sl@0: /*
sl@0: * Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies).
sl@0: * All rights reserved.
sl@0: * This component and the accompanying materials are made available
sl@0: * under the terms of "Eclipse Public License v1.0"
sl@0: * which accompanies this distribution, and is available
sl@0: * at the URL "http://www.eclipse.org/legal/epl-v10.html".
sl@0: *
sl@0: * Initial Contributors:
sl@0: * Nokia Corporation - initial contribution.
sl@0: *
sl@0: * Contributors:
sl@0: *
sl@0: * Description: 
sl@0: *
sl@0: */
sl@0: 
sl@0: 
sl@0: #include <stdlib.h>
sl@0: 
sl@0: const int KErrorIllFormedInput=-1;
sl@0: 
sl@0: int Utf8ToUnicode(wchar_t* aUnicode, const char* aUtf8)
sl@0: // must '\0'-terminate the output
sl@0: 	{
sl@0: 	wchar_t* startOfUnicode=aUnicode;
sl@0: 	for (;;)
sl@0: 		{
sl@0: 		unsigned int currentUtf8Byte=*aUtf8;
sl@0: 		if (currentUtf8Byte=='\0')
sl@0: 			{
sl@0: 			break;
sl@0: 			}
sl@0: 		if ((currentUtf8Byte&0x80)==0x00)
sl@0: 			{
sl@0: 			if (startOfUnicode!=NULL)
sl@0: 				{
sl@0: 				*aUnicode=(wchar_t)currentUtf8Byte;
sl@0: 				}
sl@0: 			}
sl@0: 		else if ((currentUtf8Byte&0xe0)==0xc0)
sl@0: 			{
sl@0: 			unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x1f)<<6);
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=(currentUtf8Byte&0x3f);
sl@0: 			if (startOfUnicode!=NULL)
sl@0: 				{
sl@0: 				*aUnicode=(wchar_t)currentUnicodeCharacter;
sl@0: 				}
sl@0: 			}
sl@0: 		else if ((currentUtf8Byte&0xf0)==0xe0)
sl@0: 			{
sl@0: 			unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x0f)<<12);
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=((currentUtf8Byte&0x3f)<<6);
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=(currentUtf8Byte&0x3f);
sl@0: 			if (startOfUnicode!=NULL)
sl@0: 				{
sl@0: 				*aUnicode=(wchar_t)currentUnicodeCharacter;
sl@0: 				}
sl@0: 			}
sl@0: 		else if ((currentUtf8Byte&0xf8)==0xf0)
sl@0: 			{
sl@0: 			unsigned int currentUnicodeCharacter=((currentUtf8Byte&0x07)<<8);
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=((currentUtf8Byte&0x3f)<<2);
sl@0: 			if (currentUnicodeCharacter<0x0040)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter-=0x0040;
sl@0: 			if (currentUnicodeCharacter>=0x0400)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=((currentUtf8Byte&0x30)>>4);
sl@0: 			if (startOfUnicode!=NULL)
sl@0: 				{
sl@0: 				*aUnicode=(wchar_t)(0xd800|currentUnicodeCharacter);
sl@0: 				}
sl@0: 			currentUnicodeCharacter=((currentUtf8Byte&0x0f)<<6);
sl@0: 			++aUtf8;
sl@0: 			currentUtf8Byte=*aUtf8;
sl@0: 			if ((currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUnicodeCharacter|=(currentUtf8Byte&0x3f);
sl@0: 			++aUnicode;
sl@0: 			if (startOfUnicode!=NULL)
sl@0: 				{
sl@0: 				*aUnicode=(wchar_t)(0xdc00|currentUnicodeCharacter);
sl@0: 				}
sl@0: 			}
sl@0: 		else
sl@0: 			{
sl@0: 			return KErrorIllFormedInput;
sl@0: 			}
sl@0: 		++aUnicode;
sl@0: 		++aUtf8;
sl@0: 		}
sl@0: 	if (startOfUnicode!=NULL)
sl@0: 		{
sl@0: 		*aUnicode='\0';
sl@0: 		}
sl@0: 	return aUnicode-startOfUnicode;
sl@0: 	}
sl@0: #include <stdio.h>
sl@0: int UnicodeToUtf8(char* aUtf8, const wchar_t* aUnicode)
sl@0: // must '\0'-terminate the output
sl@0: 	{
sl@0: 	char* startOfUtf8=aUtf8;
sl@0: 	for (;;)
sl@0: 		{
sl@0: 		unsigned int currentUnicodeCharacter=*aUnicode;
sl@0: 		if (currentUnicodeCharacter=='\0')
sl@0: 			{
sl@0: 			break;
sl@0: 			}
sl@0: 		if ((currentUnicodeCharacter&0xff80)==0x0000)
sl@0: 			{
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)currentUnicodeCharacter;
sl@0: 				}
sl@0: 			}
sl@0: 		else if ((currentUnicodeCharacter&0xf800)==0x0000)
sl@0: 			{
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0xc0|(currentUnicodeCharacter>>6));
sl@0: 				}
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f));
sl@0: 				}
sl@0: 			}
sl@0: 		else if ((currentUnicodeCharacter&0xfc00)==0xd800)
sl@0: 			{
sl@0: 			currentUnicodeCharacter+=0x0040;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0xf0|((currentUnicodeCharacter>>8)&0x07));
sl@0: 				}
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0x80|((currentUnicodeCharacter>>2)&0x3f));
sl@0: 				}
sl@0: 			{
sl@0: 			unsigned int currentUtf8Byte=(0x80|((currentUnicodeCharacter&0x03)<<4));
sl@0: 			++aUnicode;
sl@0: 			currentUnicodeCharacter=*aUnicode;
sl@0: 			if ((currentUnicodeCharacter&0xfc00)!=0xdc00)
sl@0: 				{
sl@0: 				return KErrorIllFormedInput;
sl@0: 				}
sl@0: 			currentUtf8Byte|=((currentUnicodeCharacter>>6)&0x0f);
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)currentUtf8Byte;
sl@0: 				}
sl@0: 			}
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f));
sl@0: 				}
sl@0: 			}
sl@0: 		else
sl@0: 			{
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0xe0|(currentUnicodeCharacter>>12));
sl@0: 				}
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0x80|((currentUnicodeCharacter>>6)&0x3f));
sl@0: 				}
sl@0: 			++aUtf8;
sl@0: 			if (startOfUtf8!=NULL)
sl@0: 				{
sl@0: 				*aUtf8=(char)(0x80|(currentUnicodeCharacter&0x3f));
sl@0: 				}
sl@0: 			}
sl@0: 		++aUtf8;
sl@0: 		++aUnicode;
sl@0: 		}
sl@0: 	if (startOfUtf8!=NULL)
sl@0: 		{
sl@0: 		*aUtf8='\0';
sl@0: 		}
sl@0: 	return aUtf8-startOfUtf8;
sl@0: 	}
sl@0: 
sl@0: