You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
240 lines
14 KiB
JavaScript
240 lines
14 KiB
JavaScript
/*!
|
|
* XRegExp Unicode Base 3.0.0-pre
|
|
* <http://xregexp.com/>
|
|
* Steven Levithan © 2008-2012 MIT License
|
|
* Uses Unicode 6.2.0 <http://unicode.org/>
|
|
* Unicode data generated by Mathias Bynens <http://mathiasbynens.be/>
|
|
*/
|
|
|
|
/**
|
|
* Adds support for the `\p{L}` or `\p{Letter}` Unicode category. Addon packages for other Unicode
|
|
* categories, scripts, blocks, and properties are available separately. Also adds flag A (astral),
|
|
* which enables 21-bit Unicode support. All Unicode tokens can be inverted using `\P{..}` or
|
|
* `\p{^..}`. Token names ignore case, spaces, hyphens, and underscores.
|
|
* @requires XRegExp
|
|
*/
|
|
(function(XRegExp) {
|
|
'use strict';
|
|
|
|
// Storage for Unicode data
|
|
var unicode = {};
|
|
|
|
/* ==============================
|
|
* Private functions
|
|
* ============================== */
|
|
|
|
// Generates a token lookup name: lowercase, with hyphens, spaces, and underscores removed
|
|
function normalize(name) {
|
|
return name.replace(/[- _]+/g, '').toLowerCase();
|
|
}
|
|
|
|
// Adds leading zeros if shorter than four characters
|
|
function pad4(str) {
|
|
while (str.length < 4) {
|
|
str = '0' + str;
|
|
}
|
|
return str;
|
|
}
|
|
|
|
// Converts a hexadecimal number to decimal
|
|
function dec(hex) {
|
|
return parseInt(hex, 16);
|
|
}
|
|
|
|
// Converts a decimal number to hexadecimal
|
|
function hex(dec) {
|
|
return parseInt(dec, 10).toString(16);
|
|
}
|
|
|
|
// Gets the decimal code of a literal code unit, \xHH, \uHHHH, or a backslash-escaped literal
|
|
function charCode(chr) {
|
|
var esc = /^\\[xu](.+)/.exec(chr);
|
|
return esc ?
|
|
dec(esc[1]) :
|
|
chr.charCodeAt(chr.charAt(0) === '\\' ? 1 : 0);
|
|
}
|
|
|
|
// Inverts a list of ordered BMP characters and ranges
|
|
function invertBmp(range) {
|
|
var output = '',
|
|
lastEnd = -1,
|
|
start;
|
|
XRegExp.forEach(range, /(\\x..|\\u....|\\?[\s\S])(?:-(\\x..|\\u....|\\?[\s\S]))?/, function(m) {
|
|
start = charCode(m[1]);
|
|
if (start > (lastEnd + 1)) {
|
|
output += '\\u' + pad4(hex(lastEnd + 1));
|
|
if (start > (lastEnd + 2)) {
|
|
output += '-\\u' + pad4(hex(start - 1));
|
|
}
|
|
}
|
|
lastEnd = charCode(m[2] || m[1]);
|
|
});
|
|
if (lastEnd < 0xFFFF) {
|
|
output += '\\u' + pad4(hex(lastEnd + 1));
|
|
if (lastEnd < 0xFFFE) {
|
|
output += '-\\uFFFF';
|
|
}
|
|
}
|
|
return output;
|
|
}
|
|
|
|
// Generates an inverted BMP range on first use
|
|
function cacheInvertedBmp(slug) {
|
|
var prop = 'b!';
|
|
return unicode[slug][prop] || (
|
|
unicode[slug][prop] = invertBmp(unicode[slug].bmp)
|
|
);
|
|
}
|
|
|
|
// Combines and optionally negates BMP and astral data
|
|
function buildAstral(slug, isNegated) {
|
|
var item = unicode[slug],
|
|
combined = '';
|
|
if (item.bmp && !item.isBmpLast) {
|
|
combined = '[' + item.bmp + ']' + (item.astral ? '|' : '');
|
|
}
|
|
if (item.astral) {
|
|
combined += item.astral;
|
|
}
|
|
if (item.isBmpLast && item.bmp) {
|
|
combined += (item.astral ? '|' : '') + '[' + item.bmp + ']';
|
|
}
|
|
// Astral Unicode tokens always match a code point, never a code unit
|
|
return isNegated ?
|
|
'(?:(?!' + combined + ')(?:[\uD800-\uDBFF][\uDC00-\uDFFF]|[\0-\uFFFF]))' :
|
|
'(?:' + combined + ')';
|
|
}
|
|
|
|
// Builds a complete astral pattern on first use
|
|
function cacheAstral(slug, isNegated) {
|
|
var prop = isNegated ? 'a!' : 'a=';
|
|
return unicode[slug][prop] || (
|
|
unicode[slug][prop] = buildAstral(slug, isNegated)
|
|
);
|
|
}
|
|
|
|
/* ==============================
|
|
* Core functionality
|
|
* ============================== */
|
|
|
|
/* Add Unicode token syntax: \p{..}, \P{..}, \p{^..}. Also add astral mode (flag A).
