diff options
author | Mathias Bynens <mathias@qiwi.be> | 2013-07-01 18:45:41 +0200 |
---|---|---|
committer | Mathias Bynens <mathias@qiwi.be> | 2013-07-01 18:45:41 +0200 |
commit | 600519d04c6e25dce3a138b6a853d340ba6992df (patch) | |
tree | 2623ebc8966ebd66bb8c40baf8de2bac77c62ea8 | |
parent | ef5c48beadbf5d5812bd03f61aa131686cde92c8 (diff) | |
download | he-600519d04c6e25dce3a138b6a853d340ba6992df.zip he-600519d04c6e25dce3a138b6a853d340ba6992df.tar.gz he-600519d04c6e25dce3a138b6a853d340ba6992df.tar.bz2 |
Improve malformed entity detection
-rw-r--r-- | he.js | 3 | ||||
-rw-r--r-- | src/he.js | 3 | ||||
-rw-r--r-- | tests/tests.js | 26 | ||||
-rw-r--r-- | tests/tests.src.js | 26 |
4 files changed, 56 insertions, 2 deletions
@@ -23,6 +23,7 @@ var regexHexadecimalEscape = /&#[xX]([a-fA-F0-9]+)(;?)/g; var regexNamedReference = /&([0-9a-zA-Z]+);/g; var regexLegacyReference = /&(Aacute|iacute|Uacute|plusmn|otilde|Otilde|Agrave|agrave|yacute|Yacute|oslash|Oslash|Atilde|atilde|brvbar|Ccedil|ccedil|ograve|curren|divide|Eacute|eacute|Ograve|oacute|Egrave|egrave|ugrave|frac12|frac14|frac34|Ugrave|Oacute|Iacute|ntilde|Ntilde|uacute|middot|Igrave|igrave|iquest|aacute|laquo|THORN|micro|iexcl|icirc|Icirc|Acirc|ucirc|ecirc|Ocirc|ocirc|Ecirc|Ucirc|aring|Aring|aelig|AElig|acute|pound|raquo|acirc|times|thorn|szlig|cedil|COPY|Auml|ordf|ordm|uuml|macr|Uuml|auml|Ouml|ouml|para|nbsp|Euml|quot|QUOT|euml|yuml|cent|sect|copy|sup1|sup2|sup3|Iuml|iuml|shy|eth|reg|not|yen|amp|AMP|REG|uml|ETH|deg|gt|GT|LT|lt)([=a-zA-Z0-9])?/g; + var regexInvalidEntity = /&#(?:[xX][^a-fA-F0-9]|[^0-9xX])/; var regexEncode = /<\u20D2|=\u20E5|>\u20D2|\u205F\u200A|\u219D\u0338|\u2202\u0338|\u2220\u20D2|\u2229\uFE00|\u222A\uFE00|\u223C\u20D2|\u223D\u0331|\u223E\u0333|\u2242\u0338|\u224B\u0338|\u224D\u20D2|\u224E\u0338|\u224F\u0338|\u2250\u0338|\u2261\u20E5|\u2264\u20D2|\u2265\u20D2|\u2266\u0338|\u2267\u0338|\u2268\uFE00|\u2269\uFE00|\u226A\u0338|\u226A\u20D2|\u226B\u0338|\u226B\u20D2|\u227F\u0338|\u2282\u20D2|\u2283\u20D2|\u228A\uFE00|\u228B\uFE00|\u228F\u0338|\u2290\u0338|\u2293\uFE00|\u2294\uFE00|\u22B4\u20D2|\u22B5\u20D2|\u22D8\u0338|\u22D9\u0338|\u22DA\uFE00|\u22DB\uFE00|\u22F5\u0338|\u22F9\u0338|\u2933\u0338|\u29CF\u0338|\u29D0\u0338|\u2A6D\u0338|\u2A70\u0338|\u2A7D\u0338|\u2A7E\u0338|\u2AA1\u0338|\u2AA2\u0338|\u2AAC\uFE00|\u2AAD\uFE00|\u2AAF\u0338|\u2AB0\u0338|\u2AC5\u0338|\u2AC6\u0338|\u2ACB\uFE00|\u2ACC\uFE00|\u2AFD\u20E5|[\x09\x22\x26\x27\x3C\x3E\xA0-\u0113\u0116-\u0122\u0124-\u012B\u012E-\u014D\u0150-\u017E\u0192\u01B5\u01F5\u0237\u02C6\u02C7\u02D8-\u02DD\u0311\u0391-\u03A1\u03A3-\u03A9\u03B1-\u03C9\u03D1\u03D2\u03D5\u03D6\u03DC\u03DD\u03F0\u03F1\u03F5\u03F6\u0401-\u040C\u040E-\u044F\u0451-\u045C\u045E\u045F\u2002-\u2005\u2007-\u2010\u2013-\u2016\u2018-\u201A\u201C-\u201E\u2020-\u2022\u2025\u2026\u2030-\u2035\u2039\u203A\u203E\u2041\u2043\u2044\u204F\u2057\u205F-\u2063\u20AC\u20DB\u20DC\u2102\u2105\u210A-\u2113\u2115-\u211E\u2122\u2124\u2127-\u2129\u212C\u212D\u212F-\u2131\u2133-\u2138\u2145-\u2148\u2153-\u215E\u2190-\u219B\u219D-\u21A7\u21A9-\u21AE\u21B0-\u21B3\u21B5-\u21B7\u21BA-\u21DB\u21DD\u21E4\u21E5\u21F5\u21FD-\u2205\u2207-\u2209\u220B\u220C\u220F-\u2214\u2216-\u2218\u221A\u221D-\u2238\u223A-\u2257\u2259\u225A\u225C\u225F-\u2262\u2264-\u228B\u228D-\u229B\u229D-\u22A5\u22A7-\u22B0\u22B2-\u22BB\u22BD-\u22DB\u22DE-\u22E3\u22E6-\u22F7\u22F9-\u22FE\u2305\u2306\u2308-\