sl@0: #
sl@0: # Copyright (c) 2000-2009 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: use strict;
sl@0: use integer;
sl@0: 
sl@0: package UTF;
sl@0: require Exporter;
sl@0: @UTF::ISA=qw(Exporter);
sl@0: @UTF::EXPORT=qw(Utf8ToUnicode UnicodeToUtf8);
sl@0: 
sl@0: my $KErrorIllFormedInput=-1;
sl@0: 
sl@0: sub Utf8ToUnicode
sl@0: 	{
sl@0: 	my $Unicode = shift;  
sl@0: 	my $Utf8 = shift;
sl@0: 	my $UnicodeTemplate = shift;
sl@0: 	my $Utf8Index = 0;
sl@0: 	my $UnicodeIndex = 0;
sl@0: 	my $numOfBytes = length($Utf8);
sl@0: 	my @Utf8Unpacked = unpack "C*",$Utf8;
sl@0: 	my @UnicodeUnpacked = (); 
sl@0: 
sl@0: 	for (;;)
sl@0: 		{
sl@0: 		if ($Utf8Index > $#Utf8Unpacked)
sl@0: 			{
sl@0: 			last;
sl@0: 			}
sl@0: 
sl@0: 		my $currentUtf8Byte = $Utf8Unpacked[$Utf8Index];
sl@0: 		
sl@0: 		if (($currentUtf8Byte&0x80)==0x00)
sl@0: 			{
sl@0: 			$UnicodeUnpacked[$UnicodeIndex] = $currentUtf8Byte;
sl@0: 			}
sl@0: 		
sl@0: 		elsif (($currentUtf8Byte&0xe0)==0xc0)
sl@0: 			{
sl@0: 			my $currentUnicodeCharacter=(($currentUtf8Byte&0x1f)<<6);
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
sl@0: 			$UnicodeUnpacked[$UnicodeIndex] = $currentUnicodeCharacter;
sl@0: 			}
sl@0: 
sl@0: 		elsif (($currentUtf8Byte&0xf0)==0xe0)
sl@0: 			{
sl@0: 			my $currentUnicodeCharacter=(($currentUtf8Byte&0x0f)<<12);
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUnicodeCharacter|=(($currentUtf8Byte&0x3f)<<6);
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
sl@0: 			$UnicodeUnpacked[$UnicodeIndex] = $currentUnicodeCharacter;
sl@0: 			}
sl@0: 
sl@0: 		elsif (($currentUtf8Byte&0xf8)==0xf0)
sl@0: 			{                                         
sl@0: 			my $currentUnicodeCharacter=(($currentUtf8Byte&0x07)<<8);
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($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 $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUnicodeCharacter|=(($currentUtf8Byte&0x30)>>4);
sl@0: 			$UnicodeUnpacked[$UnicodeIndex] = (0xd800|$currentUnicodeCharacter);
sl@0: 			$currentUnicodeCharacter=(($currentUtf8Byte&0x0f)<<6);
sl@0: 			++$Utf8Index;
sl@0: 			$currentUtf8Byte=$Utf8Unpacked[$Utf8Index];
sl@0: 			if (($currentUtf8Byte&0xc0)!=0x80)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUnicodeCharacter|=($currentUtf8Byte&0x3f);
sl@0: 			++$UnicodeIndex;
sl@0: 			$UnicodeUnpacked[$UnicodeIndex] = (0xdc00|$currentUnicodeCharacter);
sl@0: 			}
sl@0: 		else
sl@0: 			{
sl@0: 			return $KErrorIllFormedInput;
sl@0: 			}
sl@0: 		++$UnicodeIndex;
sl@0: 		++$Utf8Index;
sl@0: 		}
sl@0: 	$$Unicode = (); 
sl@0: 	$$Unicode = pack "$UnicodeTemplate*", @UnicodeUnpacked;
sl@0: 	return $UnicodeIndex;  
sl@0: 	}
sl@0: 
sl@0: sub UnicodeToUtf8
sl@0: 	{
sl@0: 	my $Utf8 = shift; 
sl@0: 	my $Unicode = shift;
sl@0: 	my $UnicodeTemplate = shift;
sl@0: 	my $Utf8Index = 0;
sl@0: 	my $UnicodeIndex = 0;
sl@0: 	my $numOfBytes = length($Unicode);
sl@0: 	my @UnicodeUnpacked = unpack "$UnicodeTemplate*", $Unicode;
sl@0: 	my @Utf8Unpacked = ();
sl@0: 	
sl@0: 	for (;;)
sl@0: 		{
sl@0: 		# exit the loop if no more in the UnicodeUnpacked
sl@0: 		if ($UnicodeIndex > $#UnicodeUnpacked)
sl@0: 			{
sl@0: 			last;
sl@0: 			}
sl@0: 
sl@0: 		my $currentUnicodeCharacter=$UnicodeUnpacked[$UnicodeIndex];
sl@0: 		if (($currentUnicodeCharacter&0xff80)==0x0000)
sl@0: 			{	
sl@0: 			$Utf8Unpacked[$Utf8Index]= $currentUnicodeCharacter;
sl@0: 			}
sl@0: 		elsif (($currentUnicodeCharacter&0xf800)==0x0000)
sl@0: 			{
sl@0: 
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0xc0 | $currentUnicodeCharacter >> 6);
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0x80 | $currentUnicodeCharacter&0x3f);
sl@0: 			}
sl@0: 		elsif (($currentUnicodeCharacter&0xfc00)==0xd800)
sl@0: 			{
sl@0: 			$currentUnicodeCharacter+=0x0040;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0xf0|(($currentUnicodeCharacter>>8)&0x07));
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0x80|(($currentUnicodeCharacter>>2)&0x3f));
sl@0: 			my $currentUtf8Byte=(0x80|(($currentUnicodeCharacter&0x03)<<4));
sl@0: 			++$UnicodeIndex;
sl@0: 			$currentUnicodeCharacter=$UnicodeUnpacked[$UnicodeIndex];
sl@0: 			if (($currentUnicodeCharacter&0xfc00)!=0xdc00)
sl@0: 				{
sl@0: 				return $KErrorIllFormedInput;
sl@0: 				}
sl@0: 			$currentUtf8Byte|=(($currentUnicodeCharacter>>6)&0x0f);
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= $currentUtf8Byte;
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0x80| ($currentUnicodeCharacter&0x3f));
sl@0: 			}
sl@0: 		else
sl@0: 			{
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0xe0|($currentUnicodeCharacter>>12));
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0x80|(($currentUnicodeCharacter>>6)&0x3f));
sl@0: 			++$Utf8Index;
sl@0: 			$Utf8Unpacked[$Utf8Index]= (0x80| ($currentUnicodeCharacter&0x3f));
sl@0: 			}
sl@0: 		++$Utf8Index;
sl@0: 		++$UnicodeIndex;
sl@0: 		}
sl@0: 	$$Utf8 = ();	
sl@0: 	$$Utf8 = pack "C*", @Utf8Unpacked;
sl@0: 	return $Utf8Index; 
sl@0: 
sl@0: 	}