Newer
Older
* Copyright 1999-2002,2004 The Apache Software Foundation.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
// ---------------------------------------------------------------------------
// Includes
// ---------------------------------------------------------------------------
#include <xercesc/internal/ValidationContextImpl.hpp>
#include <xercesc/util/Janitor.hpp>
#include <xercesc/util/Mutexes.hpp>
#include <xercesc/util/RuntimeException.hpp>
#include <xercesc/util/UnexpectedEOFException.hpp>
#include <xercesc/util/XMLMsgLoader.hpp>
#include <xercesc/util/XMLRegisterCleanup.hpp>
#include <xercesc/util/XMLInitializer.hpp>
#include <xercesc/framework/LocalFileInputSource.hpp>
#include <xercesc/framework/URLInputSource.hpp>
#include <xercesc/framework/XMLDocumentHandler.hpp>
#include <xercesc/framework/XMLEntityHandler.hpp>
#include <xercesc/framework/XMLPScanToken.hpp>
#include <xercesc/framework/XMLValidator.hpp>
#include <xercesc/internal/EndOfEntityException.hpp>
#include <xercesc/validators/DTD/DocTypeHandler.hpp>
#include <xercesc/validators/common/GrammarResolver.hpp>
Neil Graham
committed
#include <xercesc/util/OutOfMemoryException.hpp>
#include <xercesc/util/XMLResourceIdentifier.hpp>
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
// ---------------------------------------------------------------------------
// Local static data
// ---------------------------------------------------------------------------
static XMLUInt32 gScannerId;
static bool sRegistered = false;
static XMLMutex* sScannerMutex = 0;
static XMLRegisterCleanup scannerMutexCleanup;
static XMLMsgLoader* gMsgLoader = 0;
static XMLRegisterCleanup cleanupMsgLoader;
// ---------------------------------------------------------------------------
// Local, static functions
// ---------------------------------------------------------------------------
// Cleanup for the message loader
void XMLScanner::reinitMsgLoader()
{
delete gMsgLoader;
gMsgLoader = 0;
}
// Cleanup for the scanner mutex
void XMLScanner::reinitScannerMutex()
{
delete sScannerMutex;
sScannerMutex = 0;
sRegistered = false;
}
//
// We need to fault in this mutex. But, since its used for synchronization
// itself, we have to do this the low level way using a compare and swap.
//
static XMLMutex& gScannerMutex()
{
Khaled Noaman
committed
if (!sRegistered)
Khaled Noaman
committed
XMLMutexLock lockInit(XMLPlatformUtils::fgAtomicMutex);
Khaled Noaman
committed
sScannerMutex = new XMLMutex;
scannerMutexCleanup.registerCleanup(XMLScanner::reinitScannerMutex);
sRegistered = true;
}
}
return *sScannerMutex;
}
static XMLMsgLoader& gScannerMsgLoader()
{
if (!gMsgLoader)
{
Khaled Noaman
committed
XMLMutexLock lockInit(&gScannerMutex());
// If we haven't loaded our message yet, then do that
Khaled Noaman
committed
{
gMsgLoader = XMLPlatformUtils::loadMsgSet(XMLUni::fgXMLErrDomain);
if (!gMsgLoader)
XMLPlatformUtils::panic(PanicHandler::Panic_CantLoadMsgDomain);
Khaled Noaman
committed
// Register this object to be cleaned up at termination
cleanupMsgLoader.registerCleanup(XMLScanner::reinitMsgLoader);
}
}
return *gMsgLoader;
}
void XMLInitializer::initializeScannerMsgLoader()
{
gMsgLoader = XMLPlatformUtils::loadMsgSet(XMLUni::fgXMLErrDomain);
// Register this object to be cleaned up at termination
if (gMsgLoader) {
cleanupMsgLoader.registerCleanup(XMLScanner::reinitMsgLoader);
}
sScannerMutex = new XMLMutex;
if (sScannerMutex) {
scannerMutexCleanup.registerCleanup(XMLScanner::reinitScannerMutex);
sRegistered = true;
}
}
