Introducing endpoint for stats

This endpoint can be queried on a daily basis to retrieve cloud usage  stats. For assets and comments we take into considerations only those who belong to public projects.

cloud/__init__.py

@@ -49,7 +49,11 @@ class CloudExtension(PillarExtension):
         :rtype: list of flask.Blueprint objects.
         """
         from . import routes
-        return [routes.blueprint]
+        import cloud.stats.routes
+        return [
+            routes.blueprint,
+            cloud.stats.routes.blueprint,
+        ]
 
     @property
     def template_path(self):

cloud/stats/__init__.py

@@ -0,0 +1,47 @@
+"""Interesting usage metrics"""
+
+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:
+    c = current_app.db()['nodes']
+    # If we provide a query, we extend the first $match step in the aggregation pipeline with
+    # with the extra parameters (for example node_type)
+    if query:
+        pipeline[0]['$match'].update(query)
+    # 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
+
+
+def count_users() -> int:
+    u = current_app.db()['users']
+    return u.count()

cloud/stats/routes.py

@@ -0,0 +1,58 @@
+import logging
+import datetime
+import functools
+
+from flask import Blueprint, jsonify
+from cloud.stats import count_nodes, count_users
+
+blueprint = Blueprint('cloud.stats', __name__, url_prefix='/s')
+
+log = logging.getLogger(__name__)
+
+
+@functools.lru_cache()
+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),
+    }
+    return stats
+
+
+@blueprint.route('/')
+@blueprint.route('/before/<int:before>')
+def index(before: int=0):
+    """
+    This endpoint is queried on a daily basis by grafista to retrieve cloud usage
+    stats. For assets and comments we take into considerations only those who belong
+    to public projects.
+
+    These is the data we retrieve
+
+    - Comments count
+    - Assets count (video, images and files)
+    - Users count (subscribers count goes via store)
+    - Blender Sync users
+    """
+
+    # TODO: Implement project-level metrics (and update ad every child update)
+    if before:
+        before = datetime.datetime.strptime(before, '%Y%m%d')
+    else:
+        today = datetime.date.today()
+        before = datetime.datetime(today.year, today.month, today.day)
+
+    return jsonify(get_stats(before))