Ejemplo n.º 1
0
// ---------------------------------------------------------------------------
//
//   main
//
// ---------------------------------------------------------------------------
int main(int argC, char* argV[])
{

    // Check command line and extract arguments.
    if (argC < 2)
    {
        usage();
        return 1;
    }

    const char*                xmlFile = 0;
    AbstractDOMParser::ValSchemes valScheme = AbstractDOMParser::Val_Auto;
    bool                       doNamespaces       = false;
    bool                       doSchema           = false;
    bool                       schemaFullChecking = false;
    bool                       doList = false;
    bool                       errorOccurred = false;
    bool                       recognizeNEL = false;
    bool                       printOutEncounteredEles = false;
    char                       localeStr[65]; // We need 64 + 1 characters if we use strstr(.., .., 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 = AbstractDOMParser::Val_Never;
            else if (!strcmp(parm, "auto"))
                valScheme = AbstractDOMParser::Val_Auto;
            else if (!strcmp(parm, "always"))
                valScheme = AbstractDOMParser::Val_Always;
            else
            {
                cerr << "Unknown -v= value: " << parm << 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 (!strcmp(argV[argInd], "-p")
                 ||  !strcmp(argV[argInd], "-P"))
        {
            printOutEncounteredEles = true;
        }
        else if (!strncmp(argV[argInd], "-locale=", 8))
        {
            // Get out the end of line
            strncat(localeStr, &(argV[argInd][8]), 64);
        }
        else
        {
            cerr << "Unknown option '" << argV[argInd]
                 << "', ignoring it\n" << 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;
    }

    // Initialize the XML4C system
    try
    {
        if (strlen(localeStr))
        {
            XMLPlatformUtils::Initialize(localeStr);
        }
        else
        {
            XMLPlatformUtils::Initialize();
        }

        if (recognizeNEL)
        {
            XMLPlatformUtils::recognizeNEL(recognizeNEL);
        }
    }

    catch (const XMLException& toCatch)
    {
        cerr << "Error during initialization! :\n"
             << StrX(toCatch.getMessage()) << endl;
        return 1;
    }

    // Instantiate the DOM parser.
    static const XMLCh gLS[] = { chLatin_L, chLatin_S, chNull };
    DOMImplementation *impl = DOMImplementationRegistry::getDOMImplementation(gLS);
    DOMBuilder        *parser = ((DOMImplementationLS*)impl)->createDOMBuilder(DOMImplementationLS::MODE_SYNCHRONOUS, 0);

    parser->setFeature(XMLUni::fgDOMNamespaces, doNamespaces);
    parser->setFeature(XMLUni::fgXercesSchema, doSchema);
    parser->setFeature(XMLUni::fgXercesSchemaFullChecking, schemaFullChecking);

    if (valScheme == AbstractDOMParser::Val_Auto)
    {
        parser->setFeature(XMLUni::fgDOMValidateIfSchema, true);
    }
    else if (valScheme == AbstractDOMParser::Val_Never)
    {
        parser->setFeature(XMLUni::fgDOMValidation, false);
    }
    else if (valScheme == AbstractDOMParser::Val_Always)
    {
        parser->setFeature(XMLUni::fgDOMValidation, true);
    }

    // enable datatype normalization - default is off
    parser->setFeature(XMLUni::fgDOMDatatypeNormalization, true);

    // And create our error handler and install it
    DOMCountErrorHandler errorHandler;
    parser->setErrorHandler(&errorHandler);

    //
    //  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;

    bool more = true;
    ifstream fin;

    // the input is a list file
    if (doList)
        fin.open(argV[argInd]);

    if (fin.fail()) {
        cerr <<"Cannot open the list file: " << argV[argInd] << 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;
                    cerr << "==Parsing== " << xmlFile << endl;
                }
            }
            else
                break;
        }
        else {
            xmlFile = argV[argInd];
            more = false;
        }

        //reset error count first
        errorHandler.resetErrors();

        XERCES_CPP_NAMESPACE_QUALIFIER DOMDocument *doc = 0;

        try
        {
            // reset document pool
            parser->resetDocumentPool();

            //const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
            doc = parser->parseURI(xmlFile);
            //const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
            //duration = endMillis - startMillis;
        }

        catch (const XMLException& toCatch)
        {
            cerr << "\nError during parsing: '" << xmlFile << "'\n"
                 << "Exception message is:  \n"
                 << StrX(toCatch.getMessage()) << "\n" << endl;
            errorOccurred = true;
            continue;
        }
        catch (const DOMException& toCatch)
        {
            const unsigned int maxChars = 2047;
            XMLCh errText[maxChars + 1];

            cerr << "\nDOM Error during parsing: '" << xmlFile << "'\n"
                 << "DOMException code is:  " << toCatch.code << endl;

            if (DOMImplementation::loadDOMExceptionMsg(toCatch.code, errText, maxChars))
                cerr << "Message is: " << StrX(errText) << endl;

            errorOccurred = true;
            continue;
        }
        catch (...)
        {
            cerr << "\nUnexpected exception during parsing: '" << xmlFile << "'\n";
            errorOccurred = true;
            continue;
        }

