Issue 1170 - [adblockplus.org Anwiki to CMS migration] Migrate content

filters/get_subscriptions.py

Index: filters/get_subscriptions.py
diff --git a/filters/get_subscriptions.py b/filters/get_subscriptions.py
new file mode 100644
index 0000000000000000000000000000000000000000..d8ec68f8103ce38e693325c8e86fdc73a8ae948c
--- /dev/null
+++ b/filters/get_subscriptions.py
@@ -0,0 +1,41 @@
+# This file is part of the Adblock Plus website,
+# Copyright (C) 2006-2015 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,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+
+import codecs, tarfile, urllib

[Wladimir Palant, 2015/02/26 20:35:03]

Nit: One import per line please, as required by PEP8 (yes, our old code doesn't
do that).

[kzar, 2015/02/26 21:49:13]

Done.

+
+from sitescripts.subscriptions.subscriptionParser import parse_file, calculate_supplemented
+
+def get_subscriptions(_):
+  def subscription_dict(subscription):
+    d = subscription._data
+    if "supplemented" in d:
+      d["supplemented"] = [subscription_dict(s) for s in d["supplemented"]]
+    return d

[Wladimir Palant, 2015/02/26 20:35:03]

Why is this necessary? The original template in the sitescripts repository
operates directly on the Subscription objects.

Accessing private properties (_data) is definitely a very bad idea.

[kzar, 2015/02/26 21:49:13]

Done.

+
+  result = {}
+  source = urllib.urlopen("https://hg.adblockplus.org/subscriptionlist/archive/default.tar.gz")
+  with tarfile.open(fileobj=source, mode="r|gz") as archive:
+    for fileinfo in archive:
+      if not fileinfo.name.endswith(".subscription"):
+        continue
+
+      filedata = parse_file(fileinfo.name, codecs.getreader('utf8')(archive.extractfile(fileinfo)))
+      if filedata.unavailable:
+        continue
+
+      result[filedata.name] = filedata
+
+  calculate_supplemented(result)
+  return map(subscription_dict, result.itervalues())