HeaderID Ext now handles raw html in ids. Fixes #232

3 files changed, 32 insertions, 2 deletions

diff --git a/markdown/extensions/headerid.py b/markdown/extensions/headerid.py
index 7681b8d..8020d93 100644
--- a/markdown/extensions/headerid.py
+++ b/markdown/extensions/headerid.py
@@ -78,6 +78,7 @@ from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
 from ..treeprocessors import Treeprocessor
+from ..util import HTML_PLACEHOLDER_RE
 import re
 import logging
 import unicodedata
@@ -130,13 +131,27 @@ class HeaderIdTreeprocessor(Treeprocessor):
         start_level, force_id = self._get_meta()
         slugify = self.config['slugify']
         sep = self.config['separator']
+
+        def _html_sub(m):
+            """ Substitute raw html with plain text. """
+            try:
+                raw, safe = self.md.htmlStash.rawHtmlBlocks[int(m.group(1))]
+            except (IndexError, TypeError):
+                return m.group(0)
+            if self.md.safeMode and not safe:
+                return ''
+            # Strip out tags and entities - leaveing text
+            return re.sub(r'(<[^>]+>)|(&[\#a-zA-Z0-9]+;)', '', raw)
+
         for elem in doc.getiterator():
             if elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
                 if force_id:
                     if "id" in elem.attrib:
                         id = elem.get('id')
                     else:
-                        id = slugify(''.join(itertext(elem)), sep)
+                        id = HTML_PLACEHOLDER_RE.sub(_html_sub, 
+                                                     ''.join(itertext(elem)))
+                        id = slugify(id, sep)
                     elem.set('id', unique(id, self.IDs))
                 if start_level:
                     level = int(elem.tag[-1]) + start_level
diff --git a/markdown/util.py b/markdown/util.py
index 1036197..7cb933a 100644
--- a/markdown/util.py
+++ b/markdown/util.py
@@ -38,6 +38,9 @@ INLINE_PLACEHOLDER_PREFIX = STX+"klzzwxh:"
 INLINE_PLACEHOLDER = INLINE_PLACEHOLDER_PREFIX + "%s" + ETX
 INLINE_PLACEHOLDER_RE = re.compile(INLINE_PLACEHOLDER % r'([0-9]{4})')
 AMP_SUBSTITUTE = STX+"amp"+ETX
+HTML_PLACEHOLDER = STX + "wzxhzdk:%s" + ETX
+HTML_PLACEHOLDER_RE = re.compile(HTML_PLACEHOLDER % r'([0-9]+)')
+
 
 """
 Constants you probably do not need to change
@@ -132,5 +135,5 @@ class HtmlStash(object):
         self.rawHtmlBlocks = []
 
     def get_placeholder(self, key):
-        return "%swzxhzdk:%d%s" % (STX, key, ETX)
+        return HTML_PLACEHOLDER % key
 
diff --git a/tests/test_extensions.py b/tests/test_extensions.py
index 4eb600b..add759a 100644
--- a/tests/test_extensions.py
+++ b/tests/test_extensions.py
@@ -236,6 +236,18 @@ class TestHeaderId(unittest.TestCase):
             '<h1 id="some-header-with-markup">Some <em>Header</em> with '
             '<a href="http://example.com">markup</a>.</h1>')
 
+    def testHtmlEntities(self):
+        """ Test HeaderIDs with HTML Entities. """
+        text = '# Foo &amp; bar'
+        self.assertEqual(self.md.convert(text),
+            '<h1 id="foo-bar">Foo &amp; bar</h1>')
+
+    def testRawHtml(self):
+        """ Test HeaderIDs with raw HTML. """
+        text = '# Foo <b>Bar</b> Baz.'
+        self.assertEqual(self.md.convert(text),
+            '<h1 id="foo-bar-baz">Foo <b>Bar</b> Baz.</h1>')
+
     def testNoAutoIds(self):
         """ Test HeaderIDs with no auto generated IDs. """