63 lines
2.7 KiB
JavaScript
63 lines
2.7 KiB
JavaScript
/** Used to compose unicode character classes. */
|
|
var rsAstralRange = '\\ud800-\\udfff',
|
|
rsComboMarksRange = '\\u0300-\\u036f\\ufe20-\\ufe23',
|
|
rsComboSymbolsRange = '\\u20d0-\\u20f0',
|
|
rsDingbatRange = '\\u2700-\\u27bf',
|
|
rsLowerRange = 'a-z\\xdf-\\xf6\\xf8-\\xff',
|
|
rsMathOpRange = '\\xac\\xb1\\xd7\\xf7',
|
|
rsNonCharRange = '\\x00-\\x2f\\x3a-\\x40\\x5b-\\x60\\x7b-\\xbf',
|
|
rsPunctuationRange = '\\u2000-\\u206f',
|
|
rsSpaceRange = ' \\t\\x0b\\f\\xa0\\ufeff\\n\\r\\u2028\\u2029\\u1680\\u180e\\u2000\\u2001\\u2002\\u2003\\u2004\\u2005\\u2006\\u2007\\u2008\\u2009\\u200a\\u202f\\u205f\\u3000',
|
|
rsUpperRange = 'A-Z\\xc0-\\xd6\\xd8-\\xde',
|
|
rsVarRange = '\\ufe0e\\ufe0f',
|
|
rsBreakRange = rsMathOpRange + rsNonCharRange + rsPunctuationRange + rsSpaceRange;
|
|
|
|
/** Used to compose unicode capture groups. */
|
|
var rsApos = "['\u2019]",
|
|
rsBreak = '[' + rsBreakRange + ']',
|
|
rsCombo = '[' + rsComboMarksRange + rsComboSymbolsRange + ']',
|
|
rsDigits = '\\d+',
|
|
rsDingbat = '[' + rsDingbatRange + ']',
|
|
rsLower = '[' + rsLowerRange + ']',
|
|
rsMisc = '[^' + rsAstralRange + rsBreakRange + rsDigits + rsDingbatRange + rsLowerRange + rsUpperRange + ']',
|
|
rsFitz = '\\ud83c[\\udffb-\\udfff]',
|
|
rsModifier = '(?:' + rsCombo + '|' + rsFitz + ')',
|
|
rsNonAstral = '[^' + rsAstralRange + ']',
|
|
rsRegional = '(?:\\ud83c[\\udde6-\\uddff]){2}',
|
|
rsSurrPair = '[\\ud800-\\udbff][\\udc00-\\udfff]',
|
|
rsUpper = '[' + rsUpperRange + ']',
|
|
rsZWJ = '\\u200d';
|
|
|
|
/** Used to compose unicode regexes. */
|
|
var rsLowerMisc = '(?:' + rsLower + '|' + rsMisc + ')',
|
|
rsUpperMisc = '(?:' + rsUpper + '|' + rsMisc + ')',
|
|
rsOptLowerContr = '(?:' + rsApos + '(?:d|ll|m|re|s|t|ve))?',
|
|
rsOptUpperContr = '(?:' + rsApos + '(?:D|LL|M|RE|S|T|VE))?',
|
|
reOptMod = rsModifier + '?',
|
|
rsOptVar = '[' + rsVarRange + ']?',
|
|
rsOptJoin = '(?:' + rsZWJ + '(?:' + [rsNonAstral, rsRegional, rsSurrPair].join('|') + ')' + rsOptVar + reOptMod + ')*',
|
|
rsSeq = rsOptVar + reOptMod + rsOptJoin,
|
|
rsEmoji = '(?:' + [rsDingbat, rsRegional, rsSurrPair].join('|') + ')' + rsSeq;
|
|
|
|
/** Used to match complex or compound words. */
|
|
var reUnicodeWord = RegExp([
|
|
rsUpper + '?' + rsLower + '+' + rsOptLowerContr + '(?=' + [rsBreak, rsUpper, '$'].join('|') + ')',
|
|
rsUpperMisc + '+' + rsOptUpperContr + '(?=' + [rsBreak, rsUpper + rsLowerMisc, '$'].join('|') + ')',
|
|
rsUpper + '?' + rsLowerMisc + '+' + rsOptLowerContr,
|
|
rsUpper + '+' + rsOptUpperContr,
|
|
rsDigits,
|
|
rsEmoji
|
|
].join('|'), 'g');
|
|
|
|
/**
|
|
* Splits a Unicode `string` into an array of its words.
|
|
*
|
|
* @private
|
|
* @param {string} The string to inspect.
|
|
* @returns {Array} Returns the words of `string`.
|
|
*/
|
|
function unicodeWords(string) {
|
|
return string.match(reUnicodeWord) || [];
|
|
}
|
|
|
|
module.exports = unicodeWords;
|