ValueMap dictionaryWithContentsOfFile(const std::string& fileName)
{
_resultType = SAX_RESULT_DICT;
SAXParser parser;
CCASSERT(parser.init("UTF-8"), "The file format isn't UTF-8");
parser.setDelegator(this);
parser.parse(fileName);
return _rootDict;
}
ValueVector arrayWithContentsOfFile(const std::string& fileName)
{
_resultType = SAX_RESULT_ARRAY;
SAXParser parser;
CCASSERT(parser.init("UTF-8"), "The file format isn't UTF-8");
parser.setDelegator(this);
parser.parse(fileName);
return _rootArray;
}
ValueMap dictionaryWithDataOfFile(const char* filedata, int filesize)
{
_resultType = SAX_RESULT_DICT;
SAXParser parser;
CCASSERT(parser.init("UTF-8"), "The file format isn't UTF-8");
parser.setDelegator(this);
parser.parse(filedata, filesize);
return _rootDict;
}
Vector<SpriteFrame*> getFrames(const std::string& fileName)
{
SAXParser parser;
parser.init("UTF-8");
parser.setDelegator(this);
parser.parse(fileName);
return _frames;
}
TMXFile::TMXFile(const char* pPath)
{
TMXFileParser tParser(this, pPath);
SAXParser tSAXParser;
tSAXParser.setDelegator(&tParser);
tSAXParser.parse(pPath);
if (tParser.Failed())
{
CHU_LOGERROR("failed to load tmx from '%s'.", pPath);
throw std::logic_error("LoadFailed");
}
}
bool TMXMapInfo::parseXMLFile(const std::string& xmlFilename)
{
SAXParser parser;
if (false == parser.init("UTF-8") )
{
return false;
}
parser.setDelegator(this);
return parser.parse(FileUtils::getInstance()->fullPathForFilename(xmlFilename));
}
void SAXParserTest::testUndeclaredNamespaceNoPrefixes()
{
SAXParser parser;
parser.setFeature(XMLReader::FEATURE_NAMESPACES, true);
parser.setFeature(XMLReader::FEATURE_NAMESPACE_PREFIXES, false);
try
{
std::string xml = parse(parser, XMLWriter::CANONICAL, UNDECLARED_NAMESPACE);
fail("undeclared namespace - must throw exception");
}
catch (SAXParseException&)
{
}
}
VXIlogResult
SBlogErrorMapper::ParseErrorMappingFiles(const VXIVector *errorMapFiles)
{
VXIlogResult rc = VXIlog_RESULT_SUCCESS;
if ( errorMapFiles == NULL ) return rc;
InitializeXMLParser();
char narrowFileToParse[4096];
VXIunsigned len = VXIVectorLength(errorMapFiles);
const VXIValue *xmlFilePtr = NULL;
const VXIchar *xmlFile = NULL;
for(VXIunsigned i = 0; i < len; ++i)
{
xmlFilePtr = VXIVectorGetElement(errorMapFiles, i);
if( VXIValueGetType(xmlFilePtr) == VALUE_STRING )
{
xmlFile = VXIStringCStr((const VXIString *)xmlFilePtr);
SBlogWchar2Latin1(xmlFile, narrowFileToParse, 4095);
// Let the SAX parser do its job, it will call our handler callbacks
try
{
xmlHandler->resetData();
parser->parse(narrowFileToParse);
}
catch (const XMLException& exception)
{
showExceptionMsg(exception);
// skip and processing next file
continue;
}
if( xmlHandler->getErrorTable().size() > 0 )
{
ModuleMappingTable *map = new ModuleMappingTable;
if( map )
{
map->next = NULL;
map->moduleName = xmlHandler->getModuleName();
map->errFileName = xmlFile;
map->errTable = xmlHandler->getErrorTable();
if( errorLookUpTable == NULL )
{
errorLookUpTable = map;
}
else
{
map->next = errorLookUpTable;
errorLookUpTable = map;
}
}
else
{
return VXIlog_RESULT_FAILURE;
}
} // end-if getErrorTable()
}
}
return VXIlog_RESULT_SUCCESS;
}
bool TMXMapInfo::parseXMLString(const std::string& xmlString)
{
size_t len = xmlString.size();
if (len <= 0)
return false;
SAXParser parser;
if (false == parser.init("UTF-8") )
{
return false;
}
parser.setDelegator(this);
return parser.parse(xmlString.c_str(), len);
}
void
OptionsIO::loadConfiguration() {
OptionsCont& oc = OptionsCont::getOptions();
if (!oc.exists("configuration-file") || !oc.isSet("configuration-file")) {
return;
}
std::string path = oc.getString("configuration-file");
if (!FileHelpers::exists(path)) {
throw ProcessError("Could not find configuration '" + oc.getString("configuration-file") + "'.");
}
PROGRESS_BEGIN_MESSAGE("Loading configuration");
// build parser
SAXParser parser;
parser.setValidationScheme(SAXParser::Val_Auto);
parser.setDoNamespaces(false);
parser.setDoSchema(false);
// start the parsing
OptionsLoader handler;
try {
parser.setDocumentHandler(&handler);
parser.setErrorHandler(&handler);
parser.parse(path.c_str());
if (handler.errorOccured()) {
throw ProcessError("Could not load configuration '" + path + "'.");
}
} catch (const XMLException& e) {
throw ProcessError("Could not load configuration '" + path + "':\n " + TplConvert<XMLCh>::_2str(e.getMessage()));
}
oc.relocateFiles(path);
PROGRESS_DONE_MESSAGE();
}
void SAXParserTest::testRSS()
{
SAXParser parser;
WhitespaceFilter filter(&parser);
TestEntityResolver resolver;
filter.setEntityResolver(&resolver);
parser.setFeature(XMLReader::FEATURE_EXTERNAL_GENERAL_ENTITIES, true);
parser.setFeature(XMLReader::FEATURE_EXTERNAL_PARAMETER_ENTITIES, true);
std::istringstream istr(RSS);
Poco::FileOutputStream ostr("rss.xml");
XMLWriter writer(ostr, XMLWriter::CANONICAL | XMLWriter::PRETTY_PRINT);
filter.setContentHandler(&writer);
filter.setDTDHandler(&writer);
filter.setProperty(XMLReader::PROPERTY_LEXICAL_HANDLER, static_cast<Poco::XML::LexicalHandler*>(&writer));
InputSource source(istr);
filter.parse(&source);
}
void AreFriends::handleResponse(istream & inputstream) const
{
SAXParser parser;
parser.setFeature(XMLReader::FEATURE_NAMESPACES, true);
parser.setFeature(XMLReader::FEATURE_NAMESPACE_PREFIXES, true);
parser.setContentHandler(const_cast<AreFriends*>(this));
try
{
SharedPtr<InputSource> inputSource(new InputSource(inputstream));
parser.parse(inputSource);
mSuccessCallback.call(mFriendInfoList);
}
catch (Exception& e)
{
cerr << e.displayText() << endl;
mErrorCallback.call(ErrorResponse(0,e.message(), KeyValue()));
}
}
/* Read the file. */
bool GQCFileData::Read(const std::string &fileName)
{
Clear();
// Initialize the XML4C2 system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException&)
{
return false;
}
bool status = false;
SAXParser* parser = new SAXParser;
parser->setValidationScheme(SAXParser::Val_Never);
parser->setLoadExternalDTD(false);
parser->setDoNamespaces(false);
parser->setDoSchema(false);
parser->setValidationSchemaFullChecking(false);
SAXGenericReportHandlers handler(this);
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
try
{
parser->parse(fileName.c_str());
int errorCount = parser->getErrorCount();
if (errorCount == 0)
{
status = true;
}
}
catch (...)
