Still a problem in 3.1.1. Patch included.
Regards,
Denis Excoffier.
On Tue, Nov 03, 2009 at 09:36:00AM +0000, Boris Kolpackov (JIRA) wrote:
>>
>> [
>> https://issues.apache.org/jira/browse/XERCESC-1701?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
>> ]
>>
>> Boris Kolpackov updated XERCESC-1701:
>> -------------------------------------
>>
>> Affects Version/s: (was: 2.7.0)
>> 3.0.1
>>
>> Still a problem in 3.0.1.
>>
>> > Xerces-C++ Allows junk after root element (null characters)
>> > -----------------------------------------------------------
>> >
>> > Key: XERCESC-1701
>> > URL: https://issues.apache.org/jira/browse/XERCESC-1701
>> > Project: Xerces-C++
>> > Issue Type: Bug
>> > Components: Non-Validating Parser
>> > Affects Versions: 3.0.1
>> > Environment: WindowsXP
>> > Reporter: Maarten Koskamp
>> > Attachments: sample.xml, version.incl
>> >
>> >
>> > Xerces-C allows a sequence of null characters after the document root at
>> > the end of the xml instance.
>> > XML Specifiction states that only white-space is allowed after the
>> > document root.
>> > See attached sample for details.
>> > Info about the affected version of the parser is also added as an
>> > attachment to this issue.
>>
>> --
>> This message is automatically generated by JIRA.
>> -
>> You can reply to this email to add a comment to the issue online.
>>
>>
>> ---------------------------------------------------------------------
>> To unsubscribe, e-mail: [email protected]
>> For additional commands, e-mail: [email protected]
>>
>>
>>
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/DGXMLScanner.cpp
xerces-c-3.1.1p/src/xercesc/internal/DGXMLScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/DGXMLScanner.cpp 2009-11-05
14:21:03.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/DGXMLScanner.cpp 2012-08-06
10:45:26.765625000 +0159
@@ -1407,7 +1407,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -1858,7 +1858,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -2812,7 +2812,7 @@
{
nextCh = fReaderMgr.getNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Check for our ending quote in the same entity
@@ -3021,7 +3021,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for unexpected end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedCDATASection);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/IGXMLScanner.cpp
xerces-c-3.1.1p/src/xercesc/internal/IGXMLScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/IGXMLScanner.cpp 2009-11-20
14:43:50.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/IGXMLScanner.cpp 2012-08-06
10:46:25.703125000 +0159
@@ -762,7 +762,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -1910,7 +1910,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/IGXMLScanner2.cpp
xerces-c-3.1.1p/src/xercesc/internal/IGXMLScanner2.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/IGXMLScanner2.cpp 2010-03-19
15:29:23.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/IGXMLScanner2.cpp 2012-08-06
10:47:39.468750000 +0159
@@ -2271,7 +2271,7 @@
// Its got to at least be a valid XML character
if
(!fReaderMgr.getCurrentReader()->isXMLChar(nextCh))
{
- if (nextCh == 0)
+ if (nextCh == 0 && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
XMLCh tmpBuf[9];
@@ -2414,7 +2414,7 @@
{
nextCh = fReaderMgr.getNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Check for our ending quote in the same entity
@@ -2638,7 +2638,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for unexpected end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedCDATASection);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/ReaderMgr.cpp
xerces-c-3.1.1p/src/xercesc/internal/ReaderMgr.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/ReaderMgr.cpp 2009-11-05
14:21:03.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/ReaderMgr.cpp 2012-08-06
10:48:39.156250000 +0159
@@ -279,7 +279,7 @@
{
XMLCh nextCh;
// If we get an end of file char, then return
- while ((nextCh = getNextChar())!=0)
+ while ((nextCh = getNextChar())!=0 || !atEOF())
{
// If we get the quote char, then break out
if (nextCh == quoteCh)
@@ -292,7 +292,7 @@
{
XMLCh nextCh;
// If we get an end of file char, then return
- while ((nextCh = peekNextChar())!=0)
+ while ((nextCh = peekNextChar())!=0 || !atEOF())
{
if (XMLString::indexOf(listToSkip, nextCh) != -1)
break;
@@ -308,7 +308,7 @@
{
XMLCh nextCh;
// If we get an end of file char, then return
- while ((nextCh = peekNextChar())!=0)
+ while ((nextCh = peekNextChar())!=0 || !atEOF())
{
if (fCurReader->isWhitespace(nextCh))
break;
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/ReaderMgr.hpp
xerces-c-3.1.1p/src/xercesc/internal/ReaderMgr.hpp
--- xerces-c-3.1.1o/src/xercesc/internal/ReaderMgr.hpp 2009-11-05
14:21:03.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/ReaderMgr.hpp 2012-08-06
10:49:51.062500000 +0159
@@ -366,7 +366,7 @@
nextCh = getNextChar();
}
// Break out at end of input or the char to skip
- while((nextCh != toSkipTo) && nextCh!=0);
+ while((nextCh != toSkipTo) && (nextCh!=0 || !atEOF()));
}
inline void ReaderMgr::skipPastChar(const XMLCh toSkipPast)
@@ -377,7 +377,7 @@
// Get chars until we find the one to skip
nextCh = getNextChar();
}
- while((nextCh != toSkipPast) && nextCh!=0);
+ while((nextCh != toSkipPast) && (nextCh!=0 || !atEOF()));
}
inline bool ReaderMgr::peekString(const XMLCh* const toPeek)
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/SGXMLScanner.cpp
xerces-c-3.1.1p/src/xercesc/internal/SGXMLScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/SGXMLScanner.cpp 2010-03-19
15:29:23.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/SGXMLScanner.cpp 2012-08-06
10:50:53.609375000 +0159
@@ -680,7 +680,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -4063,7 +4063,7 @@
