ÿØÿà JFIF ÿÛ „ ( %!1!%*+... 983,7(-.-
lib64/python3.8/xml/etree/ElementTree.py 0000644 00000216331 15235773161 0013745 0 ustar 00 """Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See http://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
"canonicalize", "C14NWriterTarget",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import collections
import collections.abc
import contextlib
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
text...tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
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. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
self.tag = tag
self.attrib = {**attrib, **extra}
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def copy(self):
"""Return copy of current element.
This creates a shallow copy. Subelements will be shared with the
original tree.
"""
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"The behavior of this method will change in future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
FutureWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
if isinstance(index, slice):
for elt in element:
self._assert_is_element(elt)
else:
self._assert_is_element(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.append(element)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
self._children.remove(subelement)
def getchildren(self):
"""(Deprecated) Return all subelements.
Elements are returned in document order.
"""
warnings.warn(
"This method will be removed in future versions. "
"Use 'list(elem)' or iteration over elem instead.",
DeprecationWarning, stacklevel=2
)
return self._children
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
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.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
# compatibility
def getiterator(self, tag=None):
warnings.warn(
"This method will be removed in future versions. "
"Use 'elem.iter()' or 'list(elem.iter())' instead.",
DeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = {**attrib, **extra}
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
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 '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while True:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
# compatibility
def getiterator(self, tag=None):
warnings.warn(
"This method will be removed in future versions. "
"Use 'tree.iter()' or 'list(tree.iter())' instead.",
DeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
enc_lower = encoding.lower()
with _get_writer(file_or_filename, enc_lower) as write:
if method == "xml" and (xml_declaration or
(xml_declaration is None and
enc_lower not in ("utf-8", "us-ascii", "unicode"))):
declared_encoding = encoding
if enc_lower == "unicode":
# Retrieve the default encoding for the xml declaration
import locale
declared_encoding = locale.getpreferredencoding()
write("\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding == "unicode":
file = open(file_or_filename, "w")
else:
file = open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace")
with file:
yield file.write
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding == "unicode":
# use a text writer as is
yield write
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % text)
elif tag is ProcessingInstruction:
write("" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param")
try:
HTML_EMPTY = set(HTML_EMPTY)
except NameError:
pass
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match(r"ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
# For tests and troubleshooting
register_namespace._namespace_map = _namespace_map
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 characters, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
# The following business with carriage returns is to satisfy
# Section 2.11 of the XML specification, stating that
# CR or CR LN should be replaced with just LN
# http://www.w3.org/TR/REC-xml/#sec-line-ends
if "\r\n" in text:
text = text.replace("\r\n", "\n")
if "\r" in text:
text = text.replace("\r", "\n")
#The following four lines are issue 17582
if "\n" in text:
text = text.replace("\n", "
")
if "\t" in text:
text = text.replace("\t", " ")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
def tostring(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
"""Generate string representation of XML element.
All subelements are included. If encoding is "unicode", a string
is returned. Otherwise a bytestring is returned.
*element* is an Element instance, *encoding* is an optional output
encoding defaulting to US-ASCII, *method* is an optional output which can
be one of "xml" (default), "html", "text" or "c14n", *default_namespace*
sets the default XML namespace (for "xmlns").
Returns an (optionally) encoded string containing the XML data.
"""
stream = io.StringIO() if encoding == 'unicode' else io.BytesIO()
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return stream.getvalue()
class _ListDataStream(io.BufferedIOBase):
"""An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
def writable(self):
return True
def seekable(self):
return True
def write(self, b):
self.lst.append(b)
def tell(self):
return len(self.lst)
def tostringlist(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return lst
def dump(elem):
"""Write element tree or element structure to sys.stdout.
This function should be used for debugging only.
*elem* is either an ElementTree, or a single Element. The exact output
format is implementation dependent. In this version, it's written as an
ordinary XML file.
"""
# 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
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
def iterparse(source, events=None, parser=None):
"""Incrementally parse XML document into ElementTree.
This class also reports what's going on to the user based on the
*events* it is initialized with. The supported events are the strings
"start", "end", "start-ns" and "end-ns" (the "ns" events are used to get
detailed namespace information). If *events* is omitted, only
"end" events are reported.
*source* is a filename or file object containing XML data, *events* is
a list of events to report back, *parser* is an optional parser instance.
Returns an iterator providing (event, elem) pairs.
"""
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
pullparser = XMLPullParser(events=events, _parser=parser)
def iterator():
try:
while True:
yield from pullparser.read_events()
# load event buffer
data = source.read(16 * 1024)
if not data:
break
pullparser.feed(data)
root = pullparser._close_and_return_root()
yield from pullparser.read_events()
it.root = root
finally:
if close_source:
source.close()
class IterParseIterator(collections.abc.Iterator):
__next__ = iterator().__next__
it = IterParseIterator()
it.root = None
del iterator, IterParseIterator
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
return it
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See http://bugs.python.org/issue17741 for more details.
self._events_queue = collections.deque()
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def feed(self, data):
"""Feed encoded data to parser."""
if self._parser is None:
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
root = self._parser.close()
self._parser = None
return root
def close(self):
"""Finish feeding data to parser.
Unlike XMLParser, does not return the root element. Use
read_events() to consume elements from XMLPullParser.
"""
self._close_and_return_root()
def read_events(self):
"""Return an iterator over currently available (event, elem) pairs.
Events are consumed from the internal event queue as they are
retrieved from the iterator.
"""
events = self._events_queue
while events:
event = events.popleft()
if isinstance(event, Exception):
raise event
else:
yield event
def XML(text, parser=None):
"""Parse XML document from string constant.
This function can be used to embed "XML Literals" in Python code.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
return parser.close()
def XMLID(text, parser=None):
"""Parse XML document from string constant for its IDs.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an (Element, dict) tuple, in which the
dict maps element id:s to elements.
"""
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
# Parse XML document from string constant. Alias for XML().
fromstring = XML
def fromstringlist(sequence, parser=None):
"""Parse XML document from sequence of string fragments.
*sequence* is a list of other sequence, *parser* is an optional parser
instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
class TreeBuilder:
"""Generic element structure builder.
This builder converts a sequence of start, data, and 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.
*element_factory* is an optional element factory which is called
to create new Element instances, as necessary.
*comment_factory* is a factory to create comments to be used instead of
the standard factory. If *insert_comments* is false (the default),
comments will not be inserted into the tree.
*pi_factory* is a factory to create processing instructions to be used
instead of the standard factory. If *insert_pis* is false (the default),
processing instructions will not be inserted into the tree.
"""
def __init__(self, element_factory=None, *,
comment_factory=None, pi_factory=None,
insert_comments=False, insert_pis=False):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._root = None # root element
self._tail = None # true if we're after an end tag
if comment_factory is None:
comment_factory = Comment
self._comment_factory = comment_factory
self.insert_comments = insert_comments
if pi_factory is None:
pi_factory = ProcessingInstruction
self._pi_factory = pi_factory
self.insert_pis = insert_pis
if element_factory is None:
element_factory = Element
self._factory = element_factory
def close(self):
"""Flush builder buffers and return toplevel document Element."""
assert len(self._elem) == 0, "missing end tags"
assert self._root is not None, "missing toplevel element"
return self._root
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 = []
def data(self, data):
"""Add text to current element."""
self._data.append(data)
def start(self, tag, attrs):
"""Open new element and return it.
*tag* is the element name, *attrs* is a dict containing element
attributes.
"""
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
elif self._root is None:
self._root = elem
self._elem.append(elem)
self._tail = 0
return elem
def end(self, tag):
"""Close and return current Element.
*tag* is the element name.
"""
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
def comment(self, text):
"""Create a comment using the comment_factory.
*text* is the text of the comment.
"""
return self._handle_single(
self._comment_factory, self.insert_comments, text)
def pi(self, target, text=None):
"""Create a processing instruction using the pi_factory.
*target* is the target name of the processing instruction.
*text* is the data of the processing instruction, or ''.
"""
return self._handle_single(
self._pi_factory, self.insert_pis, target, text)
def _handle_single(self, factory, insert, *args):
elem = factory(*args)
if insert:
self._flush()
self._last = elem
if self._elem:
self._elem[-1].append(elem)
self._tail = 1
return elem
# also see ElementTree and TreeBuilder
class XMLParser:
"""Element structure builder for XML source data based on the expat parser.
*target* is an optional target object which defaults to an instance of the
standard TreeBuilder class, *encoding* is an optional encoding string
which if given, overrides the encoding specified in the XML file:
http://www.iana.org/assignments/character-sets
"""
def __init__(self, *, 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, 'start_ns'):
parser.StartNamespaceDeclHandler = self._start_ns
if hasattr(target, 'end_ns'):
parser.EndNamespaceDeclHandler = self._end_ns
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
# Configure pyexpat: buffering, new-style attribute handling.
parser.buffer_text = 1
parser.ordered_attributes = 1
parser.specified_attributes = 1
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
parser = self._parser
append = events_queue.append
for event_name in events_to_report:
if event_name == "start":
parser.ordered_attributes = 1
parser.specified_attributes = 1
def handler(tag, attrib_in, event=event_name, append=append,
start=self._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event_name == "end":
def handler(tag, event=event_name, append=append,
end=self._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event_name == "start-ns":
# TreeBuilder does not implement .start_ns()
if hasattr(self.target, "start_ns"):
def handler(prefix, uri, event=event_name, append=append,
start_ns=self._start_ns):
append((event, start_ns(prefix, uri)))
else:
def handler(prefix, uri, event=event_name, append=append):
append((event, (prefix or '', uri or '')))
parser.StartNamespaceDeclHandler = handler
elif event_name == "end-ns":
# TreeBuilder does not implement .end_ns()
if hasattr(self.target, "end_ns"):
def handler(prefix, event=event_name, append=append,
end_ns=self._end_ns):
append((event, end_ns(prefix)))
else:
def handler(prefix, event=event_name, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
elif event_name == 'comment':
def handler(text, event=event_name, append=append, self=self):
append((event, self.target.comment(text)))
parser.CommentHandler = handler
elif event_name == 'pi':
def handler(pi_target, data, event=event_name, append=append,
self=self):
append((event, self.target.pi(pi_target, data)))
parser.ProcessingInstructionHandler = handler
else:
raise ValueError("unknown event %r" % event_name)
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_ns(self, prefix, uri):
return self.target.start_ns(prefix or '', uri or '')
def _end_ns(self, prefix):
return self.target.end_ns(prefix or '')
def _start(self, tag, attr_list):
# Handler for expat's StartElementHandler. Since ordered_attributes
# is set, the attributes are reported as a list of alternating
# attribute name,value.
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attr_list:
for i in range(0, len(attr_list), 2):
attrib[fixname(attr_list[i])] = attr_list[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 hasattr(self, "doctype"):
warnings.warn(
"The doctype() method of XMLParser is ignored. "
"Define doctype() method on the TreeBuilder target.",
RuntimeWarning)
self._doctype = None
def feed(self, data):
"""Feed encoded data to parser."""
try:
self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
def close(self):
"""Finish feeding data to parser and return element structure."""
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
# --------------------------------------------------------------------
# C14N 2.0
def canonicalize(xml_data=None, *, out=None, from_file=None, **options):
"""Convert XML to its C14N 2.0 serialised form.
If *out* is provided, it must be a file or file-like object that receives
the serialised canonical XML output (text, not bytes) through its ``.write()``
method. To write to a file, open it in text mode with encoding "utf-8".
If *out* is not provided, this function returns the output as text string.
Either *xml_data* (an XML string) or *from_file* (a file path or
file-like object) must be provided as input.
The configuration options are the same as for the ``C14NWriterTarget``.
"""
if xml_data is None and from_file is None:
raise ValueError("Either 'xml_data' or 'from_file' must be provided as input")
sio = None
if out is None:
sio = out = io.StringIO()
parser = XMLParser(target=C14NWriterTarget(out.write, **options))
if xml_data is not None:
parser.feed(xml_data)
parser.close()
elif from_file is not None:
parse(from_file, parser=parser)
return sio.getvalue() if sio is not None else None
_looks_like_prefix_name = re.compile(r'^\w+:\w+$', re.UNICODE).match
class C14NWriterTarget:
"""
Canonicalization writer target for the XMLParser.
Serialises parse events to XML C14N 2.0.
The *write* function is used for writing out the resulting data stream
as text (not bytes). To write to a file, open it in text mode with encoding
"utf-8" and pass its ``.write`` method.
