Ensure collection stats are updated when WACZ is added on upload (#2351)

Fixes #2350 

Collection earliest/latest dates and the collection modified date are
also now updated when crawls or uploads are added to a collection via
the collection auto-add feature.

backend/btrixcloud/colls.py

@@ -684,11 +684,19 @@ class CollectionOps:
         )
 
     async def update_crawl_collections(self, crawl_id: str):
-        """Update counts and tags for all collections in crawl"""
+        """Update counts, dates, and modified for all collections in crawl"""
         crawl = await self.crawls.find_one({"_id": crawl_id})
         crawl_coll_ids = crawl.get("collectionIds")
-        for collection_id in crawl_coll_ids:
-            await self.update_collection_counts_and_tags(collection_id)
+        modified = dt_now()
+
+        for coll_id in crawl_coll_ids:
+            await self.update_collection_counts_and_tags(coll_id)
+            await self.update_collection_dates(coll_id)
+            await self.collections.find_one_and_update(
+                {"_id": coll_id},
+                {"$set": {"modified": modified}},
+                return_document=pymongo.ReturnDocument.AFTER,
+            )
 
     async def add_successful_crawl_to_collections(self, crawl_id: str, cid: UUID):
         """Add successful crawl to its auto-add collections."""

backend/btrixcloud/uploads.py

@@ -190,7 +190,9 @@ class UploadOps(BaseCrawlOps):
             self.event_webhook_ops.create_upload_finished_notification(crawl_id, org.id)
         )
 
-        asyncio.create_task(self.page_ops.add_crawl_pages_to_db_from_wacz(crawl_id))
+        asyncio.create_task(
+            self._add_pages_and_update_collections(crawl_id, collections)
+        )
 
         await self.orgs.inc_org_bytes_stored(org.id, file_size, "upload")
 
@@ -204,6 +206,13 @@ class UploadOps(BaseCrawlOps):
 
         return {"id": crawl_id, "added": True, "storageQuotaReached": quota_reached}
 
+    async def _add_pages_and_update_collections(
+        crawl_id: str, collections: Optional[List[str]] = None
+    ):
+        await self.page_ops.add_crawl_pages_to_db_from_wacz(crawl_id)
+        if collections:
+            await self.colls.update_crawl_collections(crawl_id)
+
     async def delete_uploads(
         self,
         delete_list: DeleteCrawlList,

backend/test/test_uploads.py

@@ -285,6 +285,26 @@ def test_get_upload_pages(admin_auth_headers, default_org_id, upload_id):
     assert data["uniquePageCount"] > 0
 
 
+def test_uploads_collection_updated(
+    admin_auth_headers, default_org_id, uploads_collection_id, upload_id
+):
+    # Verify that collection is updated when WACZ is added on upload
+    r = requests.get(
+        f"{API_PREFIX}/orgs/{default_org_id}/collections/{uploads_collection_id}",
+        headers=admin_auth_headers,
+    )
+    assert r.status_code == 200
+    data = r.json()
+
+    assert data["crawlCount"] > 0
+    assert data["pageCount"] > 0
+    assert data["uniquePageCount"] > 0
+    assert data["totalSize"] > 0
+    assert data["dateEarliest"]
+    assert data["dateLatest"]
+    assert data["modified"] > data["created"]
+
+
 def test_replace_upload(
     admin_auth_headers, default_org_id, uploads_collection_id, upload_id
 ):