"README" did not exist on "e00cbff98ad52be874584ff99d0634b1443ee0e4"
Newer
Older
* Copyright 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.
*/
/*
* $Id$
*/
#include "DOMLSSerializerImpl.hpp"
Alberto Massari
committed
#include "DOMLSOutputImpl.hpp"
Khaled Noaman
committed
#include "DOMErrorImpl.hpp"
#include "DOMLocatorImpl.hpp"
Tinny Ng
committed
#include "DOMImplementationImpl.hpp"
#include <xercesc/framework/MemBufFormatTarget.hpp>
#include <xercesc/framework/LocalFileFormatTarget.hpp>
#include <xercesc/util/TransService.hpp>
#include <xercesc/util/TranscodingException.hpp>
#include <xercesc/util/Janitor.hpp>
#include <xercesc/util/XMLString.hpp>
#include <xercesc/util/XMLUniDefs.hpp>
Tinny Ng
committed
#include <xercesc/util/XMLMsgLoader.hpp>
#include <xercesc/dom/StDOMNode.hpp>
Neil Graham
committed
#include <xercesc/util/OutOfMemoryException.hpp>
// ---------------------------------------------------------------------------
// Local const data
//
// ---------------------------------------------------------------------------
static const int INVALID_FEATURE_ID = -1;
static const int CANONICAL_FORM_ID = 0x0;
static const int DISCARD_DEFAULT_CONTENT_ID = 0x1;
static const int ENTITIES_ID = 0x2;
static const int FORMAT_PRETTY_PRINT_ID = 0x3;
static const int NORMALIZE_CHARACTERS_ID = 0x4;
static const int SPLIT_CDATA_SECTIONS_ID = 0x5;
static const int VALIDATION_ID = 0x6;
static const int WHITESPACE_IN_ELEMENT_CONTENT_ID = 0x7;
static const int BYTE_ORDER_MARK_ID = 0x8;
// feature true false
// ================================================================================
//canonical-form [optional] Not Supported [required] (default)
//discard-default-content [required] (default) [required]
//entity [required] (default) [optional]
//format-pretty-print [optional] Partially Supported [required] (default)
//normalize-characters [optional] Not Supported [required] (default)
//split-cdata-sections [required] (default) [required]
//validation [optional] Not Supported [required] (default)
//whitespace-in-element-content [requierd] (default) [optional] Not Supported
//
//
// the first for "true",
// the second for "false".
//
static const bool featuresSupported[] = {
false, true, // canonical-form
true, true, // discard-default-content
true, true, // entity
true, true, // format-pretty-print
false, true, // normalize-characters
true, true, // split-cdata-sections
false, true, // validation
true, false, // whitespace-in-element-content
true, true, // byte-order-mark
true, true // xml-declaration
};
// default end-of-line sequence
static const XMLCh gEOLSeq[] =
{
chLF, chNull
};
//UTF-8
static const XMLCh gUTF8[] =
{
chLatin_U, chLatin_T, chLatin_F, chDash, chDigit_8, chNull
};
//</
static const XMLCh gEndElement[] =
{
chOpenAngle, chForwardSlash, chNull
};
//?>
static const XMLCh gEndPI[] =
chQuestion, chCloseAngle, chNull
static const XMLCh gStartPI[] =
{
chOpenAngle, chQuestion, chNull
//<?xml version="
static const XMLCh gXMLDecl_VersionInfo[] =
chOpenAngle, chQuestion, chLatin_x, chLatin_m, chLatin_l, chSpace,
