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

@@ -1,67 +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:
-  ## internal tools ############################################################################
-
-  # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
-  - name: binny
-    version:
-      want: v0.13.0
-    method: github-release
-    with:
-      repo: anchore/binny
-
-  # used to produce SBOMs during release
-  - name: syft
-    version:
-      want: v1.42.3
-    method: github-release
-    with:
-      repo: anchore/syft
-
-  # used to sign mac binaries at release
-  - name: quill
-    version:
-      want: v0.7.1
-    method: github-release
-    with:
-      repo: anchore/quill
-
-  # used at release to generate the changelog
-  - name: chronicle
-    version:
-      want: v0.8.0
-    method: github-release
-    with:
-      repo: anchore/chronicle
-
-  ## external tools ############################################################################
-
-  # used for linting
-  - name: golangci-lint
-    version:
-      want: v2.11.4
-    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: v3.0.5
-    method: github-release
-    with:
-      repo: sigstore/cosign
-
   # used in integration tests to verify JSON schemas
   - name: yajsv
     version:
@@ -70,58 +13,18 @@ tools:
     with:
       repo: neilpa/yajsv
 
-  # used to release all artifacts
-  - name: goreleaser
-    version:
-      want: v2.15.2
-    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 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: v3.49.1
-    method: github-release
-    with:
-      repo: go-task/task
-
-  # used for triggering a release
-  - name: gh
-    version:
-      want: v2.89.0
-    method: github-release
-    with:
-      repo: cli/cli
-
   # used to upload test fixture cache
   - name: oras
     version:
-      want: v1.3.1
+      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: v4.52.5
+      want: v4.53.6
     method: github-release
     with:
       repo: mikefarah/yq

.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

@@ -1,55 +1,45 @@
 name: "Bootstrap"
-description: "Bootstrap all tools and dependencies"
+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.
+
 inputs:
   go-version:
-    description: "Go version to install"
+    description: "Go version to install (passed to go-make/setup)"
     required: true
     default: "1.26.2"
-  go-dependencies:
-    description: "Download go dependencies"
+  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: "53ac821810"
   download-test-fixture-cache:
     description: "Download test fixture cache from OCI and github actions"
     required: true
     default: "false"
-  tools:
-    description: "whether to install tools"
-    default: "true"
   bootstrap-apt-packages:
     description: "Space delimited list of tools to install via apt"
     default: "libxml2-utils"
+
 runs:
   using: "composite"
   steps:
-    # note: go mod and build is automatically cached on default with v4+
-    - uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c # v6.4.0
-      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 }}
-        check-latest: true
-    - name: Restore tool cache
-      if: inputs.tools == 'true'
-      id: tool-cache
-      uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
-      with:
-        path: ${{ github.workspace }}/.tool
-        key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
-    - name: Install project tools
+        cache-key-prefix: ${{ inputs.cache-key-prefix }}
+        cache-enabled: ${{ inputs.cache-enabled }}
+
+    - name: Install binny-managed tools
       shell: bash
-      if: inputs.tools == 'true'
-      run: |
-        make tools
-        .tool/binny list
-        .tool/binny check
-    - 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 != ''
       shell: bash
@@ -57,13 +47,34 @@ 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@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+      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
+
     - name: Download test fixture cache
       if: inputs.download-test-fixture-cache == 'true'
       shell: bash

.github/dependabot.yml

@@ -1,20 +1,13 @@
 # Dependabot configuration
-#
-# Grouping behavior (see inline comments for details):
-#   - Minor + patch updates: grouped into a single PR per ecosystem
-#   - Major version bumps: individual PR per dependency
-#   - Security updates: individual PR per dependency
-#
-# Note: "patch" refers to semver version bumps (1.2.3 -> 1.2.4), not security fixes.
-# Security updates are identified separately via GitHub's Advisory Database and
-# can be any version bump (patch, minor, or major) that fixes a known CVE.
 
 version: 2
 
 updates:
 
   - package-ecosystem: gomod
-    directory: "/"
+    directories:
+      - "/"
+      - "/.make"
     cooldown:
       default-days: 7
     schedule:
@@ -28,14 +21,6 @@ updates:
       - dependency-name: "github.com/aquasecurity/go-version"
       - dependency-name: "github.com/knqyf263/go-apk-version"
       - dependency-name: "github.com/knqyf263/go-deb-version"
-    groups:
-      go-minor-patch:
-        applies-to: version-updates  # security updates get individual PRs
-        patterns:
-          - "*"
-        update-types:  # major omitted, gets individual PRs
-          - "minor"
-          - "patch"
 
   - package-ecosystem: "github-actions"
     directories:
@@ -49,11 +34,3 @@ updates:
     open-pull-requests-limit: 10
     labels:
       - "dependencies"
-    groups:
-      actions-minor-patch:
-        applies-to: version-updates  # security updates get individual PRs
-        patterns:
-          - "*"
-        update-types:  # major omitted, gets individual PRs
-          - "minor"
-          - "patch"

.github/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/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/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.yaml

@@ -13,7 +13,7 @@ permissions: {}
 jobs:
   analyze:
     name: Analyze
-    uses: anchore/workflows/.github/workflows/codeql.yaml@e8cee3a5916cebb68cda68b54c180f43394c1910 # v0.5.0
+    uses: anchore/workflows/.github/workflows/codeql.yaml@7212994dc8fc3a53fe9c8e766ab5b4ddd16ea3d4 # v0.8.0
     permissions:
       security-events: write
       packages: read

.github/workflows/release.yaml

@@ -21,20 +21,27 @@ on:
         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:
-
   version-available:
     if: ${{ github.event.inputs.phase == 'all' }}
-    uses: anchore/workflows/.github/workflows/check-version-available.yaml@8b2b1caf40e03933c6807e03b99e883e2ceb5ac8 # v0.4.0
+    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 }}
 
   check-gate:
-    if: ${{ github.event.inputs.phase == 'all' }}
+    if: ${{ github.event.inputs.phase == 'all' && !inputs.skip-checks }}
     permissions:
-      checks: read   # required for getting the status of specific check names
-    uses: anchore/workflows/.github/workflows/check-gate.yaml@8b2b1caf40e03933c6807e03b99e883e2ceb5ac8 # v0.4.0
+      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.
@@ -42,21 +49,33 @@ jobs:
       checks: '["Acceptance tests (Linux)", "Acceptance tests (Mac)", "Build snapshot artifacts", "CLI tests (Linux)", "Integration tests", "Static analysis", "Unit tests"]'
 
   release:
-    needs: [ check-gate, version-available ]
-    if: ${{ github.event.inputs.phase == 'all' }}
+    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: >-
+      ${{ always()
+          && needs.version-available.result == 'success'
+          && !contains(fromJSON('["failure", "cancelled"]'), needs.check-gate.result) }}
+    environment: release
     # runs-on.com: compute instances for parallel builds
     #   spot disabled: reliability for build workflows (used for releases too)
     #   goreleaser uses parallelism of 12, so we need more CPUs
     #   s3-cache: faster actions cache
-    #   tmpfs: faster io-intensive workflows
-    runs-on: runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/extras=s3-cache+tmpfs
+    #   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@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           fetch-depth: 0
           persist-credentials: true
@@ -64,32 +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@4907a6ddec9925e35a0a9e82d7399ccc52663121  #v4.1.0
+        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@4907a6ddec9925e35a0a9e82d7399ccc52663121  #v4.1.0
+        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 }}
@@ -101,36 +118,18 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@e22c389904149dbc22b58101806040fa8d37a610 #v0.24.0
+      - uses: anchore/sbom-action@3ad7283483fc7af8ff2b4ea19663c2d5ca935e26 #v0.24.2
         continue-on-error: true
         with:
           file: go.mod
           artifact-name: sbom.spdx.json
 
-      - name: Notify Slack of new release
-        uses: slackapi/slack-github-action@45a88b9581bfab2566dc881e2cd66d334e621e2c #v3.0.3
-        continue-on-error: true
-        with:
-          webhook: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
-          webhook-type: incoming-webhook
-          payload: |
-            text: "A new Syft release has been published: https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}"
-            blocks:
-              - type: section
-                text:
-                  type: mrkdwn
-                  text: |
-                    *A new Syft release has been published* :rocket:
-                    • Release: <https://github.com/anchore/syft/releases/tag/${{ github.event.inputs.version }}|${{ github.event.inputs.version }}>
-                    • Repo: `${{ github.repository }}`
-                    • Workflow: `${{ github.workflow }}`
-                    • Event: `${{ github.event_name }}`
-        if: ${{ success() }}
-
   release-install-script:
-    needs: [ release ]
+    needs: [release]
     if: ${{ always() && (needs.release.result == 'success' || github.event.inputs.phase == 'install-script-only') }}
-    uses: "anchore/workflows/.github/workflows/release-install-script.yaml@main"
+    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/validate-github-actions.yaml

@@ -20,12 +20,12 @@ jobs:
       contents: read
       security-events: write  # for uploading SARIF results
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
 
       - name: "Run zizmor"
-        uses: zizmorcore/zizmor-action@b1d7e1fb5de872772f31590499237e7cce841e8e # v0.5.3
+        uses: zizmorcore/zizmor-action@cc914d7f3750a2d13d75c7f184a1060aa0e9d482 # v0.6.4
         with:
           # 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

.github/workflows/validations.yaml

@@ -21,13 +21,17 @@ jobs:
     name: "Static analysis"
     # runs-on.com: memory & general purpose instances for testing
     #   spot enabled: ok to interrupt non-production workloads
-    #   s3-cache: faster actions cache
-    #   tmpfs: faster io-intensive workflows
-    runs-on: &test-runner "runs-on=${{ github.run_id }}/cpu=4+8/ram=32+128/family=r5+r6+r7+r8+m4+m5+m6+m7+m8/spot=price-capacity-optimized/extras=s3-cache+tmpfs"
+    #   tmpfs intentionally omitted -- it RAM-backs /home/runner, /tmp and /var/lib/docker at
+    #   100% of instance memory, starving `make unit` of headroom to link with -race.
+    #   volume: the caches and docker images tmpfs used to hold. gp3 baseline throughput is
+    #   enough; a 4 vCPU instance can't pull much more than that anyway.
+    #   note: s3-cache intentionally omitted -- PR runs are untrusted and must not write to the
+    #   shared cache backend that the trusted release workflow reads from (cache poisoning).
+    runs-on: &test-runner "runs-on=${{ 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@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -45,11 +49,18 @@ jobs:
   Unit-Test:
     # Note: changing this job name requires making the same update in the .github/workflows/release.yaml pipeline
     name: "Unit tests"
+    runs-on: ubuntu-latest
+    needs: [Unit-Test-Linux, Unit-Test-Windows]
+    steps:
+      - run: echo All unit tests passed!
+
+  Unit-Test-Linux:
+    name: "Unit tests (Linux)"
     runs-on: *test-runner
     permissions:
       contents: read
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -64,6 +75,27 @@ jobs:
       - 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"
@@ -71,7 +103,7 @@ jobs:
     permissions:
       contents: read
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -91,16 +123,20 @@ jobs:
     # runs-on.com: compute instances for parallel builds
     #   spot disabled: reliability for build workflows (used for releases too)
     #   goreleaser uses parallelism of 12, so we need more CPUs
-    #   s3-cache: faster actions cache
-    #   tmpfs: faster io-intensive workflows
-    runs-on: "runs-on=${{ github.run_id }}/cpu=16+32/ram=32+128/family=c5+c6+c7+c8/spot=false/extras=s3-cache+tmpfs"
+    #   tmpfs intentionally omitted -- a RAM-backed dist/ competes with the goreleaser
+    #   build's memory peak (parallel binaries + multi-arch image assembly) and OOMs the
+    #   instance; keep dist/ on disk.
+    #   note: s3-cache intentionally omitted -- PR runs are untrusted and must not write to the
+    #   shared cache backend that the trusted release workflow reads from (cache poisoning).
+    #   volume: enlarge dist/ disk -- the default 40GB EBS root fills up during the multi-arch
+    #   image + binary build and OOMs (runs out of disk); size it well above peak usage.
+    #   provisioned throughput/iops above the gp3 free baseline (125mbs/3000iops) approximate
+    #   the tmpfs IO speed on disk, for ~1c/run.
+    runs-on: "runs-on=${{ 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:
-      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -130,10 +166,7 @@ jobs:
     permissions:
       contents: read
     steps:
-      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -175,9 +208,9 @@ jobs:
       contents: read
     steps:
       - name: Install Cosign
-        uses: sigstore/cosign-installer@cad07c2e89fa2edd6e2d7bab4c1aa38e53f76003 # v4.1.1
+        uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2
 
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 
@@ -211,10 +244,7 @@ jobs:
     permissions:
       contents: read
     steps:
-      # required for magic-cache from runs-on to function with artifact upload/download (see https://runs-on.com/caching/magic-cache/#actionsupload-artifact-compatibility)
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd #v6.0.2
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1
         with:
           persist-credentials: false
 

.github/zizmor.yml

@@ -1,9 +1,4 @@
 rules:
-  unpinned-uses:
-    config:
-      policies:
-        # anchore/workflows is an internal repository; using @main is acceptable
-        anchore/*: any
   dangerous-triggers:
     ignore:
       # Safe use of pull_request_target - only runs trusted scripts from base repo,

.gitignore

@@ -3,6 +3,8 @@ go.work
 go.work.sum
 .tool-versions
 .python-version
+.mise.toml
+.env
 
 # app configuration
 /.syft.yaml
@@ -18,8 +20,11 @@ bin/
 /.tool
 /.task
 /generate
+/spec
 /specs
 mise.toml
+.make/.make
+.conductor
 
 # changelog generation
 CHANGELOG.md
@@ -76,5 +81,3 @@ cosign.pub
 __pycache__/
 *.py[cod]
 *$py.class
-
-

.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
@@ -54,6 +66,12 @@ linters:
       - 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$
@@ -61,7 +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
@@ -70,7 +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
@@ -96,11 +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

@@ -73,306 +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}}-riscv64
-      - ghcr.io/anchore/syft:{{.Tag}}-riscv64
-    goarch: riscv64
-    dockerfile: Dockerfile
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/riscv64"
-      - "--build-arg=DEBIAN_VERSION=13"
-      - "--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-riscv64
-      - ghcr.io/anchore/syft:{{.Tag}}-nonroot-riscv64
-    goarch: riscv64
-    dockerfile: Dockerfile.nonroot
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/riscv64"
-      - "--build-arg=DEBIAN_VERSION=13"
-      - "--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-riscv64
-      - ghcr.io/anchore/syft:{{.Tag}}-debug-riscv64
-    goarch: riscv64
-    dockerfile: Dockerfile.debug
-    use: buildx
-    build_flag_templates:
-      - "--platform=linux/riscv64"
-      - "--build-arg=DEBIAN_VERSION=13"
-      - "--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}}-riscv64
-      - 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}}-riscv64
-      - 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}}-riscv64
-      - 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}}-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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-riscv64
-      - 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

.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)
+			}
+		})
+	}
+}

Dockerfile

@@ -1,4 +1,4 @@
-ARG DEBIAN_VERSION=12
+ARG DEBIAN_VERSION=13
 FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:latest AS build
 
 FROM scratch
@@ -8,23 +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

@@ -1,28 +1,10 @@
-ARG DEBIAN_VERSION=12
-FROM gcr.io/distroless/static-debian${DEBIAN_VERSION}:debug-nonroot
+ARG DEBIAN_VERSION=13
+FROM gcr.io/distroless/static-debian${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

@@ -1,28 +1,12 @@
-ARG DEBIAN_VERSION=12
+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) && NO_COLOR=1 $(TASK) -l | grep '^\* ' | cut -d' ' -f2 | tr -d ':' | tr '\n' ' '" ) $(shell bash -c "test -f $(TASK) && NO_COLOR=1 $(TASK) -l | grep 'aliases:' | cut -d ':' -f 3 | tr '\n' ' ' | tr -d ','")
-
-.PHONY: $(TASKS)
-$(TASKS): $(TASK)
-	@$(TASK) $@
-
-help: $(TASK)
-	@$(TASK) -l
+	@go run -C .make . $@

README.md

@@ -8,10 +8,9 @@
 
 <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>

Taskfile.yaml

@@ -1,6 +1,11 @@
-
 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
 
@@ -25,11 +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:
@@ -38,15 +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
@@ -57,43 +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:
@@ -102,10 +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 }}/*"
@@ -114,79 +81,14 @@ 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
@@ -203,8 +105,8 @@ tasks:
     cmds:
       - .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:
@@ -214,60 +116,35 @@ 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:
-      - task: clean-test-observations
-      - "go test -coverprofile {{ .TMP_DIR }}/unit-coverage-details.txt {{ .TEST_PKGS }}"
-      - cmd: ".github/scripts/coverage.py {{ .COVERAGE_THRESHOLD }} {{ .TMP_DIR }}/unit-coverage-details.txt"
-        silent: true
-
-  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
+    deps: [tmpdir]
     # this will look for `testdata/Makefile` and invoke the `fingerprint` target to calculate all cache input fingerprint files
     generates:
       - '**/testdata/**/*.fingerprint'
@@ -281,16 +158,10 @@ tasks:
         echo -e "${YELLOW}creating fingerprint files for non-docker fixtures...${RESET}"
         for dir in $(find . -type d -name 'testdata'); do
           if [ -f "$dir/Makefile" ]; then
-            # for debugging...
-            #echo -e "${YELLOW}• calculating fingerprints in $dir... ${RESET}"
-
             (make -C "$dir" fingerprint)
           fi
         done
 
-        # for debugging...
-        # echo -e "generated all fixture fingerprints"
-
       - .github/scripts/fingerprint_docker_fixtures.py
       - |
         # if DOWNLOAD_TEST_FIXTURE_CACHE is set to 'false', then we don't need to calculate the fingerprint for the cache
@@ -432,6 +303,7 @@ tasks:
       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:'"
@@ -452,28 +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:
+    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 \
@@ -483,11 +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 \
@@ -497,6 +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 \
@@ -506,7 +389,7 @@ tasks:
         {{ .TMP_DIR }}
 
 
-  ## Code and data generation targets #################################
+  ## Code and data generation targets ######################################
 
   generate:
     desc: Add data generation tasks
@@ -556,104 +439,7 @@ tasks:
       - "SYFT_ENABLE_COMPLETENESS_TESTS=true go test -p 1 ./internal/capabilities/... -count=1"
 
 
-  ## Build-related targets #################################
-
-  build:
-    desc: Build the project
-    deps: [tools, tmpdir]
-    generates:
-      - "{{ .PROJECT }}"
-    cmds:
-      - silent: true
-        cmd: |
-          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
-          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
-
-      - "{{ .BUILD_CMD }}"
-
-  snapshot:
-    desc: Create a snapshot release
-    aliases:
-      - build
-    deps: [tools, tmpdir]
-    sources:
-      - cmd/**/*.go
-      - syft/**/*.go
-      - internal/**/*.go
-    method: checksum
-    generates:
-      - "{{ .SNAPSHOT_BIN }}"
-    cmds:
-      - silent: true
-        cmd: |
-          echo "dist: {{ .SNAPSHOT_DIR }}" > {{ .TMP_DIR }}/goreleaser.yaml
-          cat .goreleaser.yaml >> {{ .TMP_DIR }}/goreleaser.yaml
-
-      - "{{ .SNAPSHOT_CMD }}"
-
-  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 }}"
-
-
-  ## Release targets #################################
-
-  release:
-    desc: Create a release
-    interactive: true
-    deps: [tools]
-    cmds:
-      - cmd: .github/scripts/trigger-release.sh
-        silent: true
-
-
-  ## CI-only targets #################################
-
-  ci-check:
-    # desc: "[CI only] Are you in CI?"
-    cmds:
-      - cmd: .github/scripts/ci-check.sh
-        silent: true
-
-  ci-release:
-    # desc: "[CI only] Create a release"
-    deps: [tools]
-    cmds:
-      - task: ci-check
-      - "{{ .TOOL_DIR }}/chronicle -vvv > CHANGELOG.md"
-      - cmd: "cat CHANGELOG.md"
-        silent: true
-      - "{{ .RELEASE_CMD }}"
-
-
-  ## Cleanup targets #################################
-
-  clean:
-    desc: Remove all cache files and old builds
-    cmds:
-      - task: clean-snapshot
-      - task: clean-cache
-      - task: clean-test-observations
-      - task: clean-docker-cache
-      - task: clean-oras-cache
+  ## Cleanup targets ########################################################
 
   clean-snapshot:
     desc: Remove any snapshot builds
@@ -675,6 +461,7 @@ 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'
@@ -690,6 +477,12 @@ tasks:
         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:

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 {

cmd/syft/internal/commands/cataloger_info.go

@@ -60,6 +60,7 @@ type (
 		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"`
 	}
@@ -235,7 +236,7 @@ func renderCatalogerInfoJSON(doc *capabilities.Document, catalogers []capabiliti
 		// if no parsers, use detectors instead
 		if len(info.Patterns) == 0 {
 			info.Capabilities = cat.Capabilities
-			info.Patterns = convertDetectorsToPatterns(cat.Detectors, cat.PackageTypes, cat.JSONSchemaTypes)
+			info.Patterns = convertDetectorsToPatterns(cat.Detectors, cat.PackageTypes, cat.PURLTypes, cat.JSONSchemaTypes)
 		}
 
 		info.Config = getConfigInfoFromDocument(doc, cat.Config)
@@ -278,6 +279,7 @@ func convertParsersToPatterns(parsers []capabilities.Parser) []patternInfo {
 			Packages:        convertDetectorPackages(parser.Detector.Packages),
 			Comment:         parser.Detector.Comment,
 			PackageTypes:    parser.PackageTypes,
+			PURLTypes:       parser.PURLTypes,
 			JSONSchemaTypes: parser.JSONSchemaTypes,
 			Capabilities:    parser.Capabilities,
 		})
@@ -286,7 +288,7 @@ func convertParsersToPatterns(parsers []capabilities.Parser) []patternInfo {
 }
 
 // convertDetectorsToPatterns converts detector entries to pattern info for JSON output (for non-parser catalogers)
-func convertDetectorsToPatterns(detectors []capabilities.Detector, packageTypes, jsonSchemaTypes []string) []patternInfo {
+func convertDetectorsToPatterns(detectors []capabilities.Detector, packageTypes, purlTypes, jsonSchemaTypes []string) []patternInfo {
 	var patterns []patternInfo
 	for _, det := range detectors {
 		patterns = append(patterns, patternInfo{
@@ -296,6 +298,7 @@ func convertDetectorsToPatterns(detectors []capabilities.Detector, packageTypes,
 			Packages:        convertDetectorPackages(det.Packages),
 			Comment:         det.Comment,
 			PackageTypes:    packageTypes,
+			PURLTypes:       purlTypes,
 			JSONSchemaTypes: jsonSchemaTypes,
 		})
 	}
@@ -346,14 +349,14 @@ func renderCatalogerInfoTable(_ *capabilities.Document, catalogers []capabilitie
 		})),
 		tablewriter.WithConfig(tablewriter.Config{
 			Row: tw.CellConfig{
-				Formatting: tw.CellFormatting{MergeMode: tw.MergeHierarchical},
-				Alignment:  tw.CellAlignment{Global: tw.AlignLeft},
+				Merging:   tw.CellMerging{Mode: tw.MergeHierarchical},
+				Alignment: tw.CellAlignment{Global: tw.AlignLeft},
 			},
 		}),
 	)
 
 	// set headers
-	table.Header("ECOSYSTEM", "CATALOGER", "CRITERIA", "LICENSE", "NODES", "EDGES", "KINDS", "LISTING", "DIGESTS", "HASH")
+	table.Header("ECOSYSTEM", "CATALOGER", "CRITERIA", "PURL", "LICENSE", "NODES", "EDGES", "KINDS", "LISTING", "DIGESTS", "HASH")
 
 	// build rows for each cataloger
 	var data [][]string
@@ -367,13 +370,13 @@ func renderCatalogerInfoTable(_ *capabilities.Document, catalogers []capabilitie
 			// generic catalogers: one row per parser
 			for _, parser := range cat.Parsers {
 				criteria := formatCriteria([]capabilities.Detector{parser.Detector})
-				row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, parser.Capabilities)
+				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.Capabilities)
+			row := buildTableRowFromCapabilities(ecosystem, cat.Name, criteria, cat.PURLTypes, cat.Capabilities)
 			data = append(data, row)
 		}
 	}
@@ -385,7 +388,7 @@ func renderCatalogerInfoTable(_ *capabilities.Document, catalogers []capabilitie
 }
 
 // buildTableRowFromCapabilities builds a table row from capability values
-func buildTableRowFromCapabilities(ecosystem, name, criteria string, caps capabilities.CapabilitySet) []string {
+func buildTableRowFromCapabilities(ecosystem, name, criteria string, purlTypes []string, caps capabilities.CapabilitySet) []string {
 	// extract capability default values
 	license := extractBoolCapability(caps, "license")
 	nodes := extractNodesCapability(caps)
@@ -399,6 +402,7 @@ func buildTableRowFromCapabilities(ecosystem, name, criteria string, caps capabi
 		ecosystem,
 		name,
 		criteria,
+		formatPURLTypes(purlTypes),
 		license,
 		nodes,
 		edges,
@@ -409,6 +413,14 @@ func buildTableRowFromCapabilities(ecosystem, name, criteria string, caps capabi
 	}
 }
 
+// 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 {

cmd/syft/internal/commands/cataloger_info_test.go

@@ -280,12 +280,15 @@ func Test_catalogerInfoReport(t *testing.T) {
 					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")
 			},
 		},
 		{
@@ -298,12 +301,17 @@ func Test_catalogerInfoReport(t *testing.T) {
 					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"]`)
 			},
 		},
 		{

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 {
@@ -34,6 +45,7 @@ func Convert(app clio.Application) *cobra.Command {
 	opts := &ConvertOptions{
 		UpdateCheck: options.DefaultUpdateCheck(),
 		Output:      options.DefaultOutput(),
+		Convert:     options.DefaultConvert(),
 	}
 
 	return app.SetupCommand(&cobra.Command{
@@ -46,11 +58,11 @@ func Convert(app clio.Application) *cobra.Command {
 		}),
 		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/scan.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"reflect"
 	"strings"
+	"time"
 
 	"github.com/hashicorp/go-multierror"
 	"github.com/spf13/cobra"
@@ -171,6 +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

cmd/syft/internal/options/catalog.go

@@ -20,6 +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"
@@ -44,6 +45,7 @@ type Catalog struct {
 	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"`
@@ -80,6 +82,7 @@ func DefaultCatalog() Catalog {
 		JavaScript:    defaultJavaScriptConfig(),
 		Python:        defaultPythonConfig(),
 		Nix:           defaultNixConfig(),
+		Cpp:           defaultCppConfig(),
 		Dotnet:        defaultDotnetConfig(),
 		Golang:        defaultGolangConfig(),
 		Java:          defaultJavaConfig(),
@@ -172,11 +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).
@@ -191,7 +198,9 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 					WithFromBuildSettings(cfg.Golang.MainModuleVersion.FromBuildSettings).
 					WithFromLDFlags(cfg.Golang.MainModuleVersion.FromLDFlags),
 			).
-			WithUsePackagesLib(*multiLevelOption(true, enrichmentEnabled(cfg.Enrich, task.Go, task.Golang), cfg.Golang.UsePackagesLib)),
+			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)).
@@ -299,6 +308,7 @@ var publicisedEnrichmentOptions = []string{
 	task.Java,
 	task.JavaScript,
 	task.Python,
+	task.Vcpkg,
 }
 
 func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {

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/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"
 )
 
@@ -17,10 +19,13 @@ type golangConfig struct {
 	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) {
@@ -39,12 +44,44 @@ if unset this defaults to $GONOPROXY`)
 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"`
@@ -66,6 +103,8 @@ func defaultGolangConfig() golangConfig {
 			FromContents:      def.MainModuleVersion.FromContents,
 			FromBuildSettings: def.MainModuleVersion.FromBuildSettings,
 		},
-		UsePackagesLib: nil, // this defaults to true, which is the API default
+		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/test/integration/catalog_packages_test.go

@@ -89,6 +89,8 @@ func TestPkgCoverageImage(t *testing.T) {
 	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...)
@@ -164,6 +166,8 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	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))

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/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/testdata/.gitignore

@@ -7,4 +7,6 @@
 !image-pkg-coverage/pkgs/java/*.hpi
 
 **/go.sum
-!image-go-bin-arch-coverage/go.sum
+!image-go-bin-arch-coverage/go.sum
+
+cache/

cmd/syft/internal/test/integration/testdata/image-java-no-main-package/Dockerfile

@@ -8,8 +8,6 @@ RUN mkdir tmp
 
 WORKDIR /usr/share/jenkins/tmp
 
-RUN apt-get update 2>&1 > /dev/null && apt-get install -y less zip 2>&1 > /dev/null
-
 RUN unzip ../jenkins.war 2>&1 > /dev/null
 
 RUN rm -rf ./META-INF/MANIFEST.MF ./WEB-INF ./jsbundles ./scripts ./css
@@ -18,7 +16,8 @@ WORKDIR /usr/share/jenkins
 
 RUN rm -rf jenkins.war
 
-RUN cd ./tmp && zip -r ../jenkins.war . && cd ..
+# use jar (from the JDK in the base image) to rezip -- M keeps it manifest-less, which is the point of this fixture
+RUN cd ./tmp && jar cfM ../jenkins.war . && cd ..
 
