Add an UUID field on the DiscoveredDependency model #1651 (#1654)

* Add an UUID field on the DiscoveredDependency model #1651

Signed-off-by: tdruez <[email protected]>

* Use the UUID for the DiscoveredDependency spdx_id #1651

Signed-off-by: tdruez <[email protected]>

* Add changelog entry #1651

Signed-off-by: tdruez <[email protected]>

---------

Signed-off-by: tdruez <[email protected]>

Author: tdruez

CHANGELOG.rst

@@ -1,6 +1,13 @@
 Changelog
 =========
 
+v34.10.2 (unreleased)
+---------------------
+
+- Add a ``UUID`` field on the DiscoveredDependency model.
+  Use the UUID for the DiscoveredDependency spdx_id for better SPDX compatibility.
+  https://github.com/aboutcode-org/scancode.io/issues/1651
+
 v34.10.1 (2025-03-26)
 ---------------------
 

scanpipe/migrations/0070_discovereddependency_uuid.py

@@ -0,0 +1,19 @@
+# Generated by Django 5.1.8 on 2025-04-16 06:49
+
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0069_project_purl'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='discovereddependency',
+            name='uuid',
+            field=models.UUIDField(null=True, editable=False, verbose_name='UUID'),
+        ),
+    ]

scanpipe/migrations/0071_discovereddependency_uuid_populate.py

@@ -0,0 +1,29 @@
+# Generated by Django 5.1.8 on 2025-04-16 06:57
+
+import uuid
+from django.db import migrations
+
+
+def gen_uuid_bulk(apps, schema_editor):
+    DiscoveredDependency = apps.get_model("scanpipe", "DiscoveredDependency")
+    batch_size = 10000
+    objs = []
+    for obj in DiscoveredDependency.objects.filter(uuid__isnull=True).iterator():
+        obj.uuid = uuid.uuid4()
+        objs.append(obj)
+        if len(objs) >= batch_size:
+            DiscoveredDependency.objects.bulk_update(objs, ['uuid'])
+            objs = []
+    if objs:
+        DiscoveredDependency.objects.bulk_update(objs, ['uuid'])
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0070_discovereddependency_uuid'),
+    ]
+
+    operations = [
+        migrations.RunPython(gen_uuid_bulk, reverse_code=migrations.RunPython.noop),
+    ]

scanpipe/migrations/0072_discovereddependency_uuid_unique.py

@@ -0,0 +1,19 @@
+# Generated by Django 5.1.8 on 2025-04-16 07:00
+
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0071_discovereddependency_uuid_populate'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='discovereddependency',
+            name='uuid',
+            field=models.UUIDField(default=uuid.uuid4, editable=False, unique=True, verbose_name='UUID'),
+        ),
+    ]

scanpipe/models.py

@@ -129,6 +129,18 @@ def short_uuid(self):
         return str(self.uuid)[0:8]
 
 
+class UUIDFieldMixin(models.Model):
+    uuid = models.UUIDField(
+        verbose_name=_("UUID"),
+        default=uuid.uuid4,
+        editable=False,
+        unique=True,
+    )
+
+    class Meta:
+        abstract = True
+
+
 class HashFieldsMixin(models.Model):
     """
     The hash fields are not indexed by default, use the `indexes` in Meta as needed:
@@ -3400,6 +3412,7 @@ class Meta:
 
 class DiscoveredPackage(
     ProjectRelatedModel,
+    UUIDFieldMixin,
     ExtraDataFieldMixin,
     SaveProjectMessageMixin,
     UpdateFromDataMixin,
@@ -3421,9 +3434,6 @@ class DiscoveredPackage(
 
     license_expression_field = "declared_license_expression"
 
-    uuid = models.UUIDField(
-        verbose_name=_("UUID"), default=uuid.uuid4, unique=True, editable=False
-    )
     codebase_resources = models.ManyToManyField(
         "CodebaseResource", related_name="discovered_packages"
     )
@@ -3769,6 +3779,7 @@ def only_package_url_fields(self, extra=None):
 
 class DiscoveredDependency(
     ProjectRelatedModel,
+    UUIDFieldMixin,
     SaveProjectMessageMixin,
     UpdateFromDataMixin,
     VulnerabilityMixin,
@@ -4031,7 +4042,10 @@ def populate_dependency_uuid(cls, dependency_data):
 
