PyXR

c:\python24\lib \ test \ test_pyexpat.py



0001 # Very simple test - Parse a file and print what happens
0002 
0003 # XXX TypeErrors on calling handlers, or on bad return values from a
0004 # handler, are obscure and unhelpful.
0005 
0006 import pyexpat
0007 from xml.parsers import expat
0008 
0009 from test.test_support import sortdict, TestFailed
0010 
0011 class Outputter:
0012     def StartElementHandler(self, name, attrs):
0013         print 'Start element:\n\t', repr(name), sortdict(attrs)
0014 
0015     def EndElementHandler(self, name):
0016         print 'End element:\n\t', repr(name)
0017 
0018     def CharacterDataHandler(self, data):
0019         data = data.strip()
0020         if data:
0021             print 'Character data:'
0022             print '\t', repr(data)
0023 
0024     def ProcessingInstructionHandler(self, target, data):
0025         print 'PI:\n\t', repr(target), repr(data)
0026 
0027     def StartNamespaceDeclHandler(self, prefix, uri):
0028         print 'NS decl:\n\t', repr(prefix), repr(uri)
0029 
0030     def EndNamespaceDeclHandler(self, prefix):
0031         print 'End of NS decl:\n\t', repr(prefix)
0032 
0033     def StartCdataSectionHandler(self):
0034         print 'Start of CDATA section'
0035 
0036     def EndCdataSectionHandler(self):
0037         print 'End of CDATA section'
0038 
0039     def CommentHandler(self, text):
0040         print 'Comment:\n\t', repr(text)
0041 
0042     def NotationDeclHandler(self, *args):
0043         name, base, sysid, pubid = args
0044         print 'Notation declared:', args
0045 
0046     def UnparsedEntityDeclHandler(self, *args):
0047         entityName, base, systemId, publicId, notationName = args
0048         print 'Unparsed entity decl:\n\t', args
0049 
0050     def NotStandaloneHandler(self, userData):
0051         print 'Not standalone'
0052         return 1
0053 
0054     def ExternalEntityRefHandler(self, *args):
0055         context, base, sysId, pubId = args
0056         print 'External entity ref:', args[1:]
0057         return 1
0058 
0059     def DefaultHandler(self, userData):
0060         pass
0061 
0062     def DefaultHandlerExpand(self, userData):
0063         pass
0064 
0065 
0066 def confirm(ok):
0067     if ok:
0068         print "OK."
0069     else:
0070         print "Not OK."
0071 
0072 out = Outputter()
0073 parser = expat.ParserCreate(namespace_separator='!')
0074 
0075 # Test getting/setting returns_unicode
0076 parser.returns_unicode = 0; confirm(parser.returns_unicode == 0)
0077 parser.returns_unicode = 1; confirm(parser.returns_unicode == 1)
0078 parser.returns_unicode = 2; confirm(parser.returns_unicode == 1)
0079 parser.returns_unicode = 0; confirm(parser.returns_unicode == 0)
0080 
0081 # Test getting/setting ordered_attributes
0082 parser.ordered_attributes = 0; confirm(parser.ordered_attributes == 0)
0083 parser.ordered_attributes = 1; confirm(parser.ordered_attributes == 1)
0084 parser.ordered_attributes = 2; confirm(parser.ordered_attributes == 1)
0085 parser.ordered_attributes = 0; confirm(parser.ordered_attributes == 0)
0086 
0087 # Test getting/setting specified_attributes
0088 parser.specified_attributes = 0; confirm(parser.specified_attributes == 0)
0089 parser.specified_attributes = 1; confirm(parser.specified_attributes == 1)
0090 parser.specified_attributes = 2; confirm(parser.specified_attributes == 1)
0091 parser.specified_attributes = 0; confirm(parser.specified_attributes == 0)
