unicode-base.js (13187B)
1 /*! 2 * XRegExp Unicode Base 3.0.0-pre 3 * <http://xregexp.com/> 4 * Steven Levithan © 2008-2012 MIT License 5 * Uses Unicode 6.2.0 <http://unicode.org/> 6 * Unicode data generated by Mathias Bynens <http://mathiasbynens.be/> 7 */ 8 9 /** 10 * Adds support for the `\p{L}` or `\p{Letter}` Unicode category. Addon packages for other Unicode 11 * categories, scripts, blocks, and properties are available separately. Also adds flag A (astral), 12 * which enables 21-bit Unicode support. All Unicode tokens can be inverted using `\P{..}` or 13 * `\p{^..}`. Token names ignore case, spaces, hyphens, and underscores. 14 * @requires XRegExp 15 */ 16 (function(XRegExp) { 17 'use strict'; 18 19 // Storage for Unicode data 20 var unicode = {}; 21 22 /* ============================== 23 * Private functions 24 * ============================== */ 25 26 // Generates a token lookup name: lowercase, with hyphens, spaces, and underscores removed 27 function normalize(name) { 28 return name.replace(/[- _]+/g, '').toLowerCase(); 29 } 30 31 // Adds leading zeros if shorter than four characters 32 function pad4(str) { 33 while (str.length < 4) { 34 str = '0' + str; 35 } 36 return str; 37 } 38 39 // Converts a hexadecimal number to decimal 40 function dec(hex) { 41 return parseInt(hex, 16); 42 } 43 44 // Converts a decimal number to hexadecimal 45 function hex(dec) { 46 return parseInt(dec, 10).toString(16); 47 } 48 49 // Gets the decimal code of a literal code unit, \xHH, \uHHHH, or a backslash-escaped literal 50 function charCode(chr) { 51 var esc = /^\\[xu](.+)/.exec(chr); 52 return esc ? 53 dec(esc[1]) : 54 chr.charCodeAt(chr.charAt(0) === '\\' ? 1 : 0); 55 } 56 57 // Inverts a list of ordered BMP characters and ranges 58 function invertBmp(range) { 59 var output = '', 60 lastEnd = -1, 61 start; 62 XRegExp.forEach(range, /(\\x..|\\u....|\\?[\s\S])(?:-(\\x..|\\u....|\\?[\s\S]))?/, function(m) { 63 start = charCode(m[1]); 64 if (start > (lastEnd + 1)) { 65 output += '\\u' + pad4(hex(lastEnd + 1)); 66 if (start > (lastEnd + 2)) { 67 output += '-\\u' + pad4(hex(start - 1)); 68 } 69 } 70 lastEnd = charCode(m[2] || m[1]); 71 }); 72 if (lastEnd < 0xFFFF) { 73 output += '\\u' + pad4(hex(lastEnd + 1)); 74 if (lastEnd < 0xFFFE) { 75 output += '-\\uFFFF'; 76 } 77 } 78 return output; 79 } 80 81 // Generates an inverted BMP range on first use 82 function cacheInvertedBmp(slug) { 83 var prop = 'b!'; 84 return unicode[slug][prop] || ( 85 unicode[slug][prop] = invertBmp(unicode[slug].bmp) 86 ); 87 } 88 89 // Combines and optionally negates BMP and astral data 90 function buildAstral(slug, isNegated) { 91 var item = unicode[slug], 92 combined = ''; 93 if (item.bmp && !item.isBmpLast) { 94 combined = '[' + item.bmp + ']' + (item.astral ? '|' : ''); 95 } 96 if (item.astral) { 97 combined += item.astral; 98 } 99 if (item.isBmpLast && item.bmp) { 100 combined += (item.astral ? '|' : '') + '[' + item.bmp + ']'; 101 } 102 // Astral Unicode tokens always match a code point, never a code unit 103 return isNegated ? 104 '(?:(?!' + combined + ')(?:[\uD800-\uDBFF][\uDC00-\uDFFF]|[\0-\uFFFF]))' : 105 '(?:' + combined + ')'; 106 } 107 108 // Builds a complete astral pattern on first use 109 function cacheAstral(slug, isNegated) { 110 var prop = isNegated ? 'a!' : 'a='; 111 return unicode[slug][prop] || ( 112 unicode[slug][prop] = buildAstral(slug, isNegated) 113 ); 114 } 115 116 /* ============================== 117 * Core functionality 118 * ============================== */ 119 120 /* Add Unicode token syntax: \p{..}, \P{..}, \p{^..}. Also add astral mode (flag A). 121 */ 122 XRegExp.addToken( 123 // Use `*` instead of `+` to avoid capturing `^` as the token name in `\p{^}` 124 /\\([pP])(?:{(\^?)([^}]*)}|([A-Za-z]))/, 125 function(match, scope, flags) { 126 var ERR_DOUBLE_NEG = 'Invalid double negation ', 127 ERR_UNKNOWN_NAME = 'Unknown Unicode token ', 128 ERR_UNKNOWN_REF = 'Unicode token missing data ', 129 ERR_ASTRAL_ONLY = 'Astral mode required for Unicode token ', 130 ERR_ASTRAL_IN_CLASS = 'Astral mode does not support Unicode tokens within character classes', 131 // Negated via \P{..