def PullDOMAdapter(node):
from xml.dom import Node
from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, COMMENT, CHARACTERS
if node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
for childNode in node.childNodes:
for event in PullDOMAdapter(childNode):
yield event
elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
raise NotImplementedError("DOCTYPE nodes are not supported by PullDOM")
elif node.nodeType == Node.COMMENT_NODE:
yield COMMENT, node
elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
yield CHARACTERS, node
elif node.nodeType == Node.ELEMENT_NODE:
yield START_ELEMENT, node
for childNode in node.childNodes:
for event in PullDOMAdapter(childNode):
yield event
yield END_ELEMENT, node
else:
raise NotImplementedError("Node type not supported: " + str(node.nodeType))
python类START_ELEMENT的实例源码
def test_expandItem(self):
"""Ensure expandItem works as expected."""
items = pulldom.parseString(SMALL_SAMPLE)
# Loop through the nodes until we get to a "title" start tag:
for evt, item in items:
if evt == pulldom.START_ELEMENT and item.tagName == "title":
items.expandNode(item)
self.assertEqual(1, len(item.childNodes))
break
else:
self.fail("No \"title\" element detected in SMALL_SAMPLE!")
# Loop until we get to the next start-element:
for evt, node in items:
if evt == pulldom.START_ELEMENT:
break
self.assertEqual("hr", node.tagName,
"expandNode did not leave DOMEventStream in the correct state.")
# Attempt to expand a standalone element:
items.expandNode(node)
self.assertEqual(next(items)[0], pulldom.CHARACTERS)
evt, node = next(items)
self.assertEqual(node.tagName, "p")
items.expandNode(node)
next(items) # Skip character data
evt, node = next(items)
self.assertEqual(node.tagName, "html")
with self.assertRaises(StopIteration):
next(items)
items.clear()
self.assertIsNone(items.parser)
self.assertIsNone(items.stream)
def test_basic(self):
"""Ensure SAX2DOM can parse from a stream."""
with io.StringIO(SMALL_SAMPLE) as fin:
sd = SAX2DOMTestHelper(fin, xml.sax.make_parser(),
len(SMALL_SAMPLE))
for evt, node in sd:
if evt == pulldom.START_ELEMENT and node.tagName == "html":
break
# Because the buffer is the same length as the XML, all the
# nodes should have been parsed and added:
self.assertGreater(len(node.childNodes), 0)
def test_expandItem(self):
"""Ensure expandItem works as expected."""
items = pulldom.parseString(SMALL_SAMPLE)
# Loop through the nodes until we get to a "title" start tag:
for evt, item in items:
if evt == pulldom.START_ELEMENT and item.tagName == "title":
items.expandNode(item)
self.assertEqual(1, len(item.childNodes))
break
else:
self.fail("No \"title\" element detected in SMALL_SAMPLE!")
# Loop until we get to the next start-element:
for evt, node in items:
if evt == pulldom.START_ELEMENT:
break
self.assertEqual("hr", node.tagName,
"expandNode did not leave DOMEventStream in the correct state.")
# Attempt to expand a standalone element:
items.expandNode(node)
self.assertEqual(next(items)[0], pulldom.CHARACTERS)
evt, node = next(items)
self.assertEqual(node.tagName, "p")
items.expandNode(node)
next(items) # Skip character data
evt, node = next(items)
self.assertEqual(node.tagName, "html")
with self.assertRaises(StopIteration):
next(items)
items.clear()
self.assertIsNone(items.parser)
self.assertIsNone(items.stream)
def test_basic(self):
"""Ensure SAX2DOM can parse from a stream."""
with io.StringIO(SMALL_SAMPLE) as fin:
sd = SAX2DOMTestHelper(fin, xml.sax.make_parser(),
len(SMALL_SAMPLE))
for evt, node in sd:
if evt == pulldom.START_ELEMENT and node.tagName == "html":
break
# Because the buffer is the same length as the XML, all the
# nodes should have been parsed and added:
self.assertGreater(len(node.childNodes), 0)
def test_expandItem(self):
"""Ensure expandItem works as expected."""
items = pulldom.parseString(SMALL_SAMPLE)
# Loop through the nodes until we get to a "title" start tag:
for evt, item in items:
if evt == pulldom.START_ELEMENT and item.tagName == "title":
items.expandNode(item)
self.assertEqual(1, len(item.childNodes))
break
else:
self.fail("No \"title\" element detected in SMALL_SAMPLE!")