0092 
0093 HANDLER_NAMES = [
0094     'StartElementHandler', 'EndElementHandler',
0095     'CharacterDataHandler', 'ProcessingInstructionHandler',
0096     'UnparsedEntityDeclHandler', 'NotationDeclHandler',
0097     'StartNamespaceDeclHandler', 'EndNamespaceDeclHandler',
0098     'CommentHandler', 'StartCdataSectionHandler',
0099     'EndCdataSectionHandler',
0100     'DefaultHandler', 'DefaultHandlerExpand',
0101     #'NotStandaloneHandler',
0102     'ExternalEntityRefHandler'
0103     ]
0104 for name in HANDLER_NAMES:
0105     setattr(parser, name, getattr(out, name))
0106 
0107 data = '''\
0108 <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
0109 <?xml-stylesheet href="stylesheet.css"?>
0110 <!-- comment data -->
0111 <!DOCTYPE quotations SYSTEM "quotations.dtd" [
0112 <!ELEMENT root ANY>
0113 <!NOTATION notation SYSTEM "notation.jpeg">
0114 <!ENTITY acirc "&#226;">
0115 <!ENTITY external_entity SYSTEM "entity.file">
0116 <!ENTITY unparsed_entity SYSTEM "entity.file" NDATA notation>
0117 %unparsed_entity;
0118 ]>
0119 
0120 <root attr1="value1" attr2="value2&#8000;">
0121 <myns:subelement xmlns:myns="http://www.python.org/namespace">
0122      Contents of subelements
0123 </myns:subelement>
0124 <sub2><![CDATA[contents of CDATA section]]></sub2>
0125 &external_entity;
0126 </root>
0127 '''
0128 
0129 # Produce UTF-8 output
0130 parser.returns_unicode = 0
0131 try:
0132     parser.Parse(data, 1)
0133 except expat.error:
0134     print '** Error', parser.ErrorCode, expat.ErrorString(parser.ErrorCode)
0135     print '** Line', parser.ErrorLineNumber
0136     print '** Column', parser.ErrorColumnNumber
0137     print '** Byte', parser.ErrorByteIndex
0138 
0139 # Try the parse again, this time producing Unicode output
0140 parser = expat.ParserCreate(namespace_separator='!')
0141 parser.returns_unicode = 1
0142 
0143 for name in HANDLER_NAMES:
0144     setattr(parser, name, getattr(out, name))
0145 try:
0146     parser.Parse(data, 1)
0147 except expat.error:
0148     print '** Error', parser.ErrorCode, expat.ErrorString(parser.ErrorCode)
0149     print '** Line', parser.ErrorLineNumber
0150     print '** Column', parser.ErrorColumnNumber
0151     print '** Byte', parser.ErrorByteIndex
0152 
0153 # Try parsing a file
0154 parser = expat.ParserCreate(namespace_separator='!')
0155 parser.returns_unicode = 1
0156 
0157 for name in HANDLER_NAMES:
0158     setattr(parser, name, getattr(out, name))
0159 import StringIO
0160 file = StringIO.StringIO(data)
0161 try:
0162     parser.ParseFile(file)
0163 except expat.error:
0164     print '** Error', parser.ErrorCode, expat.ErrorString(parser.ErrorCode)
0165     print '** Line', parser.ErrorLineNumber
0166     print '** Column', parser.ErrorColumnNumber
0167     print '** Byte', parser.ErrorByteIndex
0168 
0169 
0170 # Tests that make sure we get errors when the namespace_separator value
0171 # is illegal, and that we don't for good values:
0172 print
0173 print "Testing constructor for proper handling of namespace_separator values:"
0174 expat.ParserCreate()
0175 expat.ParserCreate(namespace_separator=None)
0176 expat.ParserCreate(namespace_separator=' ')
0177 print "Legal values tested o.k."
0178 try:
0179     expat.ParserCreate(namespace_separator=42)
0180 except TypeError, e:
0181     print "Caught expected TypeError:"
0182     print e
0183 else:
0184     print "Failed to catch expected TypeError."
