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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
|
from etreepublic cimport _Document, _Element, ElementBase
from etreepublic cimport _ElementIterator, ElementClassLookup
from etreepublic cimport elementFactory, import_etree, textOf
from python cimport callable, _cstr
cimport etreepublic as cetree
cimport python
cimport tree
cimport cstd
cdef object etree
from lxml import etree
# initialize C-API of lxml.etree
import_etree(etree)
__version__ = etree.__version__
cdef object re
import re
cdef object __builtin__
import __builtin__
cdef object set
try:
set = __builtin__.set
except AttributeError:
from sets import Set as set
cdef object IGNORABLE_ERRORS
IGNORABLE_ERRORS = (ValueError, TypeError)
cdef object islice
from itertools import islice
cdef object _typename(object t):
cdef char* c_name
cdef char* s
c_name = python._fqtypename(t)
s = cstd.strrchr(c_name, c'.')
if s == NULL:
return c_name
else:
return (s+1)
# namespace/name for "pytype" hint attribute
cdef object PYTYPE_NAMESPACE
cdef char* _PYTYPE_NAMESPACE
cdef object PYTYPE_ATTRIBUTE_NAME
cdef char* _PYTYPE_ATTRIBUTE_NAME
PYTYPE_ATTRIBUTE = None
cdef object TREE_PYTYPE_NAME
TREE_PYTYPE_NAME = "TREE"
def setPytypeAttributeTag(attribute_tag=None):
"""Changes name and namespace of the XML attribute that holds Python type
information.
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_ATTRIBUTE_NAME
if attribute_tag is None:
PYTYPE_NAMESPACE = "http://codespeak.net/lxml/objectify/pytype"
PYTYPE_ATTRIBUTE_NAME = "pytype"
else:
PYTYPE_NAMESPACE, PYTYPE_ATTRIBUTE_NAME = cetree.getNsTag(attribute_tag)
_PYTYPE_NAMESPACE = _cstr(PYTYPE_NAMESPACE)
_PYTYPE_ATTRIBUTE_NAME = _cstr(PYTYPE_ATTRIBUTE_NAME)
PYTYPE_ATTRIBUTE = cetree.namespacedNameFromNsName(
_PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
setPytypeAttributeTag()
# namespaces for XML Schema
cdef object XML_SCHEMA_NS
XML_SCHEMA_NS = "http://www.w3.org/2001/XMLSchema"
cdef char* _XML_SCHEMA_NS
_XML_SCHEMA_NS = _cstr(XML_SCHEMA_NS)
cdef object XML_SCHEMA_INSTANCE_NS
XML_SCHEMA_INSTANCE_NS = "http://www.w3.org/2001/XMLSchema-instance"
cdef char* _XML_SCHEMA_INSTANCE_NS
_XML_SCHEMA_INSTANCE_NS = _cstr(XML_SCHEMA_INSTANCE_NS)
cdef object XML_SCHEMA_INSTANCE_NIL_ATTR
XML_SCHEMA_INSTANCE_NIL_ATTR = "{%s}nil" % XML_SCHEMA_INSTANCE_NS
cdef object XML_SCHEMA_INSTANCE_TYPE_ATTR
XML_SCHEMA_INSTANCE_TYPE_ATTR = "{%s}type" % XML_SCHEMA_INSTANCE_NS
################################################################################
# Element class for the main API
cdef class ObjectifiedElement(ElementBase):
"""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 = etree.XML("<root><c1><c2>0</c2><c2>1</c2></c1></root>")
>>> second_c2 = root.c1.c2[1]
"""
def __iter__(self):
"""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 ''
property text:
def __get__(self):
return textOf(self._c_node)
property __dict__:
"""A fake implementation for __dict__ to support dir() etc.
Note that this only considers the first child with a given name.
"""
def __get__(self):
cdef char* c_ns
cdef char* c_child_ns
cdef _Element child
c_ns = tree._getNs(self._c_node)
if c_ns is NULL:
tag = None
else:
tag = "{%s}*" % c_ns
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 = child._c_node.name
if python.PyDict_GetItem(children, name) is NULL:
python.PyDict_SetItem(children, name, child)
return children
def __len__(self):
"""Count self and siblings with the same tag.
"""
cdef tree.xmlNode* c_self_node
cdef tree.xmlNode* c_node
cdef char* c_href
cdef char* c_tag
cdef Py_ssize_t count
c_self_node = self._c_node
c_tag = c_self_node.name
c_href = tree._getNs(c_self_node)
count = 1
c_node = c_self_node.next
while c_node is not NULL:
if c_node.type == tree.XML_ELEMENT_NODE and \
cetree.tagMatches(c_node, c_href, c_tag):
count = count + 1
c_node = c_node.next
c_node = c_self_node.prev
while c_node is not NULL:
if c_node.type == tree.XML_ELEMENT_NODE and \
cetree.tagMatches(c_node, c_href, c_tag):
count = count + 1
c_node = c_node.prev
return count
def 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 = c + 1
c_node = c_node.next
return c
def 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):
python.PyList_Append(
result, cetree.elementFactory(self._doc, c_node))
c_node = c_node.next
return result
def __getattr__(self, tag):
"""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.
"""
return _lookupChildOrRaise(self, tag)
def __setattr__(self, tag, value):
"""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 == 'text' or tag == 'pyval':
# read-only !
raise TypeError, "attribute '%s' of '%s' objects is not writable"% \
(tag, _typename(self))
elif tag == 'tail':
cetree.setTailText(self._c_node, value)
return
elif tag == 'tag':
ElementBase.tag.__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):
"""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):
"""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.).
"""
cdef tree.xmlNode* c_self_node
cdef tree.xmlNode* c_parent
cdef tree.xmlNode* c_node
if python._isString(key):
return _lookupChildOrRaise(self, key)
c_self_node = self._c_node
c_parent = c_self_node.parent
if c_parent is NULL:
if key == 0:
return self
else:
raise IndexError, key
if key < 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, key)
if c_node is NULL:
raise IndexError, key
return elementFactory(self._doc, c_node)
def __setitem__(self, key, value):
"""Set the value of a sibling, counting from the first child of the
parent.
