2000-03-31 11:44:52 -04:00
|
|
|
# XXX TypeErrors on calling handlers, or on bad return values from a
|
|
|
|
# handler, are obscure and unhelpful.
|
2000-10-23 14:22:08 -03:00
|
|
|
|
2008-01-08 10:30:55 -04:00
|
|
|
import StringIO, sys
|
2007-03-28 20:34:06 -03:00
|
|
|
import unittest
|
|
|
|
|
2000-09-23 01:47:56 -03:00
|
|
|
from xml.parsers import expat
|
2000-10-23 14:22:08 -03:00
|
|
|
|
2011-04-10 21:44:28 -03:00
|
|
|
from test import test_support
|
2007-03-28 20:34:06 -03:00
|
|
|
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],
|
|
|
|
]
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test_returns_unicode(self):
|
|
|
|
for x, y in self.set_get_pairs:
|
|
|
|
self.parser.returns_unicode = x
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.parser.returns_unicode, y)
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test_ordered_attributes(self):
|
|
|
|
for x, y in self.set_get_pairs:
|
|
|
|
self.parser.ordered_attributes = x
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.parser.ordered_attributes, y)
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test_specified_attributes(self):
|
|
|
|
for x, y in self.set_get_pairs:
|
|
|
|
self.parser.specified_attributes = x
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.parser.specified_attributes, y)
|
Get rid of the superstitious "~" in dict hashing's "i = (~hash) & mask".
The comment following used to say:
/* We use ~hash instead of hash, as degenerate hash functions, such
as for ints <sigh>, can have lots of leading zeros. It's not
really a performance risk, but better safe than sorry.
12-Dec-00 tim: so ~hash produces lots of leading ones instead --
what's the gain? */
That is, there was never a good reason for doing it. And to the contrary,
as explained on Python-Dev last December, it tended to make the *sum*
(i + incr) & mask (which is the first table index examined in case of
collison) the same "too often" across distinct hashes.
Changing to the simpler "i = hash & mask" reduced the number of string-dict
collisions (== # number of times we go around the lookup for-loop) from about
6 million to 5 million during a full run of the test suite (these are
approximate because the test suite does some random stuff from run to run).
The number of collisions in non-string dicts also decreased, but not as
dramatically.
Note that this may, for a given dict, change the order (wrt previous
releases) of entries exposed by .keys(), .values() and .items(). A number
of std tests suffered bogus failures as a result. For dicts keyed by
small ints, or (less so) by characters, the order is much more likely to be
in increasing order of key now; e.g.,
>>> d = {}
>>> for i in range(10):
... d[i] = i
...
>>> d
{0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6, 7: 7, 8: 8, 9: 9}
>>>
Unfortunately. people may latch on to that in small examples and draw a
bogus conclusion.
test_support.py
Moved test_extcall's sortdict() into test_support, made it stronger,
and imported sortdict into other std tests that needed it.
test_unicode.py
Excluced cp875 from the "roundtrip over range(128)" test, because
cp875 doesn't have a well-defined inverse for unicode("?", "cp875").
See Python-Dev for excruciating details.
Cookie.py
Chaged various output functions to sort dicts before building
strings from them.
test_extcall
Fiddled the expected-result file. This remains sensitive to native
dict ordering, because, e.g., if there are multiple errors in a
keyword-arg dict (and test_extcall sets up many cases like that), the
specific error Python complains about first depends on native dict
ordering.
