root/trunk/lib/elementtree/ElementTree.py

#
# 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.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2005 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS.  IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------

__all__ = [
    # public symbols
    "Comment",
    "dump",
    "Element", "ElementTree",
    "fromstring",
    "iselement", "iterparse",
    "parse",
    "PI", "ProcessingInstruction",
    "QName",
    "SubElement",
    "tostring",
    "TreeBuilder",
    "VERSION", "XML",
    "XMLTreeBuilder",
    ]

##
# The <b>Element</b> type is a flexible container object, designed to
# store hierarchical data structures in memory. The type can be
# described as a cross between a list and a dictionary.
# <p>
# Each element has a number of properties associated with it:
# <ul>
# <li>a <i>tag</i>. This is a string identifying what kind of data
# this element represents (the element type, in other words).</li>
# <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>
# <li>a <i>text</i> string.</li>
# <li>an optional <i>tail</i> string.</li>
# <li>a number of <i>child elements</i>, stored in a Python sequence</li>
# </ul>
#
# To create an element instance, use the {@link #Element} or {@link
# #SubElement} factory functions.
# <p>
# The {@link #ElementTree} class can be used to wrap an element
# structure, and convert it from and to XML.
##

import string, sys, re

class _SimpleElementPath:
    # emulate pre-1.2 find/findtext/findall behaviour
    def find(self, element, tag):
        for elem in element:
            if elem.tag == tag:
                return elem
        return None
    def findtext(self, element, tag, default=None):
        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

try:
    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.
# <p>
# You should not create instances of this class directly.  Use the
# appropriate factory functions instead, such as {@link #Element}
# and {@link #SubElement}.
#
# @see Element
# @see SubElement
# @see Comment
# @see ProcessingInstruction

class _ElementInterface:
    # <tag attrib>text<child/>...</tag>tail

    ##
    # (Attribute) Element tag.

    tag = None

    ##
    # (Attribute) Element attribute dictionary.  Where possible, use
    # {@link #_ElementInterface.get},
    # {@link #_ElementInterface.set},
    # {@link #_ElementInterface.keys}, and
    # {@link #_ElementInterface.items} to access
    # element attributes.

    attrib = None

    ##
    # (Attribute) Text before first subelement.  This is either a
    # string or the value None, if there was no text.

    text = None

    ##
    # (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.

    tail = None # text after end tag, if any

    def __init__(self, tag, attrib):
        self.tag = tag
        self.attrib = attrib
        self._children = []

    def __repr__(self):
        return "<Element %s at %x>" % (self.tag, id(self))

    ##
    # Creates a new element object of the same type as this element.
    #
    # @param tag Element tag.
    # @param attrib Element attributes, given as a dictionary.
    # @return A new element instance.

    def makeelement(self, tag, attrib):
        return Element(tag, attrib)

    ##
    # Returns the number of subelements.
    #
    # @return The number of subelements.

    def __len__(self):
        return len(self._children)

    ##
    # Returns the given subelement.
    #
    # @param index What subelement to return.
    # @return The given subelement.
    # @exception IndexError If the given element does not exist.

    def __getitem__(self, index):
        return self._children[index]

    ##
    # Replaces the given subelement.
    #
    # @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)
        self._children[index] = element

    ##
    # Deletes the given subelement.
    #
    # @param index What subelement to delete.
    # @exception IndexError If the given element does not exist.

    def __delitem__(self, index):
        del self._children[index]

    ##
    # 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.
    # @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)

    ##
    # Inserts a subelement at the given position in this element.
    #
    # @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)
        self._children.insert(index, element)

    ##
    # Removes a matching subelement.  Unlike the <b>find</b> methods,
    # this method compares elements based on identity, not on tag
    # value or contents.
    #
    # @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)
        self._children.remove(element)

    ##
    # Returns all subelements.  The elements are returned in document
    # order.
    #
    # @return A list of subelements.
    # @defreturn list of Element instances

    def getchildren(self):
        return self._children

    ##
    # Finds the first matching subelement, by tag name or path.
    #
    # @param path What element to look for.
    # @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)

    ##
    # Finds text for the first matching subelement, by tag name or path.
    #
    # @param path What element to look for.
    # @param default What to return if the element was not found.
    # @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
    #     empty string.
    # @defreturn string

    def findtext(self, path, default=None):
        return ElementPath.findtext(self, path, default)

    ##
    # Finds all matching subelements, by tag name or path.
    #
    # @param path What element to look for.
    # @return A list or iterator containing all matching elements,
    #    in document order.
    # @defreturn list of Element instances

    def findall(self, path):
        return ElementPath.findall(self, path)

    ##
    # Resets an element.  This function removes all subelements, clears
    # all attributes, and sets the text and tail attributes to None.

    def clear(self):
        self.attrib.clear()
        self._children = []
        self.text = self.tail = None

    ##
    # Gets an element attribute.
    #
    # @param key What attribute to look for.
    # @param default What to return if the attribute was not found.
    # @return The attribute value, or the default value, if the
    #     attribute was not found.
    # @defreturn string or None

    def get(self, key, default=None):
        return self.attrib.get(key, default)

    ##
    # Sets an element attribute.
    #
    # @param key What attribute to set.
    # @param value The attribute value.

