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
|
# XXX TypeErrors on calling handlers, or on bad return values from a
# handler, are obscure and unhelpful.
from io import BytesIO
import unittest
import pyexpat
from xml.parsers import expat
from test.test_support import sortdict, run_unittest
class SetAttributeTest(unittest.TestCase):
def setUp(self):
self.parser = expat.ParserCreate(namespace_separator='!')
self.set_get_pairs = [
[0, 0],
[1, 1],
[2, 1],
[0, 0],
]
def test_ordered_attributes(self):
for x, y in self.set_get_pairs:
self.parser.ordered_attributes = x
self.assertEquals(self.parser.ordered_attributes, y)
def test_specified_attributes(self):
for x, y in self.set_get_pairs:
self.parser.specified_attributes = x
self.assertEquals(self.parser.specified_attributes, y)
data = b'''\
<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
<?xml-stylesheet href="stylesheet.css"?>
<!-- comment data -->
<!DOCTYPE quotations SYSTEM "quotations.dtd" [
<!ELEMENT root ANY>
<!NOTATION notation SYSTEM "notation.jpeg">
<!ENTITY acirc "â">
<!ENTITY external_entity SYSTEM "entity.file">
<!ENTITY unparsed_entity SYSTEM "entity.file" NDATA notation>
%unparsed_entity;
]>
<root attr1="value1" attr2="value2ὀ">
<myns:subelement xmlns:myns="http://www.python.org/namespace">
Contents of subelements
</myns:subelement>
<sub2><![CDATA[contents of CDATA section]]></sub2>
&external_entity;
</root>
'''
# Produce UTF-8 output
class ParseTest(unittest.TestCase):
class Outputter:
def __init__(self):
self.out = []
def StartElementHandler(self, name, attrs):
self.out.append('Start element: ' + repr(name) + ' ' +
sortdict(attrs))
def EndElementHandler(self, name):
self.out.append('End element: ' + repr(name))
def CharacterDataHandler(self, data):
data = data.strip()
if data:
self.out.append('Character data: ' + repr(data))
def ProcessingInstructionHandler(self, target, data):
self.out.append('PI: ' + repr(target) + ' ' + repr(data))
def StartNamespaceDeclHandler(self, prefix, uri):
self.out.append('NS decl: ' + repr(prefix) + ' ' + repr(uri))
def EndNamespaceDeclHandler(self, prefix):
self.out.append('End of NS decl: ' + repr(prefix))
def StartCdataSectionHandler(self):
self.out.append('Start of CDATA section')
def EndCdataSectionHandler(self):
self.out.append('End of CDATA section')
def CommentHandler(self, text):
self.out.append('Comment: ' + repr(text))
def NotationDeclHandler(self, *args):
name, base, sysid, pubid = args
self.out.append('Notation declared: %s' %(args,))
def UnparsedEntityDeclHandler(self, *args):
entityName, base, systemId, publicId, notationName = args
self.out.append('Unparsed entity decl: %s' %(args,))
def NotStandaloneHandler(self, userData):
self.out.append('Not standalone')
return 1
def ExternalEntityRefHandler(self, *args):
context, base, sysId, pubId = args
self.out.append('External entity ref: %s' %(args[1:],))
return 1
def DefaultHandler(self, userData):
pass
def DefaultHandlerExpand(self, userData):
pass
handler_names = [
'StartElementHandler', 'EndElementHandler',
'CharacterDataHandler', 'ProcessingInstructionHandler',
'UnparsedEntityDeclHandler', 'NotationDeclHandler',
'StartNamespaceDeclHandler', 'EndNamespaceDeclHandler',
'CommentHandler', 'StartCdataSectionHandler',
'EndCdataSectionHandler',
'DefaultHandler', 'DefaultHandlerExpand',
#'NotStandaloneHandler',
'ExternalEntityRefHandler'
]
def _verify_parse_output(self, op):
self.assertEquals(op[0], 'PI: \'xml-stylesheet\' \'href="stylesheet.css"\'')
self.assertEquals(op[1], "Comment: ' comment data '")
self.assertEquals(op[2], "Notation declared: ('notation', None, 'notation.jpeg', None)")
self.assertEquals(op[3], "Unparsed entity decl: ('unparsed_entity', None, 'entity.file', None, 'notation')")
self.assertEquals(op[4], "Start element: 'root' {'attr1': 'value1', 'attr2': 'value2\\u1f40'}")
self.assertEquals(op[5], "NS decl: 'myns' 'http://www.python.org/namespace'")
self.assertEquals(op[6], "Start element: 'http://www.python.org/namespace!subelement' {}")
self.assertEquals(op[7], "Character data: 'Contents of subelements'")
self.assertEquals(op[8], "End element: 'http://www.python.org/namespace!subelement'")
self.assertEquals(op[9], "End of NS decl: 'myns'")
self.assertEquals(op[10], "Start element: 'sub2' {}")
self.assertEquals(op[11], 'Start of CDATA section')
self.assertEquals(op[12], "Character data: 'contents of CDATA section'")
self.assertEquals(op[13], 'End of CDATA section')
self.assertEquals(op[14], "End element: 'sub2'")
self.assertEquals(op[15], "External entity ref: (None, 'entity.file', None)")
self.assertEquals(op[16], "End element: 'root'")
def test_unicode(self):
# Try the parse again, this time producing Unicode output
out = self.Outputter()
parser = expat.ParserCreate(namespace_separator='!')
