream` PURL qualifier.
- document why this is an external reference rather than `pedigree.ancestors`, with links to the CycloneDX spec discussion (CycloneDX/specification#612)

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

.binny.yaml

@@ -1,52 +1,10 @@
+# only pull in version updates that were released more than a week ago (low-pass filter for quickly-retracted releases)
+cooldown: 7d
+# Most tools (binny, chronicle, cosign, golangci-lint, goreleaser, gosimports,
+# bouncer, quill, syft, task, gh) are inherited from anchore/go-make's embedded
+# .binny.yaml — see https://github.com/anchore/go-make. Only syft-specific tools
+# or version overrides should live here.
 tools:
-  # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
-  - name: binny
-    version:
-      want: v0.9.0
-    method: github-release
-    with:
-      repo: anchore/binny
-
-  # used to produce SBOMs during release
-  - name: syft
-    version:
-      want: latest
-    method: github-release
-    with:
-      repo: anchore/syft
-
-  # used to sign mac binaries at release
-  - name: quill
-    version:
-      want: v0.5.1
-    method: github-release
-    with:
-      repo: anchore/quill
-
-  # used for linting
-  - name: golangci-lint
-    version:
-      want: v2.3.1
-    method: github-release
-    with:
-      repo: golangci/golangci-lint
-
-  # used for showing the changelog at release
-  - name: glow
-    version:
-      want: v2.1.1
-    method: github-release
-    with:
-      repo: charmbracelet/glow
-
-  # used for signing the checksums file at release
-  - name: cosign
-    version:
-      want: v2.5.3
-    method: github-release
-    with:
-      repo: sigstore/cosign
-
   # used in integration tests to verify JSON schemas
   - name: yajsv
     version:
@@ -55,66 +13,18 @@ tools:
     with:
       repo: neilpa/yajsv
 
-  # used to release all artifacts
-  - name: goreleaser
-    version:
-      want: v2.11.2
-    method: github-release
-    with:
-      repo: goreleaser/goreleaser
-
-  # used for organizing imports during static analysis
-  - name: gosimports
-    version:
-      want: v0.3.8
-    method: github-release
-    with:
-      repo: rinchsan/gosimports
-
-  # used at release to generate the changelog
-  - name: chronicle
-    version:
-      want: v0.8.0
-    method: github-release
-    with:
-      repo: anchore/chronicle
-
-  # used during static analysis for license compliance
-  - name: bouncer
-    version:
-      want: v0.4.0
-    method: github-release
-    with:
-      repo: wagoodman/go-bouncer
-
-  # used for running all local and CI tasks
-  - name: task
-    version:
-      want: v3.44.1
-    method: github-release
-    with:
-      repo: go-task/task
-
-  # used for triggering a release
-  - name: gh
-    version:
-      want: v2.76.2
-    method: github-release
-    with:
-      repo: cli/cli
-
   # used to upload test fixture cache
   - name: oras
     version:
-      want: v1.2.3
+      want: v1.3.4
     method: github-release
     with:
       repo: oras-project/oras
 
-  # used to upload test fixture cache
+  # used to parse JSON/YAML annotations on the fixture cache image
   - name: yq
     version:
-      want: v4.47.1
+      want: v4.53.6
     method: github-release
     with:
       repo: mikefarah/yq

.bouncer.yaml

@@ -9,6 +9,9 @@ permit:
   - Unlicense
 
 ignore-packages:
+  # https://github.com/sorairolake/lzip-go/blob/34a2615d2abf740175c6b0a835baa08364e09430/go.sum.license#L3
+  # has `SPDX-License-Identifier: Apache-2.0 OR MIT`, both of which are acceptable
+  - github.com/sorairolake/lzip-go
   # packageurl-go is released under the MIT license located in the root of the repo at /mit.LICENSE
   - github.com/anchore/packageurl-go
 

.gitattributes

@@ -0,0 +1,7 @@
+# check out text files with lf on every platform (regardless of core.autocrlf), letting git detect binary files
+* text=auto eol=lf
+
+# fixtures that must keep their crlf line endings byte for byte
+syft/linux/testdata/unprintable -text
+syft/pkg/cataloger/bitnami/testdata/no-rel/opt/bitnami/redis/.spdx-redis.spdx -text
+syft/pkg/cataloger/java/testdata/jar-metadata/**/META-INF/MANIFEST.MF -text

.github/actions/bootstrap/action.yaml

@@ -1,26 +1,27 @@
 name: "Bootstrap"
+description: "Bootstrap all syft tools and dependencies on top of go-make's setup action"
+
+# This action is a thin wrapper around anchore/go-make/.github/actions/setup which
+# already handles checkout, setup-go, restore-only build/mod cache, and tool cache.
+# We add the syft-specific extras here: apt packages and the test fixture cache.
 
-description: "Bootstrap all tools and dependencies"
 inputs:
   go-version:
-    description: "Go version to install"
+    description: "Go version to install (passed to go-make/setup)"
     required: true
-    default: ">= 1.24"
-  go-dependencies:
-    description: "Download go dependencies"
+    default: "1.26.2"
+  cache-key-prefix:
+    description: "Prefix all cache keys with this value (passed to go-make/setup)"
+    required: true
+    default: "v1"
+  cache-enabled:
+    description: "Enable build/mod and tool caching (passed to go-make/setup)"
     required: true
     default: "true"
-  cache-key-prefix:
-    description: "Prefix all cache keys with this value"
-    required: true
-    default: "181053ac82"
   download-test-fixture-cache:
     description: "Download test fixture cache from OCI and github actions"
     required: true
     default: "false"
-  tools:
-    description: "whether to install tools"
-    default: "true"
   bootstrap-apt-packages:
     description: "Space delimited list of tools to install via apt"
     default: "libxml2-utils"
@@ -28,29 +29,16 @@ inputs:
 runs:
   using: "composite"
   steps:
-    # note: go mod and build is automatically cached on default with v4+
-    - uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
-      if: inputs.go-version != ''
+    - name: Setup go + go-make tooling
+      uses: anchore/go-make/.github/actions/setup@fa5421b3bf24c9d18f11a736c5eb4172f2b7d683 # v0.8.1
       with:
         go-version: ${{ inputs.go-version }}
+        cache-key-prefix: ${{ inputs.cache-key-prefix }}
+        cache-enabled: ${{ inputs.cache-enabled }}
 
-    - name: Restore tool cache
-      if: inputs.tools == 'true'
-      id: tool-cache
-      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
-      with:
-        path: ${{ github.workspace }}/.tool
-        key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
-
-    - name: Install project tools
+    - name: Install binny-managed tools
       shell: bash
-      if: inputs.tools == 'true'
-      run: make tools
-
-    - name: Install go dependencies
-      if: inputs.go-dependencies == 'true'
-      shell: bash
-      run: make ci-bootstrap-go
+      run: make binny:install
 
     - name: Install apt packages
       if: inputs.bootstrap-apt-packages != ''
@@ -59,11 +47,30 @@ runs:
         APT_PACKAGES: ${{ inputs.bootstrap-apt-packages }}
       run: |
         IFS=' ' read -ra packages <<< "$APT_PACKAGES"
-        DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y "${packages[@]}"
+        # the AMI already ships most of these, and `apt update` costs ~40MB of index (minutes,
+        # when archive.ubuntu.com throttles us) to find that out. only touch apt if we must.
+        missing=()
+        for pkg in "${packages[@]}"; do
+          dpkg -s "$pkg" >/dev/null 2>&1 || missing+=("$pkg")
+        done
+        if [ ${#missing[@]} -eq 0 ]; then
+          echo "all apt packages already present: ${packages[*]}"
+          exit 0
+        fi
+        DEBIAN_FRONTEND=noninteractive sudo apt update && sudo -E apt install -y "${missing[@]}"
 
+    # ORAS cache: restore-only on non-default branches / forks
     - name: Restore ORAS cache from github actions
-      if: inputs.download-test-fixture-cache == 'true'
-      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
+      if: ${{ inputs.download-test-fixture-cache == 'true' && (github.ref != format('refs/heads/{0}', github.event.repository.default_branch) || github.event.repository.fork == true) }}
+      uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+      with:
+        path: ${{ github.workspace }}/.tmp/oras-cache
+        key: ${{ inputs.cache-key-prefix }}-oras-cache
+
+    # ORAS cache: restore + save on the default branch of the canonical repo only.
+    - name: Restore and save ORAS cache from github actions
+      if: ${{ inputs.download-test-fixture-cache == 'true' && github.ref == format('refs/heads/{0}', github.event.repository.default_branch) && github.event.repository.fork == false }}
+      uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
       with:
         path: ${{ github.workspace }}/.tmp/oras-cache
         key: ${{ inputs.cache-key-prefix }}-oras-cache

.github/dependabot.yml

@@ -1,27 +1,36 @@
+# Dependabot configuration
+
 version: 2
 
 updates:
 
   - package-ecosystem: gomod
-    directory: "/"
+    directories:
+      - "/"
+      - "/.make"
+    cooldown:
+      default-days: 7
     schedule:
-      interval: "daily"
+      interval: "weekly"
+      day: "friday"
     open-pull-requests-limit: 10
     labels:
       - "dependencies"
+    ignore:
+      - dependency-name: "github.com/aquasecurity/go-pep440-version"
+      - dependency-name: "github.com/aquasecurity/go-version"
+      - dependency-name: "github.com/knqyf263/go-apk-version"
+      - dependency-name: "github.com/knqyf263/go-deb-version"
 
   - package-ecosystem: "github-actions"
-    directory: "/"
+    directories:
+      - "/"
+      - "/.github/actions/*"
+    cooldown:
+      default-days: 7
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 10
-    labels:
-      - "dependencies"
-
-  - package-ecosystem: "github-actions"
-    directory: "/.github/actions/bootstrap"
-    schedule:
-      interval: "daily"
+      interval: "weekly"
+      day: "friday"
     open-pull-requests-limit: 10
     labels:
       - "dependencies"

.github/pull_request_template.md

@@ -1,11 +1,10 @@
-# Description
+## Description
 
-Please include a summary of the changes along with any relevant motivation and context,
-or link to an issue where this is explained.
+<!-- Please include a summary of the changes along with any relevant motivation and context -->
 
-<!-- If this completes an issue, please include: -->
+<!-- If CLI output changed, show an example (before/after if helpful) -->
 
-- Fixes
+<!-- If this changes application or API configuration, describe new/changed/removed options -->
 
 ## Type of change
 
@@ -18,8 +17,12 @@ or link to an issue where this is explained.
 - [ ] Chore (improve the developer experience, fix a test flake, etc, without changing the visible behavior of Syft)
 - [ ] Performance (make Syft run faster or use less memory, without changing visible behavior much)
 
-# Checklist:
+## Checklist
 
 - [ ] I have added unit tests that cover changed behavior
 - [ ] I have tested my code in common scenarios and confirmed there are no regressions
 - [ ] I have added comments to my code, particularly in hard-to-understand sections
+
+## Issue references
+
+<!-- If this fixes an issue, include "Fixes #<issue-number>" or otherwise list the issue references -->

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

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

.github/scripts/check_binary_fixture_size.sh

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

.github/scripts/ci-check.sh

@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-
-red=$(tput setaf 1)
-bold=$(tput bold)
-normal=$(tput sgr0)
-
-# assert we are running in CI (or die!)
-if [[ -z "$CI" ]]; then
-    echo "${bold}${red}This step should ONLY be run in CI. Exiting...${normal}"
-    exit 1
-fi

.github/scripts/coverage.py

@@ -1,36 +0,0 @@
-#!/usr/bin/env python3
-import subprocess
-import sys
-import shlex
-
-
-class bcolors:
-    HEADER = '\033[95m'
-    OKBLUE = '\033[94m'
-    OKCYAN = '\033[96m'
-    OKGREEN = '\033[92m'
-    WARNING = '\033[93m'
-    FAIL = '\033[91m'
-    ENDC = '\033[0m'
-    BOLD = '\033[1m'
-    UNDERLINE = '\033[4m'
-
-
-if len(sys.argv) < 3:
-    print("Usage: coverage.py [threshold] [go-coverage-report]")
-    sys.exit(1)
-
-
-threshold = float(sys.argv[1])
-report = sys.argv[2]
-
-
-args = shlex.split(f"go tool cover -func {report}")
-p = subprocess.run(args, capture_output=True, text=True)
-
-percent_coverage = float(p.stdout.splitlines()[-1].split()[-1].replace("%", ""))
-print(f"{bcolors.BOLD}Coverage: {percent_coverage}%{bcolors.ENDC}")
-
-if percent_coverage < threshold:
-    print(f"{bcolors.BOLD}{bcolors.FAIL}Coverage below threshold of {threshold}%{bcolors.ENDC}")
-    sys.exit(1)

.github/scripts/find_cache_paths.py

@@ -1,35 +1,45 @@
 #!/usr/bin/env python3
 from __future__ import annotations
 
-import os
 import glob
-import sys
-import json
 import hashlib
-
+import json
+import os
+import sys
 
 IGNORED_PREFIXES = []
 
 
 def find_fingerprints_and_check_dirs(base_dir):
-    all_fingerprints = set(glob.glob(os.path.join(base_dir, '**', 'test*', '**', '*.fingerprint'), recursive=True))
+    all_fingerprints = set(
+        glob.glob(
+            os.path.join(base_dir, "**", "test*", "**", "*.fingerprint"), recursive=True
+        )
+    )
 
-    all_fingerprints = {os.path.relpath(fp) for fp in all_fingerprints
-                        if not any(fp.startswith(prefix) for prefix in IGNORED_PREFIXES)}
+    all_fingerprints = {
+        os.path.relpath(fp)
+        for fp in all_fingerprints
+        if not any(fp.startswith(prefix) for prefix in IGNORED_PREFIXES)
+    }
 
     if not all_fingerprints:
         show("No .fingerprint files or cache directories found.")
         exit(1)
 
-    missing_content = []
+    orphan_fingerprints = []
+    empty_content = []
     valid_paths = set()
     fingerprint_contents = []
 
     for fingerprint in all_fingerprints:
-        path = fingerprint.replace('.fingerprint', '')
+        path = fingerprint.replace(".fingerprint", "")
 
         if not os.path.exists(path):
-            missing_content.append(path)
+            # paired content path is entirely missing — the .fingerprint is likely
+            # leftover from a moved/deleted source (testdata trees are git-ignored,
+            # so they persist locally across rename refactors)
+            orphan_fingerprints.append(fingerprint)
             continue
 
         if not os.path.isdir(path):
@@ -39,13 +49,13 @@ def find_fingerprints_and_check_dirs(base_dir):
         if os.listdir(path):
             valid_paths.add(path)
         else:
-            missing_content.append(path)
+            empty_content.append(path)
 
-        with open(fingerprint, 'r') as f:
+        with open(fingerprint, "r") as f:
             content = f.read().strip()
             fingerprint_contents.append((fingerprint, content))
 
-    return sorted(valid_paths), missing_content, fingerprint_contents
+    return sorted(valid_paths), empty_content, orphan_fingerprints, fingerprint_contents
 
 
 def parse_fingerprint_contents(fingerprint_content):
@@ -59,7 +69,9 @@ def parse_fingerprint_contents(fingerprint_content):
 def calculate_sha256(fingerprint_contents):
     sorted_fingerprint_contents = sorted(fingerprint_contents, key=lambda x: x[0])
 
-    concatenated_contents = ''.join(content for _, content in sorted_fingerprint_contents)
+    concatenated_contents = "".join(
+        content for _, content in sorted_fingerprint_contents
+    )
 
     sha256_hash = hashlib.sha256(concatenated_contents.encode()).hexdigest()
 
@@ -68,7 +80,7 @@ def calculate_sha256(fingerprint_contents):
 
 def calculate_file_sha256(file_path):
     sha256_hash = hashlib.sha256()
-    with open(file_path, 'rb') as f:
+    with open(file_path, "rb") as f:
         for byte_block in iter(lambda: f.read(4096), b""):
             sha256_hash.update(byte_block)
     return sha256_hash.hexdigest()
@@ -79,17 +91,28 @@ def show(*s: str):
 
 
 def main(file_path: str | None):
-    base_dir = '.'
-    valid_paths, missing_content, fingerprint_contents = find_fingerprints_and_check_dirs(base_dir)
+    base_dir = "."
+    valid_paths, empty_content, orphan_fingerprints, fingerprint_contents = (
+        find_fingerprints_and_check_dirs(base_dir)
+    )
 
-    if missing_content:
-        show("The following paths are missing or have no content, but have corresponding .fingerprint files:")
-        for path in sorted(missing_content):
+    if empty_content:
+        show(
+            "The following paths exist but are empty, and have corresponding .fingerprint files:"
+        )
+        for path in sorted(empty_content):
             show(f"- {path}")
         # when adding new cache directories there is a time where it is not possible to have this directory without
         # running the tests first... but this step is a prerequisite for running the tests. We should not block on this.
-        # show("Please ensure these paths exist and have content if they are directories.")
-        # exit(1)
+
+    if orphan_fingerprints:
+        show(
+            "The following .fingerprint files reference paths that no longer exist "
+            "(likely leftover from a moved/deleted cataloger — safe to delete, "
+            "or run `task prune-orphan-fingerprints`):"
+        )
+        for fp in sorted(orphan_fingerprints):
+            show(f"- {fp}")
 
     sha256_hash = calculate_sha256(fingerprint_contents)
 
@@ -101,30 +124,24 @@ def main(file_path: str | None):
                 file_digest = calculate_file_sha256(fingerprint_file)
 
                 # Parse the fingerprint file to get the digest/path tuples
-                with open(fingerprint_file, 'r') as f:
+                with open(fingerprint_file, "r") as f:
                     fingerprint_content = f.read().strip()
                     input_map = parse_fingerprint_contents(fingerprint_content)
 
-                paths_with_digests.append({
-                    "path": path,
-                    "digest": file_digest,
-                    "input": input_map
-                })
+                paths_with_digests.append(
+                    {"path": path, "digest": file_digest, "input": input_map}
+                )
 
         except Exception as e:
             show(f"Error processing {fingerprint_file}: {e}")
             raise e
 
-
-    output = {
-        "digest": sha256_hash,
-        "paths": paths_with_digests
-    }
+    output = {"digest": sha256_hash, "paths": paths_with_digests}
 
     content = json.dumps(output, indent=2, sort_keys=True)
 
     if file_path:
-        with open(file_path, 'w') as f:
+        with open(file_path, "w") as f:
             f.write(content)
 
     print(content)

.github/scripts/fingerprint_docker_fixtures.py

@@ -33,9 +33,9 @@ def is_git_tracked_or_untracked(directory):
 
 
 def find_test_fixture_dirs_with_images(base_dir):
-    """Find directories that contain 'test-fixtures' and at least one 'image-*' directory."""
+    """Find directories that contain 'testdata' and at least one 'image-*' directory."""
     for root, dirs, files in os.walk(base_dir):
-        if 'test-fixtures' in root:
+        if 'testdata' in root:
             image_dirs = [d for d in dirs if d.startswith('image-')]
             if image_dirs:
                 yield os.path.realpath(root)

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

@@ -1,30 +0,0 @@
-#!/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 -p ${ORIGINAL_STATE_DIR}/* ./ && git update-index -q --refresh && rm -fR ${ORIGINAL_STATE_DIR} ${TIDY_STATE_DIR}" EXIT
-
-# capturing original state of files...
-cp go.mod go.sum "${ORIGINAL_STATE_DIR}"
-
-# capturing state of go.mod and go.sum after running go mod tidy...
-go mod tidy
-cp go.mod go.sum "${TIDY_STATE_DIR}"
-
-set +e
-
-# detect difference between the git HEAD state and the go mod tidy state
-DIFF_MOD=$(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/json-schema-drift-check.sh

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

.github/scripts/prune_orphan_fingerprints.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+"""
+Remove orphan *.fingerprint files left behind by moved/deleted catalogers.
+
+A fingerprint is considered orphaned when:
+  1. its paired content path (the fingerprint path with `.fingerprint` stripped)
+     does not exist, AND
+  2. the nearest ancestor `testdata/` directory has no `Makefile` claiming
+     responsibility for generating that path.
+
+The second condition is the safety check: if there is a Makefile, the
+fingerprint is "live" and might just be waiting for fixtures to be built —
+leave it alone. Without a Makefile, nothing in-repo will ever regenerate
+the content, so the fingerprint is dead weight that triggers spurious
+"missing path" warnings.
+
+Empty parent directories are also pruned after removing the fingerprint.
+
+Use --dry-run to preview without deleting.
+"""
+from __future__ import annotations
+
+import argparse
+import glob
+import os
+import sys
+
+
+def find_ancestor_testdata(path: str) -> str | None:
+    d = os.path.dirname(path)
+    while d and d not in (".", os.sep):
+        if os.path.basename(d) == "testdata":
+            return d
+        d = os.path.dirname(d)
+    return None
+
+
+def is_orphan(fingerprint: str) -> bool:
+    paired = fingerprint[: -len(".fingerprint")]
+    if os.path.exists(paired):
+        return False
+
+    testdata_dir = find_ancestor_testdata(fingerprint)
+    if testdata_dir and os.path.isfile(os.path.join(testdata_dir, "Makefile")):
+        # a Makefile exists that may regenerate this — not safe to prune
+        return False
+
+    return True
+
+
+def prune_empty_parents(start: str, stop_at: str = ".") -> list[str]:
+    removed = []
+    d = os.path.dirname(start)
+    stop_at = os.path.abspath(stop_at)
+    while d and os.path.abspath(d) != stop_at:
+        try:
+            if not os.listdir(d):
+                os.rmdir(d)
+                removed.append(d)
+                d = os.path.dirname(d)
+            else:
+                break
+        except OSError:
+            break
+    return removed
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Show what would be removed without deleting anything",
+    )
+    args = parser.parse_args()
+
+    all_fingerprints = glob.glob("**/test*/**/*.fingerprint", recursive=True)
+    orphans = sorted(fp for fp in all_fingerprints if is_orphan(fp))
+
+    if not orphans:
+        print("no orphan fingerprints found")
+        return 0
+
+    verb = "would remove" if args.dry_run else "removing"
+    print(f"{verb} {len(orphans)} orphan fingerprint(s):")
+    for fp in orphans:
+        print(f"- {fp}")
+        if args.dry_run:
+            continue
+        try:
+            os.remove(fp)
+        except OSError as e:
+            print(f"  ! failed to remove: {e}", file=sys.stderr)
+            continue
+        for d in prune_empty_parents(fp):
+            print(f"  (also removed empty dir {d})")
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.github/scripts/trigger-release.sh

@@ -1,57 +0,0 @@
-#!/usr/bin/env bash
-set -eu
-
-bold=$(tput bold)
-normal=$(tput sgr0)
-
-GH_CLI=.tool/gh
-
-if ! [ -x "$(command -v $GH_CLI)" ]; then
-    echo "The GitHub CLI could not be found. run: make bootstrap"
-    exit 1
-fi
-
-$GH_CLI auth status
-
-# set the default repo in cases where multiple remotes are defined
-$GH_CLI repo set-default anchore/syft
-
-export GITHUB_TOKEN="${GITHUB_TOKEN-"$($GH_CLI auth token)"}"
-
-# we need all of the git state to determine the next version. Since tagging is done by
-# the release pipeline it is possible to not have all of the tags from previous releases.
-git fetch --tags
-
-# populates the CHANGELOG.md and VERSION files
-echo "${bold}Generating changelog...${normal}"
-make changelog 2> /dev/null
-
-NEXT_VERSION=$(cat VERSION)
-
-if [[ "$NEXT_VERSION" == "" ||  "${NEXT_VERSION}" == "(Unreleased)" ]]; then
-    echo "Could not determine the next version to release. Exiting..."
-    exit 1
-fi
-
-while true; do
-    read -p "${bold}Do you want to trigger a release for version '${NEXT_VERSION}'?${normal} [y/n] " yn
-    case $yn in
-        [Yy]* ) echo; break;;
-        [Nn]* ) echo; echo "Cancelling release..."; exit;;
-        * ) echo "Please answer yes or no.";;
-    esac
-done
-
-echo "${bold}Kicking off release for ${NEXT_VERSION}${normal}..."
-echo
-$GH_CLI workflow run release.yaml -f version=${NEXT_VERSION}
-
-echo
-echo "${bold}Waiting for release to start...${normal}"
-sleep 10
-
-set +e
-
-echo "${bold}Head to the release workflow to monitor the release:${normal} $($GH_CLI run list --workflow=release.yaml --limit=1 --json url --jq '.[].url')"
-id=$($GH_CLI run list --workflow=release.yaml --limit=1 --json databaseId --jq '.[].databaseId')
-$GH_CLI run watch $id --exit-status || (echo ; echo "${bold}Logs of failed step:${normal}" && GH_PAGER="" $GH_CLI run view $id --log-failed)

.github/workflows/codeql-analysis.yml

@@ -1,75 +0,0 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-name: "CodeQL Security Scan"
-
-on:
-  push:
-    branches:
-      # only run when there are pushes to the main branch (not on PRs)
-      - main
-
-  schedule:
-    - cron: '0 0 * * 3'
-
-permissions:
-  contents: read
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-22.04-4core-16gb
-    if: github.repository == 'anchore/syft' # only run for main repo
-    permissions:
-      security-events: write
-
-    strategy:
-      fail-fast: false
-      matrix:
-        # Override automatic language detection by changing the below list
-        # Supported options are ['csharp', 'cpp', 'go', 'java', 'javascript', 'python']
-        language: ['go', 'python']
-        # Learn more...
-        # https://docs.github.com/en/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#overriding-automatic-language-detection
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-      with:
-        persist-credentials: false
-
-    - name: Install Go
-      uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 #v5.5.0
-      with:
-        go-version-file: go.mod
-
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@df559355d593797519d70b90fc8edd5db049e7a2 #v3.29.5
-      with:
-        languages: ${{ matrix.language }}
-        # If you wish to specify custom queries, you can do so here or in a config file.
-        # By default, queries listed here will override any specified in a config file. 
-        # Prefix the list here with "+" to use these queries and those in the config file.
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
-
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
-    # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
-      uses: github/codeql-action/autobuild@df559355d593797519d70b90fc8edd5db049e7a2 #v3.29.5
-
-    # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
-
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
-    #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
-
-    #- run: |
-    #   make bootstrap
-    #   make release
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@df559355d593797519d70b90fc8edd5db049e7a2 #v3.29.5

.github/workflows/codeql.yaml

@@ -0,0 +1,21 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  schedule:
+    - cron: '38 11 * * 3'
+
+permissions: {}
+
+jobs:
+  analyze:
+    name: Analyze
+    uses: anchore/workflows/.github/workflows/codeql.yaml@7212994dc8fc3a53fe9c8e766ab5b4ddd16ea3d4 # v0.8.0
+    permissions:
+      security-events: write
+      packages: read
+      actions: read
+      contents: read

.github/workflows/dependabot-automation.yaml

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

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

@@ -1,60 +0,0 @@
-name: "Detect schema changes"
-
-on:
-  # IMPORTANT! This workflow is triggered by the `pull_request_target` event
-  # which means that forked PRs will run with access secrets from the repo
-  # it's forked from (the "target" repo).
-  #
-  # For this reason we only NEVER checkout the code from the pull request
-  # (e.g. "ref: ${{ github.event.pull_request.head.sha }}") to prevent
-  # accidentally running potentially untrusted code.
-  #
-  # By default the checkout will be:
-  #   - GITHUB_SHA: Last commit on the PR base branch
-  #   - GITHUB_REF: PR base branch
-  #
-  # ...unlike a typical PR where:
-  #   - GITHUB_SHA: Last merge commit on the GITHUB_REF branch
-  #   - GITHUB_REF: PR merge branch refs/pull/:prNumber/merge
-  pull_request_target:
-
-env:
-  # note: this is used within hashFiles() so must be within the GITHUB_WORKSPACE path (or will silently fail)
-  CI_COMMENT_FILE: .tmp/labeler-comment.txt
-  # needs to be any string to uniquely identify the comment on a PR across multiple runs
-  COMMENT_HEADER: "label-commentary"
-
-jobs:
-  label:
-    name: "Label changes"
-    runs-on: ubuntu-22.04
-    permissions:
-      contents: read
-      pull-requests: write
-      issues: write
-    steps:
-
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - run: python .github/scripts/labeler.py
-        env:
-          # note: this token has write access to the repo
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          GITHUB_PR_NUMBER: ${{ github.event.number }}
-
-      - name: Delete existing comment
-        if: ${{ hashFiles( env.CI_COMMENT_FILE ) == '' }}
-        uses: marocchino/sticky-pull-request-comment@773744901bac0e8cbb5a0dc842800d45e9b2b405 #v2.9.4
-        with:
-          header: ${{ env.COMMENT_HEADER }}
-          hide: true
-          hide_classify: "OUTDATED"
-
-      - name: Add comment
-        if: ${{ hashFiles( env.CI_COMMENT_FILE ) != '' }}
-        uses: marocchino/sticky-pull-request-comment@773744901bac0e8cbb5a0dc842800d45e9b2b405 #v2.9.4
-        with:
-          header: ${{ env.COMMENT_HEADER }}
-          path: ${{ env.CI_COMMENT_FILE }}

.github/workflows/oss-project-board-add.yaml

@@ -1,18 +0,0 @@
-name: Add to OSS board
-
-permissions:
-  contents: read
-
-on:
-  issues:
-    types:
-      - opened
-      - reopened
-      - transferred
-      - labeled
-
-jobs:
-  run:
-    uses: "anchore/workflows/.github/workflows/oss-project-board-add.yaml@main"
-    secrets:
-      token: ${{ secrets.OSS_PROJECT_GH_TOKEN }}

.github/workflows/release.yaml

@@ -1,7 +1,11 @@
 name: "Release"
 
-permissions:
-  contents: read
+permissions: {}
+
+# there should never be two releases in progress at the same time
+concurrency:
+  group: release
+  cancel-in-progress: false
 
 on:
   workflow_dispatch:
@@ -9,114 +13,69 @@ on:
       version:
         description: tag the latest commit on main with the given version (prefixed with v)
         required: true
+      phase:
+        description: the specific workflow phase to run or all
+        required: true
+        default: "all"
+        type: choice
+        options:
+          - "all"
+          - "install-script-only"
+      skip-checks:
+        description: skip the check-gate (release even if checks haven't passed on main)
+        type: boolean
+        default: false
+        required: false
 
 jobs:
-  quality-gate:
-    environment: release
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
+  version-available:
+    if: ${{ github.event.inputs.phase == 'all' }}
+    permissions:
+      contents: read # required for fetching tags
+    uses: anchore/workflows/.github/workflows/check-version-available.yaml@7212994dc8fc3a53fe9c8e766ab5b4ddd16ea3d4 # v0.8.0
+    with:
+      version: ${{ github.event.inputs.version }}
 
-      - name: Check if running on main
-        if: github.ref != 'refs/heads/main'
-        # we are using the following flag when running `cosign blob-verify` for checksum signature verification:
-        #   --certificate-identity-regexp "https://github.com/anchore/.github/workflows/release.yaml@refs/heads/main"
-        # if we are not on the main branch, the signature will not be verifiable since the suffix requires the main branch
-        # at the time of when the OIDC token was issued on the Github Actions runner.
-        run: echo "This can only be run on the main branch otherwise releases produced will not be verifiable with cosign" && exit 1
-
-      - name: Check if tag already exists
-        # note: this will fail if the tag already exists
-        run: |
-          [[ "$VERSION" == v* ]] || (echo "version '$VERSION' does not have a 'v' prefix" && exit 1)
-          git tag "$VERSION"
-        env:
-          VERSION: ${{ github.event.inputs.version }}
-
-      - name: Check static analysis results
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: static-analysis
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "Static analysis"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Check unit test results
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: unit
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "Unit tests"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Check integration test results
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: integration
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "Integration tests"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Check acceptance test results (linux)
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: acceptance-linux
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "Acceptance tests (Linux)"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Check acceptance test results (mac)
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: acceptance-mac
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "Acceptance tests (Mac)"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Check cli test results (linux)
-        uses: fountainhead/action-wait-for-check@5a908a24814494009c4bb27c242ea38c93c593be # v1.2.0
-        id: cli-linux
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          # This check name is defined as the github action job name (in .github/workflows/testing.yaml)
-          checkName: "CLI tests (Linux)"
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
-
-      - name: Quality gate
-        if: steps.static-analysis.outputs.conclusion != 'success' || steps.unit.outputs.conclusion != 'success' || steps.integration.outputs.conclusion != 'success' || steps.cli-linux.outputs.conclusion != 'success' || steps.acceptance-linux.outputs.conclusion != 'success' || steps.acceptance-mac.outputs.conclusion != 'success'
-        env:
-          STATIC_ANALYSIS_STATUS: ${{ steps.static-analysis.conclusion }}
-          UNIT_TEST_STATUS: ${{ steps.unit.outputs.conclusion }}
-          INTEGRATION_TEST_STATUS: ${{ steps.integration.outputs.conclusion }}
-          ACCEPTANCE_LINUX_STATUS: ${{ steps.acceptance-linux.outputs.conclusion }}
-          ACCEPTANCE_MAC_STATUS: ${{ steps.acceptance-mac.outputs.conclusion }}
-          CLI_LINUX_STATUS: ${{ steps.cli-linux.outputs.conclusion }}
-        run: |
-          echo "Static Analysis Status: $STATIC_ANALYSIS_STATUS"
-          echo "Unit Test Status: $UNIT_TEST_STATUS"
-          echo "Integration Test Status: $INTEGRATION_TEST_STATUS"
-          echo "Acceptance Test (Linux) Status: $ACCEPTANCE_LINUX_STATUS"
-          echo "Acceptance Test (Mac) Status: $ACCEPTANCE_MAC_STATUS"
-          echo "CLI Test (Linux) Status: $CLI_LINUX_STATUS"
-          false
+  check-gate:
+    if: ${{ github.event.inputs.phase == 'all' && !inputs.skip-checks }}
+    permissions:
+      contents: read
+      checks: read # required for getting the status of specific check names
+    uses: anchore/workflows/.github/workflows/check-gate.yaml@7212994dc8fc3a53fe9c8e766ab5b4ddd16ea3d4 # v0.8.0
+    with:
+      # these are checks that should be run on pull-request and merges to main.
+      # we do NOT want to kick off a release if these have not been verified on main.
+      # Please see the validations.yaml workflow for the names that should be used here.
+      checks: '["Acceptance tests (Linux)", "Acceptance tests (Mac)", "Build snapshot artifacts", "CLI tests (Linux)", "Integration tests", "Static analysis", "Unit tests"]'
 
   release:
-    needs: [quality-gate]
-    runs-on: ubuntu-24.04
+    needs: [check-gate, version-available]
+    # run even when check-gate is skipped, but never when version-available
+    # failed/was skipped, nor when check-gate failed or was cancelled. note:
+    # always() disables the implicit success() gate on ALL needs, so the
+    # version-available requirement must be re-asserted explicitly here.
+    if: >-
+      ${{ always()
+          && needs.version-available.result == 'success'
+          && !contains(fromJSON('["failure", "cancelled"]'), needs.check-gate.result) }}
+    environment: release
+    # runs-on.com: compute instances for parallel builds
+    #   spot disabled: reliability for build workflows (used for releases too)
+    #   goreleaser uses parallelism of 12, so we need more CPUs
+    #   s3-cache: faster actions cache
+    #   volume: enlarge dist/ disk -- the default 40GB EBS root fills up during the multi-arch
+    #   image + binary build and OOMs (runs out of disk); size it well above peak usage.
+    #   provisioned throughput/iops above the gp3 free baseline (125mbs/3000iops) approximate
+    #   the tmpfs IO speed on disk, for ~1c/run.
+    #   note: tmpfs intentionally omitted -- a RAM-backed dist/ never touches the enlarged
+    #   volume and competes with the build's memory peak, so keep dist/ on disk.
+    runs-on: runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/extras=s3-cache/volume=120gb:gp3:500mbs:4000iops
     permissions:
-      contents: write
-      packages: write
-      # required for goreleaser signs section with cosign
-      id-token: write
+      contents: write # required for creating the GitHub release and pushing the version tag
+      packages: write # required for publishing release artifacts to GitHub packages
+      id-token: write # required for keyless signing (cosign/sigstore OIDC)
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           fetch-depth: 0
           persist-credentials: true
@@ -124,32 +83,30 @@ jobs:
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
 
