1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
|
#!/usr/bin/env python3
# encoding: utf-8
"""
minidom_extras.py
Created by Graham Dennis on 2008-06-15.
Copyright (c) 2008-2012, Graham Dennis
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
"""
from xml.dom import minidom
from xml.dom import expatbuilder
from xpdeint.ParserException import ParserException
import xpdeint.Python24Support
# These are additional functions that will be added to the XML
# classes for convenience.
def getChildElementsByTagName(self, tagName, optional=False):
"""
Return child XML elements that have the tag name `tagName`.
This function will raise an exception if there are no children
with `tagName` unless the keyword argument `optional` is passed
with a value of `True`.
"""
elements = [x for x in self.childNodes if x.nodeType == minidom.Node.ELEMENT_NODE and x.tagName == tagName]
if not optional and len(elements) == 0:
raise ParserException(self, "There must be at least one '%(tagName)s' element." % locals())
return elements
def getChildElementsByTagNames(self, tagNames, optional=False):
"""
Return child XML elements that have tag names in the collection `tagNames`.
This function will raise an exception if there are no children with a tag name in `tagNames`
unless the keyword argument `optional` is `True`.
"""
elements = [element for element in self.childNodes if element.nodeType == minidom.Node.ELEMENT_NODE and element.tagName in tagNames]
if not optional and len(elements) == 0:
raise ParserException(self, "There must be at least one element from the set {%s}." % ", ".join(tagNames))
return elements
def getChildElementByTagName(self, tagName, optional=False):
"""
Return the child XML element that has the tag name `tagName`.
This function will raise an exception if there is more than
one child with tag name `tagName`. Unless the keyword argument
`optional` is passed with a value of `True`, an exception will
also be raised if there is no child with tag name `tagName`.
"""
elements = self.getChildElementsByTagName(tagName, optional=optional)
if not optional and not len(elements) == 1:
raise ParserException(self, "There must be exactly one '%(tagName)s' element." % locals())
if optional and len(elements) > 1:
raise ParserException(self, "There may be at most one '%(tagName)s' element." % locals())
if optional and len(elements) == 0:
return None
else:
return elements[0]
def innerText(self):
"""
Return the contents of all descendent text nodes and CDATA nodes.
For example, consider the following XML::
<root>
<someTag> someText </someTag>
<![CDATA[
some other text.
]]>
</root>
On the ``root`` element, `innerText` would return " someText some other text." plus
or minus some newlines and other whitespace.
"""
contents = []
for child in self.childNodes:
if child.nodeType == minidom.Node.ELEMENT_NODE:
contents.append(child.innerText())
elif child.nodeType == minidom.Node.TEXT_NODE or child.nodeType == minidom.Node.CDATA_SECTION_NODE:
contents.append(child.data)
return "".join(contents).strip()
def cdataContents(self):
"""
Return the contents of any CDATA nodes that are children of this element.
"""
contents = []
for child in self.childNodes:
if child.nodeType == minidom.Node.CDATA_SECTION_NODE:
contents.append(child.data)
return "".join(contents)
def lineNumberForCDATASection(self):
for child in self.childNodes:
if child.nodeType == minidom.Node.CDATA_SECTION_NODE:
return child.getUserData('lineNumber')
raise ParserException(self, "Missing CDATA section.")
def userUnderstandableXPath(self):
"""
Return an XPath-like string (but more user-friendly) which allows the user to
locate this XML element.
I'd use line/column numbers too except that that information isn't available as part
of the XML spec, so there isn't any function that you can call on an element to get
that information. At least from what I can tell.
