Python xml.sax.make_parser() Examples

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def parse_to_iterate_probabilitytable(self):
        handler = SAX_Handler("iter", self.em_io_handler)
        parser = make_parser()
        parser.setContentHandler(handler)
        
        for count in range(self.NUM_TRAINING_ITERATION):
            print "Starting iteration: "+str(count+1)+" ..."

            print "Resetting all counts to ZERO ..."
            self.em_io_handler.reset_count_table()

            print "Start parsing "+self.training_xmlfile+" ..."
            parser.parse(self.training_xmlfile)  
            print "Ending iteration: "+str(count+1)+" ..."
        
            print "Updating probability table ..."
            self.em_io_handler.update_probability_table() 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is raised because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = self.ioclass()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         start + (
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>')) 

def parse(self):
        """
        Loads the StyleSheets from the associated file, if it exists.
        """
        try:
            if os.path.isfile(self.__file):
                parser = make_parser()
                parser.setContentHandler(SheetParser(self))
                with open(self.__file) as the_file:
                    parser.parse(the_file)
        except (IOError, OSError, SAXParseException):
            pass

#------------------------------------------------------------------------
#
# StyleSheet
#
#------------------------------------------------------------------------ 

def parse(self):
        """
        Loads the BookList from the associated file, if it exists.
        """
        try:
            parser = make_parser()
            parser.setContentHandler(BookParser(self, self.dbase))
            with open(self.file) as the_file:
                parser.parse(the_file)
        except (IOError, OSError, ValueError, SAXParseException, KeyError,
                AttributeError):
            LOG.debug("Failed to parse book list", exc_info=True)


#-------------------------------------------------------------------------
#
# BookParser
#
#------------------------------------------------------------------------- 

def parse(self):
        """
        Loads the :class:`OptionList` from the associated file, if it exists.
        """
        try:
            if os.path.isfile(self.filename):
                parser = make_parser()
                parser.setContentHandler(OptionParser(self))
                with open(self.filename, encoding="utf-8") as the_file:
                    parser.parse(the_file)
        except (IOError, OSError, SAXParseException):
            pass

#-------------------------------------------------------------------------
#
# OptionParser
#
#------------------------------------------------------------------------- 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def scan(self):
		if not has_xml:
			Logs.error('no xml support was found, the rcc dependencies will be incomplete!')
			return([],[])
		parser=make_parser()
		curHandler=XMLHandler()
		parser.setContentHandler(curHandler)
		fi=open(self.inputs[0].abspath(),'r')
		try:
			parser.parse(fi)
		finally:
			fi.close()
		nodes=[]
		names=[]
		root=self.inputs[0].parent
		for x in curHandler.files:
			nd=root.find_resource(x)
			if nd:nodes.append(nd)
			else:names.append(x)
		return(nodes,names) 

def scan(self):
		if not has_xml:
			Logs.error('no xml support was found, the rcc dependencies will be incomplete!')
			return([],[])
		parser=make_parser()
		curHandler=XMLHandler()
		parser.setContentHandler(curHandler)
		fi=open(self.inputs[0].abspath(),'r')
		try:
			parser.parse(fi)
		finally:
			fi.close()
		nodes=[]
		names=[]
		root=self.inputs[0].parent
		for x in curHandler.files:
			nd=root.find_resource(x)
			if nd:nodes.append(nd)
			else:names.append(x)
		return(nodes,names) 

def scan(self):
		if not has_xml:
			Logs.error('no xml support was found, the rcc dependencies will be incomplete!')
			return([],[])
		parser=make_parser()
		curHandler=XMLHandler()
		parser.setContentHandler(curHandler)
		fi=open(self.inputs[0].abspath(),'r')
		try:
			parser.parse(fi)
		finally:
			fi.close()
		nodes=[]
		names=[]
		root=self.inputs[0].parent
		for x in curHandler.files:
			nd=root.find_resource(x)
			if nd:nodes.append(nd)
			else:names.append(x)
		return(nodes,names) 

def scan(self):
		if not has_xml:
			Logs.error('no xml support was found, the rcc dependencies will be incomplete!')
			return([],[])
		parser=make_parser()
		curHandler=XMLHandler()
		parser.setContentHandler(curHandler)
		fi=open(self.inputs[0].abspath(),'r')
		try:
			parser.parse(fi)
		finally:
			fi.close()
		nodes=[]
		names=[]
		root=self.inputs[0].parent
		for x in curHandler.files:
			nd=root.find_resource(x)
			if nd:nodes.append(nd)
			else:names.append(x)
		return(nodes,names) 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is raised because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = self.ioclass()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         self.xml(
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>')) 

