+++ /dev/null
-#\r
-# ElementTree\r
-# $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $\r
-#\r
-# light-weight XML support for Python 2.3 and later.\r
-#\r
-# history (since 1.2.6):\r
-# 2005-11-12 fl added tostringlist/fromstringlist helpers\r
-# 2006-07-05 fl merged in selected changes from the 1.3 sandbox\r
-# 2006-07-05 fl removed support for 2.1 and earlier\r
-# 2007-06-21 fl added deprecation/future warnings\r
-# 2007-08-25 fl added doctype hook, added parser version attribute etc\r
-# 2007-08-26 fl added new serializer code (better namespace handling, etc)\r
-# 2007-08-27 fl warn for broken /tag searches on tree level\r
-# 2007-09-02 fl added html/text methods to serializer (experimental)\r
-# 2007-09-05 fl added method argument to tostring/tostringlist\r
-# 2007-09-06 fl improved error handling\r
-# 2007-09-13 fl added itertext, iterfind; assorted cleanups\r
-# 2007-12-15 fl added C14N hooks, copy method (experimental)\r
-#\r
-# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.\r
-#\r
-# fredrik@pythonware.com\r
-# http://www.pythonware.com\r
-#\r
-# --------------------------------------------------------------------\r
-# The ElementTree toolkit is\r
-#\r
-# Copyright (c) 1999-2008 by Fredrik Lundh\r
-#\r
-# By obtaining, using, and/or copying this software and/or its\r
-# associated documentation, you agree that you have read, understood,\r
-# and will comply with the following terms and conditions:\r
-#\r
-# Permission to use, copy, modify, and distribute this software and\r
-# its associated documentation for any purpose and without fee is\r
-# hereby granted, provided that the above copyright notice appears in\r
-# all copies, and that both that copyright notice and this permission\r
-# notice appear in supporting documentation, and that the name of\r
-# Secret Labs AB or the author not be used in advertising or publicity\r
-# pertaining to distribution of the software without specific, written\r
-# prior permission.\r
-#\r
-# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD\r
-# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-\r
-# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR\r
-# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY\r
-# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,\r
-# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS\r
-# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE\r
-# OF THIS SOFTWARE.\r
-# --------------------------------------------------------------------\r
-\r
-# Licensed to PSF under a Contributor Agreement.\r
-# See http://www.python.org/psf/license for licensing details.\r
-\r
-__all__ = [\r
- # public symbols\r
- "Comment",\r
- "dump",\r
- "Element", "ElementTree",\r
- "fromstring", "fromstringlist",\r
- "iselement", "iterparse",\r
- "parse", "ParseError",\r
- "PI", "ProcessingInstruction",\r
- "QName",\r
- "SubElement",\r
- "tostring", "tostringlist",\r
- "TreeBuilder",\r
- "VERSION",\r
- "XML",\r
- "XMLParser", "XMLTreeBuilder",\r
- ]\r
-\r
-VERSION = "1.3.0"\r
-\r
-##\r
-# The <b>Element</b> type is a flexible container object, designed to\r
-# store hierarchical data structures in memory. The type can be\r
-# described as a cross between a list and a dictionary.\r
-# <p>\r
-# Each element has a number of properties associated with it:\r
-# <ul>\r
-# <li>a <i>tag</i>. This is a string identifying what kind of data\r
-# this element represents (the element type, in other words).</li>\r
-# <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>\r
-# <li>a <i>text</i> string.</li>\r
-# <li>an optional <i>tail</i> string.</li>\r
-# <li>a number of <i>child elements</i>, stored in a Python sequence</li>\r
-# </ul>\r
-#\r
-# To create an element instance, use the {@link #Element} constructor\r
-# or the {@link #SubElement} factory function.\r
-# <p>\r
-# The {@link #ElementTree} class can be used to wrap an element\r
-# structure, and convert it from and to XML.\r
-##\r
-\r
-import sys\r
-import re\r
-import warnings\r
-\r
-\r
-class _SimpleElementPath(object):\r
- # emulate pre-1.2 find/findtext/findall behaviour\r
- def find(self, element, tag, namespaces=None):\r
- for elem in element:\r
- if elem.tag == tag:\r
- return elem\r
- return None\r
- def findtext(self, element, tag, default=None, namespaces=None):\r
- elem = self.find(element, tag)\r
- if elem is None:\r
- return default\r
- return elem.text or ""\r
- def iterfind(self, element, tag, namespaces=None):\r
- if tag[:3] == ".//":\r
- for elem in element.iter(tag[3:]):\r
- yield elem\r
- for elem in element:\r
- if elem.tag == tag:\r
- yield elem\r
- def findall(self, element, tag, namespaces=None):\r
- return list(self.iterfind(element, tag, namespaces))\r
-\r
-try:\r
- from . import ElementPath\r
-except ImportError:\r
- ElementPath = _SimpleElementPath()\r
-\r
-##\r
-# Parser error. This is a subclass of <b>SyntaxError</b>.\r
-# <p>\r
-# In addition to the exception value, an exception instance contains a\r
-# specific exception code in the <b>code</b> attribute, and the line and\r
-# column of the error in the <b>position</b> attribute.\r
-\r
-class ParseError(SyntaxError):\r
- pass\r
-\r
-# --------------------------------------------------------------------\r
-\r
-##\r
-# Checks if an object appears to be a valid element object.\r
-#\r
-# @param An element instance.\r
-# @return A true value if this is an element object.\r
-# @defreturn flag\r
-\r
-def iselement(element):\r
- # FIXME: not sure about this; might be a better idea to look\r
- # for tag/attrib/text attributes\r
- return isinstance(element, Element) or hasattr(element, "tag")\r
-\r
-##\r
-# Element class. This class defines the Element interface, and\r
-# provides a reference implementation of this interface.\r
-# <p>\r
-# The element name, attribute names, and attribute values can be\r
-# either ASCII strings (ordinary Python strings containing only 7-bit\r
-# ASCII characters) or Unicode strings.\r
-#\r
-# @param tag The element name.\r
-# @param attrib An optional dictionary, containing element attributes.\r
-# @param **extra Additional attributes, given as keyword arguments.\r
-# @see Element\r
-# @see SubElement\r
-# @see Comment\r
-# @see ProcessingInstruction\r
-\r
-class Element(object):\r
- # <tag attrib>text<child/>...</tag>tail\r
-\r
- ##\r
- # (Attribute) Element tag.\r
-\r
- tag = None\r
-\r
- ##\r
- # (Attribute) Element attribute dictionary. Where possible, use\r
