# 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 sys import re import warnings from . import ElementPath ## # Parser error. This is a subclass of SyntaxError. #
# In addition to the exception value, an exception instance contains a # specific exception code in the code attribute, and the line and # column of the error in the position attribute. class ParseError(SyntaxError): pass # -------------------------------------------------------------------- ## # Checks if an object appears to be a valid element object. # # @param An element instance. # @return A true value if this is an element object. # @defreturn flag def iselement(element): # FIXME: not sure about this; # isinstance(element, Element) or look for tag/attrib/text attributes return hasattr(element, 'tag') ## # Element class. This class defines the Element interface, and # provides a reference implementation of this interface. #
# The element name, attribute names, and attribute values can be
# either ASCII strings (ordinary Python strings containing only 7-bit
# ASCII characters) or Unicode strings.
#
# @param tag The element name.
# @param attrib An optional dictionary, containing element attributes.
# @param **extra Additional attributes, given as keyword arguments.
# @see Element
# @see SubElement
# @see Comment
# @see ProcessingInstruction
class Element:
#
# If the tree structure is modified during iteration, new or removed
# elements may or may not be included. To get a stable set, use the
# list() function on the iterator, and loop over the resulting list.
#
# @param tag What tags to look for (default is to return all elements).
# @return An iterator containing all the matching elements.
# @defreturn iterator
def iter(self, tag=None):
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
for e in e.iter(tag):
yield e
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'elem.iter()' or 'list(elem.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
##
# Creates a text iterator. The iterator loops over this element
# and all subelements, in document order, and returns all inner
# text.
#
# @return An iterator containing all inner text.
# @defreturn iterator
def itertext(self):
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
if self.text:
yield self.text
for e in self:
for s in e.itertext():
yield s
if e.tail:
yield e.tail
# compatibility
_Element = _ElementInterface = Element
##
# 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 by the standard
# serializer.
#
# 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 by the standard
# serializer.
#
# @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 __repr__(self):
return '
# 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, encoding="unicode")
tail = elem.getroot().tail
if not tail or tail[-1] != "\n":
sys.stdout.write("\n")
# --------------------------------------------------------------------
# parsing
##
# 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 XMLParser} 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.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return A (event, elem) iterator.
def iterparse(source, events=None, parser=None):
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
if not parser:
parser = XMLParser(target=TreeBuilder())
return _IterParseIterator(source, events, parser, close_source)
class _IterParseIterator:
def __init__(self, source, events, parser, close_source=False):
self._file = source
self._close_file = close_source
self._events = []
self._index = 0
self._error = None
self.root = self._root = None
self._parser = parser
# 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):
append((event, (prefix or "", uri or "")))
parser.StartNamespaceDeclHandler = handler
elif event == "end-ns":
def handler(prefix, event=event, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
else:
raise ValueError("unknown event %r" % event)
def __next__(self):
while 1:
try:
item = self._events[self._index]
self._index += 1
return item
except IndexError:
pass
if self._error:
e = self._error
self._error = None
raise e
if self._parser is None:
self.root = self._root
if self._close_file:
self._file.close()
raise StopIteration
# load event buffer
del self._events[:]
self._index = 0
data = self._file.read(16384)
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._error = exc
else:
self._root = self._parser.close()
self._parser = None
def __iter__(self):
return self
##
# 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.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return An Element instance.
# @defreturn Element
def XML(text, parser=None):
if not parser:
parser = XMLParser(target=TreeBuilder())
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.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return A tuple containing an Element instance and a dictionary.
# @defreturn (Element, dictionary)
def XMLID(text, parser=None):
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
tree = parser.close()
ids = {}
for elem in tree.iter():
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
##
# Parses an XML document from a sequence of string fragments.
#
# @param sequence A list or other sequence containing XML data fragments.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return An Element instance.
# @defreturn Element
# @since 1.3
def fromstringlist(sequence, parser=None):
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
##
# 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 = Element
self._factory = element_factory
##
# Flushes the builder buffers, and returns the toplevel document
# element.
#
# @return An Element instance.
# @defreturn Element
def close(self):
assert len(self._elem) == 0, "missing end tags"
assert self._last is not None, "missing toplevel element"
return self._last
def _flush(self):
if self._data:
if self._last is not None:
text = "".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.
