userlibandfileserver/fatfilenameconversionplugins/src/unicodeconv.cpp
changeset 0 a41df078684a
child 2 4122176ea935
equal deleted inserted replaced
-1:000000000000 0:a41df078684a
       
     1 // Copyright (c) 2006-2009 Nokia Corporation and/or its subsidiary(-ies).
       
     2 // All rights reserved.
       
     3 // This component and the accompanying materials are made available
       
     4 // under the terms of the License "Eclipse Public License v1.0"
       
     5 // which accompanies this distribution, and is available
       
     6 // at the URL "http://www.eclipse.org/legal/epl-v10.html".
       
     7 //
       
     8 // Initial Contributors:
       
     9 // Nokia Corporation - initial contribution.
       
    10 //
       
    11 // Contributors:
       
    12 //
       
    13 // Description:
       
    14 //
       
    15 
       
    16 #include <e32std.h>
       
    17 #include <e32def.h>
       
    18 #include <e32des8.h> 
       
    19 #include "unicodeconv.h"
       
    20 
       
    21 //replacement character to be used when unicode cannot be converted
       
    22 const TUint8 KForeignReplacement = 0x5F;
       
    23 
       
    24 //This function converts from Unicoded characters, to foreign characters and adds them into a descriptor
       
    25 EXPORT_C void UnicodeConv::ConvertFromUnicodeL(TDes8& aForeign, const TDesC16& aUnicode)
       
    26     {
       
    27     UnicodeConv::ConvertFromUnicodeL(aForeign, aUnicode, ETrue);
       
    28     }
       
    29 
       
    30 //This function converts from Unicoded characters, to foreign characters and adds them into a descriptor
       
    31 EXPORT_C TInt UnicodeConv::ConvertFromUnicodeL(TDes8& aForeign, const TDesC16& aUnicode, TBool leaveWhenOverflow)
       
    32 	{
       
    33 	const TInt unicodeLength = aUnicode.Length();
       
    34 	
       
    35 	//loop going through the character of the unicode descriptor
       
    36 	for(TInt i=0; i<unicodeLength; i++)
       
    37 		{
       
    38 		const TUint16 unicodeChar = aUnicode[i];
       
    39 		
       
    40 		// if the output buffer is already full, leave with KErrOverflow
       
    41 		if ( aForeign.Length() >= aForeign.MaxLength() )
       
    42 		    {
       
    43 		    if (leaveWhenOverflow)
       
    44 		        User::Leave(KErrOverflow);
       
    45 		    else
       
    46 		        return KErrOverflow;
       
    47 		    }			
       
    48 
       
    49 		//charcters from 0x0000 to 0x007F, can be mapped directly
       
    50 		if(unicodeChar<0x0080)
       
    51 			{
       
    52 			aForeign.Append(static_cast<TUint8>(unicodeChar));
       
    53 			}
       
    54 		else
       
    55 			{
       
    56 			TInt trailByte = KErrNotFound;
       
    57 			TInt returnValue = TConvDataStruct::ConvertSingleUnicode(unicodeChar,trailByte);
       
    58 			
       
    59 			if(returnValue!=KErrNotFound)
       
    60 				{
       
    61 				if(trailByte!=KErrNotFound)		
       
    62 					{					
       
    63 					// as two bytes are being added check enough space for second
       
    64 					if ( aForeign.Length() + 2 <= aForeign.MaxLength() )
       
    65 					    {
       
    66 					    aForeign.Append(static_cast<TUint8>(returnValue));
       
    67 					    aForeign.Append(static_cast<TUint8>(trailByte));
       
    68 					    }
       
    69 					else
       
    70 					    {
       
    71 			            if (leaveWhenOverflow)
       
    72 			                User::Leave(KErrOverflow);
       
    73 			            else
       
    74 			                return KErrOverflow;
       
    75 					    }					
       
    76 					}
       
    77 				else
       
    78 					aForeign.Append(static_cast<TUint8>(returnValue));
       
    79 				}		
       
    80 			else
       
    81 				aForeign.Append(KForeignReplacement);
       
    82 			}
       
    83 		}
       
    84 	
       
    85 	return KErrNone;
       
    86 	}
       
    87 				
       
    88 //This function converts from foreign characters into unicode and adds them into a descriptor
       
    89 EXPORT_C void UnicodeConv::ConvertToUnicodeL(TDes16& aUnicode, const TDesC8& aForeign)
       
    90     {
       
    91     UnicodeConv::ConvertToUnicodeL(aUnicode, aForeign, ETrue);
       
    92     }
       
    93 
       
    94 //This function converts from foreign characters into unicode and adds them into a descriptor
       
    95 EXPORT_C TInt UnicodeConv::ConvertToUnicodeL(TDes16& aUnicode, const TDesC8& aForeign, TBool leaveWhenOverflow)
       
    96 	{
       
    97 	const TInt foreignLength = aForeign.Length();
       
