@feugene/mu/src/string/unicode.ts

Helpful TS utilities without dependencies

/** Used to compose unicode character classes. */
const rsAstralRange = '\\ud800-\\udfff',
  rsComboMarksRange = '\\u0300-\\u036f',
  reComboHalfMarksRange = '\\ufe20-\\ufe2f',
  rsComboSymbolsRange = '\\u20d0-\\u20ff',
  rsComboRange = rsComboMarksRange + reComboHalfMarksRange + rsComboSymbolsRange,
  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. */
const rsApos = "['\u2019]",
  rsAstral = '[' + rsAstralRange + ']',
  rsBreak = '[' + rsBreakRange + ']',
  rsCombo = '[' + rsComboRange + ']',
  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'

const reHasUnicode = new RegExp('[' + rsZWJ + rsAstralRange + rsComboRange + rsVarRange + ']')

/** Used to compose unicode regexes. */
const rsMiscLower = '(?:' + rsLower + '|' + rsMisc + ')',
  rsMiscUpper = '(?:' + rsUpper + '|' + rsMisc + ')',
  rsOptContrLower = '(?:' + rsApos + '(?:d|ll|m|re|s|t|ve))?',
  rsOptContrUpper = '(?:' + rsApos + '(?:D|LL|M|RE|S|T|VE))?',
  reOptMod = rsModifier + '?',
  rsOptVar = '[' + rsVarRange + ']?',
  rsOptJoin =
    '(?:' + rsZWJ + '(?:' + [rsNonAstral, rsRegional, rsSurrPair].join('|') + ')' + rsOptVar + reOptMod + ')*',
  rsOrdLower = '\\d*(?:1st|2nd|3rd|(?![123])\\dth)(?=\\b|[A-Z_])',
  rsOrdUpper = '\\d*(?:1ST|2ND|3RD|(?![123])\\dTH)(?=\\b|[a-z_])',
  rsSeq = rsOptVar + reOptMod + rsOptJoin,
  rsEmoji = '(?:' + [rsDingbat, rsRegional, rsSurrPair].join('|') + ')' + rsSeq,
  rsSymbol = '(?:' + [rsNonAstral + rsCombo + '?', rsCombo, rsRegional, rsSurrPair, rsAstral].join('|') + ')'

/** Used to match [string symbols](https://mathiasbynens.be/notes/javascript-unicode). */
export const reUnicode = new RegExp(rsFitz + '(?=' + rsFitz + ')|' + rsSymbol + rsSeq, 'g')

/**
 * Checks if `string` contains Unicode symbols.
 *
 * @param {string} value The string to inspect.
 * @returns {boolean} Returns `true` if a symbol is found, else `false`.
 */
export function hasUnicode(value: string): boolean {
  return reHasUnicode.test(value)
}

export default {
  reUnicode,
  hasUnicode,
}