Python code coverage for Lib/test/test_pulldom.py

#	count	content
1	n/a	import io
2	n/a	import unittest
3	n/a	import xml.sax
4	n/a
5	n/a	from xml.sax.xmlreader import AttributesImpl
6	n/a	from xml.dom import pulldom
7	n/a
8	n/a	from test.support import findfile
9	n/a
10	n/a
11	n/a	tstfile = findfile("test.xml", subdir="xmltestdata")
12	n/a
13	n/a	# A handy XML snippet, containing attributes, a namespace prefix, and a
14	n/a	# self-closing tag:
15	n/a	SMALL_SAMPLE = """<?xml version="1.0"?>
16	n/a	<html xmlns="http://www.w3.org/1999/xhtml" xmlns:xdc="http://www.xml.com/books">
17	n/a	<!-- A comment -->
18	n/a	<title>Introduction to XSL</title>
19	n/a	<hr/>
20	n/a	<p><xdc:author xdc:attrib="prefixed attribute" attrib="other attrib">A. Namespace</xdc:author></p>
21	n/a	</html>"""
22	n/a
23	n/a
24	n/a	class PullDOMTestCase(unittest.TestCase):
25	n/a
26	n/a	def test_parse(self):
27	n/a	"""Minimal test of DOMEventStream.parse()"""
28	n/a
29	n/a	# This just tests that parsing from a stream works. Actual parser
30	n/a	# semantics are tested using parseString with a more focused XML
31	n/a	# fragment.
32	n/a
33	n/a	# Test with a filename:
34	n/a	handler = pulldom.parse(tstfile)
35	n/a	self.addCleanup(handler.stream.close)
36	n/a	list(handler)
37	n/a
38	n/a	# Test with a file object:
39	n/a	with open(tstfile, "rb") as fin:
40	n/a	list(pulldom.parse(fin))
41	n/a
42	n/a	def test_parse_semantics(self):
43	n/a	"""Test DOMEventStream parsing semantics."""
44	n/a
45	n/a	items = pulldom.parseString(SMALL_SAMPLE)
46	n/a	evt, node = next(items)
47	n/a	# Just check the node is a Document:
48	n/a	self.assertTrue(hasattr(node, "createElement"))
49	n/a	self.assertEqual(pulldom.START_DOCUMENT, evt)
50	n/a	evt, node = next(items)
51	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
52	n/a	self.assertEqual("html", node.tagName)
53	n/a	self.assertEqual(2, len(node.attributes))
54	n/a	self.assertEqual(node.attributes.getNamedItem("xmlns:xdc").value,
55	n/a	"http://www.xml.com/books")
56	n/a	evt, node = next(items)
57	n/a	self.assertEqual(pulldom.CHARACTERS, evt) # Line break
58	n/a	evt, node = next(items)
59	n/a	# XXX - A comment should be reported here!
60	n/a	# self.assertEqual(pulldom.COMMENT, evt)
61	n/a	# Line break after swallowed comment:
62	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
63	n/a	evt, node = next(items)
64	n/a	self.assertEqual("title", node.tagName)
65	n/a	title_node = node
66	n/a	evt, node = next(items)
67	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
68	n/a	self.assertEqual("Introduction to XSL", node.data)
69	n/a	evt, node = next(items)
70	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
71	n/a	self.assertEqual("title", node.tagName)
72	n/a	self.assertTrue(title_node is node)
73	n/a	evt, node = next(items)
74	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
75	n/a	evt, node = next(items)
76	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
77	n/a	self.assertEqual("hr", node.tagName)
78	n/a	evt, node = next(items)
79	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
80	n/a	self.assertEqual("hr", node.tagName)
81	n/a	evt, node = next(items)
82	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
83	n/a	evt, node = next(items)
84	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
85	n/a	self.assertEqual("p", node.tagName)
86	n/a	evt, node = next(items)
87	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
88	n/a	self.assertEqual("xdc:author", node.tagName)
89	n/a	evt, node = next(items)
90	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
91	n/a	evt, node = next(items)
92	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
93	n/a	self.assertEqual("xdc:author", node.tagName)
94	n/a	evt, node = next(items)
95	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
96	n/a	evt, node = next(items)
97	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
98	n/a	evt, node = next(items)
99	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
100	n/a	# XXX No END_DOCUMENT item is ever obtained:
101	n/a	#evt, node = next(items)
102	n/a	#self.assertEqual(pulldom.END_DOCUMENT, evt)
103	n/a
104	n/a	def test_expandItem(self):
105	n/a	"""Ensure expandItem works as expected."""
