summaryrefslogtreecommitdiffstats
path: root/Lib/xml/dom/minidom.py
blob: 2e9d866e3190c6d4fc2ce28a678b3d125f258877 (plain)
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
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
"""\
minidom.py -- a lightweight DOM implementation.

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

from xml.dom import HierarchyRequestErr, EMPTY_NAMESPACE

# 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

import xml.dom


if list is type([]):
    class NodeList(list):
        def item(self, index):
            if 0 <= index < len(self):
                return self[index]

        length = property(lambda self: len(self),
                          doc="The number of nodes in the NodeList.")

else:
    def NodeList():
        return []
    

class Node(xml.dom.Node):
    allnodes = {}
    _debug = 0
    _makeParentNodes = 1
    debug = None
    childNodeTypes = ()
    namespaceURI = None # this is non-null only for elements and attributes
    parentNode = None
    ownerDocument = None

    def __init__(self):
        self.childNodes = NodeList()
        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 __nonzero__(self):
        return 1

    def toxml(self):
        writer = _get_StringIO()
        self.writexml(writer)
        return writer.getvalue()

    def toprettyxml(self, indent="\t", newl="\n"):
        # indent = the indentation string to prepend, per level
        # newl = the newline string to append
        writer = _get_StringIO()
        self.writexml(writer, "", indent, newl)
        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]

    try:
        property
    except NameError:
        def __getattr__(self, key):
            if key[0:2] == "__":
                raise AttributeError, key
            # 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()
    else:
        firstChild = property(_get_firstChild,
                              doc="First child node, or None.")
        lastChild = property(_get_lastChild,
                             doc="Last child node, or None.")

    def insertBefore(self, newChild, refChild):
        if newChild.nodeType == self.DOCUMENT_FRAGMENT_NODE:
            for c in tuple(newChild.childNodes):
                self.insertBefore(c, refChild)
            ### The DOM does not clearly specify what to return in this case
            return newChild
        if newChild.nodeType not in self.childNodeTypes:
            raise HierarchyRequestErr, \
                  "%s cannot be child of %s" % (repr(newChild), repr(self))
        if newChild.parentNode is not None:
            newChild.parentNode.removeChild(newChild)
        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 node.nodeType == self.DOCUMENT_FRAGMENT_NODE:
            for c in tuple(node.childNodes):
                self.appendChild(c)
            ### The DOM does not clearly specify what to return in this case
            return node
        if node.nodeType not in self.childNodeTypes:
            raise HierarchyRequestErr, \
                  "%s cannot be child of %s" % (repr(node), repr(self))
        if node.parentNode is not None:
            node.parentNode.removeChild(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.nodeType == self.DOCUMENT_FRAGMENT_NODE:
            refChild = oldChild.nextSibling
            self.removeChild(oldChild)
            return self.insertBefore(newChild, refChild)
        if newChild.nodeType not in self.childNodeTypes:
            raise HierarchyRequestErr, \
                  "%s cannot be child of %s" % (repr(newChild), repr(self))
        if newChild.parentNode is not None:
            newChild.parentNode.removeChild(newChild)
        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.nextSibling = None
        oldChild.previousSibling = None
        if newChild.previousSibling:
            newChild.previousSibling.nextSibling = newChild
        if newChild.nextSibling:
            newChild.nextSibling.previousSibling = newChild
        return oldChild

    def removeChild(self, oldChild):
        self.childNodes.remove(oldChild)
        if oldChild.nextSibling is not None:
            oldChild.nextSibling.previousSibling = oldChild.previousSibling
        if oldChild.previousSibling is not None:
            oldChild.previousSibling.nextSibling = oldChild.nextSibling
        oldChild.nextSibling = oldChild.previousSibling = None

        if self._makeParentNodes:
            oldChild.parentNode = None
        return oldChild

    def normalize(self):
        L = []
        for child in self.childNodes:
            if child.nodeType == Node.TEXT_NODE:
                data = child.data
                if data and L 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()
                elif data:
                    if L:
                        L[-1].nextSibling = child
                        child.previousSibling = L[-1]
                    else:
                        child.previousSibling = None
                    L.append(child)
                else:
                    # empty text node; discard
                    child.unlink()
            else:
                if L:
                    L[-1].nextSibling = child
                    child.previousSibling = L[-1]
                else:
                    child.previousSibling = None
                L.append(child)
                if child.nodeType == Node.ELEMENT_NODE:
                    child.normalize()
        self.childNodes[:] = L

