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
|
"""Implementation of the DOM Level 3 'LS-Load' feature."""
import copy
import xmlcore.dom
from xmlcore.dom.minicompat import *
from xmlcore.dom.NodeFilter import NodeFilter
__all__ = ["DOMBuilder", "DOMEntityResolver", "DOMInputSource"]
class Options:
"""Features object that has variables set for each DOMBuilder feature.
The DOMBuilder class uses an instance of this class to pass settings to
the ExpatBuilder class.
"""
# Note that the DOMBuilder class in LoadSave constrains which of these
# values can be set using the DOM Level 3 LoadSave feature.
namespaces = 1
namespace_declarations = True
validation = False
external_parameter_entities = True
external_general_entities = True
external_dtd_subset = True
validate_if_schema = False
validate = False
datatype_normalization = False
create_entity_ref_nodes = True
entities = True
whitespace_in_element_content = True
cdata_sections = True
comments = True
charset_overrides_xml_encoding = True
infoset = False
supported_mediatypes_only = False
errorHandler = None
filter = None
class DOMBuilder:
entityResolver = None
errorHandler = None
filter = None
ACTION_REPLACE = 1
ACTION_APPEND_AS_CHILDREN = 2
ACTION_INSERT_AFTER = 3
ACTION_INSERT_BEFORE = 4
_legal_actions = (ACTION_REPLACE, ACTION_APPEND_AS_CHILDREN,
ACTION_INSERT_AFTER, ACTION_INSERT_BEFORE)
def __init__(self):
self._options = Options()
def _get_entityResolver(self):
return self.entityResolver
def _set_entityResolver(self, entityResolver):
self.entityResolver = entityResolver
def _get_errorHandler(self):
return self.errorHandler
def _set_errorHandler(self, errorHandler):
self.errorHandler = errorHandler
def _get_filter(self):
return self.filter
def _set_filter(self, filter):
self.filter = filter
def setFeature(self, name, state):
if self.supportsFeature(name):
state = state and 1 or 0
try:
settings = self._settings[(_name_xform(name), state)]
except KeyError:
raise xmlcore.dom.NotSupportedErr(
"unsupported feature: %r" % (name,))
else:
for name, value in settings:
setattr(self._options, name, value)
else:
raise xmlcore.dom.NotFoundErr("unknown feature: " + repr(name))
def supportsFeature(self, name):
return hasattr(self._options, _name_xform(name))
def canSetFeature(self, name, state):
key = (_name_xform(name), state and 1 or 0)
return self._settings.has_key(key)
# This dictionary maps from (feature,value) to a list of
# (option,value) pairs that should be set on the Options object.
# If a (feature,value) setting is not in this dictionary, it is
# not supported by the DOMBuilder.
#
_settings = {
("namespace_declarations", 0): [
("namespace_declarations", 0)],
("namespace_declarations", 1): [
("namespace_declarations", 1)],
("validation", 0): [
("validation", 0)],
("external_general_entities", 0): [
("external_general_entities", 0)],
("external_general_entities", 1): [
("external_general_entities", 1)],
("external_parameter_entities", 0): [
("external_parameter_entities", 0)],
("external_parameter_entities", 1): [
("external_parameter_entities", 1)],
("validate_if_schema", 0): [
("validate_if_schema", 0)],
("create_entity_ref_nodes", 0): [
("create_entity_ref_nodes", 0)],
("create_entity_ref_nodes", 1): [
("create_entity_ref_nodes", 1)],
("entities", 0): [
("create_entity_ref_nodes", 0),
("entities", 0)],
("entities", 1): [
("entities", 1)],
("whitespace_in_element_content", 0): [
("whitespace_in_element_content", 0)],
("whitespace_in_element_content", 1): [
("whitespace_in_element_content", 1)],
("cdata_sections", 0): [
("cdata_sections", 0)],
("cdata_sections", 1): [
("cdata_sections", 1)],
("comments", 0): [
("comments", 0)],
("comments", 1): [
("comments", 1)],
("charset_overrides_xml_encoding", 0): [
("charset_overrides_xml_encoding", 0)],
("charset_overrides_xml_encoding", 1): [
("charset_overrides_xml_encoding", 1)],
("infoset", 0): [],
("infoset", 1): [
("namespace_declarations", 0),
("validate_if_schema", 0),
("create_entity_ref_nodes", 0),
("entities", 0),
("cdata_sections", 0),
("datatype_normalization", 1),
("whitespace_in_element_content", 1),
("comments", 1),
("charset_overrides_xml_encoding", 1)],
("supported_mediatypes_only", 0): [
("supported_mediatypes_only", 0)],
("namespaces", 0): [
("namespaces", 0)],
("namespaces", 1): [
("namespaces", 1)],
}
def getFeature(self, name):
xname = _name_xform(name)
try:
return getattr(self._options, xname)
except AttributeError:
if name == "infoset":
options = self._options
return (options.datatype_normalization
and options.whitespace_in_element_content
and options.comments
and options.charset_overrides_xml_encoding
and not (options.namespace_declarations
or options.validate_if_schema
or options.create_entity_ref_nodes
or options.entities
or options.cdata_sections))
raise xmlcore.dom.NotFoundErr("feature %s not known" % repr(name))
def parseURI(self, uri):
if self.entityResolver:
input = self.entityResolver.resolveEntity(None, uri)
else:
input = DOMEntityResolver().resolveEntity(None, uri)
return self.parse(input)
def parse(self, input):
options = copy.copy(self._options)
options.filter = self.filter
options.errorHandler = self.errorHandler
fp = input.byteStream
if fp is None and options.systemId:
import urllib2
fp = urllib2.urlopen(input.systemId)
return self._parse_bytestream(fp, options)
def parseWithContext(self, input, cnode, action):
if action not in self._legal_actions:
raise ValueError("not a legal action")
raise NotImplementedError("Haven't written this yet...")