Configuration options:
- *with_comments*: set to true to include comments
- *strip_text*: set to true to strip whitespace before and after text content
- *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}"
- *qname_aware_tags*: a set of qname aware tag names in which prefixes
should be replaced in text content
- *qname_aware_attrs*: a set of qname aware attribute names in which prefixes
should be replaced in text content
- *exclude_attrs*: a set of attribute names that should not be serialised
- *exclude_tags*: a set of tag names that should not be serialised
"""
def __init__(self, write, *,
with_comments=False, strip_text=False, rewrite_prefixes=False,
qname_aware_tags=None, qname_aware_attrs=None,
exclude_attrs=None, exclude_tags=None):
self._write = write
self._data = []
self._with_comments = with_comments
self._strip_text = strip_text
self._exclude_attrs = set(exclude_attrs) if exclude_attrs else None
self._exclude_tags = set(exclude_tags) if exclude_tags else None
self._rewrite_prefixes = rewrite_prefixes
if qname_aware_tags:
self._qname_aware_tags = set(qname_aware_tags)
else:
self._qname_aware_tags = None
if qname_aware_attrs:
self._find_qname_aware_attrs = set(qname_aware_attrs).intersection
else:
self._find_qname_aware_attrs = None
# Stack with globally and newly declared namespaces as (uri, prefix) pairs.
self._declared_ns_stack = [[
("http://www.w3.org/XML/1998/namespace", "xml"),
]]
# Stack with user declared namespace prefixes as (uri, prefix) pairs.
self._ns_stack = []
if not rewrite_prefixes:
self._ns_stack.append(list(_namespace_map.items()))
self._ns_stack.append([])
self._prefix_map = {}
self._preserve_space = [False]
self._pending_start = None
self._root_seen = False
self._root_done = False
self._ignored_depth = 0
def _iter_namespaces(self, ns_stack, _reversed=reversed):
for namespaces in _reversed(ns_stack):
if namespaces: # almost no element declares new namespaces
yield from namespaces
def _resolve_prefix_name(self, prefixed_name):
prefix, name = prefixed_name.split(':', 1)
for uri, p in self._iter_namespaces(self._ns_stack):
if p == prefix:
return f'{{{uri}}}{name}'
raise ValueError(f'Prefix {prefix} of QName "{prefixed_name}" is not declared in scope')
def _qname(self, qname, uri=None):
if uri is None:
uri, tag = qname[1:].rsplit('}', 1) if qname[:1] == '{' else ('', qname)
else:
tag = qname
prefixes_seen = set()
for u, prefix in self._iter_namespaces(self._declared_ns_stack):
if u == uri and prefix not in prefixes_seen:
return f'{prefix}:{tag}' if prefix else tag, tag, uri
prefixes_seen.add(prefix)
# Not declared yet => add new declaration.
if self._rewrite_prefixes:
if uri in self._prefix_map:
prefix = self._prefix_map[uri]
else:
prefix = self._prefix_map[uri] = f'n{len(self._prefix_map)}'
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}', tag, uri
if not uri and '' not in prefixes_seen:
# No default namespace declared => no prefix needed.
return tag, tag, uri
for u, prefix in self._iter_namespaces(self._ns_stack):
if u == uri:
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}' if prefix else tag, tag, uri
if not uri:
# As soon as a default namespace is defined,
# anything that has no namespace (and thus, no prefix) goes there.
return tag, tag, uri
raise ValueError(f'Namespace "{uri}" is not declared in scope')
def data(self, data):
if not self._ignored_depth:
self._data.append(data)
def _flush(self, _join_text=''.join):
data = _join_text(self._data)
del self._data[:]
if self._strip_text and not self._preserve_space[-1]:
data = data.strip()
if self._pending_start is not None:
args, self._pending_start = self._pending_start, None
qname_text = data if data and _looks_like_prefix_name(data) else None
self._start(*args, qname_text)
if qname_text is not None:
return
if data and self._root_seen:
self._write(_escape_cdata_c14n(data))
def start_ns(self, prefix, uri):
if self._ignored_depth:
return
# we may have to resolve qnames in text content
if self._data:
self._flush()
self._ns_stack[-1].append((uri, prefix))
def start(self, tag, attrs):
if self._exclude_tags is not None and (
self._ignored_depth or tag in self._exclude_tags):
self._ignored_depth += 1
return
if self._data:
self._flush()
new_namespaces = []
self._declared_ns_stack.append(new_namespaces)
if self._qname_aware_tags is not None and tag in self._qname_aware_tags:
# Need to parse text first to see if it requires a prefix declaration.
self._pending_start = (tag, attrs, new_namespaces)
return
self._start(tag, attrs, new_namespaces)
def _start(self, tag, attrs, new_namespaces, qname_text=None):
if self._exclude_attrs is not None and attrs:
attrs = {k: v for k, v in attrs.items() if k not in self._exclude_attrs}
qnames = {tag, *attrs}
resolved_names = {}
# Resolve prefixes in attribute and tag text.
if qname_text is not None:
qname = resolved_names[qname_text] = self._resolve_prefix_name(qname_text)
qnames.add(qname)
if self._find_qname_aware_attrs is not None and attrs:
qattrs = self._find_qname_aware_attrs(attrs)
if qattrs:
for attr_name in qattrs:
value = attrs[attr_name]
if _looks_like_prefix_name(value):
qname = resolved_names[value] = self._resolve_prefix_name(value)
qnames.add(qname)
else:
qattrs = None
else:
qattrs = None
# Assign prefixes in lexicographical order of used URIs.
parse_qname = self._qname
parsed_qnames = {n: parse_qname(n) for n in sorted(
qnames, key=lambda n: n.split('}', 1))}
# Write namespace declarations in prefix order ...
if new_namespaces:
attr_list = [
('xmlns:' + prefix if prefix else 'xmlns', uri)
for uri, prefix in new_namespaces
]
attr_list.sort()
else:
# almost always empty
attr_list = []
# ... followed by attributes in URI+name order
if attrs:
for k, v in sorted(attrs.items()):
if qattrs is not None and k in qattrs and v in resolved_names:
v = parsed_qnames[resolved_names[v]][0]
attr_qname, attr_name, uri = parsed_qnames[k]
# No prefix for attributes in default ('') namespace.
attr_list.append((attr_qname if uri else attr_name, v))
# Honour xml:space attributes.
space_behaviour = attrs.get('{http://www.w3.org/XML/1998/namespace}space')
self._preserve_space.append(
space_behaviour == 'preserve' if space_behaviour
else self._preserve_space[-1])
# Write the tag.
write = self._write
write('<' + parsed_qnames[tag][0])
if attr_list:
write(''.join([f' {k}="{_escape_attrib_c14n(v)}"' for k, v in attr_list]))
write('>')
# Write the resolved qname text content.
if qname_text is not None:
write(_escape_cdata_c14n(parsed_qnames[resolved_names[qname_text]][0]))
self._root_seen = True
self._ns_stack.append([])
def end(self, tag):
if self._ignored_depth:
self._ignored_depth -= 1
return
if self._data:
self._flush()
self._write(f'')
self._preserve_space.pop()
self._root_done = len(self._preserve_space) == 1
self._declared_ns_stack.pop()
self._ns_stack.pop()
def comment(self, text):
if not self._with_comments:
return
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(f'')
if not self._root_seen:
self._write('\n')
def pi(self, target, data):
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(
f'' if data else f'')
if not self._root_seen:
self._write('\n')
def _escape_cdata_c14n(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '>' in text:
text = text.replace('>', '>')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_c14n(text):
# escape attribute value
try:
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '"' in text:
text = text.replace('"', '"')
if '\t' in text:
text = text.replace('\t', ' ')
if '\n' in text:
text = text.replace('\n', '
')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
# Import the C accelerators
try:
# Element is going to be shadowed by the C implementation. We need to keep
# the Python version of it accessible for some "creative" by external code
# (see tests)
_Element_Py = Element
# Element, SubElement, ParseError, TreeBuilder, XMLParser, _set_factories
from _elementtree import *
from _elementtree import _set_factories
except ImportError:
pass
else:
_set_factories(Comment, ProcessingInstruction)
usr/lib64/python3.12/xml/etree/ElementTree.py 0000644 00000220441 15236011105 0014606 0 ustar 00 """Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See https://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"indent", "iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
"canonicalize", "C14NWriterTarget",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import collections
import collections.abc
import contextlib
import weakref
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
text...tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
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. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
self.tag = tag
self.attrib = {**attrib, **extra}
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def __copy__(self):
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"Testing an element's truth value will always return True in "
"future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
DeprecationWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
if isinstance(index, slice):
for elt in element:
self._assert_is_element(elt)
else:
self._assert_is_element(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.append(element)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
self._children.remove(subelement)
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
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.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = {**attrib, **extra}
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
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 '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while data := source.read(65536):
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
with _get_writer(file_or_filename, encoding) as (write, declared_encoding):
if method == "xml" and (xml_declaration or
(xml_declaration is None and
encoding.lower() != "unicode" and
declared_encoding.lower() not in ("utf-8", "us-ascii"))):
write("\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding.lower() == "unicode":
encoding="utf-8"
with open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace") as file:
yield file.write, encoding
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding.lower() == "unicode":
# use a text writer as is
yield write, getattr(file_or_filename, "encoding", None) or "utf-8"
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write, encoding
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % text)
elif tag is ProcessingInstruction:
write("" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = {"area", "base", "basefont", "br", "col", "embed", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param", "source",
"track", "wbr"}
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match(r"ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
# For tests and troubleshooting
register_namespace._namespace_map = _namespace_map
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 characters, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
# Although section 2.11 of the XML specification states that CR or
# CR LN should be replaced with just LN, it applies only to EOLNs
# which take part of organizing file into lines. Within attributes,
# we are replacing these with entity numbers, so they do not count.
# http://www.w3.org/TR/REC-xml/#sec-line-ends
# The current solution, contained in following six lines, was
# discussed in issue 17582 and 39011.
if "\r" in text:
text = text.replace("\r", "
")
if "\n" in text:
text = text.replace("\n", "
")
if "\t" in text:
text = text.replace("\t", " ")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
def tostring(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
"""Generate string representation of XML element.
All subelements are included. If encoding is "unicode", a string
is returned. Otherwise a bytestring is returned.
*element* is an Element instance, *encoding* is an optional output
encoding defaulting to US-ASCII, *method* is an optional output which can
be one of "xml" (default), "html", "text" or "c14n", *default_namespace*
sets the default XML namespace (for "xmlns").
Returns an (optionally) encoded string containing the XML data.
"""
stream = io.StringIO() if encoding == 'unicode' else io.BytesIO()
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return stream.getvalue()
class _ListDataStream(io.BufferedIOBase):
"""An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
def writable(self):
return True
def seekable(self):
return True
def write(self, b):
self.lst.append(b)
def tell(self):
return len(self.lst)
def tostringlist(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return lst
def dump(elem):
"""Write element tree or element structure to sys.stdout.
This function should be used for debugging only.
*elem* is either an ElementTree, or a single Element. The exact output
format is implementation dependent. In this version, it's written as an
ordinary XML file.
"""
# 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")
def indent(tree, space=" ", level=0):
"""Indent an XML document by inserting newlines and indentation space
after elements.
*tree* is the ElementTree or Element to modify. The (root) element
itself will not be changed, but the tail text of all elements in its
subtree will be adapted.
*space* is the whitespace to insert for each indentation level, two
space characters by default.
*level* is the initial indentation level. Setting this to a higher
value than 0 can be used for indenting subtrees that are more deeply
nested inside of a document.
"""
if isinstance(tree, ElementTree):
tree = tree.getroot()
if level < 0:
raise ValueError(f"Initial indentation level must be >= 0, got {level}")
if not len(tree):
return
# Reduce the memory consumption by reusing indentation strings.
indentations = ["\n" + level * space]
def _indent_children(elem, level):
# Start a new indentation level for the first child.
child_level = level + 1
try:
child_indentation = indentations[child_level]
except IndexError:
child_indentation = indentations[level] + space
indentations.append(child_indentation)
if not elem.text or not elem.text.strip():
elem.text = child_indentation
for child in elem:
if len(child):
_indent_children(child, child_level)
if not child.tail or not child.tail.strip():
child.tail = child_indentation
# Dedent after the last child by overwriting the previous indentation.
if not child.tail.strip():
child.tail = indentations[level]
_indent_children(tree, 0)
# --------------------------------------------------------------------
# parsing
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
def iterparse(source, events=None, parser=None):
"""Incrementally parse XML document into ElementTree.
This class also reports what's going on to the user based on the
*events* it is initialized with. The supported events are the strings
"start", "end", "start-ns" and "end-ns" (the "ns" events are used to get
detailed namespace information). If *events* is omitted, only
"end" events are reported.
*source* is a filename or file object containing XML data, *events* is
a list of events to report back, *parser* is an optional parser instance.
Returns an iterator providing (event, elem) pairs.
"""
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
pullparser = XMLPullParser(events=events, _parser=parser)
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
else:
close_source = False
def iterator(source):
try:
while True:
yield from pullparser.read_events()
# load event buffer
data = source.read(16 * 1024)
if not data:
break
pullparser.feed(data)
root = pullparser._close_and_return_root()
yield from pullparser.read_events()
it = wr()
if it is not None:
it.root = root
finally:
if close_source:
source.close()
class IterParseIterator(collections.abc.Iterator):
__next__ = iterator(source).__next__
def __del__(self):
if close_source:
source.close()
it = IterParseIterator()
it.root = None
wr = weakref.ref(it)
return it
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See https://bugs.python.org/issue17741 for more details.
self._events_queue = collections.deque()
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def feed(self, data):
"""Feed encoded data to parser."""
if self._parser is None:
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
root = self._parser.close()
self._parser = None
return root
def close(self):
"""Finish feeding data to parser.
