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
|
# -*- coding: utf-8 -*-
#
# Copyright (C) 2006-2009 Edgewall Software
# All rights reserved.
#
# This software is licensed as described in the file COPYING, which
# you should have received as part of this distribution. The terms
# are also available at http://genshi.edgewall.org/wiki/License.
#
# This software consists of voluntary contributions made by many
# individuals. For the exact contribution history, see the revision
# history and logs, available at http://genshi.edgewall.org/log/.
"""This module provides different kinds of serialization methods for XML event
streams.
"""
from itertools import chain
import re
from genshi.core import escape, Attrs, Markup, Namespace, QName, StreamEventKind
from genshi.core import START, END, TEXT, XML_DECL, DOCTYPE, START_NS, END_NS, \
START_CDATA, END_CDATA, PI, COMMENT, XML_NAMESPACE
__all__ = ['encode', 'get_serializer', 'DocType', 'XMLSerializer',
'XHTMLSerializer', 'HTMLSerializer', 'TextSerializer']
__docformat__ = 'restructuredtext en'
def encode(iterator, method='xml', encoding='utf-8', out=None):
"""Encode serializer output into a string.
:param iterator: the iterator returned from serializing a stream (basically
any iterator that yields unicode objects)
:param method: the serialization method; determines how characters not
representable in the specified encoding are treated
:param encoding: how the output string should be encoded; if set to `None`,
this method returns a `unicode` object
:param out: a file-like object that the output should be written to
instead of being returned as one big string; note that if
this is a file or socket (or similar), the `encoding` must
not be `None` (that is, the output must be encoded)
:return: a `str` or `unicode` object (depending on the `encoding`
parameter), or `None` if the `out` parameter is provided
:since: version 0.4.1
:note: Changed in 0.5: added the `out` parameter
"""
if encoding is not None:
errors = 'replace'
if method != 'text' and not isinstance(method, TextSerializer):
errors = 'xmlcharrefreplace'
_encode = lambda string: string.encode(encoding, errors)
else:
_encode = lambda string: string
if out is None:
return _encode(''.join(list(iterator)))
for chunk in iterator:
out.write(_encode(chunk))
def get_serializer(method='xml', **kwargs):
"""Return a serializer object for the given method.
:param method: the serialization method; can be either "xml", "xhtml",
"html", "text", or a custom serializer class
Any additional keyword arguments are passed to the serializer, and thus
depend on the `method` parameter value.
:see: `XMLSerializer`, `XHTMLSerializer`, `HTMLSerializer`, `TextSerializer`
:since: version 0.4.1
"""
if isinstance(method, basestring):
method = {'xml': XMLSerializer,
'xhtml': XHTMLSerializer,
'html': HTMLSerializer,
'text': TextSerializer}[method.lower()]
return method(**kwargs)
class DocType(object):
"""Defines a number of commonly used DOCTYPE declarations as constants."""
HTML_STRICT = (
'html', '-//W3C//DTD HTML 4.01//EN',
'http://www.w3.org/TR/html4/strict.dtd'
)
HTML_TRANSITIONAL = (
'html', '-//W3C//DTD HTML 4.01 Transitional//EN',
'http://www.w3.org/TR/html4/loose.dtd'
)
HTML_FRAMESET = (
'html', '-//W3C//DTD HTML 4.01 Frameset//EN',
'http://www.w3.org/TR/html4/frameset.dtd'
)
HTML = HTML_STRICT
HTML5 = ('html', None, None)
XHTML_STRICT = (
'html', '-//W3C//DTD XHTML 1.0 Strict//EN',
'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'
)
XHTML_TRANSITIONAL = (
'html', '-//W3C//DTD XHTML 1.0 Transitional//EN',
'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd'
)
XHTML_FRAMESET = (
'html', '-//W3C//DTD XHTML 1.0 Frameset//EN',
'http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd'
)
XHTML = XHTML_STRICT
XHTML11 = (
'html', '-//W3C//DTD XHTML 1.1//EN',
'http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd'
)
SVG_FULL = (
'svg', '-//W3C//DTD SVG 1.1//EN',
'http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd'
)
SVG_BASIC = (
'svg', '-//W3C//DTD SVG Basic 1.1//EN',
'http://www.w3.org/Graphics/SVG/1.1/DTD/svg11-basic.dtd'
)
SVG_TINY = (
'svg', '-//W3C//DTD SVG Tiny 1.1//EN',
'http://www.w3.org/Graphics/SVG/1.1/DTD/svg11-tiny.dtd'
)
SVG = SVG_FULL
@classmethod
def get(cls, name):
"""Return the ``(name, pubid, sysid)`` tuple of the ``DOCTYPE``
declaration for the specified name.