// ---------------------------------------------------------------------------
// XMLScanner: Constructors and Destructor
// ---------------------------------------------------------------------------
XMLScanner::XMLScanner(XMLValidator* const valToAdopt,
GrammarResolver* const grammarResolver,
David Abram Cargill
committed
MemoryManager* const manager)
: fBufferSize(1024 * 1024)
, fStandardUriConformant(false)
David Abram Cargill
committed
, fCalculateSrcOfs(false)
, fExitOnFirstFatal(true)
, fValidationConstraintFatal(false)
, fInException(false)
, fStandalone(false)
, fHasNoDTD(true)
, fValidate(false)
, fValidatorFromUser(false)
, fDoSchema(false)
, fSchemaFullChecking(false)
, fToCacheGrammar(false)
, fUseCachedGrammar(false)
, fLoadExternalDTD(true)
, fNormalizeData(true)
David Abram Cargill
committed
, fGenerateSyntheticAnnotations(false)
, fValidateAnnotations(false)
, fIgnoreCachedDTD(false)
David Abram Cargill
committed
, fEntityExpansionLimit(0)
, fEntityExpansionCount(0)
, fEmptyNamespaceId(0)
, fUnknownNamespaceId(0)
, fXMLNamespaceId(0)
, fXMLNSNamespaceId(0)
, fSchemaNamespaceId(0)
David Abram Cargill
committed
, fUIntPool(0)
, fUIntPoolRow(0)
, fUIntPoolCol(0)
, fUIntPoolRowTotal(2)
, fScannerId(0)
, fSequenceId(0)
, fAttrList(0)
, fAttrDupChkRegistry(0)
, fDocHandler(0)
, fDocTypeHandler(0)
, fEntityHandler(0)
, fErrorReporter(0)
, fErrorHandler(0)
David Abram Cargill
committed
, fPSVIHandler(0)
, fValidationContext(0)
, fEntityDeclPoolRetrieved(false)
, fReaderMgr(manager)
, fGrammarResolver(grammarResolver)
, fGrammarPoolMemoryManager(grammarResolver->getGrammarPoolMemoryManager())
, fURIStringPool(0)
, fRootElemName(0)
, fExternalSchemaLocation(0)
David Abram Cargill
committed
, fExternalNoNamespaceSchemaLocation(0)
, fMemoryManager(manager)
, fBufMgr(manager)
, fAttNameBuf(1023, manager)
, fAttValueBuf(1023, manager)
, fCDataBuf(1023, manager)
, fQNameBuf(1023, manager)
, fPrefixBuf(1023, manager)
, fURIBuf(1023, manager)
Khaled Noaman
committed
, fWSNormalizeBuf(1023, manager)
David Abram Cargill
committed
, fElemStack(manager)
{
commonInit();
if (fValidator) {
fValidatorFromUser = true;
initValidator(fValidator);
}
}
XMLScanner::XMLScanner( XMLDocumentHandler* const docHandler
, DocTypeHandler* const docTypeHandler
, XMLEntityHandler* const entityHandler
, XMLErrorReporter* const errHandler
, XMLValidator* const valToAdopt
, GrammarResolver* const grammarResolver
David Abram Cargill
committed
, MemoryManager* const manager)
: fBufferSize(1024 * 1024)
, fStandardUriConformant(false)
David Abram Cargill
committed
, fCalculateSrcOfs(false)
, fExitOnFirstFatal(true)
, fValidationConstraintFatal(false)
, fInException(false)
, fStandalone(false)
, fHasNoDTD(true)
, fValidate(false)
, fValidatorFromUser(false)
, fDoSchema(false)
, fSchemaFullChecking(false)
, fToCacheGrammar(false)
, fUseCachedGrammar(false)
, fLoadExternalDTD(true)
, fNormalizeData(true)
David Abram Cargill
committed
, fGenerateSyntheticAnnotations(false)
, fValidateAnnotations(false)
, fIgnoreCachedDTD(false)
David Abram Cargill
committed
, fEntityExpansionLimit(0)
, fEntityExpansionCount(0)
, fEmptyNamespaceId(0)
, fUnknownNamespaceId(0)
, fXMLNamespaceId(0)
, fXMLNSNamespaceId(0)
, fSchemaNamespaceId(0)
David Abram Cargill
committed
, fUIntPool(0)
, fUIntPoolRow(0)
, fUIntPoolCol(0)
, fUIntPoolRowTotal(2)
, fScannerId(0)
, fSequenceId(0)
, fAttrList(0)
, fAttrDupChkRegistry(0)
, fDocHandler(docHandler)
, fDocTypeHandler(docTypeHandler)
, fEntityHandler(entityHandler)
, fErrorReporter(errHandler)
, fErrorHandler(0)