u2310\u2312\u2313\u2315\u2316\u231C-\u231F\u2322\u2323\u232D\u232E\u2336\u233D\u233F\u237C\u23B0\u23B1\u23B4-\u23B6\u23DC-\u23DF\u23E2\u23E7\u2423\u24C8\u2500\u2502\u250C\u2510\u2514\u2518\u251C\u2524\u252C\u2534\u253C\u2550-\u256C\u2580\u2584\u2588\u2591-\u2593\u25A1\u25AA\u25AB\u25AD\u25AE\u25B1\u25B3-\u25B5\u25B8\u25B9\u25BD-\u25BF\u25C2\u25C3\u25CA\u25CB\u25EC\u25EF\u25F8-\u25FC\u2605\u2606\u260E\u2640\u2642\u2660\u2663\u2665\u2666\u266A\u266D-\u266F\u2713\u2717\u2720\u2736\u2758\u2772\u2773\u27C8\u27C9\u27E6-\u27ED\u27F5-\u27FA\u27FC\u27FF\u2902-\u2905\u290C-\u2913\u2916\u2919-\u2920\u2923-\u292A\u2933\u2935-\u2939\u293C\u293D\u2945\u2948-\u294B\u294E-\u2976\u2978\u2979\u297B-\u297F\u2985\u2986\u298B-\u2996\u299A\u299C\u299D\u29A4-\u29B7\u29B9\u29BB\u29BC\u29BE-\u29C5\u29C9\u29CD-\u29D0\u29DC-\u29DE\u29E3-\u29E5\u29EB\u29F4\u29F6\u2A00-\u2A02\u2A04\u2A06\u2A0C\u2A0D\u2A10-\u2A17\u2A22-\u2A27\u2A29\u2A2A\u2A2D-\u2A31\u2A33-\u2A3C\u2A3F\u2A40\u2A42-\u2A4D\u2A50\u2A53-\u2A58\u2A5A-\u2A5D\u2A5F\u2A66\u2A6A\u2A6D-\u2A75\u2A77-\u2A9A\u2A9D-\u2AA2\u2AA4-\u2AB0\u2AB3-\u2AC8\u2ACB\u2ACC\u2ACF-\u2ADB\u2AE4\u2AE6-\u2AE9\u2AEB-\u2AF3\u2AFD\uFB00-\uFB04]|\uD835[\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDCCF\uDD04\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDD6B]/g; var encodeMap = {'\xC1':'Aacute','\xE1':'aacute','\u0102':'Abreve','\u0103':'abreve','\u223E':'ac','\u223F':'acd','\u223E\u0333':'acE','\xC2':'Acirc','\xE2':'acirc','\xB4':'acute','\u0410':'Acy','\u0430':'acy','\xC6':'AElig','\xE6':'aelig','\u2061':'af','\uD835\uDD04':'Afr','\uD835\uDD1E':'afr','\xC0':'Agrave','\xE0':'agrave','\u2135':'aleph','\u0391':'Alpha','\u03B1':'alpha','\u0100':'Amacr','\u0101':'amacr','\u2A3F':'amalg','&':'amp','\u2A55':'andand','\u2A53':'And','\u2227':'and','\u2A5C':'andd','\u2A58':'andslope','\u2A5A':'andv','\u2220':'ang','\u29A4':'ange','\u29A8':'angmsdaa','\u29A9':'angmsdab','\u29AA':'angmsdac','\u29AB':'angmsdad','\u29AC':'angmsdae','\u29AD':'angmsdaf','\u29AE':'angmsdag','\u29AF':'angmsdah','\u2221':'angmsd','\u221F':'angrt','\u22BE':'angrtvb','\u299D':'angrtvbd','\u2222':'angsph','\xC5':'angst','\u237C':'angzarr','\u0104':'Aogon','\u0105':'aogon','\uD835\uDD38':'Aopf','\uD835\uDD52':'aopf','\u2A6F':'apacir','\u2248':'ap','\u2A70':'apE','\u224A':'ape','\u224B':'apid','\'':'apos','\xE5':'aring','\uD835\uDC9C':'Ascr','\uD835\uDCB6':'ascr','\u2254':'colone','\u224D':'CupCap','\xC3':'Atilde','\xE3':'atilde','\xC4':'Auml','\xE4':'auml','\u2233':'awconint','\u2A11':'awint','\u224C':'bcong','\u03F6':'bepsi','\u2035':'bprime','\u223D':'bsim','\u22CD':'bsime','\u2216':'setmn','\u2AE7':'Barv','\u22BD':'barvee','\u2305':'barwed','\u2306':'Barwed','\u23B5':'bbrk','\u23B6':'bbrktbrk','\u0411':'Bcy','\u0431':'bcy','\u201E':'bdquo','\u2235':'becaus','\u29B0':'bemptyv','\u212C':'Bscr','\u0392':'Beta','\u03B2':'beta','\u2136':'beth','\u226C':'twixt','\uD835\uDD05':'Bfr','\uD835\uDD1F':'bfr','\u22C2':'xcap','\u25EF':'xcirc','\u22C3':'xcup','\u2A00':'xodot','\u2A01':'xoplus','\u2A02':'xotime','\u2A06':'xsqcup','\u2605':'starf','\u25BD':'xdtri','\u25B3':'xutri','\u2A04':'xuplus','\u22C1':'Vee','\u22C0':'Wedge','\u290D':'rbarr','\u29EB':'lozf','\u25AA':'squf','\u25B4':'utrif','\u25BE':'dtrif','\u25C2':'ltrif','\u25B8':'rtrif','\u2423':'blank','\u2592':'blk12','\u2591':'blk14','\u2593':'blk34','\u2588':'block','=\u20E5':'bne','\u2261\u20E5':'bnequiv','\u2AED':'bNot','\u2310':'bnot','\uD835\uDD39':'Bopf','\uD835\uDD53':'bopf','\u22A5':'bot','\u22C8':'bowtie','\u29C9':'boxbox','\u2510':'boxdl','\u2555':'boxdL','\u2556':'boxDl','\u2557':'boxDL','\u250C':'boxdr','\u2552':'boxdR','\u2553':'boxDr','\u2554':'boxDR','\u2500':'boxh','\u2550':'boxH','\u252C':'boxhd','\u2564':'boxHd','\u2565':'boxhD','\u2566':'boxHD','\u2534':'boxhu','\u2567':'boxHu','\u2568':'boxhU','\u2569':'boxHU','\u229F':'minusb','\u229E':'plusb','\u22A0':'timesb','\u2518':'boxul','\u255B':'boxuL','\u255C':'boxUl','\u255D':'boxUL','\u2514':'boxur','\u2558':'boxuR','\u2559':'boxUr','\u255A':'boxUR','\u2502':'boxv','\u2551':'boxV','\u253C':'boxvh','\u256A':'boxvH','\u256B':'boxVh','\u256C':'boxVH','\u2524':'boxvl','\u2561':'boxvL','\u2562':'boxVl','\u2563':'boxVL','\u251C':'boxvr','\u255E':'boxvR','\u255F':'boxVr','\u2560':'boxVR','\u02D8':'breve','\xA6':'brvbar','\uD835\uDCB7':'bscr','\u204F':'bsemi','\u29C5':'bsolb','\u27C8':'bsolhsub','\u2022':'bull','\u224E':'bump','\u2AAE':'bumpE','\u224F':'bumpe','\u0106':'Cacute','\u0107':'cacute','\u2A44':'capand','\u2A49':'capbrcup','\u2A4B':'capcap','\u2229':'cap','\u22D2':'Cap','\u2A47':'capcup','\u2A40':'capdot','\u2145':'DD','\u2229\uFE00':'caps','\u2041':'caret','\u02C7':'caron','\u212D':'Cfr','\u2A4D':'ccaps','\u010C':'Ccaron','\u010D':'ccaron','\xC7':'Ccedil','\xE7':'ccedil','\u0108':'Ccirc','\u0109':'ccirc','\u2230':'Cconint','\u2A4C':'ccups','\u2A50':'ccupssm','\u010A':'Cdot','\u010B':'cdot','\xB8':'cedil','\u29B2':'cemptyv','\xA2':'cent','\xB7':'middot','\uD835\uDD20':'cfr','\u0427':'CHcy','\u0447':'chcy','\u2713':'check','\u03A7':'Chi','\u03C7':'chi','\u02C6':'circ','\u2257':'cire','\u21BA':'olarr','\u21BB':'orarr','\u229B':'oast','\u229A':'ocir','\u229D':'odash','\u2299':'odot','\xAE':'reg','\u24C8':'oS','\u2296':'ominus','\u2295':'oplus','\u2297':'otimes','\u25CB':'cir','\u29C3':'cirE','\u2A10':'cirfnint','\u2AEF':'cirmid','\u29C2':'cirscir','\u2232':'cwconint','\u201D':'rdquo','\u2019':'rsquo','\u2663':'clubs','\u2237':'Colon','\u2A74':'Colone','\u2201':'comp','\u2218':'compfn','\u2102':'Copf','\u2245':'cong','\u2A6D':'congdot','\u2261':'equiv','\u222E':'oint','\u222F':'Conint','\uD835\uDD54':'copf','\u2210':'coprod','\xA9':'copy','\u2117':'copysr','\u21B5':'crarr','\u2717':'cross','\u2A2F':'Cross','\uD835\uDC9E':'Cscr','\uD835\uDCB8':'cscr','\u2ACF':'csub','\u2AD1':'csube','\u2AD0':'csup','\u2AD2':'csupe','\u22EF':'ctdot','\u2938':'cudarrl','\u2935':'cudarrr','\u22DE':'cuepr','\u22DF':'cuesc','\u21B6':'cularr','\u293D':'cularrp','\u2A48':'cupbrcap','\u2A46':'cupcap','\u222A':'cup','\u22D3':'Cup','\u2A4A':'cupcup','\u228D':'cupdot','\u2A45':'cupor','\u222A\uFE00':'cups','\u21B7':'curarr','\u293C':'curarrm','\u22CE':'cuvee','\u22CF':'cuwed','\xA4':'curren','\u2231':'cwint','\u232D':'cylcty','\u2020':'dagger','\u2021':'Dagger','\u2138':'daleth','\u2193':'darr','\u21A1':'Darr','\u21D3':'dArr','\u2010':'dash','\u2AE4':'Dashv','\u22A3':'dashv','\u290F':'rBarr','\u02DD':'dblac','\u010E':'Dcaron','\u010F':'dcaron','\u0414':'Dcy','\u0434':'dcy','\u21CA':'ddarr','\u2146':'dd','\u2911':'DDotrahd','\u2A77':'eDDot','\xB0':'deg','\u2207':'Del','\u0394':'Delta','\u03B4':'delta','\u29B1':'demptyv','\u297F':'dfisht','\uD835\uDD07':'Dfr','\uD835\uDD21':'dfr','\u2965':'dHar','\u21C3':'dharl','\u21C2':'dharr','\u02D9':'dot','\u02DC':'tilde','\u22C4':'diam','\u2666':'diams','