Repository navigation
Expand file tree
/
Copy pathElementTree.py
More file actions
2096 lines (1732 loc) · 72.8 KB
/
Copy pathElementTree.py
File metadata and controls
2096 lines (1732 loc) · 72.8 KB
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
"""Lightweight XML support for Python.
XML is an inherently hierarchical data format, and the most natural way to
represent it is with a tree. This module has two classes for this purpose:
1. ElementTree represents the whole XML document as a tree and
2. Element represents a single node in this tree.
Interactions with the whole document (reading and writing to/from files) are
usually done on the ElementTree level. Interactions with a single XML element
and its sub-elements are done on the Element level.
Element is a flexible container object designed to store hierarchical data
structures in memory. It can be described as a cross between a list and a
dictionary. Each Element has a number of properties associated with it:
'tag' - a string containing the element's name.
'attributes' - a Python dictionary storing the element's attributes.
'text' - a string containing the element's text content.
'tail' - an optional string containing text after the element's end tag.
And a number of child elements stored in a Python sequence.
To create an element instance, use the Element constructor,
or the SubElement factory function.
You can also use the ElementTree class to wrap an element structure
and convert it to and from XML.
"""
#---------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See https://www.python.org/psf/license for licensing details.
#
# ElementTree
# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
__all__ = [
# public symbols
"Comment",
"dump",
"Element", "ElementTree",
"fromstring", "fromstringlist",
"indent", "iselement", "iterparse",
"parse", "ParseError",
"PI", "ProcessingInstruction",
"QName",
"SubElement",
"tostring", "tostringlist",
"TreeBuilder",
"VERSION",
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
"canonicalize", "C14NWriterTarget",
]
VERSION = "1.3.0"
import sys
import re
import warnings
import io
import collections
import collections.abc
import contextlib
import weakref
from . import ElementPath
class ParseError(SyntaxError):
"""An error when parsing an XML document.
In addition to its exception value, a ParseError contains
two extra attributes:
'code' - the specific exception code
'position' - the line and column of the error
"""
pass
# --------------------------------------------------------------------
def iselement(element):
"""Return True if *element* appears to be an Element."""
return hasattr(element, 'tag')
class Element:
"""An XML element.
This class is the reference implementation of the Element interface.
An element's length is its number of subelements. That means if you
want to check if an element is truly empty, you should check BOTH
its length AND its text attribute.
The element tag, attribute names, and attribute values can be either
bytes or strings.
*tag* is the element name. *attrib* is an optional dictionary containing
element attributes. *extra* are additional element attributes given as
keyword arguments.
Example form:
<tag attrib>text<child/>...</tag>tail
"""
tag = None
"""The element's name."""
attrib = None
"""Dictionary of the element's attributes."""
text = None
"""
Text before first subelement. This is either a string or the value None.
Note that if there is no text, this attribute may be either
None or the empty string, depending on the parser.
"""
tail = None
"""
Text after this element's end tag, but before the next sibling element's
start tag. This is either a string or the value None. Note that if there
was no text, this attribute may be either None or an empty string,
depending on the parser.
"""
def __init__(self, tag, attrib={}, **extra):
if not isinstance(attrib, dict):
raise TypeError("attrib must be dict, not %s" % (
attrib.__class__.__name__,))
self.tag = tag
self.attrib = {**attrib, **extra}
self._children = []
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))
def makeelement(self, tag, attrib):
"""Create a new element with the same type.
*tag* is a string containing the element name.
*attrib* is a dictionary containing the element attributes.
Do not call this method, use the SubElement factory function instead.
"""
return self.__class__(tag, attrib)
def __copy__(self):
elem = self.makeelement(self.tag, self.attrib)
elem.text = self.text
elem.tail = self.tail
elem[:] = self
return elem
def __len__(self):
return len(self._children)
def __bool__(self):
warnings.warn(
"Testing an element's truth value will always return True in "
"future versions. "
"Use specific 'len(elem)' or 'elem is not None' test instead.",
DeprecationWarning, stacklevel=2
)
return len(self._children) != 0 # emulate old behaviour, for now
def __getitem__(self, index):
return self._children[index]
def __setitem__(self, index, element):
if isinstance(index, slice):
for elt in element:
self._assert_is_element(elt)
else:
self._assert_is_element(element)
self._children[index] = element
def __delitem__(self, index):
del self._children[index]
def append(self, subelement):
"""Add *subelement* to the end of this element.
