const char* TiXmlElement::ReadValue( const char* p, TiXmlParsingData* data, TiXmlEncoding encoding )
{
TiXmlDocument* document = GetDocument();
// Read in text and elements in any order.
const char* pWithWhiteSpace = p;
p = SkipWhiteSpace( p, encoding );
while ( p && *p )
{
if ( *p != '<' )
{
// Take what we have, make a text element.
TiXmlText* textNode = new TiXmlText( "" );
if ( !textNode )
{
return 0;
}
if ( TiXmlBase::IsWhiteSpaceCondensed() )
{
p = textNode->Parse( p, data, encoding );
}
else
{
// Special case: we want to keep the white space
// so that leading spaces aren't removed.
p = textNode->Parse( pWithWhiteSpace, data, encoding );
}
if ( !textNode->Blank() )
LinkEndChild( textNode );
else
delete textNode;
}
else
{
// We hit a '<'
// Have we hit a new element or an end tag? This could also be
// a TiXmlText in the "CDATA" style.
if ( StringEqual( p, "</", false, encoding ) )
{
return p;
}
else
{
TiXmlNode* node = Identify( p, encoding );
if ( node )
{
p = node->Parse( p, data, encoding );
LinkEndChild( node );
}
else
{
return 0;
}
}
}
pWithWhiteSpace = p;
p = SkipWhiteSpace( p, encoding );
}
if ( !p )
{
if ( document ) document->SetError( TIXML_ERROR_READING_ELEMENT_VALUE, 0, 0, encoding );
}
return p;
}
const char* TiXmlDocument::Parse( const char* p, TiXmlParsingData* prevData, TiXmlEncoding encoding )
{
ClearError();
// Parse away, at the document level. Since a document
// contains nothing but other tags, most of what happens
// here is skipping white space.
if ( !p || !*p )
{
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, TIXML_ENCODING_UNKNOWN );
return 0;
}
// Note that, for a document, this needs to come
// before the while space skip, so that parsing
// starts from the pointer we are given.
location.Clear();
if ( prevData )
{
location.row = prevData->cursor.row;
location.col = prevData->cursor.col;
}
else
{
location.row = 0;
location.col = 0;
}
TiXmlParsingData data( p, TabSize(), location.row, location.col );
location = data.Cursor();
if ( encoding == TIXML_ENCODING_UNKNOWN )
{
// Check for the Microsoft UTF-8 lead bytes.
const unsigned char* pU = (const unsigned char*)p;
if ( *(pU+0) && *(pU+0) == TIXML_UTF_LEAD_0
&& *(pU+1) && *(pU+1) == TIXML_UTF_LEAD_1
&& *(pU+2) && *(pU+2) == TIXML_UTF_LEAD_2 )
{
encoding = TIXML_ENCODING_UTF8;
useMicrosoftBOM = true;
}
}
p = SkipWhiteSpace( p, encoding );
if ( !p )
{
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, TIXML_ENCODING_UNKNOWN );
return 0;
}
while ( p && *p )
{
TiXmlNode* node = Identify( p, encoding );
if ( node )
{
p = node->Parse( p, &data, encoding );
LinkEndChild( node );
}
else
{
break;
}
// Did we get encoding info?
if ( encoding == TIXML_ENCODING_UNKNOWN
&& node->ToDeclaration() )
{
TiXmlDeclaration* dec = node->ToDeclaration();
const char* enc = dec->Encoding();
assert( enc );
if ( *enc == 0 )
encoding = TIXML_ENCODING_UTF8;
else if ( StringEqual( enc, "UTF-8", true, TIXML_ENCODING_UNKNOWN ) )
encoding = TIXML_ENCODING_UTF8;
else if ( StringEqual( enc, "UTF8", true, TIXML_ENCODING_UNKNOWN ) )
encoding = TIXML_ENCODING_UTF8; // incorrect, but be nice
else
encoding = TIXML_ENCODING_LEGACY;
}
p = SkipWhiteSpace( p, encoding );
}
// Was this empty?
if ( !firstChild ) {
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, encoding );
return 0;
}
// All is well.
return p;
}
const char* TiXmlDocument::Parse
( const char* p, TiXmlParsingData* prevData, TiXmlEncoding encoding )
{
ClearError();
// Parse away, at the document level. Since a document
// contains nothing but other tags, most of what happens
// here is skipping white space.
// sherm 100319: I changed this so that untagged top-level text is
// parsed as a Text node rather than a parsing error. CDATA text was
// already allowed at the top level so this seems more consistent.
if ( !p || !*p )
{
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, TIXML_ENCODING_UNKNOWN );
return 0;
}
// Note that, for a document, this needs to come
// before the while space skip, so that parsing
// starts from the pointer we are given.
location.Clear();
if ( prevData )
{
location.row = prevData->cursor.row;
location.col = prevData->cursor.col;
}
else
{
location.row = 0;
location.col = 0;
}
TiXmlParsingData data( p, TabSize(), location.row, location.col );
location = data.Cursor();
if ( encoding == TIXML_ENCODING_UNKNOWN )
{
// Check for the Microsoft UTF-8 lead bytes.
const unsigned char* pU = (const unsigned char*)p;
if ( *(pU+0) && *(pU+0) == TIXML_UTF_LEAD_0
&& *(pU+1) && *(pU+1) == TIXML_UTF_LEAD_1
&& *(pU+2) && *(pU+2) == TIXML_UTF_LEAD_2 )
{
encoding = TIXML_ENCODING_UTF8;
useMicrosoftBOM = true;
}
}
// Remember the start of white space in case we end up reading a text
// element in a "keep white space" mode.
const char* pWithWhiteSpace = p;
p = SkipWhiteSpace( p, encoding );
if ( !p )
{
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, TIXML_ENCODING_UNKNOWN );
return 0;
}
// sherm 100319: ignore all but the first Declaration
bool haveSeenDeclaration = false;
while ( p && *p )
{
TiXmlNode* node = 0;
if ( *p != '<' )
{ // sherm 100319: I added this case by stealing the code from
// Element parsing; see above comment.
// Take what we have, make a text element.
TiXmlText* textNode = new TiXmlText( "" );
if ( !textNode )
{
SetError( TIXML_ERROR_OUT_OF_MEMORY, 0, 0, encoding );
return 0;
}
if ( TiXmlBase::IsWhiteSpaceCondensed() )
{
p = textNode->Parse( p, &data, encoding );
}
else
{
// Special case: we want to keep the white space
// so that leading spaces aren't removed.
p = textNode->Parse( pWithWhiteSpace, &data, encoding );
}
if ( !textNode->Blank() ) {
LinkEndChild( textNode );
node = textNode;
}
else
delete textNode;
}
else // We saw a '<', now identify what kind of tag it is.
{
TiXmlNode* node = Identify( p, encoding );
if ( node )
{
p = node->Parse( p, &data, encoding );
if (node->ToDeclaration()) {
if (haveSeenDeclaration) {
delete node; node=0; // ignore duplicate Declaration
} else
haveSeenDeclaration = true;
}
if (node)
LinkEndChild( node );
}
else
{
// If Identify fails then no further parsing is possible.
break;
}
}
// Did we get encoding info?
if ( encoding == TIXML_ENCODING_UNKNOWN
&& node && node->ToDeclaration() )
{
TiXmlDeclaration* dec = node->ToDeclaration();
const char* enc = dec->Encoding();
assert( enc );
if ( *enc == 0 )
encoding = TIXML_ENCODING_UTF8;
else if ( StringEqual( enc, "UTF-8", true, TIXML_ENCODING_UNKNOWN ) )
encoding = TIXML_ENCODING_UTF8;
else if ( StringEqual( enc, "UTF8", true, TIXML_ENCODING_UNKNOWN ) )
encoding = TIXML_ENCODING_UTF8; // incorrect, but be nice
else
encoding = TIXML_ENCODING_LEGACY;
}
pWithWhiteSpace = p;
p = SkipWhiteSpace( p, encoding );
}
// Was this empty?
if ( !firstChild ) {
SetError( TIXML_ERROR_DOCUMENT_EMPTY, 0, 0, encoding );
return 0;
}
// All is well.
return p;
}