Merge pull request #711 from gaoflow/fix/header-ids-html-entity-decode

fix: decode HTML entities before slugifying header IDs

Author: nicholasserra

lib/markdown2.py

@@ -116,6 +116,7 @@
 __author__ = "Trent Mick"
 
 import argparse
+import html
 import logging
 import re
 import sys
@@ -1578,7 +1579,7 @@ def header_id_from_text(self,
             None to not have an id attribute and to exclude this header from
             the TOC (if the "toc" extra is specified).
         """
-        header_id = _slugify(text)
+        header_id = _slugify(html.unescape(text))
         if prefix and isinstance(prefix, str):
             header_id = prefix + '-' + header_id
 

test/tm-cases/header_ids_entity.html

@@ -0,0 +1,5 @@
+<h1 id="escaped-lt">&lt;escaped-lt</h1>
+
+<h1 id="rd-notes">R&amp;D Notes</h1>
+
+<h1 id="normal-header">Normal Header</h1>

test/tm-cases/header_ids_entity.opts

@@ -0,0 +1 @@
+{"extras": ["header-ids"]}

test/tm-cases/header_ids_entity.text

@@ -0,0 +1,5 @@
+# <escaped-lt
+
+# R&D Notes
+
+# Normal Header