Changeset 391 for python/trunk/Lib/xml/etree

Timestamp:

Mar 19, 2014, 11:31:01 PM (11 years ago)

Author:

dmik

Message:

python: Merge vendor 2.7.6 to trunk.

Location:

python/trunk

Files:

• . (modified) (1 prop)
• Lib/xml/etree/ElementInclude.py (modified) (5 diffs)
• Lib/xml/etree/ElementPath.py (modified) (5 diffs)
• Lib/xml/etree/ElementTree.py (modified) (57 diffs)
• Lib/xml/etree/__init__.py (modified) (3 diffs)

python/trunk/Lib/xml/etree/ElementInclude.py

@@ -1 +1 @@
 #
 # ElementTree
-# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
+# $Id: ElementInclude.py 3375 2008-02-13 08:05:08Z fredrik $
 #
 # limited xinclude support for element trees
@@ -17 +17 @@
 # The ElementTree toolkit is
 #
-# Copyright (c) 1999-2004 by Fredrik Lundh
+# Copyright (c) 1999-2008 by Fredrik Lundh
 #
 # By obtaining, using, and/or copying this software and/or its
@@ -43 +43 @@
 
 # Licensed to PSF under a Contributor Agreement.
-# See http://www.python.org/2.4/license for licensing details.
+# See http://www.python.org/psf/license for licensing details.
 
 ##
@@ -50 +50 @@
 
 import copy
-import ElementTree
+from . import ElementTree
 
 XINCLUDE = "{http://www.w3.org/2001/XInclude}"
@@ -126 +126 @@
                 if i:
                     node = elem[i-1]
-                    node.tail = (node.tail or "") + text
+                    node.tail = (node.tail or "") + text + (e.tail or "")
                 else:
                     elem.text = (elem.text or "") + text + (e.tail or "")

python/trunk/Lib/xml/etree/ElementPath.py

@@ -1 +1 @@
 #
 # ElementTree
-# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $
+# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
 #
 # limited xpath support for element trees
@@ -9 +9 @@
 # 2003-05-28 fl   added support for // etc
 # 2003-08-27 fl   fixed parsing of periods in element names
-#
-# Copyright (c) 2003-2004 by Fredrik Lundh.  All rights reserved.
+# 2007-09-10 fl   new selection engine
+# 2007-09-12 fl   fixed parent selector
+# 2007-09-13 fl   added iterfind; changed findall to return a list
+# 2007-11-30 fl   added namespaces support
+# 2009-10-30 fl   added child element value filter
+#
+# Copyright (c) 2003-2009 by Fredrik Lundh.  All rights reserved.
 #
 # fredrik@pythonware.com
@@ -18 +23 @@
 # The ElementTree toolkit is
 #
-# Copyright (c) 1999-2004 by Fredrik Lundh
+# Copyright (c) 1999-2009 by Fredrik Lundh
 #
 # By obtaining, using, and/or copying this software and/or its
@@ -44 +49 @@
 
 # Licensed to PSF under a Contributor Agreement.
-# See http://www.python.org/2.4/license for licensing details.
+# See http://www.python.org/psf/license for licensing details.
 
 ##
@@ -54 +59 @@
 import re
 
-xpath_tokenizer = re.compile(
-    "(::|\.\.|\(\)|[/.*:\[\]\(\)@=])|((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|\s+"
-    ).findall
-
-class xpath_descendant_or_self:
-    pass
-
-##
-# Wrapper for a compiled XPath.
-
-class Path:
-
-    ##
-    # Create an Path instance from an XPath expression.
-
-    def __init__(self, path):
-        tokens = xpath_tokenizer(path)
-        # the current version supports 'path/path'-style expressions only
-        self.path = []
-        self.tag = None
-        if tokens and tokens[0][0] == "/":
+xpath_tokenizer_re = re.compile(
+    "("
+    "'[^']*'|\"[^\"]*\"|"
+    "::|"
+    "//?|"
+    "\.\.|"
+    "\(\)|"
+    "[/.*:\[\]\(\)@=])|"
+    "((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
+    "\s+"
+    )
+
+def xpath_tokenizer(pattern, namespaces=None):
+    for token in xpath_tokenizer_re.findall(pattern):
+        tag = token[1]
+        if tag and tag[0] != "{" and ":" in tag:
+            try:
+                prefix, uri = tag.split(":", 1)
+                if not namespaces:
+                    raise KeyError
+                yield token[0], "{%s}%s" % (namespaces[prefix], uri)
+            except KeyError:
+                raise SyntaxError("prefix %r not found in prefix map" % prefix)
+        else:
+            yield token
+
+def get_parent_map(context):
+    parent_map = context.parent_map
+    if parent_map is None:
+        context.parent_map = parent_map = {}
+        for p in context.root.iter():
+            for e in p:
+                parent_map[e] = p
+    return parent_map
+
+def prepare_child(next, token):
+    tag = token[1]
+    def select(context, result):
+        for elem in result:
+            for e in elem:
+                if e.tag == tag:
+                    yield e
+    return select
+
+def prepare_star(next, token):
+    def select(context, result):
+        for elem in result:
+            for e in elem:
+                yield e
+    return select
+
+def prepare_self(next, token):
+    def select(context, result):
+        for elem in result:
+            yield elem
+    return select
+
+def prepare_descendant(next, token):
+    token = next()
+    if token[0] == "*":
+        tag = "*"
+    elif not token[0]:
+        tag = token[1]
+    else:
+        raise SyntaxError("invalid descendant")
+    def select(context, result):
+        for elem in result:
+            for e in elem.iter(tag):
+                if e is not elem:
+                    yield e
+    return select
+
+def prepare_parent(next, token):
+    def select(context, result):
+        # FIXME: raise error if .. is applied at toplevel?
+        parent_map = get_parent_map(context)
+        result_map = {}
+        for elem in result:
+            if elem in parent_map:
+                parent = parent_map[elem]
+                if parent not in result_map:
+                    result_map[parent] = None
+                    yield parent
+    return select
+
+def prepare_predicate(next, token):
+    # FIXME: replace with real parser!!! refs:
+    # http://effbot.org/zone/simple-iterator-parser.htm
+    # http://javascript.crockford.com/tdop/tdop.html
+    signature = []
+    predicate = []
+    while 1:
+        token = next()
+        if token[0] == "]":
+            break
+        if token[0] and token[0][:1] in "'\"":
+            token = "'", token[0][1:-1]
+        signature.append(token[0] or "-")
+        predicate.append(token[1])
+    signature = "".join(signature)
+    # use signature to determine predicate type
+    if signature == "@-":
+        # [@attribute] predicate
+        key = predicate[1]
+        def select(context, result):
+            for elem in result:
+                if elem.get(key) is not None:
+                    yield elem
+        return select
+    if signature == "@-='":
+        # [@attribute='value']
+        key = predicate[1]
+        value = predicate[-1]
+        def select(context, result):
+            for elem in result:
+                if elem.get(key) == value:
+                    yield elem
+        return select
+    if signature == "-" and not re.match("\d+$", predicate[0]):
+        # [tag]
+        tag = predicate[0]
+        def select(context, result):
+            for elem in result:
+                if elem.find(tag) is not None:
+                    yield elem
+        return select
+    if signature == "-='" and not re.match("\d+$", predicate[0]):
+        # [tag='value']
+        tag = predicate[0]
+        value = predicate[-1]
+        def select(context, result):
+            for elem in result:
+                for e in elem.findall(tag):
+                    if "".join(e.itertext()) == value:
+                        yield elem
+                        break
+        return select
+    if signature == "-" or signature == "-()" or signature == "-()-":
+        # [index] or [last()] or [last()-index]
+        if signature == "-":
+            index = int(predicate[0]) - 1
+        else:
+            if predicate[0] != "last":
+                raise SyntaxError("unsupported function")
+            if signature == "-()-":
+                try:
+                    index = int(predicate[2]) - 1
+                except ValueError:
+                    raise SyntaxError("unsupported expression")
+            else:
+                index = -1
+        def select(context, result):
+            parent_map = get_parent_map(context)
+            for elem in result:
+                try:
+                    parent = parent_map[elem]
+                    # FIXME: what if the selector is "*" ?
+                    elems = list(parent.findall(elem.tag))
+                    if elems[index] is elem:
+                        yield elem
+                except (IndexError, KeyError):
+                    pass
+        return select
+    raise SyntaxError("invalid predicate")
+
+ops = {
+    "": prepare_child,
+    "*": prepare_star,
+    ".": prepare_self,
+    "..": prepare_parent,
+    "//": prepare_descendant,
+    "[": prepare_predicate,
+    }
+
+_cache = {}
+
+class _SelectorContext:
+    parent_map = None
+    def __init__(self, root):
+        self.root = root
+
+# --------------------------------------------------------------------
+
+##
+# Generate all matching objects.
+
+def iterfind(elem, path, namespaces=None):
+    # compile selector pattern
+    if path[-1:] == "/":
+        path = path + "*" # implicit all (FIXME: keep this?)
+    try:
+        selector = _cache[path]
+    except KeyError:
+        if len(_cache) > 100:
+            _cache.clear()
+        if path[:1] == "/":
             raise SyntaxError("cannot use absolute path on element")
-        while tokens:
-            op, tag = tokens.pop(0)
-            if tag or op == "*":
-                self.path.append(tag or op)
-            elif op == ".":
-                pass
-            elif op == "/":
-                self.path.append(xpath_descendant_or_self())
-                continue
-            else:
-                raise SyntaxError("unsupported path syntax (%s)" % op)
-            if tokens:
-                op, tag = tokens.pop(0)
-                if op != "/":
-                    raise SyntaxError(
-                        "expected path separator (%s)" % (op or tag)
-                        )
-        if self.path and isinstance(self.path[-1], xpath_descendant_or_self):
-            raise SyntaxError("path cannot end with //")
-        if len(self.path) == 1 and isinstance(self.path[0], type("")):
-            self.tag = self.path[0]
-
-    ##
-    # Find first matching object.
-
-    def find(self, element):
-        tag = self.tag
-        if tag is None:
-            nodeset = self.findall(element)
-            if not nodeset:
-                return None
-            return nodeset[0]
-        for elem in element:
-            if elem.tag == tag:
-                return elem
-        return None
-
-    ##
-    # Find text for first matching object.
-
-    def findtext(self, element, default=None):
-        tag = self.tag
-        if tag is None:
-            nodeset = self.findall(element)
-            if not nodeset:
-                return default
-            return nodeset[0].text or ""
-        for elem in element:
-            if elem.tag == tag:
-                return elem.text or ""
-        return default
-
-    ##
-    # Find all matching objects.
-
-    def findall(self, element):
-        nodeset = [element]
-        index = 0
+        next = iter(xpath_tokenizer(path, namespaces)).next
+        token = next()
+        selector = []
         while 1:
             try:
-                path = self.path[index]
-                index = index + 1
-            except IndexError:
-                return nodeset
-            set = []
-            if isinstance(path, xpath_descendant_or_self):
-                try:
-                    tag = self.path[index]
-                    if not isinstance(tag, type("")):
-                        tag = None
-                    else:
-                        index = index + 1
-                except IndexError:
-                    tag = None # invalid path
-                for node in nodeset:
-                    new = list(node.getiterator(tag))
-                    if new and new[0] is node:
-                        set.extend(new[1:])
-                    else:
-                        set.extend(new)
-            else:
-                for node in nodeset:
-                    for node in node:
-                        if path == "*" or node.tag == path:
-                            set.append(node)
-            if not set:
-                return []
-            nodeset = set
-
-_cache = {}
-
-##
-# (Internal) Compile path.
-
-def _compile(path):
-    p = _cache.get(path)
-    if p is not None:
-        return p
-    p = Path(path)
-    if len(_cache) >= 100:
-        _cache.clear()
-    _cache[path] = p
-    return p
+                selector.append(ops[token[0]](next, token))
+            except StopIteration:
+                raise SyntaxError("invalid path")
+            try:
+                token = next()
+                if token[0] == "/":
+                    token = next()
+            except StopIteration:
+                break
+        _cache[path] = selector
+    # execute selector pattern
+    result = [elem]
+    context = _SelectorContext(elem)
+    for select in selector:
+        result = select(context, result)
+    return result
 
