Fix hashing nested HTML blocks

lib/markdown2.py

@@ -741,7 +741,11 @@ def _detab(self, text):
     _html_markdown_attr_re = re.compile(
         r'''\s+markdown=("1"|'1')''')
     def _hash_html_block_sub(self, match, raw=False):
-        html = match.group(1)
+        if isinstance(match, str):
+            html = match
+        else:
+            html = match.group(1)
+
         if raw and self.safe_mode:
             html = self._sanitize_html(html)
         elif 'markdown-in-html' in self.extras and 'markdown=' in html:
@@ -792,7 +796,7 @@ def _hash_html_blocks(self, text, raw=False):
         # the inner nested divs must be indented.
         # We need to do this before the next, more liberal match, because the next
         # match will start at the first `<div>` and stop at the first `</div>`.
-        text = self._strict_tag_block_re.sub(hash_html_block_sub, text)
+        text = self._strict_tag_block_sub(text, self._block_tags_a, hash_html_block_sub)
 
         # Now match more liberally, simply from `\n<tag>` to `</tag>\n`
         text = self._liberal_tag_block_re.sub(hash_html_block_sub, text)
@@ -871,6 +875,39 @@ def _hash_html_blocks(self, text, raw=False):
 
         return text
 
+    def _strict_tag_block_sub(self, text, html_tags_re, callback):
+        tag_count = 0
+        current_tag = html_tags_re
+        block = ''
+        result = ''
+
+        for chunk in text.splitlines(True):
+            is_markup = re.match(r'^(?:</code>(?=</pre>))?(</?(%s)\b>?)' % current_tag, chunk)
+            block += chunk
+
+            if is_markup:
+                if chunk.startswith('</'):
+                    tag_count -= 1
+                else:
+                    # if close tag is in same line
+                    if '</%s>' % is_markup.group(2) in chunk[is_markup.end():]:
+                        # we must ignore these
+                        is_markup = None
+                    else:
+                        tag_count += 1
+                        current_tag = is_markup.group(2)
+
+            if tag_count == 0:
+                if is_markup:
+                    block = callback(block.rstrip('\n'))  # remove trailing newline
+                current_tag = html_tags_re
+                result += block
+                block = ''
+
+        result += block
+
+        return result
+
     def _strip_link_definitions(self, text):
         # Strips link definitions from text, stores the URLs and titles in
         # hash references.

test/tm-cases/hash_nested_html_blocks.html

@@ -0,0 +1,7 @@
+<div class="enclosing">
+<div class="codehilite">
+<pre><span></span><code><span class="n">x</span> <span class="o">=</span> <span class="mi">1</span>
+</code></pre>
+</div>
+
+</div>

test/tm-cases/hash_nested_html_blocks.opts

@@ -0,0 +1 @@
+{"extras": ["fenced-code-blocks", "pygments"]}

test/tm-cases/hash_nested_html_blocks.tags

@@ -0,0 +1 @@
+extra fenced-code-blocks pygments

test/tm-cases/hash_nested_html_blocks.text

@@ -0,0 +1,5 @@
+<div class="enclosing">
+```python
+x = 1
+```
+</div>

test/tm-cases/sublist-para.html

@@ -11,7 +11,7 @@
 <li>Add Komodo chrome (XUL, JavaScript, CSS, DTDs).</li>
 </ul>
 
-<p><p>What this means is that work on and add significant functionality...</p></li>
+<p>What this means is that work on and add significant functionality...</p></li>
 <li><p>Komodo uses the same extension mechanisms as Firefox...</p></li>
 <li><p>Komodo builds and runs on Windows, Linux and ...</p></li>
-</ul></p>
+</ul>