+      # dockers_v2 builds multi-platform manifests in a single buildx invocation, which requires a
+      # docker-container driver builder (the default builder on the runner cannot build multi-platform).
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069 # v4.4.1
+
       - name: Login to Docker Hub
-        uses: docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1  #v3.5.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f #v4.6.0
         with:
           username: ${{ secrets.ANCHOREOSSWRITE_DH_USERNAME }}
           password: ${{ secrets.ANCHOREOSSWRITE_DH_PAT }}
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1  #v3.5.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f #v4.6.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Tag release
-        run: |
-          git config --global user.name "anchoreci"
-          git config --global user.email "anchoreci@users.noreply.github.com"
-          git tag -a "$VERSION" -m "Release $VERSION"
-          git push origin --tags
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          VERSION: ${{ github.event.inputs.version }}
-
       - name: Build & publish release artifacts
         run: make ci-release
         env:
+          # for pushing tags (does not inherit workflow permissions)
+          TAG_TOKEN: ${{ secrets.TAG_TOKEN }}
+          RELEASE_VERSION: ${{ github.event.inputs.version }}
           # for mac signing and notarization...
           QUILL_SIGN_P12: ${{ secrets.ANCHORE_APPLE_DEVELOPER_ID_CERT_CHAIN }}
           QUILL_SIGN_PASSWORD: ${{ secrets.ANCHORE_APPLE_DEVELOPER_ID_CERT_PASS }}
@@ -161,26 +118,18 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@7b36ad622f042cab6f59a75c2ac24ccb256e9b45 #v0.20.4
+      - uses: anchore/sbom-action@3ad7283483fc7af8ff2b4ea19663c2d5ca935e26 #v0.24.2
         continue-on-error: true
         with:
           file: go.mod
           artifact-name: sbom.spdx.json
 
-      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
-        continue-on-error: true
-        with:
-          status: ${{ job.status }}
-          fields: repo,workflow,action,eventName
-          text: "A new Syft release has been published: https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}"
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
-        if: ${{ success() }}
-
   release-install-script:
     needs: [release]
-    if: ${{ needs.release.result == 'success' }}
-    uses: "anchore/workflows/.github/workflows/release-install-script.yaml@main"
+    if: ${{ always() && (needs.release.result == 'success' || github.event.inputs.phase == 'install-script-only') }}
+    permissions:
+      contents: read # required for the reusable workflow to check out the repo and publish the install script
+    uses: anchore/workflows/.github/workflows/release-install-script.yaml@7212994dc8fc3a53fe9c8e766ab5b4ddd16ea3d4 # v0.8.0
     with:
       tag: ${{ github.event.inputs.version }}
     secrets:

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

@@ -1,15 +0,0 @@
-name: "Manage Awaiting Response Label"
-
-on:
-  issue_comment:
-    types: [created]
-
-jobs:
-  run:
-    permissions:
-      contents: read
-      issues: write
-      pull-requests: write
-    uses: "anchore/workflows/.github/workflows/remove-awaiting-response-label.yaml@main"
-    secrets:
-      token: ${{ secrets.OSS_PROJECT_GH_TOKEN }}

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

@@ -1,44 +0,0 @@
-name: "Test fixture cache: publish"
-
-on:
-  workflow_dispatch:
-  schedule:
-    # run nightly at 4AM UTC
-    - cron: "0 4 * * *"
-
-permissions:
-  contents: read
-
-jobs:
-
-  Publish:
-    name: "Publish test fixture image cache"
-    # we use this runner to get enough storage space for docker images and fixture cache
-    runs-on: ubuntu-22.04-4core-16gb
-    if: github.repository == 'anchore/syft' # only run for main repo
-    permissions:
-      packages: write
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-        with:
-          # we want to rebuild the cache with no previous state
-          download-test-fixture-cache: false
-
-      - name: Run all tests
-        run: make test
-        env:
-          # we want to rebuild the cache with no previous state
-          DOWNLOAD_TEST_FIXTURE_CACHE: "false"
-
-      - name: Login to GitHub Container Registry (ORAS)
-        run: echo "${{ secrets.GITHUB_TOKEN }}" | .tool/oras login ghcr.io -u "$ACTOR" --password-stdin
-        env:
-          ACTOR: ${{ github.actor }}
-
-      - name: Publish test fixture cache
-        run: make upload-test-fixture-cache

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

@@ -1,51 +0,0 @@
-name: PR to update Anchore dependencies
-on:
-  workflow_dispatch:
-    inputs:
-      repos:
-        description: "List of dependencies to update"
-        required: true
-        type: string
-
-permissions:
-  contents: read
-
-jobs:
-  update:
-    runs-on: ubuntu-latest
-    if: github.repository_owner == 'anchore' # only run for main repo (not forks)
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-        with:
-          tools: false
-          bootstrap-apt-packages: ""
-
-      - name: Update dependencies
-        id: update
-        uses: anchore/workflows/.github/actions/update-go-dependencies@main
-        with:
-          repos: ${{ github.event.inputs.repos }}
-
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
-        id: generate-token
-        with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
-
-      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
-        with:
-          signoff: true
-          delete-branch: true
-          draft: ${{ steps.update.outputs.draft }}
-          # do not change this branch, as other workflows depend on it
-          branch: auto/integration
-          labels: dependencies,pre-release
-          commit-message: "chore(deps): update anchore dependencies"
-          title: "chore(deps): update anchore dependencies"
-          body: ${{ steps.update.outputs.summary }}
-          token: ${{ steps.generate-token.outputs.token }}

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

@@ -1,67 +0,0 @@
-name: PR for latest versions of tools
-on:
-  schedule:
-    - cron: "0 8 * * *" # 3 AM EST
-
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  update-bootstrap-tools:
-    runs-on: ubuntu-latest
-    if: github.repository == 'anchore/syft' # only run for main repo
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-        with:
-          bootstrap-apt-packages: ""
-          go-dependencies: false
-
-      - name: "Update tool versions"
-        id: latest-versions
-        run: |
-          make update-tools
-          make list-tools
-          
-          export NO_COLOR=1
-          delimiter="$(openssl rand -hex 8)"
-          
-          {
-            echo "status<<${delimiter}"
-            make list-tool-updates
-            echo "${delimiter}"
-          } >> $GITHUB_OUTPUT
-          
-          {
-            echo "### Tool version status"
-            echo "\`\`\`"
-            make list-tool-updates
-            echo "\`\`\`"
-          } >> $GITHUB_STEP_SUMMARY
-
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
-        id: generate-token
-        with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
-
-      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
-        with:
-          signoff: true
-          delete-branch: true
-          branch: auto/latest-tools
-          labels: dependencies
-          commit-message: 'chore(deps): update tools to latest versions'
-          title: 'chore(deps): update tools to latest versions'
-          body: |
-            ```
-            ${{ steps.latest-versions.outputs.status }}
-            ```
-            This is an auto-generated pull request to update all of the tools to the latest versions.
-          token: ${{ steps.generate-token.outputs.token }}

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

@@ -1,57 +0,0 @@
-name: PR to update CPE dictionary index
-on:
-  schedule:
-    - cron: "0 1 * * 1" # every monday at 1 AM
-
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-env:
-  SLACK_NOTIFICATIONS: true
-
-jobs:
-  upgrade-cpe-dictionary-index:
-    runs-on: ubuntu-latest
-    if: github.repository == 'anchore/syft' # only run for main repo
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-
-      - run: |
-          make generate-cpe-dictionary-index
-
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
-        id: generate-token
-        with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
-
-      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
-        with:
-          signoff: true
-          delete-branch: true
-          branch: auto/latest-cpe-dictionary-index
-          labels: dependencies
-          commit-message: "chore(deps): update CPE dictionary index"
-          title: "chore(deps): update CPE dictionary index"
-          body: |
-            Update CPE dictionary index based on the latest available CPE dictionary
-          token: ${{ steps.generate-token.outputs.token }}
-
-      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
-        with:
-          status: ${{ job.status }}
-          fields: workflow,eventName,job
-          text: Syft CPE dictionary index update failed
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
-        if: ${{ failure() && env.SLACK_NOTIFICATIONS == 'true' }}

.github/workflows/validate-github-actions.yaml

@@ -1,10 +1,8 @@
 name: "Validate GitHub Actions"
 
 on:
+  workflow_dispatch:
   pull_request:
-    paths:
-      - '.github/workflows/**'
-      - '.github/actions/**'
   push:
     branches:
       - main
@@ -12,8 +10,7 @@ on:
       - '.github/workflows/**'
       - '.github/actions/**'
 
-permissions:
-  contents: read
+permissions: {}
 
 jobs:
   zizmor:
@@ -23,13 +20,13 @@ jobs:
       contents: read
       security-events: write  # for uploading SARIF results
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
 
       - name: "Run zizmor"
-        uses: zizmorcore/zizmor-action@5ca5fc7a4779c5263a3ffa0e1f693009994446d1 # v0.1.2
+        uses: zizmorcore/zizmor-action@cc914d7f3750a2d13d75c7f184a1060aa0e9d482 # v0.6.4
         with:
-          config-file: .github/zizmor.yml
-          sarif-upload: true
+          # there is a pass/fail gate as a repo ruleset (if there is no ruleset configured then the action will pass by default)
+          advanced-security: true
           inputs: .github

.github/workflows/validations.yaml

@@ -1,5 +1,11 @@
 name: "Validations"
 
+# we should cancel any in-progress runs for the same workflow + PR/ref
+# so that we can avoid redundant work / save on CI minutes
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
 on:
   workflow_dispatch:
   pull_request:
@@ -7,34 +13,54 @@ on:
     branches:
       - main
 
-permissions:
-    contents: read
+permissions: {}
 
 jobs:
-
   Static-Analysis:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Static analysis"
-    runs-on: ubuntu-24.04
+    # runs-on.com: memory & general purpose instances for testing
+    #   spot enabled: ok to interrupt non-production workloads
+    #   tmpfs intentionally omitted -- it RAM-backs /home/runner, /tmp and /var/lib/docker at
+    #   100% of instance memory, starving `make unit` of headroom to link with -race.
+    #   volume: the caches and docker images tmpfs used to hold. gp3 baseline throughput is
+    #   enough; a 4 vCPU instance can't pull much more than that anyway.
+    #   note: s3-cache intentionally omitted -- PR runs are untrusted and must not write to the
+    #   shared cache backend that the trusted release workflow reads from (cache poisoning).
+    runs-on: &test-runner "runs-on=${{ github.run_id }}/cpu=4+8/ram=16+32/family=m6+m7+m8+c6+c7+c8/spot=price-capacity-optimized/volume=100gb"
+    permissions:
+      contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        with:
+          # the self-consistency tests for the output of the capabilities code generation depends on unit test
+          # output from  ./syft/pkg/... packages. Therefore we need to download the test fixture cache here
+          # so that running the few unit tests as part of static analysis works correctly.
+          download-test-fixture-cache: true
 
       - name: Run static analysis
         run: make static-analysis
 
-
   Unit-Test:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Unit tests"
-    # we need more storage than what's on the default runner
-    runs-on: ubuntu-22.04-4core-16gb
+    runs-on: ubuntu-latest
+    needs: [Unit-Test-Linux, Unit-Test-Windows]
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - run: echo All unit tests passed!
+
+  Unit-Test-Linux:
+    name: "Unit tests (Linux)"
+    runs-on: *test-runner
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -46,13 +72,38 @@ jobs:
       - name: Run unit tests
         run: make unit
 
+      - name: Check for capability drift
+        run: make check-capability-drift
+
+  Unit-Test-Windows:
+    name: "Unit tests (Windows)"
+    runs-on: windows-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
+        with:
+          persist-credentials: false
+
+      # go-make's setup only (not ./.github/actions/bootstrap): no apt, binny tools, or fixture cache are needed
+      - name: Setup go + go-make tooling
+        uses: anchore/go-make/.github/actions/setup@fa5421b3bf24c9d18f11a736c5eb4172f2b7d683 # v0.8.1
+        with:
+          # keep in sync with the go-version default in ./.github/actions/bootstrap
+          go-version: "1.26.2"
+
+      # the full unit suite leans on linux docker fixtures, so this runs the windows-relevant subset
+      - name: Run unit tests
+        run: make unit:windows
 
   Integration-Test:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Integration tests"
-    runs-on: ubuntu-24.04
+    runs-on: *test-runner
+    permissions:
+      contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -67,12 +118,25 @@ jobs:
       - name: Run integration tests
         run: make integration
 
-
   Build-Snapshot-Artifacts:
     name: "Build snapshot artifacts"
-    runs-on: ubuntu-24.04
+    # runs-on.com: compute instances for parallel builds
+    #   spot disabled: reliability for build workflows (used for releases too)
+    #   goreleaser uses parallelism of 12, so we need more CPUs
+    #   tmpfs intentionally omitted -- a RAM-backed dist/ competes with the goreleaser
+    #   build's memory peak (parallel binaries + multi-arch image assembly) and OOMs the
+    #   instance; keep dist/ on disk.
+    #   note: s3-cache intentionally omitted -- PR runs are untrusted and must not write to the
+    #   shared cache backend that the trusted release workflow reads from (cache poisoning).
+    #   volume: enlarge dist/ disk -- the default 40GB EBS root fills up during the multi-arch
+    #   image + binary build and OOMs (runs out of disk); size it well above peak usage.
+    #   provisioned throughput/iops above the gp3 free baseline (125mbs/3000iops) approximate
+    #   the tmpfs IO speed on disk, for ~1c/run.
+    runs-on: "runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/volume=120gb:gp3:500mbs:4000iops"
+    permissions:
+      contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -87,84 +151,22 @@ jobs:
       - name: Smoke test snapshot build
         run: make snapshot-smoke-test
 
-      # why not use actions/upload-artifact? It is very slow (3 minutes to upload ~600MB of data, vs 10 seconds with this approach).
-      # see https://github.com/actions/upload-artifact/issues/199 for more info
       - name: Upload snapshot artifacts
-        uses: actions/cache/save@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
-          # we need to preserve the snapshot data itself as well as the task data that confirms if the
-          # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
-          # even though it already exists.
-          path: |
-            snapshot
-            .task
-          key: snapshot-build-${{ github.run_id }}
-
-
-  Upload-Snapshot-Artifacts:
-    # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
-    name: "Upload snapshot artifacts"
-    needs: [Build-Snapshot-Artifacts]
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
-        with:
-          download-test-fixture-cache: true
-
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
-        with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
-
-      # workaround for https://github.com/actions/cache/issues/1265
-      - name: (cache-miss) Snapshot build missing
-        if: steps.snapshot-cache.outputs.cache-hit != 'true'
-        run: echo "unable to download snapshots from previous job" && false
-
-      - run: npm install @actions/artifact@2.2.2
-
-      - uses: actions/github-script@v7
-        with:
-          script: |
-            const { readdirSync } = require('fs')
-            const { DefaultArtifactClient } = require('@actions/artifact')
-            const artifact = new DefaultArtifactClient()
-            const ls = d => readdirSync(d, { withFileTypes: true })
-            const baseDir = "./snapshot"
-            const dirs = ls(baseDir).filter(f => f.isDirectory()).map(f => f.name)
-            const uploads = []
-            for (const dir of dirs) {
-              // uploadArtifact returns Promise<{id, size}>
-              uploads.push(artifact.uploadArtifact(
-                // name of the archive:
-                `${dir}`,
-                // array of all files to include:
-                ls(`${baseDir}/${dir}`).map(f => `${baseDir}/${dir}/${f.name}`),
-                // base directory to trim from entries:
-                `${baseDir}/${dir}`,
-                { retentionDays: 30 }
-              ))
-            }
-            // wait for all uploads to finish
-            Promise.all(uploads)
+          name: snapshot
+          path: snapshot/
+          retention-days: 30
 
   Acceptance-Linux:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Acceptance tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
-    runs-on: ubuntu-24.04
+    runs-on: *test-runner
+    permissions:
+      contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -173,20 +175,14 @@ jobs:
         with:
           download-test-fixture-cache: true
 
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c #v8.0.1
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          name: snapshot
+          path: snapshot
 
-      # workaround for https://github.com/actions/cache/issues/1265
-      - name: (cache-miss) Snapshot build missing
-        if: steps.snapshot-cache.outputs.cache-hit != 'true'
-        run: echo "unable to download snapshots from previous job" && false
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft snapshot/*/*.exe 2>/dev/null || true
 
       - name: Run comparison tests (Linux)
         run: make compare-linux
@@ -202,17 +198,19 @@ jobs:
         if: steps.install-test-image-cache.outputs.cache-hit != 'true'
         run: make install-test-cache-save
 
-
   Acceptance-Mac:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Acceptance tests (Mac)"
     needs: [Build-Snapshot-Artifacts]
+    # note: macos runners aren't supported yet for runs-on managed runners.
     runs-on: macos-latest
+    permissions:
+      contents: read
     steps:
       - name: Install Cosign
-        uses: sigstore/cosign-installer@d58896d6a1865668819e1d91763c7751a165e159 # v3.9.2
+        uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2
 
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -223,20 +221,14 @@ jobs:
           go-dependencies: false
           download-test-fixture-cache: true
 
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c #v8.0.1
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          name: snapshot
+          path: snapshot
 
-      # workaround for https://github.com/actions/cache/issues/1265
-      - name: (cache-miss) Snapshot build missing
-        if: steps.snapshot-cache.outputs.cache-hit != 'true'
-        run: echo "unable to download snapshots from previous job" && false
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft 2>/dev/null || true
 
       - name: Run comparison tests (Mac)
         run: make compare-mac
@@ -244,14 +236,15 @@ jobs:
       - name: Run install.sh tests (Mac)
         run: make install-test-ci-mac
 
-
   Cli-Linux:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "CLI tests (Linux)"
     needs: [Build-Snapshot-Artifacts]
-    runs-on: ubuntu-24.04
+    runs-on: *test-runner
+    permissions:
+      contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -260,42 +253,14 @@ jobs:
         with:
           download-test-fixture-cache: true
 
-      - name: Download snapshot build
-        id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+      - name: Download snapshot artifacts
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c #v8.0.1
         with:
-          path: |
-            snapshot
-            .task
-          fail-on-cache-miss: true
-          key: snapshot-build-${{ github.run_id }}
+          name: snapshot
+          path: snapshot
 
-      # workaround for https://github.com/actions/cache/issues/1265
-      - name: (cache-miss) Snapshot build missing
-        if: steps.snapshot-cache.outputs.cache-hit != 'true'
-        run: echo "unable to download snapshots from previous job" && false
+      - name: Restore binary permissions
+        run: chmod +x snapshot/*/syft snapshot/*/*.exe 2>/dev/null || true
 
       - name: Run CLI Tests (Linux)
         run: make cli
-
-
-  Cleanup-Cache:
-    name: "Cleanup snapshot cache"
-    if: github.event.pull_request.head.repo.full_name == github.repository
-    runs-on: ubuntu-24.04
-    permissions:
-      actions: write
-    needs:
-      - Acceptance-Linux
-      - Acceptance-Mac
-      - Cli-Linux
-      - Upload-Snapshot-Artifacts
-    steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
-        with:
-          persist-credentials: false
-
-      - name: Delete snapshot cache
-        run: gh cache delete "snapshot-build-${{ github.run_id }}"
-        env:
-          GH_TOKEN: ${{ github.token }}

.github/zizmor.yml

@@ -1,9 +1,4 @@
 rules:
-  unpinned-uses:
-    ignore:
-      # Allow unpinned uses of trusted internal anchore/workflows actions
-      - update-anchore-dependencies.yml
-
   dangerous-triggers:
     ignore:
       # Safe use of pull_request_target - only runs trusted scripts from base repo,

.gitignore

@@ -2,6 +2,9 @@
 go.work
 go.work.sum
 .tool-versions
+.python-version
+.mise.toml
+.env
 
 # app configuration
 /.syft.yaml
@@ -16,6 +19,12 @@ bin/
 /snapshot
 /.tool
 /.task
+/generate
+/spec
+/specs
+mise.toml
+.make/.make
+.conductor
 
 # changelog generation
 CHANGELOG.md
@@ -32,6 +41,8 @@ VERSION
 /test/results
 coverage.txt
 *.log
+**/test-fixtures/test-observations.json
+**/testdata/test-observations.json
 
 # probable archives
 .images

.golangci.yaml

@@ -7,6 +7,7 @@ linters:
     - asciicheck
     - bodyclose
     - copyloopvar
+    - depguard
     - dogsled
     - dupl
     - errcheck
@@ -29,9 +30,20 @@ linters:
     - unused
     - whitespace
   settings:
+    depguard:
+      rules:
+        yaml:
+          deny:
+            # gopkg.in/yaml.v3 is unmaintained and panics on some malformed input (see #5327)
+            - pkg: gopkg.in/yaml.v3
+              desc: use go.yaml.in/yaml/v3 instead
     funlen:
       lines: 70
       statements: 50
+    goconst:
+      # the default of 3 turns every repeated literal in a lookup table or a test fixture into a finding.
+      # 5 keeps the ones worth hoisting without flagging data that reads better written out.
+      min-occurrences: 5
     gocritic:
       enabled-checks:
         - deferInLoop
@@ -49,6 +61,17 @@ linters:
       - common-false-positives
       - legacy
       - std-error-handling
+    rules:
+      # we have multiple packages in syft that might overlap with the stblib; their names reflect their purpose
+      - linters:
+          - revive
+        text: "var-naming: avoid package names that conflict"
+      # cpegenerate is almost entirely lookup tables mapping artifact names to vendors, products, and
+      # maven group ids. The repeated strings are the data itself, so hoisting them to constants would
+      # replace a readable table with indirection for no gain.
+      - linters:
+          - goconst
+        path: syft/pkg/cataloger/internal/cpegenerate/
     paths:
       - third_party$
       - builtin$
@@ -56,7 +79,6 @@ linters:
 
 # do not enable...
 #    - deadcode          # The owner seems to have abandoned the linter. Replaced by "unused".
-#    - depguard          # We don't have a configuration for this yet
 #    - goprintffuncname  # does not catch all cases and there are exceptions
 #    - nakedret          # does not catch all cases and should not fail a build
 #    - gochecknoglobals
@@ -65,7 +87,6 @@ linters:
 #    - godot
 #    - godox
 #    - goerr113
-#    - goimports   # we're using gosimports now instead to account for extra whitespaces (see https://github.com/golang/go/issues/20818)
 #    - golint      # deprecated
 #    - gomnd       # this is too aggressive
 #    - interfacer  # this is a good idea, but is no longer supported and is prone to false positives
@@ -91,11 +112,18 @@ issues:
 
 formatters:
   enable:
+    - gci
     - gofmt
-    - goimports
   exclusions:
     generated: lax
     paths:
       - third_party$
       - builtin$
       - examples$
+  settings:
+    gci:
+      # See https://golangci-lint.run/docs/formatters/configuration/#gci
+      sections:
+        - standard # Standard section: captures all standard packages.
+        - default  # Default section: contains all imports that could not be matched to another section type.
+        - prefix(github.com/anchore)

.goreleaser.yaml

@@ -14,7 +14,7 @@ builds:
     dir: ./cmd/syft
     binary: syft
     goos: [linux]
-    goarch: [amd64, arm64, ppc64le, s390x]
+    goarch: [amd64, arm64, ppc64le, riscv64, s390x]
     mod_timestamp: &build-timestamp '{{ .CommitTimestamp }}'
     ldflags: &build-ldflags |
       -w
@@ -42,7 +42,7 @@ builds:
     dir: ./cmd/syft
     binary: syft
     goos: [windows]
-    goarch: [amd64]
+    goarch: [amd64, arm64]
     mod_timestamp: *build-timestamp
     ldflags: *build-ldflags
 
@@ -73,252 +73,88 @@ brews:
     description: *description
     license: "Apache License 2.0"
 
-dockers:
-  # production images...
-  - image_templates:
-      - anchore/syft:{{.Tag}}-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-amd64
-    goarch: amd64
+dockers_v2:
+  # production images (scratch base, root)
+  - id: production
     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}}"
+    ids: &docker-ids
+      - linux-build
+    images: &docker-images
+      - anchore/syft
+      - ghcr.io/anchore/syft
+    platforms: &docker-platforms
+      - linux/amd64
+      - linux/arm64
+      - linux/ppc64le
+      - linux/riscv64
+      - linux/s390x
+    labels: &docker-labels
+      "org.opencontainers.image.created": "{{.Date}}"
+      "org.opencontainers.image.title": "syft"
+      "org.opencontainers.image.description": "CLI tool and library for generating a Software Bill of Materials from container images and filesystems"
+      "org.opencontainers.image.source": "{{.GitURL}}"
+      "org.opencontainers.image.revision": "{{.FullCommit}}"
+      "org.opencontainers.image.vendor": "Anchore, Inc."
+      "org.opencontainers.image.version": "{{.Version}}"
+      "org.opencontainers.image.licenses": "Apache-2.0"
+      "io.artifacthub.package.readme-url": "https://raw.githubusercontent.com/anchore/syft/main/README.md"
+      "io.artifacthub.package.logo-url": "https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png"
+      "io.artifacthub.package.license": "Apache-2.0"
+    tags:
+      - latest
+      - "{{.Tag}}"
+    # DEBIAN_VERSION 13 (trixie) is the first distroless release with a riscv64 base image
+    # and is a superset of debian 12 for the other targeted arches; docker_v2 builds all
+    # platforms in a single buildx invocation, so build_args cannot vary per platform.
+    build_args: &docker-build-args
+      DEBIAN_VERSION: "13"
+    # disable provenance attestations to keep the manifest free of unknown/unknown entries
+    flags: &docker-flags
+      - "--provenance=false"
+    # SBOMs are produced separately for the archives (see the sboms section)
+    sbom: &docker-sbom "false"
 
-  - image_templates:
-      - anchore/syft:{{.Tag}}-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-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}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
-    goarch: ppc64le
-    dockerfile: Dockerfile
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/ppc64le"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-s390x
-      - ghcr.io/anchore/syft:{{.Tag}}-s390x
-    goarch: s390x
-    dockerfile: Dockerfile
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/s390x"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  # nonroot images...
-  - image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
-    goarch: amd64
+  # nonroot images
+  - id: nonroot
     dockerfile: Dockerfile.nonroot
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/amd64"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
+    ids: *docker-ids
+    images: *docker-images
+    platforms: *docker-platforms
+    labels: *docker-labels
+    tags:
+      - nonroot
+      - "{{.Tag}}-nonroot"
+    build_args: *docker-build-args
+    flags: *docker-flags
+    sbom: *docker-sbom
 
-  - image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
-    goarch: arm64
-    dockerfile: Dockerfile.nonroot
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/arm64/v8"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
-    goarch: ppc64le
-    dockerfile: Dockerfile.nonroot
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/ppc64le"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-s390x
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
-    goarch: s390x
-    dockerfile: Dockerfile.nonroot
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/s390x"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  # debug images...
-  - image_templates:
-      - anchore/syft:{{.Tag}}-debug-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
-    goarch: amd64
+  # debug images (root)
+  - id: debug
     dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/amd64"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
+    ids: *docker-ids
+    images: *docker-images
+    platforms: *docker-platforms
+    labels: *docker-labels
+    tags:
+      - debug
+      - "{{.Tag}}-debug"
+    build_args: *docker-build-args
+    flags: *docker-flags
+    sbom: *docker-sbom
 
-  - image_templates:
-      - anchore/syft:{{.Tag}}-debug-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
-    goarch: arm64
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/arm64/v8"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-debug-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
-    goarch: ppc64le
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/ppc64le"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-  - image_templates:
-      - anchore/syft:{{.Tag}}-debug-s390x
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
-    goarch: s390x
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/s390x"
-      - "--build-arg=BUILD_DATE={{.Date}}"
-      - "--build-arg=BUILD_VERSION={{.Version}}"
-      - "--build-arg=VCS_REF={{.FullCommit}}"
-      - "--build-arg=VCS_URL={{.GitURL}}"
-
-docker_manifests:
-  - name_template: anchore/syft:latest
-    image_templates:
-      - anchore/syft:{{.Tag}}-amd64
-      - anchore/syft:{{.Tag}}-arm64v8
-      - anchore/syft:{{.Tag}}-ppc64le
-      - anchore/syft:{{.Tag}}-s390x
-
-  - name_template: ghcr.io/anchore/syft:latest
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-s390x
-
-  - name_template: anchore/syft:{{.Tag}}
-    image_templates:
-      - anchore/syft:{{.Tag}}-amd64
-      - anchore/syft:{{.Tag}}-arm64v8
-      - anchore/syft:{{.Tag}}-ppc64le
-      - anchore/syft:{{.Tag}}-s390x
-
-  - name_template: ghcr.io/anchore/syft:{{.Tag}}
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-s390x
-
-  # nonroot images...
-  - name_template: anchore/syft:nonroot
-    image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-amd64
-      - anchore/syft:{{.Tag}}-nonroot-arm64v8
-      - anchore/syft:{{.Tag}}-nonroot-ppc64le
-      - anchore/syft:{{.Tag}}-nonroot-s390x
-
-  - name_template: ghcr.io/anchore/syft:nonroot
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
-
-  - name_template: anchore/syft:{{.Tag}}-nonroot
-    image_templates:
-      - anchore/syft:{{.Tag}}-nonroot-amd64
-      - anchore/syft:{{.Tag}}-nonroot-arm64v8
-      - anchore/syft:{{.Tag}}-nonroot-ppc64le
-      - anchore/syft:{{.Tag}}-nonroot-s390x
-
-  - name_template: ghcr.io/anchore/syft:{{.Tag}}-nonroot
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-s390x
-
-  # debug images...
-  - name_template: anchore/syft:debug
-    image_templates:
-      - anchore/syft:{{.Tag}}-debug-amd64
-      - anchore/syft:{{.Tag}}-debug-arm64v8
-      - anchore/syft:{{.Tag}}-debug-ppc64le
-      - anchore/syft:{{.Tag}}-debug-s390x
-
-  - name_template: ghcr.io/anchore/syft:debug
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
-
-  - name_template: anchore/syft:{{.Tag}}-debug
-    image_templates:
-      - anchore/syft:{{.Tag}}-debug-amd64
-      - anchore/syft:{{.Tag}}-debug-arm64v8
-      - anchore/syft:{{.Tag}}-debug-ppc64le
-      - anchore/syft:{{.Tag}}-debug-s390x
-
-  - name_template: ghcr.io/anchore/syft:{{.Tag}}-debug
-    image_templates:
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-amd64
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-arm64v8
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-ppc64le
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-s390x
+  # debug-nonroot images
+  - id: debug-nonroot
+    dockerfile: Dockerfile.debug-nonroot
+    ids: *docker-ids
+    images: *docker-images
+    platforms: *docker-platforms
+    labels: *docker-labels
+    tags:
+      - debug-nonroot
+      - "{{.Tag}}-debug-nonroot"
+    build_args: *docker-build-args
+    flags: *docker-flags
+    sbom: *docker-sbom
 
 sboms:
   - artifacts: archive
@@ -337,6 +173,7 @@ signs:
     certificate: "${artifact}.pem"
     args:
       - "sign-blob"
+      - "--use-signing-config=false"
       - "--oidc-issuer=https://token.actions.githubusercontent.com"
       - "--output-certificate=${certificate}"
       - "--output-signature=${signature}"

.make/go.mod

@@ -0,0 +1,12 @@
+module github.com/anchore/syft/.make
+
+go 1.25.8
+
+require github.com/anchore/go-make v0.8.1
+
+require (
+	github.com/bmatcuk/doublestar/v4 v4.10.0 // indirect
+	github.com/goccy/go-yaml v1.19.2 // indirect
+	golang.org/x/mod v0.40.0 // indirect
+	golang.org/x/sys v0.47.0 // indirect
+)