* 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 _Element new_element
cdef tree.xmlNode* c_self_node
cdef tree.xmlNode* c_parent
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
c_self_node = self._c_node
c_parent = c_self_node.parent
if c_parent is NULL:
# the 'root[i] = ...' case
raise TypeError, "index assignment to root element is invalid"
if key < 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, key)
if c_node is NULL:
raise IndexError, key
element = elementFactory(self._doc, c_node)
_replaceElement(element, value)
def __getslice__(self, Py_ssize_t start, Py_ssize_t end):
return list(islice(self, start, end))
def __setslice__(self, Py_ssize_t start, Py_ssize_t end, values):
cdef _Element el
parent = self.getparent()
if parent is None:
raise TypeError, "deleting slices of root element not supported"
# replace existing items
new_items = iter(values)
del_items = iter(list(islice(self, start, end)))
try:
for el in del_items:
item = new_items.next()
_replaceElement(el, item)
except StopIteration:
remove = parent.remove
remove(el)
for el in del_items:
remove(el)
return
# append remaining new items
tag = self.tag
for item in new_items:
_appendValue(parent, tag, item)
def __delslice__(self, Py_ssize_t start, Py_ssize_t end):
parent = self.getparent()
if parent is None:
raise TypeError, "deleting slices of root element not supported"
remove = parent.remove
for el in list(islice(self, start, end)):
remove(el)
def __delitem__(self, key):
parent = self.getparent()
if parent is None:
raise TypeError, "deleting items not supported by root element"
sibling = self.__getitem__(key)
parent.remove(sibling)
def iterfind(self, path):
# Reimplementation of Element.iterfind() to make it work without child
# iteration.
xpath = etree.ETXPath(path)
return iter(xpath(self))
def findall(self, path):
# Reimplementation of Element.findall() to make it work without child
# iteration.
xpath = etree.ETXPath(path)
return xpath(self)
def find(self, path):
# Reimplementation of Element.find() to make it work without child
# iteration.
result = self.findall(path)
if isinstance(result, list) and len(result):
return result[0]
elif isinstance(result, _Element):
return result
else:
return None
def findtext(self, path, default=None):
# Reimplementation of Element.findtext() to make it work without child
# iteration.
result = self.find(path)
if isinstance(result, _Element):
return result.text or ""
else:
return default
def 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 = '.'.join(prefix)
return _buildDescendantPaths(self._c_node, prefix)
cdef tree.xmlNode* _findFollowingSibling(tree.xmlNode* c_node,
char* href, char* 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 \
cetree.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
cdef char* c_href
cdef char* c_tag
ns, tag = cetree.getNsTag(tag)
c_tag = _cstr(tag)
c_node = parent._c_node
if ns is None:
c_href = tree._getNs(c_node)
else:
c_href = _cstr(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, "no such child: " + \
_buildChildTag(parent, tag)
return element
cdef object _buildChildTag(_Element parent, tag):
cdef char* c_href
cdef char* c_tag
ns, tag = cetree.getNsTag(tag)
c_tag = _cstr(tag)
if ns is None:
c_href = tree._getNs(parent._c_node)
else:
c_href = _cstr(ns)
return cetree.namespacedNameFromNsName(c_href, c_tag)
cdef object _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 python.PyList_Check(value) or python.PyTuple_Check(value):
element.__setslice__(0, python.PY_SSIZE_T_MAX, value)
return
else:
new_element = element.makeelement(element.tag)
_setElementValue(new_element, value)
element.getparent().replace(element, new_element)
cdef object _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.appendChild(parent, new_element)
elif python.PyList_Check(value) or python.PyTuple_Check(value):
for item in value:
_appendValue(parent, tag, item)
else:
new_element = cetree.makeSubElement(
parent, tag, None, None, None, None)
_setElementValue(new_element, value)
cdef _setElementValue(_Element element, value):
cdef python.PyObject* dict_result
if value is None:
cetree.setAttributeValue(
element, XML_SCHEMA_INSTANCE_NIL_ATTR, "true")
elif isinstance(value, _Element):
_replaceElement(element, value)
else:
cetree.delAttributeFromNsName(
element._c_node, _XML_SCHEMA_INSTANCE_NS, "nil")
if python._isString(value):
pytype_name = "str"
else:
pytype_name = _typename(value)
if isinstance(value, bool):
value = _lower_bool(value)
else:
value = str(value)
dict_result = python.PyDict_GetItem(_PYTYPE_DICT, pytype_name)
if dict_result is not NULL:
cetree.setAttributeValue(element, PYTYPE_ATTRIBUTE, pytype_name)
else:
cetree.delAttributeFromNsName(element._c_node, PYTYPE_NAMESPACE,
PYTYPE_ATTRIBUTE_NAME)
cetree.setNodeText(element._c_node, value)
################################################################################
# Data type support in subclasses
cdef class ObjectifiedDataElement(ObjectifiedElement):
"""This is the base class for all data type Elements. Subclasses should
override the 'pyval' property and possibly the __str__ method.
"""
property pyval:
def __get__(self):
return textOf(self._c_node)
def __str__(self):
return textOf(self._c_node) or ''
def __repr__(self):
return textOf(self._c_node) or ''
def _setText(self, s):
"""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 _type
def _setValueParser(self, function):
"Set the function that parses the Python value from a string."