 ##
 # Find first matching object.
 
-def find(element, path):
-    return _compile(path).find(element)
+def find(elem, path, namespaces=None):
+    try:
+        return iterfind(elem, path, namespaces).next()
+    except StopIteration:
+        return None
+
+##
+# Find all matching objects.
+
+def findall(elem, path, namespaces=None):
+    return list(iterfind(elem, path, namespaces))
 
 ##
 # Find text for first matching object.
 
-def findtext(element, path, default=None):
-    return _compile(path).findtext(element, default)
-
-##
-# Find all matching objects.
-
-def findall(element, path):
-    return _compile(path).findall(element)
+def findtext(elem, path, default=None, namespaces=None):
+    try:
+        elem = iterfind(elem, path, namespaces).next()
+        return elem.text or ""
+    except StopIteration:
+        return default

python/trunk/Lib/xml/etree/ElementTree.py

@@ -1 +1 @@
 #
 # ElementTree
-# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $
-#
-# light-weight XML support for Python 1.5.2 and later.
-#
-# history:
-# 2001-10-20 fl   created (from various sources)
-# 2001-11-01 fl   return root from parse method
-# 2002-02-16 fl   sort attributes in lexical order
-# 2002-04-06 fl   TreeBuilder refactoring, added PythonDoc markup
-# 2002-05-01 fl   finished TreeBuilder refactoring
-# 2002-07-14 fl   added basic namespace support to ElementTree.write
-# 2002-07-25 fl   added QName attribute support
-# 2002-10-20 fl   fixed encoding in write
-# 2002-11-24 fl   changed default encoding to ascii; fixed attribute encoding
-# 2002-11-27 fl   accept file objects or file names for parse/write
-# 2002-12-04 fl   moved XMLTreeBuilder back to this module
-# 2003-01-11 fl   fixed entity encoding glitch for us-ascii
-# 2003-02-13 fl   added XML literal factory
-# 2003-02-21 fl   added ProcessingInstruction/PI factory
-# 2003-05-11 fl   added tostring/fromstring helpers
-# 2003-05-26 fl   added ElementPath support
-# 2003-07-05 fl   added makeelement factory method
-# 2003-07-28 fl   added more well-known namespace prefixes
-# 2003-08-15 fl   fixed typo in ElementTree.findtext (Thomas Dartsch)
-# 2003-09-04 fl   fall back on emulator if ElementPath is not installed
-# 2003-10-31 fl   markup updates
-# 2003-11-15 fl   fixed nested namespace bug
-# 2004-03-28 fl   added XMLID helper
-# 2004-06-02 fl   added default support to findtext
-# 2004-06-08 fl   fixed encoding of non-ascii element/attribute names
-# 2004-08-23 fl   take advantage of post-2.1 expat features
-# 2005-02-01 fl   added iterparse implementation
-# 2005-03-02 fl   fixed iterparse support for pre-2.2 versions
-#
-# Copyright (c) 1999-2005 by Fredrik Lundh.  All rights reserved.
+# $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $
+#
+# light-weight XML support for Python 2.3 and later.
+#
+# history (since 1.2.6):
+# 2005-11-12 fl   added tostringlist/fromstringlist helpers
+# 2006-07-05 fl   merged in selected changes from the 1.3 sandbox
+# 2006-07-05 fl   removed support for 2.1 and earlier
+# 2007-06-21 fl   added deprecation/future warnings
+# 2007-08-25 fl   added doctype hook, added parser version attribute etc
+# 2007-08-26 fl   added new serializer code (better namespace handling, etc)
+# 2007-08-27 fl   warn for broken /tag searches on tree level
+# 2007-09-02 fl   added html/text methods to serializer (experimental)
+# 2007-09-05 fl   added method argument to tostring/tostringlist
+# 2007-09-06 fl   improved error handling
+# 2007-09-13 fl   added itertext, iterfind; assorted cleanups
+# 2007-12-15 fl   added C14N hooks, copy method (experimental)
+#
+# Copyright (c) 1999-2008 by Fredrik Lundh.  All rights reserved.
 #
 # fredrik@pythonware.com
@@ -43 +27 @@
 # The ElementTree toolkit is
 #
-# Copyright (c) 1999-2005 by Fredrik Lundh
+# Copyright (c) 1999-2008 by Fredrik Lundh
 #
 # By obtaining, using, and/or copying this software and/or its
@@ -69 +53 @@
 
 # Licensed to PSF under a Contributor Agreement.
-# See http://www.python.org/2.4/license for licensing details.
+# See http://www.python.org/psf/license for licensing details.
 
 __all__ = [
@@ -76 +60 @@
     "dump",
     "Element", "ElementTree",
-    "fromstring",
+    "fromstring", "fromstringlist",
     "iselement", "iterparse",
-    "parse",
+    "parse", "ParseError",
     "PI", "ProcessingInstruction",
     "QName",
     "SubElement",
-    "tostring",
+    "tostring", "tostringlist",
     "TreeBuilder",
-    "VERSION", "XML",
+    "VERSION",
+    "XML",
     "XMLParser", "XMLTreeBuilder",
     ]
+
+VERSION = "1.3.0"
 
 ##
@@ -103 +90 @@
 # </ul>
 #
-# To create an element instance, use the {@link #Element} or {@link
-# #SubElement} factory functions.
+# To create an element instance, use the {@link #Element} constructor
+# or the {@link #SubElement} factory function.
 # <p>
 # The {@link #ElementTree} class can be used to wrap an element
@@ -110 +97 @@
 ##
 
