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
|
# xml.etree test. This file contains enough tests to make sure that
# all included components work as they should. For a more extensive
# test suite, see the selftest script in the ElementTree distribution.
import doctest
import sys
from test import support
SAMPLE_XML = """
<body>
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
SAMPLE_XML_NS = """
<body xmlns="http://effbot.org/ns">
<tag>text</tag>
<tag />
<section>
<tag>subtext</tag>
</section>
</body>
"""
def sanity():
"""
Import sanity.
>>> from xml.etree import ElementTree
>>> from xml.etree import ElementInclude
>>> from xml.etree import ElementPath
"""
def check_method(method):
if not hasattr(method, '__call__'):
print(method, "not callable")
def serialize(ET, elem):
import io
tree = ET.ElementTree(elem)
file = io.StringIO()
tree.write(file)
return file.getvalue()
def summarize(elem):
return elem.tag
def summarize_list(seq):
return list(map(summarize, seq))
def interface():
"""
Test element tree interface.
>>> from xml.etree import ElementTree as ET
>>> element = ET.Element("tag", key="value")
>>> tree = ET.ElementTree(element)
Make sure all standard element methods exist.
>>> check_method(element.append)
>>> check_method(element.insert)
>>> check_method(element.remove)
>>> check_method(element.getchildren)
>>> check_method(element.find)
>>> check_method(element.findall)
>>> check_method(element.findtext)
>>> check_method(element.clear)
>>> check_method(element.get)
>>> check_method(element.set)
>>> check_method(element.keys)
>>> check_method(element.items)
>>> check_method(element.getiterator)
Basic method sanity checks.
>>> serialize(ET, element) # 1
'<tag key="value" />'
>>> subelement = ET.Element("subtag")
>>> element.append(subelement)
>>> serialize(ET, element) # 2
'<tag key="value"><subtag /></tag>'
>>> element.insert(0, subelement)
>>> serialize(ET, element) # 3
'<tag key="value"><subtag /><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 4
'<tag key="value"><subtag /></tag>'
>>> element.remove(subelement)
>>> serialize(ET, element) # 5
'<tag key="value" />'
>>> element.remove(subelement)
Traceback (most recent call last):
ValueError: list.remove(x): x not in list
>>> serialize(ET, element) # 6
'<tag key="value" />'
"""
def find():
"""
Test find methods (including xpath syntax).
>>> from xml.etree import ElementTree as ET
>>> elem = ET.XML(SAMPLE_XML)
>>> elem.find("tag").tag
'tag'
>>> ET.ElementTree(elem).find("tag").tag
'tag'
>>> elem.find("section/tag").tag
'tag'
>>> ET.ElementTree(elem).find("section/tag").tag
'tag'
>>> elem.findtext("tag")
'text'
>>> elem.findtext("tog")
>>> elem.findtext("tog", "default")
'default'
>>> ET.ElementTree(elem).findtext("tag")
'text'
>>> elem.findtext("section/tag")
'subtext'
>>> ET.ElementTree(elem).findtext("section/tag")
'subtext'
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("*"))
['tag', 'tag', 'section']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("section/tag"))
['tag']
>>> summarize_list(elem.findall("section//tag"))
['tag']
>>> summarize_list(elem.findall("section/*"))
['tag']
>>> summarize_list(elem.findall("section//*"))
['tag']
>>> summarize_list(elem.findall("section/.//*"))
['tag']
>>> summarize_list(elem.findall("*/*"))
['tag']
>>> summarize_list(elem.findall("*//*"))
['tag']
>>> summarize_list(elem.findall("*/tag"))
['tag']
>>> summarize_list(elem.findall("*/./tag"))
['tag']
>>> summarize_list(elem.findall("./tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("././tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("/tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("./tag"))
['tag', 'tag']
>>> elem = ET.XML(SAMPLE_XML_NS)
>>> summarize_list(elem.findall("tag"))
[]
>>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
>>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
"""
def parseliteral():
r"""
>>> from xml.etree import ElementTree as ET
>>> element = ET.XML("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> element = ET.fromstring("<html><body>text</body></html>")
>>> ET.ElementTree(element).write(sys.stdout)
<html><body>text</body></html>
>>> print(ET.tostring(element))
<html><body>text</body></html>
>>> print(repr(ET.tostring(element, "ascii")))
b"<?xml version='1.0' encoding='ascii'?>\n<html><body>text</body></html>"
>>> _, ids = ET.XMLID("<html><body>text</body></html>")
>>> len(ids)
0
>>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
>>> len(ids)
1
>>> ids["body"].tag
'body'
"""
def check_encoding(ET, encoding):
"""
>>> from xml.etree import ElementTree as ET
>>> check_encoding(ET, "ascii")
>>> check_encoding(ET, "us-ascii")
>>> check_encoding(ET, "iso-8859-1")
>>> check_encoding(ET, "iso-8859-15")
>>> check_encoding(ET, "cp437")
>>> check_encoding(ET, "mac-roman")
"""
ET.XML("<?xml version='1.0' encoding='%s'?><xml />" % encoding)
#
# xinclude tests (samples from appendix C of the xinclude specification)
XINCLUDE = {}
XINCLUDE["C1.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>120 Mz is adequate for an average home user.</p>
<xi:include href="disclaimer.xml"/>
</document>
"""
XINCLUDE["disclaimer.xml"] = """\
<?xml version='1.0'?>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
"""
XINCLUDE["C2.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>This document has been accessed
<xi:include href="count.txt" parse="text"/> times.</p>
</document>
"""
XINCLUDE["count.txt"] = "324387"
XINCLUDE["C3.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>The following is the source of the "data.xml" resource:</p>
<example><xi:include href="data.xml" parse="text"/></example>
</document>
"""
XINCLUDE["data.xml"] = """\
<?xml version='1.0'?>
<data>
<item><![CDATA[Brooks & Shields]]></item>
</data>
"""
XINCLUDE["C5.xml"] = """\
<?xml version='1.0'?>
<div xmlns:xi="http://www.w3.org/2001/XInclude">
<xi:include href="example.txt" parse="text">
<xi:fallback>
<xi:include href="fallback-example.txt" parse="text">
<xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>
</xi:include>
</xi:fallback>
</xi:include>
</div>
"""
XINCLUDE["default.xml"] = """\
<?xml version='1.0'?>
<document xmlns:xi="http://www.w3.org/2001/XInclude">
<p>Example.</p>
<xi:include href="samples/simple.xml"/>
</document>
"""
def xinclude_loader(href, parse="xml", encoding=None):
try:
data = XINCLUDE[href]
except KeyError:
raise IOError("resource not found")
if parse == "xml":
from xml.etree.ElementTree import XML
return XML(data)
return data
def xinclude():
r"""
Basic inclusion example (XInclude C.1)
>>> from xml.etree import ElementTree as ET
>>> from xml.etree import ElementInclude
>>> document = xinclude_loader("C1.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print(serialize(ET, document)) # C1
<document>
<p>120 Mz is adequate for an average home user.</p>
<disclaimer>
<p>The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.</p>
</disclaimer>
</document>
Textual inclusion example (XInclude C.2)
>>> document = xinclude_loader("C2.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print(serialize(ET, document)) # C2
<document>
<p>This document has been accessed
324387 times.</p>
</document>
Textual inclusion of XML example (XInclude C.3)
>>> document = xinclude_loader("C3.xml")
>>> ElementInclude.include(document, xinclude_loader)
>>> print(serialize(ET, document)) # C3
<document>
<p>The following is the source of the "data.xml" resource:</p>
<example><?xml version='1.0'?>
<data>
<item><![CDATA[Brooks & Shields]]></item>
</data>
</example>
</document>
Fallback example (XInclude C.5)
Note! Fallback support is not yet implemented
>>> document = xinclude_loader("C5.xml")
>>> ElementInclude.include(document, xinclude_loader)
Traceback (most recent call last):
IOError: resource not found
>>> # print serialize(ET, document) # C5
"""
def test_main():
from test import test_xml_etree
support.run_doctest(test_xml_etree, verbosity=True)
if __name__ == '__main__':
test_main()
|
