You are viewing a plain text version of this content. The canonical link for it is here.
Posted to c-dev@xerces.apache.org by "Agrawal, Vikas (ELS)" <V....@elsevier.co.uk> on 2003/09/04 12:42:57 UTC
DOMBuilder is terribly slow: need quick reply
Hi All,
I am using DOMBuilder as a parser to parse my 10 MB file and it is terribly
horribly slow. Could anybody suggest me how to improve perfomance. James
clark SP parser was used to take not more than a 30 seconds to parse this
file. DOMBuilder is taking around 20 minutes to parse my file if I override
the startElement function as follows.
Normally DOMBuilder is also efficient and taking just 30 seconds if I do not
override the startElement function. I am wondering why is it adding another
19 and half minutes in parsing time if I just override the startElement and
that is just to put node location information in the node user data.
Am I doing something wrong in the overridden startElement function below.
class EsDOMBuilderImpl : public DOMBuilderImpl
void EsDOMBuilderImpl::startElement
(
const XMLElementDecl& elemDecl
, const unsigned int urlId
, const XMLCh* const elemPrefix
, const RefVectorOf<XMLAttr>& attrList
, const unsigned int attrCount
, const bool isEmpty
, const bool isRoot
)
{
const XMLCh* const systemId = 0;
AbstractDOMParser::startElement(elemDecl,urlId,elemPrefix,attrList,attrCount
,isEmpty,isRoot);
XMLScanner* sc = this->getScanner();
const Locator* loc = sc->getLocator();
int lineNum = loc->getLineNumber();
int colNum = loc->getColumnNumber();
int offset = sc->getSrcOffset();
DOMNode* node = this->getCurrentNode();
DOMLocator* location = new DOMLocatorImpl(lineNum, colNum,
getCurrentNode(), systemId);
location->setOffset(offset);
node->setUserData(locXmlStr_,location,0);
DOMLocator* vlocator = (DOMLocator*)node->getUserData(locXmlStr_);
return;
}
In the following way I am creating the parser
DOMBuilder* XmlDocumentTree::parserInstance()
{
if(parserInstance_ == NULL)
{
static const XMLCh gLS[] = { chLatin_L, chLatin_S, chNull };
DOMImplementationRegistry::addSource((DOMImplementationSource*)EsDOMImplemen
tationImpl::getDOMImplementationImpl());
DOMImplementation *impl =
DOMImplementationRegistry::getDOMImplementation(gLS);
parserInstance_ =
((DOMImplementationLS*)impl)->createDOMBuilder(DOMImplementationLS::MODE_SYN
CHRONOUS, 0); // it returns EsDOMBuilderImpl class pointer.
delete impl;
parserInstance_->setFeature(XMLUni::fgDOMValidation, true);
parserInstance_->setFeature(XMLUni::fgDOMNamespaces, false);
//parserInstance_->setFeature(X("namespaces"), true);
parserInstance_->setFeature(XMLUni::fgDOMEntities, false);
parserInstance_->setFeature(XMLUni::fgXercesCalculateSrcOfs,
true);
((EsDOMBuilderImpl*)parserInstance_)->setIncludeIgnorableWhitespace(false);
}
return parserInstance_;
}
I use it in the following way
XMLPlatformUtils::Initialize();
app->init();
parser = parserInstance();
errHandler_ = new EsDOMErrorHandler(warn);
parserInstance_->setErrorHandler(errHandler_);
entHandler_ = new EsXml4cDomEntityResolver();
entHandler_->addDirToPath(env);
parserInstance_->setEntityResolver(entHandler_);
DOMDocument * doc = 0;
doc = parser->parseURI(fname.c_str());
node = doc->getDocumentElement();
Thanks & Regards
Vikas Agrawal
---------------------------------------------------------------------
To unsubscribe, e-mail: xerces-c-dev-unsubscribe@xml.apache.org
For additional commands, e-mail: xerces-c-dev-help@xml.apache.org
Re: DOMBuilder is terribly slow: need quick reply
Posted by Gareth Reakes <ga...@decisionsoft.com>.
Hi,
I recall some discussion a while back about having lots of
userdata being very slow. Take out that line and reparse and if that is
the case then I will wrack my brain (or we could always look in the
archives). I recall a proposed solution to this as well. What version are
you using?
