Issue 527 - Only process notification requests sent by our own extensions

sitescripts/stats/bin/logprocessor.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2014 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus is distributed in the hope that it will be useful,
@@ skipping 281 matching lines @@
       diff = info["time"] - last_update
       if diff.days >= 365:
         info["downloadInterval"] = "%i year(s)" % (diff.days / 365)
       elif diff.days >= 30:
         info["downloadInterval"] = "%i month(s)" % (diff.days / 30)
       elif diff.days >= 1:
         info["downloadInterval"] = "%i day(s)" % diff.days
       else:
         info["downloadInterval"] = "%i hour(s)" % (diff.seconds / 3600)
 
-      diffdays = (info["time"].date() - last_update.date()).days
-      if diffdays == 0:
-        info["previousDownload"] = "same day"
-      elif diffdays < 30:
-        info["previousDownload"] = "%i day(s)" % diffdays
-      elif diffdays < 365:
-        info["previousDownload"] = "%i month(s)" % (diffdays / 30)
+      if info["addonName"].startswith("adblockplus"):
+        diffdays = (info["time"].date() - last_update.date()).days
+        if diffdays == 0:
+          info["previousDownload"] = "same day"
+        elif diffdays < 30:
+          info["previousDownload"] = "%i day(s)" % diffdays
+        elif diffdays < 365:
+          info["previousDownload"] = "%i month(s)" % (diffdays / 30)
+        else:
+          info["previousDownload"] = "%i year(s)" % (diffdays / 365)
       else:
-        info["previousDownload"] = "%i year(s)" % (diffdays / 365)
+        info["previousDownload"] = "unknown"
 
       if last_update.year != info["time"].year or last_update.month != info["time"].month:
         info["firstInMonth"] = info["firstInDay"] = True
       elif last_update.day != info["time"].day:
         info["firstInDay"] = True
 
       if get_week(last_update) != get_week(info["time"]):
         info["firstInWeek"] = True
     except ValueError:
       info["downloadInterval"] = "unknown"
@@ skipping 69 matching lines @@
   info["fullua"] = "%s %s" % (info["ua"], info["uaversion"])
   info["clientid"] = match.group(9)
 
   # Additional metadata depends on file type
   filename = os.path.basename(info["file"])
   ext = os.path.splitext(filename)[1]
   if ext == ".txt" or filename == "update.json" or filename == "notification.json":
     # Subscription downloads, libadblockplus update checks and notification
     # checks are performed by the downloader
     parse_downloader_query(info)
-
-    if filename == "notification.json" and info["addonName"] not in ("adblockplus", "adblockpluschrome", "adblockplusopera", "adblockplussafari"):

[Felix Dahlke, 2014/05/22 07:35:21]

I think we should filter this for all downloads really, objections Wladimir?

Also, not a fan of hard coding the addon names. How about anything that starts
with "adblockplus"?

[Wladimir Palant, 2014/05/22 07:44:05]

a) We really need to do this for all downloads, otherwise we will have a
distorted picture.
b) We don't want to filter unknown extensions in general. We want to know how
many users are on outdated Adblock Plus versions (not sending addonName
parameter) and the forks. We merely shouldn't count them for the
previousDownload field.
c) fhd is right, this approach won't scale. What about adblockplusandroid or
adblockplusie? .startswith("adblockplus") feels hacky but it seems to be the
better approach here.

[Sebastian Noack, 2014/05/22 08:40:39]

Done.

-      return None
   elif ext == ".tpl":
     # MSIE TPL download, no additional data here
     pass
   elif ext in (".xpi", ".crx", ".apk", ".msi", ".exe", ".safariextz"):
     # Package download, might be an update
     info["installType"] = parse_update_flag(info["query"])
   elif filename == "update.rdf":
     # Gecko update check or a legacy Android update check. The latter doesn't
     # have usable data anyway so trying the Chrome route won't do any harm.
     info["addonName"] = parse_addon_name(info["file"])
@@ skipping 132 matching lines @@
   parser.add_argument("mirror_name", nargs="?", help="Name of the mirror server that the file belongs to")
   parser.add_argument("server_type", nargs="?", help="Server type like download, update or subscription")
   parser.add_argument("log_file", nargs="?", help="Log file path, can be a local file path, http:// or ssh:// URL")
   args = parser.parse_args()
 
   if args.mirror_name and args.server_type and args.log_file:
     sources = [(args.mirror_name, args.server_type, args.log_file)]
   else:
     sources = get_stats_files()
   parse_sources(sources, args.factor, args.verbose)