The following names are recognized in this version:
* "html" or "html-strict" for the HTML 4.01 strict DTD
* "html-transitional" for the HTML 4.01 transitional DTD
* "html-frameset" for the HTML 4.01 frameset DTD
* "html5" for the ``DOCTYPE`` proposed for HTML5
* "xhtml" or "xhtml-strict" for the XHTML 1.0 strict DTD
* "xhtml-transitional" for the XHTML 1.0 transitional DTD
* "xhtml-frameset" for the XHTML 1.0 frameset DTD
* "xhtml11" for the XHTML 1.1 DTD
* "svg" or "svg-full" for the SVG 1.1 DTD
* "svg-basic" for the SVG Basic 1.1 DTD
* "svg-tiny" for the SVG Tiny 1.1 DTD
:param name: the name of the ``DOCTYPE``
:return: the ``(name, pubid, sysid)`` tuple for the requested
``DOCTYPE``, or ``None`` if the name is not recognized
:since: version 0.4.1
"""
return {
'html': cls.HTML, 'html-strict': cls.HTML_STRICT,
'html-transitional': DocType.HTML_TRANSITIONAL,
'html-frameset': DocType.HTML_FRAMESET,
'html5': cls.HTML5,
'xhtml': cls.XHTML, 'xhtml-strict': cls.XHTML_STRICT,
'xhtml-transitional': cls.XHTML_TRANSITIONAL,
'xhtml-frameset': cls.XHTML_FRAMESET,
'xhtml11': cls.XHTML11,
'svg': cls.SVG, 'svg-full': cls.SVG_FULL,
'svg-basic': cls.SVG_BASIC,
'svg-tiny': cls.SVG_TINY
}.get(name.lower())
class XMLSerializer(object):
"""Produces XML text from an event stream.
>>> from genshi.builder import tag
>>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True))
>>> print(''.join(XMLSerializer()(elem.generate())))
<div><a href="foo"/><br/><hr noshade="True"/></div>
"""
_PRESERVE_SPACE = frozenset()
def __init__(self, doctype=None, strip_whitespace=True,
namespace_prefixes=None, cache=True):
"""Initialize the XML serializer.
:param doctype: a ``(name, pubid, sysid)`` tuple that represents the
DOCTYPE declaration that should be included at the top
of the generated output, or the name of a DOCTYPE as
defined in `DocType.get`
:param strip_whitespace: whether extraneous whitespace should be
stripped from the output
:param cache: whether to cache the text output per event, which
improves performance for repetitive markup
:note: Changed in 0.4.2: The `doctype` parameter can now be a string.
:note: Changed in 0.6: The `cache` parameter was added
"""
self.filters = [EmptyTagFilter()]
if strip_whitespace:
self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE))
self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes,
cache=cache))
if doctype:
self.filters.append(DocTypeInserter(doctype))
self.cache = cache
def __call__(self, stream):
have_decl = have_doctype = False
in_cdata = False
cache = {}
cache_get = cache.get
if self.cache:
def _emit(kind, input, output):
cache[kind, input] = output
return output
else:
def _emit(kind, input, output):
return output
for filter_ in self.filters:
stream = filter_(stream)
for kind, data, pos in stream:
cached = cache_get((kind, data))
if cached is not None:
yield cached
elif kind is START or kind is EMPTY:
tag, attrib = data
buf = ['<', tag]
for attr, value in attrib:
buf += [' ', attr, '="', escape(value), '"']
buf.append(kind is EMPTY and '/>' or '>')
yield _emit(kind, data, Markup(''.join(buf)))
elif kind is END:
yield _emit(kind, data, Markup('</%s>' % data))
elif kind is TEXT:
if in_cdata:
yield _emit(kind, data, data)
else:
yield _emit(kind, data, escape(data, quotes=False))
elif kind is COMMENT:
yield _emit(kind, data, Markup('<!--%s-->' % data))
elif kind is XML_DECL and not have_decl:
version, encoding, standalone = data
buf = ['<?xml version="%s"' % version]
if encoding:
buf.append(' encoding="%s"' % encoding)
if standalone != -1:
standalone = standalone and 'yes' or 'no'
buf.append(' standalone="%s"' % standalone)
buf.append('?>\n')
yield Markup(''.join(buf))
have_decl = True
elif kind is DOCTYPE and not have_doctype:
name, pubid, sysid = data
buf = ['<!DOCTYPE %s']
if pubid:
buf.append(' PUBLIC "%s"')
elif sysid:
buf.append(' SYSTEM')
if sysid:
buf.append(' "%s"')
buf.append('>\n')
yield Markup(''.join(buf)) % tuple([p for p in data if p])
have_doctype = True
elif kind is START_CDATA:
yield Markup('<![CDATA[')
in_cdata = True
elif kind is END_CDATA:
yield Markup(']]>')
in_cdata = False
elif kind is PI:
yield _emit(kind, data, Markup('<?%s %s?>' % data))
class XHTMLSerializer(XMLSerializer):
"""Produces XHTML text from an event stream.
