-
-
Notifications
You must be signed in to change notification settings - Fork 559
/
objectify.pyx
2183 lines (1809 loc) · 75.3 KB
/
objectify.pyx
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
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# cython: binding=True
# cython: auto_pickle=False
# cython: language_level=2
"""
The ``lxml.objectify`` module implements a Python object API for XML.
It is based on `lxml.etree`.
"""
from __future__ import absolute_import
cimport cython
from lxml.includes.etreepublic cimport _Document, _Element, ElementBase, ElementClassLookup
from lxml.includes.etreepublic cimport elementFactory, import_lxml__etree, textOf, pyunicode
from lxml.includes.tree cimport const_xmlChar, _xcstr
from lxml cimport python
from lxml.includes cimport tree
cimport lxml.includes.etreepublic as cetree
cimport libc.string as cstring_h # not to be confused with stdlib 'string'
from libc.string cimport const_char
__all__ = [u'BoolElement', u'DataElement', u'E', u'Element', u'ElementMaker',
u'FloatElement', u'IntElement', u'LongElement', u'NoneElement',
u'NumberElement', u'ObjectPath', u'ObjectifiedDataElement',
u'ObjectifiedElement', u'ObjectifyElementClassLookup',
u'PYTYPE_ATTRIBUTE', u'PyType', u'StringElement', u'SubElement',
u'XML', u'annotate', u'deannotate', u'dump', u'enable_recursive_str',
u'fromstring', u'getRegisteredTypes', u'makeparser', u'parse',
u'pyannotate', u'pytypename', u'set_default_parser',
u'set_pytype_attribute_tag', u'xsiannotate']
cdef object etree
from lxml import etree
# initialize C-API of lxml.etree
import_lxml__etree()
__version__ = etree.__version__
cdef object _float_is_inf, _float_is_nan
from math import isinf as _float_is_inf, isnan as _float_is_nan
cdef object re
import re
cdef tuple IGNORABLE_ERRORS = (ValueError, TypeError)
cdef object is_special_method = re.compile(u'__.*__$').match
# Duplicated from apihelpers.pxi, since dependencies obstruct
# including apihelpers.pxi.
cdef strrepr(s):
"""Build a representation of strings which we can use in __repr__
methods, e.g. _Element.__repr__().
"""
return s.encode('unicode-escape') if python.IS_PYTHON2 else s
cdef object _typename(object t):
cdef const_char* c_name
c_name = python._fqtypename(t)
s = cstring_h.strrchr(c_name, c'.')
if s is not NULL:
c_name = s + 1
return pyunicode(<const_xmlChar*>c_name)
# namespace/name for "pytype" hint attribute
cdef object PYTYPE_NAMESPACE
cdef bytes PYTYPE_NAMESPACE_UTF8
cdef const_xmlChar* _PYTYPE_NAMESPACE
cdef object PYTYPE_ATTRIBUTE_NAME
cdef bytes PYTYPE_ATTRIBUTE_NAME_UTF8
cdef const_xmlChar* _PYTYPE_ATTRIBUTE_NAME
PYTYPE_ATTRIBUTE = None
cdef unicode TREE_PYTYPE_NAME = u"TREE"
cdef tuple _unicodeAndUtf8(s):
return s, python.PyUnicode_AsUTF8String(s)
def set_pytype_attribute_tag(attribute_tag=None):
u"""set_pytype_attribute_tag(attribute_tag=None)
Change name and namespace of the XML attribute that holds Python type
information.
Do not use this unless you know what you are doing.
Reset by calling without argument.