|
|
*/
|
|
XRegExp.addToken(
|
|
// Use `*` instead of `+` to avoid capturing `^` as the token name in `\p{^}`
|
|
/\\([pP])(?:{(\^?)([^}]*)}|([A-Za-z]))/,
|
|
function(match, scope, flags) {
|
|
var ERR_DOUBLE_NEG = 'Invalid double negation ',
|
|
ERR_UNKNOWN_NAME = 'Unknown Unicode token ',
|
|
ERR_UNKNOWN_REF = 'Unicode token missing data ',
|
|
ERR_ASTRAL_ONLY = 'Astral mode required for Unicode token ',
|
|
ERR_ASTRAL_IN_CLASS = 'Astral mode does not support Unicode tokens within character classes',
|
|
// Negated via \P{..} or \p{^..}
|
|
isNegated = match[1] === 'P' || !!match[2],
|
|
// Switch from BMP (U+FFFF) to astral (U+10FFFF) mode via flag A or implicit opt-in
|
|
isAstralMode = flags.indexOf('A') > -1 || XRegExp.isInstalled('astral'),
|
|
// Token lookup name. Check `[4]` first to avoid passing `undefined` via `\p{}`
|
|
slug = normalize(match[4] || match[3]),
|
|
// Token data object
|
|
item = unicode[slug];
|
|
|
|
if (match[1] === 'P' && match[2]) {
|
|
throw new SyntaxError(ERR_DOUBLE_NEG + match[0]);
|
|
}
|
|
if (!unicode.hasOwnProperty(slug)) {
|
|
throw new SyntaxError(ERR_UNKNOWN_NAME + match[0]);
|
|
}
|
|
|
|
// Switch to the negated form of the referenced Unicode token
|
|
if (item.inverseOf) {
|
|
slug = normalize(item.inverseOf);
|
|
if (!unicode.hasOwnProperty(slug)) {
|
|
throw new ReferenceError(ERR_UNKNOWN_REF + match[0] + ' -> ' + item.inverseOf);
|
|
}
|
|
item = unicode[slug];
|
|
isNegated = !isNegated;
|
|
}
|
|
|
|
if (!(item.bmp || isAstralMode)) {
|
|
throw new SyntaxError(ERR_ASTRAL_ONLY + match[0]);
|
|
}
|
|
if (isAstralMode) {
|
|
if (scope === 'class') {
|
|
throw new SyntaxError(ERR_ASTRAL_IN_CLASS);
|
|
}
|
|
|
|
return cacheAstral(slug, isNegated);
|
|
}
|
|
|
|
return scope === 'class' ?
|
|
(isNegated ? cacheInvertedBmp(slug) : item.bmp) :
|
|
(isNegated ? '[^' : '[') + item.bmp + ']';
|
|
},
|
|
{
|
|
scope: 'all',
|
|
optionalFlags: 'A'
|
|
}
|
|
);
|
|
|
|
/**
|
|
* Adds to the list of Unicode tokens that XRegExp regexes can match via `\p` or `\P`.
|
|
* @memberOf XRegExp
|
|
* @param {Array} data Objects with named character ranges. Each object may have properties `name`,
|
|
* `alias`, `isBmpLast`, `inverseOf`, `bmp`, and `astral`. All but `name` are optional, although
|
|
* one of `bmp` or `astral` is required (unless `inverseOf` is set). If `astral` is absent, the
|
|
* `bmp` data is used for BMP and astral modes. If `bmp` is absent, the name errors in BMP mode
|
|
* but works in astral mode. If both `bmp` and `astral` are provided, the `bmp` data only is used
|
|
* in BMP mode, and the combination of `bmp` and `astral` data is used in astral mode.
|
|
* `isBmpLast` is needed when a token matches orphan high surrogates *and* uses surrogate pairs
|
|
* to match astral code points. The `bmp` and `astral` data should be a combination of literal
|
|
* characters and `\xHH` or `\uHHHH` escape sequences, with hyphens to create ranges. Any regex
|
|
* metacharacters in the data should be escaped, apart from range-creating hyphens. The `astral`
|
|
* data can additionally use character classes and alternation, and should use surrogate pairs to
|
|
* represent astral code points. `inverseOf` can be used to avoid duplicating character data if a
|
|
* Unicode token is defined as the exact inverse of another token.