-import string, sys, re
-
-class _SimpleElementPath:
+import sys
+import re
+import warnings
+
+
+class _SimpleElementPath(object):
     # emulate pre-1.2 find/findtext/findall behaviour
-    def find(self, element, tag):
+    def find(self, element, tag, namespaces=None):
         for elem in element:
             if elem.tag == tag:
                 return elem
         return None
-    def findtext(self, element, tag, default=None):
+    def findtext(self, element, tag, default=None, namespaces=None):
+        elem = self.find(element, tag)
+        if elem is None:
+            return default
+        return elem.text or ""
+    def iterfind(self, element, tag, namespaces=None):
+        if tag[:3] == ".//":
+            for elem in element.iter(tag[3:]):
+                yield elem
         for elem in element:
             if elem.tag == tag:
-                return elem.text or ""
-        return default
-    def findall(self, element, tag):
-        if tag[:3] == ".//":
-            return element.getiterator(tag[3:])
-        result = []
-        for elem in element:
-            if elem.tag == tag:
-                result.append(elem)
-        return result
+                yield elem
+    def findall(self, element, tag, namespaces=None):
+        return list(self.iterfind(element, tag, namespaces))
 
 try:
-    import ElementPath
+    from . import ElementPath
 except ImportError:
-    # FIXME: issue warning in this case?
     ElementPath = _SimpleElementPath()
 
-# TODO: add support for custom namespace resolvers/default namespaces
-# TODO: add improved support for incremental parsing
-
-VERSION = "1.2.6"
-
-##
-# Internal element class.  This class defines the Element interface,
-# and provides a reference implementation of this interface.
+##
+# Parser error.  This is a subclass of <b>SyntaxError</b>.
 # <p>
-# You should not create instances of this class directly.  Use the
-# appropriate factory functions instead, such as {@link #Element}
-# and {@link #SubElement}.
-#
+# In addition to the exception value, an exception instance contains a
+# specific exception code in the <b>code</b> attribute, and the line and
+# column of the error in the <b>position</b> attribute.
+
+class ParseError(SyntaxError):
+    pass
+
+# --------------------------------------------------------------------
+
+##
+# Checks if an object appears to be a valid element object.
+#
+# @param An element instance.
+# @return A true value if this is an element object.
+# @defreturn flag
+
+def iselement(element):
+    # FIXME: not sure about this; might be a better idea to look
+    # for tag/attrib/text attributes
+    return isinstance(element, Element) or hasattr(element, "tag")
+
+##
+# Element class.  This class defines the Element interface, and
+# provides a reference implementation of this interface.
+# <p>
+# The element name, attribute names, and attribute values can be
+# either ASCII strings (ordinary Python strings containing only 7-bit
+# ASCII characters) or Unicode strings.
+#
+# @param tag The element name.
+# @param attrib An optional dictionary, containing element attributes.
+# @param **extra Additional attributes, given as keyword arguments.
 # @see Element
 # @see SubElement
@@ -157 +169 @@
 # @see ProcessingInstruction
 
-class _ElementInterface:
+class Element(object):
     # <tag attrib>text<child/>...</tag>tail
 
@@ -167 +179 @@
     ##
     # (Attribute) Element attribute dictionary.  Where possible, use
-    # {@link #_ElementInterface.get},
-    # {@link #_ElementInterface.set},
-    # {@link #_ElementInterface.keys}, and
-    # {@link #_ElementInterface.items} to access
+    # {@link #Element.get},
+    # {@link #Element.set},
+    # {@link #Element.keys}, and
+    # {@link #Element.items} to access
     # element attributes.
 
@@ -177 +189 @@
     ##
     # (Attribute) Text before first subelement.  This is either a
-    # string or the value None, if there was no text.
+    # string or the value None.  Note that if there was no text, this
+    # attribute may be either None or an empty string, depending on
+    # the parser.
 
     text = None
@@ -184 +198 @@
     # (Attribute) Text after this element's end tag, but before the
     # next sibling element's start tag.  This is either a string or
-    # the value None, if there was no text.
+    # the value None.  Note that if there was no text, this attribute
+    # may be either None or an empty string, depending on the parser.
 
     tail = None # text after end tag, if any
 
-    def __init__(self, tag, attrib):
+    # constructor
+
+    def __init__(self, tag, attrib={}, **extra):
+        attrib = attrib.copy()
+        attrib.update(extra)
         self.tag = tag
         self.attrib = attrib
@@ -194 +213 @@
 
     def __repr__(self):
-        return "<Element %s at %x>" % (self.tag, id(self))
+        return "<Element %s at 0x%x>" % (repr(self.tag), id(self))
 
     ##
@@ -204 +223 @@
 
     def makeelement(self, tag, attrib):
-        return Element(tag, attrib)
-
-    ##
-    # Returns the number of subelements.
+        return self.__class__(tag, attrib)
+
+    ##
+    # (Experimental) Copies the current element.  This creates a
+    # shallow copy; subelements will be shared with the original tree.
+    #
+    # @return A new element instance.
+
+    def copy(self):
+        elem = self.makeelement(self.tag, self.attrib)
+        elem.text = self.text
+        elem.tail = self.tail
+        elem[:] = self
+        return elem
+
+    ##
+    # Returns the number of subelements.  Note that this only counts
+    # full elements; to check if there's any content in an element, you
+    # have to check both the length and the <b>text</b> attribute.
     #
     # @return The number of subelements.
@@ -214 +248 @@
         return len(self._children)
 
-    ##
-    # Returns the given subelement.
+    def __nonzero__(self):
+        warnings.warn(
+            "The behavior of this method will change in future versions.  "
+            "Use specific 'len(elem)' or 'elem is not None' test instead.",
+            FutureWarning, stacklevel=2
+            )
+        return len(self._children) != 0 # emulate old behaviour, for now
+
+    ##
+    # Returns the given subelement, by index.
     #
     # @param index What subelement to return.
@@ -225 +267 @@
 
     ##
-    # Replaces the given subelement.
+    # Replaces the given subelement, by index.
     #
     # @param index What subelement to replace.
     # @param element The new element value.
     # @exception IndexError If the given element does not exist.
-    # @exception AssertionError If element is not a valid object.
 
     def __setitem__(self, index, element):
-        assert iselement(element)
+        # if isinstance(index, slice):
+        #     for elt in element:
+        #         assert iselement(elt)
+        # else:
+        #     assert iselement(element)
         self._children[index] = element
 
     ##
-    # Deletes the given subelement.
+    # Deletes the given subelement, by index.
     #
     # @param index What subelement to delete.
@@ -246 +291 @@
 
     ##
-    # Returns a list containing subelements in the given range.
-    #
-    # @param start The first subelement to return.
-    # @param stop The first subelement that shouldn't be returned.
-    # @return A sequence object containing subelements.
-
-    def __getslice__(self, start, stop):
-        return self._children[start:stop]
-
-    ##
-    # Replaces a number of subelements with elements from a sequence.
-    #
-    # @param start The first subelement to replace.
-    # @param stop The first subelement that shouldn't be replaced.
+    # Adds a subelement to the end of this element.  In document order,
+    # the new element will appear after the last existing subelement (or
+    # directly after the text, if it's the first subelement), but before
+    # the end tag for this element.
+    #
+    # @param element The element to add.
+
+    def append(self, element):
+        # assert iselement(element)
+        self._children.append(element)
+
+    ##
+    # Appends subelements from a sequence.
+    #
     # @param elements A sequence object with zero or more elements.
-    # @exception AssertionError If a sequence member is not a valid object.
-
-    def __setslice__(self, start, stop, elements):
-        for element in elements:
-            assert iselement(element)
-        self._children[start:stop] = list(elements)
-
-    ##
-    # Deletes a number of subelements.
-    #
-    # @param start The first subelement to delete.
-    # @param stop The first subelement to leave in there.
-
-    def __delslice__(self, start, stop):
-        del self._children[start:stop]
-
-    ##
-    # Adds a subelement to the end of this element.
-    #
-    # @param element The element to add.
-    # @exception AssertionError If a sequence member is not a valid object.
-
-    def append(self, element):
-        assert iselement(element)
-        self._children.append(element)
+    # @since 1.3
+
+    def extend(self, elements):
+        # for element in elements:
+        #     assert iselement(element)
+        self._children.extend(elements)
 
     ##
@@ -291 +317 @@
     #
     # @param index Where to insert the new subelement.
-    # @exception AssertionError If the element is not a valid object.
 
     def insert(self, index, element):
-        assert iselement(element)
+        # assert iselement(element)
         self._children.insert(index, element)
 
@@ -300 +325 @@
     # Removes a matching subelement.  Unlike the <b>find</b> methods,
     # this method compares elements based on identity, not on tag
-    # value or contents.
+    # value or contents.  To remove subelements by other means, the
+    # easiest way is often to use a list comprehension to select what
+    # elements to keep, and use slice assignment to update the parent
+    # element.
     #
     # @param element What element to remove.
     # @exception ValueError If a matching element could not be found.
-    # @exception AssertionError If the element is not a valid object.
 
     def remove(self, element):
-        assert iselement(element)
+        # assert iselement(element)
         self._children.remove(element)
 
     ##
-    # Returns all subelements.  The elements are returned in document
-    # order.
+    # (Deprecated) Returns all subelements.  The elements are returned
+    # in document order.
     #
     # @return A list of subelements.
@@ -318 +345 @@
 
     def getchildren(self):
+        warnings.warn(
+            "This method will be removed in future versions.  "
+            "Use 'list(elem)' or iteration over elem instead.",
+            DeprecationWarning, stacklevel=2
+            )
         return self._children
 
