Refine combo mark ranges.

This commit is contained in:
John-David Dalton
2016-11-04 16:34:03 -07:00
parent 1b3815928d
commit cafb9822ce

View File

@@ -199,8 +199,10 @@
/** Used to compose unicode character classes. */
var rsAstralRange = '\\ud800-\\udfff',
rsComboMarksRange = '\\u0300-\\u036f\\ufe20-\\ufe23',
rsComboSymbolsRange = '\\u20d0-\\u20f0',
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',
@@ -215,7 +217,7 @@
var rsApos = "['\u2019]",
rsAstral = '[' + rsAstralRange + ']',
rsBreak = '[' + rsBreakRange + ']',
rsCombo = '[' + rsComboMarksRange + rsComboSymbolsRange + ']',
rsCombo = '[' + rsComboRange + ']',
rsDigits = '\\d+',
rsDingbat = '[' + rsDingbatRange + ']',
rsLower = '[' + rsLowerRange + ']',
@@ -267,7 +269,7 @@
].join('|'), 'g');
/** 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/). */
var reHasUnicode = RegExp('[' + rsZWJ + rsAstralRange + rsComboMarksRange + rsComboSymbolsRange + rsVarRange + ']');
var reHasUnicode = RegExp('[' + rsZWJ + rsAstralRange + rsComboRange + rsVarRange + ']');
/** Used to detect strings that need a more robust regexp to match words. */
var reHasUnicodeWord = /[a-z][A-Z]|[A-Z]{2,}[a-z]|[0-9][a-zA-Z]|[a-zA-Z][0-9]|[^a-zA-Z0-9 ]/;