Add garbage collection task

mediagoblin.ini

@@ -23,6 +23,10 @@ allow_registration = true
 # Set to false to disable the ability for users to report offensive content
 allow_reporting = true
 
+# Frequency garbage collection will run (setting to 0 or false to disable)
+# Setting units are minutes.
+garbage_collection = 60
+
 ## Uncomment this to put some user-overriding templates here
 # local_templates = %(here)s/user_dev/templates/
 

mediagoblin/federation/task.py

@@ -0,0 +1,49 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import celery
+import datetime
+import logging
+import pytz
+
+from mediagoblin.db.models import MediaEntry
+
+_log = logging.getLogger(__name__)
+logging.basicConfig()
+_log.setLevel(logging.DEBUG)
+
+@celery.task()
+def collect_garbage():
+	"""
+		Garbage collection to clean up media
+
+		This will look for all critera on models to clean
+		up. This is primerally written to clean up media that's
+		entered a erroneous state.
+	"""
+	_log.info("Garbage collection is running.")
+	now = datetime.datetime.now(pytz.UTC) - datetime.timedelta(days=1)
+
+	garbage = MediaEntry.query.filter(MediaEntry.created > now)
+	garbage = garbage.filter(MediaEntry.state == "unprocessed")
+
+	for entry in garbage.all():
+		_log.info("Garbage media found with ID '{0}'".format(entry.id))
+		entry.delete()
+
+
+
+

mediagoblin/federation/views.py

@@ -1,3 +1,19 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
 import json
 import io
 import mimetypes
@@ -135,7 +151,7 @@ def feed(request):
                 media.license = obj["license"]
 
             media.save()
-            manager = media.media_manager.api_add_to_feed(request, media)
+            media.media_manager.api_add_to_feed(request, media)
 
             return json_response({
                 "verb": "post",
@@ -319,7 +335,6 @@ def object_comments(request):
 
     return response
 
-
 ##
 # Well known
 ##

mediagoblin/init/celery/__init__.py

@@ -16,6 +16,7 @@
 
 import os
 import sys
+import datetime
 import logging
 
 from celery import Celery
@@ -58,6 +59,18 @@ def get_celery_settings_dict(app_config, global_config,
         celery_settings['CELERY_ALWAYS_EAGER'] = True
         celery_settings['CELERY_EAGER_PROPAGATES_EXCEPTIONS'] = True
 
+    # Garbage collection periodic task
+    frequency = app_config.get('garbage_collection', 60)
+    if frequency:
+        frequency = int(app_config['garbage_collection'])
+        celery_settings['CELERYBEAT_SCHEDULE'] = {
+            'garbage-collection': {
+                'task': 'mediagoblin.federation.task.garbage_collection',
+                'schedule': datetime.timedelta(minutes=frequency),
+            }
+        }
+        celery_settings['BROKER_HEARTBEAT'] = 1
+
     return celery_settings