Issue 6920 - Only parse metadata from the top of the file

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*:\s*(.*)')
+METADATA_REGEXP = re.compile(r'([\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_header(text):
     match = HEADER_REGEXP.match(text)
@@ skipping 92 matching lines @@
     """
     if '#' in text:
         match = HIDING_FILTER_REGEXP.search(text)
         if match:
             return _parse_hiding_filter(text, *match.groups())
     return _parse_blocking_filter(text)
 
 
 def parse_line(line_text):
     """Parse one line of a filter list.
+
+    Note that parse_line() doesn't handle special comments, hence never returns
+    a Metadata() object, Adblock Plus only considers metadata when parsing the
+    whole filter list and only if they are given at the top of the filter list.
 
     Parameters
     ----------
     line_text : str
         Line of a filter list.
 
     Returns
     -------
     namedtuple
         Parsed line (see `_line_type`).
@@ skipping 45 matching lines @@
 
     """
     metadata_closed = False
 
     for line in lines:
         result = parse_line(line)
 
         if isinstance(result, Comment):
             match = METADATA_REGEXP.match(result.text)
             if match:
-                # The regular expression matches as well if we see a
-                # malformed key (e.g. "Last modified"). In that case we
-                # want to keep looking for more metadata, but yield a
-                # Comment instead of a Metadata object.
-                #
+                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.
-                key, value = match.groups()
-                if key and (not metadata_closed or key.lower() == 'checksum'):
-                    result = Metadata(key, value)
-
-                yield result
-                continue
-
-        if not isinstance(result, Header):
+                if not metadata_closed or key.lower() == 'checksum':
+                    yield Metadata(key, value)
+                    continue
+
+            if not result.text:
+                metadata_closed = True
+        elif not isinstance(result, Header):
             metadata_closed = True
 
         yield result