0185 
0186 try:
0187     expat.ParserCreate(namespace_separator='too long')
0188 except ValueError, e:
0189     print "Caught expected ValueError:"
0190     print e
0191 else:
0192     print "Failed to catch expected ValueError."
0193 
0194 # ParserCreate() needs to accept a namespace_separator of zero length
0195 # to satisfy the requirements of RDF applications that are required
0196 # to simply glue together the namespace URI and the localname.  Though
0197 # considered a wart of the RDF specifications, it needs to be supported.
0198 #
0199 # See XML-SIG mailing list thread starting with
0200 # http://mail.python.org/pipermail/xml-sig/2001-April/005202.html
0201 #
0202 expat.ParserCreate(namespace_separator='') # too short
0203 
0204 # Test the interning machinery.
0205 p = expat.ParserCreate()
0206 L = []
0207 def collector(name, *args):
0208     L.append(name)
0209 p.StartElementHandler = collector
0210 p.EndElementHandler = collector
0211 p.Parse("<e> <e/> <e></e> </e>", 1)
0212 tag = L[0]
0213 if len(L) != 6:
0214     print "L should only contain 6 entries; found", len(L)
0215 for entry in L:
0216     if tag is not entry:
0217         print "expected L to contain many references to the same string",
0218         print "(it didn't)"
0219         print "L =", repr(L)
0220         break
0221 
0222 # Tests of the buffer_text attribute.
0223 import sys
0224 
0225 class TextCollector:
0226     def __init__(self, parser):
0227         self.stuff = []
0228 
0229     def check(self, expected, label):
0230         require(self.stuff == expected,
0231                 "%s\nstuff    = %r\nexpected = %r"
0232                 % (label, self.stuff, map(unicode, expected)))
0233 
0234     def CharacterDataHandler(self, text):
0235         self.stuff.append(text)
0236 
0237     def StartElementHandler(self, name, attrs):
0238         self.stuff.append("<%s>" % name)
0239         bt = attrs.get("buffer-text")
0240         if bt == "yes":
0241             parser.buffer_text = 1
0242         elif bt == "no":
0243             parser.buffer_text = 0
0244 
0245     def EndElementHandler(self, name):
0246         self.stuff.append("</%s>" % name)
0247 
0248     def CommentHandler(self, data):
0249         self.stuff.append("<!--%s-->" % data)
0250 
0251 def require(cond, label):
0252     # similar to confirm(), but no extraneous output
0253     if not cond:
0254         raise TestFailed(label)
0255 
0256 def setup(handlers=[]):
0257     parser = expat.ParserCreate()
0258     require(not parser.buffer_text,
0259             "buffer_text not disabled by default")
0260     parser.buffer_text = 1
0261     handler = TextCollector(parser)
0262     parser.CharacterDataHandler = handler.CharacterDataHandler
0263     for name in handlers:
0264         setattr(parser, name, getattr(handler, name))
0265     return parser, handler
0266 
0267 parser, handler = setup()
0268 require(parser.buffer_text,
0269         "text buffering either not acknowledged or not enabled")
0270 parser.Parse("<a>1<b/>2<c/>3</a>", 1)
0271 handler.check(["123"],
0272               "buffered text not properly collapsed")
0273 
0274 # XXX This test exposes more detail of Expat's text chunking than we
0275 # XXX like, but it tests what we need to concisely.