} or \p{^..} 132 isNegated = match[1] === 'P' || !!match[2], 133 // Switch from BMP (U+FFFF) to astral (U+10FFFF) mode via flag A or implicit opt-in 134 isAstralMode = flags.indexOf('A') > -1 || XRegExp.isInstalled('astral'), 135 // Token lookup name. Check `[4]` first to avoid passing `undefined` via `\p{}` 136 slug = normalize(match[4] || match[3]), 137 // Token data object 138 item = unicode[slug]; 139 140 if (match[1] === 'P' && match[2]) { 141 throw new SyntaxError(ERR_DOUBLE_NEG + match[0]); 142 } 143 if (!unicode.hasOwnProperty(slug)) { 144 throw new SyntaxError(ERR_UNKNOWN_NAME + match[0]); 145 } 146 147 // Switch to the negated form of the referenced Unicode token 148 if (item.inverseOf) { 149 slug = normalize(item.inverseOf); 150 if (!unicode.hasOwnProperty(slug)) { 151 throw new ReferenceError(ERR_UNKNOWN_REF + match[0] + ' -> ' + item.inverseOf); 152 } 153 item = unicode[slug]; 154 isNegated = !isNegated; 155 } 156 157 if (!(item.bmp || isAstralMode)) { 158 throw new SyntaxError(ERR_ASTRAL_ONLY + match[0]); 159 } 160 if (isAstralMode) { 161 if (scope === 'class') { 162 throw new SyntaxError(ERR_ASTRAL_IN_CLASS); 163 } 164 165 return cacheAstral(slug, isNegated); 166 } 167 168 return scope === 'class' ? 169 (isNegated ? cacheInvertedBmp(slug) : item.bmp) : 170 (isNegated ? '[^' : '[') + item.bmp + ']'; 171 }, 172 { 173 scope: 'all', 174 optionalFlags: 'A' 175 } 176 ); 177 178 /** 179 * Adds to the list of Unicode tokens that XRegExp regexes can match via `\p` or `\P`. 180 * @memberOf XRegExp 181 * @param {Array} data Objects with named character ranges. Each object may have properties `name`, 182 * `alias`, `isBmpLast`, `inverseOf`, `bmp`, and `astral`. All but `name` are optional, although 183 * one of `bmp` or `astral` is required (unless `inverseOf` is set). If `astral` is absent, the 184 * `bmp` data is used for BMP and astral modes. If `bmp` is absent, the name errors in BMP mode 185 * but works in astral mode. If both `bmp` and `astral` are provided, the `bmp` data only is used 186 * in BMP mode, and the combination of `bmp` and `astral` data is used in astral mode. 187 * `isBmpLast` is needed when a token matches orphan high surrogates *and* uses surrogate pairs 188 * to match astral code points. The `bmp` and `astral` data should be a combination of literal 189 * characters and `\xHH` or `\uHHHH` escape sequences, with hyphens to create ranges. Any regex 190 * metacharacters in the data should be escaped, apart from range-creating hyphens. The `astral` 191 * data can additionally use character classes and alternation, and should use surrogate pairs to 192 * represent astral code points. `inverseOf` can be used to avoid duplicating character data if a 193 * Unicode token is defined as the exact inverse of another token. 194 * @example 195 * 196 * // Basic use 197 * XRegExp.addUnicodeData([{ 198 * name: 'XDigit', 199 * alias: 'Hexadecimal', 200 * bmp: '0-9A-Fa-f' 201 * }]); 202 * XRegExp('\\p{XDigit}:\\p{Hexadecimal}+').test('0:3D'); // -> true 203 */ 204 XRegExp.addUnicodeData = function(data) { 205 var ERR_NO_NAME = 'Unicode token requires name', 206 ERR_NO_DATA = 'Unicode token has no character data ', 207 item, 208 i; 209 210 for (i = 0; i < data.length; ++i) { 211 item = data[i]; 212 if (!item.name) { 213 throw new Error(ERR_NO_NAME); 214 } 215 if (!(item.inverseOf || item.bmp || item.astral)) { 216 throw new Error(ERR_NO_DATA + item.name); 217 } 218 unicode[normalize(item.name)] = item; 219 if (item.alias) { 220 unicode[normalize(item.alias)] = item; 221 } 222 } 223 224 // Reset the pattern cache used by the `XRegExp` constructor, since the same pattern and 225 // flags might now produce different results 226 XRegExp.cache.flush('patterns'); 227 }; 228 229 /* Add data for the Unicode `L` or `Letter` category. Separate addons are available that add other 230 * categories, scripts, blocks, and properties. 231 */ 232 XRegExp.addUnicodeData([{ 233 name: 'L', 234 alias: 'Letter', 235 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' 236 //astral: /* Removed to conserve space */ 237 }]); 238 239 }(XRegExp));