[Python-checkins] cpython: Issue #14007: accept incomplete TreeBuilder objects (missing
florent.xicluna
python-checkins at python.org
Mon Mar 5 10:43:03 CET 2012
http://hg.python.org/cpython/rev/47016103185f
changeset: 75411:47016103185f
user: Florent Xicluna <florent.xicluna at gmail.com>
date: Mon Mar 05 10:42:19 2012 +0100
summary:
Issue #14007: accept incomplete TreeBuilder objects (missing start/end/data/close) for the Python implementation as well. Add disabled tests for the doctype() method.
files:
Lib/test/test_xml_etree.py | 165 +++++++++++++++-------
Lib/xml/etree/ElementTree.py | 81 +++++-----
Misc/NEWS | 4 +
3 files changed, 155 insertions(+), 95 deletions(-)
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@@ -1855,58 +1855,16 @@
# --------------------------------------------------------------------
-class CleanContext(object):
- """Provide default namespace mapping and path cache."""
- checkwarnings = None
+class ElementTreeTest(unittest.TestCase):
- def __init__(self, quiet=False):
- if sys.flags.optimize >= 2:
- # under -OO, doctests cannot be run and therefore not all warnings
- # will be emitted
- quiet = True
- deprecations = (
- # Search behaviour is broken if search path starts with "/".
- ("This search is broken in 1.3 and earlier, and will be fixed "
- "in a future version. If you rely on the current behaviour, "
- "change it to '.+'", FutureWarning),
- # Element.getchildren() and Element.getiterator() are deprecated.
- ("This method will be removed in future versions. "
- "Use .+ instead.", DeprecationWarning),
- ("This method will be removed in future versions. "
- "Use .+ instead.", PendingDeprecationWarning),
- # XMLParser.doctype() is deprecated.
- ("This method of XMLParser is deprecated. Define doctype.. "
- "method on the TreeBuilder target.", DeprecationWarning))
- self.checkwarnings = support.check_warnings(*deprecations, quiet=quiet)
-
- def __enter__(self):
- from xml.etree import ElementPath
- self._nsmap = ET.register_namespace._namespace_map
- # Copy the default namespace mapping
- self._nsmap_copy = self._nsmap.copy()
- # Copy the path cache (should be empty)
- self._path_cache = ElementPath._cache
- ElementPath._cache = self._path_cache.copy()
- self.checkwarnings.__enter__()
-
- def __exit__(self, *args):
- from xml.etree import ElementPath
- # Restore mapping and path cache
- self._nsmap.clear()
- self._nsmap.update(self._nsmap_copy)
- ElementPath._cache = self._path_cache
- self.checkwarnings.__exit__(*args)
-
-
-class TestAcceleratorNotImported(unittest.TestCase):
- # Test that the C accelerator was not imported for pyET
- def test_correct_import_pyET(self):
- self.assertEqual(pyET.SubElement.__module__, 'xml.etree.ElementTree')
-
-
-class TestElementClass(unittest.TestCase):
- def test_Element_is_a_type(self):
+ def test_istype(self):
+ self.assertIsInstance(ET.ParseError, type)
+ self.assertIsInstance(ET.QName, type)
+ self.assertIsInstance(ET.ElementTree, type)
self.assertIsInstance(ET.Element, type)
+ # XXX issue 14128 with C ElementTree
+ # self.assertIsInstance(ET.TreeBuilder, type)
+ # self.assertIsInstance(ET.XMLParser, type)
def test_Element_subclass_trivial(self):
class MyElement(ET.Element):
@@ -1936,16 +1894,115 @@
self.assertEqual(mye.newmethod(), 'joe')
+class TreeBuilderTest(unittest.TestCase):
+
+ sample1 = ('<!DOCTYPE html PUBLIC'
+ ' "-//W3C//DTD XHTML 1.0 Transitional//EN"'
+ ' "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">'
+ '<html>text</html>')
+
+ def test_dummy_builder(self):
+ class BaseDummyBuilder:
+ def close(self):
+ return 42
+
+ class DummyBuilder(BaseDummyBuilder):
+ data = start = end = lambda *a: None
+
+ parser = ET.XMLParser(target=DummyBuilder())
+ parser.feed(self.sample1)