 RUN rm -rf ./tmp
 

cmd/syft/internal/test/integration/testdata/image-pkg-coverage/Dockerfile

@@ -16,7 +16,7 @@ RUN unxz /lib/modules/6.0.7-301.fc37.x86_64/kernel/drivers/tty/ttynull.ko.xz
 # dotnet pkg coverage
 # https://nuget.info/packages/DocuSign.eSign.dll/6.8.0
 # https://github.com/docusign/docusign-esign-csharp-client/blob/master/LICENSE
-RUN curl -LO https://www.nuget.org/api/v2/package/DocuSign.eSign.dll/6.8.0
+RUN curl -fLO https://www.nuget.org/api/v2/package/DocuSign.eSign.dll/6.8.0
 RUN unzip 6.8.0
 RUN chmod 600 lib/net462/DocuSign.eSign.dll
 RUN rm 6.8.0

cmd/syft/internal/ui/ui.go

@@ -1,6 +1,7 @@
 package ui
 
 import (
+	"bytes"
 	"fmt"
 	"io"
 	"os"
@@ -8,6 +9,7 @@ import (
 	"time"
 
 	tea "github.com/charmbracelet/bubbletea"
+	"github.com/charmbracelet/lipgloss"
 	"github.com/wagoodman/go-partybus"
 
 	"github.com/anchore/bubbly"
@@ -52,7 +54,7 @@ func New(out io.Writer, quiet bool, handlers ...bubbly.EventHandler) *UI {
 func (m *UI) Setup(subscription partybus.Unsubscribable) error {
 	// we still want to collect log messages, however, we also the logger shouldn't write to the screen directly
 	if logWrapper, ok := log.Get().(logger.Controller); ok {
-		logWrapper.SetOutput(m.frame.(*frame.Frame).Footer())
+		logWrapper.SetOutput(&logFooter{w: m.frame.(*frame.Frame).Footer()})
 	}
 
 	m.subscription = subscription
@@ -100,7 +102,7 @@ func (m *UI) Teardown(force bool) error {
 		})
 
 		// it may be tempting to use Kill() however it has been found that this can cause the terminal to be left in
-		// a bad state (where Ctrl+C and other control characters no longer works for future processes in that terminal).
+		// a bad state (where Ctrl+C and other control characters no longer work for future processes in that terminal).
 		m.program.Quit()
 
 		_ = runWithTimeout(250*time.Millisecond, func() error {
@@ -187,6 +189,48 @@ func (m UI) View() string {
 	return m.frame.View()
 }
 
+var (
+	logTitleStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("8")) // dark grey
+	// the first log line gets a branch pointing at it from the title, the rest are indented to match
+	logBranch = logTitleStyle.Render("└─▶") + " "
+	logIndent = "    "
+)
+
+// logFooter decorates log entries drawn below the TUI with a one-time title (written when the first entry arrives)
+// and a branch from the title to the first log line. Writes are serialized by the logger.
+type logFooter struct {
+	w       io.Writer
+	started bool
+}
+
+func (l *logFooter) Write(p []byte) (int, error) {
+	var buf bytes.Buffer
+	first := !l.started
+	if first {
+		buf.WriteString(logTitleStyle.Render("Logs (non-fatal, see -v for more):") + "\n")
+		l.started = true
+	}
+	for i, line := range bytes.SplitAfter(p, []byte("\n")) {
+		if len(line) == 0 {
+			continue
+		}
+		if first && i == 0 {
+			buf.WriteString(logBranch)
+		} else {
+			buf.WriteString(logIndent)
+		}
+		buf.Write(line)
+	}
+	if _, err := l.w.Write(buf.Bytes()); err != nil {
+		return 0, err
+	}
+	return len(p), nil
+}
+
+// IsTerminal marks the footer as terminal-bound (it is drawn by the TUI) so the logger keeps colors. NO_COLOR is
+// still honored by the formatter.
+func (*logFooter) IsTerminal() bool { return true }
+
 func runWithTimeout(timeout time.Duration, fn func() error) (err error) {
 	c := make(chan struct{}, 1)
 	go func() {

examples/README.md

@@ -5,8 +5,10 @@ This directory contains examples of how to use the Syft API.
 - `create_simple_sbom`: Create a simple SBOM from scratch
 - `create_custom_sbom`: Create an SBOM using as much custom configuration as possible, including a custom cataloger implementation
 - `decode_sbom`: Take an existing SBOM file (of arbitrary format) and decode it into a Syft SBOM object
+- `select_catalogers`: Example demonstrating how to select specific catalogers to run
 - `source_detection`: Shows how to detect what to catalog automatically from a user string (e.g. container image vs directory)
-- `source_from_image`: Construct a source from a only a container image
+- `source_from_image`: Construct a source from only a container image
+- `source_from_registry`: Construct a source directly from a container registry
 
 You can run any of these examples from this directory with:
 

go.mod

@@ -1,28 +1,28 @@
 module github.com/anchore/syft
 
-go 1.25.8
+go 1.26.8
 
 require (
 	github.com/BurntSushi/toml v1.6.0
-	github.com/CycloneDX/cyclonedx-go v0.10.0
-	github.com/Masterminds/semver/v3 v3.4.0
+	github.com/CycloneDX/cyclonedx-go v0.12.0
+	github.com/Masterminds/semver/v3 v3.5.0
 	github.com/Masterminds/sprig/v3 v3.3.0
 	github.com/OneOfOne/xxhash v1.2.8
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d
 	github.com/acobaugh/osrelease v0.1.0
 	github.com/adrg/xdg v0.5.3
-	github.com/anchore/bubbly v0.2.0
-	github.com/anchore/clio v0.1.0
-	github.com/anchore/fangs v0.1.0
-	github.com/anchore/go-collections v0.1.0
-	github.com/anchore/go-homedir v0.1.0
-	github.com/anchore/go-logger v0.1.0
-	github.com/anchore/go-macholibre v0.1.0
-	github.com/anchore/go-rpmdb v0.1.0
-	github.com/anchore/go-sync v0.1.0
+	github.com/anchore/bubbly v0.2.2
+	github.com/anchore/clio v0.1.1
+	github.com/anchore/fangs v0.1.1
+	github.com/anchore/go-collections v0.1.1
+	github.com/anchore/go-homedir v0.1.1
+	github.com/anchore/go-logger v0.2.0
+	github.com/anchore/go-macholibre v0.1.1
+	github.com/anchore/go-rpmdb v0.2.0
+	github.com/anchore/go-sync v0.1.2
 	github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b
 	github.com/anchore/packageurl-go v0.2.0
-	github.com/anchore/stereoscope v0.1.23
+	github.com/anchore/stereoscope v0.3.2
 	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
 	github.com/aquasecurity/go-pep440-version v0.0.1
 	github.com/bitnami/go-version v0.0.0-20250131085805-b1f57a8634ef
@@ -34,39 +34,40 @@ require (
 	github.com/charmbracelet/lipgloss v1.1.0
 	github.com/dave/jennifer v1.7.1
 	github.com/deitch/magic v0.0.0-20230404182410-1ff89d7342da
-	github.com/diskfs/go-diskfs v1.7.0
+	github.com/diskfs/go-diskfs v1.9.4
 	github.com/distribution/reference v0.6.0
-	github.com/dustin/go-humanize v1.0.1
+	github.com/dustin/go-humanize v1.1.0
 	github.com/elliotchance/phpserialize v1.4.0
 	github.com/facebookincubator/nvdtools v0.1.5
-	github.com/github/go-spdx/v2 v2.4.0
-	github.com/gkampitakis/go-snaps v0.5.21
-	github.com/go-git/go-billy/v5 v5.9.0
-	github.com/go-git/go-git/v5 v5.19.0
+	github.com/github/go-spdx/v2 v2.7.0
+	github.com/gkampitakis/go-snaps v0.5.23
+	github.com/go-git/go-billy/v5 v5.9.1
+	github.com/go-git/go-git/v5 v5.19.2
 	github.com/go-test/deep v1.1.1
 	github.com/go-viper/mapstructure/v2 v2.5.0
 	github.com/goccy/go-yaml v1.19.2
 	github.com/gohugoio/hashstructure v0.6.0
 	github.com/google/go-cmp v0.7.0
-	github.com/google/go-containerregistry v0.21.5
+	github.com/google/go-containerregistry v0.22.1
 	github.com/google/licensecheck v0.3.1
 	github.com/google/uuid v1.6.0
-	github.com/gookit/color v1.6.0
-	github.com/gpustack/gguf-parser-go v0.24.0
+	github.com/gookit/color v1.6.1
+	github.com/gpustack/gguf-parser-go v0.26.3
 	github.com/hashicorp/go-cleanhttp v0.5.2
-	github.com/hashicorp/go-getter v1.8.6
+	github.com/hashicorp/go-getter v1.8.9
 	github.com/hashicorp/go-multierror v1.1.1
-	github.com/hashicorp/hcl/v2 v2.24.0
+	github.com/hashicorp/hcl/v2 v2.25.0
 	github.com/iancoleman/strcase v0.3.0
-	github.com/invopop/jsonschema v0.13.0
-	github.com/jedib0t/go-pretty/v6 v6.7.8
+	github.com/invopop/jsonschema v0.14.0
+	github.com/jedib0t/go-pretty/v6 v6.8.3
 	github.com/jinzhu/copier v0.4.0
 	github.com/kastenhq/goversion v0.0.0-20230811215019-93b2f8823953
-	github.com/magiconair/properties v1.8.10
+	github.com/klauspost/compress v1.20.0
+	github.com/magiconair/properties v1.18.12
 	github.com/mholt/archives v0.1.5
 	github.com/moby/sys/mountinfo v0.7.2
 	github.com/nix-community/go-nix v0.0.0-20250101154619-4bdde671e0a1
-	github.com/olekukonko/tablewriter v1.1.4
+	github.com/olekukonko/tablewriter v1.1.5
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/pelletier/go-toml v1.9.5
 	github.com/quasilyte/go-ruleguard/dsl v0.3.23
@@ -78,75 +79,78 @@ require (
 	github.com/scylladb/go-set v1.0.3-0.20200225121959-cc7b2070d91e
 	github.com/sergi/go-diff v1.4.0
 	github.com/spdx/gordf v0.0.0-20201111095634-7098f93598fb
-	github.com/spdx/tools-golang v0.5.7
+	github.com/spdx/tools-golang v0.6.0-rc4
 	github.com/spf13/afero v1.15.0
 	github.com/spf13/cobra v1.10.2
-	github.com/stretchr/testify v1.11.1
-	github.com/ulikunitz/xz v0.5.15
+	github.com/stretchr/testify v1.12.1
+	github.com/ulikunitz/xz v0.5.16
 	github.com/vbatts/go-mtree v0.7.0
 	github.com/vifraa/gopom v1.0.0
 	github.com/wagoodman/go-partybus v0.0.0-20230516145632-8ccac152c651
 	github.com/wagoodman/go-progress v0.0.0-20260303201901-10176f79b2c0
-	github.com/wk8/go-ordered-map/v2 v2.1.8
 	github.com/xeipuuv/gojsonschema v1.2.0
 	github.com/zyedidia/generic v1.2.2-0.20230320175451-4410d2372cb1
 	go.uber.org/goleak v1.3.0
-	go.yaml.in/yaml/v3 v3.0.4
+	go.yaml.in/yaml/v3 v3.0.5
 	golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f
-	golang.org/x/mod v0.35.0
-	golang.org/x/net v0.53.0
-	golang.org/x/time v0.15.0
-	golang.org/x/tools v0.44.0
-	gopkg.in/yaml.v3 v3.0.1
-	modernc.org/sqlite v1.46.2
+	golang.org/x/mod v0.41.0
+	golang.org/x/net v0.59.0
+	golang.org/x/time v0.16.0
+	golang.org/x/tools v0.50.0
+	modernc.org/sqlite v1.59.0
 )
 
 require (
-	cel.dev/expr v0.25.1 // indirect
+	github.com/pb33f/ordered-map/v2 v2.3.1
+	github.com/tailscale/hujson v0.0.0-20260302212456-ecc657c15afd
+	howett.net/plist v1.0.1
+)
+
+require (
+	cel.dev/expr v0.25.2 // indirect
 	cloud.google.com/go v0.123.0 // indirect
-	cloud.google.com/go/auth v0.18.2 // indirect
+	cloud.google.com/go/auth v0.23.2 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
-	cloud.google.com/go/iam v1.5.3 // indirect
-	cloud.google.com/go/monitoring v1.24.3 // indirect
-	cloud.google.com/go/storage v1.61.3 // indirect
-	cyphar.com/go-pathrs v0.2.1 // indirect
+	cloud.google.com/go/iam v1.12.0 // indirect
+	cloud.google.com/go/monitoring v1.30.0 // indirect
+	cloud.google.com/go/storage v1.65.1 // indirect
 	dario.cat/mergo v1.0.2 // indirect
 	github.com/DataDog/zstd v1.5.5 // indirect
-	github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.30.0 // indirect
-	github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.55.0 // indirect
-	github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.55.0 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.33.0 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/exporter/metric v0.57.0 // indirect
+	github.com/GoogleCloudPlatform/opentelemetry-operations-go/internal/resourcemapping v0.57.0 // indirect
 	github.com/Masterminds/goutils v1.1.1 // indirect
-	github.com/Microsoft/go-winio v0.6.2 // indirect
-	github.com/Microsoft/hcsshim v0.14.0-rc.1 // indirect
-	github.com/ProtonMail/go-crypto v1.4.0 // indirect
+	github.com/Microsoft/go-winio v0.6.3-0.20251027160822-ad3df93bed29 // indirect
+	github.com/Microsoft/hcsshim v0.15.0-rc.1 // indirect
+	github.com/ProtonMail/go-crypto v1.4.1 // indirect
 	github.com/STARRY-S/zip v0.2.3 // indirect
 	github.com/agext/levenshtein v1.2.1 // indirect
-	github.com/anchore/go-lzo v0.1.0 // indirect
-	github.com/anchore/go-struct-converter v0.1.0 // indirect
+	github.com/anchore/go-lzo v0.1.1 // indirect
+	github.com/anchore/go-struct-converter v0.2.0-rc2 // indirect
 	github.com/andybalholm/brotli v1.2.0 // indirect
 	github.com/apparentlymart/go-textseg/v15 v15.0.0 // indirect
+	github.com/apparentlymart/go-textseg/v17 v17.0.1 // indirect
 	github.com/aquasecurity/go-version v0.0.1 // indirect
 	github.com/atotto/clipboard v0.1.4 // indirect
-	github.com/aws/aws-sdk-go-v2 v1.41.5 // indirect
-	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 // indirect
-	github.com/aws/aws-sdk-go-v2/config v1.32.12 // indirect
-	github.com/aws/aws-sdk-go-v2/credentials v1.19.12 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.20 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 // indirect
-	github.com/aws/aws-sdk-go-v2/service/s3 v1.97.3 // indirect
-	github.com/aws/aws-sdk-go-v2/service/signin v1.0.8 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.30.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.17 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.41.9 // indirect
-	github.com/aws/smithy-go v1.24.2 // indirect
+	github.com/aws/aws-sdk-go-v2 v1.44.0 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.20 // indirect
+	github.com/aws/aws-sdk-go-v2/config v1.32.40 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.39 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.40 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.40 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.40 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.41 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.19 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.10.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.40 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.41 // indirect
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.108.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/signin v1.6.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.34.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.39.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.46.0 // indirect
+	github.com/aws/smithy-go v1.28.1 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/bahlo/generic-list-go v0.2.0 // indirect
 	github.com/becheran/wildmatch-go v1.0.0 // indirect
@@ -155,59 +159,57 @@ require (
 	github.com/bodgit/sevenzip v1.6.1 // indirect
 	github.com/bodgit/windows v1.0.1 // indirect
 	github.com/buger/jsonparser v1.1.2 // indirect
-	github.com/charmbracelet/colorprofile v0.4.1 // indirect
+	github.com/charmbracelet/colorprofile v0.4.3 // indirect
 	github.com/charmbracelet/harmonica v0.2.0 // indirect
 	github.com/charmbracelet/x/ansi v0.11.6 // indirect
 	github.com/charmbracelet/x/cellbuf v0.0.15 // indirect
 	github.com/charmbracelet/x/term v0.2.2 // indirect
-	github.com/clipperhouse/displaywidth v0.10.0 // indirect
-	github.com/clipperhouse/uax29/v2 v2.6.0 // indirect
+	github.com/clipperhouse/displaywidth v0.11.0 // indirect
+	github.com/clipperhouse/uax29/v2 v2.7.0 // indirect
 	github.com/cloudflare/circl v1.6.3 // indirect
-	github.com/cncf/xds/go v0.0.0-20251210132809-ee656c7534f5 // indirect
-	github.com/containerd/cgroups/v3 v3.1.2 // indirect
-	github.com/containerd/containerd/api v1.10.0 // indirect
-	github.com/containerd/containerd/v2 v2.2.2 // indirect
-	github.com/containerd/continuity v0.4.5 // indirect
+	github.com/cncf/xds/go v0.0.0-20260202195803-dba9d589def2 // indirect
+	github.com/containerd/cgroups/v3 v3.1.3 // indirect
+	github.com/containerd/containerd/api v1.11.1 // indirect
+	github.com/containerd/containerd/v2 v2.3.6 // indirect
+	github.com/containerd/continuity v0.5.0 // indirect
 	github.com/containerd/errdefs v1.0.0 // indirect
 	github.com/containerd/errdefs/pkg v0.3.0 // indirect
 	github.com/containerd/fifo v1.1.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
-	github.com/containerd/platforms v1.0.0-rc.4 // indirect
-	github.com/containerd/plugin v1.0.0 // indirect
-	github.com/containerd/stargz-snapshotter/estargz v0.18.2 // indirect
-	github.com/containerd/ttrpc v1.2.7 // indirect
+	github.com/containerd/platforms v1.0.0-rc.5 // indirect
+	github.com/containerd/plugin v1.1.0 // indirect
+	github.com/containerd/ttrpc v1.2.8 // indirect
 	github.com/containerd/typeurl/v2 v2.2.3 // indirect
 	github.com/cyphar/filepath-securejoin v0.6.1 // indirect
-	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
-	github.com/docker/cli v29.4.0+incompatible // indirect
+	github.com/docker/cli v29.8.0+incompatible // indirect
 	github.com/docker/docker-credential-helpers v0.9.5 // indirect
-	github.com/docker/go-connections v0.6.0 // indirect
+	github.com/docker/go-connections v0.8.1 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/dsnet/compress v0.0.2-0.20230904184137-39efe44ab707 // indirect
 	github.com/emirpasic/gods v1.18.1 // indirect
-	github.com/envoyproxy/go-control-plane/envoy v1.36.0 // indirect
-	github.com/envoyproxy/protoc-gen-validate v1.3.0 // indirect
+	github.com/envoyproxy/go-control-plane/envoy v1.37.0 // indirect
+	github.com/envoyproxy/protoc-gen-validate v1.3.3 // indirect
 	github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f // indirect
-	github.com/fatih/color v1.18.0 // indirect
+	github.com/fatih/color v1.19.0 // indirect
 	github.com/felixge/fgprof v0.9.5 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fsnotify/fsnotify v1.9.0 // indirect
-	github.com/gabriel-vasile/mimetype v1.4.13 // indirect
-	github.com/gkampitakis/ciinfo v0.3.2 // indirect
+	github.com/gabriel-vasile/mimetype v1.4.15 // indirect
+	github.com/gkampitakis/ciinfo v0.3.4 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/go-jose/go-jose/v4 v4.1.4 // indirect
-	github.com/go-logr/logr v1.4.3 // indirect
+	github.com/go-logr/logr v1.4.4 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-restruct/restruct v1.2.0-alpha // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
-	github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e // indirect
+	github.com/google/pprof v0.0.0-20260802141513-ef3492d7dac3 // indirect
 	github.com/google/s2a-go v0.1.9 // indirect
-	github.com/googleapis/enterprise-certificate-proxy v0.3.14 // indirect
-	github.com/googleapis/gax-go/v2 v2.17.0 // indirect
-	github.com/hashicorp/aws-sdk-go-base/v2 v2.0.0-beta.72 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.3.20 // indirect
+	github.com/googleapis/gax-go/v2 v2.24.0 // indirect
+	github.com/hashicorp/aws-sdk-go-base/v2 v2.0.0-beta.74 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/hashicorp/go-version v1.8.0 // indirect
+	github.com/hashicorp/go-version v1.9.0 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
 	github.com/henvic/httpretty v0.1.4 // indirect
 	github.com/huandu/xstrings v1.5.0 // indirect
@@ -215,18 +217,16 @@ require (
 	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/kevinburke/ssh_config v1.2.0 // indirect
-	github.com/klauspost/compress v1.18.5 // indirect
 	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
 	github.com/klauspost/pgzip v1.2.6 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/lucasb-eyer/go-colorful v1.3.0 // indirect
-	github.com/mailru/easyjson v0.7.7 // indirect
-	github.com/maruel/natural v1.1.1 // indirect
+	github.com/maruel/natural v1.3.0 // indirect
 	github.com/mattn/go-colorable v0.1.14 // indirect
-	github.com/mattn/go-isatty v0.0.20 // indirect
+	github.com/mattn/go-isatty v0.0.24 // indirect
 	github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75 // indirect
-	github.com/mattn/go-runewidth v0.0.19 // indirect
+	github.com/mattn/go-runewidth v0.0.21 // indirect
 	github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d // indirect
 	github.com/mikelolasagasti/xz v1.0.1 // indirect
 	github.com/minio/minlz v1.0.1 // indirect
@@ -236,8 +236,8 @@ require (
 	github.com/mitchellh/reflectwalk v1.0.2 // indirect
 	github.com/moby/docker-image-spec v1.3.1 // indirect
 	github.com/moby/locker v1.0.1 // indirect
-	github.com/moby/moby/api v1.54.1 // indirect
-	github.com/moby/moby/client v0.4.0 // indirect
+	github.com/moby/moby/api v1.56.0 // indirect
+	github.com/moby/moby/client v0.6.0 // indirect
 	github.com/moby/sys/sequential v0.6.0 // indirect
 	github.com/moby/sys/signal v0.7.1 // indirect
 	github.com/moby/sys/user v0.4.0 // indirect
@@ -248,22 +248,22 @@ require (
 	github.com/muesli/cancelreader v0.2.2 // indirect
 	github.com/muesli/termenv v0.16.0 // indirect
 	github.com/ncruces/go-strftime v1.0.0 // indirect
-	github.com/nwaples/rardecode/v2 v2.2.0 // indirect
+	github.com/nwaples/rardecode/v2 v2.4.1 // indirect
 	github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6 // indirect
 	github.com/olekukonko/errors v1.2.0 // indirect
 	github.com/olekukonko/ll v0.1.6 // indirect
 	github.com/opencontainers/image-spec v1.1.1 // indirect
 	github.com/opencontainers/runtime-spec v1.3.0 // indirect
-	github.com/opencontainers/selinux v1.13.1 // indirect
 	github.com/pborman/indent v1.2.1 // indirect
-	github.com/pelletier/go-toml/v2 v2.2.4 // indirect
-	github.com/pierrec/lz4/v4 v4.1.22 // indirect
+	github.com/pelletier/go-toml/v2 v2.4.3 // indirect
+	github.com/pierrec/lz4/v4 v4.1.26 // indirect
+	github.com/piprate/json-gold v0.7.0 // indirect
 	github.com/pjbgf/sha1cd v0.6.0 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pkg/profile v1.7.0 // indirect
-	github.com/pkg/xattr v0.4.9 // indirect
+	github.com/pkg/xattr v0.4.12 // indirect
 	github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 // indirect
-	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/pquerna/cachecontrol v0.0.0-20180517163645-1555304b9b35 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/rogpeppe/go-internal v1.14.1 // indirect
@@ -278,52 +278,52 @@ require (
 	github.com/spf13/cast v1.10.0 // indirect
 	github.com/spf13/pflag v1.0.10 // indirect
 	github.com/spf13/viper v1.21.0 // indirect
-	github.com/spiffe/go-spiffe/v2 v2.6.0 // indirect
-	github.com/stretchr/objx v0.5.2 // indirect
+	github.com/spiffe/go-spiffe/v2 v2.7.0 // indirect
+	github.com/stretchr/objx v0.5.3 // indirect
 	github.com/subosito/gotenv v1.6.0 // indirect
-	github.com/sylabs/sif/v2 v2.24.0 // indirect
+	github.com/sylabs/sif/v2 v2.24.1 // indirect
 	github.com/sylabs/squashfs v1.0.6 // indirect
 	github.com/therootcompany/xz v1.0.1 // indirect
-	github.com/tidwall/gjson v1.18.0 // indirect
+	github.com/tidwall/gjson v1.19.0 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/sjson v1.2.5 // indirect
-	github.com/vbatts/tar-split v0.12.2 // indirect
 	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb // indirect
 	github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 // indirect
 	github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 // indirect
 	github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
-	github.com/zclconf/go-cty v1.16.3 // indirect
+	github.com/zclconf/go-cty v1.19.0 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
-	go.opentelemetry.io/contrib/detectors/gcp v1.39.0 // indirect
-	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.63.0 // indirect
-	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 // indirect
-	go.opentelemetry.io/otel v1.43.0 // indirect
-	go.opentelemetry.io/otel/metric v1.43.0 // indirect
-	go.opentelemetry.io/otel/sdk v1.43.0 // indirect
-	go.opentelemetry.io/otel/sdk/metric v1.43.0 // indirect
-	go.opentelemetry.io/otel/trace v1.43.0 // indirect
+	go.opentelemetry.io/contrib/detectors/gcp v1.44.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.68.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.68.0 // indirect
+	go.opentelemetry.io/otel v1.45.0 // indirect
+	go.opentelemetry.io/otel/metric v1.45.0 // indirect
+	go.opentelemetry.io/otel/sdk v1.45.0 // indirect
+	go.opentelemetry.io/otel/sdk/metric v1.45.0 // indirect
+	go.opentelemetry.io/otel/trace v1.45.0 // indirect
+	go.yaml.in/yaml/v4 v4.0.0-rc.2 // indirect
 	go4.org v0.0.0-20230225012048-214862532bf5 // indirect
-	golang.org/x/crypto v0.50.0 // indirect
+	golang.org/x/crypto v0.57.0 // indirect
 	golang.org/x/oauth2 v0.36.0 // indirect
-	golang.org/x/sync v0.20.0 // indirect
-	golang.org/x/sys v0.43.0 // indirect
-	golang.org/x/term v0.42.0 // indirect
-	golang.org/x/text v0.36.0 // indirect
+	golang.org/x/sync v0.23.0 // indirect
+	golang.org/x/sys v0.48.0 // indirect
+	golang.org/x/term v0.46.0 // indirect
+	golang.org/x/text v0.42.0 // indirect
 	golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 // indirect
-	gonum.org/v1/gonum v0.16.0 // indirect
-	google.golang.org/api v0.271.0 // indirect
-	google.golang.org/genproto v0.0.0-20260128011058-8636f8732409 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20260226221140-a57be14db171 // indirect
-	google.golang.org/grpc v1.79.3 // indirect
-	google.golang.org/protobuf v1.36.11 // indirect
+	gonum.org/v1/gonum v0.17.0 // indirect
+	google.golang.org/api v0.294.0 // indirect
+	google.golang.org/genproto v0.0.0-20260715232425-e75dac1f907d // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20260715232425-e75dac1f907d // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260819154853-08b0e4226688 // indirect
+	google.golang.org/grpc v1.83.2 // indirect
+	google.golang.org/protobuf v1.36.12 // indirect
 	gopkg.in/warnings.v0 v0.1.2 // indirect
-	modernc.org/libc v1.70.0 // indirect
+	modernc.org/libc v1.75.7 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
-	modernc.org/memory v1.11.0 // indirect
+	modernc.org/memory v1.12.1 // indirect
 )
 
 retract (

install.sh

@@ -35,7 +35,8 @@ is_command() (
 )
 
 echo_stderr() (
-  echo "$@" 1>&2
+  IFS=" "
+  printf "%b\n" "$*" 1>&2
 )
 
