Issue #15296: Fix minidom.toxml/toprettyxml for non-unicode encodings. Patch by Serhiy Storchaka, with some minor style adjustments by me.

eliben · eliben · commit 8a80502d2c80 · 2012-07-13T09:52:39.000+03:00
diff --git a/Doc/library/xml.dom.minidom.rst b/Doc/library/xml.dom.minidom.rst
@@ -147,12 +147,7 @@ module documentation.  This section lists the differences between the API and
    the DOM node.
 
    With an explicit *encoding* [1]_ argument, the result is a byte
-   string in the specified encoding.  It is recommended that you
-   always specify an encoding; you may use any encoding you like, but
-   an argument of "utf-8" is the most common choice, avoiding
-   :exc:`UnicodeError` exceptions in case of unrepresentable text
-   data.
-
+   string in the specified encoding.
    With no *encoding* argument, the result is a Unicode string, and the
    XML declaration in the resulting string does not specify an
    encoding. Encoding this string in an encoding other than UTF-8 is
diff --git a/Lib/test/test_minidom.py b/Lib/test/test_minidom.py
@@ -1067,6 +1067,11 @@ def testEncodings(self):
             b'<?xml version="1.0" encoding="utf-8"?><foo>\xe2\x82\xac</foo>')
         self.assertEqual(doc.toxml('iso-8859-15'),
             b'<?xml version="1.0" encoding="iso-8859-15"?><foo>\xa4</foo>')
+        self.assertEqual(doc.toxml('us-ascii'),
+            b'<?xml version="1.0" encoding="us-ascii"?><foo>&#8364;</foo>')
+        self.assertEqual(doc.toxml('utf-16'),
+            '<?xml version="1.0" encoding="utf-16"?>'
+            '<foo>\u20ac</foo>'.encode('utf-16'))
 
         # Verify that character decoding errors throw exceptions instead
         # of crashing
diff --git a/Lib/xml/dom/minidom.py b/Lib/xml/dom/minidom.py
@@ -14,7 +14,6 @@
  * SAX 2 namespaces
 """
 
-import codecs
 import io
 import xml.dom
 
@@ -47,19 +46,22 @@ def toxml(self, encoding=None):
         return self.toprettyxml("", "", encoding)
 
     def toprettyxml(self, indent="\t", newl="\n", encoding=None):
-        # indent = the indentation string to prepend, per level
-        # newl = the newline string to append
-        use_encoding = "utf-8" if encoding is None else encoding
-        writer = codecs.getwriter(use_encoding)(io.BytesIO())
+        if encoding is None:
+            writer = io.StringIO()
+        else:
+            writer = io.TextIOWrapper(io.BytesIO(),
+                                      encoding=encoding,
+                                      errors="xmlcharrefreplace",
+                                      newline='\n')
         if self.nodeType == Node.DOCUMENT_NODE:
             # Can pass encoding only to document, to put it into XML header
             self.writexml(writer, "", indent, newl, encoding)
         else:
             self.writexml(writer, "", indent, newl)
         if encoding is None:
-            return writer.stream.getvalue().decode(use_encoding)
+            return writer.getvalue()
         else:
-            return writer.stream.getvalue()
+            return writer.detach().getvalue()
 
     def hasChildNodes(self):
         return bool(self.childNodes)
@@ -1788,12 +1790,12 @@ def importNode(self, node, deep):
             raise xml.dom.NotSupportedErr("cannot import document type nodes")
         return _clone_node(node, deep, self)
 
-    def writexml(self, writer, indent="", addindent="", newl="",
-                 encoding = None):
+    def writexml(self, writer, indent="", addindent="", newl="", encoding=None):
         if encoding is None:
             writer.write('<?xml version="1.0" ?>'+newl)
         else:
-            writer.write('<?xml version="1.0" encoding="%s"?>%s' % (encoding, newl))
+            writer.write('<?xml version="1.0" encoding="%s"?>%s' % (
+                encoding, newl))
         for node in self.childNodes:
             node.writexml(writer, indent, addindent, newl)
 