Unlike XMLParser, does not return the root element. Use
read_events() to consume elements from XMLPullParser.
"""
self._close_and_return_root()
def read_events(self):
"""Return an iterator over currently available (event, elem) pairs.
Events are consumed from the internal event queue as they are
retrieved from the iterator.
"""
events = self._events_queue
while events:
event = events.popleft()
if isinstance(event, Exception):
raise event
else:
yield event
def flush(self):
if self._parser is None:
raise ValueError("flush() called after end of stream")
self._parser.flush()
def XML(text, parser=None):
"""Parse XML document from string constant.
This function can be used to embed "XML Literals" in Python code.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
return parser.close()
def XMLID(text, parser=None):
"""Parse XML document from string constant for its IDs.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an (Element, dict) tuple, in which the
dict maps element id:s to elements.
"""
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
# Parse XML document from string constant. Alias for XML().
fromstring = XML
def fromstringlist(sequence, parser=None):
"""Parse XML document from sequence of string fragments.
*sequence* is a list of other sequence, *parser* is an optional parser
instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
class TreeBuilder:
"""Generic element structure builder.
This builder converts a sequence of start, data, and 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.
*element_factory* is an optional element factory which is called
to create new Element instances, as necessary.
*comment_factory* is a factory to create comments to be used instead of
the standard factory. If *insert_comments* is false (the default),
comments will not be inserted into the tree.
*pi_factory* is a factory to create processing instructions to be used
instead of the standard factory. If *insert_pis* is false (the default),
processing instructions will not be inserted into the tree.
"""
def __init__(self, element_factory=None, *,
comment_factory=None, pi_factory=None,
insert_comments=False, insert_pis=False):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._root = None # root element
self._tail = None # true if we're after an end tag
if comment_factory is None:
comment_factory = Comment
self._comment_factory = comment_factory
self.insert_comments = insert_comments
if pi_factory is None:
pi_factory = ProcessingInstruction
self._pi_factory = pi_factory
self.insert_pis = insert_pis
if element_factory is None:
element_factory = Element
self._factory = element_factory
def close(self):
"""Flush builder buffers and return toplevel document Element."""
assert len(self._elem) == 0, "missing end tags"
assert self._root is not None, "missing toplevel element"
return self._root
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 = []
def data(self, data):
"""Add text to current element."""
self._data.append(data)
def start(self, tag, attrs):
"""Open new element and return it.
*tag* is the element name, *attrs* is a dict containing element
attributes.
"""
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
elif self._root is None:
self._root = elem
self._elem.append(elem)
self._tail = 0
return elem
def end(self, tag):
"""Close and return current Element.
*tag* is the element name.
"""
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
def comment(self, text):
"""Create a comment using the comment_factory.
*text* is the text of the comment.
"""
return self._handle_single(
self._comment_factory, self.insert_comments, text)
def pi(self, target, text=None):
"""Create a processing instruction using the pi_factory.
*target* is the target name of the processing instruction.
*text* is the data of the processing instruction, or ''.
"""
return self._handle_single(
self._pi_factory, self.insert_pis, target, text)
def _handle_single(self, factory, insert, *args):
elem = factory(*args)
if insert:
self._flush()
self._last = elem
if self._elem:
self._elem[-1].append(elem)
self._tail = 1
return elem
# also see ElementTree and TreeBuilder
class XMLParser:
"""Element structure builder for XML source data based on the expat parser.
*target* is an optional target object which defaults to an instance of the
standard TreeBuilder class, *encoding* is an optional encoding string
which if given, overrides the encoding specified in the XML file:
http://www.iana.org/assignments/character-sets
"""
def __init__(self, *, 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, 'start_ns'):
parser.StartNamespaceDeclHandler = self._start_ns
if hasattr(target, 'end_ns'):
parser.EndNamespaceDeclHandler = self._end_ns
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
# Configure pyexpat: buffering, new-style attribute handling.
parser.buffer_text = 1
parser.ordered_attributes = 1
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
parser = self._parser
append = events_queue.append
for event_name in events_to_report:
if event_name == "start":
parser.ordered_attributes = 1
def handler(tag, attrib_in, event=event_name, append=append,
start=self._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event_name == "end":
def handler(tag, event=event_name, append=append,
end=self._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event_name == "start-ns":
# TreeBuilder does not implement .start_ns()
if hasattr(self.target, "start_ns"):
def handler(prefix, uri, event=event_name, append=append,
start_ns=self._start_ns):
append((event, start_ns(prefix, uri)))
else:
def handler(prefix, uri, event=event_name, append=append):
append((event, (prefix or '', uri or '')))
parser.StartNamespaceDeclHandler = handler
elif event_name == "end-ns":
# TreeBuilder does not implement .end_ns()
if hasattr(self.target, "end_ns"):
def handler(prefix, event=event_name, append=append,
end_ns=self._end_ns):
append((event, end_ns(prefix)))
else:
def handler(prefix, event=event_name, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
elif event_name == 'comment':
def handler(text, event=event_name, append=append, self=self):
append((event, self.target.comment(text)))
parser.CommentHandler = handler
elif event_name == 'pi':
def handler(pi_target, data, event=event_name, append=append,
self=self):
append((event, self.target.pi(pi_target, data)))
parser.ProcessingInstructionHandler = handler
else:
raise ValueError("unknown event %r" % event_name)
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_ns(self, prefix, uri):
return self.target.start_ns(prefix or '', uri or '')
def _end_ns(self, prefix):
return self.target.end_ns(prefix or '')
def _start(self, tag, attr_list):
# Handler for expat's StartElementHandler. Since ordered_attributes
# is set, the attributes are reported as a list of alternating
# attribute name,value.
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attr_list:
for i in range(0, len(attr_list), 2):
attrib[fixname(attr_list[i])] = attr_list[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 hasattr(self, "doctype"):
warnings.warn(
"The doctype() method of XMLParser is ignored. "
"Define doctype() method on the TreeBuilder target.",
RuntimeWarning)
self._doctype = None
def feed(self, data):
"""Feed encoded data to parser."""
try:
self.parser.Parse(data, False)
except self._error as v:
self._raiseerror(v)
def close(self):
"""Finish feeding data to parser and return element structure."""
try:
self.parser.Parse(b"", True) # 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
def flush(self):
was_enabled = self.parser.GetReparseDeferralEnabled()
try:
self.parser.SetReparseDeferralEnabled(False)
self.parser.Parse(b"", False)
except self._error as v:
self._raiseerror(v)
finally:
self.parser.SetReparseDeferralEnabled(was_enabled)
# --------------------------------------------------------------------
# C14N 2.0
def canonicalize(xml_data=None, *, out=None, from_file=None, **options):
"""Convert XML to its C14N 2.0 serialised form.
If *out* is provided, it must be a file or file-like object that receives
the serialised canonical XML output (text, not bytes) through its ``.write()``
method. To write to a file, open it in text mode with encoding "utf-8".
If *out* is not provided, this function returns the output as text string.
Either *xml_data* (an XML string) or *from_file* (a file path or
file-like object) must be provided as input.
The configuration options are the same as for the ``C14NWriterTarget``.
"""
if xml_data is None and from_file is None:
raise ValueError("Either 'xml_data' or 'from_file' must be provided as input")
sio = None
if out is None:
sio = out = io.StringIO()
parser = XMLParser(target=C14NWriterTarget(out.write, **options))
if xml_data is not None:
parser.feed(xml_data)
parser.close()
elif from_file is not None:
parse(from_file, parser=parser)
return sio.getvalue() if sio is not None else None
_looks_like_prefix_name = re.compile(r'^\w+:\w+$', re.UNICODE).match
class C14NWriterTarget:
"""
Canonicalization writer target for the XMLParser.
Serialises parse events to XML C14N 2.0.
The *write* function is used for writing out the resulting data stream
as text (not bytes). To write to a file, open it in text mode with encoding
"utf-8" and pass its ``.write`` method.
Configuration options:
- *with_comments*: set to true to include comments
- *strip_text*: set to true to strip whitespace before and after text content
- *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}"
- *qname_aware_tags*: a set of qname aware tag names in which prefixes
should be replaced in text content
- *qname_aware_attrs*: a set of qname aware attribute names in which prefixes
should be replaced in text content
- *exclude_attrs*: a set of attribute names that should not be serialised
- *exclude_tags*: a set of tag names that should not be serialised
"""
def __init__(self, write, *,
with_comments=False, strip_text=False, rewrite_prefixes=False,
qname_aware_tags=None, qname_aware_attrs=None,
exclude_attrs=None, exclude_tags=None):
self._write = write
self._data = []
self._with_comments = with_comments
self._strip_text = strip_text
self._exclude_attrs = set(exclude_attrs) if exclude_attrs else None
self._exclude_tags = set(exclude_tags) if exclude_tags else None
self._rewrite_prefixes = rewrite_prefixes
if qname_aware_tags:
self._qname_aware_tags = set(qname_aware_tags)
else:
self._qname_aware_tags = None
if qname_aware_attrs:
self._find_qname_aware_attrs = set(qname_aware_attrs).intersection
else:
self._find_qname_aware_attrs = None
# Stack with globally and newly declared namespaces as (uri, prefix) pairs.
self._declared_ns_stack = [[
("http://www.w3.org/XML/1998/namespace", "xml"),
]]
# Stack with user declared namespace prefixes as (uri, prefix) pairs.
self._ns_stack = []
if not rewrite_prefixes:
self._ns_stack.append(list(_namespace_map.items()))
self._ns_stack.append([])
self._prefix_map = {}
self._preserve_space = [False]
self._pending_start = None
self._root_seen = False
self._root_done = False
self._ignored_depth = 0
def _iter_namespaces(self, ns_stack, _reversed=reversed):
for namespaces in _reversed(ns_stack):
if namespaces: # almost no element declares new namespaces
yield from namespaces
def _resolve_prefix_name(self, prefixed_name):
prefix, name = prefixed_name.split(':', 1)
for uri, p in self._iter_namespaces(self._ns_stack):
if p == prefix:
return f'{{{uri}}}{name}'
raise ValueError(f'Prefix {prefix} of QName "{prefixed_name}" is not declared in scope')
def _qname(self, qname, uri=None):
if uri is None:
uri, tag = qname[1:].rsplit('}', 1) if qname[:1] == '{' else ('', qname)
else:
tag = qname
prefixes_seen = set()
for u, prefix in self._iter_namespaces(self._declared_ns_stack):
if u == uri and prefix not in prefixes_seen:
return f'{prefix}:{tag}' if prefix else tag, tag, uri
prefixes_seen.add(prefix)
# Not declared yet => add new declaration.
if self._rewrite_prefixes:
if uri in self._prefix_map:
prefix = self._prefix_map[uri]
else:
prefix = self._prefix_map[uri] = f'n{len(self._prefix_map)}'
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}', tag, uri
if not uri and '' not in prefixes_seen:
# No default namespace declared => no prefix needed.
return tag, tag, uri
for u, prefix in self._iter_namespaces(self._ns_stack):
if u == uri:
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}' if prefix else tag, tag, uri
if not uri:
# As soon as a default namespace is defined,
# anything that has no namespace (and thus, no prefix) goes there.
return tag, tag, uri
raise ValueError(f'Namespace "{uri}" is not declared in scope')
def data(self, data):
if not self._ignored_depth:
self._data.append(data)
def _flush(self, _join_text=''.join):
data = _join_text(self._data)
del self._data[:]
if self._strip_text and not self._preserve_space[-1]:
data = data.strip()
if self._pending_start is not None:
args, self._pending_start = self._pending_start, None
qname_text = data if data and _looks_like_prefix_name(data) else None
self._start(*args, qname_text)
if qname_text is not None:
return
if data and self._root_seen:
self._write(_escape_cdata_c14n(data))
def start_ns(self, prefix, uri):
if self._ignored_depth:
return
# we may have to resolve qnames in text content
if self._data:
self._flush()
self._ns_stack[-1].append((uri, prefix))
def start(self, tag, attrs):
if self._exclude_tags is not None and (
self._ignored_depth or tag in self._exclude_tags):
self._ignored_depth += 1
return
if self._data:
self._flush()
new_namespaces = []
self._declared_ns_stack.append(new_namespaces)
if self._qname_aware_tags is not None and tag in self._qname_aware_tags:
# Need to parse text first to see if it requires a prefix declaration.
self._pending_start = (tag, attrs, new_namespaces)
return
self._start(tag, attrs, new_namespaces)
def _start(self, tag, attrs, new_namespaces, qname_text=None):
if self._exclude_attrs is not None and attrs:
