summaryrefslogtreecommitdiff
path: root/Lib/xml/etree
diff options
context:
space:
mode:
authorBenjamin Peterson <benjamin@python.org>2014-03-15 12:21:47 -0500
committerBenjamin Peterson <benjamin@python.org>2014-03-15 12:21:47 -0500
commitafe58888980f88d8cbcfdd6f97bf849850dcf17e (patch)
tree9fe2ca3bc2937f5232740a402b4dbde31855607f /Lib/xml/etree
parent54ac1ddd428350cbad5f4300bf94dedb75488ec8 (diff)
parentc4e5497ec6fe913bd00e318a828486c2efb20798 (diff)
downloadcpython-afe58888980f88d8cbcfdd6f97bf849850dcf17e.tar.gz
merge 3.3
Diffstat (limited to 'Lib/xml/etree')
-rw-r--r--Lib/xml/etree/ElementInclude.py6
-rw-r--r--Lib/xml/etree/ElementPath.py15
-rw-r--r--Lib/xml/etree/ElementTree.py1431
3 files changed, 658 insertions, 794 deletions
diff --git a/Lib/xml/etree/ElementInclude.py b/Lib/xml/etree/ElementInclude.py
index 71eeb05a6e..963470e3b1 100644
--- a/Lib/xml/etree/ElementInclude.py
+++ b/Lib/xml/etree/ElementInclude.py
@@ -71,8 +71,8 @@ class FatalIncludeError(SyntaxError):
# @return The expanded resource. If the parse mode is "xml", this
# is an ElementTree instance. If the parse mode is "text", this
# is a Unicode string. If the loader fails, it can return None
-# or raise an IOError exception.
-# @throws IOError If the loader fails to load the resource.
+# or raise an OSError exception.
+# @throws OSError If the loader fails to load the resource.
def default_loader(href, parse, encoding=None):
if parse == "xml":
@@ -94,7 +94,7 @@ def default_loader(href, parse, encoding=None):
# that implements the same interface as <b>default_loader</b>.
# @throws FatalIncludeError If the function fails to include a given
# resource, or if the tree contains malformed XInclude elements.
-# @throws IOError If the function fails to load a given resource.
+# @throws OSError If the function fails to load a given resource.
def include(elem, loader=None):
if loader is None:
diff --git a/Lib/xml/etree/ElementPath.py b/Lib/xml/etree/ElementPath.py
index e7015c7c61..d914ddb672 100644
--- a/Lib/xml/etree/ElementPath.py
+++ b/Lib/xml/etree/ElementPath.py
@@ -105,14 +105,12 @@ def prepare_child(next, token):
def prepare_star(next, token):
def select(context, result):
for elem in result:
- for e in elem:
- yield e
+ yield from elem
return select
def prepare_self(next, token):
def select(context, result):
- for elem in result:
- yield elem
+ yield from result
return select
def prepare_descendant(next, token):
@@ -176,7 +174,7 @@ def prepare_predicate(next, token):
if elem.get(key) == value:
yield elem
return select
- if signature == "-" and not re.match("\d+$", predicate[0]):
+ if signature == "-" and not re.match("\-?\d+$", predicate[0]):
# [tag]
tag = predicate[0]
def select(context, result):
@@ -184,7 +182,7 @@ def prepare_predicate(next, token):
if elem.find(tag) is not None:
yield elem
return select
- if signature == "-='" and not re.match("\d+$", predicate[0]):
+ if signature == "-='" and not re.match("\-?\d+$", predicate[0]):
# [tag='value']
tag = predicate[0]
value = predicate[-1]
@@ -198,7 +196,10 @@ def prepare_predicate(next, token):
if signature == "-" or signature == "-()" or signature == "-()-":
# [index] or [last()] or [last()-index]
if signature == "-":
+ # [index]
index = int(predicate[0]) - 1
+ if index < 0:
+ raise SyntaxError("XPath position >= 1 expected")
else:
if predicate[0] != "last":
raise SyntaxError("unsupported function")
@@ -207,6 +208,8 @@ def prepare_predicate(next, token):
index = int(predicate[2]) - 1
except ValueError:
raise SyntaxError("unsupported expression")
+ if index > -2:
+ raise SyntaxError("XPath offset from last() must be negative")
else:
index = -1
def select(context, result):
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
index a8e57295c6..d9e98078c8 100644
--- a/Lib/xml/etree/ElementTree.py
+++ b/Lib/xml/etree/ElementTree.py
@@ -1,28 +1,47 @@
+"""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
-# $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
#
@@ -51,9 +70,6 @@
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
-# Licensed to PSF under a Contributor Agreement.