.make/go.sum

@@ -0,0 +1,10 @@
+github.com/anchore/go-make v0.8.1 h1:GAhPXR+9qVQhFB1pfVlHFOzxAt3dTDTUIA7Tp7nx9tg=
+github.com/anchore/go-make v0.8.1/go.mod h1:xALbVsPsDoJnJxdkjPlxOLZV7GbAdT5Pv3gd0kP1Lz0=
+github.com/bmatcuk/doublestar/v4 v4.10.0 h1:zU9WiOla1YA122oLM6i4EXvGW62DvKZVxIe6TYWexEs=
+github.com/bmatcuk/doublestar/v4 v4.10.0/go.mod h1:xBQ8jztBU6kakFMg+8WGxn0c6z1fTSPVIjEY1Wr7jzc=
+github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM=
+github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
+golang.org/x/mod v0.40.0 h1:hUv+3cXcdRHz08UmSiOob7sadHig73uo5bkXxQ/tvUs=
+golang.org/x/mod v0.40.0/go.mod h1:0/weTWkPWGBikyTWAX3dkjVztMmBA5hM0DH6BElSupE=
+golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
+golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=

.make/main.go

@@ -0,0 +1,213 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"runtime"
+	"strconv"
+
+	. "github.com/anchore/go-make"
+	"github.com/anchore/go-make/config"
+	"github.com/anchore/go-make/file"
+	"github.com/anchore/go-make/lang"
+	"github.com/anchore/go-make/run"
+	"github.com/anchore/go-make/tasks/golint"
+	"github.com/anchore/go-make/tasks/goreleaser"
+	"github.com/anchore/go-make/tasks/gotask"
+	"github.com/anchore/go-make/tasks/gotest"
+)
+
+func main() {
+	Makefile(
+		// shared anchore tasks
+		golint.Tasks(),
+		goreleaser.Tasks(),
+
+		// unit tests: exclude packages under any test/ directory (matches the syft
+		// Taskfile's prior `grep -v` against test paths). Coverage threshold of 62%
+		// preserves the prior coverage gate that used to live in scripts/coverage.py.
+		gotest.Tasks(
+			gotest.Name("unit"),
+			gotest.ExcludeGlob("**/test/**"),
+			gotest.CoverageThreshold(62),
+			race(),
+		),
+
+		// integration tests: run `go test` directly instead of via gotest.Tasks(), which
+		// has no way to set a timeout. The suite is a single package of ~36 sequential
+		// tests over 18 docker fixture images, so with a cold fixture cache (every image
+		// built + saved inline, under -race) it runs well past `go test`'s default 10m
+		// timeout -- which is exactly the case when regenerating the fixture cache from
+		// scratch. -count=1 keeps the go test cache from short-circuiting a run whose
+		// side effect (the built fixtures) is the thing we're after.
+		//
+		// The race-detector smoke against a real image stays bundled here (RunsOn
+		// integration) so `make integration` behaves like the Taskfile version did.
+		Task{
+			Name:        "integration",
+			Description: "run integration tests",
+			RunsOn:      lang.List("test"),
+			Run: func() {
+				raceFlag := ""
+				if raceEnabled() {
+					raceFlag = " -race"
+				}
+				Run(
+					"go test -count=1 -timeout=30m"+raceFlag+" ./cmd/syft/internal/test/integration/...",
+					run.Env("GODEBUG", "dontfreezetheworld=1"),
+				)
+			},
+		},
+		Task{
+			Name:        "integration:race-smoke",
+			Description: "exercise the CLI with the race detector",
+			RunsOn:      lang.List("integration"),
+			Run: func() {
+				if !raceEnabled() {
+					Log("race detector disabled (RACE=false); skipping race smoke")
+					return
+				}
+				Run("go run -race cmd/syft/main.go anchore/test_images:grype-quality-dotnet-69f15d2")
+			},
+		},
+
+		// cli tests: native go-make Task. Runs SYFT_BINARY_LOCATION at an *absolute*
+		// path to the snapshot binary. Builds the snapshot only when the binary is
+		// missing rather than depending on the snapshot task unconditionally: in
+		// validations.yaml CI we download a pre-built snapshot artifact, so the binary
+		// already exists and rebuilding would both burn ~10m and clobber it. When
+		// `make test` runs cold (e.g. the release pipeline) or locally with no
+		// snapshot, we build a single-target snapshot (current OS/arch only) since
+		// that's all the CLI tests need.
+		Task{
+			Name:        "cli",
+			Description: "Run CLI tests",
+			RunsOn:      lang.List("test"),
+			Run: func() {
+				bin := snapshotBinPath()
+				if !file.Exists(bin) {
+					Log("snapshot binary not found at %s; building single-target snapshot", bin)
+					Run("make snapshot:single-target")
+				}
+				Log("testing binary: %s", bin)
+				Run(
+					"go test -count=1 -timeout=15m -v ./test/cli",
+					run.Env("SYFT_BINARY_LOCATION", bin),
+				)
+			},
+		},
+
+		// windows unit tests: deliberately not hooked into "test" (no RunsOn). The full unit suite leans on
+		// linux docker fixture images and posix-only assumptions, so this covers the packages that own
+		// host path handling (where windows bugs live) and skips the tests that need docker image fixtures.
+		// ponytail: curated package list, widen it as more of the suite is made windows-safe.
+		Task{
+			Name:        "unit:windows",
+			Description: "run the windows-relevant subset of unit tests",
+			Run: func() {
+				Run("go test -count=1"+
+					` -skip "Image|Squash|AllLayers|MixFileTypes|GivenCoordinates"`+
+					" ./syft/internal/windows/... ./syft/internal/fileresolver/... ./syft/source/directorysource/... ./syft/source/filesource/..."+
+					" ./syft/file ./syft/file/cataloger/filedigest/... ./syft/file/cataloger/filecontent/...",
+					run.Stdout(os.Stderr),
+				)
+			},
+		},
+
+		// default validation pipeline (replaces Taskfile `default`/`pr-validations`/`validations`).
+		Task{
+			Name:         "default",
+			Description:  "Run all validation tasks",
+			Dependencies: Deps("static-analysis", "test", "install-test"),
+		},
+
+		// --- everything else is implemented in Taskfile.yaml. gotask.Tasks()
+		// discovers every (non-internal) Taskfile task — including the namespaced
+		// `generate:cpe-index:*` tasks from the included task.d file — and surfaces
+		// them as first-class go-make tasks (with their canonical names and `desc:`)
+		// that forward to `task <name>`. Descriptions live in Taskfile.yaml as the
+		// single source of truth; no per-task wrapping needed here.
+		gotask.Tasks(),
+
+		// gotask.Tasks() discovers canonical task names only, not Taskfile aliases,
+		// so re-expose `refresh-fixtures`'s `fixtures` alias for manual use.
+		Task{
+			Name:         "fixtures",
+			Description:  "Clear and fetch all test fixture cache (alias of refresh-fixtures)",
+			Dependencies: Deps("refresh-fixtures"),
+		},
+
+		// gotask.Tasks() can't attach RunsOn labels, so wire the syft-specific
+		// Taskfile tasks into go-make's native phases here. These thin hooks have
+		// no body and no description (hidden from `make help`); they only pull the
+		// discovered tasks in when the labeled phase runs.
+		Task{
+			Name:         "static-analysis:syft",
+			RunsOn:       lang.List("static-analysis"),
+			Dependencies: Deps("check-json-schema-drift", "check-binary-fixture-size"),
+		},
+		Task{
+			Name:         "test:syft",
+			RunsOn:       lang.List("test"),
+			Dependencies: Deps("validate-cyclonedx-schema", "test-utils", "check-docker-cache"),
+		},
+		// refresh-fixtures hooks into "unit" so `make unit` triggers the stale-cache
+		// detection + download just like `task unit` did on main (its
+		// `deps: [tmpdir, fixtures]` is what kept the fixture cache fresh).
+		Task{
+			Name:         "unit:syft",
+			RunsOn:       lang.List("unit"),
+			Dependencies: Deps("refresh-fixtures"),
+		},
+		Task{
+			Name:   "clean:syft",
+			RunsOn: lang.List("clean"),
+			Dependencies: Deps(
+				"clean-snapshot",
+				"clean-docker-cache",
+				"clean-oras-cache",
+				"clean-cache",
+				"clean-test-observations",
+			),
+		},
+	)
+}
+
+// raceEnabled is the single switch for the race detector across every test suite.
+// Unset it and we keep go-make's behavior (on in CI, off locally and on windows);
+// set RACE=false to turn it off everywhere -- worth doing when rebuilding the test
+// fixture cache from scratch, where every suite is dominated by building docker
+// fixtures and the race detector only adds wall clock. RACE=true forces it on.
+func raceEnabled() bool {
+	if enabled, err := strconv.ParseBool(config.Env("RACE", "")); err == nil {
+		return enabled
+	}
+	return config.CI && !config.Windows
+}
+
+// race applies raceEnabled() to a gotest suite. gotest exposes no functional option
+// for the race detector, but gotest.Config.Race is exported.
+func race() gotest.Option {
+	return func(c *gotest.Config) {
+		c.Race = raceEnabled()
+	}
+}
+
+// snapshotBinPath replicates the SNAPSHOT_BIN computation from the prior Taskfile:
+// <repoRoot>/snapshot/<os>-build_<os>_<arch>/syft, where arch maps amd64->amd64_v1
+// and arm64->arm64_v8.0 to match goreleaser's per-target output directory naming.
+// Returns an absolute path: the cli tests' getSyftBinaryLocation contract requires
+// SYFT_BINARY_LOCATION to be absolute because subtests run with cmd.Dir = t.TempDir().
+func snapshotBinPath() string {
+	osName := runtime.GOOS
+	var arch string
+	switch runtime.GOARCH {
+	case "amd64":
+		arch = "amd64_v1"
+	case "arm64":
+		arch = "arm64_v8.0"
+	default:
+		arch = runtime.GOARCH
+	}
+	return filepath.Join(RootDir(), "snapshot", osName+"-build_"+osName+"_"+arch, "syft")
+}

.make/main_test.go

@@ -0,0 +1,49 @@
+package main
+
+import (
+	"os"
+	"testing"
+
+	"github.com/anchore/go-make/config"
+	"github.com/anchore/go-make/tasks/gotest"
+)
+
+func TestRaceEnabled(t *testing.T) {
+	tests := []struct {
+		name string
+		env  string // "" means RACE is unset
+		ci   bool
+		want bool
+	}{
+		{name: "default in CI", ci: true, want: true},
+		{name: "default locally", ci: false, want: false},
+		{name: "explicitly off in CI", env: "false", ci: true, want: false},
+		{name: "explicitly on locally", env: "true", ci: false, want: true},
+		{name: "unparseable falls back to default", env: "yes-please", ci: true, want: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// always go through t.Setenv (it registers the restore) so an ambient
+			// RACE from the caller's environment can't leak into the unset cases
+			t.Setenv("RACE", tt.env)
+			if tt.env == "" {
+				os.Unsetenv("RACE")
+			}
+			orig := config.CI
+			config.CI = tt.ci
+			t.Cleanup(func() { config.CI = orig })
+
+			if got := raceEnabled(); got != tt.want {
+				t.Errorf("raceEnabled() = %v, want %v", got, tt.want)
+			}
+
+			// the gotest suites get the same answer through the functional option
+			var cfg gotest.Config
+			race()(&cfg)
+			if cfg.Race != tt.want {
+				t.Errorf("race() set Race = %v, want %v", cfg.Race, tt.want)
+			}
+		})
+	}
+}

CODE_OF_CONDUCT.md

@@ -1,128 +1,5 @@
-# Contributor Covenant Code of Conduct
+# Code of Conduct
 
-## Our Pledge
+All contributors for any Anchore project must follow the [Contributor Covenant Code of Conduct](https://oss.anchore.com/docs/contributing/code-of-conduct/).
 
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the
-  overall community
-
-Examples of unacceptable behavior include:
-
-* The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email
-  address, without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-[opensource@anchore.com](mailto:opensource@anchore.com).
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior,  harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
-
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.
+**TLDR:** Be kind, be respectful, and assume good intentions. We're all here to build great software together.

CONTRIBUTING.md

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

DEVELOPING.md

@@ -1,392 +0,0 @@
-# Developing
-
-## Getting started
-
-In order to test and develop in this repo you will need the following dependencies installed:
-- Golang
-- docker
-- make
-- Python (>= 3.9)
-
-### Docker settings for getting started
-Make sure you've updated your docker settings so the default docker socket path is available.
-
-Go to:
-
-docker -> settings -> advanced
-
-Make sure:
-
-```
-Allow the default Docker socket to be used
-```
-
-is checked.
-
-Also double check that the docker context being used is the default context. If it is not, run:
-
-`docker context use default`
-
-After cloning the following step can help you get setup:
-1. run `make bootstrap` to download go mod dependencies, create the `/.tmp` dir, and download helper utilities.
-2. run `make` to view the selection of developer commands in the Makefile
-3. run `make build` to build the release snapshot binaries and packages
-4. for an even quicker start you can run `go run cmd/syft/main.go` to print the syft help.
-	- this command `go run cmd/syft/main.go alpine:latest` will compile and run syft against `alpine:latest`
-5. view the README or syft help output for more output options
-
-The main make tasks for common static analysis and testing are `lint`, `format`, `lint-fix`, `unit`, `integration`, and `cli`.
-
-See `make help` for all the current make tasks.
-
-### Internal Artifactory Settings
-
-**Not always applicable**
-
-Some companies have Artifactory setup internally as a solution for sourcing secure dependencies.
-If you're seeing an issue where the unit tests won't run because of the below error then this section might be relevant for your use case.
-
-```
-[ERROR] [ERROR] Some problems were encountered while processing the POMs
-```
-
-If you're dealing with an issue where the unit tests will not pull/build certain java fixtures check some of these settings:
-
-- a `settings.xml` file should be available to help you communicate with your internal artifactory deployment
-- this can be moved to `syft/pkg/cataloger/java/test-fixtures/java-builds/example-jenkins-plugin/` to help build the unit test-fixtures
-- you'll also want to modify the `build-example-jenkins-plugin.sh` to use `settings.xml`
-
-For more information on this setup and troubleshooting see [issue 1895](https://github.com/anchore/syft/issues/1895#issuecomment-1610085319)
-
-
-## Architecture
-
-At a high level, this is the package structure of syft:
-```
-./cmd/syft/
-│   ├── cli/
-│   │   ├── cli.go          // where all commands are wired up
-│   │   ├── commands/       // all command implementations
-│   │   ├── options/        // all command flags and configuration options
-│   │   └── ui/             // all handlers for events that are shown on the UI
-│   └── main.go             // entrypoint for the application
-└── syft/                   // the "core" syft library
-    ├── format/             // contains code to encode or decode to and from SBOM formats
-    ├── pkg/                // contains code to catalog packages from a source
-    ├── sbom/               // contains the definition of an SBOM
-    └── source/             // contains code to create a source object for some input type (e.g. container image, directory, etc)
-```
-
-Syft's core library is implemented in the `syft` package and subpackages, where the major packages are:
-
-- the `syft/source` package produces a `source.Source` object that can be used to catalog a directory, container, and other source types.
-- the `syft` package contains a single function that can take a `source.Source` object and catalog it, producing an `sbom.SBOM` object
-- the `syft/format` package contains the ability to encode and decode SBOMs to and from different SBOM formats (such as SPDX and CycloneDX)
-
-The `cmd` package at the highest level execution flow wires up [`spf13/cobra`](https://github.com/spf13/cobra) commands for execution in the main application:
-```mermaid
-sequenceDiagram
-    participant main as cmd/syft/main
-    participant cli as cli.New()
-    participant root as root.Execute()
-    participant cmd as <command>.Execute()
-
-    main->>+cli: 
-
-    Note right of cli: wire ALL CLI commands
-    Note right of cli: add flags for ALL commands
-
-    cli-->>-main:  root command 
-
-    main->>+root: 
-    root->>+cmd: 
-    cmd-->>-root: (error)  
-
-    root-->>-main: (error) 
-
-    Note right of cmd: Execute SINGLE command from USER
-```
-
-The `packages` command uses the core library to generate an SBOM for the given user input:
-```mermaid
-sequenceDiagram
-    participant source as source.New(ubuntu:latest)
-    participant sbom as sbom.SBOM
-    participant catalog as syft.CatalogPackages(src)
-    participant encoder as syft.Encode(sbom, format)
-
-    Note right of source: use "ubuntu:latest" as SBOM input
-
-    source-->>+sbom: add source to SBOM struct
-    source-->>+catalog: pass src to generate catalog
-    catalog-->-sbom: add cataloging results onto SBOM
-    sbom-->>encoder: pass SBOM and format desiered to syft encoder
-    encoder-->>source: return bytes that are the SBOM of the original input 
-
-    Note right of catalog: cataloger configuration is done based on src
-```
-
-Additionally, here is a [gist of using syft as a library](https://gist.github.com/spiffcs/3027638b7ba904d07e482a712bc00d3d) to generate a SBOM for a docker image.
-
-
-### `pkg.Package` object
-
-The `pkg.Package` object is a core data structure that represents a software package. Fields like `name` and `version` probably don't need
-a detailed explanation, but some of the other fields are worth a quick overview:
-
-- `FoundBy`: the name of the cataloger that discovered this package (e.g. `python-pip-cataloger`).
-- `Locations`: these are the set of paths and layer ids that were parsed to discover this package (e.g. `python-pip-cataloger`).
-- `Language`: the language of the package (e.g. `python`).
-- `Type`: this is a high-level categorization of the ecosystem the package resides in. For instance, even if the package is a egg, wheel, or requirements.txt reference, it is still logically a "python" package. Not all package types align with a language (e.g. `rpm`) but it is common.
-- `Metadata`: specialized data for specific location(s) parsed. We should try and raise up as much raw information that seems useful. As a rule of thumb the object here should be as flat as possible and use the raw names and values from the underlying source material parsed.
-
-When `pkg.Package` is serialized an additional `MetadataType` is shown. This is a label that helps consumers understand the datashape of the `Metadata` field.
-
-By convention the `MetadataType` value should follow these rules of thumb:
-
-- Only use lowercase letters, numbers, and hyphens. Use hyphens to separate words.
-- **Try to anchor the name in the ecosystem, language, or packaging tooling it belongs to**. For a package manager for a language ecosystem the language, framework or runtime should be used as a prefix. For instance `pubspec-lock` is an OK name, but `dart-pubspec-lock` is better. For an OS package manager this is not necessary (e.g. `apk-db-entry` is a good name, but `alpine-apk-db-entry` is not since `alpine` and the `a` in `apk` is redundant).
-- **Be as specific as possible to what the data represents**. For instance `ruby-gem` is NOT a good `MetadataType` value, but `ruby-gemspec` is. Why? Ruby gem information can come from a gemspec file or a Gemfile.lock, which are very different. The latter name provides more context as to what to expect.
-- **Should describe WHAT the data is, NOT HOW it's used**. For instance `r-description-installed-file` is NOT a good `MetadataType` value since it's trying to convey that we use the DESCRIPTION file in the R ecosystem to detect installed packages. Instead simply describe what the DESCRIPTION file is itself without context of how it's used: `r-description`.
-- **Use the `lock` suffix** to distinct between manifest files that loosely describe package version requirements vs files that strongly specify one and only one version of a package ("lock" files). These should only be used with respect to package managers that have the guide and lock distinction, but would not be appropriate otherwise (e.g. `rpm` does not have a guide vs lock, so `lock` should NOT be used to describe a db entry).
-- **Use the `archive` suffix to indicate a package archive** (e.g. rpm file, apk file, etc) that describes the contents of the package. For example an RPM file that was cataloged would have a `rpm-archive` metadata type (not to be confused with an RPM DB record entry which would be `rpm-db-entry`).
-- **Use the `entry` suffix** to indicate information about a package that was found as a single entry within file that has multiple package entries. If the entry was found within a DB or a flat-file store for an OS package manager, you should use `db-entry`.
-- **Should NOT contain the phrase `package`**, though exceptions are allowed (say if the canonical name literally has the phrase package in it).
-- **Should NOT contain have a `file` suffix** unless the canonical name has the term "file", such as a `pipfile` or `gemfile`. An example of a bad name for this rule is`ruby-gemspec-file`; a better name would be `ruby-gemspec`.
-- **Should NOT contain the exact filename+extensions**. For instance `pipfile.lock` shouldn't really be in the name, instead try and describe what the file is: `python-pipfile-lock` (but shouldn't this be `python-pip-lock` you might ask? No, since the `pip` package manger is not related to the `pipfile` project).
-- **Should NOT contain the phrase `metadata`**, unless the canonical name has this term.
-- **Should represent a single use case**. For example, trying to describe Hackage metadata with a single `HackageMetadata` struct (and thus `MetadataType`) is not allowed since it represents 3 mutually exclusive use cases: representing a `stack.yaml`, `stack.lock`, or `cabal.project` file. Instead, each of these should have their own struct types and `MetadataType` values.
-
-There are other cases that are not covered by these rules... and that's ok! The goal is to provide a consistent naming scheme that is easy to understand and use when it's applicable. If the rules do not exactly apply in your situation then just use your best judgement (or amend these rules as needed whe new common cases come up).
-
-What if the underlying parsed data represents multiple files? There are two approaches to this:
-- use the primary file to represent all the data. For instance, though the `dpkg-cataloger` looks at multiple files to get all information about a package, it's the `status` file that gets represented.
-- nest each individual file's data under the `Metadata` field. For instance, the `java-archive-cataloger` may find information from on or all of the files: `pom.xml`, `pom.properties`, and `MANIFEST.MF`. However, the metadata is simply `java-metadata' with each possibility as a nested optional field.
-
-### Syft Catalogers
-
-Catalogers are the way in which syft is able to identify and construct packages given a set a targeted list of files.
-For example, a cataloger can ask syft for all `package-lock.json` files in order to parse and raise up javascript packages 
-(see [how file globs](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) and
-[file parser functions](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/javascript/cataloger.go#L16-L21) are used 
-for a quick example).
-
-From a high level catalogers have the following properties:
-
-- _They are independent from one another_. The java cataloger has no idea of the processes, assumptions, or results of the python cataloger, for example.
-
-- _They do not know what source is being analyzed_. Are we analyzing a local directory? an image? if so, the squashed representation or all layers? The catalogers do not know the answers to these questions. Only that there is an interface to query for file paths and contents from an underlying "source" being scanned.
-
-- _Packages created by the cataloger should not be mutated after they are created_. There is one exception made for adding CPEs to a package after the cataloging phase, but that will most likely be moved back into the cataloger in the future.
-
-
-Cataloger names should be unique and named with the following rules of thumb in mind:
-
-- Must end with `-cataloger`
-- Use lowercase letters, numbers, and hyphens only
-- Use hyphens to separate words
-- Catalogers for language ecosystems should start with the language name (e.g. `python-` for a cataloger that raises up python packages)
-- Distinct between when the cataloger is searching for evidence of installed packages vs declared packages. For example, there are currently two different gemspec-based catalogers, the `ruby-gemspec-cataloger` and `ruby-installed-gemspec-cataloger`, where the latter requires that the gemspec is found within a `specifications` directory (which means it was installed, not just at the root of a source repo).
-
-#### Building a new Cataloger
-
-Catalogers must fulfill the [`pkg.Cataloger` interface](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger.go) in order to add packages to the SBOM.
-All catalogers should be added to:
-- the [global list of catalogers](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/cataloger/cataloger.go#L92-L125)
-- at least one source-specific list, today the two lists are [directory catalogers and image catalogers](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/cataloger/cataloger.go#L39-L89)
-
-For reference, catalogers are [invoked within syft](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/catalog.go#L41-L100) one after the other, and can be invoked in parallel.
-
-`generic.NewCataloger` is an abstraction syft used to make writing common components easier (see the [apkdb cataloger](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/cataloger.go) for example usage). 
-It takes the following information as input:
-- A `catalogerName` to identify the cataloger uniquely among all other catalogers.
-- Pairs of file globs as well as parser functions to parse those files. These parser functions return a slice of [`pkg.Package`](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/pkg/package.go#L19) as well as a slice of [`artifact.Relationship`](https://github.com/anchore/syft/blob/9995950c70e849f9921919faffbfcf46401f71f3/syft/artifact/relationship.go#L31) to describe how the returned packages are related. See this [the apkdb cataloger parser function](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L22-L102) as an example.
-
-Identified packages share a common `pkg.Package` struct so be sure that when the new cataloger is constructing a new package it is using the [`Package` struct](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/package.go#L16-L31).
-If you want to return more information than what is available on the `pkg.Package` struct then you can do so in the `pkg.Package.Metadata` section of the struct, which is unique for each [`pkg.Type`](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/type.go).
-See [the `pkg` package](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg) for examples of the different metadata types that are supported today. 
-These are plugged into the `MetadataType` and `Metadata` fields in the above struct. `MetadataType` informs which type is being used. `Metadata` is an interface converted to that type.
-
-Finally, here is an example of where the package construction is done within the apk cataloger:
-- [Calling the APK package constructor from the parser function](https://github.com/anchore/syft/blob/v0.70.0/syft/pkg/cataloger/apkdb/parse_apk_db.go#L106)
-- [The APK package constructor itself](https://github.com/anchore/syft/tree/v0.70.0/syft/pkg/cataloger/apkdb/package.go#L12-L27)
-
-Interested in building a new cataloger? Checkout the [list of issues with the `new-cataloger` label](https://github.com/anchore/syft/issues?q=is%3Aopen+is%3Aissue+label%3Anew-cataloger+no%3Aassignee)!
-If you have questions about implementing a cataloger feel free to file an issue or reach out to us [on discourse](https://anchore.com/discourse)!
-
-
-#### Searching for files
-
-All catalogers are provided an instance of the [`file.Resolver`](https://github.com/anchore/syft/blob/v0.70.0/syft/source/file_resolver.go#L8) to interface with the image and search for files. The implementations for these 
-abstractions leverage [`stereoscope`](https://github.com/anchore/stereoscope) in order to perform searching. Here is a 
-rough outline how that works:
-
-1. a stereoscope `file.Index` is searched based on the input given (a path, glob, or MIME type). The index is relatively fast to search, but requires results to be filtered down to the files that exist in the specific layer(s) of interest. This is done automatically by the `filetree.Searcher` abstraction. This abstraction will fallback to searching directly against the raw `filetree.FileTree` if the index does not contain the file(s) of interest. Note: the `filetree.Searcher` is used by the `file.Resolver` abstraction.
-2. Once the set of files are returned from the `filetree.Searcher` the results are filtered down further to return the most unique file results. For example, you may have requested for files by a glob that returns multiple results. These results are filtered down to deduplicate by real files, so if a result contains two references to the same file, say one accessed via symlink and one accessed via the real path, then the real path reference is returned and the symlink reference is filtered out. If both were accessed by symlink then the first (by lexical order) is returned. This is done automatically by the `file.Resolver` abstraction.
-3. By the time results reach the `pkg.Cataloger` you are guaranteed to have a set of unique files that exist in the layer(s) of interest (relative to what the resolver supports).
-
-## Testing
-
-### Testing commands
-
-* `make help` shows a list of available commands
-* `make unit`, `make integration`, `make cli`, and `make acceptance` run those test suites (see below)
-* `make test` runs all those tests (and is therefore pretty slow)
-* `make fixtures` clears and re-fetches all test fixtures.
-* `go test ./syft/pkg/` for example can test particular packages, assuming fixtures are already made
-* `make clean-cache` cleans all test cache. Note that subsequent test runs will be slower after this
-
-
-### Levels of testing
-
-- `unit`: The default level of test which is distributed throughout the repo are unit tests. Any `_test.go` file that 
-  does not reside somewhere within the `/test` directory is a unit test. Other forms of testing should be organized in 
-  the `/test` directory. These tests should focus on correctness of functionality in depth. % test coverage metrics 
-  only considers unit tests and no other forms of testing.
-
-- `integration`: located within `cmd/syft/internal/test/integration`, these tests focus on the behavior surfaced by the common library 
-  entrypoints from the `syft` package and make light assertions about the results surfaced. Additionally, these tests
-  tend to make diversity assertions for enum-like objects, ensuring that as enum values are added to a definition
-  that integration tests will automatically fail if no test attempts to use that enum value. For more details see 
-  the "Data diversity and freshness assertions" section below.
-
-- `cli`: located with in `test/cli`, these are tests that test the correctness of application behavior from a 
-  snapshot build. This should be used in cases where a unit or integration test will not do or if you are looking
-  for in-depth testing of code in the `cmd/` package (such as testing the proper behavior of application configuration,
-  CLI switches, and glue code before syft library calls).
-
-- `acceptance`: located within `test/compare` and `test/install`, these are smoke-like tests that ensure that application  
-  packaging and installation works as expected. For example, during release we provide RPM packages as a download 
-  artifact. We also have an accompanying RPM acceptance test that installs the RPM from a snapshot build and ensures the 
-  output of a syft invocation matches canned expected output. New acceptance tests should be added for each release artifact
-  and architecture supported (when possible).
-
-### Data diversity and freshness assertions
-
-It is important that tests against the codebase are flexible enough to begin failing when they do not cover "enough"
-of the objects under test. "Cover" in this case does not mean that some percentage of the code has been executed 
-during testing, but instead that there is enough diversity of data input reflected in testing relative to the
-definitions available.
-
-For instance, consider an enum-like value like so:
-```go
-type Language string
-
-const (
-  Java            Language = "java"
-  JavaScript      Language = "javascript"
-  Python          Language = "python"
-  Ruby            Language = "ruby"
-  Go              Language = "go"
-)
-```
-
-Say we have a test that exercises all the languages defined today:
-
-```go
-func TestCatalogPackages(t *testing.T) {
-  testTable := []struct {
-    // ... the set of test cases that test all languages
-  }
-  for _, test := range cases {
-    t.Run(test.name, func (t *testing.T) {
-      // use inputFixturePath and assert that syft.CatalogPackages() returns the set of expected Package objects
-      // ...
-    })
-  }
-}
-```
-
-Where each test case has a `inputFixturePath` that would result with packages from each language. This test is
-brittle since it does not assert that all languages were exercised directly and future modifications (such as 
-adding a new language) won't be covered by any test cases.
-
-To address this the enum-like object should have a definition of all objects that can be used in testing:
-
-```go
-type Language string
-
-// const( Java Language = ..., ... )
-
-var AllLanguages = []Language{
-	Java,
-	JavaScript,
-	Python,
-	Ruby,
-	Go,
-	Rust,
-}
-```
-
-Allowing testing to automatically fail when adding a new language:
-
-```go
-func TestCatalogPackages(t *testing.T) {
-  testTable := []struct {
-  	// ... the set of test cases that (hopefully) covers all languages
-  }
-
-  // new stuff...
-  observedLanguages := strset.New()
-  
-  for _, test := range cases {
-    t.Run(test.name, func (t *testing.T) {
-      // use inputFixturePath and assert that syft.CatalogPackages() returns the set of expected Package objects
-    	// ...
-    	
-    	// new stuff...
-    	for _, actualPkg := range actual {
-        observedLanguages.Add(string(actualPkg.Language))
-    	}
-    	
-    })
-  }
-
-   // new stuff...
-  for _, expectedLanguage := range pkg.AllLanguages {
-    if 	!observedLanguages.Contains(expectedLanguage) {
-      t.Errorf("failed to test language=%q", expectedLanguage)	
-    }
-  }
-}
-```
-
-This is a better test since it will fail when someone adds a new language but fails to write a test case that should
-exercise that new language. This method is ideal for integration-level testing, where testing correctness in depth 
-is not needed (that is what unit tests are for) but instead testing in breadth to ensure that units are well integrated.
-
-A similar case can be made for data freshness; if the quality of the results will be diminished if the input data
-is not kept up to date then a test should be written (when possible) to assert any input data is not stale.
-
-An example of this is the static list of licenses that is stored in `internal/spdxlicense` for use by the SPDX 
-presenters. This list is updated and published periodically by an external group and syft can grab and update this
-list by running `go generate ./...` from the root of the repo.
-
-An integration test has been written to grabs the latest license list version externally and compares that version
-with the version generated in the codebase. If they differ, the test fails, indicating to someone that there is an
-action needed to update it.
-
-**_The key takeaway is to try and write tests that fail when data assumptions change and not just when code changes.**_
-
-### Snapshot tests
-
-The format objects make a lot of use of "snapshot" testing, where you save the expected output bytes from a call into the
-git repository and during testing make a comparison of the actual bytes from the subject under test with the golden
-copy saved in the repo. The "golden" files are stored in the `test-fixtures/snapshot` directory relative to the go 
-package under test and should always be updated by invoking `go test` on the specific test file with a specific CLI 
-update flag provided.
-
-Many of the `Format` tests make use of this approach, where the raw SBOM report is saved in the repo and the test 
-compares that SBOM with what is generated from the latest presenter code. The following command can be used to
-update the golden files for the various snapshot tests:
-
-```bash
-make update-format-golden-files
-```
-
-These flags are defined at the top of the test files that have tests that use the snapshot files.
-
-Snapshot testing is only as good as the manual verification of the golden snapshot file saved to the repo! Be careful 
-and diligent when updating these files.
-
-

Dockerfile

@@ -1,4 +1,5 @@
-FROM gcr.io/distroless/static-debian12:latest AS build
+ARG DEBIAN_VERSION=13
+FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:latest AS build
 
 FROM scratch
 # needed for version check HTTPS request
@@ -7,23 +8,7 @@ COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certifica
 # create the /tmp dir, which is needed for image content cache
 WORKDIR /tmp
 
-COPY syft /
-
-ARG BUILD_DATE
-ARG BUILD_VERSION
-ARG VCS_REF
-ARG VCS_URL
-
-LABEL org.opencontainers.image.created=$BUILD_DATE
-LABEL org.opencontainers.image.title="syft"
-LABEL org.opencontainers.image.description="CLI tool and library for generating a Software Bill of Materials from container images and filesystems"
-LABEL org.opencontainers.image.source=$VCS_URL
-LABEL org.opencontainers.image.revision=$VCS_REF
-LABEL org.opencontainers.image.vendor="Anchore, Inc."
-LABEL org.opencontainers.image.version=$BUILD_VERSION
-LABEL org.opencontainers.image.licenses="Apache-2.0"
-LABEL io.artifacthub.package.readme-url="https://raw.githubusercontent.com/anchore/syft/main/README.md"
-LABEL io.artifacthub.package.logo-url="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png"
-LABEL io.artifacthub.package.license="Apache-2.0"
+ARG TARGETPLATFORM
+COPY ${TARGETPLATFORM}/syft /
 
 ENTRYPOINT ["/syft"]

Dockerfile.debug

@@ -1,27 +1,10 @@
-FROM gcr.io/distroless/static-debian12:debug-nonroot
+ARG DEBIAN_VERSION=13
+FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:debug
 
 # create the /tmp dir, which is needed for image content cache
 WORKDIR /tmp
 
-COPY syft /
-
-USER nonroot
-
-ARG BUILD_DATE
-ARG BUILD_VERSION
-ARG VCS_REF
-ARG VCS_URL
-
-LABEL org.opencontainers.image.created=$BUILD_DATE
-LABEL org.opencontainers.image.title="syft"
-LABEL org.opencontainers.image.description="CLI tool and library for generating a Software Bill of Materials from container images and filesystems"
-LABEL org.opencontainers.image.source=$VCS_URL
-LABEL org.opencontainers.image.revision=$VCS_REF
-LABEL org.opencontainers.image.vendor="Anchore, Inc."
-LABEL org.opencontainers.image.version=$BUILD_VERSION
-LABEL org.opencontainers.image.licenses="Apache-2.0"
-LABEL io.artifacthub.package.readme-url="https://raw.githubusercontent.com/anchore/syft/main/README.md"
-LABEL io.artifacthub.package.logo-url="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png"
-LABEL io.artifacthub.package.license="Apache-2.0"
+ARG TARGETPLATFORM
+COPY ${TARGETPLATFORM}/syft /
 
 ENTRYPOINT ["/syft"]

Dockerfile.debug-nonroot

@@ -0,0 +1,12 @@
+ARG DEBIAN_VERSION=13
+FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:debug-nonroot
+
+# create the /tmp dir, which is needed for image content cache
+WORKDIR /tmp
+
+ARG TARGETPLATFORM
+COPY ${TARGETPLATFORM}/syft /
+
+USER nonroot
+
+ENTRYPOINT ["/syft"]

Dockerfile.nonroot

@@ -1,27 +1,12 @@
-FROM gcr.io/distroless/static-debian12:nonroot
+ARG DEBIAN_VERSION=13
+FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:nonroot
 
 # create the /tmp dir, which is needed for image content cache
 WORKDIR /tmp
 
-COPY syft /
+ARG TARGETPLATFORM
+COPY ${TARGETPLATFORM}/syft /
 
 USER nonroot
 
-ARG BUILD_DATE
-ARG BUILD_VERSION
-ARG VCS_REF
-ARG VCS_URL
-
-LABEL org.opencontainers.image.created=$BUILD_DATE
-LABEL org.opencontainers.image.title="syft"
-LABEL org.opencontainers.image.description="CLI tool and library for generating a Software Bill of Materials from container images and filesystems"
-LABEL org.opencontainers.image.source=$VCS_URL
-LABEL org.opencontainers.image.revision=$VCS_REF
-LABEL org.opencontainers.image.vendor="Anchore, Inc."
-LABEL org.opencontainers.image.version=$BUILD_VERSION
-LABEL org.opencontainers.image.licenses="Apache-2.0"
-LABEL io.artifacthub.package.readme-url="https://raw.githubusercontent.com/anchore/syft/main/README.md"
-LABEL io.artifacthub.package.logo-url="https://user-images.githubusercontent.com/5199289/136844524-1527b09f-c5cb-4aa9-be54-5aa92a6086c1.png"
-LABEL io.artifacthub.package.license="Apache-2.0"
-
 ENTRYPOINT ["/syft"]

Makefile

@@ -1,46 +1,18 @@
-OWNER = anchore
-PROJECT = syft
+# `test` and `snapshot` have matching directory names in this repo, so make would
+# refuse to run them without an explicit .PHONY (Nothing to be done for ...).
+.PHONY: test snapshot
+test:
+	@go run -C .make . test
 
-TOOL_DIR = .tool
-BINNY = $(TOOL_DIR)/binny
-TASK = $(TOOL_DIR)/task
+snapshot:
+	@go run -C .make . snapshot
 
-.DEFAULT_GOAL := make-default
+.PHONY: *
+.DEFAULT_GOAL: make-default
 
-## Bootstrapping targets #################################
+make-default:
+	@go run -C .make .
 