    def set(self, key, value):
        self.attrib[key] = value

    ##
    # Gets a list of attribute names.  The names are returned in an
    # arbitrary order (just like for an ordinary Python dictionary).
    #
    # @return A list of element attribute names.
    # @defreturn list of strings

    def keys(self):
        return self.attrib.keys()

    ##
    # Gets element attributes, as a sequence.  The attributes are
    # returned in an arbitrary order.
    #
    # @return A list of (name, value) tuples for all attributes.
    # @defreturn list of (string, string) tuples

    def items(self):
        return self.attrib.items()

    ##
    # Creates a tree iterator.  The iterator loops over this element
    # and all subelements, in document order, and returns all elements
    # with a matching tag.
    # <p>
    # If the tree structure is modified during iteration, the result
    # is undefined.
    #
    # @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 = []
        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

# 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)

##
# Subelement factory.  This function creates an element instance, and
# appends it to an existing element.
# <p>
# The element name, attribute names, and attribute values can be
# either 8-bit ASCII strings or Unicode strings.
#
# @param parent The parent element.
# @param tag The subelement name.
# @param attrib An optional dictionary, containing element attributes.
# @param **extra Additional attributes, given as keyword arguments.
# @return An element instance.
# @defreturn Element

def SubElement(parent, tag, attrib={}, **extra):
    attrib = attrib.copy()
    attrib.update(extra)
    element = parent.makeelement(tag, attrib)
    parent.append(element)
    return element

##
# Comment element factory.  This factory function creates a special
# element that will be serialized as an XML comment.
# <p>
# The comment string can be either an 8-bit ASCII string or a Unicode
# string.
#
# @param text A string containing the comment string.
# @return An element instance, representing a comment.
# @defreturn Element

def Comment(text=None):
    element = Element(Comment)
    element.text = text
    return element

##
# PI element factory.  This factory function creates a special element
# that will be serialized as an XML processing instruction.
#
# @param target A string containing the PI target.
# @param text A string containing the PI contents, if any.
# @return An element instance, representing a PI.
# @defreturn Element

def ProcessingInstruction(target, text=None):
    element = Element(ProcessingInstruction)
    element.text = target
    if text:
        element.text = element.text + " " + text
    return element

PI = ProcessingInstruction

##
# QName wrapper.  This can be used to wrap a QName attribute value, in
# order to get proper namespace handling on output.
#
# @param text A string containing the QName value, in the form {uri}local,
#     or, if the tag argument is given, the URI part of a QName.
# @param tag Optional tag.  If given, the first argument is interpreted as
#     an URI, and this argument is interpreted as a local name.
# @return An opaque object, representing the QName.

class QName:
    def __init__(self, text_or_uri, tag=None):
        if tag:
            text_or_uri = "{%s}%s" % (text_or_uri, tag)
        self.text = text_or_uri
    def __str__(self):
        return self.text
    def __hash__(self):
        return hash(self.text)
    def __cmp__(self, other):
        if isinstance(other, QName):
            return cmp(self.text, other.text)
        return cmp(self.text, other)

##
# ElementTree wrapper class.  This class represents an entire element
# hierarchy, and adds some extra support for serialization to and from
# standard XML.
#
# @param element Optional root element.
# @keyparam file Optional file handle or name.  If given, the
#     tree is initialized with the contents of this XML file.

class ElementTree:

    def __init__(self, element=None, file=None):
        assert element is None or iselement(element)
        self._root = element # first node
        if file:
            self.parse(file)

    ##
    # Gets the root element for this tree.
    #
    # @return An element instance.
    # @defreturn Element

    def getroot(self):
        return self._root

    ##
    # Replaces the root element for this tree.  This discards the
    # current contents of the tree, and replaces it with the given
    # element.  Use with care.
    #
    # @param element An element instance.

    def _setroot(self, element):
        assert iselement(element)
        self._root = element

    ##
    # 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.
    # @return The document root element.
    # @defreturn Element

    def parse(self, source, parser=None):
        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

    ##
    # Creates a tree iterator for the root element.  The iterator loops
    # over all elements in this tree, in document order.
    #
    # @param tag What tags to look for (default is to return all elements)
    # @return An iterator.
    # @defreturn iterator

    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).
    #
    # @param path What element to look for.
    # @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
        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.
    # @param default What to return if the element was not found.
    # @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
    #     empty string.
    # @defreturn string

    def findtext(self, path, default=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).
    #
    # @param path What element to look for.
    # @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
        if path[:1] == "/":
            path = "." + path
        return self._root.findall(path)

    ##
    # Writes the element tree to a file, as XML.
    #
    # @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")
        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))
        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) + ">")
            else:
                file.write(" />")
            for k, v in xmlns_items:
                del namespaces[v]
        if node.tail:
            file.write(_escape_cdata(node.tail, encoding))

# --------------------------------------------------------------------
# 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")

##
# Writes an element tree or element structure to sys.stdout.  This
# function should be used for debugging only.
# <p>
# The exact output format is implementation dependent.  In this
# version, it's written as an ordinary XML file.
#
# @param elem An element tree or an individual element.

def dump(elem):
    # debugging
    if not isinstance(elem, ElementTree):
        elem = ElementTree(elem)
    elem.write(sys.stdout)
    tail = elem.getroot().tail
    if not tail or tail[-1] != "\n":
        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)