Hi All,
While parsing the XSD, I am using the XML_String::transcode function .
But this function is not working properly for some UTf-8 chars.
I have a node like
<xsd:attribute name="str00Aٰ" type="xsd:string"/>
This is equivalent to <xsd:attribute name="str00A\xd9\xb0"
type="xsd:string"/> when we look in some hex editor.
While transcoding the value of attribute name, I am always getting empty
string instead of getting "str00Aٰ" (actual sequence is like
"str00A\xd9\xb0")
This is for linux and in case of freebsd my application hangs.
I have attached the sample code , XSD under parsing and the sample
output of my program.
Can anyone let me know what's the exact problem in my code or schema or
this is a bug in Xerces.
I am using xerces-2.7.0
Thanks in advance.
Thanks.
Regards,
Umesh
#include <xercesc/util/PlatformUtils.hpp>
#include <xercesc/dom/DOM.hpp>
#include <xercesc/dom/DOMImplementation.hpp>
#include <xercesc/dom/DOMImplementationLS.hpp>
#include <xercesc/dom/DOMWriter.hpp>
#include <xercesc/framework/StdOutFormatTarget.hpp>
#include <xercesc/framework/LocalFileFormatTarget.hpp>
#include <xercesc/parsers/XercesDOMParser.hpp>
#include <xercesc/util/XMLUni.hpp>
#include "DOMTreeErrorReporter.hpp"
#include "DOMPrintFilter.hpp"
#include "DOMPrintErrorHandler.hpp"
#include <xercesc/util/OutOfMemoryException.hpp>
#include <string.h>
#include <stdlib.h>
// ---------------------------------------------------------------------------
// Local data
//
// gXmlFile
// The path to the file to parser. Set via command line.
//
// gDoNamespaces
// Indicates whether namespace processing should be done.
//
// gDoSchema
// Indicates whether schema processing should be done.
//
// gSchemaFullChecking
// Indicates whether full schema constraint checking should be done.
//
// gDoCreate
// Indicates whether entity reference nodes needs to be created or not
// Defaults to false
//
// gOutputEncoding
// The encoding we are to output in. If not set on the command line,
// then it is defaults to the encoding of the input XML file.
//
// gSplitCdataSections
// Indicates whether split-cdata-sections is to be enabled or not.
//
// gDiscardDefaultContent
// Indicates whether default content is discarded or not.
//
// gUseFilter
// Indicates if user wants to plug in the DOMPrintFilter.
//
// gValScheme
// Indicates what validation scheme to use. It defaults to 'auto', but
// can be set via the -v= command.
//
// ---------------------------------------------------------------------------
static char* gXmlFile = 0;
static bool gDoNamespaces = false;
static bool gDoSchema = false;
static bool gSchemaFullChecking = false;
static bool gDoCreate = false;
static char* goutputfile = 0;
// options for DOMWriter's features
static XMLCh* gOutputEncoding = 0;
static bool gSplitCdataSections = true;
static bool gDiscardDefaultContent = true;
static bool gUseFilter = false;
static bool gFormatPrettyPrint = true;
static bool gWriteBOM = false;
static XercesDOMParser::ValSchemes gValScheme = XercesDOMParser::Val_Auto;
void usage()
{
XERCES_STD_QUALIFIER cout << "\nUsage:\n"
"DOMPrint <XML file>\n\n" << XERCES_STD_QUALIFIER endl;
}
int PrintNodes_i(DOMNode * n)
{
DOMNode *child;
int rc = 0;
if (n == 0)
{
return 0;
}
if (n->getNodeType() == 1)
{
char *name = XMLString::transcode(n->getNodeName());
printf("--------------------\n");
printf("Encountered Element: %s\n", name);
XMLString::release(&name);
char *namespaceURI = XMLString::transcode(n->getNamespaceURI());
if (namespaceURI != 0)
{
printf("Namespace URI: %s\n", namespaceURI);
}
XMLString::release(&namespaceURI);
char *prefix = XMLString::transcode(n->getPrefix());
if (prefix != 0)
{
printf("Prefix: %s\n", prefix);
}
XMLString::release(&prefix);
char *localName = XMLString::transcode(n->getLocalName());
if (localName != 0)
{
printf("Local name: %s\n", localName);
}
XMLString::release(&localName);
if (n->hasAttributes())
{
DOMNamedNodeMap *pAttributes = n->getAttributes();
int nSize = pAttributes->getLength();
printf("\n");
printf("\tAttributes\n");
printf("\t----------\n");
for (int i = 0; i < nSize; i++)
{
DOMAttr *pAttributeNode = (DOMAttr *) pAttributes->item(i);
char *name = XMLString::transcode(pAttributeNode->getName());
printf("\t%s = ", name);
XMLString::release(&name);
name = XMLString::transcode(pAttributeNode->getValue());
printf("\"%s\"\n", name);
XMLString::release(&name);
}
printf("\n");
}
}
for (child = n->getFirstChild(); child != 0; child = child->getNextSibling())
{
rc = PrintNodes_i(child);
}
return rc;
}
int main(int argC, char* argV[])
{
int retval = 0;
try
{
XMLPlatformUtils::Initialize();
}
catch(const XMLException &toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during Xerces-c Initialization.\n"
<< " Exception message:"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
// Check command line and extract arguments.
if (argC < 2)
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
gXmlFile = argV[1];
//
// Create our parser, then attach an error handler to the parser.
