resources/jquery/jquery.byteLength.js

   1 /**
   2  * jQuery.byteLength
   3  *
   4  * Calculate the byte length of a string (accounting for UTF-8).
   5  *
   6  * @author Jan Paul Posma, 2011
   7  * @author Timo Tijhof, 2012
   8  * @author David Chan, 2013
   9  */
  10 jQuery.byteLength = function ( str ) {
  11
  12         // This basically figures out how many bytes a UTF-16 string (which is what js sees)
  13         // will take in UTF-8 by replacing a 2 byte character with 2 *'s, etc, and counting that.
  14         // Note, surrogate (\uD800-\uDFFF) characters are counted as 2 bytes, since there's two of them
  15         // and the actual character takes 4 bytes in UTF-8 (2*2=4). Might not work perfectly in
  16         // edge cases such as illegal sequences, but that should never happen.
  17
  18         // https://en.wikipedia.org/wiki/UTF-8#Description
  19         // The mapping from UTF-16 code units to UTF-8 bytes is as follows:
  20         // > Range 0000-007F: codepoints that become 1 byte of UTF-8
  21         // > Range 0080-07FF: codepoints that become 2 bytes of UTF-8
  22         // > Range 0800-D7FF: codepoints that become 3 bytes of UTF-8
  23         // > Range D800-DFFF: Surrogates (each pair becomes 4 bytes of UTF-8)
  24         // > Range E000-FFFF: codepoints that become 3 bytes of UTF-8 (continued)
  25
  26         return str
  27                 .replace( /[\u0080-\u07FF\uD800-\uDFFF]/g, '**' )
  28                 .replace( /[\u0800-\uD7FF\uE000-\uFFFF]/g, '***' )
  29                 .length;
  30
  31 };