expunge the xmlcore changes:
41667, 41668 - initial switch to xmlcore
47044 - mention of xmlcore in What's New
50687 - mention of xmlcore in the library reference
re-apply xmlcore changes to xml:
41674 - line ending changes (re-applied manually), directory props
41677 - add cElementTree wrapper
41678 - PSF licensing for etree
41812 - whitespace normalization
42724 - fix svn:eol-style settings
43681, 43682 - remove Python version-compatibility cruft from minidom
46773 - fix encoding of \r\n\t in attr values in saxutils
47269 - added XMLParser alias for cElementTree compatibility
additional tests were added in Lib/test/test_sax.py that failed with
the xmlcore changes; these relate to SF bugs #1511497, #1513611
diff --git a/Lib/xml/__init__.py b/Lib/xml/__init__.py
new file mode 100644
index 0000000..fa5e8cd
--- /dev/null
+++ b/Lib/xml/__init__.py
@@ -0,0 +1,47 @@
+"""Core XML support for Python.
+
+This package contains four sub-packages:
+
+dom -- The W3C Document Object Model. This supports DOM Level 1 +
+ Namespaces.
+
+parsers -- Python wrappers for XML parsers (currently only supports Expat).
+
+sax -- The Simple API for XML, developed by XML-Dev, led by David
+ Megginson and ported to Python by Lars Marius Garshol. This
+ supports the SAX 2 API.
+
+etree -- The ElementTree XML library. This is a subset of the full
+ ElementTree XML release.
+
+"""
+
+
+__all__ = ["dom", "parsers", "sax", "etree"]
+
+# When being checked-out without options, this has the form
+# "<dollar>Revision: x.y </dollar>"
+# When exported using -kv, it is "x.y".
+__version__ = "$Revision$".split()[-2:][0]
+
+
+_MINIMUM_XMLPLUS_VERSION = (0, 8, 4)
+
+
+try:
+ import _xmlplus
+except ImportError:
+ pass
+else:
+ try:
+ v = _xmlplus.version_info
+ except AttributeError:
+ # _xmlplus is too old; ignore it
+ pass
+ else:
+ if v >= _MINIMUM_XMLPLUS_VERSION:
+ import sys
+ _xmlplus.__path__.extend(__path__)
+ sys.modules[__name__] = _xmlplus
+ else:
+ del v
diff --git a/Lib/xml/dom/NodeFilter.py b/Lib/xml/dom/NodeFilter.py
new file mode 100644
index 0000000..fc05245
--- /dev/null
+++ b/Lib/xml/dom/NodeFilter.py
@@ -0,0 +1,27 @@
+# This is the Python mapping for interface NodeFilter from
+# DOM2-Traversal-Range. It contains only constants.
+
+class NodeFilter:
+ """
+ This is the DOM2 NodeFilter interface. It contains only constants.
+ """
+ FILTER_ACCEPT = 1
+ FILTER_REJECT = 2
+ FILTER_SKIP = 3
+
+ SHOW_ALL = 0xFFFFFFFFL
+ SHOW_ELEMENT = 0x00000001
+ SHOW_ATTRIBUTE = 0x00000002
+ SHOW_TEXT = 0x00000004
+ SHOW_CDATA_SECTION = 0x00000008
+ SHOW_ENTITY_REFERENCE = 0x00000010
+ SHOW_ENTITY = 0x00000020
+ SHOW_PROCESSING_INSTRUCTION = 0x00000040
+ SHOW_COMMENT = 0x00000080
+ SHOW_DOCUMENT = 0x00000100
+ SHOW_DOCUMENT_TYPE = 0x00000200
+ SHOW_DOCUMENT_FRAGMENT = 0x00000400
+ SHOW_NOTATION = 0x00000800
+
+ def acceptNode(self, node):
+ raise NotImplementedError
diff --git a/Lib/xml/dom/__init__.py b/Lib/xml/dom/__init__.py
new file mode 100644
index 0000000..6363d00
--- /dev/null
+++ b/Lib/xml/dom/__init__.py
@@ -0,0 +1,139 @@
+"""W3C Document Object Model implementation for Python.
+
+The Python mapping of the Document Object Model is documented in the
+Python Library Reference in the section on the xml.dom package.
+
+This package contains the following modules:
+
+minidom -- A simple implementation of the Level 1 DOM with namespace
+ support added (based on the Level 2 specification) and other
+ minor Level 2 functionality.
+
+pulldom -- DOM builder supporting on-demand tree-building for selected
+ subtrees of the document.
+
+"""
+
+
+class Node:
+ """Class giving the NodeType constants."""
+
+ # DOM implementations may use this as a base class for their own
+ # Node implementations. If they don't, the constants defined here
+ # should still be used as the canonical definitions as they match
+ # the values given in the W3C recommendation. Client code can
+ # safely refer to these values in all tests of Node.nodeType
+ # values.
+
+ ELEMENT_NODE = 1
+ ATTRIBUTE_NODE = 2
+ TEXT_NODE = 3
+ CDATA_SECTION_NODE = 4
+ ENTITY_REFERENCE_NODE = 5
+ ENTITY_NODE = 6
+ PROCESSING_INSTRUCTION_NODE = 7
+ COMMENT_NODE = 8
+ DOCUMENT_NODE = 9
+ DOCUMENT_TYPE_NODE = 10
+ DOCUMENT_FRAGMENT_NODE = 11
+ NOTATION_NODE = 12
+
+
+#ExceptionCode
+INDEX_SIZE_ERR = 1
+DOMSTRING_SIZE_ERR = 2
+HIERARCHY_REQUEST_ERR = 3
+WRONG_DOCUMENT_ERR = 4
+INVALID_CHARACTER_ERR = 5
+NO_DATA_ALLOWED_ERR = 6
+NO_MODIFICATION_ALLOWED_ERR = 7
+NOT_FOUND_ERR = 8
+NOT_SUPPORTED_ERR = 9
+INUSE_ATTRIBUTE_ERR = 10
+INVALID_STATE_ERR = 11
+SYNTAX_ERR = 12
+INVALID_MODIFICATION_ERR = 13
+NAMESPACE_ERR = 14
+INVALID_ACCESS_ERR = 15
+VALIDATION_ERR = 16
+
+
+class DOMException(Exception):
+ """Abstract base class for DOM exceptions.
+ Exceptions with specific codes are specializations of this class."""
+
+ def __init__(self, *args, **kw):
+ if self.__class__ is DOMException:
+ raise RuntimeError(
+ "DOMException should not be instantiated directly")
+ Exception.__init__(self, *args, **kw)
+
+ def _get_code(self):
+ return self.code
+
+
+class IndexSizeErr(DOMException):
+ code = INDEX_SIZE_ERR
+
+class DomstringSizeErr(DOMException):
+ code = DOMSTRING_SIZE_ERR
+
+class HierarchyRequestErr(DOMException):
+ code = HIERARCHY_REQUEST_ERR
+
+class WrongDocumentErr(DOMException):
+ code = WRONG_DOCUMENT_ERR
+
+class InvalidCharacterErr(DOMException):
+ code = INVALID_CHARACTER_ERR
+
+class NoDataAllowedErr(DOMException):
+ code = NO_DATA_ALLOWED_ERR
+
+class NoModificationAllowedErr(DOMException):
+ code = NO_MODIFICATION_ALLOWED_ERR
+
+class NotFoundErr(DOMException):
+ code = NOT_FOUND_ERR
+
+class NotSupportedErr(DOMException):
+ code = NOT_SUPPORTED_ERR
+
+class InuseAttributeErr(DOMException):
+ code = INUSE_ATTRIBUTE_ERR
+
+class InvalidStateErr(DOMException):
+ code = INVALID_STATE_ERR
+
+class SyntaxErr(DOMException):
+ code = SYNTAX_ERR
+
+class InvalidModificationErr(DOMException):
+ code = INVALID_MODIFICATION_ERR
+
+class NamespaceErr(DOMException):
+ code = NAMESPACE_ERR
+
+class InvalidAccessErr(DOMException):
+ code = INVALID_ACCESS_ERR
+
+class ValidationErr(DOMException):
+ code = VALIDATION_ERR
+
+class UserDataHandler:
+ """Class giving the operation constants for UserDataHandler.handle()."""
+
+ # Based on DOM Level 3 (WD 9 April 2002)
+
+ NODE_CLONED = 1
+ NODE_IMPORTED = 2
+ NODE_DELETED = 3
+ NODE_RENAMED = 4
+
+XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace"
+XMLNS_NAMESPACE = "http://www.w3.org/2000/xmlns/"
+XHTML_NAMESPACE = "http://www.w3.org/1999/xhtml"
+EMPTY_NAMESPACE = None
+EMPTY_PREFIX = None
+
+from domreg import getDOMImplementation,registerDOMImplementation
diff --git a/Lib/xml/dom/domreg.py b/Lib/xml/dom/domreg.py
new file mode 100644
index 0000000..684c436
--- /dev/null
+++ b/Lib/xml/dom/domreg.py
@@ -0,0 +1,99 @@
+"""Registration facilities for DOM. This module should not be used
+directly. Instead, the functions getDOMImplementation and
+registerDOMImplementation should be imported from xml.dom."""
+
+from xml.dom.minicompat import * # isinstance, StringTypes
+
+# This is a list of well-known implementations. Well-known names
+# should be published by posting to xml-sig@python.org, and are
+# subsequently recorded in this file.
+
+well_known_implementations = {
+ 'minidom':'xml.dom.minidom',
+ '4DOM': 'xml.dom.DOMImplementation',
+ }
+
+# DOM implementations not officially registered should register
+# themselves with their
+
+registered = {}
+
+def registerDOMImplementation(name, factory):
+ """registerDOMImplementation(name, factory)
+
+ Register the factory function with the name. The factory function
+ should return an object which implements the DOMImplementation
+ interface. The factory function can either return the same object,
+ or a new one (e.g. if that implementation supports some
+ customization)."""
+
+ registered[name] = factory
+
+def _good_enough(dom, features):
+ "_good_enough(dom, features) -> Return 1 if the dom offers the features"
+ for f,v in features:
+ if not dom.hasFeature(f,v):
+ return 0
+ return 1
+
+def getDOMImplementation(name = None, features = ()):
+ """getDOMImplementation(name = None, features = ()) -> DOM implementation.
+
+ Return a suitable DOM implementation. The name is either
+ well-known, the module name of a DOM implementation, or None. If
+ it is not None, imports the corresponding module and returns
+ DOMImplementation object if the import succeeds.
+
+ If name is not given, consider the available implementations to
+ find one with the required feature set. If no implementation can
+ be found, raise an ImportError. The features list must be a sequence
+ of (feature, version) pairs which are passed to hasFeature."""
+
+ import os
+ creator = None
+ mod = well_known_implementations.get(name)
+ if mod:
+ mod = __import__(mod, {}, {}, ['getDOMImplementation'])
+ return mod.getDOMImplementation()
+ elif name:
+ return registered[name]()
+ elif os.environ.has_key("PYTHON_DOM"):
+ return getDOMImplementation(name = os.environ["PYTHON_DOM"])
+
+ # User did not specify a name, try implementations in arbitrary
+ # order, returning the one that has the required features
+ if isinstance(features, StringTypes):
+ features = _parse_feature_string(features)
+ for creator in registered.values():
+ dom = creator()
+ if _good_enough(dom, features):
+ return dom
+
+ for creator in well_known_implementations.keys():
+ try:
+ dom = getDOMImplementation(name = creator)
+ except StandardError: # typically ImportError, or AttributeError
+ continue
+ if _good_enough(dom, features):
+ return dom
+
+ raise ImportError,"no suitable DOM implementation found"
+
+def _parse_feature_string(s):
+ features = []
+ parts = s.split()
+ i = 0
+ length = len(parts)
+ while i < length:
+ feature = parts[i]
+ if feature[0] in "0123456789":
+ raise ValueError, "bad feature name: %r" % (feature,)
+ i = i + 1
+ version = None
+ if i < length:
+ v = parts[i]
+ if v[0] in "0123456789":
+ i = i + 1
+ version = v
+ features.append((feature, version))
+ return tuple(features)
diff --git a/Lib/xml/dom/expatbuilder.py b/Lib/xml/dom/expatbuilder.py
new file mode 100644
index 0000000..a2f8a33
--- /dev/null
+++ b/Lib/xml/dom/expatbuilder.py
@@ -0,0 +1,983 @@
+"""Facility to use the Expat parser to load a minidom instance
+from a string or file.
+
+This avoids all the overhead of SAX and pulldom to gain performance.
+"""
+
+# Warning!
+#
+# This module is tightly bound to the implementation details of the
+# minidom DOM and can't be used with other DOM implementations. This
+# is due, in part, to a lack of appropriate methods in the DOM (there is
+# no way to create Entity and Notation nodes via the DOM Level 2
+# interface), and for performance. The later is the cause of some fairly
+# cryptic code.
+#
+# Performance hacks:
+#
+# - .character_data_handler() has an extra case in which continuing
+# data is appended to an existing Text node; this can be a
+# speedup since pyexpat can break up character data into multiple
+# callbacks even though we set the buffer_text attribute on the
+# parser. This also gives us the advantage that we don't need a
+# separate normalization pass.
+#
+# - Determining that a node exists is done using an identity comparison
+# with None rather than a truth test; this avoids searching for and
+# calling any methods on the node object if it exists. (A rather
+# nice speedup is achieved this way as well!)
+
+from xml.dom import xmlbuilder, minidom, Node
+from xml.dom import EMPTY_NAMESPACE, EMPTY_PREFIX, XMLNS_NAMESPACE
+from xml.parsers import expat
+from xml.dom.minidom import _append_child, _set_attribute_node
+from xml.dom.NodeFilter import NodeFilter
+
+from xml.dom.minicompat import *
+
+TEXT_NODE = Node.TEXT_NODE
+CDATA_SECTION_NODE = Node.CDATA_SECTION_NODE
+DOCUMENT_NODE = Node.DOCUMENT_NODE
+
+FILTER_ACCEPT = xmlbuilder.DOMBuilderFilter.FILTER_ACCEPT
+FILTER_REJECT = xmlbuilder.DOMBuilderFilter.FILTER_REJECT
+FILTER_SKIP = xmlbuilder.DOMBuilderFilter.FILTER_SKIP
+FILTER_INTERRUPT = xmlbuilder.DOMBuilderFilter.FILTER_INTERRUPT
+
+theDOMImplementation = minidom.getDOMImplementation()
+
+# Expat typename -> TypeInfo
+_typeinfo_map = {
+ "CDATA": minidom.TypeInfo(None, "cdata"),
+ "ENUM": minidom.TypeInfo(None, "enumeration"),
+ "ENTITY": minidom.TypeInfo(None, "entity"),
+ "ENTITIES": minidom.TypeInfo(None, "entities"),
+ "ID": minidom.TypeInfo(None, "id"),
+ "IDREF": minidom.TypeInfo(None, "idref"),
+ "IDREFS": minidom.TypeInfo(None, "idrefs"),
+ "NMTOKEN": minidom.TypeInfo(None, "nmtoken"),
+ "NMTOKENS": minidom.TypeInfo(None, "nmtokens"),
+ }
+
+class ElementInfo(object):
+ __slots__ = '_attr_info', '_model', 'tagName'
+
+ def __init__(self, tagName, model=None):
+ self.tagName = tagName
+ self._attr_info = []
+ self._model = model
+
+ def __getstate__(self):
+ return self._attr_info, self._model, self.tagName
+
+ def __setstate__(self, state):
+ self._attr_info, self._model, self.tagName = state
+
+ def getAttributeType(self, aname):
+ for info in self._attr_info:
+ if info[1] == aname:
+ t = info[-2]
+ if t[0] == "(":
+ return _typeinfo_map["ENUM"]
+ else:
+ return _typeinfo_map[info[-2]]
+ return minidom._no_type
+
+ def getAttributeTypeNS(self, namespaceURI, localName):
+ return minidom._no_type
+
+ def isElementContent(self):
+ if self._model:
+ type = self._model[0]
+ return type not in (expat.model.XML_CTYPE_ANY,
+ expat.model.XML_CTYPE_MIXED)
+ else:
+ return False
+
+ def isEmpty(self):
+ if self._model:
+ return self._model[0] == expat.model.XML_CTYPE_EMPTY
+ else:
+ return False
+
+ def isId(self, aname):
+ for info in self._attr_info:
+ if info[1] == aname:
+ return info[-2] == "ID"
+ return False
+
+ def isIdNS(self, euri, ename, auri, aname):
+ # not sure this is meaningful
+ return self.isId((auri, aname))
+
+def _intern(builder, s):
+ return builder._intern_setdefault(s, s)
+
+def _parse_ns_name(builder, name):
+ assert ' ' in name
+ parts = name.split(' ')
+ intern = builder._intern_setdefault
+ if len(parts) == 3:
+ uri, localname, prefix = parts
+ prefix = intern(prefix, prefix)
+ qname = "%s:%s" % (prefix, localname)
+ qname = intern(qname, qname)
+ localname = intern(localname, localname)
+ else:
+ uri, localname = parts
+ prefix = EMPTY_PREFIX
+ qname = localname = intern(localname, localname)
+ return intern(uri, uri), localname, prefix, qname
+
+
+class ExpatBuilder:
+ """Document builder that uses Expat to build a ParsedXML.DOM document
+ instance."""
+
+ def __init__(self, options=None):
+ if options is None:
+ options = xmlbuilder.Options()
+ self._options = options
+ if self._options.filter is not None:
+ self._filter = FilterVisibilityController(self._options.filter)
+ else:
+ self._filter = None
+ # This *really* doesn't do anything in this case, so
+ # override it with something fast & minimal.
+ self._finish_start_element = id
+ self._parser = None
+ self.reset()
+
+ def createParser(self):
+ """Create a new parser object."""
+ return expat.ParserCreate()
+
+ def getParser(self):
+ """Return the parser object, creating a new one if needed."""
+ if not self._parser:
+ self._parser = self.createParser()
+ self._intern_setdefault = self._parser.intern.setdefault
+ self._parser.buffer_text = True
+ self._parser.ordered_attributes = True
+ self._parser.specified_attributes = True
+ self.install(self._parser)
+ return self._parser
+
+ def reset(self):
+ """Free all data structures used during DOM construction."""
+ self.document = theDOMImplementation.createDocument(
+ EMPTY_NAMESPACE, None, None)
+ self.curNode = self.document
+ self._elem_info = self.document._elem_info
+ self._cdata = False
+
+ def install(self, parser):
+ """Install the callbacks needed to build the DOM into the parser."""
+ # This creates circular references!
+ parser.StartDoctypeDeclHandler = self.start_doctype_decl_handler
+ parser.StartElementHandler = self.first_element_handler
+ parser.EndElementHandler = self.end_element_handler
+ parser.ProcessingInstructionHandler = self.pi_handler
+ if self._options.entities:
+ parser.EntityDeclHandler = self.entity_decl_handler
+ parser.NotationDeclHandler = self.notation_decl_handler
+ if self._options.comments:
+ parser.CommentHandler = self.comment_handler
+ if self._options.cdata_sections:
+ parser.StartCdataSectionHandler = self.start_cdata_section_handler
+ parser.EndCdataSectionHandler = self.end_cdata_section_handler
+ parser.CharacterDataHandler = self.character_data_handler_cdata
+ else:
+ parser.CharacterDataHandler = self.character_data_handler
+ parser.ExternalEntityRefHandler = self.external_entity_ref_handler
+ parser.XmlDeclHandler = self.xml_decl_handler
+ parser.ElementDeclHandler = self.element_decl_handler
+ parser.AttlistDeclHandler = self.attlist_decl_handler
+
+ def parseFile(self, file):
+ """Parse a document from a file object, returning the document
+ node."""
+ parser = self.getParser()
+ first_buffer = True
+ try:
+ while 1:
+ buffer = file.read(16*1024)
+ if not buffer:
+ break
+ parser.Parse(buffer, 0)
+ if first_buffer and self.document.documentElement:
+ self._setup_subset(buffer)
+ first_buffer = False
+ parser.Parse("", True)
+ except ParseEscape:
+ pass
+ doc = self.document
+ self.reset()
+ self._parser = None
+ return doc
+
+ def parseString(self, string):
+ """Parse a document from a string, returning the document node."""
+ parser = self.getParser()
+ try:
+ parser.Parse(string, True)
+ self._setup_subset(string)
+ except ParseEscape:
+ pass
+ doc = self.document
+ self.reset()
+ self._parser = None
+ return doc
+
+ def _setup_subset(self, buffer):
+ """Load the internal subset if there might be one."""
+ if self.document.doctype:
+ extractor = InternalSubsetExtractor()
+ extractor.parseString(buffer)
+ subset = extractor.getSubset()
+ self.document.doctype.internalSubset = subset
+
+ def start_doctype_decl_handler(self, doctypeName, systemId, publicId,
+ has_internal_subset):
+ doctype = self.document.implementation.createDocumentType(
+ doctypeName, publicId, systemId)
+ doctype.ownerDocument = self.document
+ self.document.childNodes.append(doctype)
+ self.document.doctype = doctype
+ if self._filter and self._filter.acceptNode(doctype) == FILTER_REJECT:
+ self.document.doctype = None
+ del self.document.childNodes[-1]
+ doctype = None
+ self._parser.EntityDeclHandler = None
+ self._parser.NotationDeclHandler = None
+ if has_internal_subset:
+ if doctype is not None:
+ doctype.entities._seq = []
+ doctype.notations._seq = []
+ self._parser.CommentHandler = None
+ self._parser.ProcessingInstructionHandler = None
+ self._parser.EndDoctypeDeclHandler = self.end_doctype_decl_handler
+
+ def end_doctype_decl_handler(self):
+ if self._options.comments:
+ self._parser.CommentHandler = self.comment_handler
+ self._parser.ProcessingInstructionHandler = self.pi_handler
+ if not (self._elem_info or self._filter):
+ self._finish_end_element = id
+
+ def pi_handler(self, target, data):
+ node = self.document.createProcessingInstruction(target, data)
+ _append_child(self.curNode, node)
+ if self._filter and self._filter.acceptNode(node) == FILTER_REJECT:
+ self.curNode.removeChild(node)
+
+ def character_data_handler_cdata(self, data):
+ childNodes = self.curNode.childNodes
+ if self._cdata:
+ if ( self._cdata_continue
+ and childNodes[-1].nodeType == CDATA_SECTION_NODE):
+ childNodes[-1].appendData(data)
+ return
+ node = self.document.createCDATASection(data)
+ self._cdata_continue = True
+ elif childNodes and childNodes[-1].nodeType == TEXT_NODE:
+ node = childNodes[-1]
+ value = node.data + data
+ d = node.__dict__
+ d['data'] = d['nodeValue'] = value
+ return
+ else:
+ node = minidom.Text()
+ d = node.__dict__
+ d['data'] = d['nodeValue'] = data
+ d['ownerDocument'] = self.document
+ _append_child(self.curNode, node)
+
+ def character_data_handler(self, data):
+ childNodes = self.curNode.childNodes
+ if childNodes and childNodes[-1].nodeType == TEXT_NODE:
+ node = childNodes[-1]
+ d = node.__dict__
+ d['data'] = d['nodeValue'] = node.data + data
+ return
+ node = minidom.Text()
+ d = node.__dict__
+ d['data'] = d['nodeValue'] = node.data + data
+ d['ownerDocument'] = self.document
+ _append_child(self.curNode, node)
+
+ def entity_decl_handler(self, entityName, is_parameter_entity, value,
+ base, systemId, publicId, notationName):
+ if is_parameter_entity:
+ # we don't care about parameter entities for the DOM
+ return
+ if not self._options.entities:
+ return
+ node = self.document._create_entity(entityName, publicId,
+ systemId, notationName)
+ if value is not None:
+ # internal entity
+ # node *should* be readonly, but we'll cheat
+ child = self.document.createTextNode(value)
+ node.childNodes.append(child)
+ self.document.doctype.entities._seq.append(node)
+ if self._filter and self._filter.acceptNode(node) == FILTER_REJECT:
+ del self.document.doctype.entities._seq[-1]
+
+ def notation_decl_handler(self, notationName, base, systemId, publicId):
+ node = self.document._create_notation(notationName, publicId, systemId)
+ self.document.doctype.notations._seq.append(node)
+ if self._filter and self._filter.acceptNode(node) == FILTER_ACCEPT:
+ del self.document.doctype.notations._seq[-1]
+
+ def comment_handler(self, data):
+ node = self.document.createComment(data)
+ _append_child(self.curNode, node)
+ if self._filter and self._filter.acceptNode(node) == FILTER_REJECT:
+ self.curNode.removeChild(node)
+
+ def start_cdata_section_handler(self):
+ self._cdata = True
+ self._cdata_continue = False
+
+ def end_cdata_section_handler(self):
+ self._cdata = False
+ self._cdata_continue = False
+
+ def external_entity_ref_handler(self, context, base, systemId, publicId):
+ return 1
+
+ def first_element_handler(self, name, attributes):
+ if self._filter is None and not self._elem_info:
+ self._finish_end_element = id
+ self.getParser().StartElementHandler = self.start_element_handler
+ self.start_element_handler(name, attributes)
+
+ def start_element_handler(self, name, attributes):
+ node = self.document.createElement(name)
+ _append_child(self.curNode, node)
+ self.curNode = node
+
+ if attributes:
+ for i in range(0, len(attributes), 2):
+ a = minidom.Attr(attributes[i], EMPTY_NAMESPACE,
+ None, EMPTY_PREFIX)
+ value = attributes[i+1]
+ d = a.childNodes[0].__dict__
+ d['data'] = d['nodeValue'] = value
+ d = a.__dict__
+ d['value'] = d['nodeValue'] = value
+ d['ownerDocument'] = self.document
+ _set_attribute_node(node, a)
+
+ if node is not self.document.documentElement:
+ self._finish_start_element(node)
+
+ def _finish_start_element(self, node):
+ if self._filter:
+ # To be general, we'd have to call isSameNode(), but this
+ # is sufficient for minidom:
+ if node is self.document.documentElement:
+ return
+ filt = self._filter.startContainer(node)
+ if filt == FILTER_REJECT:
+ # ignore this node & all descendents
+ Rejecter(self)
+ elif filt == FILTER_SKIP:
+ # ignore this node, but make it's children become
+ # children of the parent node
+ Skipper(self)
+ else:
+ return
+ self.curNode = node.parentNode
+ node.parentNode.removeChild(node)
+ node.unlink()
+
+ # If this ever changes, Namespaces.end_element_handler() needs to
+ # be changed to match.