    def cloneNode(self, deep):
        import new
        clone = new.instance(self.__class__, self.__dict__.copy())
        if self._makeParentNodes:
            clone.parentNode = None
        clone.childNodes = NodeList()
        if deep:
            for child in self.childNodes:
                clone.appendChild(child.cloneNode(1))
        return clone

    # DOM Level 3 (Working Draft 2001-Jan-26)

    def isSameNode(self, other):
        return self is other

    # minidom-specific API:

    def unlink(self):
        self.parentNode = self.ownerDocument = 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, "&", "&amp;")
    data = replace(data, "<", "&lt;")
    data = replace(data, "\"", "&quot;")
    data = replace(data, ">", "&gt;")
    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.localName == localName) and
                (nsURI == "*" or node.namespaceURI == nsURI)):
                rc.append(node)
            _getElementsByTagNameNSHelper(node, nsURI, localName, rc)
    return rc

class DocumentFragment(Node):
    nodeType = Node.DOCUMENT_FRAGMENT_NODE
    nodeName = "#document-fragment"
    nodeValue = None
    attributes = None
    parentNode = None
    childNodeTypes = (Node.ELEMENT_NODE,
                      Node.TEXT_NODE,
                      Node.CDATA_SECTION_NODE,
                      Node.ENTITY_REFERENCE_NODE,
                      Node.PROCESSING_INSTRUCTION_NODE,
                      Node.COMMENT_NODE,
                      Node.NOTATION_NODE)


class Attr(Node):
    nodeType = Node.ATTRIBUTE_NODE
    attributes = None
    ownerElement = None
    childNodeTypes = (Node.TEXT_NODE, Node.ENTITY_REFERENCE_NODE)

    def __init__(self, qName, namespaceURI=EMPTY_NAMESPACE, 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):
        d = self.__dict__
        if name in ("value", "nodeValue"):
            d["value"] = d["nodeValue"] = value
        elif name in ("name", "nodeName"):
            d["name"] = d["nodeName"] = value
        else:
            d[name] = value

    def cloneNode(self, deep):
        clone = Node.cloneNode(self, deep)
        if clone.__dict__.has_key("ownerElement"):
            del clone.ownerElement
        return clone


class NamedNodeMap:
    """The attribute list is a transient interface to the underlying
    dictionaries.  Mutations here will change the underlying element's
    dictionary.

    Ordering is imposed artificially and does not reflect the order of
    attributes as found in an input document.
    """

    def __init__(self, attrs, attrsNS):
        self._attrs = attrs
        self._attrsNS = attrsNS

    try:
        property
    except NameError:
        def __getattr__(self, name):
            if name == "length":
                return len(self._attrs)
            raise AttributeError, name
    else:
        length = property(lambda self: len(self._attrs),
                          doc="Number of nodes in the NamedNodeMap.")

    def item(self, index):
        try:
            return self[self._attrs.keys()[index]]
        except IndexError:
            return None

    def items(self):
        L = []
        for node in self._attrs.values():
            L.append((node.nodeName, node.value))
        return L

    def itemsNS(self):
        L = []
        for node in self._attrs.values():
            L.append(((node.namespaceURI, 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 get(self, name, value = None):
        return self._attrs.get(name, value)

    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
        self.setNamedItem(node)

    def setNamedItem(self, node):
        if not isinstance(node, Attr):
            raise HierarchyRequestErr, \
                  "%s cannot be child of %s" % (repr(node), repr(self))
        old = self._attrs.get(node.name)
        if old:
            old.unlink()
        self._attrs[node.name] = node
        self._attrsNS[(node.namespaceURI, node.localName)] = node
        return old

    def setNamedItemNS(self, node):
        return self.setNamedItem(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)]
        self.length = len(self._attrs)

