mygpo/data/podcast.py

   1 #
   2 # This file is part of my.gpodder.org.
   3 #
   4 # my.gpodder.org is free software: you can redistribute it and/or modify it
   5 # under the terms of the GNU Affero General Public License as published by
   6 # the Free Software Foundation, either version 3 of the License, or (at your
   7 # option) any later version.
   8 #
   9 # my.gpodder.org is distributed in the hope that it will be useful, but
  10 # WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  11 # or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
  12 # License for more details.
  13 #
  14 # You should have received a copy of the GNU Affero General Public License
  15 # along with my.gpodder.org. If not, see <http://www.gnu.org/licenses/>.
  16 #
  17
  18 from mygpo.core.models import Podcast
  19 from mygpo.couch import get_main_database
  20
  21 try:
  22     from collections import Counter
  23 except ImportError:
  24     from mygpo.counter import Counter
  25
  26
  27 def calc_similar_podcasts(podcast, num=20):
  28     """
  29     calculates and returns a list of podcasts that seem to be similar
  30     to the given one.
  31
  32     Probably an expensive operation
  33     """
  34
  35     db = get_main_database()
  36
  37     res = db.view('subscriptions/by_podcast',
  38             startkey    = [podcast.get_id(), None, None],
  39             endkey      = [podcast.get_id(), {}, {}],
  40             group       = True,
  41             group_level = 2,
  42             stale       = 'update_after',
  43         )
  44
  45     users = (r['key'][1] for r in res)
  46
  47     podcasts = Counter()
  48
  49
  50     for user_id in users:
  51         subscribed = db.view('subscriptions/by_user',
  52                 startkey    = [user_id, True, None, None],
  53                 endkey      = [user_id, True, {}, {}],
  54                 group       = True,
  55                 group_level = 3,
  56                 stale       = 'update_after',
  57             )
  58         user_subscriptions = set(r['key'][2] for r in subscribed)
  59         user_counter = Counter(user_subscriptions)
  60         podcasts.update(user_counter)
  61
  62
  63     return podcasts.most_common(num)