David Abram Cargill
committed
, fPSVIHandler(0)
, fValidationContext(0)
, fEntityDeclPoolRetrieved(false)
, fReaderMgr(manager)
, fGrammarResolver(grammarResolver)
, fGrammarPoolMemoryManager(grammarResolver->getGrammarPoolMemoryManager())
, fURIStringPool(0)
, fRootElemName(0)
, fExternalSchemaLocation(0)
David Abram Cargill
committed
, fExternalNoNamespaceSchemaLocation(0)
, fMemoryManager(manager)
, fBufMgr(manager)
, fAttNameBuf(1023, manager)
, fAttValueBuf(1023, manager)
, fCDataBuf(1023, manager)
, fQNameBuf(1023, manager)
, fPrefixBuf(1023, manager)
, fURIBuf(1023, manager)
Khaled Noaman
committed
, fWSNormalizeBuf(1023, manager)
{
commonInit();
if (valToAdopt){
fValidatorFromUser = true;
initValidator(fValidator);
}
}
XMLScanner::~XMLScanner()
{
delete fAttrList;
delete fAttrDupChkRegistry;
fMemoryManager->deallocate(fRootElemName);//delete [] fRootElemName;
fMemoryManager->deallocate(fExternalSchemaLocation);//delete [] fExternalSchemaLocation;
fMemoryManager->deallocate(fExternalNoNamespaceSchemaLocation);//delete [] fExternalNoNamespaceSchemaLocation;
// delete fUIntPool
for (unsigned int i=0; i<=fUIntPoolRow; i++)
{
fMemoryManager->deallocate(fUIntPool[i]);
}
fMemoryManager->deallocate(fUIntPool);
void XMLScanner::setValidator(XMLValidator* const valToAdopt)
{
if (fValidatorFromUser)
delete fValidator;
fValidator = valToAdopt;
fValidatorFromUser = true;
initValidator(fValidator);
}
// ---------------------------------------------------------------------------
// XMLScanner: Main entry point to scan a document
// ---------------------------------------------------------------------------
void XMLScanner::scanDocument( const XMLCh* const systemId)
{
// First we try to parse it as a URL. If that fails, we assume its
// a file and try it that way.
InputSource* srcToUse = 0;
try
{
// Create a temporary URL. Since this is the primary document,
// it has to be fully qualified. If not, then assume we are just
// mistaking a file for a URL.
XMLURL tmpURL(fMemoryManager);
if (XMLURL::parse(systemId, tmpURL)) {
if (tmpURL.isRelative()) {
if (!fStandardUriConformant)
srcToUse = new (fMemoryManager) LocalFileInputSource(systemId, fMemoryManager);
else {
David Abram Cargill
committed
// since this is the top of the try/catch, cannot call ThrowXMLwithMemMgr
// emit the error directly
David Abram Cargill
committed
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_NoProtocolPresent, fMemoryManager);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return;
}
}
else
{
if (fStandardUriConformant && tmpURL.hasInvalidChar()) {
David Abram Cargill
committed
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_MalformedURL, fMemoryManager);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return;
}
srcToUse = new (fMemoryManager) URLInputSource(tmpURL, fMemoryManager);
}
}
else {
if (!fStandardUriConformant)
Khaled Noaman
committed
srcToUse = new (fMemoryManager) LocalFileInputSource(systemId, fMemoryManager);
else {
David Abram Cargill
committed
// since this is the top of the try/catch, cannot call ThrowXMLwithMemMgr
// emit the error directly
// lazy bypass ... since all MalformedURLException are fatal, no need to check the type
David Abram Cargill
committed
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_MalformedURL, fMemoryManager);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return;
}
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
catch(const XMLException& excToCatch)
{
// For any other XMLException,
// emit the error and catch any user exception thrown from here.