for name in self.handler_names:
setattr(parser, name, getattr(out, name))
parser.Parse(data, 1)
op = out.out
self._verify_parse_output(op)
def test_parse_file(self):
# Try parsing a file
out = self.Outputter()
parser = expat.ParserCreate(namespace_separator='!')
for name in self.handler_names:
setattr(parser, name, getattr(out, name))
file = BytesIO(data)
parser.ParseFile(file)
op = out.out
self._verify_parse_output(op)
class NamespaceSeparatorTest(unittest.TestCase):
def test_legal(self):
# Tests that make sure we get errors when the namespace_separator value
# is illegal, and that we don't for good values:
expat.ParserCreate()
expat.ParserCreate(namespace_separator=None)
expat.ParserCreate(namespace_separator=' ')
def test_illegal(self):
try:
expat.ParserCreate(namespace_separator=42)
self.fail()
except TypeError as e:
self.assertEquals(str(e),
'ParserCreate() argument 2 must be string or None, not int')
try:
expat.ParserCreate(namespace_separator='too long')
self.fail()
except ValueError as e:
self.assertEquals(str(e),
'namespace_separator must be at most one character, omitted, or None')
def test_zero_length(self):
# ParserCreate() needs to accept a namespace_separator of zero length
# to satisfy the requirements of RDF applications that are required
# to simply glue together the namespace URI and the localname. Though
# considered a wart of the RDF specifications, it needs to be supported.
#
# See XML-SIG mailing list thread starting with
# http://mail.python.org/pipermail/xml-sig/2001-April/005202.html
#
expat.ParserCreate(namespace_separator='') # too short
class InterningTest(unittest.TestCase):
def test(self):
# Test the interning machinery.
p = expat.ParserCreate()
L = []
def collector(name, *args):
L.append(name)
p.StartElementHandler = collector
p.EndElementHandler = collector
p.Parse("<e> <e/> <e></e> </e>", 1)
tag = L[0]
self.assertEquals(len(L), 6)
for entry in L:
# L should have the same string repeated over and over.
self.assertTrue(tag is entry)
class BufferTextTest(unittest.TestCase):
def setUp(self):
self.stuff = []
self.parser = expat.ParserCreate()
self.parser.buffer_text = 1
self.parser.CharacterDataHandler = self.CharacterDataHandler
def check(self, expected, label):
self.assertEquals(self.stuff, expected,
"%s\nstuff = %r\nexpected = %r"
% (label, self.stuff, map(str, expected)))
def CharacterDataHandler(self, text):
self.stuff.append(text)
def StartElementHandler(self, name, attrs):
self.stuff.append("<%s>" % name)
bt = attrs.get("buffer-text")
if bt == "yes":
self.parser.buffer_text = 1
elif bt == "no":
self.parser.buffer_text = 0
def EndElementHandler(self, name):
self.stuff.append("</%s>" % name)
def CommentHandler(self, data):
self.stuff.append("<!--%s-->" % data)
def setHandlers(self, handlers=[]):
for name in handlers:
setattr(self.parser, name, getattr(self, name))
def test_default_to_disabled(self):
parser = expat.ParserCreate()
self.assertFalse(parser.buffer_text)
def test_buffering_enabled(self):
# Make sure buffering is turned on
self.assertTrue(self.parser.buffer_text)
self.parser.Parse("<a>1<b/>2<c/>3</a>", 1)
self.assertEquals(self.stuff, ['123'],
"buffered text not properly collapsed")
def test1(self):