- # {@link #Element.get},\r
- # {@link #Element.set},\r
- # {@link #Element.keys}, and\r
- # {@link #Element.items} to access\r
- # element attributes.\r
-\r
- attrib = None\r
-\r
- ##\r
- # (Attribute) Text before first subelement. This is either a\r
- # string or the value None. Note that if there was no text, this\r
- # attribute may be either None or an empty string, depending on\r
- # the parser.\r
-\r
- text = None\r
-\r
- ##\r
- # (Attribute) Text after this element's end tag, but before the\r
- # next sibling element's start tag. This is either a string or\r
- # the value None. Note that if there was no text, this attribute\r
- # may be either None or an empty string, depending on the parser.\r
-\r
- tail = None # text after end tag, if any\r
-\r
- # constructor\r
-\r
- def __init__(self, tag, attrib={}, **extra):\r
- attrib = attrib.copy()\r
- attrib.update(extra)\r
- self.tag = tag\r
- self.attrib = attrib\r
- self._children = []\r
-\r
- def __repr__(self):\r
- return "<Element %s at 0x%x>" % (repr(self.tag), id(self))\r
-\r
- ##\r
- # Creates a new element object of the same type as this element.\r
- #\r
- # @param tag Element tag.\r
- # @param attrib Element attributes, given as a dictionary.\r
- # @return A new element instance.\r
-\r
- def makeelement(self, tag, attrib):\r
- return self.__class__(tag, attrib)\r
-\r
- ##\r
- # (Experimental) Copies the current element. This creates a\r
- # shallow copy; subelements will be shared with the original tree.\r
- #\r
- # @return A new element instance.\r
-\r
- def copy(self):\r
- elem = self.makeelement(self.tag, self.attrib)\r
- elem.text = self.text\r
- elem.tail = self.tail\r
- elem[:] = self\r
- return elem\r
-\r
- ##\r
- # Returns the number of subelements. Note that this only counts\r
- # full elements; to check if there's any content in an element, you\r
- # have to check both the length and the <b>text</b> attribute.\r
- #\r
- # @return The number of subelements.\r
-\r
- def __len__(self):\r
- return len(self._children)\r
-\r
- def __nonzero__(self):\r
- warnings.warn(\r
- "The behavior of this method will change in future versions. "\r
- "Use specific 'len(elem)' or 'elem is not None' test instead.",\r
- FutureWarning, stacklevel=2\r
- )\r
- return len(self._children) != 0 # emulate old behaviour, for now\r
-\r
- ##\r
- # Returns the given subelement, by index.\r
- #\r
- # @param index What subelement to return.\r
- # @return The given subelement.\r
- # @exception IndexError If the given element does not exist.\r
-\r
- def __getitem__(self, index):\r
- return self._children[index]\r
-\r
- ##\r
- # Replaces the given subelement, by index.\r
- #\r
- # @param index What subelement to replace.\r
- # @param element The new element value.\r
- # @exception IndexError If the given element does not exist.\r
-\r
- def __setitem__(self, index, element):\r
- # if isinstance(index, slice):\r
- # for elt in element:\r
- # assert iselement(elt)\r
- # else:\r
- # assert iselement(element)\r
- self._children[index] = element\r
-\r
- ##\r
- # Deletes the given subelement, by index.\r
- #\r
- # @param index What subelement to delete.\r
- # @exception IndexError If the given element does not exist.\r
-\r
- def __delitem__(self, index):\r
- del self._children[index]\r
-\r
- ##\r
- # Adds a subelement to the end of this element. In document order,\r
- # the new element will appear after the last existing subelement (or\r
- # directly after the text, if it's the first subelement), but before\r
- # the end tag for this element.\r
- #\r
- # @param element The element to add.\r
-\r
- def append(self, element):\r
- # assert iselement(element)\r
- self._children.append(element)\r
-\r
- ##\r
- # Appends subelements from a sequence.\r
- #\r
- # @param elements A sequence object with zero or more elements.\r
- # @since 1.3\r
-\r
- def extend(self, elements):\r
- # for element in elements:\r
- # assert iselement(element)\r
- self._children.extend(elements)\r
-\r
- ##\r
- # Inserts a subelement at the given position in this element.\r
- #\r
- # @param index Where to insert the new subelement.\r
-\r
- def insert(self, index, element):\r
- # assert iselement(element)\r
- self._children.insert(index, element)\r
-\r
- ##\r
- # Removes a matching subelement. Unlike the <b>find</b> methods,\r
- # this method compares elements based on identity, not on tag\r
- # value or contents. To remove subelements by other means, the\r
- # easiest way is often to use a list comprehension to select what\r
- # elements to keep, and use slice assignment to update the parent\r
- # element.\r
- #\r
- # @param element What element to remove.\r
- # @exception ValueError If a matching element could not be found.\r
-\r
- def remove(self, element):\r
- # assert iselement(element)\r
- self._children.remove(element)\r
-\r
- ##\r
- # (Deprecated) Returns all subelements. The elements are returned\r
- # in document order.\r
- #\r
- # @return A list of subelements.\r
- # @defreturn list of Element instances\r
-\r
- def getchildren(self):\r
- warnings.warn(\r
- "This method will be removed in future versions. "\r
- "Use 'list(elem)' or iteration over elem instead.",\r
- DeprecationWarning, stacklevel=2\r
- )\r
- return self._children\r
-\r
- ##\r
- # Finds the first matching subelement, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return The first matching element, or None if no element was found.\r
- # @defreturn Element or None\r
-\r
- def find(self, path, namespaces=None):\r
- return ElementPath.find(self, path, namespaces)\r
-\r
- ##\r
- # Finds text for the first matching subelement, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @param default What to return if the element was not found.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return The text content of the first matching element, or the\r
- # default value no element was found. Note that if the element\r
- # is found, but has no text content, this method returns an\r
- # empty string.\r
- # @defreturn string\r
-\r
- def findtext(self, path, default=None, namespaces=None):\r
- return ElementPath.findtext(self, path, default, namespaces)\r
-\r
- ##\r
- # Finds all matching subelements, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return A list or other sequence containing all matching elements,\r
- # in document order.\r
- # @defreturn list of Element instances\r
-\r
- def findall(self, path, namespaces=None):\r