{
status = false;
}
delete parser;
XMLPlatformUtils::Terminate();
return status;
}
int main(int argc, char** argv)
{
// parse an XML document and print the generated SAX events
if (argc < 2)
{
std::cout << "usage: " << argv[0] << ": <xmlfile>" << std::endl;
return 1;
}
MyHandler handler;
SAXParser parser;
parser.setFeature(XMLReader::FEATURE_NAMESPACES, true);
parser.setFeature(XMLReader::FEATURE_NAMESPACE_PREFIXES, true);
parser.setContentHandler(&handler);
parser.setProperty(XMLReader::PROPERTY_LEXICAL_HANDLER, static_cast<LexicalHandler*>(&handler));
try
{
parser.parse(argv[1]);
}
catch (Poco::Exception& e)
{
std::cerr << e.displayText() << std::endl;
return 2;
}
return 0;
}
int InstallationParser::parse() {
if (initialization() == 1) // Problem during the initialisation.
return(1);
SAXParser* parser = new SAXParser();
parser->setDoValidation(true);
parser->setDoNamespaces(true);
InstallationSAXHandler* handler = new InstallationSAXHandler();
parser->setDocumentHandler(handler);
parser->setErrorHandler(handler);
try {
const char* file = xmlFile.c_str(); // Name of the descriptor file in the current directory.
parser->parse(file); // Parsing procedure.
handler->get_pkgname(pkgname); // Result of the parsing.
handler->get_pkgUUID(pkgUUID);
handler->get_implementations(codefiles); // Result of the parsing.
}
catch (const XMLException& toCatch) { // File not found for the parsing.
std::cerr << "\nFile not found : '" << xmlFile << "'\n";
std::cerr << "Exception message is : \n" << toCatch.getMessage() << "\n";
return(4);
}
int err = handler->get_error(); // The error codes are got from the handler object.
delete(handler); // Object deleted.
delete(parser); // Object deleted.
return(err); // 0, 2 or 3 is returned.
}
bool
Kumu::XMLElement::ParseString(const char* document, ui32_t doc_len)
{
if ( doc_len == 0 )
return false;
init_xml_dom();
int errorCount = 0;
SAXParser* parser = new SAXParser();
parser->setValidationScheme(SAXParser::Val_Always);
parser->setDoNamespaces(true); // optional
MyTreeHandler* docHandler = new MyTreeHandler(this);
parser->setDocumentHandler(docHandler);
parser->setErrorHandler(docHandler);
try
{
MemBufInputSource xmlSource(reinterpret_cast<const XMLByte*>(document),
static_cast<const unsigned int>(doc_len),
"pidc_rules_file");
parser->parse(xmlSource);
}
catch (const XMLException& e)
{
char* message = XMLString::transcode(e.getMessage());
DefaultLogSink().Error("Parser error: %s\n", message);
XMLString::release(&message);
errorCount++;
}
catch (const SAXParseException& e)
{
char* message = XMLString::transcode(e.getMessage());
DefaultLogSink().Error("Parser error: %s at line %d\n", message, e.getLineNumber());
XMLString::release(&message);
errorCount++;
}
catch (...)
{
DefaultLogSink().Error("Unexpected XML parser error\n");
errorCount++;
}
if ( errorCount == 0 )
m_NamespaceOwner = (void*)docHandler->TakeNamespaceMap();
delete parser;
delete docHandler;
return errorCount > 0 ? false : true;
}
void PSAPAddrTest::setUp() {
#if 0
//
// Macros are defined for now by the Macro constructor
//
AEISAXHandler handler;
SAXParser parser;
parser.setFeature(XMLReader::FEATURE_NAMESPACES, true);
parser.setFeature(XMLReader::FEATURE_NAMESPACE_PREFIXES, true);
parser.setContentHandler(&handler);
parser.setProperty(XMLReader::PROPERTY_LEXICAL_HANDLER, static_cast<LexicalHandler*>(&handler));
parser.parse("../../../../../../test/iso/itu/osi/als/base/addr/Macros.xml");
#endif
}
int main (int argc, char** argv) {
if (false) {
RFC_1006 rfc1006;
NSAPAddr nsap;
const char* n = rfc1006.parse(nsap, "+03+10.0.0.6:8080");
const char*p;
Selector selector;
p = selector.parse("////NS+a433bb93c1");
p = selector.parse("#124/NS");
p = selector.parse("\"abc\"/NS");
p = selector.parse("'3a'H/NS");
string sel = "#124";
TSAPService service("echo", "#124", "pippo", "bar");
TSAPServices services;
services.add("echo", "#12", "pippo", "bar");
const OSIService* os = services.getServiceBySelector(selector);
if (os != NULL) {
os->entity();
}
}
{
AEISAXHandler handler;
SAXParser parser;
parser.setFeature(XMLReader::FEATURE_NAMESPACES, true);
parser.setFeature(XMLReader::FEATURE_NAMESPACE_PREFIXES, true);
parser.setContentHandler(&handler);
parser.setProperty(XMLReader::PROPERTY_LEXICAL_HANDLER, static_cast<LexicalHandler*>(&handler));
try {
parser.parse("AEI.xml");
ServiceFunctor functor(cout);
//TSAP_SERVICES.print(functor);
//SSAP_SERVICES.print(functor);
//PSAP_SERVICES.print(functor);
const OSIService* service = TSAP_SERVICES.getServiceByEntity("ssap");
cout << service->mangled() << endl;
} catch (Poco::Exception& e) {
std::cerr << e.displayText() << std::endl;
}
}
#if 0
<config>
void SAXParserTest::testEncoding()
{
SAXParser parser;
Poco::Latin9Encoding encoding;
parser.addEncoding("ISO-8859-15", &encoding);
std::istringstream istr(ENCODING);
std::ostringstream ostr;
XMLWriter writer(ostr, XMLWriter::WRITE_XML_DECLARATION, "ISO-8859-15", encoding);
parser.setContentHandler(&writer);
parser.setDTDHandler(&writer);
parser.setProperty(XMLReader::PROPERTY_LEXICAL_HANDLER, static_cast<Poco::XML::LexicalHandler*>(&writer));
InputSource source(istr);
parser.parse(&source);
std::string xml = ostr.str();
assert (xml == ENCODING);
}
bool streamXML(const string& filename, XMLStream& stream)
{
try {
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cerr << "XML initialization failed: " << message << endl;
return false;
}
SAXParser parser;
parser.setDoValidation(true); // optional.
parser.setDoNamespaces(true); // optional
StreamHandler docHandler(stream);
parser.setDocumentHandler(&docHandler);
parser.setErrorHandler((ErrorHandler*)&docHandler);
try {
parser.parse(filename.c_str());
}
catch (const XMLException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cerr << "XML Exception: " << message << endl;
return false;
}
catch (const SAXParseException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cerr << "XML Parsing exception: " << message << endl;
return false;
}
catch (const SAXException& e) {
char* message = XMLString::transcode(e.getMessage());
cerr << "Bad file format exception: " << message << endl;
return false;
}
catch (...) {
cerr << "Unexpected Exception \n" ;
return false;
}
return true;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{
// Initialize the XML4C system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! Message:\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
// Check command line and extract arguments.
if (argC < 2)
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
// We only have one required parameter, which is the file to process
if ((argC != 2) || (*(argV[1]) == '-'))
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
const char* xmlFile = argV[1];
SAXParser::ValSchemes valScheme = SAXParser::Val_Auto;
//
// Create a DTD validator to be used for our validation work. Then create
// a SAX parser object and pass it our validator. Then, according to what
// we were told on the command line, set it to validate or not. He owns
// the validator, so we have to allocate it.