106	n/a	items = pulldom.parseString(SMALL_SAMPLE)
107	n/a	# Loop through the nodes until we get to a "title" start tag:
108	n/a	for evt, item in items:
109	n/a	if evt == pulldom.START_ELEMENT and item.tagName == "title":
110	n/a	items.expandNode(item)
111	n/a	self.assertEqual(1, len(item.childNodes))
112	n/a	break
113	n/a	else:
114	n/a	self.fail("No \"title\" element detected in SMALL_SAMPLE!")
115	n/a	# Loop until we get to the next start-element:
116	n/a	for evt, node in items:
117	n/a	if evt == pulldom.START_ELEMENT:
118	n/a	break
119	n/a	self.assertEqual("hr", node.tagName,
120	n/a	"expandNode did not leave DOMEventStream in the correct state.")
121	n/a	# Attempt to expand a standalone element:
122	n/a	items.expandNode(node)
123	n/a	self.assertEqual(next(items)[0], pulldom.CHARACTERS)
124	n/a	evt, node = next(items)
125	n/a	self.assertEqual(node.tagName, "p")
126	n/a	items.expandNode(node)
127	n/a	next(items) # Skip character data
128	n/a	evt, node = next(items)
129	n/a	self.assertEqual(node.tagName, "html")
130	n/a	with self.assertRaises(StopIteration):
131	n/a	next(items)
132	n/a	items.clear()
133	n/a	self.assertIsNone(items.parser)
134	n/a	self.assertIsNone(items.stream)
135	n/a
136	n/a	@unittest.expectedFailure
137	n/a	def test_comment(self):
138	n/a	"""PullDOM does not receive "comment" events."""
139	n/a	items = pulldom.parseString(SMALL_SAMPLE)
140	n/a	for evt, _ in items:
141	n/a	if evt == pulldom.COMMENT:
142	n/a	break
143	n/a	else:
144	n/a	self.fail("No comment was encountered")
145	n/a
146	n/a	@unittest.expectedFailure
147	n/a	def test_end_document(self):
148	n/a	"""PullDOM does not receive "end-document" events."""
149	n/a	items = pulldom.parseString(SMALL_SAMPLE)
150	n/a	# Read all of the nodes up to and including </html>:
151	n/a	for evt, node in items:
152	n/a	if evt == pulldom.END_ELEMENT and node.tagName == "html":
153	n/a	break
154	n/a	try:
155	n/a	# Assert that the next node is END_DOCUMENT:
156	n/a	evt, node = next(items)
157	n/a	self.assertEqual(pulldom.END_DOCUMENT, evt)
158	n/a	except StopIteration:
159	n/a	self.fail(
160	n/a	"Ran out of events, but should have received END_DOCUMENT")
161	n/a
162	n/a
163	n/a	class ThoroughTestCase(unittest.TestCase):
164	n/a	"""Test the hard-to-reach parts of pulldom."""
165	n/a
166	n/a	def test_thorough_parse(self):
167	n/a	"""Test some of the hard-to-reach parts of PullDOM."""
168	n/a	self._test_thorough(pulldom.parse(None, parser=SAXExerciser()))
169	n/a
170	n/a	@unittest.expectedFailure
171	n/a	def test_sax2dom_fail(self):
172	n/a	"""SAX2DOM can"t handle a PI before the root element."""
