Skip to content

C
cpython
Commit 9ed73060 authored by Armin Rigo's avatar Armin Rigo
Browse files
Options

Subversion settings: 

  svn:ignore *.pyc *.pyo
  svn:eol-style native

The .py files appear to have been checked in with Windows or inconsistent line
endings.  The current check-in disrupts the 'svn blame', but hopefully it is
irrelevant for freshly imported code.
parent 5c8cc254
Hide whitespace changes
Inline Side-by-side
Showing with 1960 additions and 1960 deletions
Lib/test/test_xml_etree.py
View file @ 9ed73060
# xmlcore.etree test. This file contains enough tests to make sure that
# all included components work as they should. For a more extensive
# test suite, see the selftest script in the ElementTree distribution.
import doctest, sys
from test import test_support
SAMPLE_XML = """
<body>
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
SAMPLE_XML_NS = """
<body xmlns="http://effbot.org/ns">
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
def sanity():
"""
Import sanity.
>>> from xmlcore.etree import ElementTree
>>> from xmlcore.etree import ElementInclude
>>> from xmlcore.etree import ElementPath
"""
def check_method(method):
if not callable(method):
print method, "not callable"
def serialize(ET, elem, encoding=None):
import StringIO
file = StringIO.StringIO()
tree = ET.ElementTree(elem)
if encoding:
tree.write(file, encoding)
else:
tree.write(file)
return file.getvalue()
def summarize(elem):
return elem.tag
def summarize_list(seq):
return map(summarize, seq)
def interface():
"""
Test element tree interface.
>>> from xmlcore.etree import ElementTree as ET
>>> element = ET.Element("tag", key="value")
>>> tree = ET.ElementTree(element)
Make sure all standard element methods exist.
>>> check_method(element.append)
>>> check_method(element.insert)
>>> check_method(element.remove)
>>> check_method(element.getchildren)
>>> check_method(element.find)
>>> check_method(element.findall)
>>> check_method(element.findtext)
>>> check_method(element.clear)
>>> check_method(element.get)
>>> check_method(element.set)
>>> check_method(element.keys)
>>> check_method(element.items)
>>> check_method(element.getiterator)
Basic method sanity checks.
>>> serialize(ET, element) # 1
'<tag key="value" />'
>>> subelement = ET.Element("subtag")
>>> element.append(subelement)
>>> serialize(ET, element) # 2
'<tag key="value"><subtag /></tag>'
>>> element.insert(0, subelement)
>>> serialize(ET, element) # 3
'<tag key="value"><subtag /><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 4
'<tag key="value"><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 5
'<tag key="value" />'
>>> element.remove(subelement)
Traceback (most recent call last):
ValueError: list.remove(x): x not in list
>>> serialize(ET, element) # 6
'<tag key="value" />'
"""
def find():
"""
Test find methods (including xpath syntax).
>>> from xmlcore.etree import ElementTree as ET
>>> elem = ET.XML(SAMPLE_XML)
>>> elem.find("tag").tag
'tag'
>>> ET.ElementTree(elem).find("tag").tag
'tag'
>>> elem.find("section/tag").tag
'tag'
>>> ET.ElementTree(elem).find("section/tag").tag
'tag'
>>> elem.findtext("tag")
'text'
>>> elem.findtext("tog")
>>> elem.findtext("tog", "default")
'default'
>>> ET.ElementTree(elem).findtext("tag")
'text'
>>> elem.findtext("section/tag")
'subtext'
>>> ET.ElementTree(elem).findtext("section/tag")
'subtext'
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("*"))
['tag', 'tag', 'section']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("section/tag"))
['tag']
>>> summarize_list(elem.findall("section//tag"))
['tag']
>>> summarize_list(elem.findall("section/*"))
['tag']
>>> summarize_list(elem.findall("section//*"))
['tag']
>>> summarize_list(elem.findall("section/.//*"))
['tag']
>>> summarize_list(elem.findall("*/*"))
['tag']
>>> summarize_list(elem.findall("*//*"))
['tag']
>>> summarize_list(elem.findall("*/tag"))
['tag']
>>> summarize_list(elem.findall("*/./tag"))
['tag']
>>> summarize_list(elem.findall("./tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("././tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("/tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("./tag"))
['tag', 'tag']
>>> elem = ET.XML(SAMPLE_XML_NS)
>>> summarize_list(elem.findall("tag"))
[]
>>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
>>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
"""
def parseliteral():
r"""
>>> from xmlcore.etree import ElementTree as ET
>>> element = ET.XML("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> element = ET.fromstring("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> print ET.tostring(element)
<html><body>text</body></html>
>>> print ET.tostring(element, "ascii")
<?xml version='1.0' encoding='ascii'?>
<html><body>text</body></html>
>>> _, ids = ET.XMLID("<html><body>text</body></html>")
>>> len(ids)
0
>>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
>>> len(ids)
1
>>> ids["body"].tag
'body'
"""
#
# xinclude tests (samples from appendix C of the xinclude specification)
XINCLUDE = {}
XINCLUDE["C1.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>120 Mz is adequate for an average home user.</p>
<xi:include href="disclaimer.xml"/>
</document>
"""
XINCLUDE["disclaimer.xml"] = """\
<?xml version='1.0'?>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
"""
XINCLUDE["C2.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>This document has been accessed
<xi:include href="count.txt" parse="text"/> times.</p>
</document>
"""
XINCLUDE["count.txt"] = "324387"
XINCLUDE["C3.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>The following is the source of the "data.xml" resource:</p>
<example><xi:include href="data.xml" parse="text"/></example>
</document>
"""
XINCLUDE["data.xml"] = """\
<?xml version='1.0'?>
<data>
<item><![CDATA[Brooks & Shields]]></item>
</data>
"""
XINCLUDE["C5.xml"] = """\
<?xml version='1.0'?>
<div xmlns:xi="http://www.w3.org/2001/XInclude">
<xi:include href="example.txt" parse="text">
<xi:fallback>
<xi:include href="fallback-example.txt" parse="text">
<xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>
</xi:include>
</xi:fallback>
</xi:include>
</div>
"""
XINCLUDE["default.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>Example.</p>
<xi:include href="samples/simple.xml"/>
</document>
"""
def xinclude_loader(href, parse="xml", encoding=None):
try:
data = XINCLUDE[href]
except KeyError:
raise IOError("resource not found")
if parse == "xml":
from xmlcore.etree.ElementTree import XML
return XML(data)
return data
def xinclude():
r"""
Basic inclusion example (XInclude C.1)
>>> from xmlcore.etree import ElementTree as ET
>>> from xmlcore.etree import ElementInclude
>>> document = xinclude_loader("C1.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C1
<document>
<p>120 Mz is adequate for an average home user.</p>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
</document>
Textual inclusion example (XInclude C.2)
>>> document = xinclude_loader("C2.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C2
<document>
<p>This document has been accessed
324387 times.</p>
</document>
Textual inclusion of XML example (XInclude C.3)
>>> document = xinclude_loader("C3.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C3
<document>
<p>The following is the source of the "data.xml" resource:</p>
<example>&lt;?xml version='1.0'?&gt;
&lt;data&gt;
&lt;item&gt;&lt;![CDATA[Brooks &amp; Shields]]&gt;&lt;/item&gt;
&lt;/data&gt;
</example>
</document>
Fallback example (XInclude C.5)
Note! Fallback support is not yet implemented
>>> document = xinclude_loader("C5.xml")
>>> ElementInclude.include(document, xinclude_loader)
Traceback (most recent call last):
IOError: resource not found
>>> # print serialize(ET, document) # C5
"""
def test_main():
from test import test_xml_etree
test_support.run_doctest(test_xml_etree, verbosity=True)
if __name__ == '__main__':
test_main()
# xmlcore.etree test. This file contains enough tests to make sure that
# all included components work as they should. For a more extensive
# test suite, see the selftest script in the ElementTree distribution.
import doctest, sys
from test import test_support
SAMPLE_XML = """
<body>
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
SAMPLE_XML_NS = """
<body xmlns="http://effbot.org/ns">
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
def sanity():
"""
Import sanity.
>>> from xmlcore.etree import ElementTree
>>> from xmlcore.etree import ElementInclude
>>> from xmlcore.etree import ElementPath
"""
def check_method(method):
if not callable(method):
print method, "not callable"
def serialize(ET, elem, encoding=None):
import StringIO
file = StringIO.StringIO()
tree = ET.ElementTree(elem)
if encoding:
tree.write(file, encoding)
else:
tree.write(file)
return file.getvalue()
def summarize(elem):
return elem.tag
def summarize_list(seq):
return map(summarize, seq)
def interface():
"""
Test element tree interface.
>>> from xmlcore.etree import ElementTree as ET
>>> element = ET.Element("tag", key="value")
>>> tree = ET.ElementTree(element)
Make sure all standard element methods exist.
>>> check_method(element.append)
>>> check_method(element.insert)
>>> check_method(element.remove)
>>> check_method(element.getchildren)
>>> check_method(element.find)
>>> check_method(element.findall)
>>> check_method(element.findtext)
>>> check_method(element.clear)
>>> check_method(element.get)
>>> check_method(element.set)
>>> check_method(element.keys)
>>> check_method(element.items)
>>> check_method(element.getiterator)
Basic method sanity checks.
