[Python-3000-checkins] r56587 - in python/branches/py3k-struni/Lib: io.py test/test_minidom.py xml/dom/minidom.py

[guido.van.rossum]

Author: guido.van.rossum
Date: Fri Jul 27 20:03:11 2007
New Revision: 56587

Modified:
   python/branches/py3k-struni/Lib/io.py
   python/branches/py3k-struni/Lib/test/test_minidom.py
   python/branches/py3k-struni/Lib/xml/dom/minidom.py
Log:
Fix the minidom test.
In order to do this, I added an optional encoding argument to io.StringIO.
The toprettyxml() function returns bytes when you specify an encoding now.


Modified: python/branches/py3k-struni/Lib/io.py
==============================================================================
--- python/branches/py3k-struni/Lib/io.py	(original)
+++ python/branches/py3k-struni/Lib/io.py	Fri Jul 27 20:03:11 2007
@@ -1262,11 +1262,13 @@
 
     # XXX This is really slow, but fully functional
 
-    def __init__(self, initial_value=""):
-        super(StringIO, self).__init__(BytesIO(), "utf-8")
+    def __init__(self, initial_value="", encoding="utf-8", newline=None):
+        super(StringIO, self).__init__(BytesIO(),
+                                       encoding=encoding,
+                                       newline=newline)
         if initial_value:
             self.write(initial_value)
             self.seek(0)
 
     def getvalue(self):
-        return self.buffer.getvalue().decode("utf-8")
+        return self.buffer.getvalue().decode(self._encoding)

Modified: python/branches/py3k-struni/Lib/test/test_minidom.py
==============================================================================
--- python/branches/py3k-struni/Lib/test/test_minidom.py	(original)
+++ python/branches/py3k-struni/Lib/test/test_minidom.py	Fri Jul 27 20:03:11 2007
@@ -869,17 +869,17 @@
 
     def testEncodings(self):
         doc = parseString('<foo>&#x20ac;</foo>')
-        self.confirm(doc.toxml() == '<?xml version="1.0" ?><foo>\u20ac</foo>'
-                and doc.toxml('utf-8') ==
-                '<?xml version="1.0" encoding="utf-8"?><foo>\xe2\x82\xac</foo>'
-                and doc.toxml('iso-8859-15') ==
-                '<?xml version="1.0" encoding="iso-8859-15"?><foo>\xa4</foo>',
-                "testEncodings - encoding EURO SIGN")
+        self.assertEqual(doc.toxml(),
+                         '<?xml version="1.0" ?><foo>\u20ac</foo>')
+        self.assertEqual(doc.toxml('utf-8'),
+            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>')
 
         # Verify that character decoding errors throw exceptions instead
         # of crashing
         self.assertRaises(UnicodeDecodeError, parseString,
-                '<fran\xe7ais>Comment \xe7a va ? Tr\xe8s bien ?</fran\xe7ais>')
+                b'<fran\xe7ais>Comment \xe7a va ? Tr\xe8s bien ?</fran\xe7ais>')
 
         doc.unlink()
 

Modified: python/branches/py3k-struni/Lib/xml/dom/minidom.py
==============================================================================
--- python/branches/py3k-struni/Lib/xml/dom/minidom.py	(original)
+++ python/branches/py3k-struni/Lib/xml/dom/minidom.py	Fri Jul 27 20:03:11 2007
@@ -14,6 +14,7 @@
  * SAX 2 namespaces
 """
 
+import io
 import xml.dom
 
 from xml.dom import EMPTY_NAMESPACE, EMPTY_PREFIX, XMLNS_NAMESPACE, domreg
@@ -44,20 +45,19 @@
     def toxml(self, encoding = None):
         return self.toprettyxml("", "", encoding)
 
-    def toprettyxml(self, indent="\t", newl="\n", encoding = None):
+    def toprettyxml(self, indent="\t", newl="\n", encoding=None):
         # indent = the indentation string to prepend, per level
         # newl = the newline string to append
-        writer = _get_StringIO()
-        if encoding is not None:
-            import codecs
-            # Can't use codecs.getwriter to preserve 2.0 compatibility
-            writer = codecs.lookup(encoding)[3](writer)
+        writer = io.StringIO(encoding=encoding)
         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)
-        return writer.getvalue()
+        if encoding is None:
+            return writer.getvalue()
+        else:
+            return writer.buffer.getvalue()
 
     def hasChildNodes(self):
         if self.childNodes:
@@ -360,7 +360,7 @@
 
     def _get_localName(self):
         if 'localName' in self.__dict__:
-          return self.__dict__['localName']
+            return self.__dict__['localName']
         return self.nodeName.split(":", 1)[-1]
 
     def _get_name(self):
@@ -665,7 +665,7 @@
 
     def _get_localName(self):
         if 'localName' in self.__dict__:
-          return self.__dict__['localName']
+            return self.__dict__['localName']
         return self.tagName.split(":", 1)[-1]
 
     def _get_tagName(self):
@@ -1897,11 +1897,6 @@
         return (None, fields[0])
 
 
-def _get_StringIO():
-    # we can't use cStringIO since it doesn't support Unicode strings
-    from StringIO import StringIO
-    return StringIO()
-
 def _do_pulldom_parse(func, args, kwargs):
     events = func(*args, **kwargs)
     toktype, rootNode = events.getEvent()