-# See http://www.python.org/psf/license for licensing details.
-
__all__ = [
# public symbols
"Comment",
@@ -69,34 +85,12 @@ __all__ = [
"TreeBuilder",
"VERSION",
"XML", "XMLID",
- "XMLParser", "XMLTreeBuilder",
+ "XMLParser",
"register_namespace",
]
VERSION = "1.3.0"
-##
-# The <b>Element</b> type is a flexible container object, designed to
-# store hierarchical data structures in memory. The type can be
-# described as a cross between a list and a dictionary.
-# <p>
-# Each element has a number of properties associated with it:
-# <ul>
-# <li>a <i>tag</i>. This is a string identifying what kind of data
-# this element represents (the element type, in other words).</li>
-# <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>
-# <li>a <i>text</i> string.</li>
-# <li>an optional <i>tail</i> string.</li>
-# <li>a number of <i>child elements</i>, stored in a Python sequence</li>
-# </ul>
-#
-# To create an element instance, use the {@link #Element} constructor
-# or the {@link #SubElement} factory function.
-# <p>
-# 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
@@ -106,81 +100,68 @@ import contextlib
from . import ElementPath
-##
-# Parser error. This is a subclass of <b>SyntaxError</b>.
-# <p>
-# In addition to the exception value, an exception instance contains a
-# specific exception code in the <b>code</b> attribute, and the line and
-# column of the error in the <b>position</b> attribute.
-
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
# --------------------------------------------------------------------
-##
-# Checks if an object appears to be a valid element object.
-#
-# @param An element instance.
-# @return A true value if this is an element object.
-# @defreturn flag
def iselement(element):
- # FIXME: not sure about this;
- # isinstance(element, Element) or look for tag/attrib/text attributes
+ """Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
-##
-# Element class. This class defines the Element interface, and
-# provides a reference implementation of this interface.
-# <p>
-# 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:
- # <tag attrib>text<child/>...</tag>tail
+ """An XML element.
- ##
- # (Attribute) Element tag.
+ This class is the reference implementation of the Element interface.
- tag = None
+ An element's length is its number of subelements. That means if you
+ you want to check if an element is truly empty, you should check BOTH
+ its length AND its text attribute.
- ##
- # (Attribute) Element attribute dictionary. Where possible, use
- # {@link #Element.get},
- # {@link #Element.set},
- # {@link #Element.keys}, and
- # {@link #Element.items} to access
- # element attributes.
+ The element tag, attribute names, and attribute values can be either
+ bytes or strings.
- attrib = None
+ *tag* is the element name. *attrib* is an optional dictionary containing
+ element attributes. *extra* are additional element attributes given as
+ keyword arguments.
- ##
- # (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.
+ Example form:
+ <tag attrib>text<child/>...</tag>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.
- ##
- # (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
+ 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.
- # constructor
+ """
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
@@ -195,36 +176,30 @@ class Element:
def __repr__(self):
return "<Element %s at 0x%x>" % (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)
+ """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.
- ##
- # (Experimental) Copies the current element. This creates a
- # shallow copy; subelements will be shared with the original tree.
- #
- # @return A new element instance.
+ """
+ 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
- ##
- # 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 <b>text</b> attribute.
- #
- # @return The number of subelements.
-
def __len__(self):
return len(self._children)
@@ -236,23 +211,9 @@ class Element:
)
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:
@@ -261,76 +222,62 @@ class Element:
# 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, subelement):
+ """Add *subelement* to the end of this element.
- def append(self, element):
- self._assert_is_element(element)
- self._children.append(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.
- ##
- # Appends subelements from a sequence.
- #
- # @param elements A sequence object with zero or more elements.
- # @since 1.3
+ """
+ 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)
- ##
- # Inserts a subelement at the given position in this element.
- #
- # @param index Where to insert the new subelement.
-
- def insert(self, index, element):
- self._assert_is_element(element)
- self._children.insert(index, 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):
+ if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
- ##
- # Removes a matching subelement. Unlike the <b>find</b> 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)
+ 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.
- ##
- # (Deprecated) Returns all subelements. The elements are returned
- # in document order.
- #
- # @return A list of subelements.