>>> serialize(ET, element) # 1
'<tag key="value" />'
>>> subelement = ET.Element("subtag")
>>> element.append(subelement)
>>> serialize(ET, element) # 2
'<tag key="value"><subtag /></tag>'
>>> element.insert(0, subelement)
>>> serialize(ET, element) # 3
'<tag key="value"><subtag /><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 4
'<tag key="value"><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 5
'<tag key="value" />'
>>> element.remove(subelement)
Traceback (most recent call last):
ValueError: list.remove(x): x not in list
>>> serialize(ET, element) # 6
'<tag key="value" />'
"""
def find():
"""
Test find methods (including xpath syntax).
>>> from xmlcore.etree import ElementTree as ET
>>> elem = ET.XML(SAMPLE_XML)
>>> elem.find("tag").tag
'tag'
>>> ET.ElementTree(elem).find("tag").tag
'tag'
>>> elem.find("section/tag").tag
'tag'
>>> ET.ElementTree(elem).find("section/tag").tag
'tag'
>>> elem.findtext("tag")
'text'
>>> elem.findtext("tog")
>>> elem.findtext("tog", "default")
'default'
>>> ET.ElementTree(elem).findtext("tag")
'text'
>>> elem.findtext("section/tag")
'subtext'
>>> ET.ElementTree(elem).findtext("section/tag")
'subtext'
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("*"))
['tag', 'tag', 'section']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("section/tag"))
['tag']
>>> summarize_list(elem.findall("section//tag"))
['tag']
>>> summarize_list(elem.findall("section/*"))
['tag']
>>> summarize_list(elem.findall("section//*"))
['tag']
>>> summarize_list(elem.findall("section/.//*"))
['tag']
>>> summarize_list(elem.findall("*/*"))
['tag']
>>> summarize_list(elem.findall("*//*"))
['tag']
>>> summarize_list(elem.findall("*/tag"))
['tag']
>>> summarize_list(elem.findall("*/./tag"))
['tag']
>>> summarize_list(elem.findall("./tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("././tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("/tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("./tag"))
['tag', 'tag']
>>> elem = ET.XML(SAMPLE_XML_NS)
>>> summarize_list(elem.findall("tag"))
[]
>>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
>>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
"""
def parseliteral():
r"""
>>> from xmlcore.etree import ElementTree as ET
>>> element = ET.XML("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> element = ET.fromstring("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> print ET.tostring(element)
<html><body>text</body></html>
>>> print ET.tostring(element, "ascii")
<?xml version='1.0' encoding='ascii'?>
<html><body>text</body></html>
>>> _, ids = ET.XMLID("<html><body>text</body></html>")
>>> len(ids)
0
>>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
>>> len(ids)
1
>>> ids["body"].tag
'body'
"""
#
# xinclude tests (samples from appendix C of the xinclude specification)
XINCLUDE = {}
XINCLUDE["C1.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>120 Mz is adequate for an average home user.</p>
<xi:include href="disclaimer.xml"/>
</document>
"""
XINCLUDE["disclaimer.xml"] = """\
<?xml version='1.0'?>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
"""
XINCLUDE["C2.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>This document has been accessed
<xi:include href="count.txt" parse="text"/> times.</p>
</document>
"""
XINCLUDE["count.txt"] = "324387"
XINCLUDE["C3.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>The following is the source of the "data.xml" resource:</p>
<example><xi:include href="data.xml" parse="text"/></example>
</document>
"""
XINCLUDE["data.xml"] = """\
<?xml version='1.0'?>
<data>
<item><![CDATA[Brooks & Shields]]></item>
</data>
"""
XINCLUDE["C5.xml"] = """\
<?xml version='1.0'?>
<div xmlns:xi="http://www.w3.org/2001/XInclude">
<xi:include href="example.txt" parse="text">
<xi:fallback>
<xi:include href="fallback-example.txt" parse="text">
<xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>
</xi:include>
</xi:fallback>
</xi:include>
</div>
"""
XINCLUDE["default.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>Example.</p>
<xi:include href="samples/simple.xml"/>
</document>
"""
def xinclude_loader(href, parse="xml", encoding=None):
try:
data = XINCLUDE[href]
except KeyError:
raise IOError("resource not found")
if parse == "xml":
from xmlcore.etree.ElementTree import XML
return XML(data)
return data
def xinclude():
r"""
Basic inclusion example (XInclude C.1)
>>> from xmlcore.etree import ElementTree as ET
>>> from xmlcore.etree import ElementInclude
>>> document = xinclude_loader("C1.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C1
<document>
<p>120 Mz is adequate for an average home user.</p>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
</document>
Textual inclusion example (XInclude C.2)
>>> document = xinclude_loader("C2.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C2
<document>
<p>This document has been accessed
324387 times.</p>
</document>
Textual inclusion of XML example (XInclude C.3)
>>> document = xinclude_loader("C3.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print serialize(ET, document) # C3
<document>
<p>The following is the source of the "data.xml" resource:</p>
<example>&lt;?xml version='1.0'?&gt;
&lt;data&gt;
&lt;item&gt;&lt;![CDATA[Brooks &amp; Shields]]&gt;&lt;/item&gt;
&lt;/data&gt;
</example>
</document>
Fallback example (XInclude C.5)
Note! Fallback support is not yet implemented
>>> document = xinclude_loader("C5.xml")
>>> ElementInclude.include(document, xinclude_loader)
Traceback (most recent call last):
IOError: resource not found
>>> # print serialize(ET, document) # C5
"""
def test_main():
from test import test_xml_etree
test_support.run_doctest(test_xml_etree, verbosity=True)
if __name__ == '__main__':
test_main()
Lib/xmlcore/etree/ElementInclude.py
View file @ 9ed73060
#
# ElementTree
# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
#
# limited xinclude support for element trees
#
# history:
# 2003-08-15 fl created
# 2003-11-14 fl fixed default loader
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Limited XInclude support for the ElementTree package.
##
import copy
import ElementTree
XINCLUDE = "{http://www.w3.org/2001/XInclude}"
XINCLUDE_INCLUDE = XINCLUDE + "include"
XINCLUDE_FALLBACK = XINCLUDE + "fallback"
##
# Fatal include error.
class FatalIncludeError(SyntaxError):
pass
##
# Default loader. This loader reads an included resource from disk.
#
# @param href Resource reference.
# @param parse Parse mode. Either "xml" or "text".
# @param encoding Optional text encoding.
# @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.
def default_loader(href, parse, encoding=None):
file = open(href)
if parse == "xml":
data = ElementTree.parse(file).getroot()
else:
data = file.read()
if encoding:
data = data.decode(encoding)
file.close()
return data
##
# Expand XInclude directives.
#
# @param elem Root element.
# @param loader Optional resource loader. If omitted, it defaults
# to {@link default_loader}. If given, it should be a callable
# 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.
def include(elem, loader=None):
if loader is None:
loader = default_loader
# look for xinclude elements
i = 0
while i < len(elem):
e = elem[i]
if e.tag == XINCLUDE_INCLUDE:
# process xinclude directive
href = e.get("href")
parse = e.get("parse", "xml")
if parse == "xml":
node = loader(href, parse)
if node is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
node = copy.copy(node)
if e.tail:
node.tail = (node.tail or "") + e.tail
elem[i] = node
elif parse == "text":
text = loader(href, parse, e.get("encoding"))
if text is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
if i:
node = elem[i-1]
node.tail = (node.tail or "") + text
else:
elem.text = (elem.text or "") + text + (e.tail or "")
del elem[i]
continue
else:
raise FatalIncludeError(
"unknown parse type in xi:include tag (%r)" % parse
)
elif e.tag == XINCLUDE_FALLBACK:
raise FatalIncludeError(
"xi:fallback tag must be child of xi:include (%r)" % e.tag
)
else:
include(e, loader)
i = i + 1
#
# ElementTree
# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
#
# limited xinclude support for element trees
#
# history:
# 2003-08-15 fl created
# 2003-11-14 fl fixed default loader
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Limited XInclude support for the ElementTree package.
##
import copy
import ElementTree
XINCLUDE = "{http://www.w3.org/2001/XInclude}"
XINCLUDE_INCLUDE = XINCLUDE + "include"
XINCLUDE_FALLBACK = XINCLUDE + "fallback"
##
# Fatal include error.
class FatalIncludeError(SyntaxError):
pass
##
# Default loader. This loader reads an included resource from disk.
#
# @param href Resource reference.
# @param parse Parse mode. Either "xml" or "text".
# @param encoding Optional text encoding.
# @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.
def default_loader(href, parse, encoding=None):
file = open(href)
if parse == "xml":
data = ElementTree.parse(file).getroot()
else:
data = file.read()
if encoding:
data = data.decode(encoding)
file.close()
return data
##
# Expand XInclude directives.
#
# @param elem Root element.
# @param loader Optional resource loader. If omitted, it defaults
# to {@link default_loader}. If given, it should be a callable
# 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.
def include(elem, loader=None):
if loader is None:
loader = default_loader
# look for xinclude elements
i = 0
while i < len(elem):
e = elem[i]
if e.tag == XINCLUDE_INCLUDE:
# process xinclude directive
href = e.get("href")
parse = e.get("parse", "xml")
if parse == "xml":
node = loader(href, parse)
if node is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
node = copy.copy(node)
if e.tail:
node.tail = (node.tail or "") + e.tail
elem[i] = node
elif parse == "text":
text = loader(href, parse, e.get("encoding"))
if text is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
if i:
node = elem[i-1]
node.tail = (node.tail or "") + text
else:
elem.text = (elem.text or "") + text + (e.tail or "")
del elem[i]
continue
else:
raise FatalIncludeError(
"unknown parse type in xi:include tag (%r)" % parse
)
elif e.tag == XINCLUDE_FALLBACK:
raise FatalIncludeError(
"xi:fallback tag must be child of xi:include (%r)" % e.tag
)
else:
include(e, loader)
i = i + 1
Lib/xmlcore/etree/ElementPath.py
View file @ 9ed73060
#
# ElementTree
# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $
#
# limited xpath support for element trees
#
# history:
# 2003-05-23 fl created
# 2003-05-28 fl added support for // etc
# 2003-08-27 fl fixed parsing of periods in element names
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Implementation module for XPath support. There's usually no reason