@@ -324 +356 @@
     #
     # @param path What element to look for.
+    # @keyparam namespaces Optional namespace prefix map.
     # @return The first matching element, or None if no element was found.
     # @defreturn Element or None
 
-    def find(self, path):
-        return ElementPath.find(self, path)
+    def find(self, path, namespaces=None):
+        return ElementPath.find(self, path, namespaces)
 
     ##
@@ -335 +368 @@
     # @param path What element to look for.
     # @param default What to return if the element was not found.
+    # @keyparam namespaces Optional namespace prefix map.
     # @return The text content of the first matching element, or the
     #     default value no element was found.  Note that if the element
-    #     has is found, but has no text content, this method returns an
+    #     is found, but has no text content, this method returns an
     #     empty string.
     # @defreturn string
 
-    def findtext(self, path, default=None):
-        return ElementPath.findtext(self, path, default)
+    def findtext(self, path, default=None, namespaces=None):
+        return ElementPath.findtext(self, path, default, namespaces)
 
     ##
@@ -348 +382 @@
     #
     # @param path What element to look for.
-    # @return A list or iterator containing all matching elements,
+    # @keyparam namespaces Optional namespace prefix map.
+    # @return A list or other sequence containing all matching elements,
     #    in document order.
     # @defreturn list of Element instances
 
-    def findall(self, path):
-        return ElementPath.findall(self, path)
+    def findall(self, path, namespaces=None):
+        return ElementPath.findall(self, path, namespaces)
+
+    ##
+    # Finds all matching subelements, by tag name or path.
+    #
+    # @param path What element to look for.
+    # @keyparam namespaces Optional namespace prefix map.
+    # @return An iterator or sequence containing all matching elements,
+    #    in document order.
+    # @defreturn a generated sequence of Element instances
+
+    def iterfind(self, path, namespaces=None):
+        return ElementPath.iterfind(self, path, namespaces)
 
     ##
     # Resets an element.  This function removes all subelements, clears
-    # all attributes, and sets the text and tail attributes to None.
+    # all attributes, and sets the <b>text</b> and <b>tail</b> attributes
+    # to None.
 
     def clear(self):
@@ -365 +413 @@
 
     ##
-    # Gets an element attribute.
+    # Gets an element attribute.  Equivalent to <b>attrib.get</b>, but
+    # some implementations may handle this a bit more efficiently.
     #
     # @param key What attribute to look for.
@@ -377 +426 @@
 
     ##
-    # Sets an element attribute.
+    # Sets an element attribute.  Equivalent to <b>attrib[key] = value</b>,
+    # but some implementations may handle this a bit more efficiently.
     #
     # @param key What attribute to set.
@@ -388 +438 @@
     # Gets a list of attribute names.  The names are returned in an
     # arbitrary order (just like for an ordinary Python dictionary).
+    # Equivalent to <b>attrib.keys()</b>.
     #
     # @return A list of element attribute names.
@@ -397 +448 @@
     ##
     # Gets element attributes, as a sequence.  The attributes are
-    # returned in an arbitrary order.
+    # returned in an arbitrary order.  Equivalent to <b>attrib.items()</b>.
     #
     # @return A list of (name, value) tuples for all attributes.
@@ -410 +461 @@
     # with a matching tag.
     # <p>
-    # If the tree structure is modified during iteration, the result
-    # is undefined.
+    # If the tree structure is modified during iteration, new or removed
+    # elements may or may not be included.  To get a stable set, use the
+    # list() function on the iterator, and loop over the resulting list.
     #
     # @param tag What tags to look for (default is to return all elements).
-    # @return A list or iterator containing all the matching elements.
-    # @defreturn list or iterator
-
-    def getiterator(self, tag=None):
-        nodes = []
+    # @return An iterator containing all the matching elements.
+    # @defreturn iterator
+
+    def iter(self, tag=None):
         if tag == "*":
             tag = None
         if tag is None or self.tag == tag:
-            nodes.append(self)
-        for node in self._children:
-            nodes.extend(node.getiterator(tag))
-        return nodes
+            yield self
+        for e in self._children:
+            for e in e.iter(tag):
+                yield e
+
+    # compatibility
+    def getiterator(self, tag=None):
+        # Change for a DeprecationWarning in 1.4
+        warnings.warn(
+            "This method will be removed in future versions.  "
+            "Use 'elem.iter()' or 'list(elem.iter())' instead.",
+            PendingDeprecationWarning, stacklevel=2
+        )
+        return list(self.iter(tag))
+
+    ##
+    # Creates a text iterator.  The iterator loops over this element
+    # and all subelements, in document order, and returns all inner
+    # text.
+    #
+    # @return An iterator containing all inner text.
+    # @defreturn iterator
+
+    def itertext(self):
+        tag = self.tag
+        if not isinstance(tag, basestring) and tag is not None:
+            return
+        if self.text:
+            yield self.text
+        for e in self:
+            for s in e.itertext():
+                yield s
+            if e.tail:
+                yield e.tail
 
 # compatibility
-_Element = _ElementInterface
-
-##
-# Element factory.  This function returns an object implementing the
-# standard Element interface.  The exact class or type of that object
-# is implementation dependent, but it will always be compatible with
-# the {@link #_ElementInterface} class in this module.
-# <p>
-# The element name, attribute names, and attribute values can be
-# either 8-bit ASCII strings or Unicode strings.
-#
-# @param tag The element name.
-# @param attrib An optional dictionary, containing element attributes.
-# @param **extra Additional attributes, given as keyword arguments.
-# @return An element instance.
-# @defreturn Element
-
-def Element(tag, attrib={}, **extra):
-    attrib = attrib.copy()
-    attrib.update(extra)
-    return _ElementInterface(tag, attrib)
+_Element = _ElementInterface = Element
 
 ##
@@ -473 +534 @@
 ##
 # Comment element factory.  This factory function creates a special
-# element that will be serialized as an XML comment.
+# element that will be serialized as an XML comment by the standard
+# serializer.
 # <p>
 # The comment string can be either an 8-bit ASCII string or a Unicode
@@ -489 +551 @@
 ##
 # PI element factory.  This factory function creates a special element
-# that will be serialized as an XML processing instruction.
+# that will be serialized as an XML processing instruction by the standard
+# serializer.
 #
 # @param target A string containing the PI target.
@@ -515 +578 @@
 # @return An opaque object, representing the QName.
 
-class QName:
+class QName(object):
     def __init__(self, text_or_uri, tag=None):
         if tag:
@@ -529 +592 @@
         return cmp(self.text, other)
 
+# --------------------------------------------------------------------
+
 ##
 # ElementTree wrapper class.  This class represents an entire element
@@ -535 +600 @@
 #
 # @param element Optional root element.
-# @keyparam file Optional file handle or name.  If given, the
+# @keyparam file Optional file handle or file name.  If given, the
 #     tree is initialized with the contents of this XML file.
 
-class ElementTree:
+class ElementTree(object):
 
     def __init__(self, element=None, file=None):
-        assert element is None or iselement(element)
+        # assert element is None or iselement(element)
         self._root = element # first node
         if file:
@@ -563 +628 @@
 
     def _setroot(self, element):
-        assert iselement(element)
+        # assert iselement(element)
         self._root = element
 
@@ -569 +634 @@
     # Loads an external XML document into this element tree.
     #
-    # @param source A file name or file object.
-    # @param parser An optional parser instance.  If not given, the
-    #     standard {@link XMLTreeBuilder} parser is used.
+    # @param source A file name or file object.  If a file object is
+    #     given, it only has to implement a <b>read(n)</b> method.
+    # @keyparam parser An optional parser instance.  If not given, the
+    #     standard {@link XMLParser} parser is used.
     # @return The document root element.
     # @defreturn Element
+    # @exception ParseError If the parser fails to parse the document.
 
     def parse(self, source, parser=None):
+        close_source = False
         if not hasattr(source, "read"):
             source = open(source, "rb")
-        if not parser:
-            parser = XMLTreeBuilder()
-        while 1:
-            data = source.read(32768)
-            if not data:
-                break
-            parser.feed(data)
-        self._root = parser.close()
-        return self._root
+            close_source = True
+        try:
+            if not parser:
+                parser = XMLParser(target=TreeBuilder())
+            while 1:
+                data = source.read(65536)
+                if not data:
+                    break
+                parser.feed(data)
+            self._root = parser.close()
+            return self._root
+        finally:
+            if close_source:
+                source.close()
 
     ##
@@ -596 +669 @@
     # @defreturn iterator
 
+    def iter(self, tag=None):
+        # assert self._root is not None
+        return self._root.iter(tag)
+
+    # compatibility
     def getiterator(self, tag=None):
-        assert self._root is not None
-        return self._root.getiterator(tag)
-
-    ##
-    # Finds the first toplevel element with given tag.
-    # Same as getroot().find(path).
+        # Change for a DeprecationWarning in 1.4
+        warnings.warn(
+            "This method will be removed in future versions.  "
+            "Use 'tree.iter()' or 'list(tree.iter())' instead.",
+            PendingDeprecationWarning, stacklevel=2
+        )
+        return list(self.iter(tag))
+
+    ##
+    # Same as getroot().find(path), starting at the root of the
+    # tree.
     #
     # @param path What element to look for.
+    # @keyparam namespaces Optional namespace prefix map.
     # @return The first matching element, or None if no element was found.
     # @defreturn Element or None
 
