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'!\s*([\w-]+)\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_comment(text):
-    match = METADATA_REGEXP.match(text)
-    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))
 
 
 def _parse_instruction(text):
     match = INCLUDE_REGEXP.match(text)
     if not match:
@@ skipping 85 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`).
 
     Raises
     ------
     ParseError
         ParseError: If the line can't be parsed.
     """
     if isinstance(line_text, type(b'')):
         line_text = line_text.decode('utf-8')
 
     content = line_text.strip()
 
     if content == '':
         line = EmptyLine()
     elif content.startswith('!'):
-        line = _parse_comment(content)
+        line = Comment(content[1:].lstrip())
     elif content.startswith('%') and content.endswith('%'):
         line = _parse_instruction(content)
     elif content.startswith('[') and content.endswith(']'):
         line = _parse_header(content)
     else:
         line = parse_filter(content)
 
     assert line.to_string().replace(' ', '') == content.replace(' ', '')
     return line
 
@@ skipping 12 matching lines @@
         Parsed lines of the filter list.
 
     Raises
     ------
     ParseError
         Thrown during iteration for invalid filter list lines.
     TypeError
         If `lines` is not iterable.
 
     """
+    metadata_closed = False
+
     for line in lines:
-        yield parse_line(line)
+        result = parse_line(line)
+
+        if isinstance(result, 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
+
+            if not result.text:
+                metadata_closed = True
+        elif isinstance(result, (EmptyLine, Filter)):

[Vasily Kuznetsov, 2018/09/04 19:50:56]

I just thought that since this could also be used to parse fragments of filter
lists, we should probably also close metadata on an include. Does this make
sense?

[Sebastian Noack, 2018/09/04 20:23:32]

Done.

+            metadata_closed = True
+
+        yield result