attrs = {k: v for k, v in attrs.items() if k not in self._exclude_attrs}
qnames = {tag, *attrs}
resolved_names = {}
# Resolve prefixes in attribute and tag text.
if qname_text is not None:
qname = resolved_names[qname_text] = self._resolve_prefix_name(qname_text)
qnames.add(qname)
if self._find_qname_aware_attrs is not None and attrs:
qattrs = self._find_qname_aware_attrs(attrs)
if qattrs:
for attr_name in qattrs:
value = attrs[attr_name]
if _looks_like_prefix_name(value):
qname = resolved_names[value] = self._resolve_prefix_name(value)
qnames.add(qname)
else:
qattrs = None
else:
qattrs = None
# Assign prefixes in lexicographical order of used URIs.
parse_qname = self._qname
parsed_qnames = {n: parse_qname(n) for n in sorted(
qnames, key=lambda n: n.split('}', 1))}
# Write namespace declarations in prefix order ...
if new_namespaces:
attr_list = [
('xmlns:' + prefix if prefix else 'xmlns', uri)
for uri, prefix in new_namespaces
]
attr_list.sort()
else:
# almost always empty
attr_list = []
# ... followed by attributes in URI+name order
if attrs:
for k, v in sorted(attrs.items()):
if qattrs is not None and k in qattrs and v in resolved_names:
v = parsed_qnames[resolved_names[v]][0]
attr_qname, attr_name, uri = parsed_qnames[k]
# No prefix for attributes in default ('') namespace.
attr_list.append((attr_qname if uri else attr_name, v))
# Honour xml:space attributes.
space_behaviour = attrs.get('{http://www.w3.org/XML/1998/namespace}space')
self._preserve_space.append(
space_behaviour == 'preserve' if space_behaviour
else self._preserve_space[-1])
# Write the tag.
write = self._write
write('<' + parsed_qnames[tag][0])
if attr_list:
write(''.join([f' {k}="{_escape_attrib_c14n(v)}"' for k, v in attr_list]))
write('>')
# Write the resolved qname text content.
if qname_text is not None:
write(_escape_cdata_c14n(parsed_qnames[resolved_names[qname_text]][0]))
self._root_seen = True
self._ns_stack.append([])
def end(self, tag):
if self._ignored_depth:
self._ignored_depth -= 1
return
if self._data:
self._flush()
self._write(f'')
self._preserve_space.pop()
self._root_done = len(self._preserve_space) == 1
self._declared_ns_stack.pop()
self._ns_stack.pop()
def comment(self, text):
if not self._with_comments:
return
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(f'')
if not self._root_seen:
self._write('\n')
def pi(self, target, data):
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(
f'' if data else f'')
if not self._root_seen:
self._write('\n')
def _escape_cdata_c14n(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '>' in text:
text = text.replace('>', '>')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_c14n(text):
# escape attribute value
try:
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '"' in text:
text = text.replace('"', '"')
if '\t' in text:
text = text.replace('\t', ' ')
if '\n' in text:
text = text.replace('\n', '
')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
# Import the C accelerators
try:
# Element is going to be shadowed by the C implementation. We need to keep
# the Python version of it accessible for some "creative" by external code
# (see tests)
_Element_Py = Element
# Element, SubElement, ParseError, TreeBuilder, XMLParser, _set_factories
from _elementtree import *
from _elementtree import _set_factories
except ImportError:
pass
else:
_set_factories(Comment, ProcessingInstruction)
lib64/python3.6/xml/etree/ElementTree.py 0000644 00000157305 15236031222 0013732 0 ustar 00 """Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See http://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import collections
import contextlib
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
text...tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
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. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
attrib = attrib.copy()
attrib.update(extra)
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def copy(self):
"""Return copy of current element.
This creates a shallow copy. Subelements will be shared with the
original tree.
"""
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"The behavior of this method will change in future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
FutureWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
# if isinstance(index, slice):
# for elt in element:
# assert iselement(elt)
# else:
# assert iselement(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.extend(elements)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
self._children.remove(subelement)
def getchildren(self):
"""(Deprecated) Return all subelements.
Elements are returned in document order.
"""
warnings.warn(
"This method will be removed in future versions. "
"Use 'list(elem)' or iteration over elem instead.",
DeprecationWarning, stacklevel=2
)
return self._children
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
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.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
# 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))
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = attrib.copy()
attrib.update(extra)
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
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 '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while True:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'tree.iter()' or 'list(tree.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
enc_lower = encoding.lower()
with _get_writer(file_or_filename, enc_lower) as write:
if method == "xml" and (xml_declaration or
(xml_declaration is None and
enc_lower not in ("utf-8", "us-ascii", "unicode"))):
declared_encoding = encoding
if enc_lower == "unicode":
# Retrieve the default encoding for the xml declaration
import locale
declared_encoding = locale.getpreferredencoding()
write("\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding == "unicode":
file = open(file_or_filename, "w")
else:
file = open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace")
with file:
yield file.write
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding == "unicode":
# use a text writer as is
yield write
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % text)
elif tag is ProcessingInstruction:
write("" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param")
try:
HTML_EMPTY = set(HTML_EMPTY)
except NameError:
pass
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match(r"ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
# For tests and troubleshooting
register_namespace._namespace_map = _namespace_map
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 characters, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
# The following business with carriage returns is to satisfy
# Section 2.11 of the XML specification, stating that
# CR or CR LN should be replaced with just LN
# http://www.w3.org/TR/REC-xml/#sec-line-ends
if "\r\n" in text:
text = text.replace("\r\n", "\n")
if "\r" in text:
text = text.replace("\r", "\n")
#The following four lines are issue 17582
if "\n" in text:
text = text.replace("\n", "
")
if "\t" in text:
text = text.replace("\t", " ")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
def tostring(element, encoding=None, method=None, *,
short_empty_elements=True):
"""Generate string representation of XML element.
All subelements are included. If encoding is "unicode", a string
is returned. Otherwise a bytestring is returned.
*element* is an Element instance, *encoding* is an optional output
encoding defaulting to US-ASCII, *method* is an optional output which can
be one of "xml" (default), "html", "text" or "c14n".
Returns an (optionally) encoded string containing the XML data.
"""
stream = io.StringIO() if encoding == 'unicode' else io.BytesIO()
ElementTree(element).write(stream, encoding, method=method,
short_empty_elements=short_empty_elements)
return stream.getvalue()
class _ListDataStream(io.BufferedIOBase):
"""An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
def writable(self):
return True
def seekable(self):
return True
def write(self, b):
self.lst.append(b)
def tell(self):
return len(self.lst)
def tostringlist(element, encoding=None, method=None, *,
short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
ElementTree(element).write(stream, encoding, method=method,
short_empty_elements=short_empty_elements)
return lst
def dump(elem):
"""Write element tree or element structure to sys.stdout.
This function should be used for debugging only.
*elem* is either an ElementTree, or a single Element. The exact output
format is implementation dependent. In this version, it's written as an
ordinary XML file.
"""
# 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
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
def iterparse(source, events=None, parser=None):
"""Incrementally parse XML document into ElementTree.
This class also reports what's going on to the user based on the
*events* it is initialized with. The supported events are the strings
"start", "end", "start-ns" and "end-ns" (the "ns" events are used to get
detailed namespace information). If *events* is omitted, only
"end" events are reported.
*source* is a filename or file object containing XML data, *events* is
a list of events to report back, *parser* is an optional parser instance.
Returns an iterator providing (event, elem) pairs.
"""
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
pullparser = XMLPullParser(events=events, _parser=parser)
def iterator():
try:
while True:
yield from pullparser.read_events()
# load event buffer
data = source.read(16 * 1024)
if not data:
break
pullparser.feed(data)
root = pullparser._close_and_return_root()
yield from pullparser.read_events()
it.root = root
finally:
if close_source:
source.close()
class IterParseIterator(collections.Iterator):
__next__ = iterator().__next__
it = IterParseIterator()
it.root = None
del iterator, IterParseIterator
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
return it
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See http://bugs.python.org/issue17741 for more details.
self._events_queue = collections.deque()
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def feed(self, data):
"""Feed encoded data to parser."""
if self._parser is None:
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
root = self._parser.close()
self._parser = None
return root
def close(self):
"""Finish feeding data to parser.
Unlike XMLParser, does not return the root element. Use
read_events() to consume elements from XMLPullParser.
"""
self._close_and_return_root()
def read_events(self):
"""Return an iterator over currently available (event, elem) pairs.
Events are consumed from the internal event queue as they are
retrieved from the iterator.
"""
events = self._events_queue
while events:
event = events.popleft()
if isinstance(event, Exception):
raise event
else:
yield event
def XML(text, parser=None):
"""Parse XML document from string constant.
This function can be used to embed "XML Literals" in Python code.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
return parser.close()
def XMLID(text, parser=None):
"""Parse XML document from string constant for its IDs.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an (Element, dict) tuple, in which the
dict maps element id:s to elements.
"""
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
# Parse XML document from string constant. Alias for XML().
fromstring = XML
def fromstringlist(sequence, parser=None):
"""Parse XML document from sequence of string fragments.
*sequence* is a list of other sequence, *parser* is an optional parser
instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
class TreeBuilder:
"""Generic element structure builder.
This builder converts a sequence of start, data, and 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.
*element_factory* is an optional element factory which is called
to create new Element instances, as necessary.
"""
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
def close(self):
"""Flush builder buffers and return toplevel document Element."""
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 = []
def data(self, data):
"""Add text to current element."""
self._data.append(data)
def start(self, tag, attrs):
"""Open new element and return it.
*tag* is the element name, *attrs* is a dict containing element
attributes.
"""
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
def end(self, tag):
"""Close and return current Element.
*tag* is the element name.
"""
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
# also see ElementTree and TreeBuilder
class XMLParser:
"""Element structure builder for XML source data based on the expat parser.
*html* are predefined HTML entities (deprecated and not supported),
*target* is an optional target object which defaults to an instance of the
standard TreeBuilder class, *encoding* is an optional encoding string
which if given, overrides the encoding specified in the XML file:
http://www.iana.org/assignments/character-sets
"""
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
# Configure pyexpat: buffering, new-style attribute handling.
parser.buffer_text = 1
parser.ordered_attributes = 1
parser.specified_attributes = 1
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
parser = self._parser
append = events_queue.append
for event_name in events_to_report:
if event_name == "start":
parser.ordered_attributes = 1
parser.specified_attributes = 1
def handler(tag, attrib_in, event=event_name, append=append,
start=self._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event_name == "end":
def handler(tag, event=event_name, append=append,
end=self._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event_name == "start-ns":
def handler(prefix, uri, event=event_name, append=append):
append((event, (prefix or "", uri or "")))
parser.StartNamespaceDeclHandler = handler
elif event_name == "end-ns":
def handler(prefix, event=event_name, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
else:
raise ValueError("unknown event %r" % event_name)
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, attr_list):
# Handler for expat's StartElementHandler. Since ordered_attributes
# is set, the attributes are reported as a list of alternating
# attribute name,value.
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attr_list:
for i in range(0, len(attr_list), 2):
attrib[fixname(attr_list[i])] = attr_list[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
def doctype(self, name, pubid, system):
"""(Deprecated) Handle doctype declaration
*name* is the Doctype name, *pubid* is the public identifier,
and *system* is the system identifier.
"""
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
def feed(self, data):
"""Feed encoded data to parser."""
try:
self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
def close(self):
"""Finish feeding data to parser and return element structure."""
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 is going to be shadowed by the C implementation. We need to keep
# the Python version of it accessible for some "creative" by external code
# (see tests)
_Element_Py = Element
# Element, SubElement, ParseError, TreeBuilder, XMLParser
from _elementtree import *
except ImportError:
pass
lib64/python3.12/xml/etree/ElementTree.py 0000644 00000220441 15236072513 0014007 0 ustar 00 """Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See https://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"indent", "iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
"canonicalize", "C14NWriterTarget",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import collections
import collections.abc
import contextlib
import weakref
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
text...tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
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. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
self.tag = tag
self.attrib = {**attrib, **extra}
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def __copy__(self):
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"Testing an element's truth value will always return True in "
"future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
DeprecationWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
if isinstance(index, slice):
for elt in element:
self._assert_is_element(elt)
else:
self._assert_is_element(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.append(element)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
self._children.remove(subelement)
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
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.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = {**attrib, **extra}
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
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 '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while data := source.read(65536):
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
with _get_writer(file_or_filename, encoding) as (write, declared_encoding):
if method == "xml" and (xml_declaration or
(xml_declaration is None and
encoding.lower() != "unicode" and
declared_encoding.lower() not in ("utf-8", "us-ascii"))):
write("\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding.lower() == "unicode":
encoding="utf-8"
with open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace") as file:
yield file.write, encoding
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding.lower() == "unicode":
# use a text writer as is
yield write, getattr(file_or_filename, "encoding", None) or "utf-8"
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write, encoding
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % text)
elif tag is ProcessingInstruction:
write("" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = {"area", "base", "basefont", "br", "col", "embed", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param", "source",
"track", "wbr"}
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match(r"ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
# For tests and troubleshooting
register_namespace._namespace_map = _namespace_map
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 characters, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
# Although section 2.11 of the XML specification states that CR or
# CR LN should be replaced with just LN, it applies only to EOLNs
# which take part of organizing file into lines. Within attributes,
# we are replacing these with entity numbers, so they do not count.
# http://www.w3.org/TR/REC-xml/#sec-line-ends
# The current solution, contained in following six lines, was
# discussed in issue 17582 and 39011.
if "\r" in text:
text = text.replace("\r", "
")
if "\n" in text:
text = text.replace("\n", "
")
if "\t" in text:
text = text.replace("\t", " ")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
def tostring(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
"""Generate string representation of XML element.