>>> from genshi.builder import tag
>>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True))
>>> print(''.join(XHTMLSerializer()(elem.generate())))
<div><a href="foo"></a><br /><hr noshade="noshade" /></div>
"""
_EMPTY_ELEMS = frozenset(['area', 'base', 'basefont', 'br', 'col', 'frame',
'hr', 'img', 'input', 'isindex', 'link', 'meta',
'param'])
_BOOLEAN_ATTRS = frozenset(['selected', 'checked', 'compact', 'declare',
'defer', 'disabled', 'ismap', 'multiple',
'nohref', 'noresize', 'noshade', 'nowrap'])
_PRESERVE_SPACE = frozenset([
QName('pre'), QName('http://www.w3.org/1999/xhtml}pre'),
QName('textarea'), QName('http://www.w3.org/1999/xhtml}textarea')
])
def __init__(self, doctype=None, strip_whitespace=True,
namespace_prefixes=None, drop_xml_decl=True, cache=True):
super(XHTMLSerializer, self).__init__(doctype, False)
self.filters = [EmptyTagFilter()]
if strip_whitespace:
self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE))
namespace_prefixes = namespace_prefixes or {}
namespace_prefixes['http://www.w3.org/1999/xhtml'] = ''
self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes,
cache=cache))
if doctype:
self.filters.append(DocTypeInserter(doctype))
self.drop_xml_decl = drop_xml_decl
self.cache = cache
def __call__(self, stream):
boolean_attrs = self._BOOLEAN_ATTRS
empty_elems = self._EMPTY_ELEMS
drop_xml_decl = self.drop_xml_decl
have_decl = have_doctype = False
in_cdata = False
cache = {}
cache_get = cache.get
if self.cache:
def _emit(kind, input, output):
cache[kind, input] = output
return output
else:
def _emit(kind, input, output):
return output
for filter_ in self.filters:
stream = filter_(stream)
for kind, data, pos in stream:
cached = cache_get((kind, data))
if cached is not None:
yield cached
elif kind is START or kind is EMPTY:
tag, attrib = data
buf = ['<', tag]
for attr, value in attrib:
if attr in boolean_attrs:
value = attr
elif attr == 'xml:lang' and 'lang' not in attrib:
buf += [' lang="', escape(value), '"']
elif attr == 'xml:space':
continue
buf += [' ', attr, '="', escape(value), '"']
if kind is EMPTY:
if tag in empty_elems:
buf.append(' />')
else:
buf.append('></%s>' % tag)
else:
buf.append('>')
yield _emit(kind, data, Markup(''.join(buf)))
elif kind is END:
yield _emit(kind, data, Markup('</%s>' % data))
elif kind is TEXT:
if in_cdata:
yield _emit(kind, data, data)
else:
yield _emit(kind, data, escape(data, quotes=False))
elif kind is COMMENT:
yield _emit(kind, data, Markup('<!--%s-->' % data))
elif kind is DOCTYPE and not have_doctype:
name, pubid, sysid = data
buf = ['<!DOCTYPE %s']
if pubid:
buf.append(' PUBLIC "%s"')
elif sysid:
buf.append(' SYSTEM')
if sysid:
buf.append(' "%s"')
buf.append('>\n')
yield Markup(''.join(buf)) % tuple([p for p in data if p])
have_doctype = True
elif kind is XML_DECL and not have_decl and not drop_xml_decl:
version, encoding, standalone = data
buf = ['<?xml version="%s"' % version]
if encoding:
buf.append(' encoding="%s"' % encoding)
if standalone != -1:
standalone = standalone and 'yes' or 'no'
buf.append(' standalone="%s"' % standalone)
buf.append('?>\n')
yield Markup(''.join(buf))
have_decl = True
elif kind is START_CDATA:
yield Markup('<![CDATA[')
in_cdata = True
elif kind is END_CDATA:
yield Markup(']]>')
in_cdata = False
elif kind is PI:
yield _emit(kind, data, Markup('<?%s %s?>' % data))
class HTMLSerializer(XHTMLSerializer):
"""Produces HTML text from an event stream.
