Issue #17606: Fixed support of encoded byte strings in the XMLGenerator
characters() and ignorableWhitespace() methods. Original patch by Sebastian
Ortiz Vasquez.
diff --git a/Lib/test/test_sax.py b/Lib/test/test_sax.py
index 3a20eac..86638a2 100644
--- a/Lib/test/test_sax.py
+++ b/Lib/test/test_sax.py
@@ -284,6 +284,26 @@
self.assertEqual(result.getvalue(), start + "<doc> </doc>")
+ def test_xmlgen_encoding_bytes(self):
+ encodings = ('iso-8859-15', 'utf-8',
+ 'utf-16be', 'utf-16le',
+ 'utf-32be', 'utf-32le')
+ for encoding in encodings:
+ result = self.ioclass()
+ gen = XMLGenerator(result, encoding=encoding)
+
+ gen.startDocument()
+ gen.startElement("doc", {"a": u'\u20ac'})
+ gen.characters(u"\u20ac".encode(encoding))
+ gen.ignorableWhitespace(" ".encode(encoding))
+ gen.endElement("doc")
+ gen.endDocument()
+
+ self.assertEqual(result.getvalue(), (
+ u'<?xml version="1.0" encoding="%s"?>\n'
+ u'<doc a="\u20ac">\u20ac </doc>' % encoding
+ ).encode(encoding, 'xmlcharrefreplace'))
+
def test_xmlgen_ns(self):
result = self.ioclass()
gen = XMLGenerator(result)