//
int errorCount = 0;
DTDValidator* valToUse = new DTDValidator;
SAXParser* parser = new SAXParser(valToUse);
parser->setValidationScheme(valScheme);
//
// Get the starting time and kick off the parse of the indicated
// file. Catch any exceptions that might propogate out of it.
//
int errorCode = 0;
try
{
parser->parse(xmlFile);
errorCount = parser->getErrorCount();
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorCode = 5;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "\nError during parsing: '" << xmlFile << "'\n"
<< "Exception message is: \n"
<< StrX(e.getMessage()) << "\n" << XERCES_STD_QUALIFIER endl;
errorCode = 4;
}
if(errorCode) {
XMLPlatformUtils::Terminate();
return errorCode;
}
if (!errorCount) {
//
// Now we will get an enumerator for the element pool from the validator
// and enumerate the elements, printing them as we go. For each element
// we get an enumerator for its attributes and print them also.
//
DTDGrammar* grammar = (DTDGrammar*) valToUse->getGrammar();
NameIdPoolEnumerator<DTDElementDecl> elemEnum = grammar->getElemEnumerator();
if (elemEnum.hasMoreElements())
{
XERCES_STD_QUALIFIER cout << "\nELEMENTS:\n----------------------------\n";
while(elemEnum.hasMoreElements())
{
const DTDElementDecl& curElem = elemEnum.nextElement();
XERCES_STD_QUALIFIER cout << " Name: " << StrX(curElem.getFullName()) << "\n";
XERCES_STD_QUALIFIER cout << " Content Model: "
<< StrX(curElem.getFormattedContentModel())
<< "\n";
// Get an enumerator for this guy's attributes if any
if (curElem.hasAttDefs())
{
XERCES_STD_QUALIFIER cout << " Attributes:\n";
XMLAttDefList& attList = curElem.getAttDefList();
for (unsigned int i=0; i<attList.getAttDefCount(); i++)
{
const XMLAttDef& curAttDef = attList.getAttDef(i);
XERCES_STD_QUALIFIER cout << " Name:" << StrX(curAttDef.getFullName())
<< ", Type: ";
// Get the type and display it
const XMLAttDef::AttTypes type = curAttDef.getType();
switch(type)
{
case XMLAttDef::CData :
XERCES_STD_QUALIFIER cout << "CDATA";
break;
case XMLAttDef::ID :
XERCES_STD_QUALIFIER cout << "ID";
break;
case XMLAttDef::IDRef :
case XMLAttDef::IDRefs :
XERCES_STD_QUALIFIER cout << "IDREF(S)";
break;
case XMLAttDef::Entity :
case XMLAttDef::Entities :
XERCES_STD_QUALIFIER cout << "ENTITY(IES)";
break;
case XMLAttDef::NmToken :
case XMLAttDef::NmTokens :
XERCES_STD_QUALIFIER cout << "NMTOKEN(S)";
break;
case XMLAttDef::Notation :
XERCES_STD_QUALIFIER cout << "NOTATION";
break;
case XMLAttDef::Enumeration :
XERCES_STD_QUALIFIER cout << "ENUMERATION";
break;
default:
break;
}
XERCES_STD_QUALIFIER cout << "\n";
}
}
XERCES_STD_QUALIFIER cout << XERCES_STD_QUALIFIER endl;
}
}
else
{
XERCES_STD_QUALIFIER cout << "The validator has no elements to display\n" << XERCES_STD_QUALIFIER endl;
}
}
else
XERCES_STD_QUALIFIER cout << "\nErrors occurred, no output available\n" << XERCES_STD_QUALIFIER endl;
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
// And call the termination method
XMLPlatformUtils::Terminate();
if (errorCount > 0)
return 4;
else
return 0;
}
int main (int argC, char *argV[])
{
MemoryMonitor *staticMemMonitor = new MemoryMonitor();
// Initialize the XML4C system
try
{
XMLPlatformUtils::Initialize(XMLUni::fgXercescDefaultLocale, 0, 0, staticMemMonitor);
}
catch (const XMLException& toCatch)
{
char *msg = XMLString::transcode(toCatch.getMessage());
XERCES_STD_QUALIFIER cerr << "Error during initialization! :\n"
<< msg << XERCES_STD_QUALIFIER endl;
XMLString::release(&msg);
return 1;
}
// Check command line and extract arguments.
if (argC < 2)
{
usage();
return 1;
}
const char* xmlFile = 0;
AbstractDOMParser::ValSchemes domBuilderValScheme = AbstractDOMParser::Val_Auto;
bool doNamespaces = false;
bool doSchema = false;
bool schemaFullChecking = false;
bool doList = false;
int numReps =1;
int argInd;
for (argInd = 1; argInd < argC; argInd++)
{
// Break out on first parm not starting with a dash
if (argV[argInd][0] != '-')
break;
// Watch for special case help request
if (!strcmp(argV[argInd], "-?"))
{
usage();
return 2;
}
else if (!strncmp(argV[argInd], "-v=", 3)
|| !strncmp(argV[argInd], "-V=", 3))
{
const char* const parm = &argV[argInd][3];
if (!strcmp(parm, "never"))
domBuilderValScheme = AbstractDOMParser::Val_Never;
else if (!strcmp(parm, "auto"))
domBuilderValScheme = AbstractDOMParser::Val_Auto;
else if (!strcmp(parm, "always"))
domBuilderValScheme = AbstractDOMParser::Val_Always;
else
{
XERCES_STD_QUALIFIER cerr << "Unknown -v= value: " << parm << XERCES_STD_QUALIFIER endl;
return 2;
}
}
else if (!strcmp(argV[argInd], "-n")
|| !strcmp(argV[argInd], "-N"))
{
doNamespaces = true;
}
else if (!strcmp(argV[argInd], "-s")
|| !strcmp(argV[argInd], "-S"))
{
doSchema = true;
}
else if (!strcmp(argV[argInd], "-f")
|| !strcmp(argV[argInd], "-F"))
{
schemaFullChecking = true;
}
else if (!strcmp(argV[argInd], "-l")
|| !strcmp(argV[argInd], "-L"))
{
doList = true;
}
else if (!strncmp(argV[argInd], "-r=", 3)
|| !strncmp(argV[argInd], "-R=", 3))
{
const char* const numStr = &argV[argInd][3];
XMLCh* numXStr = XMLString::transcode(numStr);
numReps = XMLString::parseInt(numXStr);
XMLString::release(&numXStr);
}
else
{
XERCES_STD_QUALIFIER cerr << "Unknown option '" << argV[argInd]
<< "', ignoring it\n" << XERCES_STD_QUALIFIER endl;
}
}
//
// There should be only one and only one parameter left, and that
// should be the file name.
//
if (argInd != argC - 1)
{
usage();
return 1;
}
// Instantiate the DOM domBuilder with its memory manager.
MemoryMonitor *domBuilderMemMonitor = new MemoryMonitor();
static const XMLCh gLS[] = { chLatin_L, chLatin_S, chNull };
DOMImplementation *impl = DOMImplementationRegistry::getDOMImplementation(gLS);
DOMLSParser *domBuilder = ((DOMImplementationLS*)impl)->createLSParser(DOMImplementationLS::MODE_SYNCHRONOUS, 0, domBuilderMemMonitor);
DOMLSParserHandler domBuilderHandler;
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMErrorHandler, &domBuilderHandler);
// Instantiate the SAX2 parser with its memory manager.
