Newer
Older
tempElement = topElem->fThisElement;
elemName = (XMLCh *)tempElement->getFullName();
}
if (!fReaderMgr.skippedString(elemName))
XMLErrs::ExpectedEndOfTagX
, elemName
fReaderMgr.skipPastChar(chCloseAngle);
return;
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
}
// See if it was the root element, to avoid multiple calls below
const bool isRoot = fElemStack.isEmpty();
// Make sure we are back on the same reader as where we started
if (topElem->fReaderNum != fReaderMgr.getCurrentReaderNum())
emitError(XMLErrs::PartialTagMarkupError);
// Skip optional whitespace
fReaderMgr.skipPastSpaces();
// Make sure we find the closing bracket
if (!fReaderMgr.skippedChar(chCloseAngle))
{
emitError
(
XMLErrs::UnterminatedEndTag
, topElem->fThisElement->getFullName()
);
}
if (fGrammarType == Grammar::SchemaGrammarType)
// reset error occurred
fPSVIElemContext.fErrorOccurred = fErrorStack->pop();
if (fValidate && topElem->fThisElement->isDeclared())
{
fPSVIElemContext.fCurrentTypeInfo = ((SchemaValidator*) fValidator)->getCurrentTypeInfo();
if(!fPSVIElemContext.fCurrentTypeInfo)
fPSVIElemContext.fCurrentDV = ((SchemaValidator*) fValidator)->getCurrentDatatypeValidator();
else
fPSVIElemContext.fCurrentDV = 0;
if(fPSVIHandler)
{
fPSVIElemContext.fNormalizedValue = ((SchemaValidator*) fValidator)->getNormalizedValue();
if (XMLString::equals(fPSVIElemContext.fNormalizedValue, XMLUni::fgZeroLenString))
fPSVIElemContext.fNormalizedValue = 0;
}
}
else
{
fPSVIElemContext.fCurrentDV = 0;
fPSVIElemContext.fCurrentTypeInfo = 0;
fPSVIElemContext.fNormalizedValue = 0;
// If validation is enabled, then lets pass him the list of children and
// this element and let him validate it.
PeiYong Zhang
committed
//
// XML1.0-3rd
// Validity Constraint:
// The declaration matches EMPTY and the element has no content (not even
// entity references, comments, PIs or white space).
//
if ( (fGrammarType == Grammar::DTDGrammarType) &&
(topElem->fCommentOrPISeen) &&
(((DTDElementDecl*) topElem->fThisElement)->getModelType() == DTDElementDecl::Empty))
{
fValidator->emitError
(
XMLValid::EmptyElemHasContent
, topElem->fThisElement->getFullName()
);
}
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
//
// XML1.0-3rd
// Validity Constraint:
//
// The declaration matches children and the sequence of child elements
// belongs to the language generated by the regular expression in the
// content model, with optional white space, comments and PIs
// (i.e. markup matching production [27] Misc) between the start-tag and
// the first child element, between child elements, or between the last
// child element and the end-tag.
//
// Note that
// a CDATA section containing only white space or
// a reference to an entity whose replacement text is character references
// expanding to white space do not match the nonterminal S, and hence
// cannot appear in these positions; however,
// a reference to an internal entity with a literal value consisting
// of character references expanding to white space does match S,
// since its replacement text is the white space resulting from expansion
// of the character references.
//
if ( (fGrammarType == Grammar::DTDGrammarType) &&
(topElem->fReferenceEscaped) &&
(((DTDElementDecl*) topElem->fThisElement)->getModelType() == DTDElementDecl::Children))
{
fValidator->emitError
(
XMLValid::ElemChildrenHasInvalidWS
, topElem->fThisElement->getFullName()
);
}
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
int res = fValidator->checkContent
(
topElem->fThisElement
, topElem->fChildren
, topElem->fChildCount
);
if (res >= 0)
{
// One of the elements is not valid for the content. NOTE that
// if no children were provided but the content model requires
// them, it comes back with a zero value. But we cannot use that
// to index the child array in this case, and have to put out a
// special message.