All subelements are included. If encoding is "unicode", a string
is returned. Otherwise a bytestring is returned.
*element* is an Element instance, *encoding* is an optional output
encoding defaulting to US-ASCII, *method* is an optional output which can
be one of "xml" (default), "html", "text" or "c14n", *default_namespace*
sets the default XML namespace (for "xmlns").
Returns an (optionally) encoded string containing the XML data.
"""
stream = io.StringIO() if encoding == 'unicode' else io.BytesIO()
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return stream.getvalue()
class _ListDataStream(io.BufferedIOBase):
"""An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
def writable(self):
return True
def seekable(self):
return True
def write(self, b):
self.lst.append(b)
def tell(self):
return len(self.lst)
def tostringlist(element, encoding=None, method=None, *,
xml_declaration=None, default_namespace=None,
short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
ElementTree(element).write(stream, encoding,
xml_declaration=xml_declaration,
default_namespace=default_namespace,
method=method,
short_empty_elements=short_empty_elements)
return lst
def dump(elem):
"""Write element tree or element structure to sys.stdout.
This function should be used for debugging only.
*elem* is either an ElementTree, or a single Element. The exact output
format is implementation dependent. In this version, it's written as an
ordinary XML file.
"""
# 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")
def indent(tree, space=" ", level=0):
"""Indent an XML document by inserting newlines and indentation space
after elements.
*tree* is the ElementTree or Element to modify. The (root) element
itself will not be changed, but the tail text of all elements in its
subtree will be adapted.
*space* is the whitespace to insert for each indentation level, two
space characters by default.
*level* is the initial indentation level. Setting this to a higher
value than 0 can be used for indenting subtrees that are more deeply
nested inside of a document.
"""
if isinstance(tree, ElementTree):
tree = tree.getroot()
if level < 0:
raise ValueError(f"Initial indentation level must be >= 0, got {level}")
if not len(tree):
return
# Reduce the memory consumption by reusing indentation strings.
indentations = ["\n" + level * space]
def _indent_children(elem, level):
# Start a new indentation level for the first child.
child_level = level + 1
try:
child_indentation = indentations[child_level]
except IndexError:
child_indentation = indentations[level] + space
indentations.append(child_indentation)
if not elem.text or not elem.text.strip():
elem.text = child_indentation
for child in elem:
if len(child):
_indent_children(child, child_level)
if not child.tail or not child.tail.strip():
child.tail = child_indentation
# Dedent after the last child by overwriting the previous indentation.
if not child.tail.strip():
child.tail = indentations[level]
_indent_children(tree, 0)
# --------------------------------------------------------------------
# parsing
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
def iterparse(source, events=None, parser=None):
"""Incrementally parse XML document into ElementTree.
This class also reports what's going on to the user based on the
*events* it is initialized with. The supported events are the strings
"start", "end", "start-ns" and "end-ns" (the "ns" events are used to get
detailed namespace information). If *events* is omitted, only
"end" events are reported.
*source* is a filename or file object containing XML data, *events* is
a list of events to report back, *parser* is an optional parser instance.
Returns an iterator providing (event, elem) pairs.
"""
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
pullparser = XMLPullParser(events=events, _parser=parser)
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
else:
close_source = False
def iterator(source):
try:
while True:
yield from pullparser.read_events()
# load event buffer
data = source.read(16 * 1024)
if not data:
break
pullparser.feed(data)
root = pullparser._close_and_return_root()
yield from pullparser.read_events()
it = wr()
if it is not None:
it.root = root
finally:
if close_source:
source.close()
class IterParseIterator(collections.abc.Iterator):
__next__ = iterator(source).__next__
def __del__(self):
if close_source:
source.close()
it = IterParseIterator()
it.root = None
wr = weakref.ref(it)
return it
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See https://bugs.python.org/issue17741 for more details.
self._events_queue = collections.deque()
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def feed(self, data):
"""Feed encoded data to parser."""
if self._parser is None:
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
root = self._parser.close()
self._parser = None
return root
def close(self):
"""Finish feeding data to parser.
Unlike XMLParser, does not return the root element. Use
read_events() to consume elements from XMLPullParser.
"""
self._close_and_return_root()
def read_events(self):
"""Return an iterator over currently available (event, elem) pairs.
Events are consumed from the internal event queue as they are
retrieved from the iterator.
"""
events = self._events_queue
while events:
event = events.popleft()
if isinstance(event, Exception):
raise event
else:
yield event
def flush(self):
if self._parser is None:
raise ValueError("flush() called after end of stream")
self._parser.flush()
def XML(text, parser=None):
"""Parse XML document from string constant.
This function can be used to embed "XML Literals" in Python code.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
parser.feed(text)
return parser.close()
def XMLID(text, parser=None):
"""Parse XML document from string constant for its IDs.
*text* is a string containing XML data, *parser* is an
optional parser instance, defaulting to the standard XMLParser.
Returns an (Element, dict) tuple, in which the
dict maps element id:s to elements.
"""
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
# Parse XML document from string constant. Alias for XML().
fromstring = XML
def fromstringlist(sequence, parser=None):
"""Parse XML document from sequence of string fragments.
*sequence* is a list of other sequence, *parser* is an optional parser
instance, defaulting to the standard XMLParser.
Returns an Element instance.
"""
if not parser:
parser = XMLParser(target=TreeBuilder())
for text in sequence:
parser.feed(text)
return parser.close()
# --------------------------------------------------------------------
class TreeBuilder:
"""Generic element structure builder.
This builder converts a sequence of start, data, and 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.
*element_factory* is an optional element factory which is called
to create new Element instances, as necessary.
*comment_factory* is a factory to create comments to be used instead of
the standard factory. If *insert_comments* is false (the default),
comments will not be inserted into the tree.
*pi_factory* is a factory to create processing instructions to be used
instead of the standard factory. If *insert_pis* is false (the default),
processing instructions will not be inserted into the tree.
"""
def __init__(self, element_factory=None, *,
comment_factory=None, pi_factory=None,
insert_comments=False, insert_pis=False):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._root = None # root element
self._tail = None # true if we're after an end tag
if comment_factory is None:
comment_factory = Comment
self._comment_factory = comment_factory
self.insert_comments = insert_comments
if pi_factory is None:
pi_factory = ProcessingInstruction
self._pi_factory = pi_factory
self.insert_pis = insert_pis
if element_factory is None:
element_factory = Element
self._factory = element_factory
def close(self):
"""Flush builder buffers and return toplevel document Element."""
assert len(self._elem) == 0, "missing end tags"
assert self._root is not None, "missing toplevel element"
return self._root
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 = []
def data(self, data):
"""Add text to current element."""
self._data.append(data)
def start(self, tag, attrs):
"""Open new element and return it.
*tag* is the element name, *attrs* is a dict containing element
attributes.
"""
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
elif self._root is None:
self._root = elem
self._elem.append(elem)
self._tail = 0
return elem
def end(self, tag):
"""Close and return current Element.
*tag* is the element name.
"""
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
def comment(self, text):
"""Create a comment using the comment_factory.
*text* is the text of the comment.
"""
return self._handle_single(
self._comment_factory, self.insert_comments, text)
def pi(self, target, text=None):
"""Create a processing instruction using the pi_factory.
*target* is the target name of the processing instruction.
*text* is the data of the processing instruction, or ''.
"""
return self._handle_single(
self._pi_factory, self.insert_pis, target, text)
def _handle_single(self, factory, insert, *args):
elem = factory(*args)
if insert:
self._flush()
self._last = elem
if self._elem:
self._elem[-1].append(elem)
self._tail = 1
return elem
# also see ElementTree and TreeBuilder
class XMLParser:
"""Element structure builder for XML source data based on the expat parser.
*target* is an optional target object which defaults to an instance of the
standard TreeBuilder class, *encoding* is an optional encoding string
which if given, overrides the encoding specified in the XML file:
http://www.iana.org/assignments/character-sets
"""
def __init__(self, *, 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, 'start_ns'):
parser.StartNamespaceDeclHandler = self._start_ns
if hasattr(target, 'end_ns'):
parser.EndNamespaceDeclHandler = self._end_ns
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
# Configure pyexpat: buffering, new-style attribute handling.
parser.buffer_text = 1
parser.ordered_attributes = 1
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
parser = self._parser
append = events_queue.append
for event_name in events_to_report:
if event_name == "start":
parser.ordered_attributes = 1
def handler(tag, attrib_in, event=event_name, append=append,
start=self._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event_name == "end":
def handler(tag, event=event_name, append=append,
end=self._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event_name == "start-ns":
# TreeBuilder does not implement .start_ns()
if hasattr(self.target, "start_ns"):
def handler(prefix, uri, event=event_name, append=append,
start_ns=self._start_ns):
append((event, start_ns(prefix, uri)))
else:
def handler(prefix, uri, event=event_name, append=append):
append((event, (prefix or '', uri or '')))
parser.StartNamespaceDeclHandler = handler
elif event_name == "end-ns":
# TreeBuilder does not implement .end_ns()
if hasattr(self.target, "end_ns"):
def handler(prefix, event=event_name, append=append,
end_ns=self._end_ns):
append((event, end_ns(prefix)))
else:
def handler(prefix, event=event_name, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
elif event_name == 'comment':
def handler(text, event=event_name, append=append, self=self):
append((event, self.target.comment(text)))
parser.CommentHandler = handler
elif event_name == 'pi':
def handler(pi_target, data, event=event_name, append=append,
self=self):
append((event, self.target.pi(pi_target, data)))
parser.ProcessingInstructionHandler = handler
else:
raise ValueError("unknown event %r" % event_name)
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_ns(self, prefix, uri):
return self.target.start_ns(prefix or '', uri or '')
def _end_ns(self, prefix):
return self.target.end_ns(prefix or '')
def _start(self, tag, attr_list):
# Handler for expat's StartElementHandler. Since ordered_attributes
# is set, the attributes are reported as a list of alternating
# attribute name,value.
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attr_list:
for i in range(0, len(attr_list), 2):
attrib[fixname(attr_list[i])] = attr_list[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 hasattr(self, "doctype"):
warnings.warn(
"The doctype() method of XMLParser is ignored. "
"Define doctype() method on the TreeBuilder target.",
RuntimeWarning)
self._doctype = None
def feed(self, data):
"""Feed encoded data to parser."""
try:
self.parser.Parse(data, False)
except self._error as v:
self._raiseerror(v)
def close(self):
"""Finish feeding data to parser and return element structure."""
try:
self.parser.Parse(b"", True) # 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
def flush(self):
was_enabled = self.parser.GetReparseDeferralEnabled()
try:
self.parser.SetReparseDeferralEnabled(False)
self.parser.Parse(b"", False)
except self._error as v:
self._raiseerror(v)
finally:
self.parser.SetReparseDeferralEnabled(was_enabled)
# --------------------------------------------------------------------
# C14N 2.0
def canonicalize(xml_data=None, *, out=None, from_file=None, **options):
"""Convert XML to its C14N 2.0 serialised form.
If *out* is provided, it must be a file or file-like object that receives
the serialised canonical XML output (text, not bytes) through its ``.write()``
method. To write to a file, open it in text mode with encoding "utf-8".
If *out* is not provided, this function returns the output as text string.
Either *xml_data* (an XML string) or *from_file* (a file path or
file-like object) must be provided as input.
The configuration options are the same as for the ``C14NWriterTarget``.
"""
if xml_data is None and from_file is None:
raise ValueError("Either 'xml_data' or 'from_file' must be provided as input")
sio = None
if out is None:
sio = out = io.StringIO()
parser = XMLParser(target=C14NWriterTarget(out.write, **options))
if xml_data is not None:
parser.feed(xml_data)
parser.close()
elif from_file is not None:
parse(from_file, parser=parser)
return sio.getvalue() if sio is not None else None
_looks_like_prefix_name = re.compile(r'^\w+:\w+$', re.UNICODE).match
class C14NWriterTarget:
"""
Canonicalization writer target for the XMLParser.
Serialises parse events to XML C14N 2.0.
The *write* function is used for writing out the resulting data stream
as text (not bytes). To write to a file, open it in text mode with encoding
"utf-8" and pass its ``.write`` method.
