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

abp/filters/parser.py

Index: abp/filters/parser.py
===================================================================
--- a/abp/filters/parser.py
+++ b/abp/filters/parser.py
@@ -140,7 +140,7 @@
 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*:\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'^([^/*|@"!]*?)#([@?])?#(.+)$')
@@ -149,13 +149,6 @@
 )
 
 
-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:
@@ -284,7 +277,7 @@
     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(']'):
@@ -317,5 +310,32 @@
         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:
+                # 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.
+                #
+                # 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):
+            metadata_closed = True
+
+        yield result