if (!topElem->fChildCount)
{
fValidator->emitError
(
XMLValid::EmptyNotValidForContent
, topElem->fThisElement->getFormattedContentModel()
);
}
else if ((unsigned int)res >= topElem->fChildCount)
{
fValidator->emitError
(
XMLValid::NotEnoughElemsForCM
, topElem->fThisElement->getFormattedContentModel()
);
}
else
{
fValidator->emitError
(
XMLValid::ElementNotValidForContent
, topElem->fChildren[res]->getRawName()
, topElem->fThisElement->getFormattedContentModel()
);
}
}
Gareth Reakes
committed
if (fGrammarType == Grammar::SchemaGrammarType) {
if (((SchemaValidator*) fValidator)->getErrorOccurred())
fPSVIElemContext.fErrorOccurred = true;
else if (fPSVIElemContext.fCurrentDV && fPSVIElemContext.fCurrentDV->getType() == DatatypeValidator::Union)
psviMemberType = fValidationContext->getValidatingMemberType();
if (fPSVIHandler)
{
fPSVIElemContext.fIsSpecified = ((SchemaValidator*) fValidator)->getIsElemSpecified();
if(fPSVIElemContext.fIsSpecified)
fPSVIElemContext.fNormalizedValue = ((SchemaElementDecl *)topElem->fThisElement)->getDefaultValue();
if (toCheckIdentityConstraint())
{
fICHandler->deactivateContext
(
(SchemaElementDecl *) topElem->fThisElement
, fContent.getRawBuffer()
);
if (fGrammarType == Grammar::SchemaGrammarType)
{
if(!isRoot)
((SchemaElementDecl *)fElemStack.topElement()->fThisElement)->updateValidityFromElement(topElem->fThisElement, fGrammarType);
if (fPSVIHandler)
{
endElementPSVI(
(SchemaElementDecl*)topElem->fThisElement, psviMemberType);
}
Neil Graham
committed
// now we can reset the datatype buffer, since the
// application has had a chance to copy the characters somewhere else
((SchemaValidator *)fValidator)->clearDatatypeBuffer();
// If we have a doc handler, tell it about the end tag
if (fDocHandler)
{
fDocHandler->endElement
(
*topElem->fThisElement
, uriId
, isRoot
, fPrefixBuf.getRawBuffer()
);
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
// pass information about type info:
if(fGrammarType == Grammar::SchemaGrammarType)
{
const XMLCh *typeName = SchemaSymbols::fgATTVAL_ANYTYPE;
const XMLCh *typeURI = SchemaSymbols::fgURI_SCHEMAFORSCHEMA;
if(!fPSVIElemContext.fErrorOccurred)
{
if(fPSVIElemContext.fCurrentTypeInfo != 0)
{
if(fPSVIElemContext.fCurrentTypeInfo->getAnonymous())
typeName = XMLUni::fgZeroLenString;
else
typeName = fPSVIElemContext.fCurrentTypeInfo->getTypeLocalName();
typeURI = fPSVIElemContext.fCurrentTypeInfo->getTypeUri();
}
else
{
DatatypeValidator *actualDV = (psviMemberType)?psviMemberType:fPSVIElemContext.fCurrentDV;
if(actualDV)
{
if(actualDV->getAnonymous())
typeName = XMLUni::fgZeroLenString;
else
typeName = actualDV->getTypeLocalName();
typeURI = actualDV->getTypeUri();
}
}
}
else
{
// idiosyncratically, if there's an
// error but this element was simpleType-validated,
// the tests demand anySimpleType be returned
if(fPSVIElemContext.fCurrentDV)
typeName = SchemaSymbols::fgDT_ANYSIMPLETYPE;
}
fDocHandler->elementTypeInfo(typeName, typeURI);
}
else
{
Alberto Massari
committed
fDocHandler->elementTypeInfo(0, 0);
Gareth Reakes
committed
// reset xsi:type ComplexTypeInfo
if (fGrammarType == Grammar::SchemaGrammarType) {
Gareth Reakes
committed
((SchemaElementDecl*)topElem->fThisElement)->reset();
if (!isRoot)
Gareth Reakes
committed
((SchemaElementDecl*)(fElemStack.topElement()->fThisElement))->
setXsiComplexTypeInfo(((SchemaValidator*)fValidator)->getCurrentTypeInfo());
// update error information
fErrorStack->push(fErrorStack->pop() || fPSVIElemContext.fErrorOccurred);
}
Gareth Reakes
committed
}
// If this was the root, then done with content
gotData = !isRoot;
if (gotData) {
if (fDoNamespaces) {
// Restore the grammar
fGrammar = fElemStack.getCurrentGrammar();
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);
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
else {
fValidator = fDTDValidator;
}
}
fValidator->setGrammar(fGrammar);
}
// Restore the validation flag
fValidate = fElemStack.getValidationFlag();
}
}
// This method handles the high level logic of scanning the DOCType
// declaration. This calls the DTDScanner and kicks off both the scanning of
// the internal subset and the scanning of the external subset, if any.