|
|
* @example
|
|
*
|
|
* // Basic use
|
|
* XRegExp.addUnicodeData([{
|
|
* name: 'XDigit',
|
|
* alias: 'Hexadecimal',
|
|
* bmp: '0-9A-Fa-f'
|
|
* }]);
|
|
* XRegExp('\\p{XDigit}:\\p{Hexadecimal}+').test('0:3D'); // -> true
|
|
*/
|
|
XRegExp.addUnicodeData = function(data) {
|
|
var ERR_NO_NAME = 'Unicode token requires name',
|
|
ERR_NO_DATA = 'Unicode token has no character data ',
|
|
item,
|
|
i;
|
|
|
|
for (i = 0; i < data.length; ++i) {
|
|
item = data[i];
|
|
if (!item.name) {
|
|
throw new Error(ERR_NO_NAME);
|
|
}
|
|
if (!(item.inverseOf || item.bmp || item.astral)) {
|
|
throw new Error(ERR_NO_DATA + item.name);
|
|
}
|
|
unicode[normalize(item.name)] = item;
|
|
if (item.alias) {
|
|
unicode[normalize(item.alias)] = item;
|
|
}
|
|
}
|
|
|
|
// Reset the pattern cache used by the `XRegExp` constructor, since the same pattern and
|
|
// flags might now produce different results
|
|
XRegExp.cache.flush('patterns');
|
|
};
|
|
|
|
/* Add data for the Unicode `L` or `Letter` category. Separate addons are available that add other
|
|
* categories, scripts, blocks, and properties.
|
|
*/
|
|
XRegExp.addUnicodeData([{
|
|
name: 'L',
|
|
alias: 'Letter',
|
|
bmp: 'A-Za-z\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0\u08A2-\u08AC\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0977\u0979-\u097F\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3D\u0C58\u0C59\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D60\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F4\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191C\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19C1-\u19C7\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FCC\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA697\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA78E\uA790-\uA793\uA7A0-\uA7AA\uA7F8-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA80-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uABC0-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC',
|
|
astral: '\uD802[\uDC00-\uDC05\uDC08\uDC0A-\uDC35\uDC37\uDC38\uDC3C\uDC3F-\uDC55\uDD00-\uDD15\uDD20-\uDD39\uDD80-\uDDB7\uDDBE\uDDBF\uDE00\uDE10-\uDE13\uDE15-\uDE17\uDE19-\uDE33\uDE60-\uDE7C\uDF00-\uDF35\uDF40-\uDF55\uDF60-\uDF72]|\uD801[\uDC00-\uDC9D]|\uD800[\uDC00-\uDC0B\uDC0D-\uDC26\uDC28-\uDC3A\uDC3C\uDC3D\uDC3F-\uDC4D\uDC50-\uDC5D\uDC80-\uDCFA\uDE80-\uDE9C\uDEA0-\uDED0\uDF00-\uDF1E\uDF30-\uDF40\uDF42-\uDF49\uDF80-\uDF9D\uDFA0-\uDFC3\uDFC8-\uDFCF]|\uD81A[\uDC00-\uDE38]|\uD804[\uDC03-\uDC37\uDC83-\uDCAF\uDCD0-\uDCE8\uDD03-\uDD26\uDD83-\uDDB2\uDDC1-\uDDC4]|\uD86E[\uDC00-\uDC1D]|\uD86D[\uDC00-\uDF34\uDF40-\uDFFF]|\uD803[\uDC00-\uDC48]|\uD80D[\uDC00-\uDC2E]|\uD805[\uDE80-\uDEAA]|\uD87E[\uDC00-\uDE1D]|\uD81B[\uDF00-\uDF44\uDF50\uDF93-\uDF9F]|\uD869[\uDC00-\uDED6\uDF00-\uDFFF]|\uD82C[\uDC00\uDC01]|[\uD80C\uD840-\uD868\uD86A-\uD86C][\uDC00-\uDFFF]|\uD83B[\uDE00-\uDE03\uDE05-\uDE1F\uDE21\uDE22\uDE24\uDE27\uDE29-\uDE32\uDE34-\uDE37\uDE39\uDE3B\uDE42\uDE47\uDE49\uDE4B\uDE4D-\uDE4F\uDE51\uDE52\uDE54\uDE57\uDE59\uDE5B\uDE5D\uDE5F\uDE61\uDE62\uDE64\uDE67-\uDE6A\uDE6C-\uDE72\uDE74-\uDE77\uDE79-\uDE7C\uDE7E\uDE80-\uDE89\uDE8B-\uDE9B\uDEA1-\uDEA3\uDEA5-\uDEA9\uDEAB-\uDEBB]|\uD835[\uDC00-\uDC54\uDC56-\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDEA5\uDEA8-\uDEC0\uDEC2-\uDEDA\uDEDC-\uDEFA\uDEFC-\uDF14\uDF16-\uDF34\uDF36-\uDF4E\uDF50-\uDF6E\uDF70-\uDF88\uDF8A-\uDFA8\uDFAA-\uDFC2\uDFC4-\uDFCB]|\uD808[\uDC00-\uDF6E]'
|
|
}]);
|
|
|
|
}(XRegExp));
|