// The parser will call back to methods of the ErrorHandler if it
// discovers errors during the course of parsing the XML document.
//
XercesDOMParser *parser = new XercesDOMParser;
parser->setValidationScheme(gValScheme);
parser->setDoNamespaces(gDoNamespaces);
parser->setDoSchema(gDoSchema);
parser->setValidationSchemaFullChecking(gSchemaFullChecking);
parser->setCreateEntityReferenceNodes(gDoCreate);
DOMTreeErrorReporter *errReporter = new DOMTreeErrorReporter();
parser->setErrorHandler(errReporter);
//
// Parse the XML file, catching any XML exceptions that might propogate
// out of it.
//
bool errorsOccured = false;
try
{
parser->parse(gXmlFile);
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorsOccured = true;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "An error occurred during parsing\n Message: "
<< StrX(e.getMessage()) << XERCES_STD_QUALIFIER endl;
errorsOccured = true;
}
catch (const DOMException& e)
{
const unsigned int maxChars = 2047;
XMLCh errText[maxChars + 1];
XERCES_STD_QUALIFIER cerr << "\nDOM Error during parsing: '" << gXmlFile << "'\n"
<< "DOMException code is: " << e.code << XERCES_STD_QUALIFIER endl;
if (DOMImplementation::loadDOMExceptionMsg(e.code, errText, maxChars))
XERCES_STD_QUALIFIER cerr << "Message is: " << StrX(errText) << XERCES_STD_QUALIFIER endl;
errorsOccured = true;
}
catch (...)
{
XERCES_STD_QUALIFIER cerr << "An error occurred during parsing\n " << XERCES_STD_QUALIFIER endl;
errorsOccured = true;
}
// If the parse was successful, output the document data from the DOM tree
if (!errorsOccured && !errReporter->getSawErrors())
{
DOMDocument *doc = parser->getDocument();
PrintNodes_i(doc);
}
else
retval = 4;
//
// Clean up the error handler. The parser does not adopt handlers
// since they could be many objects or one object installed for multiple
// handlers.
//
delete errReporter;
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
// And call the termination method
XMLPlatformUtils::Terminate();
XMLString::release(&gOutputEncoding);
return retval;
}
<?xml version="1.0" encoding="UTF-8"?>
<!--
Ident: @(#)AD_name00110m2.xsd
generated from: @(#)AD_name00110m.jmpp 1.3 02/11/14
-->
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"; targetNamespace="AttrDecl/name">
<xsd:element name="root">
<xsd:complexType>
<xsd:attribute name="str00AÙ°" type="xsd:string"/>
<xsd:attribute name="str01AÛ" type="xsd:string"/>
<xsd:attribute name="str11-Û" type="xsd:string"/>
<xsd:attribute name="str21Û" type="xsd:string"/>
<xsd:attribute name="str02AÛ" type="xsd:string"/>
<xsd:attribute name="str12-Û" type="xsd:string"/>
<xsd:attribute name="str22Û" type="xsd:string"/>
<xsd:attribute name="str03AÛ " type="xsd:string"/>
<xsd:attribute name="str13-Û¢" type="xsd:string"/>
<xsd:attribute name="str23Û¤" type="xsd:string"/>
<xsd:attribute name="str04AÛ§" type="xsd:string"/>
<xsd:attribute name="str14-Û§" type="xsd:string"/>
<xsd:attribute name="str24Û¨" type="xsd:string"/>
<xsd:attribute name="str05AÛª" type="xsd:string"/>
<xsd:attribute name="str15-Û«" type="xsd:string"/>
<xsd:attribute name="str25Û" type="xsd:string"/>
<xsd:attribute name="str06Aà¤" type="xsd:string"/>
<xsd:attribute name="str16-à¤" type="xsd:string"/>
<xsd:attribute name="str26à¤" type="xsd:string"/>
<xsd:attribute name="str07A़" type="xsd:string"/>
<xsd:attribute name="str08Aा" type="xsd:string"/>
<xsd:attribute name="str18-à¥
" type="xsd:string"/>
<xsd:attribute name="str28à¥" type="xsd:string"/>
<xsd:attribute name="str09Aà¥" type="xsd:string"/>
</xsd:complexType>
</xsd:element>
</xsd:schema>--------------------
Encountered Element: xsd:schema
Attributes
----------
targetNamespace = "AttrDecl/name"
xmlns:xsd = "http://www.w3.org/2001/XMLSchema";
--------------------
Encountered Element: xsd:element
Attributes
----------
name = "root"
--------------------
Encountered Element: xsd:complexType
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
--------------------
Encountered Element: xsd:attribute
Attributes
----------
name = ""
type = "xsd:string"