- # @defreturn list of Element instances
+ """
+ # 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.",
@@ -338,131 +285,128 @@ class Element:
)
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)
+ """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.
- ##
- # 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
+ 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):
- return ElementPath.findtext(self, path, default, namespaces)
+ """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.
- ##
- # 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
+ 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):
- return ElementPath.findall(self, path, namespaces)
+ """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.
- ##
- # 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
+ Returns list containing all matching elements in document order.
+
+ """
+ return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
- return ElementPath.iterfind(self, path, namespaces)
+ """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.
- ##
- # Resets an element. This function removes all subelements, clears
- # all attributes, and sets the <b>text</b> and <b>tail</b> attributes
- # to None.
+ 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
- ##
- # Gets an element attribute. Equivalent to <b>attrib.get</b>, 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)
+ """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.
- ##
- # Sets an element attribute. Equivalent to <b>attrib[key] = value</b>,
- # but some implementations may handle this a bit more efficiently.
- #
- # @param key What attribute to set.
- # @param value The attribute value.
+ 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):
- self.attrib[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.
- ##
- # Gets a list of attribute names. The names are returned in an
- # arbitrary order (just like for an ordinary Python dictionary).
- # Equivalent to <b>attrib.keys()</b>.
- #
- # @return A list of element attribute names.
- # @defreturn list of strings
+ """
+ self.attrib[key] = value
def keys(self):
- return self.attrib.keys()
+ """Get list of attribute names.
- ##
- # Gets element attributes, as a sequence. The attributes are
- # returned in an arbitrary order. Equivalent to <b>attrib.items()</b>.
- #
- # @return A list of (name, value) tuples for all attributes.
- # @defreturn list of (string, string) tuples
+ Names are returned in an arbitrary order, just like an ordinary
+ Python dict. Equivalent to attrib.keys()
+
+ """
+ return self.attrib.keys()
def items(self):
- return self.attrib.items()
+ """Get element attributes as a sequence.
+
+ The attributes are returned in arbitrary order. Equivalent to
+ attrib.items().
- ##
- # Creates a tree iterator. The iterator loops over this element
- # and all subelements, in document order, and returns all elements
- # with a matching tag.
- # <p>
- # If the tree structure is modified during iteration, 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
+ 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:
- for e in e.iter(tag):
- yield e
+ yield from e.iter(tag)
# compatibility
def getiterator(self, tag=None):
@@ -474,78 +418,67 @@ class Element:
)
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):
+ """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
if self.text:
yield self.text
for e in self:
- for s in e.itertext():
- yield s
+ yield from e.itertext()
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.
-# <p>
-# The element name, attribute names, and attribute values can be
-# either 8-bit ASCII strings or Unicode strings.
-#
-# @param parent The parent element.
-# @param tag The subelement name.
-# @param attrib An optional dictionary, containing element attributes.
-# @param **extra Additional attributes, given as keyword arguments.
-# @return An element instance.
-# @defreturn Element
def SubElement(parent, tag, attrib={}, **extra):
+ """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
-##
-# Comment element factory. This factory function creates a special
-# element that will be serialized as an XML comment by the standard
-# serializer.
-# <p>
-# The comment string can be either an 8-bit ASCII string or a Unicode
-# string.
-#
-# @param text A string containing the comment string.
-# @return An element instance, representing a comment.
-# @defreturn Element
def Comment(text=None):
+ """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
-##
-# 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):
+ """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:
@@ -554,17 +487,21 @@ def ProcessingInstruction(target, text=None):
PI = ProcessingInstruction
-##
-# QName wrapper. This can be used to wrap a QName attribute value, in
-# order to get proper namespace handling on output.
-#
-# @param text A string containing the QName value, in the form {uri}local,
-# or, if the tag argument is given, the URI part of a QName.
-# @param tag Optional tag. If given, the first argument is interpreted as
-# an URI, and this argument is interpreted as a local name.
-# @return An opaque object, representing the QName.
class QName:
+ """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)
@@ -602,63 +539,65 @@ class QName:
# --------------------------------------------------------------------
-##
-# 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:
+ """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)
- ##
- # Gets the root element for this tree.
- #
- # @return An element instance.
- # @defreturn Element
-
def getroot(self):
+ """Return root element of this tree."""