# to import this module directly; the <b>ElementTree</b> does this for
# you, if needed.
##
import re
xpath_tokenizer = re.compile(
"(::|\.\.|\(\)|[/.*:\[\]\(\)@=])|((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|\s+"
).findall
class xpath_descendant_or_self:
pass
##
# Wrapper for a compiled XPath.
class Path:
##
# Create an Path instance from an XPath expression.
def __init__(self, path):
tokens = xpath_tokenizer(path)
# the current version supports 'path/path'-style expressions only
self.path = []
self.tag = None
if tokens and tokens[0][0] == "/":
raise SyntaxError("cannot use absolute path on element")
while tokens:
op, tag = tokens.pop(0)
if tag or op == "*":
self.path.append(tag or op)
elif op == ".":
pass
elif op == "/":
self.path.append(xpath_descendant_or_self())
continue
else:
raise SyntaxError("unsupported path syntax (%s)" % op)
if tokens:
op, tag = tokens.pop(0)
if op != "/":
raise SyntaxError(
"expected path separator (%s)" % (op or tag)
)
if self.path and isinstance(self.path[-1], xpath_descendant_or_self):
raise SyntaxError("path cannot end with //")
if len(self.path) == 1 and isinstance(self.path[0], type("")):
self.tag = self.path[0]
##
# Find first matching object.
def find(self, element):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return None
return nodeset[0]
for elem in element:
if elem.tag == tag:
return elem
return None
##
# Find text for first matching object.
def findtext(self, element, default=None):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return default
return nodeset[0].text or ""
for elem in element:
if elem.tag == tag:
return elem.text or ""
return default
##
# Find all matching objects.
def findall(self, element):
nodeset = [element]
index = 0
while 1:
try:
path = self.path[index]
index = index + 1
except IndexError:
return nodeset
set = []
if isinstance(path, xpath_descendant_or_self):
try:
tag = self.path[index]
if not isinstance(tag, type("")):
tag = None
else:
index = index + 1
except IndexError:
tag = None # invalid path
for node in nodeset:
new = list(node.getiterator(tag))
if new and new[0] is node:
set.extend(new[1:])
else:
set.extend(new)
else:
for node in nodeset:
for node in node:
if path == "*" or node.tag == path:
set.append(node)
if not set:
return []
nodeset = set
_cache = {}
##
# (Internal) Compile path.
def _compile(path):
p = _cache.get(path)
if p is not None:
return p
p = Path(path)
if len(_cache) >= 100:
_cache.clear()
_cache[path] = p
return p
##
# Find first matching object.
def find(element, path):
return _compile(path).find(element)
##
# Find text for first matching object.
def findtext(element, path, default=None):
return _compile(path).findtext(element, default)
##
# Find all matching objects.
def findall(element, path):
return _compile(path).findall(element)
#
# ElementTree
# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $
#
# limited xpath support for element trees
#
# history:
# 2003-05-23 fl created
# 2003-05-28 fl added support for // etc
# 2003-08-27 fl fixed parsing of periods in element names
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Implementation module for XPath support. There's usually no reason
# to import this module directly; the <b>ElementTree</b> does this for
# you, if needed.
##
import re
xpath_tokenizer = re.compile(
"(::|\.\.|\(\)|[/.*:\[\]\(\)@=])|((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|\s+"
).findall
class xpath_descendant_or_self:
pass
##
# Wrapper for a compiled XPath.
class Path:
##
# Create an Path instance from an XPath expression.
def __init__(self, path):
tokens = xpath_tokenizer(path)
# the current version supports 'path/path'-style expressions only
self.path = []
self.tag = None
if tokens and tokens[0][0] == "/":
raise SyntaxError("cannot use absolute path on element")
while tokens:
op, tag = tokens.pop(0)
if tag or op == "*":
self.path.append(tag or op)
elif op == ".":
pass
elif op == "/":
self.path.append(xpath_descendant_or_self())
continue
else:
raise SyntaxError("unsupported path syntax (%s)" % op)
if tokens:
op, tag = tokens.pop(0)
if op != "/":
raise SyntaxError(
"expected path separator (%s)" % (op or tag)
)
if self.path and isinstance(self.path[-1], xpath_descendant_or_self):
raise SyntaxError("path cannot end with //")
if len(self.path) == 1 and isinstance(self.path[0], type("")):
self.tag = self.path[0]
##
# Find first matching object.
def find(self, element):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return None
return nodeset[0]
for elem in element:
if elem.tag == tag:
return elem
return None
##
# Find text for first matching object.
def findtext(self, element, default=None):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return default
return nodeset[0].text or ""
for elem in element:
if elem.tag == tag:
return elem.text or ""
return default
##
# Find all matching objects.
def findall(self, element):
nodeset = [element]
index = 0
while 1:
try:
path = self.path[index]
index = index + 1
except IndexError:
return nodeset
set = []
if isinstance(path, xpath_descendant_or_self):
try:
tag = self.path[index]
if not isinstance(tag, type("")):
tag = None
else:
index = index + 1
except IndexError:
tag = None # invalid path
for node in nodeset:
new = list(node.getiterator(tag))
if new and new[0] is node:
set.extend(new[1:])
else:
set.extend(new)
else:
for node in nodeset:
for node in node:
if path == "*" or node.tag == path:
set.append(node)
if not set:
return []
nodeset = set
_cache = {}
##
# (Internal) Compile path.
def _compile(path):
p = _cache.get(path)
if p is not None:
return p
p = Path(path)
if len(_cache) >= 100:
_cache.clear()
_cache[path] = p
return p
##
# Find first matching object.
def find(element, path):
return _compile(path).find(element)
##
# Find text for first matching object.
def findtext(element, path, default=None):
return _compile(path).findtext(element, default)
##
# Find all matching objects.
def findall(element, path):
return _compile(path).findall(element)
Lib/xmlcore/etree/ElementTree.py
View file @ 9ed73060
#
# ElementTree
# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $
#
# light-weight XML support for Python 1.5.2 and later.
#
# history:
# 2001-10-20 fl created (from various sources)
# 2001-11-01 fl return root from parse method
# 2002-02-16 fl sort attributes in lexical order
# 2002-04-06 fl TreeBuilder refactoring, added PythonDoc markup
# 2002-05-01 fl finished TreeBuilder refactoring
# 2002-07-14 fl added basic namespace support to ElementTree.write
# 2002-07-25 fl added QName attribute support
# 2002-10-20 fl fixed encoding in write
# 2002-11-24 fl changed default encoding to ascii; fixed attribute encoding
# 2002-11-27 fl accept file objects or file names for parse/write
# 2002-12-04 fl moved XMLTreeBuilder back to this module
# 2003-01-11 fl fixed entity encoding glitch for us-ascii
# 2003-02-13 fl added XML literal factory
# 2003-02-21 fl added ProcessingInstruction/PI factory
# 2003-05-11 fl added tostring/fromstring helpers
# 2003-05-26 fl added ElementPath support
# 2003-07-05 fl added makeelement factory method
# 2003-07-28 fl added more well-known namespace prefixes
# 2003-08-15 fl fixed typo in ElementTree.findtext (Thomas Dartsch)
# 2003-09-04 fl fall back on emulator if ElementPath is not installed
# 2003-10-31 fl markup updates
# 2003-11-15 fl fixed nested namespace bug
# 2004-03-28 fl added XMLID helper
# 2004-06-02 fl added default support to findtext
# 2004-06-08 fl fixed encoding of non-ascii element/attribute names
# 2004-08-23 fl take advantage of post-2.1 expat features
# 2005-02-01 fl added iterparse implementation
# 2005-03-02 fl fixed iterparse support for pre-2.2 versions
#
# Copyright (c) 1999-2005 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2005 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring",
"iselement", "iterparse",
"parse",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring",
"TreeBuilder",
"VERSION", "XML",
"XMLTreeBuilder",
]
##
# 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} or {@link
# #SubElement} factory functions.
# <p>
# The {@link #ElementTree} class can be used to wrap an element
# structure, and convert it from and to XML.
##
import string, sys, re
class _SimpleElementPath:
# emulate pre-1.2 find/findtext/findall behaviour
def find(self, element, tag):
for elem in element:
if elem.tag == tag:
return elem
return None
def findtext(self, element, tag, default=None):
for elem in element:
if elem.tag == tag:
return elem.text or ""
return default
def findall(self, element, tag):
if tag[:3] == ".//":
return element.getiterator(tag[3:])
result = []
for elem in element:
if elem.tag == tag:
result.append(elem)
return result
try:
import ElementPath
except ImportError:
# FIXME: issue warning in this case?
ElementPath = _SimpleElementPath()
# TODO: add support for custom namespace resolvers/default namespaces
# TODO: add improved support for incremental parsing
VERSION = "1.2.6"