>>> from genshi.builder import tag
>>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True))
>>> print(''.join(HTMLSerializer()(elem.generate())))
<div><a href="foo"></a><br><hr noshade></div>
"""
_NOESCAPE_ELEMS = frozenset([
QName('script'), QName('http://www.w3.org/1999/xhtml}script'),
QName('style'), QName('http://www.w3.org/1999/xhtml}style')
])
def __init__(self, doctype=None, strip_whitespace=True, cache=True):
"""Initialize the HTML serializer.
:param doctype: a ``(name, pubid, sysid)`` tuple that represents the
DOCTYPE declaration that should be included at the top
of the generated output
:param strip_whitespace: whether extraneous whitespace should be
stripped from the output
:param cache: whether to cache the text output per event, which
improves performance for repetitive markup
:note: Changed in 0.6: The `cache` parameter was added
"""
super(HTMLSerializer, self).__init__(doctype, False)
self.filters = [EmptyTagFilter()]
if strip_whitespace:
self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE,
self._NOESCAPE_ELEMS))
self.filters.append(NamespaceFlattener(prefixes={
'http://www.w3.org/1999/xhtml': ''
}, cache=cache))
if doctype:
self.filters.append(DocTypeInserter(doctype))
self.cache = True
def __call__(self, stream):
boolean_attrs = self._BOOLEAN_ATTRS
empty_elems = self._EMPTY_ELEMS
noescape_elems = self._NOESCAPE_ELEMS
have_doctype = False
noescape = False
cache = {}
cache_get = cache.get
if self.cache:
def _emit(kind, input, output):
cache[kind, input] = output
return output
else:
def _emit(kind, input, output):
return output
for filter_ in self.filters:
stream = filter_(stream)
for kind, data, _ in stream:
output = cache_get((kind, data))
if output is not None:
yield output
if (kind is START or kind is EMPTY) \
and data[0] in noescape_elems:
noescape = True
elif kind is END:
noescape = False
elif kind is START or kind is EMPTY:
tag, attrib = data
buf = ['<', tag]
for attr, value in attrib:
if attr in boolean_attrs:
if value:
buf += [' ', attr]
elif ':' in attr:
if attr == 'xml:lang' and 'lang' not in attrib:
buf += [' lang="', escape(value), '"']
elif attr != 'xmlns':
buf += [' ', attr, '="', escape(value), '"']
buf.append('>')
if kind is EMPTY:
if tag not in empty_elems:
buf.append('</%s>' % tag)
yield _emit(kind, data, Markup(''.join(buf)))
if tag in noescape_elems:
noescape = True
elif kind is END:
yield _emit(kind, data, Markup('</%s>' % data))
noescape = False
elif kind is TEXT:
if noescape:
yield _emit(kind, data, data)
else:
yield _emit(kind, data, escape(data, quotes=False))
elif kind is COMMENT:
yield _emit(kind, data, Markup('<!--%s-->' % data))
elif kind is DOCTYPE and not have_doctype:
name, pubid, sysid = data
buf = ['<!DOCTYPE %s']
if pubid:
buf.append(' PUBLIC "%s"')
elif sysid:
buf.append(' SYSTEM')
if sysid:
buf.append(' "%s"')
buf.append('>\n')
yield Markup(''.join(buf)) % tuple([p for p in data if p])
have_doctype = True
elif kind is PI:
yield _emit(kind, data, Markup('<?%s %s?>' % data))
class TextSerializer(object):
"""Produces plain text from an event stream.
