@@ -240,3 +240,6 @@ EXPORT_FUNCTIONS do_configure
# https://github.com/rust-lang/libc/issues/3223
# https://github.com/rust-lang/libc/pull/3175
INSANE_SKIP:append = " 32bit-time"
+
+# Generate ecosystem-specific Package URL for SPDX
+SPDX_PACKAGE_URLS =+ "pkg:cargo/${BPN}@${PV} "
@@ -68,4 +68,15 @@ cpan_do_install () {
done
}
+# Generate ecosystem-specific Package URL for SPDX
+def cpan_spdx_name(d):
+ bpn = d.getVar('BPN')
+ if bpn.startswith('perl-'):
+ return bpn[5:]
+ elif bpn.startswith('libperl-'):
+ return bpn[8:]
+ return bpn
+
+SPDX_PACKAGE_URLS =+ "pkg:cpan/${@cpan_spdx_name(d)}@${PV} "
+
EXPORT_FUNCTIONS do_configure do_compile do_install
@@ -32,3 +32,9 @@ do_compile[dirs] += "${B}/src/${GO_WORKDIR}"
# Make go install unpack the module zip files in the module cache directory
# before the license directory is polulated with license files.
addtask do_compile before do_populate_lic
+
+# Generate ecosystem-specific Package URL for SPDX
+SPDX_PACKAGE_URLS =+ "pkg:golang/${GO_IMPORT}@${PV} "
+
+# Generate ecosystem-specific Package URL for SPDX
+SPDX_PACKAGE_URLS =+ "pkg:golang/${GO_IMPORT}@${PV} "
@@ -354,4 +354,11 @@ FILES:${PN} += " \
${nonarch_libdir} \
"
+# Generate ecosystem-specific Package URL for SPDX
+def npm_spdx_name(d):
+ bpn = d.getVar('BPN')
+ return bpn[5:] if bpn.startswith('node-') else bpn
+
+SPDX_PACKAGE_URLS =+ "pkg:npm/${@npm_spdx_name(d)}@${PV} "
+
EXPORT_FUNCTIONS do_configure do_compile do_install
@@ -43,7 +43,8 @@ SECTION = "devel/python"
SRC_URI:prepend = "${PYPI_SRC_URI} "
S = "${UNPACKDIR}/${PYPI_PACKAGE}-${PV}"
-UPSTREAM_CHECK_PYPI_PACKAGE ?= "${PYPI_PACKAGE}"
+# Replace any '_' characters in the pypi URI with '-'s to follow the PyPi website naming conventions
+UPSTREAM_CHECK_PYPI_PACKAGE ?= "${@pypi_normalize(d)}"
# Use the simple repository API rather than the potentially unstable project URL
# More information on the pypi API specification is avaialble here:
@@ -54,3 +55,6 @@ UPSTREAM_CHECK_URI ?= "https://pypi.org/simple/${@pypi_normalize(d)}/"
UPSTREAM_CHECK_REGEX ?= "${UPSTREAM_CHECK_PYPI_PACKAGE}-(?P<pver>(\d+[\.\-_]*)+).(tar\.gz|tgz|zip|tar\.bz2)"
CVE_PRODUCT ?= "python:${PYPI_PACKAGE}"
+
+# Generate ecosystem-specific Package URL for SPDX
+SPDX_PACKAGE_URLS =+ "pkg:pypi/${@pypi_normalize(d)}@${PV} "
@@ -82,6 +82,13 @@ SPDX_MULTILIB_SSTATE_ARCHS[doc] = "The list of sstate architectures to consider
when collecting SPDX dependencies. This includes multilib architectures when \
multilib is enabled. Defaults to SSTATE_ARCHS."