chLatin_v, chLatin_e, chLatin_r, chLatin_s, chLatin_i, chLatin_o,
chLatin_n, chEqual, chDoubleQuote, chNull
};
static const XMLCh gXMLDecl_ver10[] =
{
chDigit_1, chPeriod, chDigit_0, chNull
};
//encoding="
static const XMLCh gXMLDecl_EncodingDecl[] =
{
chLatin_e, chLatin_n, chLatin_c, chLatin_o, chLatin_d, chLatin_i,
chLatin_n, chLatin_g, chEqual, chDoubleQuote, chNull
};
//" standalone="
static const XMLCh gXMLDecl_SDDecl[] =
{
chLatin_s, chLatin_t, chLatin_a, chLatin_n, chLatin_d, chLatin_a,
chLatin_l, chLatin_o, chLatin_n, chLatin_e, chEqual, chDoubleQuote,
static const XMLCh gXMLDecl_separator[] =
chDoubleQuote, chSpace, chNull
//?>
static const XMLCh gXMLDecl_endtag[] =
chQuestion, chCloseAngle, chNull
};
//<![CDATA[
static const XMLCh gStartCDATA[] =
{
chOpenAngle, chBang, chOpenSquare, chLatin_C, chLatin_D,
chLatin_A, chLatin_T, chLatin_A, chOpenSquare, chNull
};
//]]>
static const XMLCh gEndCDATA[] =
{
// chCloseSquare, chCloseAngle, chCloseAngle, chNull // test only: ]>>
chCloseSquare, chCloseSquare, chCloseAngle, chNull
static const int offset = XMLString::stringLen(gEndCDATA);
//<!--
static const XMLCh gStartComment[] =
{
chOpenAngle, chBang, chDash, chDash, chNull
};
//-->
static const XMLCh gEndComment[] =
{
chDash, chDash, chCloseAngle, chNull
};
static const XMLCh gStartDoctype[] =
{
chOpenAngle, chBang, chLatin_D, chLatin_O, chLatin_C, chLatin_T,
chLatin_Y, chLatin_P, chLatin_E, chSpace, chNull
};
//PUBLIC "
static const XMLCh gPublic[] =
{
chLatin_P, chLatin_U, chLatin_B, chLatin_L, chLatin_I,
chLatin_C, chSpace, chDoubleQuote, chNull
};
//SYSTEM "
static const XMLCh gSystem[] =
{
chLatin_S, chLatin_Y, chLatin_S, chLatin_T, chLatin_E,
chLatin_M, chSpace, chDoubleQuote, chNull
};
static const XMLCh gStartEntity[] =
{
chOpenAngle, chBang, chLatin_E, chLatin_N, chLatin_T, chLatin_I,
chLatin_T, chLatin_Y, chSpace, chNull
};
//NDATA "
static const XMLCh gNotation[] =
{
chLatin_N, chLatin_D, chLatin_A, chLatin_T, chLatin_A,
chSpace, chDoubleQuote, chNull
};
static const XMLByte BOM_utf16be[] = {(XMLByte)0xFE, (XMLByte)0xFF, (XMLByte) 0};
static const XMLByte BOM_utf16le[] = {(XMLByte)0xFF, (XMLByte)0xFE, (XMLByte) 0};
static const XMLByte BOM_ucs4be[] = {(XMLByte)0x00, (XMLByte)0x00, (XMLByte)0xFE, (XMLByte)0xFF, (XMLByte) 0};
static const XMLByte BOM_ucs4le[] = {(XMLByte)0xFF, (XMLByte)0xFE, (XMLByte)0x00, (XMLByte)0x00, (XMLByte) 0};
static bool lineFeedInTextNodePrinted = false;
static int lastWhiteSpaceInTextNode = 0;
Gareth Reakes
committed
//
// Notification of the error though error handler
//
// The application may instruct the engine to abort serialization
// by returning "false".
//
// REVISIT: update the locator ctor once the line#, col#, uri and offset
// are available from DOM3 core
//
// REVISIT: use throwing exception to abort serialization is an interesting
// thing here, since the serializer is a recusive function, we
// can't use return, obviously. However we may have multiple try/catch
// along its way going back to write(). So far we don't come up with a
// "short-cut" to go "directly" back.