Only text events are included in the output. Unlike the other serializer,
special XML characters are not escaped:
>>> from genshi.builder import tag
>>> elem = tag.div(tag.a('<Hello!>', href='foo'), tag.br)
>>> print(elem)
<div><a href="foo"><Hello!></a><br/></div>
>>> print(''.join(TextSerializer()(elem.generate())))
<Hello!>
If text events contain literal markup (instances of the `Markup` class),
that markup is by default passed through unchanged:
>>> elem = tag.div(Markup('<a href="foo">Hello & Bye!</a><br/>'))
>>> print(elem.generate().render(TextSerializer, encoding=None))
<a href="foo">Hello & Bye!</a><br/>
You can use the ``strip_markup`` to change this behavior, so that tags and
entities are stripped from the output (or in the case of entities,
replaced with the equivalent character):
>>> print(elem.generate().render(TextSerializer, strip_markup=True,
... encoding=None))
Hello & Bye!
"""
def __init__(self, strip_markup=False):
"""Create the serializer.
:param strip_markup: whether markup (tags and encoded characters) found
in the text should be removed
"""
self.strip_markup = strip_markup
def __call__(self, stream):
strip_markup = self.strip_markup
for event in stream:
if event[0] is TEXT:
data = event[1]
if strip_markup and type(data) is Markup:
data = data.striptags().stripentities()
yield unicode(data)
class EmptyTagFilter(object):
"""Combines `START` and `STOP` events into `EMPTY` events for elements that
have no contents.
"""
EMPTY = StreamEventKind('EMPTY')
def __call__(self, stream):
prev = (None, None, None)
for ev in stream:
if prev[0] is START:
if ev[0] is END:
prev = EMPTY, prev[1], prev[2]
yield prev
continue
else:
yield prev
if ev[0] is not START:
yield ev
prev = ev
EMPTY = EmptyTagFilter.EMPTY
class NamespaceFlattener(object):
r"""Output stream filter that removes namespace information from the stream,
instead adding namespace attributes and prefixes as needed.
:param prefixes: optional mapping of namespace URIs to prefixes
>>> from genshi.input import XML
>>> xml = XML('''<doc xmlns="NS1" xmlns:two="NS2">
... <two:item/>
... </doc>''')
>>> for kind, data, pos in NamespaceFlattener()(xml):
... print('%s %r' % (kind, data))
START (u'doc', Attrs([('xmlns', u'NS1'), (u'xmlns:two', u'NS2')]))
TEXT u'\n '
START (u'two:item', Attrs())
END u'two:item'
TEXT u'\n'
END u'doc'
"""
def __init__(self, prefixes=None, cache=True):
self.prefixes = {XML_NAMESPACE.uri: 'xml'}
if prefixes is not None:
self.prefixes.update(prefixes)
self.cache = cache
def __call__(self, stream):
cache = {}
cache_get = cache.get
if self.cache:
def _emit(kind, input, output, pos):
cache[kind, input] = output
return kind, output, pos
else:
def _emit(kind, input, output, pos):
return output
prefixes = dict([(v, [k]) for k, v in self.prefixes.items()])
namespaces = {XML_NAMESPACE.uri: ['xml']}
def _push_ns(prefix, uri):
namespaces.setdefault(uri, []).append(prefix)
prefixes.setdefault(prefix, []).append(uri)
cache.clear()
def _pop_ns(prefix):
uris = prefixes.get(prefix)
uri = uris.pop()
if not uris:
del prefixes[prefix]
if uri not in uris or uri != uris[-1]:
uri_prefixes = namespaces[uri]
uri_prefixes.pop()
if not uri_prefixes:
del namespaces[uri]
cache.clear()
return uri
ns_attrs = []
_push_ns_attr = ns_attrs.append
def _make_ns_attr(prefix, uri):
return 'xmlns%s' % (prefix and ':%s' % prefix or ''), uri
def _gen_prefix():
val = 0
while 1:
val += 1
yield 'ns%d' % val
_gen_prefix = _gen_prefix().next
for kind, data, pos in stream:
output = cache_get((kind, data))
if output is not None:
yield kind, output, pos
elif kind is START or kind is EMPTY:
tag, attrs = data
