# Each element has a number of properties associated with it: #
# The {@link #ElementTree} class can be used to wrap an element # structure, and convert it from and to XML. ## import string, sys, re from . import ElementPath # 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. #
# 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:
#
# 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.
#
# 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.
#
# 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.
#
# 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("\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("" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("" % _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("")
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.
#
# 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.
#
# 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
# expat 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] == "":
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