+ #
+ def end_element_handler(self, name):
+ curNode = self.curNode
+ self.curNode = curNode.parentNode
+ self._finish_end_element(curNode)
+
+ def _finish_end_element(self, curNode):
+ info = self._elem_info.get(curNode.tagName)
+ if info:
+ self._handle_white_text_nodes(curNode, info)
+ if self._filter:
+ if curNode is self.document.documentElement:
+ return
+ if self._filter.acceptNode(curNode) == FILTER_REJECT:
+ self.curNode.removeChild(curNode)
+ curNode.unlink()
+
+ def _handle_white_text_nodes(self, node, info):
+ if (self._options.whitespace_in_element_content
+ or not info.isElementContent()):
+ return
+
+ # We have element type information and should remove ignorable
+ # whitespace; identify for text nodes which contain only
+ # whitespace.
+ L = []
+ for child in node.childNodes:
+ if child.nodeType == TEXT_NODE and not child.data.strip():
+ L.append(child)
+
+ # Remove ignorable whitespace from the tree.
+ for child in L:
+ node.removeChild(child)
+
+ def element_decl_handler(self, name, model):
+ info = self._elem_info.get(name)
+ if info is None:
+ self._elem_info[name] = ElementInfo(name, model)
+ else:
+ assert info._model is None
+ info._model = model
+
+ def attlist_decl_handler(self, elem, name, type, default, required):
+ info = self._elem_info.get(elem)
+ if info is None:
+ info = ElementInfo(elem)
+ self._elem_info[elem] = info
+ info._attr_info.append(
+ [None, name, None, None, default, 0, type, required])
+
+ def xml_decl_handler(self, version, encoding, standalone):
+ self.document.version = version
+ self.document.encoding = encoding
+ # This is still a little ugly, thanks to the pyexpat API. ;-(
+ if standalone >= 0:
+ if standalone:
+ self.document.standalone = True
+ else:
+ self.document.standalone = False
+
+
+# Don't include FILTER_INTERRUPT, since that's checked separately
+# where allowed.
+_ALLOWED_FILTER_RETURNS = (FILTER_ACCEPT, FILTER_REJECT, FILTER_SKIP)
+
+class FilterVisibilityController(object):
+ """Wrapper around a DOMBuilderFilter which implements the checks
+ to make the whatToShow filter attribute work."""
+
+ __slots__ = 'filter',
+
+ def __init__(self, filter):
+ self.filter = filter
+
+ def startContainer(self, node):
+ mask = self._nodetype_mask[node.nodeType]
+ if self.filter.whatToShow & mask:
+ val = self.filter.startContainer(node)
+ if val == FILTER_INTERRUPT:
+ raise ParseEscape
+ if val not in _ALLOWED_FILTER_RETURNS:
+ raise ValueError, \
+ "startContainer() returned illegal value: " + repr(val)
+ return val
+ else:
+ return FILTER_ACCEPT
+
+ def acceptNode(self, node):
+ mask = self._nodetype_mask[node.nodeType]
+ if self.filter.whatToShow & mask:
+ val = self.filter.acceptNode(node)
+ if val == FILTER_INTERRUPT:
+ raise ParseEscape
+ if val == FILTER_SKIP:
+ # move all child nodes to the parent, and remove this node
+ parent = node.parentNode
+ for child in node.childNodes[:]:
+ parent.appendChild(child)
+ # node is handled by the caller
+ return FILTER_REJECT
+ if val not in _ALLOWED_FILTER_RETURNS:
+ raise ValueError, \
+ "acceptNode() returned illegal value: " + repr(val)
+ return val
+ else:
+ return FILTER_ACCEPT
+
+ _nodetype_mask = {
+ Node.ELEMENT_NODE: NodeFilter.SHOW_ELEMENT,
+ Node.ATTRIBUTE_NODE: NodeFilter.SHOW_ATTRIBUTE,
+ Node.TEXT_NODE: NodeFilter.SHOW_TEXT,
+ Node.CDATA_SECTION_NODE: NodeFilter.SHOW_CDATA_SECTION,
+ Node.ENTITY_REFERENCE_NODE: NodeFilter.SHOW_ENTITY_REFERENCE,
+ Node.ENTITY_NODE: NodeFilter.SHOW_ENTITY,
+ Node.PROCESSING_INSTRUCTION_NODE: NodeFilter.SHOW_PROCESSING_INSTRUCTION,
+ Node.COMMENT_NODE: NodeFilter.SHOW_COMMENT,
+ Node.DOCUMENT_NODE: NodeFilter.SHOW_DOCUMENT,
+ Node.DOCUMENT_TYPE_NODE: NodeFilter.SHOW_DOCUMENT_TYPE,
+ Node.DOCUMENT_FRAGMENT_NODE: NodeFilter.SHOW_DOCUMENT_FRAGMENT,
+ Node.NOTATION_NODE: NodeFilter.SHOW_NOTATION,
+ }
+
+
+class FilterCrutch(object):
+ __slots__ = '_builder', '_level', '_old_start', '_old_end'
+
+ def __init__(self, builder):
+ self._level = 0
+ self._builder = builder
+ parser = builder._parser
+ self._old_start = parser.StartElementHandler
+ self._old_end = parser.EndElementHandler
+ parser.StartElementHandler = self.start_element_handler
+ parser.EndElementHandler = self.end_element_handler
+
+class Rejecter(FilterCrutch):
+ __slots__ = ()
+
+ def __init__(self, builder):
+ FilterCrutch.__init__(self, builder)
+ parser = builder._parser
+ for name in ("ProcessingInstructionHandler",
+ "CommentHandler",
+ "CharacterDataHandler",
+ "StartCdataSectionHandler",
+ "EndCdataSectionHandler",
+ "ExternalEntityRefHandler",
+ ):
+ setattr(parser, name, None)
+
+ def start_element_handler(self, *args):
+ self._level = self._level + 1
+
+ def end_element_handler(self, *args):
+ if self._level == 0:
+ # restore the old handlers
+ parser = self._builder._parser
+ self._builder.install(parser)
+ parser.StartElementHandler = self._old_start
+ parser.EndElementHandler = self._old_end
+ else:
+ self._level = self._level - 1
+
+class Skipper(FilterCrutch):
+ __slots__ = ()
+
+ def start_element_handler(self, *args):
+ node = self._builder.curNode
+ self._old_start(*args)
+ if self._builder.curNode is not node:
+ self._level = self._level + 1
+
+ def end_element_handler(self, *args):
+ if self._level == 0:
+ # We're popping back out of the node we're skipping, so we
+ # shouldn't need to do anything but reset the handlers.
+ self._builder._parser.StartElementHandler = self._old_start
+ self._builder._parser.EndElementHandler = self._old_end
+ self._builder = None
+ else:
+ self._level = self._level - 1
+ self._old_end(*args)
+
+
+# framework document used by the fragment builder.
+# Takes a string for the doctype, subset string, and namespace attrs string.
+
+_FRAGMENT_BUILDER_INTERNAL_SYSTEM_ID = \
+ "http://xml.python.org/entities/fragment-builder/internal"
+
+_FRAGMENT_BUILDER_TEMPLATE = (
+ '''\
+<!DOCTYPE wrapper
+ %%s [
+ <!ENTITY fragment-builder-internal
+ SYSTEM "%s">
+%%s
+]>
+<wrapper %%s
+>&fragment-builder-internal;</wrapper>'''
+ % _FRAGMENT_BUILDER_INTERNAL_SYSTEM_ID)
+
+
+class FragmentBuilder(ExpatBuilder):
+ """Builder which constructs document fragments given XML source
+ text and a context node.
+
+ The context node is expected to provide information about the
+ namespace declarations which are in scope at the start of the
+ fragment.
+ """
+
+ def __init__(self, context, options=None):
+ if context.nodeType == DOCUMENT_NODE:
+ self.originalDocument = context
+ self.context = context
+ else:
+ self.originalDocument = context.ownerDocument
+ self.context = context
+ ExpatBuilder.__init__(self, options)
+
+ def reset(self):
+ ExpatBuilder.reset(self)
+ self.fragment = None
+
+ def parseFile(self, file):
+ """Parse a document fragment from a file object, returning the
+ fragment node."""
+ return self.parseString(file.read())
+
+ def parseString(self, string):
+ """Parse a document fragment from a string, returning the
+ fragment node."""
+ self._source = string
+ parser = self.getParser()
+ doctype = self.originalDocument.doctype
+ ident = ""
+ if doctype:
+ subset = doctype.internalSubset or self._getDeclarations()
+ if doctype.publicId:
+ ident = ('PUBLIC "%s" "%s"'
+ % (doctype.publicId, doctype.systemId))
+ elif doctype.systemId:
+ ident = 'SYSTEM "%s"' % doctype.systemId
+ else:
+ subset = ""
+ nsattrs = self._getNSattrs() # get ns decls from node's ancestors
+ document = _FRAGMENT_BUILDER_TEMPLATE % (ident, subset, nsattrs)
+ try:
+ parser.Parse(document, 1)
+ except:
+ self.reset()
+ raise
+ fragment = self.fragment
+ self.reset()
+## self._parser = None
+ return fragment
+
+ def _getDeclarations(self):
+ """Re-create the internal subset from the DocumentType node.
+
+ This is only needed if we don't already have the
+ internalSubset as a string.
+ """
+ doctype = self.context.ownerDocument.doctype
+ s = ""
+ if doctype:
+ for i in range(doctype.notations.length):
+ notation = doctype.notations.item(i)
+ if s:
+ s = s + "\n "
+ s = "%s<!NOTATION %s" % (s, notation.nodeName)
+ if notation.publicId:
+ s = '%s PUBLIC "%s"\n "%s">' \
+ % (s, notation.publicId, notation.systemId)
+ else:
+ s = '%s SYSTEM "%s">' % (s, notation.systemId)
+ for i in range(doctype.entities.length):
+ entity = doctype.entities.item(i)
+ if s:
+ s = s + "\n "
+ s = "%s<!ENTITY %s" % (s, entity.nodeName)
+ if entity.publicId:
+ s = '%s PUBLIC "%s"\n "%s"' \
+ % (s, entity.publicId, entity.systemId)
+ elif entity.systemId:
+ s = '%s SYSTEM "%s"' % (s, entity.systemId)
+ else:
+ s = '%s "%s"' % (s, entity.firstChild.data)
+ if entity.notationName:
+ s = "%s NOTATION %s" % (s, entity.notationName)
+ s = s + ">"
+ return s
+
+ def _getNSattrs(self):
+ return ""
+
+ def external_entity_ref_handler(self, context, base, systemId, publicId):
+ if systemId == _FRAGMENT_BUILDER_INTERNAL_SYSTEM_ID:
+ # this entref is the one that we made to put the subtree
+ # in; all of our given input is parsed in here.
+ old_document = self.document
+ old_cur_node = self.curNode
+ parser = self._parser.ExternalEntityParserCreate(context)
+ # put the real document back, parse into the fragment to return
+ self.document = self.originalDocument
+ self.fragment = self.document.createDocumentFragment()
+ self.curNode = self.fragment
+ try:
+ parser.Parse(self._source, 1)
+ finally:
+ self.curNode = old_cur_node
+ self.document = old_document
+ self._source = None
+ return -1
+ else:
+ return ExpatBuilder.external_entity_ref_handler(
+ self, context, base, systemId, publicId)
+
+
+class Namespaces:
+ """Mix-in class for builders; adds support for namespaces."""
+
+ def _initNamespaces(self):
+ # list of (prefix, uri) ns declarations. Namespace attrs are
+ # constructed from this and added to the element's attrs.
+ self._ns_ordered_prefixes = []
+
+ def createParser(self):
+ """Create a new namespace-handling parser."""
+ parser = expat.ParserCreate(namespace_separator=" ")
+ parser.namespace_prefixes = True
+ return parser
+
+ def install(self, parser):
+ """Insert the namespace-handlers onto the parser."""
+ ExpatBuilder.install(self, parser)
+ if self._options.namespace_declarations:
+ parser.StartNamespaceDeclHandler = (
+ self.start_namespace_decl_handler)
+
+ def start_namespace_decl_handler(self, prefix, uri):
+ """Push this namespace declaration on our storage."""
+ self._ns_ordered_prefixes.append((prefix, uri))
+
+ def start_element_handler(self, name, attributes):
+ if ' ' in name:
+ uri, localname, prefix, qname = _parse_ns_name(self, name)
+ else:
+ uri = EMPTY_NAMESPACE
+ qname = name
+ localname = None
+ prefix = EMPTY_PREFIX
+ node = minidom.Element(qname, uri, prefix, localname)
+ node.ownerDocument = self.document
+ _append_child(self.curNode, node)
+ self.curNode = node
+
+ if self._ns_ordered_prefixes:
+ for prefix, uri in self._ns_ordered_prefixes:
+ if prefix:
+ a = minidom.Attr(_intern(self, 'xmlns:' + prefix),
+ XMLNS_NAMESPACE, prefix, "xmlns")
+ else:
+ a = minidom.Attr("xmlns", XMLNS_NAMESPACE,
+ "xmlns", EMPTY_PREFIX)
+ d = a.childNodes[0].__dict__
+ d['data'] = d['nodeValue'] = uri
+ d = a.__dict__
+ d['value'] = d['nodeValue'] = uri
+ d['ownerDocument'] = self.document
+ _set_attribute_node(node, a)
+ del self._ns_ordered_prefixes[:]
+
+ if attributes:
+ _attrs = node._attrs
+ _attrsNS = node._attrsNS
+ for i in range(0, len(attributes), 2):
+ aname = attributes[i]
+ value = attributes[i+1]
+ if ' ' in aname:
+ uri, localname, prefix, qname = _parse_ns_name(self, aname)
+ a = minidom.Attr(qname, uri, localname, prefix)
+ _attrs[qname] = a
+ _attrsNS[(uri, localname)] = a
+ else:
+ a = minidom.Attr(aname, EMPTY_NAMESPACE,
+ aname, EMPTY_PREFIX)
+ _attrs[aname] = a
+ _attrsNS[(EMPTY_NAMESPACE, aname)] = a
+ d = a.childNodes[0].__dict__
+ d['data'] = d['nodeValue'] = value
+ d = a.__dict__
+ d['ownerDocument'] = self.document
+ d['value'] = d['nodeValue'] = value
+ d['ownerElement'] = node
+
+ if __debug__:
+ # This only adds some asserts to the original
+ # end_element_handler(), so we only define this when -O is not
+ # used. If changing one, be sure to check the other to see if
+ # it needs to be changed as well.
+ #
+ def end_element_handler(self, name):
+ curNode = self.curNode
+ if ' ' in name:
+ uri, localname, prefix, qname = _parse_ns_name(self, name)
+ assert (curNode.namespaceURI == uri
+ and curNode.localName == localname
+ and curNode.prefix == prefix), \
+ "element stack messed up! (namespace)"
+ else:
+ assert curNode.nodeName == name, \
+ "element stack messed up - bad nodeName"
+ assert curNode.namespaceURI == EMPTY_NAMESPACE, \
+ "element stack messed up - bad namespaceURI"
+ self.curNode = curNode.parentNode
+ self._finish_end_element(curNode)
+
+
+class ExpatBuilderNS(Namespaces, ExpatBuilder):
+ """Document builder that supports namespaces."""
+
+ def reset(self):
+ ExpatBuilder.reset(self)
+ self._initNamespaces()
+
+
+class FragmentBuilderNS(Namespaces, FragmentBuilder):
+ """Fragment builder that supports namespaces."""
+
+ def reset(self):
+ FragmentBuilder.reset(self)
+ self._initNamespaces()
+
+ def _getNSattrs(self):
+ """Return string of namespace attributes from this element and
+ ancestors."""
+ # XXX This needs to be re-written to walk the ancestors of the
+ # context to build up the namespace information from
+ # declarations, elements, and attributes found in context.
+ # Otherwise we have to store a bunch more data on the DOM
+ # (though that *might* be more reliable -- not clear).
+ attrs = ""
+ context = self.context
+ L = []
+ while context:
+ if hasattr(context, '_ns_prefix_uri'):
+ for prefix, uri in context._ns_prefix_uri.items():
+ # add every new NS decl from context to L and attrs string
+ if prefix in L:
+ continue
+ L.append(prefix)
+ if prefix:
+ declname = "xmlns:" + prefix
+ else:
+ declname = "xmlns"
+ if attrs:
+ attrs = "%s\n %s='%s'" % (attrs, declname, uri)
+ else:
+ attrs = " %s='%s'" % (declname, uri)
+ context = context.parentNode
+ return attrs
+
+
+class ParseEscape(Exception):
+ """Exception raised to short-circuit parsing in InternalSubsetExtractor."""
+ pass
+
+class InternalSubsetExtractor(ExpatBuilder):
+ """XML processor which can rip out the internal document type subset."""
+
+ subset = None
+
+ def getSubset(self):
+ """Return the internal subset as a string."""
+ return self.subset
+
+ def parseFile(self, file):
+ try:
+ ExpatBuilder.parseFile(self, file)
+ except ParseEscape:
+ pass
+
+ def parseString(self, string):
+ try:
+ ExpatBuilder.parseString(self, string)
+ except ParseEscape:
+ pass
+
+ def install(self, parser):
+ parser.StartDoctypeDeclHandler = self.start_doctype_decl_handler
+ parser.StartElementHandler = self.start_element_handler
+
+ def start_doctype_decl_handler(self, name, publicId, systemId,
+ has_internal_subset):
+ if has_internal_subset:
+ parser = self.getParser()
+ self.subset = []
+ parser.DefaultHandler = self.subset.append
+ parser.EndDoctypeDeclHandler = self.end_doctype_decl_handler
+ else:
+ raise ParseEscape()
+
+ def end_doctype_decl_handler(self):
+ s = ''.join(self.subset).replace('\r\n', '\n').replace('\r', '\n')
+ self.subset = s
+ raise ParseEscape()
+
+ def start_element_handler(self, name, attrs):
+ raise ParseEscape()
+
+
+def parse(file, namespaces=True):
+ """Parse a document, returning the resulting Document node.
+
+ 'file' may be either a file name or an open file object.
+ """
+ if namespaces:
+ builder = ExpatBuilderNS()
+ else:
+ builder = ExpatBuilder()
+
+ if isinstance(file, StringTypes):
+ fp = open(file, 'rb')
+ try:
+ result = builder.parseFile(fp)
+ finally:
+ fp.close()
+ else:
+ result = builder.parseFile(file)
+ return result
+
+
+def parseString(string, namespaces=True):
+ """Parse a document from a string, returning the resulting
+ Document node.
+ """
+ if namespaces:
+ builder = ExpatBuilderNS()
+ else:
+ builder = ExpatBuilder()
+ return builder.parseString(string)
+
+
+def parseFragment(file, context, namespaces=True):
+ """Parse a fragment of a document, given the context from which it
+ was originally extracted. context should be the parent of the
+ node(s) which are in the fragment.
+
+ 'file' may be either a file name or an open file object.
+ """
+ if namespaces:
+ builder = FragmentBuilderNS(context)
+ else:
+ builder = FragmentBuilder(context)
+
+ if isinstance(file, StringTypes):
+ fp = open(file, 'rb')
+ try:
+ result = builder.parseFile(fp)
+ finally:
+ fp.close()
+ else:
+ result = builder.parseFile(file)
+ return result
+
+
+def parseFragmentString(string, context, namespaces=True):
+ """Parse a fragment of a document from a string, given the context
+ from which it was originally extracted. context should be the
+ parent of the node(s) which are in the fragment.
+ """
+ if namespaces:
+ builder = FragmentBuilderNS(context)
+ else:
+ builder = FragmentBuilder(context)
+ return builder.parseString(string)
+
+
+def makeBuilder(options):
+ """Create a builder based on an Options object."""
+ if options.namespaces:
+ return ExpatBuilderNS(options)
+ else:
+ return ExpatBuilder(options)
diff --git a/Lib/xml/dom/minicompat.py b/Lib/xml/dom/minicompat.py
new file mode 100644
index 0000000..d491fb6
--- /dev/null
+++ b/Lib/xml/dom/minicompat.py
@@ -0,0 +1,110 @@
+"""Python version compatibility support for minidom."""
+
+# This module should only be imported using "import *".
+#
+# The following names are defined:
+#
+# NodeList -- lightest possible NodeList implementation
+#
+# EmptyNodeList -- lightest possible NodeList that is guarateed to
+# remain empty (immutable)
+#
+# StringTypes -- tuple of defined string types
+#
+# defproperty -- function used in conjunction with GetattrMagic;
+# using these together is needed to make them work
+# as efficiently as possible in both Python 2.2+
+# and older versions. For example:
+#
+# class MyClass(GetattrMagic):
+# def _get_myattr(self):
+# return something
+#
+# defproperty(MyClass, "myattr",
+# "return some value")
+#
+# For Python 2.2 and newer, this will construct a
+# property object on the class, which avoids
+# needing to override __getattr__(). It will only
+# work for read-only attributes.
+#
+# For older versions of Python, inheriting from
+# GetattrMagic will use the traditional
+# __getattr__() hackery to achieve the same effect,
+# but less efficiently.
+#
+# defproperty() should be used for each version of
+# the relevant _get_<property>() function.
+
+__all__ = ["NodeList", "EmptyNodeList", "StringTypes", "defproperty"]
+
+import xml.dom
+
+try:
+ unicode
+except NameError:
+ StringTypes = type(''),
+else:
+ StringTypes = type(''), type(unicode(''))
+
+
+class NodeList(list):
+ __slots__ = ()
+
+ def item(self, index):
+ if 0 <= index < len(self):
+ return self[index]
+
+ def _get_length(self):
+ return len(self)
+
+ def _set_length(self, value):
+ raise xml.dom.NoModificationAllowedErr(
+ "attempt to modify read-only attribute 'length'")
+
+ length = property(_get_length, _set_length,
+ doc="The number of nodes in the NodeList.")
+
+ def __getstate__(self):
+ return list(self)
+
+ def __setstate__(self, state):
+ self[:] = state
+
+
+class EmptyNodeList(tuple):
+ __slots__ = ()
+
+ def __add__(self, other):
+ NL = NodeList()
+ NL.extend(other)
+ return NL
+
+ def __radd__(self, other):
+ NL = NodeList()
+ NL.extend(other)
+ return NL
+
+ def item(self, index):
+ return None
+
+ def _get_length(self):
+ return 0
+
+ def _set_length(self, value):
+ raise xml.dom.NoModificationAllowedErr(
+ "attempt to modify read-only attribute 'length'")
+
+ length = property(_get_length, _set_length,
+ doc="The number of nodes in the NodeList.")
+
+
+def defproperty(klass, name, doc):
+ get = getattr(klass, ("_get_" + name)).im_func
+ def set(self, value, name=name):
+ raise xml.dom.NoModificationAllowedErr(
+ "attempt to modify read-only attribute " + repr(name))
+ assert not hasattr(klass, "_set_" + name), \
+ "expected not to find _set_" + name
+ prop = property(get, set, doc=doc)
+ setattr(klass, name, prop)
diff --git a/Lib/xml/dom/minidom.py b/Lib/xml/dom/minidom.py
new file mode 100644
index 0000000..3a35781
--- /dev/null
+++ b/Lib/xml/dom/minidom.py
@@ -0,0 +1,1936 @@
+"""\
+minidom.py -- a lightweight DOM implementation.
+
+parse("foo.xml")
+
+parseString("<foo><bar/></foo>")
+
+Todo:
+=====
+ * convenience methods for getting elements and text.
+ * more testing
+ * bring some of the writer and linearizer code into conformance with this
+ interface
+ * SAX 2 namespaces
+"""
+
+import xml.dom
+
+from xml.dom import EMPTY_NAMESPACE, EMPTY_PREFIX, XMLNS_NAMESPACE, domreg
+from xml.dom.minicompat import *
+from xml.dom.xmlbuilder import DOMImplementationLS, DocumentLS
+
+# This is used by the ID-cache invalidation checks; the list isn't
+# actually complete, since the nodes being checked will never be the
+# DOCUMENT_NODE or DOCUMENT_FRAGMENT_NODE. (The node being checked is
+# the node being added or removed, not the node being modified.)
+#
+_nodeTypes_with_children = (xml.dom.Node.ELEMENT_NODE,
+ xml.dom.Node.ENTITY_REFERENCE_NODE)
+
+
+class Node(xml.dom.Node):
+ namespaceURI = None # this is non-null only for elements and attributes
+ parentNode = None
+ ownerDocument = None
+ nextSibling = None
+ previousSibling = None
+
+ prefix = EMPTY_PREFIX # non-null only for NS elements and attributes
+
+ def __nonzero__(self):
+ return True
+
+ def toxml(self, encoding = None):
+ return self.toprettyxml("", "", encoding)
+
+ def toprettyxml(self, indent="\t", newl="\n", encoding = None):
+ # indent = the indentation string to prepend, per level
+ # newl = the newline string to append
+ writer = _get_StringIO()
+ if encoding is not None:
+ import codecs
+ # Can't use codecs.getwriter to preserve 2.0 compatibility
+ writer = codecs.lookup(encoding)[3](writer)
+ if self.nodeType == Node.DOCUMENT_NODE:
+ # Can pass encoding only to document, to put it into XML header
+ self.writexml(writer, "", indent, newl, encoding)
+ else:
+ self.writexml(writer, "", indent, newl)
+ return writer.getvalue()
+
+ def hasChildNodes(self):
+ if self.childNodes:
+ return True
+ else:
+ return False
+
+ def _get_childNodes(self):
+ return self.childNodes
+
+ def _get_firstChild(self):
+ if self.childNodes:
+ return self.childNodes[0]
+
+ def _get_lastChild(self):
+ if self.childNodes:
+ return self.childNodes[-1]
+
+ def insertBefore(self, newChild, refChild):
+ if newChild.nodeType == self.DOCUMENT_FRAGMENT_NODE:
+ for c in tuple(newChild.childNodes):
+ self.insertBefore(c, refChild)
+ ### The DOM does not clearly specify what to return in this case
+ return newChild
+ if newChild.nodeType not in self._child_node_types:
+ raise xml.dom.HierarchyRequestErr(
+ "%s cannot be child of %s" % (repr(newChild), repr(self)))
+ if newChild.parentNode is not None:
+ newChild.parentNode.removeChild(newChild)
+ if refChild is None:
+ self.appendChild(newChild)
+ else:
+ try:
+ index = self.childNodes.index(refChild)
+ except ValueError:
+ raise xml.dom.NotFoundErr()
+ if newChild.nodeType in _nodeTypes_with_children:
+ _clear_id_cache(self)
+ self.childNodes.insert(index, newChild)
+ newChild.nextSibling = refChild
+ refChild.previousSibling = newChild
+ if index:
+ node = self.childNodes[index-1]
+ node.nextSibling = newChild
+ newChild.previousSibling = node
+ else:
+ newChild.previousSibling = None
+ newChild.parentNode = self
+ return newChild
+
+ def appendChild(self, node):
+ if node.nodeType == self.DOCUMENT_FRAGMENT_NODE:
+ for c in tuple(node.childNodes):
+ self.appendChild(c)
+ ### The DOM does not clearly specify what to return in this case
+ return node
+ if node.nodeType not in self._child_node_types:
+ raise xml.dom.HierarchyRequestErr(
+ "%s cannot be child of %s" % (repr(node), repr(self)))
+ elif node.nodeType in _nodeTypes_with_children:
+ _clear_id_cache(self)
+ if node.parentNode is not None:
+ node.parentNode.removeChild(node)
+ _append_child(self, node)
+ node.nextSibling = None
+ return node
+
+ def replaceChild(self, newChild, oldChild):
+ if newChild.nodeType == self.DOCUMENT_FRAGMENT_NODE:
+ refChild = oldChild.nextSibling
+ self.removeChild(oldChild)
+ return self.insertBefore(newChild, refChild)
+ if newChild.nodeType not in self._child_node_types:
+ raise xml.dom.HierarchyRequestErr(
+ "%s cannot be child of %s" % (repr(newChild), repr(self)))
+ if newChild is oldChild:
+ return
+ if newChild.parentNode is not None:
+ newChild.parentNode.removeChild(newChild)
+ try:
+ index = self.childNodes.index(oldChild)
+ except ValueError:
+ raise xml.dom.NotFoundErr()
+ self.childNodes[index] = newChild
+ newChild.parentNode = self
+ oldChild.parentNode = None
+ if (newChild.nodeType in _nodeTypes_with_children
+ or oldChild.nodeType in _nodeTypes_with_children):
+ _clear_id_cache(self)
+ newChild.nextSibling = oldChild.nextSibling
+ newChild.previousSibling = oldChild.previousSibling
+ oldChild.nextSibling = None
+ oldChild.previousSibling = None
+ if newChild.previousSibling:
+ newChild.previousSibling.nextSibling = newChild
+ if newChild.nextSibling:
+ newChild.nextSibling.previousSibling = newChild
+ return oldChild
+
+ def removeChild(self, oldChild):
+ try:
+ self.childNodes.remove(oldChild)
+ except ValueError:
+ raise xml.dom.NotFoundErr()
+ if oldChild.nextSibling is not None:
+ oldChild.nextSibling.previousSibling = oldChild.previousSibling
+ if oldChild.previousSibling is not None:
+ oldChild.previousSibling.nextSibling = oldChild.nextSibling
+ oldChild.nextSibling = oldChild.previousSibling = None
+ if oldChild.nodeType in _nodeTypes_with_children:
+ _clear_id_cache(self)
+
+ oldChild.parentNode = None
+ return oldChild
+
+ def normalize(self):
+ L = []
+ for child in self.childNodes:
+ if child.nodeType == Node.TEXT_NODE:
+ data = child.data
+ if data and L and L[-1].nodeType == child.nodeType:
+ # collapse text node
+ node = L[-1]
+ node.data = node.data + child.data
+ node.nextSibling = child.nextSibling
+ child.unlink()
+ elif data:
+ if L:
+ L[-1].nextSibling = child
+ child.previousSibling = L[-1]
+ else:
+ child.previousSibling = None
+ L.append(child)
+ else:
+ # empty text node; discard
+ child.unlink()
+ else:
+ if L:
+ L[-1].nextSibling = child
+ child.previousSibling = L[-1]
+ else:
+ child.previousSibling = None
+ L.append(child)
+ if child.nodeType == Node.ELEMENT_NODE:
+ child.normalize()
+ self.childNodes[:] = L
+
+ def cloneNode(self, deep):
+ return _clone_node(self, deep, self.ownerDocument or self)
+
+ def isSupported(self, feature, version):
+ return self.ownerDocument.implementation.hasFeature(feature, version)
+
+ def _get_localName(self):
+ # Overridden in Element and Attr where localName can be Non-Null
+ return None
+
+ # Node interfaces from Level 3 (WD 9 April 2002)
+
+ def isSameNode(self, other):
+ return self is other
+
+ def getInterface(self, feature):
+ if self.isSupported(feature, None):
+ return self
+ else:
+ return None
+
+ # The "user data" functions use a dictionary that is only present
+ # if some user data has been set, so be careful not to assume it
+ # exists.
+
+ def getUserData(self, key):
+ try:
+ return self._user_data[key][0]
+ except (AttributeError, KeyError):
+ return None
+
+ def setUserData(self, key, data, handler):
+ old = None
+ try:
+ d = self._user_data
+ except AttributeError:
+ d = {}
+ self._user_data = d
+ if d.has_key(key):
+ old = d[key][0]
+ if data is None:
+ # ignore handlers passed for None
+ handler = None
+ if old is not None:
+ del d[key]
+ else:
+ d[key] = (data, handler)
+ return old
+
+ def _call_user_data_handler(self, operation, src, dst):
+ if hasattr(self, "_user_data"):
+ for key, (data, handler) in self._user_data.items():
+ if handler is not None:
+ handler.handle(operation, key, data, src, dst)
+
+ # minidom-specific API:
+
+ def unlink(self):
+ self.parentNode = self.ownerDocument = None
+ if self.childNodes:
+ for child in self.childNodes:
+ child.unlink()
+ self.childNodes = NodeList()
+ self.previousSibling = None
+ self.nextSibling = None
+
+defproperty(Node, "firstChild", doc="First child node, or None.")
+defproperty(Node, "lastChild", doc="Last child node, or None.")
+defproperty(Node, "localName", doc="Namespace-local name of this node.")
+
+
+def _append_child(self, node):
+ # fast path with less checks; usable by DOM builders if careful
+ childNodes = self.childNodes
+ if childNodes:
+ last = childNodes[-1]
+ node.__dict__["previousSibling"] = last
+ last.__dict__["nextSibling"] = node
+ childNodes.append(node)
+ node.__dict__["parentNode"] = self
+
+def _in_document(node):
+ # return True iff node is part of a document tree
+ while node is not None:
+ if node.nodeType == Node.DOCUMENT_NODE:
+ return True
+ node = node.parentNode
+ return False
+
+def _write_data(writer, data):
+ "Writes datachars to writer."
+ data = data.replace("&", "&").replace("<", "<")
+ data = data.replace("\"", """).replace(">", ">")
+ writer.write(data)
+
+def _get_elements_by_tagName_helper(parent, name, rc):
+ for node in parent.childNodes:
+ if node.nodeType == Node.ELEMENT_NODE and \
+ (name == "*" or node.tagName == name):
+ rc.append(node)
+ _get_elements_by_tagName_helper(node, name, rc)
+ return rc
+
+def _get_elements_by_tagName_ns_helper(parent, nsURI, localName, rc):
+ for node in parent.childNodes:
+ if node.nodeType == Node.ELEMENT_NODE:
+ if ((localName == "*" or node.localName == localName) and
+ (nsURI == "*" or node.namespaceURI == nsURI)):
+ rc.append(node)
+ _get_elements_by_tagName_ns_helper(node, nsURI, localName, rc)
+ return rc
+
+class DocumentFragment(Node):
+ nodeType = Node.DOCUMENT_FRAGMENT_NODE
+ nodeName = "#document-fragment"
+ nodeValue = None
+ attributes = None
+ parentNode = None
+ _child_node_types = (Node.ELEMENT_NODE,
+ Node.TEXT_NODE,
+ Node.CDATA_SECTION_NODE,
+ Node.ENTITY_REFERENCE_NODE,
+ Node.PROCESSING_INSTRUCTION_NODE,
+ Node.COMMENT_NODE,
+ Node.NOTATION_NODE)
+
+ def __init__(self):
+ self.childNodes = NodeList()
+
+
+class Attr(Node):
+ nodeType = Node.ATTRIBUTE_NODE
+ attributes = None
+ ownerElement = None
+ specified = False
+ _is_id = False
+
+ _child_node_types = (Node.TEXT_NODE, Node.ENTITY_REFERENCE_NODE)
+
+ def __init__(self, qName, namespaceURI=EMPTY_NAMESPACE, localName=None,
+ prefix=None):
+ # skip setattr for performance
+ d = self.__dict__
+ d["nodeName"] = d["name"] = qName
+ d["namespaceURI"] = namespaceURI
+ d["prefix"] = prefix
+ d['childNodes'] = NodeList()
+
+ # Add the single child node that represents the value of the attr
+ self.childNodes.append(Text())
+
+ # nodeValue and value are set elsewhere
+
+ def _get_localName(self):
+ return self.nodeName.split(":", 1)[-1]
+
+ def _get_name(self):
+ return self.name
+
+ def _get_specified(self):
+ return self.specified
+
+ def __setattr__(self, name, value):
+ d = self.__dict__
+ if name in ("value", "nodeValue"):
+ d["value"] = d["nodeValue"] = value
+ d2 = self.childNodes[0].__dict__
+ d2["data"] = d2["nodeValue"] = value
+ if self.ownerElement is not None:
+ _clear_id_cache(self.ownerElement)
+ elif name in ("name", "nodeName"):
+ d["name"] = d["nodeName"] = value
+ if self.ownerElement is not None:
+ _clear_id_cache(self.ownerElement)
+ else:
+ d[name] = value
+
+ def _set_prefix(self, prefix):
+ nsuri = self.namespaceURI
+ if prefix == "xmlns":
+ if nsuri and nsuri != XMLNS_NAMESPACE:
+ raise xml.dom.NamespaceErr(
+ "illegal use of 'xmlns' prefix for the wrong namespace")
+ d = self.__dict__
+ d['prefix'] = prefix
+ if prefix is None:
+ newName = self.localName
+ else:
+ newName = "%s:%s" % (prefix, self.localName)
+ if self.ownerElement:
+ _clear_id_cache(self.ownerElement)
+ d['nodeName'] = d['name'] = newName
+
+ def _set_value(self, value):
+ d = self.__dict__
+ d['value'] = d['nodeValue'] = value
+ if self.ownerElement:
+ _clear_id_cache(self.ownerElement)
+ self.childNodes[0].data = value
+
+ def unlink(self):
+ # This implementation does not call the base implementation
+ # since most of that is not needed, and the expense of the
+ # method call is not warranted. We duplicate the removal of
+ # children, but that's all we needed from the base class.
+ elem = self.ownerElement
+ if elem is not None:
+ del elem._attrs[self.nodeName]
+ del elem._attrsNS[(self.namespaceURI, self.localName)]
+ if self._is_id:
+ self._is_id = False
+ elem._magic_id_nodes -= 1
+ self.ownerDocument._magic_id_count -= 1
+ for child in self.childNodes:
+ child.unlink()
+ del self.childNodes[:]
+
+ def _get_isId(self):
+ if self._is_id:
+ return True
+ doc = self.ownerDocument
+ elem = self.ownerElement
+ if doc is None or elem is None:
+ return False
+
+ info = doc._get_elem_info(elem)
+ if info is None:
+ return False
+ if self.namespaceURI:
+ return info.isIdNS(self.namespaceURI, self.localName)
+ else:
+ return info.isId(self.nodeName)
+
+ def _get_schemaType(self):
+ doc = self.ownerDocument
+ elem = self.ownerElement
+ if doc is None or elem is None:
+ return _no_type
+
+ info = doc._get_elem_info(elem)
+ if info is None:
+ return _no_type
+ if self.namespaceURI:
+ return info.getAttributeTypeNS(self.namespaceURI, self.localName)
+ else:
+ return info.getAttributeType(self.nodeName)
+
+defproperty(Attr, "isId", doc="True if this attribute is an ID.")
+defproperty(Attr, "localName", doc="Namespace-local name of this attribute.")
+defproperty(Attr, "schemaType", doc="Schema type for this attribute.")
+
+
+class NamedNodeMap(object):
+ """The attribute list is a transient interface to the underlying
+ dictionaries. Mutations here will change the underlying element's
+ dictionary.
+
+ Ordering is imposed artificially and does not reflect the order of
+ attributes as found in an input document.
+ """
+
+ __slots__ = ('_attrs', '_attrsNS', '_ownerElement')
+
+ def __init__(self, attrs, attrsNS, ownerElement):
+ self._attrs = attrs
+ self._attrsNS = attrsNS
+ self._ownerElement = ownerElement
+
+ def _get_length(self):
+ return len(self._attrs)
+
+ def item(self, index):
+ try:
+ return self[self._attrs.keys()[index]]
+ except IndexError:
+ return None
+
+ def items(self):
+ L = []
+ for node in self._attrs.values():
+ L.append((node.nodeName, node.value))
+ return L
+
+ def itemsNS(self):
+ L = []
+ for node in self._attrs.values():
+ L.append(((node.namespaceURI, node.localName), node.value))
+ return L
+
+ def has_key(self, key):
+ if isinstance(key, StringTypes):
+ return self._attrs.has_key(key)
+ else:
+ return self._attrsNS.has_key(key)
+
+ def keys(self):
+ return self._attrs.keys()
+
+ def keysNS(self):
+ return self._attrsNS.keys()
+
+ def values(self):
+ return self._attrs.values()
+
+ def get(self, name, value=None):
+ return self._attrs.get(name, value)
+
+ __len__ = _get_length
+
+ def __cmp__(self, other):
+ if self._attrs is getattr(other, "_attrs", None):
+ return 0
+ else:
+ return cmp(id(self), id(other))
+
+ def __getitem__(self, attname_or_tuple):
+ if isinstance(attname_or_tuple, tuple):
+ return self._attrsNS[attname_or_tuple]
+ else:
+ return self._attrs[attname_or_tuple]
+
+ # same as set
+ def __setitem__(self, attname, value):
+ if isinstance(value, StringTypes):
+ try:
+ node = self._attrs[attname]
+ except KeyError:
+ node = Attr(attname)
+ node.ownerDocument = self._ownerElement.ownerDocument
+ self.setNamedItem(node)
+ node.value = value
+ else:
+ if not isinstance(value, Attr):
+ raise TypeError, "value must be a string or Attr object"
+ node = value
+ self.setNamedItem(node)
+
+ def getNamedItem(self, name):
+ try:
+ return self._attrs[name]
+ except KeyError:
+ return None
+
+ def getNamedItemNS(self, namespaceURI, localName):
+ try:
+ return self._attrsNS[(namespaceURI, localName)]
+ except KeyError:
+ return None
+
+ def removeNamedItem(self, name):
+ n = self.getNamedItem(name)
+ if n is not None:
+ _clear_id_cache(self._ownerElement)
+ del self._attrs[n.nodeName]
+ del self._attrsNS[(n.namespaceURI, n.localName)]
+ if n.__dict__.has_key('ownerElement'):
+ n.__dict__['ownerElement'] = None
+ return n
+ else:
+ raise xml.dom.NotFoundErr()
+
+ def removeNamedItemNS(self, namespaceURI, localName):
+ n = self.getNamedItemNS(namespaceURI, localName)
+ if n is not None:
+ _clear_id_cache(self._ownerElement)
+ del self._attrsNS[(n.namespaceURI, n.localName)]
+ del self._attrs[n.nodeName]
+ if n.__dict__.has_key('ownerElement'):
+ n.__dict__['ownerElement'] = None
+ return n
+ else:
+ raise xml.dom.NotFoundErr()
+
+ def setNamedItem(self, node):
+ if not isinstance(node, Attr):
+ raise xml.dom.HierarchyRequestErr(
+ "%s cannot be child of %s" % (repr(node), repr(self)))
+ old = self._attrs.get(node.name)
+ if old:
+ old.unlink()
+ self._attrs[node.name] = node
+ self._attrsNS[(node.namespaceURI, node.localName)] = node
+ node.ownerElement = self._ownerElement
+ _clear_id_cache(node.ownerElement)
+ return old
+
+ def setNamedItemNS(self, node):
+ return self.setNamedItem(node)
+
+ def __delitem__(self, attname_or_tuple):
+ node = self[attname_or_tuple]
+ _clear_id_cache(node.ownerElement)
+ node.unlink()
+
+ def __getstate__(self):
+ return self._attrs, self._attrsNS, self._ownerElement
+
+ def __setstate__(self, state):
+ self._attrs, self._attrsNS, self._ownerElement = state
+
+defproperty(NamedNodeMap, "length",
+ doc="Number of nodes in the NamedNodeMap.")
+
+AttributeList = NamedNodeMap
+
+
+class TypeInfo(object):
+ __slots__ = 'namespace', 'name'
+
+ def __init__(self, namespace, name):
+ self.namespace = namespace
+ self.name = name
+
+ def __repr__(self):
+ if self.namespace:
+ return "<TypeInfo %r (from %r)>" % (self.name, self.namespace)
+ else:
+ return "<TypeInfo %r>" % self.name
+
+ def _get_name(self):
+ return self.name
+
+ def _get_namespace(self):
+ return self.namespace
+
+_no_type = TypeInfo(None, None)
+
+class Element(Node):
+ nodeType = Node.ELEMENT_NODE
+ nodeValue = None
+ schemaType = _no_type
+
+ _magic_id_nodes = 0
+
+ _child_node_types = (Node.ELEMENT_NODE,
+ Node.PROCESSING_INSTRUCTION_NODE,
+ Node.COMMENT_NODE,
+ Node.TEXT_NODE,
+ Node.CDATA_SECTION_NODE,
+ Node.ENTITY_REFERENCE_NODE)
+
+ def __init__(self, tagName, namespaceURI=EMPTY_NAMESPACE, prefix=None,
+ localName=None):
+ self.tagName = self.nodeName = tagName
+ self.prefix = prefix
+ self.namespaceURI = namespaceURI
+ self.childNodes = NodeList()
+
+ self._attrs = {} # attributes are double-indexed:
+ self._attrsNS = {} # tagName -> Attribute
+ # URI,localName -> Attribute
+ # in the future: consider lazy generation
+ # of attribute objects this is too tricky
+ # for now because of headaches with
+ # namespaces.
+
+ def _get_localName(self):
+ return self.tagName.split(":", 1)[-1]
+
+ def _get_tagName(self):
+ return self.tagName
+
+ def unlink(self):
+ for attr in self._attrs.values():
+ attr.unlink()
+ self._attrs = None
+ self._attrsNS = None
+ Node.unlink(self)
+
+ def getAttribute(self, attname):
+ try:
+ return self._attrs[attname].value
+ except KeyError:
+ return ""
+
+ def getAttributeNS(self, namespaceURI, localName):
+ try:
+ return self._attrsNS[(namespaceURI, localName)].value
+ except KeyError:
+ return ""
+
+ def setAttribute(self, attname, value):
+ attr = self.getAttributeNode(attname)
+ if attr is None:
+ attr = Attr(attname)
+ # for performance
+ d = attr.__dict__
+ d["value"] = d["nodeValue"] = value
+ d["ownerDocument"] = self.ownerDocument
+ self.setAttributeNode(attr)
+ elif value != attr.value:
+ d = attr.__dict__
+ d["value"] = d["nodeValue"] = value
+ if attr.isId:
+ _clear_id_cache(self)
+
+ def setAttributeNS(self, namespaceURI, qualifiedName, value):
+ prefix, localname = _nssplit(qualifiedName)
+ attr = self.getAttributeNodeNS(namespaceURI, localname)
+ if attr is None:
+ # for performance
+ attr = Attr(qualifiedName, namespaceURI, localname, prefix)
+ d = attr.__dict__
+ d["prefix"] = prefix
+ d["nodeName"] = qualifiedName
+ d["value"] = d["nodeValue"] = value
+ d["ownerDocument"] = self.ownerDocument
+ self.setAttributeNode(attr)
+ else:
+ d = attr.__dict__
+ if value != attr.value:
+ d["value"] = d["nodeValue"] = value
+ if attr.isId:
+ _clear_id_cache(self)
+ if attr.prefix != prefix:
+ d["prefix"] = prefix
+ d["nodeName"] = qualifiedName
+
+ def getAttributeNode(self, attrname):
+ return self._attrs.get(attrname)
+
+ def getAttributeNodeNS(self, namespaceURI, localName):
+ return self._attrsNS.get((namespaceURI, localName))
+
+ def setAttributeNode(self, attr):
+ if attr.ownerElement not in (None, self):
+ raise xml.dom.InuseAttributeErr("attribute node already owned")
+ old1 = self._attrs.get(attr.name, None)
+ if old1 is not None:
+ self.removeAttributeNode(old1)
+ old2 = self._attrsNS.get((attr.namespaceURI, attr.localName), None)
+ if old2 is not None and old2 is not old1:
+ self.removeAttributeNode(old2)
+ _set_attribute_node(self, attr)
+
+ if old1 is not attr:
+ # It might have already been part of this node, in which case
+ # it doesn't represent a change, and should not be returned.
+ return old1
+ if old2 is not attr:
+ return old2
+
+ setAttributeNodeNS = setAttributeNode
+
+ def removeAttribute(self, name):
+ try:
+ attr = self._attrs[name]
+ except KeyError:
+ raise xml.dom.NotFoundErr()
+ self.removeAttributeNode(attr)
+
+ def removeAttributeNS(self, namespaceURI, localName):
+ try:
+ attr = self._attrsNS[(namespaceURI, localName)]
+ except KeyError:
+ raise xml.dom.NotFoundErr()
+ self.removeAttributeNode(attr)
+
+ def removeAttributeNode(self, node):
+ if node is None:
+ raise xml.dom.NotFoundErr()
+ try:
+ self._attrs[node.name]
+ except KeyError:
+ raise xml.dom.NotFoundErr()
+ _clear_id_cache(self)
+ node.unlink()
+ # Restore this since the node is still useful and otherwise
+ # unlinked
+ node.ownerDocument = self.ownerDocument
+
+ removeAttributeNodeNS = removeAttributeNode
+
+ def hasAttribute(self, name):
+ return self._attrs.has_key(name)
+
+ def hasAttributeNS(self, namespaceURI, localName):
+ return self._attrsNS.has_key((namespaceURI, localName))
+
+ def getElementsByTagName(self, name):
+ return _get_elements_by_tagName_helper(self, name, NodeList())
+
+ def getElementsByTagNameNS(self, namespaceURI, localName):
+ return _get_elements_by_tagName_ns_helper(
+ self, namespaceURI, localName, NodeList())
+
+ def __repr__(self):
+ return "<DOM Element: %s at %#x>" % (self.tagName, id(self))
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ # indent = current indentation
+ # addindent = indentation to add to higher levels
+ # newl = newline string
+ writer.write(indent+"<" + self.tagName)
+
+ attrs = self._get_attributes()
+ a_names = attrs.keys()
+ a_names.sort()
+
+ for a_name in a_names:
+ writer.write(" %s=\"" % a_name)
+ _write_data(writer, attrs[a_name].value)
+ writer.write("\"")
+ if self.childNodes:
+ writer.write(">%s"%(newl))
+ for node in self.childNodes:
+ node.writexml(writer,indent+addindent,addindent,newl)
+ writer.write("%s</%s>%s" % (indent,self.tagName,newl))
+ else:
+ writer.write("/>%s"%(newl))
+
+ def _get_attributes(self):
+ return NamedNodeMap(self._attrs, self._attrsNS, self)
+
+ def hasAttributes(self):
+ if self._attrs:
+ return True
+ else:
+ return False
+
+ # DOM Level 3 attributes, based on the 22 Oct 2002 draft
+
+ def setIdAttribute(self, name):
+ idAttr = self.getAttributeNode(name)
+ self.setIdAttributeNode(idAttr)
+
+ def setIdAttributeNS(self, namespaceURI, localName):
+ idAttr = self.getAttributeNodeNS(namespaceURI, localName)
+ self.setIdAttributeNode(idAttr)
+
+ def setIdAttributeNode(self, idAttr):
+ if idAttr is None or not self.isSameNode(idAttr.ownerElement):
+ raise xml.dom.NotFoundErr()
+ if _get_containing_entref(self) is not None:
+ raise xml.dom.NoModificationAllowedErr()
+ if not idAttr._is_id:
+ idAttr.__dict__['_is_id'] = True
+ self._magic_id_nodes += 1
+ self.ownerDocument._magic_id_count += 1
+ _clear_id_cache(self)
+
+defproperty(Element, "attributes",
+ doc="NamedNodeMap of attributes on the element.")
+defproperty(Element, "localName",
+ doc="Namespace-local name of this element.")