\xA8':'die','\u03DD':'gammad','\u22F2':'disin','\xF7':'div','\u22C7':'divonx','\u0402':'DJcy','\u0452':'djcy','\u231E':'dlcorn','\u230D':'dlcrop','\uD835\uDD3B':'Dopf','\uD835\uDD55':'dopf','\u20DC':'DotDot','\u2250':'doteq','\u2251':'eDot','\u2238':'minusd','\u2214':'plusdo','\u22A1':'sdotb','\u21D0':'lArr','\u21D4':'iff','\u27F8':'xlArr','\u27FA':'xhArr','\u27F9':'xrArr','\u21D2':'rArr','\u22A8':'vDash','\u21D1':'uArr','\u21D5':'vArr','\u2225':'par','\u2913':'DownArrowBar','\u21F5':'duarr','\u0311':'DownBreve','\u2950':'DownLeftRightVector','\u295E':'DownLeftTeeVector','\u2956':'DownLeftVectorBar','\u21BD':'lhard','\u295F':'DownRightTeeVector','\u2957':'DownRightVectorBar','\u21C1':'rhard','\u21A7':'mapstodown','\u22A4':'top','\u2910':'RBarr','\u231F':'drcorn','\u230C':'drcrop','\uD835\uDC9F':'Dscr','\uD835\uDCB9':'dscr','\u0405':'DScy','\u0455':'dscy','\u29F6':'dsol','\u0110':'Dstrok','\u0111':'dstrok','\u22F1':'dtdot','\u25BF':'dtri','\u296F':'duhar','\u29A6':'dwangle','\u040F':'DZcy','\u045F':'dzcy','\u27FF':'dzigrarr','\xC9':'Eacute','\xE9':'eacute','\u2A6E':'easter','\u011A':'Ecaron','\u011B':'ecaron','\xCA':'Ecirc','\xEA':'ecirc','\u2256':'ecir','\u2255':'ecolon','\u042D':'Ecy','\u044D':'ecy','\u0116':'Edot','\u0117':'edot','\u2147':'ee','\u2252':'efDot','\uD835\uDD08':'Efr','\uD835\uDD22':'efr','\u2A9A':'eg','\xC8':'Egrave','\xE8':'egrave','\u2A96':'egs','\u2A98':'egsdot','\u2A99':'el','\u2208':'in','\u23E7':'elinters','\u2113':'ell','\u2A95':'els','\u2A97':'elsdot','\u0112':'Emacr','\u0113':'emacr','\u2205':'empty','\u25FB':'EmptySmallSquare','\u25AB':'EmptyVerySmallSquare','\u2004':'emsp13','\u2005':'emsp14','\u2003':'emsp','\u014A':'ENG','\u014B':'eng','\u2002':'ensp','\u0118':'Eogon','\u0119':'eogon','\uD835\uDD3C':'Eopf','\uD835\uDD56':'eopf','\u22D5':'epar','\u29E3':'eparsl','\u2A71':'eplus','\u03B5':'epsi','\u0395':'Epsilon','\u03F5':'epsiv','\u2242':'esim','\u2A75':'Equal','\u225F':'equest','\u21CC':'rlhar','\u2A78':'equivDD','\u29E5':'eqvparsl','\u2971':'erarr','\u2253':'erDot','\u212F':'escr','\u2130':'Escr','\u2A73':'Esim','\u0397':'Eta','\u03B7':'eta','\xD0':'ETH','\xF0':'eth','\xCB':'Euml','\xEB':'euml','\u20AC':'euro','\u2203':'exist','\u0424':'Fcy','\u0444':'fcy','\u2640':'female','\uFB03':'ffilig','\uFB00':'fflig','\uFB04':'ffllig','\uD835\uDD09':'Ffr','\uD835\uDD23':'ffr','\uFB01':'filig','\u25FC':'FilledSmallSquare','\u266D':'flat','\uFB02':'fllig','\u25B1':'fltns','\u0192':'fnof','\uD835\uDD3D':'Fopf','\uD835\uDD57':'fopf','\u2200':'forall','\u22D4':'fork','\u2AD9':'forkv','\u2131':'Fscr','\u2A0D':'fpartint','\xBD':'half','\u2153':'frac13','\xBC':'frac14','\u2155':'frac15','\u2159':'frac16','\u215B':'frac18','\u2154':'frac23','\u2156':'frac25','\xBE':'frac34','\u2157':'frac35','\u215C':'frac38','\u2158':'frac45','\u215A':'frac56','\u215D':'frac58','\u215E':'frac78','\u2044':'frasl','\u2322':'frown','\uD835\uDCBB':'fscr','\u01F5':'gacute','\u0393':'Gamma','\u03B3':'gamma','\u03DC':'Gammad','\u2A86':'gap','\u011E':'Gbreve','\u011F':'gbreve','\u0122':'Gcedil','\u011C':'Gcirc','\u011D':'gcirc','\u0413':'Gcy','\u0433':'gcy','\u0120':'Gdot','\u0121':'gdot','\u2265':'ge','\u2267':'gE','\u2A8C':'gEl','\u22DB':'gel','\u2A7E':'ges','\u2AA9':'gescc','\u2A80':'gesdot','\u2A82':'gesdoto','\u2A84':'gesdotol','\u22DB\uFE00':'gesl','\u2A94':'gesles','\uD835\uDD0A':'Gfr','\uD835\uDD24':'gfr','\u226B':'gg','\u22D9':'Gg','\u2137':'gimel','\u0403':'GJcy','\u0453':'gjcy','\u2AA5':'gla','\u2277':'gl','\u2A92':'glE','\u2AA4':'glj','\u2A8A':'gnap','\u2A88':'gne','\u2269':'gnE','\u22E7':'gnsim','\uD835\uDD3E':'Gopf','\uD835\uDD58':'gopf','\u2AA2':'GreaterGreater','\u2273':'gsim','\uD835\uDCA2':'Gscr','\u210A':'gscr','\u2A8E':'gsime','\u2A90':'gsiml','\u2AA7':'gtcc','\u2A7A':'gtcir','>':'gt','\u22D7':'gtdot','\u2995':'gtlPar','\u2A7C':'gtquest','\u2978':'gtrarr','\u2269\uFE00':'gvnE','\u200A':'hairsp','\u210B':'Hscr','\u042A':'HARDcy','\u044A':'hardcy','\u2948':'harrcir','\u2194':'harr','\u21AD':'harrw','\u210F':'hbar','\u0124':'Hcirc','\u0125':'hcirc','\u2665':'hearts','\u2026':'mldr','\u22B9':'hercon','\uD835\uDD25':'hfr','\u210C':'Hfr','\u2925':'searhk','\u2926':'swarhk','\u21FF':'hoarr','\u223B':'homtht','\u21A9':'larrhk','\u21AA':'rarrhk','\uD835\uDD59':'hopf','\u210D':'Hopf','\u2015':'horbar','\uD835\uDCBD':'hscr','\u0126':'Hstrok','\u0127':'hstrok','\u2043':'hybull','\xCD':'Iacute','\xED':'iacute','\u2063':'ic','\xCE':'Icirc','\xEE':'icirc','\u0418':'Icy','\u0438':'icy','\u0130':'Idot','\u0415':'IEcy','\u0435':'iecy','\xA1':'iexcl','\uD835\uDD26':'ifr','\u2111':'Im','\xCC':'Igrave','\xEC':'igrave','\u2148':'ii','\u2A0C':'qint','\u222D':'tint','\u29DC':'iinfin','\u2129':'iiota','\u0132':'IJlig','\u0133':'ijlig','\u012A':'Imacr','\u012B':'imacr','\u2110':'Iscr','\u0131':'imath','\u22B7':'imof','\u01B5':'imped','\u2105':'incare','\u221E':'infin','\u29DD':'infintie','\u22BA':'intcal','\u222B':'int','\u222C':'Int','\u2124':'Zopf','\u2A17':'intlarhk','\u2A3C':'iprod','\u2062':'it','\u0401':'IOcy','\u0451':'iocy','\u012E':'Iogon','\u012F':'iogon','\uD835\uDD40':'Iopf','\uD835\uDD5A':'iopf','\u0399':'Iota','\u03B9':'iota','\xBF':'iquest','\uD835\uDCBE':'iscr','\u22F5':'isindot','\u22F9':'isinE','\u22F4':'isins','\u22F3':'isinsv','\u0128':'Itilde','\u0129':'itilde','\u0406':'Iukcy','\u0456':'iukcy','\xCF':'Iuml','\xEF':'iuml','\u0134':'Jcirc','\u0135':'jcirc','\u0419':'Jcy','\u0439':'jcy','\uD835\uDD0D':'Jfr','\uD835\uDD27':'jfr','\u0237':'jmath','\uD835\uDD41':'Jopf','\uD835\uDD5B':'jopf','\uD835\uDCA5':'Jscr','\uD835\uDCBF':'jscr','\u0408':'Jsercy','\u0458':'jsercy','\u0404':'Jukcy','\u0454':'jukcy','\u039A':'Kappa','\u03BA':'kappa','\u03F0':'kappav','\u0136':'Kcedil','\u0137':'kcedil','\u041A':'Kcy','\u043A':'kcy','\uD835\uDD0E':'Kfr','\uD835\uDD28':'kfr','\u0138':'kgreen','\u0425':'KHcy','\u0445':'khcy','\u040C':'KJcy','\u045C':'kjcy','\uD835\uDD42':'Kopf','\uD835\uDD5C':'kopf','\uD835\uDCA6':'Kscr','\uD835\uDCC0':'kscr','\u21DA':'lAarr','\u0139':'Lacute','\u013A':'lacute','\u29B4':'laemptyv','\u2112':'Lscr','\u039B':'Lambda','\u03BB':'lambda','\u27E8':'lang','\u27EA':'Lang','\u2991':'langd','\u2A85':'lap','\xAB':'laquo','\u21E4':'larrb','\u291F':'larrbfs','\u2190':'larr','\u219E':'Larr','\u291D':'larrfs','\u21AB':'larrlp','\u2939':'larrpl','\u2973':'larrsim','\u21A2':'larrtl','\u2919':'latail','\u291B':'lAtail','\u2AAB':'lat','\u2AAD':'late','\u2AAD\uFE00':'lates','\u290C':'lbarr','\u290E':'lBarr','\u2772':'lbbrk','\u298B':'lbrke','\u298F':'lbrksld','\u298D':'lbrkslu','\u013D':'Lcaron','\u013E':'lcaron','\u013B':'Lcedil','\u013C':'lcedil','\u2308':'lceil','\u041B':'Lcy','\u043B':'lcy','\u2936':'ldca','\u201C':'ldquo','\u2967':'ldrdhar','\u294B':'ldrushar','\u21B2':'ldsh','\u2264':'le','\u2266':'lE','\u21C6':'lrarr','\u27E6':'lobrk','\u2961':'LeftDownTeeVector','\u2959':'LeftDownVectorBar','\u230A':'lfloor','\u21BC':'lharu','\u21C7':'llarr','\u21CB':'lrhar','\u294E':'LeftRightVector','\u21A4':'mapstoleft','\u295A':'LeftTeeVector','\u22CB':'lthree','\u29CF':'LeftTriangleBar','\u22B2':'vltri','\u22B4':'ltrie','\u2951':'LeftUpDownVector','\u2960':'LeftUpTeeVector','\u2958':'LeftUpVectorBar','\u21BF':'uharl','\u2952':'LeftVectorBar','\u2A8B':'lEg','\u22DA':'leg','\u2A7D':'les','\u2AA8':'lescc','\u2A7F':'lesdot','\u2A81':'lesdoto','\u2A83':'lesdotor','\u22DA\uFE00':'lesg','\u2A93':'lesges','\u22D6':'ltdot','\u2276':'lg','\u2AA1':'LessLess','\u2272':'lsim','\u297C':'lfisht','\uD835\uDD0F':'Lfr','\uD835\uDD29':'lfr','\u2A91':'lgE','\u2962':'lHar','\u296A':'lharul','\u2584':'lhblk','\u0409':'LJcy','\u0459':'ljcy','\u226A':'ll','\u22D8':'Ll','\u296B':'llhard','\u25FA':'lltri','\u013F':'Lmidot','\u0140':'lmidot','\u23B0':'lmoust','\u2A89':'lnap','\u2A87':'lne','\u2268':'lnE','\u22E6':'lnsim','\u27EC':'loang','\u21FD':'loarr','\u27F5':'xlarr','\u27F7':'xharr','\u27FC':'xmap','\u27F6':'xrarr','\u21AC':'rarrlp','\u2985':'lopar','\uD835\uDD43':'Lopf','\uD835\uDD5D':'lopf','\u2A2D':'loplus','\u2A34':'lotimes','\u2217':'lowast','\u2199':'swarr','\u2198':'searr','\u25CA':'loz','\u2993':'lparlt','\u296D':'lrhard','\u200E':'lrm','\u22BF':'lrtri','\u2039':'lsaquo','\uD835\uDCC1':'lscr','\u21B0':'lsh','\u2A8D':'lsime','\u2A8F':'lsimg','\u2018':'lsquo','\u201A':'sbquo','\u0141':'Lstrok','\u0142':'lstrok','\u2AA6':'ltcc','\u2A79':'ltcir','<':'lt','\u22C9':'ltimes','\u2976':'ltlarr','\u2A7B':'ltquest','\u25C3':'ltri','\u2996':'ltrPar','\u294A':'lurdshar','\u2966':'luruhar','\u2268\uFE00':'lvnE','\xAF':'macr','\u2642':'male','\u2720':'malt','\u2905':'Map','\u21A6':'map','\u21A5':'mapstoup','\u25AE':'marker','\u2A29':'mcomma','\u041C':'Mcy','\u043C':'mcy','\u2014':'mdash','\u223A':'mDDot','\u205F':'MediumSpace','\u2133':'Mscr','\uD835\uDD10':'Mfr','\uD835\uDD2A':'mfr','\u2127':'mho','\xB5':'micro','\u2AF0':'midcir','\u2223':'mid','\u2212':'minus','\u2A2A':'minusdu','\u2213':'mp','\u2ADB':'mlcp','\u22A7':'models','\uD835\uDD44':'Mopf','\uD835\uDD5E':'mopf','\uD835\uDCC2':'mscr','\u039C':'Mu','\u03BC':'mu','\u22B8':'mumap','\u0143':'Nacute','\u0144':'nacute','\u2220\u20D2':'nang','\u2249':'nap','\u2A70\u0338':'napE','\u224B\u0338':'napid','\u0149':'napos','\u266E':'natur','\u2115':'Nopf','\xA0':'nbsp','\u224E\u0338':'nbump','\u224F\u0338':'nbumpe','\u2A43':'ncap','\u0147':'Ncaron','\u0148':'ncaron','\u0145':'Ncedil','\u0146':'ncedil','\u2247':'ncong','\u2A6D\u0338':'ncongdot','\u2A42':'ncup','\u041D':'Ncy','\u043D':'ncy','\u2013':'ndash','\u2924':'nearhk','\u2197':'nearr','\u21D7':'neArr','\u2260':'ne','\u2250\u0338':'nedot','\u200B':'ZeroWidthSpace','\u2262':'nequiv','\u2928':'toea','\u2242\u0338':'nesim','\u2204':'nexist','\uD835\uDD11':'Nfr','\uD835\uDD2B':'nfr','\u2267\u0338':'ngE','\u2271':'nge','\u2A7E\u0338':'nges','\u22D9\u0338':'nGg','\u2275':'ngsim','\u226B\u20D2':'nGt','\u226F':'ngt','\u226B\u0338':'nGtv','\u21AE':'nharr','\u21CE':'nhArr','\u2AF2':'nhpar','\u220B':'ni','\u22FC':'nis','\u22FA':'nisd','\u040A':'NJcy','\u045A':'njcy','\u219A':'nlarr','\u21CD':'nlArr','\u2025':'nldr','\u2266\u0338':'nlE','\u2270':'nle','\u2A7D\u0338':'nles','\u226E':'nlt','\u22D8\u0338':'nLl','\u2274':'nlsim','\u226A\u20D2':'nLt','\u22EA':'nltri','\u22EC':'nltrie','\u226A\u0338':'nLtv','\u2224':'nmid','\u2060