+SPDX_FILE_EXCLUDE_PATTERNS ??= ""
+SPDX_FILE_EXCLUDE_PATTERNS[doc] = "Space-separated list of Python regular \
+ expressions to exclude files from SPDX output. Files whose paths match \
+ any pattern (via re.search) will be filtered out. Defaults to empty \
+ (no filtering). Example: \
+ SPDX_FILE_EXCLUDE_PATTERNS = '\\.patch$ \\.diff$ /test/ \\.pyc$ \\.o$'"
+
python () {
from oe.cve_check import extend_cve_status
extend_cve_status(d)
@@ -13,6 +13,8 @@ import oe.spdx30
import oe.spdx_common
import oe.sdk
import os
+import re
+import urllib.parse
from contextlib import contextmanager
from datetime import datetime, timezone
@@ -32,9 +34,7 @@ def set_timestamp_now(d, o, prop):
delattr(o, prop)
-def add_license_expression(
- d, objset, license_expression, license_data, search_objsets=[]
-):
+def add_license_expression(d, objset, license_expression, license_data):
simple_license_text = {}
license_text_map = {}
license_ref_idx = 0
@@ -46,15 +46,14 @@ def add_license_expression(
if name in simple_license_text:
return simple_license_text[name]
- for o in [objset] + search_objsets:
- lic = o.find_filter(
- oe.spdx30.simplelicensing_SimpleLicensingText,
- name=name,
- )
+ lic = objset.find_filter(
+ oe.spdx30.simplelicensing_SimpleLicensingText,
+ name=name,
+ )
- if lic is not None:
- simple_license_text[name] = lic
- return lic
+ if lic is not None:
+ simple_license_text[name] = lic
+ return lic
lic = objset.add(
oe.spdx30.simplelicensing_SimpleLicensingText(
@@ -148,42 +147,36 @@ def add_package_files(
ignore_dirs=[],
ignore_top_level_dirs=[],
):
- source_date_epoch = d.getVar("SOURCE_DATE_EPOCH")
- if source_date_epoch:
- source_date_epoch = int(source_date_epoch)
-
- spdx_files = set()
-
- file_counter = 1
- if not os.path.exists(topdir):
- bb.note(f"Skip {topdir}")
- return spdx_files
-
- check_compiled_sources = d.getVar("SPDX_INCLUDE_COMPILED_SOURCES") == "1"
- if check_compiled_sources:
- compiled_sources, types = oe.spdx_common.get_compiled_sources(d)
- bb.debug(1, f"Total compiled files: {len(compiled_sources)}")
-
- for subdir, dirs, files in os.walk(topdir, onerror=walk_error):
- dirs[:] = [d for d in dirs if d not in ignore_dirs]
- if subdir == str(topdir):
- dirs[:] = [d for d in dirs if d not in ignore_top_level_dirs]
-
- dirs.sort()
- files.sort()
- for file in files:
- filepath = Path(subdir) / file
+ if os.path.isdir(image_path):
+ a, _ = add_package_files(
+ d,
+ objset,
+ image_path,
+ lambda file_counter: objset.new_spdxid(
+ "imagefile", str(file_counter)
+ ),
+ lambda filepath: [],
+ license_data=None,
+ ignore_dirs=[],
+ ignore_top_level_dirs=[],
+ archive=None,
+ )
if filepath.is_symlink() or not filepath.is_file():
continue
filename = str(filepath.relative_to(topdir))
+
+ # Apply file exclusion filtering
+ if exclude_patterns:
+ if any(p.search(filename) for p in exclude_patterns):
+ excluded_files.add(filename)
+ continue
+
file_purposes = get_purposes(filepath)
# Check if file is compiled
if check_compiled_sources:
- if not oe.spdx_common.is_compiled_source(
- filename, compiled_sources, types
- ):
+ if not oe.spdx_common.is_compiled_source(filename, compiled_sources, types):
continue
spdx_file = objset.new_file(
@@ -218,12 +211,15 @@ def add_package_files(
bb.debug(1, "Added %d files to %s" % (len(spdx_files), objset.doc._id))
- return spdx_files
+ return spdx_files, excluded_files
def get_package_sources_from_debug(
- d, package, package_files, sources, source_hash_cache
+ d, package, package_files, sources, source_hash_cache, excluded_files=None
):
+ if excluded_files is None:
+ excluded_files = set()
+
def file_path_match(file_path, pkg_file):
if file_path.lstrip("/") == pkg_file.name.lstrip("/"):
return True
@@ -256,6 +252,12 @@ def get_package_sources_from_debug(
continue
if not any(file_path_match(file_path, pkg_file) for pkg_file in package_files):
+ if file_path.lstrip("/") in excluded_files:
+ bb.debug(
+ 1,
+ f"Skipping debug source lookup for excluded file {file_path} in {package}",
+ )
+ continue
bb.fatal(
"No package file found for %s in %s; SPDX found: %s"
% (str(file_path), package, " ".join(p.name for p in package_files))
@@ -298,14 +300,17 @@ def get_package_sources_from_debug(
return dep_source_files
-def collect_dep_objsets(d, direct_deps, subdir, fn_prefix, obj_type, **attr_filter):
+def collect_dep_objsets(d, build):
+ deps = oe.spdx_common.get_spdx_deps(d)
+
dep_objsets = []
- dep_objs = set()
+ dep_builds = set()
- for dep in direct_deps:
+ dep_build_spdxids = set()
+ for dep in deps:
bb.debug(1, "Fetching SPDX for dependency %s" % (dep.pn))
- dep_obj, dep_objset = oe.sbom30.find_root_obj_in_jsonld(
- d, subdir, fn_prefix + dep.pn, obj_type, **attr_filter
+ dep_build, dep_objset = oe.sbom30.find_root_obj_in_jsonld(
+ d, "recipes", "recipe-" + dep.pn, oe.spdx30.build_Build
)
# If the dependency is part of the taskhash, return it to be linked
# against. Otherwise, it cannot be linked against because this recipe
@@ -313,10 +318,10 @@ def collect_dep_objsets(d, direct_deps, subdir, fn_prefix, obj_type, **attr_filt
if dep.in_taskhash:
dep_objsets.append(dep_objset)
- # The object _can_ be linked against (by alias)
- dep_objs.add(dep_obj)
+ # The build _can_ be linked against (by alias)
+ dep_builds.add(dep_build)
- return dep_objsets, dep_objs
+ return dep_objsets, dep_builds
def index_sources_by_hash(sources, dest):
@@ -359,6 +364,120 @@ def collect_dep_sources(dep_objsets, dest):
index_sources_by_hash(e.to, dest)
+def _generate_git_purl(d, download_location, srcrev):
+ """Generate a Package URL for a Git source from its download location.