def _parse_bytestream(self, stream, options):
import xmlcore.dom.expatbuilder
builder = xmlcore.dom.expatbuilder.makeBuilder(options)
return builder.parseFile(stream)
def _name_xform(name):
return name.lower().replace('-', '_')
class DOMEntityResolver(NewStyle):
__slots__ = '_opener',
def resolveEntity(self, publicId, systemId):
assert systemId is not None
source = DOMInputSource()
source.publicId = publicId
source.systemId = systemId
source.byteStream = self._get_opener().open(systemId)
# determine the encoding if the transport provided it
source.encoding = self._guess_media_encoding(source)
# determine the base URI is we can
import posixpath, urlparse
parts = urlparse.urlparse(systemId)
scheme, netloc, path, params, query, fragment = parts
# XXX should we check the scheme here as well?
if path and not path.endswith("/"):
path = posixpath.dirname(path) + "/"
parts = scheme, netloc, path, params, query, fragment
source.baseURI = urlparse.urlunparse(parts)
return source
def _get_opener(self):
try:
return self._opener
except AttributeError:
self._opener = self._create_opener()
return self._opener
def _create_opener(self):
import urllib2
return urllib2.build_opener()
def _guess_media_encoding(self, source):
info = source.byteStream.info()
if info.has_key("Content-Type"):
for param in info.getplist():
if param.startswith("charset="):
return param.split("=", 1)[1].lower()
class DOMInputSource(NewStyle):
__slots__ = ('byteStream', 'characterStream', 'stringData',
'encoding', 'publicId', 'systemId', 'baseURI')
def __init__(self):
self.byteStream = None
self.characterStream = None
self.stringData = None
self.encoding = None
self.publicId = None
self.systemId = None
self.baseURI = None
def _get_byteStream(self):
return self.byteStream
def _set_byteStream(self, byteStream):
self.byteStream = byteStream
def _get_characterStream(self):
return self.characterStream
def _set_characterStream(self, characterStream):
self.characterStream = characterStream
def _get_stringData(self):
return self.stringData
def _set_stringData(self, data):
self.stringData = data
def _get_encoding(self):
return self.encoding
def _set_encoding(self, encoding):
self.encoding = encoding
def _get_publicId(self):
return self.publicId
def _set_publicId(self, publicId):
self.publicId = publicId
def _get_systemId(self):
return self.systemId
def _set_systemId(self, systemId):
self.systemId = systemId
def _get_baseURI(self):
return self.baseURI
def _set_baseURI(self, uri):
self.baseURI = uri
class DOMBuilderFilter:
"""Element filter which can be used to tailor construction of
a DOM instance.
"""
# There's really no need for this class; concrete implementations
# should just implement the endElement() and startElement()
# methods as appropriate. Using this makes it easy to only
# implement one of them.
FILTER_ACCEPT = 1
FILTER_REJECT = 2
FILTER_SKIP = 3
FILTER_INTERRUPT = 4
whatToShow = NodeFilter.SHOW_ALL
def _get_whatToShow(self):
return self.whatToShow
def acceptNode(self, element):
return self.FILTER_ACCEPT
def startContainer(self, element):
return self.FILTER_ACCEPT
del NodeFilter
class DocumentLS:
"""Mixin to create documents that conform to the load/save spec."""
async = False
def _get_async(self):
return False
def _set_async(self, async):
if async:
raise xmlcore.dom.NotSupportedErr(
"asynchronous document loading is not supported")
def abort(self):
# What does it mean to "clear" a document? Does the
# documentElement disappear?
raise NotImplementedError(
"haven't figured out what this means yet")
def load(self, uri):
raise NotImplementedError("haven't written this yet")
def loadXML(self, source):
raise NotImplementedError("haven't written this yet")
def saveXML(self, snode):
if snode is None:
snode = self
elif snode.ownerDocument is not self:
raise xmlcore.dom.WrongDocumentErr()
return snode.toxml()
class DOMImplementationLS:
MODE_SYNCHRONOUS = 1
MODE_ASYNCHRONOUS = 2
def createDOMBuilder(self, mode, schemaType):
if schemaType is not None:
raise xmlcore.dom.NotSupportedErr(
"schemaType not yet supported")
if mode == self.MODE_SYNCHRONOUS:
return DOMBuilder()
if mode == self.MODE_ASYNCHRONOUS:
raise xmlcore.dom.NotSupportedErr(
"asynchronous builders are not supported")
raise ValueError("unknown value for mode")
def createDOMWriter(self):
raise NotImplementedError(
"the writer interface hasn't been written yet!")
def createDOMInputSource(self):
return DOMInputSource()
|