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 0261c6a..502c962 100644
--- a/Lib/test/test_sax.py
+++ b/Lib/test/test_sax.py
@@ -319,6 +319,24 @@
self.assertEqual(result.getvalue(), self.xml("<doc> </doc>"))
+ def test_xmlgen_encoding_bytes(self):
+ encodings = ('iso-8859-15', 'utf-8', 'utf-8-sig',
+ 'utf-16', 'utf-16be', 'utf-16le',
+ 'utf-32', 'utf-32be', 'utf-32le')
+ for encoding in encodings:
+ result = self.ioclass()
+ gen = XMLGenerator(result, encoding=encoding)
+
+ gen.startDocument()
+ gen.startElement("doc", {"a": '\u20ac'})
+ gen.characters("\u20ac".encode(encoding))
+ gen.ignorableWhitespace(" ".encode(encoding))
+ gen.endElement("doc")
+ gen.endDocument()
+
+ self.assertEqual(result.getvalue(),
+ self.xml('<doc a="\u20ac">\u20ac </doc>', encoding=encoding))
+
def test_xmlgen_ns(self):
result = self.ioclass()
gen = XMLGenerator(result)
diff --git a/Lib/xml/sax/saxutils.py b/Lib/xml/sax/saxutils.py
index 0798ecd..74de9b0 100644
--- a/Lib/xml/sax/saxutils.py
+++ b/Lib/xml/sax/saxutils.py
@@ -209,11 +209,15 @@
def characters(self, content):
if content:
self._finish_pending_start_element()
+ if not isinstance(content, str):
+ content = str(content, self._encoding)
self._write(escape(content))
def ignorableWhitespace(self, content):
if content:
self._finish_pending_start_element()
+ if not isinstance(content, str):
+ content = str(content, self._encoding)
self._write(content)
def processingInstruction(self, target, data):