Issue 6877 - Only parse headers in the first line of the filter list

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*:\s*(.*)')
+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_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:
         raise ParseError('Unrecognized instruction', text)
     return Include(match.group(1))
 
 
 def _parse_option(option):
     if '=' in option:
         return option.split('=', 1)
@@ skipping 75 matching lines @@
         Parsed filter.
 
     """
     if '#' in text:
         match = HIDING_FILTER_REGEXP.search(text)
         if match:
             return _parse_hiding_filter(text, *match.groups())
     return _parse_blocking_filter(text)
 
 
+def _decode_if_bytes(s):
+    return s.decode('utf-8') if isinstance(s, type(b'')) else s
+   
+
 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.
+    Note that parse_line() doesn't handle headers and special comments,
+    hence never returns a Header() or Metadata() object. Adblock Plus only
+    considers headers and 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()
+    content = _decode_if_bytes(line_text).strip()
 
     if content == '':
         line = EmptyLine()
     elif content.startswith('!'):
         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
 
 
 def parse_filterlist(lines):
     """Parse filter list from an iterable.
 
@@ skipping 10 matching lines @@
     Raises
     ------
     ParseError
         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)
+    for i, line in enumerate(lines):
+        text = _decode_if_bytes(line)
 
-        if result.type == 'comment':
-            match = METADATA_REGEXP.match(result.text)
+        if i == 0:
+            match = HEADER_REGEXP.match(text)
             if match:
-                key, value = match.groups()
+                version = match.group(1)
+                if not version:
+                    raise ParseError('Malformed header', text)
 
-                # 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':
-                    result = Metadata(key, value)
+                yield Header(version)
+                continue
 
-        if result.type not in {'header', 'metadata'}:
-            metadata_closed = True
+        match = METADATA_REGEXP.match(text)
+        if match:
+            key, value = match.groups()
 
-        yield result
+            # 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
+
+        metadata_closed = True
+        yield parse_line(text)