+
+ Parses the Git URL to identify the hosting service and generates the
+ appropriate PURL type. Supports github.com by default and custom
+ mappings via SPDX_GIT_PURL_MAPPINGS.
+
+ Returns the PURL string or None if no mapping matches.
+ """
+ if not download_location or not download_location.startswith('git+'):
+ return None
+
+ git_url = download_location[4:] # Remove 'git+' prefix
+
+ # Default handler: github.com
+ git_purl_handlers = {
+ 'github.com': 'pkg:github',
+ }
+
+ # Custom PURL mappings from SPDX_GIT_PURL_MAPPINGS
+ # Format: "domain1:purl_type1 domain2:purl_type2"
+ custom_mappings = d.getVar('SPDX_GIT_PURL_MAPPINGS')
+ if custom_mappings:
+ for mapping in custom_mappings.split():
+ parts = mapping.split(':', 1)
+ if len(parts) == 2:
+ git_purl_handlers[parts[0]] = parts[1]
+ bb.debug(2, f"Added custom Git PURL mapping: {parts[0]} -> {parts[1]}")
+ else:
+ bb.warn(f"Invalid SPDX_GIT_PURL_MAPPINGS entry: {mapping} (expected format: domain:purl_type)")
+
+ try:
+ parsed = urllib.parse.urlparse(git_url)
+ except Exception:
+ return None
+
+ hostname = parsed.hostname
+ if not hostname:
+ return None
+
+ for domain, purl_type in git_purl_handlers.items():
+ if hostname == domain:
+ path = parsed.path.strip('/')
+ path_parts = path.split('/')
+ if len(path_parts) >= 2:
+ owner = path_parts[0]
+ repo = path_parts[1].replace('.git', '')
+ return f"{purl_type}/{owner}/{repo}@{srcrev}"
+ break
+
+ return None
+
+
+def _enrich_source_package(d, dl, fd, file_name, primary_purpose):
+ """Enrich a source download package with version, PURL, and external refs.
+
+ Extracts version from SRCREV for Git sources, generates PURLs for
+ known hosting services, and adds external references for VCS,
+ distribution URLs, and homepage.
+ """
+ version = None
+ purl = None
+
+ if fd.type == "git":
+ # Use full SHA-1 from fd.revision
+ srcrev = getattr(fd, 'revision', None)
+ if srcrev and srcrev not in {'${AUTOREV}', 'AUTOINC', 'INVALID'}:
+ version = srcrev
+
+ # Generate PURL for Git hosting services
+ download_location = getattr(dl, 'software_downloadLocation', None)
+ if version and download_location:
+ purl = _generate_git_purl(d, download_location, version)
+ else:
+ # Use ecosystem PURL from SPDX_PACKAGE_URLS if available
+ package_urls = (d.getVar('SPDX_PACKAGE_URLS') or '').split()
+ for url in package_urls:
+ if not url.startswith('pkg:yocto'):
+ purl = url
+ break
+
+ if version:
+ dl.software_packageVersion = version
+
+ if purl:
+ dl.software_packageUrl = purl
+
+ # Add external references
+ download_location = getattr(dl, 'software_downloadLocation', None)
+ if download_location and isinstance(download_location, str):
+ dl.externalRef = dl.externalRef or []
+
+ if download_location.startswith('git+'):
+ # VCS reference for Git repositories
+ git_url = download_location[4:]
+ if '@' in git_url:
+ git_url = git_url.split('@')[0]
+
+ dl.externalRef.append(
+ oe.spdx30.ExternalRef(
+ externalRefType=oe.spdx30.ExternalRefType.vcs,
+ locator=[git_url],
+ )
+ )
+ elif download_location.startswith(('http://', 'https://', 'ftp://')):
+ # Distribution reference for tarball/archive downloads
+ dl.externalRef.append(
+ oe.spdx30.ExternalRef(
+ externalRefType=oe.spdx30.ExternalRefType.altDownloadLocation,
+ locator=[download_location],
+ )
+ )
+
+
def add_download_files(d, objset):
inputs = set()
@@ -422,10 +541,14 @@ def add_download_files(d, objset):
)
)
+ _enrich_source_package(d, dl, fd, file_name, primary_purpose)
+
if fd.method.supports_checksum(fd):
# TODO Need something better than hard coding this
for checksum_id in ["sha256", "sha1"]:
