XS-libgeos

 view release on metacpan or  search on metacpan

geos-3.7.3/tests/xmltester/tinyxml/tinyxmlparser.cpp  view on Meta::CPAN

		{
			if ( *p == '\r' || *p == '\n' )
			{
				whitespace = true;
				++p;
			}
			else if ( IsWhiteSpace( *p ) )
			{
				whitespace = true;
				++p;
			}
			else
			{
				// If we've found whitespace, add it before the
				// new character. Any whitespace just becomes a space.
				if ( whitespace )
				{
					(*text) += ' ';
					whitespace = false;
				}
				int len;
				char cArr[4] = { 0, 0, 0, 0 };
				p = GetChar( p, cArr, &len, encoding );
				if ( len == 1 )
					(*text) += cArr[0];	// more efficient
				else
					text->append( cArr, len );
			}
		}
	}
	if ( p ) 
		p += strlen( endTag );
	return p;
}

#ifdef TIXML_USE_STL

void TiXmlDocument::StreamIn( std::istream * in, TIXML_STRING * tag )
{
	// The basic issue with a document is that we don't know what we're
	// streaming. Read something presumed to be a tag (and hope), then
	// identify it, and call the appropriate stream method on the tag.
	//
	// This "pre-streaming" will never read the closing ">" so the
	// sub-tag can orient itself.

	if ( !StreamTo( in, '<', tag ) ) 
	{
		SetError( TIXML_ERROR_PARSING_EMPTY, 0, 0, TIXML_ENCODING_UNKNOWN );
		return;
	}

	while ( in->good() )
	{
		int tagIndex = (int) tag->length();
		while ( in->good() && in->peek() != '>' )
		{
			int c = in->get();
			if ( c <= 0 )
			{
				SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
				break;
			}
			(*tag) += (char) c;
		}

		if ( in->good() )
		{
			// We now have something we presume to be a node of 
			// some sort. Identify it, and call the node to
			// continue streaming.
			TiXmlNode* node = Identify( tag->c_str() + tagIndex, TIXML_DEFAULT_ENCODING );

			if ( node )
			{
				node->StreamIn( in, tag );
				bool isElement = node->ToElement() != 0;
				delete node;
				node = 0;

				// If this is the root element, we're done. Parsing will be
				// done by the >> operator.
				if ( isElement )
				{
					return;
				}
			}
			else
			{
				SetError( TIXML_ERROR, 0, 0, TIXML_ENCODING_UNKNOWN );
				return;
			}
		}
	}
	// We should have returned sooner.
	SetError( TIXML_ERROR, 0, 0, TIXML_ENCODING_UNKNOWN );
}

#endif

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, nullptr, nullptr, TIXML_ENCODING_UNKNOWN );
		return nullptr;
	}

	// 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;

geos-3.7.3/tests/xmltester/tinyxml/tinyxmlparser.cpp  view on Meta::CPAN

		returnNode = new TiXmlComment();
	}
	else if ( StringEqual( p, cdataHeader, false, encoding ) )
	{
		#ifdef DEBUG_PARSER
			TIXML_LOG( "XML parsing CDATA\n" );
		#endif
		TiXmlText* text = new TiXmlText( "" );
		text->SetCDATA( true );
		returnNode = text;
	}
	else if ( StringEqual( p, dtdHeader, false, encoding ) )
	{
		#ifdef DEBUG_PARSER
			TIXML_LOG( "XML parsing Unknown(1)\n" );
		#endif
		returnNode = new TiXmlUnknown();
	}
	else if (    IsAlpha( *(p+1), encoding )
			  || *(p+1) == '_' )
	{
		#ifdef DEBUG_PARSER
			TIXML_LOG( "XML parsing Element\n" );
		#endif
		returnNode = new TiXmlElement( "" );
	}
	else
	{
		#ifdef DEBUG_PARSER
			TIXML_LOG( "XML parsing Unknown(2)\n" );
		#endif
		returnNode = new TiXmlUnknown();
	}

	if ( returnNode )
	{
		// Set the parent, so it can report errors
		returnNode->parent = this;
	}
	else
	{
		if ( doc )
			doc->SetError( TIXML_ERROR_OUT_OF_MEMORY, nullptr, nullptr, TIXML_ENCODING_UNKNOWN );
	}
	return returnNode;
}

