Run results for: UTF-8 byte length Arabic 4-mthods

Run details:

User agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0

Browser: Chrome 126

Operating system: Windows

Device Platform: Desktop

Date tested: 3 months ago

Test name	Executions per second
with a loop Arabic	596563.4 Ops/sec
with a regex Arabic	37533.6 Ops/sec
with a TextEncoder ِِArabic	235739.1 Ops/sec
with a Blob Arabic	10737.5 Ops/sec

Script Preparation code:

var arabic_str = "kksldfnjeoliwkfmirewogbregiojrmfikrefnهنصتةبهنمخصةبهخصثةبثصهنخقلةثقملىثقمةلكمسقنلمنكقةلمنيبةىلميبنكلكمطسيوبصثقنلحخثقتلثقنلوسيكملنسيكملklrmglkedrmg;ler,g;lkerdmglkermg;ler,g;lerkmglkerglk;ermg;lermg;hjfbwefseoifnuiwefصثعىبصثبىهصثىةبخهمصقاىلثخقتلةحخثقلةثقلةثقلةثقلةثخقلةحخثقلةخقثلةثحخقلةثينقىلنمقثيىلنمقىلمنيثقسىلقىلمقىلنمكقىلمنقىلمنيثقىلمنقىلمنقثىيةلمنخىثيقمنلةيمنلتىنثتقيىلخهمثقيةلخمثقيىلثقفيىلنثقيةلمنخىفقثيلىىىتنعصثىبمخنثةصبحةثصقخمبىثقخمنهلىةثحكقةلكحثقةلمنثقىلمنثقىلكمثةقلكمثقةلمنىثقلمنىثقلمنىثقلنمكثىقلنمكثقىلمنثيقىلمطنثقىلمنطثقىةسلبثمكسقيلةثطقكةلونطحكصثقنلخحثقةلحكخمقفةاقفهىاقفاىقفةلحخثقهخابهقعثالخهثقتلخهثقالخهاثقهعلخباثقحهخبةصحخثجؤوخحجصسثؤوحخصثرةىخهمثقيلىرخهمثقلىخهثقمللاخهثمقلتحخثقتلبحخصثتبحخصثستىبخهمثقىلخهمنثقىلحخثقىلحثقىلخهمنثقصىلثقةلحخثقىلمخهنثيقىلمصثويبجحصضثنيحخصثتبهختثصقخهلبةثقهنخلمةثقيرنمهىيؤنتءراىهخثقةرثقمرةثقيمخهنلىخهثقنلىخهمثقهتل"
var english_str = "UTF-8 encodes each of the 1,112,064 valid code points in the Unicode code space (1,114,112 code points minus 2,048 surrogate code points) using one to four 8-bit bytes (a group of 8 bits is known as an «octet» in the Unicode Standard). Code points wi"

function lengthInUtf8Bytes(str) {
  // Matches only the 10.. bytes that are non-initial characters in a multi-byte sequence.
  var m = encodeURIComponent(str).match(/%[89ABab]/g);
  return str.length + (m ? m.length : 0);
}


function byteLength(str) {
  // returns the byte length of an utf8 string
  var s = str.length;
  for (var i=str.length-1; i>=0; i--) {
    var code = str.charCodeAt(i);
    if (code > 0x7f && code <= 0x7ff) s++;
    else if (code > 0x7ff && code <= 0xffff) s+=2;
  }
  return s;
}

function byteLengthTextEncoder(str) {
  return (new TextEncoder().encode(str)).length;
}

function byteLengthBlob(str) {
  return new Blob([str]).size;
}

Tests:

with a loop Arabic
byteLength(arabic_str);
with a regex Arabic
lengthInUtf8Bytes(arabic_str);
with a TextEncoder ِِArabic
byteLengthTextEncoder(arabic_str)
with a Blob Arabic
byteLengthBlob(arabic_str);

Run results for: UTF-8 byte length Arabic 4-mthods

with a loop Arabic

with a regex Arabic

with a TextEncoder ِِArabic

with a Blob Arabic