-# note: we need to assume that binny and task have not already been installed
-$(BINNY):
-	@mkdir -p $(TOOL_DIR)
-	@curl -sSfL https://get.anchore.io/binny | sh -s -- -b $(TOOL_DIR)
-
-# note: we need to assume that binny and task have not already been installed
-.PHONY: task
-$(TASK) task: $(BINNY)
-	@$(BINNY) install task -q
-
-.PHONY: ci-bootstrap-go
-ci-bootstrap-go:
-	go mod download
-
-# this is a bootstrapping catch-all, where if the target doesn't exist, we'll ensure the tools are installed and then try again
+.DEFAULT:
 %:
-	@make --silent $(TASK)
-	@$(TASK) $@
-
-## Shim targets #################################
-
-.PHONY: make-default
-make-default: $(TASK)
-	@# run the default task in the taskfile
-	@$(TASK)
-
-# for those of us that can't seem to kick the habit of typing `make ...` lets wrap the superior `task` tool
-TASKS := $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep '^\* ' | cut -d' ' -f2 | tr -d ':' | tr '\n' ' '" ) $(shell bash -c "test -f $(TASK) && $(TASK) -l | grep 'aliases:' | cut -d ':' -f 3 | tr '\n' ' ' | tr -d ','")
-
-.PHONY: $(TASKS)
-$(TASKS): $(TASK)
-	@$(TASK) $@
-
-help: $(TASK)
-	@$(TASK) -l
+	@go run -C .make . $@

README.md

@@ -8,180 +8,83 @@
 
 <p align="center">
  &nbsp;<a href="https://github.com/anchore/syft/actions/workflows/validations.yaml" target="_blank"><img alt="Validations" src="https://github.com/anchore/syft/actions/workflows/validations.yaml/badge.svg"></a>&nbsp;
- &nbsp;<a href="https://goreportcard.com/report/github.com/anchore/syft" target="_blank"><img alt="Go Report Card" src="https://goreportcard.com/badge/github.com/anchore/syft"></a>&nbsp;
  &nbsp;<a href="https://github.com/anchore/syft/releases/latest" target="_blank"><img alt="GitHub release" src="https://img.shields.io/github/release/anchore/syft.svg"></a>&nbsp;
  &nbsp;<a href="https://github.com/anchore/syft" target="_blank"><img alt="GitHub go.mod Go version" src="https://img.shields.io/github/go-mod/go-version/anchore/syft.svg"></a>&nbsp;
- &nbsp;<a href="" target="_blank"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"></a>&nbsp;
+ &nbsp;<a href="https://github.com/anchore/syft/blob/main/LICENSE" target="_blank"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"></a>&nbsp;
  &nbsp;<a href="https://anchore.com/discourse" target="_blank"><img alt="Join our Discourse" src="https://img.shields.io/badge/Discourse-Join-blue?logo=discourse"/></a>&nbsp;
  &nbsp;<a rel="me" href="https://fosstodon.org/@syft"><img alt="Follow on Mastodon" src="https://img.shields.io/badge/Mastodon-Follow-blue?logoColor=white&logo=mastodon"/></a>&nbsp;
 </p>
 
 ![syft-demo](https://user-images.githubusercontent.com/590471/90277200-2a253000-de33-11ea-893f-32c219eea11a.gif)
 
-## Introduction
-
-Syft is a powerful and easy-to-use open-source tool for generating Software Bill of Materials (SBOMs) for container images and filesystems. It provides detailed visibility into the packages and dependencies in your software, helping you manage vulnerabilities, license compliance, and software supply chain security.
-
-Syft development is sponsored by [Anchore](https://anchore.com/), and is released under the [Apache-2.0 License](https://github.com/anchore/syft?tab=Apache-2.0-1-ov-file). For commercial support options with Syft or Grype, please [contact Anchore](https://get.anchore.com/contact/).
-
 ## Features
-- Generates SBOMs for container images, filesystems, archives, and more to discover packages and libraries
-- Supports OCI, Docker and [Singularity](https://github.com/sylabs/singularity) image formats
-- Linux distribution identification
-- Works seamlessly with [Grype](https://github.com/anchore/grype) (a fast, modern vulnerability scanner)
-- Able to create signed SBOM attestations using the [in-toto specification](https://github.com/in-toto/attestation/blob/main/spec/README.md)
-- Convert between SBOM formats, such as CycloneDX, SPDX, and Syft's own format.
+
+- Generates SBOMs for **container images**, **filesystems**, **archives** (see the docs for a full list of [supported scan targets](https://oss.anchore.com/docs/guides/sbom/scan-targets/))
+- Supports dozens of packaging ecosystems (e.g. Alpine (apk), Debian (dpkg), RPM, Go, Python, Java, JavaScript, Ruby, Rust, PHP, .NET, and [many more](https://oss.anchore.com/docs/capabilities/all-packages/))
+- Supports OCI, Docker, [Singularity](https://github.com/sylabs/singularity), and [more image formats](https://oss.anchore.com/docs/guides/sbom/scan-targets/)
+- Works seamlessly with [Grype](https://github.com/anchore/grype) for vulnerability scanning
+- Multiple output formats (**CycloneDX**, **SPDX**, **Syft JSON**, and [more](https://oss.anchore.com/docs/guides/sbom/formats/)) including the ability to [convert between SBOM formats](https://oss.anchore.com/docs/guides/sbom/conversion/)
+- Create signed SBOM attestations using the [in-toto specification](https://github.com/in-toto/attestation/blob/main/spec/README.md)
+
+> [!TIP]
+> **New to Syft? Check out the [Getting Started guide](https://oss.anchore.com/docs/guides/sbom/getting-started/) for a walkthrough!**
 
 ## Installation
 
-Syft binaries are provided for Linux, macOS and Windows.
-
-### Recommended
-> ```bash
-> curl -sSfL https://get.anchore.io/syft | sudo sh -s -- -b /usr/local/bin
-> ```
-
-Install script options:
--	`-b`: Specify a custom installation directory (defaults to `./bin`)
--	`-d`: More verbose logging levels (`-d` for debug, `-dd` for trace)
--	`-v`: Verify the signature of the downloaded artifact before installation (requires [`cosign`](https://github.com/sigstore/cosign) to be installed)
-
-### Homebrew
+The quickest way to get up and going:
 ```bash
-brew install syft
+curl -sSfL https://get.anchore.io/syft | sudo sh -s -- -b /usr/local/bin
 ```
 
-### Scoop
+> [!TIP]
+> **See [Installation docs](https://oss.anchore.com/docs/installation/syft/) for more ways to get Syft, including Homebrew, Docker, Scoop, Chocolatey, Nix, and more!**
 
-```powershell
-scoop install syft
-```
+## The basics
 
-### Chocolatey
-
-The chocolatey distribution of Syft is community-maintained and not distributed by the Anchore team
-
-```powershell
-choco install syft -y
-```
-
-### Nix
-
-**Note**: Nix packaging of Syft is [community maintained](https://github.com/NixOS/nixpkgs/blob/master/pkgs/by-name/sy/syft/package.nix). Syft is available in the [stable channel](https://wiki.nixos.org/wiki/Nix_channels#The_official_channels) since NixOS `22.05`.
+See the packages within a container image or directory:
 
 ```bash
-nix-env -i syft
+# container image
+syft alpine:latest
+
+# directory
+syft ./my-project
 ```
 
-... or, just try it out in an ephemeral nix shell:
+To get an SBOM, specify one or more output formats:
 
 ```bash
-nix-shell -p syft
+# SBOM to stdout
+syft <image> -o cyclonedx-json
+
+# Multiple SBOMs to files
+syft <image> -o spdx-json=./spdx.json -o cyclonedx-json=./cdx.json
 ```
 
-## Getting started
 
-### SBOM
+> [!TIP]
+> **Check out the [Getting Started guide](https://oss.anchore.com/docs/guides/sbom/getting-started/)** to explore all of the capabilities and features.
+>
+> **Want to know all of the ins-and-outs of Syft?** Check out the [CLI docs](https://oss.anchore.com/docs/reference/syft/cli/),  [configuration docs](https://oss.anchore.com/docs/reference/syft/configuration/), and [JSON schema](https://oss.anchore.com/docs/reference/syft/json/latest/).
 
-To generate an SBOM for a container image:
-
-```bash
-syft <image>
-```
-
-The above output includes only software that is visible in the container (i.e., the squashed representation of the image). To include software from all image layers in the SBOM, regardless of its presence in the final image, provide `--scope all-layers`:
-
-```bash
-syft <image> --scope all-layers
-```
-
-### Output formats
-
-The output format for Syft is configurable as well using the `-o` (or `--output`) option:
-
-```
-syft <image> -o <format>
-```
-
-Where the `formats` available are:
-- `syft-json`: Use this to get as much information out of Syft as possible!
-- `syft-text`: A row-oriented, human-and-machine-friendly output.
-- `cyclonedx-xml`: A XML report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-xml@1.5`: A XML report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-json@1.5`: A JSON report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
-- `spdx-tag-value`: A tag-value formatted report conforming to the [SPDX 2.3 specification](https://spdx.github.io/spdx-spec/v2.3/).
-- `spdx-tag-value@2.2`: A tag-value formatted report conforming to the [SPDX 2.2 specification](https://spdx.github.io/spdx-spec/v2.2.2/).
-- `spdx-json`: A JSON report conforming to the [SPDX 2.3 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.3/schemas/spdx-schema.json).
-- `spdx-json@2.2`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
-- `github-json`: A JSON report conforming to GitHub's dependency snapshot format.
-- `syft-table`: A columnar summary (default).
-- `template`: Lets the user specify the output format. See ["Using templates"](#using-templates) below.
-
-Note that flags using the @<version> can be used for earlier versions of each specification as well.
-
-### Supported Ecosystems
-
-- Alpine (apk)
-- Bitnami packages
-- C (conan)
-- C++ (conan)
-- Dart (pubs)
-- Debian (dpkg)
-- Dotnet (deps.json)
-- Objective-C (cocoapods)
-- Elixir (mix)
-- Erlang (rebar3)
-- Go (go.mod, Go binaries)
-- Haskell (cabal, stack)
-- Java (jar, ear, war, par, sar, nar, native-image)
-- JavaScript (npm, yarn)
-- Jenkins Plugins (jpi, hpi)
-- Linux kernel archives (vmlinz)
-- Linux kernel modules (ko)
-- Nix (outputs in /nix/store)
-- PHP (composer, PECL, Pear)
-- Python (wheel, egg, poetry, requirements.txt, uv)
-- Red Hat (rpm)
-- Ruby (gem)
-- Rust (cargo.lock, auditable binary)
-- Swift (cocoapods, swift-package-manager)
-- Wordpress plugins
-- Terraform providers (.terraform.lock.hcl)
-
-## Documentation
-
-Our [wiki](https://github.com/anchore/syft/wiki) contains further details on the following topics:
-
-* [Supported Sources](https://github.com/anchore/syft/wiki/supported-sources)
-* [File Selection](https://github.com/anchore/syft/wiki/file-selection)
-* [Excluding file paths](https://github.com/anchore/syft/wiki/excluding-file-paths)
-* [Output formats](https://github.com/anchore/syft/wiki/output-formats)
-* [Package Cataloger Selection](https://github.com/anchore/syft/wiki/package-cataloger-selection)
-  * [Concepts](https://github.com/anchore/syft/wiki/package-cataloger-selection#concepts)
-  * [Examples](https://github.com/anchore/syft/wiki/package-cataloger-selection#examples)
-* [Using templates](https://github.com/anchore/syft/wiki/using-templates)
-* [Multiple outputs](https://github.com/anchore/syft/wiki/multiple-outputs)
-* [Private Registry Authentication](https://github.com/anchore/syft/wiki/private-registry-authentication)
-  * [Local Docker Credentials](https://github.com/anchore/syft/wiki/private-registry-authentication#local-docker)
-  * [Docker Credentials in Kubernetes](https://github.com/anchore/syft/wiki/private-registry-authentication#docker-credentials-in-kubernetes)
-* [Attestation (experimental)](https://github.com/anchore/syft/wiki/attestation)
-  * [Keyless Support](https://github.com/anchore/syft/wiki/attestation#keyless-support)
-  * [Local private key support](https://github.com/anchore/syft/wiki/attestation#local-private-key-support)
-  * [Adding an SBOM to an image as an attestation using Syft](https://github.com/anchore/syft/wiki/attestation#adding-an-sbom-to-an-image-as-an-attestation-using-syft)
-* [Configuration](https://github.com/anchore/syft/wiki/configuration)
 
 ## Contributing
 
-Check out our [contributing](/CONTRIBUTING.md) guide and [developer](/DEVELOPING.md) docs.
+We encourage users to help make these tools better by [submitting issues](https://github.com/anchore/syft/issues) when you find a bug or want a new feature. 
+Check out our [contributing overview](https://oss.anchore.com/docs/contributing/) and [developer-specific documentation](https://oss.anchore.com/docs/contributing/syft/) if you are interested in providing code contributions.
 
-## Syft Team Meetings
 
-The Syft Team hold regular community meetings online. All are welcome to join to bring topics for discussion.
+
+<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/">
+  Syft development is sponsored by <a href="https://anchore.com/">Anchore</a>, and is released under the <a href="https://github.com/anchore/syft?tab=Apache-2.0-1-ov-file">Apache-2.0 License</a>.
+  The <a property="dct:title" rel="cc:attributionURL" href="https://anchore.com/wp-content/uploads/2024/11/syft-logo.svg">Syft logo</a> by <a rel="cc:attributionURL dct:creator" property="cc:attributionName" href="https://anchore.com/">Anchore</a> is licensed under <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC BY 4.0<img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg" alt=""></a>
+</p>
+
+For commercial support options with Syft or Grype, please [contact Anchore](https://get.anchore.com/contact/).
+
+## Come talk to us!
+
+The Syft Team holds regular community meetings online. All are welcome to join to bring topics for discussion.
 - Check the [calendar](https://calendar.google.com/calendar/u/0/r?cid=Y182OTM4dGt0MjRtajI0NnNzOThiaGtnM29qNEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) for the next meeting date.
 - Add items to the [agenda](https://docs.google.com/document/d/1ZtSAa6fj2a6KRWviTn3WoJm09edvrNUp4Iz_dOjjyY8/edit?usp=sharing) (join [this group](https://groups.google.com/g/anchore-oss-community) for write access to the [agenda](https://docs.google.com/document/d/1ZtSAa6fj2a6KRWviTn3WoJm09edvrNUp4Iz_dOjjyY8/edit?usp=sharing))
 - See you there!
-
-## Syft Logo
-
-<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/"><a property="dct:title" rel="cc:attributionURL" href="https://anchore.com/wp-content/uploads/2024/11/syft-logo.svg">Syft Logo</a> by <a rel="cc:attributionURL dct:creator" property="cc:attributionName" href="https://anchore.com/">Anchore</a> is licensed under <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC BY 4.0<img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg" alt=""></a></p>

SECURITY.md

@@ -2,31 +2,35 @@
 
 ## Supported Versions
 
-<!-- Use this section to tell people about which versions of your project are
-currently being supported with security updates.
-
-| Version | Supported          |
-| ------- | ------------------ |
-| 5.1.x   | :white_check_mark: |
-| 5.0.x   | :x:                |
-| 4.0.x   | :white_check_mark: |
-| < 4.0   | :x:                |
-
--->
-
 Security updates are applied only to the most recent release, try to always be up to date.
 
 ## Reporting a Vulnerability
 
-<!-- Use this section to tell people how to report a vulnerability.
-
-Tell them where to go, how often they can expect to get an update on a
-reported vulnerability, what to expect if the vulnerability is accepted or
-declined, etc. -->
-
 To report a security issue, please email
 [security@anchore.com](mailto:security@anchore.com)
 with a description of the issue, the steps you took to create the issue,
 affected versions, and, if known, mitigations for the issue.
 
-All support will be made on the best effort base, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.
+All support will be made on a best effort basis, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.
+
+For more details, see our [security policy documentation](https://oss.anchore.com/docs/contributing/security/).
+
+## Trust Boundary
+
+Syft is a tool to scan content and product an SBOM. Syft is not a tool designed to scan malicious content. Detecting and properly reporting on purposely malicious artifacts is outside the scope of Syft's expected operating environment.
+
+There are many possible ways for malicious content to cause Syft to become confused or fail to include results in an SBOM. We do not consider this to be a security vulnerability.
+
+**Examples**
+- Removing or altering a package lock file
+- Removing or altering an RPM or DEB database
+- A malicious archive that Syft will skip but the runtime may not
+- Self modifying systems that change state when running
+
+We consider the security trust boundary for Syft to be anything that causes problems for the overall system running Syft, or Syft operating in a way that is dangerous to itself, the system, or the operator.
+
+**Examples**
+- Filling up temp space permanently
+- Syft executing arbitrary code when scanning an artifact
+- Syft leaking secrets from the environment or configuration files into logs or SBOMs
+- Syft operating outside of the expected artifact or directory (directory traversal)

Taskfile.yaml

@@ -1,10 +1,22 @@
-
 version: "3"
+
+# NOTE: most generic tasks (static-analysis, format, lint, unit, snapshot, release,
+# changelog, ci-release, etc.) are now provided natively by anchore/go-make and
+# defined in .make/main.go. This file holds the syft-specific tasks, which go-make
+# auto-discovers via gotask.Tasks() and surfaces as `make <name>` — keep
+# descriptions (`desc:`) populated so they show up in `make help`.
+
+includes:
+  generate:cpe-index: ./task.d/generate/cpe-index.yaml
+
 vars:
   OWNER: anchore
   PROJECT: syft
 
-  CACHE_IMAGE: ghcr.io/{{ .OWNER }}/{{ .PROJECT }}/test-fixture-cache:latest
+  # v1: when fixtures were located at test-fixtures dirs
+  # v2: migration to testdata dirs
+  CACHE_REPO: oss-cache
+  CACHE_IMAGE: ghcr.io/{{ .OWNER }}/{{ .CACHE_REPO }}/syft-test-fixture-cache:v2
 
   # static file dirs
   TOOL_DIR: .tool
@@ -18,11 +30,7 @@ vars:
   YQ: "{{ .TOOL_DIR }}/yq"
   TASK: "{{ .TOOL_DIR }}/task"
 
-  # used for changelog generation
-  CHANGELOG: CHANGELOG.md
-  NEXT_VERSION: VERSION
-
-  # used for snapshot builds
+  # used for snapshot bin discovery in compare/install tasks
   OS:
     sh: uname -s | tr '[:upper:]' '[:lower:]'
   ARCH:
@@ -31,15 +39,16 @@ vars:
   PROJECT_ROOT:
     sh: echo $PWD
 
+  # docker platform suffix goreleaser appends to snapshot image tags (e.g. latest-amd64).
+  # snapshot builds load per-arch images rather than a multi-arch manifest, so the smoke
+  # test must run the host-native tag to avoid emulation (and red-local/green-CI splits).
+  DOCKER_ARCH:
+    sh: go env GOARCH
+
   # note: the snapshot dir must be a relative path starting with ./
   # e.g. when installing snapshot debs from a local path, ./ forces the deb to be installed in the current working directory instead of referencing a package name
   SNAPSHOT_DIR: ./snapshot
   SNAPSHOT_BIN: "{{ .PROJECT_ROOT }}/{{ .SNAPSHOT_DIR }}/{{ .OS }}-build_{{ .OS }}_{{ .ARCH }}/{{ .PROJECT }}"
-  SNAPSHOT_CMD: "{{ .TOOL_DIR }}/goreleaser release --config {{ .TMP_DIR }}/goreleaser.yaml --clean --snapshot --skip=publish --skip=sign"
-  BUILD_CMD:    "{{ .TOOL_DIR }}/goreleaser build   --config {{ .TMP_DIR }}/goreleaser.yaml --clean --snapshot --single-target"
-  RELEASE_CMD:  "{{ .TOOL_DIR }}/goreleaser release --clean --release-notes {{ .CHANGELOG }}"
-  VERSION:
-    sh: git describe --dirty --always --tags
 
   # used for install and acceptance testing
   COMPARE_DIR: ./test/compare
@@ -50,43 +59,10 @@ env:
 
 tasks:
 
-  ## High-level tasks #################################
-
-  default:
-    desc: Run all validation tasks
-    aliases:
-      - pr-validations
-      - validations
-    cmds:
-      - task: static-analysis
-      - task: test
-      - task: install-test
-
-  static-analysis:
-    desc: Run all static analysis tasks
-    cmds:
-      - task: check-go-mod-tidy
-      - task: check-licenses
-      - task: lint
-      - task: check-json-schema-drift
-      - task: check-binary-fixture-size
-
-  test:
-    desc: Run all levels of test
-    cmds:
-      - task: unit
-      - task: integration
-      - task: validate-cyclonedx-schema
-      - task: test-utils
-      - task: snapshot
-      - task: cli
-      - task: check-docker-cache
-
-  ## Bootstrap tasks #################################
+  ## Bootstrap (internal helpers used by other Taskfile tasks) ###############
 
   binny:
     internal: true
-    # desc: Get the binny tool
     generates:
       - "{{ .TOOL_DIR }}/binny"
     status:
@@ -95,10 +71,8 @@ tasks:
     silent: true
 
   tools:
-    desc: Install all tools needed for CI and local development
+    internal: true
     deps: [binny]
-    aliases:
-      - bootstrap
     generates:
       - ".binny.yaml"
       - "{{ .TOOL_DIR }}/*"
@@ -107,92 +81,32 @@ tasks:
     cmd: "{{ .TOOL_DIR }}/binny install -v"
     silent: true
 
-  update-tools:
-    desc: Update pinned versions of all tools to their latest available versions
-    deps: [binny]
-    generates:
-      - ".binny.yaml"
-      - "{{ .TOOL_DIR }}/*"
-    cmd: "{{ .TOOL_DIR }}/binny update -v"
-    silent: true
-
-  list-tools:
-    desc: List all tools needed for CI and local development
-    deps: [binny]
-    cmd: "{{ .TOOL_DIR }}/binny list"
-    silent: true
-
-  list-tool-updates:
-    desc: List all tools that are not up to date relative to the binny config
-    deps: [binny]
-    cmd: "{{ .TOOL_DIR }}/binny list --updates"
-    silent: true
-
   tmpdir:
+    internal: true
     silent: true
     generates:
       - "{{ .TMP_DIR }}"
     cmd: "mkdir -p {{ .TMP_DIR }}"
 
-  ## Static analysis tasks #################################
-
-  format:
-    desc: Auto-format all source code
-    deps: [tools]
-    cmds:
-      - gofmt -w -s .
-      - "{{ .TOOL_DIR }}/gosimports -local github.com/anchore -w ."
-      - go mod tidy
-
-  lint-fix:
-    desc: Auto-format all source code + run golangci lint fixers
-    deps: [tools]
-    cmds:
-      - task: format
-      - "{{ .TOOL_DIR }}/golangci-lint run --tests=false --fix"
-
-  lint:
-    desc: Run gofmt + golangci lint checks
-    vars:
-      BAD_FMT_FILES:
-        sh: gofmt -l -s .
-      BAD_FILE_NAMES:
-        sh: "find . | grep -e ':' || true"
-    deps: [tools]
-    cmds:
-      # ensure there are no go fmt differences
-      - cmd: 'test -z "{{ .BAD_FMT_FILES }}" || (echo "files with gofmt issues: [{{ .BAD_FMT_FILES }}]"; exit 1)'
-        silent: true
-      # ensure there are no files with ":" in it (a known back case in the go ecosystem)
-      - cmd: 'test -z "{{ .BAD_FILE_NAMES }}" || (echo "files with bad names: [{{ .BAD_FILE_NAMES }}]"; exit 1)'
-        silent: true
-      # run linting
-      - "{{ .TOOL_DIR }}/golangci-lint run --tests=false"
-
-
-  check-licenses:
-    # desc: Ensure transitive dependencies are compliant with the current license policy
-    deps: [tools]
-    cmd: "{{ .TOOL_DIR }}/bouncer check ./..."
-
-  check-go-mod-tidy:
-    # desc: Ensure go.mod and go.sum are up to date
-    cmds:
-      - cmd: .github/scripts/go-mod-tidy-check.sh && echo "go.mod and go.sum are tidy!"
-        silent: true
+  ## Static analysis extras #################################################
 
   check-json-schema-drift:
     desc: Ensure there is no drift between the JSON schema and the code
     cmds:
       - .github/scripts/json-schema-drift-check.sh
 
+  check-capability-drift:
+    desc: Ensure there is no drift between the capabilities data and the code
+    cmds:
+      - .github/scripts/capability-drift-check.sh
+
   check-binary-fixture-size:
     desc: Ensure that the binary test fixtures are not too large
     cmds:
-      - .github/scripts/check_binary_fixture_size.sh syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets
+      - .github/scripts/check_binary_fixture_size.sh syft/pkg/cataloger/binary/testdata/classifiers/snippets
 
+  ## Test extras ############################################################
 
-  ## Testing tasks #################################
   update-format-golden-files:
     desc: "Update golden (i.e. snapshot) files used by unit tests"
     cmds:
@@ -202,62 +116,38 @@ tasks:
       - go test ./syft/format/cyclonedxjson -update-cyclonedx-json
       - go test ./syft/format/syftjson -update-json
 
-  unit:
-    desc: Run unit tests
-    deps:
-      - tmpdir
-      - fixtures
-    vars:
-      TEST_PKGS:
-        sh: "go list ./... | grep -v {{ .OWNER }}/{{ .PROJECT }}/test | grep -v {{ .OWNER }}/{{ .PROJECT }}/cmd/syft/internal/test | tr '\n' ' '"
-
-      # unit test coverage threshold (in % coverage)
-      COVERAGE_THRESHOLD: 62
-    cmds:
-      - "go test -coverprofile {{ .TMP_DIR }}/unit-coverage-details.txt {{ .TEST_PKGS }}"
-      - cmd: ".github/scripts/coverage.py {{ .COVERAGE_THRESHOLD }} {{ .TMP_DIR }}/unit-coverage-details.txt"
-        silent: true
-
-  integration:
-    desc: Run integration tests
-    cmds:
-      - "go test -v ./cmd/syft/internal/test/integration"
-      # exercise most of the CLI with the data race detector
-      # we use a larger image to ensure we're using multiple catalogers at a time
-      - "go run -race cmd/syft/main.go anchore/test_images:grype-quality-dotnet-69f15d2"
-
   validate-cyclonedx-schema:
     desc: Validate that Syft produces valid CycloneDX documents
     cmds:
       - "cd schema/cyclonedx && make"
 
-  cli:
-    desc: Run CLI tests
-    deps: [tools]
-    cmds:
-      - cmd: "echo 'testing binary: {{ .SNAPSHOT_BIN }}'"
-        silent: true
-      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found for {{ .SNAPSHOT_BIN }}' && false)"
-        silent: true
-
-      - "go test -count=1 -timeout=15m -v ./test/cli"
-    env:
-      SYFT_BINARY_LOCATION: "{{ .SNAPSHOT_BIN }}"
-
   test-utils:
     desc: Run tests for pipeline utils
     cmds:
       - cmd: .github/scripts/labeler_test.py
+      - cmd: go test -C .make ./...
 
