Issue 6976 - Ignore invalid headers instead of crashing

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 124 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*!\s*(.*?)\s*:\s*(.*)')
 INCLUDE_REGEXP = re.compile(r'%include\s+(.+)%')
-HEADER_REGEXP = re.compile(r'\[(?:(Adblock(?:\s*Plus\s*[\d\.]+?)?)|.*)\]',
-                           flags=re.I)
+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_instruction(text):
     match = INCLUDE_REGEXP.match(text)
     if not match:
         raise ParseError('Unrecognized instruction', text)
@@ skipping 130 matching lines @@
         line = line.decode('utf-8')
 
     stripped = line.strip()
 
     if stripped == '':
         return EmptyLine()
 
     if position == 'start':
         match = HEADER_REGEXP.search(line)
         if match:
-            version = match.group(1)
-            if not version:
-                raise ParseError('Malformed header', line)
-            return Header(version)
+            return Header(match.group(1))
 
     if stripped.startswith('!'):
         match = METADATA_REGEXP.match(line)
         if match:
             key, value = match.groups()
             if position != 'body' or key.lower() == 'checksum':
                 return Metadata(key, value)
         return Comment(stripped[1:].lstrip())
 
     if stripped.startswith('%') and stripped.endswith('%'):
@@ skipping 28 matching lines @@
     for line in lines:
         parsed_line = parse_line(line, position)
         yield parsed_line
 
         if position != 'body' and parsed_line.type in {'header', 'metadata'}:
             # Continue parsing metadata until it's over...
             position = 'metadata'
         else:
             # ...then switch to parsing the body.
             position = 'body'