#ifdef TIXML_USE_STL

void TiXmlElement::StreamIn (std::istream * in, TIXML_STRING * tag)
{
	// We're called with some amount of pre-parsing. That is, some of "this"
	// element is in "tag". Go ahead and stream to the closing ">"
	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 == '>' )
			break;
	}

	if ( tag->length() < 3 ) return;

	// Okay...if we are a "/>" tag, then we're done. We've read a complete tag.
	// If not, identify and stream.

	if (    tag->at( tag->length() - 1 ) == '>' 
		 && tag->at( tag->length() - 2 ) == '/' )
	{
		// All good!
		return;
	}
	else if ( tag->at( tag->length() - 1 ) == '>' )
	{
		// There is more. Could be:
		//		text
		//		cdata text (which looks like another node)
		//		closing tag
		//		another node.
		for ( ;; )
		{
			StreamWhiteSpace( in, tag );

			// Do we have text?
			if ( in->good() && in->peek() != '<' ) 
			{
				// Yep, text.
				TiXmlText text( "" );
				text.StreamIn( in, tag );

				// What follows text is a closing tag or another node.
				// Go around again and figure it out.
				continue;
			}

			// We now have either a closing tag...or another node.
			// We should be at a "<", regardless.
			if ( !in->good() ) return;
			assert( in->peek() == '<' );
			int tagIndex = (int) tag->length();

			bool closingTag = false;
			bool firstCharFound = false;

			for( ;; )
			{
				if ( !in->good() )
					return;

				int c = in->peek();
				if ( c <= 0 )
				{
					TiXmlDocument* document = GetDocument();
					if ( document )
						document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
					return;
				}
				
				if ( c == '>' )
					break;

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

				// Early out if we find the CDATA id.
				if ( c == '[' && tag->size() >= 9 )
				{
					size_t len = tag->size();
					const char* start = tag->c_str() + len - 9;
					if ( strcmp( start, "<![CDATA[" ) == 0 ) {
						assert( !closingTag );
						break;
					}
				}

				if ( !firstCharFound && c != '<' && !IsWhiteSpace( c ) )
				{
					firstCharFound = true;
					if ( c == '/' )
						closingTag = true;
				}
			}
			// If it was a closing tag, then read in the closing '>' to clean up the input stream.
			// If it was not, the streaming will be done by the tag.
			if ( closingTag )
			{
				if ( !in->good() )
					return;

				int c = in->get();
				if ( c <= 0 )
				{
					TiXmlDocument* document = GetDocument();
					if ( document )
						document->SetError( TIXML_ERROR_EMBEDDED_NULL, 0, 0, TIXML_ENCODING_UNKNOWN );
					return;
				}
				assert( c == '>' );
				*tag += (char) c;

				// We are done, once we've found our closing tag.
				return;
			}
			else
			{
				// If not a closing tag, id it, and stream.
				const char* tagloc = tag->c_str() + tagIndex;
				TiXmlNode* node = Identify( tagloc, TIXML_DEFAULT_ENCODING );
				if ( !node )
					return;
				node->StreamIn( in, tag );
				delete node;
				node = 0;

				// No return: go around from the beginning: text, closing tag, or node.
			}
		}
	}
}
#endif

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

	if ( !p || !*p )
	{
		if ( document ) document->SetError( TIXML_ERROR_PARSING_ELEMENT, nullptr, nullptr, encoding );
		return nullptr;
	}

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

	if ( *p != '<' )
	{
		if ( document ) document->SetError( TIXML_ERROR_PARSING_ELEMENT, p, data, encoding );
		return nullptr;
	}

	p = SkipWhiteSpace( p+1, encoding );