+  snapshot-smoke-test:
+    desc: Run a smoke test on the snapshot builds + docker images
+    cmds:
+      - cmd: "echo 'testing snapshot binary: {{ .SNAPSHOT_BIN }}'"
+        silent: true
+      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found for {{ .SNAPSHOT_BIN }}' && false)"
+        silent: true
+      - "{{ .SNAPSHOT_BIN }} version"
+      - "{{ .SNAPSHOT_BIN }} scan alpine:latest"
+      - docker run --pull=never --rm anchore/syft:latest-{{ .DOCKER_ARCH }} version
+      - docker run --pull=never --rm anchore/syft:latest-{{ .DOCKER_ARCH }} scan alpine:latest
 
-  ## Test-fixture-related targets #################################
+  ## Test-fixture-related targets ###########################################
 
   fingerprints:
-    desc: Generate fingerprints for all non-docker test fixture
+    desc: Generate fingerprints for all non-docker test fixtures
     silent: true
-    # this will look for `test-fixtures/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
+    deps: [tmpdir]
+    # this will look for `testdata/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
     generates:
-      - '**/test-fixtures/**/*.fingerprint'
+      - '**/testdata/**/*.fingerprint'
       - test/install/cache.fingerprint
     cmds:
       - |
@@ -266,18 +156,12 @@ tasks:
         RESET='\033[0m'
 
         echo -e "${YELLOW}creating fingerprint files for non-docker fixtures...${RESET}"
-        for dir in $(find . -type d -name 'test-fixtures'); do
+        for dir in $(find . -type d -name 'testdata'); do
           if [ -f "$dir/Makefile" ]; then
-            # for debugging...
-            #echo -e "${YELLOW}• calculating fingerprints in $dir... ${RESET}"
-
             (make -C "$dir" fingerprint)
           fi
         done
 
-        # for debugging...
-        # echo -e "generated all fixture fingerprints"
-
       - .github/scripts/fingerprint_docker_fixtures.py
       - |
         # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then we don't need to calculate the fingerprint for the cache
@@ -359,18 +243,21 @@ tasks:
   build-fixtures:
     desc: Generate all non-docker test fixtures
     silent: true
-    # this will look for `test-fixtures/Makefile` and invoke the `fixtures` target to generate any and all test fixtures
+    # this will look for `testdata/Makefile` and invoke the `fixtures` target to generate any and all test fixtures
     cmds:
       - |
+        # we want to stop on the first build error
+        set -e
+
         BOLD='\033[1m'
         YELLOW='\033[0;33m'
         RESET='\033[0m'
 
         # Use a for loop with command substitution to avoid subshell issues
-        for dir in $(find . -type d -name 'test-fixtures'); do
+        for dir in $(find . -type d -name 'testdata'); do
           if [ -f "$dir/Makefile" ]; then
             echo -e "${YELLOW}${BOLD}generating fixtures in $dir${RESET}"
-            (make -C "$dir" fixtures)
+            make -C "$dir" fixtures
           fi
         done
         echo -e "${BOLD}generated all fixtures${RESET}"
@@ -409,19 +296,20 @@ tasks:
       done
       oras_command+=" {{ .CACHE_PATHS_FILE }}"
 
-      oras_command+=" --annotation org.opencontainers.image.source=https://github.com/{{ .OWNER }}/{{ .PROJECT }}"
+      oras_command+=" --annotation org.opencontainers.image.source=https://github.com/{{ .OWNER }}/{{ .CACHE_REPO }}"
       oras_command+=" --annotation fingerprint=$(cat {{ .CACHE_PATHS_FILE }} | {{ .YQ }} -r '.digest')"
 
       echo "Executing: $oras_command"
       eval $oras_command
 
   show-test-image-cache:
+    desc: Print the on-disk + docker daemon state of the stereoscope fixture image cache
     silent: true
     cmds:
       - "echo 'Docker daemon cache:'"
       - "docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}:{{`{{.Tag}}`}}' | grep stereoscope-fixture- | sort"
       - "echo '\nTar cache:'"
-      - 'find . -type f -wholename "**/test-fixtures/cache/stereoscope-fixture-*.tar" | sort'
+      - 'find . -type f -wholename "**/testdata/cache/stereoscope-fixture-*.tar" | sort'
 
   check-docker-cache:
     desc: Ensure docker caches aren't using too much disk space
@@ -436,28 +324,36 @@ tasks:
         exit 1
       fi
 
-  ## install.sh testing targets #################################
+  ## install.sh testing targets #############################################
 
   install-test:
+    desc: Run install.sh test suite (delegates to test/install/Makefile)
     cmds:
       - "cd test/install && make"
 
   install-test-cache-save:
+    desc: Save the install.sh test image cache (delegates to test/install/Makefile)
     cmds:
       - "cd test/install && make save"
 
   install-test-cache-load:
+    desc: Load the install.sh test image cache (delegates to test/install/Makefile)
     cmds:
       - "cd test/install && make load"
 
   install-test-ci-mac:
+    desc: Run install.sh CI test suite on macOS (delegates to test/install/Makefile)
     cmds:
       - "cd test/install && make ci-test-mac"
 
+  ## Compare-test targets ###################################################
+
   generate-compare-file:
-    cmd: "go run ./cmd/syft {{ .COMPARE_TEST_IMAGE }} -o json > {{ .COMPARE_DIR }}/test-fixtures/acceptance-{{ .COMPARE_TEST_IMAGE }}.json"
+    desc: Generate the acceptance comparison reference JSON for the current compare image
+    cmd: "go run ./cmd/syft {{ .COMPARE_TEST_IMAGE }} -o json > {{ .COMPARE_DIR }}/testdata/acceptance-{{ .COMPARE_TEST_IMAGE }}.json"
 
   compare-mac:
+    desc: Run macOS install + acceptance comparison against the snapshot build
     deps: [tmpdir]
     cmd: |
       {{ .COMPARE_DIR }}/mac.sh \
@@ -467,11 +363,13 @@ tasks:
         {{ .TMP_DIR }}
 
   compare-linux:
+    desc: Run Linux install + acceptance comparison (deb + rpm) against the snapshot build
     cmds:
       - task: compare-test-deb-package-install
       - task: compare-test-rpm-package-install
 
   compare-test-deb-package-install:
+    desc: Run Linux .deb install + acceptance comparison against the snapshot build
     deps: [tmpdir]
     cmd: |
       {{ .COMPARE_DIR }}/deb.sh \
@@ -481,6 +379,7 @@ tasks:
         {{ .TMP_DIR }}
 
   compare-test-rpm-package-install:
+    desc: Run Linux .rpm install + acceptance comparison against the snapshot build
     deps: [tmpdir]
     cmd: |
       {{ .COMPARE_DIR }}/rpm.sh \
@@ -490,19 +389,20 @@ tasks:
         {{ .TMP_DIR }}
 
 
-  ## Code and data generation targets #################################
+  ## Code and data generation targets ######################################
 
   generate:
     desc: Add data generation tasks
     cmds:
       - task: generate-json-schema
+      - task: generate-capabilities
       - task: generate-license-list
       - task: generate-cpe-dictionary-index
 
   generate-json-schema:
     desc: Generate a new JSON schema
     cmds:
-      - "cd syft/internal && go generate . && cd jsonschema && go run . && go fmt ../..."
+      - "cd ./internal && go generate . && cd ./jsonschema && go run . && go fmt ../..."
 
   generate-license-list:
     desc: Generate an updated license processing code off of the latest available SPDX license list
@@ -511,101 +411,35 @@ tasks:
       - "gofmt -s -w ./internal/spdxlicense"
 
   generate-cpe-dictionary-index:
-    desc: Generate the CPE index based off of the latest available CPE dictionary
-    dir: "syft/pkg/cataloger/internal/cpegenerate/dictionary"
+    desc: Generate the CPE index from local cache
     cmds:
-      - "go generate"
+      - task: generate:cpe-index:cache:pull
+      - task: generate:cpe-index:cache:update
+      - task: generate:cpe-index:build
 
-
-  ## Build-related targets #################################
-
-  build:
-    desc: Build the project
-    deps: [tools, tmpdir]
-    generates:
-      - "{{ .PROJECT }}"
+  generate-capabilities:
+    desc: Generate the capabilities data file
+    deps:
+      - tmpdir
+      - fixtures
+    vars:
+      # set REFRESH=true to run package tests first and refresh test observations (default: true)
+      REFRESH: '{{ .REFRESH | default "true" }}'
     cmds:
-      - silent: true
-        cmd: |
-          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
-          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
-
-      - "{{ .BUILD_CMD }}"
-
-  snapshot:
-    desc: Create a snapshot release
-    aliases:
-      - build
-    deps: [tools, tmpdir]
-    sources:
-      - cmd/**/*.go
-      - syft/**/*.go
-      - internal/**/*.go
-    method: checksum
-    generates:
-      - "{{ .SNAPSHOT_BIN }}"
-    cmds:
-      - silent: true
-        cmd: |
-          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
-          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
-
-      - "{{ .SNAPSHOT_CMD }}"
-
-  snapshot-smoke-test:
-    desc: Run a smoke test on the snapshot builds + docker images
-    cmds:
-      - cmd: "echo 'testing snapshot binary: {{ .SNAPSHOT_BIN }}'"
-        silent: true
-      - cmd: "test -f {{ .SNAPSHOT_BIN }} || (find {{ .SNAPSHOT_DIR }} && echo '\nno snapshot found for {{ .SNAPSHOT_BIN }}' && false)"
-        silent: true
-      - "{{ .SNAPSHOT_BIN }} version"
-      - "{{ .SNAPSHOT_BIN }} scan alpine:latest"
-      - docker run --rm anchore/syft:latest version
-      - docker run --rm anchore/syft:latest scan alpine:latest
-
-  changelog:
-    desc: Generate a changelog
-    deps: [tools]
-    generates:
-      - "{{ .CHANGELOG }}"
-      - "{{ .NEXT_VERSION }}"
-    cmds:
-      - "{{ .TOOL_DIR }}/chronicle -vv -n --version-file {{ .NEXT_VERSION }} > {{ .CHANGELOG }}"
-      - "{{ .TOOL_DIR }}/glow -w 0 {{ .CHANGELOG }}"
+      # remove all test observations prior to regenerating
+      - task: clean-test-observations
+        if: '{{ eq .REFRESH "true" }}'
+      # this is required to update test observations; such evidence is used to update the packages/*.yaml
+      - cmd: "go test ./syft/pkg/... -count=1"
+        if: '{{ eq .REFRESH "true" }}'
+      - "go generate ./internal/capabilities/..."
+      - "gofmt -s -w ./internal/capabilities"
+      # now that we have the latest capabilities, run completeness tests to ensure this is self-consistent
+      # note: -p 1 forces sequential package execution to avoid race between generate (writes) and internal (reads)
+      - "SYFT_ENABLE_COMPLETENESS_TESTS=true go test -p 1 ./internal/capabilities/... -count=1"
 
 
-  ## Release targets #################################
-
-  release:
-    desc: Create a release
-    interactive: true
-    deps: [tools]
-    cmds:
-      - cmd: .github/scripts/trigger-release.sh
-        silent: true
-
-
-  ## CI-only targets #################################
-
-  ci-check:
-    # desc: "[CI only] Are you in CI?"
-    cmds:
-      - cmd: .github/scripts/ci-check.sh
-        silent: true
-
-  ci-release:
-    # desc: "[CI only] Create a release"
-    deps: [tools]
-    cmds:
-      - task: ci-check
-      - "{{ .TOOL_DIR }}/chronicle -vvv > CHANGELOG.md"
-      - cmd: "cat CHANGELOG.md"
-        silent: true
-      - "{{ .RELEASE_CMD }}"
-
-
-  ## Cleanup targets #################################
+  ## Cleanup targets ########################################################
 
   clean-snapshot:
     desc: Remove any snapshot builds
@@ -616,7 +450,7 @@ tasks:
   clean-docker-cache:
     desc: Remove all docker cache tars and images from the daemon
     cmds:
-      - find . -type d -wholename "**/test-fixtures/cache" | xargs rm -rf
+      - find . -type d -wholename "**/testdata/cache" | xargs rm -rf
       - docker images --format '{{`{{.ID}}`}} {{`{{.Repository}}`}}' | grep stereoscope-fixture- | awk '{print $1}' | uniq | xargs -r docker rmi --force
 
   clean-oras-cache:
@@ -627,13 +461,14 @@ tasks:
     desc: Remove all image docker tar cache, images from the docker daemon, and ephemeral test fixtures
     cmds:
       - task: clean-docker-cache
+      - task: prune-orphan-fingerprints
       - |
         BOLD='\033[1m'
         YELLOW='\033[0;33m'
         RESET='\033[0m'
 
         # Use a for loop with command substitution to avoid subshell issues
-        for dir in $(find . -type d -name 'test-fixtures'); do
+        for dir in $(find . -type d -name 'testdata'); do
         if [ -f "$dir/Makefile" ]; then
           echo -e "${YELLOW}${BOLD}deleting ephemeral test fixtures in $dir${RESET}"
           (make -C "$dir" clean)
@@ -641,3 +476,14 @@ tasks:
         done
         echo -e "${BOLD}Deleted all ephemeral test fixtures${RESET}"
       - rm -f {{ .LAST_CACHE_PULL_FILE }} {{ .CACHE_PATHS_FILE }}
+
+  prune-orphan-fingerprints:
+    desc: Remove *.fingerprint files left behind by moved/deleted catalogers
+    silent: true
+    cmds:
+      - .github/scripts/prune_orphan_fingerprints.py
+
+  clean-test-observations:
+    desc: Remove all test observations (i.e. testdata/test-observations.json)
+    cmds:
+      - find . -type f -wholename "**/testdata/test-observations.json" | xargs rm -f

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

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

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

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

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

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

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

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

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

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

cmd/syft/cli/ui/handle_attestation.go

@@ -158,6 +158,11 @@ func (l *backgroundLineReader) read(reader io.Reader, stage *progress.Stage) {
 
 		l.lock.Unlock()
 	}
+	if err := s.Err(); err != nil {
+		log.WithFields("error", err).Debug("unable to read attestation output")
+		// keep draining so the writer never blocks on a full pipe
+		_, _ = io.Copy(io.Discard, reader)
+	}
 }
 
 func (l backgroundLineReader) Lines() []string {
@@ -219,7 +224,7 @@ func (l attestLogFrame) View() string {
 	sb := strings.Builder{}
 
 	for _, line := range l.lines {
-		sb.WriteString(fmt.Sprintf("     %s %s\n", l.borderStype.Render("░░"), line))
+		fmt.Fprintf(&sb, "     %s %s\n", l.borderStype.Render("░░"), line)
 	}
 
 	return sb.String()

cmd/syft/internal/clio_setup_config.go

@@ -49,7 +49,7 @@ func AppClioSetupConfig(id clio.Identification, out io.Writer) *clio.SetupConfig
 			},
 		).
 		WithPostRuns(func(_ *clio.State, _ error) {
-			stereoscope.Cleanup()
+			stereoscope.Cleanup() //nolint:staticcheck // we don't have access to the image object here
 		})
 	return clioCfg
 }

cmd/syft/internal/commands/attest.go

@@ -35,6 +35,7 @@ const (
 	attestSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp
 	attestHelp       = attestExample + attestSchemeHelp
 	cosignBinName    = "cosign"
+	jsonFormat       = "json"
 )
 
 type attestOptions struct {
@@ -58,7 +59,7 @@ func Attest(app clio.Application) *cobra.Command {
 		Use:   "attest --output [FORMAT] <IMAGE>",
 		Short: "Generate an SBOM as an attestation for the given [SOURCE] container image",
 		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from a container image as the predicate of an in-toto attestation that will be uploaded to the image registry",
-		Example: internal.Tprintf(attestHelp, map[string]interface{}{
+		Example: internal.Tprintf(attestHelp, map[string]any{
 			"appName": id.Name,
 			"command": "attest",
 		}),
@@ -93,9 +94,7 @@ func defaultAttestOutputOptions() options.Output {
 			string(spdxtagvalue.ID),
 		},
 		Outputs: []string{syftjson.ID.String()},
-		OutputFile: options.OutputFile{ //nolint:staticcheck
-			Enabled: false, // explicitly not allowed
-		},
+		// OutputFile is omitted (defaults to Enabled: false, explicitly not allowed for attestation)
 		Format: options.DefaultFormat(),
 	}
 }
@@ -240,7 +239,7 @@ func predicateType(outputName string) string {
 		return "cyclonedx"
 	case "spdx-tag-value", "spdx-tv":
 		return "spdx"
-	case "spdx-json", "json":
+	case "spdx-json", jsonFormat:
 		return "spdxjson"
 	default:
 		return "custom"
@@ -253,7 +252,6 @@ func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opt
 	}
 
 	src, err := getSource(ctx, opts, userInput, stereoscope.RegistryTag)
-
 	if err != nil {
 		return nil, err
 	}

cmd/syft/internal/commands/cataloger.go

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

cmd/syft/internal/commands/cataloger_info.go

@@ -0,0 +1,597 @@
+package commands
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"os"
+	"slices"
+	"sort"
+	"strings"
+
+	"github.com/charmbracelet/lipgloss"
+	"github.com/olekukonko/tablewriter"
+	"github.com/olekukonko/tablewriter/renderer"
+	"github.com/olekukonko/tablewriter/tw"
+	"github.com/scylladb/go-set/strset"
+	"github.com/spf13/cobra"
+
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/cmd/syft/internal/options"
+	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/capabilities"
+	"github.com/anchore/syft/internal/task"
+	"github.com/anchore/syft/syft/cataloging"
+	_ "github.com/anchore/syft/syft/pkg/cataloger" // register all cataloger capabilities, otherwise the info command will not function
+)
+
+var (
+	yesStyle       = lipgloss.NewStyle().Foreground(lipgloss.Color("10")) // hi green
+	noStyle        = lipgloss.NewStyle().Foreground(lipgloss.Color("8"))  // dark grey
+	criteriaWidth  = 60
+	criteriaMargin = 10
+)
+
+// types for JSON cataloger info output
+type (
+	configFieldInfo struct {
+		Key         string `json:"key"`
+		Description string `json:"description"`
+		AppKey      string `json:"app_key,omitempty"`
+	}
+
+	configInfo struct {
+		Type   string            `json:"type"`
+		Fields []configFieldInfo `json:"fields,omitempty"`
+	}
+
+	detectorPackageInfo struct {
+		Class string   `json:"class"`
+		Name  string   `json:"name"`
+		PURL  string   `json:"purl"`
+		CPEs  []string `json:"cpes"`
+		Type  string   `json:"type"`
+	}
+
+	patternInfo struct {
+		Method          string                           `json:"method"`
+		Criteria        []string                         `json:"criteria"`
+		Conditions      []capabilities.DetectorCondition `json:"conditions,omitempty"`
+		Packages        []detectorPackageInfo            `json:"packages,omitempty"`
+		Comment         string                           `json:"comment,omitempty"`
+		PackageTypes    []string                         `json:"package_types,omitempty"`
+		PURLTypes       []string                         `json:"purl_types,omitempty"`
+		JSONSchemaTypes []string                         `json:"json_schema_types,omitempty"`
+		Capabilities    capabilities.CapabilitySet       `json:"capabilities,omitempty"`
+	}
+
+	catalogerInfo struct {
+		Ecosystem    string                     `json:"ecosystem,omitempty"`
+		Name         string                     `json:"name"`
+		Type         string                     `json:"type"`
+		Selectors    []string                   `json:"selectors,omitempty"`
+		Deprecated   bool                       `json:"deprecated,omitempty"`
+		Patterns     []patternInfo              `json:"patterns,omitempty"`
+		Capabilities capabilities.CapabilitySet `json:"capabilities,omitempty"`
+		Config       *configInfo                `json:"config,omitempty"`
+	}
+)
+
+type catalogerInfoOptions struct {
+	Output                     string `yaml:"output" json:"output" mapstructure:"output"`
+	options.CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+	Names                      []string // cataloger names from args
+}
+
+func (o *catalogerInfoOptions) setNames(args []string) error {
+	o.Names = args
+
+	usingLegacyCatalogers := len(o.Catalogers) > 0
+	usingNewCatalogers := len(o.DefaultCatalogers) > 0 || len(o.SelectCatalogers) > 0
+	usingSelection := usingNewCatalogers || usingLegacyCatalogers
+
+	if usingSelection && len(o.Names) > 0 {
+		return fmt.Errorf("cannot use both cataloger name arguments and '--catalogers'/'--select-catalogers'/'--default-catalogers' flags")
+	}
+
+	if usingSelection {
+		// get all available package cataloger tasks
+		pkgTaskFactories := task.DefaultPackageTaskFactories()
+		allPkgTasks, err := pkgTaskFactories.Tasks(task.DefaultCatalogingFactoryConfig())
+		if err != nil {
+			return fmt.Errorf("unable to create pkg cataloger tasks: %w", err)
+		}
+
+		// make the selection based on user input
+		defaultCatalogers := options.FlattenAndSort(o.DefaultCatalogers)
+		selectCatalogers := options.FlattenAndSort(o.SelectCatalogers)
+		selectedTaskGroups, _, err := task.SelectInGroups(
+			[][]task.Task{allPkgTasks},
+			cataloging.NewSelectionRequest().
+				WithDefaults(defaultCatalogers...).
+				WithExpression(selectCatalogers...),
+		)
+
+		if err != nil {
+			return fmt.Errorf("unable to select catalogers: %w", err)
+		}
+
+		// build the list of cataloger names based on the selection
+		for _, g := range selectedTaskGroups {
+			for _, t := range g {
+				o.Names = append(o.Names, t.Name())
+			}
+		}
+	}
+	return nil
+}
+
+func (o *catalogerInfoOptions) AddFlags(flags clio.FlagSet) {
+	flags.StringVarP(&o.Output, "output", "o", "format to output the cataloger info (available: table, json)")
+}
+
+func defaultCatalogerCapsOptions() *catalogerInfoOptions {
+	return &catalogerInfoOptions{
+		CatalogerSelection: options.CatalogerSelection{
+			// this is different than the default behavior where a scan will automatically detect the default set
+			DefaultCatalogers: []string{"all"},
+		},
+	}
+}
+
+func CatalogerCaps(app clio.Application) *cobra.Command {
+	opts := defaultCatalogerCapsOptions()
+
+	return app.SetupCommand(&cobra.Command{
+		Use:     "info [OPTIONS] [CATALOGER_NAMES...]",
+		Short:   "Show detailed capabilities of catalogers",
+		Args:    cobra.ArbitraryArgs,
+		PreRunE: disableUI(app, os.Stdout),
+		RunE: func(_ *cobra.Command, args []string) error {
+			if err := opts.setNames(args); err != nil {
+				return err
+			}
+
+			return runCatalogerInfo(opts)
+		},
+	}, opts)
+}
+
+func runCatalogerInfo(opts *catalogerInfoOptions) error {
+	doc, err := capabilities.LoadDocument()
+	if err != nil {
+		return fmt.Errorf("unable to load cataloger capabilities: %w", err)
+	}
+
+	// filter by cataloger names if provided
+	catalogers := doc.Catalogers
+	if len(opts.Names) > 0 {
+		catalogers = filterCatalogersByName(catalogers, opts.Names)
+	}
+
+	report, err := catalogerInfoReport(opts, doc, catalogers)
+	if err != nil {
+		return fmt.Errorf("unable to generate cataloger info report: %w", err)
+	}
+
+	bus.Report(report)
+	bus.Notify("Note: the `cataloger info` command is experimental and may change or be removed without notice. Do not depend on its output in production systems.")
+
+	return nil
+}
+
+func filterCatalogersByName(catalogers []capabilities.CatalogerEntry, names []string) []capabilities.CatalogerEntry {
+	nameSet := make(map[string]bool)
+	for _, name := range names {
+		nameSet[name] = true
+	}
+
+	var filtered []capabilities.CatalogerEntry
+	for _, cat := range catalogers {
+		if nameSet[cat.Name] {
+			filtered = append(filtered, cat)
+		}
+	}
+	return filtered
+}
+
+func catalogerInfoReport(opts *catalogerInfoOptions, doc *capabilities.Document, catalogers []capabilities.CatalogerEntry) (string, error) {
+	switch opts.Output {
+	case jsonFormat:
+		return renderCatalogerInfoJSON(doc, catalogers)
+	case "table", "":
+		return renderCatalogerInfoTable(doc, catalogers), nil
+	default:
+		return "", fmt.Errorf("invalid output format %q, must be one of: table, json", opts.Output)
+	}
+}
+
+func renderCatalogerInfoJSON(doc *capabilities.Document, catalogers []capabilities.CatalogerEntry) (string, error) {
+	type document struct {
+		Catalogers []catalogerInfo `json:"catalogers"`
+	}
+
+	docOut := document{}
+
+	// sort catalogers by ecosystem then name
+	sort.Slice(catalogers, func(i, j int) bool {
+		if catalogers[i].Ecosystem != catalogers[j].Ecosystem {
+			return catalogers[i].Ecosystem < catalogers[j].Ecosystem
+		}
+		return catalogers[i].Name < catalogers[j].Name
+	})
+
+	for _, cat := range catalogers {
+		info := catalogerInfo{
+			Ecosystem:  cat.Ecosystem,
+			Name:       cat.Name,
+			Type:       cat.Type,
+			Selectors:  cat.Selectors,
+			Deprecated: isDeprecatedCataloger(cat.Selectors),
+		}
+
+		// convert parsers to patterns if available
+		info.Patterns = convertParsersToPatterns(cat.Parsers)
+
+		// if no parsers, use detectors instead
+		if len(info.Patterns) == 0 {
+			info.Capabilities = cat.Capabilities
+			info.Patterns = convertDetectorsToPatterns(cat.Detectors, cat.PackageTypes, cat.PURLTypes, cat.JSONSchemaTypes)
+		}
+
+		info.Config = getConfigInfoFromDocument(doc, cat.Config)
+
+		docOut.Catalogers = append(docOut.Catalogers, info)
+	}
+
+	by, err := json.Marshal(docOut)
+	return string(by), err
+}
+
+// isDeprecatedCataloger checks if a cataloger is deprecated based on its selectors
+func isDeprecatedCataloger(selectors []string) bool {
+	return slices.Contains(selectors, "deprecated")
+}
+
+// convertDetectorPackages converts detector package info to the JSON output format
+func convertDetectorPackages(pkgs []capabilities.DetectorPackageInfo) []detectorPackageInfo {
+	var result []detectorPackageInfo
+	for _, pkg := range pkgs {
+		result = append(result, detectorPackageInfo{
+			Class: pkg.Class,
+			Name:  pkg.Name,
+			PURL:  pkg.PURL,
+			CPEs:  pkg.CPEs,
+			Type:  pkg.Type,
+		})
+	}
+	return result
+}
+
+// convertParsersToPatterns converts parser entries to pattern info for JSON output
+func convertParsersToPatterns(parsers []capabilities.Parser) []patternInfo {
+	var patterns []patternInfo
+	for _, parser := range parsers {
+		patterns = append(patterns, patternInfo{
+			Method:          string(parser.Detector.Method),
+			Criteria:        parser.Detector.Criteria,
+			Conditions:      parser.Detector.Conditions,
+			Packages:        convertDetectorPackages(parser.Detector.Packages),
+			Comment:         parser.Detector.Comment,
+			PackageTypes:    parser.PackageTypes,
+			PURLTypes:       parser.PURLTypes,
+			JSONSchemaTypes: parser.JSONSchemaTypes,
+			Capabilities:    parser.Capabilities,
+		})
+	}
+	return patterns
+}
+
+// convertDetectorsToPatterns converts detector entries to pattern info for JSON output (for non-parser catalogers)
+func convertDetectorsToPatterns(detectors []capabilities.Detector, packageTypes, purlTypes, jsonSchemaTypes []string) []patternInfo {
+	var patterns []patternInfo
+	for _, det := range detectors {
+		patterns = append(patterns, patternInfo{
+			Method:          string(det.Method),
+			Criteria:        det.Criteria,
+			Conditions:      det.Conditions,
+			Packages:        convertDetectorPackages(det.Packages),
+			Comment:         det.Comment,
+			PackageTypes:    packageTypes,
+			PURLTypes:       purlTypes,
+			JSONSchemaTypes: jsonSchemaTypes,
+		})
+	}
+	return patterns
+}
+
+// getConfigInfoFromDocument retrieves config info from the capabilities document
+func getConfigInfoFromDocument(doc *capabilities.Document, configType string) *configInfo {
+	if configType == "" {
+		return nil
+	}
+	configEntry, ok := doc.Configs[configType]
+	if !ok {
+		return nil
+	}
+	cfg := &configInfo{
+		Type: configType,
+	}
+	for _, field := range configEntry.Fields {
+		cfg.Fields = append(cfg.Fields, configFieldInfo{
+			Key:         field.Key,
+			Description: field.Description,
+			AppKey:      field.AppKey,
+		})
+	}
+	return cfg
+}
+
+func renderCatalogerInfoTable(_ *capabilities.Document, catalogers []capabilities.CatalogerEntry) string {
+	if len(catalogers) == 0 {
+		return noStyle.Render("No catalogers found")
+	}
+
+	// sort catalogers by ecosystem then name
+	sort.Slice(catalogers, func(i, j int) bool {
+		if catalogers[i].Ecosystem != catalogers[j].Ecosystem {
+			return catalogers[i].Ecosystem < catalogers[j].Ecosystem
+		}
+		return catalogers[i].Name < catalogers[j].Name
+	})
+
+	var buf bytes.Buffer
+
+	// create table with hierarchical merging
+	table := tablewriter.NewTable(&buf,
+		tablewriter.WithRenderer(renderer.NewBlueprint(tw.Rendition{
+			Settings: tw.Settings{Separators: tw.Separators{BetweenRows: tw.On}},
+		})),
+		tablewriter.WithConfig(tablewriter.Config{
+			Row: tw.CellConfig{
+				Merging:   tw.CellMerging{Mode: tw.MergeHierarchical},
+				Alignment: tw.CellAlignment{Global: tw.AlignLeft},
+			},
+		}),
+	)
+
+	// set headers
+	table.Header("ECOSYSTEM", "CATALOGER", "CRITERIA", "PURL", "LICENSE", "NODES", "EDGES", "KINDS", "LISTING", "DIGESTS", "HASH")
+
+	// build rows for each cataloger
+	var data [][]string
+	for _, cat := range catalogers {
+		ecosystem := cat.Ecosystem
+		if ecosystem == "" {
+			ecosystem = "other"
+		}
+
+		if cat.Type == "generic" {
+			// generic catalogers: one row per parser
+			for _, parser := range cat.Parsers {
+				criteria := formatCriteria([]capabilities.Detector{parser.Detector})
+				row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, parser.PURLTypes, parser.Capabilities)
+				data = append(data, row)
+			}
+		} else {
+			// custom catalogers: one row with all detectors
+			criteria := formatCriteria(cat.Detectors)
+			row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, cat.PURLTypes, cat.Capabilities)
+			data = append(data, row)
+		}
+	}
+
+	// add all rows at once for better merging
+	_ = table.Bulk(data)
+	_ = table.Render()
+	return buf.String()
+}
+
+// buildTableRowFromCapabilities builds a table row from capability values
+func buildTableRowFromCapabilities(ecosystem, name, criteria string, purlTypes []string, caps capabilities.CapabilitySet) []string {
+	// extract capability default values
+	license := extractBoolCapability(caps, "license")
+	nodes := extractNodesCapability(caps)
+	edges := extractStringCapability(caps, "dependency.edges")
+	kinds := extractArrayCapability(caps, "dependency.kinds")
+	listing := extractBoolCapability(caps, "package_manager.files.listing")
+	digests := extractBoolCapability(caps, "package_manager.files.digests")
+	hash := extractBoolCapability(caps, "package_manager.package_integrity_hash")
+
+	return []string{
+		ecosystem,
+		name,
+		criteria,
+		formatPURLTypes(purlTypes),
+		license,
+		nodes,
+		edges,
+		kinds,
+		listing,
+		digests,
+		hash,
+	}
+}
+
+// formatPURLTypes renders the PURL types as a comma-separated list, or a placeholder when empty
+func formatPURLTypes(purlTypes []string) string {
+	if len(purlTypes) == 0 {
+		return noStyle.Render("·")
+	}
+	return strings.Join(purlTypes, ", ")
+}
+
+// extractBoolCapability extracts a boolean capability value and formats it
+func extractBoolCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			if b, ok := cap.Default.(bool); ok {
+				if b {
+					return yesStyle.Render("✔")
+				}
+				return noStyle.Render("·")
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractStringCapability extracts a string capability value
+func extractStringCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			if s, ok := cap.Default.(string); ok && s != "" {
+				return s
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractArrayCapability extracts an array capability value and formats it as comma-separated
+func extractArrayCapability(caps capabilities.CapabilitySet, name string) string {
+	for _, cap := range caps {
+		if cap.Name == name {
+			// handle various array types
+			switch v := cap.Default.(type) {
+			case []string:
+				if len(v) > 0 {
+					return strings.Join(v, ", ")
+				}
+			case []any:
+				if len(v) > 0 {
+					strs := make([]string, 0, len(v))
+					for _, item := range v {
+						strs = append(strs, fmt.Sprintf("%v", item))
+					}
+					return strings.Join(strs, ", ")
+				}
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// extractNodesCapability extracts dependency.depth and formats it
+// maps ["direct", "indirect"] to "transitive"
+func extractNodesCapability(caps capabilities.CapabilitySet) string {
+	for _, cap := range caps {
+		if cap.Name == "dependency.depth" {
+			switch v := cap.Default.(type) {
+			case []string:
+				return formatDepthStringArray(v)
+			case []any:
+				return formatDepthInterfaceArray(v)
+			}
+			return noStyle.Render("·")
+		}
+	}
+	return noStyle.Render("·")
+}
+
+// formatDepthStringArray formats a []string dependency depth value
+func formatDepthStringArray(v []string) string {
+	if len(v) == 0 {
+		return noStyle.Render("·")
+	}
+	if hasBothDirectAndIndirect(v) {
+		return "transitive"
+	}
+	return strings.Join(v, ", ")
+}
+
+// formatDepthInterfaceArray formats a []interface{} dependency depth value
+func formatDepthInterfaceArray(v []any) string {
+	if len(v) == 0 {
+		return noStyle.Render("·")
+	}
+	strs := make([]string, 0, len(v))
+	for _, item := range v {
+		strs = append(strs, fmt.Sprintf("%v", item))
+	}
+	if hasBothDirectAndIndirect(strs) {
+		return "transitive"
+	}
+	return strings.Join(strs, ", ")
+}
+
+// hasBothDirectAndIndirect checks if a slice contains both "direct" and "indirect" strings
+func hasBothDirectAndIndirect(items []string) bool {
+	hasDirect := false
+	hasIndirect := false
+	for _, item := range items {
+		if item == "direct" {
+			hasDirect = true
+		}
+		if item == "indirect" {
+			hasIndirect = true
+		}
+	}
+	return hasDirect && hasIndirect
+}
+
+func formatCriteria(detectors []capabilities.Detector) string {
+	var allCriteria []string
+	methods := strset.New()
+
+	for _, det := range detectors {
+		allCriteria = append(allCriteria, det.Criteria...)
+		methods.Add(string(det.Method))
+	}
+
+	// smart word wrapping: wrap by word (criterion) up to criteriaWidth,
+	// allow up to criteriaWidth+criteriaMargin before forcing a new line
+	var lines []string
+	var currentLine []string
+	currentLength := 0
+
+	for _, criterion := range allCriteria {
+		// calculate length including the criterion plus ", " separator (except for first item)
+		itemLength := len(criterion)
+		if len(currentLine) > 0 {
+			itemLength += 2 // for ", "
+		}
+
+		newLength := currentLength + itemLength
+
+		if len(currentLine) > 0 && newLength > criteriaWidth {
+			// check if it's within margin
+			if newLength <= criteriaWidth+criteriaMargin {
+				// close enough, add it anyway
+				currentLine = append(currentLine, criterion)
+				currentLength = newLength
+			} else {
+				// too long, finalize current line and start new one
+				lines = append(lines, strings.Join(currentLine, ", "))
+				currentLine = []string{criterion}
+				currentLength = len(criterion)
+			}
+		} else {
+			// fits within width or first item
+			currentLine = append(currentLine, criterion)
+			currentLength = newLength
+		}
+	}
+
+	// add final line
+	if len(currentLine) > 0 {
+		lines = append(lines, strings.Join(currentLine, ", "))
+	}
+
+	methodsList := methods.List()
+	sort.Strings(methodsList)
+	method := strings.Join(methodsList, ", ")
+
+	if len(lines) == 0 {
+		return ""
+	}
+
+	joined := strings.Join(lines, "\n")
+	if method != string(capabilities.GlobDetection) {
+		return fmt.Sprintf("%s (%s)", joined, method)
+	}
+	return joined
+}