- expected_checksum = getattr(fd, "%s_expected" % checksum_id, None)
+ expected_checksum = getattr(
+ fd, "%s_expected" % checksum_id, None
+ )
if expected_checksum is None:
continue
@@ -462,220 +585,6 @@ def set_purposes(d, element, *var_names, force_purposes=[]):
]
-def set_purls(spdx_package, purls):
- if purls:
- spdx_package.software_packageUrl = purls[0]
-
- for p in sorted(set(purls)):
- spdx_package.externalIdentifier.append(
- oe.spdx30.ExternalIdentifier(
- externalIdentifierType=oe.spdx30.ExternalIdentifierType.packageUrl,
- identifier=p,
- )
- )
-
-
-def get_is_native(d):
- return bb.data.inherits_class("native", d) or bb.data.inherits_class("cross", d)
-
-
-def create_recipe_spdx(d):
- deploydir = Path(d.getVar("SPDXRECIPEDEPLOY"))
- deploy_dir_spdx = Path(d.getVar("DEPLOY_DIR_SPDX"))
- pn = d.getVar("PN")
-
- license_data = oe.spdx_common.load_spdx_license_data(d)
-
- include_vex = d.getVar("SPDX_INCLUDE_VEX")
- if not include_vex in ("none", "current", "all"):
- bb.fatal("SPDX_INCLUDE_VEX must be one of 'none', 'current', 'all'")
-
- recipe_objset = oe.sbom30.ObjectSet.new_objset(d, "static-" + pn)
-
- recipe = recipe_objset.add_root(
- oe.spdx30.software_Package(
- _id=recipe_objset.new_spdxid("recipe", pn),
- creationInfo=recipe_objset.doc.creationInfo,
- name=d.getVar("PN"),
- software_packageVersion=d.getVar("PV"),
- software_primaryPurpose=oe.spdx30.software_SoftwarePurpose.specification,
- software_sourceInfo=json.dumps(
- {
- "FILENAME": os.path.basename(d.getVar("FILE")),
- "FILE_LAYERNAME": d.getVar("FILE_LAYERNAME"),
- },
- separators=(",", ":"),
- ),
- )
- )
-
- if get_is_native(d):
- ext = oe.sbom30.OERecipeExtension()
- ext.is_native = True
- recipe.extension.append(ext)
-
- set_purls(recipe, (d.getVar("SPDX_PACKAGE_URLS") or "").split())
-
- # TODO: This doesn't work before do_unpack because the license text has to
- # be available for recipes with NO_GENERIC_LICENSE
- # recipe_spdx_license = add_license_expression(
- # d,
- # recipe_objset,
- # d.getVar("LICENSE"),
- # license_data,
- # )
- # recipe_objset.new_relationship(
- # [recipe],
- # oe.spdx30.RelationshipType.hasDeclaredLicense,
- # [oe.sbom30.get_element_link_id(recipe_spdx_license)],
- # )
-
- if val := d.getVar("HOMEPAGE"):
- recipe.software_homePage = val
-
- if val := d.getVar("SUMMARY"):
- recipe.summary = val
-
- if val := d.getVar("DESCRIPTION"):
- recipe.description = val
-
- for cpe_id in oe.cve_check.get_cpe_ids(
- d.getVar("CVE_PRODUCT"), d.getVar("CVE_VERSION")
- ):
- recipe.externalIdentifier.append(
- oe.spdx30.ExternalIdentifier(
- externalIdentifierType=oe.spdx30.ExternalIdentifierType.cpe23,
- identifier=cpe_id,
- )
- )
-
- direct_deps = oe.spdx_common.collect_direct_deps(d, "do_create_recipe_spdx")
-
- dep_objsets, dep_recipes = collect_dep_objsets(
- d, direct_deps, "static", "static-", oe.spdx30.software_Package
- )
-
- if dep_recipes:
- recipe_objset.new_scoped_relationship(
- [recipe],
- oe.spdx30.RelationshipType.dependsOn,
- oe.spdx30.LifecycleScopeType.build,
- sorted(oe.sbom30.get_element_link_id(dep) for dep in dep_recipes),
- )
-
- # Add CVEs
- cve_by_status = {}
- if include_vex != "none":
- patched_cves = oe.cve_check.get_patched_cves(d)
- for cve, patched_cve in patched_cves.items():
- mapping = patched_cve["abbrev-status"]
- detail = patched_cve["status"]
- description = patched_cve.get("justification", None)
- resources = patched_cve.get("resource", [])
-
- # If this CVE is fixed upstream, skip it unless all CVEs are
- # specified.