 _logp=2
@@ -75,12 +76,12 @@ init_colors
 
 log_tag() (
   case $1 in
-    0) echo "${RED}${BOLD}[error]${RESET}" ;;
-    1) echo "${RED}[warn]${RESET}" ;;
-    2) echo "[info]${RESET}" ;;
-    3) echo "${BLUE}[debug]${RESET}" ;;
-    4) echo "${PURPLE}[trace]${RESET}" ;;
-    *) echo "[$1]" ;;
+    0) printf "%b" "${RED}${BOLD}[error]${RESET}" ;;
+    1) printf "%b" "${RED}[warn]${RESET}" ;;
+    2) printf "%b" "[info]${RESET}" ;;
+    3) printf "%b" "${BLUE}[debug]${RESET}" ;;
+    4) printf "%b" "${PURPLE}[trace]${RESET}" ;;
+    *) printf "[%s]" "$1" ;;
   esac
 )
 

internal/capabilities/appconfig.yaml

@@ -2,6 +2,8 @@
 # This file is partially auto-generated. Run 'go generate ./internal/capabilities' to regenerate.
 
 application: # AUTO-GENERATED - application-level config keys
+  - key: cpp.vcpkg-allow-git-clone
+    description: enables Syft to use clone remote repositories for vcpkg custom git registries. (also useful if the builtin vcpkg registry is not cloned locally)
   - key: dotnet.dep-packages-must-claim-dll
     description: 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.
   - key: dotnet.dep-packages-must-have-dll
@@ -12,6 +14,10 @@ application: # AUTO-GENERATED - application-level config keys
     description: treat DLL claims or on-disk evidence for child packages as DLL claims or on-disk evidence for any parent package
   - key: dotnet.relax-dll-claims-when-bundling-detected
     description: show all packages from the deps.json if bundling tooling is present as a dependency (e.g. ILRepack)
+  - key: golang.capture-symbols
+    description: '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)'
+  - key: golang.capture-symbols-modules
+    description: 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
   - key: golang.local-mod-cache-dir
     description: specify an explicit go mod cache directory, if unset this defaults to $GOPATH/pkg/mod or $HOME/go/pkg/mod
   - key: golang.local-vendor-dir

internal/capabilities/capabilities.go

@@ -9,7 +9,7 @@ import (
 	"sort"
 
 	"github.com/scylladb/go-set/strset"
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 
 	"github.com/anchore/syft/internal/task"
 )

internal/capabilities/generate/io.go

@@ -1,4 +1,4 @@
-// this file handles YAML file reading and writing with comment preservation, using gopkg.in/yaml.v3's node tree to maintain all existing comments during regeneration.
+// this file handles YAML file reading and writing with comment preservation, using go.yaml.in/yaml/v3's node tree to maintain all existing comments during regeneration.
 package main
 
 import (
@@ -6,7 +6,7 @@ import (
 	"os"
 	"regexp"
 
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 
 	"github.com/anchore/syft/internal/capabilities"
 	"github.com/anchore/syft/internal/capabilities/internal"
@@ -297,6 +297,11 @@ func addCatalogerFieldComment(keyNode, valueNode *yaml.Node, catalogerName strin
 		if keyNode.LineComment == "" {
 			keyNode.LineComment = autoGeneratedComment
 		}
+	case "purl_types":
+		// cataloger-level purl_types (for custom catalogers) are AUTO-GENERATED
+		if keyNode.LineComment == "" {
+			keyNode.LineComment = autoGeneratedComment
+		}
 	case "json_schema_types":
 		// json_schema_types are AUTO-GENERATED
 		if keyNode.LineComment == "" {
@@ -367,7 +372,7 @@ func addParserComments(parsersNode *yaml.Node) {
 			valueNode := parserNode.Content[i+1]
 
 			switch keyNode.Value {
-			case "parser_function", "metadata_types", "package_types", "json_schema_types":
+			case "parser_function", "metadata_types", "package_types", "purl_types", "json_schema_types":
 				// add AUTO-GENERATED comment to these fields
 				if keyNode.LineComment == "" {
 					keyNode.LineComment = autoGeneratedComment

internal/capabilities/generate/io_test.go

@@ -4,7 +4,7 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/require"
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 )
 
 func TestFindFieldValue(t *testing.T) {

internal/capabilities/generate/merge.go

@@ -3,6 +3,7 @@ package main
 
 import (
 	"fmt"
+	"sort"
 	"strings"
 
 	"github.com/scylladb/go-set/strset"
@@ -10,6 +11,7 @@ import (
 	"github.com/anchore/syft/internal/capabilities"
 	"github.com/anchore/syft/internal/capabilities/internal"
 	"github.com/anchore/syft/internal/packagemetadata"
+	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
 )
 
@@ -192,6 +194,9 @@ func RegenerateCapabilities(catalogerDir string, repoRoot string) (*Statistics,
 			formatOrphans(orphans))
 	}
 
+	// 5a. Derive PURL types from the discovered package types (purely a function of pkg.Type)
+	derivePURLTypes(updated)
+
 	// 6. Write back to YAML files with comments, preserving existing node trees
 	fmt.Print("  → Writing updated capabilities files...")
 	if err := saveCapabilities(catalogerDir, repoRoot, updated, existingNodes); err != nil {
@@ -427,6 +432,39 @@ func (e *EnrichmentData) GetMetadataTypes(catalogerName string) ([]string, bool)
 	return types, ok
 }
 
+// derivePURLTypes populates the PURLTypes field on every cataloger and parser by mapping each
+// observed package type to its canonical PURL type via pkg.Type.PackageURLType. this is a pure
+// function of the already-discovered package_types, so it needs no additional test observations.
+func derivePURLTypes(doc *capabilities.Document) {
+	for i := range doc.Catalogers {
+		cat := &doc.Catalogers[i]
+		cat.PURLTypes = purlTypesFromPackageTypes(cat.PackageTypes)
+		for j := range cat.Parsers {
+			cat.Parsers[j].PURLTypes = purlTypesFromPackageTypes(cat.Parsers[j].PackageTypes)
+		}
+	}
+}
+
+// purlTypesFromPackageTypes maps syft package type strings (e.g. "go-module") to their PURL types
+// (e.g. "golang"), returning a deduplicated, sorted slice. package types with no PURL mapping are skipped.
+func purlTypesFromPackageTypes(packageTypes []string) []string {
+	if len(packageTypes) == 0 {
+		return nil
+	}
+	set := strset.New()
+	for _, pt := range packageTypes {
+		if purlType := pkg.Type(pt).PackageURLType(); purlType != "" {
+			set.Add(purlType)
+		}
+	}
+	if set.IsEmpty() {
+		return nil
+	}
+	result := set.List()
+	sort.Strings(result)
+	return result
+}
+
 // GetPackageTypes returns the package types for the given cataloger name
 func (e *EnrichmentData) GetPackageTypes(catalogerName string) ([]string, bool) {
 	types, ok := e.packageTypes[catalogerName]
@@ -490,11 +528,15 @@ func (e *EnrichmentData) EnrichWithBinaryClassifier(catalogerName string, entry
 			}
 
 			for _, o := range binaryClassifierOverrides[classifier.Class] {
+				cpeStrings := make([]string, len(o.CPEs))
+				for i, c := range o.CPEs {
+					cpeStrings[i] = c.Attributes.BindToFmtString()
+				}
 				packages = append(packages, capabilities.DetectorPackageInfo{
 					Class: o.Class,
 					Name:  o.Package,
 					PURL:  stripPURLVersion(o.PURL),
-					CPEs:  o.CPEs,
+					CPEs:  cpeStrings,
 					Type:  "BinaryPkg",
 				})
 			}

internal/capabilities/generate/merge_test.go

@@ -552,3 +552,48 @@ func TestConvertToJSONSchemaTypesFromMetadata(t *testing.T) {
 		})
 	}
 }
+
+func TestPURLTypesFromPackageTypes(t *testing.T) {
+	tests := []struct {
+		name         string
+		packageTypes []string
+		want         []string
+	}{
+		{
+			name:         "nil slice returns nil",
+			packageTypes: nil,
+			want:         nil,
+		},
+		{
+			name:         "single package type maps to purl type",
+			packageTypes: []string{"go-module"},
+			want:         []string{"golang"},
+		},
+		{
+			name:         "multiple package types are sorted",
+			packageTypes: []string{"npm", "go-module"},
+			want:         []string{"golang", "npm"},
+		},
+		{
+			// java and jenkins-plugin both map to maven, so the result is deduplicated
+			name:         "distinct package types collapsing to one purl type are deduplicated",
+			packageTypes: []string{"java-archive", "jenkins-plugin"},
+			want:         []string{"maven"},
+		},
+		{
+			// unknown package types have no purl mapping and are skipped
+			name:         "package type without a purl mapping is skipped",
+			packageTypes: []string{"UnknownPackage"},
+			want:         nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := purlTypesFromPackageTypes(tt.packageTypes)
+			if diff := cmp.Diff(tt.want, got); diff != "" {
+				t.Errorf("purlTypesFromPackageTypes() mismatch (-want +got):\n%s", diff)
+			}
+		})
+	}
+}

internal/capabilities/generate/overrides.go

@@ -10,7 +10,7 @@ type binaryClassifierOverride struct {
 	Class   string
 	Package string
 	PURL    string
-	CPEs    []string
+	CPEs    []cpe.CPE
 }
 
 var binaryClassifierOverrides = map[string][]binaryClassifierOverride{
@@ -110,12 +110,47 @@ var binaryClassifierOverrides = map[string][]binaryClassifierOverride{
 			CPEs:    singleCPE("cpe:2.3:a:openssl:openssl:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
 		},
 	},
+	"mysqld-binary": {
+		{
+			Class:   "mysqld-mysql-cluster-legacy-binary",
+			Package: "mysql-cluster",
+			PURL:    mustPURL("pkg:generic/mysql-cluster@version"),
+			CPEs: []cpe.CPE{
+				cpe.Must("cpe:2.3:a:oracle:mysql_cluster:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+			},
+		},
+		{
+			Class:   "mysqld-mysql-cluster-binary",
+			Package: "mysql-cluster",
+			PURL:    mustPURL("pkg:generic/mysql-cluster@version"),
+			CPEs: []cpe.CPE{
+				cpe.Must("cpe:2.3:a:oracle:mysql:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+				cpe.Must("cpe:2.3:a:oracle:mysql_server:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+				cpe.Must("cpe:2.3:a:oracle:mysql_cluster:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+			},
+		},
+		{
+			Class:   "mysqld-mysql-server-binary",
+			Package: "mysql-server",
+			PURL:    mustPURL("pkg:generic/mysql-server@version"),
+			CPEs: []cpe.CPE{
+				cpe.Must("cpe:2.3:a:oracle:mysql:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+				cpe.Must("cpe:2.3:a:oracle:mysql_server:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+			},
+		},
+	},
 }
 
 func mustPURL(purl string) string {
 	return purl
 }
 
-func singleCPE(cpeString string, _ ...any) []string {
-	return []string{cpeString}
+func singleCPE(cpeString string, source ...cpe.Source) []cpe.CPE {
+	src := cpe.GeneratedSource
+	if len(source) > 0 {
+		src = source[0]
+	}
+	return []cpe.CPE{
+		cpe.Must(cpeString, src),
+	}
 }

internal/capabilities/internal/load_capabilities.go

@@ -5,7 +5,7 @@ import (
 	"os"
 	"path/filepath"
 
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 
 	"github.com/anchore/syft/internal/capabilities"
 )

internal/capabilities/model.go

@@ -82,6 +82,7 @@ type CatalogerEntry struct {
 	Detectors       []Detector    `yaml:"detectors,omitempty" json:"detectors,omitempty"`                 // AUTO-GENERATED - detection methods (only for type=custom)
 	MetadataTypes   []string      `yaml:"metadata_types,omitempty" json:"metadata_types,omitempty"`       // AUTO-GENERATED - pkg metadata types emitted (only for type=custom)
 	PackageTypes    []string      `yaml:"package_types,omitempty" json:"package_types,omitempty"`         // AUTO-GENERATED - package types emitted (only for type=custom)
+	PURLTypes       []string      `yaml:"purl_types,omitempty" json:"purl_types,omitempty"`               // AUTO-GENERATED - PURL types derived from package_types (only for type=custom)
 	JSONSchemaTypes []string      `yaml:"json_schema_types,omitempty" json:"json_schema_types,omitempty"` // AUTO-GENERATED - JSON schema type names (UpperCamelCase)
 	Capabilities    CapabilitySet `yaml:"capabilities,omitempty" json:"capabilities,omitempty"`           // MANUAL - config-driven capability definitions (only for type=custom)
 }
@@ -92,6 +93,7 @@ type Parser struct {
 	Detector        Detector      `yaml:"detector" json:"detector"`                                       // AUTO-GENERATED - how artifacts are detected
 	MetadataTypes   []string      `yaml:"metadata_types,omitempty" json:"metadata_types,omitempty"`       // AUTO-GENERATED - pkg metadata types emitted by this parser
 	PackageTypes    []string      `yaml:"package_types,omitempty" json:"package_types,omitempty"`         // AUTO-GENERATED - package types emitted by this parser
+	PURLTypes       []string      `yaml:"purl_types,omitempty" json:"purl_types,omitempty"`               // AUTO-GENERATED - PURL types derived from package_types
 	JSONSchemaTypes []string      `yaml:"json_schema_types,omitempty" json:"json_schema_types,omitempty"` // AUTO-GENERATED - JSON schema type names (UpperCamelCase)
 	Capabilities    CapabilitySet `yaml:"capabilities,omitempty" json:"capabilities,omitempty"`           // MANUAL - config-driven capability definitions
 }

internal/capabilities/model_test.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/google/go-cmp/cmp"
 	"github.com/stretchr/testify/require"
-	"gopkg.in/yaml.v3"
+	"go.yaml.in/yaml/v3"
 )
 
 func TestConfigSchemaExtensions(t *testing.T) {

internal/constants.go

@@ -3,12 +3,18 @@ package internal
 const (
 	// JSONSchemaVersion is the current schema version output by the JSON encoder
 	// This is roughly following the "SchemaVer" guidelines for versioning the JSON schema. Please see schema/json/README.md for details on how to increment.
-	JSONSchemaVersion = "16.1.3"
+	JSONSchemaVersion = "16.1.10"
 
 	// Changelog
 	// 16.1.0 - reformulated the python pdm fields (added "URL" and removed the unused "path" field).
 	// 16.1.1 - correct elf package osCpe field according to the document of systemd (also add appCpe field)
 	// 16.1.2 - placeholder for 16.1.2 changelog
 	// 16.1.3 - add GGUFFileParts to GGUFFileHeader metadata
-
+	// 16.1.4 - add BunLockEntry metadata type for bun.lock support
+	// 16.1.5 - add DenoLockEntry and DenoRemoteLockEntry metadata types for deno.lock support
+	// 16.1.6 - add Dependencies to ElixirMixLockEntry metadata
+	// 16.1.7 - add AppleAppBundleEntry metadata type for the apple app bundle cataloger
+	// 16.1.8 - add VcpkgManifest metadata type for vcpkg manifest support
+	// 16.1.9 - add Symbols (grouped by owning package import path) to GolangBinaryBuildinfoEntry metadata
+	// 16.1.10 - add SafeTensorsModelInfo metadata type for the safetensors AI model cataloger
 )

internal/file/reader_size.go

@@ -0,0 +1,66 @@
+package file
+
+import "io"
+
+// ReaderSize reports the number of bytes behind r. The bool is false when that cannot be determined, and
+// callers must branch on it rather than treating the zero as a size.
+//
+// Binary parsers read sizes out of the files they are parsing and allocate against them. Those sizes are
+// 32- and 64-bit fields under the control of whoever produced the file, so a truncated or hostile input
+// can declare gigabytes that are not there. The read would fail afterwards either way; what matters is
+// refusing before the allocation, and that needs a real byte count to weigh the claim against.
+//
+// The bool is the whole point of the signature. An earlier version returned 0 for every failure mode, and
+// a caller that forgot to special-case it got a bound of "nothing is allowed" or, more often, silently
+// fell back to an unbounded path. Making the caller name the failure keeps that from happening by
+// omission.
+//
+// Both *bytes.Reader and *io.SectionReader answer directly. A file handle only has Seek, so fall back to
+// a save-and-restore seek, which leaves the caller's cursor where it found it. That fallback is not
+// atomic: it moves the cursor and puts it back, so a reader being read concurrently can observe the
+// intermediate position.
+//
+// Neither answer is taken on faith, because a reader can report a length it cannot deliver: an
+// *io.SectionReader answers with the length it was constructed with, and debug/elf and friends construct
+// theirs with a nominal one, so io.NewSectionReader(r, 0, 1<<63-1) would otherwise report a bound that
+// permits everything as if it had been measured. The last byte is read back to confirm the count, which is
+// one ReadAt whatever the size, and the read is what the caller was going to weigh anyway.
+//
+// A wrapper that embeds io.ReaderAt as an interface promotes only ReadAt, so it answers no size here
+// however sizable the reader underneath it is. A type meant to be bounded needs to forward Size() itself.
+func ReaderSize(r io.ReaderAt) (int64, bool) {
+	size, ok := reportedSize(r)
+	if !ok {
+		return 0, false
+	}
+	// ReadAt may return io.EOF alongside a full read, so the count is what says the byte is there
+	var last [1]byte
+	if n, _ := r.ReadAt(last[:], size-1); n != len(last) {
+		return 0, false
+	}
+	return size, true
+}
+
+// reportedSize is what the reader says about itself, before ReaderSize checks whether it can back it up.
+func reportedSize(r io.ReaderAt) (int64, bool) {
+	if sr, ok := r.(interface{ Size() int64 }); ok {
+		size := sr.Size()
+		return size, size > 0
+	}
+	s, ok := r.(io.Seeker)
+	if !ok {
+		return 0, false
+	}
+	cur, err := s.Seek(0, io.SeekCurrent)
+	if err != nil {
+		return 0, false
+	}
+	size, err := s.Seek(0, io.SeekEnd)
+	if err != nil {
+		return 0, false
+	}
+	if _, err := s.Seek(cur, io.SeekStart); err != nil {
+		return 0, false
+	}
+	return size, size > 0
+}

internal/file/reader_size_test.go

@@ -0,0 +1,140 @@
+package file
+
+import (
+	"bytes"
+	"io"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestReaderSize(t *testing.T) {
+	tests := []struct {
+		name   string
+		r      io.ReaderAt
+		want   int64
+		wantOK bool
+	}{
+		{
+			name:   "bytes.Reader answers directly",
+			r:      bytes.NewReader(make([]byte, 1234)),
+			want:   1234,
+			wantOK: true,
+		},
+		{
+			// an empty reader is not a size to bound against, so it reports not-ok along with everything
+			// else that cannot be measured
+			name: "empty bytes.Reader",
+			r:    bytes.NewReader(nil),
+			want: 0,
+		},
+		{
+			name:   "SectionReader over a real length",
+			r:      io.NewSectionReader(bytes.NewReader(make([]byte, 500)), 100, 300),
+			want:   300,
+			wantOK: true,
+		},
+		{
+			name:   "seek-only reader falls back to seeking",
+			r:      seekOnly{bytes.NewReader(make([]byte, 4096))},
+			want:   4096,
+			wantOK: true,
+		},
+		{
+			name: "reader with neither Size nor Seek cannot be measured",
+			r:    readAtOnly{bytes.NewReader(make([]byte, 4096))},
+			want: 0,
+		},
+		{
+			// the shape debug/elf, debug/pe and debug/macho build internally. Taking this at its word hands
+			// back a bound that permits everything, reported as if it had been measured.
+			name: "SectionReader over a nominal length reports what it can deliver",
+			r:    io.NewSectionReader(bytes.NewReader(make([]byte, 500)), 0, 1<<63-1),
+			want: 0,
+		},
+		{
+			// a Size() a type simply got wrong is the same failure: the bytes are what decides
+			name: "a size the reader cannot back up is refused",
+			r:    overstatedSize{ReaderAt: bytes.NewReader(make([]byte, 10)), size: 1 << 30},
+			want: 0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			size, ok := ReaderSize(tt.r)
+			assert.Equal(t, tt.want, size)
+			assert.Equal(t, tt.wantOK, ok)
+		})
+	}
+}
+
+func TestReaderSize_FileHandle(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "f.bin")
+	require.NoError(t, os.WriteFile(path, make([]byte, 7777), 0o600))
+	f, err := os.Open(path)
+	require.NoError(t, err)
+	defer f.Close()
+
+	// the cursor has to come back where it was found: the caller may be mid-read, and an *os.File is the
+	// one input here that carries a shared position
+	_, err = f.Seek(101, io.SeekStart)
+	require.NoError(t, err)
+
+	size, ok := ReaderSize(f)
+	assert.True(t, ok)
+	assert.Equal(t, int64(7777), size)
+
+	at, err := f.Seek(0, io.SeekCurrent)
+	require.NoError(t, err)
+	assert.Equal(t, int64(101), at, "measuring the file must not move the caller's cursor")
+}
+
+// TestReaderSize_WrapperMustForwardSize pins the shape that made every bound expressed against this
+// helper go silently inert. A type that embeds io.ReaderAt as an interface promotes only ReadAt, so it
+// answers 0 here however sizable the reader underneath is, and a caller that treats 0 as "fall back to
+// unbounded" then stops bounding anything. Forwarding Size() is what fixes it, and this is the assertion
+// that a new wrapper has to satisfy.
+func TestReaderSize_WrapperMustForwardSize(t *testing.T) {
+	inner := bytes.NewReader(make([]byte, 2048))
+
+	size, ok := ReaderSize(embedsReaderAt{inner})
+	assert.False(t, ok, "a wrapper that only embeds the interface cannot be measured")
+	assert.Equal(t, int64(0), size)
+
+	size, ok = ReaderSize(forwardsSize{inner})
+	assert.True(t, ok, "a wrapper meant to be bounded has to forward Size itself")
+	assert.Equal(t, int64(2048), size)
+}
+
+type seekOnly struct{ inner *bytes.Reader }
+
+func (s seekOnly) ReadAt(p []byte, off int64) (int, error) { return s.inner.ReadAt(p, off) }
+func (s seekOnly) Seek(off int64, whence int) (int64, error) {
+	return s.inner.Seek(off, whence)
+}
+
+type readAtOnly struct{ inner *bytes.Reader }
+
+func (r readAtOnly) ReadAt(p []byte, off int64) (int, error) { return r.inner.ReadAt(p, off) }
+
+type embedsReaderAt struct{ io.ReaderAt }
+
+type forwardsSize struct{ io.ReaderAt }
+
+func (f forwardsSize) Size() int64 {
+	size, _ := ReaderSize(f.ReaderAt)
+	return size
+}
+
+// overstatedSize answers with a size larger than the bytes behind it, the way a wrapper that returns a
+// declared length rather than a measured one would.
+type overstatedSize struct {
+	io.ReaderAt
+	size int64
+}
+
+func (o overstatedSize) Size() int64 { return o.size }

internal/file/squashfs.go

@@ -5,6 +5,7 @@ import (
 	"io/fs"
 	"os"
 	"path/filepath"
+	"strings"
 
 	"github.com/diskfs/go-diskfs/filesystem"
 )
@@ -14,8 +15,7 @@ type WalkDiskDirFunc func(fsys filesystem.FileSystem, path string, d os.FileInfo
 // WalkDiskDir walks the file tree within the go-diskfs filesystem at root, calling fn for each file or directory in the tree, including root.
 // This is meant to mimic the behavior of fs.WalkDir in the standard library.
 func WalkDiskDir(fsys filesystem.FileSystem, root string, fn WalkDiskDirFunc) error {
-	infos, err := fsys.ReadDir(root)
-
+	infos, err := readDiskDir(fsys, root)
 	if err != nil {
 		return err
 	}
@@ -51,7 +51,7 @@ func walkDiskDir(fsys filesystem.FileSystem, name string, d os.FileInfo, walkDir
 
 	isDir := d != nil && d.IsDir()
 	if d == nil {
-		_, err := fsys.ReadDir(name)
+		_, err := readDiskDir(fsys, name)
 		if err != nil {
 			return nil
 		}
@@ -62,7 +62,7 @@ func walkDiskDir(fsys filesystem.FileSystem, name string, d os.FileInfo, walkDir
 		return nil
 	}
 
-	dirs, err := fsys.ReadDir(name)
+	dirs, err := readDiskDir(fsys, name)
 	if err != nil {
 		err = walkDirFn(fsys, name, d, err)
 		if err != nil {
@@ -87,3 +87,33 @@ func walkDiskDir(fsys filesystem.FileSystem, name string, d os.FileInfo, walkDir
 	}
 	return nil
 }
+
+// readDiskDir reads the directory entries at the given path from a go-diskfs filesystem.
+// go-diskfs returns fs.DirEntry values; these are resolved to os.FileInfo so callers have
+// access to the full file metadata (mode, size, modification time).
+func readDiskDir(fsys filesystem.FileSystem, p string) ([]os.FileInfo, error) {
+	entries, err := fsys.ReadDir(ToFSPath(p))
+	if err != nil {
+		return nil, err
+	}
+
+	infos := make([]os.FileInfo, 0, len(entries))
+	for _, entry := range entries {
+		info, err := entry.Info()
+		if err != nil {
+			return nil, err
+		}
+		infos = append(infos, info)
+	}
+	return infos, nil
+}
+
+// ToFSPath converts an absolute ("/"-rooted) path into an io/fs-valid path as required by
+// go-diskfs, where the root is "." and other paths carry no leading slash (see io/fs.ValidPath).
+func ToFSPath(p string) string {
+	p = strings.TrimPrefix(p, "/")
+	if p == "" {
+		return "."
+	}
+	return p
+}

internal/file/squashfs_test.go

@@ -43,10 +43,10 @@ func createTestFS(t *testing.T) filesystem.FileSystem {
 
 	for _, tf := range testFiles {
 		if tf.isDir {
-			err := fsys.Mkdir(tf.path)
+			err := fsys.Mkdir(ToFSPath(tf.path))
 			require.NoError(t, err)
 		} else {
-			f, err := fsys.OpenFile(tf.path, os.O_CREATE|os.O_RDWR)
+			f, err := fsys.OpenFile(ToFSPath(tf.path), os.O_CREATE|os.O_RDWR)
 			require.NoError(t, err)
 			_, err = f.Write([]byte(tf.content))
 			require.NoError(t, err)

internal/jsonschema/comments_test.go

@@ -6,9 +6,9 @@ import (
 	"testing"
 
 	"github.com/invopop/jsonschema"
+	orderedmap "github.com/pb33f/ordered-map/v2"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-	orderedmap "github.com/wk8/go-ordered-map/v2"
 )
 
 // TestCopyAliasFieldComments verifies that field comments from source types are correctly copied to alias types.