Default: "{http://codespeak.net/lxml/objectify/pytype}pytype"
"""
global PYTYPE_ATTRIBUTE, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME
global PYTYPE_NAMESPACE, PYTYPE_NAMESPACE_UTF8
global PYTYPE_ATTRIBUTE_NAME, PYTYPE_ATTRIBUTE_NAME_UTF8
if attribute_tag is None:
PYTYPE_NAMESPACE, PYTYPE_NAMESPACE_UTF8 = \
_unicodeAndUtf8(u"http://codespeak.net/lxml/objectify/pytype")
PYTYPE_ATTRIBUTE_NAME, PYTYPE_ATTRIBUTE_NAME_UTF8 = \
_unicodeAndUtf8(u"pytype")
else:
PYTYPE_NAMESPACE_UTF8, PYTYPE_ATTRIBUTE_NAME_UTF8 = \
cetree.getNsTag(attribute_tag)
PYTYPE_NAMESPACE = PYTYPE_NAMESPACE_UTF8.decode('utf8')
PYTYPE_ATTRIBUTE_NAME = PYTYPE_ATTRIBUTE_NAME_UTF8.decode('utf8')
_PYTYPE_NAMESPACE = PYTYPE_NAMESPACE_UTF8
_PYTYPE_ATTRIBUTE_NAME = PYTYPE_ATTRIBUTE_NAME_UTF8
PYTYPE_ATTRIBUTE = cetree.namespacedNameFromNsName(
_PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
set_pytype_attribute_tag()
# namespaces for XML Schema
cdef object XML_SCHEMA_NS, XML_SCHEMA_NS_UTF8
XML_SCHEMA_NS, XML_SCHEMA_NS_UTF8 = \
_unicodeAndUtf8(u"http://www.w3.org/2001/XMLSchema")
cdef const_xmlChar* _XML_SCHEMA_NS = _xcstr(XML_SCHEMA_NS_UTF8)
cdef object XML_SCHEMA_INSTANCE_NS, XML_SCHEMA_INSTANCE_NS_UTF8
XML_SCHEMA_INSTANCE_NS, XML_SCHEMA_INSTANCE_NS_UTF8 = \
_unicodeAndUtf8(u"http://www.w3.org/2001/XMLSchema-instance")
cdef const_xmlChar* _XML_SCHEMA_INSTANCE_NS = _xcstr(XML_SCHEMA_INSTANCE_NS_UTF8)
cdef object XML_SCHEMA_INSTANCE_NIL_ATTR = u"{%s}nil" % XML_SCHEMA_INSTANCE_NS
cdef object XML_SCHEMA_INSTANCE_TYPE_ATTR = u"{%s}type" % XML_SCHEMA_INSTANCE_NS
################################################################################
# Element class for the main API
cdef class ObjectifiedElement(ElementBase):
u"""Main XML Element class.
Element children are accessed as object attributes. Multiple children
with the same name are available through a list index. Example::
>>> root = XML("<root><c1><c2>0</c2><c2>1</c2></c1></root>")
>>> second_c2 = root.c1.c2[1]
>>> print(second_c2.text)
1
Note that you cannot (and must not) instantiate this class or its
subclasses.
"""
def __iter__(self):
u"""Iterate over self and all siblings with the same tag.
"""
parent = self.getparent()
if parent is None:
return iter([self])
return etree.ElementChildIterator(parent, tag=self.tag)
def __str__(self):
if __RECURSIVE_STR:
return _dump(self, 0)
else:
return textOf(self._c_node) or u''
# pickle support for objectified Element
def __reduce__(self):
return fromstring, (etree.tostring(self),)
@property
def text(self):
return textOf(self._c_node)
@property
def __dict__(self):
"""A fake implementation for __dict__ to support dir() etc.
Note that this only considers the first child with a given name.
"""
cdef _Element child
cdef dict children
c_ns = tree._getNs(self._c_node)
tag = u"{%s}*" % pyunicode(c_ns) if c_ns is not NULL else None
children = {}
for child in etree.ElementChildIterator(self, tag=tag):
if c_ns is NULL and tree._getNs(child._c_node) is not NULL:
continue
name = pyunicode(child._c_node.name)
if name not in children:
children[name] = child
return children
def __len__(self):
u"""Count self and siblings with the same tag.
"""
return _countSiblings(self._c_node)
def countchildren(self):
u"""countchildren(self)
Return the number of children of this element, regardless of their
name.
"""
# copied from etree
cdef Py_ssize_t c
cdef tree.xmlNode* c_node
c = 0
c_node = self._c_node.children
while c_node is not NULL:
if tree._isElement(c_node):
c += 1
c_node = c_node.next
return c
def getchildren(self):
u"""getchildren(self)
Returns a sequence of all direct children. The elements are
returned in document order.
"""
cdef tree.xmlNode* c_node
result = []
c_node = self._c_node.children
while c_node is not NULL:
if tree._isElement(c_node):
result.append(cetree.elementFactory(self._doc, c_node))
c_node = c_node.next
return result
def __getattr__(self, tag):
u"""Return the (first) child with the given tag name. If no namespace
is provided, the child will be looked up in the same one as self.
