SGXMLScanner.cpp

                XMLElementDecl::CharDataOpts charOpts = XMLElementDecl::AllCharData;
                // And see if the current element is a 'Children' style content model
                ComplexTypeInfo *currType = ((SchemaValidator*)fValidator)->getCurrentTypeInfo();
                if(currType) 
                {
                    SchemaElementDecl::ModelTypes modelType = (SchemaElementDecl::ModelTypes) currType->getContentType(); 
                    if(modelType == SchemaElementDecl::Children) 
                        charOpts = XMLElementDecl::SpacesOk;
                } 

                if (charOpts == XMLElementDecl::SpacesOk)  // => Element Content
                {
                    // Error - standalone should have a value of "no" as whitespace detected in an
                    // element type with element content whose element declaration was external
                    //
                    fValidator->emitError(XMLValid::NoWSForStandalone);
                    ((SchemaElementDecl *)fElemStack.topElement()->fThisElement)->setValidity(PSVIDefs::INVALID);
                }
            }
        }
    }
    // Send any char data that we accumulated into the buffer
    sendCharData(toUse);
}


//  This method will scan a general/character entity ref. It will either
//  expand a char ref and return it directly, or push a reader for a general
//  entity.
//
//  The return value indicates whether the char parameters hold the value
//  or whether the value was pushed as a reader, or that it failed.
//
//  The escaped flag tells the caller whether the returned parameter resulted
//  from a character reference, which escapes the character in some cases. It
//  only makes any difference if the return value indicates the value was
//  returned directly.
SGXMLScanner::EntityExpRes
SGXMLScanner::scanEntityRef(  const   bool    inAttVal
                            ,       XMLCh&  firstCh
                            ,       XMLCh&  secondCh
                            ,       bool&   escaped)
{
    // Assume no escape
    secondCh = 0;
    escaped = false;

    // We have to insure that its all in one entity
    const unsigned int curReader = fReaderMgr.getCurrentReaderNum();

    //  If the next char is a pound, then its a character reference and we
    //  need to expand it always.
    if (fReaderMgr.skippedChar(chPound))
    {
        //  Its a character reference, so scan it and get back the numeric
        //  value it represents.
        if (!scanCharRef(firstCh, secondCh))
            return EntityExp_Failed;

        escaped = true;

        if (curReader != fReaderMgr.getCurrentReaderNum())
            emitError(XMLErrs::PartialMarkupInEntity);

        return EntityExp_Returned;
    }

    // Expand it since its a normal entity ref
    XMLBufBid bbName(&fBufMgr);
    if (!fReaderMgr.getName(bbName.getBuffer()))
    {
        emitError(XMLErrs::ExpectedEntityRefName);
        return EntityExp_Failed;
    }

    //  Next char must be a semi-colon. But if its not, just emit
    //  an error and try to continue.
    if (!fReaderMgr.skippedChar(chSemiColon))
        emitError(XMLErrs::UnterminatedEntityRef, bbName.getRawBuffer());

    // Make sure we ended up on the same entity reader as the & char
    if (curReader != fReaderMgr.getCurrentReaderNum())
        emitError(XMLErrs::PartialMarkupInEntity);

    // Look up the name in the general entity pool
    // If it does not exist, then obviously an error
    if (!fEntityTable->containsKey(bbName.getRawBuffer()))
    {
        // XML 1.0 Section 4.1
        // Well-formedness Constraint for entity not found:
        //   In a document without any DTD, a document with only an internal DTD subset which contains no parameter entity references,
        //      or a document with "standalone='yes'", for an entity reference that does not occur within the external subset
        //      or a parameter entity
        if (fStandalone || fHasNoDTD)
            emitError(XMLErrs::EntityNotFound, bbName.getRawBuffer());

        return EntityExp_Failed;
    }

    // here's where we need to check if there's a SecurityManager,
    // how many entity references we've had
    if(fSecurityManager != 0 && ++fEntityExpansionCount > fEntityExpansionLimit) {
        XMLCh expLimStr[16];
        XMLString::binToText(fEntityExpansionLimit, expLimStr, 15, 10);
        emitError
        ( 
            XMLErrs::EntityExpansionLimitExceeded
            , expLimStr
        );
        // there seems nothing better to be done than to reset the entity expansion limit
        fEntityExpansionCount = 0;
    }

    firstCh = fEntityTable->get(bbName.getRawBuffer());
    escaped = true;
    return EntityExp_Returned;
}


bool SGXMLScanner::switchGrammar(const XMLCh* const newGrammarNameSpace)
{
    Grammar* tempGrammar = fGrammarResolver->getGrammar(newGrammarNameSpace);

    if (!tempGrammar) {
        tempGrammar = fSchemaGrammar;
    }

    if (!tempGrammar)
        return false;
    else {
        fGrammar = tempGrammar;
        fGrammarType = fGrammar->getGrammarType();
        if (fGrammarType == Grammar::DTDGrammarType) {
            ThrowXML(RuntimeException, XMLExcepts::Gen_NoDTDValidator);
        }

        fValidator->setGrammar(fGrammar);
        return true;
    }
}

// check if we should skip or lax the validation of the element
// if skip - no validation
// if lax - validate only if the element if found
bool SGXMLScanner::laxElementValidation(QName* element, ContentLeafNameTypeVector* cv,
                                        const XMLContentModel* const cm,
                                        const unsigned int parentElemDepth)
{
    bool skipThisOne = false;
    bool laxThisOne = false;
    unsigned int elementURI = element->getURI();
    unsigned int currState = fElemState[parentElemDepth];

    if (currState == XMLContentModel::gInvalidTrans) {
        return laxThisOne;
    }

