swc/crates/swc_bundler/tests/.cache/untrusted/c7f1067bf34e40ce7f0f971b7607268ece822a0a.ts
2021-11-09 20:42:49 +09:00

74 lines
3.1 KiB
TypeScript

// Loaded from https://raw.githubusercontent.com/lodash/lodash/master/.internal/unicodeWords.js
/** Used to compose unicode character classes. */
const rsAstralRange = '\\ud800-\\udfff'
const rsComboMarksRange = '\\u0300-\\u036f'
const reComboHalfMarksRange = '\\ufe20-\\ufe2f'
const rsComboSymbolsRange = '\\u20d0-\\u20ff'
const rsComboMarksExtendedRange = '\\u1ab0-\\u1aff'
const rsComboMarksSupplementRange = '\\u1dc0-\\u1dff'
const rsComboRange = rsComboMarksRange + reComboHalfMarksRange + rsComboSymbolsRange + rsComboMarksExtendedRange + rsComboMarksSupplementRange
const rsDingbatRange = '\\u2700-\\u27bf'
const rsLowerRange = 'a-z\\xdf-\\xf6\\xf8-\\xff'
const rsMathOpRange = '\\xac\\xb1\\xd7\\xf7'
const rsNonCharRange = '\\x00-\\x2f\\x3a-\\x40\\x5b-\\x60\\x7b-\\xbf'
const rsPunctuationRange = '\\u2000-\\u206f'
const 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'
const rsUpperRange = 'A-Z\\xc0-\\xd6\\xd8-\\xde'
const rsVarRange = '\\ufe0e\\ufe0f'
const rsBreakRange = rsMathOpRange + rsNonCharRange + rsPunctuationRange + rsSpaceRange
/** Used to compose unicode capture groups. */
const rsApos = "['\u2019]"
const rsBreak = `[${rsBreakRange}]`
const rsCombo = `[${rsComboRange}]`
const rsDigit = '\\d'
const rsDingbat = `[${rsDingbatRange}]`
const rsLower = `[${rsLowerRange}]`
const rsMisc = `[^${rsAstralRange}${rsBreakRange + rsDigit + rsDingbatRange + rsLowerRange + rsUpperRange}]`
const rsFitz = '\\ud83c[\\udffb-\\udfff]'
const rsModifier = `(?:${rsCombo}|${rsFitz})`
const rsNonAstral = `[^${rsAstralRange}]`
const rsRegional = '(?:\\ud83c[\\udde6-\\uddff]){2}'
const rsSurrPair = '[\\ud800-\\udbff][\\udc00-\\udfff]'
const rsUpper = `[${rsUpperRange}]`
const rsZWJ = '\\u200d'
/** Used to compose unicode regexes. */
const rsMiscLower = `(?:${rsLower}|${rsMisc})`
const rsMiscUpper = `(?:${rsUpper}|${rsMisc})`
const rsOptContrLower = `(?:${rsApos}(?:d|ll|m|re|s|t|ve))?`
const rsOptContrUpper = `(?:${rsApos}(?:D|LL|M|RE|S|T|VE))?`
const reOptMod = `${rsModifier}?`
const rsOptVar = `[${rsVarRange}]?`
const rsOptJoin = `(?:${rsZWJ}(?:${[rsNonAstral, rsRegional, rsSurrPair].join('|')})${rsOptVar + reOptMod})*`
const rsOrdLower = '\\d*(?:1st|2nd|3rd|(?![123])\\dth)(?=\\b|[A-Z_])'
const rsOrdUpper = '\\d*(?:1ST|2ND|3RD|(?![123])\\dTH)(?=\\b|[a-z_])'
const rsSeq = rsOptVar + reOptMod + rsOptJoin
const rsEmoji = `(?:${[rsDingbat, rsRegional, rsSurrPair].join('|')})${rsSeq}`
const reUnicodeWords = RegExp([
`${rsUpper}?${rsLower}+${rsOptContrLower}(?=${[rsBreak, rsUpper, '$'].join('|')})`,
`${rsMiscUpper}+${rsOptContrUpper}(?=${[rsBreak, rsUpper + rsMiscLower, '$'].join('|')})`,
`${rsUpper}?${rsMiscLower}+${rsOptContrLower}`,
`${rsUpper}+${rsOptContrUpper}`,
rsOrdUpper,
rsOrdLower,
`${rsDigit}+`,
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(reUnicodeWords)
}
export default unicodeWords