The new element will appear in document order after the last existing
subelement (or directly after the text, if it's the first subelement),
but before the end tag for this element.
"""
self._assert_is_element(subelement)
self._children.append(subelement)
def extend(self, elements):
"""Append subelements from a sequence.
*elements* is a sequence with zero or more elements.
"""
for element in elements:
self._assert_is_element(element)
self._children.append(element)
def insert(self, index, subelement):
"""Insert *subelement* at position *index*."""
self._assert_is_element(subelement)
self._children.insert(index, subelement)
def _assert_is_element(self, e):
# Need to refer to the actual Python implementation, not the
# shadowing C implementation.
if not isinstance(e, _Element_Py):
raise TypeError('expected an Element, not %s' % type(e).__name__)
def remove(self, subelement):
"""Remove matching subelement.
Unlike the find methods, this method compares elements based on
identity, NOT ON tag value or contents. To remove subelements by
other means, the easiest way is to use a list comprehension to
select what elements to keep, and then use slice assignment to update
the parent element.
ValueError is raised if a matching element could not be found.
"""
# assert iselement(element)
try:
self._children.remove(subelement)
except ValueError:
# to align the error message with the C implementation
raise ValueError("Element.remove(x): element not found") from None
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
return ElementPath.find(self, path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find text for first matching element by tag name or path.
*path* is a string having either an element tag or an XPath,
*default* is the value to return if the element was not found,
*namespaces* is an optional mapping from namespace prefix to full name.
Return text content of first matching element, or default value if
none was found. Note that if an element is found having no text
content, the empty string is returned.
"""
return ElementPath.findtext(self, path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Returns list containing all matching elements in document order.
"""
return ElementPath.findall(self, path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
return ElementPath.iterfind(self, path, namespaces)
def clear(self):
"""Reset element.
This function removes all subelements, clears all attributes, and sets
the text and tail attributes to None.
"""
self.attrib.clear()
self._children = []
self.text = self.tail = None
def get(self, key, default=None):
"""Get element attribute.
Equivalent to attrib.get, but some implementations may handle this a
bit more efficiently. *key* is what attribute to look for, and
*default* is what to return if the attribute was not found.
Returns a string containing the attribute value, or the default if
attribute was not found.
"""
return self.attrib.get(key, default)
def set(self, key, value):
"""Set element attribute.
Equivalent to attrib[key] = value, but some implementations may handle
this a bit more efficiently. *key* is what attribute to set, and
*value* is the attribute value to set it to.
"""
self.attrib[key] = value
def keys(self):
"""Get list of attribute names.
Names are returned in an arbitrary order, just like an ordinary
Python dict. Equivalent to attrib.keys()
"""
return self.attrib.keys()
def items(self):
"""Get element attributes as a sequence.
The attributes are returned in arbitrary order. Equivalent to
attrib.items().
Return a list of (name, value) tuples.
"""
return self.attrib.items()
def iter(self, tag=None):
"""Create tree iterator.
The iterator loops over the element and all subelements in document
order, returning all elements with a matching tag.
If the tree structure is modified during iteration, new or removed
elements may or may not be included. To get a stable set, use the
list() function on the iterator, and loop over the resulting list.
*tag* is what tags to look for (default is to return all elements)
Return an iterator containing all the matching elements.
"""
if tag == "*":
tag = None
if tag is None or self.tag == tag:
yield self
for e in self._children:
yield from e.iter(tag)
def itertext(self):
"""Create text iterator.
The iterator loops over the element and all subelements in document
order, returning all inner text.
"""
tag = self.tag
if not isinstance(tag, str) and tag is not None:
return
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def SubElement(parent, tag, attrib={}, **extra):
"""Subelement factory which creates an element instance, and appends it
to an existing parent.
The element tag, attribute names, and attribute values can be either
bytes or Unicode strings.
*parent* is the parent element, *tag* is the subelements name, *attrib* is
an optional directory containing element attributes, *extra* are
additional attributes given as keyword arguments.
"""
attrib = {**attrib, **extra}
element = parent.makeelement(tag, attrib)
parent.append(element)
return element
def Comment(text=None):
"""Comment element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*text* is a string containing the comment string.