-    def find(self, path):
-        assert self._root is not None
+    def find(self, path, namespaces=None):
+        # assert self._root is not None
         if path[:1] == "/":
             path = "." + path
-        return self._root.find(path)
-
-    ##
-    # Finds the element text for the first toplevel element with given
-    # tag.  Same as getroot().findtext(path).
-    #
-    # @param path What toplevel element to look for.
+            warnings.warn(
+                "This search is broken in 1.3 and earlier, and will be "
+                "fixed in a future version.  If you rely on the current "
+                "behaviour, change it to %r" % path,
+                FutureWarning, stacklevel=2
+                )
+        return self._root.find(path, namespaces)
+
+    ##
+    # Same as getroot().findtext(path), starting at the root of the tree.
+    #
+    # @param path What element to look for.
     # @param default What to return if the element was not found.
+    # @keyparam namespaces Optional namespace prefix map.
     # @return The text content of the first matching element, or the
     #     default value no element was found.  Note that if the element
-    #     has is found, but has no text content, this method returns an
+    #     is found, but has no text content, this method returns an
     #     empty string.
     # @defreturn string
 
-    def findtext(self, path, default=None):
-        assert self._root is not None
+    def findtext(self, path, default=None, namespaces=None):
+        # assert self._root is not None
         if path[:1] == "/":
             path = "." + path
-        return self._root.findtext(path, default)
-
-    ##
-    # Finds all toplevel elements with the given tag.
-    # Same as getroot().findall(path).
+            warnings.warn(
+                "This search is broken in 1.3 and earlier, and will be "
+                "fixed in a future version.  If you rely on the current "
+                "behaviour, change it to %r" % path,
+                FutureWarning, stacklevel=2
+                )
+        return self._root.findtext(path, default, namespaces)
+
+    ##
+    # Same as getroot().findall(path), starting at the root of the tree.
     #
     # @param path What element to look for.
+    # @keyparam namespaces Optional namespace prefix map.
     # @return A list or iterator containing all matching elements,
     #    in document order.
     # @defreturn list of Element instances
 
-    def findall(self, path):
-        assert self._root is not None
+    def findall(self, path, namespaces=None):
+        # assert self._root is not None
         if path[:1] == "/":
             path = "." + path
-        return self._root.findall(path)
+            warnings.warn(
+                "This search is broken in 1.3 and earlier, and will be "
+                "fixed in a future version.  If you rely on the current "
+                "behaviour, change it to %r" % path,
+                FutureWarning, stacklevel=2
+                )
+        return self._root.findall(path, namespaces)
+
+    ##
+    # Finds all matching subelements, by tag name or path.
+    # Same as getroot().iterfind(path).
+    #
+    # @param path What element to look for.
+    # @keyparam namespaces Optional namespace prefix map.
+    # @return An iterator or sequence containing all matching elements,
+    #    in document order.
+    # @defreturn a generated sequence of Element instances
+
+    def iterfind(self, path, namespaces=None):
+        # assert self._root is not None
+        if path[:1] == "/":
+            path = "." + path
+            warnings.warn(
+                "This search is broken in 1.3 and earlier, and will be "
+                "fixed in a future version.  If you rely on the current "
+                "behaviour, change it to %r" % path,
+                FutureWarning, stacklevel=2
+                )
+        return self._root.iterfind(path, namespaces)
 