	// Read the name.
	const char* pErr = p;

    p = ReadName( p, &value, encoding );
	if ( !p || !*p )
	{
		if ( document )	document->SetError( TIXML_ERROR_FAILED_TO_READ_ELEMENT_NAME, pErr, data, encoding );
		return nullptr;
	}

geos-3.7.3/tests/xmltester/tinyxml/tinyxmlparser.cpp  view on Meta::CPAN

			{
				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 nullptr;
				}
			}
		}
		pWithWhiteSpace = p;
		p = SkipWhiteSpace( p, encoding );
	}

	if ( !p )
	{
		if ( document ) document->SetError( TIXML_ERROR_READING_ELEMENT_VALUE, nullptr, nullptr, encoding );
	}	
	return p;
}


#ifdef TIXML_USE_STL
void TiXmlUnknown::StreamIn( std::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 nullptr;
	}
	++p;
    value = "";

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

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

#ifdef TIXML_USE_STL
void TiXmlComment::StreamIn( std::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 nullptr;
	}
	p += strlen( startTag );

	// [ 1475201 ] TinyXML parses entities in comments
	// Oops - ReadText doesn't work, because we don't want to parse the entities.
	// p = ReadText( p, &value, false, endTag, false, encoding );
	//
	// from the XML spec:
	/*
	 [Definition: Comments may appear anywhere in a document outside other markup; in addition, 
	              they may appear within the document type declaration at places allowed by the grammar. 
				  They are not part of the document's character data; an XML processor MAY, but need not, 
				  make it possible for an application to retrieve the text of comments. For compatibility, 
				  the string "--" (double-hyphen) MUST NOT occur within comments.] Parameter entity 
				  references MUST NOT be recognized within comments.

				  An example of a comment:

				  <!-- declarations for <head> & <body> -->
	*/

    value = "";
	// Keep all the white space.
	while (	p && *p && !StringEqual( p, endTag, false, encoding ) )

geos-3.7.3/tests/xmltester/tinyxml/tinyxmlparser.cpp  view on Meta::CPAN

	if ( !p || !*p )
	{
		if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, p, data, encoding );
		return nullptr;
	}
	
	const char* end;
	const char SINGLE_QUOTE = '\'';
	const char DOUBLE_QUOTE = '\"';

	if ( *p == SINGLE_QUOTE )
	{
		++p;
		end = "\'";		// single quote in string
		p = ReadText( p, &value, false, end, false, encoding );
	}
	else if ( *p == DOUBLE_QUOTE )
	{
		++p;
		end = "\"";		// double quote in string
		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
		{
			if ( *p == SINGLE_QUOTE || *p == DOUBLE_QUOTE ) {
				// [ 1451649 ] Attribute values with trailing quotes not handled correctly
				// We did not have an opening quote but seem to have a 
				// closing one. Give up and throw an error.
				if ( document ) document->SetError( TIXML_ERROR_READING_ATTRIBUTES, p, data, encoding );
				return nullptr;
			}
			value += *p;
			++p;
		}
	}
	return p;
}

#ifdef TIXML_USE_STL
void TiXmlText::StreamIn( std::istream * in, TIXML_STRING * tag )
{
	while ( in->good() )
	{
		int c = in->peek();	
		if ( !cdata && (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();	// "commits" the peek made above

		if ( cdata && c == '>' && tag->size() >= 3 ) {
			size_t len = tag->size();
			if ( (*tag)[len-2] == ']' && (*tag)[len-3] == ']' ) {
				// terminator of cdata.
				return;
			}
		}    
	}
}
#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 nullptr;
		}
		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 nullptr;
	}
}

#ifdef TIXML_USE_STL
void TiXmlDeclaration::StreamIn( std::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, nullptr, nullptr, _encoding );
		return nullptr;
	}
	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 );		



( run in 0.907 second using v1.01-cache-2.11-cpan-0b58ddf2af1 )