williamr@2: // Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies).
williamr@2: // All rights reserved.
williamr@2: // This component and the accompanying materials are made available
williamr@2: // under the terms of the License "Symbian Foundation License v1.0" to Symbian Foundation members and "Symbian Foundation End User License Agreement v1.0" to non-members
williamr@2: // which accompanies this distribution, and is available
williamr@2: // at the URL "http://www.symbianfoundation.org/legal/licencesv10.html".
williamr@2: //
williamr@2: // Initial Contributors:
williamr@2: // Nokia Corporation - initial contribution.
williamr@2: //
williamr@2: // Contributors:
williamr@2: //
williamr@2: // Description:
williamr@2: //
williamr@2: 
williamr@2: #if !defined(__UTF_H__)
williamr@2: #define __UTF_H__
williamr@2: 
williamr@2: #if !defined(__E32STD_H__)
williamr@2: #include <e32std.h>
williamr@2: #endif
williamr@2: 
williamr@2: 
williamr@2: class CnvUtfConverter
williamr@2: /** 
williamr@2: Converts text between Unicode (UCS-2) and the two Unicode transformation 
williamr@2: formats UTF-7 and UTF-8. There are no functions to convert directly between 
williamr@2: UTF-7 and UTF-8.
williamr@2: 
williamr@2: Objects of this class do not need to be created because all the member functions 
williamr@2: are static. The four functions are passed text in the second argument and 
williamr@2: output the resulting text in the first argument. Sixteen-bit descriptors are 
williamr@2: used to hold text encoded in UCS-2 (i.e. normal 16 bit Unicode), and eight-bit 
williamr@2: descriptors are used to hold text encoded in either of the transformation 
williamr@2: formats.
williamr@2: 
williamr@2: The conversion functions return the number of characters which were not converted 
williamr@2: because the output descriptor was not long enough to hold all of the converted 
williamr@2: text. This allows users of this class to perform partial conversions on an 
williamr@2: input descriptor, handling the case when the input descriptor is truncated 
williamr@2: mid way through a multi-byte character. The caller does not have to guess 
williamr@2: how big to make the output descriptor for a given input descriptor- they 
williamr@2: can simply do the conversion in a loop using a small output descriptor. The 
williamr@2: ability to handle truncated descriptors is particularly useful if the caller 
williamr@2: is receiving information in chunks from an external source. 
williamr@2: @publishedAll
williamr@2: @released
williamr@2: */
williamr@2: 	{
williamr@2: public:
williamr@2: 	/** Conversion error flags. At this stage there is only one error flag 
williamr@2: 	- others may be added in the future. */
williamr@2: 	enum TError
williamr@2: 		{
williamr@2:  		/** The input descriptor contains a single corrupt character. This 
williamr@2:  		might occur when the input descriptor only contains some of the bytes 
williamr@2:  		of a single multi-byte character. */
williamr@2: 		EErrorIllFormedInput=KErrCorrupt
williamr@2: 		};
williamr@2: 	 
williamr@2: 	 /** Initial value for the state argument in a set of related calls to
williamr@2: 	ConvertToUnicode(). */
williamr@2: 	enum {KStateDefault=0}; 
williamr@2: public:
williamr@2: 	// the conversion functions return either one of the TError values above, or the number of unconverted elements left at the end of the input descriptor
williamr@2: 	IMPORT_C static TInt ConvertFromUnicodeToUtf7(TDes8& aUtf7, const TDesC16& aUnicode, TBool aEncodeOptionalDirectCharactersInBase64);
williamr@2: 	static TInt ConvertFromUnicodeToUtf7(TDes8& aUtf7, const TDesC16& aUnicode, TBool aIsImapUtf7, TBool aEncodeOptionalDirectCharactersInBase64);
williamr@2: 	IMPORT_C static TInt ConvertFromUnicodeToUtf8(TDes8& aUtf8, const TDesC16& aUnicode);
williamr@2: 	static TInt ConvertFromUnicodeToUtf8(TDes8& aUtf8, const TDesC16& aUnicode, TBool aGenerateJavaConformantUtf8);
williamr@2: 	IMPORT_C static TInt ConvertToUnicodeFromUtf7(TDes16& aUnicode, const TDesC8& aUtf7, TInt& aState);
williamr@2: 	static TInt ConvertToUnicodeFromUtf7(TDes16& aUnicode, const TDesC8& aUtf7, TBool aIsImapUtf7, TInt& aState);
williamr@2: 	IMPORT_C static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8);
williamr@2: 	static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8, TBool aGenerateJavaConformantUtf8);
williamr@2: 	static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8, TBool aGenerateJavaConformantUtf8,
williamr@2: 			TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter);
williamr@2: 
williamr@2: 	IMPORT_C static HBufC8* ConvertFromUnicodeToUtf7L(const TDesC16& aUnicode,TBool aEncodeOptionalDirectCharactersInBase64);
williamr@2: 	IMPORT_C static HBufC8* ConvertFromUnicodeToUtf8L(const TDesC16& aUnicode);
williamr@2: 	IMPORT_C static HBufC16* ConvertToUnicodeFromUtf7L(const TDesC8& aUtf7); 
williamr@2: 	IMPORT_C static HBufC16* ConvertToUnicodeFromUtf8L(const TDesC8& aUtf8);
williamr@2: 
williamr@2: 
williamr@2: 	};
williamr@2: 
williamr@2: #endif