internal/line_scanner.go

@@ -0,0 +1,19 @@
+package internal
+
+import (
+	"bufio"
+	"io"
+)
+
+// maxScannedLineSize is the longest line NewLineScanner will return before Scan stops with bufio.ErrTooLong.
+// The buffer only grows to this size when a line needs it.
+const maxScannedLineSize = 1024 * 1024
+
+// NewLineScanner returns a bufio.Scanner that accepts lines up to 1MB rather than the 64KB default, since
+// package metadata files carry long single-line fields (descriptions, license text, dependency lists). Callers
+// must still check Err() after scanning.
+func NewLineScanner(r io.Reader) *bufio.Scanner {
+	s := bufio.NewScanner(r)
+	s.Buffer(nil, maxScannedLineSize)
+	return s
+}

internal/line_scanner_test.go

@@ -0,0 +1,24 @@
+package internal
+
+import (
+	"bufio"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestNewLineScanner(t *testing.T) {
+	long := strings.Repeat("a", 100*1024)
+	s := NewLineScanner(strings.NewReader(long + "\nb\n"))
+	require.True(t, s.Scan())
+	require.Equal(t, long, s.Text())
+	require.True(t, s.Scan())
+	require.Equal(t, "b", s.Text())
+	require.False(t, s.Scan())
+	require.NoError(t, s.Err())
+
+	s = NewLineScanner(strings.NewReader(strings.Repeat("a", maxScannedLineSize+1)))
+	require.False(t, s.Scan())
+	require.ErrorIs(t, s.Err(), bufio.ErrTooLong)
+}

internal/os/feature_detection.go

@@ -2,14 +2,18 @@ package os
 
 import (
 	"context"
+	"encoding/json"
+	"errors"
 	"fmt"
 	"regexp"
+	"slices"
 
 	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/internal/sbomsync"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/linux"
+	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/sbom"
 )
 
@@ -19,8 +23,11 @@ func DetectFeatures(_ context.Context, resolver file.Resolver, builder sbomsync.
 			return
 		}
 
-		err := findRhelFeatures(resolver, s.Artifacts.LinuxDistribution)
-		if err != nil {
+		if err := findRhelFeatures(resolver, s.Artifacts.LinuxDistribution); err != nil {
+			log.WithFields("error", err, "release", s.Artifacts.LinuxDistribution).Trace("error searching for extended support")
+		}
+
+		if err := findUbuntuFeatures(resolver, s.Artifacts.LinuxDistribution, s.Artifacts.Packages); err != nil {
 			log.WithFields("error", err, "release", s.Artifacts.LinuxDistribution).Trace("error searching for extended support")
 		}
 	})
@@ -28,6 +35,9 @@ func DetectFeatures(_ context.Context, resolver file.Resolver, builder sbomsync.
 	return nil
 }
 
+// rhelEUSPatterns match a RHEL content manifest referencing an extended-update-support (EUS) repo.
+var rhelEUSPatterns = []*regexp.Regexp{regexp.MustCompile(`baseos-eus`), regexp.MustCompile(`baseos-eus|appstream-eus`)}
+
 func findRhelFeatures(resolver file.Resolver, release *linux.Release) error {
 	if release == nil || release.ID != "rhel" {
 		return nil
@@ -37,9 +47,9 @@ func findRhelFeatures(resolver file.Resolver, release *linux.Release) error {
 		return fmt.Errorf("unable to find content manifests: %w", err)
 	}
 	for _, contentManifestFile := range contentManifestFiles {
-		found, err := hasRhelExtendedSupportInContentManifest(resolver, contentManifestFile)
+		found, err := fileMatchesAny(resolver, contentManifestFile, rhelEUSPatterns...)
 		if err != nil {
-			return fmt.Errorf("unable to read content manifest from %s: %w", contentManifestFile.String(), err)
+			return fmt.Errorf("unable to read content manifest from %s: %w", contentManifestFile.RealPath, err)
 		}
 		if found {
 			release.ExtendedSupport = true
@@ -49,13 +59,149 @@ func findRhelFeatures(resolver file.Resolver, release *linux.Release) error {
 	return nil
 }
 
-func hasRhelExtendedSupportInContentManifest(resolver file.Resolver, contentManifestFile file.Location) (bool, error) {
-	contents, err := resolver.FileContentsByLocation(contentManifestFile)
-	if err != nil {
-		return false, fmt.Errorf("unable to read content manifest from %s: %w", contentManifestFile.String(), err)
-	}
-	defer internal.CloseAndLogError(contents, "content-manifest")
+// Ubuntu Pro (formerly Ubuntu Advantage) is Canonical's subscription that unlocks Expanded Security
+// Maintenance (ESM): security fixes past a package's standard support window. we detect the two base ESM
+// streams, esm-infra (the `main` repo) and esm-apps (`universe`), and collapse them into one ExtendedSupport
+// signal; the infra-vs-apps split is disambiguated by the downstream consumer, not by this boolean.
+//
+// the other Pro streams on the same host (esm.ubuntu.com/fips, /fips-updates, /realtime) are deliberately
+// excluded: they are separate compliance products with their own downstream channels, and a host can run
+// them with base ESM disabled, so folding them in would be unsound.
+//
+// detection is deliberately forgiving: apt/status evidence disappears when ESM is disabled, but an installed
+// +esmN package is durable proof ESM content is on disk. so ExtendedSupport means "ESM was or is in effect
+// for this host or its content", not "currently entitled" (mere eligibility, without evidence, is not enough).
 
-	patterns := []*regexp.Regexp{regexp.MustCompile(`baseos-eus`), regexp.MustCompile(`baseos-eus|appstream-eus`)}
+// esmAptSourcePattern matches an uncommented apt source (classic or DEB822) or auth entry pointing at the
+// plain ESM streams esm.ubuntu.com/infra or /apps. it deliberately scopes to /(infra|apps) so the other
+// Pro streams served from the same host (/fips, /fips-updates, /realtime) are never folded into the base
+// esm channel. the [^#\n]* before the host ensures a leading `#` (comment) can never satisfy the match.
+var esmAptSourcePattern = regexp.MustCompile(`(?m)^[^#\n]*esm\.ubuntu\.com/(infra|apps)`)
+
+// esmVersionPattern matches a dpkg version carrying a numbered ESM pocket suffix, e.g. `...+esm1` or
+// `...~esm2`. the trailing \d scopes this to the ESM pocket and excludes other Pro pockets (e.g. +fips).
+var esmVersionPattern = regexp.MustCompile(`[~+]esm\d`)
+
+func findUbuntuFeatures(resolver file.Resolver, release *linux.Release, packages *pkg.Collection) error {
+	if release == nil || release.ID != "ubuntu" {
+		return nil
+	}
+
+	// an uncommented esm.ubuntu.com apt source or an active pro esm service both prove Pro/ESM was enabled.
+	// these are the durable, file-based signals present on attached hosts. a read error in one signal must
+	// not suppress the others, so errors are collected and detection continues to the next signal.
+	var errs error
+	for _, check := range []func() (bool, error){
+		func() (bool, error) { return hasUbuntuESMAptEvidence(resolver) },
+		func() (bool, error) { return hasActiveUbuntuESMService(resolver) },
+	} {
+		found, err := check()
+		if err != nil {
+			errs = errors.Join(errs, err)
+			continue
+		}
+		if found {
+			release.ExtendedSupport = true
+			return errs
+		}
+	}
+
+	// fallback for images (typically not pro-attached): an installed package whose version carries an
+	// +esm/~esm suffix was pulled from an ESM pocket, so ESM was in effect when it was installed.
+	if hasInstalledESMPackage(packages) {
+		release.ExtendedSupport = true
+	}
+	return errs
+}
+
+// hasUbuntuESMAptEvidence reports whether any apt source (classic .list or DEB822 .sources) or auth entry
+// references esm.ubuntu.com via an uncommented line.
+func hasUbuntuESMAptEvidence(resolver file.Resolver) (bool, error) {
+	// apt source files live in a directory (classic .list or DEB822 .sources), the credentials file is a fixed path.
+	sourceLocations, err := resolver.FilesByGlob("/etc/apt/sources.list.d/*")
+	if err != nil {
+		return false, fmt.Errorf("unable to find apt esm sources: %w", err)
+	}
+	authLocations, err := resolver.FilesByPath("/etc/apt/auth.conf.d/90ubuntu-advantage")
+	if err != nil {
+		return false, fmt.Errorf("unable to find apt esm auth: %w", err)
+	}
+
+	// ponytail: a DEB822 source with `Enabled: no` would still match; the pro client removes/comments the
+	// file on disable rather than toggling that key, so this is an accepted false-positive ceiling. the
+	// auth.conf.d entry is deleted by the pro client on disable, so it is a durable positive-only signal.
+	for _, location := range append(sourceLocations, authLocations...) {
+		match, err := fileMatchesAny(resolver, location, esmAptSourcePattern)
+		if err != nil {
+			return false, err
+		}
+		if match {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+// hasActiveUbuntuESMService reports whether the ubuntu-advantage/pro status cache shows an enabled esm service.
+func hasActiveUbuntuESMService(resolver file.Resolver) (bool, error) {
+	locations, err := resolver.FilesByPath("/var/lib/ubuntu-advantage/status.json")
+	if err != nil {
+		return false, fmt.Errorf("unable to find ubuntu-advantage status: %w", err)
+	}
+	for _, location := range locations {
+		enabled, err := hasEnabledESMServiceInStatus(resolver, location)
+		if err != nil {
+			return false, err
+		}
+		if enabled {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+func hasEnabledESMServiceInStatus(resolver file.Resolver, location file.Location) (bool, error) {
+	contents, err := resolver.FileContentsByLocation(location)
+	if err != nil {
+		return false, fmt.Errorf("unable to read ubuntu-advantage status from %s: %w", location.RealPath, err)
+	}
+	defer internal.CloseAndLogError(contents, location.RealPath)
+
+	var status struct {
+		Services []struct {
+			Name   string `json:"name"`
+			Status string `json:"status"`
+		} `json:"services"`
+	}
+	if err := json.NewDecoder(contents).Decode(&status); err != nil {
+		return false, fmt.Errorf("unable to parse ubuntu-advantage status from %s: %w", location.RealPath, err)
+	}
+
+	// pro status values are enabled/disabled/n-a/warning/—; only "enabled" proves the stream is active.
+	// warning/expired states are intentionally excluded here and left to the apt-source and installed-package signals.
+	for _, svc := range status.Services {
+		if (svc.Name == "esm-infra" || svc.Name == "esm-apps") && svc.Status == "enabled" {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+// hasInstalledESMPackage reports whether any installed dpkg package version carries an ESM pocket suffix.
+func hasInstalledESMPackage(packages *pkg.Collection) bool {
+	if packages == nil {
+		return false
+	}
+	return slices.ContainsFunc(packages.Sorted(pkg.DebPkg), func(p pkg.Package) bool {
+		return esmVersionPattern.MatchString(p.Version)
+	})
+}
+
+func fileMatchesAny(resolver file.Resolver, location file.Location, patterns ...*regexp.Regexp) (bool, error) {
+	contents, err := resolver.FileContentsByLocation(location)
+	if err != nil {
+		return false, fmt.Errorf("unable to read %s: %w", location.RealPath, err)
+	}
+	defer internal.CloseAndLogError(contents, location.RealPath)
 	return internal.MatchAnyFromReader(contents, patterns...)
 }

internal/os/feature_detection_test.go

@@ -2,7 +2,13 @@ package os_test
 
 import (
 	"context"
+	"io"
+	stdos "os"
+	"path"
+	"path/filepath"
+	"slices"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/require"
 
@@ -11,7 +17,9 @@ import (
 	"github.com/anchore/syft/internal/sbomsync"
 	"github.com/anchore/syft/internal/task"
 	"github.com/anchore/syft/syft"
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/linux"
+	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"
 )
@@ -99,3 +107,237 @@ func Test_EnvironmentTask(t *testing.T) {
 		})
 	}
 }
+
+func Test_findUbuntuFeatures(t *testing.T) {
+	tests := []struct {
+		name      string
+		dir       string
+		releaseID string
+		packages  []pkg.Package
+		expected  bool
+	}{
+		{
+			name:      "esm apt source present",
+			dir:       "testdata/ubuntu_esm_apt",
+			releaseID: "ubuntu",
+			expected:  true,
+		},
+		{
+			name:      "esm apt source in DEB822 .sources format",
+			dir:       "testdata/ubuntu_esm_deb822",
+			releaseID: "ubuntu",
+			expected:  true,
+		},
+		{
+			name:      "esm evidence in apt auth.conf.d",
+			dir:       "testdata/ubuntu_esm_authconf",
+			releaseID: "ubuntu",
+			expected:  true,
+		},
+		{
+			name:      "active esm service in ubuntu-advantage status",
+			dir:       "testdata/ubuntu_esm_status",
+			releaseID: "ubuntu",
+			expected:  true,
+		},
+		{
+			name:      "only esm-infra enabled (esm-apps disabled)",
+			dir:       "testdata/ubuntu_esm_infra_only",
+			releaseID: "ubuntu",
+			expected:  true,
+		},
+		{
+			name:      "malformed status.json does not panic or match",
+			dir:       "testdata/ubuntu_esm_malformed",
+			releaseID: "ubuntu",
+			expected:  false,
+		},
+		{
+			name:      "installed +esm package version",
+			dir:       "testdata/ubuntu_plain",
+			releaseID: "ubuntu",
+			packages: []pkg.Package{
+				{Name: "openssl", Version: "1.1.1f-1ubuntu2.19+esm1", Type: pkg.DebPkg},
+			},
+			expected: true,
+		},
+		{
+			name:      "installed ~esm package version",
+			dir:       "testdata/ubuntu_plain",
+			releaseID: "ubuntu",
+			packages: []pkg.Package{
+				{Name: "libcap2", Version: "1:2.32-1ubuntu0.1~esm1", Type: pkg.DebPkg},
+			},
+			expected: true,
+		},
+		{
+			name:      "plain ubuntu with no esm evidence",
+			dir:       "testdata/ubuntu_plain",
+			releaseID: "ubuntu",
+			packages: []pkg.Package{
+				{Name: "openssl", Version: "1.1.1f-1ubuntu2.19", Type: pkg.DebPkg},
+			},
+			expected: false,
+		},
+		{
+			name:      "commented esm source and disabled esm service",
+			dir:       "testdata/ubuntu_esm_disabled",
+			releaseID: "ubuntu",
+			expected:  false,
+		},
+		{
+			name:      "esm disabled but +esm package remains installed",
+			dir:       "testdata/ubuntu_esm_disabled",
+			releaseID: "ubuntu",
+			packages: []pkg.Package{
+				{Name: "openssl", Version: "1.1.1f-1ubuntu2.19+esm1", Type: pkg.DebPkg},
+			},
+			expected: true, // durable proof: ESM content is on disk even though the channel is now off
+		},
+		{
+			name:      "fips-only pro host is not plain esm",
+			dir:       "testdata/ubuntu_fips_only",
+			releaseID: "ubuntu",
+			expected:  false, // esm.ubuntu.com/fips must not be folded into the base esm channel
+		},
+		{
+			name:      "non-ubuntu is unaffected by esm evidence",
+			dir:       "testdata/ubuntu_esm_apt",
+			releaseID: "debian",
+			expected:  false,
+		},
+		{
+			name:      "non-ubuntu is unaffected by esm package version",
+			dir:       "testdata/ubuntu_plain",
+			releaseID: "debian",
+			packages: []pkg.Package{
+				{Name: "openssl", Version: "1.1.1f-1ubuntu2.19+esm1", Type: pkg.DebPkg},
+			},
+			expected: false,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			resolver := fixtureResolverForDir(t, test.dir)
+
+			s := sbom.SBOM{}
+			s.Artifacts.LinuxDistribution = &linux.Release{ID: test.releaseID}
+			s.Artifacts.Packages = pkg.NewCollection(test.packages...)
+
+			err := os.DetectFeatures(context.Background(), resolver, sbomsync.NewBuilder(&s))
+			require.NoError(t, err)
+
+			require.Equal(t, test.expected, s.Artifacts.LinuxDistribution.ExtendedSupport)
+		})
+	}
+}
+
+// returning early from Collection.Enumerate leaks its goroutine and read lock, so any later write blocks forever.
+func Test_findUbuntuFeatures_releasesPackageCollectionLock(t *testing.T) {
+	resolver := fixtureResolverForDir(t, "testdata/ubuntu_plain")
+
+	s := sbom.SBOM{}
+	s.Artifacts.LinuxDistribution = &linux.Release{ID: "ubuntu"}
+	s.Artifacts.Packages = pkg.NewCollection(
+		pkg.Package{Name: "openssl", Version: "1.1.1f-1ubuntu2.19+esm1", Type: pkg.DebPkg},
+		pkg.Package{Name: "libcap2", Version: "1:2.32-1ubuntu0.1~esm1", Type: pkg.DebPkg},
+	)
+
+	require.NoError(t, os.DetectFeatures(context.Background(), resolver, sbomsync.NewBuilder(&s)))
+	require.True(t, s.Artifacts.LinuxDistribution.ExtendedSupport)
+
+	added := make(chan struct{})
+	go func() {
+		s.Artifacts.Packages.Add(pkg.Package{Name: "zlib1g", Version: "1:1.2.11.dfsg-2ubuntu1", Type: pkg.DebPkg})
+		close(added)
+	}()
+
+	select {
+	case <-added:
+	case <-time.After(5 * time.Second):
+		t.Fatal("package collection is still read-locked after feature detection")
+	}
+}
+
+// a read error in the apt-source signal must not suppress the ubuntu-advantage status signal; the three
+// signals are meant to be independent fallbacks.
+func Test_findUbuntuFeatures_signalErrorDoesNotSuppressOthers(t *testing.T) {
+	resolver := errOnGlobResolver{
+		fixtureResolver: fixtureResolverForDir(t, "testdata/ubuntu_esm_status").(fixtureResolver),
+		errOnGlob:       "/etc/apt/sources.list.d/*",
+	}
+
+	s := sbom.SBOM{}
+	s.Artifacts.LinuxDistribution = &linux.Release{ID: "ubuntu"}
+	s.Artifacts.Packages = pkg.NewCollection()
+
+	require.NoError(t, os.DetectFeatures(context.Background(), resolver, sbomsync.NewBuilder(&s)))
+
+	// the apt glob errors, but the status.json signal (esm-infra enabled) should still be consulted
+	require.True(t, s.Artifacts.LinuxDistribution.ExtendedSupport)
+}
+
+// errOnGlobResolver injects a failure for a specific glob to simulate an unreadable apt directory.
+type errOnGlobResolver struct {
+	fixtureResolver
+	errOnGlob string
+}
+
+func (r errOnGlobResolver) FilesByGlob(patterns ...string) ([]file.Location, error) {
+	if slices.Contains(patterns, r.errOnGlob) {
+		return nil, stdos.ErrPermission
+	}
+	return r.fixtureResolver.FilesByGlob(patterns...)
+}
+
+// fixtureResolver maps in-image logical paths to on-disk fixture files so DetectFeatures can be driven
+// without building a container image.
+type fixtureResolver struct {
+	file.Resolver // unused methods; nil is fine since only the three below are called
+	files         map[string]string
+}
+
+func (r fixtureResolver) FilesByGlob(patterns ...string) ([]file.Location, error) {
+	var out []file.Location
+	for logical := range r.files {
+		for _, p := range patterns {
+			if ok, _ := path.Match(p, logical); ok {
+				out = append(out, file.NewLocation(logical))
+				break
+			}
+		}
+	}
+	return out, nil
+}
+
+func (r fixtureResolver) FilesByPath(paths ...string) ([]file.Location, error) {
+	var out []file.Location
+	for _, p := range paths {
+		if _, ok := r.files[p]; ok {
+			out = append(out, file.NewLocation(p))
+		}
+	}
+	return out, nil
+}
+
+func (r fixtureResolver) FileContentsByLocation(l file.Location) (io.ReadCloser, error) {
+	return stdos.Open(r.files[l.RealPath])
+}
+
+func fixtureResolverForDir(t *testing.T, dir string) file.Resolver {
+	t.Helper()
+	files := map[string]string{}
+	require.NoError(t, filepath.WalkDir(dir, func(p string, d stdos.DirEntry, err error) error {
+		if err != nil || d.IsDir() {
+			return err
+		}
+		rel, err := filepath.Rel(dir, p)
+		if err != nil {
+			return err
+		}
+		files["/"+filepath.ToSlash(rel)] = p
+		return nil
+	}))
+	return fixtureResolver{files: files}
+}

internal/os/testdata/ubuntu_esm_apt/etc/apt/sources.list.d/ubuntu-esm-infra.list

@@ -0,0 +1,6 @@
+# Written by ubuntu-advantage-tools
+deb https://esm.ubuntu.com/infra/ubuntu focal-infra-security main
+# deb-src https://esm.ubuntu.com/infra/ubuntu focal-infra-security main
+
+deb https://esm.ubuntu.com/infra/ubuntu focal-infra-updates main
+# deb-src https://esm.ubuntu.com/infra/ubuntu focal-infra-updates main

internal/os/testdata/ubuntu_esm_authconf/etc/apt/auth.conf.d/90ubuntu-advantage

@@ -0,0 +1,2 @@
+machine esm.ubuntu.com/infra/ubuntu/ login bearer password DUMMYTOKENREDACTED  # ubuntu-pro-client
+machine esm.ubuntu.com/apps/ubuntu/ login bearer password DUMMYTOKENREDACTED  # ubuntu-pro-client

internal/os/testdata/ubuntu_esm_deb822/etc/apt/sources.list.d/ubuntu-esm-infra.sources

@@ -0,0 +1,5 @@
+Types: deb
+URIs: https://esm.ubuntu.com/infra/ubuntu
+Suites: noble-infra-security noble-infra-updates
+Components: main
+Signed-By: /usr/share/keyrings/ubuntu-pro-esm-infra-keyring.gpg

internal/os/testdata/ubuntu_esm_disabled/etc/apt/sources.list.d/ubuntu-esm-infra.list

@@ -0,0 +1,3 @@
+# Written by ubuntu-advantage-tools
+# deb https://esm.ubuntu.com/infra/ubuntu focal-infra-security main
+# deb-src https://esm.ubuntu.com/infra/ubuntu focal-infra-security main

internal/os/testdata/ubuntu_esm_disabled/var/lib/ubuntu-advantage/status.json

@@ -0,0 +1,18 @@
+{
+  "_schema_version": "0.1",
+  "attached": true,
+  "services": [
+    {
+      "name": "esm-apps",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "disabled"
+    },
+    {
+      "name": "esm-infra",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "disabled"
+    }
+  ]
+}

internal/os/testdata/ubuntu_esm_infra_only/var/lib/ubuntu-advantage/status.json

@@ -0,0 +1,21 @@
+{
+  "_schema_version": "0.1",
+  "attached": true,
+  "execution_status": "success",
+  "services": [
+    {
+      "name": "esm-apps",
+      "description": "Expanded Security Maintenance for Applications",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "disabled"
+    },
+    {
+      "name": "esm-infra",
+      "description": "Expanded Security Maintenance for Infrastructure",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "enabled"
+    }
+  ]
+}

internal/os/testdata/ubuntu_esm_malformed/var/lib/ubuntu-advantage/status.json

@@ -0,0 +1 @@
+{ this is not valid json

internal/os/testdata/ubuntu_esm_status/var/lib/ubuntu-advantage/status.json

@@ -0,0 +1,28 @@
+{
+  "_doc": "Content provided in json response is currently considered Experimental and may change",
+  "_schema_version": "0.1",
+  "attached": true,
+  "services": [
+    {
+      "name": "esm-apps",
+      "description": "Expanded Security Maintenance for Applications",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "enabled"
+    },
+    {
+      "name": "esm-infra",
+      "description": "Expanded Security Maintenance for Infrastructure",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "enabled"
+    },
+    {
+      "name": "fips",
+      "description": "NIST-certified FIPS crypto packages",
+      "available": "no",
+      "entitled": "no",
+      "status": "n/a"
+    }
+  ]
+}

internal/os/testdata/ubuntu_fips_only/etc/apt/sources.list.d/ubuntu-fips.list

@@ -0,0 +1,3 @@
+# Written by ubuntu-pro-client
+deb https://esm.ubuntu.com/fips/ubuntu focal main
+# deb-src https://esm.ubuntu.com/fips/ubuntu focal main

internal/os/testdata/ubuntu_fips_only/var/lib/ubuntu-advantage/status.json

@@ -0,0 +1,28 @@
+{
+  "_schema_version": "0.1",
+  "attached": true,
+  "execution_status": "success",
+  "services": [
+    {
+      "name": "esm-apps",
+      "description": "Expanded Security Maintenance for Applications",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "disabled"
+    },
+    {
+      "name": "esm-infra",
+      "description": "Expanded Security Maintenance for Infrastructure",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "disabled"
+    },
+    {
+      "name": "fips",
+      "description": "NIST-certified FIPS crypto packages",
+      "available": "yes",
+      "entitled": "yes",
+      "status": "enabled"
+    }
+  ]
+}

internal/os/testdata/ubuntu_plain/etc/apt/sources.list.d/ubuntu.sources

@@ -0,0 +1,5 @@
+Types: deb
+URIs: http://archive.ubuntu.com/ubuntu/
+Suites: noble noble-updates noble-backports
+Components: main restricted universe multiverse
+Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg

internal/packagemetadata/discover_type_names.go

@@ -27,6 +27,7 @@ var knownNonMetadataTypeNames = strset.New(
 var knownMetadataTypeNames = strset.New(
 	"DotnetPortableExecutableEntry",
 	"GGUFFileHeader",
+	"SafeTensorsModelInfo",
 )
 
 func DiscoverTypeNames() ([]string, error) {

internal/packagemetadata/generated.go

@@ -9,8 +9,10 @@ func AllTypes() []any {
 	return []any{
 		pkg.AlpmDBEntry{},
 		pkg.ApkDBEntry{},
+		pkg.AppleAppBundleEntry{},
 		pkg.BinarySignature{},
 		pkg.BitnamiSBOMEntry{},
+		pkg.BunLockEntry{},
 		pkg.CocoaPodfileLockEntry{},
 		pkg.ConanV1LockEntry{},
 		pkg.ConanV2LockEntry{},
@@ -19,6 +21,8 @@ func AllTypes() []any {
 		pkg.CondaMetaPackage{},
 		pkg.DartPubspec{},
 		pkg.DartPubspecLockEntry{},
+		pkg.DenoLockEntry{},
+		pkg.DenoRemoteLockEntry{},
 		pkg.DotnetDepsEntry{},
 		pkg.DotnetPackagesLockEntry{},
 		pkg.DotnetPortableExecutableEntry{},
@@ -64,10 +68,12 @@ func AllTypes() []any {
 		pkg.RubyGemspec{},
 		pkg.RustBinaryAuditEntry{},
 		pkg.RustCargoLockEntry{},
+		pkg.SafeTensorsModelInfo{},
 		pkg.SnapEntry{},
 		pkg.SwiftPackageManagerResolvedEntry{},
 		pkg.SwiplPackEntry{},
 		pkg.TerraformLockProviderEntry{},
+		pkg.VcpkgManifest{},
 		pkg.WordpressPluginEntry{},
 		pkg.YarnLockEntry{},
 	}

internal/packagemetadata/names.go

@@ -73,6 +73,8 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.ConaninfoEntry{}, "c-conan-info-entry"),
 	jsonNames(pkg.DartPubspecLockEntry{}, "dart-pubspec-lock-entry", "DartPubMetadata"),
 	jsonNames(pkg.DartPubspec{}, "dart-pubspec"),
+	jsonNames(pkg.DenoLockEntry{}, "deno-lock-entry"),
+	jsonNames(pkg.DenoRemoteLockEntry{}, "deno-remote-lock-entry"),
 	jsonNames(pkg.DotnetDepsEntry{}, "dotnet-deps-entry", "DotnetDepsMetadata"),
 	jsonNames(pkg.DotnetPortableExecutableEntry{}, "dotnet-portable-executable-entry"),
 	jsonNames(pkg.DpkgArchiveEntry{}, "dpkg-archive-entry"),
@@ -96,6 +98,7 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.NpmPackageLockEntry{}, "javascript-npm-package-lock-entry", "NpmPackageLockJsonMetadata"),
 	jsonNames(pkg.YarnLockEntry{}, "javascript-yarn-lock-entry", "YarnLockJsonMetadata"),
 	jsonNames(pkg.PnpmLockEntry{}, "javascript-pnpm-lock-entry"),
+	jsonNames(pkg.BunLockEntry{}, "javascript-bun-lock-entry"),
 	jsonNames(pkg.PEBinary{}, "pe-binary"),
 	jsonNames(pkg.PhpComposerLockEntry{}, "php-composer-lock-entry", "PhpComposerJsonMetadata"),
 	jsonNamesWithoutLookup(pkg.PhpComposerInstalledEntry{}, "php-composer-installed-entry", "PhpComposerJsonMetadata"), // the legacy value is split into two types, where the other is preferred
@@ -121,11 +124,14 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.SnapEntry{}, "snap-entry"),
 	jsonNames(pkg.WordpressPluginEntry{}, "wordpress-plugin-entry", "WordpressMetadata"),
 	jsonNames(pkg.HomebrewFormula{}, "homebrew-formula"),
+	jsonNames(pkg.AppleAppBundleEntry{}, "apple-app-bundle-entry"),
 	jsonNames(pkg.LuaRocksPackage{}, "luarocks-package"),
 	jsonNames(pkg.TerraformLockProviderEntry{}, "terraform-lock-provider-entry"),
 	jsonNames(pkg.DotnetPackagesLockEntry{}, "dotnet-packages-lock-entry"),
 	jsonNames(pkg.CondaMetaPackage{}, "conda-metadata-entry", "CondaPackageMetadata"),
 	jsonNames(pkg.GGUFFileHeader{}, "gguf-file-header"),
+	jsonNames(pkg.SafeTensorsModelInfo{}, "safetensors-model-info"),
+	jsonNames(pkg.VcpkgManifest{}, "vcpkg-manifest"),
 )
 
 func expandLegacyNameVariants(names ...string) []string {

internal/packagemetadata/untyped_fields_test.go

@@ -0,0 +1,74 @@
+package packagemetadata
+
+import (
+	"reflect"
+	"strings"
+	"testing"
+)
+
+// untypedFieldAllowlist holds package metadata fields that are allowed to carry untyped (interface) values.
+// Values in these fields come straight from whatever a parser decoded, so they are not shaped by syft
+// and can hold anything an encoder or hasher chokes on. Every entry is part of existing SBOM output and
+// cannot be retyped without breaking it; new entries need a reason and a review.
+var untypedFieldAllowlist = map[string]string{
+	"GGUFFileHeader.RemainingKeyValues": "raw GGUF header key-values; retyping changes the header output and metadataHash",
+}
+
+// TestNoUntypedMetadataFields fails when a package metadata type gains a field typed any, []any,
+// map[string]any (or any other interface) that is not on the allowlist.
+func TestNoUntypedMetadataFields(t *testing.T) {
+	var hits []string
+	for _, ty := range AllTypes() {
+		rt := reflect.TypeOf(ty)
+		collectUntyped(rt, rt.Name(), map[reflect.Type]bool{}, &hits)
+	}
+
+	seen := map[string]bool{}
+	for _, h := range hits {
+		seen[h] = true
+		if _, ok := untypedFieldAllowlist[h]; !ok {
+			t.Errorf("untyped field %s: use a concrete type, or add it to untypedFieldAllowlist with a reason", h)
+		}
+	}
+	for k := range untypedFieldAllowlist {
+		if !seen[k] {
+			t.Errorf("stale untypedFieldAllowlist entry %s: field no longer exists or is now typed", k)
+		}
+	}
+}
+
+// collectUntyped records "Struct.Field" for every field whose type reaches an interface, descending
+// through pointers, slices, arrays, maps and nested syft-owned structs.
+func collectUntyped(rt reflect.Type, path string, visited map[reflect.Type]bool, hits *[]string) {
+	switch rt.Kind() {
+	case reflect.Interface:
+		*hits = append(*hits, path)
+	case reflect.Pointer, reflect.Slice, reflect.Array:
+		collectUntyped(rt.Elem(), path, visited, hits)
+	case reflect.Map:
+		collectUntyped(rt.Key(), path, visited, hits)
+		collectUntyped(rt.Elem(), path, visited, hits)
+	case reflect.Struct:
+		if visited[rt] {
+			return
+		}
+		if rt.Name() != "" && !strings.HasPrefix(rt.PkgPath(), "github.com/anchore/syft/") {
+			// a third-party type in the model carries whatever shape the library gives it (the same leak as an
+			// interface field), so it counts as untyped. The standard library is left alone.
+			if strings.Contains(strings.Split(rt.PkgPath(), "/")[0], ".") {
+				*hits = append(*hits, path)
+			}
+			return
+		}
+		visited[rt] = true
+		for i := 0; i < rt.NumField(); i++ {
+			f := rt.Field(i)
+			// unexported embedded structs still promote their exported fields to the encoders and the hasher. A
+			// field is only out of reach when it is neither encoded nor hashed by SetID.
+			if (!f.IsExported() && !f.Anonymous) || (f.Tag.Get("json") == "-" && f.Tag.Get("hash") == "ignore") {
+				continue
+			}
+			collectUntyped(f.Type, rt.Name()+"."+f.Name, visited, hits)
+		}
+	}
+}

internal/relationship/index.go

@@ -65,6 +65,30 @@ func (i *Index) Add(relationships ...artifact.Relationship) {
 }
 
 func (i *Index) Remove(id artifact.ID) {
+	// scrub this node's edges from the adjacent nodes' maps before dropping the node itself. without this, the
+	// edges live on as dangling pointers inside the other endpoints' mappedRelationships, so query methods
+	// (From/To/References/Coordinates/Contains) would keep returning relationships that have been removed.
+	if mapped := i.fromID[id]; mapped != nil {
+		for _, sr := range mapped.allRelated {
+			if sr.to == id {
+				continue // self-edge: this node's own maps are deleted below
+			}
+			if other := i.toID[sr.to]; other != nil {
+				other.remove(id, sr)
+			}
+		}
+	}
+	if mapped := i.toID[id]; mapped != nil {
+		for _, sr := range mapped.allRelated {
+			if sr.from == id {
+				continue // self-edge: this node's own maps are deleted below
+			}
+			if other := i.fromID[sr.from]; other != nil {
+				other.remove(id, sr)
+			}
+		}
+	}
+
 	delete(i.fromID, id)
 	delete(i.toID, id)
 
@@ -78,6 +102,12 @@ func (i *Index) Remove(id artifact.ID) {
 }
 
 func (i *Index) Replace(ogID artifact.ID, replacement artifact.Identifiable) {
+	if replacement == nil || replacement.ID() == ogID {
+		// replacing a node with one that has the same ID would re-add the (deduped) edges and then the trailing
+		// Remove(ogID) would delete them, silently wiping all of the node's relationships. treat it as a no-op.
+		return
+	}
+
 	for _, mapped := range fromMappedByID(i.fromID, ogID) {
 		// the stale relationship(i.e. if there's an elder ID in either side) should be discarded
 		if len(fromMappedByID(i.toID, mapped.relationship.To.ID())) == 0 {
@@ -91,8 +121,10 @@ func (i *Index) Replace(ogID artifact.ID, replacement artifact.Identifiable) {
 	}
 
 	for _, mapped := range fromMappedByID(i.toID, ogID) {
-		// same as the above
-		if len(fromMappedByID(i.fromID, mapped.relationship.To.ID())) == 0 {
+		// same as the above, but check the surviving other endpoint (the From side, since these are edges TO ogID).
+		// note: this must reference From (not To, which is ogID itself) so that nodes appearing only on the To side
+		// of relationships (e.g. a go main module that nothing depends on) keep their edges after an ID change.
+		if len(fromMappedByID(i.fromID, mapped.relationship.From.ID())) == 0 {
 			continue
 		}
 		i.Add(artifact.Relationship{
@@ -206,6 +238,22 @@ func (m *mappedRelationships) add(id artifact.ID, newRelationship *sortableRelat
 	typeMap[id] = newRelationship
 }
 
+// remove deletes a single relationship (the other endpoint keyed by id) from this node's maps. it is the inverse
+// of add and is used to keep adjacent nodes consistent when a node is removed from the index.
+func (m *mappedRelationships) remove(id artifact.ID, target *sortableRelationship) {
+	filtered := m.allRelated[:0]
+	for _, r := range m.allRelated {
+		if r != target {
+			filtered = append(filtered, r)
+		}
+	}
+	m.allRelated = filtered
+
+	if typeMap := m.typeMap[target.relationship.Type]; typeMap != nil && typeMap[id] == target {
+		delete(typeMap, id)
+	}
+}
+
 type sortableRelationship struct {
 	from         artifact.ID
 	to           artifact.ID

internal/relationship/index_test.go

@@ -380,6 +380,41 @@ func TestReplace(t *testing.T) {
 	compareRelationships(t, expectedRels, index.All())
 }
 
+func TestReplace_NodeOnlyOnToSide(t *testing.T) {
+	// regression: a node that only appears on the To side of relationships (nothing depends on it, e.g. a go main
+	// module that other modules are a dependency-of) must keep its incoming edges when its ID changes (such as when a
+	// compliance rule stubs a missing version and recomputes the package ID). previously the To-side remap guard
+	// checked ogID itself instead of the surviving From endpoint, so all such edges were dropped.
+	main := pkg.Package{Name: "main-module"} // empty version, like a go main module
+	dep1 := pkg.Package{Name: "dep-1", Version: "1.0.0"}
+	dep2 := pkg.Package{Name: "dep-2", Version: "2.0.0"}
+
+	for _, p := range []*pkg.Package{&main, &dep1, &dep2} {
+		p.SetID()
+	}
+
+	// both deps are a dependency-of main; main has no outgoing edges
+	r1 := artifact.Relationship{From: dep1, To: main, Type: artifact.DependencyOfRelationship}
+	r2 := artifact.Relationship{From: dep2, To: main, Type: artifact.DependencyOfRelationship}
+
+	index := NewIndex(r1, r2)
+
+	// simulate the version stub: main gets a new ID
+	stubbedMain := main
+	stubbedMain.Version = "UNKNOWN"
+	stubbedMain.SetID()
+	require.NotEqual(t, main.ID(), stubbedMain.ID())
+
+	index.Replace(main.ID(), &stubbedMain)
+
+	expectedRels := []artifact.Relationship{
+		{From: dep1, To: stubbedMain, Type: artifact.DependencyOfRelationship},
+		{From: dep2, To: stubbedMain, Type: artifact.DependencyOfRelationship},
+	}
+
+	compareRelationships(t, expectedRels, index.All())
+}
+
 func compareRelationships(t testing.TB, expected, actual []artifact.Relationship) {
 	assert.Equal(t, len(expected), len(actual), "number of relationships should match")
 	for _, e := range expected {
@@ -408,3 +443,94 @@ func TestReplace_NoExistingRelations(t *testing.T) {
 	allRels := index.All()
 	assert.Len(t, allRels, 0)
 }
+
+// Remove must scrub the removed node's edges from adjacent nodes too, otherwise query methods keep returning
+// relationships that no longer exist. the original Remove only deleted the removed node's own maps, leaving
+// dangling pointers in the other endpoints.
+func TestRemove_NoStaleEdgesInAdjacentNodes(t *testing.T) {
+	p1 := pkg.Package{Name: "pkg-1", Version: "1"}
+	p2 := pkg.Package{Name: "pkg-2", Version: "2"}
+	p3 := pkg.Package{Name: "pkg-3", Version: "3"}
+	for _, p := range []*pkg.Package{&p1, &p2, &p3} {
+		p.SetID()
+	}
+
+	r12 := artifact.Relationship{From: p1, To: p2, Type: artifact.DependencyOfRelationship}
+	r32 := artifact.Relationship{From: p3, To: p2, Type: artifact.DependencyOfRelationship}
+	index := NewIndex(r12, r32)
+
+	index.Remove(p1.ID())
+
+	// p2 was on the To side of the removed edge; its incoming view must no longer include the stale p1 edge,
+	// but must still include the live p3 edge.
+	compareRelationships(t, []artifact.Relationship{r32}, index.To(p2, artifact.DependencyOfRelationship))
+	assert.False(t, index.Contains(r12), "Contains must not report a removed edge")
+	assert.Len(t, index.References(p2), 1, "p2 should only reference the surviving p3 edge")
+	assert.True(t, index.Contains(r32), "surviving edge should remain")
+	compareRelationships(t, []artifact.Relationship{r32}, index.All())
+}
+
+// Replace must leave no dangling references to the old ID in adjacent nodes' query views.
+func TestReplace_NoStaleEdgesAfterReplace(t *testing.T) {
+	main := pkg.Package{Name: "main-module"} // empty version
+	dep := pkg.Package{Name: "dep", Version: "1.0.0"}
+	main.SetID()
+	dep.SetID()
+
+	oldEdge := artifact.Relationship{From: dep, To: main, Type: artifact.DependencyOfRelationship}
+	index := NewIndex(oldEdge)
+
+	stubbed := main
+	stubbed.Version = "UNKNOWN"
+	stubbed.SetID()
+	require.NotEqual(t, main.ID(), stubbed.ID())
+
+	index.Replace(main.ID(), &stubbed)
+
+	newEdge := artifact.Relationship{From: dep, To: stubbed, Type: artifact.DependencyOfRelationship}
+	// the dep's outgoing view must point at the stubbed node, not the old one
+	from := index.From(dep, artifact.DependencyOfRelationship)
+	require.Len(t, from, 1)
+	assert.Equal(t, stubbed.ID(), from[0].To.ID())
+	assert.True(t, index.Contains(newEdge))
+	assert.False(t, index.Contains(oldEdge), "stale edge to old ID must be gone")
+	assert.Empty(t, index.To(main), "old node should have no incoming edges")
+	compareRelationships(t, []artifact.Relationship{newEdge}, index.All())
+}
+
+// replacing a node with one that has the same ID must be a no-op, not silently wipe its edges.
+func TestReplace_SameIDIsNoOp(t *testing.T) {
+	a := pkg.Package{Name: "a", Version: "1"}
+	b := pkg.Package{Name: "b", Version: "2"}
+	a.SetID()
+	b.SetID()
+	edge := artifact.Relationship{From: a, To: b, Type: artifact.DependencyOfRelationship}
+	index := NewIndex(edge)
+
+	// same identity object -> same ID
+	index.Replace(b.ID(), b)
+
+	compareRelationships(t, []artifact.Relationship{edge}, index.All())
+	assert.True(t, index.Contains(edge))
+}
+
+// a self-edge on the replaced node should be remapped to replacement->replacement, not dropped.
+func TestReplace_SelfEdge(t *testing.T) {
+	n := pkg.Package{Name: "n"} // empty version
+	n.SetID()
+	index := NewIndex(artifact.Relationship{From: n, To: n, Type: artifact.DependencyOfRelationship})
+
+	sn := n
+	sn.Version = "UNKNOWN"
+	sn.SetID()
+	require.NotEqual(t, n.ID(), sn.ID())
+
+	index.Replace(n.ID(), &sn)
+
+	all := index.All()
+	require.Len(t, all, 1)
+	assert.Equal(t, sn.ID(), all[0].From.ID())
+	assert.Equal(t, sn.ID(), all[0].To.ID())
+	assert.Empty(t, index.From(n), "no edges should reference the old ID")
+	assert.Empty(t, index.To(n), "no edges should reference the old ID")
+}

internal/safetensors.go

@@ -0,0 +1,7 @@
+package internal
+
+// MaxSafeTensorsHeaderSize caps a safetensors header's JSON (excluding its
+// 8-byte length prefix). Shared by the ai cataloger and the OCI model source so
+// dir and OCI scans accept the same headers. Real-world shard headers are well
+// under 1 MB.
+const MaxSafeTensorsHeaderSize = 8 * 1024 * 1024

internal/spdxlicense/license.go

@@ -44,6 +44,7 @@ type LicenseInfo struct {
 // LicenseByURL returns the license ID and name for a given URL from the SPDX license list.
 // The URL should match one of the URLs in the seeAlso field of an SPDX license.
 // The scheme (http:// or https://) is stripped before lookup, so both schemes match.
+// opensource.org URLs additionally match regardless of the form used (see normalizeOpenSourceOrgURL).
 func LicenseByURL(url string) (LicenseInfo, bool) {
 	url = strings.TrimSpace(url)
 	url = stripScheme(url)
@@ -52,9 +53,51 @@ func LicenseByURL(url string) (LicenseInfo, bool) {
 			ID: id,
 		}, true
 	}
+	if normalized, ok := normalizeOpenSourceOrgURL(url); ok {
+		if id, exists := openSourceOrgURLToLicense[normalized]; exists {
+			return LicenseInfo{
+				ID: id,
+			}, true
+		}
+	}
 	return LicenseInfo{}, false
 }
 
+// openSourceOrgURLToLicense indexes the opensource.org entries of urlToLicense by normalized URL.
+var openSourceOrgURLToLicense = buildOpenSourceOrgURLToLicense(urlToLicense)
+
+func buildOpenSourceOrgURLToLicense(urls map[string]string) map[string]string {
+	index := make(map[string]string)
+	ambiguous := make(map[string]bool)
+	for url, id := range urls {
+		normalized, ok := normalizeOpenSourceOrgURL(url)
+		if !ok || ambiguous[normalized] {
+			continue
+		}
+		if existing, exists := index[normalized]; exists && existing != id {
+			// don't guess between licenses that only differ by URL form
+			delete(index, normalized)
+			ambiguous[normalized] = true
+			continue
+		}
+		index[normalized] = id
+	}
+	return index
+}
+
+// normalizeOpenSourceOrgURL reduces a scheme-less opensource.org URL to a canonical form.
+// SPDX has changed these URLs over time (e.g. 3.29.0 replaced opensource.org/licenses/MIT and
+// opensource.org/license/mit/ with opensource.org/license/MIT), while package metadata in the wild
+// still uses the older forms. The www. prefix, /licenses/ vs /license/, case, and trailing slash are ignored.
+func normalizeOpenSourceOrgURL(url string) (string, bool) {
+	url = strings.TrimPrefix(strings.ToLower(url), "www.")
+	if !strings.HasPrefix(url, "opensource.org/") {
+		return "", false
+	}
+	url = strings.Replace(url, "opensource.org/licenses/", "opensource.org/license/", 1)
+	return strings.TrimSuffix(url, "/"), true
+}
+
 // stripScheme removes http:// or https:// prefix from a URL.
 // This allows a single map entry to match both schemes.
 func stripScheme(url string) string {

internal/spdxlicense/license_list.go

@@ -2,7 +2,7 @@
 // This file was generated using data from https://spdx.org/licenses/licenses.json
 package spdxlicense
 
-const Version = "3.28.0"
+const Version = "3.29.0"
 