- return ElementPath.findall(self, path, namespaces)\r
-\r
- ##\r
- # Finds all matching subelements, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return An iterator or sequence containing all matching elements,\r
- # in document order.\r
- # @defreturn a generated sequence of Element instances\r
-\r
- def iterfind(self, path, namespaces=None):\r
- return ElementPath.iterfind(self, path, namespaces)\r
-\r
- ##\r
- # Resets an element. This function removes all subelements, clears\r
- # all attributes, and sets the <b>text</b> and <b>tail</b> attributes\r
- # to None.\r
-\r
- def clear(self):\r
- self.attrib.clear()\r
- self._children = []\r
- self.text = self.tail = None\r
-\r
- ##\r
- # Gets an element attribute. Equivalent to <b>attrib.get</b>, but\r
- # some implementations may handle this a bit more efficiently.\r
- #\r
- # @param key What attribute to look for.\r
- # @param default What to return if the attribute was not found.\r
- # @return The attribute value, or the default value, if the\r
- # attribute was not found.\r
- # @defreturn string or None\r
-\r
- def get(self, key, default=None):\r
- return self.attrib.get(key, default)\r
-\r
- ##\r
- # Sets an element attribute. Equivalent to <b>attrib[key] = value</b>,\r
- # but some implementations may handle this a bit more efficiently.\r
- #\r
- # @param key What attribute to set.\r
- # @param value The attribute value.\r
-\r
- def set(self, key, value):\r
- self.attrib[key] = value\r
-\r
- ##\r
- # Gets a list of attribute names. The names are returned in an\r
- # arbitrary order (just like for an ordinary Python dictionary).\r
- # Equivalent to <b>attrib.keys()</b>.\r
- #\r
- # @return A list of element attribute names.\r
- # @defreturn list of strings\r
-\r
- def keys(self):\r
- return self.attrib.keys()\r
-\r
- ##\r
- # Gets element attributes, as a sequence. The attributes are\r
- # returned in an arbitrary order. Equivalent to <b>attrib.items()</b>.\r
- #\r
- # @return A list of (name, value) tuples for all attributes.\r
- # @defreturn list of (string, string) tuples\r
-\r
- def items(self):\r
- return self.attrib.items()\r
-\r
- ##\r
- # Creates a tree iterator. The iterator loops over this element\r
- # and all subelements, in document order, and returns all elements\r
- # with a matching tag.\r
- # <p>\r
- # If the tree structure is modified during iteration, new or removed\r
- # elements may or may not be included. To get a stable set, use the\r
- # list() function on the iterator, and loop over the resulting list.\r
- #\r
- # @param tag What tags to look for (default is to return all elements).\r
- # @return An iterator containing all the matching elements.\r
- # @defreturn iterator\r
-\r
- def iter(self, tag=None):\r
- if tag == "*":\r
- tag = None\r
- if tag is None or self.tag == tag:\r
- yield self\r
- for e in self._children:\r
- for e in e.iter(tag):\r
- yield e\r
-\r
- # compatibility\r
- def getiterator(self, tag=None):\r
- # Change for a DeprecationWarning in 1.4\r
- warnings.warn(\r
- "This method will be removed in future versions. "\r
- "Use 'elem.iter()' or 'list(elem.iter())' instead.",\r
- PendingDeprecationWarning, stacklevel=2\r
- )\r
- return list(self.iter(tag))\r
-\r
- ##\r
- # Creates a text iterator. The iterator loops over this element\r
- # and all subelements, in document order, and returns all inner\r
- # text.\r
- #\r
- # @return An iterator containing all inner text.\r
- # @defreturn iterator\r
-\r
- def itertext(self):\r
- tag = self.tag\r
- if not isinstance(tag, basestring) and tag is not None:\r
- return\r
- if self.text:\r
- yield self.text\r
- for e in self:\r
- for s in e.itertext():\r
- yield s\r
- if e.tail:\r
- yield e.tail\r
-\r
-# compatibility\r
-_Element = _ElementInterface = Element\r
-\r
-##\r
-# Subelement factory. This function creates an element instance, and\r
-# appends it to an existing element.\r
-# <p>\r
-# The element name, attribute names, and attribute values can be\r
-# either 8-bit ASCII strings or Unicode strings.\r
-#\r
-# @param parent The parent element.\r
-# @param tag The subelement name.\r
-# @param attrib An optional dictionary, containing element attributes.\r
-# @param **extra Additional attributes, given as keyword arguments.\r
-# @return An element instance.\r
-# @defreturn Element\r
-\r
-def SubElement(parent, tag, attrib={}, **extra):\r
- attrib = attrib.copy()\r
- attrib.update(extra)\r
- element = parent.makeelement(tag, attrib)\r
- parent.append(element)\r
- return element\r
-\r
-##\r
-# Comment element factory. This factory function creates a special\r
-# element that will be serialized as an XML comment by the standard\r
-# serializer.\r
-# <p>\r
-# The comment string can be either an 8-bit ASCII string or a Unicode\r
-# string.\r
-#\r
-# @param text A string containing the comment string.\r
-# @return An element instance, representing a comment.\r
-# @defreturn Element\r
-\r
-def Comment(text=None):\r
- element = Element(Comment)\r
- element.text = text\r
- return element\r
-\r
-##\r
-# PI element factory. This factory function creates a special element\r
-# that will be serialized as an XML processing instruction by the standard\r
-# serializer.\r
-#\r
-# @param target A string containing the PI target.\r
-# @param text A string containing the PI contents, if any.\r
-# @return An element instance, representing a PI.\r
-# @defreturn Element\r
-\r
-def ProcessingInstruction(target, text=None):\r
- element = Element(ProcessingInstruction)\r
- element.text = target\r
- if text:\r
- element.text = element.text + " " + text\r
- return element\r
-\r
-PI = ProcessingInstruction\r
-\r
-##\r
-# QName wrapper. This can be used to wrap a QName attribute value, in\r
-# order to get proper namespace handling on output.\r
-#\r
-# @param text A string containing the QName value, in the form {uri}local,\r
-# or, if the tag argument is given, the URI part of a QName.\r
-# @param tag Optional tag. If given, the first argument is interpreted as\r
-# an URI, and this argument is interpreted as a local name.\r
-# @return An opaque object, representing the QName.\r
-\r
-class QName(object):\r
- def __init__(self, text_or_uri, tag=None):\r
- if tag:\r
- text_or_uri = "{%s}%s" % (text_or_uri, tag)\r
- self.text = text_or_uri\r
- def __str__(self):\r
- return self.text\r
- def __hash__(self):\r
- return hash(self.text)\r
- def __cmp__(self, other):\r
- if isinstance(other, QName):\r