"""
if is_special_method(tag):
return object.__getattr__(self, tag)
return _lookupChildOrRaise(self, tag)
def __setattr__(self, tag, value):
u"""Set the value of the (first) child with the given tag name. If no
namespace is provided, the child will be looked up in the same one as
self.
"""
cdef _Element element
# properties are looked up /after/ __setattr__, so we must emulate them
if tag == u'text' or tag == u'pyval':
# read-only !
raise TypeError, f"attribute '{tag}' of '{_typename(self)}' objects is not writable"
elif tag == u'tail':
cetree.setTailText(self._c_node, value)
return
elif tag == u'tag':
ElementBase.tag.__set__(self, value)
return
elif tag == u'base':
ElementBase.base.__set__(self, value)
return
tag = _buildChildTag(self, tag)
element = _lookupChild(self, tag)
if element is None:
_appendValue(self, tag, value)
else:
_replaceElement(element, value)
def __delattr__(self, tag):
child = _lookupChildOrRaise(self, tag)
self.remove(child)
def addattr(self, tag, value):
u"""addattr(self, tag, value)
Add a child value to the element.
As opposed to append(), it sets a data value, not an element.
"""
_appendValue(self, _buildChildTag(self, tag), value)
def __getitem__(self, key):
u"""Return a sibling, counting from the first child of the parent. The
method behaves like both a dict and a sequence.
* If argument is an integer, returns the sibling at that position.
* If argument is a string, does the same as getattr(). This can be
used to provide namespaces for element lookup, or to look up
children with special names (``text`` etc.).
* If argument is a slice object, returns the matching slice.
"""
cdef tree.xmlNode* c_self_node
cdef tree.xmlNode* c_parent
cdef tree.xmlNode* c_node
cdef Py_ssize_t c_index
if python._isString(key):
return _lookupChildOrRaise(self, key)
elif isinstance(key, slice):
return list(self)[key]
# normal item access
c_index = key # raises TypeError if necessary
c_self_node = self._c_node
c_parent = c_self_node.parent
if c_parent is NULL:
if c_index == 0 or c_index == -1:
return self
raise IndexError, unicode(key)
if c_index < 0:
c_node = c_parent.last
else:
c_node = c_parent.children
c_node = _findFollowingSibling(
c_node, tree._getNs(c_self_node), c_self_node.name, c_index)
if c_node is NULL:
raise IndexError, unicode(key)
return elementFactory(self._doc, c_node)
def __setitem__(self, key, value):
u"""Set the value of a sibling, counting from the first child of the
parent. Implements key assignment, item assignment and slice
assignment.
* If argument is an integer, sets the sibling at that position.
* If argument is a string, does the same as setattr(). This is used
to provide namespaces for element lookup.
* If argument is a sequence (list, tuple, etc.), assign the contained
items to the siblings.
"""
cdef _Element element
cdef tree.xmlNode* c_node
if python._isString(key):
key = _buildChildTag(self, key)
element = _lookupChild(self, key)
if element is None:
_appendValue(self, key, value)
else:
_replaceElement(element, value)
return
if self._c_node.parent is NULL:
# the 'root[i] = ...' case
raise TypeError, u"assignment to root element is invalid"
if isinstance(key, slice):
# slice assignment
_setSlice(key, self, value)
else:
# normal index assignment
if key < 0:
c_node = self._c_node.parent.last
else:
c_node = self._c_node.parent.children
c_node = _findFollowingSibling(
c_node, tree._getNs(self._c_node), self._c_node.name, key)
if c_node is NULL:
raise IndexError, unicode(key)
element = elementFactory(self._doc, c_node)
_replaceElement(element, value)
def __delitem__(self, key):
parent = self.getparent()
if parent is None:
raise TypeError, u"deleting items not supported by root element"
if isinstance(key, slice):
# slice deletion
del_items = list(self)[key]
remove = parent.remove
for el in del_items:
remove(el)
else:
# normal index deletion
sibling = self.__getitem__(key)
parent.remove(sibling)
def descendantpaths(self, prefix=None):
u"""descendantpaths(self, prefix=None)
Returns a list of object path expressions for all descendants.