self._type = function
cdef _value(self):
return self._type(textOf(self._c_node))
property pyval:
def __get__(self):
return self._value()
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 __str__(self):
return str(self._type(textOf(self._c_node)))
def __repr__(self):
return repr(self._type(textOf(self._c_node)))
# def __oct__(self):
# def __hex__(self):
def __richcmp__(self, other, int op):
if hasattr(other, 'pyval'):
other = other.pyval
return python.PyObject_RichCompare(
_numericValueOf(self), other, op)
def __add__(self, other):
return _numericValueOf(self) + _numericValueOf(other)
def __sub__(self, other):
return _numericValueOf(self) - _numericValueOf(other)
def __mul__(self, other):
return _numericValueOf(self) * _numericValueOf(other)
def __div__(self, other):
return _numericValueOf(self) / _numericValueOf(other)
def __truediv__(self, other):
return _numericValueOf(self) / _numericValueOf(other)
def __mod__(self, other):
return _numericValueOf(self) % _numericValueOf(other)
def __pow__(self, other, modulo):
if modulo is None:
return _numericValueOf(self) ** _numericValueOf(other)
else:
return pow(_numericValueOf(self), _numericValueOf(other), modulo)
def __neg__(self):
return - _numericValueOf(self)
def __pos__(self):
return + _numericValueOf(self)
def __abs__(self):
return abs( _numericValueOf(self) )
def __nonzero__(self):
return _numericValueOf(self) != 0
def __invert__(self):
return ~ _numericValueOf(self)
def __lshift__(self, other):
return _numericValueOf(self) << _numericValueOf(other)
def __rshift__(self, other):
return _numericValueOf(self) >> _numericValueOf(other)
def __and__(self, other):
return _numericValueOf(self) & _numericValueOf(other)
def __or__(self, other):
return _numericValueOf(self) | _numericValueOf(other)
def __xor__(self, other):
return _numericValueOf(self) ^ _numericValueOf(other)
cdef class IntElement(NumberElement):
def _init(self):
self._type = int
cdef class LongElement(NumberElement):
def _init(self):
self._type = long
cdef class FloatElement(NumberElement):
def _init(self):
self._type = float
cdef class StringElement(ObjectifiedDataElement):
"""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 pyval:
def __get__(self):
return textOf(self._c_node) or ''
def __repr__(self):
return repr(textOf(self._c_node) or '')
def strlen(self):
text = textOf(self._c_node)
if text is None:
return 0
else:
return len(text)
def __nonzero__(self):
text = textOf(self._c_node)
if text is None:
return False
return len(text) > 0
def __richcmp__(self, other, int op):
if hasattr(other, 'pyval'):
other = other.pyval
return python.PyObject_RichCompare(
_strValueOf(self), other, op)
def __add__(self, other):
text = _strValueOf(self)
other = _strValueOf(other)
if text is None:
return other
if other is None:
return text
return text + other
def __mul__(self, other):
if isinstance(self, StringElement):
return textOf((<StringElement>self)._c_node) * _numericValueOf(other)
elif isinstance(other, StringElement):
return _numericValueOf(self) * textOf((<StringElement>other)._c_node)
else:
raise TypeError, "invalid types for * operator"
def __mod__(self, other):
if python.PyTuple_Check(other):
l = []
for item in other:
python.PyList_Append(l, _strValueOf(item))
other = tuple(l)
else:
other = _strValueOf(other)
return _strValueOf(self) % other
cdef class NoneElement(ObjectifiedDataElement):
def __str__(self):
return "None"
def __repr__(self):
return "None"
def __nonzero__(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)
property pyval:
def __get__(self):
return None
cdef class BoolElement(ObjectifiedDataElement):
"""Boolean type base on string values: 'true' or 'false'.
"""
cdef int _boolval(self) except -1:
cdef char* c_str
text = textOf(self._c_node)
if text is None:
return 0
c_str = _cstr(text)
if c_str[0] == c'0' or c_str[0] == c'f' or c_str[0] == c'F':
if c_str[1] == c'\0' or text == "false" or text.lower() == "false":
# '0' or 'f' or 'false'
return 0
elif c_str[0] == c'1' or c_str[0] == c't' or c_str[0] == c'T':
if c_str[1] == c'\0' or text == "true" or text.lower() == "true":
# '1' or 't' or 'true'
return 1
raise ValueError, "Invalid boolean value: '%s'" % text
def __nonzero__(self):
if self._boolval():
return True
else:
return False
def __richcmp__(self, other, int op):
if hasattr(other, 'pyval'):
other = other.pyval
if hasattr(self, 'pyval'):
self_val = self.pyval
else:
self_val = bool(self)
return python.PyObject_RichCompare(self_val, other, op)
def __str__(self):
if self._boolval():
return "True"
else:
return "False"
def __repr__(self):
if self._boolval():
return "True"
else:
return "False"
property pyval:
def __get__(self):
return self.__nonzero__()
def __checkBool(s):
if s != 'true' and s != 'false' and s != '1' and s != '0':
raise ValueError
cdef object _strValueOf(obj):
if python._isString(obj):
return obj
if isinstance(obj, _Element):
return textOf((<_Element>obj)._c_node)
if obj is None:
return ''
return str(obj)
cdef object _numericValueOf(obj):
if isinstance(obj, NumberElement):
return (<NumberElement>obj)._type(
textOf((<NumberElement>obj)._c_node))
elif hasattr(obj, 'pyval'):
# not always numeric, but Python will raise the right exception
return obj.pyval
return obj
################################################################################
# Python type registry
cdef class PyType:
"""User defined type.
Named type that contains a type check function and a type class that
inherits from ObjectifiedDataElement. The type check must take a string
as argument and raise ValueError or TypeError if it cannot handle the
string value. It may be None in which case it is not considered for type
guessing.
Example::
PyType('int', int, MyIntClass).register()
Note that the order in which types are registered matters. The first
matching type will be used.
"""
cdef readonly object name
cdef readonly object type_check
cdef object _add_text
cdef object _type
cdef object _schema_types
def __init__(self, name, type_check, type_class, stringify=None):
if not python._isString(name):
raise TypeError, "Type name must be a string"
if type_check is not None and not callable(type_check):
raise TypeError, "Type check function must be callable (or None)"
if name != TREE_PYTYPE_NAME and \
not issubclass(type_class, ObjectifiedDataElement):
raise TypeError, \
"Data classes must inherit from ObjectifiedDataElement"
self.name = name
self._type = type_class
self.type_check = type_check
if stringify is None:
self._add_text = _StringValueSetter(str)
else:
self._add_text = _StringValueSetter(stringify)
self._schema_types = []
def __repr__(self):
return "PyType(%s, %s)" % (self.name, self._type.__name__)
def register(self, before=None, after=None):
"""Register the type.
