1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
/** Used to compose unicode character classes. */var 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. */var rsApos = "['\u2019]",    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';
/** Used to compose unicode regexes. */var 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;
/** Used to match complex or compound words. */var reUnicodeWord = RegExp([  rsUpper + '?' + rsLower + '+' + rsOptContrLower + '(?=' + [rsBreak, rsUpper, '$'].join('|') + ')',  rsMiscUpper + '+' + rsOptContrUpper + '(?=' + [rsBreak, rsUpper + rsMiscLower, '$'].join('|') + ')',  rsUpper + '?' + rsMiscLower + '+' + rsOptContrLower,  rsUpper + '+' + rsOptContrUpper,  rsOrdUpper,  rsOrdLower,  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;