From 703ee4a184e491be056ae5c4c7549e004be12622 Mon Sep 17 00:00:00 2001
From: Leonard Richardson <leonard.richardson@canonical.com>
Date: Fri, 20 Jan 2012 16:18:45 -0500
Subject: Made it easier to convert BS3 code to BS4.

---
 bs4/builder/_htmlparser.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'bs4/builder/_htmlparser.py')

diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py
index f9476cd..53374f0 100644
--- a/bs4/builder/_htmlparser.py
+++ b/bs4/builder/_htmlparser.py
@@ -65,7 +65,13 @@ class HTMLParserTreeBuilder(HTMLParser, HTMLTreeBuilder):
         self.soup.handle_data(data)
 
     def handle_charref(self, name):
-        self.handle_data(unichr(int(name)))
+        # XXX workaround for a bug in HTMLParser. Remove this once
+        # it's fixed.
+        if name.startswith('x'):
+            data = unichr(int(name.lstrip('x'), 16))
+        else:
+            data = unichr(int(name))
+        self.handle_data(data)
 
     def handle_entityref(self, name):
         character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
-- 
cgit v1.2.3