MemoryMonitor *sax2MemMonitor = new MemoryMonitor();
SAX2XMLReader *sax2parser = XMLReaderFactory::createXMLReader(sax2MemMonitor);
SAXErrorHandler saxErrorHandler;
sax2parser->setErrorHandler(&saxErrorHandler);
// Instantiate the SAX 1 parser with its memory manager.
MemoryMonitor *sax1MemMonitor = new MemoryMonitor();
SAXParser *saxParser = new (sax1MemMonitor) SAXParser(0, sax1MemMonitor);
saxParser->setErrorHandler(&saxErrorHandler);
// set features
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMNamespaces, doNamespaces);
sax2parser->setFeature(XMLUni::fgSAX2CoreNameSpaces, doNamespaces);
saxParser->setDoNamespaces(doNamespaces);
domBuilder->getDomConfig()->setParameter(XMLUni::fgXercesSchema, doSchema);
sax2parser->setFeature(XMLUni::fgXercesSchema, doSchema);
saxParser->setDoSchema(doSchema);
domBuilder->getDomConfig()->setParameter(XMLUni::fgXercesHandleMultipleImports, true);
sax2parser->setFeature(XMLUni::fgXercesHandleMultipleImports, true);
saxParser->setHandleMultipleImports (true);
domBuilder->getDomConfig()->setParameter(XMLUni::fgXercesSchemaFullChecking, schemaFullChecking);
sax2parser->setFeature(XMLUni::fgXercesSchemaFullChecking, schemaFullChecking);
saxParser->setValidationSchemaFullChecking(schemaFullChecking);
if (domBuilderValScheme == AbstractDOMParser::Val_Auto)
{
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMValidateIfSchema, true);
sax2parser->setFeature(XMLUni::fgSAX2CoreValidation, true);
sax2parser->setFeature(XMLUni::fgXercesDynamic, true);
saxParser->setValidationScheme(SAXParser::Val_Auto);
}
else if (domBuilderValScheme == AbstractDOMParser::Val_Never)
{
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMValidate, false);
sax2parser->setFeature(XMLUni::fgSAX2CoreValidation, false);
saxParser->setValidationScheme(SAXParser::Val_Never);
}
else if (domBuilderValScheme == AbstractDOMParser::Val_Always)
{
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMValidate, true);
sax2parser->setFeature(XMLUni::fgSAX2CoreValidation, true);
sax2parser->setFeature(XMLUni::fgXercesDynamic, false);
saxParser->setValidationScheme(SAXParser::Val_Always);
}
// enable datatype normalization - default is off
domBuilder->getDomConfig()->setParameter(XMLUni::fgDOMDatatypeNormalization, true);
XERCES_STD_QUALIFIER ifstream fin;
bool more = true;
// the input is a list file
if (doList)
fin.open(argV[argInd]);
if (fin.fail()) {
XERCES_STD_QUALIFIER cerr <<"Cannot open the list file: " << argV[argInd] << XERCES_STD_QUALIFIER endl;
return 2;
}
while (more)
{
char fURI[1000];
//initialize the array to zeros
memset(fURI,0,sizeof(fURI));
if (doList) {
if (! fin.eof() ) {
fin.getline (fURI, sizeof(fURI));
if (!*fURI)
continue;
else {
xmlFile = fURI;
XERCES_STD_QUALIFIER cerr << "==Parsing== " << xmlFile << XERCES_STD_QUALIFIER endl;
}
}
else
break;
}
else {
xmlFile = argV[argInd];
more = false;
}
// parse numReps times (in case we need it for some reason)
for (int i=0; i<numReps; i++)
{
XERCES_CPP_NAMESPACE_QUALIFIER DOMDocument *doc = 0;
try
{
// reset document pool
domBuilder->resetDocumentPool();
doc = domBuilder->parseURI(xmlFile);
if(doc && doc->getDocumentElement())
{
XERCES_CPP_NAMESPACE_QUALIFIER DOMNodeList *list=NULL;
if(doNamespaces)
list=doc->getElementsByTagNameNS(doc->getDocumentElement()->getNamespaceURI(), doc->getDocumentElement()->getLocalName());
else
list=doc->getElementsByTagName(doc->getDocumentElement()->getNodeName());
if(list==NULL)
XERCES_STD_QUALIFIER cout << "getElementsByTagName didn't return a valid DOMNodeList." << XERCES_STD_QUALIFIER endl;
else if(list->item(0)!=doc->getDocumentElement())
XERCES_STD_QUALIFIER cout << "getElementsByTagName didn't find the root element." << XERCES_STD_QUALIFIER endl;
}
sax2parser->parse(xmlFile);
saxParser->parse(xmlFile);
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException during parsing: '" << xmlFile << "'\n" << XERCES_STD_QUALIFIER endl;;
continue;
}
catch (const XMLException& toCatch)
{
char *msg = XMLString::transcode(toCatch.getMessage());
XERCES_STD_QUALIFIER cerr << "\nError during parsing: '" << xmlFile << "'\n"
<< "Exception message is: \n"
<< msg << "\n" << XERCES_STD_QUALIFIER endl;
XMLString::release(&msg);
continue;
}
catch (const DOMException& toCatch)
{
const unsigned int maxChars = 2047;
XMLCh errText[maxChars + 1];
XERCES_STD_QUALIFIER cerr << "\nDOM Error during parsing: '" << xmlFile << "'\n"
<< "DOMException code is: " << toCatch.code << XERCES_STD_QUALIFIER endl;
if (DOMImplementation::loadDOMExceptionMsg(toCatch.code, errText, maxChars))
{
char * msg = XMLString::transcode(errText);
XERCES_STD_QUALIFIER cerr << "Message is: " << msg << XERCES_STD_QUALIFIER endl;
continue;
}
}
catch (...)
{
XERCES_STD_QUALIFIER cerr << "\nUnexpected exception during parsing: '" << xmlFile << "'\n";
continue;
}
}
}
//
// Delete the domBuilder itself. Must be done prior to calling Terminate, below.
//
domBuilder->release();
delete sax2parser;
delete saxParser;
XERCES_STD_QUALIFIER cout << "At destruction, domBuilderMemMonitor has " << domBuilderMemMonitor->getTotalMemory() << " bytes." << XERCES_STD_QUALIFIER endl;
XERCES_STD_QUALIFIER cout << "At destruction, sax2MemMonitor has " << sax2MemMonitor->getTotalMemory() << " bytes." << XERCES_STD_QUALIFIER endl;
XERCES_STD_QUALIFIER cout << "At destruction, sax1MemMonitor has " << sax1MemMonitor->getTotalMemory() << " bytes." << XERCES_STD_QUALIFIER endl;
delete domBuilderMemMonitor;
delete sax2MemMonitor;
delete sax1MemMonitor;
XMLPlatformUtils::Terminate();
XERCES_STD_QUALIFIER cout << "At destruction, staticMemMonitor has " << staticMemMonitor->getTotalMemory() << " bytes." << XERCES_STD_QUALIFIER endl;
delete staticMemMonitor;
return 0;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{
// Initialize the XML4C system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! Message:\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
int parmInd;
for (parmInd = 1; parmInd < argC; parmInd++)
{
// Break out on first parm not starting with a dash
if (argV[parmInd][0] != '-')
break;
// Watch for special case help request
if (!strcmp(argV[parmInd], "-?"))
