time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

_hasUnicode.js (949B)


      1 /** Used to compose unicode character classes. */
      2 var rsAstralRange = '\\ud800-\\udfff',
      3     rsComboMarksRange = '\\u0300-\\u036f',
      4     reComboHalfMarksRange = '\\ufe20-\\ufe2f',
      5     rsComboSymbolsRange = '\\u20d0-\\u20ff',
      6     rsComboRange = rsComboMarksRange + reComboHalfMarksRange + rsComboSymbolsRange,
      7     rsVarRange = '\\ufe0e\\ufe0f';
      8 
      9 /** Used to compose unicode capture groups. */
     10 var rsZWJ = '\\u200d';
     11 
     12 /** Used to detect strings with [zero-width joiners or code points from the astral planes](http://eev.ee/blog/2015/09/12/dark-corners-of-unicode/). */
     13 var reHasUnicode = RegExp('[' + rsZWJ + rsAstralRange  + rsComboRange + rsVarRange + ']');
     14 
     15 /**
     16  * Checks if `string` contains Unicode symbols.
     17  *
     18  * @private
     19  * @param {string} string The string to inspect.
     20  * @returns {boolean} Returns `true` if a symbol is found, else `false`.
     21  */
     22 function hasUnicode(string) {
     23   return reHasUnicode.test(string);
     24 }
     25 
     26 module.exports = hasUnicode;