"""
if prefix is not None and not python._isString(prefix):
prefix = u'.'.join(prefix)
return _build_descendant_paths(self._c_node, prefix)
cdef inline bint _tagMatches(tree.xmlNode* c_node, const_xmlChar* c_href, const_xmlChar* c_name):
if c_node.name != c_name:
return 0
if c_href == NULL:
return 1
c_node_href = tree._getNs(c_node)
if c_node_href == NULL:
return c_href[0] == c'\0'
return tree.xmlStrcmp(c_node_href, c_href) == 0
cdef Py_ssize_t _countSiblings(tree.xmlNode* c_start_node):
cdef tree.xmlNode* c_node
cdef Py_ssize_t count
c_tag = c_start_node.name
c_href = tree._getNs(c_start_node)
count = 1
c_node = c_start_node.next
while c_node is not NULL:
if c_node.type == tree.XML_ELEMENT_NODE and \
_tagMatches(c_node, c_href, c_tag):
count += 1
c_node = c_node.next
c_node = c_start_node.prev
while c_node is not NULL:
if c_node.type == tree.XML_ELEMENT_NODE and \
_tagMatches(c_node, c_href, c_tag):
count += 1
c_node = c_node.prev
return count
cdef tree.xmlNode* _findFollowingSibling(tree.xmlNode* c_node,
const_xmlChar* href, const_xmlChar* name,
Py_ssize_t index):
cdef tree.xmlNode* (*next)(tree.xmlNode*)
if index >= 0:
next = cetree.nextElement
else:
index = -1 - index
next = cetree.previousElement
while c_node is not NULL:
if c_node.type == tree.XML_ELEMENT_NODE and \
_tagMatches(c_node, href, name):
index = index - 1
if index < 0:
return c_node
c_node = next(c_node)
return NULL
cdef object _lookupChild(_Element parent, tag):
cdef tree.xmlNode* c_result
cdef tree.xmlNode* c_node
c_node = parent._c_node
ns, tag = cetree.getNsTagWithEmptyNs(tag)
c_tag = tree.xmlDictExists(
c_node.doc.dict, _xcstr(tag), python.PyBytes_GET_SIZE(tag))
if c_tag is NULL:
return None # not in the hash map => not in the tree
if ns is None:
# either inherit ns from parent or use empty (i.e. no) namespace
c_href = tree._getNs(c_node) or <const_xmlChar*>''
else:
c_href = _xcstr(ns)
c_result = _findFollowingSibling(c_node.children, c_href, c_tag, 0)
if c_result is NULL:
return None
return elementFactory(parent._doc, c_result)
cdef object _lookupChildOrRaise(_Element parent, tag):
element = _lookupChild(parent, tag)
if element is None:
raise AttributeError, u"no such child: " + _buildChildTag(parent, tag)
return element
cdef object _buildChildTag(_Element parent, tag):
ns, tag = cetree.getNsTag(tag)
c_tag = _xcstr(tag)
c_href = tree._getNs(parent._c_node) if ns is None else _xcstr(ns)
return cetree.namespacedNameFromNsName(c_href, c_tag)
cdef _replaceElement(_Element element, value):
cdef _Element new_element
if isinstance(value, _Element):
# deep copy the new element
new_element = cetree.deepcopyNodeToDocument(
element._doc, (<_Element>value)._c_node)
new_element.tag = element.tag
elif isinstance(value, (list, tuple)):
element[:] = value
return
else:
new_element = element.makeelement(element.tag)
_setElementValue(new_element, value)
element.getparent().replace(element, new_element)
cdef _appendValue(_Element parent, tag, value):
cdef _Element new_element
if isinstance(value, _Element):
# deep copy the new element
new_element = cetree.deepcopyNodeToDocument(
parent._doc, (<_Element>value)._c_node)
new_element.tag = tag
cetree.appendChildToElement(parent, new_element)
elif isinstance(value, (list, tuple)):
for item in value:
_appendValue(parent, tag, item)
else:
new_element = cetree.makeElement(
tag, parent._doc, None, None, None, None, None)
_setElementValue(new_element, value)
cetree.appendChildToElement(parent, new_element)
cdef _setElementValue(_Element element, value):
