[PATCH v2 03/18] spdx30: Add ecosystem-specific PURL generation

[Stefano Tondo <stondo@gmail.com>]

From: Stefano Tondo <stefano.tondo.ext@siemens.com>

Add a function that identifies ecosystem-specific PURLs (cargo, golang,
pypi, npm, cpan, nuget, maven) for dependency packages, working alongside
oe.purl.get_base_purl() which provides pkg:yocto PURLs.

Key design decision: Does NOT return pkg:generic fallback. This ensures:
- No overlap with the base pkg:yocto generation
- Packages get BOTH purls: pkg:yocto/layer/pkg@ver AND pkg:cargo/pkg@ver
- Maximum traceability for compliance tools

Detects ecosystems via:
- Unambiguous file extensions (.crate for Rust)
- Recipe inheritance (pypi, npm, cpan, nuget, maven classes)
- BitBake variables (GO_IMPORT, PYPI_PACKAGE, MAVEN_GROUP_ID)

Signed-off-by: Stefano Tondo <stefano.tondo.ext@siemens.com>
---
 meta/lib/oe/spdx30_tasks.py | 113 ++++++++++++++++++++++++++++++++++++
 1 file changed, 113 insertions(+)

diff --git a/meta/lib/oe/spdx30_tasks.py b/meta/lib/oe/spdx30_tasks.py
index 789b39bd93..0ee39ffcd5 100644
--- a/meta/lib/oe/spdx30_tasks.py
+++ b/meta/lib/oe/spdx30_tasks.py
@@ -13,12 +13,125 @@ import oe.spdx30
 import oe.spdx_common
 import oe.sdk
 import os
+import re
 
 from contextlib import contextmanager
 from datetime import datetime, timezone
 from pathlib import Path
 
 
+
+def extract_dependency_metadata(d, file_name):
+    """Extract ecosystem-specific PURL for dependency packages.
+
+    Uses recipe metadata to identify ecosystem PURLs (cargo, golang, pypi,
+    npm, cpan, nuget, maven). Returns (version, purl) or (None, None).
+    Does NOT return pkg:generic; base pkg:yocto is handled by get_base_purl().
+    """
+
+    pv = d.getVar("PV")
+    version = pv if pv else None
+    purl = None
+
+    # Rust crate (.crate extension is unambiguous)
+    if file_name.endswith('.crate'):
+        crate_match = re.match(r'^(.+?)-(\d+\.\d+\.\d+(?:\.\d+)?(?:[-+][\w.]+)?)\.crate$', file_name)
+        if crate_match:
+            name = crate_match.group(1)
+            version = crate_match.group(2)
+            purl = f"pkg:cargo/{name}@{version}"
+            return (version, purl)
+
+    # Go module via GO_IMPORT variable
+    go_import = d.getVar("GO_IMPORT")
+    if go_import and version:
+        purl = f"pkg:golang/{go_import}@{version}"
+        return (version, purl)
+
+    # Go module from filename with explicit hosting domain
+    go_match = re.match(
+        r'^((?:github|gitlab|gopkg|golang|go\.googlesource)\.com\.[\w.]+(?:\.[\w-]+)*?)-(v?\d+\.\d+\.\d+(?:[-+][\w.]+)?)\.',
+        file_name
+    )
+    if go_match:
+        module_path = go_match.group(1).replace('.', '/', 1)
+        parts = module_path.split('/', 1)
+        if len(parts) == 2:
+            domain = parts[0]
+            path = parts[1].replace('.', '/')
+            module_path = f"{domain}/{path}"
+
+        version = go_match.group(2)
+        purl = f"pkg:golang/{module_path}@{version}"
+        return (version, purl)
+
+    # PyPI package
+    if bb.data.inherits_class("pypi", d) and version:
+        pypi_package = d.getVar("PYPI_PACKAGE")
+        if pypi_package:
+            # Normalize per PEP 503
+            name = re.sub(r"[-_.]+", "-", pypi_package).lower()
+            purl = f"pkg:pypi/{name}@{version}"
+            return (version, purl)
+
+    # NPM package
+    if bb.data.inherits_class("npm", d) and version:
+        bpn = d.getVar("BPN")
+        if bpn:
+            name = bpn[4:] if bpn.startswith('npm-') else bpn
+            purl = f"pkg:npm/{name}@{version}"
+            return (version, purl)
+
+    # CPAN package
+    if bb.data.inherits_class("cpan", d) and version:
+        bpn = d.getVar("BPN")
+        if bpn:
+            if bpn.startswith('perl-'):
+                name = bpn[5:]
+            elif bpn.startswith('libperl-'):
+                name = bpn[8:]
+            else:
+                name = bpn
+            purl = f"pkg:cpan/{name}@{version}"
+            return (version, purl)
+
+    # NuGet package
+    if (bb.data.inherits_class("nuget", d) or bb.data.inherits_class("dotnet", d)) and version:
+        bpn = d.getVar("BPN")
+        if bpn:
+            if bpn.startswith('dotnet-'):
+                name = bpn[7:]
+            elif bpn.startswith('nuget-'):
+                name = bpn[6:]
+            else:
+                name = bpn
+            purl = f"pkg:nuget/{name}@{version}"
+            return (version, purl)
+
+    # Maven package
+    if bb.data.inherits_class("maven", d) and version:
+        group_id = d.getVar("MAVEN_GROUP_ID")
+        artifact_id = d.getVar("MAVEN_ARTIFACT_ID")
+
+        if group_id and artifact_id:
+            purl = f"pkg:maven/{group_id}/{artifact_id}@{version}"
+            return (version, purl)
+        else:
+            bpn = d.getVar("BPN")
+            if bpn:
+                if bpn.startswith('maven-'):
+                    name = bpn[6:]
+                elif bpn.startswith('java-'):
+                    name = bpn[5:]
+                else:
+                    name = bpn
+                purl = f"pkg:maven/{name}@{version}"
+                return (version, purl)
+
+    # Base pkg:yocto PURL is handled by oe.purl.get_base_purl()
+    return (version, None)
+
+
 def walk_error(err):
     bb.error(f"ERROR walking {err.filename}: {err}")
 
-- 
2.53.0