- return cmp(self.text, other.text)\r
- return cmp(self.text, other)\r
-\r
-# --------------------------------------------------------------------\r
-\r
-##\r
-# ElementTree wrapper class. This class represents an entire element\r
-# hierarchy, and adds some extra support for serialization to and from\r
-# standard XML.\r
-#\r
-# @param element Optional root element.\r
-# @keyparam file Optional file handle or file name. If given, the\r
-# tree is initialized with the contents of this XML file.\r
-\r
-class ElementTree(object):\r
-\r
- def __init__(self, element=None, file=None):\r
- # assert element is None or iselement(element)\r
- self._root = element # first node\r
- if file:\r
- self.parse(file)\r
-\r
- ##\r
- # Gets the root element for this tree.\r
- #\r
- # @return An element instance.\r
- # @defreturn Element\r
-\r
- def getroot(self):\r
- return self._root\r
-\r
- ##\r
- # Replaces the root element for this tree. This discards the\r
- # current contents of the tree, and replaces it with the given\r
- # element. Use with care.\r
- #\r
- # @param element An element instance.\r
-\r
- def _setroot(self, element):\r
- # assert iselement(element)\r
- self._root = element\r
-\r
- ##\r
- # Loads an external XML document into this element tree.\r
- #\r
- # @param source A file name or file object. If a file object is\r
- # given, it only has to implement a <b>read(n)</b> method.\r
- # @keyparam parser An optional parser instance. If not given, the\r
- # standard {@link XMLParser} parser is used.\r
- # @return The document root element.\r
- # @defreturn Element\r
- # @exception ParseError If the parser fails to parse the document.\r
-\r
- def parse(self, source, parser=None):\r
- close_source = False\r
- if not hasattr(source, "read"):\r
- source = open(source, "rb")\r
- close_source = True\r
- try:\r
- if not parser:\r
- parser = XMLParser(target=TreeBuilder())\r
- while 1:\r
- data = source.read(65536)\r
- if not data:\r
- break\r
- parser.feed(data)\r
- self._root = parser.close()\r
- return self._root\r
- finally:\r
- if close_source:\r
- source.close()\r
-\r
- ##\r
- # Creates a tree iterator for the root element. The iterator loops\r
- # over all elements in this tree, in document order.\r
- #\r
- # @param tag What tags to look for (default is to return all elements)\r
- # @return An iterator.\r
- # @defreturn iterator\r
-\r
- def iter(self, tag=None):\r
- # assert self._root is not None\r
- return self._root.iter(tag)\r
-\r
- # compatibility\r
- def getiterator(self, tag=None):\r
- # Change for a DeprecationWarning in 1.4\r
- warnings.warn(\r
- "This method will be removed in future versions. "\r
- "Use 'tree.iter()' or 'list(tree.iter())' instead.",\r
- PendingDeprecationWarning, stacklevel=2\r
- )\r
- return list(self.iter(tag))\r
-\r
- ##\r
- # Same as getroot().find(path), starting at the root of the\r
- # tree.\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return The first matching element, or None if no element was found.\r
- # @defreturn Element or None\r
-\r
- def find(self, path, namespaces=None):\r
- # assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- warnings.warn(\r
- "This search is broken in 1.3 and earlier, and will be "\r
- "fixed in a future version. If you rely on the current "\r
- "behaviour, change it to %r" % path,\r
- FutureWarning, stacklevel=2\r
- )\r
- return self._root.find(path, namespaces)\r
-\r
- ##\r
- # Same as getroot().findtext(path), starting at the root of the tree.\r
- #\r
- # @param path What element to look for.\r
- # @param default What to return if the element was not found.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return The text content of the first matching element, or the\r
- # default value no element was found. Note that if the element\r
- # is found, but has no text content, this method returns an\r
- # empty string.\r
- # @defreturn string\r
-\r
- def findtext(self, path, default=None, namespaces=None):\r
- # assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- warnings.warn(\r
- "This search is broken in 1.3 and earlier, and will be "\r
- "fixed in a future version. If you rely on the current "\r
- "behaviour, change it to %r" % path,\r
- FutureWarning, stacklevel=2\r
- )\r
- return self._root.findtext(path, default, namespaces)\r
-\r
- ##\r
- # Same as getroot().findall(path), starting at the root of the tree.\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return A list or iterator containing all matching elements,\r
- # in document order.\r
- # @defreturn list of Element instances\r
-\r
- def findall(self, path, namespaces=None):\r
- # assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- warnings.warn(\r
- "This search is broken in 1.3 and earlier, and will be "\r
- "fixed in a future version. If you rely on the current "\r
- "behaviour, change it to %r" % path,\r
- FutureWarning, stacklevel=2\r
- )\r
- return self._root.findall(path, namespaces)\r
-\r
- ##\r
- # Finds all matching subelements, by tag name or path.\r
- # Same as getroot().iterfind(path).\r
- #\r
- # @param path What element to look for.\r
- # @keyparam namespaces Optional namespace prefix map.\r
- # @return An iterator or sequence containing all matching elements,\r
- # in document order.\r
- # @defreturn a generated sequence of Element instances\r
-\r
- def iterfind(self, path, namespaces=None):\r
- # assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- warnings.warn(\r
- "This search is broken in 1.3 and earlier, and will be "\r
- "fixed in a future version. If you rely on the current "\r
- "behaviour, change it to %r" % path,\r
- FutureWarning, stacklevel=2\r
- )\r
- return self._root.iterfind(path, namespaces)\r
-\r
- ##\r
- # Writes the element tree to a file, as XML.\r
- #\r
- # @def write(file, **options)\r
- # @param file A file name, or a file object opened for writing.\r
- # @param **options Options, given as keyword arguments.\r
- # @keyparam encoding Optional output encoding (default is US-ASCII).\r
- # @keyparam xml_declaration Controls if an XML declaration should\r
- # be added to the file. Use False for never, True for always,\r
- # None for only if not US-ASCII or UTF-8. None is default.\r
- # @keyparam default_namespace Sets the default XML namespace (for "xmlns").\r
- # @keyparam method Optional output method ("xml", "html", "text" or\r
- # "c14n"; default is "xml").\r
-\r