2001-05-12 21:19:31 -03:00
|
|
|
|
2000-03-31 11:44:52 -04:00
|
|
|
|
2000-09-21 17:32:13 -03:00
|
|
|
data = '''\
|
|
|
|
<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
|
2000-03-31 11:44:52 -04:00
|
|
|
<?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;
|
|
|
|
]>
|
|
|
|
|
2000-06-26 21:37:25 -03:00
|
|
|
<root attr1="value1" attr2="value2ὀ">
|
2000-03-31 11:44:52 -04:00
|
|
|
<myns:subelement xmlns:myns="http://www.python.org/namespace">
|
|
|
|
Contents of subelements
|
|
|
|
</myns:subelement>
|
|
|
|
<sub2><![CDATA[contents of CDATA section]]></sub2>
|
|
|
|
&external_entity;
|
|
|
|
</root>
|
2000-09-21 17:32:13 -03:00
|
|
|
'''
|
2000-03-31 11:44:52 -04:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
|
2000-06-26 21:37:25 -03:00
|
|
|
# Produce UTF-8 output
|
2007-03-28 20:34:06 -03:00
|
|
|
class ParseTest(unittest.TestCase):
|
|
|
|
class Outputter:
|
|
|
|
def __init__(self):
|
|
|
|
self.out = []
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def StartElementHandler(self, name, attrs):
|
2007-04-25 03:30:05 -03:00
|
|
|
self.out.append('Start element: ' + repr(name) + ' ' +
|
2007-03-28 20:34:06 -03:00
|
|
|
sortdict(attrs))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def EndElementHandler(self, name):
|
|
|
|
self.out.append('End element: ' + repr(name))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def CharacterDataHandler(self, data):
|
|
|
|
data = data.strip()
|
|
|
|
if data:
|
|
|
|
self.out.append('Character data: ' + repr(data))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def ProcessingInstructionHandler(self, target, data):
|
|
|
|
self.out.append('PI: ' + repr(target) + ' ' + repr(data))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def StartNamespaceDeclHandler(self, prefix, uri):
|
|
|
|
self.out.append('NS decl: ' + repr(prefix) + ' ' + repr(uri))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def EndNamespaceDeclHandler(self, prefix):
|
|
|
|
self.out.append('End of NS decl: ' + repr(prefix))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def StartCdataSectionHandler(self):
|
|
|
|
self.out.append('Start of CDATA section')
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def EndCdataSectionHandler(self):
|
|
|
|
self.out.append('End of CDATA section')
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def CommentHandler(self, text):
|
|
|
|
self.out.append('Comment: ' + repr(text))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def NotationDeclHandler(self, *args):
|
|
|
|
name, base, sysid, pubid = args
|
|
|
|
self.out.append('Notation declared: %s' %(args,))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def UnparsedEntityDeclHandler(self, *args):
|
|
|
|
entityName, base, systemId, publicId, notationName = args
|
|
|
|
self.out.append('Unparsed entity decl: %s' %(args,))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def NotStandaloneHandler(self, userData):
|
|
|
|
self.out.append('Not standalone')
|
|
|
|
return 1
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def ExternalEntityRefHandler(self, *args):
|
|
|
|
context, base, sysId, pubId = args
|
|
|
|
self.out.append('External entity ref: %s' %(args[1:],))
|
|
|
|
return 1
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def DefaultHandler(self, userData):
|
|
|
|
pass
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def DefaultHandlerExpand(self, userData):
|
|
|
|
pass
|
|
|
|
|
|
|
|
handler_names = [
|
|
|
|
'StartElementHandler', 'EndElementHandler',
|
|
|
|
'CharacterDataHandler', 'ProcessingInstructionHandler',
|
|
|
|
'UnparsedEntityDeclHandler', 'NotationDeclHandler',
|
|
|
|
'StartNamespaceDeclHandler', 'EndNamespaceDeclHandler',
|
|
|
|
'CommentHandler', 'StartCdataSectionHandler',
|
|
|
|
'EndCdataSectionHandler',
|
|
|
|
'DefaultHandler', 'DefaultHandlerExpand',
|
|
|
|
#'NotStandaloneHandler',
|
|
|
|
'ExternalEntityRefHandler'
|
|
|
|
]
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test_utf8(self):
|
|
|
|
|
|
|
|
out = self.Outputter()
|
|
|
|
parser = expat.ParserCreate(namespace_separator='!')