AttributeList = NamedNodeMap


class Element(Node):
    nodeType = Node.ELEMENT_NODE
    nextSibling = None
    previousSibling = None
    childNodeTypes = (Node.ELEMENT_NODE, Node.PROCESSING_INSTRUCTION_NODE,
                      Node.COMMENT_NODE, Node.TEXT_NODE,
                      Node.CDATA_SECTION_NODE, Node.ENTITY_REFERENCE_NODE)

    def __init__(self, tagName, namespaceURI=EMPTY_NAMESPACE, prefix=None,
                 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):
        try:
            return self._attrs[attname].value
        except KeyError:
            return ""

    def getAttributeNS(self, namespaceURI, localName):
        try:
            return self._attrsNS[(namespaceURI, localName)].value
        except KeyError:
            return ""

    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.get((namespaceURI, localName))

    def setAttributeNode(self, attr):
        if attr.ownerElement not in (None, self):
            raise xml.dom.InuseAttributeErr("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

    setAttributeNodeNS = setAttributeNode

    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)]

    removeAttributeNodeNS = removeAttributeNode

    def hasAttribute(self, name):
        return self._attrs.has_key(name)

    def hasAttributeNS(self, namespaceURI, localName):
        return self._attrsNS.has_key((namespaceURI, localName))

    def getElementsByTagName(self, name):
        return _getElementsByTagNameHelper(self, name, [])

    def getElementsByTagNameNS(self, namespaceURI, localName):
        return _getElementsByTagNameNSHelper(self, namespaceURI, localName, [])

    def __repr__(self):
        return "<DOM Element: %s at %s>" % (self.tagName, id(self))

    def writexml(self, writer, indent="", addindent="", newl=""):
        # indent = current indentation
        # addindent = indentation to add to higher levels
        # newl = newline string
        writer.write(indent+"<" + 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(">%s"%(newl))
            for node in self.childNodes:
                node.writexml(writer,indent+addindent,addindent,newl)
            writer.write("%s</%s>%s" % (indent,self.tagName,newl))
        else:
            writer.write("/>%s"%(newl))

    def _get_attributes(self):
        return AttributeList(self._attrs, self._attrsNS)

    try:
        property
    except NameError:
        pass
    else:
        attributes = property(_get_attributes,
                              doc="NamedNodeMap of attributes on the element.")

    def hasAttributes(self):
        if self._attrs or self._attrsNS:
            return 1
        else:
            return 0

class Comment(Node):
    nodeType = Node.COMMENT_NODE
    nodeName = "#comment"
    attributes = None
    childNodeTypes = ()

    def __init__(self, data):
        Node.__init__(self)
        self.data = self.nodeValue = data

    def writexml(self, writer, indent="", addindent="", newl=""):
        writer.write("%s<!--%s-->%s" % (indent,self.data,newl))

class ProcessingInstruction(Node):
    nodeType = Node.PROCESSING_INSTRUCTION_NODE
    attributes = None
    childNodeTypes = ()

    def __init__(self, target, data):
        Node.__init__(self)
        self.target = self.nodeName = target
        self.data = self.nodeValue = data

    def writexml(self, writer, indent="", addindent="", newl=""):
        writer.write("%s<?%s %s?>%s" % (indent,self.target, self.data, newl))

class CharacterData(Node):
    def __init__(self, data):
        if type(data) not in _StringTypes:
            raise TypeError, "node contents must be a string"
        Node.__init__(self)
        self.data = self.nodeValue = data
        self.length = len(data)

    def __repr__(self):
        if len(self.data) > 10:
            dotdotdot = "..."
        else:
            dotdotdot = ""
        return "<DOM %s node \"%s%s\">" % (
            self.__class__.__name__, self.data[0:10], dotdotdot)

    def substringData(self, offset, count):
        if offset < 0:
            raise xml.dom.IndexSizeErr("offset cannot be negative")
        if offset >= len(self.data):
            raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
        if count < 0:
            raise xml.dom.IndexSizeErr("count cannot be negative")
        return self.data[offset:offset+count]

    def appendData(self, arg):
        self.data = self.data + arg
        self.nodeValue = self.data
        self.length = len(self.data)

