Add an UUID field on the DiscoveredDependency model #1651

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

Author: tdruez

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,