The additional keyword arguments 'before' and 'after' accept a
sequence of type names that must appear before/after the new type in
the type list. If any of them is not currently known, it is simply
ignored. Raises ValueError if the dependencies cannot be fulfilled.
"""
if self.name == TREE_PYTYPE_NAME:
raise ValueError, "Cannot register tree type"
if self.type_check is not None:
for item in _TYPE_CHECKS:
if item[0] is self.type_check:
_TYPE_CHECKS.remove(item)
break
entry = (self.type_check, self)
first_pos = 0
last_pos = -1
if before or after:
if before is None:
before = ()
elif after is None:
after = ()
for i, (check, pytype) in enumerate(_TYPE_CHECKS):
if last_pos == -1 and pytype.name in before:
last_pos = i
if pytype.name in after:
first_pos = i+1
if last_pos == -1:
_TYPE_CHECKS.append(entry)
elif first_pos > last_pos:
raise ValueError, "inconsistent before/after dependencies"
else:
_TYPE_CHECKS.insert(last_pos, entry)
_PYTYPE_DICT[self.name] = self
for xs_type in self._schema_types:
_SCHEMA_TYPE_DICT[xs_type] = self
def unregister(self):
if _PYTYPE_DICT.get(self.name) is self:
del _PYTYPE_DICT[self.name]
for xs_type, pytype in _SCHEMA_TYPE_DICT.items():
if pytype is self:
del _SCHEMA_TYPE_DICT[xs_type]
if self.type_check is None:
return
try:
_TYPE_CHECKS.remove( (self.type_check, self) )
except ValueError:
pass
property xmlSchemaTypes:
"""The list of XML Schema datatypes this Python type maps to.
Note that this must be set before registering the type!
"""
def __get__(self):
return self._schema_types
def __set__(self, types):
self._schema_types = list(types)
cdef class _StringValueSetter:
cdef object _stringify
def __init__(self, stringify):
self._stringify = stringify
def __call__(self, elem, value):
_add_text(elem, self._stringify(value))
cdef object _PYTYPE_DICT
_PYTYPE_DICT = {}
cdef object _SCHEMA_TYPE_DICT
_SCHEMA_TYPE_DICT = {}
cdef object _TYPE_CHECKS
_TYPE_CHECKS = []
cdef _lower_bool(b):
if b:
return "true"
else:
return "false"
def __lower_bool(b):
return _lower_bool(b)
cdef _pytypename(obj):
if python._isString(obj):
return "str"
else:
return _typename(obj)
def pytypename(obj):
"""Find the name of the corresponding PyType for a Python object.
"""
return _pytypename(obj)
cdef _registerPyTypes():
pytype = PyType('int', int, IntElement)
pytype.xmlSchemaTypes = ("int", "short", "byte", "unsignedShort",
"unsignedByte",)
pytype.register()
pytype = PyType('long', long, LongElement)
pytype.xmlSchemaTypes = ("integer", "nonPositiveInteger", "negativeInteger",
"long", "nonNegativeInteger", "unsignedLong",
"unsignedInt", "positiveInteger",)
pytype.register()
pytype = PyType('float', float, FloatElement)
pytype.xmlSchemaTypes = ("double", "float")
pytype.register()
pytype = PyType('bool', __checkBool, BoolElement, __lower_bool)
pytype.xmlSchemaTypes = ("boolean",)
pytype.register()
pytype = PyType('str', None, StringElement)
pytype.xmlSchemaTypes = ("string", "normalizedString", "token", "language",
"Name", "NCName", "ID", "IDREF", "ENTITY",
"NMTOKEN", )
pytype.register()
# since lxml 2.0
pytype = PyType('NoneType', None, NoneElement)
pytype.register()
# backwards compatibility
pytype = PyType('none', None, NoneElement)
pytype.register()
# non-registered PyType for inner tree elements
cdef object TREE_PYTYPE
TREE_PYTYPE = PyType(TREE_PYTYPE_NAME, None, ObjectifiedElement)
_registerPyTypes()
def getRegisteredTypes():
"""Returns a list of the currently registered PyType objects.
To add a new type, retrieve this list and call unregister() for all
entries. Then add the new type at a suitable position (possibly replacing
an existing one) and call register() for all entries.
This is necessary if the new type interferes with the type check functions
of existing ones (normally only int/float/bool) and must the tried before
other types. To add a type that is not yet parsable by the current type
check functions, you can simply register() it, which will append it to the
end of the type list.
