Extended Meta Data Extension for Python-Markdown

[DevTwilight]

I wrote an extended version of the Python-Markdown Meta Data extension with a small improvement to multiline metadata handling.

Here is the extended version code:

  # Meta Data Extension for Python-Markdown
  # =======================================
  
  # This extension adds Meta Data handling to markdown.
  
  # See https://Python-Markdown.github.io/extensions/meta_data
  # for documentation.
  
  # Original code Copyright 2007-2008 [Waylan Limberg](https://github.com/waylan).
  # Modifications Copyright 2026 DevTwilight
  
  # --------------------------------------------------------------------
  # Modifications by DevTwilight:
  # - Added YAML-style list support (e.g. "- item" under keys)
  # - Added LIST_ITEM_RE regex for parsing indented list items
  # - Extended MetaPreprocessor to recognize list-style metadata values
  # - Improved meta parsing robustness for multiline structured input
  # --------------------------------------------------------------------
  
  # All changes Copyright 2008-2014 The Python Markdown Project
  
  # License: [BSD](https://opensource.org/licenses/bsd-license.php)
  
  """
  This extension adds Meta Data handling to markdown.
  
  See the [documentation](https://Python-Markdown.github.io/extensions/meta_data)
  for details.
  """
  
  from __future__ import annotations
  
  from markdown import Extension
  from markdown.preprocessors import Preprocessor
  import re
  import logging
  from typing import Any
  
  log = logging.getLogger('MARKDOWN')
  
  # Global Vars
  META_RE = re.compile(r'^[ ]{0,3}(?P<key>[A-Za-z0-9_-]+):\s*(?P<value>.*)')
  META_MORE_RE = re.compile(r'^[ ]{4,}(?P<value>.*)')
  LIST_ITEM_RE = re.compile(r'^[ ]{2,}-\s+(?P<value>.*)')  # NEW: YAML list support
  BEGIN_RE = re.compile(r'^-{3}(\s.*)?')
  END_RE = re.compile(r'^(-{3}|\.{3})(\s.*)?')
  
  
  class MetaExtension(Extension):
      """ Meta-Data extension for Python-Markdown. """
  
      def extendMarkdown(self, md):
          """ Add `MetaPreprocessor` to Markdown instance. """
          md.registerExtension(self)
          self.md = md
          md.preprocessors.register(MetaPreprocessor(md), 'meta', 27)
  
      def reset(self) -> None:
          self.md.Meta = {}
  
  
  class MetaPreprocessor(Preprocessor):
      """ Get Meta-Data. """
  
      def run(self, lines: list[str]) -> list[str]:
          """ Parse Meta-Data and store in Markdown.Meta. """
          meta: dict[str, Any] = {}
          key = None
  
          if lines and BEGIN_RE.match(lines[0]):
              lines.pop(0)
  
          while lines:
              line = lines.pop(0)
  
              # Stop conditions
              if line.strip() == '' or END_RE.match(line):
                  break
  
              m1 = META_RE.match(line)
  
              # Standard key: value
              if m1:
                  key = m1.group('key').lower().strip()
                  value = m1.group('value').strip()
  
                  meta[key] = [value] if key not in meta else meta[key]
                  continue
  
              # NEW: YAML-style list items
              m3 = LIST_ITEM_RE.match(line)
              if m3 and key:
                  value = m3.group('value').strip()
                  meta.setdefault(key, []).append(value)
                  continue
  
              # Multiline continuation
              m2 = META_MORE_RE.match(line)
              if m2 and key:
                  meta[key].append(m2.group('value').strip())
                  continue
  
              # Not meta → stop parsing
              lines.insert(0, line)
              break
  
          self.md.Meta = meta
          return lines
  
  
  def makeExtension(**kwargs):  # pragma: no cover
      return MetaExtension(**kwargs)

AI Disclosure

This code was prepared with assistance from an AI language model.

Could it be integrated in the library?
so that multi line yaml list support could be achieved