    def insertData(self, offset, arg):
        if offset < 0:
            raise xml.dom.IndexSizeErr("offset cannot be negative")
        if offset >= len(self.data):
            raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
        if arg:
            self.data = "%s%s%s" % (
                self.data[:offset], arg, self.data[offset:])
            self.nodeValue = self.data
            self.length = len(self.data)

    def deleteData(self, offset, count):
        if offset < 0:
            raise xml.dom.IndexSizeErr("offset cannot be negative")
        if offset >= len(self.data):
            raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
        if count < 0:
            raise xml.dom.IndexSizeErr("count cannot be negative")
        if count:
            self.data = self.data[:offset] + self.data[offset+count:]
            self.nodeValue = self.data
            self.length = len(self.data)

    def replaceData(self, offset, count, arg):
        if offset < 0:
            raise xml.dom.IndexSizeErr("offset cannot be negative")
        if offset >= len(self.data):
            raise xml.dom.IndexSizeErr("offset cannot be beyond end of data")
        if count < 0:
            raise xml.dom.IndexSizeErr("count cannot be negative")
        if count:
            self.data = "%s%s%s" % (
                self.data[:offset], arg, self.data[offset+count:])
            self.nodeValue = self.data
            self.length = len(self.data)

class Text(CharacterData):
    nodeType = Node.TEXT_NODE
    nodeName = "#text"
    attributes = None
    childNodeTypes = ()

    def splitText(self, offset):
        if offset < 0 or offset > len(self.data):
            raise xml.dom.IndexSizeErr("illegal offset value")
        newText = Text(self.data[offset:])
        next = self.nextSibling
        if self.parentNode and self in self.parentNode.childNodes:
            if next is None:
                self.parentNode.appendChild(newText)
            else:
                self.parentNode.insertBefore(newText, next)
        self.data = self.data[:offset]
        self.nodeValue = self.data
        self.length = len(self.data)
        return newText

    def writexml(self, writer, indent="", addindent="", newl=""):
        _write_data(writer, "%s%s%s"%(indent, self.data, newl))


class CDATASection(Text):
    nodeType = Node.CDATA_SECTION_NODE
    nodeName = "#cdata-section"

    def writexml(self, writer, indent="", addindent="", newl=""):
        writer.write("<![CDATA[%s]]>" % self.data)


def _nssplit(qualifiedName):
    fields = _string.split(qualifiedName, ':', 1)
    if len(fields) == 2:
        return fields
    elif len(fields) == 1:
        return (None, fields[0])


class DocumentType(Node):
    nodeType = Node.DOCUMENT_TYPE_NODE
    nodeValue = None
    attributes = None
    name = None
    publicId = None
    systemId = None
    internalSubset = None
    entities = None
    notations = None

    def __init__(self, qualifiedName):
        Node.__init__(self)
        if qualifiedName:
            prefix, localname = _nssplit(qualifiedName)
            self.name = localname


class DOMImplementation:
    def hasFeature(self, feature, version):
        if version not in ("1.0", "2.0"):
            return 0
        feature = _string.lower(feature)
        return feature == "core"

    def createDocument(self, namespaceURI, qualifiedName, doctype):
        if doctype and doctype.parentNode is not None:
            raise xml.dom.WrongDocumentErr(
                "doctype object owned by another DOM tree")
        doc = self._createDocument()
        if doctype is None:
            doctype = self.createDocumentType(qualifiedName, None, None)
        if not qualifiedName:
            # The spec is unclear what to raise here; SyntaxErr
            # would be the other obvious candidate. Since Xerces raises
            # InvalidCharacterErr, and since SyntaxErr is not listed
            # for createDocument, that seems to be the better choice.
            # XXX: need to check for illegal characters here and in
            # createElement.
            raise xml.dom.InvalidCharacterErr("Element with no name")
        prefix, localname = _nssplit(qualifiedName)
        if prefix == "xml" \
           and namespaceURI != "http://www.w3.org/XML/1998/namespace":
            raise xml.dom.NamespaceErr("illegal use of 'xml' prefix")
        if prefix and not namespaceURI:
            raise xml.dom.NamespaceErr(
                "illegal use of prefix without namespaces")
        element = doc.createElementNS(namespaceURI, qualifiedName)
        doc.appendChild(element)
        doctype.parentNode = doctype.ownerDocument = doc
        doc.doctype = doctype
        doc.implementation = self
        return doc

    def createDocumentType(self, qualifiedName, publicId, systemId):
        doctype = DocumentType(qualifiedName)
        doctype.publicId = publicId
        doctype.systemId = systemId
        return doctype