fInException = true;
if (excToCatch.getErrorType() == XMLErrorReporter::ErrType_Warning)
emitError
(
XMLErrs::XMLException_Warning
, excToCatch.getType()
, excToCatch.getMessage()
);
else if (excToCatch.getErrorType() >= XMLErrorReporter::ErrType_Fatal)
emitError
(
XMLErrs::XMLException_Fatal
, excToCatch.getType()
, excToCatch.getMessage()
);
else
emitError
(
XMLErrs::XMLException_Error
, excToCatch.getType()
, excToCatch.getMessage()
);
return;
}
scanDocument(*srcToUse);
void XMLScanner::scanDocument( const char* const systemId)
{
// We just delegate this to the XMLCh version after transcoding
XMLCh* tmpBuf = XMLString::transcode(systemId, fMemoryManager);
ArrayJanitor<XMLCh> janBuf(tmpBuf, fMemoryManager);
scanDocument(tmpBuf);
}
// This method begins a progressive parse. It scans through the prolog and
// returns a token to be used on subsequent scanNext() calls. If the return
// value is true, then the token is legal and ready for further use. If it
// returns false, then the scan of the prolog failed and the token is not
// going to work on subsequent scanNext() calls.
bool XMLScanner::scanFirst( const XMLCh* const systemId
, XMLPScanToken& toFill)
{
// First we try to parse it as a URL. If that fails, we assume its
// a file and try it that way.
InputSource* srcToUse = 0;
try
{
// Create a temporary URL. Since this is the primary document,
// it has to be fully qualified. If not, then assume we are just
// mistaking a file for a URL.
David Abram Cargill
committed
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
XMLURL tmpURL(fMemoryManager);
if (XMLURL::parse(systemId, tmpURL)) {
if (tmpURL.isRelative()) {
if (!fStandardUriConformant)
srcToUse = new (fMemoryManager) LocalFileInputSource(systemId, fMemoryManager);
else {
// since this is the top of the try/catch, cannot call ThrowXMLwithMemMgr
// emit the error directly
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_NoProtocolPresent, fMemoryManager);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return false;
}
}
else
{
if (fStandardUriConformant && tmpURL.hasInvalidChar()) {
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_MalformedURL, fMemoryManager);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return false;
}
srcToUse = new (fMemoryManager) URLInputSource(tmpURL, fMemoryManager);
}
}
else {
if (!fStandardUriConformant)
David Abram Cargill
committed
srcToUse = new (fMemoryManager) LocalFileInputSource(systemId, fMemoryManager);
else {
David Abram Cargill
committed
// since this is the top of the try/catch, cannot call ThrowXMLwithMemMgr
// emit the error directly
David Abram Cargill
committed
// lazy bypass ... since all MalformedURLException are fatal, no need to check the type
MalformedURLException e(__FILE__, __LINE__, XMLExcepts::URL_MalformedURL);
fInException = true;
emitError
(
XMLErrs::XMLException_Fatal
, e.getType()
, e.getMessage()
);
return false;
}
}
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
catch(const XMLException& excToCatch)
{
// For any other XMLException,
// emit the error and catch any user exception thrown from here.
fInException = true;
if (excToCatch.getErrorType() == XMLErrorReporter::ErrType_Warning)
emitError
(
XMLErrs::XMLException_Warning
, excToCatch.getType()
, excToCatch.getMessage()
);
else if (excToCatch.getErrorType() >= XMLErrorReporter::ErrType_Fatal)
emitError
(
XMLErrs::XMLException_Fatal
, excToCatch.getType()
, excToCatch.getMessage()
);
else
emitError
(
XMLErrs::XMLException_Error
, excToCatch.getType()
, excToCatch.getMessage()
);
return false;
}
return scanFirst(*srcToUse, toFill);
}
bool XMLScanner::scanFirst( const char* const systemId
, XMLPScanToken& toFill)
{
// We just delegate this to the XMLCh version after transcoding
XMLCh* tmpBuf = XMLString::transcode(systemId, fMemoryManager);
ArrayJanitor<XMLCh> janBuf(tmpBuf, fMemoryManager);
return scanFirst(tmpBuf, toFill);
}
bool XMLScanner::scanFirst( const InputSource& src
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
{
// Bump up the sequence id for this new scan cycle. This will invalidate
// any previous tokens we've returned.
fSequenceId++;
// Reset the scanner and its plugged in stuff for a new run. This
// resets all the data structures, creates the initial reader and
// pushes it on the stack, and sets up the base document path
scanReset(src);
// If we have a document handler, then call the start document
if (fDocHandler)
fDocHandler->startDocument();
try
{
// Scan the prolog part, which is everything before the root element
// including the DTD subsets. This is all that is done on the scan
// first.
scanProlog();
// If we got to the end of input, then its not a valid XML file.