//
// When we get here the '<!DOCTYPE' part has already been scanned, which is
// what told us that we had a doc type decl to parse.
void IGXMLScanner::scanDocTypeDecl()
{
// We have a doc type. So, switch the Grammar.
switchGrammar(XMLUni::fgDTDEntityString);
if (fDocTypeHandler)
fDocTypeHandler->resetDocType();
// There must be some space after DOCTYPE
if (!fReaderMgr.skipPastSpaces())
{
emitError(XMLErrs::ExpectedWhitespace);
// Just skip the Doctype declaration and return
fReaderMgr.skipPastChar(chCloseAngle);
return;
}
// Get a buffer for the root element
XMLBufBid bbRootName(&fBufMgr);
// Get a name from the input, which should be the name of the root
// element of the upcoming content.
fReaderMgr.getName(bbRootName.getBuffer());
if (bbRootName.isEmpty())
{
emitError(XMLErrs::NoRootElemInDOCTYPE);
fReaderMgr.skipPastChar(chCloseAngle);
return;
}
// Store the root element name for later check
setRootElemName(bbRootName.getRawBuffer());
// This element obviously is not going to exist in the element decl
// pool yet, but we need to call docTypeDecl. So force it into
// the element decl pool, marked as being there because it was in
// the DOCTYPE. Later, when its declared, the status will be updated.
//
// Only do this if we are not reusing the validator! If we are reusing,
// then look it up instead. It has to exist!
DTDElementDecl* rootDecl = new (fGrammarPoolMemoryManager) DTDElementDecl
(
bbRootName.getRawBuffer()
, fEmptyNamespaceId
, DTDElementDecl::Any
, fGrammarPoolMemoryManager
Neil Graham
committed
);
Janitor<DTDElementDecl> rootDeclJanitor(rootDecl);
rootDecl->setCreateReason(DTDElementDecl::AsRootElem);
rootDecl->setExternalElemDeclaration(true);
Neil Graham
committed
if(!fUseCachedGrammar)
{
// this will break getRootElemId on DTDGrammar when
// cached grammars are in use, but
// why would one use this anyway???
((DTDGrammar*)fGrammar)->setRootElemId(fGrammar->putElemDecl(rootDecl));
rootDeclJanitor.release();
Neil Graham
committed
} else
{
// attach this to the undeclared element pool so that it gets deleted
XMLElementDecl* elemDecl = fDTDElemNonDeclPool->getByKey(bbRootName.getRawBuffer());
if (elemDecl)
{
rootDecl->setId(elemDecl->getId());
}
else
{
rootDecl->setId(fDTDElemNonDeclPool->put((DTDElementDecl*)rootDecl));
rootDeclJanitor.release();
Neil Graham
committed
}
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
// Skip any spaces after the name
fReaderMgr.skipPastSpaces();
// And now if we are looking at a >, then we are done. It is not
// required to have an internal or external subset, though why you
// would not escapes me.
if (fReaderMgr.skippedChar(chCloseAngle)) {
// If we have a doc type handler and advanced callbacks are enabled,
// call the doctype event.
if (fDocTypeHandler)
fDocTypeHandler->doctypeDecl(*rootDecl, 0, 0, false);
return;
}
// either internal/external subset
if (fValScheme == Val_Auto && !fValidate)
fValidate = true;
bool hasIntSubset = false;
bool hasExtSubset = false;
XMLCh* sysId = 0;
XMLCh* pubId = 0;
DTDScanner dtdScanner
(
(DTDGrammar*) fGrammar
, fDocTypeHandler
, fGrammarPoolMemoryManager
, fMemoryManager
);
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
dtdScanner.setScannerInfo(this, &fReaderMgr, &fBufMgr);
// If the next character is '[' then we have no external subset cause
// there is no system id, just the opening character of the internal
// subset. Else, has to be an id.