    # internal
    def _createDocument(self):
        return Document()

class Document(Node):
    nodeType = Node.DOCUMENT_NODE
    nodeName = "#document"
    nodeValue = None
    attributes = None
    doctype = None
    parentNode = None
    previousSibling = nextSibling = None

    implementation = DOMImplementation()
    childNodeTypes = (Node.ELEMENT_NODE, Node.PROCESSING_INSTRUCTION_NODE,
                      Node.COMMENT_NODE, Node.DOCUMENT_TYPE_NODE)

    def appendChild(self, node):
        if node.nodeType not in self.childNodeTypes:
            raise HierarchyRequestErr, \
                  "%s cannot be child of %s" % (repr(node), repr(self))
        if node.parentNode is not None:
            node.parentNode.removeChild(node)

        if node.nodeType == Node.ELEMENT_NODE \
           and self._get_documentElement():
            raise xml.dom.HierarchyRequestErr(
                "two document elements disallowed")
        return Node.appendChild(self, node)

    def removeChild(self, oldChild):
        self.childNodes.remove(oldChild)
        oldChild.nextSibling = oldChild.previousSibling = None
        oldChild.parentNode = None
        if self.documentElement is oldChild:
            self.documentElement = None

        return oldChild

    def _get_documentElement(self):
        for node in self.childNodes:
            if node.nodeType == Node.ELEMENT_NODE:
                return node

    try:
        property
    except NameError:
        pass
    else:
        documentElement = property(_get_documentElement,
                                   doc="Top-level element of this document.")

    def unlink(self):
        if self.doctype is not None:
            self.doctype.unlink()
            self.doctype = None
        Node.unlink(self)

    def createDocumentFragment(self):
        d = DocumentFragment()
        d.ownerDoc = self
        return d

    def createElement(self, tagName):
        e = Element(tagName)
        e.ownerDocument = self
        return e

    def createTextNode(self, data):
        t = Text(data)
        t.ownerDocument = self
        return t

    def createCDATASection(self, data):
        c = CDATASection(data)
        c.ownerDocument = self
        return c

    def createComment(self, data):
        c = Comment(data)
        c.ownerDocument = self
        return c

    def createProcessingInstruction(self, target, data):
        p = ProcessingInstruction(target, data)
        p.ownerDocument = self
        return p

    def createAttribute(self, qName):
        a = Attr(qName)
        a.ownerDocument = self
        a.value = ""
        return a

    def createElementNS(self, namespaceURI, qualifiedName):
        prefix, localName = _nssplit(qualifiedName)
        e = Element(qualifiedName, namespaceURI, prefix, localName)
        e.ownerDocument = self
        return e

    def createAttributeNS(self, namespaceURI, qualifiedName):
        prefix, localName = _nssplit(qualifiedName)
        a = Attr(qualifiedName, namespaceURI, localName, prefix)
        a.ownerDocument = self
        a.value = ""
        return a

    def getElementsByTagName(self, name):
        return _getElementsByTagNameHelper(self, name, [])

    def getElementsByTagNameNS(self, namespaceURI, localName):
        return _getElementsByTagNameNSHelper(self, namespaceURI, localName, [])

    def writexml(self, writer, indent="", addindent="", newl=""):
        writer.write('<?xml version="1.0" ?>\n')
        for node in self.childNodes:
            node.writexml(writer, indent, addindent, newl)

def _get_StringIO():
    # we can't use cStringIO since it doesn't support Unicode strings
    from StringIO import StringIO
    return StringIO()

def _doparse(func, args, kwargs):
    events = apply(func, args, kwargs)
    toktype, rootNode = events.getEvent()
    events.expandNode(rootNode)
    events.clear()
    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)

def getDOMImplementation():
    return Document.implementation