Allow boolean attribute syntax in markdown-in-html

.github/workflows/python.yaml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
         os:
           - ubuntu-latest
           - macos-latest

CHANGES.md

@@ -6,6 +6,7 @@
 - [pull #692] Fix XSS from code spans in link titles (#691)
 - [pull #695] Fix XSS issue from incomplete tags with no attributes (#694)
 - [pull #700] Fix XSS from code spans in image alt text (#699)
+- [pull #701] Allow boolean attribute syntax in `markdown-in-html` extra
 
 
 ## python-markdown2 2.5.5

lib/markdown2.py

@@ -67,8 +67,9 @@
 * link-shortrefs: allow shortcut reference links, not followed by `[]` or
   a link label.
 * markdown-file-links: Replace links to `.md` files with `.html` links
-* markdown-in-html: Allow the use of `markdown="1"` in a block HTML tag to
-  have markdown processing be done on its contents. Similar to
+* markdown-in-html: Allow the use of `markdown="1"` or simply a `markdown` boolean
+  attribute in a block HTML tag to have markdown processing be done on its
+  contents. Similar to
   <http://michelf.com/projects/php-markdown/extra/#markdown-attr> but with
   some limitations.
 * metadata: Extract metadata from a leading '---'-fenced block.
@@ -903,7 +904,8 @@ def _detab(self, text: str) -> str:
         re.X | re.M)
 
     _html_markdown_attr_re = re.compile(
-        r'''\s+markdown=("1"|'1')''')
+        # markdown attr, with optional assignment to true, must be followed by whitespace/boundary/closing tag chars
+        r'''\s+markdown(?:="1"|='1'|=1)?(?![^\s/>\b])''')
     def _hash_html_block_sub(
         self,
         match: Union[re.Match[str], str],
@@ -927,20 +929,20 @@ def _hash_html_block_sub(
 
         if raw and self.safe_mode:
             html = self._sanitize_html(html)
-        elif 'markdown-in-html' in self.extras and 'markdown=' in html:
+        elif 'markdown-in-html' in self.extras and 'markdown' in html:
             first_line = html.split('\n', 1)[0]
             m = self._html_markdown_attr_re.search(first_line)
             if m:
                 lines = html.split('\n')
                 # if MD is on same line as opening tag then split across two lines
-                lines = list(filter(None, (re.split(r'(.*?<%s.*markdown=.*?>)' % tag, lines[0])))) + lines[1:]
+                lines = list(filter(None, (re.split(r'(.*?<%s.*markdown.*?>)' % tag, lines[0])))) + lines[1:]
                 # if MD on same line as closing tag, split across two lines
                 lines = lines[:-1] + list(filter(None, re.split(r'(\s*?</%s>.*?$)' % tag, lines[-1])))
                 # extract key sections of the match
                 first_line = lines[0]
                 middle = '\n'.join(lines[1:-1])
                 last_line = lines[-1]
-                # remove `markdown="1"` attr from tag
+                # remove `markdown="1"` or `markdown` attr from tag
                 first_line = first_line[:m.start()] + first_line[m.end():]
                 # hash the HTML segments to protect them
                 f_key = _hash_text(first_line)

test/tm-cases/markdown_in_html.html

@@ -46,3 +46,21 @@ <h1 id="veggies">Veggies</h1>
 <td markdown="1">This is *true* markdown text.</td>
 </tr>
 </table>
+
+<h2 id="also-allowed">Also allowed</h2>
+
+<div>
+
+<p>Markdown attr <em>without</em> a truthy assignment, for your convenience</p>
+
+</div>
+
+<div class="abcdef">
+
+<p>Mix it with other attrs, <em>why don't you?</em></p>
+
+</div>
+
+<div my_markdown_attr>
+The check is smarter than `if 'markdown' in text`. This is invalid
+</div>

test/tm-cases/markdown_in_html.text

@@ -17,7 +17,7 @@ And a paragraph
 And **this**.
 </div>
 
-<section markdown="1">
+<section markdown='1'>
 And even **this** in an HTML5 block tag.
 </section>
 
@@ -33,3 +33,18 @@ And even **this** in an HTML5 block tag.
 <td markdown="1">This is *true* markdown text.</td>
 </tr>
 </table>
+
+
+## Also allowed
+
+<div markdown>
+Markdown attr *without* a truthy assignment, for your convenience
+</div>
+
+<div markdown class="abcdef">
+Mix it with other attrs, _why don't you?_
+</div>
+
+<div my_markdown_attr>
+The check is smarter than `if 'markdown' in text`. This is invalid
+</div>

test/tm-cases/markdown_in_html.toc_html

@@ -3,5 +3,8 @@
   <ul>
     <li><a href="#this-too">This <strong>too</strong>.</a></li>
   </ul></li>
-  <li><a href="#veggies">Veggies</a></li>
+  <li><a href="#veggies">Veggies</a>
+  <ul>
+    <li><a href="#also-allowed">Also allowed</a></li>
+  </ul></li>
 </ul>