 var licenseIDs = map[string]string{
 	"0bsd":                                  "0BSD",
@@ -116,6 +116,7 @@ var licenseIDs = map[string]string{
 	"aswfdigitalassets1.0.0":                "ASWF-Digital-Assets-1.0",
 	"aswfdigitalassets1.1":                  "ASWF-Digital-Assets-1.1",
 	"aswfdigitalassets1.1.0":                "ASWF-Digital-Assets-1.1",
+	"atcgame":                               "atc-game",
 	"baekmuk":                               "Baekmuk",
 	"bahyph":                                "Bahyph",
 	"barr":                                  "Barr",
@@ -142,8 +143,11 @@ var licenseIDs = map[string]string{
 	"briangladman2.0clause":                 "Brian-Gladman-2-Clause",
 	"briangladman2clause":                   "Brian-Gladman-2-Clause",
 	"briangladman3.0.0clause":               "Brian-Gladman-3-Clause",
+	"briangladman3.0.0clausenoconversion":   "Brian-Gladman-3-Clause-no-conversion",
 	"briangladman3.0clause":                 "Brian-Gladman-3-Clause",
+	"briangladman3.0clausenoconversion":     "Brian-Gladman-3-Clause-no-conversion",
 	"briangladman3clause":                   "Brian-Gladman-3-Clause",
+	"briangladman3clausenoconversion":       "Brian-Gladman-3-Clause-no-conversion",
 	"bsd1.0.0clause":                        "BSD-1-Clause",
 	"bsd1.0clause":                          "BSD-1-Clause",
 	"bsd1clause":                            "BSD-1-Clause",
@@ -154,6 +158,7 @@ var licenseIDs = map[string]string{
 	"bsd2.0.0clausenetbsd":                  "BSD-2-Clause",
 	"bsd2.0.0clausepatent":                  "BSD-2-Clause-Patent",
 	"bsd2.0.0clausepkgconfdisclaimer":       "BSD-2-Clause-pkgconf-disclaimer",
+	"bsd2.0.0clauseposunchanged":            "BSD-2-Clause-pos-unchanged",
 	"bsd2.0.0clauseviews":                   "BSD-2-Clause-Views",
 	"bsd2.0clause":                          "BSD-2-Clause",
 	"bsd2.0clausedarwin":                    "BSD-2-Clause-Darwin",
@@ -162,6 +167,7 @@ var licenseIDs = map[string]string{
 	"bsd2.0clausenetbsd":                    "BSD-2-Clause",
 	"bsd2.0clausepatent":                    "BSD-2-Clause-Patent",
 	"bsd2.0clausepkgconfdisclaimer":         "BSD-2-Clause-pkgconf-disclaimer",
+	"bsd2.0clauseposunchanged":              "BSD-2-Clause-pos-unchanged",
 	"bsd2.0clauseviews":                     "BSD-2-Clause-Views",
 	"bsd2clause":                            "BSD-2-Clause",
 	"bsd2clausedarwin":                      "BSD-2-Clause-Darwin",
@@ -170,6 +176,7 @@ var licenseIDs = map[string]string{
 	"bsd2clausenetbsd":                      "BSD-2-Clause",
 	"bsd2clausepatent":                      "BSD-2-Clause-Patent",
 	"bsd2clausepkgconfdisclaimer":           "BSD-2-Clause-pkgconf-disclaimer",
+	"bsd2clauseposunchanged":                "BSD-2-Clause-pos-unchanged",
 	"bsd2clauseviews":                       "BSD-2-Clause-Views",
 	"bsd3.0.0clause":                        "BSD-3-Clause",
 	"bsd3.0.0clauseacpica":                  "BSD-3-Clause-acpica",
@@ -184,6 +191,7 @@ var licenseIDs = map[string]string{
 	"bsd3.0.0clausenonuclearlicense2014":    "BSD-3-Clause-No-Nuclear-License-2014",
 	"bsd3.0.0clausenonuclearwarranty":       "BSD-3-Clause-No-Nuclear-Warranty",
 	"bsd3.0.0clauseopenmpi":                 "BSD-3-Clause-Open-MPI",
+	"bsd3.0.0clauseopenwebui":               "BSD-3-Clause-OpenWebUI",
 	"bsd3.0.0clausesun":                     "BSD-3-Clause-Sun",
 	"bsd3.0.0clausetso":                     "BSD-3-Clause-Tso",
 	"bsd3.0clause":                          "BSD-3-Clause",
@@ -199,6 +207,7 @@ var licenseIDs = map[string]string{
 	"bsd3.0clausenonuclearlicense2014":      "BSD-3-Clause-No-Nuclear-License-2014",
 	"bsd3.0clausenonuclearwarranty":         "BSD-3-Clause-No-Nuclear-Warranty",
 	"bsd3.0clauseopenmpi":                   "BSD-3-Clause-Open-MPI",
+	"bsd3.0clauseopenwebui":                 "BSD-3-Clause-OpenWebUI",
 	"bsd3.0clausesun":                       "BSD-3-Clause-Sun",
 	"bsd3.0clausetso":                       "BSD-3-Clause-Tso",
 	"bsd3clause":                            "BSD-3-Clause",
@@ -214,6 +223,7 @@ var licenseIDs = map[string]string{
 	"bsd3clausenonuclearlicense2014":        "BSD-3-Clause-No-Nuclear-License-2014",
 	"bsd3clausenonuclearwarranty":           "BSD-3-Clause-No-Nuclear-Warranty",
 	"bsd3clauseopenmpi":                     "BSD-3-Clause-Open-MPI",
+	"bsd3clauseopenwebui":                   "BSD-3-Clause-OpenWebUI",
 	"bsd3clausesun":                         "BSD-3-Clause-Sun",
 	"bsd3clausetso":                         "BSD-3-Clause-Tso",
 	"bsd4.0.0clause":                        "BSD-4-Clause",
@@ -232,12 +242,15 @@ var licenseIDs = map[string]string{
 	"bsd4reno":                              "BSD-4.3RENO",
 	"bsd4tahoe":                             "BSD-4.3TAHOE",
 	"bsdadvertisingacknowledgement":         "BSD-Advertising-Acknowledgement",
+	"bsdasktoendorse":                       "BSD-ask-to-endorse",
 	"bsdattributionhpnddisclaimer":          "BSD-Attribution-HPND-disclaimer",
 	"bsdinfernonettverk":                    "BSD-Inferno-Nettverk",
 	"bsdmarkmodifications":                  "BSD-Mark-Modifications",
 	"bsdprotection":                         "BSD-Protection",
+	"bsdsourcealtgpl":                       "BSD-Source-alt-GPL",
 	"bsdsourcebeginningfile":                "BSD-Source-beginning-file",
 	"bsdsourcecode":                         "BSD-Source-Code",
+	"bsdsourcecodenodisclaimer":             "BSD-Source-Code-no-disclaimer",
 	"bsdsystemics":                          "BSD-Systemics",
 	"bsdsystemicsw3.0.0works":               "BSD-Systemics-W3Works",
 	"bsdsystemicsw3.0works":                 "BSD-Systemics-W3Works",
@@ -246,6 +259,7 @@ var licenseIDs = map[string]string{
 	"bsl1.0":                                "BSL-1.0",
 	"bsl1.0.0":                              "BSL-1.0",
 	"buddy":                                 "Buddy",
+	"bugroff":                               "Bugroff",
 	"busl1":                                 "BUSL-1.1",
 	"busl1.1":                               "BUSL-1.1",
 	"busl1.1.0":                             "BUSL-1.1",
@@ -316,8 +330,11 @@ var licenseIDs = map[string]string{
 	"ccbync3.0":                             "CC-BY-NC-3.0",
 	"ccbync3.0.0":                           "CC-BY-NC-3.0",
 	"ccbync3.0.0de":                         "CC-BY-NC-3.0-DE",
+	"ccbync3.0.0igo":                        "CC-BY-NC-3.0-IGO",
 	"ccbync3.0de":                           "CC-BY-NC-3.0-DE",
+	"ccbync3.0igo":                          "CC-BY-NC-3.0-IGO",
 	"ccbync3de":                             "CC-BY-NC-3.0-DE",
+	"ccbync3igo":                            "CC-BY-NC-3.0-IGO",
 	"ccbync4":                               "CC-BY-NC-4.0",
 	"ccbync4.0":                             "CC-BY-NC-4.0",
 	"ccbync4.0.0":                           "CC-BY-NC-4.0",
@@ -592,6 +609,7 @@ var licenseIDs = map[string]string{
 	"fair":                                  "Fair",
 	"fbm":                                   "FBM",
 	"fdkaac":                                "FDK-AAC",
+	"fdkmpegh":                              "FDK-MPEG-H",
 	"fergusontwofish":                       "Ferguson-Twofish",
 	"frameworx1":                            "Frameworx-1.0",
 	"frameworx1.0":                          "Frameworx-1.0",
@@ -767,6 +785,9 @@ var licenseIDs = map[string]string{
 	"hippocratic2":                          "Hippocratic-2.1",
 	"hippocratic2.1":                        "Hippocratic-2.1",
 	"hippocratic2.1.0":                      "Hippocratic-2.1",
+	"hippocratic3.0.0core":                  "Hippocratic-3.0-core",
+	"hippocratic3.0core":                    "Hippocratic-3.0-core",
+	"hippocratic3core":                      "Hippocratic-3.0-core",
 	"hp1986":                                "HP-1986",
 	"hp1986.0":                              "HP-1986",
 	"hp1986.0.0":                            "HP-1986",
@@ -813,6 +834,7 @@ var licenseIDs = map[string]string{
 	"imlib2":                                "Imlib2",
 	"imlib2.0":                              "Imlib2",
 	"imlib2.0.0":                            "Imlib2",
+	"informatica":                           "Informatica",
 	"infozip":                               "Info-ZIP",
 	"innernet2":                             "Inner-Net-2.0",
 	"innernet2.0":                           "Inner-Net-2.0",
@@ -1011,6 +1033,9 @@ var licenseIDs = map[string]string{
 	"mulanpsl2.0.0":                         "MulanPSL-2.0",
 	"multics":                               "Multics",
 	"mup":                                   "Mup",
+	"mvt1":                                  "MVT-1.1",
+	"mvt1.1":                                "MVT-1.1",
+	"mvt1.1.0":                              "MVT-1.1",
 	"naist2003":                             "NAIST-2003",
 	"naist2003.0":                           "NAIST-2003",
 	"naist2003.0.0":                         "NAIST-2003",
@@ -1489,6 +1514,8 @@ var urlToLicense = map[string]string{
 	"cdla.io/permissive-1-0":                                                                                       "CDLA-Permissive-1.0",
 	"cdla.io/sharing-1-0":                                                                                          "CDLA-Sharing-1.0",
 	"celestrak.org/publications/AIAA/2006-6753/faq.php":                                                            "SGP4",
+	"cgit.freebsd.org/src/plain/sys/dev/aic7xxx/aic7xxx_osm.c":                                                     "BSD-Source-alt-GPL",
+	"cgit.freebsd.org/src/tree/usr.bin/sockstat/sockstat.c":                                                        "BSD-2-Clause-pos-unchanged",
 	"cgit.freedesktop.org/libbsd/tree/man/setproctitle.3bsd":                                                       "libutil-David-Nugent",
 	"coil.apotheon.org/plaintext/01.0.txt":                                                                         "COIL-1.0",
 	"core.tcl-lang.org/tk/file?name=compat/unistd.h":                                                               "HPND-UC",
@@ -1512,6 +1539,7 @@ var urlToLicense = map[string]string{
 	"creativecommons.org/licenses/by-nc/2.0/legalcode":                                                             "CC-BY-NC-2.0",
 	"creativecommons.org/licenses/by-nc/2.5/legalcode":                                                             "CC-BY-NC-2.5",
 	"creativecommons.org/licenses/by-nc/3.0/de/legalcode":                                                          "CC-BY-NC-3.0-DE",
+	"creativecommons.org/licenses/by-nc/3.0/igo/legalcode":                                                         "CC-BY-NC-3.0-IGO",
 	"creativecommons.org/licenses/by-nc/3.0/legalcode":                                                             "CC-BY-NC-3.0",
 	"creativecommons.org/licenses/by-nc/4.0/legalcode":                                                             "CC-BY-NC-4.0",
 	"creativecommons.org/licenses/by-nd-nc/1.0/legalcode":                                                          "CC-BY-NC-ND-1.0",
@@ -1564,6 +1592,7 @@ var urlToLicense = map[string]string{
 	"directory.fsf.org/wiki/License:Fdk":                                                                           "FDK-AAC",
 	"doc.qt.io/archives/3.3/license.html":                                                                          "QPL-1.0",
 	"doc.qt.nokia.com/3.3/license.html":                                                                            "QPL-1.0",
+	"docs.mvt.re/en/latest/license/":                                                                               "MVT-1.1",
 	"docs.omniverse.nvidia.com/install-guide/latest/common/licenses.html":                                          "AML-glslang",
 	"docs.oracle.com/cd/E81115_01/html/E81116/licenses.html":                                                       "man2html",
 	"docs.python.org/3/license.html":                                                                               "Python-2.0.1",
@@ -1669,6 +1698,7 @@ var urlToLicense = map[string]string{
 	"fedoraproject.org/wiki/Licensing:Mplus?rd=Licensing/mplus":                                                    "mplus",
 	"fedoraproject.org/wiki/Licensing:ThorPublicLicense":                                                           "TPL-1.0",
 	"firstdonoharm.dev/version/2/1/license.html":                                                                   "Hippocratic-2.1",
+	"firstdonoharm.dev/version/3/0/core.txt":                                                                       "Hippocratic-3.0-core",
 	"forge.gouv.qc.ca/licence/fr/liliq-v1-1/":                                                                      "LiLiQ-P-1.1",
 	"forge.gouv.qc.ca/licence/liliq-p":                                                                             "LiLiQ-R-1.1",
 	"forge.gouv.qc.ca/licence/liliq-p/":                                                                            "LiLiQ-P-1.1",
@@ -1686,68 +1716,70 @@ var urlToLicense = map[string]string{
 	"ftp://ftp.tin.org/pub/news/utils/newsx/newsx-1.6.tar.gz":                                                      "Zeeff",
 	"gianluca.dellavedova.org/2011/01/03/clarified-artistic-license/":                                              "ClArtistic",
 	"git.denx.de/?p=u-boot.git;a=blob;f=arch/powerpc/cpu/ppc4xx/miiphy.c;h=297155fdafa064b955e53e9832de93bfb0cfb85b;hb=9fab4bf4cc077c21e43941866f3f2c196f28670d": "IBM-pibs",
-	"git.enlightenment.org/legacy/imlib2.git/tree/COPYING":                                                               "Imlib2",
-	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/getcpu.2#n4":                                          "Linux-man-pages-1-para",
-	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/migrate_pages.2#n8":                                   "Linux-man-pages-copyleft-2-para",
-	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/move_pages.2#n5":                                      "Linux-man-pages-copyleft-2-para",
-	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/set_mempolicy.2#n5":                                   "Linux-man-pages-copyleft-var",
-	"git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/infiniband/core/sa.h":                       "Linux-OpenIB",
-	"git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/net/sunrpc/auth_gss/gss_generic_token.c?h=v4.19":    "HPND-sell-variant",
-	"git.openldap.org/openldap/openldap/-/blob/master/COPYRIGHT#L55-63":                                                  "BSD-4.3RENO",
-	"git.openldap.org/openldap/openldap/-/blob/master/COPYRIGHT?ref_type=heads#L39-51":                                   "Furuseth",
-	"git.openldap.org/openldap/openldap/-/blob/master/libraries/libldap/os-local.c?ref_type=heads#L19-23":                "PADL",
-	"git.savannah.gnu.org/cgit/freetype/freetype2.git/tree/docs/FTL.TXT":                                                 "FTL",
-	"git.savannah.gnu.org/cgit/gcl.git/tree/gcl/lsp/gcl_loop.lsp?h=Version_2_6_13pre":                                    "LOOP",
-	"git.savannah.gnu.org/cgit/gnulib.git/tree/modules/COPYING?id=7b08932179d0d6b017f7df01a2ddf6e096b038e3":              "FSFULLRSD",
-	"git.savannah.gnu.org/cgit/indent.git/tree/doc/indent.texi?id=a74c6b4ee49397cf330b333da1042bffa60ed14f#n1788":        "BSD-4.3TAHOE",
-	"git.savannah.gnu.org/cgit/indent.git/tree/doc/indent.texi?id=a74c6b4ee49397cf330b333da1042bffa60ed14f#n74":          "Latex2e-translated-notice",
-	"git.savannah.gnu.org/cgit/kazlib.git/tree/except.c?id=0062df360c2d17d57f6af19b0e444c51feb99036":                     "Kazlib",
-	"git.savannah.gnu.org/cgit/wget.git/tree/util/trunc.c?h=v1.21.3&id=40747a11e44ced5a8ac628a41f879ced3e2ebce9#n6":      "FSFAP-no-warranty-disclaimer",
-	"git.sr.ht/~nabijaczleweli/ossp-var":                                                                                 "OSSP",
-	"github.com/389ds/389-ds-base/blob/main/ldap/include/sysexits-compat.h#L15":                                          "BSD-4.3TAHOE",
-	"github.com/AcademySoftwareFoundation/foundation/blob/main/digital_assets/aswf_digital_assets_license_v1.0.txt":      "ASWF-Digital-Assets-1.0",
-	"github.com/AcademySoftwareFoundation/foundation/blob/main/digital_assets/aswf_digital_assets_license_v1.1.txt":      "ASWF-Digital-Assets-1.1",
-	"github.com/AdaCore/gnatcoll-core/blob/master/docs/index.rst":                                                        "AdaCore-doc",
-	"github.com/AdaCore/gnatcoll-db/blob/master/docs/index.rst":                                                          "AdaCore-doc",
-	"github.com/AdaCore/xmlada/blob/master/docs/index.rst":                                                               "AdaCore-doc",
-	"github.com/BuildCraft/BuildCraft/blob/623d323b1868712f29f4a8b0979a02e8d1835131/LICENSE":                             "MMPL-1.0.1",
-	"github.com/CommunitySpecification/1.0/blob/master/1._Community_Specification_License-v1.md":                         "Community-Spec-1.0",
-	"github.com/CorsixTH/deps/blob/fd339a9f526d1d9c9f01ccf39e438a015da50035/licences/libgsm.txt":                         "TU-Berlin-2.0",
-	"github.com/Cyan4973/xxHash/blob/dev/doc/xxhash_spec.md":                                                             "LPD-document",
-	"github.com/DISIC/politique-de-contribution-open-source/blob/master/LICENSE.pdf":                                     "etalab-2.0",
-	"github.com/Distrotech/hdparm/blob/4517550db29a91420fb2b020349523b1b4512df2/LICENSE.TXT":                             "hdparm",
-	"github.com/Distrotech/transfig/blob/master/transfig/transfig.c":                                                     "Xfig",
-	"github.com/DrItanium/maya/blob/master/LICENSE.CLIPS":                                                                "Clips",
-	"github.com/Dual-Life/mime-base64/blob/master/Base64.xs#L12":                                                         "metamail",
-	"github.com/EthicalSource/hippocratic-license/blob/58c0e646d64ff6fbee275bfe2b9492f914e3ab2a/LICENSE.txt":             "Hippocratic-2.1",
-	"github.com/FreeRADIUS/freeradius-client/blob/master/COPYRIGHT#L32":                                                  "HPND-Fenneberg-Livingston",
-	"github.com/GNOME/gcr/blob/master/docs/COPYING":                                                                      "GCR-docs",
-	"github.com/GNOME/libxml2/blob/master/dict.c":                                                                        "ISC-Veillard",
-	"github.com/HDFGroup/hdf5/?tab=License-1-ov-file#readme":                                                             "HDF5",
-	"github.com/KhronosGroup/SPIRV-Cross/blob/main/LICENSES/LicenseRef-KhronosFreeUse.txt":                               "MIT-Khronos-old",
-	"github.com/KhronosGroup/glslang/blob/main/LICENSE.txt#L949":                                                         "AML-glslang",
-	"github.com/MariaDB/server/blob/11.6/libmysqld/lib_sql.cc":                                                           "Boehm-GC-without-fee",
-	"github.com/Neo23x0/sigma/blob/master/LICENSE.Detection.Rules.md":                                                    "DRL-1.0",
-	"github.com/OGRECave/ogre/blob/master/OgreMain/include/OgreSingleton.h#L28C3-L35C46":                                 "Game-Programming-Gems",
-	"github.com/Perl/perl5/blob/blead/util.c#L6136":                                                                      "Martin-Birgmeier",
-	"github.com/PixarAnimationStudios/OpenSubdiv/blob/v3_5_0/opensubdiv/version.cpp#L2-L22":                              "Pixar",
-	"github.com/PixarAnimationStudios/OpenSubdiv/raw/v3_5_0/LICENSE.txt":                                                 "Pixar",
-	"github.com/RTimothyEdwards/magic/blob/master/LICENSE":                                                               "HPND-UC-export-US",
-	"github.com/SELinuxProject/selinux/blob/master/libselinux/LICENSE":                                                   "libselinux-1.0",
-	"github.com/SWI-Prolog/packages-clib/blob/master/sha1/brg_endian.h":                                                  "Brian-Gladman-3-Clause",
-	"github.com/SWI-Prolog/packages-xpce/blob/161a40cd82004f731ba48024f9d30af388a7edf5/src/img/gifwrite.c#L21-L26":       "FBM",
-	"github.com/SWI-Prolog/swipl-devel/blob/master/src/os/dtoa.c":                                                        "dtoa",
-	"github.com/SigmaHQ/Detection-Rule-License/blob/6ec7fbde6101d101b5b5d1fcb8f9b69fbc76c04a/LICENSE.Detection.Rules.md": "DRL-1.1",
-	"github.com/Slicer/Slicer/blob/main/License.txt":                                                                     "3D-Slicer-1.0",
-	"github.com/Unidata/UDUNITS-2/blob/master/COPYRIGHT":                                                                 "UCAR",
-	"github.com/acpica/acpica/blob/master/source/common/acfileio.c#L119":                                                 "BSD-3-Clause-acpica",
-	"github.com/adaptivecomputing/torque/blob/master/PBS_License.txt":                                                    "OpenPBS-2.3",
-	"github.com/adversary-org/wtfnmf/raw/3f2cd8235a64350a57a51b9739715edaea63ec1a/COPYING.WTFNMFPL-utf8":                 "WTFNMFPL",
-	"github.com/adversary-org/wtfnmf/raw/refs/tags/1.0/COPYING.WTFNMFPL":                                                 "WTFNMFPL",
-	"github.com/ap/Text-Tabs/blob/master/lib.modern/Text/Tabs.pm#L148":                                                   "TTWL",
-	"github.com/apache/apr/blob/trunk/LICENSE#L298C6-L298C29":                                                            "Caldera-no-preamble",
-	"github.com/audacious-media-player/audacious/blob/master/COPYING":                                                    "BSD-2-Clause-pkgconf-disclaimer",
-	"github.com/audacious-media-player/audacious/blob/master/src/audacious/main.cc":                                      "BSD-2-Clause-pkgconf-disclaimer",
+	"git.enlightenment.org/legacy/imlib2.git/tree/COPYING":                                                                                   "Imlib2",
+	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/getcpu.2#n4":                                                              "Linux-man-pages-1-para",
+	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/migrate_pages.2#n8":                                                       "Linux-man-pages-copyleft-2-para",
+	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/move_pages.2#n5":                                                          "Linux-man-pages-copyleft-2-para",
+	"git.kernel.org/pub/scm/docs/man-pages/man-pages.git/tree/man2/set_mempolicy.2#n5":                                                       "Linux-man-pages-copyleft-var",
+	"git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/infiniband/core/sa.h":                                           "Linux-OpenIB",
+	"git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/net/sunrpc/auth_gss/gss_generic_token.c?h=v4.19":                        "HPND-sell-variant",
+	"git.openldap.org/openldap/openldap/-/blob/master/COPYRIGHT#L55-63":                                                                      "BSD-4.3RENO",
+	"git.openldap.org/openldap/openldap/-/blob/master/COPYRIGHT?ref_type=heads#L39-51":                                                       "Furuseth",
+	"git.openldap.org/openldap/openldap/-/blob/master/libraries/libldap/os-local.c?ref_type=heads#L19-23":                                    "PADL",
+	"git.savannah.gnu.org/cgit/freetype/freetype2.git/tree/docs/FTL.TXT":                                                                     "FTL",
+	"git.savannah.gnu.org/cgit/gcl.git/tree/gcl/lsp/gcl_loop.lsp?h=Version_2_6_13pre":                                                        "LOOP",
+	"git.savannah.gnu.org/cgit/gnulib.git/tree/modules/COPYING?id=7b08932179d0d6b017f7df01a2ddf6e096b038e3":                                  "FSFULLRSD",
+	"git.savannah.gnu.org/cgit/indent.git/tree/doc/indent.texi?id=a74c6b4ee49397cf330b333da1042bffa60ed14f#n1788":                            "BSD-4.3TAHOE",
+	"git.savannah.gnu.org/cgit/indent.git/tree/doc/indent.texi?id=a74c6b4ee49397cf330b333da1042bffa60ed14f#n74":                              "Latex2e-translated-notice",
+	"git.savannah.gnu.org/cgit/kazlib.git/tree/except.c?id=0062df360c2d17d57f6af19b0e444c51feb99036":                                         "Kazlib",
+	"git.savannah.gnu.org/cgit/wget.git/tree/util/trunc.c?h=v1.21.3&id=40747a11e44ced5a8ac628a41f879ced3e2ebce9#n6":                          "FSFAP-no-warranty-disclaimer",
+	"git.sr.ht/~nabijaczleweli/ossp-var":                                                                                                     "OSSP",
+	"github.com/389ds/389-ds-base/blob/main/ldap/include/sysexits-compat.h#L15":                                                              "BSD-4.3TAHOE",
+	"github.com/AcademySoftwareFoundation/foundation/blob/main/digital_assets/aswf_digital_assets_license_v1.0.txt":                          "ASWF-Digital-Assets-1.0",
+	"github.com/AcademySoftwareFoundation/foundation/blob/main/digital_assets/aswf_digital_assets_license_v1.1.txt":                          "ASWF-Digital-Assets-1.1",
+	"github.com/AdaCore/gnatcoll-core/blob/master/docs/index.rst":                                                                            "AdaCore-doc",
+	"github.com/AdaCore/gnatcoll-db/blob/master/docs/index.rst":                                                                              "AdaCore-doc",
+	"github.com/AdaCore/xmlada/blob/master/docs/index.rst":                                                                                   "AdaCore-doc",
+	"github.com/BuildCraft/BuildCraft/blob/623d323b1868712f29f4a8b0979a02e8d1835131/LICENSE":                                                 "MMPL-1.0.1",
+	"github.com/CommunitySpecification/1.0/blob/master/1._Community_Specification_License-v1.md":                                             "Community-Spec-1.0",
+	"github.com/CorsixTH/deps/blob/fd339a9f526d1d9c9f01ccf39e438a015da50035/licences/libgsm.txt":                                             "TU-Berlin-2.0",
+	"github.com/Cyan4973/xxHash/blob/dev/doc/xxhash_spec.md":                                                                                 "LPD-document",
+	"github.com/DISIC/politique-de-contribution-open-source/blob/master/LICENSE.pdf":                                                         "etalab-2.0",
+	"github.com/Distrotech/hdparm/blob/4517550db29a91420fb2b020349523b1b4512df2/LICENSE.TXT":                                                 "hdparm",
+	"github.com/Distrotech/transfig/blob/master/transfig/transfig.c":                                                                         "Xfig",
+	"github.com/DrItanium/maya/blob/master/LICENSE.CLIPS":                                                                                    "Clips",
+	"github.com/Dual-Life/mime-base64/blob/master/Base64.xs#L12":                                                                             "metamail",
+	"github.com/EthicalSource/hippocratic-license/blob/58c0e646d64ff6fbee275bfe2b9492f914e3ab2a/LICENSE.txt":                                 "Hippocratic-2.1",
+	"github.com/Fraunhofer-IIS/mpeghdec/blob/main/LICENSE.txt":                                                                               "FDK-MPEG-H",
+	"github.com/FreeRADIUS/freeradius-client/blob/master/COPYRIGHT#L32":                                                                      "HPND-Fenneberg-Livingston",
+	"github.com/GNOME/gcr/blob/master/docs/COPYING":                                                                                          "GCR-docs",
+	"github.com/GNOME/libxml2/blob/master/dict.c":                                                                                            "ISC-Veillard",
+	"github.com/HDFGroup/hdf5/?tab=License-1-ov-file#readme":                                                                                 "HDF5",
+	"github.com/KhronosGroup/SPIRV-Cross/blob/main/LICENSES/LicenseRef-KhronosFreeUse.txt":                                                   "MIT-Khronos-old",
+	"github.com/KhronosGroup/glslang/blob/main/LICENSE.txt#L949":                                                                             "AML-glslang",
+	"github.com/MariaDB/server/blob/11.6/libmysqld/lib_sql.cc":                                                                               "Boehm-GC-without-fee",
+	"github.com/Neo23x0/sigma/blob/master/LICENSE.Detection.Rules.md":                                                                        "DRL-1.0",
+	"github.com/OGRECave/ogre/blob/master/OgreMain/include/OgreSingleton.h#L28C3-L35C46":                                                     "Game-Programming-Gems",
+	"github.com/Perl/perl5/blob/blead/util.c#L6136":                                                                                          "Martin-Birgmeier",
+	"github.com/PicoEFI/PicoEFI/blob/2263ac1a2bc98e5534d64a4896d3cfbbae00745a/LICENSES/LicenseRef-scancode-bsd-no-disclaimer-unmodified.txt": "BSD-Source-Code-no-disclaimer",
+	"github.com/PixarAnimationStudios/OpenSubdiv/blob/v3_5_0/opensubdiv/version.cpp#L2-L22":                                                  "Pixar",
+	"github.com/PixarAnimationStudios/OpenSubdiv/raw/v3_5_0/LICENSE.txt":                                                                     "Pixar",
+	"github.com/RTimothyEdwards/magic/blob/master/LICENSE":                                                                                   "HPND-UC-export-US",
+	"github.com/SELinuxProject/selinux/blob/master/libselinux/LICENSE":                                                                       "libselinux-1.0",
+	"github.com/SWI-Prolog/packages-clib/blob/master/sha1/brg_endian.h":                                                                      "Brian-Gladman-3-Clause",
+	"github.com/SWI-Prolog/packages-xpce/blob/161a40cd82004f731ba48024f9d30af388a7edf5/src/img/gifwrite.c#L21-L26":                           "FBM",
+	"github.com/SWI-Prolog/swipl-devel/blob/master/src/os/dtoa.c":                                                                            "dtoa",
+	"github.com/SigmaHQ/Detection-Rule-License/blob/6ec7fbde6101d101b5b5d1fcb8f9b69fbc76c04a/LICENSE.Detection.Rules.md":                     "DRL-1.1",
+	"github.com/Slicer/Slicer/blob/main/License.txt":                                                                                         "3D-Slicer-1.0",
+	"github.com/Unidata/UDUNITS-2/blob/master/COPYRIGHT":                                                                                     "UCAR",
+	"github.com/acpica/acpica/blob/master/source/common/acfileio.c#L119":                                                                     "BSD-3-Clause-acpica",
+	"github.com/adaptivecomputing/torque/blob/master/PBS_License.txt":                                                                        "OpenPBS-2.3",
+	"github.com/adversary-org/wtfnmf/raw/3f2cd8235a64350a57a51b9739715edaea63ec1a/COPYING.WTFNMFPL-utf8":                                     "WTFNMFPL",
+	"github.com/adversary-org/wtfnmf/raw/refs/tags/1.0/COPYING.WTFNMFPL":                                                                     "WTFNMFPL",
+	"github.com/ap/Text-Tabs/blob/master/lib.modern/Text/Tabs.pm#L148":                                                                       "TTWL",
+	"github.com/apache/apr/blob/trunk/LICENSE#L298C6-L298C29":                                                                                "Caldera-no-preamble",
+	"github.com/audacious-media-player/audacious/blob/master/COPYING":                                                                        "BSD-2-Clause-pkgconf-disclaimer",
+	"github.com/audacious-media-player/audacious/blob/master/src/audacious/main.cc":                                                          "BSD-2-Clause-pkgconf-disclaimer",
 	"github.com/aws/mit-0": "MIT-0",
 	"github.com/awsdocs/aws-cloud9-user-guide/blob/master/LICENSE-SAMPLECODE":                                                 "MIT-0",
 	"github.com/bagder/curl/blob/master/COPYING":                                                                              "curl",
@@ -1772,6 +1804,7 @@ var urlToLicense = map[string]string{
 	"github.com/file/file/blob/master/COPYING":                                                                                                                            "BSD-2-Clause-Darwin",
 	"github.com/freebsd/freebsd-src/blob/main/lib/msun/src/e_acosh.c":                                                                                                     "SunPro",
 	"github.com/freebsd/freebsd-src/blob/main/lib/msun/src/e_lgammal.c":                                                                                                   "SunPro",
+	"github.com/freebsd/pkg/blob/main/src/add.c":                                                                                                                          "BSD-2-Clause-pos-unchanged",
 	"github.com/gabegundy/atlserver/blob/master/License.txt":                                                                                                              "MS-LPL",
 	"github.com/greymass/swift-eosio/blob/master/LICENSE":                                                                                                                 "BSD-3-Clause-No-Military-License",
 	"github.com/hamano/man2html/blob/master/man2html.c":                                                                                                                   "man2html",
@@ -1784,6 +1817,7 @@ var urlToLicense = map[string]string{
 	"github.com/jsommers/pytricia/blob/master/patricia.c#L33-L67":                                                                                                         "BSD-4-Clause",
 	"github.com/kfish/xsel/blob/master/COPYING":                                                                                                                           "HPND-sell-variant",
 	"github.com/kohler/t1utils/blob/master/LICENSE":                                                                                                                       "MIT-Click",
+	"github.com/krb5/krb5/blob/kfw-4.0.1-beta1/src/lib/crypto/builtin/aes/aesopt.h":                                                                                       "Brian-Gladman-3-Clause-no-conversion",
 	"github.com/krb5/krb5/blob/krb5-1.21.2-final/NOTICE#L111-L133":                                                                                                        "HPND-export2-US",
 	"github.com/krb5/krb5/blob/krb5-1.21.2-final/NOTICE#L1157-L1182":                                                                                                      "HPND-export-US-modify",
 	"github.com/krb5/krb5/blob/krb5-1.21.2-final/NOTICE#L140-L156":                                                                                                        "Brian-Gladman-2-Clause",
@@ -1793,6 +1827,7 @@ var urlToLicense = map[string]string{
 	"github.com/krb5/krb5/blob/krb5-1.21.2-final/NOTICE#L831-L852":                                                                                                        "HPND-export-US-acknowledgement",
 	"github.com/krzyzanowskim/CryptoSwift/blob/main/LICENSE":                                                                                                              "CryptoSwift",
 	"github.com/lattera/freebsd/blob/master/sys/cam/cam.c#L4":                                                                                                             "BSD-Source-beginning-file",
+	"github.com/libarchive/libarchive/blob/master/libarchive_fe/line_reader.c":                                                                                            "BSD-2-Clause-pos-unchanged",
 	"github.com/libcheck/check/blob/master/checkmk/checkmk.in":                                                                                                            "checkmk",
 	"github.com/libjpeg-turbo/libjpeg-turbo/blob/main/README.ijg#L117-L161":                                                                                               "IJG",
 	"github.com/lsof-org/lsof/blob/master/COPYING":                                                                                                                        "lsof",
@@ -1805,6 +1840,7 @@ var urlToLicense = map[string]string{
 	"github.com/mm2/Little-CMS/blob/master/src/cmssm.c#L207":                                                                                                              "softSurfer",
 	"github.com/mruby/mruby/blob/83d12f8d52522cdb7c8cc46fad34821359f453e6/mrbgems/mruby-dir/src/Win/dirent.c#L127-L140":                                                   "HPND-Kevlin-Henney",
 	"github.com/mtoyoda/sl/blob/master/LICENSE":                                                                                                                           "SL",
+	"github.com/mvt-project/mvt/blob/main/LICENSE":                                                                                                                        "MVT-1.1",
 	"github.com/n8n-io/n8n/blob/master/LICENSE.md":                                                                                                                        "SUL-1.0",
 	"github.com/ncbi/datasets/blob/0ea4cd16b61e5b799d9cc55aecfa016d6c9bd2bf/LICENSE.md":                                                                                   "NCBI-PD",
 	"github.com/ncbi/datasets/blob/master/LICENSE.md":                                                                                                                     "NCBI-PD",
@@ -1815,6 +1851,7 @@ var urlToLicense = map[string]string{
 	"github.com/novnc/noVNC/blob/master/core/crypto/des.js#L24":                                                                                                           "Widget-Workshop",
 	"github.com/oetiker/rrdtool-1.x/blob/master/src/plbasename.c#L8-L11":                                                                                                  "gtkbook",
 	"github.com/open-quantum-safe/liboqs/blob/40b01fdbb270f8614fde30e65d30e9da18c02393/src/common/rand/rand_nist.c#L1-L15":                                                "NIST-Software",
+	"github.com/open-webui/open-webui/blob/main/LICENSE":                                                                                                                  "BSD-3-Clause-OpenWebUI",
 	"github.com/openjdk/jdk/blob/6162e2c5213c5dd7c1127fd9616b543efa898962/LICENSE":                                                                                        "GPL-2.0-or-later",
 	"github.com/openssh/openssh-portable/blob/1b11ea7c58cd5c59838b5fa574cd456d6047b2d4/LICENCE#L10":                                                                       "SSH-OpenSSH",
 	"github.com/openssh/openssh-portable/blob/1b11ea7c58cd5c59838b5fa574cd456d6047b2d4/pathnames.h":                                                                       "SSH-short",
@@ -1846,6 +1883,7 @@ var urlToLicense = map[string]string{
 	"github.com/sigmavirus24/x11-ssh-askpass/blob/master/dynlist.c":                                                                                                       "HPND-sell-variant-MIT-disclaimer-rev",
 	"github.com/signal11/hidapi/blob/master/LICENSE-orig.txt":                                                                                                             "HIDAPI",
 	"github.com/slogan621/gtkbook":                                                                                                                                        "gtkbook",
+	"github.com/sudo-project/sudo/blob/c1307ea9ff340ce0538779f8e456501461fc44b7/plugins/sudoers/redblack.c#L24-L43":                                                       "BSD-ask-to-endorse",
 	"github.com/swh/ladspa/blob/7bf6f3799fdba70fda297c2d8fd9f526803d9680/gsm/COPYRIGHT":                                                                                   "TU-Berlin-1.0",
 	"github.com/tats/w3m/blob/master/COPYING":                                                                                                                             "w3m",
 	"github.com/tcheneau/Routing/blob/f09f46fcfe636107f22f2c98348188a65a135d98/README.md":                                                                                 "NIST-PD",
@@ -1856,6 +1894,7 @@ var urlToLicense = map[string]string{
 	"github.com/uim/libgcroots/blob/master/COPYING":                                                                                                                       "Boehm-GC",
 	"github.com/usnistgov/fipy/blob/86aaa5c2ba2c6f1be19593c5986071cf6568cc34/LICENSE.rst":                                                                                 "NIST-PD-fallback",
 	"github.com/usnistgov/jsip/blob/59700e6926cbe96c5cdae897d9a7d2656b42abe3/LICENSE":                                                                                     "NIST-PD-fallback",
+	"github.com/vattam/BSDGames/blob/master/atc/extern.c#L36":                                                                                                             "atc-game",
 	"github.com/vixie/cron/tree/545b3f5246824a9cda5905eeb7cf019c95e66995":                                                                                                 "Vixie-Cron",
 	"github.com/vstroebel/jpeg-encoder/blob/main/src/fdct.rs#L1-L72":                                                                                                      "IJG",
 	"github.com/wernerd/ZRTPCPP/blob/6b3cd8e6783642292bad0c21e3e5e5ce45ff3e03/cryptcommon/twofish.c#L113C3-L127":                                                          "Ferguson-Twofish",
@@ -1869,6 +1908,7 @@ var urlToLicense = map[string]string{
 	"gitlab.com/embeddable-common-lisp/ecl/-/blob/develop/src/lsp/loop.lsp":                                                                                               "LOOP",
 	"gitlab.com/libeigen/eigen/-/blob/master/COPYING.MINPACK":                                                                                                             "Minpack",
 	"gitlab.common-lisp.net/cmucl/cmucl/-/blob/master/src/code/loop.lisp":                                                                                                 "LOOP",
+	"gitlab.freedesktop.org/dbus/dbus/-/blob/789d97ad53044f94351a958e785c2923643b346a/COPYING#L11-207":                                                                    "AFL-2.1",
 	"gitlab.freedesktop.org/freetype/freetype/-/raw/master/docs/FTL.TXT":                                                                                                  "FTL",
 	"gitlab.freedesktop.org/libopenraw/libopenraw/blob/master/lib/ljpegdecompressor.cpp#L32":                                                                              "Cornell-Lossless-JPEG",
 	"gitlab.freedesktop.org/mesa/glw/-/blob/master/README?ref_type=heads":                                                                                                 "SGI-OpenGL",
@@ -1892,6 +1932,7 @@ var urlToLicense = map[string]string{
 	"gitlab.freedesktop.org/xorg/lib/libxinerama/-/blob/cc22c2f60c3862482562955116d5455263b443dc/COPYING#L44-66":                                                          "X11-no-permit-persons",
 	"gitlab.freedesktop.org/xorg/lib/libxtst/-/blob/master/COPYING?ref_type=heads#L108-117":                                                                               "HPND-doc-sell",
 	"gitlab.freedesktop.org/xorg/lib/libxtst/-/blob/master/COPYING?ref_type=heads#L70-77":                                                                                 "HPND-doc",
+	"gitlab.freedesktop.org/xorg/xserver/-/blob/dd5c2595a42d3ff0c4f18d9b53d1f6c3fd934fd4/COPYING#L365-389":                                                                "MIT",
 	"gitlab.freedesktop.org/xorg/xserver/-/blob/master/COPYING?ref_type=heads#L1781":                                                                                      "HPND-sell-MIT-disclaimer-xserver",
 	"gitlab.freedesktop.org/xorg/xserver/-/blob/master/COPYING?ref_type=heads#L239":                                                                                       "DEC-3-Clause",
 	"gitlab.freedesktop.org/xorg/xserver/-/blob/master/COPYING?ref_type=heads#L752":                                                                                       "Adobe-Display-PostScript",
@@ -1906,6 +1947,7 @@ var urlToLicense = map[string]string{
 	"heasarc.gsfc.nasa.gov/docs/software/ftools/fv/doc/license.html":                                                                                                      "CFITSIO",
 	"helixcommunity.org/content/rpsl":                                                                                                                                     "RPSL-1.0",
 	"hstechdocs.helpsystems.com/manuals/globalscape/archive/cuteftp6/open_ssl_license_agreement.htm":                                                                      "OpenSSL-standalone",