- if include_vex != "all" and detail in (
- "fixed-version",
- "cpe-stable-backport",
- ):
- bb.debug(1, "Skipping %s since it is already fixed upstream" % cve)
- continue
-
- spdx_cve = recipe_objset.new_cve_vuln(cve)
-
- cve_by_status.setdefault(mapping, {})[cve] = (
- spdx_cve,
- detail,
- description,
- resources,
- )
-
- all_cves = set()
- for status, cves in cve_by_status.items():
- for cve, items in cves.items():
- spdx_cve, detail, description, resources = items
- spdx_cve_id = oe.sbom30.get_element_link_id(spdx_cve)
-
- all_cves.add(spdx_cve)
-
- if status == "Patched":
- spdx_vex = recipe_objset.new_vex_patched_relationship(
- [spdx_cve_id], [recipe]
- )
- patches = []
- for idx, filepath in enumerate(resources):
- patches.append(
- recipe_objset.new_file(
- recipe_objset.new_spdxid(
- "patch", str(idx), os.path.basename(filepath)
- ),
- os.path.basename(filepath),
- filepath,
- purposes=[oe.spdx30.software_SoftwarePurpose.patch],
- hashfile=os.path.isfile(filepath),
- )
- )
-
- if patches:
- recipe_objset.new_scoped_relationship(
- spdx_vex,
- oe.spdx30.RelationshipType.patchedBy,
- oe.spdx30.LifecycleScopeType.build,
- patches,
- )
-
- elif status == "Unpatched":
- recipe_objset.new_vex_unpatched_relationship([spdx_cve_id], [recipe])
- elif status == "Ignored":
- spdx_vex = recipe_objset.new_vex_ignored_relationship(
- [spdx_cve_id],
- [recipe],
- impact_statement=description,
- )
-
- vex_just_type = d.getVarFlag("CVE_CHECK_VEX_JUSTIFICATION", detail)
- if vex_just_type:
- if (
- vex_just_type
- not in oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS
- ):
- bb.fatal(
- f"Unknown vex justification '{vex_just_type}', detail '{detail}', for ignored {cve}"
- )
-
- for v in spdx_vex:
- v.security_justificationType = (
- oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS[
- vex_just_type
- ]
- )
-
- elif status == "Unknown":
- bb.note(f"Skipping {cve} with status 'Unknown'")
- else:
- bb.fatal(f"Unknown {cve} status '{status}'")
-
- if all_cves:
- recipe_objset.new_relationship(
- [recipe],
- oe.spdx30.RelationshipType.hasAssociatedVulnerability,
- sorted(list(all_cves)),
- )
-
- oe.sbom30.write_recipe_jsonld_doc(d, recipe_objset, "static", deploydir)
-
-
-def load_recipe_spdx(d):
-
- return oe.sbom30.find_root_obj_in_jsonld(
- d,
- "static",
- "static-" + d.getVar("PN"),
- oe.spdx30.software_Package,
- )
-
-
def create_spdx(d):
def set_var_field(var, obj, name, package=None):
val = None
@@ -690,17 +599,19 @@ def create_spdx(d):
license_data = oe.spdx_common.load_spdx_license_data(d)
- pn = d.getVar("PN")
deploydir = Path(d.getVar("SPDXDEPLOY"))
deploy_dir_spdx = Path(d.getVar("DEPLOY_DIR_SPDX"))
spdx_workdir = Path(d.getVar("SPDXWORK"))
include_sources = d.getVar("SPDX_INCLUDE_SOURCES") == "1"
pkg_arch = d.getVar("SSTATE_PKGARCH")
- is_native = get_is_native(d)
-
- recipe, recipe_objset = load_recipe_spdx(d)
+ is_native = bb.data.inherits_class("native", d) or bb.data.inherits_class(
+ "cross", d
+ )
+ include_vex = d.getVar("SPDX_INCLUDE_VEX")
+ if not include_vex in ("none", "current", "all"):
+ bb.fatal("SPDX_INCLUDE_VEX must be one of 'none', 'current', 'all'")
- build_objset = oe.sbom30.ObjectSet.new_objset(d, "build-" + pn)
+ build_objset = oe.sbom30.ObjectSet.new_objset(d, "recipe-" + d.getVar("PN"))
build = build_objset.new_task_build("recipe", "recipe")
build_objset.set_element_alias(build)
@@ -718,13 +629,47 @@ def create_spdx(d):
build_inputs = set()
+ # Add CVEs
+ cve_by_status = {}
+ if include_vex != "none":
+ patched_cves = oe.cve_check.get_patched_cves(d)
+ for cve, patched_cve in patched_cves.items():
+ decoded_status = {
+ "mapping": patched_cve["abbrev-status"],
+ "detail": patched_cve["status"],
+ "description": patched_cve.get("justification", None)
+ }
+
+ # If this CVE is fixed upstream, skip it unless all CVEs are
+ # specified.
