Difference between revisions of "UTF-8"

Revision as of 06:39, 4 February 2008

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 written by Strife Onizuka.

General Use

This version will work fine in LSO and Mono but not in LSLEditor. <lsl>//===================================================// // Combined Library // // "Feb 4 2008", "08:35:00" // // Copyright (C) 2004-2008, Strife Onizuka (cc-by) // // http://creativecommons.org/licenses/by/3.0/ // //===================================================// //{

integer UTF8ToUnicodeInteger(string input)//LSLEditor 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)//LSLEditor 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)) / 5))));
   while (bytes)
       result += "%" + byte2hex((((input >> (6 * (bytes = ~-bytes))) | 0x80) & 0xBF));
   return llUnescapeURL(result);

}

string byte2hex(integer x)//LSLEditor Safe, LSO Safe {//Helper function for use with unicode characters.

   integer y = (x >> 4) & 0xF;
   return llGetSubString(hexc, y, y) + llGetSubString(hexc, x & 0xF, x & 0xF);

}//This function would benefit greatly from the DUP opcode, it would remove 19 bytes.

string hexc="0123456789ABCDEF";

//} Combined Library</lsl>

LSLEditor Safe

This version will work in Mono, LSO & LSLEditor. There will be a slight performance hit in LSO as compared to the LSLEditor Unsafe version. <lsl>//===================================================// // Combined Library // // "Feb 4 2008", "08:38:13" // // Copyright (C) 2004-2008, Strife Onizuka (cc-by) // // http://creativecommons.org/licenses/by/3.0/ // //===================================================// //{

integer UTF8ToUnicodeInteger(string input)//LSLEditor Safe, 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.
       integer end = (integer)("0x"+llGetSubString(input = (string)llParseString2List(llEscapeURL(input),(list)"%",[]),-8,-1));
       integer begin = (integer)("0x"+llDeleteSubString(input,-8,-1));
       return  (   (  0x0000003f &  end       ) |
                   (( 0x00003f00 &  end) >> 2 ) | 
                   (( 0x003f0000 &  end) >> 4 ) | 
                   (( 0x3f000000 &  end) >> 6 ) |
                   (( 0x0000003f &  begin) << 24) |
                   (( 0x00000100 &  begin) << 22)
               ) & (0x7FFFFFFF >> (5 * ((integer)(llLog(~result) / 0.69314718055994530941723212145818) - 25)));
   }
   return result >> 24;

}

string UnicodeIntegerToUTF8(integer input)//LSLEditor Safe, LSO Safe {

   integer bytes = llCeil((llLog(input) / 0.69314718055994530941723212145818));
   bytes = (input >= 0x80) * (bytes + ~(((1 << bytes) - input) > 0)) / 5;//adjust
   string result = "%" + byte2hex((input >> (6 * bytes)) | ((0x3F80 >> bytes) << !bytes));
   while (bytes)
       result += "%" + byte2hex((((input >> (6 * (bytes = ~-bytes))) | 0x80) & 0xBF));
   return llUnescapeURL(result);

}