- def write(self, file_or_filename,\r
- # keyword arguments\r
- encoding=None,\r
- xml_declaration=None,\r
- default_namespace=None,\r
- method=None):\r
- # assert self._root is not None\r
- if not method:\r
- method = "xml"\r
- elif method not in _serialize:\r
- # FIXME: raise an ImportError for c14n if ElementC14N is missing?\r
- raise ValueError("unknown method %r" % method)\r
- if hasattr(file_or_filename, "write"):\r
- file = file_or_filename\r
- else:\r
- file = open(file_or_filename, "wb")\r
- write = file.write\r
- if not encoding:\r
- if method == "c14n":\r
- encoding = "utf-8"\r
- else:\r
- encoding = "us-ascii"\r
- elif xml_declaration or (xml_declaration is None and\r
- encoding not in ("utf-8", "us-ascii")):\r
- if method == "xml":\r
- write("<?xml version='1.0' encoding='%s'?>\n" % encoding)\r
- if method == "text":\r
- _serialize_text(write, self._root, encoding)\r
- else:\r
- qnames, namespaces = _namespaces(\r
- self._root, encoding, default_namespace\r
- )\r
- serialize = _serialize[method]\r
- serialize(write, self._root, encoding, qnames, namespaces)\r
- if file_or_filename is not file:\r
- file.close()\r
-\r
- def write_c14n(self, file):\r
- # lxml.etree compatibility. use output method instead\r
- return self.write(file, method="c14n")\r
-\r
-# --------------------------------------------------------------------\r
-# serialization support\r
-\r
-def _namespaces(elem, encoding, default_namespace=None):\r
- # identify namespaces used in this tree\r
-\r
- # maps qnames to *encoded* prefix:local names\r
- qnames = {None: None}\r
-\r
- # maps uri:s to prefixes\r
- namespaces = {}\r
- if default_namespace:\r
- namespaces[default_namespace] = ""\r
-\r
- def encode(text):\r
- return text.encode(encoding)\r
-\r
- def add_qname(qname):\r
- # calculate serialized qname representation\r
- try:\r
- if qname[:1] == "{":\r
- uri, tag = qname[1:].rsplit("}", 1)\r
- prefix = namespaces.get(uri)\r
- if prefix is None:\r
- prefix = _namespace_map.get(uri)\r
- if prefix is None:\r
- prefix = "ns%d" % len(namespaces)\r
- if prefix != "xml":\r
- namespaces[uri] = prefix\r
- if prefix:\r
- qnames[qname] = encode("%s:%s" % (prefix, tag))\r
- else:\r
- qnames[qname] = encode(tag) # default element\r
- else:\r
- if default_namespace:\r
- # FIXME: can this be handled in XML 1.0?\r
- raise ValueError(\r
- "cannot use non-qualified names with "\r
- "default_namespace option"\r
- )\r
- qnames[qname] = encode(qname)\r
- except TypeError:\r
- _raise_serialization_error(qname)\r
-\r
- # populate qname and namespaces table\r
- try:\r
- iterate = elem.iter\r
- except AttributeError:\r
- iterate = elem.getiterator # cET compatibility\r
- for elem in iterate():\r
- tag = elem.tag\r
- if isinstance(tag, QName):\r
- if tag.text not in qnames:\r
- add_qname(tag.text)\r
- elif isinstance(tag, basestring):\r
- if tag not in qnames:\r
- add_qname(tag)\r
- elif tag is not None and tag is not Comment and tag is not PI:\r
- _raise_serialization_error(tag)\r
- for key, value in elem.items():\r
- if isinstance(key, QName):\r
- key = key.text\r
- if key not in qnames:\r
- add_qname(key)\r
- if isinstance(value, QName) and value.text not in qnames:\r
- add_qname(value.text)\r
- text = elem.text\r
- if isinstance(text, QName) and text.text not in qnames:\r
- add_qname(text.text)\r
- return qnames, namespaces\r
-\r
-def _serialize_xml(write, elem, encoding, qnames, namespaces):\r
- tag = elem.tag\r
- text = elem.text\r
- if tag is Comment:\r
- write("<!--%s-->" % _encode(text, encoding))\r
- elif tag is ProcessingInstruction:\r
- write("<?%s?>" % _encode(text, encoding))\r
- else:\r
- tag = qnames[tag]\r
- if tag is None:\r
- if text:\r
- write(_escape_cdata(text, encoding))\r
- for e in elem:\r
- _serialize_xml(write, e, encoding, qnames, None)\r
- else:\r
- write("<" + tag)\r
- items = elem.items()\r
- if items or namespaces:\r
- if namespaces:\r
- for v, k in sorted(namespaces.items(),\r
- key=lambda x: x[1]): # sort on prefix\r
- if k:\r
- k = ":" + k\r
- write(" xmlns%s=\"%s\"" % (\r
- k.encode(encoding),\r
- _escape_attrib(v, encoding)\r
- ))\r
- for k, v in sorted(items): # lexical order\r
- if isinstance(k, QName):\r
- k = k.text\r
- if isinstance(v, QName):\r
- v = qnames[v.text]\r
- else:\r
- v = _escape_attrib(v, encoding)\r
- write(" %s=\"%s\"" % (qnames[k], v))\r
- if text or len(elem):\r
- write(">")\r
- if text:\r
- write(_escape_cdata(text, encoding))\r
- for e in elem:\r
- _serialize_xml(write, e, encoding, qnames, None)\r
- write("</" + tag + ">")\r
- else:\r
- write(" />")\r
- if elem.tail:\r
- write(_escape_cdata(elem.tail, encoding))\r
-\r
-HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",\r
- "img", "input", "isindex", "link", "meta", "param")\r
-\r
-try:\r
- HTML_EMPTY = set(HTML_EMPTY)\r
-except NameError:\r
- pass\r
-\r
-def _serialize_html(write, elem, encoding, qnames, namespaces):\r
- tag = elem.tag\r
- text = elem.text\r
- if tag is Comment:\r
- write("<!--%s-->" % _escape_cdata(text, encoding))\r
- elif tag is ProcessingInstruction:\r
- write("<?%s?>" % _escape_cdata(text, encoding))\r
- else:\r
- tag = qnames[tag]\r
- if tag is None:\r
- if text:\r
- write(_escape_cdata(text, encoding))\r
- for e in elem:\r
- _serialize_html(write, e, encoding, qnames, None)\r
- else:\r
- write("<" + tag)\r
- items = elem.items()\r
- if items or namespaces:\r
- if namespaces:\r
- for v, k in sorted(namespaces.items(),\r
- key=lambda x: x[1]): # sort on prefix\r
- if k:\r
- k = ":" + k\r
- write(" xmlns%s=\"%s\"" % (\r
- k.encode(encoding),\r
- _escape_attrib(v, encoding)\r
- ))\r
- for k, v in sorted(items): # lexical order\r
- if isinstance(k, QName):\r
- k = k.text\r
- if isinstance(v, QName):\r
- v = qnames[v.text]\r
- else:\r
- v = _escape_attrib_html(v, encoding)\r
- # FIXME: handle boolean attributes\r
- write(" %s=\"%s\"" % (qnames[k], v))\r
- write(">")\r
- ltag = tag.lower()\r
- if text:\r
- if ltag == "script" or ltag == "style":\r
- write(_encode(text, encoding))\r
- else:\r
- write(_escape_cdata(text, encoding))\r
- for e in elem:\r
- _serialize_html(write, e, encoding, qnames, None)\r
- if ltag not in HTML_EMPTY:\r
- write("</" + tag + ">")\r
- if elem.tail:\r
- write(_escape_cdata(elem.tail, encoding))\r
-\r
-def _serialize_text(write, elem, encoding):\r
- for part in elem.itertext():\r
- write(part.encode(encoding))\r
- if elem.tail:\r
- write(elem.tail.encode(encoding))\r
-\r
-_serialize = {\r
- "xml": _serialize_xml,\r
