Issue 3168 - Add a script for generating new content blocker lists

generate_lists.py

Index: generate_lists.py
===================================================================
new file mode 100755
--- /dev/null
+++ b/generate_lists.py
@@ -0,0 +1,83 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# This file is part of Adblock Plus <https://adblockplus.org/>,
+# 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 os
+import shutil
+import subprocess
+import tempfile
+import urllib2
+
+BASE_PATH = os.path.dirname(os.path.abspath(__file__))
+ABP2BLOCKLIST_URL = "https://hg.adblockplus.org/abp2blocklist"
+ABP2BLOCKLIST_PATH = os.path.join(BASE_PATH, "abp2blocklist")
+EASYLIST_URL = "https://easylist-downloads.adblockplus.org/easylist_noadult.txt"
+EXCEPTIONRULES_URL = "https://easylist-downloads.adblockplus.org/exceptionrules.txt"
+EASYLIST_CONTENT_BLOCKER_PATH = os.path.join(BASE_PATH, "easylist_content_blocker.json")
+COMBINED_CONTENT_BLOCKER_PATH = os.path.join(BASE_PATH, "easylist+exceptionrules_content_blocker.json")
+
+def _update_abp2blocklist():
+  if os.path.isdir(ABP2BLOCKLIST_PATH):
+    subprocess.check_call(["hg", "pull", "-u", "-R", ABP2BLOCKLIST_PATH])
+  else:
+    subprocess.check_call(["hg", "clone", ABP2BLOCKLIST_URL,
+                           ABP2BLOCKLIST_PATH])
+    subprocess.check_call(["npm", "install", "tldjs"], cwd=ABP2BLOCKLIST_PATH)

[Felix Dahlke, 2015/10/06 18:23:58]

Well, this is a bit ugly. Once my patch that adds package.json lands in
abp2blocklist, I can change this to just call "npm install" after every
clone/pull.

[Sebastian Noack, 2015/10/12 13:08:31]

This can be addressed now.

[Felix Dahlke, 2015/10/21 20:36:21]

Done.

+
+def _download_filter_lists():
+  easylist_response = urllib2.urlopen(EASYLIST_URL)

[Sebastian Noack, 2015/10/12 13:08:31]

Please close the file like object returned by urlopen() in a finally-block.

[Felix Dahlke, 2015/10/21 20:36:22]

Done.

+  with tempfile.NamedTemporaryFile(mode="w", delete=False) as easylist_file:

[Sebastian Noack, 2015/10/12 13:08:31]

Always add "b" to the mode when dealing with binary files, for same behavior on
all platforms.

[Sebastian Noack, 2015/10/12 13:08:31]

How about, using mode NamedTemporaryFile("wb+"), passing around the file object
instead the filename? That way you don't have to unnecessarily open the file
multiple times, and the cleanup is done implicitly when it gets closed.

[Felix Dahlke, 2015/10/21 20:36:21]

Passing around RW file objects seemed pretty hacky to me. I tried it now, and it
does feel hacky, but I like how it gets rid of the manual cleanup and shortens
things a bit. So I'm fine with this if you prefer it, it's in the latest patch
set.

[Felix Dahlke, 2015/10/21 20:36:22]

Those are ASCII files, however, should I still add the "b"?

[Sebastian Noack, 2015/10/21 20:56:23]

Either you treat it as a binary file. Then you should add "b" to prevent Windows
from messing with line endings. Or you can treat if as text files using
io.open(.., encoding=..).

[Felix Dahlke, 2015/10/22 02:43:45]

I see, done.

+    easylist_file.write(easylist_response.read())

[Sebastian Noack, 2015/10/12 13:08:31]

Please use shutil.copyfileobj consistently.

[Felix Dahlke, 2015/10/21 20:36:21]

Done.

+  exceptionrules_response = urllib2.urlopen(EXCEPTIONRULES_URL)
+  with tempfile.NamedTemporaryFile(mode="w", delete=False) as exceptionrules_file:
+    exceptionrules_file.write(exceptionrules_response.read())
+  return (easylist_file.name, exceptionrules_file.name)
+
+def _concatenate_files(*source_paths):
+  with tempfile.NamedTemporaryFile(mode="w", delete=False) as destination_file:
+    for source_path in source_paths:
+      with open(source_path, "r") as source_file:
+        shutil.copyfileobj(source_file, destination_file)
+  return destination_file.name
+
+def _convert_filter_list(source_path, destination_path):
+  with open(source_path, "r") as source_file, \
+       open(destination_path, "w") as destination_file:
+    subprocess.check_call(["node", "abp2blocklist.js"],
+                          cwd=ABP2BLOCKLIST_PATH, stdin=source_file,
+                          stdout=destination_file)
+
+if __name__ == "__main__":
+  print "Fetching/updating abp2blocklist ..."
+  _update_abp2blocklist()
+
+  print "Downloading filter lists ..."
+  easylist_path, exceptionrules_path = _download_filter_lists()
+
+  try:
+    print "Generating %s ..." % os.path.basename(EASYLIST_CONTENT_BLOCKER_PATH)
+    _convert_filter_list(easylist_path, EASYLIST_CONTENT_BLOCKER_PATH)
+
+    print "Generating %s ..." % os.path.basename(COMBINED_CONTENT_BLOCKER_PATH)
+    combined_path = _concatenate_files(easylist_path, exceptionrules_path)
+    try:
+      _convert_filter_list(combined_path, COMBINED_CONTENT_BLOCKER_PATH)
+    finally:
+      os.remove(combined_path)
+  finally:
+    os.remove(easylist_path)
+    os.remove(exceptionrules_path)