//
// Just look at the next char, don't eat it.
if (fReaderMgr.peekNextChar() == chOpenSquare)
{
hasIntSubset = true;
}
else
{
// Indicate we have an external subset
hasExtSubset = true;
fHasNoDTD = false;
// Get buffers for the ids
XMLBufBid bbPubId(&fBufMgr);
XMLBufBid bbSysId(&fBufMgr);
// Get the external subset id
if (!dtdScanner.scanId(bbPubId.getBuffer(), bbSysId.getBuffer(), DTDScanner::IDType_External))
{
fReaderMgr.skipPastChar(chCloseAngle);
return;
}
// Get copies of the ids we got
pubId = XMLString::replicate(bbPubId.getRawBuffer(), fMemoryManager);
sysId = XMLString::replicate(bbSysId.getRawBuffer(), fMemoryManager);
// Skip spaces and check again for the opening of an internal subset
fReaderMgr.skipPastSpaces();
// Just look at the next char, don't eat it.
if (fReaderMgr.peekNextChar() == chOpenSquare) {
hasIntSubset = true;
}
}
// Insure that the ids get cleaned up, if they got allocated
ArrayJanitor<XMLCh> janSysId(sysId, fMemoryManager);
ArrayJanitor<XMLCh> janPubId(pubId, fMemoryManager);
// If we have a doc type handler and advanced callbacks are enabled,
// call the doctype event.
if (fDocTypeHandler)
fDocTypeHandler->doctypeDecl(*rootDecl, pubId, sysId, hasIntSubset, hasExtSubset);
// Ok, if we had an internal subset, we are just past the [ character
// and need to parse that first.
if (hasIntSubset)
{
// Eat the opening square bracket
fReaderMgr.getNextChar();
checkInternalDTD(hasExtSubset, sysId);
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
// And try to scan the internal subset. If we fail, try to recover
// by skipping forward tot he close angle and returning.
if (!dtdScanner.scanInternalSubset())
{
fReaderMgr.skipPastChar(chCloseAngle);
return;
}
// Do a sanity check that some expanded PE did not propogate out of
// the doctype. This could happen if it was terminated early by bad
// syntax.
if (fReaderMgr.getReaderDepth() > 1)
{
emitError(XMLErrs::PEPropogated);
// Ask the reader manager to pop back down to the main level
fReaderMgr.cleanStackBackTo(1);
}
fReaderMgr.skipPastSpaces();
}
// And that should leave us at the closing > of the DOCTYPE line
if (!fReaderMgr.skippedChar(chCloseAngle))
{
// Do a special check for the common scenario of an extra ] char at
// the end. This is easy to recover from.
if (fReaderMgr.skippedChar(chCloseSquare)
&& fReaderMgr.skippedChar(chCloseAngle))
{
emitError(XMLErrs::ExtraCloseSquare);
}
else
{
emitError(XMLErrs::UnterminatedDOCTYPE);
fReaderMgr.skipPastChar(chCloseAngle);
}
}
// If we had an external subset, then we need to deal with that one
// next. If we are reusing the validator, then don't scan it.
if (hasExtSubset) {
if (fUseCachedGrammar)
{
InputSource* sysIdSrc = resolveSystemId(sysId);
Janitor<InputSource> janSysIdSrc(sysIdSrc);
Grammar* grammar = fGrammarResolver->getGrammar(sysIdSrc->getSystemId());
if (grammar && grammar->getGrammarType() == Grammar::DTDGrammarType) {
fDTDGrammar = (DTDGrammar*) grammar;
fGrammar = fDTDGrammar;
fValidator->setGrammar(fGrammar);
Neil Graham
committed
// should not be modifying cached grammars!