##
# Internal element class. This class defines the Element interface,
# and provides a reference implementation of this interface.
# <p>
# You should not create instances of this class directly. Use the
# appropriate factory functions instead, such as {@link #Element}
# and {@link #SubElement}.
#
# @see Element
# @see SubElement
# @see Comment
# @see ProcessingInstruction
class _ElementInterface:
# <tag attrib>text<child/>...</tag>tail
##
# (Attribute) Element tag.
tag = None
##
# (Attribute) Element attribute dictionary. Where possible, use
# {@link #_ElementInterface.get},
# {@link #_ElementInterface.set},
# {@link #_ElementInterface.keys}, and
# {@link #_ElementInterface.items} to access
# element attributes.
attrib = None
##
# (Attribute) Text before first subelement. This is either a
# string or the value None, if there was no text.
text = None
##
# (Attribute) Text after this element's end tag, but before the
# next sibling element's start tag. This is either a string or
# the value None, if there was no text.
tail = None # text after end tag, if any
def __init__(self, tag, attrib):
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "<Element %s at %x>" % (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 Element(tag, attrib)
##
# Returns the number of subelements.
#
# @return The number of subelements.
def __len__(self):
return len(self._children)
##
# Returns the given subelement.
#
# @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.
#
# @param index What subelement to replace.
# @param element The new element value.
# @exception IndexError If the given element does not exist.
# @exception AssertionError If element is not a valid object.
def __setitem__(self, index, element):
assert iselement(element)
self._children[index] = element
##
# Deletes the given subelement.
#
# @param index What subelement to delete.
# @exception IndexError If the given element does not exist.
def __delitem__(self, index):
del self._children[index]
##
# Returns a list containing subelements in the given range.
#
# @param start The first subelement to return.
# @param stop The first subelement that shouldn't be returned.
# @return A sequence object containing subelements.
def __getslice__(self, start, stop):
return self._children[start:stop]
##
# Replaces a number of subelements with elements from a sequence.
#
# @param start The first subelement to replace.
# @param stop The first subelement that shouldn't be replaced.
# @param elements A sequence object with zero or more elements.
# @exception AssertionError If a sequence member is not a valid object.
def __setslice__(self, start, stop, elements):
for element in elements:
assert iselement(element)
self._children[start:stop] = list(elements)
##
# Deletes a number of subelements.
#
# @param start The first subelement to delete.
# @param stop The first subelement to leave in there.
def __delslice__(self, start, stop):
del self._children[start:stop]
##
# Adds a subelement to the end of this element.
#
# @param element The element to add.
# @exception AssertionError If a sequence member is not a valid object.
def append(self, element):
assert iselement(element)
self._children.append(element)
##
# Inserts a subelement at the given position in this element.
#
# @param index Where to insert the new subelement.
# @exception AssertionError If the element is not a valid object.
def insert(self, index, element):
assert iselement(element)
self._children.insert(index, element)
##
# Removes a matching subelement. Unlike the <b>find</b> methods,
# this method compares elements based on identity, not on tag
# value or contents.
#
# @param element What element to remove.
# @exception ValueError If a matching element could not be found.
# @exception AssertionError If the element is not a valid object.
def remove(self, element):
assert iselement(element)
self._children.remove(element)
##
# Returns all subelements. The elements are returned in document
# order.
#
# @return A list of subelements.
# @defreturn list of Element instances
def getchildren(self):
return self._children
##
# Finds the first matching subelement, by tag name or path.
#
# @param path What element to look for.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path):
return ElementPath.find(self, path)
##
# 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.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# has is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None):
return ElementPath.findtext(self, path, default)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path):
return ElementPath.findall(self, path)
##
# Resets an element. This function removes all subelements, clears
# all attributes, and sets the text and tail attributes to None.
def clear(self):
self.attrib.clear()
self._children = []
self.text = self.tail = None
##
# Gets an element attribute.
#
# @param key What attribute to look for.
# @param default What to return if the attribute was not found.
# @return The attribute value, or the default value, if the
# attribute was not found.
# @defreturn string or None
def get(self, key, default=None):
return self.attrib.get(key, default)
##
# Sets an element attribute.
#
# @param key What attribute to set.
# @param value The attribute value.
def set(self, key, value):
self.attrib[key] = value
##
# Gets a list of attribute names. The names are returned in an
# arbitrary order (just like for an ordinary Python dictionary).
#
# @return A list of element attribute names.
# @defreturn list of strings
def keys(self):
return self.attrib.keys()
##
# Gets element attributes, as a sequence. The attributes are
# returned in an arbitrary order.
#
# @return A list of (name, value) tuples for all attributes.
# @defreturn list of (string, string) tuples
def items(self):
return self.attrib.items()
##
# Creates a tree iterator. The iterator loops over this element
# and all subelements, in document order, and returns all elements
# with a matching tag.
# <p>
# If the tree structure is modified during iteration, the result
# is undefined.
#
# @param tag What tags to look for (default is to return all elements).
# @return A list or iterator containing all the matching elements.
# @defreturn list or iterator
def getiterator(self, tag=None):
nodes = []
if tag == "*":
tag = None
if tag is None or self.tag == tag:
nodes.append(self)
for node in self._children:
nodes.extend(node.getiterator(tag))
return nodes
# compatibility
_Element = _ElementInterface
##
# Element factory. This function returns an object implementing the
# standard Element interface. The exact class or type of that object
# is implementation dependent, but it will always be compatible with
# the {@link #_ElementInterface} class in this module.
# <p>
# The element name, attribute names, and attribute values can be
# either 8-bit ASCII strings or Unicode strings.
#
# @param tag The element name.
# @param attrib An optional dictionary, containing element attributes.
# @param **extra Additional attributes, given as keyword arguments.
# @return An element instance.
# @defreturn Element
def Element(tag, attrib={}, **extra):
attrib = attrib.copy()
attrib.update(extra)
return _ElementInterface(tag, attrib)
##
# Subelement factory. This function creates an element instance, and
# appends it to an existing element.
# <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):
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.
# <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):
element = Element(Comment)
element.text = text
return element
##
# PI element factory. This factory function creates a special element
# that will be serialized as an XML processing instruction.
#
# @param target A string containing the PI target.
# @param text A string containing the PI contents, if any.
# @return An element instance, representing a PI.
# @defreturn Element
def ProcessingInstruction(target, text=None):
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
##
# QName wrapper. This can be used to wrap a QName attribute value, in
# order to get proper namespace handling on output.
#
# @param text A string containing the QName value, in the form {uri}local,
# or, if the tag argument is given, the URI part of a QName.
# @param tag Optional tag. If given, the first argument is interpreted as
# an URI, and this argument is interpreted as a local name.
# @return An opaque object, representing the QName.
class QName:
def __init__(self, text_or_uri, tag=None):
if tag:
text_or_uri = "{%s}%s" % (text_or_uri, tag)
self.text = text_or_uri
def __str__(self):
return self.text
def __hash__(self):
return hash(self.text)
def __cmp__(self, other):
if isinstance(other, QName):
return cmp(self.text, other.text)
return cmp(self.text, other)
##
# ElementTree wrapper class. This class represents an entire element
# hierarchy, and adds some extra support for serialization to and from
# standard XML.
#
# @param element Optional root element.
# @keyparam file Optional file handle or name. If given, the
# tree is initialized with the contents of this XML file.
class ElementTree:
def __init__(self, element=None, file=None):
assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
##
# Gets the root element for this tree.
#
# @return An element instance.
# @defreturn Element
def getroot(self):
return self._root
##
# Replaces the root element for this tree. This discards the
# current contents of the tree, and replaces it with the given
# element. Use with care.
#
# @param element An element instance.
def _setroot(self, element):
assert iselement(element)
self._root = element
##
# Loads an external XML document into this element tree.
#
# @param source A file name or file object.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLTreeBuilder} parser is used.
# @return The document root element.
# @defreturn Element
def parse(self, source, parser=None):
if not hasattr(source, "read"):
source = open(source, "rb")
if not parser:
parser = XMLTreeBuilder()
while 1:
data = source.read(32768)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
##
# Creates a tree iterator for the root element. The iterator loops
# over all elements in this tree, in document order.
#
# @param tag What tags to look for (default is to return all elements)
# @return An iterator.
# @defreturn iterator
def getiterator(self, tag=None):
assert self._root is not None
return self._root.getiterator(tag)
##
# Finds the first toplevel element with given tag.
# Same as getroot().find(path).
#
# @param path What element to look for.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.find(path)
##
# Finds the element text for the first toplevel element with given
# tag. Same as getroot().findtext(path).
#
# @param path What toplevel element to look for.
# @param default What to return if the element was not found.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# has is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.findtext(path, default)