def main():
    xmlString = "<note>\n<to>Tove</to>\n<from>Jani</from>\n<heading>Reminder</heading>\n<body>Don't forget me this weekend!</body>\n</note>"
    # bad
    xml.sax.parseString(xmlString, ExampleContentHandler())
    xml.sax.parse('notaxmlfilethatexists.xml', ExampleContentHandler())
    sax.parseString(xmlString, ExampleContentHandler())
    sax.parse('notaxmlfilethatexists.xml', ExampleContentHandler)

    # good
    defusedxml.sax.parseString(xmlString, ExampleContentHandler())

    # bad
    xml.sax.make_parser()
    sax.make_parser()
    print('nothing')
    # good
    defusedxml.sax.make_parser() 

def _flatsaxParse(fl):
    """
    Perform a SAX parse of an XML document with the _ToStan class.

    @param fl: The XML document to be parsed.
    @type fl: A file object or filename.

    @return: a C{list} of Stan objects.
    """
    parser = make_parser()
    parser.setFeature(handler.feature_validation, 0)
    parser.setFeature(handler.feature_namespaces, 1)
    parser.setFeature(handler.feature_external_ges, 0)
    parser.setFeature(handler.feature_external_pes, 0)

    s = _ToStan(getattr(fl, "name", None))
    parser.setContentHandler(s)
    parser.setEntityResolver(s)
    parser.setProperty(handler.property_lexical_handler, s)

    parser.parse(fl)

    return s.document 

def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is raised because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = self.ioclass()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         self.xml(
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>')) 

def load_data_and_labels_xml_string(stringXml):
    """
    Load data and label from a string 
    the format is as follow:
    <p> 
        bla bla you are a <rs type="insult">CENSURED</rs>, 
        and I will <rs type="threat">find and kill</rs> you bla bla
    </p>
    only the insulting expression is labelled, and similarly only the threat 
    "action" is tagged

    Returns:
        tuple(numpy array, numpy array): data and labels

    """
    # as we have XML mixed content, we need a real XML parser...
    parser = make_parser()
    handler = TEIContentHandler()
    parser.setContentHandler(handler)
    parser.parseString(stringXml)
    tokens = handler.getSents()
    labels = handler.getAllLabels()
    return tokens, labels 

def load_data_and_labels_xml_file(filepathXml):
    """
    Load data and label from an XML file
    the format is as follow:
    <p> 
        bla bla you are a <rs type="insult">CENSURED</rs>, 
        and I will <rs type="threat">find and kill</rs> you bla bla
    </p>
    only the insulting expression is labelled, and similarly only the threat 
    "action" is tagged

    Returns:
        tuple(numpy array, numpy array): data and labels

    """
    # as we have XML mixed content, we need a real XML parser...
    parser = make_parser()
    handler = TEIContentHandler()
    parser.setContentHandler(handler)
    parser.parse(filepathXml)
    tokens = handler.getSents()
    labels = handler.getAllLabels()
    return tokens, labels 

def load_data_and_labels_lemonde(filepathXml):
    """
    Load data and label from Le Monde XML corpus file
    the format is ENAMEX-style, as follow:
    <sentence id="E14">Les ventes de micro-ordinateurs en <ENAMEX type="Location" sub_type="Country" 
        eid="2000000003017382" name="Republic of France">France</ENAMEX> se sont ralenties en 1991. </sentence>

    Returns:
        tuple(numpy array, numpy array): data and labels

    """
    # as we have XML mixed content, we need a real XML parser...
    parser = make_parser()
    handler = ENAMEXContentHandler()
    parser.setContentHandler(handler)
    parser.parse(filepathXml)
    tokens = handler.getSents()
    labels = handler.getAllLabels()

    return tokens, labels 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is raised because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = self.ioclass()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         start + (
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>')) 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# =========================================================================== 

def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is raised because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = self.ioclass()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         self.xml(
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>')) 

def test_expat_dtdhandler():
    parser = make_parser()
    handler = TestDTDHandler()
    parser.setDTDHandler(handler)

    parser.parse(StringIO('''<!DOCTYPE doc [
  <!ENTITY img SYSTEM "expat.gif" NDATA GIF>
  <!NOTATION GIF PUBLIC "-//CompuServe//NOTATION Graphics Interchange Format 89a//EN">
]>
<doc></doc>'''))
    if len(handler._entities) != 1 or len(handler._entities[0]) != 4:
        return 0
    name, pubId, sysId, ndata = handler._entities[0]
    if name != 'img' or not pubId is None or not sysId.endswith('expat.gif') or ndata != 'GIF':
        return 0
    return handler._notations == [("GIF", "-//CompuServe//NOTATION Graphics Interchange Format 89a//EN", None)]

