Merge pull request #509 from Crozzers/fix-issue-508

Fix HTML elements not unhashing correctly (issue 508)

CHANGES.md

@@ -6,6 +6,7 @@
 - [pull #501] Fix link patterns extra matching against internal hashes
 - [pull #502] Replace deprecated `optparse` with `argparse`
 - [pull #506] Fix `_uniform_outdent` failing with empty strings (issue #505)
+- [pull #509] Fix HTML elements not unhashing correctly (issue 508)
 
 
 ## python-markdown2 2.4.8

lib/markdown2.py

@@ -890,7 +890,7 @@ def _strict_tag_block_sub(self, text, html_tags_re, callback):
                     tag_count -= 1
                 else:
                     # if close tag is in same line
-                    if '</%s>' % is_markup.group(2) in chunk[is_markup.end():]:
+                    if self._tag_is_closed(is_markup.group(2), chunk):
                         # we must ignore these
                         is_markup = None
                     else:
@@ -908,6 +908,10 @@ def _strict_tag_block_sub(self, text, html_tags_re, callback):
 
         return result
 
+    def _tag_is_closed(self, tag_name, text):
+        # super basic check if number of open tags == number of closing tags
+        return len(re.findall('<%s(?:.*?)>' % tag_name, text)) == len(re.findall('</%s>' % tag_name, text))
+
     def _strip_link_definitions(self, text):
         # Strips link definitions from text, stores the URLs and titles in
         # hash references.

test/tm-cases/hash_html_blocks_issue_508.html

@@ -0,0 +1,12 @@
+<div><div></div>
+</div>
+
+<div></div>
+
+<div></div>
+
+<div></div>
+
+<ul>
+<li>A</li>
+</ul>

test/tm-cases/hash_html_blocks_issue_508.text

@@ -0,0 +1,7 @@
+<div><div></div>
+</div>
+<div></div>
+<div></div>
+<div></div>
+
+- A