##
# Finds all toplevel elements with the given tag.
# Same as getroot().findall(path).
#
# @param path What element to look for.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.findall(path)
##
# Writes the element tree to a file, as XML.
#
# @param file A file name, or a file object opened for writing.
# @param encoding Optional output encoding (default is US-ASCII).
def write(self, file, encoding="us-ascii"):
assert self._root is not None
if not hasattr(file, "write"):
file = open(file, "wb")
if not encoding:
encoding = "us-ascii"
elif encoding != "utf-8" and encoding != "us-ascii":
file.write("<?xml version='1.0' encoding='%s'?>\n" % encoding)
self._write(file, self._root, encoding, {})
def _write(self, file, node, encoding, namespaces):
# write XML to file
tag = node.tag
if tag is Comment:
file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("<?%s?>" % _escape_cdata(node.text, encoding))
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = fixtag(tag, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
file.write("<" + _encode(tag, encoding))
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = fixtag(k, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = fixtag(v, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
for k, v in xmlns_items:
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
if node.text or len(node):
file.write(">")
if node.text:
file.write(_escape_cdata(node.text, encoding))
for n in node:
self._write(file, n, encoding, namespaces)
file.write("</" + _encode(tag, encoding) + ">")
else:
file.write(" />")
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
file.write(_escape_cdata(node.tail, encoding))
# --------------------------------------------------------------------
# helpers
##
# Checks if an object appears to be a valid element object.
#
# @param An element instance.
# @return A true value if this is an element object.
# @defreturn flag
def iselement(element):
# FIXME: not sure about this; might be a better idea to look
# for tag/attrib/text attributes
return isinstance(element, _ElementInterface) or hasattr(element, "tag")
##
# Writes an element tree or element structure to sys.stdout. This
# function should be used for debugging only.
# <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):
# debugging
if not isinstance(elem, ElementTree):
elem = ElementTree(elem)
elem.write(sys.stdout)
tail = elem.getroot().tail
if not tail or tail[-1] != "\n":
sys.stdout.write("\n")
def _encode(s, encoding):
try:
return s.encode(encoding)
except AttributeError:
return s # 1.5.2: assume the string uses the right encoding
if sys.version[:3] == "1.5":
_escape = re.compile(r"[&<>\"\x80-\xff]+") # 1.5.2
else:
_escape = re.compile(eval(r'u"[&<>\"\u0080-\uffff]+"'))
_escape_map = {
"&": "&amp;",
"<": "&lt;",
">": "&gt;",
'"': "&quot;",
}
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
}
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _encode_entity(text, pattern=_escape):
# map reserved and non-ascii characters to numerical entities
def escape_entities(m, map=_escape_map):
out = []
append = out.append
for char in m.group():
text = map.get(char)
if text is None:
text = "&#%d;" % ord(char)
append(text)
return string.join(out, "")
try:
return _encode(pattern.sub(escape_entities, text), "ascii")
except TypeError:
_raise_serialization_error(text)
#
# the following functions assume an ascii-compatible encoding
# (or "utf-16")
def _escape_cdata(text, encoding=None, replace=string.replace):
# escape character data
try:
if encoding:
try:
text = _encode(text, encoding)
except UnicodeError:
return _encode_entity(text)
text = replace(text, "&", "&amp;")
text = replace(text, "<", "&lt;")
text = replace(text, ">", "&gt;")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text, encoding=None, replace=string.replace):
# escape attribute value
try:
if encoding:
try:
text = _encode(text, encoding)
except UnicodeError:
return _encode_entity(text)
text = replace(text, "&", "&amp;")
text = replace(text, "'", "&apos;") # FIXME: overkill
text = replace(text, "\"", "&quot;")
text = replace(text, "<", "&lt;")
text = replace(text, ">", "&gt;")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def fixtag(tag, namespaces):
# given a decorated tag (of the form {uri}tag), return prefixed
# tag and namespace declaration, if any
if isinstance(tag, QName):
tag = tag.text
namespace_uri, tag = string.split(tag[1:], "}", 1)
prefix = namespaces.get(namespace_uri)
if prefix is None:
prefix = _namespace_map.get(namespace_uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
namespaces[namespace_uri] = prefix
if prefix == "xml":
xmlns = None
else:
xmlns = ("xmlns:%s" % prefix, namespace_uri)
else:
xmlns = None
return "%s:%s" % (prefix, tag), xmlns
##
# Parses an XML document into an element tree.
#
# @param source A filename or file object containing XML data.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLTreeBuilder} parser is used.
# @return An ElementTree instance
def parse(source, parser=None):
tree = ElementTree()
tree.parse(source, parser)
return tree
##
# Parses an XML document into an element tree incrementally, and reports
# what's going on to the user.
#
# @param source A filename or file object containing XML data.
# @param events A list of events to report back. If omitted, only "end"
# events are reported.
# @return A (event, elem) iterator.
class iterparse:
def __init__(self, source, events=None):
if not hasattr(source, "read"):
source = open(source, "rb")
self._file = source
self._events = []
self._index = 0
self.root = self._root = None
self._parser = XMLTreeBuilder()
# wire up the parser for event reporting
parser = self._parser._parser
append = self._events.append
if events is None:
events = ["end"]
for event in events:
if event == "start":
try:
parser.ordered_attributes = 1
parser.specified_attributes = 1
def handler(tag, attrib_in, event=event, append=append,
start=self._parser._start_list):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
except AttributeError:
def handler(tag, attrib_in, event=event, append=append,
start=self._parser._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event == "end":
def handler(tag, event=event, append=append,
end=self._parser._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event == "start-ns":
def handler(prefix, uri, event=event, append=append):
try:
uri = _encode(uri, "ascii")
except UnicodeError:
pass
append((event, (prefix or "", uri)))
parser.StartNamespaceDeclHandler = handler
elif event == "end-ns":
def handler(prefix, event=event, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
def next(self):
while 1:
try:
item = self._events[self._index]
except IndexError:
if self._parser is None:
self.root = self._root
try:
raise StopIteration
except NameError:
raise IndexError
# load event buffer
del self._events[:]
self._index = 0
data = self._file.read(16384)
if data:
self._parser.feed(data)
else:
self._root = self._parser.close()
self._parser = None
else:
self._index = self._index + 1
return item
try:
iter
def __iter__(self):
return self
except NameError:
def __getitem__(self, index):
return self.next()
##
# Parses an XML document from a string constant. This function can
# be used to embed "XML literals" in Python code.
#
# @param source A string containing XML data.
# @return An Element instance.
# @defreturn Element
def XML(text):
parser = XMLTreeBuilder()
parser.feed(text)
return parser.close()
##
# Parses an XML document from a string constant, and also returns
# a dictionary which maps from element id:s to elements.
#
# @param source A string containing XML data.
# @return A tuple containing an Element instance and a dictionary.
# @defreturn (Element, dictionary)
def XMLID(text):
parser = XMLTreeBuilder()
parser.feed(text)
tree = parser.close()
ids = {}
for elem in tree.getiterator():
id = elem.get("id")
if id:
ids[id] = elem
return tree, ids
##
# Parses an XML document from a string constant. Same as {@link #XML}.
#
# @def fromstring(text)
# @param source A string containing XML data.
# @return An Element instance.
# @defreturn Element
fromstring = XML
##
# Generates a string representation of an XML element, including all
# subelements.
#
# @param element An Element instance.
# @return An encoded string containing the XML data.
# @defreturn string
def tostring(element, encoding=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding)
return string.join(data, "")
##
# Generic element structure builder. This builder converts a sequence
# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link
# #TreeBuilder.end} method calls to a well-formed element structure.
# <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:
def __init__(self, element_factory=None):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._tail = None # true if we're after an end tag
if element_factory is None:
element_factory = _ElementInterface
self._factory = element_factory
##
# Flushes the parser buffers, and returns the toplevel documen
# element.
#
# @return An Element instance.
# @defreturn Element
def close(self):
assert len(self._elem) == 0, "missing end tags"
assert self._last != None, "missing toplevel element"
return self._last
def _flush(self):
if self._data:
if self._last is not None:
text = string.join(self._data, "")
if self._tail:
assert self._last.tail is None, "internal error (tail)"
self._last.tail = text
else:
assert self._last.text is None, "internal error (text)"
self._last.text = text
self._data = []
##
# Adds text to the current element.
#
# @param data A string. This should be either an 8-bit string
# containing ASCII text, or a Unicode string.
def data(self, data):
self._data.append(data)
##
# Opens a new element.
#
# @param tag The element name.
# @param attrib A dictionary containing element attributes.
# @return The opened element.
# @defreturn Element
def start(self, tag, attrs):
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
self._elem.append(elem)
self._tail = 0
return elem
##
# Closes the current element.
#
# @param tag The element name.
# @return The closed element.
# @defreturn Element
def end(self, tag):
self._flush()
self._last = self._elem.pop()
assert self._last.tag == tag,\
"end tag mismatch (expected %s, got %s)" % (
self._last.tag, tag)
