//
// UTF8Encoding.h
//
// $Id: //poco/1.3/Foundation/include/Poco/UTF8Encoding.h#6 $
//
// Library: Foundation
// Package: Text
// Module:  UTF8Encoding
//
// Definition of the UTF8Encoding class.
//
// Copyright (c) 2004-2007, Applied Informatics Software Engineering GmbH.
// and Contributors.
//
// Permission is hereby granted, free of charge, to any person or organization
// obtaining a copy of the software and accompanying documentation covered by
// this license (the "Software") to use, reproduce, display, distribute,
// execute, and transmit the Software, and to prepare derivative works of the
// Software, and to permit third-parties to whom the Software is furnished to
// do so, all subject to the following:
// 
// The copyright notices in the Software and this entire statement, including
// the above license grant, this restriction and the following disclaimer,
// must be included in all copies of the Software, in whole or in part, and
// all derivative works of the Software, unless such copies or derivative
// works are solely in the form of machine-executable object code generated by
// a source language processor.
// 
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
// SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
// FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
// ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
// DEALINGS IN THE SOFTWARE.
//


#ifndef Foundation_UTF8Encoding_INCLUDED
#define Foundation_UTF8Encoding_INCLUDED


#include "Poco/Foundation.h"
#include "Poco/TextEncoding.h"


namespace Poco {


class Foundation_API UTF8Encoding: public TextEncoding
	/// UTF-8 text encoding, as defined in RFC 2279.
{
public:
	UTF8Encoding();
	~UTF8Encoding();
	const char* canonicalName() const;
	bool isA(const std::string& encodingName) const;
	const CharacterMap& characterMap() const;
	int convert(const unsigned char* bytes) const;
	int convert(int ch, unsigned char* bytes, int length) const;
	int queryConvert(const unsigned char* bytes, int length) const;
	int sequenceLength(const unsigned char* bytes, int length) const;

	static bool isLegal(const unsigned char *bytes, int length);
		/// Utility routine to tell whether a sequence of bytes is legal UTF-8.
		/// This must be called with the length pre-determined by the first byte.
		/// The sequence is illegal right away if there aren't enough bytes 
		/// available. If presented with a length > 4, this function returns false.
		/// The Unicode definition of UTF-8 goes up to 4-byte sequences.
		/// 
		/// Adapted from ftp://ftp.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.c
		/// Copyright 2001-2004 Unicode, Inc.

private:
	static const char* _names[];
	static const CharacterMap _charMap;
};


} // namespace Poco


#endif // Foundation_UTF8Encoding_INCLUDED