cmd/syft/internal/commands/cataloger_info_test.go

@@ -0,0 +1,381 @@
+package commands
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/internal/capabilities"
+)
+
+func Test_isDeprecatedCataloger(t *testing.T) {
+	tests := []struct {
+		name      string
+		selectors []string
+		want      bool
+	}{
+		{
+			name:      "empty selectors",
+			selectors: nil,
+			want:      false,
+		},
+		{
+			name:      "no deprecated selector",
+			selectors: []string{"python", "pip", "package"},
+			want:      false,
+		},
+		{
+			name:      "has deprecated selector",
+			selectors: []string{"python", "deprecated", "package"},
+			want:      true,
+		},
+		{
+			name:      "only deprecated selector",
+			selectors: []string{"deprecated"},
+			want:      true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := isDeprecatedCataloger(tt.selectors)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func Test_hasBothDirectAndIndirect(t *testing.T) {
+	tests := []struct {
+		name  string
+		items []string
+		want  bool
+	}{
+		{
+			name:  "empty slice",
+			items: nil,
+			want:  false,
+		},
+		{
+			name:  "only direct",
+			items: []string{"direct"},
+			want:  false,
+		},
+		{
+			name:  "only indirect",
+			items: []string{"indirect"},
+			want:  false,
+		},
+		{
+			name:  "both direct and indirect",
+			items: []string{"direct", "indirect"},
+			want:  true,
+		},
+		{
+			name:  "both with other items",
+			items: []string{"other", "direct", "more", "indirect", "stuff"},
+			want:  true,
+		},
+		{
+			name:  "unrelated items",
+			items: []string{"foo", "bar", "baz"},
+			want:  false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := hasBothDirectAndIndirect(tt.items)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func Test_filterCatalogersByName(t *testing.T) {
+	catalogers := []capabilities.CatalogerEntry{
+		{Name: "python-cataloger", Ecosystem: "python"},
+		{Name: "java-cataloger", Ecosystem: "java"},
+		{Name: "go-cataloger", Ecosystem: "golang"},
+		{Name: "npm-cataloger", Ecosystem: "javascript"},
+	}
+
+	tests := []struct {
+		name       string
+		catalogers []capabilities.CatalogerEntry
+		names      []string
+		want       []capabilities.CatalogerEntry
+	}{
+		{
+			name:       "empty names returns empty",
+			catalogers: catalogers,
+			names:      nil,
+			want:       nil,
+		},
+		{
+			name:       "single match",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+			},
+		},
+		{
+			name:       "multiple matches",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger", "java-cataloger"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+				{Name: "java-cataloger", Ecosystem: "java"},
+			},
+		},
+		{
+			name:       "no matches",
+			catalogers: catalogers,
+			names:      []string{"nonexistent"},
+			want:       nil,
+		},
+		{
+			name:       "partial matches",
+			catalogers: catalogers,
+			names:      []string{"python-cataloger", "nonexistent"},
+			want: []capabilities.CatalogerEntry{
+				{Name: "python-cataloger", Ecosystem: "python"},
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := filterCatalogersByName(tt.catalogers, tt.names)
+			if diff := cmp.Diff(tt.want, got); diff != "" {
+				t.Errorf("filterCatalogersByName() mismatch (-want +got):\n%s", diff)
+			}
+		})
+	}
+}
+
+func Test_formatCriteria(t *testing.T) {
+	tests := []struct {
+		name      string
+		detectors []capabilities.Detector
+		want      string
+	}{
+		{
+			name:      "empty detectors",
+			detectors: nil,
+			want:      "",
+		},
+		{
+			name: "single glob detector",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py"},
+				},
+			},
+			want: "**/*.py",
+		},
+		{
+			name: "multiple criteria single detector",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py", "**/*.pyc", "**/requirements.txt"},
+				},
+			},
+			want: "**/*.py, **/*.pyc, **/requirements.txt",
+		},
+		{
+			name: "path detection shows method",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.PathDetection,
+					Criteria: []string{"/usr/bin/python"},
+				},
+			},
+			want: "/usr/bin/python (path)",
+		},
+		{
+			name: "mimetype detection shows method",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.MIMETypeDetection,
+					Criteria: []string{"application/x-python"},
+				},
+			},
+			want: "application/x-python (mimetype)",
+		},
+		{
+			name: "multiple detectors combine criteria",
+			detectors: []capabilities.Detector{
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.py"},
+				},
+				{
+					Method:   capabilities.GlobDetection,
+					Criteria: []string{"**/*.pyc"},
+				},
+			},
+			want: "**/*.py, **/*.pyc",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := formatCriteria(tt.detectors)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func testDocument() *capabilities.Document {
+	return &capabilities.Document{
+		Configs: map[string]capabilities.CatalogerConfigEntry{
+			"test-config": {
+				Fields: []capabilities.CatalogerConfigFieldEntry{
+					{Key: "field1", Description: "test field"},
+				},
+			},
+		},
+	}
+}
+
+func Test_catalogerInfoReport(t *testing.T) {
+	tests := []struct {
+		name       string
+		opts       *catalogerInfoOptions
+		doc        *capabilities.Document
+		catalogers []capabilities.CatalogerEntry
+		wantErr    require.ErrorAssertionFunc
+		assertions func(t *testing.T, got string)
+	}{
+		{
+			name: "empty catalogers table",
+			opts: &catalogerInfoOptions{Output: "table"},
+			doc:  testDocument(),
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, "No catalogers found")
+			},
+		},
+		{
+			name: "empty catalogers json",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"catalogers":null`)
+			},
+		},
+		{
+			name: "single cataloger table output",
+			opts: &catalogerInfoOptions{Output: "table"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "test-cataloger",
+					Ecosystem: "test",
+					Type:      "custom",
+					Detectors: []capabilities.Detector{
+						{Method: capabilities.GlobDetection, Criteria: []string{"**/*.test"}},
+					},
+					PURLTypes: []string{"npm"},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, "test-cataloger")
+				assert.Contains(t, got, "ECOSYSTEM")
+				assert.Contains(t, got, "CATALOGER")
+				assert.Contains(t, got, "PURL")
+				assert.Contains(t, got, "npm")
+			},
+		},
+		{
+			name: "single cataloger json output",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "test-cataloger",
+					Ecosystem: "test",
+					Type:      "custom",
+					Selectors: []string{"test", "custom"},
+					Detectors: []capabilities.Detector{
+						{Method: capabilities.GlobDetection, Criteria: []string{"**/*.test"}},
+					},
+					PURLTypes: []string{"npm"},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"name":"test-cataloger"`)
+				assert.Contains(t, got, `"ecosystem":"test"`)
+				assert.Contains(t, got, `"type":"custom"`)
+				assert.Contains(t, got, `"purl_types":["npm"]`)
+			},
+		},
+		{
+			name: "deprecated cataloger json output",
+			opts: &catalogerInfoOptions{Output: "json"},
+			doc:  testDocument(),
+			catalogers: []capabilities.CatalogerEntry{
+				{
+					Name:      "old-cataloger",
+					Ecosystem: "legacy",
+					Type:      "custom",
+					Selectors: []string{"legacy", "deprecated"},
+				},
+			},
+			assertions: func(t *testing.T, got string) {
+				assert.Contains(t, got, `"deprecated":true`)
+			},
+		},
+		{
+			name:    "invalid output format",
+			opts:    &catalogerInfoOptions{Output: "invalid"},
+			doc:     testDocument(),
+			wantErr: require.Error,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = require.NoError
+			}
+
+			got, err := catalogerInfoReport(tt.opts, tt.doc, tt.catalogers)
+			tt.wantErr(t, err)
+
+			if err != nil {
+				return
+			}
+
+			if tt.assertions != nil {
+				tt.assertions(t, got)
+			}
+		})
+	}
+}
+
+func Test_formatCriteria_wordWrapping(t *testing.T) {
+	// test word wrapping behavior with long criteria lists
+	longCriteria := make([]string, 20)
+	for i := range longCriteria {
+		longCriteria[i] = "**/file" + strings.Repeat("x", 10)
+	}
+
+	detector := capabilities.Detector{
+		Method:   capabilities.GlobDetection,
+		Criteria: longCriteria,
+	}
+
+	got := formatCriteria([]capabilities.Detector{detector})
+
+	// should contain newlines for wrapping
+	assert.Contains(t, got, "\n")
+	// should contain all criteria (joined with ", " and possibly split across lines)
+	for _, c := range longCriteria {
+		assert.Contains(t, got, c)
+	}
+}

cmd/syft/internal/commands/cataloger_list.go

@@ -15,6 +15,7 @@ import (
 	"github.com/anchore/clio"
 	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/capabilities"
 	"github.com/anchore/syft/internal/task"
 	"github.com/anchore/syft/syft/cataloging"
 )
@@ -28,25 +29,23 @@ var (
 )
 
 type catalogerListOptions struct {
-	Output            string   `yaml:"output" json:"output" mapstructure:"output"`
-	DefaultCatalogers []string `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
-	SelectCatalogers  []string `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
-	ShowHidden        bool     `yaml:"show-hidden" json:"show-hidden" mapstructure:"show-hidden"`
+	Output                     string `yaml:"output" json:"output" mapstructure:"output"`
+	options.CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+	ShowHidden                 bool `yaml:"show-hidden" json:"show-hidden" mapstructure:"show-hidden"`
 }
 
 func (o *catalogerListOptions) AddFlags(flags clio.FlagSet) {
 	flags.StringVarP(&o.Output, "output", "o", "format to output the cataloger list (available: table, json)")
 
-	flags.StringArrayVarP(&o.DefaultCatalogers, "override-default-catalogers", "", "override the default catalogers with an expression")
-
-	flags.StringArrayVarP(&o.SelectCatalogers, "select-catalogers", "", "select catalogers with an expression")
-
 	flags.BoolVarP(&o.ShowHidden, "show-hidden", "s", "show catalogers that have been de-selected")
 }
 
 func defaultCatalogerListOptions() *catalogerListOptions {
 	return &catalogerListOptions{
-		DefaultCatalogers: []string{"all"},
+		CatalogerSelection: options.CatalogerSelection{
+			// this is different than the default behavior where a scan will automatically detect the default set
+			DefaultCatalogers: []string{"all"},
+		},
 	}
 }
 
@@ -87,8 +86,8 @@ func runCatalogerList(opts *catalogerListOptions) error {
 }
 
 func catalogerListReport(opts *catalogerListOptions, allTaskGroups [][]task.Task) (string, error) {
-	defaultCatalogers := options.Flatten(opts.DefaultCatalogers)
-	selectCatalogers := options.Flatten(opts.SelectCatalogers)
+	defaultCatalogers := options.FlattenAndSort(opts.DefaultCatalogers)
+	selectCatalogers := options.FlattenAndSort(opts.SelectCatalogers)
 	selectedTaskGroups, selectionEvidence, err := task.SelectInGroups(
 		allTaskGroups,
 		cataloging.NewSelectionRequest().
@@ -101,7 +100,7 @@ func catalogerListReport(opts *catalogerListOptions, allTaskGroups [][]task.Task
 	var report string
 
 	switch opts.Output {
-	case "json":
+	case jsonFormat:
 		report, err = renderCatalogerListJSON(flattenTaskGroups(selectedTaskGroups), selectionEvidence, defaultCatalogers, selectCatalogers)
 	case "table", "":
 		if opts.ShowHidden {
@@ -306,22 +305,14 @@ func formatToken(token string, selection *task.TokenSelection, included bool, de
 }
 
 func extractTaskInfo(tasks []task.Task) ([]string, map[string][]string) {
+	infos := capabilities.ExtractCatalogerInfo(tasks)
+
 	tagsByName := make(map[string][]string)
 	var names []string
 
-	for _, tsk := range tasks {
-		var tags []string
-		name := tsk.Name()
-
-		if s, ok := tsk.(task.Selector); ok {
-			set := strset.New(s.Selectors()...)
-			set.Remove(name)
-			tags = set.List()
-			sort.Strings(tags)
-		}
-
-		tagsByName[name] = tags
-		names = append(names, name)
+	for _, info := range infos {
+		tagsByName[info.Name] = info.Selectors
+		names = append(names, info.Name)
 	}
 
 	sort.Strings(names)

cmd/syft/internal/commands/convert.go

@@ -1,24 +1,34 @@
 package commands
 
 import (
+	"context"
 	"fmt"
 	"io"
 	"os"
+	"path/filepath"
+	"strings"
 
 	"github.com/spf13/cobra"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/go-homedir"
 	"github.com/anchore/syft/cmd/syft/internal/options"
 	"github.com/anchore/syft/cmd/syft/internal/ui"
 	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/bus"
 	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/spillbuf"
+	"github.com/anchore/syft/internal/tmpdir"
 	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/syftjson"
+	"github.com/anchore/syft/syft/sbom"
 )
 
 const (
 	convertExample = `  {{.appName}} {{.command}} img.syft.json -o spdx-json                      convert a syft SBOM to spdx-json, output goes to stdout
   {{.appName}} {{.command}} img.syft.json -o cyclonedx-json=img.cdx.json    convert a syft SBOM to CycloneDX, output is written to the file "img.cdx.json"
   {{.appName}} {{.command}} - -o spdx-json                                  convert an SBOM from STDIN to spdx-json
+  SYFT_CONVERT_PASSTHROUGH_EXACT_FORMAT=true {{.appName}} {{.command}} img.syft.json -o syft-json=out.syft.json    copy the input to "out.syft.json" unchanged if it is already syft-json at the current schema version
 `
 )
 
@@ -26,6 +36,7 @@ type ConvertOptions struct {
 	options.Config      `yaml:",inline" mapstructure:",squash"`
 	options.Output      `yaml:",inline" mapstructure:",squash"`
 	options.UpdateCheck `yaml:",inline" mapstructure:",squash"`
+	Convert             options.Convert `yaml:"convert" json:"convert" mapstructure:"convert"`
 }
 
 func Convert(app clio.Application) *cobra.Command {
@@ -34,23 +45,24 @@ func Convert(app clio.Application) *cobra.Command {
 	opts := &ConvertOptions{
 		UpdateCheck: options.DefaultUpdateCheck(),
 		Output:      options.DefaultOutput(),
+		Convert:     options.DefaultConvert(),
 	}
 
 	return app.SetupCommand(&cobra.Command{
 		Use:   "convert [SOURCE-SBOM] -o [FORMAT]",
 		Short: "Convert between SBOM formats",
 		Long:  "[Experimental] Convert SBOM files to, and from, SPDX, CycloneDX and Syft's format. For more info about data loss between formats see https://github.com/anchore/syft/wiki/format-conversion",
-		Example: internal.Tprintf(convertExample, map[string]interface{}{
+		Example: internal.Tprintf(convertExample, map[string]any{
 			"appName": id.Name,
 			"command": "convert",
 		}),
 		Args:    validateConvertArgs,
 		PreRunE: applicationUpdateCheck(id, &opts.UpdateCheck),
-		RunE: func(_ *cobra.Command, args []string) error {
+		RunE: func(cmd *cobra.Command, args []string) error {
 			restoreStdout := ui.CaptureStdoutToTraceLog()
 			defer restoreStdout()
 
-			return RunConvert(opts, args[0])
+			return RunConvert(cmd.Context(), opts, args[0])
 		},
 	}, opts)
 }
@@ -59,30 +71,63 @@ func validateConvertArgs(cmd *cobra.Command, args []string) error {
 	return validateArgs(cmd, args, "an SBOM argument is required")
 }
 
-func RunConvert(opts *ConvertOptions, userInput string) error {
+func RunConvert(ctx context.Context, opts *ConvertOptions, userInput string) error {
 	log.Warn("convert is an experimental feature, run `syft convert -h` for help")
 
-	writer, err := opts.SBOMWriter()
+	// a temp dir is only needed when STDIN is a pipe and has to be spilled to disk; it is created lazily on
+	// first use (under the user's TMPDIR), so a file input never touches it. Mirrors syft.CreateSBOM, which
+	// also honors a TempDir already attached to the context.
+	td := tmpdir.FromContext(ctx)
+	if td == nil {
+		_, td = tmpdir.Root(ctx, "syft-convert")
+		defer func() {
+			_ = td.Cleanup()
+		}()
+	}
+
+	reader, inputInfo, err := openConvertInput(userInput, td)
 	if err != nil {
 		return err
 	}
+	defer func() {
+		_ = reader.Close()
+	}()
 
-	var reader io.ReadSeekCloser
+	outputs := opts.Outputs
+	var unchanged []string
+	if opts.Convert.PassthroughExactFormat {
+		log.Warn("convert.passthrough-exact-format is enabled: syft-json input that already exactly matches a requested output format and schema version will be copied to that output unchanged (this does not apply to any other input format)")
 
-	if userInput == "-" {
-		// though os.Stdin is an os.File, it does not support seeking
-		// you will get errors such as "seek /dev/stdin: illegal seek".
-		// We need to buffer what we read.
-		reader = internal.NewBufferedSeeker(os.Stdin)
-	} else {
-		f, err := os.Open(userInput)
+		unchanged, outputs, err = partitionOutputsBySourceFormat(opts.Output, reader)
 		if err != nil {
-			return fmt.Errorf("failed to open SBOM file: %w", err)
+			return err
 		}
-		defer func() {
-			_ = f.Close()
-		}()
-		reader = f
+	}
+
+	// resolve (and validate) every output that needs converting before writing anything, so that
+	// a bad -o value fails the command without leaving partial results behind
+	var writer sbom.Writer
+	if len(outputs) > 0 {
+		outputOpts := opts.Output
+		outputOpts.Outputs = outputs
+		writer, err = outputOpts.SBOMWriter()
+		if err != nil {
+			return err
+		}
+	}
+
+	for _, output := range unchanged {
+		if err := writeUnchanged(output, opts.LegacyFile, inputInfo, reader); err != nil {
+			return err
+		}
+	}
+
+	if writer == nil {
+		return nil
+	}
+
+	if _, err := reader.Seek(0, io.SeekStart); err != nil {
+		return fmt.Errorf("unable to seek to start of SBOM: %w", err)
 	}
 
 	s, _, _, err := format.Decode(reader)
@@ -100,3 +145,171 @@ func RunConvert(opts *ConvertOptions, userInput string) error {
 
 	return nil
 }
+
+// openConvertInput opens the SBOM document at the given path, or STDIN when "-". The returned reader is seekable so
+// the document can be identified, copied, and decoded in turn without being loaded into memory. The returned
+// os.FileInfo describes the file the document is being read from, so that writing back over it can be recognized;
+// it is nil when the input is not a file (a pipe or a terminal on STDIN).
+func openConvertInput(userInput string, td *tmpdir.TempDir) (io.ReadSeekCloser, os.FileInfo, error) {
+	if userInput == "-" {
+		return openStdin(td)
+	}
+
+	f, err := os.Open(userInput)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to open SBOM file: %w", err)
+	}
+
+	info, err := f.Stat()
+	if err != nil {
+		// the document is readable, we just cannot recognize it as an output destination
+		log.WithFields("error", err, "path", userInput).Debug("unable to stat SBOM file")
+	}
+	return f, info, nil
+}
+
+// openStdin returns a seekable view of STDIN. When STDIN is a regular file (such as a shell redirect) it is read in
+// place. A pipe or terminal cannot seek (you will get errors such as "seek /dev/stdin: illegal seek"), so its
+// contents are drained into a spill buffer: a small head stays in memory and everything beyond it goes to a temp
+// file under td, so an arbitrarily large piped SBOM never has to be held in memory to be made seekable.
+func openStdin(td *tmpdir.TempDir) (io.ReadSeekCloser, os.FileInfo, error) {
+	if info, err := os.Stdin.Stat(); err == nil && info.Mode().IsRegular() {
+		if start, err := os.Stdin.Seek(0, io.SeekCurrent); err == nil {
+			// a redirect reads the file in place, so it is just as much an input file as a path argument is
+			return readSeekNopCloser{io.NewSectionReader(os.Stdin, start, info.Size()-start)}, info, nil
+		}
+	}
+
+	buf := spillbuf.New(td)
+	if _, err := io.Copy(io.NewOffsetWriter(buf, 0), os.Stdin); err != nil {
+		_ = buf.Close()
+		return nil, nil, fmt.Errorf("failed to read SBOM from STDIN: %w", err)
+	}
+
+	return &spilledReader{
+		SectionReader: io.NewSectionReader(buf, 0, buf.Size()),
+		buf:           buf,
+	}, nil, nil
+}
+
+type readSeekNopCloser struct {
+	io.ReadSeeker
+}
+
+func (readSeekNopCloser) Close() error {
+	return nil
+}
+
+// spilledReader is a seekable view over a spill buffer; closing it releases the buffer's memory and spill file.
+type spilledReader struct {
+	*io.SectionReader
+	buf *spillbuf.Buffer
+}
+
+func (r *spilledReader) Close() error {
+	return r.buf.Close()
+}
+
+// partitionOutputsBySourceFormat splits the requested outputs (in "<format>[@<version>][=<path>]" form) into those
+// that exactly match the format and schema version of a syft-json input document (which can be written out
+// unchanged) and those that still require conversion. Input in any other format is always converted. Outputs that
+// cannot be resolved to an encoder are left for the writer to report on.
+func partitionOutputsBySourceFormat(output options.Output, reader io.ReadSeeker) (unchanged []string, toConvert []string, err error) {
+	if _, err := reader.Seek(0, io.SeekStart); err != nil {
+		return nil, nil, fmt.Errorf("unable to seek to start of SBOM: %w", err)
+	}
+
+	id, version := format.Identify(reader)
+	if id == "" || version == "" {
+		// let decoding surface the appropriate error
+		return nil, output.Outputs, nil
+	}
+
+	if id != syftjson.ID {
+		log.WithFields("format", id, "version", version).Debug("input is not syft-json, passthrough does not apply")
+		return nil, output.Outputs, nil
+	}
+
+	encoders, err := output.Encoders()
+	if err != nil {
+		return nil, nil, err
+	}
+	collection := format.NewEncoderCollection(encoders...)
+
+	for _, out := range output.Outputs {
+		name, _, _ := strings.Cut(strings.TrimSpace(out), "=")
+		enc := collection.GetByString(name)
+		if enc != nil && enc.ID() == id && enc.Version() == version {
+			log.WithFields("format", id, "version", version, "output", out).Warn("input already exactly matches the requested output format and schema version, copying it unchanged instead of converting it")
+			unchanged = append(unchanged, out)
+			continue
+		}
+		toConvert = append(toConvert, out)
+	}
+
+	return unchanged, toConvert, nil
+}
+
+// writeUnchanged copies the SBOM document as-is to the destination described by the given "<format>[=<path>]"
+// output value, falling back to the (deprecated) --file path, and finally to the report bus (STDOUT). When the
+// destination is the input file itself there is nothing to do.
+func writeUnchanged(output string, defaultFile string, inputInfo os.FileInfo, reader io.ReadSeeker) error {
+	if _, err := reader.Seek(0, io.SeekStart); err != nil {
+		return fmt.Errorf("unable to seek to start of SBOM: %w", err)
+	}
+
+	_, path, _ := strings.Cut(strings.TrimSpace(output), "=")
+	if path == "" {
+		path = defaultFile
+	}
+
+	if path == "" {
+		// the report bus only carries strings, so STDOUT output must be materialized in memory
+		content, err := io.ReadAll(reader) //nolint:gocritic // the whole SBOM is the report; there is no meaningful bound
+		if err != nil {
+			return fmt.Errorf("unable to read SBOM: %w", err)
+		}
+		bus.Report(string(content))
+		return nil
+	}
+
+	expandedPath, err := homedir.Expand(path)
+	if err != nil {
+		log.Warnf("could not expand given writer output path=%q: %w", path, err)
+		expandedPath = path
+	}
+
+	if isSameFile(inputInfo, expandedPath) {
+		log.WithFields("path", expandedPath).Info("output is the input file, leaving it as-is")
+		return nil
+	}
+
+	if err := os.MkdirAll(filepath.Dir(expandedPath), 0755); err != nil {
+		return fmt.Errorf("unable to create report directory: %w", err)
+	}
+
+	f, err := os.OpenFile(expandedPath, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0644)
+	if err != nil {
+		return fmt.Errorf("unable to create report file: %w", err)
+	}
+
+	if _, err := io.Copy(f, reader); err != nil {
+		_ = f.Close()
+		return fmt.Errorf("unable to write report file: %w", err)
+	}
+
+	return f.Close()
+}
+
+// isSameFile reports whether the given path names the file the input is being read from. Comparing the input's
+// os.FileInfo rather than its path covers a shell redirect onto STDIN, which has no path to compare.
+func isSameFile(inputInfo os.FileInfo, path string) bool {
+	if inputInfo == nil {
+		return false
+	}
+	pathInfo, err := os.Stat(path)
+	if err != nil {
+		return false
+	}
+	return os.SameFile(inputInfo, pathInfo)
+}

cmd/syft/internal/commands/convert_test.go

@@ -0,0 +1,448 @@
+package commands
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"github.com/wagoodman/go-partybus"
+
+	"github.com/anchore/syft/cmd/syft/internal/options"
+	"github.com/anchore/syft/internal/bus"
+	"github.com/anchore/syft/internal/spillbuf"
+	"github.com/anchore/syft/syft/event"
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/format"
+	"github.com/anchore/syft/syft/format/cyclonedxjson"
+	"github.com/anchore/syft/syft/format/spdxjson"
+	"github.com/anchore/syft/syft/format/syftjson"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+	"github.com/anchore/syft/syft/source"
+)
+
+func convertTestSBOM() sbom.SBOM {
+	catalog := pkg.NewCollection()
+	catalog.Add(pkg.Package{
+		Name:    "musl-utils",
+		Version: "1.2.3-r4",
+		Type:    pkg.ApkPkg,
+		FoundBy: "apk-db-cataloger",
+		Locations: file.NewLocationSet(
+			file.NewLocation("/lib/apk/db/installed"),
+		),
+		PURL: "pkg:apk/alpine/musl-utils@1.2.3-r4",
+	})
+
+	return sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			Packages: catalog,
+		},
+		Source: source.Description{
+			ID:      "some-id",
+			Name:    "some-dir",
+			Version: "latest",
+			Metadata: source.DirectoryMetadata{
+				Path: "/some/path",
+			},
+		},
+		Descriptor: sbom.Descriptor{
+			Name:    "syft",
+			Version: "v0.0.0-test",
+		},
+	}
+}
+
+func mustConvertEncoder(enc sbom.FormatEncoder, err error) sbom.FormatEncoder {
+	if err != nil {
+		panic(err)
+	}
+	return enc
+}
+
+func encodeConvertTestSBOM(t *testing.T, enc sbom.FormatEncoder) []byte {
+	buf := &bytes.Buffer{}
+	require.NoError(t, enc.Encode(buf, convertTestSBOM()))
+	return buf.Bytes()
+}
+
+// prettySyftJSON returns the test SBOM as pretty-printed syft-json. Pretty input makes a verbatim copy
+// distinguishable from a re-encode, since re-encoding always produces compact output here.
+func prettySyftJSON(t *testing.T) []byte {
+	cfg := syftjson.DefaultEncoderConfig()
+	cfg.Pretty = true
+	return encodeConvertTestSBOM(t, mustConvertEncoder(syftjson.NewFormatEncoderWithConfig(cfg)))
+}
+
+func Test_partitionOutputsBySourceFormat(t *testing.T) {
+	syftEncoder := mustConvertEncoder(syftjson.NewFormatEncoderWithConfig(syftjson.DefaultEncoderConfig()))
+	syftVersion := syftEncoder.Version()
+	syftContent := encodeConvertTestSBOM(t, syftEncoder)
+
+	// the same document claiming an older schema version
+	olderSyftContent := bytes.ReplaceAll(syftContent, []byte(`"version":"`+syftVersion+`"`), []byte(`"version":"16.0.0"`))
+	require.NotEqual(t, syftContent, olderSyftContent)
+
+	cdxContent := encodeConvertTestSBOM(t, mustConvertEncoder(cyclonedxjson.NewFormatEncoderWithConfig(cyclonedxjson.DefaultEncoderConfig())))
+
+	tests := []struct {
+		name          string
+		content       []byte
+		outputs       []string
+		wantUnchanged []string
+		wantToConvert []string
+	}{
+		{
+			name:          "syft-json matches the bare format name",
+			content:       syftContent,
+			outputs:       []string{"syft-json"},
+			wantUnchanged: []string{"syft-json"},
+		},
+		{
+			name:          "syft-json matches its alias",
+			content:       syftContent,
+			outputs:       []string{"json"},
+			wantUnchanged: []string{"json"},
+		},
+		{
+			name:          "syft-json matches an explicit version and file path",
+			content:       syftContent,
+			outputs:       []string{"syft-json@" + syftVersion + "=out/some.syft.json"},
+			wantUnchanged: []string{"syft-json@" + syftVersion + "=out/some.syft.json"},
+		},
+		{
+			name:          "syft-json at an older schema version requires conversion",
+			content:       olderSyftContent,
+			outputs:       []string{"syft-json"},
+			wantToConvert: []string{"syft-json"},
+		},
+		{
+			name:          "a different output format requires conversion",
+			content:       syftContent,
+			outputs:       []string{"spdx-json"},
+			wantToConvert: []string{"spdx-json"},
+		},
+		{
+			name:          "mixed outputs are partitioned",
+			content:       syftContent,
+			outputs:       []string{"syft-json=a.json", "spdx-json=b.json", "cyclonedx-xml"},
+			wantUnchanged: []string{"syft-json=a.json"},
+			wantToConvert: []string{"spdx-json=b.json", "cyclonedx-xml"},
+		},
+		{
+			name:          "unknown format is left for the writer to report",
+			content:       syftContent,
+			outputs:       []string{"bogus"},
+			wantToConvert: []string{"bogus"},
+		},
+		{
+			name:          "non syft-json input is always converted, even when it matches the output",
+			content:       cdxContent,
+			outputs:       []string{"cyclonedx-json"},
+			wantToConvert: []string{"cyclonedx-json"},
+		},
+		{
+			name:          "unidentifiable content is left for the decoder to report",
+			content:       []byte("definitely not an sbom"),
+			outputs:       []string{"syft-json"},
+			wantToConvert: []string{"syft-json"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			output := options.DefaultOutput()
+			output.Outputs = tt.outputs
+
+			unchanged, toConvert, err := partitionOutputsBySourceFormat(output, bytes.NewReader(tt.content))
+			require.NoError(t, err)
+			assert.Equal(t, tt.wantUnchanged, unchanged)
+			assert.Equal(t, tt.wantToConvert, toConvert)
+		})
+	}
+}
+
+func Test_RunConvert_passthroughExactFormat(t *testing.T) {
+	syftContent := prettySyftJSON(t)
+
+	newOpts := func(passthrough bool, outputs ...string) *ConvertOptions {
+		opts := &ConvertOptions{
+			Output: options.DefaultOutput(),
+			Convert: options.Convert{
+				PassthroughExactFormat: passthrough,
+			},
+		}
+		opts.Outputs = outputs
+		return opts
+	}
+
+	writeInput := func(t *testing.T, content []byte) string {
+		input := filepath.Join(t.TempDir(), "input.json")
+		require.NoError(t, os.WriteFile(input, content, 0600))
+		return input
+	}
+
+	t.Run("matching output is copied unchanged while others are converted", func(t *testing.T) {
+		dir := t.TempDir()
+		syftOut := filepath.Join(dir, "out.syft.json")
+		spdxOut := filepath.Join(dir, "out.spdx.json")
+
+		opts := newOpts(true, "syft-json="+syftOut, "spdx-json="+spdxOut)
+		require.NoError(t, RunConvert(context.Background(), opts, writeInput(t, syftContent)))
+
+		got, err := os.ReadFile(syftOut)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+
+		spdx, err := os.ReadFile(spdxOut)
+		require.NoError(t, err)
+		id, _ := format.Identify(bytes.NewReader(spdx))
+		assert.Equal(t, spdxjson.ID, id)
+	})
+
+	t.Run("STDIN input is copied unchanged while others are converted", func(t *testing.T) {
+		dir := t.TempDir()
+		syftOut := filepath.Join(dir, "out.syft.json")
+		spdxOut := filepath.Join(dir, "out.spdx.json")
+
+		stdin, err := os.Open(writeInput(t, syftContent))
+		require.NoError(t, err)
+		defer stdin.Close()
+
+		originalStdin := os.Stdin
+		os.Stdin = stdin
+		t.Cleanup(func() { os.Stdin = originalStdin })
+
+		opts := newOpts(true, "syft-json="+syftOut, "spdx-json="+spdxOut)
+		require.NoError(t, RunConvert(context.Background(), opts, "-"))
+
+		got, err := os.ReadFile(syftOut)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+
+		spdx, err := os.ReadFile(spdxOut)
+		require.NoError(t, err)
+		id, _ := format.Identify(bytes.NewReader(spdx))
+		assert.Equal(t, spdxjson.ID, id)
+	})
+
+	t.Run("piped STDIN input is copied unchanged while others are converted", func(t *testing.T) {
+		dir := t.TempDir()
+		syftOut := filepath.Join(dir, "out.syft.json")
+		spdxOut := filepath.Join(dir, "out.spdx.json")
+
+		pipeReader, pipeWriter, err := os.Pipe()
+		require.NoError(t, err)
+		defer pipeReader.Close()
+		go func() {
+			defer pipeWriter.Close()
+			_, _ = pipeWriter.Write(syftContent)
+		}()
+
+		originalStdin := os.Stdin
+		os.Stdin = pipeReader
+		t.Cleanup(func() { os.Stdin = originalStdin })
+
+		opts := newOpts(true, "syft-json="+syftOut, "spdx-json="+spdxOut)
+		require.NoError(t, RunConvert(context.Background(), opts, "-"))
+
+		got, err := os.ReadFile(syftOut)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+
+		spdx, err := os.ReadFile(spdxOut)
+		require.NoError(t, err)
+		id, _ := format.Identify(bytes.NewReader(spdx))
+		assert.Equal(t, spdxjson.ID, id)
+	})
+
+	t.Run("without the option the matching output is re-encoded", func(t *testing.T) {
+		syftOut := filepath.Join(t.TempDir(), "out.syft.json")
+
+		opts := newOpts(false, "syft-json="+syftOut)
+		require.NoError(t, RunConvert(context.Background(), opts, writeInput(t, syftContent)))
+
+		got, err := os.ReadFile(syftOut)
+		require.NoError(t, err)
+		id, _ := format.Identify(bytes.NewReader(got))
+		assert.Equal(t, syftjson.ID, id)
+		// the input was pretty-printed and the encoder is not configured to be, so a re-encode cannot reproduce it
+		assert.NotEqual(t, syftContent, got)
+	})
+
+	t.Run("non syft-json input is re-encoded even when it matches the output", func(t *testing.T) {
+		cdxContent := encodeConvertTestSBOM(t, mustConvertEncoder(cyclonedxjson.NewFormatEncoderWithConfig(cyclonedxjson.DefaultEncoderConfig())))
+		cdxOut := filepath.Join(t.TempDir(), "out.cdx.json")
+
+		opts := newOpts(true, "cyclonedx-json="+cdxOut)
+		require.NoError(t, RunConvert(context.Background(), opts, writeInput(t, cdxContent)))
+
+		got, err := os.ReadFile(cdxOut)
+		require.NoError(t, err)
+		id, _ := format.Identify(bytes.NewReader(got))
+		assert.Equal(t, cyclonedxjson.ID, id)
+		// a fresh serial number is minted on every encode, so a round trip never reproduces the input
+		assert.NotEqual(t, cdxContent, got)
+	})
+
+	t.Run("the deprecated --file path is honored", func(t *testing.T) {
+		syftOut := filepath.Join(t.TempDir(), "out.syft.json")
+
+		opts := newOpts(true, "syft-json")
+		opts.LegacyFile = syftOut
+		require.NoError(t, RunConvert(context.Background(), opts, writeInput(t, syftContent)))
+
+		got, err := os.ReadFile(syftOut)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+	})
+
+	t.Run("writing over the input file leaves it intact", func(t *testing.T) {
+		input := writeInput(t, syftContent)
+
+		opts := newOpts(true, "syft-json="+input)
+		require.NoError(t, RunConvert(context.Background(), opts, input))
+
+		got, err := os.ReadFile(input)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+	})
+
+	t.Run("writing over a redirected STDIN input leaves it intact", func(t *testing.T) {
+		input := writeInput(t, syftContent)
+
+		stdin, err := os.Open(input)
+		require.NoError(t, err)
+		defer stdin.Close()
+
+		originalStdin := os.Stdin
+		os.Stdin = stdin
+		t.Cleanup(func() { os.Stdin = originalStdin })
+
+		opts := newOpts(true, "syft-json="+input)
+		require.NoError(t, RunConvert(context.Background(), opts, "-"))
+
+		got, err := os.ReadFile(input)
+		require.NoError(t, err)
+		assert.Equal(t, syftContent, got)
+	})
+
+	t.Run("an invalid output fails before anything is written", func(t *testing.T) {
+		syftOut := filepath.Join(t.TempDir(), "out.syft.json")
+
+		opts := newOpts(true, "syft-json="+syftOut, "bogus")
+		require.Error(t, RunConvert(context.Background(), opts, writeInput(t, syftContent)))
+
+		assert.NoFileExists(t, syftOut)
+	})
+
+	t.Run("a missing input file is reported", func(t *testing.T) {
+		syftOut := filepath.Join(t.TempDir(), "out.syft.json")
+
+		opts := newOpts(true, "syft-json="+syftOut)
+		err := RunConvert(context.Background(), opts, filepath.Join(t.TempDir(), "does-not-exist.json"))
+		require.ErrorContains(t, err, "failed to open SBOM file")
+
+		assert.NoFileExists(t, syftOut)
+	})
+
+	t.Run("unrecognized input is left to the decoder to reject", func(t *testing.T) {
+		syftOut := filepath.Join(t.TempDir(), "out.syft.json")
+
+		opts := newOpts(true, "syft-json="+syftOut)
+		err := RunConvert(context.Background(), opts, writeInput(t, []byte("definitely not an sbom")))
+		require.ErrorContains(t, err, "failed to decode SBOM")
+	})
+}
+
+// largeSyftJSON returns a pretty-printed syft-json document of at least minBytes, built from many small packages.
+func largeSyftJSON(t *testing.T, minBytes int64) []byte {
+	catalog := pkg.NewCollection()
+	for i := 0; i < int(minBytes/100); i++ {
+		catalog.Add(pkg.Package{
+			Name:    fmt.Sprintf("pkg-%d", i),
+			Version: "1.0.0",
+			Type:    pkg.ApkPkg,
+			PURL:    fmt.Sprintf("pkg:apk/alpine/pkg-%d@1.0.0", i),
+		})
+	}
+	s := convertTestSBOM()
+	s.Artifacts.Packages = catalog
+
+	cfg := syftjson.DefaultEncoderConfig()
+	cfg.Pretty = true
+	enc := mustConvertEncoder(syftjson.NewFormatEncoderWithConfig(cfg))
+
+	buf := &bytes.Buffer{}
+	require.NoError(t, enc.Encode(buf, s))
+	require.Greater(t, int64(buf.Len()), minBytes)
+	return buf.Bytes()
+}
+
+func Test_RunConvert_pipedInputLargerThanMemoryLimitSpillsToDisk(t *testing.T) {
+	// a piped document bigger than the spill buffer's in-memory tier is written to a temp file under TMPDIR;
+	// the conversion must identify, copy and clean up from there rather than holding the document in memory
+	dir := t.TempDir()
+	syftOut := filepath.Join(dir, "out.syft.json")
+	spillRoot := filepath.Join(dir, "spill")
+	require.NoError(t, os.Mkdir(spillRoot, 0o755))
+	t.Setenv("TMPDIR", spillRoot)
+
+	content := largeSyftJSON(t, 2*spillbuf.DefaultMemLimit)
+
+	pipeReader, pipeWriter, err := os.Pipe()
+	require.NoError(t, err)
+	defer pipeReader.Close()
+	go func() {
+		defer pipeWriter.Close()
+		_, _ = pipeWriter.Write(content)
+	}()
+
+	originalStdin := os.Stdin
+	os.Stdin = pipeReader
+	t.Cleanup(func() { os.Stdin = originalStdin })
+
+	opts := &ConvertOptions{
+		Output: options.DefaultOutput(),
+		Convert: options.Convert{
+			PassthroughExactFormat: true,
+		},
+	}
+	opts.Outputs = []string{"syft-json=" + syftOut}
+	require.NoError(t, RunConvert(context.Background(), opts, "-"))
+
+	got, err := os.ReadFile(syftOut)
+	require.NoError(t, err)
+	assert.Equal(t, content, got)
+
+	entries, err := os.ReadDir(spillRoot)
+	require.NoError(t, err)
+	assert.Empty(t, entries, "the spill directory must be removed once the conversion finishes")
+}
+
+func Test_writeUnchanged_stdout(t *testing.T) {
+	// with no output path the document is published on the report bus, which is how the CLI writes to STDOUT
+	b := partybus.NewBus()
+	subscription := b.Subscribe()
+	bus.Set(b)
+	t.Cleanup(func() {
+		bus.Set(nil)
+	})
+
+	content := []byte(`{"some":"document"}`)
+	require.NoError(t, writeUnchanged("syft-json", "", nil, bytes.NewReader(content)))
+
+	select {
+	case e := <-subscription.Events():
+		assert.Equal(t, event.CLIReport, e.Type)
+		assert.Equal(t, string(content), e.Value)
+	case <-time.After(time.Second):
+		t.Fatal("no report was published")
+	}
+}