{
usage();
XMLPlatformUtils::Terminate();
return 2;
}
else if (!strncmp(argV[parmInd], "-v=", 3)
|| !strncmp(argV[parmInd], "-V=", 3))
{
const char* const parm = &argV[parmInd][3];
if (!strcmp(parm, "never"))
valScheme = SAXParser::Val_Never;
else if (!strcmp(parm, "auto"))
valScheme = SAXParser::Val_Auto;
else if (!strcmp(parm, "always"))
valScheme = SAXParser::Val_Always;
else
{
XERCES_STD_QUALIFIER cerr << "Unknown -v= value: " << parm << XERCES_STD_QUALIFIER endl;
XMLPlatformUtils::Terminate();
return 2;
}
}
else if (!strcmp(argV[parmInd], "-n")
|| !strcmp(argV[parmInd], "-N"))
{
doNamespaces = true;
}
else if (!strcmp(argV[parmInd], "-s")
|| !strcmp(argV[parmInd], "-S"))
{
doSchema = true;
}
else if (!strcmp(argV[parmInd], "-f")
|| !strcmp(argV[parmInd], "-F"))
{
schemaFullChecking = true;
}
else
{
XERCES_STD_QUALIFIER cerr << "Unknown option '" << argV[parmInd]
<< "', ignoring it\n" << XERCES_STD_QUALIFIER endl;
}
}
//
// Create a SAX parser object. Then, according to what we were told on
// the command line, set the options.
//
SAXParser* parser = new SAXParser;
parser->setValidationScheme(valScheme);
parser->setDoNamespaces(doNamespaces);
parser->setDoSchema(doSchema);
parser->setValidationSchemaFullChecking(schemaFullChecking);
//
// Create our SAX handler object and install it on the parser, as the
// document and error handler. We are responsible for cleaning them
// up, but since its just stack based here, there's nothing special
// to do.
//
StdInParseHandlers handler;
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
unsigned long duration;
int errorCount = 0;
// create a faux scope so that 'src' destructor is called before
// XMLPlatformUtils::Terminate
{
//
// Kick off the parse and catch any exceptions. Create a standard
// input input source and tell the parser to parse from that.
//
StdInInputSource src;
try
{
const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
parser->parse(src);
const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
duration = endMillis - startMillis;
errorCount = parser->getErrorCount();
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorCount = 2;
return 4;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "\nError during parsing: \n"
<< StrX(e.getMessage())
<< "\n" << XERCES_STD_QUALIFIER endl;
errorCount = 1;
return 4;
}
// Print out the stats that we collected and time taken
if (!errorCount) {
XERCES_STD_QUALIFIER cout << StrX(src.getSystemId()) << ": " << duration << " ms ("
<< handler.getElementCount() << " elems, "
<< handler.getAttrCount() << " attrs, "
<< handler.getSpaceCount() << " spaces, "
<< handler.getCharacterCount() << " chars)" << XERCES_STD_QUALIFIER endl;
}
}
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
XMLPlatformUtils::Terminate();
if (errorCount > 0)
return 4;
else
return 0;
}
void process(char* const xmlFile)
{
//
// Create a Schema validator to be used for our validation work. Then create
// a SAX parser object and pass it our validator. Then, according to what
// we were told on the command line, set it to validate or not. He owns
// the validator, so we have to allocate it.
//
SAXParser parser;
parser.setValidationScheme(SAXParser::Val_Always);
parser.setDoNamespaces(true);
parser.setDoSchema(true);
parser.parse(xmlFile);
if (parser.getErrorCount())
{
XERCES_STD_QUALIFIER cout << "\nErrors occurred, no output available\n" << XERCES_STD_QUALIFIER endl;
return;
}
if (!parser.getValidator().handlesSchema())
{
XERCES_STD_QUALIFIER cout << "\n Non schema document, no output available\n" << XERCES_STD_QUALIFIER endl;
return;
}
Grammar* rootGrammar = parser.getRootGrammar();
if (!rootGrammar || rootGrammar->getGrammarType() != Grammar::SchemaGrammarType)
{
XERCES_STD_QUALIFIER cout << "\n Non schema grammar, no output available\n" << XERCES_STD_QUALIFIER endl;
return;
}
//
// Now we will get an enumerator for the element pool from the validator
// and enumerate the elements, printing them as we go. For each element
// we get an enumerator for its attributes and print them also.
//
SchemaGrammar* grammar = (SchemaGrammar*) rootGrammar;
RefHash3KeysIdPoolEnumerator<SchemaElementDecl> elemEnum = grammar->getElemEnumerator();
if (!elemEnum.hasMoreElements())
{
XERCES_STD_QUALIFIER cout << "\nThe validator has no elements to display\n" << XERCES_STD_QUALIFIER endl;
return;
}
while(elemEnum.hasMoreElements())
{
const SchemaElementDecl& curElem = elemEnum.nextElement();
// Name
XERCES_STD_QUALIFIER cout << "Name:\t\t\t" << StrX(curElem.getFullName()) << "\n";
// Model Type
XERCES_STD_QUALIFIER cout << "Model Type:\t\t";
switch( curElem.getModelType() )
{
case SchemaElementDecl::Empty: XERCES_STD_QUALIFIER cout << "Empty"; break;
case SchemaElementDecl::Any: XERCES_STD_QUALIFIER cout << "Any"; break;
case SchemaElementDecl::Mixed_Simple: XERCES_STD_QUALIFIER cout << "Mixed_Simple"; break;
case SchemaElementDecl::Mixed_Complex: XERCES_STD_QUALIFIER cout << "Mixed_Complex"; break;
case SchemaElementDecl::Children: XERCES_STD_QUALIFIER cout << "Children"; break;
case SchemaElementDecl::Simple: XERCES_STD_QUALIFIER cout << "Simple"; break;
case SchemaElementDecl::ElementOnlyEmpty: XERCES_STD_QUALIFIER cout << "ElementOnlyEmpty"; break;
default: XERCES_STD_QUALIFIER cout << "Unknown"; break;
}
XERCES_STD_QUALIFIER cout << "\n";
// Create Reason
XERCES_STD_QUALIFIER cout << "Create Reason:\t";
switch( curElem.getCreateReason() )
{
case XMLElementDecl::NoReason: XERCES_STD_QUALIFIER cout << "Empty"; break;
case XMLElementDecl::Declared: XERCES_STD_QUALIFIER cout << "Declared"; break;
case XMLElementDecl::AttList: XERCES_STD_QUALIFIER cout << "AttList"; break;
case XMLElementDecl::InContentModel: XERCES_STD_QUALIFIER cout << "InContentModel"; break;
case XMLElementDecl::AsRootElem: XERCES_STD_QUALIFIER cout << "AsRootElem"; break;
case XMLElementDecl::JustFaultIn: XERCES_STD_QUALIFIER cout << "JustFaultIn"; break;
default: XERCES_STD_QUALIFIER cout << "Unknown"; break;
}
XERCES_STD_QUALIFIER cout << "\n";
// Content Spec Node
processContentSpecNode( curElem.getContentSpec() );
// Misc Flags
int mflags = curElem.getMiscFlags();
if( mflags !=0 )
{
XERCES_STD_QUALIFIER cout << "Misc. Flags:\t";
}
if ( mflags & SchemaSymbols::XSD_NILLABLE )
XERCES_STD_QUALIFIER cout << "Nillable ";
if ( mflags & SchemaSymbols::XSD_ABSTRACT )
XERCES_STD_QUALIFIER cout << "Abstract ";
if ( mflags & SchemaSymbols::XSD_FIXED )
XERCES_STD_QUALIFIER cout << "Fixed ";
if( mflags !=0 )
{
XERCES_STD_QUALIFIER cout << "\n";
}
// Substitution Name
SchemaElementDecl* subsGroup = curElem.getSubstitutionGroupElem();
if( subsGroup )
{
const XMLCh* uriText = parser.getURIText(subsGroup->getURI());
XERCES_STD_QUALIFIER cout << "Substitution Name:\t" << StrX(uriText)
<< "," << StrX(subsGroup->getBaseName()) << "\n";
}
// Content Model
const XMLCh* fmtCntModel = curElem.getFormattedContentModel();
if( fmtCntModel != NULL )
{
XERCES_STD_QUALIFIER cout << "Content Model:\t" << StrX(fmtCntModel) << "\n";
}
const ComplexTypeInfo* ctype = curElem.getComplexTypeInfo();
if( ctype != NULL)
{
XERCES_STD_QUALIFIER cout << "ComplexType:\n";
XERCES_STD_QUALIFIER cout << "\tTypeName:\t" << StrX(ctype->getTypeName()) << "\n";
ContentSpecNode* cSpecNode = ctype->getContentSpec();
processContentSpecNode(cSpecNode, true );
}
// Datatype
DatatypeValidator* dtValidator = curElem.getDatatypeValidator();
processDatatypeValidator( dtValidator );
// Get an enumerator for this guy's attributes if any
if ( curElem.hasAttDefs() )
{
processAttributes( curElem.getAttDefList() );
}
XERCES_STD_QUALIFIER cout << "--------------------------------------------";
XERCES_STD_QUALIFIER cout << XERCES_STD_QUALIFIER endl;
}
return;
}
//------------------------------------------------------------------------
//
// parse - This is the method that is invoked by the rest of
// the test program to actually parse an XML file.