|
|
|
|
for name in self.handler_names:
|
|
|
|
setattr(parser, name, getattr(out, name))
|
|
|
|
parser.returns_unicode = 0
|
|
|
|
parser.Parse(data, 1)
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
# Verify output
|
|
|
|
op = out.out
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(op[0], 'PI: \'xml-stylesheet\' \'href="stylesheet.css"\'')
|
|
|
|
self.assertEqual(op[1], "Comment: ' comment data '")
|
|
|
|
self.assertEqual(op[2], "Notation declared: ('notation', None, 'notation.jpeg', None)")
|
|
|
|
self.assertEqual(op[3], "Unparsed entity decl: ('unparsed_entity', None, 'entity.file', None, 'notation')")
|
|
|
|
self.assertEqual(op[4], "Start element: 'root' {'attr1': 'value1', 'attr2': 'value2\\xe1\\xbd\\x80'}")
|
|
|
|
self.assertEqual(op[5], "NS decl: 'myns' 'http://www.python.org/namespace'")
|
|
|
|
self.assertEqual(op[6], "Start element: 'http://www.python.org/namespace!subelement' {}")
|
|
|
|
self.assertEqual(op[7], "Character data: 'Contents of subelements'")
|
|
|
|
self.assertEqual(op[8], "End element: 'http://www.python.org/namespace!subelement'")
|
|
|
|
self.assertEqual(op[9], "End of NS decl: 'myns'")
|
|
|
|
self.assertEqual(op[10], "Start element: 'sub2' {}")
|
|
|
|
self.assertEqual(op[11], 'Start of CDATA section')
|
|
|
|
self.assertEqual(op[12], "Character data: 'contents of CDATA section'")
|
|
|
|
self.assertEqual(op[13], 'End of CDATA section')
|
|
|
|
self.assertEqual(op[14], "End element: 'sub2'")
|
|
|
|
self.assertEqual(op[15], "External entity ref: (None, 'entity.file', None)")
|
|
|
|
self.assertEqual(op[16], "End element: 'root'")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test_unicode(self):
|
|
|
|
# Try the parse again, this time producing Unicode output
|
|
|
|
out = self.Outputter()
|
|
|
|
parser = expat.ParserCreate(namespace_separator='!')
|
|
|
|
parser.returns_unicode = 1
|
|
|
|
for name in self.handler_names:
|
|
|
|
setattr(parser, name, getattr(out, name))
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
parser.Parse(data, 1)
|
|
|
|
|
|
|
|
op = out.out
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(op[0], 'PI: u\'xml-stylesheet\' u\'href="stylesheet.css"\'')
|
|
|
|
self.assertEqual(op[1], "Comment: u' comment data '")
|
|
|
|
self.assertEqual(op[2], "Notation declared: (u'notation', None, u'notation.jpeg', None)")
|
|
|
|
self.assertEqual(op[3], "Unparsed entity decl: (u'unparsed_entity', None, u'entity.file', None, u'notation')")
|
|
|
|
self.assertEqual(op[4], "Start element: u'root' {u'attr1': u'value1', u'attr2': u'value2\\u1f40'}")
|
|
|
|
self.assertEqual(op[5], "NS decl: u'myns' u'http://www.python.org/namespace'")
|
|
|
|
self.assertEqual(op[6], "Start element: u'http://www.python.org/namespace!subelement' {}")
|
|
|
|
self.assertEqual(op[7], "Character data: u'Contents of subelements'")
|
|
|
|
self.assertEqual(op[8], "End element: u'http://www.python.org/namespace!subelement'")
|
|
|
|
self.assertEqual(op[9], "End of NS decl: u'myns'")
|
|
|
|
self.assertEqual(op[10], "Start element: u'sub2' {}")
|
|
|
|
self.assertEqual(op[11], 'Start of CDATA section')
|
|
|
|
self.assertEqual(op[12], "Character data: u'contents of CDATA section'")
|
|
|
|
self.assertEqual(op[13], 'End of CDATA section')
|
|
|
|
self.assertEqual(op[14], "End element: u'sub2'")
|
|
|
|
self.assertEqual(op[15], "External entity ref: (None, u'entity.file', None)")
|
|
|
|
self.assertEqual(op[16], "End element: u'root'")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test_parse_file(self):
|
|
|
|
# Try parsing a file
|
|
|
|
out = self.Outputter()
|
|
|
|
parser = expat.ParserCreate(namespace_separator='!')