"""
element = Element(Comment)
element.text = text
return element
def ProcessingInstruction(target, text=None):
"""Processing Instruction element factory.
This function creates a special element which the standard serializer
serializes as an XML comment.
*target* is a string containing the processing instruction, *text* is a
string containing the processing instruction contents, if any.
"""
element = Element(ProcessingInstruction)
element.text = target
if text:
element.text = element.text + " " + text
return element
PI = ProcessingInstruction
class QName:
"""Qualified name wrapper.
This class can be used to wrap a QName attribute value in order to get
proper namespace handing on output.
*text_or_uri* is a string containing the QName value either in the form
{uri}local, or if the tag argument is given, the URI part of a QName.
*tag* is an optional argument which if given, will make the first
argument (text_or_uri) be interpreted as a URI, and this argument (tag)
be interpreted as a local name.
"""
def __init__(self, text_or_uri, tag=None):
if tag:
text_or_uri = "{%s}%s" % (text_or_uri, tag)
self.text = text_or_uri
def __str__(self):
return self.text
def __repr__(self):
return '<%s %r>' % (self.__class__.__name__, self.text)
def __hash__(self):
return hash(self.text)
def __le__(self, other):
if isinstance(other, QName):
return self.text <= other.text
return self.text <= other
def __lt__(self, other):
if isinstance(other, QName):
return self.text < other.text
return self.text < other
def __ge__(self, other):
if isinstance(other, QName):
return self.text >= other.text
return self.text >= other
def __gt__(self, other):
if isinstance(other, QName):
return self.text > other.text
return self.text > other
def __eq__(self, other):
if isinstance(other, QName):
return self.text == other.text
return self.text == other
# --------------------------------------------------------------------
class ElementTree:
"""An XML element hierarchy.
This class also provides support for serialization to and from
standard XML.
*element* is an optional root element node,
*file* is an optional file handle or file name of an XML file whose
contents will be used to initialize the tree with.
"""
def __init__(self, element=None, file=None):
# assert element is None or iselement(element)
self._root = element # first node
if file:
self.parse(file)
def getroot(self):
"""Return root element of this tree."""
return self._root
def _setroot(self, element):
"""Replace root element of this tree.
This will discard the current contents of the tree and replace it
with the given element. Use with care!
"""
# assert iselement(element)
self._root = element
def parse(self, source, parser=None):
"""Load external XML document into element tree.
*source* is a file name or file object, *parser* is an optional parser
instance that defaults to XMLParser.
ParseError is raised if the parser fails to parse the document.
Returns the root element of the given source document.
"""
close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True
try:
if parser is None:
# If no parser was specified, create a default XMLParser
parser = XMLParser()
if hasattr(parser, '_parse_whole'):
# The default XMLParser, when it comes from an accelerator,
# can define an internal _parse_whole API for efficiency.
# It can be used to parse the whole source without feeding
# it with chunks.
self._root = parser._parse_whole(source)
return self._root
while data := source.read(65536):
parser.feed(data)
self._root = parser.close()
return self._root
finally:
if close_source:
source.close()
def iter(self, tag=None):
"""Create and return tree iterator for the root element.
The iterator loops over all elements in this tree, in document order.
*tag* is a string with the tag name to iterate over
(default is to return all elements).
"""
# assert self._root is not None
return self._root.iter(tag)
def find(self, path, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().find(path), which is Element.find()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.find(path, namespaces)
def findtext(self, path, default=None, namespaces=None):
"""Find first matching element by tag name or path.
Same as getroot().findtext(path), which is Element.findtext()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return the first matching element, or None if no element was found.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findtext(path, default, namespaces)
def findall(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().findall(path), which is Element.findall().
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return list containing all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.findall(path, namespaces)
def iterfind(self, path, namespaces=None):
"""Find all matching subelements by tag name or path.
Same as getroot().iterfind(path), which is element.iterfind()
*path* is a string having either an element tag or an XPath,
*namespaces* is an optional mapping from namespace prefix to full name.
Return an iterable yielding all matching elements in document order.
