Issue 199 - [filter lists] Don`t allow multiple Expires comments

sitescripts/subscriptions/combineSubscriptions.py

 #!/usr/bin/env python
 # 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.
 #
@@ skipping 71 matching lines @@
   if len(lines) > 0:
     header = lines.pop(0)
   if not re.search(r"\[Adblock(?:\s*Plus\s*([\d\.]+)?)?\]", header, re.I):
     raise Exception("This is not a valid Adblock Plus subscription file.")
 
   lines = resolve_includes(source_name, sources, lines, timeout)
   seen = set(["checksum", "version"])
   def check_line(line):
     if line == "":
       return False
-    match = re.search(r"^\s*!\s*(Redirect|Homepage|Title|Checksum|Version)\s*:", line, re.M | re.I)
+    match = re.search(r"^\s*!\s*(Redirect|Homepage|Title|Checksum|Version|Expires)\s*:", line, re.M | re.I)
     if not match:
       return True
     key = match.group(1).lower()
     if key in seen:
       return False
     seen.add(key)
     return True
   lines = filter(check_line, lines)
 
   write_tpl(save_file, os.path.splitext(filename)[0] + ".tpl", lines)
@@ skipping 28 matching lines @@
           except urllib2.URLError, e:
             error = e
             time.sleep(5)
         if error:
           raise error
 
         # We should really get the charset from the headers rather than assuming
         # that it is UTF-8. However, some of the Google Code mirrors are
         # misconfigured and will return ISO-8859-1 as charset instead of UTF-8.
         newlines = data.decode("utf-8").splitlines()
-        newlines = filter(lambda l: not re.search(r"^\s*!.*?\bExpires\s*(?::|after)\s*(\d+)\s*(h)?", l, re.M | re.I), newlines)
-        newlines = filter(lambda l: not re.search(r"^\s*!\s*(Redirect|Homepage|Title|Version)\s*:", l, re.M | re.I), newlines)
+        newlines = filter(lambda l: not re.search(r"^\s*!\s*(Redirect|Homepage|Title|Version|Expires)\s*:", l, re.M | re.I), newlines)
       else:
         result.append("! *** %s ***" % filename)
 
         include_source = source_name
         if ":" in filename:
           include_source, filename = filename.split(":", 1)
         if not include_source in sources:
           raise Exception('Cannot include file from repository "%s", this repository is unknown' % include_source)
 
         source = sources[include_source]
@@ skipping 11 matching lines @@
           line = ""
       result.append(line)
   return result
 
 def write_tpl(save_file, filename, lines):
   result = []
   result.append("msFilterList")
   for line in lines:
     if re.search(r"^\s*!", line):
       # This is a comment. Handle "Expires" comment in a special way, keep the rest.
-      match = re.search(r"\bExpires\s*(?::|after)\s*(\d+)\s*(h)?", line, re.I)
+      match = re.search(r"^\s*!\s*Expires\s*:\s*(\d+)\s*(h)?", line, re.I)
       if match:
         interval = int(match.group(1))
         if match.group(2):
           interval = int(interval / 24)
         result.append(": Expires=%i" % interval)
       else:
         result.append(re.sub(r"^\s*!", "#", re.sub(r"--!$", "--#", line)))
     elif line.find("#") >= 0:
       # Element hiding rules are not supported in MSIE, drop them
       pass
@@ skipping 133 matching lines @@
 
   timeout = 30
   for option, value in opts:
     if option in ("-h", "--help"):
       usage()
       sys.exit()
     elif option in ("-t", "--timeout"):
       timeout = int(value)
 
   combine_subscriptions(sources, target_dir, timeout)