- "html": _serialize_html,\r
- "text": _serialize_text,\r
-# this optional method is imported at the end of the module\r
-# "c14n": _serialize_c14n,\r
-}\r
-\r
-##\r
-# Registers a namespace prefix. The registry is global, and any\r
-# existing mapping for either the given prefix or the namespace URI\r
-# will be removed.\r
-#\r
-# @param prefix Namespace prefix.\r
-# @param uri Namespace uri. Tags and attributes in this namespace\r
-# will be serialized with the given prefix, if at all possible.\r
-# @exception ValueError If the prefix is reserved, or is otherwise\r
-# invalid.\r
-\r
-def register_namespace(prefix, uri):\r
- if re.match("ns\d+$", prefix):\r
- raise ValueError("Prefix format reserved for internal use")\r
- for k, v in _namespace_map.items():\r
- if k == uri or v == prefix:\r
- del _namespace_map[k]\r
- _namespace_map[uri] = prefix\r
-\r
-_namespace_map = {\r
- # "well-known" namespace prefixes\r
- "http://www.w3.org/XML/1998/namespace": "xml",\r
- "http://www.w3.org/1999/xhtml": "html",\r
- "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",\r
- "http://schemas.xmlsoap.org/wsdl/": "wsdl",\r
- # xml schema\r
- "http://www.w3.org/2001/XMLSchema": "xs",\r
- "http://www.w3.org/2001/XMLSchema-instance": "xsi",\r
- # dublin core\r
- "http://purl.org/dc/elements/1.1/": "dc",\r
-}\r
-\r
-def _raise_serialization_error(text):\r
- raise TypeError(\r
- "cannot serialize %r (type %s)" % (text, type(text).__name__)\r
- )\r
-\r
-def _encode(text, encoding):\r
- try:\r
- return text.encode(encoding, "xmlcharrefreplace")\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-def _escape_cdata(text, encoding):\r
- # escape character data\r
- try:\r
- # it's worth avoiding do-nothing calls for strings that are\r
- # shorter than 500 character, or so. assume that's, by far,\r
- # the most common case in most applications.\r
- if "&" in text:\r
- text = text.replace("&", "&")\r
- if "<" in text:\r
- text = text.replace("<", "<")\r
- if ">" in text:\r
- text = text.replace(">", ">")\r
- return text.encode(encoding, "xmlcharrefreplace")\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-def _escape_attrib(text, encoding):\r
- # escape attribute value\r
- try:\r
- if "&" in text:\r
- text = text.replace("&", "&")\r
- if "<" in text:\r
- text = text.replace("<", "<")\r
- if ">" in text:\r
- text = text.replace(">", ">")\r
- if "\"" in text:\r
- text = text.replace("\"", """)\r
- if "\n" in text:\r
- text = text.replace("\n", " ")\r
- return text.encode(encoding, "xmlcharrefreplace")\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-def _escape_attrib_html(text, encoding):\r
- # escape attribute value\r
- try:\r
- if "&" in text:\r
- text = text.replace("&", "&")\r
- if ">" in text:\r
- text = text.replace(">", ">")\r
- if "\"" in text:\r
- text = text.replace("\"", """)\r
- return text.encode(encoding, "xmlcharrefreplace")\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-# --------------------------------------------------------------------\r
-\r
-##\r
-# Generates a string representation of an XML element, including all\r
-# subelements.\r
-#\r
-# @param element An Element instance.\r
-# @keyparam encoding Optional output encoding (default is US-ASCII).\r
-# @keyparam method Optional output method ("xml", "html", "text" or\r
-# "c14n"; default is "xml").\r
-# @return An encoded string containing the XML data.\r
-# @defreturn string\r
-\r
-def tostring(element, encoding=None, method=None):\r
- class dummy:\r
- pass\r
- data = []\r
- file = dummy()\r
- file.write = data.append\r
- ElementTree(element).write(file, encoding, method=method)\r
- return "".join(data)\r
-\r
-##\r
-# Generates a string representation of an XML element, including all\r
-# subelements. The string is returned as a sequence of string fragments.\r
-#\r
-# @param element An Element instance.\r
-# @keyparam encoding Optional output encoding (default is US-ASCII).\r
-# @keyparam method Optional output method ("xml", "html", "text" or\r
-# "c14n"; default is "xml").\r
-# @return A sequence object containing the XML data.\r
-# @defreturn sequence\r
-# @since 1.3\r
-\r
-def tostringlist(element, encoding=None, method=None):\r
- class dummy:\r
- pass\r
- data = []\r
- file = dummy()\r
- file.write = data.append\r
- ElementTree(element).write(file, encoding, method=method)\r
- # FIXME: merge small fragments into larger parts\r
- return data\r
-\r
-##\r
-# Writes an element tree or element structure to sys.stdout. This\r
-# function should be used for debugging only.\r
-# <p>\r
-# The exact output format is implementation dependent. In this\r
-# version, it's written as an ordinary XML file.\r
-#\r
-# @param elem An element tree or an individual element.\r
-\r
-def dump(elem):\r
- # debugging\r
- if not isinstance(elem, ElementTree):\r
- elem = ElementTree(elem)\r
- elem.write(sys.stdout)\r
- tail = elem.getroot().tail\r
- if not tail or tail[-1] != "\n":\r
- sys.stdout.write("\n")\r
-\r
-# --------------------------------------------------------------------\r
-# parsing\r
-\r
-##\r
-# Parses an XML document into an element tree.\r
-#\r
-# @param source A filename or file object containing XML data.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLParser} parser is used.\r
-# @return An ElementTree instance\r
-\r
-def parse(source, parser=None):\r
- tree = ElementTree()\r
- tree.parse(source, parser)\r
- return tree\r
-\r
-##\r
-# Parses an XML document into an element tree incrementally, and reports\r
-# what's going on to the user.\r
-#\r
-# @param source A filename or file object containing XML data.\r
-# @param events A list of events to report back. If omitted, only "end"\r
-# events are reported.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLParser} parser is used.\r
-# @return A (event, elem) iterator.\r
-\r
-def iterparse(source, events=None, parser=None):\r
- close_source = False\r
- if not hasattr(source, "read"):\r
- source = open(source, "rb")\r
- close_source = True\r
- if not parser:\r
- parser = XMLParser(target=TreeBuilder())\r
- return _IterParseIterator(source, events, parser, close_source)\r
-\r
-class _IterParseIterator(object):\r
-\r
- def __init__(self, source, events, parser, close_source=False):\r
- self._file = source\r
- self._close_file = close_source\r
- self._events = []\r
- self._index = 0\r
- self._error = None\r
- self.root = self._root = None\r
- self._parser = parser\r
