Issue 6685 - Offer incremental filter list downloads

abp/filters/parser.py

 # This file is part of Adblock Plus <https://adblockplus.org/>,
 # Copyright (C) 2006-present 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
@@ skipping 122 matching lines @@
 
 
 Header = _line_type('Header', 'version', '[{.version}]')
 EmptyLine = _line_type('EmptyLine', '', '')
 Comment = _line_type('Comment', 'text', '! {.text}')
 Metadata = _line_type('Metadata', 'key value', '! {0.key}: {0.value}')
 Filter = _line_type('Filter', 'text selector action options', '{.text}')
 Include = _line_type('Include', 'target', '%include {0.target}%')
 
 
-METADATA_REGEXP = re.compile(r'!\s*(\w+)\s*:\s*(.*)')
-METADATA_KEYS = {'Homepage', 'Title', 'Expires', 'Checksum', 'Redirect',
-                 'Version'}
+METADATA_REGEXP = re.compile(r'!\s*([\w-]+)\s*:(?!//)\s*(.*)')
 INCLUDE_REGEXP = re.compile(r'%include\s+(.+)%')
 HEADER_REGEXP = re.compile(r'\[(Adblock(?:\s*Plus\s*[\d\.]+?)?)\]', flags=re.I)
 HIDING_FILTER_REGEXP = re.compile(r'^([^/*|@"!]*?)#([@?])?#(.+)$')
 FILTER_OPTIONS_REGEXP = re.compile(
     r'\$(~?[\w-]+(?:=[^,]+)?(?:,~?[\w-]+(?:=[^,]+)?)*)$'
 )
 
 
 def _parse_comment(text):
     match = METADATA_REGEXP.match(text)
-    if match and match.group(1) in METADATA_KEYS:
+    if match:
         return Metadata(match.group(1), match.group(2))
     return Comment(text[1:].strip())
 
 
 def _parse_header(text):
     match = HEADER_REGEXP.match(text)
     if not match:
         raise ParseError('Malformed header', text)
     return Header(match.group(1))
 
@@ skipping 147 matching lines @@
     Raises
     ------
     ParseError
         Thrown during iteration for invalid filter list lines.
     TypeError
         If `lines` is not iterable.
 
     """
     for line in lines:
         yield parse_line(line)