+ if (
+ include_vex != "all"
+ and "detail" in decoded_status
+ and decoded_status["detail"]
+ in (
+ "fixed-version",
+ "cpe-stable-backport",
+ )
+ ):
+ bb.debug(1, "Skipping %s since it is already fixed upstream" % cve)
+ continue
+
+ spdx_cve = build_objset.new_cve_vuln(cve)
+ build_objset.set_element_alias(spdx_cve)
+
+ cve_by_status.setdefault(decoded_status["mapping"], {})[cve] = (
+ spdx_cve,
+ decoded_status["detail"],
+ decoded_status["description"],
+ )
+
cpe_ids = oe.cve_check.get_cpe_ids(d.getVar("CVE_PRODUCT"), d.getVar("CVE_VERSION"))
source_files = add_download_files(d, build_objset)
build_inputs |= source_files
recipe_spdx_license = add_license_expression(
- d, build_objset, d.getVar("LICENSE"), license_data, [recipe_objset]
+ d, build_objset, d.getVar("LICENSE"), license_data
)
build_objset.new_relationship(
source_files,
@@ -737,7 +682,7 @@ def create_spdx(d):
bb.debug(1, "Adding source files to SPDX")
oe.spdx_common.get_patched_src(d)
- files = add_package_files(
+ files, _ = add_package_files(
d,
build_objset,
spdx_workdir,
@@ -753,12 +698,7 @@ def create_spdx(d):
build_inputs |= files
index_sources_by_hash(files, dep_sources)
- direct_deps = oe.spdx_common.collect_direct_deps(d, "do_create_spdx")
-
- dep_objsets, dep_builds = collect_dep_objsets(
- d, direct_deps, "builds", "build-", oe.spdx30.build_Build
- )
-
+ dep_objsets, dep_builds = collect_dep_objsets(d, build)
if dep_builds:
build_objset.new_scoped_relationship(
[build],
@@ -828,7 +768,16 @@ def create_spdx(d):
or ""
).split()
- set_purls(spdx_package, purls)
+ if purls:
+ spdx_package.software_packageUrl = purls[0]
+
+ for p in sorted(set(purls)):
+ spdx_package.externalIdentifier.append(
+ oe.spdx30.ExternalIdentifier(
+ externalIdentifierType=oe.spdx30.ExternalIdentifierType.packageUrl,
+ identifier=p,
+ )
+ )
pkg_objset.new_scoped_relationship(
[oe.sbom30.get_element_link_id(build)],
@@ -837,13 +786,6 @@ def create_spdx(d):
[spdx_package],
)
- pkg_objset.new_scoped_relationship(
- [oe.sbom30.get_element_link_id(recipe)],
- oe.spdx30.RelationshipType.generates,
- oe.spdx30.LifecycleScopeType.build,
- [spdx_package],
- )
-
for cpe_id in cpe_ids:
spdx_package.externalIdentifier.append(
oe.spdx30.ExternalIdentifier(
@@ -877,11 +819,7 @@ def create_spdx(d):
package_license = d.getVar("LICENSE:%s" % package)
if package_license and package_license != d.getVar("LICENSE"):
package_spdx_license = add_license_expression(
- d,
- build_objset,
- package_license,
- license_data,
- [recipe_objset],
+ d, build_objset, package_license, license_data
)
else:
package_spdx_license = recipe_spdx_license
@@ -894,9 +832,7 @@ def create_spdx(d):
# Add concluded license relationship if manually set
# Only add when license analysis has been explicitly performed
- concluded_license_str = d.getVar(
- "SPDX_CONCLUDED_LICENSE:%s" % package
- ) or d.getVar("SPDX_CONCLUDED_LICENSE")
+ concluded_license_str = d.getVar("SPDX_CONCLUDED_LICENSE:%s" % package) or d.getVar("SPDX_CONCLUDED_LICENSE")
if concluded_license_str:
concluded_spdx_license = add_license_expression(
d, build_objset, concluded_license_str, license_data
@@ -908,8 +844,61 @@ def create_spdx(d):
[oe.sbom30.get_element_link_id(concluded_spdx_license)],
)
+ # NOTE: CVE Elements live in the recipe collection
+ all_cves = set()
+ for status, cves in cve_by_status.items():
+ for cve, items in cves.items():
+ spdx_cve, detail, description = items
+ spdx_cve_id = oe.sbom30.get_element_link_id(spdx_cve)
+
+ all_cves.add(spdx_cve_id)
+
+ if status == "Patched":
+ pkg_objset.new_vex_patched_relationship(
+ [spdx_cve_id], [spdx_package]
+ )
+ elif status == "Unpatched":
+ pkg_objset.new_vex_unpatched_relationship(