- # wire up the parser for event reporting\r
- parser = self._parser._parser\r
- append = self._events.append\r
- if events is None:\r
- events = ["end"]\r
- for event in events:\r
- if event == "start":\r
- try:\r
- parser.ordered_attributes = 1\r
- parser.specified_attributes = 1\r
- def handler(tag, attrib_in, event=event, append=append,\r
- start=self._parser._start_list):\r
- append((event, start(tag, attrib_in)))\r
- parser.StartElementHandler = handler\r
- except AttributeError:\r
- def handler(tag, attrib_in, event=event, append=append,\r
- start=self._parser._start):\r
- append((event, start(tag, attrib_in)))\r
- parser.StartElementHandler = handler\r
- elif event == "end":\r
- def handler(tag, event=event, append=append,\r
- end=self._parser._end):\r
- append((event, end(tag)))\r
- parser.EndElementHandler = handler\r
- elif event == "start-ns":\r
- def handler(prefix, uri, event=event, append=append):\r
- try:\r
- uri = (uri or "").encode("ascii")\r
- except UnicodeError:\r
- pass\r
- append((event, (prefix or "", uri or "")))\r
- parser.StartNamespaceDeclHandler = handler\r
- elif event == "end-ns":\r
- def handler(prefix, event=event, append=append):\r
- append((event, None))\r
- parser.EndNamespaceDeclHandler = handler\r
- else:\r
- raise ValueError("unknown event %r" % event)\r
-\r
- def next(self):\r
- while 1:\r
- try:\r
- item = self._events[self._index]\r
- self._index += 1\r
- return item\r
- except IndexError:\r
- pass\r
- if self._error:\r
- e = self._error\r
- self._error = None\r
- raise e\r
- if self._parser is None:\r
- self.root = self._root\r
- if self._close_file:\r
- self._file.close()\r
- raise StopIteration\r
- # load event buffer\r
- del self._events[:]\r
- self._index = 0\r
- data = self._file.read(16384)\r
- if data:\r
- try:\r
- self._parser.feed(data)\r
- except SyntaxError as exc:\r
- self._error = exc\r
- else:\r
- self._root = self._parser.close()\r
- self._parser = None\r
-\r
- def __iter__(self):\r
- return self\r
-\r
-##\r
-# Parses an XML document from a string constant. This function can\r
-# be used to embed "XML literals" in Python code.\r
-#\r
-# @param source A string containing XML data.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLParser} parser is used.\r
-# @return An Element instance.\r
-# @defreturn Element\r
-\r
-def XML(text, parser=None):\r
- if not parser:\r
- parser = XMLParser(target=TreeBuilder())\r
- parser.feed(text)\r
- return parser.close()\r
-\r
-##\r
-# Parses an XML document from a string constant, and also returns\r
-# a dictionary which maps from element id:s to elements.\r
-#\r
-# @param source A string containing XML data.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLParser} parser is used.\r
-# @return A tuple containing an Element instance and a dictionary.\r
-# @defreturn (Element, dictionary)\r
-\r
-def XMLID(text, parser=None):\r
- if not parser:\r
- parser = XMLParser(target=TreeBuilder())\r
- parser.feed(text)\r
- tree = parser.close()\r
- ids = {}\r
- for elem in tree.iter():\r
- id = elem.get("id")\r
- if id:\r
- ids[id] = elem\r
- return tree, ids\r
-\r
-##\r
-# Parses an XML document from a string constant. Same as {@link #XML}.\r
-#\r
-# @def fromstring(text)\r
-# @param source A string containing XML data.\r
-# @return An Element instance.\r
-# @defreturn Element\r
-\r
-fromstring = XML\r
-\r
-##\r
-# Parses an XML document from a sequence of string fragments.\r
-#\r
-# @param sequence A list or other sequence containing XML data fragments.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLParser} parser is used.\r
-# @return An Element instance.\r
-# @defreturn Element\r
-# @since 1.3\r
-\r
-def fromstringlist(sequence, parser=None):\r
- if not parser:\r
- parser = XMLParser(target=TreeBuilder())\r
- for text in sequence:\r
- parser.feed(text)\r
- return parser.close()\r
-\r
-# --------------------------------------------------------------------\r
-\r
-##\r
-# Generic element structure builder. This builder converts a sequence\r
-# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link\r
-# #TreeBuilder.end} method calls to a well-formed element structure.\r
-# <p>\r
-# You can use this class to build an element structure using a custom XML\r
-# parser, or a parser for some other XML-like format.\r
-#\r
-# @param element_factory Optional element factory. This factory\r
-# is called to create new Element instances, as necessary.\r
-\r
-class TreeBuilder(object):\r
-\r
- def __init__(self, element_factory=None):\r
- self._data = [] # data collector\r
- self._elem = [] # element stack\r
- self._last = None # last element\r
- self._tail = None # true if we're after an end tag\r
- if element_factory is None:\r
- element_factory = Element\r
- self._factory = element_factory\r
-\r
- ##\r
- # Flushes the builder buffers, and returns the toplevel document\r
- # element.\r
- #\r
- # @return An Element instance.\r
- # @defreturn Element\r
-\r
- def close(self):\r
- assert len(self._elem) == 0, "missing end tags"\r
- assert self._last is not None, "missing toplevel element"\r
- return self._last\r
-\r
- def _flush(self):\r
- if self._data:\r
- if self._last is not None:\r
- text = "".join(self._data)\r
- if self._tail:\r
- assert self._last.tail is None, "internal error (tail)"\r
- self._last.tail = text\r
- else:\r
- assert self._last.text is None, "internal error (text)"\r
- self._last.text = text\r
- self._data = []\r
-\r
- ##\r
- # Adds text to the current element.\r
- #\r
- # @param data A string. This should be either an 8-bit string\r
- # containing ASCII text, or a Unicode string.\r
-\r
- def data(self, data):\r
- self._data.append(data)\r
-\r
- ##\r
- # Opens a new element.\r
- #\r
- # @param tag The element name.\r
- # @param attrib A dictionary containing element attributes.\r
- # @return The opened element.\r
- # @defreturn Element\r
-\r
- def start(self, tag, attrs):\r
- self._flush()\r
- self._last = elem = self._factory(tag, attrs)\r
- if self._elem:\r
- self._elem[-1].append(elem)\r
- self._elem.append(elem)\r
- self._tail = 0\r
- return elem\r
-\r
- ##\r
- # Closes the current element.\r
- #\r
- # @param tag The element name.\r
- # @return The closed element.\r
- # @defreturn Element\r
-\r
- def end(self, tag):\r
- self._flush()\r
- self._last = self._elem.pop()\r
- assert self._last.tag == tag,\\r
- "end tag mismatch (expected %s, got %s)" % (\r
- self._last.tag, tag)\r
- self._tail = 1\r