0276 parser, handler = setup(["StartElementHandler"])
0277 parser.Parse("<a>1<b buffer-text='no'/>2\n3<c buffer-text='yes'/>4\n5</a>", 1)
0278 handler.check(["<a>", "1", "<b>", "2", "\n", "3", "<c>", "4\n5"],
0279               "buffering control not reacting as expected")
0280 
0281 parser, handler = setup()
0282 parser.Parse("<a>1<b/>&lt;2&gt;<c/>&#32;\n&#x20;3</a>", 1)
0283 handler.check(["1<2> \n 3"],
0284               "buffered text not properly collapsed")
0285 
0286 parser, handler = setup(["StartElementHandler"])
0287 parser.Parse("<a>1<b/>2<c/>3</a>", 1)
0288 handler.check(["<a>", "1", "<b>", "2", "<c>", "3"],
0289               "buffered text not properly split")
0290 
0291 parser, handler = setup(["StartElementHandler", "EndElementHandler"])
0292 parser.CharacterDataHandler = None
0293 parser.Parse("<a>1<b/>2<c/>3</a>", 1)
0294 handler.check(["<a>", "<b>", "</b>", "<c>", "</c>", "</a>"],
0295               "huh?")
0296 
0297 parser, handler = setup(["StartElementHandler", "EndElementHandler"])
0298 parser.Parse("<a>1<b></b>2<c/>3</a>", 1)
0299 handler.check(["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3", "</a>"],
0300               "huh?")
0301 
0302 parser, handler = setup(["CommentHandler", "EndElementHandler",
0303                          "StartElementHandler"])
0304 parser.Parse("<a>1<b/>2<c></c>345</a> ", 1)
0305 handler.check(["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "345", "</a>"],
0306               "buffered text not properly split")
0307 
0308 parser, handler = setup(["CommentHandler", "EndElementHandler",
0309                          "StartElementHandler"])
0310 parser.Parse("<a>1<b/>2<c></c>3<!--abc-->4<!--def-->5</a> ", 1)
0311 handler.check(["<a>", "1", "<b>", "</b>", "2", "<c>", "</c>", "3",
0312                "<!--abc-->", "4", "<!--def-->", "5", "</a>"],
0313               "buffered text not properly split")
0314 
0315 # Test handling of exception from callback:
0316 def StartElementHandler(name, attrs):
0317     raise RuntimeError(name)
0318 
0319 parser = expat.ParserCreate()
0320 parser.StartElementHandler = StartElementHandler
0321 
0322 try:
0323     parser.Parse("<a><b><c/></b></a>", 1)
0324 except RuntimeError, e:
0325     if e.args[0] != "a":
0326         print "Expected RuntimeError for element 'a'; found %r" % e.args[0]
0327 else:
0328     print "Expected RuntimeError for 'a'"
0329 
0330 # Test Current* members:
0331 class PositionTest:
0332 
0333     def __init__(self, expected_list, parser):
0334         self.parser = parser
0335         self.parser.StartElementHandler = self.StartElementHandler
0336         self.parser.EndElementHandler = self.EndElementHandler
0337         self.expected_list = expected_list
0338         self.upto = 0
0339 
0340     def StartElementHandler(self, name, attrs):
0341         self.check_pos('s')
0342 
0343     def EndElementHandler(self, name):
0344         self.check_pos('e')
0345 
0346     def check_pos(self, event):
0347         pos = (event,
0348                self.parser.CurrentByteIndex,
0349                self.parser.CurrentLineNumber,
0350                self.parser.CurrentColumnNumber)
0351         require(self.upto < len(self.expected_list),
0352                 'too many parser events')
0353         expected = self.expected_list[self.upto]
0354         require(pos == expected,
0355                 'expected position %s, got %s' % (expected, pos))
0356         self.upto += 1
0357 
0358 
0359 parser = expat.ParserCreate()
0360 handler = PositionTest([('s', 0, 1, 0), ('s', 5, 2, 1), ('s', 11, 3, 2),
0361                         ('e', 15, 3, 6), ('e', 17, 4, 1), ('e', 22, 5, 0)],
0362                        parser)
0363 parser.Parse('''<a>
0364  <b>
0365   <c/>
0366  </b>
0367 </a>''', 1)
0368 

Generated by PyXR 0.9.4
SourceForge.net Logo