     ##
     # Writes the element tree to a file, as XML.
     #
+    # @def write(file, **options)
     # @param file A file name, or a file object opened for writing.
-    # @param encoding Optional output encoding (default is US-ASCII).
-
-    def write(self, file, encoding="us-ascii"):
-        assert self._root is not None
-        if not hasattr(file, "write"):
-            file = open(file, "wb")
+    # @param **options Options, given as keyword arguments.
+    # @keyparam encoding Optional output encoding (default is US-ASCII).
+    # @keyparam xml_declaration Controls if an XML declaration should
+    #     be added to the file.  Use False for never, True for always,
+    #     None for only if not US-ASCII or UTF-8.  None is default.
+    # @keyparam default_namespace Sets the default XML namespace (for "xmlns").
+    # @keyparam method Optional output method ("xml", "html", "text" or
+    #     "c14n"; default is "xml").
+
+    def write(self, file_or_filename,
+              # keyword arguments
+              encoding=None,
+              xml_declaration=None,
+              default_namespace=None,
+              method=None):
+        # assert self._root is not None
+        if not method:
+            method = "xml"
+        elif method not in _serialize:
+            # FIXME: raise an ImportError for c14n if ElementC14N is missing?
+            raise ValueError("unknown method %r" % method)
+        if hasattr(file_or_filename, "write"):
+            file = file_or_filename
+        else:
+            file = open(file_or_filename, "wb")
+        write = file.write
         if not encoding:
-            encoding = "us-ascii"
-        elif encoding != "utf-8" and encoding != "us-ascii":
-            file.write("<?xml version='1.0' encoding='%s'?>\n" % encoding)
-        self._write(file, self._root, encoding, {})
-
-    def _write(self, file, node, encoding, namespaces):
-        # write XML to file
-        tag = node.tag
-        if tag is Comment:
-            file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
-        elif tag is ProcessingInstruction:
-            file.write("<?%s?>" % _escape_cdata(node.text, encoding))
+            if method == "c14n":
+                encoding = "utf-8"
+            else:
+                encoding = "us-ascii"
+        elif xml_declaration or (xml_declaration is None and
+                                 encoding not in ("utf-8", "us-ascii")):
+            if method == "xml":
+                write("<?xml version='1.0' encoding='%s'?>\n" % encoding)
+        if method == "text":
+            _serialize_text(write, self._root, encoding)
         else:
-            items = node.items()
-            xmlns_items = [] # new namespaces in this scope
-            try:
-                if isinstance(tag, QName) or tag[:1] == "{":
-                    tag, xmlns = fixtag(tag, namespaces)
-                    if xmlns: xmlns_items.append(xmlns)
-            except TypeError:
-                _raise_serialization_error(tag)
-            file.write("<" + _encode(tag, encoding))
-            if items or xmlns_items:
-                items.sort() # lexical order
-                for k, v in items:
-                    try:
-                        if isinstance(k, QName) or k[:1] == "{":
-                            k, xmlns = fixtag(k, namespaces)
-                            if xmlns: xmlns_items.append(xmlns)
-                    except TypeError:
-                        _raise_serialization_error(k)
-                    try:
-                        if isinstance(v, QName):
-                            v, xmlns = fixtag(v, namespaces)
-                            if xmlns: xmlns_items.append(xmlns)
-                    except TypeError:
-                        _raise_serialization_error(v)
-                    file.write(" %s=\"%s\"" % (_encode(k, encoding),
-                                               _escape_attrib(v, encoding)))
-                for k, v in xmlns_items:
-                    file.write(" %s=\"%s\"" % (_encode(k, encoding),
-                                               _escape_attrib(v, encoding)))
-            if node.text or len(node):
-                file.write(">")
-                if node.text:
-                    file.write(_escape_cdata(node.text, encoding))
-                for n in node:
-                    self._write(file, n, encoding, namespaces)
-                file.write("</" + _encode(tag, encoding) + ">")
+            qnames, namespaces = _namespaces(
+                self._root, encoding, default_namespace
+                )
+            serialize = _serialize[method]
+            serialize(write, self._root, encoding, qnames, namespaces)
+        if file_or_filename is not file:
+            file.close()
+
+    def write_c14n(self, file):
+        # lxml.etree compatibility.  use output method instead
+        return self.write(file, method="c14n")
+
+# --------------------------------------------------------------------
+# serialization support
+
+def _namespaces(elem, encoding, default_namespace=None):
+    # identify namespaces used in this tree
+
+    # maps qnames to *encoded* prefix:local names
+    qnames = {None: None}
+
+    # maps uri:s to prefixes
+    namespaces = {}
+    if default_namespace:
+        namespaces[default_namespace] = ""
+
+    def encode(text):
+        return text.encode(encoding)
+
+    def add_qname(qname):
+        # calculate serialized qname representation
+        try:
+            if qname[:1] == "{":
+                uri, tag = qname[1:].rsplit("}", 1)
+                prefix = namespaces.get(uri)
+                if prefix is None:
+                    prefix = _namespace_map.get(uri)
+                    if prefix is None:
+                        prefix = "ns%d" % len(namespaces)
+                    if prefix != "xml":
+                        namespaces[uri] = prefix
+                if prefix:
+                    qnames[qname] = encode("%s:%s" % (prefix, tag))
+                else:
+                    qnames[qname] = encode(tag) # default element
             else:
-                file.write(" />")
-            for k, v in xmlns_items:
-                del namespaces[v]
-        if node.tail:
-            file.write(_escape_cdata(node.tail, encoding))
+                if default_namespace:
+                    # FIXME: can this be handled in XML 1.0?
+                    raise ValueError(
+                        "cannot use non-qualified names with "
+                        "default_namespace option"
+                        )
+                qnames[qname] = encode(qname)
+        except TypeError:
+            _raise_serialization_error(qname)
+
+    # populate qname and namespaces table
+    try:
+        iterate = elem.iter
+    except AttributeError:
+        iterate = elem.getiterator # cET compatibility
+    for elem in iterate():
+        tag = elem.tag
+        if isinstance(tag, QName):
+            if tag.text not in qnames:
+                add_qname(tag.text)
+        elif isinstance(tag, basestring):
+            if tag not in qnames:
+                add_qname(tag)
+        elif tag is not None and tag is not Comment and tag is not PI:
+            _raise_serialization_error(tag)
+        for key, value in elem.items():
+            if isinstance(key, QName):
+                key = key.text
+            if key not in qnames:
+                add_qname(key)
+            if isinstance(value, QName) and value.text not in qnames:
+                add_qname(value.text)
+        text = elem.text
+        if isinstance(text, QName) and text.text not in qnames:
+            add_qname(text.text)
+    return qnames, namespaces
+
+def _serialize_xml(write, elem, encoding, qnames, namespaces):
+    tag = elem.tag
+    text = elem.text
+    if tag is Comment:
+        write("<!--%s-->" % _encode(text, encoding))
+    elif tag is ProcessingInstruction:
+        write("<?%s?>" % _encode(text, encoding))
+    else:
+        tag = qnames[tag]
+        if tag is None:
+            if text:
+                write(_escape_cdata(text, encoding))
+            for e in elem:
+                _serialize_xml(write, e, encoding, qnames, None)
+        else:
+            write("<" + tag)
+            items = elem.items()
+            if items or namespaces:
+                if namespaces:
+                    for v, k in sorted(namespaces.items(),
+                                       key=lambda x: x[1]):  # sort on prefix
+                        if k:
+                            k = ":" + k
+                        write(" xmlns%s=\"%s\"" % (
+                            k.encode(encoding),
+                            _escape_attrib(v, encoding)
+                            ))
+                for k, v in sorted(items):  # lexical order
+                    if isinstance(k, QName):
+                        k = k.text
+                    if isinstance(v, QName):
+                        v = qnames[v.text]
+                    else:
+                        v = _escape_attrib(v, encoding)
+                    write(" %s=\"%s\"" % (qnames[k], v))
+            if text or len(elem):
+                write(">")
+                if text:
+                    write(_escape_cdata(text, encoding))
+                for e in elem:
+                    _serialize_xml(write, e, encoding, qnames, None)
+                write("</" + tag + ">")
+            else:
+                write(" />")
+    if elem.tail:
+        write(_escape_cdata(elem.tail, encoding))
+
+HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
+              "img", "input", "isindex", "link", "meta", "param")
+
+try:
+    HTML_EMPTY = set(HTML_EMPTY)
+except NameError:
+    pass
+
+def _serialize_html(write, elem, encoding, qnames, namespaces):
+    tag = elem.tag
+    text = elem.text
+    if tag is Comment:
+        write("<!--%s-->" % _escape_cdata(text, encoding))
+    elif tag is ProcessingInstruction:
+        write("<?%s?>" % _escape_cdata(text, encoding))
+    else:
+        tag = qnames[tag]
+        if tag is None:
+            if text:
+                write(_escape_cdata(text, encoding))
+            for e in elem:
+                _serialize_html(write, e, encoding, qnames, None)
+        else:
+            write("<" + tag)
+            items = elem.items()
+            if items or namespaces:
+                if namespaces:
+                    for v, k in sorted(namespaces.items(),
+                                       key=lambda x: x[1]):  # sort on prefix
+                        if k:
+                            k = ":" + k
+                        write(" xmlns%s=\"%s\"" % (
+                            k.encode(encoding),
+                            _escape_attrib(v, encoding)
+                            ))
+                for k, v in sorted(items):  # lexical order
+                    if isinstance(k, QName):
+                        k = k.text
+                    if isinstance(v, QName):
+                        v = qnames[v.text]
+                    else:
+                        v = _escape_attrib_html(v, encoding)
+                    # FIXME: handle boolean attributes
+                    write(" %s=\"%s\"" % (qnames[k], v))
+            write(">")
+            ltag = tag.lower()
+            if text:
+                if ltag == "script" or ltag == "style":
+                    write(_encode(text, encoding))
+                else:
+                    write(_escape_cdata(text, encoding))
+            for e in elem:
+                _serialize_html(write, e, encoding, qnames, None)
+            if ltag not in HTML_EMPTY:
+                write("</" + tag + ">")
+    if elem.tail:
+        write(_escape_cdata(elem.tail, encoding))
+
+def _serialize_text(write, elem, encoding):
+    for part in elem.itertext():
+        write(part.encode(encoding))
+    if elem.tail:
+        write(elem.tail.encode(encoding))
+
+_serialize = {
+    "xml": _serialize_xml,
+    "html": _serialize_html,
+    "text": _serialize_text,
+# this optional method is imported at the end of the module
+#   "c14n": _serialize_c14n,
+}
+
+##
+# Registers a namespace prefix.  The registry is global, and any
+# existing mapping for either the given prefix or the namespace URI
+# will be removed.
+#
+# @param prefix Namespace prefix.
+# @param uri Namespace uri.  Tags and attributes in this namespace
+#     will be serialized with the given prefix, if at all possible.
+# @exception ValueError If the prefix is reserved, or is otherwise
+#     invalid.
+
+def register_namespace(prefix, uri):
+    if re.match("ns\d+$", prefix):
+        raise ValueError("Prefix format reserved for internal use")
+    for k, v in _namespace_map.items():
+        if k == uri or v == prefix:
+            del _namespace_map[k]
+    _namespace_map[uri] = prefix
+
+_namespace_map = {
+    # "well-known" namespace prefixes
+    "http://www.w3.org/XML/1998/namespace": "xml",
+    "http://www.w3.org/1999/xhtml": "html",
+    "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
+    "http://schemas.xmlsoap.org/wsdl/": "wsdl",
+    # xml schema
+    "http://www.w3.org/2001/XMLSchema": "xs",
+    "http://www.w3.org/2001/XMLSchema-instance": "xsi",
+    # dublin core
+    "http://purl.org/dc/elements/1.1/": "dc",
+}
+
+def _raise_serialization_error(text):
+    raise TypeError(
+        "cannot serialize %r (type %s)" % (text, type(text).__name__)
+        )
+
+def _encode(text, encoding):
+    try:
+        return text.encode(encoding, "xmlcharrefreplace")
+    except (TypeError, AttributeError):
+        _raise_serialization_error(text)
+
+def _escape_cdata(text, encoding):
+    # escape character data
+    try:
+        # it's worth avoiding do-nothing calls for strings that are
+        # shorter than 500 character, or so.  assume that's, by far,
+        # the most common case in most applications.
+        if "&" in text:
+            text = text.replace("&", "&amp;")
+        if "<" in text:
+            text = text.replace("<", "&lt;")
+        if ">" in text:
+            text = text.replace(">", "&gt;")
+        return text.encode(encoding, "xmlcharrefreplace")
+    except (TypeError, AttributeError):
+        _raise_serialization_error(text)
+
+def _escape_attrib(text, encoding):
+    # escape attribute value
+    try:
+        if "&" in text:
+            text = text.replace("&", "&amp;")
+        if "<" in text:
+            text = text.replace("<", "&lt;")
+        if ">" in text:
+            text = text.replace(">", "&gt;")
+        if "\"" in text:
+            text = text.replace("\"", "&quot;")
+        if "\n" in text:
+            text = text.replace("\n", "&#10;")
+        return text.encode(encoding, "xmlcharrefreplace")
+    except (TypeError, AttributeError):
+        _raise_serialization_error(text)
+
+def _escape_attrib_html(text, encoding):
+    # escape attribute value
+    try:
+        if "&" in text:
+            text = text.replace("&", "&amp;")
+        if ">" in text:
+            text = text.replace(">", "&gt;")
+        if "\"" in text:
+            text = text.replace("\"", "&quot;")
+        return text.encode(encoding, "xmlcharrefreplace")
+    except (TypeError, AttributeError):
+        _raise_serialization_error(text)
 