"""
types = []
known = set()
add_to_known = known.add
for check, pytype in _TYPE_CHECKS:
name = pytype.name
if name not in known:
add_to_known(name)
python.PyList_Append(types, pytype)
for pytype in _PYTYPE_DICT.itervalues():
name = pytype.name
if name not in known:
add_to_known(name)
python.PyList_Append(types, pytype)
return types
cdef PyType _guessPyType(value, PyType defaulttype):
if value is None:
return None
for type_check, tested_pytype in _TYPE_CHECKS:
try:
type_check(value)
return <PyType>tested_pytype
except IGNORABLE_ERRORS:
# could not be parsed as the specififed type => ignore
pass
return defaulttype
cdef object _guessElementClass(tree.xmlNode* c_node):
value = textOf(c_node)
if value is None:
return None
if value == '':
return StringElement
for type_check, pytype in _TYPE_CHECKS:
try:
type_check(value)
return (<PyType>pytype)._type
except IGNORABLE_ERRORS:
pass
return None
################################################################################
# adapted ElementMaker supports registered PyTypes
cdef class _ObjectifyElementMakerCaller # forward declaration
cdef extern from "etree_defs.h":
# macro call to 't->tp_new()' for fast instantiation
cdef _ObjectifyElementMakerCaller NEW_ELEMENT_MAKER "PY_NEW" (object t)
cdef class ElementMaker:
cdef object _makeelement
cdef object _namespace
cdef object _nsmap
cdef bint _annotate
def __init__(self, namespace=None, nsmap=None, annotate=True,
makeelement=None):
if nsmap is None:
nsmap = _DEFAULT_NSMAP
self._nsmap = nsmap
if namespace is None:
self._namespace = None
else:
self._namespace = "{%s}" % namespace
self._annotate = annotate
if makeelement is not None:
assert callable(makeelement)
self._makeelement = makeelement
else:
self._makeelement = None
def __getattr__(self, tag):
cdef _ObjectifyElementMakerCaller element_maker
if self._namespace is not None and tag[0] != "{":
tag = self._namespace + tag
element_maker = NEW_ELEMENT_MAKER(_ObjectifyElementMakerCaller)
element_maker._tag = tag
element_maker._nsmap = self._nsmap
element_maker._annotate = self._annotate
element_maker._element_factory = self._makeelement
return element_maker
cdef class _ObjectifyElementMakerCaller:
cdef object _tag
cdef object _nsmap
cdef object _element_factory
cdef bint _annotate
def __call__(self, *children, **attrib):
cdef _ObjectifyElementMakerCaller elementMaker
cdef python.PyObject* pytype
cdef _Element element
cdef _Element childElement
cdef bint has_children
cdef bint has_string_value
if self._element_factory is None:
element = _makeElement(self._tag, None, attrib, self._nsmap)
else:
element = self._element_factory(self._tag, attrib, self._nsmap)
pytype_name = None
has_children = 0
has_string_value = 0
for child in children:
if child is None:
if python.PyTuple_GET_SIZE(children) == 1:
cetree.setAttributeValue(
element, XML_SCHEMA_INSTANCE_NIL_ATTR, "true")
elif python._isString(child):
_add_text(element, child)
has_string_value = 1
elif isinstance(child, _Element):
cetree.appendChild(element, <_Element>child)
has_children = 1
elif isinstance(child, _ObjectifyElementMakerCaller):
elementMaker = <_ObjectifyElementMakerCaller>child
if elementMaker._element_factory is None:
cetree.makeSubElement(element, elementMaker._tag,
None, None, None, None)
else:
childElement = elementMaker._element_factory(
elementMaker._tag)
cetree.appendChild(element, childElement)
has_children = 1
else:
if pytype_name is not None:
# concatenation always makes the result a string
has_string_value = 1
pytype_name = _typename(child)
pytype = python.PyDict_GetItem(_PYTYPE_DICT, pytype_name)
if pytype is not NULL:
(<PyType>pytype)._add_text(element, child)
else:
has_string_value = 1
child = str(child)
_add_text(element, child)
if self._annotate and not has_children:
if has_string_value:
cetree.setAttributeValue(element, PYTYPE_ATTRIBUTE, "str")
elif pytype_name is not None:
cetree.setAttributeValue(element, PYTYPE_ATTRIBUTE, pytype_name)
return element
cdef _add_text(_Element elem, text):
cdef tree.xmlNode* c_child
c_child = cetree.findChildBackwards(elem._c_node, 0)
if c_child is not NULL:
old = cetree.tailOf(c_child)
if old is not None:
text = old + text
cetree.setTailText(c_child, text)
else:
old = cetree.textOf(elem._c_node)
if old is not None:
text = old + text
cetree.setNodeText(elem._c_node, text)
################################################################################
# Recursive element dumping
cdef bint __RECURSIVE_STR
__RECURSIVE_STR = 0 # default: off
def enableRecursiveStr(on=True):
"""Enable a recursively generated tree representation for str(element),
based on objectify.dump(element).
"""
global __RECURSIVE_STR
__RECURSIVE_STR = on
def dump(_Element element not None):
"""Return a recursively generated string representation of an element.
"""
return _dump(element, 0)
cdef object _dump(_Element element, int indent):
indentstr = " " * indent
if isinstance(element, ObjectifiedDataElement):
value = repr(element)
else:
value = textOf(element._c_node)
if value is not None:
if python.PyString_GET_SIZE( value.strip() ) == 0:
value = None
else:
value = repr(value)
result = "%s%s = %s [%s]\n" % (indentstr, element.tag,
value, _typename(element))
xsi_ns = "{%s}" % XML_SCHEMA_INSTANCE_NS
pytype_ns = "{%s}" % PYTYPE_NAMESPACE
for name, value in cetree.iterattributes(element, 3):
if '{' in name:
if name == PYTYPE_ATTRIBUTE:
if value == TREE_PYTYPE_NAME:
continue
else:
name = name.replace(pytype_ns, 'py:')
name = name.replace(xsi_ns, 'xsi:')
result = result + "%s * %s = %r\n" % (indentstr, name, value)
indent = indent + 1
for child in element.iterchildren():
result = result + _dump(child, indent)
if indent == 1:
return result[:-1] # strip last '\n'
else:
return result
################################################################################
# Pickle support
cdef void _setupPickle(reduceFunction):
import copy_reg
copy_reg.constructor(fromstring)
copy_reg.pickle(ObjectifiedElement, reduceFunction, fromstring)
def pickleReduce(obj):
return (fromstring, (etree.tostring(obj),))
_setupPickle(pickleReduce)
del pickleReduce
################################################################################
# Element class lookup
cdef class ObjectifyElementClassLookup(ElementClassLookup):
"""Element class lookup method that uses the objectify classes.
"""
cdef object empty_data_class
cdef object tree_class
def __init__(self, tree_class=None, empty_data_class=None):
"""Lookup mechanism for objectify.
The default Element classes can be replaced by passing subclasses of
ObjectifiedElement and ObjectifiedDataElement as keyword arguments.
'tree_class' defines inner tree classes (defaults to
ObjectifiedElement), 'empty_data_class' defines the default class for
empty data elements (defauls to StringElement).