self._tail = 1
return self._last
##
# Element structure builder for XML source data, based on the
# <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.
# @see #ElementTree
# @see #TreeBuilder
class XMLTreeBuilder:
def __init__(self, html=0, target=None):
try:
from xmlcore.parsers import expat
except ImportError:
raise ImportError(
"No module named expat; use SimpleXMLTreeBuilder instead"
)
self._parser = parser = expat.ParserCreate(None, "}")
if target is None:
target = TreeBuilder()
self._target = target
self._names = {} # name memo cache
# callbacks
parser.DefaultHandlerExpand = self._default
parser.StartElementHandler = self._start
parser.EndElementHandler = self._end
parser.CharacterDataHandler = self._data
# let expat do the buffering, if supported
try:
self._parser.buffer_text = 1
except AttributeError:
pass
# use new-style attribute handling, if supported
try:
self._parser.ordered_attributes = 1
self._parser.specified_attributes = 1
parser.StartElementHandler = self._start_list
except AttributeError:
pass
encoding = None
if not parser.returns_unicode:
encoding = "utf-8"
# target.xml(encoding, None)
self._doctype = None
self.entity = {}
def _fixtext(self, text):
# convert text string to ascii, if possible
try:
return _encode(text, "ascii")
except UnicodeError:
return text
def _fixname(self, key):
# expand qname, and convert name string to ascii, if possible
try:
name = self._names[key]
except KeyError:
name = key
if "}" in name:
name = "{" + name
self._names[key] = name = self._fixtext(name)
return name
def _start(self, tag, attrib_in):
fixname = self._fixname
tag = fixname(tag)
attrib = {}
for key, value in attrib_in.items():
attrib[fixname(key)] = self._fixtext(value)
return self._target.start(tag, attrib)
def _start_list(self, tag, attrib_in):
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attrib_in:
for i in range(0, len(attrib_in), 2):
attrib[fixname(attrib_in[i])] = self._fixtext(attrib_in[i+1])
return self._target.start(tag, attrib)
def _data(self, text):
return self._target.data(self._fixtext(text))
def _end(self, tag):
return self._target.end(self._fixname(tag))
def _default(self, text):
prefix = text[:1]
if prefix == "&":
# deal with undefined entities
try:
self._target.data(self.entity[text[1:-1]])
except KeyError:
from xmlcore.parsers import expat
raise expat.error(
"undefined entity %s: line %d, column %d" %
(text, self._parser.ErrorLineNumber,
self._parser.ErrorColumnNumber)
)
elif prefix == "<" and text[:9] == "<!DOCTYPE":
self._doctype = [] # inside a doctype declaration
elif self._doctype is not None:
# parse doctype contents
if prefix == ">":
self._doctype = None
return
text = string.strip(text)
if not text:
return
self._doctype.append(text)
n = len(self._doctype)
if n > 2:
type = self._doctype[1]
if type == "PUBLIC" and n == 4:
name, type, pubid, system = self._doctype
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if pubid:
pubid = pubid[1:-1]
self.doctype(name, pubid, system[1:-1])
self._doctype = None
##
# Handles a doctype declaration.
#
# @param name Doctype name.
# @param pubid Public identifier.
# @param system System identifier.
def doctype(self, name, pubid, system):
pass
##
# Feeds data to the parser.
#
# @param data Encoded data.
def feed(self, data):
self._parser.Parse(data, 0)
##
# Finishes feeding data to the parser.
#
# @return An element structure.
# @defreturn Element
def close(self):
self._parser.Parse("", 1) # end of data
tree = self._target.close()
del self._target, self._parser # get rid of circular references
return tree
#
# ElementTree
# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $
#
# light-weight XML support for Python 1.5.2 and later.
#
# history:
# 2001-10-20 fl created (from various sources)
# 2001-11-01 fl return root from parse method
# 2002-02-16 fl sort attributes in lexical order
# 2002-04-06 fl TreeBuilder refactoring, added PythonDoc markup
# 2002-05-01 fl finished TreeBuilder refactoring
# 2002-07-14 fl added basic namespace support to ElementTree.write
# 2002-07-25 fl added QName attribute support
# 2002-10-20 fl fixed encoding in write
# 2002-11-24 fl changed default encoding to ascii; fixed attribute encoding
# 2002-11-27 fl accept file objects or file names for parse/write
# 2002-12-04 fl moved XMLTreeBuilder back to this module
# 2003-01-11 fl fixed entity encoding glitch for us-ascii
# 2003-02-13 fl added XML literal factory
# 2003-02-21 fl added ProcessingInstruction/PI factory
# 2003-05-11 fl added tostring/fromstring helpers
# 2003-05-26 fl added ElementPath support
# 2003-07-05 fl added makeelement factory method
# 2003-07-28 fl added more well-known namespace prefixes
# 2003-08-15 fl fixed typo in ElementTree.findtext (Thomas Dartsch)
# 2003-09-04 fl fall back on emulator if ElementPath is not installed
# 2003-10-31 fl markup updates
# 2003-11-15 fl fixed nested namespace bug
# 2004-03-28 fl added XMLID helper
# 2004-06-02 fl added default support to findtext
# 2004-06-08 fl fixed encoding of non-ascii element/attribute names
# 2004-08-23 fl take advantage of post-2.1 expat features
# 2005-02-01 fl added iterparse implementation
# 2005-03-02 fl fixed iterparse support for pre-2.2 versions
#
# Copyright (c) 1999-2005 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2005 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring",
"iselement", "iterparse",
"parse",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring",
"TreeBuilder",
"VERSION", "XML",
"XMLTreeBuilder",
]
##
# 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} or {@link
# #SubElement} factory functions.
# <p>
# The {@link #ElementTree} class can be used to wrap an element
# structure, and convert it from and to XML.
##
import string, sys, re
class _SimpleElementPath:
# emulate pre-1.2 find/findtext/findall behaviour
def find(self, element, tag):
for elem in element:
if elem.tag == tag:
return elem
return None
def findtext(self, element, tag, default=None):
for elem in element:
if elem.tag == tag:
return elem.text or ""
return default
def findall(self, element, tag):
if tag[:3] == ".//":
return element.getiterator(tag[3:])
result = []
for elem in element:
if elem.tag == tag:
result.append(elem)
return result
try:
import ElementPath
except ImportError:
# FIXME: issue warning in this case?
ElementPath = _SimpleElementPath()
# TODO: add support for custom namespace resolvers/default namespaces
# TODO: add improved support for incremental parsing
VERSION = "1.2.6"
##
# Internal element class. This class defines the Element interface,
# and provides a reference implementation of this interface.
# <p>
# You should not create instances of this class directly. Use the
# appropriate factory functions instead, such as {@link #Element}
# and {@link #SubElement}.
#
# @see Element
# @see SubElement
# @see Comment
# @see ProcessingInstruction
class _ElementInterface:
# <tag attrib>text<child/>...</tag>tail
##
# (Attribute) Element tag.
tag = None
##
# (Attribute) Element attribute dictionary. Where possible, use
# {@link #_ElementInterface.get},
# {@link #_ElementInterface.set},
# {@link #_ElementInterface.keys}, and
# {@link #_ElementInterface.items} to access
# element attributes.
attrib = None
##
# (Attribute) Text before first subelement. This is either a
# string or the value None, if there was no text.
text = None
##
# (Attribute) Text after this element's end tag, but before the
# next sibling element's start tag. This is either a string or
# the value None, if there was no text.
tail = None # text after end tag, if any
def __init__(self, tag, attrib):
self.tag = tag
self.attrib = attrib
self._children = []
def __repr__(self):
return "<Element %s at %x>" % (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 Element(tag, attrib)
##
# Returns the number of subelements.
#
# @return The number of subelements.
def __len__(self):
return len(self._children)
##
# Returns the given subelement.
#
# @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.
#
# @param index What subelement to replace.
# @param element The new element value.
# @exception IndexError If the given element does not exist.
# @exception AssertionError If element is not a valid object.
def __setitem__(self, index, element):
assert iselement(element)
self._children[index] = element
##
# Deletes the given subelement.
#
# @param index What subelement to delete.
# @exception IndexError If the given element does not exist.
def __delitem__(self, index):
del self._children[index]
##
# Returns a list containing subelements in the given range.
#
# @param start The first subelement to return.
# @param stop The first subelement that shouldn't be returned.
# @return A sequence object containing subelements.
def __getslice__(self, start, stop):
return self._children[start:stop]
##
# Replaces a number of subelements with elements from a sequence.
#
# @param start The first subelement to replace.
# @param stop The first subelement that shouldn't be replaced.
# @param elements A sequence object with zero or more elements.
# @exception AssertionError If a sequence member is not a valid object.
def __setslice__(self, start, stop, elements):
for element in elements:
assert iselement(element)
self._children[start:stop] = list(elements)
##
# Deletes a number of subelements.
#
# @param start The first subelement to delete.
# @param stop The first subelement to leave in there.
def __delslice__(self, start, stop):
del self._children[start:stop]
##
# Adds a subelement to the end of this element.
#
# @param element The element to add.
# @exception AssertionError If a sequence member is not a valid object.
def append(self, element):
assert iselement(element)
self._children.append(element)
##
# Inserts a subelement at the given position in this element.
#
# @param index Where to insert the new subelement.
# @exception AssertionError If the element is not a valid object.
def insert(self, index, element):
assert iselement(element)
self._children.insert(index, element)
##
# Removes a matching subelement. Unlike the <b>find</b> methods,
# this method compares elements based on identity, not on tag
# value or contents.
#
# @param element What element to remove.
# @exception ValueError If a matching element could not be found.
# @exception AssertionError If the element is not a valid object.
def remove(self, element):
assert iselement(element)
self._children.remove(element)
##
# Returns all subelements. The elements are returned in document
# order.
#
# @return A list of subelements.
# @defreturn list of Element instances
def getchildren(self):
return self._children
##
# Finds the first matching subelement, by tag name or path.
#
# @param path What element to look for.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path):
return ElementPath.find(self, path)
##
# 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.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# has is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None):
return ElementPath.findtext(self, path, default)
##
# Finds all matching subelements, by tag name or path.
#
# @param path What element to look for.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path):
return ElementPath.findall(self, path)
##
# Resets an element. This function removes all subelements, clears
# all attributes, and sets the text and tail attributes to None.
def clear(self):
self.attrib.clear()
self._children = []
self.text = self.tail = None
##
# Gets an element attribute.
#
# @param key What attribute to look for.
# @param default What to return if the attribute was not found.
# @return The attribute value, or the default value, if the
# attribute was not found.
# @defreturn string or None
def get(self, key, default=None):
return self.attrib.get(key, default)
