Newer
Older
// Put a janitor on the source so it gets cleaned up on exit
Janitor<InputSource> janSrc(srcUsed);
// If the creation failed, and its not because the source was empty,
// then emit an error and return.
if (!reader)
David Abram Cargill
committed
ThrowXMLwithMemMgr1(RuntimeException, XMLExcepts::Gen_CouldNotOpenExtEntity, srcUsed->getSystemId(), fMemoryManager);
// Push the reader. If its a recursive expansion, then emit an error
// and return an failure.
if (!fReaderMgr.pushReader(reader, decl))
{
emitError(XMLErrs::RecursiveEntity, decl->getName());
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];
David Abram Cargill
committed
XMLString::binToText(fEntityExpansionLimit, expLimStr, 15, 10, fMemoryManager);
emitError
(
XMLErrs::EntityExpansionLimitExceeded
, expLimStr
);
// there seems nothing better to be done than to reset the entity expansion counter
fEntityExpansionCount = 0;
}
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
// Do a start entity reference event.
//
// <TBD> For now, we supress them in att values. Later, when
// the stuff is in place to correctly allow DOM to handle them
// we'll turn this back on.
if (fDocHandler && !inAttVal)
fDocHandler->startEntityReference(*decl);
// If it starts with the XML string, then parse a text decl
if (checkXMLDecl(true))
scanXMLDecl(Decl_Text);
}
else
{
// If its one of the special char references, then we can return
// it as a character, and its considered escaped.
if (decl->getIsSpecialChar())
{
firstCh = decl->getValue()[0];
escaped = true;
return EntityExp_Returned;
}
// Create a reader over a memory stream over the entity value
// We force it to assume UTF-16 by passing in an encoding
// string. This way it won't both trying to predecode the
// first line, looking for an XML/TextDecl.
XMLReader* valueReader = fReaderMgr.createIntEntReader
(
decl->getName()
, XMLReader::RefFrom_NonLiteral
, XMLReader::Type_General
, decl->getValue()
, decl->getValueLen()
, false
);
// Try to push the entity reader onto the reader manager stack,
// where it will become the subsequent input. If it fails, that
// means the entity is recursive, so issue an error. The reader
// will have just been discarded, but we just keep going.
if (!fReaderMgr.pushReader(valueReader, decl))
emitError(XMLErrs::RecursiveEntity, decl->getName());
// 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];
David Abram Cargill
committed
XMLString::binToText(fEntityExpansionLimit, expLimStr, 15, 10, fMemoryManager);
emitError
(
XMLErrs::EntityExpansionLimitExceeded
, expLimStr
);
}
// Do a start entity reference event.
//
// <TBD> For now, we supress them in att values. Later, when
// the stuff is in place to correctly allow DOM to handle them
// we'll turn this back on.
if (fDocHandler && !inAttVal)
fDocHandler->startEntityReference(*decl);
// If it starts with the XML string, then it's an error
if (checkXMLDecl(true)) {
emitError(XMLErrs::TextDeclNotLegalHere);
fReaderMgr.skipPastChar(chCloseAngle);
}
}
return EntityExp_Pushed;
}
bool IGXMLScanner::switchGrammar(const XMLCh* const newGrammarNameSpace)
{
Grammar* tempGrammar = fGrammarResolver->getGrammar(newGrammarNameSpace);
if (!tempGrammar) {
// This is a case where namespaces is on with a DTD grammar.
tempGrammar = fDTDGrammar;
}
Gareth Reakes
committed
if (!tempGrammar) {
Gareth Reakes
committed
}
Gareth Reakes
committed
fGrammar = tempGrammar;
fGrammarType = fGrammar->getGrammarType();
if (fGrammarType == Grammar::SchemaGrammarType && !fValidator->handlesSchema()) {
if (fValidatorFromUser)
David Abram Cargill
committed
ThrowXMLwithMemMgr(RuntimeException, XMLExcepts::Gen_NoSchemaValidator, fMemoryManager);
else {
fValidator = fSchemaValidator;
}
}
else if (fGrammarType == Grammar::DTDGrammarType && !fValidator->handlesDTD()) {
if (fValidatorFromUser)
David Abram Cargill
committed
ThrowXMLwithMemMgr(RuntimeException, XMLExcepts::Gen_NoDTDValidator, fMemoryManager);
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
else {
fValidator = fDTDValidator;
}
}
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 IGXMLScanner::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 IGXMLScanner::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)
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
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;
}
else if (defType == XMLAttDef::ProcessContents_Lax) {
laxThisOne = true;
}
}
return anyEncountered;
}
inline XMLAttDefList& getAttDefList(bool isSchemaGrammar
, ComplexTypeInfo* currType
, XMLElementDecl* elemDecl)
{
if (isSchemaGrammar && currType)
return currType->getAttDefList();
else
return elemDecl->getAttDefList();
}