+ self.assertEqual(parser.close(), 42)
+
+ parser = ET.XMLParser(target=BaseDummyBuilder())
+ parser.feed(self.sample1)
+ self.assertEqual(parser.close(), 42)
+
+ parser = ET.XMLParser(target=object())
+ parser.feed(self.sample1)
+ self.assertIsNone(parser.close())
+
+
+ @unittest.expectedFailure # XXX issue 14007 with C ElementTree
+ def test_doctype(self):
+ class DoctypeParser:
+ _doctype = None
+
+ def doctype(self, name, pubid, system):
+ self._doctype = (name, pubid, system)
+
+ def close(self):
+ return self._doctype
+
+ parser = ET.XMLParser(target=DoctypeParser())
+ parser.feed(self.sample1)
+
+ self.assertEqual(parser.close(),
+ ('html', '-//W3C//DTD XHTML 1.0 Transitional//EN',
+ 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd'))
+
+
+class NoAcceleratorTest(unittest.TestCase):
+
+ # Test that the C accelerator was not imported for pyET
+ def test_correct_import_pyET(self):
+ self.assertEqual(pyET.Element.__module__, 'xml.etree.ElementTree')
+ self.assertEqual(pyET.SubElement.__module__, 'xml.etree.ElementTree')
+
+# --------------------------------------------------------------------
+
+
+class CleanContext(object):
+ """Provide default namespace mapping and path cache."""
+ checkwarnings = None
+
+ def __init__(self, quiet=False):
+ if sys.flags.optimize >= 2:
+ # under -OO, doctests cannot be run and therefore not all warnings
+ # will be emitted
+ quiet = True
+ deprecations = (
+ # Search behaviour is broken if search path starts with "/".
+ ("This search is broken in 1.3 and earlier, and will be fixed "
+ "in a future version. If you rely on the current behaviour, "
+ "change it to '.+'", FutureWarning),
+ # Element.getchildren() and Element.getiterator() are deprecated.
+ ("This method will be removed in future versions. "
+ "Use .+ instead.", DeprecationWarning),
+ ("This method will be removed in future versions. "
+ "Use .+ instead.", PendingDeprecationWarning))
+ self.checkwarnings = support.check_warnings(*deprecations, quiet=quiet)
+
+ def __enter__(self):
+ from xml.etree import ElementPath
+ self._nsmap = ET.register_namespace._namespace_map
+ # Copy the default namespace mapping
+ self._nsmap_copy = self._nsmap.copy()
+ # Copy the path cache (should be empty)
+ self._path_cache = ElementPath._cache
+ ElementPath._cache = self._path_cache.copy()
+ self.checkwarnings.__enter__()
+
+ def __exit__(self, *args):
+ from xml.etree import ElementPath
+ # Restore mapping and path cache
+ self._nsmap.clear()
+ self._nsmap.update(self._nsmap_copy)
+ ElementPath._cache = self._path_cache
+ self.checkwarnings.__exit__(*args)
+
+
def test_main(module=pyET):
from test import test_xml_etree
- # Run the tests specific to the Python implementation
- support.run_unittest(TestAcceleratorNotImported)
-
# The same doctests are used for both the Python and the C implementations
test_xml_etree.ET = module
- support.run_unittest(TestElementClass)
+ test_classes = [ElementTreeTest, TreeBuilderTest]
+ if module is pyET:
+ # Run the tests specific to the Python implementation
+ test_classes += [NoAcceleratorTest]
+
+ support.run_unittest(*test_classes)
# XXX the C module should give the same warnings as the Python module
with CleanContext(quiet=(module is not pyET)):
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
--- a/Lib/xml/etree/ElementTree.py
+++ b/Lib/xml/etree/ElementTree.py
@@ -1511,24 +1511,30 @@
self.target = self._target = target
self._error = expat.error
self._names = {} # name memo cache
- # callbacks
+ # main callbacks
parser.DefaultHandlerExpand = self._default
- parser.StartElementHandler = self._start
- parser.EndElementHandler = self._end
- parser.CharacterDataHandler = self._data
- # optional callbacks
- parser.CommentHandler = self._comment