 # --------------------------------------------------------------------
-# helpers
-
-##
-# Checks if an object appears to be a valid element object.
-#
-# @param An element instance.
-# @return A true value if this is an element object.
-# @defreturn flag
-
-def iselement(element):
-    # FIXME: not sure about this; might be a better idea to look
-    # for tag/attrib/text attributes
-    return isinstance(element, _ElementInterface) or hasattr(element, "tag")
+
+##
+# Generates a string representation of an XML element, including all
+# subelements.
+#
+# @param element An Element instance.
+# @keyparam encoding Optional output encoding (default is US-ASCII).
+# @keyparam method Optional output method ("xml", "html", "text" or
+#     "c14n"; default is "xml").
+# @return An encoded string containing the XML data.
+# @defreturn string
+
+def tostring(element, encoding=None, method=None):
+    class dummy:
+        pass
+    data = []
+    file = dummy()
+    file.write = data.append
+    ElementTree(element).write(file, encoding, method=method)
+    return "".join(data)
+
+##
+# Generates a string representation of an XML element, including all
+# subelements.  The string is returned as a sequence of string fragments.
+#
+# @param element An Element instance.
+# @keyparam encoding Optional output encoding (default is US-ASCII).
+# @keyparam method Optional output method ("xml", "html", "text" or
+#     "c14n"; default is "xml").
+# @return A sequence object containing the XML data.
+# @defreturn sequence
+# @since 1.3
+
+def tostringlist(element, encoding=None, method=None):
+    class dummy:
+        pass
+    data = []
+    file = dummy()
+    file.write = data.append
+    ElementTree(element).write(file, encoding, method=method)
+    # FIXME: merge small fragments into larger parts
+    return data
 
 ##
@@ -747 +1167 @@
         sys.stdout.write("\n")
 
-def _encode(s, encoding):
-    try:
-        return s.encode(encoding)
-    except AttributeError:
-        return s # 1.5.2: assume the string uses the right encoding
-
-if sys.version[:3] == "1.5":
-    _escape = re.compile(r"[&<>\"\x80-\xff]+") # 1.5.2
-else:
-    _escape = re.compile(eval(r'u"[&<>\"\u0080-\uffff]+"'))
-
-_escape_map = {
-    "&": "&amp;",
-    "<": "&lt;",
-    ">": "&gt;",
-    '"': "&quot;",
-}
-
-_namespace_map = {
-    # "well-known" namespace prefixes
-    "http://www.w3.org/XML/1998/namespace": "xml",
-    "http://www.w3.org/1999/xhtml": "html",
-    "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
-    "http://schemas.xmlsoap.org/wsdl/": "wsdl",
-}
-
-def _raise_serialization_error(text):
-    raise TypeError(
-        "cannot serialize %r (type %s)" % (text, type(text).__name__)
-        )
-
-def _encode_entity(text, pattern=_escape):
-    # map reserved and non-ascii characters to numerical entities
-    def escape_entities(m, map=_escape_map):
-        out = []
-        append = out.append
-        for char in m.group():
-            text = map.get(char)
-            if text is None:
-                text = "&#%d;" % ord(char)
-            append(text)
-        return string.join(out, "")
-    try:
-        return _encode(pattern.sub(escape_entities, text), "ascii")
-    except TypeError:
-        _raise_serialization_error(text)
-
-#
-# the following functions assume an ascii-compatible encoding
-# (or "utf-16")
-
-def _escape_cdata(text, encoding=None, replace=string.replace):
-    # escape character data
-    try:
-        if encoding:
-            try:
-                text = _encode(text, encoding)
-            except UnicodeError:
-                return _encode_entity(text)
-        text = replace(text, "&", "&amp;")
-        text = replace(text, "<", "&lt;")
-        text = replace(text, ">", "&gt;")
-        return text
-    except (TypeError, AttributeError):
-        _raise_serialization_error(text)
-
-def _escape_attrib(text, encoding=None, replace=string.replace):
-    # escape attribute value
-    try:
-        if encoding:
-            try:
-                text = _encode(text, encoding)
-            except UnicodeError:
-                return _encode_entity(text)
-        text = replace(text, "&", "&amp;")
-        text = replace(text, "'", "&apos;") # FIXME: overkill
-        text = replace(text, "\"", "&quot;")
-        text = replace(text, "<", "&lt;")
-        text = replace(text, ">", "&gt;")
-        return text
-    except (TypeError, AttributeError):
-        _raise_serialization_error(text)
-
-def fixtag(tag, namespaces):
-    # given a decorated tag (of the form {uri}tag), return prefixed
-    # tag and namespace declaration, if any
-    if isinstance(tag, QName):
-        tag = tag.text
-    namespace_uri, tag = string.split(tag[1:], "}", 1)
-    prefix = namespaces.get(namespace_uri)
-    if prefix is None:
-        prefix = _namespace_map.get(namespace_uri)
-        if prefix is None:
-            prefix = "ns%d" % len(namespaces)
-        namespaces[namespace_uri] = prefix
-        if prefix == "xml":
-            xmlns = None
-        else:
-            xmlns = ("xmlns:%s" % prefix, namespace_uri)
-    else:
-        xmlns = None
-    return "%s:%s" % (prefix, tag), xmlns
+# --------------------------------------------------------------------
+# parsing
 
 ##
@@ -855 +1175 @@
 # @param source A filename or file object containing XML data.
 # @param parser An optional parser instance.  If not given, the
-#     standard {@link XMLTreeBuilder} parser is used.
+#     standard {@link XMLParser} parser is used.
 # @return An ElementTree instance
 
@@ -870 +1190 @@
 # @param events A list of events to report back.  If omitted, only "end"
 #     events are reported.
+# @param parser An optional parser instance.  If not given, the
+#     standard {@link XMLParser} parser is used.
 # @return A (event, elem) iterator.
 
-class iterparse:
-
-    def __init__(self, source, events=None):
-        if not hasattr(source, "read"):
-            source = open(source, "rb")
+def iterparse(source, events=None, parser=None):
+    close_source = False
+    if not hasattr(source, "read"):
+        source = open(source, "rb")
+        close_source = True
+    if not parser:
+        parser = XMLParser(target=TreeBuilder())
+    return _IterParseIterator(source, events, parser, close_source)
+
+class _IterParseIterator(object):
+
+    def __init__(self, source, events, parser, close_source=False):
         self._file = source
+        self._close_file = close_source
         self._events = []
         self._index = 0
+        self._error = None
         self.root = self._root = None
-        self._parser = XMLTreeBuilder()
+        self._parser = parser
         # wire up the parser for event reporting
         parser = self._parser._parser
@@ -909 +1240 @@
                 def handler(prefix, uri, event=event, append=append):
                     try:
-                        uri = _encode(uri, "ascii")
+                        uri = (uri or "").encode("ascii")
                     except UnicodeError:
                         pass
-                    append((event, (prefix or "", uri)))
+                    append((event, (prefix or "", uri or "")))
                 parser.StartNamespaceDeclHandler = handler
             elif event == "end-ns":
@@ -918 +1249 @@
                     append((event, None))
                 parser.EndNamespaceDeclHandler = handler
+            else:
+                raise ValueError("unknown event %r" % event)
 
     def next(self):
@@ -923 +1256 @@
             try:
                 item = self._events[self._index]
+                self._index += 1
+                return item
             except IndexError:
-                if self._parser is None:
-                    self.root = self._root
-                    try:
-                        raise StopIteration
-                    except NameError:
-                        raise IndexError
-                # load event buffer
-                del self._events[:]
-                self._index = 0
-                data = self._file.read(16384)
-                if data:
+                pass
+            if self._error:
+                e = self._error
+                self._error = None
+                raise e
+            if self._parser is None:
+                self.root = self._root
+                if self._close_file:
+                    self._file.close()
+                raise StopIteration
+            # load event buffer
+            del self._events[:]
+            self._index = 0
+            data = self._file.read(16384)
+            if data:
+                try:
                     self._parser.feed(data)
-                else:
-                    self._root = self._parser.close()
-                    self._parser = None
+                except SyntaxError as exc:
+                    self._error = exc
             else:
-                self._index = self._index + 1
-                return item
-
-    try:
-        iter
-        def __iter__(self):
-            return self
-    except NameError:
-        def __getitem__(self, index):
-            return self.next()
+                self._root = self._parser.close()
+                self._parser = None
+
+    def __iter__(self):
+        return self
 
 ##
@@ -956 +1290 @@
 #
 # @param source A string containing XML data.
+# @param parser An optional parser instance.  If not given, the
+#     standard {@link XMLParser} parser is used.
 # @return An Element instance.
 # @defreturn Element
 
-def XML(text):
-    parser = XMLTreeBuilder()
+def XML(text, parser=None):
+    if not parser:
+        parser = XMLParser(target=TreeBuilder())
     parser.feed(text)
     return parser.close()
@@ -969 +1306 @@
 #
 # @param source A string containing XML data.
+# @param parser An optional parser instance.  If not given, the
+#     standard {@link XMLParser} parser is used.
 # @return A tuple containing an Element instance and a dictionary.
 # @defreturn (Element, dictionary)
 
-def XMLID(text):
-    parser = XMLTreeBuilder()
+def XMLID(text, parser=None):
+    if not parser:
+        parser = XMLParser(target=TreeBuilder())
     parser.feed(text)
     tree = parser.close()
     ids = {}
-    for elem in tree.getiterator():
+    for elem in tree.iter():
         id = elem.get("id")
         if id:
@@ -994 +1334 @@
 