# XXX This test exposes more detail of Expat's text chunking than we
# XXX like, but it tests what we need to concisely.
self.setHandlers(["StartElementHandler"])
self.parser.Parse("<a>1<b buffer-text='no'/>2\n3<c buffer-text='yes'/>4\n5</a>", 1)
self.assertEquals(self.stuff,
["<a>", "1", "<b>", "2", "\n", "3", "<c>", "4\n5"],
"buffering control not reacting as expected")
def test2(self):
self.parser.Parse("<a>1<b/><2><c/> \n 3</a>", 1)
self.assertEquals(self.stuff, ["1<2> \n 3"],
"buffered text not properly collapsed")
def test3(self):
self.setHandlers(["StartElementHandler"])
self.parser.Parse("<a>1<b/>2<c/>3</a>", 1)
self.assertEquals(self.stuff, ["<a>", "1", "<b>", "2", "<c>", "3"],
"buffered text not properly split")
def test4(self):
self.setHandlers(["StartElementHandler", "EndElementHandler"])
self.parser.CharacterDataHandler = None
self.parser.Parse("<a>1<b/>2<c/>3</a>", 1)
self.assertEquals(self.stuff,
["<a>", "<b>", "</b>", "<c>", "</c>", "</a>"])
def test5(self):
self.setHandlers(["StartElementHandler", "EndElementHandler"])
self.parser.Parse("<a>1<b></b>2<c/>3</a>", 1)
self.assertEquals(self.stuff,
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3", "</a>"])
def test6(self):
self.setHandlers(["CommentHandler", "EndElementHandler",
"StartElementHandler"])
self.parser.Parse("<a>1<b/>2<c></c>345</a> ", 1)
self.assertEquals(self.stuff,
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "345", "</a>"],
"buffered text not properly split")
def test7(self):
self.setHandlers(["CommentHandler", "EndElementHandler",
"StartElementHandler"])
self.parser.Parse("<a>1<b/>2<c></c>3<!--abc-->4<!--def-->5</a> ", 1)
self.assertEquals(self.stuff,
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3",
"<!--abc-->", "4", "<!--def-->", "5", "</a>"],
"buffered text not properly split")
# Test handling of exception from callback:
class HandlerExceptionTest(unittest.TestCase):
def StartElementHandler(self, name, attrs):
raise RuntimeError(name)
def test(self):
parser = expat.ParserCreate()
parser.StartElementHandler = self.StartElementHandler
try:
parser.Parse("<a><b><c/></b></a>", 1)
self.fail()
except RuntimeError as e:
self.assertEquals(e.args[0], 'a',
"Expected RuntimeError for element 'a', but" + \
" found %r" % e.args[0])
# Test Current* members:
class PositionTest(unittest.TestCase):
def StartElementHandler(self, name, attrs):
self.check_pos('s')
def EndElementHandler(self, name):
self.check_pos('e')
def check_pos(self, event):
pos = (event,
self.parser.CurrentByteIndex,
self.parser.CurrentLineNumber,
self.parser.CurrentColumnNumber)
self.assertTrue(self.upto < len(self.expected_list),
'too many parser events')
expected = self.expected_list[self.upto]
self.assertEquals(pos, expected,
'Expected position %s, got position %s' %(pos, expected))
self.upto += 1
def test(self):
self.parser = expat.ParserCreate()
self.parser.StartElementHandler = self.StartElementHandler
self.parser.EndElementHandler = self.EndElementHandler
self.upto = 0
self.expected_list = [('s', 0, 1, 0), ('s', 5, 2, 1), ('s', 11, 3, 2),
('e', 15, 3, 6), ('e', 17, 4, 1), ('e', 22, 5, 0)]
xml = '<a>\n <b>\n <c/>\n </b>\n</a>'
self.parser.Parse(xml, 1)
class sf1296433Test(unittest.TestCase):
def test_parse_only_xml_data(self):
# http://python.org/sf/1296433
#
xml = "<?xml version='1.0' encoding='iso8859'?><s>%s</s>" % ('a' * 1025)
# this one doesn't crash
#xml = "<?xml version='1.0'?><s>%s</s>" % ('a' * 10000)
class SpecificException(Exception):
pass
def handler(text):
raise SpecificException
parser = expat.ParserCreate()
parser.CharacterDataHandler = handler
self.assertRaises(Exception, parser.Parse, xml)
def test_main():
run_unittest(SetAttributeTest,
ParseTest,
NamespaceSeparatorTest,
InterningTest,
BufferTextTest,
HandlerExceptionTest,
PositionTest,
sf1296433Test)
if __name__ == "__main__":
test_main()
|