Properly count Blender Sync users

Use a dedicated aggregation pipeline to filter one startup.blend per home project and count them.

cloud/stats/__init__.py

@@ -2,35 +2,34 @@
 
 from flask import current_app
 
-pipeline = [
-    {'$match': {'_deleted': {'$ne': 'true'}}},
-    {
-        '$lookup':
-            {
-                'from': "projects",
-                'localField': "project",
-                'foreignField': "_id",
-                'as': "project",
-            }
-    },
-    {
-        '$unwind':
-            {
-                'path': '$project',
-            }
-    },
-    {
-        '$project':
-            {
-                'p.is_private': 1,
-            }
-    },
-    {'$match': {'p.is_private': {'$ne': True}}},
-    {'$count': 'tot'}
-]
-
 
 def count_nodes(query=None) -> int:
+    pipeline = [
+        {'$match': {'_deleted': {'$ne': 'true'}}},
+        {
+            '$lookup':
+                {
+                    'from': "projects",
+                    'localField': "project",
+                    'foreignField': "_id",
+                    'as': "project",
+                }
+        },
+        {
+            '$unwind':
+                {
+                    'path': '$project',
+                }
+        },
+        {
+            '$project':
+                {
+                    'p.is_private': 1,
+                }
+        },
+        {'$match': {'p.is_private': {'$ne': True}}},
+        {'$count': 'tot'}
+    ]
     c = current_app.db()['nodes']
     # If we provide a query, we extend the first $match step in the aggregation pipeline with
     # with the extra parameters (for example node_type)
@@ -45,3 +44,42 @@ def count_nodes(query=None) -> int:
 def count_users() -> int:
     u = current_app.db()['users']
     return u.count()
+
+
+def count_blender_sync() -> int:
+    pipeline = [
+        # 0 Find all startups.blend that are not deleted
+        {
+            '$match': {
+                '_deleted': {'$ne': 'true'},
+                'name': 'startup.blend',
+            }
+        },
+        # 1 Group them per project (drops any duplicates)
+        {'$group': {'_id': '$project'}},
+        # 2 Join the project info
+        {
+            '$lookup':
+                {
+                    'from': "projects",
+                    'localField': "_id",
+                    'foreignField': "_id",
+                    'as': "project",
+                }
+        },
+        # 3 Unwind the project list (there is always only one project)
+        {
+            '$unwind':
+                {
+                    'path': '$project',
+                }
+        },
+        # 4 Find all home projects
+        {'$match': {'project.category': 'home'}},
+        {'$count': 'tot'}
+    ]
+    c = current_app.db()['nodes']
+    # Return either a list with one item or an empty list
+    r = list(c.aggregate(pipeline=pipeline))
+    count = 0 if not r else r[0]['tot']
+    return count

cloud/stats/routes.py

@@ -3,7 +3,7 @@ import datetime
 import functools
 
 from flask import Blueprint, jsonify
-from cloud.stats import count_nodes, count_users
+from cloud.stats import count_nodes, count_users, count_blender_sync
 
 blueprint = Blueprint('cloud.stats', __name__, url_prefix='/s')
 
@@ -14,20 +14,17 @@ log = logging.getLogger(__name__)
 def get_stats(before: datetime.datetime):
     query_comments = {'node_type': 'comment'}
     query_assets = {'node_type': 'asset'}
-    # TODO Actually query per home project (and 1 blend per project)
-    query_user_blender_sync = {'name': 'startup.blend'}
 
     if before:
         d = {'_created': {'$lt': before}}
         query_comments.update(d)
         query_assets.update(d)
-        query_user_blender_sync.update(d)
 
     stats = {
         'comments': count_nodes(query_comments),
         'assets': count_nodes(query_assets),
         'users_total': count_users(),
-        'users_blender_sync': count_nodes(query_user_blender_sync),
+        'users_blender_sync': count_blender_sync(),
     }
     return stats