     @property
     def spdx_id(self):
-        return f"SPDXRef-scancodeio-{self._meta.model_name}-{self.dependency_uid}"
+        # We cannot rely on `dependency_uid` for the SPDX ID because it may contain
+        # PURL components that are not SPDX-compliant. According to the spec,
+        # "SPDXID is a unique string containing letters, numbers, ., and/or -"
+        return f"SPDXRef-scancodeio-{self._meta.model_name}-{self.uuid}"
 
     def as_spdx(self):
         """Return this Dependency as an SPDX Package entry."""

scanpipe/tests/data/asgiref/asgiref-3.3.0.spdx.json

@@ -52,7 +52,7 @@
     },
     {
       "name": "pytest",
-      "SPDXID": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=cfa26c80-95fc-4da3-a290-5e7403d0d9bc",
+      "SPDXID": "SPDXRef-scancodeio-discovereddependency-13818fb7-6094-4868-97ca-384a8fc8d16d",
       "downloadLocation": "NOASSERTION",
       "licenseConcluded": "NOASSERTION",
       "copyrightText": "NOASSERTION",
@@ -68,7 +68,7 @@
     },
     {
       "name": "pytest",
-      "SPDXID": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=bfafc414-739f-4747-bfb0-1b3ad03d62c7",
+      "SPDXID": "SPDXRef-scancodeio-discovereddependency-2f1d3742-0553-4c4f-8731-1ffbbc13827d",
       "downloadLocation": "NOASSERTION",
       "licenseConcluded": "NOASSERTION",
       "copyrightText": "NOASSERTION",
@@ -84,7 +84,7 @@
     },
     {
       "name": "pytest-asyncio",
-      "SPDXID": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=68b8d3cb-eddb-4727-b6cb-707dde279301",
+      "SPDXID": "SPDXRef-scancodeio-discovereddependency-fd5a81e5-0739-406e-9189-7b8a3644ef0d",
       "downloadLocation": "NOASSERTION",
       "licenseConcluded": "NOASSERTION",
       "copyrightText": "NOASSERTION",
@@ -100,7 +100,7 @@
     },
     {
       "name": "pytest-asyncio",
-      "SPDXID": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=570878e1-aa7c-46bc-9216-122b73b34f9b",
+      "SPDXID": "SPDXRef-scancodeio-discovereddependency-e175db55-d0f3-4224-b6d4-2b0ad553b865",
       "downloadLocation": "NOASSERTION",
       "licenseConcluded": "NOASSERTION",
       "copyrightText": "NOASSERTION",
@@ -118,30 +118,30 @@
   "documentDescribes": [
     "SPDXRef-scancodeio-discoveredpackage-101147dd-f8a7-4ea3-87a1-01b9b0af5d4f",
     "SPDXRef-scancodeio-discoveredpackage-b5035991-5b4b-40be-b68b-1c9c528078cd",
-    "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=cfa26c80-95fc-4da3-a290-5e7403d0d9bc",
-    "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=bfafc414-739f-4747-bfb0-1b3ad03d62c7",
-    "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=68b8d3cb-eddb-4727-b6cb-707dde279301",
-    "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=570878e1-aa7c-46bc-9216-122b73b34f9b"
+    "SPDXRef-scancodeio-discovereddependency-13818fb7-6094-4868-97ca-384a8fc8d16d",
+    "SPDXRef-scancodeio-discovereddependency-2f1d3742-0553-4c4f-8731-1ffbbc13827d",
+    "SPDXRef-scancodeio-discovereddependency-fd5a81e5-0739-406e-9189-7b8a3644ef0d",
+    "SPDXRef-scancodeio-discovereddependency-e175db55-d0f3-4224-b6d4-2b0ad553b865"
   ],
   "files": [],
   "relationships": [
     {
-      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=cfa26c80-95fc-4da3-a290-5e7403d0d9bc",
+      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-13818fb7-6094-4868-97ca-384a8fc8d16d",
       "relatedSpdxElement": "SPDXRef-scancodeio-discoveredpackage-101147dd-f8a7-4ea3-87a1-01b9b0af5d4f",
       "relationshipType": "DEPENDENCY_OF"
     },
     {
-      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest?uuid=bfafc414-739f-4747-bfb0-1b3ad03d62c7",
+      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-2f1d3742-0553-4c4f-8731-1ffbbc13827d",
       "relatedSpdxElement": "SPDXRef-scancodeio-discoveredpackage-b5035991-5b4b-40be-b68b-1c9c528078cd",
       "relationshipType": "DEPENDENCY_OF"
     },
     {
-      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=68b8d3cb-eddb-4727-b6cb-707dde279301",
+      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-fd5a81e5-0739-406e-9189-7b8a3644ef0d",
       "relatedSpdxElement": "SPDXRef-scancodeio-discoveredpackage-101147dd-f8a7-4ea3-87a1-01b9b0af5d4f",
       "relationshipType": "DEPENDENCY_OF"
     },
     {
-      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-pkg:pypi/pytest-asyncio?uuid=570878e1-aa7c-46bc-9216-122b73b34f9b",
+      "spdxElementId": "SPDXRef-scancodeio-discovereddependency-e175db55-d0f3-4224-b6d4-2b0ad553b865",
       "relatedSpdxElement": "SPDXRef-scancodeio-discoveredpackage-b5035991-5b4b-40be-b68b-1c9c528078cd",
       "relationshipType": "DEPENDENCY_OF"
     }

scanpipe/tests/data/asgiref/asgiref-3.3.0_fixtures.json

@@ -1714,6 +1714,7 @@
   "model": "scanpipe.discovereddependency",
   "pk": 1,
   "fields": {
+    "uuid": "13818fb7-6094-4868-97ca-384a8fc8d16d",
     "type": "pypi",
     "namespace": "",
     "name": "pytest",
@@ -1739,6 +1740,7 @@
   "model": "scanpipe.discovereddependency",
   "pk": 2,
   "fields": {
+    "uuid": "fd5a81e5-0739-406e-9189-7b8a3644ef0d",
     "type": "pypi",
     "namespace": "",
     "name": "pytest-asyncio",
@@ -1764,6 +1766,7 @@
   "model": "scanpipe.discovereddependency",
   "pk": 3,
   "fields": {
+    "uuid": "2f1d3742-0553-4c4f-8731-1ffbbc13827d",
     "type": "pypi",
     "namespace": "",
     "name": "pytest",
@@ -1789,6 +1792,7 @@
   "model": "scanpipe.discovereddependency",
   "pk": 4,
   "fields": {
+    "uuid": "e175db55-d0f3-4224-b6d4-2b0ad553b865",
     "type": "pypi",
     "namespace": "",
     "name": "pytest-asyncio",

scanpipe/tests/test_models.py

@@ -2429,6 +2429,11 @@ def test_scanpipe_discovered_package_model_compliance_alert(self):
         # Reset the index value
         scanpipe_app.license_policies_index = None
 
+    def test_scanpipe_discovered_package_model_spdx_id(self):
+        package1 = make_package(self.project1, "pkg:type/a")
+        expected = f"SPDXRef-scancodeio-discoveredpackage-{package1.uuid}"
+        self.assertEqual(expected, package1.spdx_id)
+
     def test_scanpipe_model_create_user_creates_auth_token(self):
         basic_user = User.objects.create_user(username="basic_user")
         self.assertTrue(basic_user.auth_token.key)
@@ -2492,14 +2497,19 @@ def test_scanpipe_discovered_dependency_model_many_to_many(self):
         self.assertEqual([], list(c.declared_dependencies.all()))
         self.assertEqual([b_c], list(c.resolved_from_dependencies.all()))
 
-    def test_scanpipe_discovered_dependency_model_is_vulnerable_property(self):
+    def test_scanpipe_discovered_package_model_is_vulnerable_property(self):
         package = DiscoveredPackage.create_from_data(self.project1, package_data1)
         self.assertFalse(package.is_vulnerable)
         package.update(
             affected_by_vulnerabilities=[{"vulnerability_id": "VCID-cah8-awtr-aaad"}]
         )
         self.assertTrue(package.is_vulnerable)
 
+    def test_scanpipe_discovered_dependency_model_spdx_id(self):
+        dependency1 = make_dependency(self.project1)
+        expected = f"SPDXRef-scancodeio-discovereddependency-{dependency1.uuid}"
+        self.assertEqual(expected, dependency1.spdx_id)
+
     def test_scanpipe_package_model_integrity_with_toolkit_package_model(self):
         scanpipe_only_fields = [
             "id",