[Python-checkins] cpython (2.7): Issue #17606: Fixed support of encoded byte strings in the XMLGenerator

[serhiy.storchaka]

http://hg.python.org/cpython/rev/a32a3b79f5e8
changeset:   83747:a32a3b79f5e8
branch:      2.7
parent:      83727:f420a9ea4f25
user:        Serhiy Storchaka <storchaka at gmail.com>
date:        Sun May 12 17:29:34 2013 +0300
summary:
  Issue #17606: Fixed support of encoded byte strings in the XMLGenerator
characters() and ignorableWhitespace() methods.  Original patch by Sebastian
Ortiz Vasquez.

files:
  Lib/test/test_sax.py    |  20 ++++++++++++++++++++
  Lib/xml/sax/saxutils.py |   8 ++++++--
  Misc/ACKS               |   1 +
  Misc/NEWS               |   4 ++++
  4 files changed, 31 insertions(+), 2 deletions(-)


diff --git a/Lib/test/test_sax.py b/Lib/test/test_sax.py
--- 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)
diff --git a/Lib/xml/sax/saxutils.py b/Lib/xml/sax/saxutils.py
--- a/Lib/xml/sax/saxutils.py
+++ b/Lib/xml/sax/saxutils.py
@@ -180,10 +180,14 @@
         self._write(u'</%s>' % self._qname(name))
 
     def characters(self, content):
-        self._write(escape(unicode(content)))
+        if not isinstance(content, unicode):
+            content = unicode(content, self._encoding)
+        self._write(escape(content))
 
     def ignorableWhitespace(self, content):
-        self._write(unicode(content))
+        if not isinstance(content, unicode):
+            content = unicode(content, self._encoding)
+        self._write(content)
 
     def processingInstruction(self, target, data):
         self._write(u'<?%s %s?>' % (target, data))
diff --git a/Misc/ACKS b/Misc/ACKS
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -1045,6 +1045,7 @@
 Kyle VanderBeek
 Atul Varma
 Dmitry Vasiliev
+Sebastian Ortiz Vasquez
 Alexandre Vassalotti
 Frank Vercruesse
 Mike Verdone
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -38,6 +38,10 @@
 Library
 -------
 
+- Issue #17606: Fixed support of encoded byte strings in the XMLGenerator
+ .characters() and ignorableWhitespace() methods.  Original patch by Sebastian
+  Ortiz Vasquez.
+
 - Issue #16601: Restarting iteration over tarfile no more continues from where
   it left off.  Patch by Michael Birtwell.
 

-- 
Repository URL: http://hg.python.org/cpython