|
|
|
|
parser.returns_unicode = 1
|
|
|
|
for name in self.handler_names:
|
|
|
|
setattr(parser, name, getattr(out, name))
|
|
|
|
file = StringIO.StringIO(data)
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
parser.ParseFile(file)
|
|
|
|
|
|
|
|
op = out.out
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(op[0], 'PI: u\'xml-stylesheet\' u\'href="stylesheet.css"\'')
|
|
|
|
self.assertEqual(op[1], "Comment: u' comment data '")
|
|
|
|
self.assertEqual(op[2], "Notation declared: (u'notation', None, u'notation.jpeg', None)")
|
|
|
|
self.assertEqual(op[3], "Unparsed entity decl: (u'unparsed_entity', None, u'entity.file', None, u'notation')")
|
|
|
|
self.assertEqual(op[4], "Start element: u'root' {u'attr1': u'value1', u'attr2': u'value2\\u1f40'}")
|
|
|
|
self.assertEqual(op[5], "NS decl: u'myns' u'http://www.python.org/namespace'")
|
|
|
|
self.assertEqual(op[6], "Start element: u'http://www.python.org/namespace!subelement' {}")
|
|
|
|
self.assertEqual(op[7], "Character data: u'Contents of subelements'")
|
|
|
|
self.assertEqual(op[8], "End element: u'http://www.python.org/namespace!subelement'")
|
|
|
|
self.assertEqual(op[9], "End of NS decl: u'myns'")
|
|
|
|
self.assertEqual(op[10], "Start element: u'sub2' {}")
|
|
|
|
self.assertEqual(op[11], 'Start of CDATA section')
|
|
|
|
self.assertEqual(op[12], "Character data: u'contents of CDATA section'")
|
|
|
|
self.assertEqual(op[13], 'End of CDATA section')
|
|
|
|
self.assertEqual(op[14], "End element: u'sub2'")
|
|
|
|
self.assertEqual(op[15], "External entity ref: (None, u'entity.file', None)")
|
|
|
|
self.assertEqual(op[16], "End element: u'root'")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
2011-04-10 21:44:28 -03:00
|
|
|
# Issue 4877: expat.ParseFile causes segfault on a closed file.
|
|
|
|
fp = open(test_support.TESTFN, 'wb')
|
|
|
|
try:
|
|
|
|
fp.close()
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
with self.assertRaises(ValueError):
|
|
|
|
parser.ParseFile(fp)
|
|
|
|
finally:
|
|
|
|
test_support.unlink(test_support.TESTFN)
|
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
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=' ')
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test_illegal(self):
|
|
|
|
try:
|
|
|
|
expat.ParserCreate(namespace_separator=42)
|
|
|
|
self.fail()
|
|
|
|
except TypeError, e:
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(str(e),
|
2007-03-28 20:34:06 -03:00
|
|
|
'ParserCreate() argument 2 must be string or None, not int')
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
try:
|
|
|
|
expat.ParserCreate(namespace_separator='too long')
|
|
|
|
self.fail()
|
|
|
|
except ValueError, e:
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(str(e),
|
2007-03-28 20:34:06 -03:00
|
|
|
'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]
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(len(L), 6)
|
2007-03-28 20:34:06 -03:00
|
|
|
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):
|
2002-06-28 19:56:48 -03:00
|
|
|
self.stuff = []
|
2007-03-28 20:34:06 -03:00
|
|
|
self.parser = expat.ParserCreate()
|
|
|
|
self.parser.buffer_text = 1
|
|
|
|
self.parser.CharacterDataHandler = self.CharacterDataHandler
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2002-06-28 19:56:48 -03:00
|
|
|
def check(self, expected, label):
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff, expected,
|