"""
self._lookup_function = _lookupElementClass
if tree_class is None:
tree_class = ObjectifiedElement
self.tree_class = tree_class
if empty_data_class is None:
empty_data_class = StringElement
self.empty_data_class = empty_data_class
cdef object _lookupElementClass(state, _Document doc, tree.xmlNode* c_node):
cdef ObjectifyElementClassLookup lookup
cdef python.PyObject* dict_result
lookup = <ObjectifyElementClassLookup>state
# if element has children => no data class
if cetree.hasChild(c_node):
return lookup.tree_class
# if element is defined as xsi:nil, return NoneElement class
if "true" == cetree.attributeValueFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "nil"):
return NoneElement
# check for Python type hint
value = cetree.attributeValueFromNsName(
c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
if value is not None:
if value == TREE_PYTYPE_NAME:
return lookup.tree_class
dict_result = python.PyDict_GetItem(_PYTYPE_DICT, value)
if dict_result is not NULL:
return (<PyType>dict_result)._type
# unknown 'pyval' => try to figure it out ourself, just go on
# check for XML Schema type hint
value = cetree.attributeValueFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "type")
if value is not None:
dict_result = python.PyDict_GetItem(_SCHEMA_TYPE_DICT, value)
if dict_result is NULL and ':' in value:
prefix, value = value.split(':', 1)
dict_result = python.PyDict_GetItem(_SCHEMA_TYPE_DICT, value)
if dict_result is not NULL:
return (<PyType>dict_result)._type
# otherwise determine class based on text content type
el_class = _guessElementClass(c_node)
if el_class is not None:
return el_class
# if element is a root node => default to tree node
if c_node.parent is NULL or not tree._isElement(c_node.parent):
return lookup.tree_class
return lookup.empty_data_class
################################################################################
# Type annotations
cdef PyType _check_type(tree.xmlNode* c_node, PyType pytype):
if pytype is None:
return None
value = textOf(c_node)
try:
pytype.type_check(value)
return pytype
except IGNORABLE_ERRORS:
# could not be parsed as the specified type => ignore
pass
return None
def pyannotate(element_or_tree, ignore_old=False, ignore_xsi=False,
empty_pytype=None):
"""Recursively annotates the elements of an XML tree with 'pytype'
attributes.
If the 'ignore_old' keyword argument is True (the default), current 'pytype'
attributes will be ignored and replaced. Otherwise, they will be checked
and only replaced if they no longer fit the current text value.
Setting the keyword argument ``ignore_xsi`` to True makes the function
additionally ignore existing ``xsi:type`` annotations. The default is to
use them as a type hint.
The default annotation of empty elements can be set with the
``empty_pytype`` keyword argument. The default is not to annotate empty
elements. Pass 'str', for example, to make string values the default.
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
_annotate(element, 0, 1, ignore_xsi, ignore_old, None, empty_pytype)
def xsiannotate(element_or_tree, ignore_old=False, ignore_pytype=False,
empty_type=None):
"""Recursively annotates the elements of an XML tree with 'xsi:type'
attributes.
If the 'ignore_old' keyword argument is True (the default), current
'xsi:type' attributes will be ignored and replaced. Otherwise, they will be
checked and only replaced if they no longer fit the current text value.
Note that the mapping from Python types to XSI types is usually ambiguous.
Currently, only the first XSI type name in the corresponding PyType
definition will be used for annotation. Thus, you should consider naming
the widest type first if you define additional types.
Setting the keyword argument ``ignore_pytype`` to True makes the function
additionally ignore existing ``pytype`` annotations. The default is to
use them as a type hint.
The default annotation of empty elements can be set with the
``empty_type`` keyword argument. The default is not to annotate empty
elements. Pass 'string', for example, to make string values the default.
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
_annotate(element, 1, 0, ignore_old, ignore_pytype, empty_type, None)
def annotate(element_or_tree, ignore_old=True, ignore_xsi=False,
empty_pytype=None, empty_type=None, annotate_xsi=0,
annotate_pytype=1):
"""Recursively annotates the elements of an XML tree with 'xsi:type'
and/or 'py:pytype' attributes.
If the 'ignore_old' keyword argument is True (the default), current
'py:pytype' attributes will be ignored for the type annotation. Set to False
if you want reuse existing 'py:pytype' information (iff appropriate for the
element text value).
If the 'ignore_xsi' keyword argument is False (the default), existing
'xsi:type' attributes will be used for the type annotation, if they fit the
element text values.
Note that the mapping from Python types to XSI types is usually ambiguous.
Currently, only the first XSI type name in the corresponding PyType
definition will be used for annotation. Thus, you should consider naming
the widest type first if you define additional types.
The default 'py:pytype' annotation of empty elements can be set with the
``empty_pytype`` keyword argument. Pass 'str', for example, to make
string values the default.
The default 'xsi:type' annotation of empty elements can be set with the
``empty_type`` keyword argument. The default is not to annotate empty
elements. Pass 'string', for example, to make string values the default.
The keyword arguments 'annotate_xsi' (default: 0) and 'annotate_pytype'
(default: 1) control which kind(s) of annotation to use.
