Improved Snapshot Generation

backend/apps/github/models/managers/release.py

@@ -0,0 +1,23 @@
+"""GitHub app release managers."""
+
+from django.db import models
+
+
+class ActiveReleaseManager(models.Manager):
+    """Active releases manager."""
+
+    def get_queryset(self):
+        """Get queryset of active releases.
+
+        Filters out draft and pre-releases, and ensures repository exists.
+        """
+        return (
+            super()
+            .get_queryset()
+            .select_related("repository")
+            .filter(
+                is_draft=False,
+                is_pre_release=False,
+                repository__is_empty=False,
+            )
+        )

backend/apps/github/models/release.py

@@ -4,12 +4,16 @@
 
 from apps.common.models import BulkSaveModel, TimestampedModel
 from apps.github.models.common import NodeModel
+from apps.github.models.managers.release import ActiveReleaseManager
 from apps.github.models.mixins.release import ReleaseIndexMixin
 
 
 class Release(BulkSaveModel, NodeModel, ReleaseIndexMixin, TimestampedModel):
     """Release model."""
 
+    objects = models.Manager()
+    active_releases = ActiveReleaseManager()
+
     class Meta:
         db_table = "github_releases"
         indexes = [

backend/apps/owasp/management/commands/owasp_process_snapshots.py

@@ -66,32 +66,22 @@ def process_snapshot(self, snapshot: Snapshot) -> None:
 
         try:
             # Fetch new data for each model type
-            new_chapters = self.get_new_items(
-                Chapter,
-                snapshot.start_at,
-                snapshot.end_at,
-            ).filter(
-                is_active=True,
+            new_chapters = Chapter.active_chapters.filter(
+                created_at__gte=snapshot.start_at,
+                created_at__lte=snapshot.end_at,
             )
             new_issues = self.get_new_items(
                 Issue,
                 snapshot.start_at,
                 snapshot.end_at,
             )
-            new_projects = self.get_new_items(
-                Project,
-                snapshot.start_at,
-                snapshot.end_at,
-            ).filter(
-                is_active=True,
+            new_projects = Project.active_projects.filter(
+                created_at__gte=snapshot.start_at,
+                created_at__lte=snapshot.end_at,
             )
-            new_releases = self.get_new_items(
-                Release,
-                snapshot.start_at,
-                snapshot.end_at,
-            ).filter(
-                is_draft=False,
-                is_pre_release=False,
+            new_releases = Release.active_releases.filter(
+                created_at__gte=snapshot.start_at,
+                created_at__lte=snapshot.end_at,
             )
             new_users = self.get_new_items(
                 User,