//
//------------------------------------------------------------------------
int ThreadParser::parse(int fileNum)
{
MemBufInputSource *mbis = 0;
InFileInfo *fInfo = &gRunInfo.files[fileNum];
bool errors = false;
fCheckSum = 0;
if (gRunInfo.inMemory) {
mbis = new MemBufInputSource((const XMLByte *) fInfo->fileContent,
fInfo->fileSize,
fInfo->uFileName,
false);
}
try
{
if (gRunInfo.dom) {
// Do a DOM parse
fXercesDOMParser->resetDocumentPool();
if (gRunInfo.inMemory)
fXercesDOMParser->parse(*mbis);
else
fXercesDOMParser->parse(fInfo->fileName);
fDoc = fXercesDOMParser->getDocument();
domCheckSum(fDoc);
}
else if (gRunInfo.sax) {
// Do a SAX1 parse
if (gRunInfo.inMemory)
fSAXParser->parse(*mbis);
else
fSAXParser->parse(fInfo->fileName);
}
else {
// Do a SAX2 parse
if (gRunInfo.inMemory)
fSAX2Parser->parse(*mbis);
else
fSAX2Parser->parse(fInfo->fileName);
}
}
catch (const OutOfMemoryException&)
{
fprintf(stderr, " during parsing: %s\n OutOfMemoryException.\n", fInfo->fileName);
errors = true;
}
catch (const XMLException& e)
{
char *exceptionMessage = XMLString::transcode(e.getMessage());
fprintf(stderr, " during parsing: %s\n Exception message is: %s\n",
fInfo->fileName, exceptionMessage);
XMLString::release(&exceptionMessage);
errors = true;
}
catch (const DOMException& toCatch)
{
fprintf(stderr, " during parsing: %s\n DOMException code is: %i\n",
fInfo->fileName, toCatch.code);
errors = true;
}
catch (const SAXParseException& e)
{
char *exceptionMessage = XMLString::transcode(e.getMessage());
fprintf(stderr, " during parsing: %s\n Exception message is: %s\n",
fInfo->fileName, exceptionMessage);
XMLString::release(&exceptionMessage);
errors = true;
}
catch (...)
{
fprintf(stderr, "Unexpected exception during parsing\n");
errors = true;
}
delete mbis;
if (errors) {
fflush(stderr);
return 0; // if errors occurred, return zero as if checksum = 0;
}
return fCheckSum;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{
// Initialize the XML4C2 system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! Message:\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
SAXParser::ValSchemes valScheme = SAXParser::Val_Auto;
bool doNamespaces = false;
bool doSchema = false;
bool schemaFullChecking = false;
int argInd;
for (argInd = 1; argInd < argC; argInd++)
{
// Break out on first parm not starting with a dash
if (argV[argInd][0] != '-')
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
// Watch for special case help request
if (!strcmp(argV[argInd], "-?"))
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
else if (!strncmp(argV[argInd], "-v=", 3)
|| !strncmp(argV[argInd], "-V=", 3))
{
const char* const parm = &argV[argInd][3];
if (!strcmp(parm, "never"))
valScheme = SAXParser::Val_Never;
else if (!strcmp(parm, "auto"))
valScheme = SAXParser::Val_Auto;
else if (!strcmp(parm, "always"))
valScheme = SAXParser::Val_Always;
else
{
XERCES_STD_QUALIFIER cerr << "Unknown -v= value: " << parm << XERCES_STD_QUALIFIER endl;
return 2;
}
}
else if (!strcmp(argV[argInd], "-n")
|| !strcmp(argV[argInd], "-N"))
{
doNamespaces = true;
}
else if (!strcmp(argV[argInd], "-s")
|| !strcmp(argV[argInd], "-S"))
{
doSchema = true;
}
else if (!strcmp(argV[argInd], "-f")
|| !strcmp(argV[argInd], "-F"))
{
schemaFullChecking = true;
}
else
{
XERCES_STD_QUALIFIER cerr << "Unknown option '" << argV[argInd]
<< "', ignoring it\n" << XERCES_STD_QUALIFIER endl;
}
}
//
// Create a SAX parser object. Then, according to what we were told on
// the command line, set it to validate or not.
//
SAXParser* parser = new SAXParser;
parser->setValidationScheme(valScheme);
parser->setDoNamespaces(doNamespaces);
parser->setDoSchema(doSchema);
parser->setValidationSchemaFullChecking(schemaFullChecking);
//
// Create our SAX handler object and install it on the parser, as the
// document and error handlers.
//
MemParseHandlers handler;
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
//
// Create MemBufferInputSource from the buffer containing the XML
// statements.
//
// NOTE: We are using strlen() here, since we know that the chars in
// our hard coded buffer are single byte chars!!! The parameter wants
// the number of BYTES, not chars, so when you create a memory buffer
// give it the byte size (which just happens to be the same here.)
//
MemBufInputSource* memBufIS = new MemBufInputSource
(
(const XMLByte*)gXMLInMemBuf
, strlen(gXMLInMemBuf)
, gMemBufId
, false
);
//
// Get the starting time and kick off the parse of the indicated
// file. Catch any exceptions that might propogate out of it.