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
_annotate(element, annotate_xsi, annotate_pytype, ignore_xsi,
ignore_old, empty_type, empty_pytype)
cdef _annotate(_Element element, bint annotate_xsi, bint annotate_pytype,
bint ignore_xsi, bint ignore_pytype,
empty_type_name, empty_pytype_name):
cdef _Document doc
cdef tree.xmlNode* c_node
cdef tree.xmlNs* c_ns
cdef python.PyObject* dict_result
cdef PyType pytype, empty_pytype, StrType, NoneType
if not annotate_xsi and not annotate_pytype:
return
doc = element._doc
if empty_type_name is not None:
dict_result = python.PyDict_GetItem(_SCHEMA_TYPE_DICT, empty_type_name)
elif empty_pytype_name is not None:
dict_result = python.PyDict_GetItem(_PYTYPE_DICT, empty_pytype_name)
else:
dict_result = NULL
if dict_result is not NULL:
empty_pytype = <PyType>dict_result
else:
empty_pytype = None
StrType = _PYTYPE_DICT.get('str')
NoneType = _PYTYPE_DICT.get('NoneType')
c_node = element._c_node
tree.BEGIN_FOR_EACH_ELEMENT_FROM(c_node, c_node, 1)
if c_node.type == tree.XML_ELEMENT_NODE:
typename = None
pytype = None
value = None
istree = 0
# if element is defined as xsi:nil, represent it as None
if cetree.attributeValueFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "nil") == "true":
pytype = NoneType
if pytype is None and not ignore_xsi:
# check that old xsi type value is valid
typename = cetree.attributeValueFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "type")
if typename is not None:
dict_result = python.PyDict_GetItem(
_SCHEMA_TYPE_DICT, typename)
if dict_result is NULL and ':' in typename:
prefix, typename = typename.split(':', 1)
dict_result = python.PyDict_GetItem(
_SCHEMA_TYPE_DICT, typename)
if dict_result is not NULL:
pytype = <PyType>dict_result
if pytype is not StrType:
# StrType does not have a typecheck but is the default
# anyway, so just accept it if given as type
# information
pytype = _check_type(c_node, pytype)
if pytype is None:
typename = None
if pytype is None and not ignore_pytype:
# check that old pytype value is valid
old_pytypename = cetree.attributeValueFromNsName(
c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
if old_pytypename is not None:
if old_pytypename == TREE_PYTYPE_NAME:
if not cetree.hasChild(c_node):
# only case where we should keep it,
# everything else is clear enough
pytype = TREE_PYTYPE
else:
if old_pytypename == 'none':
# transition from lxml 1.x
old_pytypename = "NoneType"
dict_result = python.PyDict_GetItem(
_PYTYPE_DICT, old_pytypename)
if dict_result is not NULL:
pytype = <PyType>dict_result
if pytype is not StrType:
# StrType does not have a typecheck but is the
# default anyway, so just accept it if given as
# type information
pytype = _check_type(c_node, pytype)
if pytype is None:
# try to guess type
if not cetree.hasChild(c_node):
# element has no children => data class
pytype = _guessPyType(textOf(c_node), StrType)
else:
istree = 1
if pytype is None:
# use default type for empty elements
if cetree.hasText(c_node):
pytype = StrType
else:
pytype = empty_pytype
if typename is None:
typename = empty_type_name
if pytype is not None:
if typename is None:
if not istree:
if python.PyList_GET_SIZE(pytype._schema_types) > 0:
# pytype->xsi:type is a 1:n mapping
# simply take the first
typename = pytype._schema_types[0]
elif typename not in pytype._schema_types:
typename = pytype._schema_types[0]
if annotate_xsi:
if typename is None or istree:
cetree.delAttributeFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "type")
else:
# update or create attribute
c_ns = cetree.findOrBuildNodeNsPrefix(
doc, c_node, _XML_SCHEMA_NS, 'xsd')
if c_ns is not NULL:
if ':' in typename:
prefix, name = typename.split(':', 1)
if c_ns.prefix is NULL or c_ns.prefix[0] == c'\0':
typename = name
elif cstd.strcmp(_cstr(prefix), c_ns.prefix) != 0:
prefix = c_ns.prefix
typename = prefix + ':' + name
elif c_ns.prefix is not NULL or c_ns.prefix[0] != c'\0':
prefix = c_ns.prefix
typename = prefix + ':' + typename
c_ns = cetree.findOrBuildNodeNsPrefix(
doc, c_node, _XML_SCHEMA_INSTANCE_NS, 'xsi')
tree.xmlSetNsProp(c_node, c_ns, "type", _cstr(typename))
if annotate_pytype:
if pytype is None:
# delete attribute if it exists
cetree.delAttributeFromNsName(
c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
else:
# update or create attribute
c_ns = cetree.findOrBuildNodeNsPrefix(
doc, c_node, _PYTYPE_NAMESPACE, 'py')
tree.xmlSetNsProp(c_node, c_ns, _PYTYPE_ATTRIBUTE_NAME,
_cstr(pytype.name))
if pytype is NoneType:
c_ns = cetree.findOrBuildNodeNsPrefix(
doc, c_node, _XML_SCHEMA_INSTANCE_NS, 'xsi')
tree.xmlSetNsProp(c_node, c_ns, "nil", "true")
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
def deannotate(element_or_tree, pytype=True, xsi=True):
"""Recursively de-annotate the elements of an XML tree by removing 'pytype'
and/or 'type' attributes.
If the 'pytype' keyword argument is True (the default), 'pytype' attributes
will be removed. If the 'xsi' keyword argument is True (the default),
'xsi:type' attributes will be removed.
"""
cdef _Element element
cdef tree.xmlNode* c_node
element = cetree.rootNodeOrRaise(element_or_tree)
c_node = element._c_node
if pytype and xsi:
tree.BEGIN_FOR_EACH_ELEMENT_FROM(c_node, c_node, 1)
if c_node.type == tree.XML_ELEMENT_NODE:
cetree.delAttributeFromNsName(
c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
cetree.delAttributeFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "type")
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
elif pytype:
tree.BEGIN_FOR_EACH_ELEMENT_FROM(c_node, c_node, 1)
if c_node.type == tree.XML_ELEMENT_NODE:
cetree.delAttributeFromNsName(
c_node, _PYTYPE_NAMESPACE, _PYTYPE_ATTRIBUTE_NAME)
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
else:
tree.BEGIN_FOR_EACH_ELEMENT_FROM(c_node, c_node, 1)
if c_node.type == tree.XML_ELEMENT_NODE:
cetree.delAttributeFromNsName(
c_node, _XML_SCHEMA_INSTANCE_NS, "type")
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
################################################################################
# Module level parser setup
cdef object __DEFAULT_PARSER
__DEFAULT_PARSER = etree.XMLParser(remove_blank_text=True)
__DEFAULT_PARSER.setElementClassLookup( ObjectifyElementClassLookup() )
cdef object objectify_parser
objectify_parser = __DEFAULT_PARSER
def setDefaultParser(new_parser = None):
set_default_parser(new_parser)
def set_default_parser(new_parser = None):
"""Replace the default parser used by objectify's Element() and
fromstring() functions.
The new parser must be an etree.XMLParser.
