Difference between revisions of "UTF-8"

From Second Life Wiki
Jump to: navigation, search
(Out of date)
Line 13: Line 13:
 
integer UTF8ToUnicodeInteger(string input)//Mono Unsafe, LSO Safe
 
integer UTF8ToUnicodeInteger(string input)//Mono Unsafe, LSO Safe
 
{
 
{
integer result = llBase64ToInteger(llStringToBase64(input = llGetSubString(input,0,0)));
+
    integer result = llBase64ToInteger(llStringToBase64(input = llGetSubString(input,0,0)));
if(result & 0x80000000)//multibyte, continuing to use base64 is impractical because it requires smart shifting.
+
    if(result & 0x80000000)//multibyte, continuing to use base64 is impractical because it requires smart shifting.
return  (  (  0x0000003f &  result      ) |
+
        return  (  (  0x0000003f &  result      ) |
(( 0x00003f00 &  result) >> 2 ) |  
+
                    (( 0x00003f00 &  result) >> 2 ) |  
(( 0x003f0000 &  result) >> 4 ) |  
+
                    (( 0x003f0000 &  result) >> 4 ) |  
(( 0x3f000000 & (result = (integer)("0x"+llGetSubString(input,-8,-1)))) >> 6 ) |  
+
                    (( 0x3f000000 & (result = (integer)("0x"+llGetSubString(input,-8,-1)))) >> 6 ) |  
(( 0x0000003f &  result) << 24) |  
+
                    (( 0x0000003f &  result) << 24) |  
(( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[]),-8,-1)))) << 22)
+
                    (( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[]),-8,-1)))) << 22)
) & (  0x7FFFFFFF >> (5 * ((integer)(llLog(~result) / 0.69314718055994530941723212145818) - 25)));
+
                ) & (  0x7FFFFFFF >> (5 * ((integer)(llLog(~result) / 0.69314718055994530941723212145818) - 25)));
 
//                    (( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input,-8,-1)))) << 22)
 
//                    (( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input,-8,-1)))) << 22)
 
//                ) & (  0x7FFFFFFF >> (30 - (5 * (llStringLength(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[])) >> 1))));
 
//                ) & (  0x7FFFFFFF >> (30 - (5 * (llStringLength(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[])) >> 1))));
return result >> 24;
+
    return result >> 24;
 
}
 
}
  
 
string UnicodeIntegerToUTF8(integer input)//Mono Unsafe, LSO Safe
 
string UnicodeIntegerToUTF8(integer input)//Mono Unsafe, LSO Safe
 
{
 
{
integer bytes = llCeil(llLog(input) / 0.69314718055994530941723212145818);
+
    integer bytes = llCeil(llLog(input) / 0.69314718055994530941723212145818);
string result = "%" + byte2hex((input >> (6 * bytes)) | ((0x3F80 >> bytes) << !(bytes = ((input >= 0x80) * (bytes + (((1 << bytes) - input) <= 0) - 2 ) / 5))));
+
    string result = "%" + byte2hex((input >> (6 * bytes)) | ((0x3F80 >> bytes) << !(bytes = ((input >= 0x80) * (bytes + (((1 << bytes) - input) <= 0) - 2 ) / 5))));
while (bytes)
+
    while (bytes)
result += "%" + byte2hex((((input >> (6 * (bytes = ~-bytes))) | 0x80) & 0xBF));
+
        result += "%" + byte2hex((((input >> (6 * (bytes = ~-bytes))) | 0x80) & 0xBF));
return llUnescapeURL(result);
+
    return llUnescapeURL(result);
 
}
 
}
  
 
string byte2hex(integer x)//Mono Unsafe, LSO Safe
 
string byte2hex(integer x)//Mono Unsafe, LSO Safe
 
{//Helper function for use with unicode characters.
 
{//Helper function for use with unicode characters.
return llGetSubString(hexc, x = ((x >> 4) & 0xF), x) + llGetSubString(hexc, x & 0xF, x & 0xF);
+
    return llGetSubString(hexc, x = ((x >> 4) & 0xF), x) + llGetSubString(hexc, x & 0xF, x & 0xF);
 
}//This function would benifit greatly from the DUP opcode, it would remove 19 bytes.
 
}//This function would benifit greatly from the DUP opcode, it would remove 19 bytes.
  

Revision as of 18:32, 2 November 2007

SL uses UTF-8 for storing and transmitting strings and with these functions you can work with Unicode characters.

These functions are part of the Combined Library (which includes many other functions written by Strife.

//===================================================//
//                 Combined Library                  //
//             "Nov  2 2007", "22:30:43"             //
//  Copyright (C) 2004-2007, Strife Onizuka (cc-by)  //
//    http://creativecommons.org/licenses/by/3.0/    //
//===================================================//
//{

integer UTF8ToUnicodeInteger(string input)//Mono Unsafe, LSO Safe
{
    integer result = llBase64ToInteger(llStringToBase64(input = llGetSubString(input,0,0)));
    if(result & 0x80000000)//multibyte, continuing to use base64 is impractical because it requires smart shifting.
        return  (   (  0x0000003f &  result       ) |
                    (( 0x00003f00 &  result) >> 2 ) | 
                    (( 0x003f0000 &  result) >> 4 ) | 
                    (( 0x3f000000 & (result = (integer)("0x"+llGetSubString(input,-8,-1)))) >> 6 ) | 
                    (( 0x0000003f &  result) << 24) | 
                    (( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[]),-8,-1)))) << 22)
                ) & (  0x7FFFFFFF >> (5 * ((integer)(llLog(~result) / 0.69314718055994530941723212145818) - 25)));
//                    (( 0x00000100 & (result = (integer)("0x"+llDeleteSubString(input,-8,-1)))) << 22)
//                ) & (  0x7FFFFFFF >> (30 - (5 * (llStringLength(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[])) >> 1))));
    return result >> 24;
}

string UnicodeIntegerToUTF8(integer input)//Mono Unsafe, LSO Safe
{
    integer bytes = llCeil(llLog(input) / 0.69314718055994530941723212145818);
    string result = "%" + byte2hex((input >> (6 * bytes)) | ((0x3F80 >> bytes) << !(bytes = ((input >= 0x80) * (bytes + (((1 << bytes) - input) <= 0) - 2 ) / 5))));
    while (bytes)
        result += "%" + byte2hex((((input >> (6 * (bytes = ~-bytes))) | 0x80) & 0xBF));
    return llUnescapeURL(result);
}

string byte2hex(integer x)//Mono Unsafe, LSO Safe
{//Helper function for use with unicode characters.
    return llGetSubString(hexc, x = ((x >> 4) & 0xF), x) + llGetSubString(hexc, x & 0xF, x & 0xF);
}//This function would benifit greatly from the DUP opcode, it would remove 19 bytes.

string hexc="0123456789ABCDEF";

//} Combined Library