tokenizer.h

简单的xml解析类

//************************************************************************************************************************** 
//* Blue Xml Extension
//* Copyright (c) 2002-2004 Josh Harler
//* 
//* Blue - General Purpose C++ Library
//* Copyright (c) 2002-2004 Josh Harler
//* 
//* This software is provided 'as-is', without any express or implied warranty. In no event
//* will the authors be held liable for any damages arising from the use of this software.
//* 
//* Permission is granted to anyone to use this software for any purpose, including commercial
//* applications, and to alter it and redistribute it freely, subject to the following restrictions:
//* 
//* 	1. The origin of this software must not be misrepresented; you must not claim that you
//* 	wrote the original software. If you use this software in a product, an acknowledgment in the
//* 	product documentation would be appreciated but is not required.
//* 
//* 	2. Altered source versions must be plainly marked as such, and must not be misrepresented as
//* 	being the original software.
//* 
//* 	3. This notice may not be removed or altered from any source distribution.
//*
//*
//* file   Blue/Extension/Xml/internal/Tokenizer.h
//**

#ifndef __blue_ext_xml_Tokenizer_h_included__
#define __blue_ext_xml_Tokenizer_h_included__

// Public Headers ==========================================================================================================

// Extension headers
#include "../Xml.h"

// Blue library headers
#include "Blue/Data/InputStream.h"


// Public Defines/Enums/Typedefs/Etc. ======================================================================================

// Public Classes/Structs ==================================================================================================

namespace blue {
namespace ext {
namespace xml {

	/****
	 * \class Tokenizer
	 * \brief Breaks data received into XML tokens.
	 * \ingroup Xml
	 */
	class Tokenizer
	{
	public:

		/**
		 * Identifies the type of token being returned.
		 */
		enum token_type_e
		{
			TOKEN_UNKNOWN,      // The token type is unknown
			TOKEN_BRACKET_L,    // Left bracket: '<'
			TOKEN_BRACKET_R,    // Right bracket: '>'
			TOKEN_SLASH,        // Slash: '/'
			TOKEN_EQUALS,       // Equal sign: '='
			TOKEN_QUOTED,       // Quoted text.  The text returned is not quoted, but was in the stream.
			TOKEN_QUESTION,     // Question mark: '?'
			TOKEN_EXCLAMATION,  // Exclamation point: '!'
			TOKEN_WHITESPACE,   // Whitespace: ' ', '\t', '\r', '\n'
			TOKEN_ALPHANUMERIC, // Alphanumeric
		};


		// ===========================================================
		//  creation/destruction
		// ===========================================================

		/** Constructor. */
		Tokenizer();
		/** Constructor. */
		Tokenizer( data::InputStream* input );

		/** Destructor. */
		~Tokenizer();


		// ===========================================================
		//  query
		// ===========================================================

		/** Returns the InputStream being read from. */
		data::InputStream* getInputStream() const;

		/** Returns the type of the given token. */
		token_type_e getTokenType( String token );


		// ===========================================================
		//  manipulation
		// ===========================================================

		/** Sets the InputStream to read from. */
		void setInputStream( data::InputStream* input );

		/**
		 * Reads from the InputStream and returns the next valid XML
		 * token.  If the InputStream cannot be read from, the given
		 * String variable will contain what was read and the function
		 * will return false.  In this case, if the InputStream will
		 * eventually have data to read again, the String passed back
		 * into the function during the next call should contain the
		 * value that was previously set to it.
		 */
		bool getNextToken( String& str, token_type_e& type );

		/**
		 * Passes over all data until the given text is encountered,
		 * returning the data skipped as the token.
		 */
		void readUntil( String text, bool ignoreQuotes, bool include = true );


	private:
		/**
		 * Copy constructor. Private because Tokenizers should not be
		 * manipulated by more than one instance.
		 */
		Tokenizer( const Tokenizer& );
		/** Private assignment operator. See copy constructor documentation. */
		const Tokenizer& operator=( const Tokenizer& );

		void writeToBuffer( uint8_t byte );

		String getBufferString( bool asConst = true );


		data::InputStream*  m_input;
		uint8_t             m_lastChar;
		String              m_readUntil;
		bool                m_readInclude;
		bool                m_readIgnoreQuotes;
		Buffer              m_buffer;
		int                 m_bufferIdx;
	};


	/****
	 * \class XmlTokenizeException
	 * \brief Thrown when tokenizer encounters an error.
	 * \ingroup XmlExceptions
	 */
	class XmlTokenizeException :public Exception
	{
	public:
		XmlTokenizeException( String desc )
			:Exception(desc) {}

		virtual String getException() const {
			return (String("XmlTokenizeException", String::STATIC));
		}
	};


}}}	// namespaces


// Public External Variables ===============================================================================================

// Public Function Prototypes ==============================================================================================

// Public Inline Functions =================================================================================================

#endif // include guard