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):
+ """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
- ##
- # 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 <b>read(n)</b> 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):
+ """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 not parser:
- parser = XMLParser(target=TreeBuilder())
- while 1:
+ 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
@@ -669,15 +608,15 @@ class ElementTree:
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):
+ """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)
@@ -691,15 +630,17 @@ class ElementTree:
)
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):
+ """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
@@ -711,19 +652,17 @@ class ElementTree:
)
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):
+ """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
@@ -735,16 +674,17 @@ class ElementTree:
)
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):
+ """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
@@ -756,17 +696,17 @@ class ElementTree:
)
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):
+ """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
@@ -778,26 +718,35 @@ class ElementTree:
)
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).
- # Use "unicode" to return a Unicode string.
- # @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 or Unicode. 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,
encoding=None,
xml_declaration=None,
default_namespace=None,
- method=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:
@@ -825,7 +774,8 @@ class ElementTree:
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
- serialize(write, self._root, qnames, namespaces)
+ serialize(write, self._root, qnames, namespaces,
+ short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
@@ -947,7 +897,8 @@ def _namespaces(elem, default_namespace=None):
add_qname(text.text)
return qnames, namespaces
-def _serialize_xml(write, elem, qnames, namespaces):
+def _serialize_xml(write, elem, qnames, namespaces,
+ short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
@@ -960,7 +911,8 @@ def _serialize_xml(write, elem, qnames, namespaces):
if text:
write(_escape_cdata(text))
for e in elem:
- _serialize_xml(write, e, qnames, None)
+ _serialize_xml(write, e, qnames, None,
+ short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
@@ -982,12 +934,13 @@ def _serialize_xml(write, elem, qnames, namespaces):
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
- if text or len(elem):
+ 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)
+ _serialize_xml(write, e, qnames, None,
+ short_empty_elements=short_empty_elements)
write("</" + tag + ">")
else:
write(" />")
@@ -1002,7 +955,7 @@ try:
except NameError:
pass
-def _serialize_html(write, elem, qnames, namespaces):
+def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
@@ -1066,18 +1019,19 @@ _serialize = {
# "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):
+ """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("ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
@@ -1153,40 +1107,27 @@ def _escape_attrib_html(text):
# --------------------------------------------------------------------
-##
-# Generates a string representation of an XML element, including all
-# subelements. If encoding is "unicode", the return type is a string;
-# otherwise it is a bytes array.
-#
-# @param element An Element instance.
-# @keyparam encoding Optional output encoding (default is US-ASCII).
-# Use "unicode" to return a Unicode string.
-# @keyparam method Optional output method ("xml", "html", "text" or
-# "c14n"; default is "xml").
-# @return An (optionally) encoded string containing the XML data.
-# @defreturn string
-
-def tostring(element, encoding=None, method=None):
+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)
+ ElementTree(element).write(stream, encoding, method=method,
+ short_empty_elements=short_empty_elements)
return stream.getvalue()
-##
-# 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).
-# Use "unicode" to return a Unicode string.
-# @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
-
class _ListDataStream(io.BufferedIOBase):
- """ An auxiliary stream accumulating into a list reference
- """
+ """An auxiliary stream accumulating into a list reference."""
def __init__(self, lst):
self.lst = lst
@@ -1202,22 +1143,25 @@ class _ListDataStream(io.BufferedIOBase):
def tell(self):
return len(self.lst)
-def tostringlist(element, encoding=None, method=None):
+def tostringlist(element, encoding=None, method=None, *,
+ short_empty_elements=True):
lst = []
stream = _ListDataStream(lst)
- ElementTree(element).write(stream, encoding, method=method)
+ ElementTree(element).write(stream, encoding, method=method,
+ short_empty_elements=short_empty_elements)
return lst
-##
-# Writes an element tree or element structure to sys.stdout. This
-# function should be used for debugging only.
-# <p>
-# The exact output format is implementation dependent. In this
-# version, it's written as an ordinary XML file.
-#
-# @param elem An element tree or an individual element.
def dump(elem):
+ """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)
@@ -1229,144 +1173,169 @@ def dump(elem):
# --------------------------------------------------------------------
# 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):
+ """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
-##
-# 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):
+ """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.
+
+ """
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
- if not parser:
- parser = XMLParser(target=TreeBuilder())
return _IterParseIterator(source, events, parser, close_source)
+
+class 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.