//
unsigned long duration;
int errorCount = 0;
int errorCode = 0;
try
{
const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
parser->parse(*memBufIS);
const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
duration = endMillis - startMillis;
errorCount = parser->getErrorCount();
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorCode = 5;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "\nError during parsing memory stream:\n"
<< "Exception message is: \n"
<< StrX(e.getMessage()) << "\n" << XERCES_STD_QUALIFIER endl;
errorCode = 4;
}
if(errorCode) {
XMLPlatformUtils::Terminate();
return errorCode;
}
// Print out the stats that we collected and time taken.
if (!errorCount) {
XERCES_STD_QUALIFIER cout << "\nFinished parsing the memory buffer containing the following "
<< "XML statements:\n\n"
<< gXMLInMemBuf
<< "\n\n\n"
<< "Parsing took " << duration << " ms ("
<< handler.getElementCount() << " elements, "
<< handler.getAttrCount() << " attributes, "
<< handler.getSpaceCount() << " spaces, "
<< handler.getCharacterCount() << " characters).\n" << XERCES_STD_QUALIFIER endl;
}
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
delete memBufIS;
// And call the termination method
XMLPlatformUtils::Terminate();
if (errorCount > 0)
return 4;
else
return 0;
}
void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) {
#else
int main (int argc, char* argv[]) {
//int nlhs;
//mxArray *plhs[3];
//int nrhs;
//const mxArray *prhs[];
#endif
#ifdef MAT
if (nrhs < 1) {
#else
if (argc < 1) {
#endif
cout << "XML corpus file required";
exit(1);
}
// get the corpus file name
#ifdef MAT
int strlen = mxGetN(prhs[0])+1;
char* corpus_file = (char*)mxCalloc(strlen, sizeof(char)); //mxCalloc is similar to malloc in C
mxGetString(prhs[0], corpus_file, strlen);
#else
char* corpus_file = argv[1];
#endif
#ifdef DEBUG
cout << "Parsing document: " << corpus_file << "\n";
#endif
try {
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cout << "Error during initialization! :\n"
<< message << "\n";
XMLString::release(&message);
exit(1);//return 1;
}
SAXParser* parser = new SAXParser();
parser->setValidationScheme(SAXParser::Val_Always);
parser->setDoNamespaces(true); // optional
MovieSAXHandler* content = new MovieSAXHandler();
ErrorHandler* errHandler = (ErrorHandler*) content;
parser->setDocumentHandler(content);
parser->setErrorHandler(errHandler);
try {
parser->parse(corpus_file);
}
catch (const XMLException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cout << "Exception message is: \n"
<< message << "\n";
XMLString::release(&message);
exit(1);//return -1;
}
catch (const SAXParseException& toCatch) {
char* message = XMLString::transcode(toCatch.getMessage());
cout << "Exception message is: \n"
<< message << "\n";
XMLString::release(&message);
exit(1);//return -1;
}
catch (...) {
cout << "Unexpected Exception \n" ;
exit(1);//return -1;
}
#ifdef DEBUG
cout << "Printing the inverted index: \n";
cout << InvertedIndex::instance() << "\n";
#endif
#ifdef MAT
// call this function to output all the matrices to the MATLAB environment.
MATProcedure(nlhs, plhs, nrhs, prhs);
#else
// call this function to output features to files
OUTProcedure();
#endif
#ifdef DEBUG
cout << "Done \n";
#endif
delete InvertedIndex::instance();
delete parser;
delete content;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{
// Check command line and extract arguments.
if (argC < 2)
{
usage();
return 1;
}
const char* xmlFile = 0;
SAXParser::ValSchemes valScheme = SAXParser::Val_Auto;
bool doNamespaces = false;
bool doSchema = false;
bool schemaFullChecking = false;
bool doList = false;
bool errorOccurred = false;
bool recognizeNEL = false;
char localeStr[64];
memset(localeStr, 0, sizeof localeStr);
int argInd;
for (argInd = 1; argInd < argC; argInd++)
{
// Break out on first parm not starting with a dash
if (argV[argInd][0] != '-')
break;
// Watch for special case help request
if (!strcmp(argV[argInd], "-?"))
{
usage();
return 2;
}
else if (!strncmp(argV[argInd], "-v=", 3)
|| !strncmp(argV[argInd], "-V=", 3))
{
const char* const parm = &argV[argInd][3];
if (!strcmp(parm, "never"))
valScheme = SAXParser::Val_Never;
else if (!strcmp(parm, "auto"))
valScheme = SAXParser::Val_Auto;
else if (!strcmp(parm, "always"))
valScheme = SAXParser::Val_Always;
else
{
XERCES_STD_QUALIFIER cerr << "Unknown -v= value: " << parm << XERCES_STD_QUALIFIER endl;
return 2;
}
}
else if (!strcmp(argV[argInd], "-n")
|| !strcmp(argV[argInd], "-N"))
{
doNamespaces = true;
}
else if (!strcmp(argV[argInd], "-s")
|| !strcmp(argV[argInd], "-S"))
{
doSchema = true;
}
else if (!strcmp(argV[argInd], "-f")
|| !strcmp(argV[argInd], "-F"))
{
schemaFullChecking = true;
}
else if (!strcmp(argV[argInd], "-l")
|| !strcmp(argV[argInd], "-L"))
{
doList = true;
}
else if (!strcmp(argV[argInd], "-special:nel"))
{
// turning this on will lead to non-standard compliance behaviour
// it will recognize the unicode character 0x85 as new line character
// instead of regular character as specified in XML 1.0
// do not turn this on unless really necessary
recognizeNEL = true;
}
else if (!strncmp(argV[argInd], "-locale=", 8))
{
// Get out the end of line
strcpy(localeStr, &(argV[argInd][8]));
}
else
{
XERCES_STD_QUALIFIER cerr << "Unknown option '" << argV[argInd]
<< "', ignoring it\n" << XERCES_STD_QUALIFIER endl;
}
}
//
// There should at least one parameter left, and that
// should be the file name(s).
//
if (argInd == argC)
{
usage();
return 1;
}
// Initialize the XML4C2 system
try
{
if (strlen(localeStr))
{
XMLPlatformUtils::Initialize(localeStr);
}
else
{
XMLPlatformUtils::Initialize();
}
if (recognizeNEL)
{
XMLPlatformUtils::recognizeNEL(recognizeNEL);
}
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! Message:\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
//
// Create a SAX parser object. Then, according to what we were told on
// the command line, set it to validate or not.
//
SAXParser* parser = new SAXParser;
parser->setValidationScheme(valScheme);
parser->setDoNamespaces(doNamespaces);
parser->setDoSchema(doSchema);
parser->setHandleMultipleImports (true);
parser->setValidationSchemaFullChecking(schemaFullChecking);
//
// Create our SAX handler object and install it on the parser, as the
// document and error handler.
//
SAXCountHandlers handler;
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
//
// Get the starting time and kick off the parse of the indicated
// file. Catch any exceptions that might propogate out of it.
//
unsigned long duration;
XERCES_STD_QUALIFIER ifstream fin;
// the input is a list file
if (doList)
fin.open(argV[argInd]);
if (fin.fail()) {
XERCES_STD_QUALIFIER cerr <<"Cannot open the list file: " << argV[argInd] << XERCES_STD_QUALIFIER endl;
return 2;
}
while (true)
{
char fURI[1000];
//initialize the array to zeros
memset(fURI,0,sizeof(fURI));
if (doList) {
if (! fin.eof() ) {
fin.getline (fURI, sizeof(fURI));
if (!*fURI)
continue;
else {
xmlFile = fURI;
XERCES_STD_QUALIFIER cerr << "==Parsing== " << xmlFile << XERCES_STD_QUALIFIER endl;
}
}
else
break;
}
else {
if (argInd < argC)
{
xmlFile = argV[argInd];
argInd++;
}
else
break;
}
//reset error count first
handler.resetErrors();
try
{
const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
parser->parse(xmlFile);
const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
duration = endMillis - startMillis;
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorOccurred = true;
continue;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "\nError during parsing: '" << xmlFile << "'\n"
<< "Exception message is: \n"
<< StrX(e.getMessage()) << "\n" << XERCES_STD_QUALIFIER endl;
errorOccurred = true;
continue;
}
catch (...)