tagname = tag.localname
tagns = tag.namespace
if tagns:
if tagns in namespaces:
prefix = namespaces[tagns][-1]
if prefix:
tagname = '%s:%s' % (prefix, tagname)
else:
_push_ns_attr(('xmlns', tagns))
_push_ns('', tagns)
new_attrs = []
for attr, value in attrs:
attrname = attr.localname
attrns = attr.namespace
if attrns:
if attrns not in namespaces:
prefix = _gen_prefix()
_push_ns(prefix, attrns)
_push_ns_attr(('xmlns:%s' % prefix, attrns))
else:
prefix = namespaces[attrns][-1]
if prefix:
attrname = '%s:%s' % (prefix, attrname)
new_attrs.append((attrname, value))
yield _emit(kind, data, (tagname, Attrs(ns_attrs + new_attrs)), pos)
del ns_attrs[:]
elif kind is END:
tagname = data.localname
tagns = data.namespace
if tagns:
prefix = namespaces[tagns][-1]
if prefix:
tagname = '%s:%s' % (prefix, tagname)
yield _emit(kind, data, tagname, pos)
elif kind is START_NS:
prefix, uri = data
if uri not in namespaces:
prefix = prefixes.get(uri, [prefix])[-1]
_push_ns_attr(_make_ns_attr(prefix, uri))
_push_ns(prefix, uri)
elif kind is END_NS:
if data in prefixes:
uri = _pop_ns(data)
if ns_attrs:
attr = _make_ns_attr(data, uri)
if attr in ns_attrs:
ns_attrs.remove(attr)
else:
yield kind, data, pos
class WhitespaceFilter(object):
"""A filter that removes extraneous ignorable white space from the
stream.
"""
def __init__(self, preserve=None, noescape=None):
"""Initialize the filter.
:param preserve: a set or sequence of tag names for which white-space
should be preserved
:param noescape: a set or sequence of tag names for which text content
should not be escaped
The `noescape` set is expected to refer to elements that cannot contain
further child elements (such as ``<style>`` or ``<script>`` in HTML
documents).
"""
if preserve is None:
preserve = []
self.preserve = frozenset(preserve)
if noescape is None:
noescape = []
self.noescape = frozenset(noescape)
def __call__(self, stream, ctxt=None, space=XML_NAMESPACE['space'],
trim_trailing_space=re.compile('[ \t]+(?=\n)').sub,
collapse_lines=re.compile('\n{2,}').sub):
mjoin = Markup('').join
preserve_elems = self.preserve
preserve = 0
noescape_elems = self.noescape
noescape = False
textbuf = []
push_text = textbuf.append
pop_text = textbuf.pop
for kind, data, pos in chain(stream, [(None, None, None)]):
if kind is TEXT:
if noescape:
data = Markup(data)
push_text(data)
else:
if textbuf:
if len(textbuf) > 1:
text = mjoin(textbuf, escape_quotes=False)
del textbuf[:]
else:
text = escape(pop_text(), quotes=False)
if not preserve:
text = collapse_lines('\n', trim_trailing_space('', text))
yield TEXT, Markup(text), pos
if kind is START:
tag, attrs = data
if preserve or (tag in preserve_elems or
attrs.get(space) == 'preserve'):
preserve += 1
if not noescape and tag in noescape_elems:
noescape = True
elif kind is END:
noescape = False
if preserve:
preserve -= 1
elif kind is START_CDATA:
noescape = True
elif kind is END_CDATA:
noescape = False
if kind:
yield kind, data, pos
class DocTypeInserter(object):
"""A filter that inserts the DOCTYPE declaration in the correct location,
after the XML declaration.
"""
def __init__(self, doctype):
"""Initialize the filter.
:param doctype: DOCTYPE as a string or DocType object.
"""
if isinstance(doctype, basestring):
doctype = DocType.get(doctype)
self.doctype_event = (DOCTYPE, doctype, (None, -1, -1))
def __call__(self, stream):
doctype_inserted = False
for kind, data, pos in stream:
if not doctype_inserted:
doctype_inserted = True
if kind is XML_DECL:
yield (kind, data, pos)
yield self.doctype_event
continue
yield self.doctype_event
yield (kind, data, pos)
if not doctype_inserted:
yield self.doctype_event
|