//
fFormatter->setUnRepFlags(XMLFormatter::UnRep_Fail); \
try \
{ \
action; \
} \
catch(TranscodingException const &e) \
{ \
reportError(nodeToWrite, DOMError::DOM_SEVERITY_FATAL_ERROR, e.getMessage()); \
throw e; \
DOMLSSerializerImpl::~DOMLSSerializerImpl()
fMemoryManager->deallocate(fNewLine);//delete [] fNewLine;
Gareth Reakes
committed
delete fNamespaceStack;
// we don't own/adopt error handler and filter
DOMLSSerializerImpl::DOMLSSerializerImpl(MemoryManager* const manager)
:fFeatures(0)
,fNewLine(0)
,fErrorHandler(0)
,fFilter(0)
,fDocumentVersion(XMLUni::fgVersion1_0)
,fSupportedParameters(0)
,fEncodingUsed(0)
,fNewLineUsed(0)
,fFormatter(0)
,fErrorCount(0)
,fCurrentLine(0)
Gareth Reakes
committed
,fNamespaceStack(0)
,fMemoryManager(manager)
fNamespaceStack=new (fMemoryManager) RefVectorOf< RefHashTableOf<XMLCh> >(0,true, fMemoryManager);
Gareth Reakes
committed
//
// set features to default setting
//
setFeature(CANONICAL_FORM_ID, false);
setFeature(DISCARD_DEFAULT_CONTENT_ID, true );
setFeature(ENTITIES_ID, true );
setFeature(FORMAT_PRETTY_PRINT_ID, false);
setFeature(NORMALIZE_CHARACTERS_ID, false);
setFeature(SPLIT_CDATA_SECTIONS_ID, true );
setFeature(VALIDATION_ID, false);
setFeature(WHITESPACE_IN_ELEMENT_CONTENT_ID, true );
setFeature(BYTE_ORDER_MARK_ID, false);
setFeature(XML_DECLARATION, true );
fSupportedParameters=new (fMemoryManager) DOMStringListImpl(11, fMemoryManager);
fSupportedParameters->add(XMLUni::fgDOMErrorHandler);
fSupportedParameters->add(XMLUni::fgDOMWRTCanonicalForm);
fSupportedParameters->add(XMLUni::fgDOMWRTDiscardDefaultContent);
fSupportedParameters->add(XMLUni::fgDOMWRTEntities);
fSupportedParameters->add(XMLUni::fgDOMWRTFormatPrettyPrint);
fSupportedParameters->add(XMLUni::fgDOMWRTNormalizeCharacters);
fSupportedParameters->add(XMLUni::fgDOMWRTSplitCdataSections);
fSupportedParameters->add(XMLUni::fgDOMWRTValidation);
fSupportedParameters->add(XMLUni::fgDOMWRTWhitespaceInElementContent);
fSupportedParameters->add(XMLUni::fgDOMWRTBOM);
fSupportedParameters->add(XMLUni::fgDOMXMLDeclaration);
bool DOMLSSerializerImpl::canSetParameter(const XMLCh* const featName
, const void* /*value*/) const
{
if(XMLString::compareIStringASCII(featName, XMLUni::fgDOMErrorHandler)==0)
return true;
return false;
}
bool DOMLSSerializerImpl::canSetParameter(const XMLCh* const featName
, bool state) const
int featureId = INVALID_FEATURE_ID;
return checkFeature(featName, false, featureId) ? canSetFeature(featureId, state) : false;
void DOMLSSerializerImpl::setParameter(const XMLCh* const featName
, const void* value)
{
if(XMLString::compareIStringASCII(featName, XMLUni::fgDOMErrorHandler)==0)
fErrorHandler = (DOMErrorHandler*)value;
else
throw DOMException(DOMException::NOT_SUPPORTED_ERR, 0, fMemoryManager);
}
void DOMLSSerializerImpl::setParameter(const XMLCh* const featName
, bool state)
int featureId = INVALID_FEATURE_ID;
checkFeature(featName, true, featureId);
if (!canSetFeature(featureId, state))
Alberto Massari
committed
throw DOMException(DOMException::NOT_SUPPORTED_ERR, 0, fMemoryManager);
setFeature(featureId, state);
//
// setting "canonical-form" to true will set the parameters "format-pretty-print",
// "discard-default-content", and "xml-declaration", to false
if ((featureId == CANONICAL_FORM_ID) && state)
setFeature(FORMAT_PRETTY_PRINT_ID, false);
setFeature(DISCARD_DEFAULT_CONTENT_ID, false);
setFeature(XML_DECLARATION, false);
}
// Setting one of those parameters to true will set "canonical-form" to false.
if ((featureId == FORMAT_PRETTY_PRINT_ID || featureId == DISCARD_DEFAULT_CONTENT_ID || featureId == XML_DECLARATION) && state)
setFeature(CANONICAL_FORM_ID, false);
const void* DOMLSSerializerImpl::getParameter(const XMLCh* const featName) const
{
if(XMLString::compareIStringASCII(featName, XMLUni::fgDOMErrorHandler)==0)
{
return (void*)fErrorHandler;
}
else
{
int featureId = INVALID_FEATURE_ID;
checkFeature(featName, true, featureId);
return (void*)getFeature(featureId);
}
const DOMStringList* DOMLSSerializerImpl::getParameterNames() const
return fSupportedParameters;
void DOMLSSerializerImpl::setNewLine(const XMLCh* const newLine)
fMemoryManager->deallocate(fNewLine);//delete [] fNewLine;
fNewLine = XMLString::replicate(newLine, fMemoryManager);
const XMLCh* DOMLSSerializerImpl::getNewLine() const
return fNewLine;
void DOMLSSerializerImpl::setFilter(DOMLSSerializerFilter *filter)
fFilter = filter;
DOMLSSerializerFilter* DOMLSSerializerImpl::getFilter() const
return fFilter;
}
//
//
//
Alberto Massari
committed
bool DOMLSSerializerImpl::write(const DOMNode* nodeToWrite,
DOMLSOutput* const destination)
Alberto Massari
committed
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
XMLFormatTarget* pTarget=destination->getByteStream();
Janitor<XMLFormatTarget> janTarget(0);
if(!pTarget)
{
const XMLCh* szSystemId=destination->getSystemId();
if(!szSystemId)
{
//TODO: report error "missing target"
return false;
}
pTarget=new LocalFileFormatTarget(szSystemId, fMemoryManager);
janTarget.reset(pTarget);
}
/**
* When writing to a LSOutput, the encoding is found by looking at the encoding information
* that is reachable through the LSOutput and the item to be written (or its owner document) in this order:
*
* 1. LSOutput.encoding,
* 2. Document.inputEncoding,
* 3. Document.xmlEncoding.
*
* If no encoding is reachable through the above properties, a default encoding of "UTF-8" will be used.
* If the specified encoding is not supported an "unsupported-encoding" fatal error is raised.
*/
fEncodingUsed = gUTF8;
const DOMDocument *docu = (nodeToWrite->getNodeType() == DOMNode::DOCUMENT_NODE)?
(const DOMDocument*)nodeToWrite : nodeToWrite->getOwnerDocument();
const XMLCh* lsEncoding=destination->getEncoding();
if (lsEncoding && *lsEncoding)
{
fEncodingUsed = lsEncoding;
}
else if (docu)
{
const XMLCh* tmpEncoding = docu->getInputEncoding();
if ( tmpEncoding && *tmpEncoding)
{
fEncodingUsed = tmpEncoding;
}
else
{
tmpEncoding = docu->getXmlEncoding();
if ( tmpEncoding && *tmpEncoding)
{
fEncodingUsed = tmpEncoding;
}
}
}
/**
* The end-of-line sequence of characters to be used in the XML being
* written out. The only permitted values are these:
* . null
*
* Use a default end-of-line sequence. DOM implementations should choose
* the default to match the usual convention for text files in the
* environment being used. Implementations must choose a default
* sequence that matches one of those allowed by 2.11 "End-of-Line
* Handling".
*
* CR The carriage-return character (#xD)
* CR-LF The carriage-return and line-feed characters (#xD #xA)
* LF The line-feed character (#xA)
*
* The default value for this attribute is null
*/
fNewLineUsed = (fNewLine && *fNewLine)? fNewLine : gEOLSeq;
/**
* get Document Version
*/
Alberto Massari
committed
fDocumentVersion = (docu && docu->getXmlVersion() && *(docu->getXmlVersion()))?docu->getXmlVersion():XMLUni::fgVersion1_0;
Alberto Massari
committed
fErrorCount = 0;
Alberto Massari
committed
fFormatter = new (fMemoryManager) XMLFormatter( fEncodingUsed
,fDocumentVersion
,pTarget
,XMLFormatter::NoEscapes
,XMLFormatter::UnRep_CharRef
,fMemoryManager);
}
catch (const TranscodingException& e)
{
reportError(nodeToWrite, DOMError::DOM_SEVERITY_FATAL_ERROR, e.getMessage());
return false;
}
try
{
Janitor<XMLFormatter> janName(fFormatter);
processNode(nodeToWrite);
Alberto Massari
committed
pTarget->flush();
}
//
// The serialize engine (processNode) throws an exception to abort
// serialization if
//
// . A fatal error occurs which renters the output ill-formed, or
// . Instructed by the application's error handler
//
catch (const TranscodingException&)
{
Alberto Massari
committed
pTarget->flush();
return false;
}
Tinny Ng
committed
catch (const XMLDOMMsg::Codes)
{
Alberto Massari
committed
pTarget->flush();
return false;
}
Neil Graham
committed
catch(const OutOfMemoryException&)
{
throw;
}
catch (...)
{
Alberto Massari
committed
pTarget->flush();
throw;
}
//
// true if node was successfully serialized and
// false in case a failure occured and the
// failure wasn't canceled by the error handler.
//
return ((fErrorCount == 0)? true : false);
bool DOMLSSerializerImpl::writeToURI(const DOMNode* nodeToWrite, const XMLCh* uri)
{
Alberto Massari
committed
DOMLSOutputImpl output(fMemoryManager);
output.setSystemId(uri);
return write(nodeToWrite, &output);
//
// We don't throw DOMSTRING_SIZE_ERR since we are no longer
// using DOMString.
//
XMLCh* DOMLSSerializerImpl::writeToString(const DOMNode* nodeToWrite)
Khaled Noaman
committed
MemBufFormatTarget destination(1023, fMemoryManager);
bool retVal;
bool bBOMFlag=getFeature(BYTE_ORDER_MARK_ID);
setFeature(BYTE_ORDER_MARK_ID, false);
try
{
Alberto Massari
committed
DOMLSOutputImpl output(fMemoryManager);
output.setByteStream(&destination);
output.setEncoding(XMLUni::fgUTF16EncodingString);
retVal = write(nodeToWrite, &output);
}
Neil Graham
committed
catch(const OutOfMemoryException&)
{
throw;
}
catch (...)
{
//
// there is a possibility that memory allocation
// exception thrown in XMLBuffer class
//
return 0;
}
return (retVal ? XMLString::replicate((XMLCh*) destination.getRawBuffer(), fMemoryManager) : 0);
}
//
// Characters not representable in output encoding,
//
// 1. CHARACTER DATA (outside of markup) --- no error
// ordinary character -> numeric character reference
// '<' and '&' -> < and &
// 2. Within MARKUP, but outside of attributes
// reported as an error --- ERROR
// markup:
// start tag done
// end tag done
// empty element tag done
// entity references done
// character references // REVISIT
// comments done
// CDATA section delimiters done, done
// document type declarartions done
// processing instructions (PI) done
//
// 3. With in ATTRIBUTE
// -> numeric character reference
// no quotes -> in quotes
// with quotes, no apostrophe -> in apostrophe
// with quotes and apostrophe -> in quotes and "
//
// "split_cdata_section" true --- char ref
// false --- ERROR
//
// ---------------------------------------------------------------------------
// Stream out a DOM node, and, recursively, all of its children. This
// function is the heart of writing a DOM tree out as XML source. Give it
// a document node and it will do the whole thing.
// ---------------------------------------------------------------------------
void DOMLSSerializerImpl::processNode(const DOMNode* const nodeToWrite, int level)
// Get the name and value out for convenience
const XMLCh* nodeName = nodeToWrite->getNodeName();
const XMLCh* nodeValue = nodeToWrite->getNodeValue();
unsigned long lent = XMLString::stringLen(nodeValue);
switch (nodeToWrite->getNodeType())
{
case DOMNode::TEXT_NODE:
if (checkFilter(nodeToWrite) != DOMNodeFilter::FILTER_ACCEPT)
break;
{
lineFeedInTextNodePrinted = false;
lastWhiteSpaceInTextNode = 0;
if(XMLString::isAllWhiteSpace(nodeValue))
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
{
// skips whitespace-only text nodes unless whitespace-in-element is set.
if (!getFeature(WHITESPACE_IN_ELEMENT_CONTENT_ID))
{
break;
}
else
{
//
// we need to trace if newline(s) have been printed out
// to avoid generate extra newline for pretty printing,
// as well as the number of whitespaces after the last
// newline character to do indentation properly.
//
int pos = XMLString::lastIndexOf(nodeValue, chLF);
if (-1 != pos)
{
lineFeedInTextNodePrinted = true;
lastWhiteSpaceInTextNode = lent - pos;
}
else
{
// for those platforms using chCR alone as
// a newline character
pos = XMLString::lastIndexOf(nodeValue, chCR);
if (-1 != pos)
{
lineFeedInTextNodePrinted = true;
lastWhiteSpaceInTextNode = lent - pos;
}
}
}
}
}
setURCharRef(); // character data
fFormatter->formatBuf(nodeValue, lent, XMLFormatter::CharEscapes);
break;
}
case DOMNode::PROCESSING_INSTRUCTION_NODE:
if (checkFilter(nodeToWrite) != DOMNodeFilter::FILTER_ACCEPT)
break;
if(level == 1)
printNewLine();
printNewLine();
printIndent(level);
TRY_CATCH_THROW
(
*fFormatter << XMLFormatter::NoEscapes << gStartPI << nodeName;
if (lent > 0)
{
*fFormatter << chSpace << nodeValue;
}
*fFormatter << gEndPI;
)
case DOMNode::DOCUMENT_NODE: // Not to be shown to Filter
// output BOM if needed
processBOM();
setURCharRef();
const DOMDocument *docu = (const DOMDocument*)nodeToWrite;
//[23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
//[24] VersionInfo ::= S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"')
//[80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName
//[32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))
Alberto Massari
committed
// use the version and encoding resolved
*fFormatter << gXMLDecl_VersionInfo << fDocumentVersion << gXMLDecl_separator;
*fFormatter << gXMLDecl_EncodingDecl << fEncodingUsed << gXMLDecl_separator;
const XMLCh* st = (docu->getXmlStandalone())? XMLUni::fgYesString : XMLUni::fgNoString;
*fFormatter << gXMLDecl_SDDecl << st << gXMLDecl_separator;
*fFormatter << gXMLDecl_endtag;
}
Neil Graham
committed
DOMNodeSPtr child = nodeToWrite->getFirstChild();
processNode(child, level);
child = child->getNextSibling();
}
printNewLine();
break;
}
case DOMNode::DOCUMENT_FRAGMENT_NODE:
{
setURCharRef();
DOMNode *child = nodeToWrite->getFirstChild();
while( child != 0)
{
processNode(child, level);
child = child->getNextSibling();
}
case DOMNode::ELEMENT_NODE:
DOMNodeFilter::FilterAction filterAction = checkFilter(nodeToWrite);
if ( filterAction == DOMNodeFilter::FILTER_REJECT)
break;
if (!lineFeedInTextNodePrinted)
{
if(level == 1)