Configuration options:
- *with_comments*: set to true to include comments
- *strip_text*: set to true to strip whitespace before and after text content
- *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}"
- *qname_aware_tags*: a set of qname aware tag names in which prefixes
should be replaced in text content
- *qname_aware_attrs*: a set of qname aware attribute names in which prefixes
should be replaced in text content
- *exclude_attrs*: a set of attribute names that should not be serialised
- *exclude_tags*: a set of tag names that should not be serialised
"""
def __init__(self, write, *,
with_comments=False, strip_text=False, rewrite_prefixes=False,
qname_aware_tags=None, qname_aware_attrs=None,
exclude_attrs=None, exclude_tags=None):
self._write = write
self._data = []
self._with_comments = with_comments
self._strip_text = strip_text
self._exclude_attrs = set(exclude_attrs) if exclude_attrs else None
self._exclude_tags = set(exclude_tags) if exclude_tags else None
self._rewrite_prefixes = rewrite_prefixes
if qname_aware_tags:
self._qname_aware_tags = set(qname_aware_tags)
else:
self._qname_aware_tags = None
if qname_aware_attrs:
self._find_qname_aware_attrs = set(qname_aware_attrs).intersection
else:
self._find_qname_aware_attrs = None
# Stack with globally and newly declared namespaces as (uri, prefix) pairs.
self._declared_ns_stack = [[
("http://www.w3.org/XML/1998/namespace", "xml"),
]]
# Stack with user declared namespace prefixes as (uri, prefix) pairs.
self._ns_stack = []
if not rewrite_prefixes:
self._ns_stack.append(list(_namespace_map.items()))
self._ns_stack.append([])
self._prefix_map = {}
self._preserve_space = [False]
self._pending_start = None
self._root_seen = False
self._root_done = False
self._ignored_depth = 0
def _iter_namespaces(self, ns_stack, _reversed=reversed):
for namespaces in _reversed(ns_stack):
if namespaces: # almost no element declares new namespaces
yield from namespaces
def _resolve_prefix_name(self, prefixed_name):
prefix, name = prefixed_name.split(':', 1)
for uri, p in self._iter_namespaces(self._ns_stack):
if p == prefix:
return f'{{{uri}}}{name}'
raise ValueError(f'Prefix {prefix} of QName "{prefixed_name}" is not declared in scope')
def _qname(self, qname, uri=None):
if uri is None:
uri, tag = qname[1:].rsplit('}', 1) if qname[:1] == '{' else ('', qname)
else:
tag = qname
prefixes_seen = set()
for u, prefix in self._iter_namespaces(self._declared_ns_stack):
if u == uri and prefix not in prefixes_seen:
return f'{prefix}:{tag}' if prefix else tag, tag, uri
prefixes_seen.add(prefix)
# Not declared yet => add new declaration.
if self._rewrite_prefixes:
if uri in self._prefix_map:
prefix = self._prefix_map[uri]
else:
prefix = self._prefix_map[uri] = f'n{len(self._prefix_map)}'
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}', tag, uri
if not uri and '' not in prefixes_seen:
# No default namespace declared => no prefix needed.
return tag, tag, uri
for u, prefix in self._iter_namespaces(self._ns_stack):
if u == uri:
self._declared_ns_stack[-1].append((uri, prefix))
return f'{prefix}:{tag}' if prefix else tag, tag, uri
if not uri:
# As soon as a default namespace is defined,
# anything that has no namespace (and thus, no prefix) goes there.
return tag, tag, uri
raise ValueError(f'Namespace "{uri}" is not declared in scope')
def data(self, data):
if not self._ignored_depth:
self._data.append(data)
def _flush(self, _join_text=''.join):
data = _join_text(self._data)
del self._data[:]
if self._strip_text and not self._preserve_space[-1]:
data = data.strip()
if self._pending_start is not None:
args, self._pending_start = self._pending_start, None
qname_text = data if data and _looks_like_prefix_name(data) else None
self._start(*args, qname_text)
if qname_text is not None:
return
if data and self._root_seen:
self._write(_escape_cdata_c14n(data))
def start_ns(self, prefix, uri):
if self._ignored_depth:
return
# we may have to resolve qnames in text content
if self._data:
self._flush()
self._ns_stack[-1].append((uri, prefix))
def start(self, tag, attrs):
if self._exclude_tags is not None and (
self._ignored_depth or tag in self._exclude_tags):
self._ignored_depth += 1
return
if self._data:
self._flush()
new_namespaces = []
self._declared_ns_stack.append(new_namespaces)
if self._qname_aware_tags is not None and tag in self._qname_aware_tags:
# Need to parse text first to see if it requires a prefix declaration.
self._pending_start = (tag, attrs, new_namespaces)
return
self._start(tag, attrs, new_namespaces)
def _start(self, tag, attrs, new_namespaces, qname_text=None):
if self._exclude_attrs is not None and attrs:
attrs = {k: v for k, v in attrs.items() if k not in self._exclude_attrs}
qnames = {tag, *attrs}
resolved_names = {}
# Resolve prefixes in attribute and tag text.
if qname_text is not None:
qname = resolved_names[qname_text] = self._resolve_prefix_name(qname_text)
qnames.add(qname)
if self._find_qname_aware_attrs is not None and attrs:
qattrs = self._find_qname_aware_attrs(attrs)
if qattrs:
for attr_name in qattrs:
value = attrs[attr_name]
if _looks_like_prefix_name(value):
qname = resolved_names[value] = self._resolve_prefix_name(value)
qnames.add(qname)
else:
qattrs = None
else:
qattrs = None
# Assign prefixes in lexicographical order of used URIs.
parse_qname = self._qname
parsed_qnames = {n: parse_qname(n) for n in sorted(
qnames, key=lambda n: n.split('}', 1))}
# Write namespace declarations in prefix order ...
if new_namespaces:
attr_list = [
('xmlns:' + prefix if prefix else 'xmlns', uri)
for uri, prefix in new_namespaces
]
attr_list.sort()
else:
# almost always empty
attr_list = []
# ... followed by attributes in URI+name order
if attrs:
for k, v in sorted(attrs.items()):
if qattrs is not None and k in qattrs and v in resolved_names:
v = parsed_qnames[resolved_names[v]][0]
attr_qname, attr_name, uri = parsed_qnames[k]
# No prefix for attributes in default ('') namespace.
attr_list.append((attr_qname if uri else attr_name, v))
# Honour xml:space attributes.
space_behaviour = attrs.get('{http://www.w3.org/XML/1998/namespace}space')
self._preserve_space.append(
space_behaviour == 'preserve' if space_behaviour
else self._preserve_space[-1])
# Write the tag.
write = self._write
write('<' + parsed_qnames[tag][0])
if attr_list:
write(''.join([f' {k}="{_escape_attrib_c14n(v)}"' for k, v in attr_list]))
write('>')
# Write the resolved qname text content.
if qname_text is not None:
write(_escape_cdata_c14n(parsed_qnames[resolved_names[qname_text]][0]))
self._root_seen = True
self._ns_stack.append([])
def end(self, tag):
if self._ignored_depth:
self._ignored_depth -= 1
return
if self._data:
self._flush()
self._write(f'')
self._preserve_space.pop()
self._root_done = len(self._preserve_space) == 1
self._declared_ns_stack.pop()
self._ns_stack.pop()
def comment(self, text):
if not self._with_comments:
return
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(f'')
if not self._root_seen:
self._write('\n')
def pi(self, target, data):
if self._ignored_depth:
return
if self._root_done:
self._write('\n')
elif self._root_seen and self._data:
self._flush()
self._write(
f'' if data else f'')
if not self._root_seen:
self._write('\n')
def _escape_cdata_c14n(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '>' in text:
text = text.replace('>', '>')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_c14n(text):
# escape attribute value
try:
if '&' in text:
text = text.replace('&', '&')
if '<' in text:
text = text.replace('<', '<')
if '"' in text:
text = text.replace('"', '"')
if '\t' in text:
text = text.replace('\t', ' ')
if '\n' in text:
text = text.replace('\n', '
')
if '\r' in text:
text = text.replace('\r', '
')
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
# Import the C accelerators
try:
# Element is going to be shadowed by the C implementation. We need to keep
# the Python version of it accessible for some "creative" by external code
# (see tests)
_Element_Py = Element
# Element, SubElement, ParseError, TreeBuilder, XMLParser, _set_factories
from _elementtree import *
from _elementtree import _set_factories
except ImportError:
pass
else:
_set_factories(Comment, ProcessingInstruction)
lib64/python2.7/xml/etree/ElementTree.py 0000644 00000157310 15236267561 0013747 0 ustar 00 #
# ElementTree
# $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $
#
# light-weight XML support for Python 2.3 and later.
#
# history (since 1.2.6):
# 2005-11-12 fl added tostringlist/fromstringlist helpers
# 2006-07-05 fl merged in selected changes from the 1.3 sandbox
# 2006-07-05 fl removed support for 2.1 and earlier
# 2007-06-21 fl added deprecation/future warnings
# 2007-08-25 fl added doctype hook, added parser version attribute etc
# 2007-08-26 fl added new serializer code (better namespace handling, etc)
# 2007-08-27 fl warn for broken /tag searches on tree level
# 2007-09-02 fl added html/text methods to serializer (experimental)
# 2007-09-05 fl added method argument to tostring/tostringlist
# 2007-09-06 fl improved error handling
# 2007-09-13 fl added itertext, iterfind; assorted cleanups
# 2007-12-15 fl added C14N hooks, copy method (experimental)
#
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 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/psf/license for licensing details.
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML",
"XMLParser", "XMLTreeBuilder",
]
VERSION = "1.3.0"
##
# The Element 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.
#
# Each element has a number of properties associated with it:
#
# - a tag. This is a string identifying what kind of data
# this element represents (the element type, in other words).
# - a number of attributes, stored in a Python dictionary.
# - a text string.
# - an optional tail string.
# - a number of child elements, stored in a Python sequence
#
#
# To create an element instance, use the {@link #Element} constructor
# or the {@link #SubElement} factory function.
#
# 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
class _SimpleElementPath(object):
# emulate pre-1.2 find/findtext/findall behaviour
def find(self, element, tag, namespaces=None):
for elem in element:
if elem.tag == tag:
return elem
return None
def findtext(self, element, tag, default=None, namespaces=None):
elem = self.find(element, tag)
if elem is None:
return default
return elem.text or ""
def iterfind(self, element, tag, namespaces=None):
if tag[:3] == ".//":
for elem in element.iter(tag[3:]):
yield elem
for elem in element:
if elem.tag == tag:
yield elem
def findall(self, element, tag, namespaces=None):
return list(self.iterfind(element, tag, namespaces))
try:
from . import ElementPath
except ImportError:
ElementPath = _SimpleElementPath()
##
# 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; might be a better idea to look
# for tag/attrib/text attributes
return isinstance(element, Element) or hasattr(element, "tag")
##
# Element class. This class defines the Element interface, and
# provides a reference implementation of this interface.
#
# 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(object):
# text...tail
##
# (Attribute) Element tag.
tag = None
##
# (Attribute) Element attribute dictionary. Where possible, use
# {@link #Element.get},
# {@link #Element.set},
# {@link #Element.keys}, and
# {@link #Element.items} to access
# element attributes.
attrib = None
##
# (Attribute) Text before first subelement. This is either a
# string or the value None. Note that if there was no text, this
# attribute may be either None or an empty string, depending on
# the parser.
text = None
##
# (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. Note that if there was no text, this attribute
# may be either None or an empty string, depending on the parser.
tail = None # text after end tag, if any
# constructor
def __init__(self, tag, attrib={}, **extra):
attrib = attrib.copy()
attrib.update(extra)
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "" % (repr(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 self.__class__(tag, attrib)
##
# (Experimental) Copies the current element. This creates a
# shallow copy; subelements will be shared with the original tree.
#
# @return A new element instance.
def copy(self):
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
##
# Returns the number of subelements. Note that this only counts
# full elements; to check if there's any content in an element, you
# have to check both the length and the text attribute.
#
# @return The number of subelements.
def __len__(self):
return len(self._children)
def __nonzero__(self):
warnings.warn(
"The behavior of this method will change in future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
FutureWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
##
# Returns the given subelement, by index.
#
# @param index What subelement to return.
# @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, by index.
#
# @param index What subelement to replace.
# @param element The new element value.
# @exception IndexError If the given element does not exist.
def __setitem__(self, index, element):
# if isinstance(index, slice):
# for elt in element:
# assert iselement(elt)
# else:
# assert iselement(element)
self._children[index] = element
##
# Deletes the given subelement, by index.
#
# @param index What subelement to delete.
# @exception IndexError If the given element does not exist.
def __delitem__(self, index):
del self._children[index]
##
# Adds a subelement to the end of this element. In document order,
# the new element will appear after the last existing subelement (or
# directly after the text, if it's the first subelement), but before
# the end tag for this element.
#
# @param element The element to add.
def append(self, element):
# assert iselement(element)
self._children.append(element)