# Loop until we get to the next start-element:
for evt, node in items:
if evt == pulldom.START_ELEMENT:
break
self.assertEqual("hr", node.tagName,
"expandNode did not leave DOMEventStream in the correct state.")
# Attempt to expand a standalone element:
items.expandNode(node)
self.assertEqual(next(items)[0], pulldom.CHARACTERS)
evt, node = next(items)
self.assertEqual(node.tagName, "p")
items.expandNode(node)
next(items) # Skip character data
evt, node = next(items)
self.assertEqual(node.tagName, "html")
with self.assertRaises(StopIteration):
next(items)
items.clear()
self.assertIsNone(items.parser)
self.assertIsNone(items.stream)
def test_basic(self):
"""Ensure SAX2DOM can parse from a stream."""
with io.StringIO(SMALL_SAMPLE) as fin:
sd = SAX2DOMTestHelper(fin, xml.sax.make_parser(),
len(SMALL_SAMPLE))
for evt, node in sd:
if evt == pulldom.START_ELEMENT and node.tagName == "html":
break
# Because the buffer is the same length as the XML, all the
# nodes should have been parsed and added:
self.assertGreater(len(node.childNodes), 0)
def dmoz_reader(filename):
doc = pulldom.parse(filename)
for event, node in doc:
if event == pulldom.START_ELEMENT and node.tagName == 'ExternalPage':
doc.expandNode(node)
url = node.attributes['about'].value
topic_node = node.getElementsByTagName('topic')[0]
topics = topic_node.childNodes[0].data
yield url, topics
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.iteritems():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def test_parse_semantics(self):
"""Test DOMEventStream parsing semantics."""
items = pulldom.parseString(SMALL_SAMPLE)
evt, node = next(items)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
self.assertEqual(pulldom.START_DOCUMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
self.assertEqual(2, len(node.attributes))
self.assertEqual(node.attributes.getNamedItem("xmlns:xdc").value,
"http://www.xml.com/books")
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt) # Line break
evt, node = next(items)
# XXX - A comment should be reported here!
# self.assertEqual(pulldom.COMMENT, evt)
# Line break after swallowed comment:
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual("title", node.tagName)
title_node = node
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("Introduction to XSL", node.data)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("title", node.tagName)
self.assertTrue(title_node is node)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
# XXX No END_DOCUMENT item is ever obtained:
#evt, node = next(items)
#self.assertEqual(pulldom.END_DOCUMENT, evt)
def _test_thorough(self, pd, before_root=True):
"""Test some of the hard-to-reach parts of the parser, using a mock
parser."""
evt, node = next(pd)
self.assertEqual(pulldom.START_DOCUMENT, evt)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
if before_root:
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("text", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_DOCUMENT, evt)
def startElementNS(self, name, tagName , attrs):
# Retrieve xml namespace declaration attributes.
xmlns_uri = 'http://www.w3.org/2000/xmlns/'
xmlns_attrs = getattr(self, '_xmlns_attrs', None)
if xmlns_attrs is not None:
for aname, value in xmlns_attrs:
attrs._attrs[(xmlns_uri, aname)] = value
self._xmlns_attrs = []
uri, localname = name
if uri:
# When using namespaces, the reader may or may not
# provide us with the original name. If not, create
# *a* valid tagName from the current context.
if tagName is None:
prefix = self._current_context[uri]
if prefix:
tagName = prefix + ":" + localname
else:
tagName = localname
if self.document:
node = self.document.createElementNS(uri, tagName)
else:
node = self.buildDocument(uri, tagName)
else:
# When the tagname is not prefixed, it just appears as
# localname
if self.document:
node = self.document.createElement(localname)
else:
node = self.buildDocument(None, localname)
for aname,value in attrs.items():
a_uri, a_localname = aname
if a_uri == xmlns_uri:
if a_localname == 'xmlns':
qname = a_localname
else:
qname = 'xmlns:' + a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
elif a_uri:
prefix = self._current_context[a_uri]
if prefix:
qname = prefix + ":" + a_localname
else:
qname = a_localname
attr = self.document.createAttributeNS(a_uri, qname)
node.setAttributeNodeNS(attr)
else:
attr = self.document.createAttribute(a_localname)
node.setAttributeNode(attr)
attr.value = value
self.lastEvent[1] = [(START_ELEMENT, node), None]
self.lastEvent = self.lastEvent[1]
self.push(node)
def test_parse_semantics(self):
"""Test DOMEventStream parsing semantics."""
items = pulldom.parseString(SMALL_SAMPLE)
evt, node = next(items)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
self.assertEqual(pulldom.START_DOCUMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
self.assertEqual(2, len(node.attributes))
self.assertEqual(node.attributes.getNamedItem("xmlns:xdc").value,
"http://www.xml.com/books")
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt) # Line break
evt, node = next(items)
# XXX - A comment should be reported here!
# self.assertEqual(pulldom.COMMENT, evt)
# Line break after swallowed comment:
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual("title", node.tagName)
title_node = node
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("Introduction to XSL", node.data)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("title", node.tagName)
self.assertTrue(title_node is node)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
# XXX No END_DOCUMENT item is ever obtained:
#evt, node = next(items)
#self.assertEqual(pulldom.END_DOCUMENT, evt)
def _test_thorough(self, pd, before_root=True):
"""Test some of the hard-to-reach parts of the parser, using a mock
parser."""
evt, node = next(pd)
self.assertEqual(pulldom.START_DOCUMENT, evt)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
if before_root:
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("text", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_DOCUMENT, evt)
def test_parse_semantics(self):
"""Test DOMEventStream parsing semantics."""
items = pulldom.parseString(SMALL_SAMPLE)
evt, node = next(items)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
self.assertEqual(pulldom.START_DOCUMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
self.assertEqual(2, len(node.attributes))
self.assertEqual(node.attributes.getNamedItem("xmlns:xdc").value,
"http://www.xml.com/books")
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt) # Line break
evt, node = next(items)
# XXX - A comment should be reported here!
# self.assertEqual(pulldom.COMMENT, evt)
# Line break after swallowed comment:
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual("title", node.tagName)
title_node = node
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("Introduction to XSL", node.data)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("title", node.tagName)
self.assertTrue(title_node is node)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("hr", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("xdc:author", node.tagName)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
evt, node = next(items)
self.assertEqual(pulldom.CHARACTERS, evt)
evt, node = next(items)
self.assertEqual(pulldom.END_ELEMENT, evt)
# XXX No END_DOCUMENT item is ever obtained:
#evt, node = next(items)
#self.assertEqual(pulldom.END_DOCUMENT, evt)
def _test_thorough(self, pd, before_root=True):
"""Test some of the hard-to-reach parts of the parser, using a mock
parser."""
evt, node = next(pd)
self.assertEqual(pulldom.START_DOCUMENT, evt)
# Just check the node is a Document:
self.assertTrue(hasattr(node, "createElement"))
if before_root:
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.COMMENT, evt)
self.assertEqual("a comment", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.PROCESSING_INSTRUCTION, evt)
self.assertEqual("target", node.target)
self.assertEqual("data", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.START_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.CHARACTERS, evt)
self.assertEqual("text", node.data)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("p", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_ELEMENT, evt)
self.assertEqual("html", node.tagName)
evt, node = next(pd)
self.assertEqual(pulldom.END_DOCUMENT, evt)