printNewLine();
}
else
{
lineFeedInTextNodePrinted = false;
}
printIndent(level);
//track the line number the current node begins on
int nodeLine = fCurrentLine;
// add an entry in the namespace stack
Alberto Massari
committed
RefHashTableOf<XMLCh>* namespaceMap=NULL;
Gareth Reakes
committed
if ( filterAction == DOMNodeFilter::FILTER_ACCEPT)
{
// this element attributes child elements
// skip no no yes
//
TRY_CATCH_THROW
(
// The name has to be representable without any escapes
*fFormatter << XMLFormatter::NoEscapes
<< chOpenAngle << nodeName;
)
// Output any attributes on this element
setURCharRef();
DOMNamedNodeMap *attributes = nodeToWrite->getAttributes();
int attrCount = attributes->getLength();
Gareth Reakes
committed
// check if the namespace for the current node is already defined
const XMLCh* prefix = nodeToWrite->getPrefix();
const XMLCh* uri = nodeToWrite->getNamespaceURI();
if(uri && uri[0])
{
if(prefix==0 || prefix[0]==0)
prefix=XMLUni::fgZeroLenString;
bool bPrefixDeclared=false;
for(int i=fNamespaceStack->size()-1;i>=0;i--)
{
RefHashTableOf<XMLCh>* curNamespaceMap=fNamespaceStack->elementAt(i);
const XMLCh* thisUri=curNamespaceMap->get((void*)prefix);
Alberto Massari
committed
if(thisUri)
Gareth Reakes
committed
{
Alberto Massari
committed
// the prefix has been declared: check if it binds to the correct namespace, otherwise, redeclare it
if(XMLString::equals(thisUri,nodeToWrite->getNamespaceURI()))
bPrefixDeclared=true;
Gareth Reakes
committed
break;
}
}
if(!bPrefixDeclared)
{
Alberto Massari
committed
if(namespaceMap==NULL)
{
namespaceMap=new (fMemoryManager) RefHashTableOf<XMLCh>(12, false, fMemoryManager);
fNamespaceStack->addElement(namespaceMap);
}
Gareth Reakes
committed
namespaceMap->put((void*)prefix,(XMLCh*)nodeToWrite->getNamespaceURI());
*fFormatter << XMLFormatter::NoEscapes
<< chSpace << XMLUni::fgXMLNSString;
Gareth Reakes
committed
if(!XMLString::equals(prefix,XMLUni::fgZeroLenString))
*fFormatter << chColon << prefix;
*fFormatter << chEqual << chDoubleQuote
<< XMLFormatter::AttrEscapes
<< nodeToWrite->getNamespaceURI()
<< XMLFormatter::NoEscapes
<< chDoubleQuote;
}
}
bool discard = getFeature(DISCARD_DEFAULT_CONTENT_ID);
for (int i = 0; i < attrCount; i++)
{
DOMAttrSPtr attribute = (DOMAttr*)attributes->item(i);
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
// Not to be shown to Filter
//
//"discard-default-content"
// true
// [required] (default)
// Use whatever information available to the implementation
// (i.e. XML schema, DTD, the specified flag on Attr nodes,
// and so on) to decide what attributes and content should be
// discarded or not.
// Note that the specified flag on Attr nodes in itself is
// not always reliable, it is only reliable when it is set
// to false since the only case where it can be set to false
// is if the attribute was created by the implementation.
// The default content won't be removed if an implementation
// does not have any information available.
// false
// [required]
// Keep all attributes and all content.
//
if (discard && !((DOMAttr*)attribute )->getSpecified())
continue;
//
// Again the name has to be completely representable. But the
// attribute can have refs and requires the attribute style
// escaping.