+	"interoperable-europe.ec.europa.eu/sites/default/files/inline-files/EUPL%20v1_2%20EN(1).txt":                                                                          "EUPL-1.2",
 	"java.net/projects/javaeetutorial/pages/BerkeleyLicense":                                                                                                              "BSD-3-Clause-No-Nuclear-License-2014",
 	"javaee.github.io/glassfish/LICENSE":                                                                                                                                  "CDDL-1.1",
 	"jogamp.org/git/?p=gluegen.git;a=blob_plain;f=LICENSE.txt":                                                                                                            "BSD-3-Clause-No-Nuclear-Warranty",
@@ -1924,6 +1966,7 @@ var urlToLicense = map[string]string{
 	"library.netapp.com/ecm/ecm_download_file/ECMP1196395":                                                                                                                "OpenSSL-standalone",
 	"license.coscl.org.cn/MulanPSL/":                                                                                                                                      "MulanPSL-1.0",
 	"license.coscl.org.cn/MulanPSL2":                                                                                                                                      "MulanPSL-2.0",
+	"license.mvt.re/1.1/":                                                                                                                                                 "MVT-1.1",
 	"lists.gnu.org/archive/html/autoconf/2012-04/msg00061.html":                                                                                                           "FSFULLRWD",
 	"lists.opensource.org/pipermail/license-discuss_lists.opensource.org/2002-November/006304.html":                                                                       "HPND",
 	"mariadb.com/bsl11/":                                                                                             "BUSL-1.1",
@@ -1965,99 +2008,105 @@ var urlToLicense = map[string]string{
 	"opensource.linux-mirror.org/licenses/afl-1.1.txt":                                                               "AFL-1.1",
 	"opensource.linux-mirror.org/licenses/afl-1.2.txt":                                                               "AFL-1.2",
 	"opensource.linux-mirror.org/licenses/afl-2.1.txt":                                                               "AFL-2.1",
-	"opensource.org/license/apache-2-0":                                                                              "Apache-2.0",
-	"opensource.org/license/mit/":                                                                                    "MIT",
-	"opensource.org/license/olfl-1-3/":                                                                               "OLFL-1.3",
-	"opensource.org/license/osc-license-1-0":                                                                         "OSC-1.0",
-	"opensource.org/licenses/0BSD":                                                                                   "0BSD",
-	"opensource.org/licenses/AGPL-3.0":                                                                               "AGPL-3.0-or-later",
-	"opensource.org/licenses/APL-1.0":                                                                                "APL-1.0",
-	"opensource.org/licenses/Apache-1.1":                                                                             "Apache-1.1",
-	"opensource.org/licenses/Apache-2.0":                                                                             "Apache-2.0",
-	"opensource.org/licenses/Artistic-1.0":                                                                           "Artistic-1.0-cl8",
-	"opensource.org/licenses/BSD-2-Clause":                                                                           "BSD-2-Clause",
-	"opensource.org/licenses/BSD-3-Clause":                                                                           "BSD-3-Clause",
-	"opensource.org/licenses/BSDplusPatent":                                                                          "BSD-2-Clause-Patent",
-	"opensource.org/licenses/BSL-1.0":                                                                                "BSL-1.0",
-	"opensource.org/licenses/CAL-1.0":                                                                                "CAL-1.0-Combined-Work-Exception",
-	"opensource.org/licenses/CATOSL-1.1":                                                                             "CATOSL-1.1",
-	"opensource.org/licenses/CNRI-Python":                                                                            "CNRI-Python",
-	"opensource.org/licenses/CPAL-1.0":                                                                               "CPAL-1.0",
-	"opensource.org/licenses/CPL-1.0":                                                                                "CPL-1.0",
-	"opensource.org/licenses/CUA-OPL-1.0":                                                                            "CUA-OPL-1.0",
-	"opensource.org/licenses/ECL-1.0":                                                                                "ECL-1.0",
-	"opensource.org/licenses/ECL-2.0":                                                                                "ECL-2.0",
-	"opensource.org/licenses/EFL-1.0":                                                                                "EFL-1.0",
-	"opensource.org/licenses/EFL-2.0":                                                                                "EFL-2.0",
-	"opensource.org/licenses/EPL-1.0":                                                                                "EPL-1.0",
-	"opensource.org/licenses/EUDatagrid":                                                                             "EUDatagrid",
-	"opensource.org/licenses/EUPL-1.1":                                                                               "EUPL-1.1",
-	"opensource.org/licenses/EUPL-1.2":                                                                               "EUPL-1.2",
-	"opensource.org/licenses/Entessa":                                                                                "Entessa",
-	"opensource.org/licenses/Fair":                                                                                   "Fair",
-	"opensource.org/licenses/Frameworx-1.0":                                                                          "Frameworx-1.0",
-	"opensource.org/licenses/GPL-2.0":                                                                                "GPL-2.0-or-later",
-	"opensource.org/licenses/GPL-3.0":                                                                                "GPL-3.0-or-later",
-	"opensource.org/licenses/HPND":                                                                                   "HPND",
-	"opensource.org/licenses/IPA":                                                                                    "IPA",
-	"opensource.org/licenses/IPL-1.0":                                                                                "IPL-1.0",
-	"opensource.org/licenses/ISC":                                                                                    "ISC",
-	"opensource.org/licenses/Intel":                                                                                  "Intel",
-	"opensource.org/licenses/LGPL-2.1":                                                                               "LGPL-2.1-or-later",
-	"opensource.org/licenses/LGPL-3.0":                                                                               "LGPL-3.0-or-later",
-	"opensource.org/licenses/LPL-1.0":                                                                                "LPL-1.0",
-	"opensource.org/licenses/LPL-1.02":                                                                               "LPL-1.02",
-	"opensource.org/licenses/LPPL-1.3c":                                                                              "LPPL-1.3c",
-	"opensource.org/licenses/LiLiQ-P-1.1":                                                                            "LiLiQ-P-1.1",
-	"opensource.org/licenses/LiLiQ-R-1.1":                                                                            "LiLiQ-R-1.1",
-	"opensource.org/licenses/LiLiQ-Rplus-1.1":                                                                        "LiLiQ-Rplus-1.1",
-	"opensource.org/licenses/MIT":                                                                                    "MIT",
-	"opensource.org/licenses/MPL-1.0":                                                                                "MPL-1.0",
-	"opensource.org/licenses/MPL-1.1":                                                                                "MPL-1.1",
-	"opensource.org/licenses/MPL-2.0":                                                                                "MPL-2.0-no-copyleft-exception",
-	"opensource.org/licenses/MS-PL":                                                                                  "MS-PL",
-	"opensource.org/licenses/MS-RL":                                                                                  "MS-RL",
-	"opensource.org/licenses/MirOS":                                                                                  "MirOS",
-	"opensource.org/licenses/Motosoto":                                                                               "Motosoto",
-	"opensource.org/licenses/Multics":                                                                                "Multics",
-	"opensource.org/licenses/NASA-1.3":                                                                               "NASA-1.3",
-	"opensource.org/licenses/NCSA":                                                                                   "NCSA",
-	"opensource.org/licenses/NGPL":                                                                                   "NGPL",
-	"opensource.org/licenses/NOSL3.0":                                                                                "NPOSL-3.0",
-	"opensource.org/licenses/NTP":                                                                                    "NTP",
-	"opensource.org/licenses/Naumen":                                                                                 "Naumen",
-	"opensource.org/licenses/OCLC-2.0":                                                                               "OCLC-2.0",
-	"opensource.org/licenses/OFL-1.1":                                                                                "OFL-1.1-no-RFN",
-	"opensource.org/licenses/OGTSL":                                                                                  "OGTSL",
-	"opensource.org/licenses/OPL-2.1":                                                                                "OSET-PL-2.1",
-	"opensource.org/licenses/OSL-1.0":                                                                                "OSL-1.0",
-	"opensource.org/licenses/OSL-2.1":                                                                                "OSL-2.1",
-	"opensource.org/licenses/OSL-3.0":                                                                                "OSL-3.0",
-	"opensource.org/licenses/PHP-3.0":                                                                                "PHP-3.0",
-	"opensource.org/licenses/PostgreSQL":                                                                             "PostgreSQL",
-	"opensource.org/licenses/Python-2.0":                                                                             "Python-2.0",
-	"opensource.org/licenses/QPL-1.0":                                                                                "QPL-1.0",
-	"opensource.org/licenses/RPL-1.1":                                                                                "RPL-1.1",
-	"opensource.org/licenses/RPL-1.5":                                                                                "RPL-1.5",
-	"opensource.org/licenses/RPSL-1.0":                                                                               "RPSL-1.0",
-	"opensource.org/licenses/RSCPL":                                                                                  "RSCPL",
-	"opensource.org/licenses/SISSL":                                                                                  "SISSL",
-	"opensource.org/licenses/SPL-1.0":                                                                                "SPL-1.0",
-	"opensource.org/licenses/SimPL-2.0":                                                                              "SimPL-2.0",
-	"opensource.org/licenses/Sleepycat":                                                                              "Sleepycat",
-	"opensource.org/licenses/UCL-1.0":                                                                                "UCL-1.0",
-	"opensource.org/licenses/UPL":                                                                                    "UPL-1.0",
-	"opensource.org/licenses/VSL-1.0":                                                                                "VSL-1.0",
-	"opensource.org/licenses/W3C":                                                                                    "W3C",
-	"opensource.org/licenses/Watcom-1.0":                                                                             "Watcom-1.0",
-	"opensource.org/licenses/Xnet":                                                                                   "Xnet",
-	"opensource.org/licenses/ZPL-2.0":                                                                                "ZPL-2.0",
-	"opensource.org/licenses/Zlib":                                                                                   "Zlib",
-	"opensource.org/licenses/afl-3.0":                                                                                "AFL-3.0",
-	"opensource.org/licenses/artistic-license-2.0":                                                                   "Artistic-2.0",
-	"opensource.org/licenses/attribution":                                                                            "AAL",
-	"opensource.org/licenses/cddl1":                                                                                  "CDDL-1.0",
-	"opensource.org/licenses/nokia":                                                                                  "Nokia",
+	"opensource.org/license/0BSD":                                                                                    "0BSD",
+	"opensource.org/license/AAL":                                                                                     "AAL",
+	"opensource.org/license/AFL-3.0":                                                                                 "AFL-3.0",
+	"opensource.org/license/AGPL-3.0":                                                                                "AGPL-3.0-or-later",
+	"opensource.org/license/AGPL-3.0-only":                                                                           "AGPL-3.0-only",
+	"opensource.org/license/APL-1.0":                                                                                 "APL-1.0",
+	"opensource.org/license/Artistic-1.0":                                                                            "Artistic-1.0-cl8",
+	"opensource.org/license/Artistic-2.0":                                                                            "Artistic-2.0",
+	"opensource.org/license/BSD-2-Clause":                                                                            "BSD-2-Clause",
+	"opensource.org/license/BSD-2-Clause-Patent":                                                                     "BSD-2-Clause-Patent",
+	"opensource.org/license/BSD-3-Clause":                                                                            "BSD-3-Clause",
+	"opensource.org/license/BSL-1.0":                                                                                 "BSL-1.0",
+	"opensource.org/license/CAL-1.0":                                                                                 "CAL-1.0-Combined-Work-Exception",
+	"opensource.org/license/CATOSL-1.1":                                                                              "CATOSL-1.1",
+	"opensource.org/license/CDDL-1.0":                                                                                "CDDL-1.0",
+	"opensource.org/license/CNRI-Python":                                                                             "CNRI-Python",
+	"opensource.org/license/CNRI-Python-GPL-Compatible":                                                              "CNRI-Python-GPL-Compatible",
+	"opensource.org/license/CPAL-1.0":                                                                                "CPAL-1.0",
+	"opensource.org/license/CPL-1.0":                                                                                 "CPL-1.0",
+	"opensource.org/license/CUA-OPL-1.0":                                                                             "CUA-OPL-1.0",
+	"opensource.org/license/ECL-1.0":                                                                                 "ECL-1.0",
+	"opensource.org/license/ECL-2.0":                                                                                 "ECL-2.0",
+	"opensource.org/license/EFL-1.0":                                                                                 "EFL-1.0",
+	"opensource.org/license/EFL-2.0":                                                                                 "EFL-2.0",
+	"opensource.org/license/EPL-1.0":                                                                                 "EPL-1.0",
+	"opensource.org/license/EUDatagrid":                                                                              "EUDatagrid",
+	"opensource.org/license/EUPL-1.1":                                                                                "EUPL-1.1",
+	"opensource.org/license/EUPL-1.2":                                                                                "EUPL-1.2",
+	"opensource.org/license/Entessa":                                                                                 "Entessa",
+	"opensource.org/license/Fair":                                                                                    "Fair",
+	"opensource.org/license/Frameworx-1.0":                                                                           "Frameworx-1.0",
+	"opensource.org/license/GPL-2.0":                                                                                 "GPL-2.0-or-later",
+	"opensource.org/license/GPL-2.0-only":                                                                            "GPL-2.0-only",
+	"opensource.org/license/GPL-3.0":                                                                                 "GPL-3.0-or-later",
+	"opensource.org/license/GPL-3.0-only":                                                                            "GPL-3.0-only",
+	"opensource.org/license/HPND":                                                                                    "HPND",
+	"opensource.org/license/IPA":                                                                                     "IPA",
+	"opensource.org/license/IPL-1.0":                                                                                 "IPL-1.0",
+	"opensource.org/license/ISC":                                                                                     "ISC",
+	"opensource.org/license/Intel":                                                                                   "Intel",
+	"opensource.org/license/LGPL-2.1":                                                                                "LGPL-2.1-or-later",
+	"opensource.org/license/LGPL-2.1-only":                                                                           "LGPL-2.1-only",
+	"opensource.org/license/LGPL-3.0":                                                                                "LGPL-3.0-or-later",
+	"opensource.org/license/LPL-1.0":                                                                                 "LPL-1.0",
+	"opensource.org/license/LPL-1.02":                                                                                "LPL-1.02",
+	"opensource.org/license/LPPL-1.3c":                                                                               "LPPL-1.3c",
+	"opensource.org/license/LiLiQ-P-1.1":                                                                             "LiLiQ-P-1.1",
+	"opensource.org/license/LiLiQ-R-1.1":                                                                             "LiLiQ-R-1.1",
+	"opensource.org/license/LiLiQ-Rplus-1.1":                                                                         "LiLiQ-Rplus-1.1",
+	"opensource.org/license/MIT":                                                                                     "MIT",
+	"opensource.org/license/MPL-1.0":                                                                                 "MPL-1.0",
+	"opensource.org/license/MPL-1.1":                                                                                 "MPL-1.1",
+	"opensource.org/license/MPL-2.0":                                                                                 "MPL-2.0-no-copyleft-exception",
+	"opensource.org/license/MS-PL":                                                                                   "MS-PL",
+	"opensource.org/license/MS-RL":                                                                                   "MS-RL",
+	"opensource.org/license/MirOS":                                                                                   "MirOS",
+	"opensource.org/license/Motosoto":                                                                                "Motosoto",
+	"opensource.org/license/Multics":                                                                                 "Multics",
+	"opensource.org/license/NASA-1.3":                                                                                "NASA-1.3",
+	"opensource.org/license/NCSA":                                                                                    "NCSA",
+	"opensource.org/license/NGPL":                                                                                    "NGPL",
+	"opensource.org/license/NPOSL-3.0":                                                                               "NPOSL-3.0",
+	"opensource.org/license/NTP":                                                                                     "NTP",
+	"opensource.org/license/Naumen":                                                                                  "Naumen",
+	"opensource.org/license/Nokia":                                                                                   "Nokia",
+	"opensource.org/license/OCLC-2.0":                                                                                "OCLC-2.0",
+	"opensource.org/license/OFL-1.1":                                                                                 "OFL-1.1-no-RFN",
+	"opensource.org/license/OGTSL":                                                                                   "OGTSL",
+	"opensource.org/license/OLFL-1.3":                                                                                "OLFL-1.3",
+	"opensource.org/license/OSC-1.0":                                                                                 "OSC-1.0",
+	"opensource.org/license/OSET-PL-2.1":                                                                             "OSET-PL-2.1",
+	"opensource.org/license/OSL-1.0":                                                                                 "OSL-1.0",
+	"opensource.org/license/OSL-2.1":                                                                                 "OSL-2.1",
+	"opensource.org/license/OSL-3.0":                                                                                 "OSL-3.0",
+	"opensource.org/license/PHP-3.0":                                                                                 "PHP-3.0",
+	"opensource.org/license/PSF-2-0":                                                                                 "PSF-2.0",
+	"opensource.org/license/PostgreSQL":                                                                              "PostgreSQL",
+	"opensource.org/license/Python-2.0":                                                                              "Python-2.0",
+	"opensource.org/license/Python-2.0.1":                                                                            "Python-2.0.1",
+	"opensource.org/license/QPL-1.0":                                                                                 "QPL-1.0",
+	"opensource.org/license/RPL-1.1":                                                                                 "RPL-1.1",
+	"opensource.org/license/RPL-1.5":                                                                                 "RPL-1.5",
+	"opensource.org/license/RPSL-1.0":                                                                                "RPSL-1.0",
+	"opensource.org/license/RSCPL":                                                                                   "RSCPL",
+	"opensource.org/license/SISSL":                                                                                   "SISSL",
+	"opensource.org/license/SPL-1.0":                                                                                 "SPL-1.0",
+	"opensource.org/license/SiMPL-2.0":                                                                               "SimPL-2.0",
+	"opensource.org/license/Sleepycat":                                                                               "Sleepycat",
+	"opensource.org/license/UCL-1.0":                                                                                 "UCL-1.0",
+	"opensource.org/license/UPL-1.0":                                                                                 "UPL-1.0",
+	"opensource.org/license/VSL-1.0":                                                                                 "VSL-1.0",
+	"opensource.org/license/W3C":                                                                                     "W3C",
+	"opensource.org/license/Watcom-1.0":                                                                              "Watcom-1.0",
+	"opensource.org/license/Xnet":                                                                                    "Xnet",
+	"opensource.org/license/ZPL-2.0":                                                                                 "ZPL-2.0",
+	"opensource.org/license/Zlib":                                                                                    "Zlib",
+	"opensource.org/license/apache-1.1":                                                                              "Apache-1.1",
+	"opensource.org/license/apache-2.0":                                                                              "Apache-2.0",
+	"opensource.org/license/curl":                                                                                    "curl",
 	"oss.sgi.com/projects/FreeB/":                                                                                    "SGI-B-1.1",
 	"oss.sgi.com/projects/FreeB/SGIFreeSWLicB.1.0.html":                                                              "SGI-B-1.0",
 	"oss.sgi.com/projects/FreeB/SGIFreeSWLicB.2.0.pdf":                                                               "SGI-B-2.0",
@@ -2082,37 +2131,40 @@ var urlToLicense = map[string]string{
 	"raw.githubusercontent.com/NTIA/scos-sensor/refs/heads/master/LICENSE.md":                                        "NTIA-PD",
 	"raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.0/LICENSE.openmdw":                                  "OpenMDW-1.0",
 	"raw.githubusercontent.com/blackhole89/notekit/master/data/fonts/Charter%20license.txt":                          "Bitstream-Charter",
-	"rc.quest.com/topics/openssh/license.php#tcpwrappers":                                                            "TCP-wrappers",
-	"research.cs.wisc.edu/condor/license.html#condor":                                                                "Condor-1.1",
-	"research.scea.com/scea_shared_source_license.html":                                                              "SCEA",
-	"romanrm.net/mit-zero":                                                                                           "MIT-0",
-	"sam.zoy.org/wtfpl/COPYING":                                                                                      "WTFPL",
-	"scripts.sil.org/cms/scripts/page.php?item_id=OFL10_web":                                                         "OFL-1.0-no-RFN",
-	"scripts.sil.org/cms/scripts/page.php?item_id=OFL_web":                                                           "OFL-1.1-no-RFN",
-	"slicer.org/LICENSE":                                                                                             "3D-Slicer-1.0",
-	"solderpad.org/licenses/SHL-0.5/":                                                                                "SHL-0.5",
-	"solderpad.org/licenses/SHL-0.51/":                                                                               "SHL-0.51",
-	"source.icu-project.org/repos/icu/icu/trunk/license.html":                                                        "ICU",
-	"sourceforge.net/p/buddy/gitcode/ci/master/tree/README":                                                          "Buddy",
-	"sourceforge.net/p/ctrio/git/ci/master/tree/README":                                                              "ISC-Veillard",
-	"sourceforge.net/p/mcj/xfig/ci/master/tree/src/Makefile.am":                                                      "Xfig",
-	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/other/pnmtorle.c":                                "URT-RLE",
-	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/other/rletopnm.c":                                "URT-RLE",
-	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/ppm/ppmtompeg/jrevdct.c#l1189":                   "MPEG-SSG",
-	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/editor/pnmstitch.c#l2":                                     "pnmstitch",
-	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/netpbm.c#l8":                                               "HPND-Pbmplus",
-	"sourceforge.net/p/sbcl/sbcl/ci/master/tree/src/code/loop.lisp":                                                  "LOOP",
-	"sourceforge.net/p/trustedqsl/tqsl/ci/master/tree/LICENSE.txt":                                                   "TrustedQSL",
-	"sourceforge.net/p/xmedcon/code/ci/master/tree/libs/dicom/README":                                                "OFFIS",
-	"sourceforge.net/p/xmedcon/code/ci/master/tree/libs/ljpg/":                                                       "IJG-short",
-	"sourceforge.net/projects/sevenzip/files/LZMA%20SDK/":                                                            "LZMA-SDK-9.22",
-	"sources.debian.org/copyright/license/debianutils/4.11.2/":                                                       "SMAIL-GPL",
-	"sources.debian.org/src/openmpi/4.1.0-10/ompi/debuggers/msgq_interface.h/?hl=19#L19":                             "mpi-permissive",
-	"sources.gentoo.org/cgi-bin/viewvc.cgi/gentoo-x86/licenses/BitTorrent?r1=1.1&r2=1.1.1.1&diff_format=s":           "BitTorrent-1.0",
-	"sourceware.org/bzip2/1.0.5/bzip2-manual-1.0.5.html":                                                             "bzip2-1.0.6",
-	"sourceware.org/cgit/binutils-gdb/tree/include/coff/sym.h#n11":                                                   "MIPS",
-	"sourceware.org/cgit/binutils-gdb/tree/include/coff/symconst.h#n11":                                              "ThirdEye",
-	"sourceware.org/cgit/valgrind/tree/mpi/libmpiwrap.c":                                                             "bzip2-1.0.6",
+	"raw.githubusercontent.com/landtuna/open-mtools/6c04c2882eca7c4313ec267766ea53ac9bfe129b/mdump.c": "Informatica",
+	"raw.githubusercontent.com/landtuna/open-mtools/6c04c2882eca7c4313ec267766ea53ac9bfe129b/msend.c": "Informatica",
+	"rc.quest.com/topics/openssh/license.php#tcpwrappers":                                             "TCP-wrappers",
+	"research.cs.wisc.edu/condor/license.html#condor":                                                 "Condor-1.1",
+	"research.scea.com/scea_shared_source_license.html":                                               "SCEA",
+	"romanrm.net/mit-zero":                                                                                                                       "MIT-0",
+	"sam.zoy.org/wtfpl/COPYING":                                                                                                                  "WTFPL",
+	"scancode-licensedb.aboutcode.org/bsd-unchanged":                                                                                             "BSD-2-Clause-pos-unchanged",
+	"scripts.sil.org/cms/scripts/page.php?item_id=OFL10_web":                                                                                     "OFL-1.0-no-RFN",
+	"scripts.sil.org/cms/scripts/page.php?item_id=OFL_web":                                                                                       "OFL-1.1-no-RFN",
+	"slicer.org/LICENSE":                                                                                                                         "3D-Slicer-1.0",
+	"solderpad.org/licenses/SHL-0.5/":                                                                                                            "SHL-0.5",
+	"solderpad.org/licenses/SHL-0.51/":                                                                                                           "SHL-0.51",
+	"source.icu-project.org/repos/icu/icu/trunk/license.html":                                                                                    "ICU",
+	"sourceforge.net/p/buddy/gitcode/ci/master/tree/README":                                                                                      "Buddy",
+	"sourceforge.net/p/ctrio/git/ci/master/tree/README":                                                                                          "ISC-Veillard",
+	"sourceforge.net/p/mcj/xfig/ci/master/tree/src/Makefile.am":                                                                                  "Xfig",
+	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/other/pnmtorle.c":                                                            "URT-RLE",
+	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/other/rletopnm.c":                                                            "URT-RLE",
+	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/converter/ppm/ppmtompeg/jrevdct.c#l1189":                                               "MPEG-SSG",
+	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/editor/pnmstitch.c#l2":                                                                 "pnmstitch",
+	"sourceforge.net/p/netpbm/code/HEAD/tree/super_stable/netpbm.c#l8":                                                                           "HPND-Pbmplus",
+	"sourceforge.net/p/sbcl/sbcl/ci/master/tree/src/code/loop.lisp":                                                                              "LOOP",
+	"sourceforge.net/p/trustedqsl/tqsl/ci/master/tree/LICENSE.txt":                                                                               "TrustedQSL",
+	"sourceforge.net/p/xmedcon/code/ci/master/tree/libs/dicom/README":                                                                            "OFFIS",
+	"sourceforge.net/p/xmedcon/code/ci/master/tree/libs/ljpg/":                                                                                   "IJG-short",
+	"sourceforge.net/projects/sevenzip/files/LZMA%20SDK/":                                                                                        "LZMA-SDK-9.22",
+	"sources.debian.org/copyright/license/debianutils/4.11.2/":                                                                                   "SMAIL-GPL",
+	"sources.debian.org/src/openmpi/4.1.0-10/ompi/debuggers/msgq_interface.h/?hl=19#L19":                                                         "mpi-permissive",
+	"sources.gentoo.org/cgi-bin/viewvc.cgi/gentoo-x86/licenses/BitTorrent?r1=1.1&r2=1.1.1.1&diff_format=s":                                       "BitTorrent-1.0",
+	"sourceware.org/bzip2/1.0.5/bzip2-manual-1.0.5.html":                                                                                         "bzip2-1.0.6",
+	"sourceware.org/cgit/binutils-gdb/tree/include/coff/sym.h#n11":                                                                               "MIPS",
+	"sourceware.org/cgit/binutils-gdb/tree/include/coff/symconst.h#n11":                                                                          "ThirdEye",
+	"sourceware.org/cgit/valgrind/tree/mpi/libmpiwrap.c":                                                                                         "bzip2-1.0.6",
 	"sourceware.org/git/?p=binutils-gdb.git;a=blob;f=libiberty/strcasecmp.c;h=131d81c2ce7881fa48c363dc5bf5fb302c61ce0b;hb=HEAD":                  "BSD-4.3RENO",
 	"sourceware.org/git/?p=binutils-gdb.git;a=blob;f=readline/readline/support/wcwidth.c;h=0f5ec995796f4813abbcf4972aec0378ab74722a;hb=HEAD#l55": "HPND-Markus-Kuhn",
 	"sourceware.org/git/?p=bzip2.git;a=blob;f=LICENSE;hb=bzip2-1.0.6":                                                                            "bzip2-1.0.6",
@@ -2129,6 +2181,7 @@ var urlToLicense = map[string]string{
 	"tahoe-lafs.org/trac/tahoe-lafs/browser/trunk/COPYING.TGPPL.rst":                                                      "TGPPL-1.0",
 	"ti.arc.nasa.gov/opensource/nosa/":                                                                                    "NASA-1.3",
 	"trac.enlightenment.org/e/browser/trunk/imlib2/COPYING":                                                               "Imlib2",
+	"tunes.org/legalese/bugroff.html":                                                                                     "Bugroff",
 	"ubuntu.com/legal/font-licence":                                                                                       "Ubuntu-font-1.0",
 	"unlicense.org/":                                                                                                      "Unlicense",
 	"vimdoc.sourceforge.net/htmldoc/uganda.html":                                                                          "Vim",
@@ -2139,6 +2192,7 @@ var urlToLicense = map[string]string{
 	"web.archive.org/web/20041020171434/http://www.rosenlaw.com/osl2.0.html":                                              "OSL-2.0",
 	"web.archive.org/web/20050212003940/http://www.rosenlaw.com/osl21.htm":                                                "OSL-2.1",
 	"web.archive.org/web/20060319014854/http://info.borland.com/devsupport/interbase/opensource/IPL.html":                 "Interbase-1.0",
+	"web.archive.org/web/20061013013632/http://opensource.linux-mirror.org/licenses/afl-2.1.txt":                          "AFL-2.1",
 	"web.archive.org/web/20080207013128/http://www.gnome.org/fonts/":                                                      "Bitstream-Vera",
 	"web.archive.org/web/20100302225219/http://www.zimbra.com/license/zimbra-public-license-1-3.html":                     "Zimbra-1.3",
 	"web.archive.org/web/20111123062036/http://research.cs.wisc.edu/condor/license.html#condor":                           "Condor-1.1",
@@ -2243,11 +2297,11 @@ var urlToLicense = map[string]string{
 	"www.jython.org/license.html":                                                         "CNRI-Jython",
 	"www.kermitproject.org/ck90.html#source":                                              "HPND-export-US",
 	"www.kernel.org/doc/man-pages/licenses.html":                                          "Linux-man-pages-copyleft",
+	"www.latex-project.org/lppl/LPPL-1.3c.txt":                                            "LPPL-1.3c",
 	"www.latex-project.org/lppl/lppl-1-0.txt":                                             "LPPL-1.0",
 	"www.latex-project.org/lppl/lppl-1-1.txt":                                             "LPPL-1.1",
 	"www.latex-project.org/lppl/lppl-1-2.txt":                                             "LPPL-1.2",
 	"www.latex-project.org/lppl/lppl-1-3a.txt":                                            "LPPL-1.3a",
-	"www.latex-project.org/lppl/lppl-1-3c.txt":                                            "LPPL-1.3c",
 	"www.lemis.com/grog/UNIX/ancient-source-all.pdf":                                      "Caldera",
 	"www.libpng.org/pub/png/src/libpng-LICENSE.txt":                                       "libpng-2.0",
 	"www.mail-archive.com/debian-bugs-rc@lists.debian.org/msg11494.html":                  "Symlinks",
@@ -2269,16 +2323,17 @@ var urlToLicense = map[string]string{
 	"www.netlib.org/lapack/LICENSE.txt":                                                   "BSD-3-Clause-Open-MPI",
 	"www.netlib.org/minpack/disclaimer":                                                   "Minpack",
 	"www.networkcultures.org/_uploads/%233notebook_telekommunist.pdf":                     "PPL",
-	"www.oclc.org/research/activities/software/license/v2final.htm":                       "OCLC-2.0",
-	"www.ogc.org/ogc/software/1.0":                                                        "OGC-1.0",
-	"www.ohwr.org/project/cernohl/wikis/Documents/CERN-OHL-version-2":                     "CERN-OHL-W-2.0",
-	"www.ohwr.org/project/licenses/wikis/cern-ohl-v1.1":                                   "CERN-OHL-1.1",
-	"www.ohwr.org/project/licenses/wikis/cern-ohl-v1.2":                                   "CERN-OHL-1.2",
-	"www.open-mpi.org/community/license.php":                                              "BSD-3-Clause-Open-MPI",
-	"www.opencascade.com/content/occt-public-license":                                     "OCCT-PL",
-	"www.opendatacommons.org/licenses/odbl/1.0/":                                          "ODbL-1.0",
-	"www.opengroup.org/testing/downloads/The_Open_Group_TSL.txt":                          "OGTSL",
-	"www.openhub.net/licenses/mslpl":                                                      "MS-LPL",
+	"www.nist.gov/open/copyright-fair-use-and-licensing-statements-srd-data-software-and-technical-series-publications": "NIST-Software",
+	"www.oclc.org/research/activities/software/license/v2final.htm":                                                     "OCLC-2.0",
+	"www.ogc.org/ogc/software/1.0":                                                                                  "OGC-1.0",
+	"www.ohwr.org/project/cernohl/wikis/Documents/CERN-OHL-version-2":                                               "CERN-OHL-W-2.0",
+	"www.ohwr.org/project/licenses/wikis/cern-ohl-v1.1":                                                             "CERN-OHL-1.1",
+	"www.ohwr.org/project/licenses/wikis/cern-ohl-v1.2":                                                             "CERN-OHL-1.2",
+	"www.open-mpi.org/community/license.php":                                                                        "BSD-3-Clause-Open-MPI",
+	"www.opencascade.com/content/occt-public-license":                                                               "OCCT-PL",
+	"www.opendatacommons.org/licenses/odbl/1.0/":                                                                    "ODbL-1.0",
+	"www.opengroup.org/testing/downloads/The_Open_Group_TSL.txt":                                                    "OGTSL",
+	"www.openhub.net/licenses/mslpl":                                                                                "MS-LPL",
 	"www.openldap.org/devel/gitweb.cgi?p=openldap.git;a=blob;f=LICENSE;hb=1cae062821881f41b73012ba816434897abf4205": "OLDAP-2.6",
 	"www.openldap.org/devel/gitweb.cgi?p=openldap.git;a=blob;f=LICENSE;hb=37b4b3f6cc4bf34e1d3dec61e69914b9819d8894": "NBPL-1.0",
 	"www.openldap.org/devel/gitweb.cgi?p=openldap.git;a=blob;f=LICENSE;hb=42b0383c50c299977b5893ee695cf4e486fb0dc7": "OLDAP-1.2",
@@ -2301,7 +2356,7 @@ var urlToLicense = map[string]string{
 	"www.opensource.apple.com/license/apsl/":                                                             "APSL-2.0",
 	"www.opensource.apple.com/source/IOSerialFamily/IOSerialFamily-7/APPLE_LICENSE":                      "APSL-1.1",
 	"www.opensource.apple.com/source/tcl/tcl-5/tcl/generic/regfronts.c":                                  "Spencer-99",
-	"www.opensource.org/licenses/EPL-2.0":                                                                "EPL-2.0",
+	"www.opensource.org/license/EPL-2.0":                                                                 "EPL-2.0",
 	"www.openssl.org/source/license.html":                                                                "OpenSSL",
 	"www.osetfoundation.org/public-license":                                                              "OSET-PL-2.1",
 	"www.parliament.uk/site-information/copyright-parliament/open-parliament-licence/":                   "OPL-UK-3.0",

