tinyxmlparser.cpp

xml 简单解析器

	}

    TIXML_STRING endTag ("</");
	endTag += value;
	endTag += ">";

	// Check for and read attributes. Also look for an empty
	// tag or an end tag.
	while ( p && *p )
	{
		pErr = p;
		p = SkipWhiteSpace( p, encoding );
		if ( !p || !*p )
		{
			if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, pErr, data, encoding );
			return 0;
		}
		if ( *p == '/' )
		{
			++p;
			// Empty tag.
			if ( *p  != '>' )
			{
				if ( document ) document->SetError( TIXML_ERROR_PARSING_EMPTY, p, data, encoding );		
				return 0;
			}
			return (p+1);
		}
		else if ( *p == '>' )
		{
			// Done with attributes (if there were any.)
			// Read the value -- which can include other
			// elements -- read the end tag, and return.
			++p;
			p = ReadValue( p, data, encoding );		// Note this is an Element method, and will set the error if one happens.
			if ( !p || !*p )
				return 0;

			// We should find the end tag now
			if ( StringEqual( p, endTag.c_str(), false, encoding ) )
			{
				p += endTag.length();
				return p;
			}
			else
			{
				if ( document ) document->SetError( TIXML_ERROR_READING_END_TAG, p, data, encoding );
				return 0;
			}
		}
		else
		{
			// Try to read an attribute:
			TiXmlAttribute* attrib = new TiXmlAttribute();
			if ( !attrib )
			{
				if ( document ) document->SetError( TIXML_ERROR_OUT_OF_MEMORY, pErr, data, encoding );
				return 0;
			}

			attrib->SetDocument( document );
			const char* pErr = p;
			p = attrib->Parse( p, data, encoding );

			if ( !p || !*p )
			{
				if ( document ) document->SetError( TIXML_ERROR_PARSING_ELEMENT, pErr, data, encoding );
				delete attrib;
				return 0;
			}

			// Handle the strange case of double attributes:
			TiXmlAttribute* node = attributeSet.Find( attrib->NameTStr() );
			if ( node )
			{
				node->SetValue( attrib->Value() );
				delete attrib;
				return 0;
			}

			attributeSet.Add( attrib );
		}
	}
	return p;
}


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 )
			{
				if ( document ) document->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 );
			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;
}


#ifdef TIXML_USE_STL
void TiXmlUnknown::StreamIn( TIXML_ISTREAM * in, TIXML_STRING * tag )
{
	while ( in->good() )
	{
		int c = in->get();	
		if ( c <= 0 )
		{
			TiXmlDocument* document = GetDocument();
			if ( document )
				document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
			return;
		}
		(*tag) += (char) c;

		if ( c == '>' )
		{
			// All is well.
			return;		
		}
	}
}
#endif


const char* TiXmlUnknown::Parse( const char* p, TiXmlParsingData* data, TiXmlEncoding encoding )
{
	TiXmlDocument* document = GetDocument();
	p = SkipWhiteSpace( p, encoding );

	if ( data )
	{
		data->Stamp( p, encoding );
		location = data->Cursor();
	}
	if ( !p || !*p || *p != '<' )
	{
		if ( document ) document->SetError( TIXML_ERROR_PARSING_UNKNOWN, p, data, encoding );
		return 0;
	}
	++p;
    value = "";

	while ( p && *p && *p != '>' )
	{
		value += *p;
		++p;
	}

	if ( !p )
	{
		if ( document )	document->SetError( TIXML_ERROR_PARSING_UNKNOWN, 0, 0, encoding );
	}
	if ( *p == '>' )
		return p+1;
	return p;
}

#ifdef TIXML_USE_STL
void TiXmlComment::StreamIn( TIXML_ISTREAM * in, TIXML_STRING * tag )
{
	while ( in->good() )
	{
		int c = in->get();	
		if ( c <= 0 )
		{
			TiXmlDocument* document = GetDocument();
			if ( document )
				document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
			return;
		}

		(*tag) += (char) c;

		if ( c == '>' 
			 && tag->at( tag->length() - 2 ) == '-'
			 && tag->at( tag->length() - 3 ) == '-' )
		{
			// All is well.
			return;		
		}
	}
}
#endif


const char* TiXmlComment::Parse( const char* p, TiXmlParsingData* data, TiXmlEncoding encoding )
{
	TiXmlDocument* document = GetDocument();
	value = "";

	p = SkipWhiteSpace( p, encoding );

	if ( data )
	{
		data->Stamp( p, encoding );
		location = data->Cursor();
	}
	const char* startTag = "<!--";
	const char* endTag   = "-->";

	if ( !StringEqual( p, startTag, false, encoding ) )
	{
		document->SetError( TIXML_ERROR_PARSING_COMMENT, p, data, encoding );
		return 0;
	}
	p += strlen( startTag );
	p = ReadText( p, &value, false, endTag, false, encoding );
	return p;
}


const char* TiXmlAttribute::Parse( const char* p, TiXmlParsingData* data, TiXmlEncoding encoding )
{
	p = SkipWhiteSpace( p, encoding );
	if ( !p || !*p ) return 0;

	int tabsize = 4;
	if ( document )
		tabsize = document->TabSize();

	if ( data )
	{
		data->Stamp( p, encoding );
		location = data->Cursor();
	}
	// Read the name, the '=' and the value.
	const char* pErr = p;
	p = ReadName( p, &name, encoding );
	if ( !p || !*p )
	{
		if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, pErr, data, encoding );
		return 0;
	}
	p = SkipWhiteSpace( p, encoding );
	if ( !p || !*p || *p != '=' )
	{
		if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, p, data, encoding );
		return 0;
	}