Gareth
On Thu, 4 Sep 2003, Agrawal, Vikas (ELS) wrote:
> Hi All,
>
> I am using DOMBuilder as a parser to parse my 10 MB file and it is terribly
> horribly slow. Could anybody suggest me how to improve perfomance. James
> clark SP parser was used to take not more than a 30 seconds to parse this
> file. DOMBuilder is taking around 20 minutes to parse my file if I override
> the startElement function as follows.
>
> Normally DOMBuilder is also efficient and taking just 30 seconds if I do not
> override the startElement function. I am wondering why is it adding another
> 19 and half minutes in parsing time if I just override the startElement and
> that is just to put node location information in the node user data.
>
> Am I doing something wrong in the overridden startElement function below.
>
> class EsDOMBuilderImpl : public DOMBuilderImpl
>
> void EsDOMBuilderImpl::startElement
> (
> const XMLElementDecl& elemDecl
> , const unsigned int urlId
> , const XMLCh* const elemPrefix
> , const RefVectorOf<XMLAttr>& attrList
> , const unsigned int attrCount
> , const bool isEmpty
> , const bool isRoot
> )
> {
> const XMLCh* const systemId = 0;
>
> AbstractDOMParser::startElement(elemDecl,urlId,elemPrefix,attrList,attrCount
> ,isEmpty,isRoot);
> XMLScanner* sc = this->getScanner();
> const Locator* loc = sc->getLocator();
>
> int lineNum = loc->getLineNumber();
> int colNum = loc->getColumnNumber();
> int offset = sc->getSrcOffset();
> DOMNode* node = this->getCurrentNode();
> DOMLocator* location = new DOMLocatorImpl(lineNum, colNum,
> getCurrentNode(), systemId);
> location->setOffset(offset);
>
> node->setUserData(locXmlStr_,location,0);
>
> DOMLocator* vlocator = (DOMLocator*)node->getUserData(locXmlStr_);
> return;
> }
>
> In the following way I am creating the parser
> DOMBuilder* XmlDocumentTree::parserInstance()
> {
> if(parserInstance_ == NULL)
> {
> static const XMLCh gLS[] = { chLatin_L, chLatin_S, chNull };
>
> DOMImplementationRegistry::addSource((DOMImplementationSource*)EsDOMImplemen
> tationImpl::getDOMImplementationImpl());
> DOMImplementation *impl =
> DOMImplementationRegistry::getDOMImplementation(gLS);
>
> parserInstance_ =
> ((DOMImplementationLS*)impl)->createDOMBuilder(DOMImplementationLS::MODE_SYN
> CHRONOUS, 0); // it returns EsDOMBuilderImpl class pointer.
> delete impl;
> parserInstance_->setFeature(XMLUni::fgDOMValidation, true);
> parserInstance_->setFeature(XMLUni::fgDOMNamespaces, false);
> //parserInstance_->setFeature(X("namespaces"), true);
>
>
> parserInstance_->setFeature(XMLUni::fgDOMEntities, false);
> parserInstance_->setFeature(XMLUni::fgXercesCalculateSrcOfs,
> true);
>
> ((EsDOMBuilderImpl*)parserInstance_)->setIncludeIgnorableWhitespace(false);
> }
> return parserInstance_;
> }
>
> I use it in the following way
>
> XMLPlatformUtils::Initialize();
> app->init();
> parser = parserInstance();
>
> errHandler_ = new EsDOMErrorHandler(warn);
> parserInstance_->setErrorHandler(errHandler_);
>
> entHandler_ = new EsXml4cDomEntityResolver();
> entHandler_->addDirToPath(env);
> parserInstance_->setEntityResolver(entHandler_);
> DOMDocument * doc = 0;
> doc = parser->parseURI(fname.c_str());
> node = doc->getDocumentElement();
>
> Thanks & Regards
> Vikas Agrawal
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: xerces-c-dev-unsubscribe@xml.apache.org
> For additional commands, e-mail: xerces-c-dev-help@xml.apache.org
>
>
>
--
Gareth Reakes, Head of Product Development +44-1865-203192
DecisionSoft Limited http://www.decisionsoft.com
XML Development and Services
---------------------------------------------------------------------
To unsubscribe, e-mail: xerces-c-dev-unsubscribe@xml.apache.org
For additional commands, e-mail: xerces-c-dev-help@xml.apache.org