##
# Sets an element attribute.
#
# @param key What attribute to set.
# @param value The attribute value.
def set(self, key, value):
self.attrib[key] = value
##
# Gets a list of attribute names. The names are returned in an
# arbitrary order (just like for an ordinary Python dictionary).
#
# @return A list of element attribute names.
# @defreturn list of strings
def keys(self):
return self.attrib.keys()
##
# Gets element attributes, as a sequence. The attributes are
# returned in an arbitrary order.
#
# @return A list of (name, value) tuples for all attributes.
# @defreturn list of (string, string) tuples
def items(self):
return self.attrib.items()
##
# Creates a tree iterator. The iterator loops over this element
# and all subelements, in document order, and returns all elements
# with a matching tag.
# <p>
# If the tree structure is modified during iteration, the result
# is undefined.
#
# @param tag What tags to look for (default is to return all elements).
# @return A list or iterator containing all the matching elements.
# @defreturn list or iterator
def getiterator(self, tag=None):
nodes = []
if tag == "*":
tag = None
if tag is None or self.tag == tag:
nodes.append(self)
for node in self._children:
nodes.extend(node.getiterator(tag))
return nodes
# compatibility
_Element = _ElementInterface
##
# Element factory. This function returns an object implementing the
# standard Element interface. The exact class or type of that object
# is implementation dependent, but it will always be compatible with
# the {@link #_ElementInterface} class in this module.
# <p>
# The element name, attribute names, and attribute values can be
# either 8-bit ASCII strings or Unicode strings.
#
# @param tag The element name.
# @param attrib An optional dictionary, containing element attributes.
# @param **extra Additional attributes, given as keyword arguments.
# @return An element instance.
# @defreturn Element
def Element(tag, attrib={}, **extra):
attrib = attrib.copy()
attrib.update(extra)
return _ElementInterface(tag, attrib)
##
# Subelement factory. This function creates an element instance, and
# appends it to an existing element.
# <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):
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.
# <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):
element = Element(Comment)
element.text = text
return element
##
# PI element factory. This factory function creates a special element
# that will be serialized as an XML processing instruction.
#
# @param target A string containing the PI target.
# @param text A string containing the PI contents, if any.
# @return An element instance, representing a PI.
# @defreturn Element
def ProcessingInstruction(target, text=None):
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
##
# QName wrapper. This can be used to wrap a QName attribute value, in
# order to get proper namespace handling on output.
#
# @param text A string containing the QName value, in the form {uri}local,
# or, if the tag argument is given, the URI part of a QName.
# @param tag Optional tag. If given, the first argument is interpreted as
# an URI, and this argument is interpreted as a local name.
# @return An opaque object, representing the QName.
class QName:
def __init__(self, text_or_uri, tag=None):
if tag:
text_or_uri = "{%s}%s" % (text_or_uri, tag)
self.text = text_or_uri
def __str__(self):
return self.text
def __hash__(self):
return hash(self.text)
def __cmp__(self, other):
if isinstance(other, QName):
return cmp(self.text, other.text)
return cmp(self.text, other)
##
# ElementTree wrapper class. This class represents an entire element
# hierarchy, and adds some extra support for serialization to and from
# standard XML.
#
# @param element Optional root element.
# @keyparam file Optional file handle or name. If given, the
# tree is initialized with the contents of this XML file.
class ElementTree:
def __init__(self, element=None, file=None):
assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
##
# Gets the root element for this tree.
#
# @return An element instance.
# @defreturn Element
def getroot(self):
return self._root
##
# Replaces the root element for this tree. This discards the
# current contents of the tree, and replaces it with the given
# element. Use with care.
#
# @param element An element instance.
def _setroot(self, element):
assert iselement(element)
self._root = element
##
# Loads an external XML document into this element tree.
#
# @param source A file name or file object.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLTreeBuilder} parser is used.
# @return The document root element.
# @defreturn Element
def parse(self, source, parser=None):
if not hasattr(source, "read"):
source = open(source, "rb")
if not parser:
parser = XMLTreeBuilder()
while 1:
data = source.read(32768)
if not data:
break
parser.feed(data)
self._root = parser.close()
return self._root
##
# Creates a tree iterator for the root element. The iterator loops
# over all elements in this tree, in document order.
#
# @param tag What tags to look for (default is to return all elements)
# @return An iterator.
# @defreturn iterator
def getiterator(self, tag=None):
assert self._root is not None
return self._root.getiterator(tag)
##
# Finds the first toplevel element with given tag.
# Same as getroot().find(path).
#
# @param path What element to look for.
# @return The first matching element, or None if no element was found.
# @defreturn Element or None
def find(self, path):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.find(path)
##
# Finds the element text for the first toplevel element with given
# tag. Same as getroot().findtext(path).
#
# @param path What toplevel element to look for.
# @param default What to return if the element was not found.
# @return The text content of the first matching element, or the
# default value no element was found. Note that if the element
# has is found, but has no text content, this method returns an
# empty string.
# @defreturn string
def findtext(self, path, default=None):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.findtext(path, default)
##
# Finds all toplevel elements with the given tag.
# Same as getroot().findall(path).
#
# @param path What element to look for.
# @return A list or iterator containing all matching elements,
# in document order.
# @defreturn list of Element instances
def findall(self, path):
assert self._root is not None
if path[:1] == "/":
path = "." + path
return self._root.findall(path)
##
# Writes the element tree to a file, as XML.
#
# @param file A file name, or a file object opened for writing.
# @param encoding Optional output encoding (default is US-ASCII).
def write(self, file, encoding="us-ascii"):
assert self._root is not None
if not hasattr(file, "write"):
file = open(file, "wb")
if not encoding:
encoding = "us-ascii"
elif encoding != "utf-8" and encoding != "us-ascii":
file.write("<?xml version='1.0' encoding='%s'?>\n" % encoding)
self._write(file, self._root, encoding, {})
def _write(self, file, node, encoding, namespaces):
# write XML to file
tag = node.tag
if tag is Comment:
file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("<?%s?>" % _escape_cdata(node.text, encoding))
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = fixtag(tag, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
file.write("<" + _encode(tag, encoding))
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = fixtag(k, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = fixtag(v, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
for k, v in xmlns_items:
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
if node.text or len(node):
file.write(">")
if node.text:
file.write(_escape_cdata(node.text, encoding))
for n in node:
self._write(file, n, encoding, namespaces)
file.write("</" + _encode(tag, encoding) + ">")
else:
file.write(" />")
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
file.write(_escape_cdata(node.tail, encoding))
# --------------------------------------------------------------------
# helpers
##
# Checks if an object appears to be a valid element object.
#
# @param An element instance.
# @return A true value if this is an element object.
# @defreturn flag
def iselement(element):
# FIXME: not sure about this; might be a better idea to look
# for tag/attrib/text attributes
return isinstance(element, _ElementInterface) or hasattr(element, "tag")
##
# Writes an element tree or element structure to sys.stdout. This
# function should be used for debugging only.
# <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):
# debugging
if not isinstance(elem, ElementTree):
elem = ElementTree(elem)
elem.write(sys.stdout)
tail = elem.getroot().tail
if not tail or tail[-1] != "\n":
sys.stdout.write("\n")
def _encode(s, encoding):
try:
return s.encode(encoding)
except AttributeError:
return s # 1.5.2: assume the string uses the right encoding
if sys.version[:3] == "1.5":
_escape = re.compile(r"[&<>\"\x80-\xff]+") # 1.5.2
else:
_escape = re.compile(eval(r'u"[&<>\"\u0080-\uffff]+"'))
_escape_map = {
"&": "&amp;",
"<": "&lt;",
">": "&gt;",
'"': "&quot;",
}
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
}
def _raise_serialization_error(text):
raise TypeError(
"cannot serialize %r (type %s)" % (text, type(text).__name__)
)
def _encode_entity(text, pattern=_escape):
# map reserved and non-ascii characters to numerical entities
def escape_entities(m, map=_escape_map):
out = []
append = out.append
for char in m.group():
text = map.get(char)
if text is None:
text = "&#%d;" % ord(char)
append(text)
return string.join(out, "")
try:
return _encode(pattern.sub(escape_entities, text), "ascii")
except TypeError:
_raise_serialization_error(text)
#
# the following functions assume an ascii-compatible encoding
# (or "utf-16")
def _escape_cdata(text, encoding=None, replace=string.replace):
# escape character data
try:
if encoding:
try:
text = _encode(text, encoding)
except UnicodeError:
return _encode_entity(text)
text = replace(text, "&", "&amp;")
text = replace(text, "<", "&lt;")
text = replace(text, ">", "&gt;")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(text, encoding=None, replace=string.replace):
# escape attribute value
try:
if encoding:
try:
text = _encode(text, encoding)
except UnicodeError:
return _encode_entity(text)
text = replace(text, "&", "&amp;")
text = replace(text, "'", "&apos;") # FIXME: overkill
text = replace(text, "\"", "&quot;")
text = replace(text, "<", "&lt;")
text = replace(text, ">", "&gt;")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def fixtag(tag, namespaces):
# given a decorated tag (of the form {uri}tag), return prefixed
# tag and namespace declaration, if any
if isinstance(tag, QName):
tag = tag.text
namespace_uri, tag = string.split(tag[1:], "}", 1)
prefix = namespaces.get(namespace_uri)
if prefix is None:
prefix = _namespace_map.get(namespace_uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
namespaces[namespace_uri] = prefix
if prefix == "xml":
xmlns = None
else:
xmlns = ("xmlns:%s" % prefix, namespace_uri)
else:
xmlns = None
return "%s:%s" % (prefix, tag), xmlns
##
# Parses an XML document into an element tree.
#
# @param source A filename or file object containing XML data.
# @param parser An optional parser instance. If not given, the
# standard {@link XMLTreeBuilder} parser is used.
# @return An ElementTree instance
def parse(source, parser=None):
tree = ElementTree()
tree.parse(source, parser)
return tree
##
# Parses an XML document into an element tree incrementally, and reports
# what's going on to the user.
#
# @param source A filename or file object containing XML data.
# @param events A list of events to report back. If omitted, only "end"
# events are reported.
# @return A (event, elem) iterator.
class iterparse:
def __init__(self, source, events=None):
if not hasattr(source, "read"):
source = open(source, "rb")
self._file = source
self._events = []
self._index = 0
self.root = self._root = None
self._parser = XMLTreeBuilder()
# wire up the parser for event reporting
parser = self._parser._parser
append = self._events.append
if events is None:
events = ["end"]
for event in events:
if event == "start":
try:
parser.ordered_attributes = 1
parser.specified_attributes = 1
def handler(tag, attrib_in, event=event, append=append,
start=self._parser._start_list):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
except AttributeError:
def handler(tag, attrib_in, event=event, append=append,
start=self._parser._start):
append((event, start(tag, attrib_in)))
parser.StartElementHandler = handler
elif event == "end":
def handler(tag, event=event, append=append,
end=self._parser._end):
append((event, end(tag)))
parser.EndElementHandler = handler
elif event == "start-ns":
def handler(prefix, uri, event=event, append=append):
try:
uri = _encode(uri, "ascii")
except UnicodeError:
pass
append((event, (prefix or "", uri)))
parser.StartNamespaceDeclHandler = handler
elif event == "end-ns":
def handler(prefix, event=event, append=append):
append((event, None))
parser.EndNamespaceDeclHandler = handler
def next(self):
while 1:
try:
item = self._events[self._index]
except IndexError:
if self._parser is None:
self.root = self._root
try:
raise StopIteration
except NameError:
raise IndexError
# load event buffer
del self._events[:]
self._index = 0
data = self._file.read(16384)
if data:
self._parser.feed(data)
else:
self._root = self._parser.close()
self._parser = None
else:
self._index = self._index + 1
return item
try:
iter
def __iter__(self):
return self
except NameError:
def __getitem__(self, index):
return self.next()
##
# Parses an XML document from a string constant. This function can
# be used to embed "XML literals" in Python code.
#
# @param source A string containing XML data.
# @return An Element instance.
# @defreturn Element
def XML(text):
parser = XMLTreeBuilder()
parser.feed(text)
return parser.close()
##
# Parses an XML document from a string constant, and also returns
# a dictionary which maps from element id:s to elements.
#
# @param source A string containing XML data.
# @return A tuple containing an Element instance and a dictionary.
# @defreturn (Element, dictionary)
def XMLID(text):
parser = XMLTreeBuilder()
parser.feed(text)
tree = parser.close()
ids = {}
for elem in tree.getiterator():
id = elem.get("id")
if id:
ids[id] = elem
return tree, ids
##
# Parses an XML document from a string constant. Same as {@link #XML}.
#
# @def fromstring(text)
# @param source A string containing XML data.
# @return An Element instance.
# @defreturn Element
fromstring = XML
##
# Generates a string representation of an XML element, including all
# subelements.
#
# @param element An Element instance.
# @return An encoded string containing the XML data.
# @defreturn string
def tostring(element, encoding=None):
class dummy:
pass
data = []
file = dummy()
file.write = data.append
ElementTree(element).write(file, encoding)
return string.join(data, "")
##
# Generic element structure builder. This builder converts a sequence
# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link
# #TreeBuilder.end} method calls to a well-formed element structure.
# <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:
def __init__(self, element_factory=None):
self._data = [] # data collector
self._elem = [] # element stack
self._last = None # last element
self._tail = None # true if we're after an end tag
if element_factory is None:
element_factory = _ElementInterface
self._factory = element_factory
##
# Flushes the parser buffers, and returns the toplevel documen
# element.
#
# @return An Element instance.
# @defreturn Element
def close(self):
assert len(self._elem) == 0, "missing end tags"
assert self._last != None, "missing toplevel element"
return self._last
def _flush(self):
if self._data:
if self._last is not None:
text = string.join(self._data, "")
if self._tail:
assert self._last.tail is None, "internal error (tail)"
self._last.tail = text
else:
assert self._last.text is None, "internal error (text)"
self._last.text = text
self._data = []
##
# Adds text to the current element.
#
# @param data A string. This should be either an 8-bit string
# containing ASCII text, or a Unicode string.
def data(self, data):
self._data.append(data)
##
# Opens a new element.
#
# @param tag The element name.
# @param attrib A dictionary containing element attributes.
# @return The opened element.
# @defreturn Element
def start(self, tag, attrs):
self._flush()
self._last = elem = self._factory(tag, attrs)
if self._elem:
self._elem[-1].append(elem)
self._elem.append(elem)
self._tail = 0
return elem
##
# Closes the current element.
#
# @param tag The element name.
# @return The closed element.
# @defreturn Element
def end(self, tag):
self._flush()
self._last = self._elem.pop()
assert self._last.tag == tag,\
"end tag mismatch (expected %s, got %s)" % (
self._last.tag, tag)
self._tail = 1
return self._last
##
# Element structure builder for XML source data, based on the
# <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.
# @see #ElementTree
# @see #TreeBuilder
class XMLTreeBuilder:
def __init__(self, html=0, target=None):
try:
from xmlcore.parsers import expat
except ImportError:
raise ImportError(
"No module named expat; use SimpleXMLTreeBuilder instead"
)
self._parser = parser = expat.ParserCreate(None, "}")
if target is None:
target = TreeBuilder()
self._target = target
self._names = {} # name memo cache
# callbacks
parser.DefaultHandlerExpand = self._default
parser.StartElementHandler = self._start
parser.EndElementHandler = self._end
parser.CharacterDataHandler = self._data
# let expat do the buffering, if supported
try:
self._parser.buffer_text = 1
except AttributeError:
pass
# use new-style attribute handling, if supported
try:
self._parser.ordered_attributes = 1
self._parser.specified_attributes = 1
parser.StartElementHandler = self._start_list
except AttributeError:
pass
encoding = None
if not parser.returns_unicode:
encoding = "utf-8"
# target.xml(encoding, None)
self._doctype = None
self.entity = {}
def _fixtext(self, text):
# convert text string to ascii, if possible
try:
return _encode(text, "ascii")
except UnicodeError:
return text
def _fixname(self, key):
# expand qname, and convert name string to ascii, if possible
try:
name = self._names[key]
except KeyError:
name = key
if "}" in name:
name = "{" + name
self._names[key] = name = self._fixtext(name)
return name
def _start(self, tag, attrib_in):
fixname = self._fixname
tag = fixname(tag)
attrib = {}
for key, value in attrib_in.items():
attrib[fixname(key)] = self._fixtext(value)
return self._target.start(tag, attrib)
def _start_list(self, tag, attrib_in):
fixname = self._fixname
tag = fixname(tag)
attrib = {}
if attrib_in:
for i in range(0, len(attrib_in), 2):
attrib[fixname(attrib_in[i])] = self._fixtext(attrib_in[i+1])
return self._target.start(tag, attrib)
def _data(self, text):
return self._target.data(self._fixtext(text))
def _end(self, tag):
return self._target.end(self._fixname(tag))
def _default(self, text):
prefix = text[:1]
if prefix == "&":
# deal with undefined entities
try:
self._target.data(self.entity[text[1:-1]])
except KeyError:
from xmlcore.parsers import expat
raise expat.error(
"undefined entity %s: line %d, column %d" %
(text, self._parser.ErrorLineNumber,
self._parser.ErrorColumnNumber)
)
elif prefix == "<" and text[:9] == "<!DOCTYPE":
self._doctype = [] # inside a doctype declaration
elif self._doctype is not None:
# parse doctype contents
if prefix == ">":
self._doctype = None
return
text = string.strip(text)
if not text:
return
self._doctype.append(text)
n = len(self._doctype)
if n > 2:
type = self._doctype[1]
if type == "PUBLIC" and n == 4:
name, type, pubid, system = self._doctype
elif type == "SYSTEM" and n == 3:
name, type, system = self._doctype
pubid = None
else:
return
if pubid:
pubid = pubid[1:-1]
self.doctype(name, pubid, system[1:-1])
self._doctype = None
##
# Handles a doctype declaration.
#
# @param name Doctype name.
# @param pubid Public identifier.
# @param system System identifier.
def doctype(self, name, pubid, system):
pass
##
# Feeds data to the parser.
#
# @param data Encoded data.
def feed(self, data):
self._parser.Parse(data, 0)
##
# Finishes feeding data to the parser.
#
# @return An element structure.
# @defreturn Element
def close(self):
self._parser.Parse("", 1) # end of data
tree = self._target.close()
del self._target, self._parser # get rid of circular references
return tree
Lib/xmlcore/etree/__init__.py
View file @ 9ed73060
# $Id: __init__.py 1821 2004-06-03 16:57:49Z fredrik $
# elementtree package
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
# $Id: __init__.py 1821 2004-06-03 16:57:49Z fredrik $
# elementtree package
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7