cmd/syft/internal/commands/packages.go

@@ -18,7 +18,7 @@ func Packages(app clio.Application, scanCmd *cobra.Command) *cobra.Command {
 		Short: scanCmd.Short,
 		Long:  scanCmd.Long,
 		Args:  scanCmd.Args,
-		Example: internal.Tprintf(scanHelp, map[string]interface{}{
+		Example: internal.Tprintf(scanHelp, map[string]any{
 			"appName": id.Name,
 			"command": "packages",
 		}),

cmd/syft/internal/commands/packages_test.go

@@ -29,7 +29,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 		{
 			name: "single non-expression error is retained",
 			err:  errors.New("foo"),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				return assert.Equal(t, "foo", err.Error())
 			},
 			wantHelp: "",
@@ -42,7 +42,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 				err = multierror.Append(err, errors.New("bar"))
 				return err
 			}(),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				// note: this is the default formatting from the hashicorp multierror object
 				expected := `2 errors occurred:
 	* foo
@@ -64,7 +64,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 				err = multierror.Append(err, errors.New("last"))
 				return err
 			}(),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				expected := `5 errors occurred:
 	* foo
 	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
@@ -103,7 +103,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 
 				return fmt.Errorf("top: %w", fmt.Errorf("middle: %w", err))
 			}(),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				expected := `top: middle: 4 errors occurred:
 	* foo: bar: last
 	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
@@ -142,7 +142,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 				// note we wrap the top error in a chain
 				return fmt.Errorf("top: %w", fmt.Errorf("middle: %w", err))
 			}(),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				expected := `top: middle: 4 errors occurred:
 	* foo: bar: last
 	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)
@@ -178,7 +178,7 @@ func Test_filterExpressionErrors_expressionErrorsHelp(t *testing.T) {
 
 				return err
 			}(),
-			wantErr: func(t assert.TestingT, err error, i ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, i ...any) bool {
 				// note: the errors are removed and the help text shows the enriched error help
 				expected := `2 errors occurred:
 	* invalid expression: "foo": tags are not allowed with this operation (must use exact names)

cmd/syft/internal/commands/scan.go

@@ -7,10 +7,11 @@ import (
 	"os"
 	"reflect"
 	"strings"
+	"time"
 
 	"github.com/hashicorp/go-multierror"
 	"github.com/spf13/cobra"
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 
 	"github.com/anchore/clio"
 	"github.com/anchore/fangs"
@@ -59,7 +60,9 @@ const (
 	nonImageSchemeHelp = `    {{.appName}} {{.command}} dir:path/to/yourproject                  read directly from a path on disk (any directory)
     {{.appName}} {{.command}} file:path/to/yourproject/file            read directly from a path on disk (any single file)
 `
-	scanSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp + nonImageSchemeHelp
+	modelSchemeHelp = `    {{.appName}} {{.command}} oci-model-registry:ai/llama3.2           scan an OCI model artifact from a registry (e.g. Docker Hub AI models)
+`
+	scanSchemeHelp = "\n  " + schemeHelpHeader + "\n" + imageSchemeHelp + modelSchemeHelp + nonImageSchemeHelp
 
 	scanHelp = scanExample + scanSchemeHelp
 )
@@ -90,7 +93,7 @@ func Scan(app clio.Application) *cobra.Command {
 		Use:   "scan [SOURCE]",
 		Short: "Generate an SBOM",
 		Long:  "Generate a packaged-based Software Bill Of Materials (SBOM) from container images and filesystems",
-		Example: internal.Tprintf(scanHelp, map[string]interface{}{
+		Example: internal.Tprintf(scanHelp, map[string]any{
 			"appName": id.Name,
 			"command": "scan",
 		}),
@@ -169,6 +172,11 @@ func validateArgs(cmd *cobra.Command, args []string, err string) error {
 }
 
 func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, userInput string) error {
+	scanStart := time.Now()
+	defer func() {
+		log.Infof("scan completed in %s", time.Since(scanStart).Round(time.Millisecond))
+	}()
+
 	writer, err := opts.SBOMWriter()
 	if err != nil {
 		return err
@@ -185,7 +193,6 @@ func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, use
 	}
 
 	src, err := getSource(ctx, &opts.Catalog, userInput, sources...)
-
 	if err != nil {
 		return err
 	}

cmd/syft/internal/commands/scan_test.go

@@ -19,30 +19,30 @@ func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
 		},
 		{
 			name: "config file with no legacy options",
-			cfg:  "test-fixtures/scan-configs/no-legacy-options.yaml",
+			cfg:  "testdata/scan-configs/no-legacy-options.yaml",
 		},
 		{
 			name:    "config file with default image pull source legacy option",
-			cfg:     "test-fixtures/scan-configs/with-default-pull-source.yaml",
+			cfg:     "testdata/scan-configs/with-default-pull-source.yaml",
 			wantErr: assertErrorContains("source.image.default-pull-source"),
 		},
 		{
 			name:    "config file with exclude-binary-overlap-by-ownership legacy option",
-			cfg:     "test-fixtures/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
+			cfg:     "testdata/scan-configs/with-exclude-binary-overlap-by-ownership.yaml",
 			wantErr: assertErrorContains("package.exclude-binary-overlap-by-ownership"),
 		},
 		{
 			name:    "config file with file string legacy option",
-			cfg:     "test-fixtures/scan-configs/with-file-string.yaml",
+			cfg:     "testdata/scan-configs/with-file-string.yaml",
 			wantErr: assertErrorContains("outputs"),
 		},
 		{
 			name: "config file with file section",
-			cfg:  "test-fixtures/scan-configs/with-file-section.yaml",
+			cfg:  "testdata/scan-configs/with-file-section.yaml",
 		},
 		{
 			name:    "config file with base-path legacy option",
-			cfg:     "test-fixtures/scan-configs/with-base-path.yaml",
+			cfg:     "testdata/scan-configs/with-base-path.yaml",
 			wantErr: assertErrorContains("source.base-path"),
 		},
 	}
@@ -60,7 +60,7 @@ func Test_scanOptions_validateLegacyOptionsNotUsed(t *testing.T) {
 }
 
 func assertErrorContains(contains string) assert.ErrorAssertionFunc {
-	return func(t assert.TestingT, err error, i ...interface{}) bool {
+	return func(t assert.TestingT, err error, i ...any) bool {
 		return assert.ErrorContains(t, err, contains, i...)
 	}
 }

cmd/syft/internal/commands/update.go

@@ -107,7 +107,7 @@ func fetchLatestApplicationVersion(id clio.Identification) (*hashiVersion.Versio
 		return nil, fmt.Errorf("HTTP %d on fetching latest version: %s", resp.StatusCode, resp.Status)
 	}
 
-	versionBytes, err := io.ReadAll(resp.Body)
+	versionBytes, err := io.ReadAll(io.LimitReader(resp.Body, 500))
 	if err != nil {
 		return nil, fmt.Errorf("failed to read latest version: %w", err)
 	}

cmd/syft/internal/options/catalog.go

@@ -2,6 +2,7 @@ package options
 
 import (
 	"fmt"
+	"slices"
 	"sort"
 	"strings"
 
@@ -19,6 +20,7 @@ import (
 	"github.com/anchore/syft/syft/file/cataloger/executable"
 	"github.com/anchore/syft/syft/file/cataloger/filecontent"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
+	"github.com/anchore/syft/syft/pkg/cataloger/cpp"
 	"github.com/anchore/syft/syft/pkg/cataloger/dotnet"
 	"github.com/anchore/syft/syft/pkg/cataloger/golang"
 	"github.com/anchore/syft/syft/pkg/cataloger/java"
@@ -31,19 +33,19 @@ import (
 
 type Catalog struct {
 	// high-level cataloger configuration
-	Catalogers        []string            `yaml:"-" json:"catalogers" mapstructure:"catalogers"` // deprecated and not shown in yaml output
-	DefaultCatalogers []string            `yaml:"default-catalogers" json:"default-catalogers" mapstructure:"default-catalogers"`
-	SelectCatalogers  []string            `yaml:"select-catalogers" json:"select-catalogers" mapstructure:"select-catalogers"`
-	Package           packageConfig       `yaml:"package" json:"package" mapstructure:"package"`
-	License           licenseConfig       `yaml:"license" json:"license" mapstructure:"license"`
-	File              fileConfig          `yaml:"file" json:"file" mapstructure:"file"`
-	Scope             string              `yaml:"scope" json:"scope" mapstructure:"scope"`
-	Parallelism       int                 `yaml:"parallelism" json:"parallelism" mapstructure:"parallelism"` // the number of catalog workers to run in parallel
-	Relationships     relationshipsConfig `yaml:"relationships" json:"relationships" mapstructure:"relationships"`
-	Compliance        complianceConfig    `yaml:"compliance" json:"compliance" mapstructure:"compliance"`
-	Enrich            []string            `yaml:"enrich" json:"enrich" mapstructure:"enrich"`
+	CatalogerSelection `yaml:",inline" json:",inline" mapstructure:",squash"`
+
+	Package       packageConfig       `yaml:"package" json:"package" mapstructure:"package"`
+	License       licenseConfig       `yaml:"license" json:"license" mapstructure:"license"`
+	File          fileConfig          `yaml:"file" json:"file" mapstructure:"file"`
+	Scope         string              `yaml:"scope" json:"scope" mapstructure:"scope"`
+	Parallelism   int                 `yaml:"parallelism" json:"parallelism" mapstructure:"parallelism"` // the number of catalog workers to run in parallel
+	Relationships relationshipsConfig `yaml:"relationships" json:"relationships" mapstructure:"relationships"`
+	Compliance    complianceConfig    `yaml:"compliance" json:"compliance" mapstructure:"compliance"`
+	Enrich        []string            `yaml:"enrich" json:"enrich" mapstructure:"enrich"`
 
 	// ecosystem-specific cataloger configuration
+	Cpp         cppConfig         `yaml:"cpp" json:"cpp" mapstructure:"cpp"`
 	Dotnet      dotnetConfig      `yaml:"dotnet" json:"dotnet" mapstructure:"dotnet"`
 	Golang      golangConfig      `yaml:"golang" json:"golang" mapstructure:"golang"`
 	Java        javaConfig        `yaml:"java" json:"java" mapstructure:"java"`
@@ -77,7 +79,10 @@ func DefaultCatalog() Catalog {
 		Package:       defaultPackageConfig(),
 		License:       defaultLicenseConfig(),
 		LinuxKernel:   defaultLinuxKernelConfig(),
+		JavaScript:    defaultJavaScriptConfig(),
+		Python:        defaultPythonConfig(),
 		Nix:           defaultNixConfig(),
+		Cpp:           defaultCppConfig(),
 		Dotnet:        defaultDotnetConfig(),
 		Golang:        defaultGolangConfig(),
 		Java:          defaultJavaConfig(),
@@ -170,11 +175,15 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 	}
 	return pkgcataloging.Config{
 		Binary: binary.DefaultClassifierCatalogerConfig(),
+		Cpp: cpp.DefaultCatalogerConfig().
+			WithVcpkgAllowGitClone(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Cpp, task.Vcpkg), cfg.Cpp.VcpkgAllowGitClone)),
 		Dotnet: dotnet.DefaultCatalogerConfig().
 			WithDepPackagesMustHaveDLL(cfg.Dotnet.DepPackagesMustHaveDLL).
 			WithDepPackagesMustClaimDLL(cfg.Dotnet.DepPackagesMustClaimDLL).
 			WithPropagateDLLClaimsToParents(cfg.Dotnet.PropagateDLLClaimsToParents).
-			WithRelaxDLLClaimsWhenBundlingDetected(cfg.Dotnet.RelaxDLLClaimsWhenBundlingDetected),
+			WithRelaxDLLClaimsWhenBundlingDetected(cfg.Dotnet.RelaxDLLClaimsWhenBundlingDetected).
+			WithExcludeProjectReferences(cfg.Dotnet.ExcludeProjectReferences),
+
 		Golang: golang.DefaultCatalogerConfig().
 			WithSearchLocalModCacheLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.SearchLocalModCacheLicenses)).
 			WithLocalModCacheDir(cfg.Golang.LocalModCacheDir).
@@ -188,7 +197,10 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 					WithFromContents(cfg.Golang.MainModuleVersion.FromContents).
 					WithFromBuildSettings(cfg.Golang.MainModuleVersion.FromBuildSettings).
 					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
-			),
+			).
+			WithUsePackagesLib(*multiLevelOption(true, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.UsePackagesLib)).
+			WithCaptureSymbols(cfg.Golang.CaptureSymbols).
+			WithCaptureSymbolsModules(cfg.Golang.CaptureSymbolsModules),
 		JavaScript: javascript.DefaultCatalogerConfig().
 			WithIncludeDevDependencies(*multiLevelOption(false, cfg.JavaScript.IncludeDevDependencies)).
 			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.JavaScript, task.Node, task.NPM), cfg.JavaScript.SearchRemoteLicenses)).
@@ -198,9 +210,10 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 		},
 		Nix: nix.DefaultConfig().
 			WithCaptureOwnedFiles(cfg.Nix.CaptureOwnedFiles),
-		Python: python.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
+		Python: python.DefaultCatalogerConfig().
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.SearchRemoteLicenses)).
+			WithPypiBaseURL(cfg.Python.PypiBaseURL).
+			WithGuessUnpinnedRequirements(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.GuessUnpinnedRequirements)),
 		JavaArchive: java.DefaultArchiveCatalogerConfig().
 			WithUseMavenLocalRepository(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseMavenLocalRepository)).
 			WithMavenLocalRepositoryDir(cfg.Java.MavenLocalRepositoryDir).
@@ -228,26 +241,9 @@ func (cfg *Catalog) AddFlags(flags clio.FlagSet) {
 	flags.StringArrayVarP(&cfg.Exclusions, "exclude", "",
 		"exclude paths from being scanned using a glob expression")
 
-	flags.StringArrayVarP(&cfg.Catalogers, "catalogers", "",
-		"enable one or more package catalogers")
-
 	flags.IntVarP(&cfg.Parallelism, "parallelism", "",
 		"number of cataloger workers to run in parallel")
 
-	if pfp, ok := flags.(fangs.PFlagSetProvider); ok {
-		if err := pfp.PFlagSet().MarkDeprecated("catalogers", "use: override-default-catalogers and select-catalogers"); err != nil {
-			panic(err)
-		}
-	} else {
-		panic("unable to mark flags as deprecated")
-	}
-
-	flags.StringArrayVarP(&cfg.DefaultCatalogers, "override-default-catalogers", "",
-		"set the base set of catalogers to use (defaults to 'image' or 'directory' depending on the scan source)")
-
-	flags.StringArrayVarP(&cfg.SelectCatalogers, "select-catalogers", "",
-		"add, remove, and filter the catalogers to be used")
-
 	flags.StringArrayVarP(&cfg.Enrich, "enrich", "",
 		fmt.Sprintf("enable package data enrichment from local and online sources (options: %s)", strings.Join(publicisedEnrichmentOptions, ", ")))
 
@@ -274,22 +270,8 @@ Available options are: %s`, strings.Join(publicisedEnrichmentOptions, ", ")))
 }
 
 func (cfg *Catalog) PostLoad() error {
-	usingLegacyCatalogers := len(cfg.Catalogers) > 0
-	usingNewCatalogers := len(cfg.DefaultCatalogers) > 0 || len(cfg.SelectCatalogers) > 0
-
-	if usingLegacyCatalogers && usingNewCatalogers {
-		return fmt.Errorf("cannot use both 'catalogers' and 'select-catalogers'/'default-catalogers' flags")
-	}
-
 	cfg.From = Flatten(cfg.From)
-
-	cfg.Catalogers = Flatten(cfg.Catalogers)
-	cfg.DefaultCatalogers = Flatten(cfg.DefaultCatalogers)
-	cfg.SelectCatalogers = Flatten(cfg.SelectCatalogers)
-	cfg.Enrich = Flatten(cfg.Enrich)
-
-	// for backwards compatibility
-	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
+	cfg.Enrich = FlattenAndSort(cfg.Enrich)
 
 	s := source.ParseScope(cfg.Scope)
 	if s == source.UnknownScope {
@@ -311,6 +293,11 @@ func Flatten(commaSeparatedEntries []string) []string {
 			out = append(out, strings.TrimSpace(s))
 		}
 	}
+	return out
+}
+
+func FlattenAndSort(commaSeparatedEntries []string) []string {
+	out := Flatten(commaSeparatedEntries)
 	sort.Strings(out)
 	return out
 }
@@ -320,6 +307,8 @@ var publicisedEnrichmentOptions = []string{
 	task.Golang,
 	task.Java,
 	task.JavaScript,
+	task.Python,
+	task.Vcpkg,
 }
 
 func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {
@@ -335,10 +324,8 @@ func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {
 				directive = directive[1:]
 				enable = false
 			}
-			for _, feature := range features {
-				if directive == feature {
-					return &enable
-				}
+			if slices.Contains(features, directive) {
+				return &enable
 			}
 		}
 		return nil

cmd/syft/internal/options/catalog_test.go

@@ -8,55 +8,12 @@ import (
 )
 
 func TestCatalog_PostLoad(t *testing.T) {
-
 	tests := []struct {
 		name    string
 		options Catalog
 		assert  func(t *testing.T, options Catalog)
 		wantErr assert.ErrorAssertionFunc
 	}{
-		{
-			name: "mutually exclusive cataloger flags (cat / def-cat)",
-			options: Catalog{
-				Catalogers:        []string{"foo,bar", "42"},
-				DefaultCatalogers: []string{"some,thing"},
-				Scope:             "squashed",
-			},
-			wantErr: assert.Error,
-		},
-		{
-			name: "mutually exclusive cataloger flags (cat / sel-cat)",
-			options: Catalog{
-				Catalogers:       []string{"foo,bar", "42"},
-				SelectCatalogers: []string{"some,thing"},
-				Scope:            "squashed",
-			},
-			wantErr: assert.Error,
-		},
-		{
-			name: "allow old cataloger flags",
-			options: Catalog{
-				Catalogers: []string{"foo,bar"},
-				Scope:      "squashed",
-			},
-			assert: func(t *testing.T, options Catalog) {
-				assert.Equal(t, []string{"bar", "foo"}, options.DefaultCatalogers) // note: sorted order
-				assert.Equal(t, []string{"bar", "foo"}, options.Catalogers)        // note: sorted order
-			},
-		},
-		{
-			name: "allow new cataloger flags",
-			options: Catalog{
-				SelectCatalogers:  []string{"foo,bar", "42"},
-				DefaultCatalogers: []string{"some,thing"},
-				Scope:             "squashed",
-			},
-			assert: func(t *testing.T, options Catalog) {
-				assert.Equal(t, []string{"42", "bar", "foo"}, options.SelectCatalogers) // note: sorted order
-				assert.Equal(t, []string{"some", "thing"}, options.DefaultCatalogers)   // note: sorted order
-				assert.Empty(t, options.Catalogers)
-			},
-		},
 		{
 			name: "must have package overlap flag when pruning binaries by overlap",
 			options: Catalog{
@@ -79,6 +36,98 @@ func TestCatalog_PostLoad(t *testing.T) {
 	}
 }
 
+func TestFlatten(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "preserves order of comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "preserves order across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "trims whitespace",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "preserves reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"zebra", "yankee", "xray"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Flatten(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+func TestFlattenAndSort(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "sorts comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "sorts across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "trims whitespace and sorts",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "sorts reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"xray", "yankee", "zebra"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := FlattenAndSort(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
 func Test_enrichmentEnabled(t *testing.T) {
 	tests := []struct {
 		directives string
@@ -139,7 +188,7 @@ func Test_enrichmentEnabled(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.directives, func(t *testing.T) {
-			got := enrichmentEnabled(Flatten([]string{test.directives}), test.test)
+			got := enrichmentEnabled(FlattenAndSort([]string{test.directives}), test.test)
 			assert.Equal(t, test.expected, got)
 		})
 	}

cmd/syft/internal/options/cataloger_selection.go

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

cmd/syft/internal/options/cataloger_selection_test.go

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

cmd/syft/internal/options/convert.go

@@ -0,0 +1,27 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+)
+
+var _ clio.FieldDescriber = (*Convert)(nil)
+
+// Convert holds the options specific to the convert command. These are deliberately configuration-only (config file
+// or environment) rather than flags: they change how the command behaves for every invocation in a pipeline and are
+// not expected to vary from one call to the next.
+type Convert struct {
+	PassthroughExactFormat bool `yaml:"passthrough-exact-format" json:"passthrough-exact-format" mapstructure:"passthrough-exact-format"`
+}
+
+func DefaultConvert() Convert {
+	return Convert{
+		PassthroughExactFormat: false,
+	}
+}
+
+func (o *Convert) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.PassthroughExactFormat, `when a syft-json input SBOM already exactly matches the requested output format and schema version, copy it to that output unchanged instead of decoding and re-encoding it.
+Note: this only applies to syft-json input, and only when the document's schema version is identical to the schema version this version of syft produces. Any other input is always converted.
+Note: output written this way is a byte-for-byte copy of the input, so format options (such as 'format.pretty' or 'format.json.legacy') are not applied to it.
+Note: to keep memory use minimal on large documents, give the input as a file path (or a shell redirect) and write the output with '-o <format>=<path>'. Piped input, or output to STDOUT, requires the whole document to be held in memory.`)
+}

cmd/syft/internal/options/cpp.go

@@ -0,0 +1,30 @@
+package options
+
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/cpp"
+)
+
+type cppConfig struct {
+	VcpkgAllowGitClone *bool `yaml:"vcpkg-allow-git-clone" json:"vcpkg-allow-git-clone" mapstructure:"vcpkg-allow-git-clone"`
+}
+
+func defaultCppConfig() cppConfig {
+	// reference the cataloger default so capability generation can associate this config with the cpp
+	// ecosystem (it discovers ecosystem configs by their cataloger import). the value itself stays nil:
+	// nil defaults to false (no network), and leaving it unset lets --enrich opt in. cloning requires a
+	// network connection, which must be opt-in.
+	_ = cpp.DefaultCatalogerConfig()
+	return cppConfig{
+		VcpkgAllowGitClone: nil,
+	}
+}
+
+var _ interface {
+	clio.FieldDescriber
+} = (*cppConfig)(nil)
+
+func (o *cppConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.VcpkgAllowGitClone, `enables Syft to use clone remote repositories for vcpkg custom git registries. 
+	(also useful if the builtin vcpkg registry is not cloned locally)`)
+}

cmd/syft/internal/options/dotnet.go

@@ -13,6 +13,8 @@ type dotnetConfig struct {
 	PropagateDLLClaimsToParents bool `mapstructure:"propagate-dll-claims-to-parents" json:"propagate-dll-claims-to-parents" yaml:"propagate-dll-claims-to-parents"`
 
 	RelaxDLLClaimsWhenBundlingDetected bool `mapstructure:"relax-dll-claims-when-bundling-detected" json:"relax-dll-claims-when-bundling-detected" yaml:"relax-dll-claims-when-bundling-detected"`
+
+	ExcludeProjectReferences bool `mapstructure:"exclude-project-references" json:"exclude-project-references" yaml:"exclude-project-references"`
 }
 
 var _ interface {
@@ -24,6 +26,7 @@ func (o *dotnetConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
 	descriptions.Add(&o.DepPackagesMustClaimDLL, `only keep dep.json packages which have a runtime/resource DLL claimed in the deps.json targets section (but not necessarily found on disk). The package is also included if any child package claims a DLL, even if the package itself does not claim a DLL.`)
 	descriptions.Add(&o.PropagateDLLClaimsToParents, `treat DLL claims or on-disk evidence for child packages as DLL claims or on-disk evidence for any parent package`)
 	descriptions.Add(&o.RelaxDLLClaimsWhenBundlingDetected, `show all packages from the deps.json if bundling tooling is present as a dependency (e.g. ILRepack)`)
+	descriptions.Add(&o.ExcludeProjectReferences, `exclude packages with type "project" from deps.json output (these are internal project references, not NuGet packages)`)
 }
 
 func defaultDotnetConfig() dotnetConfig {
@@ -33,5 +36,6 @@ func defaultDotnetConfig() dotnetConfig {
 		DepPackagesMustClaimDLL:            def.DepPackagesMustClaimDLL,
 		PropagateDLLClaimsToParents:        def.PropagateDLLClaimsToParents,
 		RelaxDLLClaimsWhenBundlingDetected: def.RelaxDLLClaimsWhenBundlingDetected,
+		ExcludeProjectReferences:           def.ExcludeProjectReferences,
 	}
 }

cmd/syft/internal/options/format_spdx_json.go

@@ -13,12 +13,10 @@ func DefaultFormatSPDXJSON() FormatSPDXJSON {
 }
 
 func (o FormatSPDXJSON) config(v string) spdxjson.EncoderConfig {
-	var pretty bool
+	c := spdxjson.DefaultEncoderConfig()
+	c.Version = v
 	if o.Pretty != nil {
-		pretty = *o.Pretty
-	}
-	return spdxjson.EncoderConfig{
-		Version: v,
-		Pretty:  pretty,
+		c.Pretty = *o.Pretty
 	}
+	return c
 }

cmd/syft/internal/options/format_spdx_json_test.go

@@ -2,6 +2,8 @@ package options
 
 import (
 	"testing"
+
+	"github.com/stretchr/testify/require"
 )
 
 func TestFormatSPDXJSON_buildConfig(t *testing.T) {
@@ -11,5 +13,7 @@ func TestFormatSPDXJSON_buildConfig(t *testing.T) {
 	ft = setAllToNonZero(t, ft).(*FormatSPDXJSON)
 
 	subject := ft.config("Version")
-	assertExpectedValue(t, subject)
+	require.Equal(t, "Version", subject.Version)
+	require.Equal(t, "2.3", subject.DefaultVersion)
+	require.True(t, subject.Pretty)
 }

cmd/syft/internal/options/golang.go

@@ -4,6 +4,8 @@ import (
 	"strings"
 
 	"github.com/anchore/clio"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/cataloging"
 	"github.com/anchore/syft/syft/pkg/cataloger/golang"
 )
 