+ [spdx_cve_id], [spdx_package]
+ )
+ elif status == "Ignored":
+ spdx_vex = pkg_objset.new_vex_ignored_relationship(
+ [spdx_cve_id],
+ [spdx_package],
+ impact_statement=description,
+ )
+
+ vex_just_type = d.getVarFlag(
+ "CVE_CHECK_VEX_JUSTIFICATION", detail
+ )
+ if vex_just_type:
+ if (
+ vex_just_type
+ not in oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS
+ ):
+ bb.fatal(
+ f"Unknown vex justification '{vex_just_type}', detail '{detail}', for ignored {cve}"
+ )
+
+ for v in spdx_vex:
+ v.security_justificationType = oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS[
+ vex_just_type
+ ]
+
+ elif status == "Unknown":
+ bb.note(f"Skipping {cve} with status 'Unknown'")
+ else:
+ bb.fatal(f"Unknown {cve} status '{status}'")
+
+ if all_cves:
+ pkg_objset.new_relationship(
+ [spdx_package],
+ oe.spdx30.RelationshipType.hasAssociatedVulnerability,
+ sorted(list(all_cves)),
+ )
+
bb.debug(1, "Adding package files to SPDX for package %s" % pkg_name)
- package_files = add_package_files(
+ package_files, excluded_files = add_package_files(
d,
pkg_objset,
pkgdest / package,
@@ -932,7 +921,8 @@ def create_spdx(d):
if include_sources:
debug_sources = get_package_sources_from_debug(
- d, package, package_files, dep_sources, source_hash_cache
+ d, package, package_files, dep_sources, source_hash_cache,
+ excluded_files=excluded_files,
)
debug_source_ids |= set(
oe.sbom30.get_element_link_id(d) for d in debug_sources
@@ -944,7 +934,7 @@ def create_spdx(d):
if include_sources:
bb.debug(1, "Adding sysroot files to SPDX")
- sysroot_files = add_package_files(
+ sysroot_files, _ = add_package_files(
d,
build_objset,
d.expand("${COMPONENTS_DIR}/${PACKAGE_ARCH}/${PN}"),
@@ -985,27 +975,27 @@ def create_spdx(d):
status = "enabled" if feature in enabled else "disabled"
build.build_parameter.append(
oe.spdx30.DictionaryEntry(
- key=f"PACKAGECONFIG:{feature}", value=status
+ key=f"PACKAGECONFIG:{feature}",
+ value=status
)
)
- bb.note(
- f"Added PACKAGECONFIG entries: {len(enabled)} enabled, {len(disabled)} disabled"
- )
+ bb.note(f"Added PACKAGECONFIG entries: {len(enabled)} enabled, {len(disabled)} disabled")
- oe.sbom30.write_recipe_jsonld_doc(d, build_objset, "builds", deploydir)
+ oe.sbom30.write_recipe_jsonld_doc(d, build_objset, "recipes", deploydir)
def create_package_spdx(d):
deploy_dir_spdx = Path(d.getVar("DEPLOY_DIR_SPDX"))
deploydir = Path(d.getVar("SPDXRUNTIMEDEPLOY"))
+ is_native = bb.data.inherits_class("native", d) or bb.data.inherits_class(
+ "cross", d
+ )
- direct_deps = oe.spdx_common.collect_direct_deps(d, "do_create_spdx")
-
- providers = oe.spdx_common.collect_package_providers(d, direct_deps)
+ providers = oe.spdx_common.collect_package_providers(d)
pkg_arch = d.getVar("SSTATE_PKGARCH")
- if get_is_native(d):
+ if is_native:
return
bb.build.exec_func("read_subpackage_metadata", d)
@@ -1179,15 +1169,15 @@ def write_bitbake_spdx(d):
def collect_build_package_inputs(d, objset, build, packages, files_by_hash=None):
import oe.sbom30
- direct_deps = oe.spdx_common.collect_direct_deps(d, "do_create_spdx")
-
+ direct_deps = oe.spdx_common.collect_direct_deps(d, "do_create_package_spdx")
providers = oe.spdx_common.collect_package_providers(d, direct_deps)
build_deps = set()
+ missing_providers = set()
for name in sorted(packages.keys()):
if name not in providers:
- bb.note(f"Unable to find SPDX provider for '{name}'")
+ missing_providers.add(name)
continue
pkg_name, pkg_hashfn = providers[name]
@@ -1206,6 +1196,11 @@ def collect_build_package_inputs(d, objset, build, packages, files_by_hash=None)
for h, f in pkg_objset.by_sha256_hash.items():
files_by_hash.setdefault(h, set()).update(f)
