2363d6de43
git-svn-id: http://google-refine.googlecode.com/svn/trunk@517 7d457c2a-affb-35e4-300a-418c747d4874
144 lines
4.9 KiB
Python
144 lines
4.9 KiB
Python
#
|
|
# 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.
|
|
# --------------------------------------------------------------------
|
|
|
|
# Licensed to PSF under a Contributor Agreement.
|
|
# See http://www.python.org/2.4/license for licensing details.
|
|
|
|
##
|
|
# 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
|