@@ -16,10 +18,14 @@ type golangConfig struct {
 	Proxy                       string                        `json:"proxy" yaml:"proxy" mapstructure:"proxy"`
 	NoProxy                     string                        `json:"no-proxy" yaml:"no-proxy" mapstructure:"no-proxy"`
 	MainModuleVersion           golangMainModuleVersionConfig `json:"main-module-version" yaml:"main-module-version" mapstructure:"main-module-version"`
+	UsePackagesLib              *bool                         `json:"use-packages-lib" yaml:"use-packages-lib" mapstructure:"use-packages-lib"`
+	CaptureSymbols              cataloging.SymbolScope        `json:"capture-symbols" yaml:"capture-symbols" mapstructure:"capture-symbols"`
+	CaptureSymbolsModules       []string                      `json:"capture-symbols-modules" yaml:"capture-symbols-modules" mapstructure:"capture-symbols-modules"`
 }
 
 var _ interface {
 	clio.FieldDescriber
+	clio.PostLoader
 } = (*golangConfig)(nil)
 
 func (o *golangConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
@@ -37,12 +43,45 @@ if unset this defaults to $GONOPROXY`)
 	descriptions.Add(&o.MainModuleVersion, `the go main module version discovered from binaries built with the go compiler will
 always show (devel) as the version. Use these options to control heuristics to guess
 a more accurate version from the binary.`)
+	descriptions.Add(&o.UsePackagesLib, `use the golang.org/x/tools/go/packages library, which executes golang tooling found on the path in addition to potential network access to get the most accurate results`)
+	// note: descriptions must be static string literals; the app config discovery that generates the
+	// capability docs reads them straight out of the AST
+	descriptions.Add(&o.CaptureSymbols, `capture function symbols from the binary symbol table (pclntab). valid values are:
+"none" (disabled), "stdlib" (only the synthetic stdlib package), "extended-stdlib" (stdlib plus every
+module under golang.org/x/), and "all" (all module packages plus stdlib)`)
+	descriptions.Add(&o.CaptureSymbolsModules, `glob patterns matched against go module paths (e.g. github.com/klauspost/**) that should have symbols
+captured in addition to whatever capture-symbols selects. ** crosses path separators, * does not.
+a trailing major version suffix is ignored when matching, so github.com/foo/* covers github.com/foo/bar/v2;
+spelling a suffix out in the pattern selects only that major version.
+this can only widen the selection, never narrow it, and is inert when capture-symbols is none`)
 	descriptions.Add(&o.MainModuleVersion.FromLDFlags, `look for LD flags that appear to be setting a version (e.g. -X main.version=1.0.0)`)
-	descriptions.Add(&o.MainModuleVersion.FromBuildSettings, `use the build settings (e.g. vcs.version & vcs.time) to craft a v0 pseudo version 
+	descriptions.Add(&o.MainModuleVersion.FromBuildSettings, `use the build settings (e.g. vcs.version & vcs.time) to craft a v0 pseudo version
 (e.g. v0.0.0-20220308212642-53e6d0aaf6fb) when a more accurate version cannot be found otherwise`)
 	descriptions.Add(&o.MainModuleVersion.FromContents, `search for semver-like strings in the binary contents`)
 }
 
+func (o *golangConfig) PostLoad() error {
+	raw := strings.TrimSpace(string(o.CaptureSymbols))
+	o.CaptureSymbols = o.CaptureSymbols.Parse()
+
+	// an unrecognized value still resolves to "none", but say so rather than silently capturing nothing.
+	// stay quiet for unset and an explicit "none", which is the default and would otherwise warn on nearly
+	// every scan.
+	if o.CaptureSymbols == cataloging.SymbolScopeNone && raw != "" && !strings.EqualFold(raw, string(cataloging.SymbolScopeNone)) {
+		log.Warnf("unknown golang.capture-symbols value %q, defaulting to %q (valid values: none, stdlib, extended-stdlib, all)", raw, cataloging.SymbolScopeNone)
+	}
+
+	// trim only, deliberately not Flatten: viper already splits a comma-separated scalar (env var or a bare
+	// yaml string) into a slice before this point, and there is no CLI flag feeding this key. The one thing
+	// Flatten would add is splitting commas *inside* a list entry, which silently breaks doublestar brace
+	// alternation like github.com/{foo,bar}/**. Viper's split does not trim, so that part is still needed.
+	for i, pattern := range o.CaptureSymbolsModules {
+		o.CaptureSymbolsModules[i] = strings.TrimSpace(pattern)
+	}
+
+	return nil
+}
+
 type golangMainModuleVersionConfig struct {
 	FromLDFlags       bool `json:"from-ld-flags" yaml:"from-ld-flags" mapstructure:"from-ld-flags"`
 	FromContents      bool `json:"from-contents" yaml:"from-contents" mapstructure:"from-contents"`
@@ -64,5 +103,8 @@ func defaultGolangConfig() golangConfig {
 			FromContents:      def.MainModuleVersion.FromContents,
 			FromBuildSettings: def.MainModuleVersion.FromBuildSettings,
 		},
+		UsePackagesLib:        nil, // this defaults to true, which is the API default
+		CaptureSymbols:        def.CaptureSymbols,
+		CaptureSymbolsModules: def.CaptureSymbolsModules,
 	}
 }

cmd/syft/internal/options/golang_test.go

@@ -0,0 +1,95 @@
+package options
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/anchore/syft/syft/cataloging"
+)
+
+func Test_golangConfig_PostLoad(t *testing.T) {
+	tests := []struct {
+		name            string
+		cfg             golangConfig
+		expected        cataloging.SymbolScope
+		expectedModules []string
+		wantErr         assert.ErrorAssertionFunc
+	}{
+		{
+			name:     "normalize all",
+			cfg:      golangConfig{CaptureSymbols: "all"},
+			expected: cataloging.SymbolScopeAll,
+		},
+		{
+			name:     "normalize stdlib",
+			cfg:      golangConfig{CaptureSymbols: "stdlib"},
+			expected: cataloging.SymbolScopeStdlib,
+		},
+		{
+			name:     "normalize extended-stdlib",
+			cfg:      golangConfig{CaptureSymbols: " Extended-Stdlib "},
+			expected: cataloging.SymbolScopeExtendedStdlib,
+		},
+		{
+			name: "module patterns keep embedded commas",
+			cfg: golangConfig{
+				CaptureSymbols: "stdlib",
+				// brace alternation contains a comma; splitting on it would corrupt the pattern
+				CaptureSymbolsModules: []string{"github.com/{foo,bar}/**", "golang.org/x/**"},
+			},
+			expected:        cataloging.SymbolScopeStdlib,
+			expectedModules: []string{"github.com/{foo,bar}/**", "golang.org/x/**"},
+		},
+		{
+			// viper splits a comma-separated scalar (env var or bare yaml string) but does not trim,
+			// so a leading space would otherwise survive into a pattern that silently matches nothing
+			name: "module patterns are trimmed",
+			cfg: golangConfig{
+				CaptureSymbols:        "stdlib",
+				CaptureSymbolsModules: []string{"golang.org/x/**", " github.com/foo/** "},
+			},
+			expected:        cataloging.SymbolScopeStdlib,
+			expectedModules: []string{"golang.org/x/**", "github.com/foo/**"},
+		},
+		{
+			name:     "empty defaults to none",
+			cfg:      golangConfig{CaptureSymbols: ""},
+			expected: cataloging.SymbolScopeNone,
+		},
+		{
+			name:     "invalid value defaults to none",
+			cfg:      golangConfig{CaptureSymbols: "stdlbi"},
+			expected: cataloging.SymbolScopeNone,
+		},
+		{
+			name:     "boolean spellings default to none",
+			cfg:      golangConfig{CaptureSymbols: "true"},
+			expected: cataloging.SymbolScopeNone,
+		},
+		{
+			name:     "explicit none resolves to none",
+			cfg:      golangConfig{CaptureSymbols: "none"},
+			expected: cataloging.SymbolScopeNone,
+		},
+		{
+			name:     "explicit none is not case sensitive",
+			cfg:      golangConfig{CaptureSymbols: " NONE "},
+			expected: cataloging.SymbolScopeNone,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.wantErr == nil {
+				tt.wantErr = assert.NoError
+			}
+			err := tt.cfg.PostLoad()
+			tt.wantErr(t, err)
+			if err != nil {
+				return
+			}
+			assert.Equal(t, tt.expected, tt.cfg.CaptureSymbols)
+			assert.Equal(t, tt.expectedModules, tt.cfg.CaptureSymbolsModules)
+		})
+	}
+}

cmd/syft/internal/options/javascript.go

@@ -1,6 +1,9 @@
 package options
 
-import "github.com/anchore/clio"
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/javascript"
+)
 
 type javaScriptConfig struct {
 	SearchRemoteLicenses   *bool  `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
@@ -12,6 +15,24 @@ var _ interface {
 	clio.FieldDescriber
 } = (*javaScriptConfig)(nil)
 
+func defaultJavaScriptConfig() javaScriptConfig {
+	def := javascript.DefaultCatalogerConfig()
+	var includeDevDependencies *bool
+	if def.IncludeDevDependencies {
+		includeDevDependencies = &def.IncludeDevDependencies
+	}
+
+	var searchRemoteLicenses *bool
+	if def.SearchRemoteLicenses {
+		searchRemoteLicenses = &def.SearchRemoteLicenses
+	}
+	return javaScriptConfig{
+		NpmBaseURL:             def.NPMBaseURL,
+		SearchRemoteLicenses:   searchRemoteLicenses,
+		IncludeDevDependencies: includeDevDependencies,
+	}
+}
+
 func (o *javaScriptConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
 	descriptions.Add(&o.SearchRemoteLicenses, `enables Syft to use the network to fill in more detailed license information`)
 	descriptions.Add(&o.NpmBaseURL, `base NPM url to use`)

cmd/syft/internal/options/linux_kernel.go

@@ -1,14 +1,18 @@
 package options
 
-import "github.com/anchore/clio"
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/kernel"
+)
 
 type linuxKernelConfig struct {
 	CatalogModules bool `json:"catalog-modules" yaml:"catalog-modules" mapstructure:"catalog-modules"`
 }
 
 func defaultLinuxKernelConfig() linuxKernelConfig {
+	def := kernel.DefaultLinuxKernelCatalogerConfig()
 	return linuxKernelConfig{
-		CatalogModules: true,
+		CatalogModules: def.CatalogModules,
 	}
 }
 

cmd/syft/internal/options/python.go

@@ -1,16 +1,30 @@
 package options
 
-import "github.com/anchore/clio"
+import (
+	"github.com/anchore/clio"
+	"github.com/anchore/syft/syft/pkg/cataloger/python"
+)
 
 type pythonConfig struct {
-	GuessUnpinnedRequirements bool `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
+	SearchRemoteLicenses      *bool  `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	PypiBaseURL               string `json:"pypi-base-url" yaml:"pypi-base-url" mapstructure:"pypi-base-url"`
+	GuessUnpinnedRequirements *bool  `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
 }
 
 var _ interface {
 	clio.FieldDescriber
 } = (*pythonConfig)(nil)
 
+func defaultPythonConfig() pythonConfig {
+	def := python.DefaultCatalogerConfig()
+	return pythonConfig{
+		GuessUnpinnedRequirements: &def.GuessUnpinnedRequirements,
+	}
+}
+
 func (o *pythonConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.SearchRemoteLicenses, `enables Syft to use the network to fill in more detailed license information`)
+	descriptions.Add(&o.PypiBaseURL, `base Pypi url to use`)
 	descriptions.Add(&o.GuessUnpinnedRequirements, `when running across entries in requirements.txt that do not specify a specific version 
 (e.g. "sqlalchemy >= 1.0.0, <= 2.0.0, != 3.0.0, <= 3.0.0"), attempt to guess what the version could
 be based on the version requirements specified (e.g. "1.0.0"). When enabled the lowest expressible version 

cmd/syft/internal/options/writer.go

@@ -122,7 +122,7 @@ func formatVersionOptions(nameVersionPairs []string) string {
 	for _, name := range sortedAvailableFormats {
 		s.WriteString("\n")
 
-		s.WriteString(fmt.Sprintf("   - %s", name))
+		fmt.Fprintf(&s, "   - %s", name)
 
 		if len(availableVersions[name]) > 0 {
 			s.WriteString(" @ ")

cmd/syft/internal/options/writer_test.go

@@ -32,7 +32,7 @@ func Test_MakeSBOMWriter(t *testing.T) {
 		{
 			name:    "unknown format",
 			outputs: []string{"unknown"},
-			wantErr: func(t assert.TestingT, err error, bla ...interface{}) bool {
+			wantErr: func(t assert.TestingT, err error, bla ...any) bool {
 				return assert.ErrorContains(t, err, `unsupported output format "unknown", supported formats are:`)
 			},
 		},

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

@@ -97,7 +97,7 @@ var imageOnlyTestCases = []testCase{
 			"Serilog.Sinks.Console":                                 "4.0.1",
 			//"System.Diagnostics.DiagnosticSource":                   "6.0.0", // no dll claims in deps.json targets section
 			//"System.Runtime.CompilerServices.Unsafe":                "6.0.0", // no dll claims in deps.json targets section
-			"TestCommon":  "1.0.0",
+			//"TestCommon":  "1.0.0",
 			"TestLibrary": "1.0.0",
 		},
 	},
@@ -274,7 +274,7 @@ var dirOnlyTestCases = []testCase{
 			"Serilog.Sinks.Console":                                 "4.0.1",
 			//"System.Diagnostics.DiagnosticSource":                   "6.0.0", // no dll claims in deps.json targets section
 			//"System.Runtime.CompilerServices.Unsafe":                "6.0.0", // no dll claims in deps.json targets section
-			"TestCommon":  "1.0.0",
+			//"TestCommon":  "1.0.0",
 			"TestLibrary": "1.0.0",
 		},
 	},

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

@@ -2,6 +2,7 @@ package integration
 
 import (
 	"context"
+	"slices"
 	"strings"
 	"testing"
 
@@ -25,7 +26,6 @@ func BenchmarkImagePackageCatalogers(b *testing.B) {
 	// get the source object for the image
 	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(b, err)
-
 	b.Cleanup(func() {
 		require.NoError(b, theSource.Close())
 	})
@@ -87,6 +87,10 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedPkgs.Remove(string(pkg.GithubActionWorkflowPkg))
 	definedPkgs.Remove(string(pkg.TerraformPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // we have coverage for pear instead
+	definedPkgs.Remove(string(pkg.CondaPkg))
+	definedPkgs.Remove(string(pkg.ModelPkg))
+	definedPkgs.Remove(string(pkg.VcpkgPkg))
+	definedPkgs.Remove(string(pkg.AppleAppBundlePkg))
 
 	var cases []testCase
 	cases = append(cases, commonTestCases...)
@@ -124,7 +128,7 @@ func TestPkgCoverageImage(t *testing.T) {
 }
 
 func TestPkgCoverageDirectory(t *testing.T) {
-	sbom, _ := catalogDirectory(t, "test-fixtures/image-pkg-coverage")
+	sbom, _ := catalogDirectory(t, "testdata/image-pkg-coverage")
 
 	observedLanguages := strset.New()
 	definedLanguages := strset.New()
@@ -159,7 +163,11 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	definedPkgs.Remove(string(pkg.LinuxKernelModulePkg))
 	definedPkgs.Remove(string(pkg.Rpkg))
 	definedPkgs.Remove(string(pkg.UnknownPkg))
+	definedPkgs.Remove(string(pkg.CondaPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // this is covered as pear packages
+	definedPkgs.Remove(string(pkg.ModelPkg))
+	definedPkgs.Remove(string(pkg.VcpkgPkg))
+	definedPkgs.Remove(string(pkg.AppleAppBundlePkg))
 
 	// for directory scans we should not expect to see any of the following package types
 	definedPkgs.Remove(string(pkg.KbPkg))
@@ -191,11 +199,8 @@ func assertPackages(t *testing.T, sbom sbom.SBOM, test testCase, observedLanguag
 		}
 
 		var foundLang bool
-		for _, lang := range strings.Split(test.pkgLanguage.String(), ",") {
-			if actualPkg.Language.String() == lang {
-				foundLang = true
-				break
-			}
+		if slices.Contains(strings.Split(test.pkgLanguage.String(), ","), actualPkg.Language.String()) {
+			foundLang = true
 		}
 		if !foundLang {
 			t.Errorf("bad language (pkg=%+v): %+v", actualPkg.Name, actualPkg.Language)
@@ -258,7 +263,7 @@ func TestPkgCoverageImage_HasEvidence(t *testing.T) {
 }
 
 func TestPkgCoverageDirectory_HasEvidence(t *testing.T) {
-	sbom, _ := catalogDirectory(t, "test-fixtures/image-pkg-coverage")
+	sbom, _ := catalogDirectory(t, "testdata/image-pkg-coverage")
 
 	var cases []testCase
 	cases = append(cases, commonTestCases...)

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

@@ -22,7 +22,7 @@ import (
 func TestFileCataloging_Default(t *testing.T) {
 	cfg := options.DefaultCatalog().ToSBOMConfig(clio.Identification{})
 	cfg = cfg.WithFilesConfig(filecataloging.DefaultConfig())
-	sbom, _ := catalogDirectoryWithConfig(t, "test-fixtures/files", cfg)
+	sbom, _ := catalogDirectoryWithConfig(t, "testdata/files", cfg)
 
 	var metadata map[file.Coordinates]file.Metadata
 
@@ -48,13 +48,13 @@ func TestFileCataloging_AllFiles(t *testing.T) {
 			SkipFilesAboveSize: 30,
 		},
 	})
-	sbom, _ := catalogDirectoryWithConfig(t, "test-fixtures/files", cfg)
+	sbom, _ := catalogDirectoryWithConfig(t, "testdata/files", cfg)
 
 	pwd, err := os.Getwd()
 	require.NoError(t, err)
 
 	testPath := func(path string) string {
-		return filepath.Join(pwd, "test-fixtures/files", path)
+		return filepath.Join(pwd, "testdata/files", path)
 	}
 
 	metadata := map[file.Coordinates]file.Metadata{

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

@@ -0,0 +1,147 @@
+package integration
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"runtime"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/stereoscope/pkg/image"
+	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/source"
+)
+
+// multiplatformImage is busybox:1.38.0 pinned by index digest, since docker hub periodically rebuilds and
+// re-pushes official image tags, which changes the per-platform digests asserted below.
+const multiplatformImage = "docker.io/library/busybox@sha256:fd7dc98638c8e305f4dc34e979f1c0fdfdcaeb0fbf8fcff77ae834b6da3d7e6e"
+
+// TestMultiPlatformOCIImageSelection verifies that syft can load a single platform out of a
+// multi-platform OCI image on disk (both --from oci-dir and --from oci-archive) by selecting the
+// image that matches the requested platform.
+func TestMultiPlatformOCIImageSelection(t *testing.T) {
+	// Per-platform image config digests within the multi-platform index, obtained from the OCI layout
+	// (see anchore/stereoscope integration tests: TestPlatformSelectionWithOciLocalSources).
+	expectedDigest := map[string]string{
+		"arm64":   "sha256:d2482869a6b838d3b4c9cad0c8085c06277909482771eb525d298fc3a7d07927",
+		"s390x":   "sha256:e55a0fa55032cceac2d983f4b4a25b28e42303b46a2f1915fc0fa45051e6ca70",
+		"amd64":   "sha256:aaef90e065235eb0b2d9938be85d1b81add2902cf89affe2cdfa19be33476ac0",
+		"ppc64le": "sha256:8158829b015d1c5285d63d54d37e95998ef0af4177e3f416678decbcaff3170c",
+	}
+
+	// syft --from source tag -> stereoscope OCI source used to prepare the local fixture
+	sources := map[string]image.Source{
+		"oci-dir":     image.OciDirectorySource,
+		"oci-archive": image.OciTarballSource,
+	}
+
+	for from, imageSource := range sources {
+		t.Run(from, func(t *testing.T) {
+			localPath := imagetest.PrepareMultiplatformFixtureImage(t, imageSource, multiplatformImage)
+			for _, arch := range []string{"amd64", "arm64", "s390x", "ppc64le"} {
+				t.Run(fmt.Sprintf("linux/%s", arch), func(t *testing.T) {
+					platform, err := image.NewPlatform("linux/" + arch)
+					require.NoError(t, err)
+
+					src, err := syft.GetSource(
+						context.Background(),
+						localPath,
+						syft.DefaultGetSourceConfig().WithSources(from).WithPlatform(platform),
+					)
+					require.NoError(t, err)
+					t.Cleanup(func() {
+						require.NoError(t, src.Close())
+					})
+
+					meta, ok := src.Describe().Metadata.(source.ImageMetadata)
+					require.True(t, ok, "expected image metadata, got %T", src.Describe().Metadata)
+
+					// The raw config of the selected image must match the requested platform...
+					assertConfigPlatform(t, meta.RawConfig, "linux", arch)
+					assert.Equal(t, "linux", meta.OS)
+					assert.Equal(t, arch, meta.Architecture)
+					// ...and it must be the exact per-platform image from the multi-platform index.
+					assert.Equal(t, expectedDigest[arch], meta.ID)
+				})
+			}
+		})
+	}
+}
+
+// TestMultiPlatformOCIImageSelection_UnavailablePlatform verifies that requesting a platform not present
+// in the multi-platform OCI image results in an error rather than silently selecting the wrong image.
+func TestMultiPlatformOCIImageSelection_UnavailablePlatform(t *testing.T) {
+	// windows/amd64 is not present in this linux-only multi-platform image
+	platform, err := image.NewPlatform("windows/amd64")
+	require.NoError(t, err)
+
+	sources := map[string]image.Source{
+		"oci-dir":     image.OciDirectorySource,
+		"oci-archive": image.OciTarballSource,
+	}
+
+	for from, imageSource := range sources {
+		t.Run(from, func(t *testing.T) {
+			localPath := imagetest.PrepareMultiplatformFixtureImage(t, imageSource, multiplatformImage)
+
+			_, err := syft.GetSource(
+				context.Background(),
+				localPath,
+				syft.DefaultGetSourceConfig().WithSources(from).WithPlatform(platform),
+			)
+			require.ErrorContains(t, err, "windows/amd64")
+		})
+	}
+}
+
+// TestMultiPlatformOCIImageSelection_DefaultPlatform verifies that not specifying a platform results
+// in the current platform being selected.
+func TestMultiPlatformOCIImageSelection_DefaultPlatform(t *testing.T) {
+	sources := map[string]image.Source{
+		"oci-dir":     image.OciDirectorySource,
+		"oci-archive": image.OciTarballSource,
+	}
+
+	for from, imageSource := range sources {
+		t.Run(from, func(t *testing.T) {
+			localPath := imagetest.PrepareMultiplatformFixtureImage(t, imageSource, multiplatformImage)
+
+			src, err := syft.GetSource(
+				context.Background(),
+				localPath,
+				syft.DefaultGetSourceConfig().WithSources(from),
+			)
+			require.NoError(t, err)
+			t.Cleanup(func() {
+				require.NoError(t, src.Close())
+			})
+
+			meta, ok := src.Describe().Metadata.(source.ImageMetadata)
+			require.True(t, ok, "expected image metadata, got %T", src.Describe().Metadata)
+
+			// The raw config of the selected image must match the current platform
+			assertConfigPlatform(t, meta.RawConfig, "linux", runtime.GOARCH)
+			assert.Equal(t, "linux", meta.OS)
+			assert.Equal(t, runtime.GOARCH, meta.Architecture)
+		})
+	}
+}
+
+// assertConfigPlatform asserts the os/architecture recorded in a raw OCI image config document.
+func assertConfigPlatform(t *testing.T, rawConfig []byte, os, architecture string) {
+	t.Helper()
+	require.NotEmpty(t, rawConfig)
+
+	var cfg struct {
+		OS           string `json:"os"`
+		Architecture string `json:"architecture"`
+	}
+	require.NoError(t, json.Unmarshal(rawConfig, &cfg))
+
+	assert.Equal(t, os, cfg.OS)
+	assert.Equal(t, architecture, cfg.Architecture)
+}

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

@@ -11,7 +11,7 @@ import (
 )
 
 func TestNpmPackageLockDirectory(t *testing.T) {
-	sbom, _ := catalogDirectory(t, "test-fixtures/npm-lock")
+	sbom, _ := catalogDirectory(t, "testdata/npm-lock")
 
 	foundPackages := strset.New()
 
@@ -32,10 +32,11 @@ func TestNpmPackageLockDirectory(t *testing.T) {
 }
 
 func TestYarnPackageLockDirectory(t *testing.T) {
-	sbom, _ := catalogDirectory(t, "test-fixtures/yarn-lock")
+	sbom, _ := catalogDirectory(t, "testdata/yarn-lock")
 
 	foundPackages := strset.New()
-	expectedPackages := strset.New("async@0.9.2", "async@3.2.3", "merge-objects@1.0.5", "should-type@1.3.0", "@4lolo/resize-observer-polyfill@1.5.2")
+	// merge-objects and should-type are devDependencies in package.json and are excluded by default
+	expectedPackages := strset.New("async@0.9.2", "async@3.2.3", "@4lolo/resize-observer-polyfill@1.5.2")
 
 	for actualPkg := range sbom.Artifacts.Packages.Enumerate(pkg.NpmPkg) {
 		for _, actualLocation := range actualPkg.Locations.ToSlice() {

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

@@ -26,7 +26,7 @@ func TestBinaryElfRelationships(t *testing.T) {
 	}
 
 	// run the test...
-	sbom, _ := catalogFixtureImage(t, "elf-test-fixtures", source.SquashedScope)
+	sbom, _ := catalogFixtureImage(t, "elf-testdata", source.SquashedScope)
 
 	// get a mapping of package names to their IDs
 	nameToId := map[string]artifact.ID{}

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

@@ -278,7 +278,7 @@ func packageCatalogerExports(t *testing.T) map[string]exportTokenSet {
 		if info.IsDir() ||
 			!strings.HasSuffix(info.Name(), ".go") ||
 			strings.HasSuffix(info.Name(), "_test.go") ||
-			strings.Contains(path, "test-fixtures") ||
+			strings.Contains(path, "testdata") ||
 			strings.Contains(path, "internal") {
 			return nil
 		}
@@ -329,7 +329,7 @@ func packageCatalogerExports(t *testing.T) map[string]exportTokenSet {
 					}
 					exportsPerPackage[pkg].Add(exportToken{
 						Name:            decl.Name.Name,
-						Type:            reflect.TypeOf(decl.Type).String(),
+						Type:            reflect.TypeFor[*ast.FuncType]().String(),
 						SignatureSize:   len(decl.Type.Params.List),
 						ReturnTypeNames: returnTypes,
 					})

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

@@ -1,7 +1,6 @@
 package integration
 
 import (
-	"fmt"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -11,47 +10,52 @@ import (
 )
 
 func TestPackageDeduplication(t *testing.T) {
+	// this test verifies that package deduplication works correctly across layers.
+	// The test fixture installs/upgrades packages in multiple stages, creating
+	// duplicate RPM DB entries across layers. Without deduplication, we'd see ~600 packages.
+	//
+	// Note: we index by package name (not name-version) to be resilient to Rocky Linux
+	// repo updates. Location counts are summed across all versions of each package.
 	tests := []struct {
 		scope         source.Scope
 		packageCount  int
-		instanceCount map[string]int
-		locationCount map[string]int
+		instanceCount map[string]int // how many distinct package instances (by name)
+		locationCount map[string]int // total locations across ALL versions of each package
 	}{
 		{
 			scope:        source.AllLayersScope,
-			packageCount: 175, // without deduplication this would be ~600
+			packageCount: 176, // without deduplication this would be ~600
 			instanceCount: map[string]int{
 				"basesystem":   1,
 				"wget":         1,
-				"curl-minimal": 2, // upgraded in the image
+				"curl-minimal": 2, // base + upgraded (2 different versions)
 				"vsftpd":       1,
-				"httpd":        1, // rpm, - we exclude binary
+				"httpd":        1,
 			},
 			locationCount: map[string]int{
-				"basesystem-11-13.el9":               5, // in all layers
-				"curl-minimal-7.76.1-26.el9_3.2.0.1": 2, // base + wget layer
-				"curl-minimal-7.76.1-31.el9":         3, // curl upgrade layer + all above layers
-				"wget-1.21.1-8.el9_4":                4, // wget + all above layers
-				"vsftpd-3.0.5-6.el9":                 2, // vsftpd + all above layers
-				"httpd-2.4.62-4.el9":                 1, // last layer
+				"basesystem":   5, // in all layers
+				"curl-minimal": 5, // total across both versions (2 + 3)
+				"wget":         4, // wget + all above layers
+				"vsftpd":       2, // vsftpd + all above layers
+				"httpd":        1, // last layer
 			},
 		},
 		{
 			scope:        source.SquashedScope,
-			packageCount: 169,
+			packageCount: 170,
 			instanceCount: map[string]int{
 				"basesystem":   1,
 				"wget":         1,
-				"curl-minimal": 1, // upgraded, but the most recent
+				"curl-minimal": 1, // deduped to latest
 				"vsftpd":       1,
-				"httpd":        1, // rpm, binary is now excluded by overlap
+				"httpd":        1,
 			},
 			locationCount: map[string]int{
-				"basesystem-11-13.el9":       1,
-				"curl-minimal-7.76.1-31.el9": 1, // upgrade
-				"wget-1.21.1-8.el9_4":        1,
-				"vsftpd-3.0.5-6.el9":         1,
-				"httpd-2.4.62-4.el9":         1,
+				"basesystem":   1,
+				"curl-minimal": 1,
+				"wget":         1,
+				"vsftpd":       1,
+				"httpd":        1,
 			},
 		},
 	}
@@ -59,35 +63,32 @@ func TestPackageDeduplication(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(string(tt.scope), func(t *testing.T) {
 			sbom, _ := catalogFixtureImage(t, "image-vertical-package-dups", tt.scope)
+
+			// verify binary packages have names
 			for _, p := range sbom.Artifacts.Packages.Sorted() {
 				if p.Type == pkg.BinaryPkg {
 					assert.NotEmpty(t, p.Name)
 				}
 			}
 
+			// verify exact package count
 			assert.Equal(t, tt.packageCount, sbom.Artifacts.Packages.PackageCount())
-			for name, expectedInstanceCount := range tt.instanceCount {
+
+			// verify instance count by package name
+			for name, expectedCount := range tt.instanceCount {
 				pkgs := sbom.Artifacts.Packages.PackagesByName(name)
-
-				// with multiple packages with the same name, something is wrong (or this is the wrong fixture)
-				if assert.Len(t, pkgs, expectedInstanceCount, "unexpected package count for %s", name) {
-					for _, p := range pkgs {
-						nameVersion := fmt.Sprintf("%s-%s", name, p.Version)
-						expectedLocationCount, ok := tt.locationCount[nameVersion]
-						if !ok {
-							t.Errorf("missing name-version: %s", nameVersion)
-							continue
-						}
-
-						// we should see merged locations (assumption, there was 1 location for each package)
-						assert.Len(t, p.Locations.ToSlice(), expectedLocationCount, "unexpected location count for %s", nameVersion)
-
-						// all paths should match
-						assert.Len(t, p.Locations.CoordinateSet().Paths(), 1, "unexpected location count for %s", nameVersion)
-					}
-				}
+				assert.Len(t, pkgs, expectedCount, "unexpected instance count for %s", name)
 			}
 
+			// verify total location count across all versions of each package
+			for name, expectedLocCount := range tt.locationCount {
+				pkgs := sbom.Artifacts.Packages.PackagesByName(name)
+				totalLocations := 0
+				for _, p := range pkgs {
+					totalLocations += len(p.Locations.ToSlice())
+				}
+				assert.Equal(t, expectedLocCount, totalLocations, "unexpected total location count for %s", name)
+			}
 		})
 	}
 }

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

@@ -0,0 +1,64 @@
+package integration
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/stereoscope/pkg/image"
+	"github.com/anchore/stereoscope/pkg/imagetest"
+	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/source"
+)
+
+// TestSinglePlatformOCIImage covers the single-image (non-index) OCI layouts, where syft used to report
+// empty os/architecture metadata and silently accept any --platform. Both now come from the image config.
+func TestSinglePlatformOCIImage(t *testing.T) {
+	// a platform this fixture is never built for, so the mismatch is not host dependent
+	unavailablePlatform, err := image.NewPlatform("linux/ppc64le")
+	require.NoError(t, err)
+
+	sources := map[string]image.Source{
+		"oci-dir":     image.OciDirectorySource,
+		"oci-archive": image.OciTarballSource,
+	}
+
+	for from, imageSource := range sources {
+		t.Run(from, func(t *testing.T) {
+			localPath := strings.TrimPrefix(imagetest.PrepareFixtureImage(t, imageSource, "image-distro-id"), string(imageSource)+":")
+
+			t.Run("reports the platform from the image config", func(t *testing.T) {
+				src, err := syft.GetSource(
+					context.Background(),
+					localPath,
+					syft.DefaultGetSourceConfig().WithSources(from),
+				)
+				require.NoError(t, err)
+				t.Cleanup(func() {
+					require.NoError(t, src.Close())
+				})
+
+				meta, ok := src.Describe().Metadata.(source.ImageMetadata)
+				require.True(t, ok, "expected image metadata, got %T", src.Describe().Metadata)
+
+				// the fixture is built for whatever the local docker daemon runs, so assert against the
+				// config rather than a fixed platform
+				assert.NotEmpty(t, meta.OS)
+				assert.NotEmpty(t, meta.Architecture)
+				assertConfigPlatform(t, meta.RawConfig, meta.OS, meta.Architecture)
+			})
+
+			t.Run("rejects a platform the image does not match", func(t *testing.T) {
+				_, err := syft.GetSource(
+					context.Background(),
+					localPath,
+					syft.DefaultGetSourceConfig().WithSources(from).WithPlatform(unavailablePlatform),
+				)
+				require.ErrorContains(t, err, "linux/ppc64le")
+			})
+		})
+	}
+}

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

@@ -1 +0,0 @@
-../../../../../../syft/pkg/cataloger/binary/test-fixtures/elf-test-fixtures

cmd/syft/internal/test/integration/test-fixtures/image-pkg-coverage/pkgs/java/generate-fixtures.md

@@ -1 +0,0 @@
-See the syft/cataloger/java/test-fixtures/java-builds dir to generate test fixtures and copy to here manually.