- return self._last\r
-\r
-##\r
-# Element structure builder for XML source data, based on the\r
-# <b>expat</b> parser.\r
-#\r
-# @keyparam target Target object. If omitted, the builder uses an\r
-# instance of the standard {@link #TreeBuilder} class.\r
-# @keyparam html Predefine HTML entities. This flag is not supported\r
-# by the current implementation.\r
-# @keyparam encoding Optional encoding. If given, the value overrides\r
-# the encoding specified in the XML file.\r
-# @see #ElementTree\r
-# @see #TreeBuilder\r
-\r
-class XMLParser(object):\r
-\r
- def __init__(self, html=0, target=None, encoding=None):\r
- try:\r
- from xml.parsers import expat\r
- except ImportError:\r
- try:\r
- import pyexpat as expat\r
- except ImportError:\r
- raise ImportError(\r
- "No module named expat; use SimpleXMLTreeBuilder instead"\r
- )\r
- parser = expat.ParserCreate(encoding, "}")\r
- if target is None:\r
- target = TreeBuilder()\r
- # underscored names are provided for compatibility only\r
- self.parser = self._parser = parser\r
- self.target = self._target = target\r
- self._error = expat.error\r
- self._names = {} # name memo cache\r
- # callbacks\r
- parser.DefaultHandlerExpand = self._default\r
- parser.StartElementHandler = self._start\r
- parser.EndElementHandler = self._end\r
- parser.CharacterDataHandler = self._data\r
- # optional callbacks\r
- parser.CommentHandler = self._comment\r
- parser.ProcessingInstructionHandler = self._pi\r
- # let expat do the buffering, if supported\r
- try:\r
- self._parser.buffer_text = 1\r
- except AttributeError:\r
- pass\r
- # use new-style attribute handling, if supported\r
- try:\r
- self._parser.ordered_attributes = 1\r
- self._parser.specified_attributes = 1\r
- parser.StartElementHandler = self._start_list\r
- except AttributeError:\r
- pass\r
- self._doctype = None\r
- self.entity = {}\r
- try:\r
- self.version = "Expat %d.%d.%d" % expat.version_info\r
- except AttributeError:\r
- pass # unknown\r
-\r
- def _raiseerror(self, value):\r
- err = ParseError(value)\r
- err.code = value.code\r
- err.position = value.lineno, value.offset\r
- raise err\r
-\r
- def _fixtext(self, text):\r
- # convert text string to ascii, if possible\r
- try:\r
- return text.encode("ascii")\r
- except UnicodeError:\r
- return text\r
-\r
- def _fixname(self, key):\r
- # expand qname, and convert name string to ascii, if possible\r
- try:\r
- name = self._names[key]\r
- except KeyError:\r
- name = key\r
- if "}" in name:\r
- name = "{" + name\r
- self._names[key] = name = self._fixtext(name)\r
- return name\r
-\r
- def _start(self, tag, attrib_in):\r
- fixname = self._fixname\r
- fixtext = self._fixtext\r
- tag = fixname(tag)\r
- attrib = {}\r
- for key, value in attrib_in.items():\r
- attrib[fixname(key)] = fixtext(value)\r
- return self.target.start(tag, attrib)\r
-\r
- def _start_list(self, tag, attrib_in):\r
- fixname = self._fixname\r
- fixtext = self._fixtext\r
- tag = fixname(tag)\r
- attrib = {}\r
- if attrib_in:\r
- for i in range(0, len(attrib_in), 2):\r
- attrib[fixname(attrib_in[i])] = fixtext(attrib_in[i+1])\r
- return self.target.start(tag, attrib)\r
-\r
- def _data(self, text):\r
- return self.target.data(self._fixtext(text))\r
-\r
- def _end(self, tag):\r
- return self.target.end(self._fixname(tag))\r
-\r
- def _comment(self, data):\r
- try:\r
- comment = self.target.comment\r
- except AttributeError:\r
- pass\r
- else:\r
- return comment(self._fixtext(data))\r
-\r
- def _pi(self, target, data):\r
- try:\r
- pi = self.target.pi\r
- except AttributeError:\r
- pass\r
- else:\r
- return pi(self._fixtext(target), self._fixtext(data))\r
-\r
- def _default(self, text):\r
- prefix = text[:1]\r
- if prefix == "&":\r
- # deal with undefined entities\r
- try:\r
- self.target.data(self.entity[text[1:-1]])\r
- except KeyError:\r
- from xml.parsers import expat\r
- err = expat.error(\r
- "undefined entity %s: line %d, column %d" %\r
- (text, self._parser.ErrorLineNumber,\r
- self._parser.ErrorColumnNumber)\r
- )\r
- err.code = 11 # XML_ERROR_UNDEFINED_ENTITY\r
- err.lineno = self._parser.ErrorLineNumber\r
- err.offset = self._parser.ErrorColumnNumber\r
- raise err\r
- elif prefix == "<" and text[:9] == "<!DOCTYPE":\r
- self._doctype = [] # inside a doctype declaration\r
- elif self._doctype is not None:\r
- # parse doctype contents\r
- if prefix == ">":\r
- self._doctype = None\r
- return\r
- text = text.strip()\r
- if not text:\r
- return\r
- self._doctype.append(text)\r
- n = len(self._doctype)\r
- if n > 2:\r
- type = self._doctype[1]\r
- if type == "PUBLIC" and n == 4:\r
- name, type, pubid, system = self._doctype\r
- elif type == "SYSTEM" and n == 3:\r
- name, type, system = self._doctype\r
- pubid = None\r
- else:\r
- return\r
- if pubid:\r
- pubid = pubid[1:-1]\r
- if hasattr(self.target, "doctype"):\r
- self.target.doctype(name, pubid, system[1:-1])\r
- elif self.doctype is not self._XMLParser__doctype:\r
- # warn about deprecated call\r
- self._XMLParser__doctype(name, pubid, system[1:-1])\r
- self.doctype(name, pubid, system[1:-1])\r
- self._doctype = None\r
-\r
- ##\r
- # (Deprecated) Handles a doctype declaration.\r
- #\r
- # @param name Doctype name.\r
- # @param pubid Public identifier.\r
- # @param system System identifier.\r
-\r
- def doctype(self, name, pubid, system):\r
- """This method of XMLParser is deprecated."""\r
- warnings.warn(\r
- "This method of XMLParser is deprecated. Define doctype() "\r
- "method on the TreeBuilder target.",\r
- DeprecationWarning,\r
- )\r
-\r
- # sentinel, if doctype is redefined in a subclass\r
- __doctype = doctype\r
-\r
- ##\r
- # Feeds data to the parser.\r
- #\r
- # @param data Encoded data.\r
-\r
- def feed(self, data):\r
- try:\r
- self._parser.Parse(data, 0)\r
- except self._error, v:\r
- self._raiseerror(v)\r
-\r
- ##\r
- # Finishes feeding data to the parser.\r
- #\r
- # @return An element structure.\r
- # @defreturn Element\r
-\r
- def close(self):\r
- try:\r
- self._parser.Parse("", 1) # end of data\r
- except self._error, v:\r
- self._raiseerror(v)\r
- tree = self.target.close()\r
- del self.target, self._parser # get rid of circular references\r
- return tree\r
-\r
-# compatibility\r
-XMLTreeBuilder = XMLParser\r
-\r
-# workaround circular import.\r
-try:\r
- from ElementC14N import _serialize_c14n\r
- _serialize["c14n"] = _serialize_c14n\r
-except ImportError:\r
- pass\r
projects / mirror_edk2.git / blobdiff