/********
rootDecl = (DTDElementDecl*) fGrammar->getElemDecl(fEmptyNamespaceId, 0, bbRootName.getRawBuffer(), Grammar::TOP_LEVEL_SCOPE);
if (rootDecl)
((DTDGrammar*)fGrammar)->setRootElemId(rootDecl->getId());
else {
rootDecl = new (fGrammarPoolMemoryManager) DTDElementDecl
(
bbRootName.getRawBuffer()
, fEmptyNamespaceId
, DTDElementDecl::Any
, fGrammarPoolMemoryManager
rootDecl->setCreateReason(DTDElementDecl::AsRootElem);
rootDecl->setExternalElemDeclaration(true);
((DTDGrammar*)fGrammar)->setRootElemId(fGrammar->putElemDecl(rootDecl));
}
Neil Graham
committed
********/
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
return;
}
}
if (fLoadExternalDTD || fValidate)
{
// And now create a reader to read this entity
InputSource* srcUsed;
XMLReader* reader = fReaderMgr.createReader
(
sysId
, pubId
, false
, XMLReader::RefFrom_NonLiteral
, XMLReader::Type_General
, XMLReader::Source_External
, srcUsed
, fCalculateSrcOfs
);
// Put a janitor on the input source
Janitor<InputSource> janSrc(srcUsed);
// If it failed then throw an exception
if (!reader)
David Abram Cargill
committed
ThrowXMLwithMemMgr1(RuntimeException, XMLExcepts::Gen_CouldNotOpenDTD, srcUsed->getSystemId(), fMemoryManager);
if (fToCacheGrammar) {
unsigned int stringId = fGrammarResolver->getStringPool()->addOrFind(srcUsed->getSystemId());
const XMLCh* sysIdStr = fGrammarResolver->getStringPool()->getValueForId(stringId);
fGrammarResolver->orphanGrammar(XMLUni::fgDTDEntityString);
((XMLDTDDescription*) (fGrammar->getGrammarDescription()))->setSystemId(sysIdStr);
fGrammarResolver->putGrammar(fGrammar);
}
// In order to make the processing work consistently, we have to
// make this look like an external entity. So create an entity
// decl and fill it in and push it with the reader, as happens
// with an external entity. Put a janitor on it to insure it gets
// cleaned up. The reader manager does not adopt them.
const XMLCh gDTDStr[] = { chLatin_D, chLatin_T, chLatin_D , chNull };
DTDEntityDecl* declDTD = new (fGrammarPoolMemoryManager) DTDEntityDecl(gDTDStr, false, fGrammarPoolMemoryManager);
declDTD->setSystemId(sysId);
Janitor<DTDEntityDecl> janDecl(declDTD);
// Mark this one as a throw at end
reader->setThrowAtEnd(true);
// And push it onto the stack, with its pseudo name
fReaderMgr.pushReader(reader, declDTD);
// Tell it its not in an include section
dtdScanner.scanExtSubsetDecl(false, true);
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
}
}
}
bool IGXMLScanner::scanStartTag(bool& gotData)
{
// Assume we will still have data until proven otherwise. It will only
// ever be false if this is the root and its empty.
gotData = true;
// Get the QName. In this case, we are not doing namespaces, so we just
// use it as is and don't have to break it into parts.
if (!fReaderMgr.getName(fQNameBuf))
{
emitError(XMLErrs::ExpectedElementName);
fReaderMgr.skipToChar(chOpenAngle);
return false;
}
// Assume it won't be an empty tag
bool isEmpty = false;
// Lets try to look up the element in the validator's element decl pool
// We can pass bogus values for the URI id and the base name. We know that
// this can only be called if we are doing a DTD style validator and that
// he will only look at the QName.
//
// We tell him to fault in a decl if he does not find one.
Neil Graham
committed
// Actually, we *don't* tell him to fault in a decl if he does not find one- NG
Neil Graham
committed
const XMLCh *rawQName = fQNameBuf.getRawBuffer();
XMLElementDecl* elemDecl = fGrammar->getElemDecl
Neil Graham
committed
, rawQName
Neil Graham
committed
// look for it in the undeclared pool:
if(!elemDecl)
{
elemDecl = fDTDElemNonDeclPool->getByKey(rawQName);
}
if(!elemDecl)
{
// we're assuming this must be a DTD element. DTD's can be
// used with or without namespaces, but schemas cannot be used without
// namespaces.
wasAdded = true;
elemDecl = new (fMemoryManager) DTDElementDecl
(
rawQName
, fEmptyNamespaceId
, DTDElementDecl::Any
, fMemoryManager
);
elemDecl->setId(fDTDElemNonDeclPool->put((DTDElementDecl*)elemDecl));
}
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
// We do something different here according to whether we found the
// element or not.