{
XERCES_STD_QUALIFIER cerr << "\nUnexpected exception during parsing: '" << xmlFile << "'\n";
errorOccurred = true;
continue;
}
// Print out the stats that we collected and time taken
if (!handler.getSawErrors())
{
XERCES_STD_QUALIFIER cout << xmlFile << ": " << duration << " ms ("
<< handler.getElementCount() << " elems, "
<< handler.getAttrCount() << " attrs, "
<< handler.getSpaceCount() << " spaces, "
<< handler.getCharacterCount() << " chars)" << XERCES_STD_QUALIFIER endl;
}
else
errorOccurred = true;
}
if (doList)
fin.close();
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
// And call the termination method
XMLPlatformUtils::Terminate();
if (errorOccurred)
return 4;
else
return 0;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{
// Initialize the XML4C system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! :\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
// Check command line and extract arguments.
if (argC < 2)
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
// See if non validating dom parser configuration is requested.
int parmInd;
for (parmInd = 1; parmInd < argC; parmInd++)
{
// Break out on first parm not starting with a dash
if (argV[parmInd][0] != '-')
break;
// Watch for special case help request
if (!strcmp(argV[parmInd], "-?"))
{
usage();
XMLPlatformUtils::Terminate();
return 2;
}
else if (!strncmp(argV[parmInd], "-v=", 3)
|| !strncmp(argV[parmInd], "-V=", 3))
{
const char* const parm = &argV[parmInd][3];
if (!strcmp(parm, "never"))
valScheme = SAXParser::Val_Never;
else if (!strcmp(parm, "auto"))
valScheme = SAXParser::Val_Auto;
else if (!strcmp(parm, "always"))
valScheme = SAXParser::Val_Always;
else
{
XERCES_STD_QUALIFIER cerr << "Unknown -v= value: " << parm << XERCES_STD_QUALIFIER endl;
XMLPlatformUtils::Terminate();
return 2;
}
}
else if (!strcmp(argV[parmInd], "-n")
|| !strcmp(argV[parmInd], "-N"))
{
doNamespaces = true;
}
else if (!strcmp(argV[parmInd], "-s")
|| !strcmp(argV[parmInd], "-S"))
{
doSchema = true;
}
else if (!strcmp(argV[parmInd], "-f")
|| !strcmp(argV[parmInd], "-F"))
{
schemaFullChecking = true;
}
else
{
XERCES_STD_QUALIFIER cerr << "Unknown option '" << argV[parmInd]
<< "', ignoring it\n" << XERCES_STD_QUALIFIER endl;
}
}
//
// And now we have to have only one parameter left and it must be
// the file name.
//
if (parmInd + 1 != argC)
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
xmlFile = argV[parmInd];
int errorCount = 0;
//
// Create a SAX parser object to use and create our SAX event handlers
// and plug them in.
//
SAXParser* parser = new SAXParser;
PParseHandlers handler;
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
parser->setValidationScheme(valScheme);
parser->setDoNamespaces(doNamespaces);
parser->setDoSchema(doSchema);
parser->setValidationSchemaFullChecking(schemaFullChecking);
//
// Ok, lets do the progressive parse loop. On each time around the
// loop, we look and see if the handler has found what its looking
// for. When it does, we fall out then.
//
unsigned long duration;
int errorCode = 0;
try
{
// Create a progressive scan token
XMLPScanToken token;
const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
if (!parser->parseFirst(xmlFile, token))
{
XERCES_STD_QUALIFIER cerr << "scanFirst() failed\n" << XERCES_STD_QUALIFIER endl;
XMLPlatformUtils::Terminate();
return 1;
}
//
// We started ok, so lets call scanNext() until we find what we want
// or hit the end.
//
bool gotMore = true;
while (gotMore && !parser->getErrorCount())
gotMore = parser->parseNext(token);
const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
duration = endMillis - startMillis;
errorCount = parser->getErrorCount();
//
// Reset the parser-> In this simple progrma, since we just exit
// now, its not technically required. But, in programs which
// would remain open, you should reset after a progressive parse
// in case you broke out before the end of the file. This insures
// that all opened files, sockets, etc... are closed.
//
parser->parseReset(token);
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorCode = 5;
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "\nAn error occurred: '" << xmlFile << "'\n"
<< "Exception message is: \n"
<< StrX(toCatch.getMessage())
<< "\n" << XERCES_STD_QUALIFIER endl;
errorCode = 4;
}
if(errorCode) {
XMLPlatformUtils::Terminate();
return errorCode;
}
if (!errorCount) {
XERCES_STD_QUALIFIER cout << xmlFile << ": " << duration << " ms ("
<< handler.getElementCount() << " elems, "
<< handler.getAttrCount() << " attrs, "
<< handler.getSpaceCount() << " spaces, "
<< handler.getCharacterCount() << " chars)" << XERCES_STD_QUALIFIER endl;
}
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
// And call the termination method
XMLPlatformUtils::Terminate();
if (errorCount > 0)
return 4;
else
return 0;
}
// ---------------------------------------------------------------------------
// Program entry point
// ---------------------------------------------------------------------------
int main(int argc, char* args[])
{
// Initialize the XML4C system
try
{
XMLPlatformUtils::Initialize();
}
catch (const XMLException& toCatch)
{
XERCES_STD_QUALIFIER cerr << "Error during initialization! Message:\n"
<< StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
return 1;
}
// We only have one parameter, which is the file to process
// We only have one required parameter, which is the file to process
if ((argc != 2) || (*(args[1]) == '-'))
{
usage();
XMLPlatformUtils::Terminate();
return 1;
}
const char* xmlFile = args[1];
//
// Create a SAX parser object. Then, according to what we were told on
// the command line, set it to validate or not.
//
SAXParser* parser = new SAXParser;
//
// Create our SAX handler object and install it on the parser, as the
// document, entity and error handlers.
//
RedirectHandlers handler;
parser->setDocumentHandler(&handler);
parser->setErrorHandler(&handler);
parser->setEntityResolver(&handler);
//
// Get the starting time and kick off the parse of the indicated file.
// Catch any exceptions that might propogate out of it.
//
unsigned long duration;
int errorCount = 0;
int errorCode = 0;
try
{
const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
parser->parse(xmlFile);
const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
duration = endMillis - startMillis;
errorCount = parser->getErrorCount();
}
catch (const OutOfMemoryException&)
{
XERCES_STD_QUALIFIER cerr << "OutOfMemoryException" << XERCES_STD_QUALIFIER endl;
errorCode = 5;
}
catch (const XMLException& e)
{
XERCES_STD_QUALIFIER cerr << "\nError during parsing: '" << xmlFile << "'\n"
<< "Exception message is: \n"
<< StrX(e.getMessage()) << "\n" << XERCES_STD_QUALIFIER endl;
errorCode = 4;
}
if(errorCode) {
XMLPlatformUtils::Terminate();
return errorCode;
}
// Print out the stats that we collected and time taken.
if (!errorCount) {
XERCES_STD_QUALIFIER cout << xmlFile << ": " << duration << " ms ("
<< handler.getElementCount() << " elems, "
<< handler.getAttrCount() << " attrs, "
<< handler.getSpaceCount() << " spaces, "
<< handler.getCharacterCount() << " chars)" << XERCES_STD_QUALIFIER endl;
}
//
// Delete the parser itself. Must be done prior to calling Terminate, below.
//
delete parser;
XMLPlatformUtils::Terminate();
if (errorCount > 0)
return 4;
else
return 0;
}