# @keyparam encoding Optional encoding. If given, the value overrides
# the encoding specified in the XML file.
# @see #ElementTree
# @see #TreeBuilder
class XMLParser:
def __init__(self, html=0, target=None, encoding=None):
try:
from xml.parsers import expat
except ImportError:
try:
import pyexpat as expat
except ImportError:
raise ImportError(
"No module named expat; use SimpleXMLTreeBuilder instead"
)
parser = expat.ParserCreate(encoding, "}")
if target is None:
target = TreeBuilder()
# underscored names are provided for compatibility only
self.parser = self._parser = parser
self.target = self._target = target
self._error = expat.error
self._names = {} # name memo cache
# main callbacks
parser.DefaultHandlerExpand = self._default
if hasattr(target, 'start'):
parser.StartElementHandler = self._start
if hasattr(target, 'end'):
parser.EndElementHandler = self._end
if hasattr(target, 'data'):
parser.CharacterDataHandler = target.data
# miscellaneous callbacks
if hasattr(target, 'comment'):
parser.CommentHandler = target.comment
if hasattr(target, 'pi'):
parser.ProcessingInstructionHandler = target.pi
# let expat do the buffering, if supported
try:
parser.buffer_text = 1
except AttributeError:
pass
# use new-style attribute handling, if supported
try:
parser.ordered_attributes = 1
parser.specified_attributes = 1
if hasattr(target, 'start'):
parser.StartElementHandler = self._start_list
except AttributeError:
pass
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _raiseerror(self, value):
err = ParseError(value)
err.code = value.code
err.position = value.lineno, value.offset
raise err
def _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
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)] = 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])] = attrib_in[i+1]
return self.target.start(tag, attrib)
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:
data_handler = self.target.data
except AttributeError:
return
try:
data_handler(self.entity[text[1:-1]])
except KeyError:
from xml.parsers import expat
err = expat.error(
"undefined entity %s: line %d, column %d" %
(text, self.parser.ErrorLineNumber,
self.parser.ErrorColumnNumber)
)
err.code = 11 # XML_ERROR_UNDEFINED_ENTITY
err.lineno = self.parser.ErrorLineNumber
err.offset = self.parser.ErrorColumnNumber
raise err
elif prefix == "<" and text[:9] == "":
self._doctype = None
return
text = text.strip()
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
if pubid:
pubid = pubid[1:-1]
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if hasattr(self.target, "doctype"):
self.target.doctype(name, pubid, system[1:-1])
elif self.doctype != self._XMLParser__doctype:
# warn about deprecated call
self._XMLParser__doctype(name, pubid, system[1:-1])
self.doctype(name, pubid, system[1:-1])
self._doctype = None
##
# (Deprecated) Handles a doctype declaration.
#
# @param name Doctype name.
# @param pubid Public identifier.
# @param system System identifier.
def doctype(self, name, pubid, system):
"""This method of XMLParser is deprecated."""
warnings.warn(
"This method of XMLParser is deprecated. Define doctype() "
"method on the TreeBuilder target.",
DeprecationWarning,
)
# sentinel, if doctype is redefined in a subclass
__doctype = doctype
##
# Feeds data to the parser.
#
# @param data Encoded data.
def feed(self, data):
try:
self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
##
# Finishes feeding data to the parser.
#
# @return An element structure.
# @defreturn Element
def close(self):
try:
self.parser.Parse("", 1) # end of data
except self._error as v:
self._raiseerror(v)
try:
close_handler = self.target.close
except AttributeError:
pass
else:
return close_handler()
finally:
# get rid of circular references
del self.parser, self._parser
del self.target, self._target
# Import the C accelerators
try:
# Element, SubElement, ParseError, TreeBuilder, XMLParser
from _elementtree import *
except ImportError:
pass
else:
# Overwrite 'ElementTree.parse' and 'iterparse' to use the C XMLParser
class ElementTree(ElementTree):
def parse(self, source, parser=None):
close_source = False
if not hasattr(source, 'read'):
source = open(source, 'rb')
close_source = True
try:
if parser is not None:
while True:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
else:
parser = XMLParser()
self._root = parser._parse(source)
return self._root
finally:
if close_source:
source.close()
class iterparse:
root = None
def __init__(self, file, events=None):
self._close_file = False
if not hasattr(file, 'read'):
file = open(file, 'rb')
self._close_file = True
self._file = file
self._events = []
self._index = 0
self._error = None
self.root = self._root = None
b = TreeBuilder()
self._parser = XMLParser(b)
self._parser._setevents(self._events, events)
def __next__(self):
while True:
try:
item = self._events[self._index]
self._index += 1
return item
except IndexError:
pass
if self._error:
e = self._error
self._error = None
raise e
if self._parser is None:
self.root = self._root
if self._close_file:
self._file.close()
raise StopIteration
# load event buffer
del self._events[:]
self._index = 0
data = self._file.read(16384)
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._error = exc
else:
self._root = self._parser.close()
self._parser = None
def __iter__(self):
return self
# compatibility
XMLTreeBuilder = XMLParser
# workaround circular import.
try:
from ElementC14N import _serialize_c14n
_serialize["c14n"] = _serialize_c14n
except ImportError:
pass