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: * Little-Endian converter
sl@0: *
sl@0: */
sl@0: 
sl@0: 
sl@0: #include <e32std.h>
sl@0: #include <convdata.h>
sl@0: #include "unicode.h"
sl@0: 
sl@0: #define ARRAY_LENGTH(aArray) (sizeof(aArray)/sizeof((aArray)[0]))
sl@0: 
sl@0: 
sl@0: GLREF_D const SCnvConversionData unicodeConversionDataLittle=
sl@0: 	{
sl@0: 	SCnvConversionData::EFixedLittleEndian,
sl@0: 		{
sl@0: 		ARRAY_LENGTH(unicodeVariableByteDataRanges),
sl@0: 		unicodeVariableByteDataRanges
sl@0: 		},
sl@0: 		{
sl@0: 		ARRAY_LENGTH(unicodeTounicodeDataRanges),
sl@0: 		unicodeTounicodeDataRanges
sl@0: 		},
sl@0: 		{
sl@0: 		ARRAY_LENGTH(unicodeTounicodeDataRanges),
sl@0: 		unicodeTounicodeDataRanges
sl@0: 		},
sl@0: 	NULL,
sl@0: 	NULL
sl@0: 	};
sl@0: 
sl@0: GLREF_C void IsCharacterSetUnicodeLittle(TInt& aConfidenceLevel, const TDesC8& aSample)
sl@0: 	{
sl@0: 	
sl@0: 	TInt sampleLength = aSample.Length();
sl@0: 	aConfidenceLevel =70;
sl@0: 	if (sampleLength < 2)
sl@0: 		return;
sl@0: 
sl@0: 	if (aSample[0]==0xff)
sl@0: 		{
sl@0: 		// The first byte is a possible ByteOrderMark
sl@0: 		// Try matching the next character 
sl@0: 		if(aSample[1]==0xfe)
sl@0: 			{
sl@0: 			// the byte order mark could be 0xFEFF or 0xFFFE depending on 
sl@0: 			// endianness of the sample text.
sl@0: 			aConfidenceLevel=100;
sl@0: 			}
sl@0: 		}
sl@0: 
sl@0: 	for (TInt i = 0; i < sampleLength-1; ++i)
sl@0: 		{
sl@0: 		if (aSample[i] == 0x0d)
sl@0:  			{
sl@0:  			if (aSample[i+1] == 0x0a)
sl@0:  				{
sl@0:  				// reduce the confidence level
sl@0:  				aConfidenceLevel -= 25;
sl@0:  				}
sl@0:  			}
sl@0: 		}
sl@0: 
sl@0: 	// if not 100% confident already, check if most odd bytes zero 
sl@0: 	#define MAX_SAMPLE_LENGTH 2048
sl@0: 	if ( aConfidenceLevel < 100 )
sl@0: 		{	
sl@0: 		TInt repeat=0;
sl@0: 
sl@0: 		// only check the first MAX_SAMPLE_LENGTH if big sample
sl@0: 		TInt length =( sampleLength > MAX_SAMPLE_LENGTH ? MAX_SAMPLE_LENGTH : sampleLength);
sl@0: 
sl@0: 		// start from 1 and check the odd bytes
sl@0: 		for (TInt i = 1; i < length-1; i+=2)
sl@0: 			{
sl@0: 			if (aSample[i] == 0x0) 
sl@0: 				repeat ++;
sl@0: 			}
sl@0: 
sl@0: 		// if more than 80% odd bytes zero, then this IS little Endian
sl@0: 		if ( (repeat * 100) /  (length * 5) >= 8)
sl@0: 			aConfidenceLevel  = 100;
sl@0: 		}
sl@0: 
sl@0: 	aConfidenceLevel =(aConfidenceLevel >0)? ((aConfidenceLevel > 100)? 100: aConfidenceLevel): 0;
sl@0: 	}
sl@0: