tng 2002/12/20 14:10:48
Modified: c/src/xercesc/validators/DTD DTDScanner.cpp DTDValidator.cpp
c/src/xercesc/validators/schema SchemaValidator.cpp
c/src/xercesc/validators/schema/identity XercesXPath.cpp
Log:
XML 1.1
Revision Changes Path
1.19 +105 -53 xml-xerces/c/src/xercesc/validators/DTD/DTDScanner.cpp
Index: DTDScanner.cpp
===================================================================
RCS file: /home/cvs/xml-xerces/c/src/xercesc/validators/DTD/DTDScanner.cpp,v
retrieving revision 1.18
retrieving revision 1.19
diff -u -r1.18 -r1.19
--- DTDScanner.cpp 18 Dec 2002 14:17:55 -0000 1.18
+++ DTDScanner.cpp 20 Dec 2002 22:10:47 -0000 1.19
@@ -56,6 +56,9 @@
/*
* $Log$
+ * Revision 1.19 2002/12/20 22:10:47 tng
+ * XML 1.1
+ *
* Revision 1.18 2002/12/18 14:17:55 gareth
* Fix to bug #13438. When you eant a vector that calls delete[] on its members you
should use RefArrayVectorOf.
*
@@ -803,7 +806,7 @@
fReaderMgr->getNextChar();
break;
}
- else if (XMLReader::isWhitespace(nextCh))
+ else if (fReaderMgr->getCurrentReader()->isWhitespace(nextCh))
{
//
// If advanced callbacks are enabled and we have a doc
@@ -915,6 +918,7 @@
bool firstNonWS = false;
bool gotLeadingSurrogate = false;
bool escaped;
+ bool charref_expanded = false;
while (true)
{
try
@@ -962,6 +966,7 @@
gotLeadingSurrogate = false;
continue;
}
+ charref_expanded = true;
}
// Check for correct surrogate pairs
@@ -980,25 +985,29 @@
fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
}
// Its got to at least be a valid XML character
- else if (!XMLReader::isXMLChar(nextCh)) {
-
- XMLCh tmpBuf[9];
- XMLString::binToText
- (
- nextCh
- , tmpBuf
- , 8
- , 16
- );
- fScanner->emitError
- (
- XMLErrs::InvalidCharacterInAttrValue
- , attrName
- , tmpBuf
- );
+ else if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh)) {
+ // if it was a character reference and is control char, then
it's ok
+ if (!(charref_expanded &&
fReaderMgr->getCurrentReader()->isControlChar(nextCh)))
+ {
+ XMLCh tmpBuf[9];
+ XMLString::binToText
+ (
+ nextCh
+ , tmpBuf
+ , 8
+ , 16
+ );
+ fScanner->emitError
+ (
+ XMLErrs::InvalidCharacterInAttrValue
+ , attrName
+ , tmpBuf
+ );
+ }
}
gotLeadingSurrogate = false;
+ charref_expanded = false;
}
//
@@ -1029,7 +1038,7 @@
{
if (curState == InWhitespace)
{
- if (!XMLReader::isWhitespace(nextCh))
+ if (!fReaderMgr->getCurrentReader()->isWhitespace(nextCh))
{
if (firstNonWS)
toFill.append(chSpace);
@@ -1043,7 +1052,7 @@
}
else if (curState == InContent)
{
- if (XMLReader::isWhitespace(nextCh))
+ if (fReaderMgr->getCurrentReader()->isWhitespace(nextCh))
{
curState = InWhitespace;
continue;
@@ -1509,7 +1518,7 @@
fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
}
// Its got to at least be a valid XML character
- else if (!XMLReader::isXMLChar(nextCh)) {
+ else if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh)) {
XMLCh tmpBuf[9];
XMLString::binToText
@@ -2147,6 +2156,7 @@
XMLCh nextCh;
XMLCh secondCh = 0;
bool gotLeadingSurrogate = false;
+ bool charref_expanded = false;
while (true)
{
// Get the second char if we have one, else get another
@@ -2216,6 +2226,8 @@
gotLeadingSurrogate = false;
continue;
}
+ charref_expanded = true;
+
}
else
{
@@ -2265,20 +2277,25 @@
if ((nextCh < 0xDC00) || (nextCh > 0xDFFF))
fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
}
- else if (!XMLReader::isXMLChar(nextCh))
+ else if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh))
{
- XMLCh tmpBuf[9];
- XMLString::binToText
- (
- nextCh
- , tmpBuf
- , 8
- , 16
- );
- fScanner->emitError(XMLErrs::InvalidCharacter, tmpBuf);
- fReaderMgr->skipPastChar(quoteCh);
- return false;
+ // if it was a character reference and is control char, then it's ok
+ if (!(charref_expanded &&
fReaderMgr->getCurrentReader()->isControlChar(nextCh)))
+ {
+ XMLCh tmpBuf[9];
+ XMLString::binToText
+ (
+ nextCh
+ , tmpBuf
+ , 8
+ , 16
+ );
+ fScanner->emitError(XMLErrs::InvalidCharacter, tmpBuf);
+ fReaderMgr->skipPastChar(quoteCh);
+ return false;
+ }
}
+ charref_expanded = false;
gotLeadingSurrogate = false;
}
@@ -2570,7 +2587,7 @@
}
}
- else if (XMLReader::isWhitespace(nextCh))
+ else if (fReaderMgr->getCurrentReader()->isWhitespace(nextCh))
{
//
// If we have a doc type handler, and advanced callbacks are
@@ -2629,13 +2646,13 @@
return;
}
else if (!nextCh)
- {
- return; // nothing left
- }
- else
+ {
+ return; // nothing left
+ }
+ else
{
fReaderMgr->getNextChar();
- if (!XMLReader::isXMLChar(nextCh))
+ if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh))
{
XMLCh tmpBuf[9];
XMLString::binToText
@@ -2647,7 +2664,7 @@
);
fScanner->emitError(XMLErrs::InvalidCharacter, tmpBuf);
}
- else
+ else
{
fScanner->emitError(XMLErrs::InvalidDocumentStructure);
}
@@ -2851,6 +2868,7 @@
// to parse until we hit its end.
//
unsigned long depth = 1;
+ bool gotLeadingSurrogate = false;
while (true)
{
const XMLCh nextCh = fReaderMgr->getNextChar();
@@ -2883,17 +2901,50 @@
}
}
}
- else if (!XMLReader::isXMLChar(nextCh))
+ // Deal with surrogate pairs
+ else if ((nextCh >= 0xD800) && (nextCh <= 0xDBFF))
{
- XMLCh tmpBuf[9];
- XMLString::binToText
- (
- nextCh
- , tmpBuf
- , 8
- , 16
- );
- fScanner->emitError(XMLErrs::InvalidCharacter, tmpBuf);
+ // Its a leading surrogate. If we already got one, then
+ // issue an error, else set leading flag to make sure that
+ // we look for a trailing next time.
+ if (gotLeadingSurrogate)
+ fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
+ else
+ gotLeadingSurrogate = true;
+ }
+ else
+ {
+ // If its a trailing surrogate, make sure that we are
+ // prepared for that. Else, its just a regular char so make
+ // sure that we were not expected a trailing surrogate.
+ if ((nextCh >= 0xDC00) && (nextCh <= 0xDFFF))
+ {
+ // Its trailing, so make sure we were expecting it
+ if (!gotLeadingSurrogate)
+ fScanner->emitError(XMLErrs::Unexpected2ndSurrogateChar);
+ }
+ else
+ {
+ // Its just a char, so make sure we were not expecting a
+ // trailing surrogate.
+ if (gotLeadingSurrogate)
+ fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
+
+ // Its got to at least be a valid XML character
+ else if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh))
+ {
+ XMLCh tmpBuf[9];
+ XMLString::binToText
+ (
+ nextCh
+ , tmpBuf
+ , 8
+ , 16
+ );
+ fScanner->emitError(XMLErrs::InvalidCharacter, tmpBuf);
+ }
+ }
+ gotLeadingSurrogate = false;
}
}
}
@@ -2968,7 +3019,7 @@
fScanner->getValidator()->emitError(XMLValid::PartialMarkupInPE);
}
}
- else if (XMLReader::isWhitespace(nextCh))
+ else if (fReaderMgr->getCurrentReader()->isWhitespace(nextCh))
{
//
// IF we are doing advanced callbacks and have a doc type
@@ -3572,7 +3623,7 @@
fScanner->emitError(XMLErrs::Expected2ndSurrogateChar);
}
// Its got to at least be a valid XML character
- else if (!XMLReader::isXMLChar(nextCh)) {
+ else if (!fReaderMgr->getCurrentReader()->isXMLChar(nextCh)) {
XMLCh tmpBuf[9];
XMLString::binToText
@@ -3656,7 +3707,7 @@
// If its not a valid public id char, then report it but keep going
// since that's the best recovery scheme.
//
- if (!XMLReader::isPublicIdChar(nextCh))
+ if (!fReaderMgr->getCurrentReader()->isPublicIdChar(nextCh))
{
XMLCh tmpBuf[9];
XMLString::binToText
@@ -3746,7 +3797,8 @@
}
// If its not our supported version, issue an error but continue
- if (!XMLString::equals(bbVersion.getRawBuffer(),
XMLUni::fgSupportedVersion))
+ if (!XMLString::equals(bbVersion.getRawBuffer(), XMLUni::fgVersion1_0) &&
+ !XMLString::equals(bbVersion.getRawBuffer(), XMLUni::fgVersion1_1))
fScanner->emitError(XMLErrs::UnsupportedXMLVersion,
bbVersion.getRawBuffer());
}
1.11 +4 -4 xml-xerces/c/src/xercesc/validators/DTD/DTDValidator.cpp
Index: DTDValidator.cpp
===================================================================
RCS file: /home/cvs/xml-xerces/c/src/xercesc/validators/DTD/DTDValidator.cpp,v
retrieving revision 1.10
retrieving revision 1.11
diff -u -r1.10 -r1.11
--- DTDValidator.cpp 28 Nov 2002 19:20:33 -0000 1.10
+++ DTDValidator.cpp 20 Dec 2002 22:10:47 -0000 1.11
@@ -318,7 +318,7 @@
if (firstNameChar)
{
// If its not, emit and error but try to keep going
- if (!XMLReader::isFirstNameChar(*valPtr))
+ if (!getReaderMgr()->getCurrentReader()->isFirstNameChar(*valPtr))
emitError(XMLValid::AttrValNotName, fullName);
valPtr++;
}
@@ -330,7 +330,7 @@
// If we hit a whitespace, its either a break between two
// or more values, or an error if we have a single value.
//
- if (XMLReader::isWhitespace(*valPtr))
+ if (getReaderMgr()->getCurrentReader()->isWhitespace(*valPtr))
{
if (!multipleValues)
{
@@ -348,7 +348,7 @@
if (doNamespace && *valPtr == chColon && firstNameChar)
getScanner()->emitError(XMLErrs::ColonNotLegalWithNS);
- if (!XMLReader::isNameChar(*valPtr))
+ if (!getReaderMgr()->getCurrentReader()->isNameChar(*valPtr))
{
emitError(XMLValid::AttrValNotName, fullName);
return;
1.24 +11 -8 xml-xerces/c/src/xercesc/validators/schema/SchemaValidator.cpp
Index: SchemaValidator.cpp
===================================================================
RCS file: /home/cvs/xml-xerces/c/src/xercesc/validators/schema/SchemaValidator.cpp,v
retrieving revision 1.23
retrieving revision 1.24
diff -u -r1.23 -r1.24
--- SchemaValidator.cpp 12 Dec 2002 20:53:28 -0000 1.23
+++ SchemaValidator.cpp 20 Dec 2002 22:10:47 -0000 1.24
@@ -1,7 +1,7 @@
/*
* The Apache Software License, Version 1.1
*
- * Copyright (c) 2001 The Apache Software Foundation. All rights
+ * Copyright (c) 2001-2002 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -56,6 +56,9 @@
/*
* $Log$
+ * Revision 1.24 2002/12/20 22:10:47 tng
+ * XML 1.1
+ *
* Revision 1.23 2002/12/12 20:53:28 knoaman
* Schema Errata E1-15.
*
@@ -480,7 +483,7 @@
fCurrentDV->validate(value);
}
}
- }
+ }
catch (XMLException& idve) {
emitError (XMLValid::DatatypeError, idve.getType(),
idve.getMessage());
}
@@ -676,9 +679,9 @@
attDefDV->validate(attrValue);
}
- }
+ }
catch (XMLException& idve) {
- emitError (XMLValid::DatatypeError, idve.getType(),
idve.getMessage());
+ emitError (XMLValid::DatatypeError, idve.getType(),
idve.getMessage());
}
catch (...) {
emitError(XMLValid::GenericError);
@@ -1124,14 +1127,14 @@
}
else if (fWhiteSpace == DatatypeValidator::REPLACE)
{
- if (XMLReader::isWhitespace(nextCh))
+ if (getReaderMgr()->getCurrentReader()->isWhitespace(nextCh))
nextCh = chSpace;
}
else // COLLAPSE case
{
if (curState == InWhitespace)
{
- if (!XMLReader::isWhitespace(nextCh))
+ if (!getReaderMgr()->getCurrentReader()->isWhitespace(nextCh))
{
if (firstNonWS)
toFill.append(chSpace);
@@ -1146,7 +1149,7 @@
}
else if (curState == InContent)
{
- if (XMLReader::isWhitespace(nextCh))
+ if (getReaderMgr()->getCurrentReader()->isWhitespace(nextCh))
{
curState = InWhitespace;
srcPtr++;
@@ -1163,7 +1166,7 @@
}
srcPtr--;
nextCh = *srcPtr;
- if (XMLReader::isWhitespace(nextCh))
+ if (getReaderMgr()->getCurrentReader()->isWhitespace(nextCh))
fTrailing = true;
}
1.5 +9 -6
xml-xerces/c/src/xercesc/validators/schema/identity/XercesXPath.cpp
Index: XercesXPath.cpp
===================================================================
RCS file:
/home/cvs/xml-xerces/c/src/xercesc/validators/schema/identity/XercesXPath.cpp,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- XercesXPath.cpp 4 Dec 2002 18:21:23 -0000 1.4
+++ XercesXPath.cpp 20 Dec 2002 22:10:48 -0000 1.5
@@ -56,6 +56,9 @@
/*
* $Log$
+ * Revision 1.5 2002/12/20 22:10:48 tng
+ * XML 1.1
+ *
* Revision 1.4 2002/12/04 18:21:23 knoaman
* Identity constraint fix.
*
@@ -687,7 +690,7 @@
ch = data[currentOffset];
- while (XMLReader::isWhitespace(ch)) {
+ while (XMLChar1_0::isWhitespace(ch)) {
if (++currentOffset == endOffset) {
break;
@@ -757,13 +760,13 @@
addToken(tokens, XercesXPath::EXPRTOKEN_PERIOD);
starIsMultiplyOperator = true;
currentOffset++;
- } else if (XMLReader::isWhitespace(ch)) {
+ } else if (XMLChar1_0::isWhitespace(ch)) {
do {
if (++currentOffset == endOffset)
break;
ch = data[currentOffset];
- } while (XMLReader::isWhitespace(ch));
+ } while (XMLChar1_0::isWhitespace(ch));
if (currentOffset == endOffset || ch == chPipe) {
addToken(tokens, XercesXPath::EXPRTOKEN_PERIOD);
@@ -1088,7 +1091,7 @@
//
// [39] ExprWhitespace ::= S
//
- while (XMLReader::isWhitespace(ch)) {
+ while (XMLChar1_0::isWhitespace(ch)) {
if (++currentOffset == endOffset) {
break;
}
@@ -1224,7 +1227,7 @@
XMLCh ch = data[currentOffset];
- if (!XMLReader::isXMLLetter(ch) && ch != chUnderscore) {
+ if (!XMLChar1_0::isXMLLetter(ch) && ch != chUnderscore) {
return currentOffset;
}
@@ -1232,7 +1235,7 @@
ch = data[currentOffset];
- if (ch == chColon || !XMLReader::isNameChar(ch)) {
+ if (ch == chColon || !XMLChar1_0::isNameChar(ch)) {
break;
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