+
+
+def _set_attribute_node(element, attr):
+ _clear_id_cache(element)
+ element._attrs[attr.name] = attr
+ element._attrsNS[(attr.namespaceURI, attr.localName)] = attr
+
+ # This creates a circular reference, but Element.unlink()
+ # breaks the cycle since the references to the attribute
+ # dictionaries are tossed.
+ attr.__dict__['ownerElement'] = element
+
+
+class Childless:
+ """Mixin that makes childless-ness easy to implement and avoids
+ the complexity of the Node methods that deal with children.
+ """
+
+ attributes = None
+ childNodes = EmptyNodeList()
+ firstChild = None
+ lastChild = None
+
+ def _get_firstChild(self):
+ return None
+
+ def _get_lastChild(self):
+ return None
+
+ def appendChild(self, node):
+ raise xml.dom.HierarchyRequestErr(
+ self.nodeName + " nodes cannot have children")
+
+ def hasChildNodes(self):
+ return False
+
+ def insertBefore(self, newChild, refChild):
+ raise xml.dom.HierarchyRequestErr(
+ self.nodeName + " nodes do not have children")
+
+ def removeChild(self, oldChild):
+ raise xml.dom.NotFoundErr(
+ self.nodeName + " nodes do not have children")
+
+ def replaceChild(self, newChild, oldChild):
+ raise xml.dom.HierarchyRequestErr(
+ self.nodeName + " nodes do not have children")
+
+
+class ProcessingInstruction(Childless, Node):
+ nodeType = Node.PROCESSING_INSTRUCTION_NODE
+
+ def __init__(self, target, data):
+ self.target = self.nodeName = target
+ self.data = self.nodeValue = data
+
+ def _get_data(self):
+ return self.data
+ def _set_data(self, value):
+ d = self.__dict__
+ d['data'] = d['nodeValue'] = value
+
+ def _get_target(self):
+ return self.target
+ def _set_target(self, value):
+ d = self.__dict__
+ d['target'] = d['nodeName'] = value
+
+ def __setattr__(self, name, value):
+ if name == "data" or name == "nodeValue":
+ self.__dict__['data'] = self.__dict__['nodeValue'] = value
+ elif name == "target" or name == "nodeName":
+ self.__dict__['target'] = self.__dict__['nodeName'] = value
+ else:
+ self.__dict__[name] = value
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ writer.write("%s<?%s %s?>%s" % (indent,self.target, self.data, newl))
+
+
+class CharacterData(Childless, Node):
+ def _get_length(self):
+ return len(self.data)
+ __len__ = _get_length
+
+ def _get_data(self):
+ return self.__dict__['data']
+ def _set_data(self, data):
+ d = self.__dict__
+ d['data'] = d['nodeValue'] = data
+
+ _get_nodeValue = _get_data
+ _set_nodeValue = _set_data
+
+ def __setattr__(self, name, value):
+ if name == "data" or name == "nodeValue":
+ self.__dict__['data'] = self.__dict__['nodeValue'] = value
+ else:
+ self.__dict__[name] = value
+
+ def __repr__(self):
+ data = self.data
+ if len(data) > 10:
+ dotdotdot = "..."
+ else:
+ dotdotdot = ""
+ return "<DOM %s node \"%s%s\">" % (
+ self.__class__.__name__, data[0:10], dotdotdot)
+
+ def substringData(self, offset, count):
+ if offset < 0:
+ raise xml.dom.IndexSizeErr("offset cannot be negative")
+ if offset >= len(self.data):
+ raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
+ if count < 0:
+ raise xml.dom.IndexSizeErr("count cannot be negative")
+ return self.data[offset:offset+count]
+
+ def appendData(self, arg):
+ self.data = self.data + arg
+
+ def insertData(self, offset, arg):
+ if offset < 0:
+ raise xml.dom.IndexSizeErr("offset cannot be negative")
+ if offset >= len(self.data):
+ raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
+ if arg:
+ self.data = "%s%s%s" % (
+ self.data[:offset], arg, self.data[offset:])
+
+ def deleteData(self, offset, count):
+ if offset < 0:
+ raise xml.dom.IndexSizeErr("offset cannot be negative")
+ if offset >= len(self.data):
+ raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
+ if count < 0:
+ raise xml.dom.IndexSizeErr("count cannot be negative")
+ if count:
+ self.data = self.data[:offset] + self.data[offset+count:]
+
+ def replaceData(self, offset, count, arg):
+ if offset < 0:
+ raise xml.dom.IndexSizeErr("offset cannot be negative")
+ if offset >= len(self.data):
+ raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
+ if count < 0:
+ raise xml.dom.IndexSizeErr("count cannot be negative")
+ if count:
+ self.data = "%s%s%s" % (
+ self.data[:offset], arg, self.data[offset+count:])
+
+defproperty(CharacterData, "length", doc="Length of the string data.")
+
+
+class Text(CharacterData):
+ # Make sure we don't add an instance __dict__ if we don't already
+ # have one, at least when that's possible:
+ # XXX this does not work, CharacterData is an old-style class
+ # __slots__ = ()
+
+ nodeType = Node.TEXT_NODE
+ nodeName = "#text"
+ attributes = None
+
+ def splitText(self, offset):
+ if offset < 0 or offset > len(self.data):
+ raise xml.dom.IndexSizeErr("illegal offset value")
+ newText = self.__class__()
+ newText.data = self.data[offset:]
+ newText.ownerDocument = self.ownerDocument
+ next = self.nextSibling
+ if self.parentNode and self in self.parentNode.childNodes:
+ if next is None:
+ self.parentNode.appendChild(newText)
+ else:
+ self.parentNode.insertBefore(newText, next)
+ self.data = self.data[:offset]
+ return newText
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ _write_data(writer, "%s%s%s"%(indent, self.data, newl))
+
+ # DOM Level 3 (WD 9 April 2002)
+
+ def _get_wholeText(self):
+ L = [self.data]
+ n = self.previousSibling
+ while n is not None:
+ if n.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
+ L.insert(0, n.data)
+ n = n.previousSibling
+ else:
+ break
+ n = self.nextSibling
+ while n is not None:
+ if n.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
+ L.append(n.data)
+ n = n.nextSibling
+ else:
+ break
+ return ''.join(L)
+
+ def replaceWholeText(self, content):
+ # XXX This needs to be seriously changed if minidom ever
+ # supports EntityReference nodes.
+ parent = self.parentNode
+ n = self.previousSibling
+ while n is not None:
+ if n.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
+ next = n.previousSibling
+ parent.removeChild(n)
+ n = next
+ else:
+ break
+ n = self.nextSibling
+ if not content:
+ parent.removeChild(self)
+ while n is not None:
+ if n.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
+ next = n.nextSibling
+ parent.removeChild(n)
+ n = next
+ else:
+ break
+ if content:
+ d = self.__dict__
+ d['data'] = content
+ d['nodeValue'] = content
+ return self
+ else:
+ return None
+
+ def _get_isWhitespaceInElementContent(self):
+ if self.data.strip():
+ return False
+ elem = _get_containing_element(self)
+ if elem is None:
+ return False
+ info = self.ownerDocument._get_elem_info(elem)
+ if info is None:
+ return False
+ else:
+ return info.isElementContent()
+
+defproperty(Text, "isWhitespaceInElementContent",
+ doc="True iff this text node contains only whitespace"
+ " and is in element content.")
+defproperty(Text, "wholeText",
+ doc="The text of all logically-adjacent text nodes.")
+
+
+def _get_containing_element(node):
+ c = node.parentNode
+ while c is not None:
+ if c.nodeType == Node.ELEMENT_NODE:
+ return c
+ c = c.parentNode
+ return None
+
+def _get_containing_entref(node):
+ c = node.parentNode
+ while c is not None:
+ if c.nodeType == Node.ENTITY_REFERENCE_NODE:
+ return c
+ c = c.parentNode
+ return None
+
+
+class Comment(Childless, CharacterData):
+ nodeType = Node.COMMENT_NODE
+ nodeName = "#comment"
+
+ def __init__(self, data):
+ self.data = self.nodeValue = data
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ writer.write("%s<!--%s-->%s" % (indent, self.data, newl))
+
+
+class CDATASection(Text):
+ # Make sure we don't add an instance __dict__ if we don't already
+ # have one, at least when that's possible:
+ # XXX this does not work, Text is an old-style class
+ # __slots__ = ()
+
+ nodeType = Node.CDATA_SECTION_NODE
+ nodeName = "#cdata-section"
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ if self.data.find("]]>") >= 0:
+ raise ValueError("']]>' not allowed in a CDATA section")
+ writer.write("<![CDATA[%s]]>" % self.data)
+
+
+class ReadOnlySequentialNamedNodeMap(object):
+ __slots__ = '_seq',
+
+ def __init__(self, seq=()):
+ # seq should be a list or tuple
+ self._seq = seq
+
+ def __len__(self):
+ return len(self._seq)
+
+ def _get_length(self):
+ return len(self._seq)
+
+ def getNamedItem(self, name):
+ for n in self._seq:
+ if n.nodeName == name:
+ return n
+
+ def getNamedItemNS(self, namespaceURI, localName):
+ for n in self._seq:
+ if n.namespaceURI == namespaceURI and n.localName == localName:
+ return n
+
+ def __getitem__(self, name_or_tuple):
+ if isinstance(name_or_tuple, tuple):
+ node = self.getNamedItemNS(*name_or_tuple)
+ else:
+ node = self.getNamedItem(name_or_tuple)
+ if node is None:
+ raise KeyError, name_or_tuple
+ return node
+
+ def item(self, index):
+ if index < 0:
+ return None
+ try:
+ return self._seq[index]
+ except IndexError:
+ return None
+
+ def removeNamedItem(self, name):
+ raise xml.dom.NoModificationAllowedErr(
+ "NamedNodeMap instance is read-only")
+
+ def removeNamedItemNS(self, namespaceURI, localName):
+ raise xml.dom.NoModificationAllowedErr(
+ "NamedNodeMap instance is read-only")
+
+ def setNamedItem(self, node):
+ raise xml.dom.NoModificationAllowedErr(
+ "NamedNodeMap instance is read-only")
+
+ def setNamedItemNS(self, node):
+ raise xml.dom.NoModificationAllowedErr(
+ "NamedNodeMap instance is read-only")
+
+ def __getstate__(self):
+ return [self._seq]
+
+ def __setstate__(self, state):
+ self._seq = state[0]
+
+defproperty(ReadOnlySequentialNamedNodeMap, "length",
+ doc="Number of entries in the NamedNodeMap.")
+
+
+class Identified:
+ """Mix-in class that supports the publicId and systemId attributes."""
+
+ # XXX this does not work, this is an old-style class
+ # __slots__ = 'publicId', 'systemId'
+
+ def _identified_mixin_init(self, publicId, systemId):
+ self.publicId = publicId
+ self.systemId = systemId
+
+ def _get_publicId(self):
+ return self.publicId
+
+ def _get_systemId(self):
+ return self.systemId
+
+class DocumentType(Identified, Childless, Node):
+ nodeType = Node.DOCUMENT_TYPE_NODE
+ nodeValue = None
+ name = None
+ publicId = None
+ systemId = None
+ internalSubset = None
+
+ def __init__(self, qualifiedName):
+ self.entities = ReadOnlySequentialNamedNodeMap()
+ self.notations = ReadOnlySequentialNamedNodeMap()
+ if qualifiedName:
+ prefix, localname = _nssplit(qualifiedName)
+ self.name = localname
+ self.nodeName = self.name
+
+ def _get_internalSubset(self):
+ return self.internalSubset
+
+ def cloneNode(self, deep):
+ if self.ownerDocument is None:
+ # it's ok
+ clone = DocumentType(None)
+ clone.name = self.name
+ clone.nodeName = self.name
+ operation = xml.dom.UserDataHandler.NODE_CLONED
+ if deep:
+ clone.entities._seq = []
+ clone.notations._seq = []
+ for n in self.notations._seq:
+ notation = Notation(n.nodeName, n.publicId, n.systemId)
+ clone.notations._seq.append(notation)
+ n._call_user_data_handler(operation, n, notation)
+ for e in self.entities._seq:
+ entity = Entity(e.nodeName, e.publicId, e.systemId,
+ e.notationName)
+ entity.actualEncoding = e.actualEncoding
+ entity.encoding = e.encoding
+ entity.version = e.version
+ clone.entities._seq.append(entity)
+ e._call_user_data_handler(operation, n, entity)
+ self._call_user_data_handler(operation, self, clone)
+ return clone
+ else:
+ return None
+
+ def writexml(self, writer, indent="", addindent="", newl=""):
+ writer.write("<!DOCTYPE ")
+ writer.write(self.name)
+ if self.publicId:
+ writer.write("%s PUBLIC '%s'%s '%s'"
+ % (newl, self.publicId, newl, self.systemId))
+ elif self.systemId:
+ writer.write("%s SYSTEM '%s'" % (newl, self.systemId))
+ if self.internalSubset is not None:
+ writer.write(" [")
+ writer.write(self.internalSubset)
+ writer.write("]")
+ writer.write(">"+newl)
+
+class Entity(Identified, Node):
+ attributes = None
+ nodeType = Node.ENTITY_NODE
+ nodeValue = None
+
+ actualEncoding = None
+ encoding = None
+ version = None
+
+ def __init__(self, name, publicId, systemId, notation):
+ self.nodeName = name
+ self.notationName = notation
+ self.childNodes = NodeList()
+ self._identified_mixin_init(publicId, systemId)
+
+ def _get_actualEncoding(self):
+ return self.actualEncoding
+
+ def _get_encoding(self):
+ return self.encoding
+
+ def _get_version(self):
+ return self.version
+
+ def appendChild(self, newChild):
+ raise xml.dom.HierarchyRequestErr(
+ "cannot append children to an entity node")
+
+ def insertBefore(self, newChild, refChild):
+ raise xml.dom.HierarchyRequestErr(
+ "cannot insert children below an entity node")
+
+ def removeChild(self, oldChild):
+ raise xml.dom.HierarchyRequestErr(
+ "cannot remove children from an entity node")
+
+ def replaceChild(self, newChild, oldChild):
+ raise xml.dom.HierarchyRequestErr(
+ "cannot replace children of an entity node")
+
+class Notation(Identified, Childless, Node):
+ nodeType = Node.NOTATION_NODE
+ nodeValue = None
+
+ def __init__(self, name, publicId, systemId):
+ self.nodeName = name
+ self._identified_mixin_init(publicId, systemId)
+
+
+class DOMImplementation(DOMImplementationLS):
+ _features = [("core", "1.0"),
+ ("core", "2.0"),
+ ("core", "3.0"),
+ ("core", None),
+ ("xml", "1.0"),
+ ("xml", "2.0"),
+ ("xml", "3.0"),
+ ("xml", None),
+ ("ls-load", "3.0"),
+ ("ls-load", None),
+ ]
+
+ def hasFeature(self, feature, version):
+ if version == "":
+ version = None
+ return (feature.lower(), version) in self._features
+
+ def createDocument(self, namespaceURI, qualifiedName, doctype):
+ if doctype and doctype.parentNode is not None:
+ raise xml.dom.WrongDocumentErr(
+ "doctype object owned by another DOM tree")
+ doc = self._create_document()
+
+ add_root_element = not (namespaceURI is None
+ and qualifiedName is None
+ and doctype is None)
+
+ if not qualifiedName and add_root_element:
+ # The spec is unclear what to raise here; SyntaxErr
+ # would be the other obvious candidate. Since Xerces raises
+ # InvalidCharacterErr, and since SyntaxErr is not listed
+ # for createDocument, that seems to be the better choice.
+ # XXX: need to check for illegal characters here and in
+ # createElement.
+
+ # DOM Level III clears this up when talking about the return value
+ # of this function. If namespaceURI, qName and DocType are
+ # Null the document is returned without a document element
+ # Otherwise if doctype or namespaceURI are not None
+ # Then we go back to the above problem
+ raise xml.dom.InvalidCharacterErr("Element with no name")
+
+ if add_root_element:
+ prefix, localname = _nssplit(qualifiedName)
+ if prefix == "xml" \
+ and namespaceURI != "http://www.w3.org/XML/1998/namespace":
+ raise xml.dom.NamespaceErr("illegal use of 'xml' prefix")
+ if prefix and not namespaceURI:
+ raise xml.dom.NamespaceErr(
+ "illegal use of prefix without namespaces")
+ element = doc.createElementNS(namespaceURI, qualifiedName)
+ if doctype:
+ doc.appendChild(doctype)
+ doc.appendChild(element)
+
+ if doctype:
+ doctype.parentNode = doctype.ownerDocument = doc
+
+ doc.doctype = doctype
+ doc.implementation = self
+ return doc
+
+ def createDocumentType(self, qualifiedName, publicId, systemId):
+ doctype = DocumentType(qualifiedName)
+ doctype.publicId = publicId
+ doctype.systemId = systemId
+ return doctype
+
+ # DOM Level 3 (WD 9 April 2002)
+
+ def getInterface(self, feature):
+ if self.hasFeature(feature, None):
+ return self
+ else:
+ return None
+
+ # internal
+ def _create_document(self):
+ return Document()
+
+class ElementInfo(object):
+ """Object that represents content-model information for an element.
+
+ This implementation is not expected to be used in practice; DOM
+ builders should provide implementations which do the right thing
+ using information available to it.
+
+ """
+
+ __slots__ = 'tagName',
+
+ def __init__(self, name):
+ self.tagName = name
+
+ def getAttributeType(self, aname):
+ return _no_type
+
+ def getAttributeTypeNS(self, namespaceURI, localName):
+ return _no_type
+
+ def isElementContent(self):
+ return False
+
+ def isEmpty(self):
+ """Returns true iff this element is declared to have an EMPTY
+ content model."""
+ return False
+
+ def isId(self, aname):
+ """Returns true iff the named attribte is a DTD-style ID."""
+ return False
+
+ def isIdNS(self, namespaceURI, localName):
+ """Returns true iff the identified attribute is a DTD-style ID."""
+ return False
+
+ def __getstate__(self):
+ return self.tagName
+
+ def __setstate__(self, state):
+ self.tagName = state
+
+def _clear_id_cache(node):
+ if node.nodeType == Node.DOCUMENT_NODE:
+ node._id_cache.clear()
+ node._id_search_stack = None
+ elif _in_document(node):
+ node.ownerDocument._id_cache.clear()
+ node.ownerDocument._id_search_stack= None
+
+class Document(Node, DocumentLS):
+ _child_node_types = (Node.ELEMENT_NODE, Node.PROCESSING_INSTRUCTION_NODE,
+ Node.COMMENT_NODE, Node.DOCUMENT_TYPE_NODE)
+
+ nodeType = Node.DOCUMENT_NODE
+ nodeName = "#document"
+ nodeValue = None
+ attributes = None
+ doctype = None
+ parentNode = None
+ previousSibling = nextSibling = None
+
+ implementation = DOMImplementation()
+
+ # Document attributes from Level 3 (WD 9 April 2002)
+
+ actualEncoding = None
+ encoding = None
+ standalone = None
+ version = None
+ strictErrorChecking = False
+ errorHandler = None
+ documentURI = None
+
+ _magic_id_count = 0
+
+ def __init__(self):
+ self.childNodes = NodeList()
+ # mapping of (namespaceURI, localName) -> ElementInfo
+ # and tagName -> ElementInfo
+ self._elem_info = {}
+ self._id_cache = {}
+ self._id_search_stack = None
+
+ def _get_elem_info(self, element):
+ if element.namespaceURI:
+ key = element.namespaceURI, element.localName
+ else:
+ key = element.tagName
+ return self._elem_info.get(key)
+
+ def _get_actualEncoding(self):
+ return self.actualEncoding
+
+ def _get_doctype(self):
+ return self.doctype
+
+ def _get_documentURI(self):
+ return self.documentURI
+
+ def _get_encoding(self):
+ return self.encoding
+
+ def _get_errorHandler(self):
+ return self.errorHandler
+
+ def _get_standalone(self):
+ return self.standalone
+
+ def _get_strictErrorChecking(self):
+ return self.strictErrorChecking
+
+ def _get_version(self):
+ return self.version
+
+ def appendChild(self, node):
+ if node.nodeType not in self._child_node_types:
+ raise xml.dom.HierarchyRequestErr(
+ "%s cannot be child of %s" % (repr(node), repr(self)))
+ if node.parentNode is not None:
+ # This needs to be done before the next test since this
+ # may *be* the document element, in which case it should
+ # end up re-ordered to the end.
+ node.parentNode.removeChild(node)
+
+ if node.nodeType == Node.ELEMENT_NODE \
+ and self._get_documentElement():
+ raise xml.dom.HierarchyRequestErr(
+ "two document elements disallowed")
+ return Node.appendChild(self, node)
+
+ def removeChild(self, oldChild):
+ try:
+ self.childNodes.remove(oldChild)
+ except ValueError:
+ raise xml.dom.NotFoundErr()
+ oldChild.nextSibling = oldChild.previousSibling = None
+ oldChild.parentNode = None
+ if self.documentElement is oldChild:
+ self.documentElement = None
+
+ return oldChild
+
+ def _get_documentElement(self):
+ for node in self.childNodes:
+ if node.nodeType == Node.ELEMENT_NODE:
+ return node
+
+ def unlink(self):
+ if self.doctype is not None:
+ self.doctype.unlink()
+ self.doctype = None
+ Node.unlink(self)
+
+ def cloneNode(self, deep):
+ if not deep:
+ return None
+ clone = self.implementation.createDocument(None, None, None)
+ clone.encoding = self.encoding
+ clone.standalone = self.standalone
+ clone.version = self.version
+ for n in self.childNodes:
+ childclone = _clone_node(n, deep, clone)
+ assert childclone.ownerDocument.isSameNode(clone)
+ clone.childNodes.append(childclone)
+ if childclone.nodeType == Node.DOCUMENT_NODE:
+ assert clone.documentElement is None
+ elif childclone.nodeType == Node.DOCUMENT_TYPE_NODE:
+ assert clone.doctype is None
+ clone.doctype = childclone
+ childclone.parentNode = clone
+ self._call_user_data_handler(xml.dom.UserDataHandler.NODE_CLONED,
+ self, clone)
+ return clone
+
+ def createDocumentFragment(self):
+ d = DocumentFragment()
+ d.ownerDocument = self
+ return d
+
+ def createElement(self, tagName):
+ e = Element(tagName)
+ e.ownerDocument = self
+ return e
+
+ def createTextNode(self, data):
+ if not isinstance(data, StringTypes):
+ raise TypeError, "node contents must be a string"
+ t = Text()
+ t.data = data
+ t.ownerDocument = self
+ return t
+
+ def createCDATASection(self, data):
+ if not isinstance(data, StringTypes):
+ raise TypeError, "node contents must be a string"
+ c = CDATASection()
+ c.data = data
+ c.ownerDocument = self
+ return c
+
+ def createComment(self, data):
+ c = Comment(data)
+ c.ownerDocument = self
+ return c
+
+ def createProcessingInstruction(self, target, data):
+ p = ProcessingInstruction(target, data)
+ p.ownerDocument = self
+ return p
+
+ def createAttribute(self, qName):
+ a = Attr(qName)
+ a.ownerDocument = self
+ a.value = ""
+ return a
+
+ def createElementNS(self, namespaceURI, qualifiedName):
+ prefix, localName = _nssplit(qualifiedName)
+ e = Element(qualifiedName, namespaceURI, prefix)
+ e.ownerDocument = self
+ return e
+
+ def createAttributeNS(self, namespaceURI, qualifiedName):
+ prefix, localName = _nssplit(qualifiedName)
+ a = Attr(qualifiedName, namespaceURI, localName, prefix)
+ a.ownerDocument = self
+ a.value = ""
+ return a
+
+ # A couple of implementation-specific helpers to create node types
+ # not supported by the W3C DOM specs:
+
+ def _create_entity(self, name, publicId, systemId, notationName):
+ e = Entity(name, publicId, systemId, notationName)
+ e.ownerDocument = self
+ return e
+
+ def _create_notation(self, name, publicId, systemId):
+ n = Notation(name, publicId, systemId)
+ n.ownerDocument = self
+ return n
+
+ def getElementById(self, id):
+ if self._id_cache.has_key(id):
+ return self._id_cache[id]
+ if not (self._elem_info or self._magic_id_count):
+ return None
+
+ stack = self._id_search_stack
+ if stack is None:
+ # we never searched before, or the cache has been cleared
+ stack = [self.documentElement]
+ self._id_search_stack = stack
+ elif not stack:
+ # Previous search was completed and cache is still valid;
+ # no matching node.
+ return None
+
+ result = None
+ while stack:
+ node = stack.pop()
+ # add child elements to stack for continued searching
+ stack.extend([child for child in node.childNodes
+ if child.nodeType in _nodeTypes_with_children])
+ # check this node
+ info = self._get_elem_info(node)
+ if info:
+ # We have to process all ID attributes before
+ # returning in order to get all the attributes set to
+ # be IDs using Element.setIdAttribute*().