// Else, go on to scan the content.
if (fReaderMgr.atEOF())
{
emitError(XMLErrs::EmptyMainEntity);
}
}
// NOTE:
//
// In all of the error processing below, the emitError() call MUST come
// before the flush of the reader mgr, or it will fail because it tries
// to find out the position in the XML source of the error.
catch(const XMLErrs::Codes)
{
// This is a 'first failure' exception so reset and return a failure
fReaderMgr.reset();
return false;
}
catch(const XMLValid::Codes)
{
// This is a 'first fatal error' type exit, so reset and reuturn failure
fReaderMgr.reset();
return false;
}
catch(const XMLException& excToCatch)
{
// Emit the error and catch any user exception thrown from here. Make
// sure in all cases we flush the reader manager.
fInException = true;
try
{
if (excToCatch.getErrorType() == XMLErrorReporter::ErrType_Warning)
emitError
(
XMLErrs::XMLException_Warning
, excToCatch.getType()
, excToCatch.getMessage()
);
else if (excToCatch.getErrorType() >= XMLErrorReporter::ErrType_Fatal)
emitError
(
XMLErrs::XMLException_Fatal
, excToCatch.getType()
, excToCatch.getMessage()
);
else
emitError
(
XMLErrs::XMLException_Error
, excToCatch.getType()
, excToCatch.getMessage()
);
}
Neil Graham
committed
catch(const OutOfMemoryException&)
{
throw;
}
catch(...)
{
// Reset and rethrow the user error
fReaderMgr.reset();
throw;
}
// Reset and return a failure
fReaderMgr.reset();
return false;
}
Neil Graham
committed
catch(const OutOfMemoryException&)
{
throw;
}
catch(...)
{
// Reset and rethrow original error
fReaderMgr.reset();
throw;
}
// Fill in the caller's token to make it legal and return success
toFill.set(fScannerId, fSequenceId);
return true;
}
void XMLScanner::scanReset(XMLPScanToken& token)
{
// Make sure this token is still legal
if (!isLegalToken(token))
David Abram Cargill
committed
ThrowXMLwithMemMgr(RuntimeException, XMLExcepts::Scan_BadPScanToken, fMemoryManager);
// Reset the reader manager
fReaderMgr.reset();
// And invalidate any tokens by bumping our sequence number
fSequenceId++;
// Reset our error count
fErrorCount = 0;
}
void XMLScanner::setParseSettings(XMLScanner* const refScanner)
{
setDocHandler(refScanner->getDocHandler());
setDocTypeHandler(refScanner->getDocTypeHandler());
setErrorHandler(refScanner->getErrorHandler());
setErrorReporter(refScanner->getErrorReporter());
setEntityHandler(refScanner->getEntityHandler());
setDoNamespaces(refScanner->getDoNamespaces());
setDoSchema(refScanner->getDoSchema());
setCalculateSrcOfs(refScanner->getCalculateSrcOfs());
setStandardUriConformant(refScanner->getStandardUriConformant());
setExitOnFirstFatal(refScanner->getExitOnFirstFatal());
setValidationConstraintFatal(refScanner->getValidationConstraintFatal());
setIdentityConstraintChecking(refScanner->getIdentityConstraintChecking());
setValidationSchemaFullChecking(refScanner->getValidationSchemaFullChecking());
cacheGrammarFromParse(refScanner->isCachingGrammarFromParse());
useCachedGrammarInParse(refScanner->isUsingCachedGrammarInParse());
setLoadExternalDTD(refScanner->getLoadExternalDTD());
setNormalizeData(refScanner->getNormalizeData());
setExternalSchemaLocation(refScanner->getExternalSchemaLocation());
setExternalNoNamespaceSchemaLocation(refScanner->getExternalNoNamespaceSchemaLocation());
setValidationScheme(refScanner->getValidationScheme());
setSecurityManager(refScanner->getSecurityManager());
setPSVIHandler(refScanner->getPSVIHandler());
// ---------------------------------------------------------------------------
// XMLScanner: Private helper methods.
// ---------------------------------------------------------------------------
// This method handles the common initialization, to avoid having to do
// it redundantly in multiple constructors.
void XMLScanner::commonInit()
{
// We have to do a little init that involves statics, so we have to
// use the mutex to protect it.