+
+ # _elementtree.c expects a list, not a deque
+ self._events_queue = []
+ self._index = 0
+ 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 True:
+ index = self._index
+ try:
+ event = events[self._index]
+ # Avoid retaining references to past events
+ events[self._index] = None
+ except IndexError:
+ break
+ index += 1
+ # Compact the list in a O(1) amortized fashion
+ # As noted above, _elementree.c needs a list, not a deque
+ if index * 2 >= len(events):
+ events[:index] = []
+ self._index = 0
+ else:
+ self._index = index
+ if isinstance(event, Exception):
+ raise event
+ else:
+ yield event
+
+
class _IterParseIterator:
def __init__(self, source, events, parser, close_source=False):
+ # Use the internal, undocumented _parser argument for now; When the
+ # parser argument of iterparse is removed, this can be killed.
+ self._parser = XMLPullParser(events=events, _parser=parser)
self._file = source
self._close_file = close_source
- self._events = []
- self._index = 0
- self._error = None
self.root = self._root = None
- self._parser = parser
- # wire up the parser for event reporting
- parser = self._parser._parser
- append = self._events.append
- if events is None:
- events = ["end"]
- for event in events:
- if event == "start":
- try:
- parser.ordered_attributes = 1
- parser.specified_attributes = 1
- def handler(tag, attrib_in, event=event, append=append,
- start=self._parser._start_list):
- append((event, start(tag, attrib_in)))
- parser.StartElementHandler = handler
- except AttributeError:
- def handler(tag, attrib_in, event=event, append=append,
- start=self._parser._start):
- append((event, start(tag, attrib_in)))
- parser.StartElementHandler = handler
- elif event == "end":
- def handler(tag, event=event, append=append,
- end=self._parser._end):
- append((event, end(tag)))
- parser.EndElementHandler = handler
- elif event == "start-ns":
- def handler(prefix, uri, event=event, append=append):
- append((event, (prefix or "", uri or "")))
- parser.StartNamespaceDeclHandler = handler
- elif event == "end-ns":
- def handler(prefix, event=event, append=append):
- append((event, None))
- parser.EndNamespaceDeclHandler = handler
- else:
- raise ValueError("unknown event %r" % event)
def __next__(self):
while 1:
- try:
- item = self._events[self._index]
- self._index += 1
- return item
- except IndexError:
- pass
- if self._error:
- e = self._error
- self._error = None
- raise e
- if self._parser is None:
+ for event in self._parser.read_events():
+ return event
+ if self._parser._parser is None:
self.root = self._root
if self._close_file:
self._file.close()
raise StopIteration
# load event buffer
- del self._events[:]
- self._index = 0
- data = self._file.read(16384)
+ data = self._file.read(16 * 1024)
if data:
- try:
- self._parser.feed(data)
- except SyntaxError as exc:
- self._error = exc
+ self._parser.feed(data)
else:
- self._root = self._parser.close()
- self._parser = None
+ self._root = self._parser._close_and_return_root()
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):
+ """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()
-##
-# 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):
+ """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)
@@ -1378,27 +1347,18 @@ def XMLID(text, parser=None):
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
-
+# Parse XML document from string constant. Alias for XML().
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):
+ """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:
@@ -1407,19 +1367,20 @@ def fromstringlist(sequence, parser=None):
# --------------------------------------------------------------------
-##
-# Generic element structure builder. This builder converts a sequence
-# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link
-# #TreeBuilder.end} method calls to a well-formed element structure.
-# <p>
-# You can use this class to build an element structure using a custom XML
-# parser, or a parser for some other XML-like format.
-#
-# @param element_factory Optional element factory. This factory
-# is called to create new Element instances, as necessary.
class TreeBuilder:
+ """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
@@ -1429,14 +1390,8 @@ class TreeBuilder:
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):
+ """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
@@ -1453,24 +1408,17 @@ class TreeBuilder:
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):
+ """Add text to current element."""
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):
+ """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:
@@ -1479,14 +1427,12 @@ class TreeBuilder:
self._tail = 0
return elem
- ##
- # Closes the current element.
- #
- # @param tag The element name.
- # @return The closed element.
- # @defreturn Element
-
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,\
@@ -1495,20 +1441,18 @@ class TreeBuilder:
self._tail = 1
return self._last
-##
-# Element structure builder for XML source data, based on the
-# <b>expat</b> parser.
-#
-# @keyparam target Target object. If omitted, the builder uses an
-# instance of the standard {@link #TreeBuilder} class.
-# @keyparam html Predefine HTML entities. This flag is not supported
-# by the current implementation.
-# @keyparam encoding Optional encoding. If given, the value overrides
-# the encoding specified in the XML file.