    98 
       
    99 	//loop going through the characters of the foreign descriptor
       
   100 	for(TInt i = 0; i<foreignLength; i++)
       
   101 		{
       
   102 		const TUint8 leadForeign = aForeign[i];
       
   103 		TUint8 tailForeign = 0x00;
       
   104 
       
   105 		// Check there is enough space in the output buffer, and leave with KErrOverflow if not
       
   106 		if ( aUnicode.Length() == aUnicode.MaxLength() )
       
   107             {
       
   108             if (leaveWhenOverflow)
       
   109                 User::Leave(KErrOverflow);
       
   110             else
       
   111                 return KErrOverflow;
       
   112             }
       
   113 
       
   114 		//charcters from 0x00 to 0x7F, can be mapped directly
       
   115 		if(leadForeign < 0x80)
       
   116 			aUnicode.Append(static_cast<TUint16>(leadForeign));
       
   117 		else
       
   118 			{
       
   119 			if((i+1)<foreignLength)
       
   120 				tailForeign = aForeign[i+1];
       
   121 
       
   122 			const TLeadOrSingle* structPtr = TConvDataStruct::KFirstByteConversions + (leadForeign-0x80);
       
   123 			
       
   124 			if(structPtr->iUnicodeIfSingle)
       
   125 				aUnicode.Append(structPtr->iUnicodeIfSingle);
       
   126 			else
       
   127 				{
       
   128 				if(TConvDataStruct::KMinTrailByte<=tailForeign && tailForeign<=TConvDataStruct::KMaxTrailByte)
       
   129 					aUnicode.Append(TConvDataStruct::KDoubleByteConversions[structPtr->iDoubleByteIndex+
       
   130 						(tailForeign - TConvDataStruct::KMinTrailByte)]);
       
   131 				else
       
   132 					aUnicode.Append(0xFFFD);
       
   133 				i++;
       
   134 				}
       
   135 			}
       
   136 		}
       
   137 
       
   138 	return KErrNone;
       
   139 	}
       
   140 
       
   141 EXPORT_C TBool UnicodeConv::IsLegalShortNameCharacter (TUint aCharacter)
       
   142 	{
       
   143 	//1. aCharacter >= 0x0080 
       
   144 	if (aCharacter>=0x0080)
       
   145 		{
       
   146 		if (aCharacter>0xFFFF)
       
   147 			return EFalse;
       
   148 		
       
   149 		TInt trailByte = KErrNotFound;
       
   150 		TInt returnValue = TConvDataStruct::ConvertSingleUnicode(aCharacter,trailByte);
       
   151 		
       
   152 		if(returnValue!=KErrNotFound)
       
   153 			return ETrue;
       
   154 		else
       
   155 			return EFalse;
       
   156 		}
       
   157 	
       
   158     // For most common cases: 
       
   159     // Note: lower case characters are considered legal DOS char here. 
       
   160 	if ((aCharacter>='a' && aCharacter<='z') || 
       
   161 	    (aCharacter>='A' && aCharacter<='Z') || 
       
   162 	    (aCharacter>='0' && aCharacter<='9'))
       
   163 			{
       
   164 			return ETrue;
       
   165 			}
       
   166     // Checking for illegal chars: 
       
   167     // 2. aCharacter <= 0x20 
       
   168     // Note: leading 0x05 byte should be guarded by callers of this function 
       
   169     //  as the information of the position of the character is required. 
       
   170 	if (aCharacter < 0x20)
       
   171 		return EFalse;
       
   172 	// Space (' ') is not considered as a legal DOS char here.
       
   173 	if (aCharacter == 0x20)
       
   174 		return EFalse;
       
   175 	
       
   176 	// 3. 0x20 < aCharacter < 0x80 
       
   177     // According to FAT Spec, "following characters are not legal in any bytes of DIR_Name": 
       
   178     switch (aCharacter) 
       
   179             { 
       
   180             case 0x22:        // '"' 
       
   181             case 0x2A:        // '*' 
       
   182             case 0x2B:        // '+' 
       
   183             case 0x2C:        // ',' 
       
   184             //case 0x2E:        // '.'   // Although '.' is not allowed in any bytes of DIR_Name, it 
       
   185                                          // is a valid character in short file names. 
       
   186             case 0x2F:        // '/' 
       
   187             case 0x3A:        // ':' 
       
   188             case 0x3B:        // ';' 
       
   189             case 0x3C:        // '<' 
       
   190             case 0x3D:        // '=' 
       
   191             case 0x3E:        // '>' 
       
   192             case 0x3F:        // '?' 
       
   193             case 0x5B:        // '[' 
       
   194             case 0x5C:        // '\' 
       
   195             case 0x5D:        // ']' 
       
   196             case 0x7C:        // '|' 
       
   197             	return EFalse; 
       
   198             default: 
       
   199             	return ETrue; 
       
   200             } 
       
   201 	}		
       
   202