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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
|
"""\
minidom.py -- a lightweight DOM implementation based on SAX.
parse( "foo.xml" )
parseString( "<foo><bar/></foo>" )
Todo:
=====
* convenience methods for getting elements and text.
* more testing
* bring some of the writer and linearizer code into conformance with this
interface
* SAX 2 namespaces
"""
import string
_string = string
del string
# localize the types, and allow support for Unicode values if available:
import types
_TupleType = types.TupleType
try:
_StringTypes = (types.StringType, types.UnicodeType)
except AttributeError:
_StringTypes = (types.StringType,)
del types
class Node:
ELEMENT_NODE = 1
ATTRIBUTE_NODE = 2
TEXT_NODE = 3
CDATA_SECTION_NODE = 4
ENTITY_REFERENCE_NODE = 5
ENTITY_NODE = 6
PROCESSING_INSTRUCTION_NODE = 7
COMMENT_NODE = 8
DOCUMENT_NODE = 9
DOCUMENT_TYPE_NODE = 10
DOCUMENT_FRAGMENT_NODE = 11
NOTATION_NODE = 12
allnodes = {}
_debug = 0
_makeParentNodes = 1
debug = None
def __init__(self):
self.childNodes = []
if Node._debug:
index = repr(id(self)) + repr(self.__class__)
Node.allnodes[index] = repr(self.__dict__)
if Node.debug is None:
Node.debug = _get_StringIO()
#open( "debug4.out", "w" )
Node.debug.write("create %s\n" % index)
def __getattr__(self, key):
if key[0:2] == "__":
raise AttributeError
# getattr should never call getattr!
if self.__dict__.has_key("inGetAttr"):
del self.inGetAttr
raise AttributeError, key
prefix, attrname = key[:5], key[5:]
if prefix == "_get_":
self.inGetAttr = 1
if hasattr(self, attrname):
del self.inGetAttr
return (lambda self=self, attrname=attrname:
getattr(self, attrname))
else:
del self.inGetAttr
raise AttributeError, key
else:
self.inGetAttr = 1
try:
func = getattr(self, "_get_" + key)
except AttributeError:
raise AttributeError, key
del self.inGetAttr
return func()
def __nonzero__(self):
return 1
def toxml(self):
writer = _get_StringIO()
self.writexml(writer)
return writer.getvalue()
def hasChildNodes(self):
if self.childNodes:
return 1
else:
return 0
def _get_firstChild(self):
if self.childNodes:
return self.childNodes[0]
def _get_lastChild(self):
if self.childNodes:
return self.childNodes[-1]
def insertBefore(self, newChild, refChild):
if refChild is None:
self.appendChild(newChild)
else:
index = self.childNodes.index(refChild)
self.childNodes.insert(index, newChild)
newChild.nextSibling = refChild
refChild.previousSibling = newChild
if index:
node = self.childNodes[index-1]
node.nextSibling = newChild
newChild.previousSibling = node
else:
newChild.previousSibling = None
if self._makeParentNodes:
newChild.parentNode = self
return newChild
def appendChild(self, node):
if self.childNodes:
last = self.lastChild
node.previousSibling = last
last.nextSibling = node
else:
node.previousSibling = None
node.nextSibling = None
self.childNodes.append(node)
if self._makeParentNodes:
node.parentNode = self
return node
def replaceChild(self, newChild, oldChild):
if newChild is oldChild:
return
index = self.childNodes.index(oldChild)
self.childNodes[index] = newChild
if self._makeParentNodes:
newChild.parentNode = self
oldChild.parentNode = None
newChild.nextSibling = oldChild.nextSibling
newChild.previousSibling = oldChild.previousSibling
oldChild.newChild = None
oldChild.previousSibling = None
return oldChild
def removeChild(self, oldChild):
self.childNodes.remove(oldChild)
if self._makeParentNodes:
oldChild.parentNode = None
return oldChild
def normalize(self):
if len(self.childNodes) > 1:
L = [self.childNodes[0]]
for child in self.childNodes[1:]:
if ( child.nodeType == Node.TEXT_NODE
and L[-1].nodeType == child.nodeType):
# collapse text node
node = L[-1]
node.data = node.nodeValue = node.data + child.data
node.nextSibling = child.nextSibling
child.unlink()
else:
L[-1].nextSibling = child
child.previousSibling = L[-1]
L.append(child)
child.normalize()
self.childNodes = L
elif self.childNodes:
# exactly one child -- just recurse
self.childNodes[0].normalize()
def cloneNode(self, deep):
import new
clone = new.instance(self.__class__, self.__dict__.copy())
if self._makeParentNodes:
clone.parentNode = None
clone.childNodes = []
if deep:
for child in self.childNodes:
clone.appendChild(child.cloneNode(1))
return clone
def unlink(self):
self.parentNode = None
for child in self.childNodes:
child.unlink()
self.childNodes = None
self.previousSibling = None
self.nextSibling = None
if Node._debug:
index = repr(id(self)) + repr(self.__class__)
self.debug.write("Deleting: %s\n" % index)
del Node.allnodes[index]
def _write_data(writer, data):
"Writes datachars to writer."