Call without arguments to reset to the original parser.
"""
global objectify_parser
if new_parser is None:
objectify_parser = __DEFAULT_PARSER
elif isinstance(new_parser, etree.XMLParser):
objectify_parser = new_parser
else:
raise TypeError, "parser must inherit from lxml.etree.XMLParser"
cdef _Element _makeElement(tag, text, attrib, nsmap):
return cetree.makeElement(tag, None, objectify_parser, text, None, attrib, nsmap)
################################################################################
# Module level factory functions
cdef object _fromstring
_fromstring = etree.fromstring
def fromstring(xml, parser=None):
"""Objectify specific version of the lxml.etree fromstring() function
that uses the objectify parser.
You can pass a different parser as second argument.
"""
if parser is None:
parser = objectify_parser
return _fromstring(xml, parser)
XML = fromstring
cdef object _parse
_parse = etree.parse
def parse(f, parser=None):
"""Parse a file or file-like object with the objectify parser.
You can pass a different parser as second argument.
"""
if parser is None:
parser = objectify_parser
return _parse(f, parser)
cdef object _DEFAULT_NSMAP
_DEFAULT_NSMAP = { "py" : PYTYPE_NAMESPACE,
"xsi" : XML_SCHEMA_INSTANCE_NS,
"xsd" : XML_SCHEMA_NS}
E = ElementMaker()
def Element(_tag, attrib=None, nsmap=None, _pytype=None, **_attributes):
"""Objectify specific version of the lxml.etree Element() factory that
always creates a structural (tree) element.
NOTE: requires parser based element class lookup activated in lxml.etree!
"""
if attrib is not None:
if python.PyDict_Size(_attributes):
attrib.update(_attributes)
_attributes = attrib
if _pytype is None:
_pytype = TREE_PYTYPE_NAME
if nsmap is None:
nsmap = _DEFAULT_NSMAP
_attributes[PYTYPE_ATTRIBUTE] = _pytype
return _makeElement(_tag, None, _attributes, nsmap)
def DataElement(_value, attrib=None, nsmap=None, _pytype=None, _xsi=None,
**_attributes):
"""Create a new element from a Python value and XML attributes taken from
keyword arguments or a dictionary passed as second argument.
Automatically adds a 'pytype' attribute for the Python type of the value,
if the type can be identified. If '_pytype' or '_xsi' are among the
keyword arguments, they will be used instead.
If the _value argument is an ObjectifiedDataElement instance, its py:pytype,
xsi:type and other attributes and nsmap are reused unless they are redefined
in attrib and/or keyword arguments.
"""
cdef python.PyObject* dict_result
if nsmap is None:
nsmap = _DEFAULT_NSMAP
if attrib is not None and attrib:
if python.PyDict_Size(_attributes):
attrib = dict(attrib)
attrib.update(_attributes)
_attributes = attrib
if isinstance(_value, ObjectifiedElement):
if _pytype is None:
if _xsi is None and not _attributes and nsmap is _DEFAULT_NSMAP:
# special case: no change!
return _value.__copy__()
if isinstance(_value, ObjectifiedDataElement):
# reuse existing nsmap unless redefined in nsmap parameter
temp = _value.nsmap
if temp is not None and temp:
temp = dict(temp)
temp.update(nsmap)
nsmap = temp
# reuse existing attributes unless redefined in attrib/_attributes
temp = _value.attrib
if temp is not None and temp:
temp = dict(temp)
temp.update(_attributes)
_attributes = temp
# reuse existing xsi:type or py:pytype attributes, unless provided as
# arguments
if _xsi is None and _pytype is None:
dict_result = python.PyDict_GetItem(_attributes,
XML_SCHEMA_INSTANCE_TYPE_ATTR)
if dict_result is not NULL:
_xsi = <object>dict_result
dict_result = python.PyDict_GetItem(_attributes, PYTYPE_ATTRIBUTE)
if dict_result is not NULL:
_pytype = <object>dict_result
if _xsi is not None:
if ':' in _xsi:
prefix, name = _xsi.split(':', 1)
ns = nsmap.get(prefix)
if ns != XML_SCHEMA_NS:
raise ValueError, "XSD types require the XSD namespace"
elif nsmap is _DEFAULT_NSMAP:
name = _xsi
_xsi = 'xsd:' + _xsi
else:
name = _xsi
for prefix, ns in nsmap.items():
if ns == XML_SCHEMA_NS:
if prefix is not None and prefix:
_xsi = prefix + ':' + _xsi
break
else:
raise ValueError, "XSD types require the XSD namespace"
python.PyDict_SetItem(_attributes, XML_SCHEMA_INSTANCE_TYPE_ATTR, _xsi)
if _pytype is None:
# allow using unregistered or even wrong xsi:type names
dict_result = python.PyDict_GetItem(_SCHEMA_TYPE_DICT, _xsi)
if dict_result is NULL:
dict_result = python.PyDict_GetItem(_SCHEMA_TYPE_DICT, name)
if dict_result is not NULL:
_pytype = (<PyType>dict_result).name
if _value is None and _pytype != "str":
_pytype = _pytype or "NoneType"
strval = None
elif python._isString(_value):
strval = _value
elif python.PyBool_Check(_value):
if _value:
strval = "true"
else:
strval = "false"
else:
strval = str(_value)
if _pytype is None:
_pytype = _pytypename(_value)
if _pytype is not None:
if _pytype == "NoneType" or _pytype == "none":
strval = None
python.PyDict_SetItem(_attributes, XML_SCHEMA_INSTANCE_NIL_ATTR, "true")
else:
# check if type information from arguments is valid
dict_result = python.PyDict_GetItem(_PYTYPE_DICT, _pytype)
if dict_result is not NULL:
type_check = (<PyType>dict_result).type_check
if type_check is not None:
type_check(strval)
python.PyDict_SetItem(_attributes, PYTYPE_ATTRIBUTE, _pytype)
return _makeElement("value", strval, _attributes, nsmap)
################################################################################
# ObjectPath
include "objectpath.pxi"
|