- parser.ProcessingInstructionHandler = self._pi
+ if hasattr(target, 'start'):
+ parser.StartElementHandler = self._start
+ if hasattr(target, 'end'):
+ parser.EndElementHandler = self._end
+ if hasattr(target, 'data'):
+ parser.CharacterDataHandler = target.data
+ # miscellaneous callbacks
+ if hasattr(target, 'comment'):
+ parser.CommentHandler = target.comment
+ if hasattr(target, 'pi'):
+ parser.ProcessingInstructionHandler = target.pi
# let expat do the buffering, if supported
try:
- self._parser.buffer_text = 1
+ parser.buffer_text = 1
except AttributeError:
pass
# use new-style attribute handling, if supported
try:
- self._parser.ordered_attributes = 1
- self._parser.specified_attributes = 1
- parser.StartElementHandler = self._start_list
+ parser.ordered_attributes = 1
+ parser.specified_attributes = 1
+ if hasattr(target, 'start'):
+ parser.StartElementHandler = self._start_list
except AttributeError:
pass
self._doctype = None
@@ -1572,44 +1578,29 @@
attrib[fixname(attrib_in[i])] = attrib_in[i+1]
return self.target.start(tag, attrib)
- def _data(self, text):
- return self.target.data(text)
-
def _end(self, tag):
return self.target.end(self._fixname(tag))
- def _comment(self, data):
- try:
- comment = self.target.comment
- except AttributeError:
- pass
- else:
- return comment(data)
-
- def _pi(self, target, data):
- try:
- pi = self.target.pi
- except AttributeError:
- pass
- else:
- return pi(target, data)
-
def _default(self, text):
prefix = text[:1]
if prefix == "&":
# deal with undefined entities
try:
- self.target.data(self.entity[text[1:-1]])
+ data_handler = self.target.data
+ except AttributeError:
+ return
+ try:
+ data_handler(self.entity[text[1:-1]])
except KeyError:
from xml.parsers import expat
err = expat.error(
"undefined entity %s: line %d, column %d" %
- (text, self._parser.ErrorLineNumber,
- self._parser.ErrorColumnNumber)
+ (text, self.parser.ErrorLineNumber,
+ self.parser.ErrorColumnNumber)
)
err.code = 11 # XML_ERROR_UNDEFINED_ENTITY
- err.lineno = self._parser.ErrorLineNumber
- err.offset = self._parser.ErrorColumnNumber
+ err.lineno = self.parser.ErrorLineNumber
+ err.offset = self.parser.ErrorColumnNumber
raise err
elif prefix == "<" and text[:9] == "<!DOCTYPE":
self._doctype = [] # inside a doctype declaration
@@ -1636,7 +1627,7 @@
pubid = pubid[1:-1]
if hasattr(self.target, "doctype"):
self.target.doctype(name, pubid, system[1:-1])
- elif self.doctype is not self._XMLParser__doctype:
+ elif self.doctype != self._XMLParser__doctype:
# warn about deprecated call
self._XMLParser__doctype(name, pubid, system[1:-1])
self.doctype(name, pubid, system[1:-1])
@@ -1667,7 +1658,7 @@
def feed(self, data):
try:
- self._parser.Parse(data, 0)
+ self.parser.Parse(data, 0)
except self._error as v:
self._raiseerror(v)
@@ -1679,12 +1670,20 @@
def close(self):
try:
- self._parser.Parse("", 1) # end of data
+ self.parser.Parse("", 1) # end of data
except self._error as v:
self._raiseerror(v)
- tree = self.target.close()
- del self.target, self._parser # get rid of circular references
- return tree
+ try:
+ try:
+ close_handler = self.target.close
+ except AttributeError:
+ pass
+ else:
+ return close_handler()
+ finally:
+ # get rid of circular references
+ del self.parser, self._parser
+ del self.target, self._target
# Import the C accelerators
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -13,6 +13,10 @@
Library
-------
+- Issue #14007: Accept incomplete TreeBuilder objects (missing start, end,
+ data or close method) for the Python implementation as well.
+ Drop the no-op TreeBuilder().xml() method from the C implementation.
+
What's New in Python 3.3.0 Alpha 1?
===================================
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list