if (wasAdded)
{
// If validating then emit an error
if (fValidate)
{
// This is to tell the reuse Validator that this element was
// faulted-in, was not an element in the validator pool originally
elemDecl->setCreateReason(XMLElementDecl::JustFaultIn);
fValidator->emitError
(
XMLValid::ElementNotDefined
, elemDecl->getFullName()
);
}
}
else
{
// If its not marked declared and validating, then emit an error
if (fValidate && !elemDecl->isDeclared())
{
fValidator->emitError
(
XMLValid::ElementNotDefined
, elemDecl->getFullName()
);
}
}
// See if its the root element
const bool isRoot = fElemStack.isEmpty();
// Expand the element stack and add the new element
fElemStack.addLevel(elemDecl, fReaderMgr.getCurrentReaderNum());
fElemStack.setValidationFlag(fValidate);
// Validate the element
if (fValidate)
fValidator->validateElement(elemDecl);
// If this is the first element and we are validating, check the root
// element.
if (isRoot)
{
fRootGrammar = fGrammar;
if (fValidate)
{
// If a DocType exists, then check if it matches the root name there.
if (fRootElemName && !XMLString::equals(fQNameBuf.getRawBuffer(), fRootElemName))
fValidator->emitError(XMLValid::RootElemNotLikeDocType);
// Some validators may also want to check the root, call the
// XMLValidator::checkRootElement
if (fValidatorFromUser && !fValidator->checkRootElement(elemDecl->getId()))
fValidator->emitError(XMLValid::RootElemNotLikeDocType);
}
}
else
{
// If the element stack is not empty, then add this element as a
// child of the previous top element. If its empty, this is the root
// elem and is not the child of anything.
fElemStack.addChild(elemDecl->getElementName(), true);
}
// Ask the element decl to clear out the 'provided' flag on all of its
// att defs.
elemDecl->resetDefs();
// Skip any whitespace after the name
fReaderMgr.skipPastSpaces();
// We loop until we either see a /> or >, handling attribute/value
// pairs until we get there.
unsigned int attCount = 0;
unsigned int curAttListSize = fAttrList->size();
wasAdded = false;
Alberto Massari
committed
fElemCount++;
while (true)
{
// And get the next non-space character
XMLCh nextCh = fReaderMgr.peekNextChar();
// If the next character is not a slash or closed angle bracket,
// then it must be whitespace, since whitespace is required
// between the end of the last attribute and the name of the next
// one.
if (attCount)
{
if ((nextCh != chForwardSlash) && (nextCh != chCloseAngle))
{
{
// Ok, skip by them and peek another char
fReaderMgr.skipPastSpaces();
nextCh = fReaderMgr.peekNextChar();
}
else
{
// Emit the error but keep on going
emitError(XMLErrs::ExpectedWhitespace);
}
}
}
// Ok, here we first check for any of the special case characters.
// If its not one, then we do the normal case processing, which
// assumes that we've hit an attribute value, Otherwise, we do all
// the special case checks.
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
{
// Assume its going to be an attribute, so get a name from
// the input.
if (!fReaderMgr.getName(fAttNameBuf))
{
emitError(XMLErrs::ExpectedAttrName);
fReaderMgr.skipPastChar(chCloseAngle);
return false;
}
// And next must be an equal sign
if (!scanEq())
{
static const XMLCh tmpList[] =
{
chSingleQuote, chDoubleQuote, chCloseAngle
, chOpenAngle, chForwardSlash, chNull
};
emitError(XMLErrs::ExpectedEqSign);
// Try to sync back up by skipping forward until we either
// hit something meaningful.
const XMLCh chFound = fReaderMgr.skipUntilInOrWS(tmpList);
if ((chFound == chCloseAngle) || (chFound == chForwardSlash))
{
// Jump back to top for normal processing of these
continue;
}
else if ((chFound == chSingleQuote)
|| (chFound == chDoubleQuote)
{
// Just fall through assuming that the value is to follow
}
else if (chFound == chOpenAngle)
{
// Assume a malformed tag and that new one is starting
emitError(XMLErrs::UnterminatedStartTag, elemDecl->getFullName());
return false;
}
else
{
// Something went really wrong
return false;
}
}
// See if this attribute is declared for this element. If we are
// not validating of course it will not be at first, but we will
// fault it into the pool (to avoid lots of redundant errors.)
XMLCh * namePtr = fAttNameBuf.getRawBuffer();
XMLAttDef* attDef = ((DTDElementDecl *)elemDecl)->getAttDef(namePtr);
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
// Add this attribute to the attribute list that we use to
// pass them to the handler. We reuse its existing elements
// but expand it as required.