##
# Appends subelements from a sequence.
#
# @param elements A sequence object with zero or more elements.
# @since 1.3
def extend(self, elements):
# for element in elements:
# assert iselement(element)
self._children.extend(elements)
##
# Inserts a subelement at the given position in this element.
#
# @param index Where to insert the new subelement.
def insert(self, index, element):
# assert iselement(element)
self._children.insert(index, element)
##
# Removes a matching subelement. Unlike the find methods,
# this method compares elements based on identity, not on tag
# value or contents. To remove subelements by other means, the
# easiest way is often to use a list comprehension to select what
# elements to keep, and use slice assignment to update the parent
# element.
#
# @param element What element to remove.
# @exception ValueError If a matching element could not be found.
def remove(self, element):
# assert iselement(element)
self._children.remove(element)
##
# (Deprecated) Returns all subelements. The elements are returned
# in document order.
#
# @return A list of subelements.
# @defreturn list of Element instances
def getchildren(self):
warnings.warn(
"This method will be removed in future versions. "
"Use 'list(elem)' or iteration over elem instead.",
DeprecationWarning, stacklevel=2
)
return self._children
##
# Finds the first matching subelement, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path, namespaces=None):
return ElementPath.find(self, path, namespaces)
##
# 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.
# @keyparam namespaces Optional namespace prefix map.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None, namespaces=None):
return ElementPath.findtext(self, path, default, namespaces)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return A list or other sequence containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path, namespaces=None):
return ElementPath.findall(self, path, namespaces)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return An iterator or sequence containing all matching elements,
# in document order.
# @defreturn a generated sequence of Element instances
def iterfind(self, path, namespaces=None):
return ElementPath.iterfind(self, path, namespaces)
##
# Resets an element. This function removes all subelements, clears
# all attributes, and sets the text and tail attributes
# to None.
def clear(self):
self.attrib.clear()
self._children = []
self.text = self.tail = None
##
# Gets an element attribute. Equivalent to attrib.get, but
# some implementations may handle this a bit more efficiently.
#
# @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. Equivalent to attrib[key] = value,
# but some implementations may handle this a bit more efficiently.
#
# @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).
# Equivalent to attrib.keys().
#
# @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. Equivalent to attrib.items().
#
# @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.
#
# 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, basestring) and tag is not None:
return
if self.text:
yield self.text
for e in self:
for s in e.itertext():
yield s
if e.tail:
yield e.tail
# compatibility
_Element = _ElementInterface = Element
##
# 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
# a URI, and this argument is interpreted as a local name.
# @return An opaque object, representing the QName.
class QName(object):
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 file name. If given, the
# tree is initialized with the contents of this XML file.
class ElementTree(object):
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. If a file object is
# given, it only has to implement a read(n) method.
# @keyparam parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return The document root element.
# @defreturn Element
# @exception ParseError If the parser fails to parse the document.
def parse(self, source, parser=None):
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
while 1:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
##
# 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 iter(self, tag=None):
# assert self._root is not None
return self._root.iter(tag)
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'tree.iter()' or 'list(tree.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
##
# Same as getroot().find(path), starting at the root of the
# tree.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
##
# Same as getroot().findtext(path), starting at the root of the tree.
#
# @param path What element to look for.
# @param default What to return if the element was not found.
# @keyparam namespaces Optional namespace prefix map.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
##
# Same as getroot().findall(path), starting at the root of the tree.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
##
# Finds all matching subelements, by tag name or path.
# Same as getroot().iterfind(path).
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return An iterator or sequence containing all matching elements,
# in document order.
# @defreturn a generated sequence of Element instances
def iterfind(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
##
# Writes the element tree to a file, as XML.
#
# @def write(file, **options)
# @param file A file name, or a file object opened for writing.
# @param **options Options, given as keyword arguments.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam xml_declaration Controls if an XML declaration should
# be added to the file. Use False for never, True for always,
# None for only if not US-ASCII or UTF-8. None is default.
# @keyparam default_namespace Sets the default XML namespace (for "xmlns").
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
def write(self, file_or_filename,
# keyword arguments
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None):
# assert self._root is not None
if not method:
method = "xml"
elif method not in _serialize:
# FIXME: raise an ImportError for c14n if ElementC14N is missing?
raise ValueError("unknown method %r" % method)
if hasattr(file_or_filename, "write"):
file = file_or_filename
else:
file = open(file_or_filename, "wb")
write = file.write
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
elif xml_declaration or (xml_declaration is None and
encoding not in ("utf-8", "us-ascii")):
if method == "xml":
write("\n" % encoding)
if method == "text":
_serialize_text(write, self._root, encoding)
else:
qnames, namespaces = _namespaces(
self._root, encoding, default_namespace
)
serialize = _serialize[method]
serialize(write, self._root, encoding, qnames, namespaces)
if file_or_filename is not file:
file.close()
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
def _namespaces(elem, encoding, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def encode(text):
return text.encode(encoding)
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = encode("%s:%s" % (prefix, tag))
else:
qnames[qname] = encode(tag) # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = encode(qname)
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
try:
iterate = elem.iter
except AttributeError:
iterate = elem.getiterator # cET compatibility
for elem in iterate():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, basestring):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, encoding, qnames, namespaces):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _encode(text, encoding))
elif tag is ProcessingInstruction:
write("" % _encode(text, encoding))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_xml(write, e, encoding, qnames, None)
else:
write("<" + tag)
items = elem.items()
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k.encode(encoding),
_escape_attrib(v, encoding)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v, encoding)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem):
write(">")
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_xml(write, e, encoding, qnames, None)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail, encoding))
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param")
try:
HTML_EMPTY = set(HTML_EMPTY)
except NameError:
pass
def _serialize_html(write, elem, encoding, qnames, namespaces):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text, encoding))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text, encoding))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_html(write, e, encoding, qnames, None)
else:
write("<" + tag)
items = elem.items()
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k.encode(encoding),
_escape_attrib(v, encoding)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v, encoding)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(_encode(text, encoding))
else:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_html(write, e, encoding, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail, encoding))
def _serialize_text(write, elem, encoding):
for part in elem.itertext():
write(part.encode(encoding))
if elem.tail:
write(elem.tail.encode(encoding))
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
##
# Registers a namespace prefix. The registry is global, and any
# existing mapping for either the given prefix or the namespace URI
# will be removed.
#
# @param prefix Namespace prefix.
# @param uri Namespace uri. Tags and attributes in this namespace
# will be serialized with the given prefix, if at all possible.
# @exception ValueError If the prefix is reserved, or is otherwise
# invalid.
def register_namespace(prefix, uri):
if re.match("ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in _namespace_map.items():
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _encode(text, encoding):
try:
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_cdata(text, encoding):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text, encoding):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
if "\n" in text:
text = text.replace("\n", "
")
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text, encoding):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
##
# Generates a string representation of an XML element, including all
# subelements.
#
# @param element An Element instance.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
# @return An encoded string containing the XML data.
# @defreturn string
def tostring(element, encoding=None, method=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding, method=method)
return "".join(data)
##
# Generates a string representation of an XML element, including all
# subelements. The string is returned as a sequence of string fragments.
#
# @param element An Element instance.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
# @return A sequence object containing the XML data.
# @defreturn sequence
# @since 1.3
def tostringlist(element, encoding=None, method=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding, method=method)
# FIXME: merge small fragments into larger parts
return data
##
# 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")
# --------------------------------------------------------------------
# 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
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
return _IterParseIterator(source, events, parser, close_source)
except:
if close_source:
source.close()
raise
class _IterParseIterator(object):
def __init__(self, source, events, parser, close_source=False):
self._file = source
self._close_file = close_source
self._events = []
self._index = 0
self._error = None
self.root = self._root = None
self._parser = 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):
try:
uri = (uri or "").encode("ascii")
except UnicodeError:
pass
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):
try:
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
break
# 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
except:
if self._close_file:
self._file.close()
raise
if self._close_file:
self._file.close()
raise StopIteration
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(object):
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
_sentinel = ['sentinel']
##
# 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(object):
def __init__(self, html=_sentinel, target=None, encoding=None):
if html is not _sentinel:
warnings.warnpy3k(
"The html argument of XMLParser() is deprecated",
DeprecationWarning, stacklevel=2)
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
# callbacks
parser.DefaultHandlerExpand = self._default
parser.StartElementHandler = self._start
parser.EndElementHandler = self._end
parser.CharacterDataHandler = self._data
# optional callbacks
parser.CommentHandler = self._comment
parser.ProcessingInstructionHandler = self._pi
# let expat do the buffering, if supported
try:
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
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _raiseerror(self, value):
err = ParseError(value)
err.code = value.code
err.position = value.lineno, value.offset
raise err
def _fixtext(self, text):
# convert text string to ascii, if possible
try:
return text.encode("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
fixtext = self._fixtext
tag = fixname(tag)
attrib = {}
for key, value in attrib_in.items():
attrib[fixname(key)] = fixtext(value)
return self.target.start(tag, attrib)
def _start_list(self, tag, attrib_in):
fixname = self._fixname
fixtext = self._fixtext
tag = fixname(tag)
attrib = {}
if attrib_in:
for i in range(0, len(attrib_in), 2):
attrib[fixname(attrib_in[i])] = 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 _comment(self, data):
try:
comment = self.target.comment
except AttributeError:
pass
else:
return comment(self._fixtext(data))
def _pi(self, target, data):
try:
pi = self.target.pi
except AttributeError:
pass
else:
return pi(self._fixtext(target), self._fixtext(data))
def _default(self, text):
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
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
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if pubid:
pubid = pubid[1:-1]
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, 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, v:
self._raiseerror(v)
tree = self.target.close()
del self.target, self._parser # get rid of circular references
return tree
# compatibility
XMLTreeBuilder = XMLParser
# workaround circular import.
try:
from ElementC14N import _serialize_c14n
_serialize["c14n"] = _serialize_c14n
except ImportError:
pass
usr/lib64/python2.7/xml/etree/ElementTree.py 0000644 00000157310 15237063000 0014537 0 ustar 00 #
# ElementTree
# $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $
#
# light-weight XML support for Python 2.3 and later.
#
# history (since 1.2.6):
# 2005-11-12 fl added tostringlist/fromstringlist helpers
# 2006-07-05 fl merged in selected changes from the 1.3 sandbox
# 2006-07-05 fl removed support for 2.1 and earlier
# 2007-06-21 fl added deprecation/future warnings
# 2007-08-25 fl added doctype hook, added parser version attribute etc
# 2007-08-26 fl added new serializer code (better namespace handling, etc)
# 2007-08-27 fl warn for broken /tag searches on tree level
# 2007-09-02 fl added html/text methods to serializer (experimental)
# 2007-09-05 fl added method argument to tostring/tostringlist
# 2007-09-06 fl improved error handling
# 2007-09-13 fl added itertext, iterfind; assorted cleanups
# 2007-12-15 fl added C14N hooks, copy method (experimental)
#
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 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/psf/license for licensing details.
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML",
"XMLParser", "XMLTreeBuilder",
]
VERSION = "1.3.0"
##
# The Element 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.
#
# Each element has a number of properties associated with it:
#
# - a tag. This is a string identifying what kind of data
# this element represents (the element type, in other words).
# - a number of attributes, stored in a Python dictionary.
# - a text string.
# - an optional tail string.
# - a number of child elements, stored in a Python sequence
#
#
# To create an element instance, use the {@link #Element} constructor
# or the {@link #SubElement} factory function.
#
# 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
class _SimpleElementPath(object):
# emulate pre-1.2 find/findtext/findall behaviour
def find(self, element, tag, namespaces=None):
for elem in element:
if elem.tag == tag:
return elem
return None
def findtext(self, element, tag, default=None, namespaces=None):
elem = self.find(element, tag)
if elem is None:
return default
return elem.text or ""
def iterfind(self, element, tag, namespaces=None):
if tag[:3] == ".//":
for elem in element.iter(tag[3:]):
yield elem
for elem in element:
if elem.tag == tag:
yield elem
def findall(self, element, tag, namespaces=None):
return list(self.iterfind(element, tag, namespaces))
try:
from . import ElementPath
except ImportError:
ElementPath = _SimpleElementPath()
##
# 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; might be a better idea to look
# for tag/attrib/text attributes
return isinstance(element, Element) or hasattr(element, "tag")
##
# Element class. This class defines the Element interface, and
# provides a reference implementation of this interface.
#
# 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(object):
# text...tail
##
# (Attribute) Element tag.
tag = None
##
# (Attribute) Element attribute dictionary. Where possible, use
# {@link #Element.get},
# {@link #Element.set},
# {@link #Element.keys}, and
# {@link #Element.items} to access
# element attributes.
attrib = None
##
# (Attribute) Text before first subelement. This is either a
# string or the value None. Note that if there was no text, this
# attribute may be either None or an empty string, depending on
# the parser.
text = None
##
# (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. Note that if there was no text, this attribute
# may be either None or an empty string, depending on the parser.
tail = None # text after end tag, if any
# constructor
def __init__(self, tag, attrib={}, **extra):
attrib = attrib.copy()
attrib.update(extra)
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "" % (repr(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 self.__class__(tag, attrib)
