Add package_uid field to DiscoveredPackage #411

    * Update expected test results

Signed-off-by: Jono Yang <jyang@nexb.com>

Author: JonoYang

scanpipe/migrations/0016_discoveredpackage_package_uid.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.0.4 on 2022-06-09 18:26
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0015_alter_codebaseresource_project_and_more'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='discoveredpackage',
+            name='package_uid',
+            field=models.CharField(blank=True, help_text='Unique identifier for this package.', max_length=1024),
+        ),
+    ]

scanpipe/models.py

@@ -1726,6 +1726,11 @@ class DiscoveredPackage(
         blank=True,
         help_text=_("A list of dependencies for this package."),
     )
+    package_uid = models.CharField(
+        max_length=1024,
+        blank=True,
+        help_text=_("Unique identifier for this package."),
+    )
 
     # `AbstractPackage` model overrides:
     keywords = models.JSONField(default=list, blank=True)

scanpipe/pipes/__init__.py

@@ -75,25 +75,16 @@ def update_or_create_package(project, package_data, codebase_resource=None):
     Uses the `project` and `package_data` mapping to lookup and creates the
     DiscoveredPackage using its Package URL and package_uid as a unique key.
     """
-    purl_data = DiscoveredPackage.extract_purl_data(package_data)
     package_uid = package_data.get("package_uid")
-    purl_data_and_package_uid = {
-        **purl_data,
-        "extra_data": {"package_uid": package_uid},
-    }
 
     try:
         package = DiscoveredPackage.objects.get(
             project=project,
-            **purl_data_and_package_uid
+            package_uid=package_uid,
         )
     except DiscoveredPackage.DoesNotExist:
         package = None
 
-    package_data = {
-        **package_data,
-        "extra_data": {"package_uid": package_uid},
-    }
     if package:
         package.update_from_data(package_data)
 

scanpipe/pipes/scancode.py

@@ -396,7 +396,7 @@ def create_codebase_resources(project, scanned_codebase):
         if hasattr(scanned_resource, "for_packages"):
             for package_uid in scanned_resource.for_packages:
                 package = DiscoveredPackage.objects.get(
-                    extra_data__contains={"package_uid": package_uid}
+                    package_uid=package_uid
                 )
                 set_codebase_resource_for_package(
                     codebase_resource=cbr, discovered_package=package