//
Gareth Reakes
committed
// if this attribute is a namespace declaration, add it to the namespace map for the current level
const XMLCh* ns = attribute->getNamespaceURI();
if (ns != 0 )
{
if(XMLString::equals(ns, XMLUni::fgXMLNSURIName))
Gareth Reakes
committed
{
Alberto Massari
committed
if(namespaceMap==NULL)
{
namespaceMap=new (fMemoryManager) RefHashTableOf<XMLCh>(12, false, fMemoryManager);
fNamespaceStack->addElement(namespaceMap);
}
Gareth Reakes
committed
const XMLCh* nsPrefix = attribute->getLocalName();
if(XMLString::equals(attribute->getNodeName(),XMLUni::fgXMLNSString))
Gareth Reakes
committed
nsPrefix = XMLUni::fgZeroLenString;
if(namespaceMap->containsKey((void*)nsPrefix))
continue;
Gareth Reakes
committed
namespaceMap->put((void*)attribute->getLocalName(),(XMLCh*)attribute->getNodeValue());
}
else if(!XMLString::equals(ns, XMLUni::fgXMLURIName))
Gareth Reakes
committed
{
// check if the namespace for the current node is already defined
const XMLCh* prefix = attribute->getPrefix();
if(prefix && prefix[0])
{
bool bPrefixDeclared=false;
for(int i=fNamespaceStack->size()-1;i>=0;i--)
{
RefHashTableOf<XMLCh>* curNamespaceMap=fNamespaceStack->elementAt(i);
const XMLCh* thisUri=curNamespaceMap->get((void*)prefix);
Alberto Massari
committed
if(thisUri)
Gareth Reakes
committed
{
Alberto Massari
committed
// the prefix has been declared: check if it binds to the correct namespace, otherwise, redeclare it
if(XMLString::equals(thisUri,attribute->getNamespaceURI()))
bPrefixDeclared=true;
Gareth Reakes
committed
break;
}
}
if(!bPrefixDeclared)
{
Alberto Massari
committed
if(namespaceMap==NULL)
{
namespaceMap=new (fMemoryManager) RefHashTableOf<XMLCh>(12, false, fMemoryManager);
fNamespaceStack->addElement(namespaceMap);
}
Gareth Reakes
committed
namespaceMap->put((void*)prefix,(XMLCh*)attribute->getNamespaceURI());
*fFormatter << XMLFormatter::NoEscapes
<< chSpace << XMLUni::fgXMLNSString << chColon << prefix
Gareth Reakes
committed
<< chEqual << chDoubleQuote
<< XMLFormatter::AttrEscapes
<< attribute->getNamespaceURI()
<< XMLFormatter::NoEscapes
<< chDoubleQuote;
}
}
}
}
if (XMLString::equals(ns, XMLUni::fgXMLNSURIName) || checkFilter(attribute) == DOMNodeFilter::FILTER_ACCEPT)
{
*fFormatter << XMLFormatter::NoEscapes
<< chSpace << attribute->getNodeName()
<< chEqual << chDoubleQuote
Alberto Massari
committed
<< XMLFormatter::AttrEscapes;
if (getFeature(ENTITIES_ID))
{
DOMNodeSPtr child = attribute->getFirstChild();
while( child != 0)
{
if(child->getNodeType()==DOMNode::TEXT_NODE)
*fFormatter << child->getNodeValue();
else if(child->getNodeType()==DOMNode::ENTITY_REFERENCE_NODE)
*fFormatter << XMLFormatter::NoEscapes
<< chAmpersand << child->getNodeName() << chSemiColon
<< XMLFormatter::AttrEscapes;
child = child->getNextSibling();
}
}
else
*fFormatter << attribute->getNodeValue();
*fFormatter << XMLFormatter::NoEscapes
} // end of for
} // end of FILTER_ACCEPT
level++;
// FILTER_SKIP may start from here
//
// Test for the presence of children, which includes both
// text content and nested elements.
//
Neil Graham
committed
DOMNodeSPtr child = nodeToWrite->getFirstChild();
if (child != 0)
{
// There are children. Close start-tag, and output children.
// No escapes are legal here
if (filterAction == DOMNodeFilter::FILTER_ACCEPT)
*fFormatter << XMLFormatter::NoEscapes << chCloseAngle;
processNode(child, level);
child = child->getNextSibling();
}
level--;
if (filterAction == DOMNodeFilter::FILTER_ACCEPT)
{
//if we are not on the same line as when we started
//this node then print a new line and indent
if(nodeLine != fCurrentLine)
{
if (!lineFeedInTextNodePrinted)
{
printNewLine();
}
else
{
lineFeedInTextNodePrinted = false;
}
if(nodeLine != fCurrentLine && level == 0)