-# @see #ElementTree
-# @see #TreeBuilder
+# also see ElementTree and TreeBuilder
class XMLParser:
+ """Element structure builder for XML source data based on the expat parser.
+
+ *html* are predefined HTML entities (not supported currently),
+ *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:
@@ -1541,19 +1485,10 @@ class XMLParser:
parser.CommentHandler = target.comment
if hasattr(target, 'pi'):
parser.ProcessingInstructionHandler = target.pi
- # let expat do the buffering, if supported
- try:
- parser.buffer_text = 1
- except AttributeError:
- pass
- # use new-style attribute handling, if supported
- try:
- parser.ordered_attributes = 1
- parser.specified_attributes = 1
- if hasattr(target, 'start'):
- parser.StartElementHandler = self._start_list
- except AttributeError:
- pass
+ # 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:
@@ -1561,6 +1496,39 @@ class XMLParser:
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
@@ -1578,21 +1546,16 @@ class XMLParser:
self._names[key] = name
return name
- def _start(self, tag, attrib_in):
+ 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 = {}
- for key, value in attrib_in.items():
- attrib[fixname(key)] = value
- return self.target.start(tag, attrib)
-
- def _start_list(self, tag, attrib_in):
- fixname = self._fixname
- tag = fixname(tag)
- attrib = {}
- if attrib_in:
- for i in range(0, len(attrib_in), 2):
- attrib[fixname(attrib_in[i])] = attrib_in[i+1]
+ 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):
@@ -1650,15 +1613,13 @@ class XMLParser:
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."""
+ """(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.",
@@ -1668,24 +1629,15 @@ class XMLParser:
# sentinel, if doctype is redefined in a subclass
__doctype = doctype
- ##
- # Feeds data to the parser.
- #
- # @param data Encoded data.
-
def feed(self, data):
+ """Feed encoded data to parser."""
try:
self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
- ##
- # Finishes feeding data to the parser.
- #
- # @return An element structure.
- # @defreturn Element
-
def close(self):
+ """Finish feeding data to parser and return element structure."""
try:
self.parser.Parse("", 1) # end of data
except self._error as v:
@@ -1704,103 +1656,12 @@ class XMLParser:
# 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
-else:
- # Overwrite 'ElementTree.parse' and 'iterparse' to use the C XMLParser
-
- class ElementTree(ElementTree):
- def parse(self, source, parser=None):
- close_source = False
- if not hasattr(source, 'read'):
- source = open(source, 'rb')
- close_source = True
- try:
- if parser is not None:
- while True:
- data = source.read(65536)
- if not data:
- break
- parser.feed(data)
- self._root = parser.close()
- else:
- parser = XMLParser()
- self._root = parser._parse(source)
- return self._root
- finally:
- if close_source:
- source.close()
-
- class iterparse:
- """Parses an XML section into an element tree incrementally.
-
- Reports what’s going on to the user. 'source' is a filename or file
- object containing XML data. 'events' is a list of events to report back.
- 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.
- 'parser' is an optional parser instance. If not given, the standard
- XMLParser parser is used. Returns an iterator providing
- (event, elem) pairs.
- """
-
- root = None
- def __init__(self, file, events=None, parser=None):
- self._close_file = False
- if not hasattr(file, 'read'):
- file = open(file, 'rb')
- self._close_file = True
- self._file = file
- self._events = []
- self._index = 0
- self._error = None
- self.root = self._root = None
- if parser is None:
- parser = XMLParser(target=TreeBuilder())
- self._parser = parser
- self._parser._setevents(self._events, events)
-
- def __next__(self):
- while True:
- try:
- item = self._events[self._index]
- self._index += 1
- return item
- except IndexError:
- pass
- if self._error:
- e = self._error
- self._error = None
- raise e
- if self._parser is None:
- self.root = self._root
- if self._close_file:
- self._file.close()
- raise StopIteration
- # load event buffer
- del self._events[:]
- self._index = 0
- data = self._file.read(16384)
- if data:
- try:
- self._parser.feed(data)
- except SyntaxError as exc:
- self._error = exc
- else:
- self._root = self._parser.close()
- self._parser = None
-
- def __iter__(self):
- return self
-
-# compatibility
-XMLTreeBuilder = XMLParser
-
-# workaround circular import.
-try:
- from ElementC14N import _serialize_c14n
- _serialize["c14n"] = _serialize_c14n
-except ImportError:
- pass