示例#1
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;
}
示例#2
0
文件: SAXCount.cpp 项目: kanbang/Colt
// ---------------------------------------------------------------------------
//  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;

}