2004-02-12 13:35:32 -04:00
|
|
|
"%s\nstuff = %r\nexpected = %r"
|
|
|
|
% (label, self.stuff, map(unicode, expected)))
|
2002-06-28 19:56:48 -03:00
|
|
|
|
|
|
|
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":
|
2007-03-28 20:34:06 -03:00
|
|
|
self.parser.buffer_text = 1
|
2002-06-28 19:56:48 -03:00
|
|
|
elif bt == "no":
|
2007-03-28 20:34:06 -03:00
|
|
|
self.parser.buffer_text = 0
|
2002-06-28 19:56:48 -03:00
|
|
|
|
|
|
|
def EndElementHandler(self, name):
|
|
|
|
self.stuff.append("</%s>" % name)
|
|
|
|
|
|
|
|
def CommentHandler(self, data):
|
|
|
|
self.stuff.append("<!--%s-->" % data)
|
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
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)
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
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)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff, ['123'],
|
|
|
|
"buffered text not properly collapsed")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
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)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff,
|
|
|
|
["<a>", "1", "<b>", "2", "\n", "3", "<c>", "4\n5"],
|
|
|
|
"buffering control not reacting as expected")
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test2(self):
|
|
|
|
self.parser.Parse("<a>1<b/><2><c/> \n 3</a>", 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff, ["1<2> \n 3"],
|
|
|
|
"buffered text not properly collapsed")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test3(self):
|
|
|
|
self.setHandlers(["StartElementHandler"])
|
|
|
|
self.parser.Parse("<a>1<b/>2<c/>3</a>", 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff, ["<a>", "1", "<b>", "2", "<c>", "3"],
|
2007-03-28 20:34:06 -03:00
|
|
|
"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)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff,
|
|
|
|
["<a>", "<b>", "</b>", "<c>", "</c>", "</a>"])
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test5(self):
|
|
|
|
self.setHandlers(["StartElementHandler", "EndElementHandler"])
|
|
|
|
self.parser.Parse("<a>1<b></b>2<c/>3</a>", 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff,
|
2007-03-28 20:34:06 -03:00
|
|
|
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3", "</a>"])
|
|
|
|
|
|
|
|
def test6(self):
|
2007-04-25 03:30:05 -03:00
|
|
|
self.setHandlers(["CommentHandler", "EndElementHandler",
|
2007-03-28 20:34:06 -03:00
|
|
|
"StartElementHandler"])
|
|
|
|
self.parser.Parse("<a>1<b/>2<c></c>345</a> ", 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff,
|
2007-04-25 03:30:05 -03:00
|
|
|
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "345", "</a>"],
|
2007-03-28 20:34:06 -03:00
|
|
|
"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)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.stuff,
|
|
|
|
["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3",
|
|
|
|
"<!--abc-->", "4", "<!--def-->", "5", "</a>"],
|
|
|
|
"buffered text not properly split")
|
2007-03-28 20:34:06 -03:00
|
|
|
|
2004-08-13 00:09:07 -03:00
|
|
|
|
|
|
|
# Test handling of exception from callback:
|
2007-03-28 20:34:06 -03:00
|
|
|
class HandlerExceptionTest(unittest.TestCase):
|
|
|
|
def StartElementHandler(self, name, attrs):
|
|
|
|
raise RuntimeError(name)
|
2004-08-13 00:09:07 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def test(self):
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.StartElementHandler = self.StartElementHandler
