textencoding.h

This software aims to create an applet and panel tools to manage a wireless interface card, such as

//
// TextEncoding.h
//
// $Id: //poco/Main/Foundation/include/Foundation/TextEncoding.h#5 $
//
// Definition of the abstract TextEncoding class.
//
// Copyright (c) 2004, Guenter Obiltschnig/Applied Informatics.
// All rights reserved.
// 
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// 
// 1. Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
// 
// 2. Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
// 
// 3. Redistributions in any form must be accompanied by information on
//    how to obtain complete source code for this software and any
//    accompanying software that uses this software.  The source code
//    must either be included in the distribution or be available for no
//    more than the cost of distribution plus a nominal fee, and must be
//    freely redistributable under reasonable conditions.  For an
//    executable file, complete source code means the source code for all
//    modules it contains.  It does not include source code for modules or
//    files that typically accompany the major components of the operating
//    system on which the executable file runs.
// 
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
// FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
// COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
// INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
// BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
// LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
// LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
// ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
// POSSIBILITY OF SUCH DAMAGE.
//


#ifndef Foundation_TextEncoding_INCLUDED
#define Foundation_TextEncoding_INCLUDED


#ifndef Foundation_Foundation_INCLUDED
#include "Foundation/Foundation.h"
#endif


Foundation_BEGIN


class Foundation_API TextEncoding
	/// An abstract base class for implementing text encodings
	/// like UTF-8 or ISO 8859-1. 
	///
	/// Subclasses must override the characterMap() and convert()
	/// methods.
{
public:
	enum
	{
		MAX_SEQUENCE_LENGTH = 6 /// The maximum character byte sequence length supported.
	};
	
	typedef int CharacterMap[256];
		/// The map[b] member gives information about byte sequences
		/// whose first byte is b.
		/// If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar value c.
		/// If map[b] is -1, then the byte sequence is malformed.
		/// If map[b] is -n, where n >= 2, then b is the first byte of an n-byte
		/// sequence that encodes a single Unicode scalar value. Byte sequences up
		/// to 6 bytes in length are supported.

	virtual ~TextEncoding();
		/// Destroys the encoding.
			
	virtual const CharacterMap& characterMap() const = 0;
		/// Returns the CharacterMap for the encoding.
		/// The CharacterMap should be kept in a static member. As
		/// characterMap() can be called frequently, it should be
		/// implemented in such a way that it just returns a static
		/// map. If the map is built at runtime, this should be
		/// done in the constructor.
		
	virtual int convert(const unsigned char* bytes) const;
		/// The convert function is used to convert multibyte sequences;
		/// bytes will point to a byte sequence of n bytes where 
		/// getCharacterMap()[*bytes] == -n.
		///
		/// The convert function must return the Unicode scalar value
		/// represented by this byte sequence or -1 if the byte sequence is malformed.
		/// The default implementation returns (int) bytes[0].

	virtual int convert(int ch, unsigned char* bytes, int length) const;
		/// Transform the Unicode character ch into the encoding's 
		/// byte sequence. The method returns the number of bytes
		/// used. The method must not use more than length characters.
		/// Bytes and length can also be null - in this case only the number
		/// of bytes required to represent ch is returned.
		/// If the character cannot be converted, 0 is returned and
		/// the byte sequence remains unchanged.
		/// The default implementation simply returns 0.
};


Foundation_END


#endif // Foundation_TextEncoding_INCLUDED