{
XMLMutexLock lockInit(&gScannerMutex());
// And assign ourselves the next available scanner id
fScannerId = ++gScannerId;
}
// Create the attribute list, which is used to store attribute values
// during start tag processing. Give it a reasonable initial size that
// will serve for most folks, though it will grow as required.
fAttrList = new (fMemoryManager) RefVectorOf<XMLAttr>(32, true, fMemoryManager);
// Create the id ref list. This is used to enforce XML 1.0 ID ref
// semantics, i.e. all id refs must refer to elements that exist
fValidationContext = new (fMemoryManager) ValidationContextImpl(fMemoryManager);
// Create the GrammarResolver
//fGrammarResolver = new GrammarResolver();
// create initial, 64-element, fUIntPool
fUIntPool = (unsigned int **)fMemoryManager->allocate(sizeof(unsigned int *) *fUIntPoolRowTotal);
fUIntPool[0] = (unsigned int *)fMemoryManager->allocate(sizeof(unsigned int) << 6);
memset(fUIntPool[0], 0, sizeof(unsigned int) << 6);
fUIntPool[1] = 0;
// Register self as handler for XMLBufferFull events on the CDATA buffer
fCDataBuf.setFullHandler(this, fBufferSize);
void XMLScanner::initValidator(XMLValidator* theValidator) {
// Tell the validator about the stuff it needs to know in order to
// do its work.
theValidator->setScannerInfo(this, &fReaderMgr, &fBufMgr);
theValidator->setErrorReporter(fErrorReporter);
}
// ---------------------------------------------------------------------------
// XMLScanner: Error emitting methods
// ---------------------------------------------------------------------------
// These methods are called whenever the scanner wants to emit an error.
// It handles getting the message loaded, doing token replacement, etc...
// and then calling the error handler, if its installed.
bool XMLScanner::emitErrorWillThrowException(const XMLErrs::Codes toEmit)
{
if (XMLErrs::isFatal(toEmit) && fExitOnFirstFatal && !fInException)
return true;
return false;
}
void XMLScanner::emitError(const XMLErrs::Codes toEmit)
{
// Bump the error count if it is not a warning
if (XMLErrs::errorType(toEmit) != XMLErrorReporter::ErrType_Warning)
incrementErrorCount();
if (fErrorReporter)
{
// Load the message into a local for display
const unsigned int msgSize = 1023;
XMLCh errText[msgSize + 1];
if (!gScannerMsgLoader().loadMsg(toEmit, errText, msgSize))
{
// <TBD> Probably should load a default msg here
}
// Create a LastExtEntityInfo structure and get the reader manager
// to fill it in for us. This will give us the information about
// the last reader on the stack that was an external entity of some
// sort (i.e. it will ignore internal entities.
ReaderMgr::LastExtEntityInfo lastInfo;
fReaderMgr.getLastExtEntityInfo(lastInfo);
fErrorReporter->error
(
toEmit
, XMLUni::fgXMLErrDomain
, XMLErrs::errorType(toEmit)
, errText
, lastInfo.systemId
, lastInfo.publicId
, lastInfo.lineNumber
, lastInfo.colNumber
);
}
// Bail out if its fatal an we are to give up on the first fatal error
if (emitErrorWillThrowException(toEmit))
throw toEmit;
}
void XMLScanner::emitError( const XMLErrs::Codes toEmit
, const XMLCh* const text1
, const XMLCh* const text2
, const XMLCh* const text3
, const XMLCh* const text4)
{
// Bump the error count if it is not a warning
if (XMLErrs::errorType(toEmit) != XMLErrorReporter::ErrType_Warning)
incrementErrorCount();
if (fErrorReporter)
{
// Load the message into alocal and replace any tokens found in
// the text.
const unsigned int maxChars = 2047;
XMLCh errText[maxChars + 1];
if (!gScannerMsgLoader().loadMsg(toEmit, errText, maxChars, text1, text2, text3, text4, fMemoryManager))
{
// <TBD> Should probably load a default message here
}
// Create a LastExtEntityInfo structure and get the reader manager
// to fill it in for us. This will give us the information about
// the last reader on the stack that was an external entity of some
// sort (i.e. it will ignore internal entities.