internal/spdxlicense/license_url_test.go

@@ -123,6 +123,96 @@ func TestLicenseByURL_AlternateScheme(t *testing.T) {
 	}
 }
 
+func TestLicenseByURL_OpenSourceOrgVariants(t *testing.T) {
+	// SPDX has changed the form of opensource.org URLs across list versions (e.g. 3.29.0 moved
+	// opensource.org/licenses/MIT to opensource.org/license/MIT); every form should keep resolving.
+	tests := []struct {
+		name   string
+		url    string
+		wantID string
+	}{
+		{name: "old plural path", url: "http://opensource.org/licenses/MIT", wantID: "MIT"},
+		{name: "new singular path", url: "https://opensource.org/license/MIT", wantID: "MIT"},
+		{name: "lowercase with trailing slash", url: "https://opensource.org/license/mit/", wantID: "MIT"},
+		{name: "plural path with trailing slash", url: "https://opensource.org/licenses/MIT/", wantID: "MIT"},
+		{name: "www prefix", url: "https://www.opensource.org/licenses/MIT", wantID: "MIT"},
+		{name: "uppercase host", url: "https://WWW.OpenSource.org/licenses/MIT", wantID: "MIT"},
+		{name: "old plural path BSD-3-Clause", url: "https://opensource.org/licenses/BSD-3-Clause", wantID: "BSD-3-Clause"},
+		{name: "new singular path BSD-3-Clause", url: "https://opensource.org/license/BSD-3-Clause", wantID: "BSD-3-Clause"},
+		{name: "lowercase BSD-3-Clause", url: "https://opensource.org/licenses/bsd-3-clause", wantID: "BSD-3-Clause"},
+		{name: "old plural path Apache-2.0", url: "http://opensource.org/licenses/Apache-2.0", wantID: "Apache-2.0"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			info, found := LicenseByURL(tt.url)
+			if !found {
+				t.Fatalf("LicenseByURL(%q) found = false, want true", tt.url)
+			}
+			if info.ID != tt.wantID {
+				t.Errorf("LicenseByURL(%q) ID = %v, want %v", tt.url, info.ID, tt.wantID)
+			}
+		})
+	}
+}
+
+func TestLicenseByURL_NonOpenSourceOrgStaysExact(t *testing.T) {
+	// the relaxed matching is scoped to opensource.org; other hosts may have case-sensitive paths
+	if _, found := LicenseByURL("https://www.apache.org/licenses/license-2.0"); found {
+		t.Errorf("LicenseByURL() found = true for case-altered non-opensource.org URL, want false")
+	}
+	if _, found := LicenseByURL("https://opensource.org/licenses/not-a-real-license"); found {
+		t.Errorf("LicenseByURL() found = true for unknown opensource.org URL, want false")
+	}
+}
+
+func TestNormalizeOpenSourceOrgURL(t *testing.T) {
+	tests := []struct {
+		url    string
+		want   string
+		wantOK bool
+	}{
+		{url: "opensource.org/licenses/MIT", want: "opensource.org/license/mit", wantOK: true},
+		{url: "opensource.org/license/mit/", want: "opensource.org/license/mit", wantOK: true},
+		{url: "www.opensource.org/licenses/EPL-2.0", want: "opensource.org/license/epl-2.0", wantOK: true},
+		{url: "lists.opensource.org/pipermail/license-discuss", wantOK: false},
+		{url: "www.apache.org/licenses/LICENSE-2.0", wantOK: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.url, func(t *testing.T) {
+			got, ok := normalizeOpenSourceOrgURL(tt.url)
+			if ok != tt.wantOK {
+				t.Fatalf("normalizeOpenSourceOrgURL(%q) ok = %v, want %v", tt.url, ok, tt.wantOK)
+			}
+			if got != tt.want {
+				t.Errorf("normalizeOpenSourceOrgURL(%q) = %q, want %q", tt.url, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestBuildOpenSourceOrgURLToLicense(t *testing.T) {
+	index := buildOpenSourceOrgURLToLicense(map[string]string{
+		"opensource.org/licenses/MIT": "MIT",
+		"opensource.org/license/mit/": "MIT",
+		"opensource.org/licenses/Foo": "Foo-1.0",
+		"opensource.org/license/foo":  "Foo-2.0",
+		"opensource.org/license/FOO/": "Foo-1.0",
+		"www.apache.org/licenses/Bar": "Bar",
+	})
+
+	if got := index["opensource.org/license/mit"]; got != "MIT" {
+		t.Errorf("index[mit] = %q, want MIT", got)
+	}
+	if got, exists := index["opensource.org/license/foo"]; exists {
+		t.Errorf("index[foo] = %q, want no entry for URL forms mapping to different licenses", got)
+	}
+	if len(index) != 1 {
+		t.Errorf("len(index) = %d, want 1 (non-opensource.org URLs excluded): %v", len(index), index)
+	}
+}
+
 func TestStripScheme(t *testing.T) {
 	tests := []struct {
 		name string

internal/spillbuf/buffer.go

@@ -0,0 +1,330 @@
+// Package spillbuf provides a sparse, offset-addressed byte buffer that keeps a bounded amount in memory
+// and spills the rest to a temp file.
+//
+// It exists for the shape where output arrives out of order, at offsets the input itself declares: a
+// decompressor placing extents, an archive rebuilding a file from chunks. A plain []byte cannot do that
+// without either pre-sizing to a length the input claims or growing to the furthest offset it names, and
+// both hand a hostile input an allocation knob.
+//
+// The buffer reports only what it actually stored. Size is the contiguous run written from offset zero,
+// and a read past it is io.EOF rather than the zeros an unwritten region would otherwise hand back. That
+// distinction is the whole point: sparse storage serves holes as zeros for free, so a reader that reported
+// a length covering them would let a write offset stand in for real output. Anything sizing an allocation
+// against this reader (debug/elf's saferio does exactly that) would then allocate bytes nothing produced.
+//
+// Allocation is bounded by the memory limit rather than by how much is written: filling 1MB and filling
+// 64MB cost about the same, because everything past the limit goes to the file. Only memory is bounded
+// here: how much ends up on disk is whatever the caller writes, so bounding that stays the caller's job.
+package spillbuf
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"math"
+	"os"
+	"slices"
+
+	"github.com/anchore/syft/internal/tmpdir"
+)
+
+// DefaultMemLimit is how much a buffer keeps in memory before it spills, when the caller does not say.
+// Small on purpose: the memory tier saves a temp file for the common small case, it is not a place to
+// hold output. A limit large enough to matter is a limit large enough to be an amplification path.
+const DefaultMemLimit int64 = 1 << 20 // 1MB
+
+// ErrNoTempDir is returned when a buffer needs to spill and has nowhere to spill to.
+var ErrNoTempDir = errors.New("no temp dir available to spill to")
+
+// Buffer is a sparse, offset-addressed buffer. The zero value is not usable; call New.
+//
+// Storage is two tiers with a fixed boundary: bytes below memLimit live in mem, bytes at or past it live
+// in file. Nothing ever moves between them, so an offset belongs to exactly one tier for the life of the
+// buffer and the only case needing care is a range that straddles the boundary.
+//
+// Not safe for concurrent use. Every consumer writes from a single goroutine, and guarding it would cost
+// each write an uncontended lock for no reader.
+type Buffer struct {
+	td       *tmpdir.TempDir
+	memLimit int64
+
+	// mem holds [0, memLimit). Grown geometrically to fit what has been written, never past the limit.
+	mem []byte
+
+	// file holds [memLimit, ...), created on the first write that reaches there, so a buffer that stays
+	// small never touches disk. remove deletes it on Close.
+	file   *os.File
+	remove func()
+
+	// written is the set of ranges stored, sorted by start and merged, so runs of adjacent writes collapse
+	// to one entry rather than growing per call. Everything the buffer reports comes from it.
+	written []extent
+
+	closed bool
+}
+
+// extent is a half-open byte range that has been written.
+//
+// Unexported on purpose. What a caller needs to know about the contents is answered by Size and FirstGap;
+// handing out the bookkeeping invites re-deriving those at the call site and getting them subtly wrong,
+// which is the bug this package exists to prevent.
+type extent struct {
+	start, end int64
+}
+
+// Option configures a Buffer.
+type Option func(*Buffer)
+
+// WithMemLimit sets how many bytes are held in memory before the buffer spills to disk. Zero sends every
+// write to the temp file. Negative is treated as zero.
+//
+// Peak allocation is a small multiple of this, since growing the tier holds the old copy alongside the
+// new one and the new one may be rounded up past what was asked for.
+func WithMemLimit(n int64) Option {
+	return func(b *Buffer) {
+		b.memLimit = max(n, 0)
+	}
+}
+
+// New returns a buffer that spills into td.
+//
+// td may be nil only when every write is known to stay inside the memory limit; a write past it then
+// fails with ErrNoTempDir rather than allocating. Nothing is created on disk until a write needs it.
+func New(td *tmpdir.TempDir, opts ...Option) *Buffer {
+	b := &Buffer{td: td, memLimit: DefaultMemLimit}
+	for _, opt := range opts {
+		opt(b)
+	}
+	return b
+}
+
+// split divides a range of n bytes starting at off across the two tiers, reporting how many bytes fall in
+// each. The file portion starts at off+inMem.
+func (b *Buffer) split(off, n int64) (inMem, inFile int64) {
+	if off >= b.memLimit {
+		return 0, n
+	}
+	inMem = min(n, b.memLimit-off)
+	return inMem, n - inMem
+}
+
+// fileOffset translates a buffer offset at or past the limit into an offset within the spill file.
+func (b *Buffer) fileOffset(off int64) int64 { return off - b.memLimit }
+
+// WriteAt stores p at off. Writes may land anywhere, in any order, and may overlap. A write that fails
+// leaves the buffer as it was.
+func (b *Buffer) WriteAt(p []byte, off int64) (int, error) {
+	if b.closed {
+		return 0, fmt.Errorf("spillbuf: write to a closed buffer: %w", os.ErrClosed)
+	}
+	if off < 0 {
+		return 0, fmt.Errorf("spillbuf: negative offset %d", off)
+	}
+	if len(p) == 0 {
+		return 0, nil
+	}
+	// subtraction form so off+len(p) cannot wrap into a small in-range end
+	if off > math.MaxInt64-int64(len(p)) {
+		return 0, fmt.Errorf("spillbuf: write of %d bytes at %d overflows", len(p), off)
+	}
+
+	inMem, inFile := b.split(off, int64(len(p)))
+	// the fallible half goes first: once the memory tier is stamped the old bytes are gone, so a file
+	// write that fails afterward would report failure over a buffer it had already changed
+	if inFile > 0 {
+		if err := b.writeFile(p[inMem:], b.fileOffset(off+inMem)); err != nil {
+			return 0, err
+		}
+	}
+	if inMem > 0 {
+		b.writeMem(p[:inMem], off)
+	}
+
+	b.record(extent{start: off, end: off + int64(len(p))})
+	return len(p), nil
+}
+
+func (b *Buffer) writeMem(p []byte, off int64) {
+	if need := off + int64(len(p)); int64(len(b.mem)) < need {
+		// geometric, capped at the limit. Sizing to exactly what each write needs looks tidier and is
+		// quadratic: a caller streaming a block in 32KB chunks reallocates and copies the whole tier every
+		// chunk, so filling 1MB costs ~16MB of allocation.
+		grown := min(b.memLimit, max(need, 2*int64(len(b.mem))))
+		// sized to exactly the geometric target rather than grown through append: append rounds the new
+		// capacity up past what was asked for, and the tier is already capped, so the slack is pure waste
+		mem := make([]byte, grown)
+		copy(mem, b.mem)
+		b.mem = mem
+	}
+	copy(b.mem[off:], p)
+}
+
+func (b *Buffer) writeFile(p []byte, off int64) error {
+	if b.file == nil {
+		if b.td == nil {
+			return ErrNoTempDir
+		}
+		f, remove, err := b.td.NewFile("syft-spill-*.bin") //nolint:gocritic // removal happens in Close
+		if err != nil {
+			return fmt.Errorf("spillbuf: unable to create spill file: %w", err)
+		}
+		b.file, b.remove = f, remove
+	}
+	if _, err := b.file.WriteAt(p, off); err != nil {
+		return fmt.Errorf("spillbuf: unable to write to spill file: %w", err)
+	}
+	return nil
+}
+
+// ReadAt returns bytes this buffer actually stored. A read starting at or past Size is io.EOF, and one
+// running past it is short, because everything beyond is a hole the buffer never held.
+func (b *Buffer) ReadAt(p []byte, off int64) (int, error) {
+	if b.closed {
+		return 0, fmt.Errorf("spillbuf: read from a closed buffer: %w", os.ErrClosed)
+	}
+	if off < 0 {
+		return 0, fmt.Errorf("spillbuf: negative offset %d", off)
+	}
+	if len(p) == 0 {
+		return 0, nil
+	}
+	size := b.Size()
+	if off >= size {
+		return 0, io.EOF
+	}
+
+	// bounded by Size, so every byte in [off, off+want) was written and both tiers really hold theirs
+	want := min(int64(len(p)), size-off)
+	inMem, inFile := b.split(off, want)
+
+	// guarded rather than relying on a zero-length copy: when off is past the limit the slice expression
+	// itself is out of range, since mem is only as long as what was written into it
+	if inMem > 0 {
+		copy(p[:inMem], b.mem[off:off+inMem])
+	}
+	if inFile > 0 {
+		if err := readFullAt(b.file, p[inMem:want], b.fileOffset(off+inMem)); err != nil {
+			return int(inMem), fmt.Errorf("spillbuf: unable to read spill file: %w", err)
+		}
+	}
+
+	if want < int64(len(p)) {
+		return int(want), io.EOF
+	}
+	return int(want), nil
+}
+
+// readFullAt fills p from r. A short read is an error rather than a short return: the caller has already
+// bounded the range by what was written, so the file failing to deliver means it is not what we left.
+func readFullAt(r io.ReaderAt, p []byte, off int64) error {
+	for read := 0; read < len(p); {
+		n, err := r.ReadAt(p[read:], off+int64(read))
+		read += n
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// Size reports the contiguous run written from offset zero, which is the length this buffer is willing to
+// stand behind. Deliberately not the furthest offset written: see the package doc for why the two are not
+// interchangeable.
+//
+// record keeps the set merged and sorted, so the run from zero is at most the first two entries and the
+// loop stops there: the cost this adds to every ReadAt is effectively constant, not a scan of the set.
+func (b *Buffer) Size() int64 {
+	var covered int64
+	for _, e := range b.written {
+		if e.start > covered {
+			break
+		}
+		covered = max(covered, e.end)
+	}
+	return covered
+}
+
+// FirstGap returns the offset of the earliest unwritten run of at least size bytes lying entirely within
+// [0, within), and whether there is one. Callers that place output at offsets of their own choosing use it
+// to fill what they left behind, without needing the buffer's bookkeeping.
+//
+// The arithmetic is in subtraction form throughout: within comes from caller input and the result is used
+// as a write offset, so a wrap here would be a write nobody bounded.
+func (b *Buffer) FirstGap(size, within int64) (int64, bool) {
+	if b.closed || size < 0 || within < 0 {
+		return 0, false
+	}
+
+	var at int64
+	for _, e := range b.written {
+		// once the cursor is at the bound there is nothing left to offer, and it only moves forward
+		if at >= within {
+			return 0, false
+		}
+		// the gap ahead of this extent ends at whichever comes first, the extent or the bound
+		end := min(e.start, within)
+		if end > at && end-at >= size {
+			return at, true
+		}
+		at = max(at, e.end)
+	}
+	if at <= within && within-at >= size {
+		return at, true
+	}
+	return 0, false
+}
+
+// record merges e into the written set, keeping it sorted by start with no overlapping or adjacent pairs.
+func (b *Buffer) record(e extent) {
+	if e.end <= e.start {
+		return
+	}
+
+	// inserted in place rather than appended and re-sorted: the set is already ordered, so a run of
+	// ascending writes (the common case) stays linear
+	i, _ := slices.BinarySearchFunc(b.written, e, func(x, y extent) int {
+		return cmpInt64(x.start, y.start)
+	})
+	b.written = slices.Insert(b.written, i, e)
+
+	merged := b.written[:1]
+	for _, cur := range b.written[1:] {
+		last := &merged[len(merged)-1]
+		if cur.start <= last.end {
+			last.end = max(last.end, cur.end)
+			continue
+		}
+		merged = append(merged, cur)
+	}
+	b.written = merged
+}
+
+func cmpInt64(x, y int64) int {
+	switch {
+	case x < y:
+		return -1
+	case x > y:
+		return 1
+	}
+	return 0
+}
+
+// Close releases the spill file, if one was ever created, and drops the memory tier. Safe on a nil
+// receiver and safe to call more than once. Reads and writes after it fail with os.ErrClosed.
+func (b *Buffer) Close() error {
+	if b == nil {
+		return nil
+	}
+	b.mem = nil
+	b.written = nil
+	b.closed = true
+	if b.file == nil {
+		return nil
+	}
+	err := b.file.Close()
+	if b.remove != nil {
+		b.remove()
+	}
+	b.file, b.remove = nil, nil
+	return err
+}