        //
        //  Extract the DOM tree, get the list of all the elements and report the
        //  length as the count of elements.
        //
        if (errorHandler.getSawErrors())
        {
            cout << "\nErrors occurred, no output available\n" << endl;
            errorOccurred = true;
        }
        else
        {
            unsigned int elementCount = 0;
            if (doc) {
                elementCount = countChildElements((DOMNode*)doc->getDocumentElement(), printOutEncounteredEles);
                // test getElementsByTagName and getLength
                XMLCh xa[] = {chAsterisk, chNull};
                if (elementCount != doc->getElementsByTagName(xa)->getLength()) {
                    cout << "\nErrors occurred, element count is wrong\n" << endl;
                    errorOccurred = true;
                }
            }

            // Print out the stats that we collected and time taken.
            cout << xmlFile << ": " << elementCount << " elems." << endl;
        }
    }

    //
    //  Delete the parser itself.  Must be done prior to calling Terminate, below.
    //
    parser->release();

    // And call the termination method
    XMLPlatformUtils::Terminate();

    if (doList)
        fin.close();

    if (errorOccurred)
        return 4;
    else
        return 0;
}
Ejemplo n.º 2
0
DOMDocument *CouchRunHttpServer::parsePrologue( std::string S_PrologueXMLFilename ){
  bool recognizeNEL = false;
  char localeStr[64];
  memset(localeStr, 0, sizeof localeStr);

  // Initialize the XML4C 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! :\n"
			      << StrX(toCatch.getMessage()) << XERCES_STD_QUALIFIER endl;
    return NULL;
  }

  // Instantiate the DOM parser.
  static const XMLCh gLS[] = { chLatin_L, chLatin_S, chNull };
  DOMImplementation *impl = 
    DOMImplementationRegistry::getDOMImplementation(gLS);
  DOMLSParser *parser = 
    ((DOMImplementationLS*)impl)->createLSParser(DOMImplementationLS::MODE_SYNCHRONOUS, 0);
  DOMConfiguration  *config = parser->getDomConfig();
  // enable datatype normalization - default is off
  config->setParameter(XMLUni::fgDOMDatatypeNormalization, true);

  // And create our error handler and install it
  DOMCountErrorHandler errorHandler;
  config->setParameter(XMLUni::fgDOMErrorHandler, &errorHandler);

  //
  //  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;
  const char *xmlFile = 0;
  bool more = true;
  XERCES_STD_QUALIFIER ifstream fin;

  // Later possibly a list of prologue files rather than a single one
  while (more){
    xmlFile = S_PrologueXMLFilename.c_str();
    more = false;
  }
      
  // Parse XML prologue file
  // Reset error count first
  errorHandler.resetErrors();

  bool errorOccurred = false;

  try{
    // reset document pool
    parser->resetDocumentPool();
      
    const unsigned long startMillis = XMLPlatformUtils::getCurrentMillis();
    XERCES_CPP_NAMESPACE_QUALIFIER DOMDocument *doc = parser->parseURI(xmlFile);
    const unsigned long endMillis = XMLPlatformUtils::getCurrentMillis();
    duration = endMillis - startMillis;
    // Print out the stats that we collected and time taken.
    XERCES_STD_QUALIFIER cout << "Parsed " 
			      << xmlFile << ": " << duration << " ms."
			      << XERCES_STD_QUALIFIER endl;
    return doc;
  }
  catch (const XMLException& toCatch){
    XERCES_STD_QUALIFIER cerr << "\nError during parsing: '" << xmlFile << "'\n"
			      << "Exception message is:  \n"
			      << StrX(toCatch.getMessage()) << "\n" 
                              << XERCES_STD_QUALIFIER endl;
    errorOccurred = true;
    //    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))
      XERCES_STD_QUALIFIER cerr << "Message is: " 
				<< StrX(errText) 
				<< XERCES_STD_QUALIFIER endl;
      
    errorOccurred = true;
    //    continue;
  }
  catch (...){
    XERCES_STD_QUALIFIER cerr << "\nUnexpected exception during parsing: '" << xmlFile << "'\n";
    errorOccurred = true;
    //    continue;
  }

  return NULL;
}