replace = _string.replace
data = replace(data, "&", "&")
data = replace(data, "<", "<")
data = replace(data, "\"", """)
data = replace(data, ">", ">")
writer.write(data)
def _getElementsByTagNameHelper(parent, name, rc):
for node in parent.childNodes:
if node.nodeType == Node.ELEMENT_NODE and \
(name == "*" or node.tagName == name):
rc.append(node)
_getElementsByTagNameHelper(node, name, rc)
return rc
def _getElementsByTagNameNSHelper(parent, nsURI, localName, rc):
for node in parent.childNodes:
if node.nodeType == Node.ELEMENT_NODE:
if ((localName == "*" or node.tagName == localName) and
(nsURI == "*" or node.namespaceURI == nsURI)):
rc.append(node)
_getElementsByTagNameNSHelper(node, name, rc)
class Attr(Node):
nodeType = Node.ATTRIBUTE_NODE
attributes = None
ownerElement = None
def __init__(self, qName, namespaceURI="", localName=None, prefix=None):
# skip setattr for performance
d = self.__dict__
d["localName"] = localName or qName
d["nodeName"] = d["name"] = qName
d["namespaceURI"] = namespaceURI
d["prefix"] = prefix
Node.__init__(self)
# nodeValue and value are set elsewhere
def __setattr__(self, name, value):
if name in ("value", "nodeValue"):
self.__dict__["value"] = self.__dict__["nodeValue"] = value
else:
self.__dict__[name] = value
def cloneNode(self, deep):
clone = Node.cloneNode(self, deep)
if clone.__dict__.has_key("ownerElement"):
del clone.ownerElement
return clone
class AttributeList:
"""The attribute list is a transient interface to the underlying
dictionaries. Mutations here will change the underlying element's
dictionary"""
def __init__(self, attrs, attrsNS):
self._attrs = attrs
self._attrsNS = attrsNS
self.length = len(self._attrs)
def item(self, index):
try:
return self[self.keys()[index]]
except IndexError:
return None
def items(self):
L = []
for node in self._attrs.values():
L.append((node.tagName, node.value))
return L
def itemsNS(self):
L = []
for node in self._attrs.values():
L.append(((node.URI, node.localName), node.value))
return L
def keys(self):
return self._attrs.keys()
def keysNS(self):
return self._attrsNS.keys()
def values(self):
return self._attrs.values()
def __len__(self):
return self.length
def __cmp__(self, other):
if self._attrs is getattr(other, "_attrs", None):
return 0
else:
return cmp(id(self), id(other))
#FIXME: is it appropriate to return .value?
def __getitem__(self, attname_or_tuple):
if type(attname_or_tuple) is _TupleType:
return self._attrsNS[attname_or_tuple]
else:
return self._attrs[attname_or_tuple]
# same as set
def __setitem__(self, attname, value):
if type(value) in _StringTypes:
node = Attr(attname)
node.value = value
else:
if not isinstance(value, Attr):
raise TypeError, "value must be a string or Attr object"
node = value
old = self._attrs.get(attname, None)
if old:
old.unlink()
self._attrs[node.name] = node
self._attrsNS[(node.namespaceURI, node.localName)] = node
def __delitem__(self, attname_or_tuple):
node = self[attname_or_tuple]
node.unlink()
del self._attrs[node.name]
del self._attrsNS[(node.namespaceURI, node.localName)]
class Element(Node):
nodeType = Node.ELEMENT_NODE
nextSibling = None
previousSibling = None
def __init__(self, tagName, namespaceURI="", prefix="",
localName=None):
Node.__init__(self)
self.tagName = self.nodeName = tagName
self.localName = localName or tagName
self.prefix = prefix
self.namespaceURI = namespaceURI
self.nodeValue = None
self._attrs = {} # attributes are double-indexed:
self._attrsNS = {} # tagName -> Attribute
# URI,localName -> Attribute
# in the future: consider lazy generation
# of attribute objects this is too tricky
# for now because of headaches with
# namespaces.
def cloneNode(self, deep):
clone = Node.cloneNode(self, deep)
clone._attrs = {}
clone._attrsNS = {}
for attr in self._attrs.values():
node = attr.cloneNode(1)
clone._attrs[node.name] = node
clone._attrsNS[(node.namespaceURI, node.localName)] = node
node.ownerElement = clone
return clone
def unlink(self):
for attr in self._attrs.values():
attr.unlink()
self._attrs = None
self._attrsNS = None
Node.unlink(self)
def getAttribute(self, attname):
return self._attrs[attname].value
def getAttributeNS(self, namespaceURI, localName):
return self._attrsNS[(namespaceURI, localName)].value
def setAttribute(self, attname, value):
attr = Attr(attname)
# for performance
attr.__dict__["value"] = attr.__dict__["nodeValue"] = value
self.setAttributeNode(attr)
def setAttributeNS(self, namespaceURI, qualifiedName, value):
prefix, localname = _nssplit(qualifiedName)
# for performance
attr = Attr(qualifiedName, namespaceURI, localname, prefix)
attr.__dict__["value"] = attr.__dict__["nodeValue"] = value
self.setAttributeNode(attr)
def getAttributeNode(self, attrname):
return self._attrs.get(attrname)
def getAttributeNodeNS(self, namespaceURI, localName):
return self._attrsNS[(namespaceURI, localName)]
def setAttributeNode(self, attr):
if attr.ownerElement not in (None, self):
raise ValueError, "attribute node already owned"
old = self._attrs.get(attr.name, None)
if old:
old.unlink()