if value is None:
cetree.setAttributeValue(
element, XML_SCHEMA_INSTANCE_NIL_ATTR, u"true")
elif isinstance(value, _Element):
_replaceElement(element, value)
return
else:
cetree.delAttributeFromNsName(
element._c_node, _XML_SCHEMA_INSTANCE_NS, <unsigned char*>"nil")
if python._isString(value):
pytype_name = u"str"
py_type = <PyType>_PYTYPE_DICT.get(pytype_name)
else:
pytype_name = _typename(value)
py_type = <PyType>_PYTYPE_DICT.get(pytype_name)
if py_type is not None:
value = py_type.stringify(value)
else:
value = unicode(value)
if py_type is not None:
cetree.setAttributeValue(element, PYTYPE_ATTRIBUTE, pytype_name)
else:
cetree.delAttributeFromNsName(
element._c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
cetree.setNodeText(element._c_node, value)
cdef _setSlice(sliceobject, _Element target, items):
cdef _Element parent
cdef tree.xmlNode* c_node
cdef Py_ssize_t c_step, c_start, pos
# collect existing slice
if (<slice>sliceobject).step is None:
c_step = 1
else:
c_step = (<slice>sliceobject).step
if c_step == 0:
raise ValueError, u"Invalid slice"
cdef list del_items = target[sliceobject]
# collect new values
new_items = []
tag = target.tag
for item in items:
if isinstance(item, _Element):
# deep copy the new element
new_element = cetree.deepcopyNodeToDocument(
target._doc, (<_Element>item)._c_node)
new_element.tag = tag
else:
new_element = cetree.makeElement(
tag, target._doc, None, None, None, None, None)
_setElementValue(new_element, item)
new_items.append(new_element)
# sanity check - raise what a list would raise
if c_step != 1 and len(del_items) != len(new_items):
raise ValueError, \
f"attempt to assign sequence of size {len(new_items)} to extended slice of size {len(del_items)}"
# replace existing items
pos = 0
parent = target.getparent()
replace = parent.replace
while pos < len(new_items) and pos < len(del_items):
replace(del_items[pos], new_items[pos])
pos += 1
# remove leftover items
if pos < len(del_items):
remove = parent.remove
while pos < len(del_items):
remove(del_items[pos])
pos += 1
# append remaining new items
if pos < len(new_items):
# the sanity check above guarantees (step == 1)
if pos > 0:
item = new_items[pos-1]
else:
if (<slice>sliceobject).start > 0:
c_node = parent._c_node.children
else:
c_node = parent._c_node.last
c_node = _findFollowingSibling(
c_node, tree._getNs(target._c_node), target._c_node.name,
(<slice>sliceobject).start - 1)
if c_node is NULL:
while pos < len(new_items):
cetree.appendChildToElement(parent, new_items[pos])
pos += 1
return
item = cetree.elementFactory(parent._doc, c_node)
while pos < len(new_items):
add = item.addnext
item = new_items[pos]
add(item)
pos += 1
################################################################################
# Data type support in subclasses
cdef class ObjectifiedDataElement(ObjectifiedElement):
u"""This is the base class for all data type Elements. Subclasses should
override the 'pyval' property and possibly the __str__ method.
"""
@property
def pyval(self):
return textOf(self._c_node)
def __str__(self):
return textOf(self._c_node) or ''
def __repr__(self):
return strrepr(textOf(self._c_node) or '')
def _setText(self, s):
u"""For use in subclasses only. Don't use unless you know what you are
doing.
"""
cetree.setNodeText(self._c_node, s)
cdef class NumberElement(ObjectifiedDataElement):
cdef object _parse_value
def _setValueParser(self, function):
u"""Set the function that parses the Python value from a string.
Do not use this unless you know what you are doing.