##
# (Experimental) Copies the current element. This creates a
# shallow copy; subelements will be shared with the original tree.
#
# @return A new element instance.
def copy(self):
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
##
# Returns the number of subelements. Note that this only counts
# full elements; to check if there's any content in an element, you
# have to check both the length and the text attribute.
#
# @return The number of subelements.
def __len__(self):
return len(self._children)
def __nonzero__(self):
warnings.warn(
"The behavior of this method will change in future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
FutureWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
##
# Returns the given subelement, by index.
#
# @param index What subelement to return.
# @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, by index.
#
# @param index What subelement to replace.
# @param element The new element value.
# @exception IndexError If the given element does not exist.
def __setitem__(self, index, element):
# if isinstance(index, slice):
# for elt in element:
# assert iselement(elt)
# else:
# assert iselement(element)
self._children[index] = element
##
# Deletes the given subelement, by index.
#
# @param index What subelement to delete.
# @exception IndexError If the given element does not exist.
def __delitem__(self, index):
del self._children[index]
##
# Adds a subelement to the end of this element. In document order,
# the new element will appear after the last existing subelement (or
# directly after the text, if it's the first subelement), but before
# the end tag for this element.
#
# @param element The element to add.
def append(self, element):
# assert iselement(element)
self._children.append(element)
##
# Appends subelements from a sequence.
#
# @param elements A sequence object with zero or more elements.
# @since 1.3
def extend(self, elements):
# for element in elements:
# assert iselement(element)
self._children.extend(elements)
##
# Inserts a subelement at the given position in this element.
#
# @param index Where to insert the new subelement.
def insert(self, index, element):
# assert iselement(element)
self._children.insert(index, element)
##
# Removes a matching subelement. Unlike the find methods,
# this method compares elements based on identity, not on tag
# value or contents. To remove subelements by other means, the
# easiest way is often to use a list comprehension to select what
# elements to keep, and use slice assignment to update the parent
# element.
#
# @param element What element to remove.
# @exception ValueError If a matching element could not be found.
def remove(self, element):
# assert iselement(element)
self._children.remove(element)
##
# (Deprecated) Returns all subelements. The elements are returned
# in document order.
#
# @return A list of subelements.
# @defreturn list of Element instances
def getchildren(self):
warnings.warn(
"This method will be removed in future versions. "
"Use 'list(elem)' or iteration over elem instead.",
DeprecationWarning, stacklevel=2
)
return self._children
##
# Finds the first matching subelement, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path, namespaces=None):
return ElementPath.find(self, path, namespaces)
##
# 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.
# @keyparam namespaces Optional namespace prefix map.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None, namespaces=None):
return ElementPath.findtext(self, path, default, namespaces)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return A list or other sequence containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path, namespaces=None):
return ElementPath.findall(self, path, namespaces)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return An iterator or sequence containing all matching elements,
# in document order.
# @defreturn a generated sequence of Element instances
def iterfind(self, path, namespaces=None):
return ElementPath.iterfind(self, path, namespaces)
##
# Resets an element. This function removes all subelements, clears
# all attributes, and sets the text and tail attributes
# to None.
def clear(self):
self.attrib.clear()
self._children = []
self.text = self.tail = None
##
# Gets an element attribute. Equivalent to attrib.get, but
# some implementations may handle this a bit more efficiently.
#
# @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. Equivalent to attrib[key] = value,
# but some implementations may handle this a bit more efficiently.
#
# @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).
# Equivalent to attrib.keys().
#
# @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. Equivalent to attrib.items().
#
# @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.
#
# 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, basestring) and tag is not None:
return
if self.text:
yield self.text
for e in self:
for s in e.itertext():
yield s
if e.tail:
yield e.tail
# compatibility
_Element = _ElementInterface = Element
##
# 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
# a URI, and this argument is interpreted as a local name.
# @return An opaque object, representing the QName.
class QName(object):
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 file name. If given, the
# tree is initialized with the contents of this XML file.
class ElementTree(object):
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. If a file object is
# given, it only has to implement a read(n) method.
# @keyparam parser An optional parser instance. If not given, the
# standard {@link XMLParser} parser is used.
# @return The document root element.
# @defreturn Element
# @exception ParseError If the parser fails to parse the document.
def parse(self, source, parser=None):
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
while 1:
data = source.read(65536)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
##
# 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 iter(self, tag=None):
# assert self._root is not None
return self._root.iter(tag)
# compatibility
def getiterator(self, tag=None):
# Change for a DeprecationWarning in 1.4
warnings.warn(
"This method will be removed in future versions. "
"Use 'tree.iter()' or 'list(tree.iter())' instead.",
PendingDeprecationWarning, stacklevel=2
)
return list(self.iter(tag))
##
# Same as getroot().find(path), starting at the root of the
# tree.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
##
# Same as getroot().findtext(path), starting at the root of the tree.
#
# @param path What element to look for.
# @param default What to return if the element was not found.
# @keyparam namespaces Optional namespace prefix map.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
##
# Same as getroot().findall(path), starting at the root of the tree.
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
##
# Finds all matching subelements, by tag name or path.
# Same as getroot().iterfind(path).
#
# @param path What element to look for.
# @keyparam namespaces Optional namespace prefix map.
# @return An iterator or sequence containing all matching elements,
# in document order.
# @defreturn a generated sequence of Element instances
def iterfind(self, path, namespaces=None):
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
##
# Writes the element tree to a file, as XML.
#
# @def write(file, **options)
# @param file A file name, or a file object opened for writing.
# @param **options Options, given as keyword arguments.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam xml_declaration Controls if an XML declaration should
# be added to the file. Use False for never, True for always,
# None for only if not US-ASCII or UTF-8. None is default.
# @keyparam default_namespace Sets the default XML namespace (for "xmlns").
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
def write(self, file_or_filename,
# keyword arguments
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None):
# assert self._root is not None
if not method:
method = "xml"
elif method not in _serialize:
# FIXME: raise an ImportError for c14n if ElementC14N is missing?
raise ValueError("unknown method %r" % method)
if hasattr(file_or_filename, "write"):
file = file_or_filename
else:
file = open(file_or_filename, "wb")
write = file.write
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
elif xml_declaration or (xml_declaration is None and
encoding not in ("utf-8", "us-ascii")):
if method == "xml":
write("\n" % encoding)
if method == "text":
_serialize_text(write, self._root, encoding)
else:
qnames, namespaces = _namespaces(
self._root, encoding, default_namespace
)
serialize = _serialize[method]
serialize(write, self._root, encoding, qnames, namespaces)
if file_or_filename is not file:
file.close()
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
def _namespaces(elem, encoding, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def encode(text):
return text.encode(encoding)
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = encode("%s:%s" % (prefix, tag))
else:
qnames[qname] = encode(tag) # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = encode(qname)
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
try:
iterate = elem.iter
except AttributeError:
iterate = elem.getiterator # cET compatibility
for elem in iterate():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, basestring):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, encoding, qnames, namespaces):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _encode(text, encoding))
elif tag is ProcessingInstruction:
write("" % _encode(text, encoding))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_xml(write, e, encoding, qnames, None)
else:
write("<" + tag)
items = elem.items()
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k.encode(encoding),
_escape_attrib(v, encoding)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v, encoding)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem):
write(">")
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_xml(write, e, encoding, qnames, None)
write("")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail, encoding))
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param")
try:
HTML_EMPTY = set(HTML_EMPTY)
except NameError:
pass
def _serialize_html(write, elem, encoding, qnames, namespaces):
tag = elem.tag
text = elem.text
if tag is Comment:
write("" % _escape_cdata(text, encoding))
elif tag is ProcessingInstruction:
write("" % _escape_cdata(text, encoding))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_html(write, e, encoding, qnames, None)
else:
write("<" + tag)
items = elem.items()
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k.encode(encoding),
_escape_attrib(v, encoding)
))
for k, v in sorted(items): # lexical order
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v, encoding)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(_encode(text, encoding))
else:
write(_escape_cdata(text, encoding))
for e in elem:
_serialize_html(write, e, encoding, qnames, None)
if ltag not in HTML_EMPTY:
write("")
if elem.tail:
write(_escape_cdata(elem.tail, encoding))
def _serialize_text(write, elem, encoding):
for part in elem.itertext():
write(part.encode(encoding))
if elem.tail:
write(elem.tail.encode(encoding))
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
##
# Registers a namespace prefix. The registry is global, and any
# existing mapping for either the given prefix or the namespace URI
# will be removed.
#
# @param prefix Namespace prefix.
# @param uri Namespace uri. Tags and attributes in this namespace
# will be serialized with the given prefix, if at all possible.
# @exception ValueError If the prefix is reserved, or is otherwise
# invalid.
def register_namespace(prefix, uri):
if re.match("ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in _namespace_map.items():
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
# dublin core
"http://purl.org/dc/elements/1.1/": "dc",
}
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _encode(text, encoding):
try:
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_cdata(text, encoding):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text, encoding):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
if "\n" in text:
text = text.replace("\n", "
")
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib_html(text, encoding):
# escape attribute value
try:
if "&" in text:
text = text.replace("&", "&")
if ">" in text:
text = text.replace(">", ">")
if "\"" in text:
text = text.replace("\"", """)
return text.encode(encoding, "xmlcharrefreplace")
except (TypeError, AttributeError):
_raise_serialization_error(text)
# --------------------------------------------------------------------
##
# Generates a string representation of an XML element, including all
# subelements.
#
# @param element An Element instance.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
# @return An encoded string containing the XML data.
# @defreturn string
def tostring(element, encoding=None, method=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding, method=method)
return "".join(data)
##
# Generates a string representation of an XML element, including all
# subelements. The string is returned as a sequence of string fragments.
#
# @param element An Element instance.
# @keyparam encoding Optional output encoding (default is US-ASCII).
# @keyparam method Optional output method ("xml", "html", "text" or
# "c14n"; default is "xml").
# @return A sequence object containing the XML data.
# @defreturn sequence
# @since 1.3
def tostringlist(element, encoding=None, method=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding, method=method)
# FIXME: merge small fragments into larger parts
return data
##
# 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")
# --------------------------------------------------------------------
# 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
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
return _IterParseIterator(source, events, parser, close_source)
except:
if close_source:
source.close()
raise
class _IterParseIterator(object):
def __init__(self, source, events, parser, close_source=False):
self._file = source
self._close_file = close_source
self._events = []
self._index = 0
self._error = None
self.root = self._root = None
self._parser = 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):
try:
uri = (uri or "").encode("ascii")
except UnicodeError:
pass
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):
try:
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
break
# 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
except:
if self._close_file:
self._file.close()
raise
if self._close_file:
self._file.close()
raise StopIteration
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(object):
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
_sentinel = ['sentinel']
##
# 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(object):
def __init__(self, html=_sentinel, target=None, encoding=None):
if html is not _sentinel:
warnings.warnpy3k(
"The html argument of XMLParser() is deprecated",
DeprecationWarning, stacklevel=2)
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
# callbacks
parser.DefaultHandlerExpand = self._default
parser.StartElementHandler = self._start
parser.EndElementHandler = self._end
parser.CharacterDataHandler = self._data
# optional callbacks
parser.CommentHandler = self._comment
parser.ProcessingInstructionHandler = self._pi
# let expat do the buffering, if supported
try:
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
self._doctype = None
self.entity = {}
try:
self.version = "Expat %d.%d.%d" % expat.version_info
except AttributeError:
pass # unknown
def _raiseerror(self, value):
err = ParseError(value)
err.code = value.code
err.position = value.lineno, value.offset
raise err
def _fixtext(self, text):
# convert text string to ascii, if possible
try:
return text.encode("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
fixtext = self._fixtext
tag = fixname(tag)
attrib = {}
for key, value in attrib_in.items():
attrib[fixname(key)] = fixtext(value)
return self.target.start(tag, attrib)
def _start_list(self, tag, attrib_in):
fixname = self._fixname
fixtext = self._fixtext
tag = fixname(tag)
attrib = {}
if attrib_in:
for i in range(0, len(attrib_in), 2):
attrib[fixname(attrib_in[i])] = 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 _comment(self, data):
try:
comment = self.target.comment
except AttributeError:
pass
else:
return comment(self._fixtext(data))
def _pi(self, target, data):
try:
pi = self.target.pi
except AttributeError:
pass
else:
return pi(self._fixtext(target), self._fixtext(data))
def _default(self, text):
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
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
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if pubid:
pubid = pubid[1:-1]
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, 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, v:
self._raiseerror(v)
tree = self.target.close()
del self.target, self._parser # get rid of circular references
return tree
# compatibility
XMLTreeBuilder = XMLParser
# workaround circular import.
try:
from ElementC14N import _serialize_c14n
_serialize["c14n"] = _serialize_c14n
except ImportError:
pass