ReaderMgr::LastExtEntityInfo lastInfo;
fReaderMgr.getLastExtEntityInfo(lastInfo);
fErrorReporter->error
(
toEmit
, XMLUni::fgXMLErrDomain
, XMLErrs::errorType(toEmit)
, errText
, lastInfo.systemId
, lastInfo.publicId
, lastInfo.lineNumber
, lastInfo.colNumber
);
}
// Bail out if its fatal an we are to give up on the first fatal error
if (emitErrorWillThrowException(toEmit))
throw toEmit;
}
void XMLScanner::emitError( const XMLErrs::Codes toEmit
, const char* const text1
, const char* const text2
, const char* const text3
, const char* const text4)
{
// Bump the error count if it is not a warning
if (XMLErrs::errorType(toEmit) != XMLErrorReporter::ErrType_Warning)
incrementErrorCount();
if (fErrorReporter)
{
// Load the message into alocal and replace any tokens found in
// the text.
const unsigned int maxChars = 2047;
XMLCh errText[maxChars + 1];
David Abram Cargill
committed
if (!gScannerMsgLoader().loadMsg(toEmit, errText, maxChars, text1, text2, text3, text4, fMemoryManager))
{
// <TBD> Should probably load a default message here
}
// Create a LastExtEntityInfo structure and get the reader manager
// to fill it in for us. This will give us the information about
// the last reader on the stack that was an external entity of some
// sort (i.e. it will ignore internal entities.
ReaderMgr::LastExtEntityInfo lastInfo;
fReaderMgr.getLastExtEntityInfo(lastInfo);
fErrorReporter->error
(
toEmit
, XMLUni::fgXMLErrDomain
, XMLErrs::errorType(toEmit)
, errText
, lastInfo.systemId
, lastInfo.publicId
, lastInfo.lineNumber
, lastInfo.colNumber
);
}
// Bail out if its fatal an we are to give up on the first fatal error
if (emitErrorWillThrowException(toEmit))
throw toEmit;
}
// ---------------------------------------------------------------------------
// XMLScanner: Getter methods
// ---------------------------------------------------------------------------
// This method allows the caller to query the current location of the scanner.
// It will return the sys/public ids of the current entity, and the line/col
// position within it.
//
// NOTE: This API returns the location with the last external file. So if its
// currently scanning an entity, the position returned will be the end of
// the entity reference in the file that had the reference.
//
XMLScanner::getLastExtLocation( XMLCh* const sysIdToFill
, const unsigned int maxSysIdChars
, XMLCh* const pubIdToFill
, const unsigned int maxPubIdChars
Tinny Ng
committed
, XMLSSize_t& lineToFill
, XMLSSize_t& colToFill) const
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
{
// Create a local info object and get it filled in by the reader manager
ReaderMgr::LastExtEntityInfo lastInfo;
fReaderMgr.getLastExtEntityInfo(lastInfo);
// Fill in the line and column number
lineToFill = lastInfo.lineNumber;
colToFill = lastInfo.colNumber;
// And copy over as much of the ids as will fit
sysIdToFill[0] = 0;
if (lastInfo.systemId)
{
if (XMLString::stringLen(lastInfo.systemId) > maxSysIdChars)
return false;
XMLString::copyString(sysIdToFill, lastInfo.systemId);
}
pubIdToFill[0] = 0;
if (lastInfo.publicId)
{
if (XMLString::stringLen(lastInfo.publicId) > maxPubIdChars)
return false;
XMLString::copyString(pubIdToFill, lastInfo.publicId);
}
return true;
// ---------------------------------------------------------------------------
// XMLScanner: Private scanning methods
// ---------------------------------------------------------------------------
// This method is called after the end of the root element, to handle
// any miscellaneous stuff hanging around.
void XMLScanner::scanMiscellaneous()
// Get a buffer for this work
XMLBufBid bbCData(&fBufMgr);
const XMLCh nextCh = fReaderMgr.peekNextChar();
// Watch for end of file and break out
if (!nextCh)
break;
// Can't have an XML decl here
emitError(XMLErrs::NotValidAfterContent);
fReaderMgr.skipPastChar(chCloseAngle);
else if (fReaderMgr.skippedString(XMLUni::fgPIString))
else if (fReaderMgr.skippedString(XMLUni::fgCommentString))
// This can't be possible, so just give up
emitError(XMLErrs::ExpectedCommentOrPI);
fReaderMgr.skipPastChar(chCloseAngle);
// If we have a doc handler, then gather up the spaces and