self._attrs[attr.name] = attr
self._attrsNS[(attr.namespaceURI, attr.localName)] = attr
# This creates a circular reference, but Element.unlink()
# breaks the cycle since the references to the attribute
# dictionaries are tossed.
attr.ownerElement = self
if old is not attr:
# It might have already been part of this node, in which case
# it doesn't represent a change, and should not be returned.
return old
def removeAttribute(self, name):
attr = self._attrs[name]
self.removeAttributeNode(attr)
def removeAttributeNS(self, namespaceURI, localName):
attr = self._attrsNS[(namespaceURI, localName)]
self.removeAttributeNode(attr)
def removeAttributeNode(self, node):
node.unlink()
del self._attrs[node.name]
del self._attrsNS[(node.namespaceURI, node.localName)]
def getElementsByTagName(self, name):
return _getElementsByTagNameHelper(self, name, [])
def getElementsByTagNameNS(self, namespaceURI, localName):
_getElementsByTagNameNSHelper(self, namespaceURI, localName, [])
def __repr__(self):
return "<DOM Element: %s at %s>" % (self.tagName, id(self))
def writexml(self, writer):
writer.write("<" + self.tagName)
attrs = self._get_attributes()
a_names = attrs.keys()
a_names.sort()
for a_name in a_names:
writer.write(" %s=\"" % a_name)
_write_data(writer, attrs[a_name].value)
writer.write("\"")
if self.childNodes:
writer.write(">")
for node in self.childNodes:
node.writexml(writer)
writer.write("</%s>" % self.tagName)
else:
writer.write("/>")
def _get_attributes(self):
return AttributeList(self._attrs, self._attrsNS)
class Comment(Node):
nodeType = Node.COMMENT_NODE
nodeName = "#comment"
attributes = None
def __init__(self, data):
Node.__init__(self)
self.data = self.nodeValue = data
def writexml(self, writer):
writer.write("<!--%s-->" % self.data)
class ProcessingInstruction(Node):
nodeType = Node.PROCESSING_INSTRUCTION_NODE
attributes = None
def __init__(self, target, data):
Node.__init__(self)
self.target = self.nodeName = target
self.data = self.nodeValue = data
def writexml(self, writer):
writer.write("<?%s %s?>" % (self.target, self.data))
class Text(Node):
nodeType = Node.TEXT_NODE
nodeName = "#text"
attributes = None
def __init__(self, data):
Node.__init__(self)
self.data = self.nodeValue = data
def __repr__(self):
if len(self.data) > 10:
dotdotdot = "..."
else:
dotdotdot = ""
return "<DOM Text node \"%s%s\">" % (self.data[0:10], dotdotdot)
def writexml(self, writer):
_write_data(writer, self.data)
def _nssplit(qualifiedName):
fields = _string.split(qualifiedName, ':', 1)
if len(fields) == 2:
return fields
elif len(fields) == 1:
return ('', fields[0])
class Document(Node):
nodeType = Node.DOCUMENT_NODE
nodeName = "#document"
nodeValue = None
attributes = None
documentElement = None
def appendChild(self, node):
if node.nodeType == Node.ELEMENT_NODE:
if self.documentElement:
raise TypeError, "Two document elements disallowed"
else:
self.documentElement = node
return Node.appendChild(self, node)
createElement = Element
createTextNode = Text
createComment = Comment
createProcessingInstruction = ProcessingInstruction
createAttribute = Attr
def createElementNS(self, namespaceURI, qualifiedName):
prefix, localName = _nssplit(qualifiedName)
return self.createElement(qualifiedName, namespaceURI,
prefix, localName)
def createAttributeNS(self, namespaceURI, qualifiedName):
prefix, localName = _nssplit(qualifiedName)
return self.createAttribute(qualifiedName, namespaceURI,
localName, prefix)
def getElementsByTagNameNS(self, namespaceURI, localName):
_getElementsByTagNameNSHelper(self, namespaceURI, localName)
def unlink(self):
self.documentElement = None
Node.unlink(self)
def getElementsByTagName(self, name):
rc = []
_getElementsByTagNameHelper(self, name, rc)
return rc
def writexml(self, writer):
for node in self.childNodes:
node.writexml(writer)
def _get_StringIO():
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
return StringIO()
def _doparse(func, args, kwargs):
events = apply(func, args, kwargs)
toktype, rootNode = events.getEvent()
events.expandNode(rootNode)
return rootNode
def parse(*args, **kwargs):
"Parse a file into a DOM by filename or file object"
from xml.dom import pulldom
return _doparse(pulldom.parse, args, kwargs)
def parseString(*args, **kwargs):
"Parse a file into a DOM from a string"
from xml.dom import pulldom
return _doparse(pulldom.parseString, args, kwargs)
|