	++p;	// skip '='
	p = SkipWhiteSpace( p, encoding );
	if ( !p || !*p )
	{
		if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, p, data, encoding );
		return 0;
	}
	
	const char* end;

	if ( *p == '\'' )
	{
		++p;
		end = "\'";
		p = ReadText( p, &value, false, end, false, encoding );
	}
	else if ( *p == '"' )
	{
		++p;
		end = "\"";
		p = ReadText( p, &value, false, end, false, encoding );
	}
	else
	{
		// All attribute values should be in single or double quotes.
		// But this is such a common error that the parser will try
		// its best, even without them.
		value = "";
		while (    p && *p										// existence
				&& !IsWhiteSpace( *p ) && *p != '\n' && *p != '\r'	// whitespace
				&& *p != '/' && *p != '>' )						// tag end
		{
			value += *p;
			++p;
		}
	}
	return p;
}

#ifdef TIXML_USE_STL
void TiXmlText::StreamIn( TIXML_ISTREAM * in, TIXML_STRING * tag )
{
	if ( cdata )
	{
		int c = in->get();	
		if ( c <= 0 )
		{
			TiXmlDocument* document = GetDocument();
			if ( document )
				document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
			return;
		}

		(*tag) += (char) c;

		if ( c == '>' 
			 && tag->at( tag->length() - 2 ) == ']'
			 && tag->at( tag->length() - 3 ) == ']' )
		{
			// All is well.
			return;		
		}
	}
	else
	{
		while ( in->good() )
		{
			int c = in->peek();	
			if ( c == '<' )
				return;
			if ( c <= 0 )
			{
				TiXmlDocument* document = GetDocument();
				if ( document )
					document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
				return;
			}

			(*tag) += (char) c;
			in->get();
		}
	}
}
#endif

const char* TiXmlText::Parse( const char* p, TiXmlParsingData* data, TiXmlEncoding encoding )
{
	value = "";
	TiXmlDocument* document = GetDocument();

	if ( data )
	{
		data->Stamp( p, encoding );
		location = data->Cursor();
	}

	const char* const startTag = "<![CDATA[";
	const char* const endTag   = "]]>";

	if ( cdata || StringEqual( p, startTag, false, encoding ) )
	{
		cdata = true;

		if ( !StringEqual( p, startTag, false, encoding ) )
		{
			document->SetError( TIXML_ERROR_PARSING_CDATA, p, data, encoding );
			return 0;
		}
		p += strlen( startTag );

		// Keep all the white space, ignore the encoding, etc.
		while (	   p && *p
				&& !StringEqual( p, endTag, false, encoding )
			  )
		{
			value += *p;
			++p;
		}

		TIXML_STRING dummy; 
		p = ReadText( p, &dummy, false, endTag, false, encoding );
		return p;
	}
	else
	{
		bool ignoreWhite = true;

		const char* end = "<";
		p = ReadText( p, &value, ignoreWhite, end, false, encoding );
		if ( p )
			return p-1;	// don't truncate the '<'
		return 0;
	}
}

#ifdef TIXML_USE_STL
void TiXmlDeclaration::StreamIn( TIXML_ISTREAM * in, TIXML_STRING * tag )
{
	while ( in->good() )
	{
		int c = in->get();
		if ( c <= 0 )
		{
			TiXmlDocument* document = GetDocument();
			if ( document )
				document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
			return;
		}
		(*tag) += (char) c;

		if ( c == '>' )
		{
			// All is well.
			return;
		}
	}
}
#endif

const char* TiXmlDeclaration::Parse( const char* p, TiXmlParsingData* data, TiXmlEncoding _encoding )
{
	p = SkipWhiteSpace( p, _encoding );
	// Find the beginning, find the end, and look for
	// the stuff in-between.
	TiXmlDocument* document = GetDocument();
	if ( !p || !*p || !StringEqual( p, "<?xml", true, _encoding ) )
	{
		if ( document ) document->SetError( TIXML_ERROR_PARSING_DECLARATION, 0, 0, _encoding );
		return 0;
	}
	if ( data )
	{
		data->Stamp( p, _encoding );
		location = data->Cursor();
	}
	p += 5;

	version = "";
	encoding = "";
	standalone = "";

	while ( p && *p )
	{
		if ( *p == '>' )
		{
			++p;
			return p;
		}

		p = SkipWhiteSpace( p, _encoding );
		if ( StringEqual( p, "version", true, _encoding ) )
		{
			TiXmlAttribute attrib;
			p = attrib.Parse( p, data, _encoding );		
			version = attrib.Value();
		}
		else if ( StringEqual( p, "encoding", true, _encoding ) )
		{
			TiXmlAttribute attrib;
			p = attrib.Parse( p, data, _encoding );		
			encoding = attrib.Value();
		}
		else if ( StringEqual( p, "standalone", true, _encoding ) )
		{
			TiXmlAttribute attrib;
			p = attrib.Parse( p, data, _encoding );		
			standalone = attrib.Value();
		}
		else
		{
			// Read over whatever it is.
			while( p && *p && *p != '>' && !IsWhiteSpace( *p ) )
				++p;
		}
	}
	return 0;
}

bool TiXmlText::Blank() const
{
	for ( unsigned i=0; i<value.length(); i++ )
		if ( !IsWhiteSpace( value[i] ) )
			return false;
	return true;
}