+ for attr in node.attributes.values():
+ if attr.namespaceURI:
+ if info.isIdNS(attr.namespaceURI, attr.localName):
+ self._id_cache[attr.value] = node
+ if attr.value == id:
+ result = node
+ elif not node._magic_id_nodes:
+ break
+ elif info.isId(attr.name):
+ self._id_cache[attr.value] = node
+ if attr.value == id:
+ result = node
+ elif not node._magic_id_nodes:
+ break
+ elif attr._is_id:
+ self._id_cache[attr.value] = node
+ if attr.value == id:
+ result = node
+ elif node._magic_id_nodes == 1:
+ break
+ elif node._magic_id_nodes:
+ for attr in node.attributes.values():
+ if attr._is_id:
+ self._id_cache[attr.value] = node
+ if attr.value == id:
+ result = node
+ if result is not None:
+ break
+ return result
+
+ def getElementsByTagName(self, name):
+ return _get_elements_by_tagName_helper(self, name, NodeList())
+
+ def getElementsByTagNameNS(self, namespaceURI, localName):
+ return _get_elements_by_tagName_ns_helper(
+ self, namespaceURI, localName, NodeList())
+
+ def isSupported(self, feature, version):
+ return self.implementation.hasFeature(feature, version)
+
+ def importNode(self, node, deep):
+ if node.nodeType == Node.DOCUMENT_NODE:
+ raise xml.dom.NotSupportedErr("cannot import document nodes")
+ elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
+ raise xml.dom.NotSupportedErr("cannot import document type nodes")
+ return _clone_node(node, deep, self)
+
+ def writexml(self, writer, indent="", addindent="", newl="",
+ encoding = None):
+ if encoding is None:
+ writer.write('<?xml version="1.0" ?>'+newl)
+ else:
+ writer.write('<?xml version="1.0" encoding="%s"?>%s' % (encoding, newl))
+ for node in self.childNodes:
+ node.writexml(writer, indent, addindent, newl)
+
+ # DOM Level 3 (WD 9 April 2002)
+
+ def renameNode(self, n, namespaceURI, name):
+ if n.ownerDocument is not self:
+ raise xml.dom.WrongDocumentErr(
+ "cannot rename nodes from other documents;\n"
+ "expected %s,\nfound %s" % (self, n.ownerDocument))
+ if n.nodeType not in (Node.ELEMENT_NODE, Node.ATTRIBUTE_NODE):
+ raise xml.dom.NotSupportedErr(
+ "renameNode() only applies to element and attribute nodes")
+ if namespaceURI != EMPTY_NAMESPACE:
+ if ':' in name:
+ prefix, localName = name.split(':', 1)
+ if ( prefix == "xmlns"
+ and namespaceURI != xml.dom.XMLNS_NAMESPACE):
+ raise xml.dom.NamespaceErr(
+ "illegal use of 'xmlns' prefix")
+ else:
+ if ( name == "xmlns"
+ and namespaceURI != xml.dom.XMLNS_NAMESPACE
+ and n.nodeType == Node.ATTRIBUTE_NODE):
+ raise xml.dom.NamespaceErr(
+ "illegal use of the 'xmlns' attribute")
+ prefix = None
+ localName = name
+ else:
+ prefix = None
+ localName = None
+ if n.nodeType == Node.ATTRIBUTE_NODE:
+ element = n.ownerElement
+ if element is not None:
+ is_id = n._is_id
+ element.removeAttributeNode(n)
+ else:
+ element = None
+ # avoid __setattr__
+ d = n.__dict__
+ d['prefix'] = prefix
+ d['localName'] = localName
+ d['namespaceURI'] = namespaceURI
+ d['nodeName'] = name
+ if n.nodeType == Node.ELEMENT_NODE:
+ d['tagName'] = name
+ else:
+ # attribute node
+ d['name'] = name
+ if element is not None:
+ element.setAttributeNode(n)
+ if is_id:
+ element.setIdAttributeNode(n)
+ # It's not clear from a semantic perspective whether we should
+ # call the user data handlers for the NODE_RENAMED event since
+ # we're re-using the existing node. The draft spec has been
+ # interpreted as meaning "no, don't call the handler unless a
+ # new node is created."
+ return n
+
+defproperty(Document, "documentElement",
+ doc="Top-level element of this document.")
+
+
+def _clone_node(node, deep, newOwnerDocument):
+ """
+ Clone a node and give it the new owner document.
+ Called by Node.cloneNode and Document.importNode
+ """
+ if node.ownerDocument.isSameNode(newOwnerDocument):
+ operation = xml.dom.UserDataHandler.NODE_CLONED
+ else:
+ operation = xml.dom.UserDataHandler.NODE_IMPORTED
+ if node.nodeType == Node.ELEMENT_NODE:
+ clone = newOwnerDocument.createElementNS(node.namespaceURI,
+ node.nodeName)
+ for attr in node.attributes.values():
+ clone.setAttributeNS(attr.namespaceURI, attr.nodeName, attr.value)
+ a = clone.getAttributeNodeNS(attr.namespaceURI, attr.localName)
+ a.specified = attr.specified
+
+ if deep:
+ for child in node.childNodes:
+ c = _clone_node(child, deep, newOwnerDocument)
+ clone.appendChild(c)
+
+ elif node.nodeType == Node.DOCUMENT_FRAGMENT_NODE:
+ clone = newOwnerDocument.createDocumentFragment()
+ if deep:
+ for child in node.childNodes:
+ c = _clone_node(child, deep, newOwnerDocument)
+ clone.appendChild(c)
+
+ elif node.nodeType == Node.TEXT_NODE:
+ clone = newOwnerDocument.createTextNode(node.data)
+ elif node.nodeType == Node.CDATA_SECTION_NODE:
+ clone = newOwnerDocument.createCDATASection(node.data)
+ elif node.nodeType == Node.PROCESSING_INSTRUCTION_NODE:
+ clone = newOwnerDocument.createProcessingInstruction(node.target,
+ node.data)
+ elif node.nodeType == Node.COMMENT_NODE:
+ clone = newOwnerDocument.createComment(node.data)
+ elif node.nodeType == Node.ATTRIBUTE_NODE:
+ clone = newOwnerDocument.createAttributeNS(node.namespaceURI,
+ node.nodeName)
+ clone.specified = True
+ clone.value = node.value
+ elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
+ assert node.ownerDocument is not newOwnerDocument
+ operation = xml.dom.UserDataHandler.NODE_IMPORTED
+ clone = newOwnerDocument.implementation.createDocumentType(
+ node.name, node.publicId, node.systemId)
+ clone.ownerDocument = newOwnerDocument
+ if deep:
+ clone.entities._seq = []
+ clone.notations._seq = []
+ for n in node.notations._seq:
+ notation = Notation(n.nodeName, n.publicId, n.systemId)
+ notation.ownerDocument = newOwnerDocument
+ clone.notations._seq.append(notation)
+ if hasattr(n, '_call_user_data_handler'):
+ n._call_user_data_handler(operation, n, notation)
+ for e in node.entities._seq:
+ entity = Entity(e.nodeName, e.publicId, e.systemId,
+ e.notationName)
+ entity.actualEncoding = e.actualEncoding
+ entity.encoding = e.encoding
+ entity.version = e.version
+ entity.ownerDocument = newOwnerDocument
+ clone.entities._seq.append(entity)
+ if hasattr(e, '_call_user_data_handler'):
+ e._call_user_data_handler(operation, n, entity)
+ else:
+ # Note the cloning of Document and DocumentType nodes is
+ # implemenetation specific. minidom handles those cases
+ # directly in the cloneNode() methods.
+ raise xml.dom.NotSupportedErr("Cannot clone node %s" % repr(node))
+
+ # Check for _call_user_data_handler() since this could conceivably
+ # used with other DOM implementations (one of the FourThought
+ # DOMs, perhaps?).
+ if hasattr(node, '_call_user_data_handler'):
+ node._call_user_data_handler(operation, node, clone)
+ return clone
+
+
+def _nssplit(qualifiedName):
+ fields = qualifiedName.split(':', 1)
+ if len(fields) == 2:
+ return fields
+ else:
+ return (None, fields[0])
+
+
+def _get_StringIO():
+ # we can't use cStringIO since it doesn't support Unicode strings
+ from StringIO import StringIO
+ return StringIO()
+
+def _do_pulldom_parse(func, args, kwargs):
+ events = func(*args, **kwargs)
+ toktype, rootNode = events.getEvent()
+ events.expandNode(rootNode)
+ events.clear()
+ return rootNode
+
+def parse(file, parser=None, bufsize=None):
+ """Parse a file into a DOM by filename or file object."""
+ if parser is None and not bufsize:
+ from xml.dom import expatbuilder
+ return expatbuilder.parse(file)
+ else:
+ from xml.dom import pulldom
+ return _do_pulldom_parse(pulldom.parse, (file,),
+ {'parser': parser, 'bufsize': bufsize})
+
+def parseString(string, parser=None):
+ """Parse a file into a DOM from a string."""
+ if parser is None:
+ from xml.dom import expatbuilder
+ return expatbuilder.parseString(string)
+ else:
+ from xml.dom import pulldom
+ return _do_pulldom_parse(pulldom.parseString, (string,),
+ {'parser': parser})
+
+def getDOMImplementation(features=None):
+ if features:
+ if isinstance(features, StringTypes):
+ features = domreg._parse_feature_string(features)
+ for f, v in features:
+ if not Document.implementation.hasFeature(f, v):
+ return None
+ return Document.implementation
diff --git a/Lib/xml/dom/pulldom.py b/Lib/xml/dom/pulldom.py
new file mode 100644
index 0000000..18f49b5
--- /dev/null
+++ b/Lib/xml/dom/pulldom.py
@@ -0,0 +1,351 @@
+import xml.sax
+import xml.sax.handler
+import types
+
+try:
+ _StringTypes = [types.StringType, types.UnicodeType]
+except AttributeError:
+ _StringTypes = [types.StringType]
+
+START_ELEMENT = "START_ELEMENT"
+END_ELEMENT = "END_ELEMENT"
+COMMENT = "COMMENT"
+START_DOCUMENT = "START_DOCUMENT"
+END_DOCUMENT = "END_DOCUMENT"
+PROCESSING_INSTRUCTION = "PROCESSING_INSTRUCTION"
+IGNORABLE_WHITESPACE = "IGNORABLE_WHITESPACE"
+CHARACTERS = "CHARACTERS"
+
+class PullDOM(xml.sax.ContentHandler):
+ _locator = None
+ document = None
+
+ def __init__(self, documentFactory=None):
+ from xml.dom import XML_NAMESPACE
+ self.documentFactory = documentFactory
+ self.firstEvent = [None, None]
+ self.lastEvent = self.firstEvent
+ self.elementStack = []
+ self.push = self.elementStack.append
+ try:
+ self.pop = self.elementStack.pop
+ except AttributeError:
+ # use class' pop instead
+ pass
+ self._ns_contexts = [{XML_NAMESPACE:'xml'}] # contains uri -> prefix dicts
+ self._current_context = self._ns_contexts[-1]
+ self.pending_events = []
+
+ def pop(self):
+ result = self.elementStack[-1]
+ del self.elementStack[-1]
+ return result
+
+ def setDocumentLocator(self, locator):
+ self._locator = locator
+
+ def startPrefixMapping(self, prefix, uri):
+ if not hasattr(self, '_xmlns_attrs'):
+ self._xmlns_attrs = []
+ self._xmlns_attrs.append((prefix or 'xmlns', uri))
+ self._ns_contexts.append(self._current_context.copy())
+ self._current_context[uri] = prefix or None
+
+ def endPrefixMapping(self, prefix):
+ self._current_context = self._ns_contexts.pop()
+
+ def startElementNS(self, name, tagName , attrs):
+ # Retrieve xml namespace declaration attributes.
+ xmlns_uri = 'http://www.w3.org/2000/xmlns/'
+ xmlns_attrs = getattr(self, '_xmlns_attrs', None)
+ if xmlns_attrs is not None:
+ for aname, value in xmlns_attrs:
+ attrs._attrs[(xmlns_uri, aname)] = value
+ self._xmlns_attrs = []
+ uri, localname = name
+ if uri:
+ # When using namespaces, the reader may or may not
+ # provide us with the original name. If not, create
+ # *a* valid tagName from the current context.
+ if tagName is None:
+ prefix = self._current_context[uri]
+ if prefix:
+ tagName = prefix + ":" + localname
+ else:
+ tagName = localname
+ if self.document:
+ node = self.document.createElementNS(uri, tagName)
+ else:
+ node = self.buildDocument(uri, tagName)
+ else:
+ # When the tagname is not prefixed, it just appears as
+ # localname
+ if self.document:
+ node = self.document.createElement(localname)
+ else:
+ node = self.buildDocument(None, localname)
+
+ for aname,value in attrs.items():
+ a_uri, a_localname = aname
+ if a_uri == xmlns_uri:
+ if a_localname == 'xmlns':
+ qname = a_localname
+ else:
+ qname = 'xmlns:' + a_localname
+ attr = self.document.createAttributeNS(a_uri, qname)
+ node.setAttributeNodeNS(attr)
+ elif a_uri:
+ prefix = self._current_context[a_uri]
+ if prefix:
+ qname = prefix + ":" + a_localname
+ else:
+ qname = a_localname
+ attr = self.document.createAttributeNS(a_uri, qname)
+ node.setAttributeNodeNS(attr)
+ else:
+ attr = self.document.createAttribute(a_localname)
+ node.setAttributeNode(attr)
+ attr.value = value
+
+ self.lastEvent[1] = [(START_ELEMENT, node), None]
+ self.lastEvent = self.lastEvent[1]
+ self.push(node)
+
+ def endElementNS(self, name, tagName):
+ self.lastEvent[1] = [(END_ELEMENT, self.pop()), None]
+ self.lastEvent = self.lastEvent[1]
+
+ def startElement(self, name, attrs):
+ if self.document:
+ node = self.document.createElement(name)
+ else:
+ node = self.buildDocument(None, name)
+
+ for aname,value in attrs.items():
+ attr = self.document.createAttribute(aname)
+ attr.value = value
+ node.setAttributeNode(attr)
+
+ self.lastEvent[1] = [(START_ELEMENT, node), None]
+ self.lastEvent = self.lastEvent[1]
+ self.push(node)
+
+ def endElement(self, name):
+ self.lastEvent[1] = [(END_ELEMENT, self.pop()), None]
+ self.lastEvent = self.lastEvent[1]
+
+ def comment(self, s):
+ if self.document:
+ node = self.document.createComment(s)
+ self.lastEvent[1] = [(COMMENT, node), None]
+ self.lastEvent = self.lastEvent[1]
+ else:
+ event = [(COMMENT, s), None]
+ self.pending_events.append(event)
+
+ def processingInstruction(self, target, data):
+ if self.document:
+ node = self.document.createProcessingInstruction(target, data)
+ self.lastEvent[1] = [(PROCESSING_INSTRUCTION, node), None]
+ self.lastEvent = self.lastEvent[1]
+ else:
+ event = [(PROCESSING_INSTRUCTION, target, data), None]
+ self.pending_events.append(event)
+
+ def ignorableWhitespace(self, chars):
+ node = self.document.createTextNode(chars)
+ self.lastEvent[1] = [(IGNORABLE_WHITESPACE, node), None]
+ self.lastEvent = self.lastEvent[1]
+
+ def characters(self, chars):
+ node = self.document.createTextNode(chars)
+ self.lastEvent[1] = [(CHARACTERS, node), None]
+ self.lastEvent = self.lastEvent[1]
+
+ def startDocument(self):
+ if self.documentFactory is None:
+ import xml.dom.minidom
+ self.documentFactory = xml.dom.minidom.Document.implementation
+
+ def buildDocument(self, uri, tagname):
+ # Can't do that in startDocument, since we need the tagname
+ # XXX: obtain DocumentType
+ node = self.documentFactory.createDocument(uri, tagname, None)
+ self.document = node
+ self.lastEvent[1] = [(START_DOCUMENT, node), None]
+ self.lastEvent = self.lastEvent[1]
+ self.push(node)
+ # Put everything we have seen so far into the document
+ for e in self.pending_events:
+ if e[0][0] == PROCESSING_INSTRUCTION:
+ _,target,data = e[0]
+ n = self.document.createProcessingInstruction(target, data)
+ e[0] = (PROCESSING_INSTRUCTION, n)
+ elif e[0][0] == COMMENT:
+ n = self.document.createComment(e[0][1])
+ e[0] = (COMMENT, n)
+ else:
+ raise AssertionError("Unknown pending event ",e[0][0])
+ self.lastEvent[1] = e
+ self.lastEvent = e
+ self.pending_events = None
+ return node.firstChild
+
+ def endDocument(self):
+ self.lastEvent[1] = [(END_DOCUMENT, self.document), None]
+ self.pop()
+
+ def clear(self):
+ "clear(): Explicitly release parsing structures"
+ self.document = None
+
+class ErrorHandler:
+ def warning(self, exception):
+ print exception
+ def error(self, exception):
+ raise exception
+ def fatalError(self, exception):
+ raise exception
+
+class DOMEventStream:
+ def __init__(self, stream, parser, bufsize):
+ self.stream = stream
+ self.parser = parser
+ self.bufsize = bufsize
+ if not hasattr(self.parser, 'feed'):
+ self.getEvent = self._slurp
+ self.reset()
+
+ def reset(self):
+ self.pulldom = PullDOM()
+ # This content handler relies on namespace support
+ self.parser.setFeature(xml.sax.handler.feature_namespaces, 1)
+ self.parser.setContentHandler(self.pulldom)
+
+ def __getitem__(self, pos):
+ rc = self.getEvent()
+ if rc:
+ return rc
+ raise IndexError
+
+ def next(self):
+ rc = self.getEvent()
+ if rc:
+ return rc
+ raise StopIteration
+
+ def __iter__(self):
+ return self
+
+ def expandNode(self, node):
+ event = self.getEvent()
+ parents = [node]
+ while event:
+ token, cur_node = event
+ if cur_node is node:
+ return
+ if token != END_ELEMENT:
+ parents[-1].appendChild(cur_node)
+ if token == START_ELEMENT:
+ parents.append(cur_node)
+ elif token == END_ELEMENT:
+ del parents[-1]
+ event = self.getEvent()
+
+ def getEvent(self):
+ # use IncrementalParser interface, so we get the desired
+ # pull effect
+ if not self.pulldom.firstEvent[1]:
+ self.pulldom.lastEvent = self.pulldom.firstEvent
+ while not self.pulldom.firstEvent[1]:
+ buf = self.stream.read(self.bufsize)
+ if not buf:
+ self.parser.close()
+ return None
+ self.parser.feed(buf)
+ rc = self.pulldom.firstEvent[1][0]
+ self.pulldom.firstEvent[1] = self.pulldom.firstEvent[1][1]
+ return rc
+
+ def _slurp(self):
+ """ Fallback replacement for getEvent() using the
+ standard SAX2 interface, which means we slurp the
+ SAX events into memory (no performance gain, but
+ we are compatible to all SAX parsers).
+ """
+ self.parser.parse(self.stream)
+ self.getEvent = self._emit
+ return self._emit()
+
+ def _emit(self):
+ """ Fallback replacement for getEvent() that emits
+ the events that _slurp() read previously.
+ """
+ rc = self.pulldom.firstEvent[1][0]
+ self.pulldom.firstEvent[1] = self.pulldom.firstEvent[1][1]
+ return rc
+
+ def clear(self):
+ """clear(): Explicitly release parsing objects"""
+ self.pulldom.clear()
+ del self.pulldom
+ self.parser = None
+ self.stream = None
+
+class SAX2DOM(PullDOM):
+
+ def startElementNS(self, name, tagName , attrs):
+ PullDOM.startElementNS(self, name, tagName, attrs)
+ curNode = self.elementStack[-1]
+ parentNode = self.elementStack[-2]
+ parentNode.appendChild(curNode)
+
+ def startElement(self, name, attrs):
+ PullDOM.startElement(self, name, attrs)
+ curNode = self.elementStack[-1]
+ parentNode = self.elementStack[-2]
+ parentNode.appendChild(curNode)
+
+ def processingInstruction(self, target, data):
+ PullDOM.processingInstruction(self, target, data)
+ node = self.lastEvent[0][1]
+ parentNode = self.elementStack[-1]
+ parentNode.appendChild(node)
+
+ def ignorableWhitespace(self, chars):
+ PullDOM.ignorableWhitespace(self, chars)
+ node = self.lastEvent[0][1]
+ parentNode = self.elementStack[-1]
+ parentNode.appendChild(node)
+
+ def characters(self, chars):
+ PullDOM.characters(self, chars)
+ node = self.lastEvent[0][1]
+ parentNode = self.elementStack[-1]
+ parentNode.appendChild(node)
+
+
+default_bufsize = (2 ** 14) - 20
+
+def parse(stream_or_string, parser=None, bufsize=None):
+ if bufsize is None:
+ bufsize = default_bufsize
+ if type(stream_or_string) in _StringTypes:
+ stream = open(stream_or_string)
+ else:
+ stream = stream_or_string
+ if not parser:
+ parser = xml.sax.make_parser()
+ return DOMEventStream(stream, parser, bufsize)
+
+def parseString(string, parser=None):
+ try:
+ from cStringIO import StringIO
+ except ImportError:
+ from StringIO import StringIO
+
+ bufsize = len(string)
+ buf = StringIO(string)
+ if not parser:
+ parser = xml.sax.make_parser()
+ return DOMEventStream(buf, parser, bufsize)
diff --git a/Lib/xml/dom/xmlbuilder.py b/Lib/xml/dom/xmlbuilder.py
new file mode 100644
index 0000000..ac1d448
--- /dev/null
+++ b/Lib/xml/dom/xmlbuilder.py
@@ -0,0 +1,386 @@
+"""Implementation of the DOM Level 3 'LS-Load' feature."""
+
+import copy
+import xml.dom
+
+from xml.dom.NodeFilter import NodeFilter
+
+
+__all__ = ["DOMBuilder", "DOMEntityResolver", "DOMInputSource"]
+
+
+class Options:
+ """Features object that has variables set for each DOMBuilder feature.
+
+ The DOMBuilder class uses an instance of this class to pass settings to
+ the ExpatBuilder class.
+ """
+
+ # Note that the DOMBuilder class in LoadSave constrains which of these
+ # values can be set using the DOM Level 3 LoadSave feature.
+
+ namespaces = 1
+ namespace_declarations = True
+ validation = False
+ external_parameter_entities = True
+ external_general_entities = True
+ external_dtd_subset = True
+ validate_if_schema = False
+ validate = False
+ datatype_normalization = False
+ create_entity_ref_nodes = True
+ entities = True
+ whitespace_in_element_content = True
+ cdata_sections = True
+ comments = True
+ charset_overrides_xml_encoding = True
+ infoset = False
+ supported_mediatypes_only = False
+
+ errorHandler = None
+ filter = None
+
+
+class DOMBuilder:
+ entityResolver = None
+ errorHandler = None
+ filter = None
+
+ ACTION_REPLACE = 1
+ ACTION_APPEND_AS_CHILDREN = 2
+ ACTION_INSERT_AFTER = 3
+ ACTION_INSERT_BEFORE = 4
+
+ _legal_actions = (ACTION_REPLACE, ACTION_APPEND_AS_CHILDREN,
+ ACTION_INSERT_AFTER, ACTION_INSERT_BEFORE)
+
+ def __init__(self):
+ self._options = Options()
+
+ def _get_entityResolver(self):
+ return self.entityResolver
+ def _set_entityResolver(self, entityResolver):
+ self.entityResolver = entityResolver
+
+ def _get_errorHandler(self):
+ return self.errorHandler
+ def _set_errorHandler(self, errorHandler):
+ self.errorHandler = errorHandler
+
+ def _get_filter(self):
+ return self.filter
+ def _set_filter(self, filter):
+ self.filter = filter
+
+ def setFeature(self, name, state):
+ if self.supportsFeature(name):
+ state = state and 1 or 0
+ try:
+ settings = self._settings[(_name_xform(name), state)]
+ except KeyError:
+ raise xml.dom.NotSupportedErr(
+ "unsupported feature: %r" % (name,))
+ else:
+ for name, value in settings:
+ setattr(self._options, name, value)
+ else:
+ raise xml.dom.NotFoundErr("unknown feature: " + repr(name))
+
+ def supportsFeature(self, name):
+ return hasattr(self._options, _name_xform(name))
+
+ def canSetFeature(self, name, state):
+ key = (_name_xform(name), state and 1 or 0)
+ return self._settings.has_key(key)
+
+ # This dictionary maps from (feature,value) to a list of
+ # (option,value) pairs that should be set on the Options object.
+ # If a (feature,value) setting is not in this dictionary, it is
+ # not supported by the DOMBuilder.
+ #
+ _settings = {
+ ("namespace_declarations", 0): [
+ ("namespace_declarations", 0)],
+ ("namespace_declarations", 1): [
+ ("namespace_declarations", 1)],
+ ("validation", 0): [
+ ("validation", 0)],
+ ("external_general_entities", 0): [
+ ("external_general_entities", 0)],
+ ("external_general_entities", 1): [
+ ("external_general_entities", 1)],
+ ("external_parameter_entities", 0): [
+ ("external_parameter_entities", 0)],
+ ("external_parameter_entities", 1): [
+ ("external_parameter_entities", 1)],
+ ("validate_if_schema", 0): [
+ ("validate_if_schema", 0)],
+ ("create_entity_ref_nodes", 0): [
+ ("create_entity_ref_nodes", 0)],
+ ("create_entity_ref_nodes", 1): [
+ ("create_entity_ref_nodes", 1)],
+ ("entities", 0): [
+ ("create_entity_ref_nodes", 0),
+ ("entities", 0)],
+ ("entities", 1): [
+ ("entities", 1)],
+ ("whitespace_in_element_content", 0): [
+ ("whitespace_in_element_content", 0)],
+ ("whitespace_in_element_content", 1): [
+ ("whitespace_in_element_content", 1)],
+ ("cdata_sections", 0): [
+ ("cdata_sections", 0)],
+ ("cdata_sections", 1): [
+ ("cdata_sections", 1)],
+ ("comments", 0): [
+ ("comments", 0)],
+ ("comments", 1): [
+ ("comments", 1)],
+ ("charset_overrides_xml_encoding", 0): [
+ ("charset_overrides_xml_encoding", 0)],
+ ("charset_overrides_xml_encoding", 1): [
+ ("charset_overrides_xml_encoding", 1)],
+ ("infoset", 0): [],
+ ("infoset", 1): [
+ ("namespace_declarations", 0),
+ ("validate_if_schema", 0),
+ ("create_entity_ref_nodes", 0),
+ ("entities", 0),
+ ("cdata_sections", 0),
+ ("datatype_normalization", 1),
+ ("whitespace_in_element_content", 1),
+ ("comments", 1),
+ ("charset_overrides_xml_encoding", 1)],
+ ("supported_mediatypes_only", 0): [
+ ("supported_mediatypes_only", 0)],
+ ("namespaces", 0): [
+ ("namespaces", 0)],
+ ("namespaces", 1): [
+ ("namespaces", 1)],
+ }
+
+ def getFeature(self, name):
+ xname = _name_xform(name)
+ try:
+ return getattr(self._options, xname)
+ except AttributeError:
+ if name == "infoset":
+ options = self._options
+ return (options.datatype_normalization
+ and options.whitespace_in_element_content
+ and options.comments
+ and options.charset_overrides_xml_encoding
+ and not (options.namespace_declarations
+ or options.validate_if_schema
+ or options.create_entity_ref_nodes
+ or options.entities
+ or options.cdata_sections))
+ raise xml.dom.NotFoundErr("feature %s not known" % repr(name))
+
+ def parseURI(self, uri):
+ if self.entityResolver:
+ input = self.entityResolver.resolveEntity(None, uri)
+ else:
+ input = DOMEntityResolver().resolveEntity(None, uri)
+ return self.parse(input)
+
+ def parse(self, input):
+ options = copy.copy(self._options)
+ options.filter = self.filter
+ options.errorHandler = self.errorHandler
+ fp = input.byteStream
+ if fp is None and options.systemId:
+ import urllib2
+ fp = urllib2.urlopen(input.systemId)
+ return self._parse_bytestream(fp, options)
+
+ def parseWithContext(self, input, cnode, action):
+ if action not in self._legal_actions:
+ raise ValueError("not a legal action")
+ raise NotImplementedError("Haven't written this yet...")
+
+ def _parse_bytestream(self, stream, options):
+ import xml.dom.expatbuilder
+ builder = xml.dom.expatbuilder.makeBuilder(options)
+ return builder.parseFile(stream)
+
+
+def _name_xform(name):
+ return name.lower().replace('-', '_')
+
+
+class DOMEntityResolver(object):
+ __slots__ = '_opener',
+
+ def resolveEntity(self, publicId, systemId):
+ assert systemId is not None
+ source = DOMInputSource()
+ source.publicId = publicId
+ source.systemId = systemId
+ source.byteStream = self._get_opener().open(systemId)
+
+ # determine the encoding if the transport provided it
+ source.encoding = self._guess_media_encoding(source)
+
+ # determine the base URI is we can
+ import posixpath, urlparse
+ parts = urlparse.urlparse(systemId)
+ scheme, netloc, path, params, query, fragment = parts
+ # XXX should we check the scheme here as well?
+ if path and not path.endswith("/"):
+ path = posixpath.dirname(path) + "/"
+ parts = scheme, netloc, path, params, query, fragment
+ source.baseURI = urlparse.urlunparse(parts)
+
+ return source
+
+ def _get_opener(self):
+ try:
+ return self._opener
+ except AttributeError:
+ self._opener = self._create_opener()
+ return self._opener
+
+ def _create_opener(self):
+ import urllib2
+ return urllib2.build_opener()
+
+ def _guess_media_encoding(self, source):
+ info = source.byteStream.info()
+ if info.has_key("Content-Type"):
+ for param in info.getplist():
+ if param.startswith("charset="):
+ return param.split("=", 1)[1].lower()
+
+
+class DOMInputSource(object):
+ __slots__ = ('byteStream', 'characterStream', 'stringData',
+ 'encoding', 'publicId', 'systemId', 'baseURI')
+
+ def __init__(self):
+ self.byteStream = None
+ self.characterStream = None
+ self.stringData = None
+ self.encoding = None
+ self.publicId = None
+ self.systemId = None
+ self.baseURI = None
+
+ def _get_byteStream(self):
+ return self.byteStream
+ def _set_byteStream(self, byteStream):
+ self.byteStream = byteStream
+
+ def _get_characterStream(self):
+ return self.characterStream
+ def _set_characterStream(self, characterStream):
+ self.characterStream = characterStream
+
+ def _get_stringData(self):
+ return self.stringData
+ def _set_stringData(self, data):
+ self.stringData = data
+
+ def _get_encoding(self):
+ return self.encoding
+ def _set_encoding(self, encoding):
+ self.encoding = encoding
+
+ def _get_publicId(self):
+ return self.publicId
+ def _set_publicId(self, publicId):
+ self.publicId = publicId
+
+ def _get_systemId(self):
+ return self.systemId
+ def _set_systemId(self, systemId):
+ self.systemId = systemId
+
+ def _get_baseURI(self):
+ return self.baseURI
+ def _set_baseURI(self, uri):
+ self.baseURI = uri
+
+
+class DOMBuilderFilter:
+ """Element filter which can be used to tailor construction of
+ a DOM instance.
+ """
+
+ # There's really no need for this class; concrete implementations
+ # should just implement the endElement() and startElement()
+ # methods as appropriate. Using this makes it easy to only
+ # implement one of them.
+
+ FILTER_ACCEPT = 1
+ FILTER_REJECT = 2
+ FILTER_SKIP = 3
+ FILTER_INTERRUPT = 4
+
+ whatToShow = NodeFilter.SHOW_ALL
+
+ def _get_whatToShow(self):
+ return self.whatToShow
+
+ def acceptNode(self, element):
+ return self.FILTER_ACCEPT
+
+ def startContainer(self, element):
+ return self.FILTER_ACCEPT
+
+del NodeFilter
+
+
+class DocumentLS:
+ """Mixin to create documents that conform to the load/save spec."""
+
+ async = False
+
+ def _get_async(self):
+ return False
+ def _set_async(self, async):
+ if async:
+ raise xml.dom.NotSupportedErr(
+ "asynchronous document loading is not supported")
+
+ def abort(self):
+ # What does it mean to "clear" a document? Does the
+ # documentElement disappear?
+ raise NotImplementedError(
+ "haven't figured out what this means yet")
+
+ def load(self, uri):
+ raise NotImplementedError("haven't written this yet")
+
+ def loadXML(self, source):
+ raise NotImplementedError("haven't written this yet")
+
+ def saveXML(self, snode):
+ if snode is None:
+ snode = self
+ elif snode.ownerDocument is not self:
+ raise xml.dom.WrongDocumentErr()
+ return snode.toxml()
+
+
+class DOMImplementationLS:
+ MODE_SYNCHRONOUS = 1
+ MODE_ASYNCHRONOUS = 2
+
+ def createDOMBuilder(self, mode, schemaType):
+ if schemaType is not None:
+ raise xml.dom.NotSupportedErr(
+ "schemaType not yet supported")
+ if mode == self.MODE_SYNCHRONOUS:
+ return DOMBuilder()
+ if mode == self.MODE_ASYNCHRONOUS:
+ raise xml.dom.NotSupportedErr(
+ "asynchronous builders are not supported")
+ raise ValueError("unknown value for mode")
+
+ def createDOMWriter(self):
+ raise NotImplementedError(
+ "the writer interface hasn't been written yet!")
+
+ def createDOMInputSource(self):
+ return DOMInputSource()
diff --git a/Lib/xml/etree/ElementInclude.py b/Lib/xml/etree/ElementInclude.py
new file mode 100644
index 0000000..974cc21
--- /dev/null
+++ b/Lib/xml/etree/ElementInclude.py
@@ -0,0 +1,143 @@
+#
+# ElementTree
+# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
+#
+# limited xinclude support for element trees
+#
+# history:
+# 2003-08-15 fl created
+# 2003-11-14 fl fixed default loader
+#
+# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 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.
+# --------------------------------------------------------------------
+
+# Licensed to PSF under a Contributor Agreement.
+# See http://www.python.org/2.4/license for licensing details.
+
+##
+# Limited XInclude support for the ElementTree package.
+##
+
+import copy
+import ElementTree
+
+XINCLUDE = "{http://www.w3.org/2001/XInclude}"
+
+XINCLUDE_INCLUDE = XINCLUDE + "include"
+XINCLUDE_FALLBACK = XINCLUDE + "fallback"
+
+##
+# Fatal include error.
+
+class FatalIncludeError(SyntaxError):
+ pass
+
+##
+# Default loader. This loader reads an included resource from disk.
+#
+# @param href Resource reference.
+# @param parse Parse mode. Either "xml" or "text".
+# @param encoding Optional text encoding.
+# @return The expanded resource. If the parse mode is "xml", this
+# is an ElementTree instance. If the parse mode is "text", this
+# is a Unicode string. If the loader fails, it can return None
+# or raise an IOError exception.
+# @throws IOError If the loader fails to load the resource.
+
+def default_loader(href, parse, encoding=None):
+ file = open(href)
+ if parse == "xml":
+ data = ElementTree.parse(file).getroot()
+ else:
+ data = file.read()
+ if encoding:
+ data = data.decode(encoding)
+ file.close()
+ return data
+
+##
+# Expand XInclude directives.
+#
+# @param elem Root element.
+# @param loader Optional resource loader. If omitted, it defaults
+# to {@link default_loader}. If given, it should be a callable
+# that implements the same interface as <b>default_loader</b>.
+# @throws FatalIncludeError If the function fails to include a given
+# resource, or if the tree contains malformed XInclude elements.
+# @throws IOError If the function fails to load a given resource.
+
+def include(elem, loader=None):
+ if loader is None:
+ loader = default_loader
+ # look for xinclude elements
+ i = 0
+ while i < len(elem):
+ e = elem[i]
+ if e.tag == XINCLUDE_INCLUDE:
+ # process xinclude directive
+ href = e.get("href")
+ parse = e.get("parse", "xml")
+ if parse == "xml":
+ node = loader(href, parse)
+ if node is None:
+ raise FatalIncludeError(
+ "cannot load %r as %r" % (href, parse)
+ )
+ node = copy.copy(node)
+ if e.tail:
+ node.tail = (node.tail or "") + e.tail
+ elem[i] = node
+ elif parse == "text":
+ text = loader(href, parse, e.get("encoding"))
+ if text is None:
+ raise FatalIncludeError(
+ "cannot load %r as %r" % (href, parse)
+ )
+ if i:
+ node = elem[i-1]
+ node.tail = (node.tail or "") + text
+ else:
+ elem.text = (elem.text or "") + text + (e.tail or "")
+ del elem[i]
+ continue
+ else:
+ raise FatalIncludeError(
+ "unknown parse type in xi:include tag (%r)" % parse
+ )
+ elif e.tag == XINCLUDE_FALLBACK:
+ raise FatalIncludeError(
+ "xi:fallback tag must be child of xi:include (%r)" % e.tag
+ )
+ else:
+ include(e, loader)
+ i = i + 1
diff --git a/Lib/xml/etree/ElementPath.py b/Lib/xml/etree/ElementPath.py
new file mode 100644
index 0000000..00dbe9d
--- /dev/null
+++ b/Lib/xml/etree/ElementPath.py
@@ -0,0 +1,198 @@
+#
+# ElementTree
+# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $
+#
+# limited xpath support for element trees
+#
+# history:
+# 2003-05-23 fl created
+# 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.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 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.
+# --------------------------------------------------------------------
+
+# Licensed to PSF under a Contributor Agreement.
+# See http://www.python.org/2.4/license for licensing details.
+
+##
+# Implementation module for XPath support. There's usually no reason
+# to import this module directly; the <b>ElementTree</b> does this for
+# you, if needed.
+##
+
+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] == "/":
+ 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
+ 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
+
+##
+# Find first matching object.
+
+def find(element, path):
+ return _compile(path).find(element)
+
+##
+# 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)
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
new file mode 100644
index 0000000..7dbc72e
--- /dev/null
+++ b/Lib/xml/etree/ElementTree.py
@@ -0,0 +1,1260 @@
+#
+# 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.
+# --------------------------------------------------------------------
+
+# Licensed to PSF under a Contributor Agreement.
+# See http://www.python.org/2.4/license for licensing details.
+
+__all__ = [
+ # public symbols
+ "Comment",
+ "dump",
+ "Element", "ElementTree",
+ "fromstring",
+ "iselement", "iterparse",
+ "parse",
+ "PI", "ProcessingInstruction",
+ "QName",
+ "SubElement",
+ "tostring",
+ "TreeBuilder",
+ "VERSION", "XML",
+ "XMLParser", "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 = {
+ "&": "&",
+ "<": "<",
+ ">": ">",
+ '"': """,
+}
+
+_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, "&", "&")
+ text = replace(text, "<", "<")
+ text = replace(text, ">", ">")
+ 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, "&", "&")
+ text = replace(text, "'", "'") # FIXME: overkill
+ text = replace(text, "\"", """)
+ text = replace(text, "<", "<")
+ text = replace(text, ">", ">")
+ 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
+
+##
+# Parses an XML document into an element tree.
+#
+# @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.
+# @return An ElementTree instance
+
+def parse(source, parser=None):
+ tree = ElementTree()
+ tree.parse(source, parser)
+ return tree
+
+##
+# Parses an XML document into an element tree incrementally, and reports
+# what's going on to the user.
+#
+# @param source A filename or file object containing XML data.
+# @param events A list of events to report back. If omitted, only "end"
+# events are reported.
+# @return A (event, elem) iterator.
+
+class iterparse:
+
+ def __init__(self, source, events=None):
+ if not hasattr(source, "read"):
+ source = open(source, "rb")
+ self._file = source
+ self._events = []
+ self._index = 0
+ self.root = self._root = None
+ self._parser = XMLTreeBuilder()
+ # wire up the parser for event reporting
+ parser = self._parser._parser
+ append = self._events.append
+ if events is None:
+ events = ["end"]
+ for event in events:
+ if event == "start":
+ try:
+ parser.ordered_attributes = 1
+ parser.specified_attributes = 1
+ def handler(tag, attrib_in, event=event, append=append,
+ start=self._parser._start_list):
+ append((event, start(tag, attrib_in)))
+ parser.StartElementHandler = handler
+ except AttributeError:
+ def handler(tag, attrib_in, event=event, append=append,
+ start=self._parser._start):
+ append((event, start(tag, attrib_in)))
+ parser.StartElementHandler = handler
+ elif event == "end":
+ def handler(tag, event=event, append=append,
+ end=self._parser._end):
+ append((event, end(tag)))
+ parser.EndElementHandler = handler
+ elif event == "start-ns":
+ def handler(prefix, uri, event=event, append=append):
+ try:
+ uri = _encode(uri, "ascii")
+ except UnicodeError:
+ pass
+ append((event, (prefix or "", uri)))
+ parser.StartNamespaceDeclHandler = handler
+ elif event == "end-ns":
+ def handler(prefix, event=event, append=append):
+ append((event, None))
+ parser.EndNamespaceDeclHandler = handler
+
+ def next(self):
+ while 1:
+ try:
+ item = self._events[self._index]
+ 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:
+ self._parser.feed(data)
+ else:
+ self._root = self._parser.close()
+ self._parser = None
+ else:
+ self._index = self._index + 1
+ return item
+
+ try:
+ iter
+ def __iter__(self):
+ return self
+ except NameError:
+ def __getitem__(self, index):
+ return self.next()
+
+##
+# Parses an XML document from a string constant. This function can
+# be used to embed "XML literals" in Python code.
+#
+# @param source A string containing XML data.
+# @return An Element instance.
+# @defreturn Element
+
+def XML(text):
+ parser = XMLTreeBuilder()
+ parser.feed(text)
+ return parser.close()
+
+##
+# Parses an XML document from a string constant, and also returns
+# a dictionary which maps from element id:s to elements.
+#
+# @param source A string containing XML data.
+# @return A tuple containing an Element instance and a dictionary.
+# @defreturn (Element, dictionary)
+
+def XMLID(text):
+ parser = XMLTreeBuilder()
+ parser.feed(text)
+ tree = parser.close()
+ ids = {}
+ for elem in tree.getiterator():
+ id = elem.get("id")
+ if id:
+ ids[id] = elem
+ return tree, ids
+
+##
+# Parses an XML document from a string constant. Same as {@link #XML}.
+#
+# @def fromstring(text)
+# @param source A string containing XML data.
+# @return An Element instance.
+# @defreturn Element
+
+fromstring = XML
+
+##
+# 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, "")
+
+##
+# Generic element structure builder. This builder converts a sequence
+# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link
+# #TreeBuilder.end} method calls to a well-formed element structure.
+# <p>
+# You can use this class to build an element structure using a custom XML
+# parser, or a parser for some other XML-like format.
+#
+# @param element_factory Optional element factory. This factory
+# is called to create new Element instances, as necessary.
+
+class TreeBuilder:
+
+ def __init__(self, element_factory=None):
+ self._data = [] # data collector
+ self._elem = [] # element stack
+ self._last = None # last element
+ self._tail = None # true if we're after an end tag
+ if element_factory is None:
+ element_factory = _ElementInterface
+ self._factory = element_factory
+
+ ##
+ # Flushes the parser buffers, and returns the toplevel documen
+ # element.
+ #
+ # @return An Element instance.
+ # @defreturn Element
+
+ def close(self):
+ assert len(self._elem) == 0, "missing end tags"
+ assert self._last != None, "missing toplevel element"
+ return self._last
+
+ def _flush(self):
+ if self._data:
+ if self._last is not None:
+ text = string.join(self._data, "")
+ if self._tail:
+ assert self._last.tail is None, "internal error (tail)"
+ self._last.tail = text
+ else:
+ assert self._last.text is None, "internal error (text)"
+ self._last.text = text
+ self._data = []
+
+ ##
+ # Adds text to the current element.
+ #
+ # @param data A string. This should be either an 8-bit string
+ # containing ASCII text, or a Unicode string.
+
+ def data(self, data):
+ self._data.append(data)
+
+ ##
+ # Opens a new element.
+ #
+ # @param tag The element name.
+ # @param attrib A dictionary containing element attributes.
+ # @return The opened element.
+ # @defreturn Element
+
+ def start(self, tag, attrs):
+ self._flush()
+ self._last = elem = self._factory(tag, attrs)
+ if self._elem:
+ self._elem[-1].append(elem)
+ self._elem.append(elem)
+ self._tail = 0
+ return elem
+
+ ##
+ # Closes the current element.
+ #
+ # @param tag The element name.
+ # @return The closed element.
+ # @defreturn Element
+
+ def end(self, tag):
+ self._flush()
+ self._last = self._elem.pop()
+ assert self._last.tag == tag,\
+ "end tag mismatch (expected %s, got %s)" % (
+ self._last.tag, tag)
+ self._tail = 1
+ return self._last
+
+##
+# Element structure builder for XML source data, based on the
+# <b>expat</b> parser.
+#
+# @keyparam target Target object. If omitted, the builder uses an
+# instance of the standard {@link #TreeBuilder} class.
+# @keyparam html Predefine HTML entities. This flag is not supported
+# by the current implementation.
+# @see #ElementTree
+# @see #TreeBuilder
+
+class XMLTreeBuilder:
+
+ def __init__(self, html=0, target=None):
+ try:
+ from xml.parsers import expat
+ except ImportError:
+ raise ImportError(
+ "No module named expat; use SimpleXMLTreeBuilder instead"
+ )
+ self._parser = parser = expat.ParserCreate(None, "}")
+ if target is None:
+ target = TreeBuilder()
+ self._target = target
+ self._names = {} # name memo cache
+ # callbacks
+ parser.DefaultHandlerExpand = self._default
+ parser.StartElementHandler = self._start
+ parser.EndElementHandler = self._end
+ parser.CharacterDataHandler = self._data
+ # let expat do the buffering, if supported
+ try:
+ self._parser.buffer_text = 1
+ except AttributeError:
+ pass
+ # use new-style attribute handling, if supported
+ try:
+ self._parser.ordered_attributes = 1
+ self._parser.specified_attributes = 1
+ parser.StartElementHandler = self._start_list
+ except AttributeError:
+ pass
+ encoding = None
+ if not parser.returns_unicode:
+ encoding = "utf-8"
+ # target.xml(encoding, None)
+ self._doctype = None
+ self.entity = {}
+
+ def _fixtext(self, text):
+ # convert text string to ascii, if possible
+ try:
+ return _encode(text, "ascii")
+ except UnicodeError:
+ return text
+
+ def _fixname(self, key):
+ # expand qname, and convert name string to ascii, if possible
+ try:
+ name = self._names[key]
+ except KeyError:
+ name = key
+ if "}" in name:
+ name = "{" + name
+ self._names[key] = name = self._fixtext(name)
+ return name
+
+ def _start(self, tag, attrib_in):
+ fixname = self._fixname
+ tag = fixname(tag)
+ attrib = {}
+ for key, value in attrib_in.items():
+ attrib[fixname(key)] = self._fixtext(value)
+ return self._target.start(tag, attrib)
+
+ def _start_list(self, tag, attrib_in):
+ fixname = self._fixname
+ 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)
+
+ def _data(self, text):
+ return self._target.data(self._fixtext(text))
+
+ def _end(self, tag):
+ return self._target.end(self._fixname(tag))
+
+ def _default(self, text):
+ prefix = text[:1]
+ if prefix == "&":
+ # deal with undefined entities
+ try:
+ self._target.data(self.entity[text[1:-1]])
+ except KeyError:
+ from xml.parsers import expat
+ raise expat.error(
+ "undefined entity %s: line %d, column %d" %
+ (text, self._parser.ErrorLineNumber,
+ self._parser.ErrorColumnNumber)
+ )
+ elif prefix == "<" and text[:9] == "<!DOCTYPE":
+ self._doctype = [] # inside a doctype declaration
+ elif self._doctype is not None:
+ # parse doctype contents
+ if prefix == ">":
+ self._doctype = None
+ return
+ text = string.strip(text)
+ if not text:
+ return
+ self._doctype.append(text)
+ n = len(self._doctype)
+ if n > 2:
+ type = self._doctype[1]
+ if type == "PUBLIC" and n == 4:
+ name, type, pubid, system = self._doctype
+ elif type == "SYSTEM" and n == 3:
+ name, type, system = self._doctype
+ pubid = None
+ else:
+ return
+ if pubid:
+ pubid = pubid[1:-1]
+ self.doctype(name, pubid, system[1:-1])
+ self._doctype = None
+
+ ##
+ # Handles a doctype declaration.
+ #
+ # @param name Doctype name.
+ # @param pubid Public identifier.
+ # @param system System identifier.
+
+ def doctype(self, name, pubid, system):
+ pass
+
+ ##
+ # Feeds data to the parser.
+ #
+ # @param data Encoded data.
+
+ def feed(self, data):
+ self._parser.Parse(data, 0)
+
+ ##
+ # Finishes feeding data to the parser.
+ #
+ # @return An element structure.
+ # @defreturn Element
+
+ def close(self):
+ self._parser.Parse("", 1) # end of data
+ tree = self._target.close()
+ del self._target, self._parser # get rid of circular references
+ return tree
+
+# compatibility
+XMLParser = XMLTreeBuilder
diff --git a/Lib/xml/etree/__init__.py b/Lib/xml/etree/__init__.py
new file mode 100644
index 0000000..3dd2c92
--- /dev/null
+++ b/Lib/xml/etree/__init__.py
@@ -0,0 +1,33 @@
+# $Id: __init__.py 1821 2004-06-03 16:57:49Z fredrik $
+# elementtree package
+
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 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.
+# --------------------------------------------------------------------
+
+# Licensed to PSF under a Contributor Agreement.
+# See http://www.python.org/2.4/license for licensing details.
diff --git a/Lib/xml/etree/cElementTree.py b/Lib/xml/etree/cElementTree.py
new file mode 100644
index 0000000..a6f127a
--- /dev/null
+++ b/Lib/xml/etree/cElementTree.py
@@ -0,0 +1,3 @@
+# Wrapper module for _elementtree
+
+from _elementtree import *
diff --git a/Lib/xml/parsers/__init__.py b/Lib/xml/parsers/__init__.py
new file mode 100644
index 0000000..eb314a3
--- /dev/null
+++ b/Lib/xml/parsers/__init__.py
@@ -0,0 +1,8 @@
+"""Python interfaces to XML parsers.
+
+This package contains one module:
+
+expat -- Python wrapper for James Clark's Expat parser, with namespace
+ support.
+
+"""
diff --git a/Lib/xml/parsers/expat.py b/Lib/xml/parsers/expat.py
new file mode 100644
index 0000000..11359a0
--- /dev/null
+++ b/Lib/xml/parsers/expat.py
@@ -0,0 +1,4 @@
+"""Interface to the Expat non-validating XML parser."""
+__version__ = '$Revision$'
+
+from pyexpat import *
diff --git a/Lib/xml/sax/__init__.py b/Lib/xml/sax/__init__.py
new file mode 100644
index 0000000..6b1b1ba
--- /dev/null
+++ b/Lib/xml/sax/__init__.py
@@ -0,0 +1,108 @@
+"""Simple API for XML (SAX) implementation for Python.
+
+This module provides an implementation of the SAX 2 interface;
+information about the Java version of the interface can be found at
+http://www.megginson.com/SAX/. The Python version of the interface is
+documented at <...>.
+
+This package contains the following modules:
+
+handler -- Base classes and constants which define the SAX 2 API for
+ the 'client-side' of SAX for Python.
+
+saxutils -- Implementation of the convenience classes commonly used to
+ work with SAX.
+
+xmlreader -- Base classes and constants which define the SAX 2 API for
+ the parsers used with SAX for Python.
+
+expatreader -- Driver that allows use of the Expat parser with SAX.
