Issue 6950 - Don't include headers and metadata from includes into output

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'([\w-]+)\s*:\s*(.*)')
+METADATA_REGEXP = re.compile(r'(.*?)\s*:\s*(.*)')

[Sebastian Noack, 2018/09/14 14:36:54]

This is what we will be going with in Adblock Plus, after Manish's suggestion.

[Vasily Kuznetsov, 2018/09/14 15:09:35]

Acknowledged.

 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_header(text):
     match = HEADER_REGEXP.match(text)
@@ skipping 158 matching lines @@
         Thrown during iteration for invalid filter list lines.
     TypeError
         If `lines` is not iterable.
 
     """
     metadata_closed = False
 
     for line in lines:
         result = parse_line(line)
 
-        if isinstance(result, Comment):
+        if result.type == 'comment':
             match = METADATA_REGEXP.match(result.text)
             if match:
                 key, value = match.groups()
 
                 # Historically, checksums can occur at the bottom of the
                 # filter list. Checksums are no longer used by Adblock Plus,
                 # but in order to strip them (in abp.filters.renderer),
                 # we have to make sure to still parse them regardless of
                 # their position in the filter list.
                 if not metadata_closed or key.lower() == 'checksum':
-                    yield Metadata(key, value)
-                    continue
+                    result = Metadata(key, value)
 
-            if not result.text:
-                metadata_closed = True
-        elif not isinstance(result, Header):
+        if result.type not in {'header', 'metadata'}:
             metadata_closed = True
 
         yield result