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 0261c6a73e5053181d82628fac2518a78779fc53..502c962d8e0d427884b7a9ea7fd8659b45bc9b30 100644 (file)
--- a/Lib/test/test_sax.py
+++ b/Lib/test/test_sax.py
@@ -319,6 +319,24 @@ class XmlgenTest:
 
         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 0798ecd70d10508d54a03a72eb0be7edd6d8ccfb..74de9b07fc11b57092afc3b6de9bf45b5c99d58d 100644 (file)
--- a/Lib/xml/sax/saxutils.py
+++ b/Lib/xml/sax/saxutils.py
@@ -209,11 +209,15 @@ class XMLGenerator(handler.ContentHandler):
     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):

diff --git a/Misc/ACKS b/Misc/ACKS
index 47b354d16c9b48193f3e73e05af63b43192b7834..1b4940e3337611663e6900712073c44b62fd2af7 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -1254,6 +1254,7 @@ Kyle VanderBeek
 Andrew Vant
 Atul Varma
 Dmitry Vasiliev
+Sebastian Ortiz Vasquez
 Alexandre Vassalotti
 Nadeem Vawda
 Frank Vercruesse

diff --git a/Misc/NEWS b/Misc/NEWS
index 0d7700f6324e6dfc8d282cd69f299d585fa07274..af14f93d416e538f486977507f3e56417d7bbf2b 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -49,6 +49,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #17606: Fixed support of encoded byte strings in the XMLGenerator
+ .characters() and ignorableWhitespace() methods.  Original patch by Sebastian
+  Ortiz Vasquez.
+
 - Issue #17732: Ignore distutils.cfg options pertaining to install paths if a
   virtual environment is active.