// Note that we want to this first since this will
// make a copy of the namePtr; we can then make use of
// that copy in the hashtable lookup that checks
// for duplicates. This will mean we may have to update
// the type of the XMLAttr later.
XMLAttr* curAtt;
if (attCount >= curAttListSize)
{
curAtt = new (fMemoryManager) XMLAttr
(
-1
, namePtr
, XMLUni::fgZeroLenString
, XMLUni::fgZeroLenString
, (attDef)?attDef->getType():XMLAttDef::CData
, true
, fMemoryManager
);
fAttrList->addElement(curAtt);
}
else
{
curAtt = fAttrList->elementAt(attCount);
curAtt->set
(
-1
, namePtr
, XMLUni::fgZeroLenString
, XMLUni::fgZeroLenString
, (attDef)?attDef->getType():XMLAttDef::CData
);
curAtt->setSpecified(true);
}
// reset namePtr so it refers to newly-allocated memory
namePtr = (XMLCh *)curAtt->getName();
if (!attDef)
{
// If there is a validation handler, then we are validating
// so emit an error.
if (fValidate)
fValidator->emitError
(
XMLValid::AttNotDefinedForElement
, fAttNameBuf.getRawBuffer()
, elemDecl->getFullName()
);
}
unsigned int *curCountPtr = fUndeclaredAttrRegistry->get(namePtr);
if(!curCountPtr)
{
curCountPtr = getNewUIntPtr();
*curCountPtr = fElemCount;
fUndeclaredAttrRegistry->put((void *)namePtr, curCountPtr);
}
else if(*curCountPtr < fElemCount)
*curCountPtr = fElemCount;
else
{
emitError
(
XMLErrs::AttrAlreadyUsedInSTag
, namePtr
, elemDecl->getFullName()
);
}
// prepare for duplicate detection
unsigned int *curCountPtr = fAttDefRegistry->get(attDef);
if(!curCountPtr)
curCountPtr = getNewUIntPtr();
*curCountPtr = fElemCount;
fAttDefRegistry->put(attDef, curCountPtr);
}
else if(*curCountPtr < fElemCount)
*curCountPtr = fElemCount;
else
{
emitError
(
XMLErrs::AttrAlreadyUsedInSTag
, attDef->getFullName()
// Skip any whitespace before the value and then scan the att
// value. This will come back normalized with entity refs and
// char refs expanded.
fReaderMgr.skipPastSpaces();
if (!scanAttValue(attDef, namePtr, fAttValueBuf))
{
static const XMLCh tmpList[] =
{
chCloseAngle, chOpenAngle, chForwardSlash, chNull
};
emitError(XMLErrs::ExpectedAttrValue);
// It failed, so lets try to get synced back up. We skip
// forward until we find some whitespace or one of the
// chars in our list.
const XMLCh chFound = fReaderMgr.skipUntilInOrWS(tmpList);
if ((chFound == chCloseAngle)
|| (chFound == chForwardSlash)
{
// Just fall through and process this attribute, though
// the value will be "".
}
else if (chFound == chOpenAngle)
{
// Assume a malformed tag and that new one is starting
emitError(XMLErrs::UnterminatedStartTag, elemDecl->getFullName());
return false;
}
else
{
// Something went really wrong
return false;
}
}
// must set the newly-minted value on the XMLAttr:
curAtt->setValue(fAttValueBuf.getRawBuffer());
// Now that its all stretched out, lets look at its type and
// determine if it has a valid value. It will output any needed
// errors, but we just keep going. We only need to do this if
// we are validating.
if (attDef)
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
{
// Let the validator pass judgement on the attribute value
if (fValidate)
{
fValidator->validateAttrValue
(
attDef
, fAttValueBuf.getRawBuffer()
, false
, elemDecl
);
}
}
attCount++;
// And jump back to the top of the loop
continue;
}
// It was some special case character so do all of the checks and
// deal with it.
if (!nextCh)
David Abram Cargill
committed
ThrowXMLwithMemMgr(UnexpectedEOFException, XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
{
fReaderMgr.getNextChar();
isEmpty = true;
if (!fReaderMgr.skippedChar(chCloseAngle))
emitError(XMLErrs::UnterminatedStartTag, elemDecl->getFullName());
break;
}
else if (nextCh == chCloseAngle)
{
fReaderMgr.getNextChar();
break;
}