+"""
+
+from xmlreader import InputSource
+from handler import ContentHandler, ErrorHandler
+from _exceptions import SAXException, SAXNotRecognizedException, \
+ SAXParseException, SAXNotSupportedException, \
+ SAXReaderNotAvailable
+
+
+def parse(source, handler, errorHandler=ErrorHandler()):
+ parser = make_parser()
+ parser.setContentHandler(handler)
+ parser.setErrorHandler(errorHandler)
+ parser.parse(source)
+
+def parseString(string, handler, errorHandler=ErrorHandler()):
+ try:
+ from cStringIO import StringIO
+ except ImportError:
+ from StringIO import StringIO
+
+ if errorHandler is None:
+ errorHandler = ErrorHandler()
+ parser = make_parser()
+ parser.setContentHandler(handler)
+ parser.setErrorHandler(errorHandler)
+
+ inpsrc = InputSource()
+ inpsrc.setByteStream(StringIO(string))
+ parser.parse(inpsrc)
+
+# this is the parser list used by the make_parser function if no
+# alternatives are given as parameters to the function
+
+default_parser_list = ["xml.sax.expatreader"]
+
+# tell modulefinder that importing sax potentially imports expatreader
+_false = 0
+if _false:
+ import xml.sax.expatreader
+
+import os, sys
+if os.environ.has_key("PY_SAX_PARSER"):
+ default_parser_list = os.environ["PY_SAX_PARSER"].split(",")
+del os
+
+_key = "python.xml.sax.parser"
+if sys.platform[:4] == "java" and sys.registry.containsKey(_key):
+ default_parser_list = sys.registry.getProperty(_key).split(",")
+
+
+def make_parser(parser_list = []):
+ """Creates and returns a SAX parser.
+
+ Creates the first parser it is able to instantiate of the ones
+ given in the list created by doing parser_list +
+ default_parser_list. The lists must contain the names of Python
+ modules containing both a SAX parser and a create_parser function."""
+
+ for parser_name in parser_list + default_parser_list:
+ try:
+ return _create_parser(parser_name)
+ except ImportError,e:
+ import sys
+ if sys.modules.has_key(parser_name):
+ # The parser module was found, but importing it
+ # failed unexpectedly, pass this exception through
+ raise
+ except SAXReaderNotAvailable:
+ # The parser module detected that it won't work properly,
+ # so try the next one
+ pass
+
+ raise SAXReaderNotAvailable("No parsers found", None)
+
+# --- Internal utility methods used by make_parser
+
+if sys.platform[ : 4] == "java":
+ def _create_parser(parser_name):
+ from org.python.core import imp
+ drv_module = imp.importName(parser_name, 0, globals())
+ return drv_module.create_parser()
+
+else:
+ def _create_parser(parser_name):
+ drv_module = __import__(parser_name,{},{},['create_parser'])
+ return drv_module.create_parser()
+
+del sys
diff --git a/Lib/xml/sax/_exceptions.py b/Lib/xml/sax/_exceptions.py
new file mode 100644
index 0000000..fdd614a
--- /dev/null
+++ b/Lib/xml/sax/_exceptions.py
@@ -0,0 +1,131 @@
+"""Different kinds of SAX Exceptions"""
+import sys
+if sys.platform[:4] == "java":
+ from java.lang import Exception
+del sys
+
+# ===== SAXEXCEPTION =====
+
+class SAXException(Exception):
+ """Encapsulate an XML error or warning. This class can contain
+ basic error or warning information from either the XML parser or
+ the application: you can subclass it to provide additional
+ functionality, or to add localization. Note that although you will
+ receive a SAXException as the argument to the handlers in the
+ ErrorHandler interface, you are not actually required to throw
+ the exception; instead, you can simply read the information in
+ it."""
+
+ def __init__(self, msg, exception=None):
+ """Creates an exception. The message is required, but the exception
+ is optional."""
+ self._msg = msg
+ self._exception = exception
+ Exception.__init__(self, msg)
+
+ def getMessage(self):
+ "Return a message for this exception."
+ return self._msg
+
+ def getException(self):
+ "Return the embedded exception, or None if there was none."
+ return self._exception
+
+ def __str__(self):
+ "Create a string representation of the exception."
+ return self._msg
+
+ def __getitem__(self, ix):
+ """Avoids weird error messages if someone does exception[ix] by
+ mistake, since Exception has __getitem__ defined."""
+ raise AttributeError("__getitem__")
+
+
+# ===== SAXPARSEEXCEPTION =====
+
+class SAXParseException(SAXException):
+ """Encapsulate an XML parse error or warning.
+
+ This exception will include information for locating the error in
+ the original XML document. Note that although the application will
+ receive a SAXParseException as the argument to the handlers in the
+ ErrorHandler interface, the application is not actually required
+ to throw the exception; instead, it can simply read the
+ information in it and take a different action.
+
+ Since this exception is a subclass of SAXException, it inherits
+ the ability to wrap another exception."""
+
+ def __init__(self, msg, exception, locator):
+ "Creates the exception. The exception parameter is allowed to be None."
+ SAXException.__init__(self, msg, exception)
+ self._locator = locator
+
+ # We need to cache this stuff at construction time.
+ # If this exception is thrown, the objects through which we must
+ # traverse to get this information may be deleted by the time
+ # it gets caught.
+ self._systemId = self._locator.getSystemId()
+ self._colnum = self._locator.getColumnNumber()
+ self._linenum = self._locator.getLineNumber()
+
+ def getColumnNumber(self):
+ """The column number of the end of the text where the exception
+ occurred."""
+ return self._colnum
+
+ def getLineNumber(self):
+ "The line number of the end of the text where the exception occurred."
+ return self._linenum
+
+ def getPublicId(self):
+ "Get the public identifier of the entity where the exception occurred."
+ return self._locator.getPublicId()
+
+ def getSystemId(self):
+ "Get the system identifier of the entity where the exception occurred."
+ return self._systemId
+
+ def __str__(self):
+ "Create a string representation of the exception."
+ sysid = self.getSystemId()
+ if sysid is None:
+ sysid = "<unknown>"
+ linenum = self.getLineNumber()
+ if linenum is None:
+ linenum = "?"
+ colnum = self.getColumnNumber()
+ if colnum is None:
+ colnum = "?"
+ return "%s:%s:%s: %s" % (sysid, linenum, colnum, self._msg)
+
+
+# ===== SAXNOTRECOGNIZEDEXCEPTION =====
+
+class SAXNotRecognizedException(SAXException):
+ """Exception class for an unrecognized identifier.
+
+ An XMLReader will raise this exception when it is confronted with an
+ unrecognized feature or property. SAX applications and extensions may
+ use this class for similar purposes."""
+
+
+# ===== SAXNOTSUPPORTEDEXCEPTION =====
+
+class SAXNotSupportedException(SAXException):
+ """Exception class for an unsupported operation.
+
+ An XMLReader will raise this exception when a service it cannot
+ perform is requested (specifically setting a state or value). SAX
+ applications and extensions may use this class for similar
+ purposes."""
+
+# ===== SAXNOTSUPPORTEDEXCEPTION =====
+
+class SAXReaderNotAvailable(SAXNotSupportedException):
+ """Exception class for a missing driver.
+
+ An XMLReader module (driver) should raise this exception when it
+ is first imported, e.g. when a support module cannot be imported.
+ It also may be raised during parsing, e.g. if executing an external
+ program is not permitted."""
diff --git a/Lib/xml/sax/expatreader.py b/Lib/xml/sax/expatreader.py
new file mode 100644
index 0000000..bb9c294
--- /dev/null
+++ b/Lib/xml/sax/expatreader.py
@@ -0,0 +1,414 @@
+"""
+SAX driver for the pyexpat C module. This driver works with
+pyexpat.__version__ == '2.22'.
+"""
+
+version = "0.20"
+
+from xml.sax._exceptions import *
+from xml.sax.handler import feature_validation, feature_namespaces
+from xml.sax.handler import feature_namespace_prefixes
+from xml.sax.handler import feature_external_ges, feature_external_pes
+from xml.sax.handler import feature_string_interning
+from xml.sax.handler import property_xml_string, property_interning_dict
+
+# xml.parsers.expat does not raise ImportError in Jython
+import sys
+if sys.platform[:4] == "java":
+ raise SAXReaderNotAvailable("expat not available in Java", None)
+del sys
+
+try:
+ from xml.parsers import expat
+except ImportError:
+ raise SAXReaderNotAvailable("expat not supported", None)
+else:
+ if not hasattr(expat, "ParserCreate"):
+ raise SAXReaderNotAvailable("expat not supported", None)
+from xml.sax import xmlreader, saxutils, handler
+
+AttributesImpl = xmlreader.AttributesImpl
+AttributesNSImpl = xmlreader.AttributesNSImpl
+
+# If we're using a sufficiently recent version of Python, we can use
+# weak references to avoid cycles between the parser and content
+# handler, otherwise we'll just have to pretend.
+try:
+ import _weakref
+except ImportError:
+ def _mkproxy(o):
+ return o
+else:
+ import weakref
+ _mkproxy = weakref.proxy
+ del weakref, _weakref
+
+# --- ExpatLocator
+
+class ExpatLocator(xmlreader.Locator):
+ """Locator for use with the ExpatParser class.
+
+ This uses a weak reference to the parser object to avoid creating
+ a circular reference between the parser and the content handler.
+ """
+ def __init__(self, parser):
+ self._ref = _mkproxy(parser)
+
+ def getColumnNumber(self):
+ parser = self._ref
+ if parser._parser is None:
+ return None
+ return parser._parser.ErrorColumnNumber
+
+ def getLineNumber(self):
+ parser = self._ref
+ if parser._parser is None:
+ return 1
+ return parser._parser.ErrorLineNumber
+
+ def getPublicId(self):
+ parser = self._ref
+ if parser is None:
+ return None
+ return parser._source.getPublicId()
+
+ def getSystemId(self):
+ parser = self._ref
+ if parser is None:
+ return None
+ return parser._source.getSystemId()
+
+
+# --- ExpatParser
+
+class ExpatParser(xmlreader.IncrementalParser, xmlreader.Locator):
+ """SAX driver for the pyexpat C module."""
+
+ def __init__(self, namespaceHandling=0, bufsize=2**16-20):
+ xmlreader.IncrementalParser.__init__(self, bufsize)
+ self._source = xmlreader.InputSource()
+ self._parser = None
+ self._namespaces = namespaceHandling
+ self._lex_handler_prop = None
+ self._parsing = 0
+ self._entity_stack = []
+ self._external_ges = 1
+ self._interning = None
+
+ # XMLReader methods
+
+ def parse(self, source):
+ "Parse an XML document from a URL or an InputSource."
+ source = saxutils.prepare_input_source(source)
+
+ self._source = source
+ self.reset()
+ self._cont_handler.setDocumentLocator(ExpatLocator(self))
+ xmlreader.IncrementalParser.parse(self, source)
+
+ def prepareParser(self, source):
+ if source.getSystemId() != None:
+ self._parser.SetBase(source.getSystemId())
+
+ # Redefined setContentHandler to allow changing handlers during parsing
+
+ def setContentHandler(self, handler):
+ xmlreader.IncrementalParser.setContentHandler(self, handler)
+ if self._parsing:
+ self._reset_cont_handler()
+
+ def getFeature(self, name):
+ if name == feature_namespaces:
+ return self._namespaces
+ elif name == feature_string_interning:
+ return self._interning is not None
+ elif name in (feature_validation, feature_external_pes,
+ feature_namespace_prefixes):
+ return 0
+ elif name == feature_external_ges:
+ return self._external_ges
+ raise SAXNotRecognizedException("Feature '%s' not recognized" % name)
+
+ def setFeature(self, name, state):
+ if self._parsing:
+ raise SAXNotSupportedException("Cannot set features while parsing")
+
+ if name == feature_namespaces:
+ self._namespaces = state
+ elif name == feature_external_ges:
+ self._external_ges = state
+ elif name == feature_string_interning:
+ if state:
+ if self._interning is None:
+ self._interning = {}
+ else:
+ self._interning = None
+ elif name == feature_validation:
+ if state:
+ raise SAXNotSupportedException(
+ "expat does not support validation")
+ elif name == feature_external_pes:
+ if state:
+ raise SAXNotSupportedException(
+ "expat does not read external parameter entities")
+ elif name == feature_namespace_prefixes:
+ if state:
+ raise SAXNotSupportedException(
+ "expat does not report namespace prefixes")
+ else:
+ raise SAXNotRecognizedException(
+ "Feature '%s' not recognized" % name)
+
+ def getProperty(self, name):
+ if name == handler.property_lexical_handler:
+ return self._lex_handler_prop
+ elif name == property_interning_dict:
+ return self._interning
+ elif name == property_xml_string:
+ if self._parser:
+ if hasattr(self._parser, "GetInputContext"):
+ return self._parser.GetInputContext()
+ else:
+ raise SAXNotRecognizedException(
+ "This version of expat does not support getting"
+ " the XML string")
+ else:
+ raise SAXNotSupportedException(
+ "XML string cannot be returned when not parsing")
+ raise SAXNotRecognizedException("Property '%s' not recognized" % name)
+
+ def setProperty(self, name, value):
+ if name == handler.property_lexical_handler:
+ self._lex_handler_prop = value
+ if self._parsing:
+ self._reset_lex_handler_prop()
+ elif name == property_interning_dict:
+ self._interning = value
+ elif name == property_xml_string:
+ raise SAXNotSupportedException("Property '%s' cannot be set" %
+ name)
+ else:
+ raise SAXNotRecognizedException("Property '%s' not recognized" %
+ name)
+
+ # IncrementalParser methods
+
+ def feed(self, data, isFinal = 0):
+ if not self._parsing:
+ self.reset()
+ self._parsing = 1
+ self._cont_handler.startDocument()
+
+ try:
+ # The isFinal parameter is internal to the expat reader.
+ # If it is set to true, expat will check validity of the entire
+ # document. When feeding chunks, they are not normally final -
+ # except when invoked from close.
+ self._parser.Parse(data, isFinal)
+ except expat.error, e:
+ exc = SAXParseException(expat.ErrorString(e.code), e, self)
+ # FIXME: when to invoke error()?
+ self._err_handler.fatalError(exc)
+
+ def close(self):
+ if self._entity_stack:
+ # If we are completing an external entity, do nothing here
+ return
+ self.feed("", isFinal = 1)
+ self._cont_handler.endDocument()
+ self._parsing = 0
+ # break cycle created by expat handlers pointing to our methods
+ self._parser = None
+
+ def _reset_cont_handler(self):
+ self._parser.ProcessingInstructionHandler = \
+ self._cont_handler.processingInstruction
+ self._parser.CharacterDataHandler = self._cont_handler.characters
+
+ def _reset_lex_handler_prop(self):
+ lex = self._lex_handler_prop
+ parser = self._parser
+ if lex is None:
+ parser.CommentHandler = None
+ parser.StartCdataSectionHandler = None
+ parser.EndCdataSectionHandler = None
+ parser.StartDoctypeDeclHandler = None
+ parser.EndDoctypeDeclHandler = None
+ else:
+ parser.CommentHandler = lex.comment
+ parser.StartCdataSectionHandler = lex.startCDATA
+ parser.EndCdataSectionHandler = lex.endCDATA
+ parser.StartDoctypeDeclHandler = self.start_doctype_decl
+ parser.EndDoctypeDeclHandler = lex.endDTD
+
+ def reset(self):
+ if self._namespaces:
+ self._parser = expat.ParserCreate(self._source.getEncoding(), " ",
+ intern=self._interning)
+ self._parser.namespace_prefixes = 1
+ self._parser.StartElementHandler = self.start_element_ns
+ self._parser.EndElementHandler = self.end_element_ns
+ else:
+ self._parser = expat.ParserCreate(self._source.getEncoding(),
+ intern = self._interning)
+ self._parser.StartElementHandler = self.start_element
+ self._parser.EndElementHandler = self.end_element
+
+ self._reset_cont_handler()
+ self._parser.UnparsedEntityDeclHandler = self.unparsed_entity_decl
+ self._parser.NotationDeclHandler = self.notation_decl
+ self._parser.StartNamespaceDeclHandler = self.start_namespace_decl
+ self._parser.EndNamespaceDeclHandler = self.end_namespace_decl
+
+ self._decl_handler_prop = None
+ if self._lex_handler_prop:
+ self._reset_lex_handler_prop()
+# self._parser.DefaultHandler =
+# self._parser.DefaultHandlerExpand =
+# self._parser.NotStandaloneHandler =
+ self._parser.ExternalEntityRefHandler = self.external_entity_ref
+ try:
+ self._parser.SkippedEntityHandler = self.skipped_entity_handler
+ except AttributeError:
+ # This pyexpat does not support SkippedEntity
+ pass
+ self._parser.SetParamEntityParsing(
+ expat.XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE)
+
+ self._parsing = 0
+ self._entity_stack = []
+
+ # Locator methods
+
+ def getColumnNumber(self):
+ if self._parser is None:
+ return None
+ return self._parser.ErrorColumnNumber
+
+ def getLineNumber(self):
+ if self._parser is None:
+ return 1
+ return self._parser.ErrorLineNumber
+
+ def getPublicId(self):
+ return self._source.getPublicId()
+
+ def getSystemId(self):
+ return self._source.getSystemId()
+
+ # event handlers
+ def start_element(self, name, attrs):
+ self._cont_handler.startElement(name, AttributesImpl(attrs))
+
+ def end_element(self, name):
+ self._cont_handler.endElement(name)
+
+ def start_element_ns(self, name, attrs):
+ pair = name.split()
+ if len(pair) == 1:
+ # no namespace
+ pair = (None, name)
+ elif len(pair) == 3:
+ pair = pair[0], pair[1]
+ else:
+ # default namespace
+ pair = tuple(pair)
+
+ newattrs = {}
+ qnames = {}
+ for (aname, value) in attrs.items():
+ parts = aname.split()
+ length = len(parts)
+ if length == 1:
+ # no namespace
+ qname = aname
+ apair = (None, aname)
+ elif length == 3:
+ qname = "%s:%s" % (parts[2], parts[1])
+ apair = parts[0], parts[1]
+ else:
+ # default namespace
+ qname = parts[1]
+ apair = tuple(parts)
+
+ newattrs[apair] = value
+ qnames[apair] = qname
+
+ self._cont_handler.startElementNS(pair, None,
+ AttributesNSImpl(newattrs, qnames))
+
+ def end_element_ns(self, name):
+ pair = name.split()
+ if len(pair) == 1:
+ pair = (None, name)
+ elif len(pair) == 3:
+ pair = pair[0], pair[1]
+ else:
+ pair = tuple(pair)
+
+ self._cont_handler.endElementNS(pair, None)
+
+ # this is not used (call directly to ContentHandler)
+ def processing_instruction(self, target, data):
+ self._cont_handler.processingInstruction(target, data)
+
+ # this is not used (call directly to ContentHandler)
+ def character_data(self, data):
+ self._cont_handler.characters(data)
+
+ def start_namespace_decl(self, prefix, uri):
+ self._cont_handler.startPrefixMapping(prefix, uri)
+
+ def end_namespace_decl(self, prefix):
+ self._cont_handler.endPrefixMapping(prefix)
+
+ def start_doctype_decl(self, name, sysid, pubid, has_internal_subset):
+ self._lex_handler_prop.startDTD(name, pubid, sysid)
+
+ def unparsed_entity_decl(self, name, base, sysid, pubid, notation_name):
+ self._dtd_handler.unparsedEntityDecl(name, pubid, sysid, notation_name)
+
+ def notation_decl(self, name, base, sysid, pubid):
+ self._dtd_handler.notationDecl(name, pubid, sysid)
+
+ def external_entity_ref(self, context, base, sysid, pubid):
+ if not self._external_ges:
+ return 1
+
+ source = self._ent_handler.resolveEntity(pubid, sysid)
+ source = saxutils.prepare_input_source(source,
+ self._source.getSystemId() or
+ "")
+
+ self._entity_stack.append((self._parser, self._source))
+ self._parser = self._parser.ExternalEntityParserCreate(context)
+ self._source = source
+
+ try:
+ xmlreader.IncrementalParser.parse(self, source)
+ except:
+ return 0 # FIXME: save error info here?
+
+ (self._parser, self._source) = self._entity_stack[-1]
+ del self._entity_stack[-1]
+ return 1
+
+ def skipped_entity_handler(self, name, is_pe):
+ if is_pe:
+ # The SAX spec requires to report skipped PEs with a '%'
+ name = '%'+name
+ self._cont_handler.skippedEntity(name)
+
+# ---
+
+def create_parser(*args, **kwargs):
+ return ExpatParser(*args, **kwargs)
+
+# ---
+
+if __name__ == "__main__":
+ import xml.sax
+ p = create_parser()
+ p.setContentHandler(xml.sax.XMLGenerator())
+ p.setErrorHandler(xml.sax.ErrorHandler())
+ p.parse("../../../hamlet.xml")
diff --git a/Lib/xml/sax/handler.py b/Lib/xml/sax/handler.py
new file mode 100644
index 0000000..f9e91b6
--- /dev/null
+++ b/Lib/xml/sax/handler.py
@@ -0,0 +1,342 @@
+"""
+This module contains the core classes of version 2.0 of SAX for Python.
+This file provides only default classes with absolutely minimum
+functionality, from which drivers and applications can be subclassed.
+
+Many of these classes are empty and are included only as documentation
+of the interfaces.
+
+$Id$
+"""
+
+version = '2.0beta'
+
+#============================================================================
+#
+# HANDLER INTERFACES
+#
+#============================================================================
+
+# ===== ERRORHANDLER =====
+
+class ErrorHandler:
+ """Basic interface for SAX error handlers.
+
+ If you create an object that implements this interface, then
+ register the object with your XMLReader, the parser will call the
+ methods in your object to report all warnings and errors. There
+ are three levels of errors available: warnings, (possibly)
+ recoverable errors, and unrecoverable errors. All methods take a
+ SAXParseException as the only parameter."""
+
+ def error(self, exception):
+ "Handle a recoverable error."
+ raise exception
+
+ def fatalError(self, exception):
+ "Handle a non-recoverable error."
+ raise exception
+
+ def warning(self, exception):
+ "Handle a warning."
+ print exception
+
+
+# ===== CONTENTHANDLER =====
+
+class ContentHandler:
+ """Interface for receiving logical document content events.
+
+ This is the main callback interface in SAX, and the one most
+ important to applications. The order of events in this interface
+ mirrors the order of the information in the document."""
+
+ def __init__(self):
+ self._locator = None
+
+ def setDocumentLocator(self, locator):
+ """Called by the parser to give the application a locator for
+ locating the origin of document events.
+
+ SAX parsers are strongly encouraged (though not absolutely
+ required) to supply a locator: if it does so, it must supply
+ the locator to the application by invoking this method before
+ invoking any of the other methods in the DocumentHandler
+ interface.
+
+ The locator allows the application to determine the end
+ position of any document-related event, even if the parser is
+ not reporting an error. Typically, the application will use
+ this information for reporting its own errors (such as
+ character content that does not match an application's
+ business rules). The information returned by the locator is
+ probably not sufficient for use with a search engine.
+
+ Note that the locator will return correct information only
+ during the invocation of the events in this interface. The
+ application should not attempt to use it at any other time."""
+ self._locator = locator
+
+ def startDocument(self):
+ """Receive notification of the beginning of a document.
+
+ The SAX parser will invoke this method only once, before any
+ other methods in this interface or in DTDHandler (except for
+ setDocumentLocator)."""
+
+ def endDocument(self):
+ """Receive notification of the end of a document.
+
+ The SAX parser will invoke this method only once, and it will
+ be the last method invoked during the parse. The parser shall
+ not invoke this method until it has either abandoned parsing
+ (because of an unrecoverable error) or reached the end of
+ input."""
+
+ def startPrefixMapping(self, prefix, uri):
+ """Begin the scope of a prefix-URI Namespace mapping.
+
+ The information from this event is not necessary for normal
+ Namespace processing: the SAX XML reader will automatically
+ replace prefixes for element and attribute names when the
+ http://xml.org/sax/features/namespaces feature is true (the
+ default).
+
+ There are cases, however, when applications need to use
+ prefixes in character data or in attribute values, where they
+ cannot safely be expanded automatically; the
+ start/endPrefixMapping event supplies the information to the
+ application to expand prefixes in those contexts itself, if
+ necessary.
+
+ Note that start/endPrefixMapping events are not guaranteed to
+ be properly nested relative to each-other: all
+ startPrefixMapping events will occur before the corresponding
+ startElement event, and all endPrefixMapping events will occur
+ after the corresponding endElement event, but their order is
+ not guaranteed."""
+
+ def endPrefixMapping(self, prefix):
+ """End the scope of a prefix-URI mapping.
+
+ See startPrefixMapping for details. This event will always
+ occur after the corresponding endElement event, but the order
+ of endPrefixMapping events is not otherwise guaranteed."""
+
+ def startElement(self, name, attrs):
+ """Signals the start of an element in non-namespace mode.
+
+ The name parameter contains the raw XML 1.0 name of the
+ element type as a string and the attrs parameter holds an
+ instance of the Attributes class containing the attributes of
+ the element."""
+
+ def endElement(self, name):
+ """Signals the end of an element in non-namespace mode.
+
+ The name parameter contains the name of the element type, just
+ as with the startElement event."""
+
+ def startElementNS(self, name, qname, attrs):
+ """Signals the start of an element in namespace mode.
+
+ The name parameter contains the name of the element type as a
+ (uri, localname) tuple, the qname parameter the raw XML 1.0
+ name used in the source document, and the attrs parameter
+ holds an instance of the Attributes class containing the
+ attributes of the element.
+
+ The uri part of the name tuple is None for elements which have
+ no namespace."""
+
+ def endElementNS(self, name, qname):
+ """Signals the end of an element in namespace mode.
+
+ The name parameter contains the name of the element type, just
+ as with the startElementNS event."""
+
+ def characters(self, content):
+ """Receive notification of character data.
+
+ The Parser will call this method to report each chunk of
+ character data. SAX parsers may return all contiguous
+ character data in a single chunk, or they may split it into
+ several chunks; however, all of the characters in any single
+ event must come from the same external entity so that the
+ Locator provides useful information."""
+
+ def ignorableWhitespace(self, whitespace):
+ """Receive notification of ignorable whitespace in element content.
+
+ Validating Parsers must use this method to report each chunk
+ of ignorable whitespace (see the W3C XML 1.0 recommendation,
+ section 2.10): non-validating parsers may also use this method
+ if they are capable of parsing and using content models.
+
+ SAX parsers may return all contiguous whitespace in a single
+ chunk, or they may split it into several chunks; however, all
+ of the characters in any single event must come from the same
+ external entity, so that the Locator provides useful
+ information."""