// Its got to at least be a valid XML character
if
(!fReaderMgr.getCurrentReader()->isXMLChar(nextCh))
{
- if (nextCh == 0)
+ if (nextCh == 0 && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
XMLCh tmpBuf[9];
@@ -4212,7 +4212,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for unexpected end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedCDATASection);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/WFXMLScanner.cpp
xerces-c-3.1.1p/src/xercesc/internal/WFXMLScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/WFXMLScanner.cpp 2009-11-05
14:21:03.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/WFXMLScanner.cpp 2012-08-06
10:51:52.234375000 +0159
@@ -980,7 +980,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -1359,7 +1359,7 @@
// It was some special case character so do all of the checks and
// deal with it.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chForwardSlash)
@@ -1535,7 +1535,7 @@
{
nextCh = fReaderMgr.getNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Check for our ending quote in the same entity
@@ -1680,7 +1680,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for unexpected end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedCDATASection);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
diff -uNr xerces-c-3.1.1o/src/xercesc/internal/XMLScanner.cpp
xerces-c-3.1.1p/src/xercesc/internal/XMLScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/internal/XMLScanner.cpp 2009-11-20
14:43:50.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/internal/XMLScanner.cpp 2012-08-06
10:53:06.437500000 +0159
@@ -1010,7 +1010,7 @@
const XMLCh nextCh = fReaderMgr.peekNextChar();
// Watch for end of file and break out
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
break;
if (nextCh == chOpenAngle)
@@ -1130,7 +1130,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for an end of file, which is always bad here
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedPI);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
@@ -1310,7 +1310,7 @@
emitError(XMLErrs::InvalidDocumentStructure);
// Watch for end of file and break out
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
break;
else
fReaderMgr.skipPastChar(chCloseAngle);
@@ -1971,7 +1971,7 @@
// We should never get either an end of file null char here. If we
// do, just fail. It will be handled more gracefully in the higher
// level code that called us.
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
return false;
// Else add it to the buffer
@@ -2008,7 +2008,7 @@
const XMLCh nextCh = fReaderMgr.peekNextChar();
// Watch for EOF
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Break out on the terminating semicolon
@@ -2128,7 +2128,7 @@
const XMLCh nextCh = fReaderMgr.getNextChar();
// Watch for an end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr.atEOF())
{
emitError(XMLErrs::UnterminatedComment);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
diff -uNr xerces-c-3.1.1o/src/xercesc/validators/DTD/DTDScanner.cpp
xerces-c-3.1.1p/src/xercesc/validators/DTD/DTDScanner.cpp
--- xerces-c-3.1.1o/src/xercesc/validators/DTD/DTDScanner.cpp 2009-11-05
14:21:03.000000000 +0059
+++ xerces-c-3.1.1p/src/xercesc/validators/DTD/DTDScanner.cpp 2012-08-06
10:55:04.921875000 +0159
@@ -387,7 +387,7 @@
// do, just fail. It will be handled more gracefully in the higher
// level code that called us.
//
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
return false;
// Else add it to the buffer
@@ -652,7 +652,7 @@
const XMLCh nextCh = fReaderMgr->peekNextChar();
// Watch for EOF
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chCloseAngle)
@@ -781,7 +781,7 @@
{
nextCh = fReaderMgr->getNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Check for our ending quote in the same entity
@@ -950,7 +950,7 @@
const XMLCh nextCh = fReaderMgr->peekNextChar();
// Watch for EOF
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
// Break out on the terminating semicolon
@@ -1426,7 +1426,7 @@
const XMLCh nextCh = fReaderMgr->getNextChar();
// Watch for an end of file
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
{
fScanner->emitError(XMLErrs::UnterminatedComment);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
@@ -2126,7 +2126,7 @@
// if that occurs (since an unterminated quoted char can cause
// this easily.)
//
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
{
fScanner->emitError(XMLErrs::UnterminatedEntityLiteral);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
@@ -2511,7 +2511,7 @@
{
const XMLCh nextCh = fReaderMgr->peekNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
{
return; // nothing left
}
@@ -2832,7 +2832,7 @@
{
const XMLCh nextCh = fReaderMgr->getNextChar();
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == chOpenAngle)
@@ -2939,7 +2939,7 @@
// failure status. The caller will then see the end of file and
// faill out correctly.
//
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
return false;
// Watch for the end of internal subset marker
@@ -3599,7 +3599,7 @@
const XMLCh nextCh = fReaderMgr->getNextChar();
// Watch for an end of file, which is always bad here
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
{
fScanner->emitError(XMLErrs::UnterminatedPI);
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
@@ -3704,7 +3704,7 @@
const XMLCh nextCh = fReaderMgr->getNextChar();
// Watch for EOF
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
if (nextCh == quoteCh)
@@ -3755,7 +3755,7 @@
while ((nextCh=fReaderMgr->getNextChar())!=quoteCh)
{
// Watch for EOF
- if (!nextCh)
+ if (!nextCh && fReaderMgr->atEOF())
ThrowXMLwithMemMgr(UnexpectedEOFException,
XMLExcepts::Gen_UnexpectedEOF, fMemoryManager);
toFill.append(nextCh);
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