"""
currentElement = self
elementPath = []
while 1:
if not currentElement:
break
elementPath.append(currentElement)
currentElement = currentElement.parentNode
elementPathStringList = []
for currentElement in reversed(elementPath):
if len(elementPathStringList) > 0:
elementPathStringList.append(" --> ")
elementDescription = currentElement.nodeName
if currentElement.parentNode:
siblingElements = currentElement.parentNode.getChildElementsByTagName(currentElement.tagName)
if len(siblingElements) > 1:
elementDescription += '[' + str(siblingElements.index(currentElement)) + ']'
elementPathStringList.extend(["'", elementDescription, "'"])
return ''.join(elementPathStringList)
from functools import wraps
def concatenateFunctions(f1, f2):
"""
Returns a function that calls two functions in turn.
The function returned by this function first calls `f1`, and then
`f2`, but returns the result of `f1`.
"""
@wraps(f1)
def wrapper(*args, **KWs):
result = f1(*args, **KWs)
f2(*args, **KWs)
return result
return wrapper
def composeFunctions(f1, f2):
"""
Returns a function that calls ``f2(f1(args))``.
"""
@wraps(f1)
def wrapper(*args, **KWs):
return f2(f1(*args, **KWs))
return wrapper
def setLineAndColumnHandlers(self, *argsOuter, **KWsOuter):
"""
Set the line and column number handlers for an ExpatBuilder.
"""
def setLineAndColumnValuesForElement(*args, **KWs):
"""
Set the line and column numbers from the expat parser.
This data is copied into the ``userData`` dictionary of the node.
The start of the XML tag's line number is available with the key
'lineNumber', and its column number with the key 'columnNumber'.
"""
parser = self._parser
self.curNode.setUserData('lineNumber', parser.CurrentLineNumber, None)
self.curNode.setUserData('columnNumber', parser.CurrentColumnNumber, None)
def getLineNumberForCDATASection(*args, **KWs):
parser = self._parser
self.curNode.ownerDocument.setUserData('_cdata_section_line_number_start', parser.CurrentLineNumber, None)
self.start_element_handler = concatenateFunctions(self.start_element_handler, setLineAndColumnValuesForElement)
self.start_cdata_section_handler = concatenateFunctions(self.start_cdata_section_handler, getLineNumberForCDATASection)
def setLineNumberForCDATASection(node):
node.setUserData('lineNumber', node.ownerDocument.getUserData('_cdata_section_line_number_start'), None)
return node
def external_entity_ref_handler(self, context, base, systemId, publicId):
childParser = self._parser.ExternalEntityParserCreate(context)
fragment = self.document.createDocumentFragment()
childParser.Parse(open(systemId,'r').read(), 1)
return 1
def install_minidom_extras():
"""
This is the function to call to get the minidom extras installed.
"""
# Add the helper methods defined earlier to the XML classes
minidom.Element.getChildElementsByTagName = getChildElementsByTagName
minidom.Document.getChildElementsByTagName = getChildElementsByTagName
minidom.Element.getChildElementsByTagNames = getChildElementsByTagNames
minidom.Document.getChildElementsByTagNames = getChildElementsByTagNames
minidom.Element.getChildElementByTagName = getChildElementByTagName
minidom.Document.getChildElementByTagName = getChildElementByTagName
minidom.Document.createCDATASection = composeFunctions(minidom.Document.createCDATASection, setLineNumberForCDATASection)
minidom.Element.innerText = innerText
minidom.Element.cdataContents = cdataContents
minidom.Element.lineNumberForCDATASection = lineNumberForCDATASection
minidom.Element.userUnderstandableXPath = userUnderstandableXPath
expatbuilder.ExpatBuilder.external_entity_ref_handler = external_entity_ref_handler
# Add our setLineAndColumnHandlers function to the end of the 'reset' function of ExpatBuilder
# This will ensure that our line and column number handlers are installed when any ExpatBuilder
# instance is created. This gets us line and column number information on our XML nodes as minidom
# uses ExpatBuilder to do the parsing for it.
# Note that 'reset' gets called during initialisation of the ExpatBuilder.
expatbuilder.ExpatBuilder.install = concatenateFunctions(setLineAndColumnHandlers, expatbuilder.ExpatBuilder.install)
install_minidom_extras()
|