"""
# assert self._root is not None
if path[:1] == "/":
path = "." + path
warnings.warn(
"This search is broken in 1.3 and earlier, and will be "
"fixed in a future version. If you rely on the current "
"behaviour, change it to %r" % path,
FutureWarning, stacklevel=2
)
return self._root.iterfind(path, namespaces)
def write(self, file_or_filename,
encoding=None,
xml_declaration=None,
default_namespace=None,
method=None, *,
short_empty_elements=True):
"""Write element tree to a file as XML.
Arguments:
*file_or_filename* -- file name or a file object opened for writing
*encoding* -- the output encoding (default: US-ASCII)
*xml_declaration* -- bool indicating if an XML declaration should be
added to the output. If None, an XML declaration
is added if encoding IS NOT either of:
US-ASCII, UTF-8, or Unicode
*default_namespace* -- sets the default XML namespace (for "xmlns")
*method* -- either "xml" (default), "html, "text", or "c14n"
*short_empty_elements* -- controls the formatting of elements
that contain no content. If True (default)
they are emitted as a single self-closed
tag, otherwise they are emitted as a pair
of start/end tags
"""
if not method:
method = "xml"
elif method not in _serialize:
raise ValueError("unknown method %r" % method)
if not encoding:
if method == "c14n":
encoding = "utf-8"
else:
encoding = "us-ascii"
with _get_writer(file_or_filename, encoding) as (write, declared_encoding):
if method == "xml" and (xml_declaration or
(xml_declaration is None and
encoding.lower() != "unicode" and
declared_encoding.lower() not in ("utf-8", "us-ascii"))):
write("<?xml version='1.0' encoding='%s'?>\n" % (
declared_encoding,))
if method == "text":
_serialize_text(write, self._root)
else:
qnames, namespaces = _namespaces(self._root, default_namespace)
serialize = _serialize[method]
serialize(write, self._root, qnames, namespaces,
short_empty_elements=short_empty_elements)
def write_c14n(self, file):
# lxml.etree compatibility. use output method instead
return self.write(file, method="c14n")
# --------------------------------------------------------------------
# serialization support
@contextlib.contextmanager
def _get_writer(file_or_filename, encoding):
# returns text write method and release all resources after using
try:
write = file_or_filename.write
except AttributeError:
# file_or_filename is a file name
if encoding.lower() == "unicode":
encoding="utf-8"
with open(file_or_filename, "w", encoding=encoding,
errors="xmlcharrefreplace") as file:
yield file.write, encoding
else:
# file_or_filename is a file-like object
# encoding determines if it is a text or binary writer
if encoding.lower() == "unicode":
# use a text writer as is
yield write, getattr(file_or_filename, "encoding", None) or "utf-8"
else:
# wrap a binary writer with TextIOWrapper
with contextlib.ExitStack() as stack:
if isinstance(file_or_filename, io.BufferedIOBase):
file = file_or_filename
elif isinstance(file_or_filename, io.RawIOBase):
file = io.BufferedWriter(file_or_filename)
# Keep the original file open when the BufferedWriter is
# destroyed
stack.callback(file.detach)
else:
# This is to handle passed objects that aren't in the
# IOBase hierarchy, but just have a write method
file = io.BufferedIOBase()
file.writable = lambda: True
file.write = write
try:
# TextIOWrapper uses this methods to determine
# if BOM (for UTF-16, etc) should be added
file.seekable = file_or_filename.seekable
file.tell = file_or_filename.tell
except AttributeError:
pass
file = io.TextIOWrapper(file,
encoding=encoding,
errors="xmlcharrefreplace",
newline="\n")
# Keep the original file open when the TextIOWrapper is
# destroyed
stack.callback(file.detach)
yield file.write, encoding
def _namespaces(elem, default_namespace=None):
# identify namespaces used in this tree
# maps qnames to *encoded* prefix:local names
qnames = {None: None}
# maps uri:s to prefixes
namespaces = {}
if default_namespace:
namespaces[default_namespace] = ""
def add_qname(qname):
# calculate serialized qname representation
try:
if qname[:1] == "{":
uri, tag = qname[1:].rsplit("}", 1)
prefix = namespaces.get(uri)
if prefix is None:
prefix = _namespace_map.get(uri)
if prefix is None:
prefix = "ns%d" % len(namespaces)
if prefix != "xml":
namespaces[uri] = prefix
if prefix:
qnames[qname] = "%s:%s" % (prefix, tag)
else:
qnames[qname] = tag # default element
else:
if default_namespace:
# FIXME: can this be handled in XML 1.0?
raise ValueError(
"cannot use non-qualified names with "
"default_namespace option"
)
qnames[qname] = qname
except TypeError:
_raise_serialization_error(qname)
# populate qname and namespaces table
for elem in elem.iter():
tag = elem.tag
if isinstance(tag, QName):
if tag.text not in qnames:
add_qname(tag.text)
elif isinstance(tag, str):
if tag not in qnames:
add_qname(tag)
elif tag is not None and tag is not Comment and tag is not PI:
_raise_serialization_error(tag)
for key, value in elem.items():
if isinstance(key, QName):
key = key.text
if key not in qnames:
add_qname(key)
if isinstance(value, QName) and value.text not in qnames:
add_qname(value.text)
text = elem.text
if isinstance(text, QName) and text.text not in qnames:
add_qname(text.text)
return qnames, namespaces
def _serialize_xml(write, elem, qnames, namespaces,
short_empty_elements, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("<!--%s-->" % text)
elif tag is ProcessingInstruction:
write("<?%s?>" % text)
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib(v)
write(" %s=\"%s\"" % (qnames[k], v))
if text or len(elem) or not short_empty_elements:
write(">")
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_xml(write, e, qnames, None,
short_empty_elements=short_empty_elements)
write("</" + tag + ">")
else:
write(" />")
if elem.tail:
write(_escape_cdata(elem.tail))
HTML_EMPTY = {"area", "base", "basefont", "br", "col", "embed", "frame", "hr",
"img", "input", "isindex", "link", "meta", "param", "source",
"track", "wbr"}
def _serialize_html(write, elem, qnames, namespaces, **kwargs):
tag = elem.tag
text = elem.text
if tag is Comment:
write("<!--%s-->" % _escape_cdata(text))
elif tag is ProcessingInstruction:
write("<?%s?>" % _escape_cdata(text))
else:
tag = qnames[tag]
if tag is None:
if text:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
else:
write("<" + tag)
items = list(elem.items())
if items or namespaces:
if namespaces:
for v, k in sorted(namespaces.items(),
key=lambda x: x[1]): # sort on prefix
if k:
k = ":" + k
write(" xmlns%s=\"%s\"" % (
k,
_escape_attrib(v)
))
for k, v in items:
if isinstance(k, QName):
k = k.text
if isinstance(v, QName):
v = qnames[v.text]
else:
v = _escape_attrib_html(v)
# FIXME: handle boolean attributes
write(" %s=\"%s\"" % (qnames[k], v))
write(">")
ltag = tag.lower()
if text:
if ltag == "script" or ltag == "style":
write(text)
else:
write(_escape_cdata(text))
for e in elem:
_serialize_html(write, e, qnames, None)
if ltag not in HTML_EMPTY:
write("</" + tag + ">")
if elem.tail:
write(_escape_cdata(elem.tail))
def _serialize_text(write, elem):
for part in elem.itertext():
write(part)
if elem.tail:
write(elem.tail)
_serialize = {
"xml": _serialize_xml,
"html": _serialize_html,
"text": _serialize_text,
# this optional method is imported at the end of the module
# "c14n": _serialize_c14n,
}
def register_namespace(prefix, uri):
"""Register a namespace prefix.
The registry is global, and any existing mapping for either the
given prefix or the namespace URI will be removed.
*prefix* is the namespace prefix, *uri* is a namespace uri. Tags and
attributes in this namespace will be serialized with prefix if possible.
ValueError is raised if prefix is reserved or is invalid.
"""
if re.match(r"ns\d+$", prefix):
raise ValueError("Prefix format reserved for internal use")
for k, v in list(_namespace_map.items()):
if k == uri or v == prefix:
del _namespace_map[k]
_namespace_map[uri] = prefix
_namespace_map = {
# "well-known" namespace prefixes
"http://www.w3.org/XML/1998/namespace": "xml",
"http://www.w3.org/1999/xhtml": "html",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
# xml schema
"http://www.w3.org/2001/XMLSchema": "xs",
"http://www.w3.org/2001/XMLSchema-instance": "xsi",