Merged revisions 78123 via svnmerge from

pitrou · pitrou · commit 54319287c9b3 · 2010-02-09T16:53:09.000Z
svn+ssh://pythondev@svn.python.org/python/branches/py3k ........ r78123 | antoine.pitrou | 2010-02-09 17:51:16 +0100 (mar., 09 févr. 2010) | 5 lines Issue #6233: ElementTree failed converting unicode characters to XML entities when they could't be represented in the requested output encoding. Patch by Jerry Chen. ........
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
@@ -210,6 +210,17 @@ def check_encoding(ET, encoding):
     """
     ET.XML("<?xml version='1.0' encoding='%s'?><xml />" % encoding)
 
+def check_issue6233():
+    """
+    >>> from xml.etree import ElementTree as ET
+
+    >>> e = ET.XML("<?xml version='1.0' encoding='utf-8'?><body>t\xe3g</body>")
+    >>> ET.tostring(e, 'ascii')
+    b"<?xml version='1.0' encoding='ascii'?>\\n<body>t&#227;g</body>"
+    >>> e = ET.XML("<?xml version='1.0' encoding='iso-8859-1'?><body>t\xe3g</body>".encode('iso-8859-1')) # create byte string with the right encoding
+    >>> ET.tostring(e, 'ascii')
+    b"<?xml version='1.0' encoding='ascii'?>\\n<body>t&#227;g</body>"
+    """
 
 #
 # xinclude tests (samples from appendix C of the xinclude specification)
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
@@ -662,9 +662,9 @@ def _write(self, file, node, encoding, namespaces):
         # write XML to file
         tag = node.tag
         if tag is Comment:
-            file.write(_encode("<!-- %s -->" % _escape_cdata(node.text), encoding))
+            file.write(b"<!-- " + _encode_cdata(node.text, encoding) + b" -->")
         elif tag is ProcessingInstruction:
-            file.write(_encode("<?%s?>" % _escape_cdata(node.text), encoding))
+            file.write(b"<?" + _encode_cdata(node.text, encoding) + b"?>")
         else:
             items = list(node.items())
             xmlns_items = [] # new namespaces in this scope
@@ -696,7 +696,7 @@ def _write(self, file, node, encoding, namespaces):
             if node.text or len(node):
                 file.write(_encode(">", encoding))
                 if node.text:
-                    file.write(_encode(_escape_cdata(node.text), encoding))
+                    file.write(_encode_cdata(node.text, encoding))
                 for n in node:
                     self._write(file, n, encoding, namespaces)
                 file.write(_encode("</" + tag + ">", encoding))
@@ -705,7 +705,7 @@ def _write(self, file, node, encoding, namespaces):
             for k, v in xmlns_items:
                 del namespaces[v]
         if node.tail:
-            file.write(_encode(_escape_cdata(node.tail), encoding))
+            file.write(_encode_cdata(node.tail, encoding))
 
 # --------------------------------------------------------------------
 # helpers
@@ -788,13 +788,16 @@ def escape_entities(m, map=_escape_map):
 # the following functions assume an ascii-compatible encoding
 # (or "utf-16")
 
-def _escape_cdata(text):
+def _encode_cdata(text, encoding):
     # escape character data
     try:
         text = text.replace("&", "&amp;")
         text = text.replace("<", "&lt;")
         text = text.replace(">", "&gt;")
-        return text
+        if encoding:
+            return text.encode(encoding, "xmlcharrefreplace")
+        else:
+            return text
     except (TypeError, AttributeError):
         _raise_serialization_error(text)
 
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -126,6 +126,7 @@ Greg Chapman
 Brad Chapman
 David Chaum
 Nicolas Chauvat
+Jerry Chen
 Michael Chermside
 Albert Chin-A-Young
 Adal Chiriliuc
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -79,6 +79,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #6233: ElementTree failed converting unicode characters to XML
+  entities when they could't be represented in the requested output
+  encoding.  Patch by Jerry Chen.
+
 - Issue #4772: Raise a ValueError when an unknown Bluetooth protocol is
   specified, rather than fall through to AF_PACKET (in the `socket` module).
   Also, raise ValueError rather than TypeError when an unknown TIPC address