 ##
-# Generates a string representation of an XML element, including all
-# subelements.
-#
-# @param element An Element instance.
-# @return An encoded string containing the XML data.
-# @defreturn string
-
-def tostring(element, encoding=None):
-    class dummy:
-        pass
-    data = []
-    file = dummy()
-    file.write = data.append
-    ElementTree(element).write(file, encoding)
-    return string.join(data, "")
+# Parses an XML document from a sequence of string fragments.
+#
+# @param sequence A list or other sequence containing XML data fragments.
+# @param parser An optional parser instance.  If not given, the
+#     standard {@link XMLParser} parser is used.
+# @return An Element instance.
+# @defreturn Element
+# @since 1.3
+
+def fromstringlist(sequence, parser=None):
+    if not parser:
+        parser = XMLParser(target=TreeBuilder())
+    for text in sequence:
+        parser.feed(text)
+    return parser.close()
+
+# --------------------------------------------------------------------
 
 ##
@@ -1021 +1363 @@
 #    is called to create new Element instances, as necessary.
 
-class TreeBuilder:
+class TreeBuilder(object):
 
     def __init__(self, element_factory=None):
@@ -1029 +1371 @@
         self._tail = None # true if we're after an end tag
         if element_factory is None:
-            element_factory = _ElementInterface
+            element_factory = Element
         self._factory = element_factory
 
     ##
-    # Flushes the parser buffers, and returns the toplevel documen
+    # Flushes the builder buffers, and returns the toplevel document
     # element.
     #
@@ -1041 +1383 @@
     def close(self):
         assert len(self._elem) == 0, "missing end tags"
-        assert self._last != None, "missing toplevel element"
+        assert self._last is not None, "missing toplevel element"
         return self._last
 
@@ -1047 +1389 @@
         if self._data:
             if self._last is not None:
-                text = string.join(self._data, "")
+                text = "".join(self._data)
                 if self._tail:
                     assert self._last.tail is None, "internal error (tail)"
@@ -1106 +1448 @@
 # @keyparam html Predefine HTML entities.  This flag is not supported
 #     by the current implementation.
+# @keyparam encoding Optional encoding.  If given, the value overrides
+#     the encoding specified in the XML file.
 # @see #ElementTree
 # @see #TreeBuilder
 
-class XMLTreeBuilder:
-
-    def __init__(self, html=0, target=None):
+class XMLParser(object):
+
+    def __init__(self, html=0, target=None, encoding=None):
         try:
             from xml.parsers import expat
         except ImportError:
-            raise ImportError(
-                "No module named expat; use SimpleXMLTreeBuilder instead"
-                )
-        self._parser = parser = expat.ParserCreate(None, "}")
+            try:
+                import pyexpat as expat
+            except ImportError:
+                raise ImportError(
+                    "No module named expat; use SimpleXMLTreeBuilder instead"
+                    )
+        parser = expat.ParserCreate(encoding, "}")
         if target is None:
             target = TreeBuilder()
-        self._target = target
+        # underscored names are provided for compatibility only
+        self.parser = self._parser = parser
+        self.target = self._target = target
+        self._error = expat.error
         self._names = {} # name memo cache
         # callbacks
@@ -1128 +1478 @@
         parser.EndElementHandler = self._end
         parser.CharacterDataHandler = self._data
+        # optional callbacks
+        parser.CommentHandler = self._comment
+        parser.ProcessingInstructionHandler = self._pi
         # let expat do the buffering, if supported
         try:
@@ -1140 +1493 @@
         except AttributeError:
             pass
-        encoding = None
-        if not parser.returns_unicode:
-            encoding = "utf-8"
-        # target.xml(encoding, None)
         self._doctype = None
         self.entity = {}
+        try:
+            self.version = "Expat %d.%d.%d" % expat.version_info
+        except AttributeError:
+            pass # unknown
+
+    def _raiseerror(self, value):
+        err = ParseError(value)
+        err.code = value.code
+        err.position = value.lineno, value.offset
+        raise err
 
     def _fixtext(self, text):
         # convert text string to ascii, if possible
         try:
-            return _encode(text, "ascii")
+            return text.encode("ascii")
         except UnicodeError:
             return text
@@ -1167 +1526 @@
     def _start(self, tag, attrib_in):
         fixname = self._fixname
+        fixtext = self._fixtext
         tag = fixname(tag)
         attrib = {}
         for key, value in attrib_in.items():
-            attrib[fixname(key)] = self._fixtext(value)
-        return self._target.start(tag, attrib)
+            attrib[fixname(key)] = fixtext(value)
+        return self.target.start(tag, attrib)
 
     def _start_list(self, tag, attrib_in):
         fixname = self._fixname
+        fixtext = self._fixtext
         tag = fixname(tag)
         attrib = {}
         if attrib_in:
             for i in range(0, len(attrib_in), 2):
-                attrib[fixname(attrib_in[i])] = self._fixtext(attrib_in[i+1])
-        return self._target.start(tag, attrib)
+                attrib[fixname(attrib_in[i])] = fixtext(attrib_in[i+1])
+        return self.target.start(tag, attrib)
 
     def _data(self, text):
-        return self._target.data(self._fixtext(text))
+        return self.target.data(self._fixtext(text))
 
     def _end(self, tag):
-        return self._target.end(self._fixname(tag))
+        return self.target.end(self._fixname(tag))
+
+    def _comment(self, data):
+        try:
+            comment = self.target.comment
+        except AttributeError:
+            pass
+        else:
+            return comment(self._fixtext(data))
+
+    def _pi(self, target, data):
+        try:
+            pi = self.target.pi
+        except AttributeError:
+            pass
+        else:
+            return pi(self._fixtext(target), self._fixtext(data))
 
     def _default(self, text):
@@ -1193 +1570 @@
             # deal with undefined entities
             try:
-                self._target.data(self.entity[text[1:-1]])
+                self.target.data(self.entity[text[1:-1]])
             except KeyError:
                 from xml.parsers import expat
-                raise expat.error(
+                err = expat.error(
                     "undefined entity %s: line %d, column %d" %
                     (text, self._parser.ErrorLineNumber,
                     self._parser.ErrorColumnNumber)
                     )
+                err.code = 11 # XML_ERROR_UNDEFINED_ENTITY
+                err.lineno = self._parser.ErrorLineNumber
+                err.offset = self._parser.ErrorColumnNumber
+                raise err
         elif prefix == "<" and text[:9] == "<!DOCTYPE":
             self._doctype = [] # inside a doctype declaration
@@ -1208 +1589 @@
                 self._doctype = None
                 return
-            text = string.strip(text)
+            text = text.strip()
             if not text:
                 return
@@ -1224 +1605 @@
                 if pubid:
                     pubid = pubid[1:-1]
-                self.doctype(name, pubid, system[1:-1])
+                if hasattr(self.target, "doctype"):
+                    self.target.doctype(name, pubid, system[1:-1])
+                elif self.doctype is not self._XMLParser__doctype:
+                    # warn about deprecated call
+                    self._XMLParser__doctype(name, pubid, system[1:-1])
+                    self.doctype(name, pubid, system[1:-1])
                 self._doctype = None
 
     ##
-    # Handles a doctype declaration.
+    # (Deprecated) Handles a doctype declaration.
     #
     # @param name Doctype name.
@@ -1235 +1621 @@
 
     def doctype(self, name, pubid, system):
-        pass
+        """This method of XMLParser is deprecated."""
+        warnings.warn(
+            "This method of XMLParser is deprecated.  Define doctype() "
+            "method on the TreeBuilder target.",
+            DeprecationWarning,
+            )
+
+    # sentinel, if doctype is redefined in a subclass
+    __doctype = doctype
 
     ##
@@ -1243 +1637 @@
 
     def feed(self, data):
-        self._parser.Parse(data, 0)
+        try:
+            self._parser.Parse(data, 0)
+        except self._error, v:
+            self._raiseerror(v)
 
     ##
@@ -1252 +1649 @@
 
     def close(self):
-        self._parser.Parse("", 1) # end of data
-        tree = self._target.close()
-        del self._target, self._parser # get rid of circular references
+        try:
+            self._parser.Parse("", 1) # end of data
+        except self._error, v:
+            self._raiseerror(v)
+        tree = self.target.close()
+        del self.target, self._parser # get rid of circular references
         return tree
 
 # compatibility
-XMLParser = XMLTreeBuilder
+XMLTreeBuilder = XMLParser
+
+# workaround circular import.
+try:
+    from ElementC14N import _serialize_c14n
+    _serialize["c14n"] = _serialize_c14n
+except ImportError:
+    pass

python/trunk/Lib/xml/etree/__init__.py

@@ -1 @@
-# $Id: __init__.py 1821 2004-06-03 16:57:49Z fredrik $
+# $Id: __init__.py 3375 2008-02-13 08:05:08Z fredrik $
 # elementtree package
 
@@ -5 +5 @@
 # The ElementTree toolkit is
 #
-# Copyright (c) 1999-2004 by Fredrik Lundh
+# Copyright (c) 1999-2008 by Fredrik Lundh
 #
 # By obtaining, using, and/or copying this software and/or its
@@ -31 +31 @@
 
 # Licensed to PSF under a Contributor Agreement.
-# See http://www.python.org/2.4/license for licensing details.
+# See http://www.python.org/psf/license for licensing details.