173	n/a	pd = SAX2DOMTestHelper(None, SAXExerciser(), 12)
174	n/a	self._test_thorough(pd)
175	n/a
176	n/a	def test_thorough_sax2dom(self):
177	n/a	"""Test some of the hard-to-reach parts of SAX2DOM."""
178	n/a	pd = SAX2DOMTestHelper(None, SAX2DOMExerciser(), 12)
179	n/a	self._test_thorough(pd, False)
180	n/a
181	n/a	def _test_thorough(self, pd, before_root=True):
182	n/a	"""Test some of the hard-to-reach parts of the parser, using a mock
183	n/a	parser."""
184	n/a
185	n/a	evt, node = next(pd)
186	n/a	self.assertEqual(pulldom.START_DOCUMENT, evt)
187	n/a	# Just check the node is a Document:
188	n/a	self.assertTrue(hasattr(node, "createElement"))
189	n/a
190	n/a	if before_root:
191	n/a	evt, node = next(pd)
192	n/a	self.assertEqual(pulldom.COMMENT, evt)
193	n/a	self.assertEqual("a comment", node.data)
194	n/a	evt, node = next(pd)
195	n/a	self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
196	n/a	self.assertEqual("target", node.target)
197	n/a	self.assertEqual("data", node.data)
198	n/a
199	n/a	evt, node = next(pd)
200	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
201	n/a	self.assertEqual("html", node.tagName)
202	n/a
203	n/a	evt, node = next(pd)
204	n/a	self.assertEqual(pulldom.COMMENT, evt)
205	n/a	self.assertEqual("a comment", node.data)
206	n/a	evt, node = next(pd)
207	n/a	self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
208	n/a	self.assertEqual("target", node.target)
209	n/a	self.assertEqual("data", node.data)
210	n/a
211	n/a	evt, node = next(pd)
212	n/a	self.assertEqual(pulldom.START_ELEMENT, evt)
213	n/a	self.assertEqual("p", node.tagName)
214	n/a
215	n/a	evt, node = next(pd)
216	n/a	self.assertEqual(pulldom.CHARACTERS, evt)
217	n/a	self.assertEqual("text", node.data)
218	n/a	evt, node = next(pd)
219	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
220	n/a	self.assertEqual("p", node.tagName)
221	n/a	evt, node = next(pd)
222	n/a	self.assertEqual(pulldom.END_ELEMENT, evt)
223	n/a	self.assertEqual("html", node.tagName)
224	n/a	evt, node = next(pd)
225	n/a	self.assertEqual(pulldom.END_DOCUMENT, evt)
226	n/a
227	n/a
228	n/a	class SAXExerciser(object):
229	n/a	"""A fake sax parser that calls some of the harder-to-reach sax methods to
230	n/a	ensure it emits the correct events"""
231	n/a
232	n/a	def setContentHandler(self, handler):
233	n/a	self._handler = handler
234	n/a
235	n/a	def parse(self, _):
236	n/a	h = self._handler
237	n/a	h.startDocument()
238	n/a
239	n/a	# The next two items ensure that items preceding the first
240	n/a	# start_element are properly stored and emitted:
241	n/a	h.comment("a comment")
242	n/a	h.processingInstruction("target", "data")
243	n/a
244	n/a	h.startElement("html", AttributesImpl({}))
245	n/a
246	n/a	h.comment("a comment")
247	n/a	h.processingInstruction("target", "data")
248	n/a
249	n/a	h.startElement("p", AttributesImpl({"class": "paraclass"}))
250	n/a	h.characters("text")
251	n/a	h.endElement("p")
252	n/a	h.endElement("html")
253	n/a	h.endDocument()
254	n/a
255	n/a	def stub(self, args, *kwargs):
256	n/a	"""Stub method. Does nothing."""
