Difference between revisions of "Unescape"
Jump to navigation
Jump to search
m |
m |
||
Line 38: | Line 38: | ||
integer f = 0; | integer f = 0; | ||
string g; | string g; | ||
while(d = (-~(llSubStringIndex(b, "\\")))) | while(d = (-~(llSubStringIndex(b, "\\")))) //" //wiki highlighter bug | ||
{ | { | ||
c += d; | c += d; |
Revision as of 10:31, 20 September 2013
Takes a string and unescapes "\" style escape codes
Code | Replace |
---|---|
\\ | \ |
\" | " |
\s | single space |
\n | new line |
\t | 4 spaces (tab) |
\uxxxx | xxxx is a 4 char hex string, of the unicode character 0000xxxx |
\Uxxxxxxxx | xxxxxxxx is am 8 char hex string, of the unicode character xxxxxxxx |
\hXxxx... | X is a hex character, it's value is the number of pairs of hex characters that follow it, xxx is a raw byte array of utf-8 characters, be sure they are valid characters |
<lsl>//===================================================// // Combined Library // // "Jan 2 2008", "04:48:12" // // Copyright (C) 2004-2007, Strife Onizuka (cc-by) // // http://creativecommons.org/licenses/by/3.0/ // //===================================================// //{
string Unescape(string a)//Mono Safe, LSO Safe {
string b = a; integer c = -1; integer d; integer e; integer f = 0; string g; while(d = (-~(llSubStringIndex(b, "\\")))) //" //wiki highlighter bug { c += d; if(2 < (e = llSubStringIndex("uUhts\"q\\n",llGetSubString(b,d,d)))) a = llInsertString(llDeleteSubString(a,c, (-~(c))), c, llGetSubString(" \"\"\\\n",e * (e != 3), e)); else if(e==2)//hx[11,22,33,44,55,66,77,88,99,AA,BB,CC,DD,EE,FF] { if((f = llStringLength(b)) <= ((d) - ~(e = ((integer)("0x"+llGetSubString(b,(-~(d)),(-~(d)))) << 1)))) { e = (f - d) & -2; b += "0";//a pad may be needed. } g = "";//flush the buffer. if((f = e))//this may look like a mistake, it's not { do g = "%"+llGetSubString(b,d + e, ((d) - ~(e))) + g; while((e -= 2));//(e-=2) > 0, e should always be even } a = llInsertString(llDeleteSubString(a,c, 2 + f + c),c, g = llUnescapeURL(g)); c += (~-(llStringLength(g)));//add to c so we don't accidentily unescape result } else if(~e)// \uXXXX or \UXXXXXXXX { a = llDeleteSubString(a, c, ((e = 4 << e) - ~(c))); if(0 < (e = ((integer)("0x"+(llGetSubString(b, (-~(d)), d + e)))))) { f = llCeil((llLog(e) / 0.69314718055994530941723212145818)); f = (e >= 0x80) * ((f) + ~((((1 << f) - e) > 0))) / 5;//adjust g = "%" + byte2hex((e >> (6 * f)) | ((0x3F80 >> f) << !f)); while (f) g += "%" + byte2hex((((e >> (6 * (f = ~-f))) | 0x80) & 0xBF)); a = llInsertString(a, c, llUnescapeURL(g)); } } b = llDeleteSubString(a,0,c); } return a;
}
string byte2hex(integer x)//Mono 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";
//}</lsl>
<lsl>//Testbed default {
state_entry() { llOwnerSay((string)llGetFreeMemory()); string a = "-\\h3414243\\h3444546\\\"\\uFFFD"; string d = Unescape(a); llOwnerSay(llList2CSV([a, d])); }
}</lsl>