|
|
|
|
try:
|
|
|
|
parser.Parse("<a><b><c/></b></a>", 1)
|
|
|
|
self.fail()
|
|
|
|
except RuntimeError, e:
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(e.args[0], 'a',
|
|
|
|
"Expected RuntimeError for element 'a', but" + \
|
|
|
|
" found %r" % e.args[0])
|
2004-08-13 00:09:07 -03:00
|
|
|
|
2004-08-25 21:37:31 -03:00
|
|
|
|
|
|
|
# Test Current* members:
|
2007-03-28 20:34:06 -03:00
|
|
|
class PositionTest(unittest.TestCase):
|
2004-08-25 21:37:31 -03:00
|
|
|
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)
|
2007-03-28 20:34:06 -03:00
|
|
|
self.assertTrue(self.upto < len(self.expected_list),
|
|
|
|
'too many parser events')
|
2004-08-25 21:37:31 -03:00
|
|
|
expected = self.expected_list[self.upto]
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(pos, expected,
|
2007-03-28 20:34:06 -03:00
|
|
|
'Expected position %s, got position %s' %(pos, expected))
|
2004-08-25 21:37:31 -03:00
|
|
|
self.upto += 1
|
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
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)
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
class SpecificException(Exception):
|
|
|
|
pass
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
def handler(text):
|
|
|
|
raise SpecificException
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = handler
|
2007-04-25 03:30:05 -03:00
|
|
|
|
2007-03-28 20:34:06 -03:00
|
|
|
self.assertRaises(Exception, parser.Parse, xml)
|
|
|
|
|
2008-01-08 10:30:55 -04:00
|
|
|
class ChardataBufferTest(unittest.TestCase):
|
|
|
|
"""
|
|
|
|
test setting of chardata buffer size
|
|
|
|
"""
|
|
|
|
|
|
|
|
def test_1025_bytes(self):
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.small_buffer_test(1025), 2)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
def test_1000_bytes(self):
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.small_buffer_test(1000), 1)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
def test_wrong_size(self):
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.buffer_text = 1
|
|
|
|
def f(size):
|
|
|
|
parser.buffer_size = size
|
|
|
|
|
|
|
|
self.assertRaises(TypeError, f, sys.maxint+1)
|
|
|
|
self.assertRaises(ValueError, f, -1)
|
|
|
|
self.assertRaises(ValueError, f, 0)
|
|
|
|
|
|
|
|
def test_unchanged_size(self):
|
|
|
|
xml1 = ("<?xml version='1.0' encoding='iso8859'?><s>%s" % ('a' * 512))
|
|
|
|
xml2 = 'a'*512 + '</s>'
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = self.counting_handler
|
|
|
|
parser.buffer_size = 512
|
|
|
|
parser.buffer_text = 1
|
|
|
|
|
|
|
|
# Feed 512 bytes of character data: the handler should be called
|
|
|
|
# once.
|
|
|
|
self.n = 0
|
|
|
|
parser.Parse(xml1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 1)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
# Reassign to buffer_size, but assign the same size.
|
|
|
|
parser.buffer_size = parser.buffer_size
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 1)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
# Try parsing rest of the document
|
|
|
|
parser.Parse(xml2)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 2)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
|
|
|
|
def test_disabling_buffer(self):
|
|
|
|
xml1 = "<?xml version='1.0' encoding='iso8859'?><a>%s" % ('a' * 512)
|
|
|
|
xml2 = ('b' * 1024)
|
|
|
|
xml3 = "%s</a>" % ('c' * 1024)
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = self.counting_handler
|
|
|
|
parser.buffer_text = 1
|
|
|
|
parser.buffer_size = 1024
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
# Parse one chunk of XML
|
|
|
|
self.n = 0
|
|
|
|
parser.Parse(xml1, 0)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
|
|
|
self.assertEqual(self.n, 1)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
# Turn off buffering and parse the next chunk.
|
|
|
|
parser.buffer_text = 0
|
|
|
|
self.assertFalse(parser.buffer_text)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
2008-01-08 10:30:55 -04:00
|
|
|
for i in range(10):
|
|
|
|
parser.Parse(xml2, 0)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 11)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
parser.buffer_text = 1
|
|
|
|
self.assertTrue(parser.buffer_text)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
2008-01-08 10:30:55 -04:00
|
|
|
parser.Parse(xml3, 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 12)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def make_document(self, bytes):
|
|
|
|
return ("<?xml version='1.0'?><tag>" + bytes * 'a' + '</tag>')
|
|
|
|
|
|
|
|
def counting_handler(self, text):
|
|
|
|
self.n += 1
|
|
|
|
|
|
|
|
def small_buffer_test(self, buffer_len):
|
|
|
|
xml = "<?xml version='1.0' encoding='iso8859'?><s>%s</s>" % ('a' * buffer_len)
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = self.counting_handler
|
|
|
|
parser.buffer_size = 1024
|
|
|
|
parser.buffer_text = 1
|
|
|
|
|
|
|
|
self.n = 0
|
|
|
|
parser.Parse(xml)
|
|
|
|
return self.n
|
|
|
|
|
|
|
|
def test_change_size_1(self):
|
|
|
|
xml1 = "<?xml version='1.0' encoding='iso8859'?><a><s>%s" % ('a' * 1024)
|
|
|
|
xml2 = "aaa</s><s>%s</s></a>" % ('a' * 1025)
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = self.counting_handler
|
|
|
|
parser.buffer_text = 1
|
|
|
|
parser.buffer_size = 1024
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
self.n = 0
|
|
|
|
parser.Parse(xml1, 0)
|
|
|
|
parser.buffer_size *= 2
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 2048)
|
2008-01-08 10:30:55 -04:00
|
|
|
parser.Parse(xml2, 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 2)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
def test_change_size_2(self):
|
|
|
|
xml1 = "<?xml version='1.0' encoding='iso8859'?><a>a<s>%s" % ('a' * 1023)
|
|
|
|
xml2 = "aaa</s><s>%s</s></a>" % ('a' * 1025)
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
parser.CharacterDataHandler = self.counting_handler
|
|
|
|
parser.buffer_text = 1
|
|
|
|
parser.buffer_size = 2048
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 2048)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
|
|
|
self.n=0
|
|
|
|
parser.Parse(xml1, 0)
|
2010-02-03 01:37:26 -04:00
|
|
|
parser.buffer_size //= 2
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(parser.buffer_size, 1024)
|
2008-01-08 10:30:55 -04:00
|
|
|
parser.Parse(xml2, 1)
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(self.n, 4)
|
2008-01-08 10:30:55 -04:00
|
|
|
|
2009-08-13 16:27:12 -03:00
|
|
|
class MalformedInputText(unittest.TestCase):
|
|
|
|
def test1(self):
|
|
|
|
xml = "\0\r\n"
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
try:
|
|
|
|
parser.Parse(xml, True)
|
|
|
|
self.fail()
|
|
|
|
except expat.ExpatError as e:
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(str(e), 'unclosed token: line 2, column 0')
|
2009-08-13 16:27:12 -03:00
|
|
|
|
|
|
|
def test2(self):
|
|
|
|
xml = "<?xml version\xc2\x85='1.0'?>\r\n"
|
|
|
|
parser = expat.ParserCreate()
|
|
|
|
try:
|
|
|
|
parser.Parse(xml, True)
|
|
|
|
self.fail()
|
|
|
|
except expat.ExpatError as e:
|
2010-11-21 09:34:58 -04:00
|
|
|
self.assertEqual(str(e), 'XML declaration not well-formed: line 1, column 14')
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
def test_main():
|
|
|
|
run_unittest(SetAttributeTest,
|
|
|
|
ParseTest,
|
|
|
|
NamespaceSeparatorTest,
|
|
|
|
InterningTest,
|
|
|
|
BufferTextTest,
|
|
|
|
HandlerExceptionTest,
|
|
|
|
PositionTest,
|
2008-01-08 10:30:55 -04:00
|
|
|
sf1296433Test,
|
2009-08-13 16:27:12 -03:00
|
|
|
ChardataBufferTest,
|
|
|
|
MalformedInputText)
|
2007-03-28 20:34:06 -03:00
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
test_main()
|