    SubstitutionGroupComparator comparator(fGrammarResolver, fURIStringPool);

    if (cv) {
        unsigned int i = 0;
        unsigned int leafCount = cv->getLeafCount();

        for (; i < leafCount; i++) {

            QName* fElemMap = cv->getLeafNameAt(i);
            unsigned int uri = fElemMap->getURI();
            unsigned int nextState;
            bool anyEncountered = false;
            ContentSpecNode::NodeTypes type = cv->getLeafTypeAt(i);

            if (type == ContentSpecNode::Leaf) {
                if (((uri == elementURI)
                      && XMLString::equals(fElemMap->getLocalPart(), element->getLocalPart()))
                    || comparator.isEquivalentTo(element, fElemMap)) {

                    nextState = cm->getNextState(currState, i);

                    if (nextState != XMLContentModel::gInvalidTrans) {
                        fElemState[parentElemDepth] = nextState;
                        break;
                    }
                }
            } else if ((type & 0x0f) == ContentSpecNode::Any) {
                anyEncountered = true;
            }
            else if ((type & 0x0f) == ContentSpecNode::Any_Other) {
                if (uri != elementURI) {
                    anyEncountered = true;
                }
            }
            else if ((type & 0x0f) == ContentSpecNode::Any_NS) {
                if (uri == elementURI) {
                    anyEncountered = true;
                }
            }

            if (anyEncountered) {

                nextState = cm->getNextState(currState, i);
                if (nextState != XMLContentModel::gInvalidTrans) {
                    fElemState[parentElemDepth] = nextState;

                    if (type == ContentSpecNode::Any_Skip ||
                        type == ContentSpecNode::Any_NS_Skip ||
                        type == ContentSpecNode::Any_Other_Skip) {
                        skipThisOne = true;
                    }
                    else if (type == ContentSpecNode::Any_Lax ||
                             type == ContentSpecNode::Any_NS_Lax ||
                             type == ContentSpecNode::Any_Other_Lax) {
                        laxThisOne = true;
                    }

                    break;
                }
            }
        } // for

        if (i == leafCount) { // no match
            fElemState[parentElemDepth] = XMLContentModel::gInvalidTrans;
            return laxThisOne;
        }

    } // if

    if (skipThisOne) {
        fValidate = false;
        fElemStack.setValidationFlag(fValidate);
    }

    return laxThisOne;
}


// check if there is an AnyAttribute, and if so, see if we should lax or skip
// if skip - no validation
// if lax - validate only if the attribute if found
bool SGXMLScanner::anyAttributeValidation(SchemaAttDef* attWildCard, unsigned int uriId, bool& skipThisOne, bool& laxThisOne)
{
    XMLAttDef::AttTypes wildCardType = attWildCard->getType();
    bool anyEncountered = false;
    skipThisOne = false;
    laxThisOne = false;
    if (wildCardType == XMLAttDef::Any_Any)
        anyEncountered = true;
    else if (wildCardType == XMLAttDef::Any_Other) {
        if (attWildCard->getAttName()->getURI() != uriId
            && uriId != fEmptyNamespaceId)
            anyEncountered = true;
    }
    else if (wildCardType == XMLAttDef::Any_List) {
        ValueVectorOf<unsigned int>* nameURIList = attWildCard->getNamespaceList();
        unsigned int listSize = (nameURIList) ? nameURIList->size() : 0;

        if (listSize) {
            for (unsigned int i=0; i < listSize; i++) {
                if (nameURIList->elementAt(i) == uriId)
                    anyEncountered = true;
            }
        }
    }

    if (anyEncountered) {
        XMLAttDef::DefAttTypes   defType   = attWildCard->getDefaultType();
        if (defType == XMLAttDef::ProcessContents_Skip) {
            // attribute should just be bypassed,
            skipThisOne = true;
            attWildCard->setValidationAttempted(PSVIDefs::NONE);
        }
        else if (defType == XMLAttDef::ProcessContents_Lax) {
            laxThisOne = true;
        }
    }

    return anyEncountered;
}

void SGXMLScanner::normalizeURI(const XMLCh* const systemURI,
                                XMLBuffer& normalizedURI)
{
    const XMLCh* pszSrc = systemURI;

    normalizedURI.reset();

    while (*pszSrc) {

        if ((*(pszSrc) == chPercent)
        &&  (*(pszSrc+1) == chDigit_2)
        &&  (*(pszSrc+2) == chDigit_0))
        {
            pszSrc += 3;
            normalizedURI.append(chSpace);
        }
        else if (*pszSrc == 0xFFFF) { //escaped character
            pszSrc++;
        }
        else {
            normalizedURI.append(*pszSrc);
            pszSrc++;
        }
    }
}

inline XMLAttDefList& getAttDefList(ComplexTypeInfo* currType, XMLElementDecl* elemDecl)
{
    if (currType)
        return currType->getAttDefList();
    else
        return elemDecl->getAttDefList();
}

XERCES_CPP_NAMESPACE_END