257	n/a	pass
258	n/a	setProperty = stub
259	n/a	setFeature = stub
260	n/a
261	n/a
262	n/a	class SAX2DOMExerciser(SAXExerciser):
263	n/a	"""The same as SAXExerciser, but without the processing instruction and
264	n/a	comment before the root element, because S2D can"t handle it"""
265	n/a
266	n/a	def parse(self, _):
267	n/a	h = self._handler
268	n/a	h.startDocument()
269	n/a	h.startElement("html", AttributesImpl({}))
270	n/a	h.comment("a comment")
271	n/a	h.processingInstruction("target", "data")
272	n/a	h.startElement("p", AttributesImpl({"class": "paraclass"}))
273	n/a	h.characters("text")
274	n/a	h.endElement("p")
275	n/a	h.endElement("html")
276	n/a	h.endDocument()
277	n/a
278	n/a
279	n/a	class SAX2DOMTestHelper(pulldom.DOMEventStream):
280	n/a	"""Allows us to drive SAX2DOM from a DOMEventStream."""
281	n/a
282	n/a	def reset(self):
283	n/a	self.pulldom = pulldom.SAX2DOM()
284	n/a	# This content handler relies on namespace support
285	n/a	self.parser.setFeature(xml.sax.handler.feature_namespaces, 1)
286	n/a	self.parser.setContentHandler(self.pulldom)
287	n/a
288	n/a
289	n/a	class SAX2DOMTestCase(unittest.TestCase):
290	n/a
291	n/a	def confirm(self, test, testname="Test"):
292	n/a	self.assertTrue(test, testname)
293	n/a
294	n/a	def test_basic(self):
295	n/a	"""Ensure SAX2DOM can parse from a stream."""
296	n/a	with io.StringIO(SMALL_SAMPLE) as fin:
297	n/a	sd = SAX2DOMTestHelper(fin, xml.sax.make_parser(),
298	n/a	len(SMALL_SAMPLE))
299	n/a	for evt, node in sd:
300	n/a	if evt == pulldom.START_ELEMENT and node.tagName == "html":
301	n/a	break
302	n/a	# Because the buffer is the same length as the XML, all the
303	n/a	# nodes should have been parsed and added:
304	n/a	self.assertGreater(len(node.childNodes), 0)
305	n/a
306	n/a	def testSAX2DOM(self):
307	n/a	"""Ensure SAX2DOM expands nodes as expected."""
308	n/a	sax2dom = pulldom.SAX2DOM()
309	n/a	sax2dom.startDocument()
310	n/a	sax2dom.startElement("doc", {})
311	n/a	sax2dom.characters("text")
312	n/a	sax2dom.startElement("subelm", {})
313	n/a	sax2dom.characters("text")
314	n/a	sax2dom.endElement("subelm")
315	n/a	sax2dom.characters("text")
316	n/a	sax2dom.endElement("doc")
317	n/a	sax2dom.endDocument()
318	n/a
319	n/a	doc = sax2dom.document
320	n/a	root = doc.documentElement
321	n/a	(text1, elm1, text2) = root.childNodes
322	n/a	text3 = elm1.childNodes[0]
323	n/a
324	n/a	self.assertIsNone(text1.previousSibling)
325	n/a	self.assertIs(text1.nextSibling, elm1)
326	n/a	self.assertIs(elm1.previousSibling, text1)
327	n/a	self.assertIs(elm1.nextSibling, text2)
328	n/a	self.assertIs(text2.previousSibling, elm1)
329	n/a	self.assertIsNone(text2.nextSibling)
330	n/a	self.assertIsNone(text3.previousSibling)
331	n/a	self.assertIsNone(text3.nextSibling)
332	n/a
333	n/a	self.assertIs(root.parentNode, doc)
334	n/a	self.assertIs(text1.parentNode, root)
335	n/a	self.assertIs(elm1.parentNode, root)
336	n/a	self.assertIs(text2.parentNode, root)
337	n/a	self.assertIs(text3.parentNode, elm1)
338	n/a	doc.unlink()
339	n/a
340	n/a
341	n/a	if __name__ == "__main__":
342	n/a	unittest.main()