Difference between revisions of "UTF-8"

From Second Life Wiki
Jump to: navigation, search
m
Line 1: Line 1:
 +
{{LSL Header}}{{LSLC|UD Functions}}
 
SL uses UTF-8 for storing and transmitting strings and with these functions you can work with Unicode characters. See: [[Unicode In 5 Minutes]] for a brief introduction to Unicode.
 
SL uses UTF-8 for storing and transmitting strings and with these functions you can work with Unicode characters. See: [[Unicode In 5 Minutes]] for a brief introduction to Unicode.
  
  
 
These functions are part of the [[Combined Library]] written by {{User|Strife Onizuka}}.
 
These functions are part of the [[Combined Library]] written by {{User|Strife Onizuka}}.
 +
 +
== Standard ==
 +
This version of UnicodeIntegerToUTF8 complies to the latest standard. LSO on the other hand complies to an earlier standard. The newer standard includes only a subset of the older standard. The extended range of the old standard went unused so this incompleteness is moot.
 +
 +
<lsl>string UnicodeIntegerToUTF8(integer input)//Mono Safe, LSLEditor Safe, LSO Incomplete
 +
{//LSO allows for the older UTF-8 range, this function only supports the new UTF-16 range.
 +
    if(input > 0)
 +
    {
 +
        if(input <= 0x7FF)
 +
        {
 +
            if(input <= 0x7F)
 +
                return llBase64ToString(llIntegerToBase64(input << 24));
 +
            return llBase64ToString(llIntegerToBase64(0xC0800000 | ((input << 18) & 0x1F000000) | ((input << 16) & 0x3F0000)));
 +
        }
 +
        if(input <= 0xFFFF)
 +
            return llBase64ToString(llIntegerToBase64(0xE0808000 | ((input << 12) & 0x0F000000) | ((input << 10) & 0x3F0000) | ((input << 8) & 0x3F00)));
 +
        if(input <= 0x10FFFF)
 +
            return llBase64ToString(llIntegerToBase64(0xF0808080 | ((input << 06) & 0x0E000000) | ((input << 04) & 0x3F0000) | ((input << 2) & 0x3F00) | (input & 0x3F)));
 +
    }
 +
    return "";
 +
}</lsl>
  
 
== General Use==
 
== General Use==

Revision as of 12:22, 25 May 2010

SL uses UTF-8 for storing and transmitting strings and with these functions you can work with Unicode characters. See: Unicode In 5 Minutes for a brief introduction to Unicode.


These functions are part of the Combined Library written by Strife Onizuka.

Standard

This version of UnicodeIntegerToUTF8 complies to the latest standard. LSO on the other hand complies to an earlier standard. The newer standard includes only a subset of the older standard. The extended range of the old standard went unused so this incompleteness is moot.

<lsl>string UnicodeIntegerToUTF8(integer input)//Mono Safe, LSLEditor Safe, LSO Incomplete {//LSO allows for the older UTF-8 range, this function only supports the new UTF-16 range.

   if(input > 0)
   {
       if(input <= 0x7FF)
       {
           if(input <= 0x7F)
               return llBase64ToString(llIntegerToBase64(input << 24));
           return llBase64ToString(llIntegerToBase64(0xC0800000 | ((input << 18) & 0x1F000000) | ((input << 16) & 0x3F0000)));
       }
       if(input <= 0xFFFF)
           return llBase64ToString(llIntegerToBase64(0xE0808000 | ((input << 12) & 0x0F000000) | ((input << 10) & 0x3F0000) | ((input << 8) & 0x3F00)));
       if(input <= 0x10FFFF)
           return llBase64ToString(llIntegerToBase64(0xF0808080 | ((input << 06) & 0x0E000000) | ((input << 04) & 0x3F0000) | ((input << 2) & 0x3F00) | (input & 0x3F)));
   }
   return "";

}</lsl>

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);

}

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>