"""
self._parse_value = function
@property
def pyval(self):
return _parseNumber(self)
def __int__(self):
return int(_parseNumber(self))
def __long__(self):
return long(_parseNumber(self))
def __float__(self):
return float(_parseNumber(self))
def __complex__(self):
return complex(_parseNumber(self))
def __str__(self):
return unicode(_parseNumber(self))
def __repr__(self):
return repr(_parseNumber(self))
def __oct__(self):
return oct(_parseNumber(self))
def __hex__(self):
return hex(_parseNumber(self))
def __richcmp__(self, other, int op):
return _richcmpPyvals(self, other, op)
def __hash__(self):
return hash(_parseNumber(self))
def __add__(self, other):
return _numericValueOf(self) + _numericValueOf(other)
def __radd__(self, other):
return _numericValueOf(other) + _numericValueOf(self)
def __sub__(self, other):
return _numericValueOf(self) - _numericValueOf(other)
def __rsub__(self, other):
return _numericValueOf(other) - _numericValueOf(self)
def __mul__(self, other):
return _numericValueOf(self) * _numericValueOf(other)
def __rmul__(self, other):
return _numericValueOf(other) * _numericValueOf(self)
def __div__(self, other):
return _numericValueOf(self) / _numericValueOf(other)
def __rdiv__(self, other):
return _numericValueOf(other) / _numericValueOf(self)
def __truediv__(self, other):
return _numericValueOf(self) / _numericValueOf(other)
def __rtruediv__(self, other):
return _numericValueOf(other) / _numericValueOf(self)
def __floordiv__(self, other):
return _numericValueOf(self) // _numericValueOf(other)
def __rfloordiv__(self, other):
return _numericValueOf(other) // _numericValueOf(self)
def __mod__(self, other):
return _numericValueOf(self) % _numericValueOf(other)
def __rmod__(self, other):
return _numericValueOf(other) % _numericValueOf(self)
def __divmod__(self, other):
return divmod(_numericValueOf(self), _numericValueOf(other))
def __rdivmod__(self, other):
return divmod(_numericValueOf(other), _numericValueOf(self))
def __pow__(self, other, modulo):
if modulo is None:
return _numericValueOf(self) ** _numericValueOf(other)
else:
return pow(_numericValueOf(self), _numericValueOf(other), modulo)
def __rpow__(self, other, modulo):
if modulo is None:
return _numericValueOf(other) ** _numericValueOf(self)
else:
return pow(_numericValueOf(other), _numericValueOf(self), modulo)
def __neg__(self):
return - _numericValueOf(self)
def __pos__(self):
return + _numericValueOf(self)
def __abs__(self):
return abs( _numericValueOf(self) )
def __bool__(self):
return bool(_numericValueOf(self))
def __invert__(self):
return ~ _numericValueOf(self)
def __lshift__(self, other):
return _numericValueOf(self) << _numericValueOf(other)
def __rlshift__(self, other):
return _numericValueOf(other) << _numericValueOf(self)
def __rshift__(self, other):
return _numericValueOf(self) >> _numericValueOf(other)
def __rrshift__(self, other):
return _numericValueOf(other) >> _numericValueOf(self)
def __and__(self, other):
return _numericValueOf(self) & _numericValueOf(other)
def __rand__(self, other):
return _numericValueOf(other) & _numericValueOf(self)
def __or__(self, other):
return _numericValueOf(self) | _numericValueOf(other)
def __ror__(self, other):
return _numericValueOf(other) | _numericValueOf(self)
def __xor__(self, other):
return _numericValueOf(self) ^ _numericValueOf(other)
def __rxor__(self, other):
return _numericValueOf(other) ^ _numericValueOf(self)
cdef class IntElement(NumberElement):
def _init(self):
self._parse_value = int
def __index__(self):
return int(_parseNumber(self))
cdef class LongElement(NumberElement):
def _init(self):
self._parse_value = long
def __index__(self):
return int(_parseNumber(self))
cdef class FloatElement(NumberElement):
def _init(self):
self._parse_value = float
cdef class StringElement(ObjectifiedDataElement):
u"""String data class.
Note that this class does *not* support the sequence protocol of strings:
len(), iter(), str_attr[0], str_attr[0:1], etc. are *not* supported.
Instead, use the .text attribute to get a 'real' string.
"""
@property
def pyval(self):
return textOf(self._c_node) or u''
def __repr__(self):
return repr(textOf(self._c_node) or u'')
def strlen(self):
text = textOf(self._c_node)
if text is None:
return 0
else:
return len(text)
def __bool__(self):
return bool(textOf(self._c_node))
def __richcmp__(self, other, int op):
return _richcmpPyvals(self, other, op)
def __hash__(self):
return hash(textOf(self._c_node) or u'')
def __add__(self, other):
text = _strValueOf(self)
other = _strValueOf(other)
return text + other
def __radd__(self, other):
text = _strValueOf(self)
other = _strValueOf(other)
return other + text
def __mul__(self, other):
if isinstance(self, StringElement):
return (textOf((<StringElement>self)._c_node) or '') * _numericValueOf(other)
elif isinstance(other, StringElement):
return _numericValueOf(self) * (textOf((<StringElement>other)._c_node) or '')
else:
return NotImplemented
def __rmul__(self, other):
return _numericValueOf(other) * (textOf((<StringElement>self)._c_node) or '')
def __mod__(self, other):
return (_strValueOf(self) or '') % other
def __int__(self):
return int(textOf(self._c_node))
def __long__(self):
return long(textOf(self._c_node))
def __float__(self):
return float(textOf(self._c_node))
def __complex__(self):
return complex(textOf(self._c_node))
cdef class NoneElement(ObjectifiedDataElement):
def __str__(self):
return u"None"
def __repr__(self):
return "None"
def __bool__(self):
return False
def __richcmp__(self, other, int op):
if other is None or self is None:
return python.PyObject_RichCompare(None, None, op)
if isinstance(self, NoneElement):
return python.PyObject_RichCompare(None, other, op)
else:
return python.PyObject_RichCompare(self, None, op)
def __hash__(self):
return hash(None)
@property
def pyval(self):
return None
cdef class BoolElement(IntElement):
u"""Boolean type base on string values: 'true' or 'false'.
Note that this inherits from IntElement to mimic the behaviour of
Python's bool type.
"""
def _init(self):
self._parse_value = _parseBool # wraps as Python callable
def __bool__(self):
return _parseBool(textOf(self._c_node))
def __int__(self):
return 0 + _parseBool(textOf(self._c_node))
def __float__(self):
return 0.0 + _parseBool(textOf(self._c_node))
def __richcmp__(self, other, int op):
return _richcmpPyvals(self, other, op)
def __hash__(self):
return hash(_parseBool(textOf(self._c_node)))
def __str__(self):
return unicode(_parseBool(textOf(self._c_node)))
def __repr__(self):
return repr(_parseBool(textOf(self._c_node)))
@property
def pyval(self):
return _parseBool(textOf(self._c_node))
cdef _checkBool(s):
cdef int value = -1
if s is not None:
value = __parseBoolAsInt(s)
if value == -1:
raise ValueError
cdef bint _parseBool(s) except -1:
cdef int value
if s is None:
return False
value = __parseBoolAsInt(s)
if value == -1:
raise ValueError, f"Invalid boolean value: '{s}'"
return value
cdef inline int __parseBoolAsInt(text) except -2:
if text == 'false':
return 0
elif text == 'true':
return 1
elif text == '0':
return 0
elif text == '1':
return 1
return -1
cdef object _parseNumber(NumberElement element):
return element._parse_value(textOf(element._c_node))
cdef enum NumberParserState:
NPS_SPACE_PRE = 0
NPS_SIGN = 1
NPS_DIGITS = 2
NPS_POINT_LEAD = 3
NPS_POINT = 4
NPS_FRACTION = 5
NPS_EXP = 6
NPS_EXP_SIGN = 7
NPS_DIGITS_EXP = 8
NPS_SPACE_TAIL = 9
NPS_INF1 = 20
NPS_INF2 = 21
NPS_INF3 = 22
NPS_NAN1 = 23
NPS_NAN2 = 24
NPS_NAN3 = 25
NPS_ERROR = 99
ctypedef fused bytes_unicode:
bytes
unicode
cdef _checkNumber(bytes_unicode s, bint allow_float):
cdef Py_UCS4 c
cdef NumberParserState state = NPS_SPACE_PRE
for c in s:
if c.isdigit() if (bytes_unicode is unicode) else c in b'0123456789':
if state in (NPS_DIGITS, NPS_FRACTION, NPS_DIGITS_EXP):
pass
elif state in (NPS_SPACE_PRE, NPS_SIGN):
state = NPS_DIGITS
elif state in (NPS_POINT_LEAD, NPS_POINT):
state = NPS_FRACTION
elif state in (NPS_EXP, NPS_EXP_SIGN):
state = NPS_DIGITS_EXP
else:
state = NPS_ERROR
else:
if c == u'.':
if state in (NPS_SPACE_PRE, NPS_SIGN):
state = NPS_POINT_LEAD
elif state == NPS_DIGITS:
state = NPS_POINT
else:
state = NPS_ERROR
if not allow_float:
state = NPS_ERROR
elif c in u'-+':