fix for xml_escape called with unicode characters, string.translate want an unicode map...

__init__.py

@@ -95,6 +95,7 @@ TR_CONTROL_CHARS[ord('\f')] = '\n'
 TR_CONTROL_CHARS[ord('\v')] = '\n'
 ESC_CAR_TABLE = string.maketrans(''.join(CONTROL_CHARS),
                                  ''.join(TR_CONTROL_CHARS))
+ESC_UCAR_TABLE = unicode(ESC_CAR_TABLE, 'latin1')
 
 # XXX deprecate at some point (once less used :)
 #@obsolete('use xml_escape')
@@ -103,7 +104,10 @@ def html_escape(data):
 
 def xml_escape(data):
     """escapes XML forbidden characters in attributes and PCDATA"""
-    data = data.translate(ESC_CAR_TABLE)
+    if isinstance(data, unicode):
+        data = data.translate(ESC_UCAR_TABLE)
+    else:
+        data = data.translate(ESC_CAR_TABLE)
     return (data.replace('&','&amp;').replace('<','&lt;').replace('>','&gt;')
             .replace('"','&quot;').replace("'",'&#39;'))
 

test/unittest_utils.py

@@ -34,6 +34,16 @@ class HtmlEscapeTC(TestCase):
             if car in SPECIAL_CHARS:
                 continue
             yield self.assertEquals, xml_escape(car), ' '
+        yield self.assertEquals, xml_escape(u'é'), u'é'
+
+    def test_escape_special_chars_unicode(self):
+        for car, trcar in SPECIAL_CHARS.items():
+            yield self.assertEquals, xml_escape(unicode(car)), trcar
+        for carnum in xrange(32):
+            car = chr(carnum)
+            if car in SPECIAL_CHARS:
+                continue
+            yield self.assertEquals, xml_escape(unicode(car)), ' '
 
     def test_html_unescape(self):
         for data, expected in [('toto', 'toto'),