# ===== EntityResolver support 

def test_expat_nsattrs_wattr():
    parser = make_parser()
    parser.setFeature(handler.feature_namespaces, 1)
    gather = AttrGatherer()
    parser.setContentHandler(gather)

    a_name = "id" ; a_val = "val"
    parser.parse(StringIO("<doc xmlns:ns='%s' ns:%s='%s'/>" % (ns_uri, a_name, a_val) ))

    attrs = gather._attrs

    return attrs.getLength() == 1 and \
           attrs.getNames() == [(ns_uri, a_name)] and \
           attrs.getQNames() == ["ns:%s" % a_name] and \
           len(attrs) == 1 and \
           attrs.has_key((ns_uri, a_name)) and \
           attrs.keys() == [(ns_uri, a_name)] and \
           attrs.get((ns_uri, a_name)) == a_val and \
           attrs.get((ns_uri, a_name), 25) == a_val and \
           attrs.items() == [((ns_uri, a_name), a_val)] and \
           attrs.values() == [a_val] and \
           attrs.getValue((ns_uri, a_name)) == a_val and \
           attrs[(ns_uri, a_name)] == a_val 

def test_expat_nsattrs_no_namespace():
    parser = make_parser()
    parser.setFeature(handler.feature_namespaces, 1)
    gather = AttrGatherer()
    parser.setContentHandler(gather)

    a_name = "id" ; a_val = "val"
    parser.parse(StringIO("<doc %s='%s'/>" % (a_name, a_val) ))

    attrs = gather._attrs

    return attrs.getLength() == 1 and \
           attrs.getNames() == [(None, a_name)] and \
           attrs.getQNames() == [a_name] and \
           len(attrs) == 1 and \
           attrs.has_key((None, a_name)) and \
           attrs.keys() == [(None, a_name)] and \
           attrs.get((None, a_name)) == a_val and \
           attrs.get((None, a_name), 25) == a_val and \
           attrs.items() == [((None, a_name), a_val)] and \
           attrs.values() == [a_val] and \
           attrs.getValue((None, a_name)) == a_val and \
           attrs[(None, a_name)] == a_val

# ===== InputSource support 

def test_expat_locator_withinfo():
    result = StringIO()
    xmlgen = LocatorTest(result)
    parser = make_parser()
    parser.setContentHandler(xmlgen)
    testfile = findfile("test.xml")
    parser.parse(testfile)
    if is_jython:
        # In Jython, the system id is a URL with forward slashes, and
        # under Windows findfile returns a path with backslashes, so
        # replace the backslashes with forward
        testfile = testfile.replace('\\', '/')

    # urllib.quote isn't the exact encoder (e.g. ':' isn't escaped)
    expected = urllib.quote(testfile).replace('%3A', ':')
    return xmlgen.location.getSystemId().endswith(expected) and \
           xmlgen.location.getPublicId() is None


# ===========================================================================
#
#   error reporting
#
# =========================================================================== 

def run_parse(settings: Settings, print_fun=None):
    """
    Start the parsing of an Evernote enex file.

    :param settings: Settings is a custom class to pass application wide settings.
    :param print_fun: func Pass in a callback function that will be passed a string for printing
                            and disable printing to console.
    """

    # Setup xml parser
    parser = make_parser()
    parser.setFeature(handler.feature_namespaces, 0)

    for file in settings.files:
        base = os.path.basename(file)
        current_file = base.replace(".enex", "")
        note_handler = NoteParser(current_file, settings, print_fun)
        parser.setContentHandler(note_handler)
        parser.parse(file) 

def test_make_parser2(self):
        # Creating parsers several times in a row should succeed.
        # Testing this because there have been failures of this kind
        # before.
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()
        from xml.sax import make_parser
        p = make_parser()


# ===========================================================================
#
#   saxutils tests
#
# ===========================================================================