+ if missing_providers:
+ bb.fatal(
+ f"Unable to find SPDX provider(s) for: {', '.join(sorted(missing_providers))}"
+ )
+
if build_deps:
objset.new_scoped_relationship(
[build],
@@ -1326,18 +1321,18 @@ def create_image_spdx(d):
image_filename = image["filename"]
image_path = image_deploy_dir / image_filename
if os.path.isdir(image_path):
- a = add_package_files(
- d,
- objset,
- image_path,
- lambda file_counter: objset.new_spdxid(
- "imagefile", str(file_counter)
- ),
- lambda filepath: [],
- license_data=None,
- ignore_dirs=[],
- ignore_top_level_dirs=[],
- archive=None,
+ a, _ = add_package_files(
+ d,
+ objset,
+ image_path,
+ lambda file_counter: objset.new_spdxid(
+ "imagefile", str(file_counter)
+ ),
+ lambda filepath: [],
+ license_data=None,
+ ignore_dirs=[],
+ ignore_top_level_dirs=[],
+ archive=None,
)
artifacts.extend(a)
else:
@@ -1364,6 +1359,7 @@ def create_image_spdx(d):
set_timestamp_now(d, a, "builtTime")
+
if artifacts:
objset.new_scoped_relationship(
[image_build],
@@ -1423,6 +1419,16 @@ def create_image_sbom_spdx(d):
objset, sbom = oe.sbom30.create_sbom(d, image_name, root_elements)
+ # Set supplier on root elements if SPDX_IMAGE_SUPPLIER is defined
+ supplier = objset.new_agent("SPDX_IMAGE_SUPPLIER", add=False)
+ if supplier is not None:
+ supplier_id = supplier if isinstance(supplier, str) else supplier._id
+ if not isinstance(supplier, str):
+ objset.add(supplier)
+ for elem in sbom.rootElement:
+ if hasattr(elem, "suppliedBy"):
+ elem.suppliedBy = supplier_id
+
oe.sbom30.write_jsonld_doc(d, objset, spdx_path)
def make_image_link(target_path, suffix):
@@ -1534,16 +1540,16 @@ def create_sdk_sbom(d, sdk_deploydir, spdx_work_dir, toolchain_outputname):
d, toolchain_outputname, sorted(list(files)), [rootfs_objset]
)
+ # Set supplier on root elements if SPDX_SDK_SUPPLIER is defined
+ supplier = objset.new_agent("SPDX_SDK_SUPPLIER", add=False)
+ if supplier is not None:
+ supplier_id = supplier if isinstance(supplier, str) else supplier._id
+ if not isinstance(supplier, str):
+ objset.add(supplier)
+ for elem in sbom.rootElement:
+ if hasattr(elem, "suppliedBy"):
+ elem.suppliedBy = supplier_id
+
oe.sbom30.write_jsonld_doc(
d, objset, sdk_deploydir / (toolchain_outputname + ".spdx.json")
)
-
-
-def create_recipe_sbom(d, deploydir):
- sbom_name = d.getVar("SPDX_RECIPE_SBOM_NAME")
-
- recipe, recipe_objset = load_recipe_spdx(d)
-
- objset, sbom = oe.sbom30.create_sbom(d, sbom_name, [recipe], [recipe_objset])
-
- oe.sbom30.write_jsonld_doc(d, objset, deploydir / (sbom_name + ".spdx.json"))
Add SPDX_FILE_EXCLUDE_PATTERNS variable that allows filtering files from SPDX output by regex matching. The variable accepts a space-separated list of Python regular expressions; files whose paths match any pattern (via re.search) are excluded. When empty (the default), no filtering is applied and all files are included, preserving existing behavior. This enables users to reduce SBOM size by excluding files that are not relevant for compliance (e.g., test files, object files, patches). Excluded files are tracked in a set returned from add_package_files() and passed to get_package_sources_from_debug(), which uses the set for precise cross-checking rather than re-evaluating patterns. Signed-off-by: Stefano Tondo <stefano.tondo.ext@siemens.com> --- meta/classes-recipe/cargo_common.bbclass | 3 + meta/classes-recipe/cpan.bbclass | 11 + meta/classes-recipe/go-mod.bbclass | 6 + meta/classes-recipe/npm.bbclass | 7 + meta/classes-recipe/pypi.bbclass | 6 +- meta/classes/spdx-common.bbclass | 7 + meta/lib/oe/spdx30_tasks.py | 666 ++++++++++++----------- 7 files changed, 375 insertions(+), 331 deletions(-)