+
+ def processingInstruction(self, target, data):
+ """Receive notification of a processing instruction.
+
+ The Parser will invoke this method once for each processing
+ instruction found: note that processing instructions may occur
+ before or after the main document element.
+
+ A SAX parser should never report an XML declaration (XML 1.0,
+ section 2.8) or a text declaration (XML 1.0, section 4.3.1)
+ using this method."""
+
+ def skippedEntity(self, name):
+ """Receive notification of a skipped entity.
+
+ The Parser will invoke this method once for each entity
+ skipped. Non-validating processors may skip entities if they
+ have not seen the declarations (because, for example, the
+ entity was declared in an external DTD subset). All processors
+ may skip external entities, depending on the values of the
+ http://xml.org/sax/features/external-general-entities and the
+ http://xml.org/sax/features/external-parameter-entities
+ properties."""
+
+
+# ===== DTDHandler =====
+
+class DTDHandler:
+ """Handle DTD events.
+
+ This interface specifies only those DTD events required for basic
+ parsing (unparsed entities and attributes)."""
+
+ def notationDecl(self, name, publicId, systemId):
+ "Handle a notation declaration event."
+
+ def unparsedEntityDecl(self, name, publicId, systemId, ndata):
+ "Handle an unparsed entity declaration event."
+
+
+# ===== ENTITYRESOLVER =====
+
+class EntityResolver:
+ """Basic interface for resolving entities. If you create an object
+ implementing this interface, then register the object with your
+ Parser, the parser will call the method in your object to
+ resolve all external entities. Note that DefaultHandler implements
+ this interface with the default behaviour."""
+
+ def resolveEntity(self, publicId, systemId):
+ """Resolve the system identifier of an entity and return either
+ the system identifier to read from as a string, or an InputSource
+ to read from."""
+ return systemId
+
+
+#============================================================================
+#
+# CORE FEATURES
+#
+#============================================================================
+
+feature_namespaces = "http://xml.org/sax/features/namespaces"
+# true: Perform Namespace processing (default).
+# false: Optionally do not perform Namespace processing
+# (implies namespace-prefixes).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_namespace_prefixes = "http://xml.org/sax/features/namespace-prefixes"
+# true: Report the original prefixed names and attributes used for Namespace
+# declarations.
+# false: Do not report attributes used for Namespace declarations, and
+# optionally do not report original prefixed names (default).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_string_interning = "http://xml.org/sax/features/string-interning"
+# true: All element names, prefixes, attribute names, Namespace URIs, and
+# local names are interned using the built-in intern function.
+# false: Names are not necessarily interned, although they may be (default).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_validation = "http://xml.org/sax/features/validation"
+# true: Report all validation errors (implies external-general-entities and
+# external-parameter-entities).
+# false: Do not report validation errors.
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_external_ges = "http://xml.org/sax/features/external-general-entities"
+# true: Include all external general (text) entities.
+# false: Do not include external general entities.
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_external_pes = "http://xml.org/sax/features/external-parameter-entities"
+# true: Include all external parameter entities, including the external
+# DTD subset.
+# false: Do not include any external parameter entities, even the external
+# DTD subset.
+# access: (parsing) read-only; (not parsing) read/write
+
+all_features = [feature_namespaces,
+ feature_namespace_prefixes,
+ feature_string_interning,
+ feature_validation,
+ feature_external_ges,
+ feature_external_pes]
+
+
+#============================================================================
+#
+# CORE PROPERTIES
+#
+#============================================================================
+
+property_lexical_handler = "http://xml.org/sax/properties/lexical-handler"
+# data type: xml.sax.sax2lib.LexicalHandler
+# description: An optional extension handler for lexical events like comments.
+# access: read/write
+
+property_declaration_handler = "http://xml.org/sax/properties/declaration-handler"
+# data type: xml.sax.sax2lib.DeclHandler
+# description: An optional extension handler for DTD-related events other
+# than notations and unparsed entities.
+# access: read/write
+
+property_dom_node = "http://xml.org/sax/properties/dom-node"
+# data type: org.w3c.dom.Node
+# description: When parsing, the current DOM node being visited if this is
+# a DOM iterator; when not parsing, the root DOM node for
+# iteration.
+# access: (parsing) read-only; (not parsing) read/write
+
+property_xml_string = "http://xml.org/sax/properties/xml-string"
+# data type: String
+# description: The literal string of characters that was the source for
+# the current event.
+# access: read-only
+
+property_encoding = "http://www.python.org/sax/properties/encoding"
+# data type: String
+# description: The name of the encoding to assume for input data.
+# access: write: set the encoding, e.g. established by a higher-level
+# protocol. May change during parsing (e.g. after
+# processing a META tag)
+# read: return the current encoding (possibly established through
+# auto-detection.
+# initial value: UTF-8
+#
+
+property_interning_dict = "http://www.python.org/sax/properties/interning-dict"
+# data type: Dictionary
+# description: The dictionary used to intern common strings in the document
+# access: write: Request that the parser uses a specific dictionary, to
+# allow interning across different documents
+# read: return the current interning dictionary, or None
+#
+
+all_properties = [property_lexical_handler,
+ property_dom_node,
+ property_declaration_handler,
+ property_xml_string,
+ property_encoding,
+ property_interning_dict]
diff --git a/Lib/xml/sax/saxutils.py b/Lib/xml/sax/saxutils.py
new file mode 100644
index 0000000..a496519
--- /dev/null
+++ b/Lib/xml/sax/saxutils.py
@@ -0,0 +1,299 @@
+"""\
+A library of useful helper classes to the SAX classes, for the
+convenience of application and driver writers.
+"""
+
+import os, urlparse, urllib, types
+import handler
+import xmlreader
+
+try:
+ _StringTypes = [types.StringType, types.UnicodeType]
+except AttributeError:
+ _StringTypes = [types.StringType]
+
+# See whether the xmlcharrefreplace error handler is
+# supported
+try:
+ from codecs import xmlcharrefreplace_errors
+ _error_handling = "xmlcharrefreplace"
+ del xmlcharrefreplace_errors
+except ImportError:
+ _error_handling = "strict"
+
+def __dict_replace(s, d):
+ """Replace substrings of a string using a dictionary."""
+ for key, value in d.items():
+ s = s.replace(key, value)
+ return s
+
+def escape(data, entities={}):
+ """Escape &, <, and > in a string of data.
+
+ You can escape other strings of data by passing a dictionary as
+ the optional entities parameter. The keys and values must all be
+ strings; each key will be replaced with its corresponding value.
+ """
+
+ # must do ampersand first
+ data = data.replace("&", "&")
+ data = data.replace(">", ">")
+ data = data.replace("<", "<")
+ if entities:
+ data = __dict_replace(data, entities)
+ return data
+
+def unescape(data, entities={}):
+ """Unescape &, <, and > in a string of data.
+
+ You can unescape other strings of data by passing a dictionary as
+ the optional entities parameter. The keys and values must all be
+ strings; each key will be replaced with its corresponding value.
+ """
+ data = data.replace("<", "<")
+ data = data.replace(">", ">")
+ if entities:
+ data = __dict_replace(data, entities)
+ # must do ampersand last
+ return data.replace("&", "&")
+
+def quoteattr(data, entities={}):
+ """Escape and quote an attribute value.
+
+ Escape &, <, and > in a string of data, then quote it for use as
+ an attribute value. The \" character will be escaped as well, if
+ necessary.
+
+ You can escape other strings of data by passing a dictionary as
+ the optional entities parameter. The keys and values must all be
+ strings; each key will be replaced with its corresponding value.
+ """
+ entities = entities.copy()
+ entities.update({'\n': ' ', '\r': ' ', '\t':'	'})
+ data = escape(data, entities)
+ if '"' in data:
+ if "'" in data:
+ data = '"%s"' % data.replace('"', """)
+ else:
+ data = "'%s'" % data
+ else:
+ data = '"%s"' % data
+ return data
+
+
+class XMLGenerator(handler.ContentHandler):
+
+ def __init__(self, out=None, encoding="iso-8859-1"):
+ if out is None:
+ import sys
+ out = sys.stdout
+ handler.ContentHandler.__init__(self)
+ self._out = out
+ self._ns_contexts = [{}] # contains uri -> prefix dicts
+ self._current_context = self._ns_contexts[-1]
+ self._undeclared_ns_maps = []
+ self._encoding = encoding
+
+ def _write(self, text):
+ if isinstance(text, str):
+ self._out.write(text)
+ else:
+ self._out.write(text.encode(self._encoding, _error_handling))
+
+ # ContentHandler methods
+
+ def startDocument(self):
+ self._write('<?xml version="1.0" encoding="%s"?>\n' %
+ self._encoding)
+
+ def startPrefixMapping(self, prefix, uri):
+ self._ns_contexts.append(self._current_context.copy())
+ self._current_context[uri] = prefix
+ self._undeclared_ns_maps.append((prefix, uri))
+
+ def endPrefixMapping(self, prefix):
+ self._current_context = self._ns_contexts[-1]
+ del self._ns_contexts[-1]
+
+ def startElement(self, name, attrs):
+ self._write('<' + name)
+ for (name, value) in attrs.items():
+ self._write(' %s=%s' % (name, quoteattr(value)))
+ self._write('>')
+
+ def endElement(self, name):
+ self._write('</%s>' % name)
+
+ def startElementNS(self, name, qname, attrs):
+ if name[0] is None:
+ # if the name was not namespace-scoped, use the unqualified part
+ name = name[1]
+ else:
+ # else try to restore the original prefix from the namespace
+ name = self._current_context[name[0]] + ":" + name[1]
+ self._write('<' + name)
+
+ for pair in self._undeclared_ns_maps:
+ self._write(' xmlns:%s="%s"' % pair)
+ self._undeclared_ns_maps = []
+
+ for (name, value) in attrs.items():
+ name = self._current_context[name[0]] + ":" + name[1]
+ self._write(' %s=%s' % (name, quoteattr(value)))
+ self._write('>')
+
+ def endElementNS(self, name, qname):
+ if name[0] is None:
+ name = name[1]
+ else:
+ name = self._current_context[name[0]] + ":" + name[1]
+ self._write('</%s>' % name)
+
+ def characters(self, content):
+ self._write(escape(content))
+
+ def ignorableWhitespace(self, content):
+ self._write(content)
+
+ def processingInstruction(self, target, data):
+ self._write('<?%s %s?>' % (target, data))
+
+
+class XMLFilterBase(xmlreader.XMLReader):
+ """This class is designed to sit between an XMLReader and the
+ client application's event handlers. By default, it does nothing
+ but pass requests up to the reader and events on to the handlers
+ unmodified, but subclasses can override specific methods to modify
+ the event stream or the configuration requests as they pass
+ through."""
+
+ def __init__(self, parent = None):
+ xmlreader.XMLReader.__init__(self)
+ self._parent = parent
+
+ # ErrorHandler methods
+
+ def error(self, exception):
+ self._err_handler.error(exception)
+
+ def fatalError(self, exception):
+ self._err_handler.fatalError(exception)
+
+ def warning(self, exception):
+ self._err_handler.warning(exception)
+
+ # ContentHandler methods
+
+ def setDocumentLocator(self, locator):
+ self._cont_handler.setDocumentLocator(locator)
+
+ def startDocument(self):
+ self._cont_handler.startDocument()
+
+ def endDocument(self):
+ self._cont_handler.endDocument()
+
+ def startPrefixMapping(self, prefix, uri):
+ self._cont_handler.startPrefixMapping(prefix, uri)
+
+ def endPrefixMapping(self, prefix):
+ self._cont_handler.endPrefixMapping(prefix)
+
+ def startElement(self, name, attrs):
+ self._cont_handler.startElement(name, attrs)
+
+ def endElement(self, name):
+ self._cont_handler.endElement(name)
+
+ def startElementNS(self, name, qname, attrs):
+ self._cont_handler.startElementNS(name, qname, attrs)
+
+ def endElementNS(self, name, qname):
+ self._cont_handler.endElementNS(name, qname)
+
+ def characters(self, content):
+ self._cont_handler.characters(content)
+
+ def ignorableWhitespace(self, chars):
+ self._cont_handler.ignorableWhitespace(chars)
+
+ def processingInstruction(self, target, data):
+ self._cont_handler.processingInstruction(target, data)
+
+ def skippedEntity(self, name):
+ self._cont_handler.skippedEntity(name)
+
+ # DTDHandler methods
+
+ def notationDecl(self, name, publicId, systemId):
+ self._dtd_handler.notationDecl(name, publicId, systemId)
+
+ def unparsedEntityDecl(self, name, publicId, systemId, ndata):
+ self._dtd_handler.unparsedEntityDecl(name, publicId, systemId, ndata)
+
+ # EntityResolver methods
+
+ def resolveEntity(self, publicId, systemId):
+ return self._ent_handler.resolveEntity(publicId, systemId)
+
+ # XMLReader methods
+
+ def parse(self, source):
+ self._parent.setContentHandler(self)
+ self._parent.setErrorHandler(self)
+ self._parent.setEntityResolver(self)
+ self._parent.setDTDHandler(self)
+ self._parent.parse(source)
+
+ def setLocale(self, locale):
+ self._parent.setLocale(locale)
+
+ def getFeature(self, name):
+ return self._parent.getFeature(name)
+
+ def setFeature(self, name, state):
+ self._parent.setFeature(name, state)
+
+ def getProperty(self, name):
+ return self._parent.getProperty(name)
+
+ def setProperty(self, name, value):
+ self._parent.setProperty(name, value)
+
+ # XMLFilter methods
+
+ def getParent(self):
+ return self._parent
+
+ def setParent(self, parent):
+ self._parent = parent
+
+# --- Utility functions
+
+def prepare_input_source(source, base = ""):
+ """This function takes an InputSource and an optional base URL and
+ returns a fully resolved InputSource object ready for reading."""
+
+ if type(source) in _StringTypes:
+ source = xmlreader.InputSource(source)
+ elif hasattr(source, "read"):
+ f = source
+ source = xmlreader.InputSource()
+ source.setByteStream(f)
+ if hasattr(f, "name"):
+ source.setSystemId(f.name)
+
+ if source.getByteStream() is None:
+ sysid = source.getSystemId()
+ basehead = os.path.dirname(os.path.normpath(base))
+ sysidfilename = os.path.join(basehead, sysid)
+ if os.path.isfile(sysidfilename):
+ source.setSystemId(sysidfilename)
+ f = open(sysidfilename, "rb")
+ else:
+ source.setSystemId(urlparse.urljoin(base, sysid))
+ f = urllib.urlopen(source.getSystemId())
+
+ source.setByteStream(f)
+
+ return source
diff --git a/Lib/xml/sax/xmlreader.py b/Lib/xml/sax/xmlreader.py
new file mode 100644
index 0000000..9a2361e
--- /dev/null
+++ b/Lib/xml/sax/xmlreader.py
@@ -0,0 +1,381 @@
+"""An XML Reader is the SAX 2 name for an XML parser. XML Parsers
+should be based on this code. """
+
+import handler
+
+from _exceptions import SAXNotSupportedException, SAXNotRecognizedException
+
+
+# ===== XMLREADER =====
+
+class XMLReader:
+ """Interface for reading an XML document using callbacks.
+
+ XMLReader is the interface that an XML parser's SAX2 driver must
+ implement. This interface allows an application to set and query
+ features and properties in the parser, to register event handlers
+ for document processing, and to initiate a document parse.
+
+ All SAX interfaces are assumed to be synchronous: the parse
+ methods must not return until parsing is complete, and readers
+ must wait for an event-handler callback to return before reporting
+ the next event."""
+
+ def __init__(self):
+ self._cont_handler = handler.ContentHandler()
+ self._dtd_handler = handler.DTDHandler()
+ self._ent_handler = handler.EntityResolver()
+ self._err_handler = handler.ErrorHandler()
+
+ def parse(self, source):
+ "Parse an XML document from a system identifier or an InputSource."
+ raise NotImplementedError("This method must be implemented!")
+
+ def getContentHandler(self):
+ "Returns the current ContentHandler."
+ return self._cont_handler
+
+ def setContentHandler(self, handler):
+ "Registers a new object to receive document content events."
+ self._cont_handler = handler
+
+ def getDTDHandler(self):
+ "Returns the current DTD handler."
+ return self._dtd_handler
+
+ def setDTDHandler(self, handler):
+ "Register an object to receive basic DTD-related events."
+ self._dtd_handler = handler
+
+ def getEntityResolver(self):
+ "Returns the current EntityResolver."
+ return self._ent_handler
+
+ def setEntityResolver(self, resolver):
+ "Register an object to resolve external entities."
+ self._ent_handler = resolver
+
+ def getErrorHandler(self):
+ "Returns the current ErrorHandler."
+ return self._err_handler
+
+ def setErrorHandler(self, handler):
+ "Register an object to receive error-message events."
+ self._err_handler = handler
+
+ def setLocale(self, locale):
+ """Allow an application to set the locale for errors and warnings.
+
+ SAX parsers are not required to provide localization for errors
+ and warnings; if they cannot support the requested locale,
+ however, they must throw a SAX exception. Applications may
+ request a locale change in the middle of a parse."""
+ raise SAXNotSupportedException("Locale support not implemented")
+
+ def getFeature(self, name):
+ "Looks up and returns the state of a SAX2 feature."
+ raise SAXNotRecognizedException("Feature '%s' not recognized" % name)
+
+ def setFeature(self, name, state):
+ "Sets the state of a SAX2 feature."
+ raise SAXNotRecognizedException("Feature '%s' not recognized" % name)
+
+ def getProperty(self, name):
+ "Looks up and returns the value of a SAX2 property."
+ raise SAXNotRecognizedException("Property '%s' not recognized" % name)
+
+ def setProperty(self, name, value):
+ "Sets the value of a SAX2 property."
+ raise SAXNotRecognizedException("Property '%s' not recognized" % name)
+
+class IncrementalParser(XMLReader):
+ """This interface adds three extra methods to the XMLReader
+ interface that allow XML parsers to support incremental
+ parsing. Support for this interface is optional, since not all
+ underlying XML parsers support this functionality.
+
+ When the parser is instantiated it is ready to begin accepting
+ data from the feed method immediately. After parsing has been
+ finished with a call to close the reset method must be called to
+ make the parser ready to accept new data, either from feed or
+ using the parse method.
+
+ Note that these methods must _not_ be called during parsing, that
+ is, after parse has been called and before it returns.
+
+ By default, the class also implements the parse method of the XMLReader
+ interface using the feed, close and reset methods of the
+ IncrementalParser interface as a convenience to SAX 2.0 driver
+ writers."""
+
+ def __init__(self, bufsize=2**16):
+ self._bufsize = bufsize
+ XMLReader.__init__(self)
+
+ def parse(self, source):
+ import saxutils
+ source = saxutils.prepare_input_source(source)
+
+ self.prepareParser(source)
+ file = source.getByteStream()
+ buffer = file.read(self._bufsize)
+ while buffer != "":
+ self.feed(buffer)
+ buffer = file.read(self._bufsize)
+ self.close()
+
+ def feed(self, data):
+ """This method gives the raw XML data in the data parameter to
+ the parser and makes it parse the data, emitting the
+ corresponding events. It is allowed for XML constructs to be
+ split across several calls to feed.
+
+ feed may raise SAXException."""
+ raise NotImplementedError("This method must be implemented!")
+
+ def prepareParser(self, source):
+ """This method is called by the parse implementation to allow
+ the SAX 2.0 driver to prepare itself for parsing."""
+ raise NotImplementedError("prepareParser must be overridden!")
+
+ def close(self):
+ """This method is called when the entire XML document has been
+ passed to the parser through the feed method, to notify the
+ parser that there are no more data. This allows the parser to
+ do the final checks on the document and empty the internal
+ data buffer.
+
+ The parser will not be ready to parse another document until
+ the reset method has been called.
+
+ close may raise SAXException."""
+ raise NotImplementedError("This method must be implemented!")
+
+ def reset(self):
+ """This method is called after close has been called to reset
+ the parser so that it is ready to parse new documents. The
+ results of calling parse or feed after close without calling
+ reset are undefined."""
+ raise NotImplementedError("This method must be implemented!")
+
+# ===== LOCATOR =====
+
+class Locator:
+ """Interface for associating a SAX event with a document
+ location. A locator object will return valid results only during
+ calls to DocumentHandler methods; at any other time, the
+ results are unpredictable."""
+
+ def getColumnNumber(self):
+ "Return the column number where the current event ends."
+ return -1
+
+ def getLineNumber(self):
+ "Return the line number where the current event ends."
+ return -1
+
+ def getPublicId(self):
+ "Return the public identifier for the current event."
+ return None
+
+ def getSystemId(self):
+ "Return the system identifier for the current event."
+ return None
+
+# ===== INPUTSOURCE =====
+
+class InputSource:
+ """Encapsulation of the information needed by the XMLReader to
+ read entities.
+
+ This class may include information about the public identifier,
+ system identifier, byte stream (possibly with character encoding
+ information) and/or the character stream of an entity.
+
+ Applications will create objects of this class for use in the
+ XMLReader.parse method and for returning from
+ EntityResolver.resolveEntity.
+
+ An InputSource belongs to the application, the XMLReader is not
+ allowed to modify InputSource objects passed to it from the
+ application, although it may make copies and modify those."""
+
+ def __init__(self, system_id = None):
+ self.__system_id = system_id
+ self.__public_id = None
+ self.__encoding = None
+ self.__bytefile = None
+ self.__charfile = None
+
+ def setPublicId(self, public_id):
+ "Sets the public identifier of this InputSource."
+ self.__public_id = public_id
+
+ def getPublicId(self):
+ "Returns the public identifier of this InputSource."
+ return self.__public_id
+
+ def setSystemId(self, system_id):
+ "Sets the system identifier of this InputSource."
+ self.__system_id = system_id
+
+ def getSystemId(self):
+ "Returns the system identifier of this InputSource."
+ return self.__system_id
+
+ def setEncoding(self, encoding):
+ """Sets the character encoding of this InputSource.
+
+ The encoding must be a string acceptable for an XML encoding
+ declaration (see section 4.3.3 of the XML recommendation).
+
+ The encoding attribute of the InputSource is ignored if the
+ InputSource also contains a character stream."""
+ self.__encoding = encoding
+
+ def getEncoding(self):
+ "Get the character encoding of this InputSource."
+ return self.__encoding
+
+ def setByteStream(self, bytefile):
+ """Set the byte stream (a Python file-like object which does
+ not perform byte-to-character conversion) for this input
+ source.
+
+ The SAX parser will ignore this if there is also a character
+ stream specified, but it will use a byte stream in preference
+ to opening a URI connection itself.
+
+ If the application knows the character encoding of the byte
+ stream, it should set it with the setEncoding method."""
+ self.__bytefile = bytefile
+
+ def getByteStream(self):
+ """Get the byte stream for this input source.
+
+ The getEncoding method will return the character encoding for
+ this byte stream, or None if unknown."""
+ return self.__bytefile
+
+ def setCharacterStream(self, charfile):
+ """Set the character stream for this input source. (The stream
+ must be a Python 2.0 Unicode-wrapped file-like that performs
+ conversion to Unicode strings.)
+
+ If there is a character stream specified, the SAX parser will
+ ignore any byte stream and will not attempt to open a URI
+ connection to the system identifier."""
+ self.__charfile = charfile
+
+ def getCharacterStream(self):
+ "Get the character stream for this input source."
+ return self.__charfile
+
+# ===== ATTRIBUTESIMPL =====
+
+class AttributesImpl:
+
+ def __init__(self, attrs):
+ """Non-NS-aware implementation.
+
+ attrs should be of the form {name : value}."""
+ self._attrs = attrs
+
+ def getLength(self):
+ return len(self._attrs)
+
+ def getType(self, name):
+ return "CDATA"
+
+ def getValue(self, name):
+ return self._attrs[name]
+
+ def getValueByQName(self, name):
+ return self._attrs[name]
+
+ def getNameByQName(self, name):
+ if not self._attrs.has_key(name):
+ raise KeyError, name
+ return name
+
+ def getQNameByName(self, name):
+ if not self._attrs.has_key(name):
+ raise KeyError, name
+ return name
+
+ def getNames(self):
+ return self._attrs.keys()
+
+ def getQNames(self):
+ return self._attrs.keys()
+
+ def __len__(self):
+ return len(self._attrs)
+
+ def __getitem__(self, name):
+ return self._attrs[name]
+
+ def keys(self):
+ return self._attrs.keys()
+
+ def has_key(self, name):
+ return self._attrs.has_key(name)
+
+ def __contains__(self, name):
+ return self._attrs.has_key(name)
+
+ def get(self, name, alternative=None):
+ return self._attrs.get(name, alternative)
+
+ def copy(self):
+ return self.__class__(self._attrs)
+
+ def items(self):
+ return self._attrs.items()
+
+ def values(self):
+ return self._attrs.values()
+
+# ===== ATTRIBUTESNSIMPL =====
+
+class AttributesNSImpl(AttributesImpl):
+
+ def __init__(self, attrs, qnames):
+ """NS-aware implementation.
+
+ attrs should be of the form {(ns_uri, lname): value, ...}.
+ qnames of the form {(ns_uri, lname): qname, ...}."""
+ self._attrs = attrs
+ self._qnames = qnames
+
+ def getValueByQName(self, name):
+ for (nsname, qname) in self._qnames.items():
+ if qname == name:
+ return self._attrs[nsname]
+
+ raise KeyError, name
+
+ def getNameByQName(self, name):
+ for (nsname, qname) in self._qnames.items():
+ if qname == name:
+ return nsname
+
+ raise KeyError, name
+
+ def getQNameByName(self, name):
+ return self._qnames[name]
+
+ def getQNames(self):
+ return self._qnames.values()
+
+ def copy(self):
+ return self.__class__(self._attrs, self._qnames)
+
+
+def _test():
+ XMLReader()
+ IncrementalParser()
+ Locator()
+
+if __name__ == "__main__":
+ _test()