':'NoBreak','\uD835\uDD5F':'nopf','\u2AEC':'Not','\xAC':'not','\u226D':'NotCupCap','\u2226':'npar','\u2209':'notin','\u2279':'ntgl','\u22F5\u0338':'notindot','\u22F9\u0338':'notinE','\u22F7':'notinvb','\u22F6':'notinvc','\u29CF\u0338':'NotLeftTriangleBar','\u2278':'ntlg','\u2AA2\u0338':'NotNestedGreaterGreater','\u2AA1\u0338':'NotNestedLessLess','\u220C':'notni','\u22FE':'notnivb','\u22FD':'notnivc','\u2280':'npr','\u2AAF\u0338':'npre','\u22E0':'nprcue','\u29D0\u0338':'NotRightTriangleBar','\u22EB':'nrtri','\u22ED':'nrtrie','\u228F\u0338':'NotSquareSubset','\u22E2':'nsqsube','\u2290\u0338':'NotSquareSuperset','\u22E3':'nsqsupe','\u2282\u20D2':'vnsub','\u2288':'nsube','\u2281':'nsc','\u2AB0\u0338':'nsce','\u22E1':'nsccue','\u227F\u0338':'NotSucceedsTilde','\u2283\u20D2':'vnsup','\u2289':'nsupe','\u2241':'nsim','\u2244':'nsime','\u2AFD\u20E5':'nparsl','\u2202\u0338':'npart','\u2A14':'npolint','\u2933\u0338':'nrarrc','\u219B':'nrarr','\u21CF':'nrArr','\u219D\u0338':'nrarrw','\uD835\uDCA9':'Nscr','\uD835\uDCC3':'nscr','\u2284':'nsub','\u2AC5\u0338':'nsubE','\u2285':'nsup','\u2AC6\u0338':'nsupE','\xD1':'Ntilde','\xF1':'ntilde','\u039D':'Nu','\u03BD':'nu','\u2116':'numero','\u2007':'numsp','\u224D\u20D2':'nvap','\u22AC':'nvdash','\u22AD':'nvDash','\u22AE':'nVdash','\u22AF':'nVDash','\u2265\u20D2':'nvge','>\u20D2':'nvgt','\u2904':'nvHarr','\u29DE':'nvinfin','\u2902':'nvlArr','\u2264\u20D2':'nvle','<\u20D2':'nvlt','\u22B4\u20D2':'nvltrie','\u2903':'nvrArr','\u22B5\u20D2':'nvrtrie','\u223C\u20D2':'nvsim','\u2923':'nwarhk','\u2196':'nwarr','\u21D6':'nwArr','\u2927':'nwnear','\xD3':'Oacute','\xF3':'oacute','\xD4':'Ocirc','\xF4':'ocirc','\u041E':'Ocy','\u043E':'ocy','\u0150':'Odblac','\u0151':'odblac','\u2A38':'odiv','\u29BC':'odsold','\u0152':'OElig','\u0153':'oelig','\u29BF':'ofcir','\uD835\uDD12':'Ofr','\uD835\uDD2C':'ofr','\u02DB':'ogon','\xD2':'Ograve','\xF2':'ograve','\u29C1':'ogt','\u29B5':'ohbar','\u03A9':'ohm','\u29BE':'olcir','\u29BB':'olcross','\u203E':'oline','\u29C0':'olt','\u014C':'Omacr','\u014D':'omacr','\u03C9':'omega','\u039F':'Omicron','\u03BF':'omicron','\u29B6':'omid','\uD835\uDD46':'Oopf','\uD835\uDD60':'oopf','\u29B7':'opar','\u29B9':'operp','\u2A54':'Or','\u2228':'or','\u2A5D':'ord','\u2134':'oscr','\xAA':'ordf','\xBA':'ordm','\u22B6':'origof','\u2A56':'oror','\u2A57':'orslope','\u2A5B':'orv','\uD835\uDCAA':'Oscr','\xD8':'Oslash','\xF8':'oslash','\u2298':'osol','\xD5':'Otilde','\xF5':'otilde','\u2A36':'otimesas','\u2A37':'Otimes','\xD6':'Ouml','\xF6':'ouml','\u233D':'ovbar','\u23DE':'OverBrace','\u23B4':'tbrk','\u23DC':'OverParenthesis','\xB6':'para','\u2AF3':'parsim','\u2AFD':'parsl','\u2202':'part','\u041F':'Pcy','\u043F':'pcy','\u2030':'permil','\u2031':'pertenk','\uD835\uDD13':'Pfr','\uD835\uDD2D':'pfr','\u03A6':'Phi','\u03C6':'phi','\u03D5':'phiv','\u260E':'phone','\u03A0':'Pi','\u03C0':'pi','\u03D6':'piv','\u210E':'planckh','\u2A23':'plusacir','\u2A22':'pluscir','\u2A25':'plusdu','\u2A72':'pluse','\xB1':'pm','\u2A26':'plussim','\u2A27':'plustwo','\u2A15':'pointint','\uD835\uDD61':'popf','\u2119':'Popf','\xA3':'pound','\u2AB7':'prap','\u2ABB':'Pr','\u227A':'pr','\u227C':'prcue','\u2AAF':'pre','\u227E':'prsim','\u2AB9':'prnap','\u2AB5':'prnE','\u22E8':'prnsim','\u2AB3':'prE','\u2032':'prime','\u2033':'Prime','\u220F':'prod','\u232E':'profalar','\u2312':'profline','\u2313':'profsurf','\u221D':'prop','\u22B0':'prurel','\uD835\uDCAB':'Pscr','\uD835\uDCC5':'pscr','\u03A8':'Psi','\u03C8':'psi','\u2008':'puncsp','\uD835\uDD14':'Qfr','\uD835\uDD2E':'qfr','\uD835\uDD62':'qopf','\u211A':'Qopf','\u2057':'qprime','\uD835\uDCAC':'Qscr','\uD835\uDCC6':'qscr','\u2A16':'quatint','"':'quot','\u21DB':'rAarr','\u223D\u0331':'race','\u0154':'Racute','\u0155':'racute','\u221A':'Sqrt','\u29B3':'raemptyv','\u27E9':'rang','\u27EB':'Rang','\u2992':'rangd','\u29A5':'range','\xBB':'raquo','\u2975':'rarrap','\u21E5':'rarrb','\u2920':'rarrbfs','\u2933':'rarrc','\u2192':'rarr','\u21A0':'Rarr','\u291E':'rarrfs','\u2945':'rarrpl','\u2974':'rarrsim','\u2916':'Rarrtl','\u21A3':'rarrtl','\u219D':'rarrw','\u291A':'ratail','\u291C':'rAtail','\u2236':'ratio','\u2773':'rbbrk','\u298C':'rbrke','\u298E':'rbrksld','\u2990':'rbrkslu','\u0158':'Rcaron','\u0159':'rcaron','\u0156':'Rcedil','\u0157':'rcedil','\u2309':'rceil','\u0420':'Rcy','\u0440':'rcy','\u2937':'rdca','\u2969':'rdldhar','\u21B3':'rdsh','\u211C':'Re','\u211B':'Rscr','\u211D':'Ropf','\u25AD':'rect','\u297D':'rfisht','\u230B':'rfloor','\uD835\uDD2F':'rfr','\u2964':'rHar','\u21C0':'rharu','\u296C':'rharul','\u03A1':'Rho','\u03C1':'rho','\u03F1':'rhov','\u21C4':'rlarr','\u27E7':'robrk','\u295D':'RightDownTeeVector','\u2955':'RightDownVectorBar','\u21C9':'rrarr','\u22A2':'vdash','\u295B':'RightTeeVector','\u22CC':'rthree','\u29D0':'RightTriangleBar','\u22B3':'vrtri','\u22B5':'rtrie','\u294F':'RightUpDownVector','\u295C':'RightUpTeeVector','\u2954':'RightUpVectorBar','\u21BE':'uharr','\u2953':'RightVectorBar','\u02DA':'ring','\u200F':'rlm','\u23B1':'rmoust','\u2AEE':'rnmid','\u27ED':'roang','\u21FE':'roarr','\u2986':'ropar','\uD835\uDD63':'ropf','\u2A2E':'roplus','\u2A35':'rotimes','\u2970':'RoundImplies','\u2994':'rpargt','\u2A12':'rppolint','\u203A':'rsaquo','\uD835\uDCC7':'rscr','\u21B1':'rsh','\u22CA':'rtimes','\u25B9':'rtri','\u29CE':'rtriltri','\u29F4':'RuleDelayed','\u2968':'ruluhar','\u211E':'rx','\u015A':'Sacute','\u015B':'sacute','\u2AB8':'scap','\u0160':'Scaron','\u0161':'scaron','\u2ABC':'Sc','\u227B':'sc','\u227D':'sccue','\u2AB0':'sce','\u2AB4':'scE','\u015E':'Scedil','\u015F':'scedil','\u015C':'Scirc','\u015D':'scirc','\u2ABA':'scnap','\u2AB6':'scnE','\u22E9':'scnsim','\u2A13':'scpolint','\u227F':'scsim','\u0421':'Scy','\u0441':'scy','\u22C5':'sdot','\u2A66':'sdote','\u21D8':'seArr','\xA7':'sect','\u2929':'tosa','\u2736':'sext','\uD835\uDD16':'Sfr','\uD835\uDD30':'sfr','\u266F':'sharp','\u0429':'SHCHcy','\u0449':'shchcy','\u0428':'SHcy','\u0448':'shcy','\u2191':'uarr','\xAD':'shy','\u03A3':'Sigma','\u03C3':'sigma','\u03C2':'sigmaf','\u223C':'sim','\u2A6A':'simdot','\u2243':'sime','\u2A9E':'simg','\u2AA0':'simgE','\u2A9D':'siml','\u2A9F':'simlE','\u2246':'simne','\u2A24':'simplus','\u2972':'simrarr','\u2A33':'smashp','\u29E4':'smeparsl','\u2323':'smile','\u2AAA':'smt','\u2AAC':'smte','\u2AAC\uFE00':'smtes','\u042C':'SOFTcy','\u044C':'softcy','\u233F':'solbar','\u29C4':'solb','\uD835\uDD4A':'Sopf','\uD835\uDD64':'sopf','\u2660':'spades','\u2293':'sqcap','\u2293\uFE00':'sqcaps','\u2294':'sqcup','\u2294\uFE00':'sqcups','\u228F':'sqsub','\u2291':'sqsube','\u2290':'sqsup','\u2292':'sqsupe','\u25A1':'squ','\uD835\uDCAE':'Sscr','\uD835\uDCC8':'sscr','\u22C6':'Star','\u2606':'star','\u2282':'sub','\u22D0':'Sub','\u2ABD':'subdot','\u2AC5':'subE','\u2286':'sube','\u2AC3':'subedot','\u2AC1':'submult','\u2ACB':'subnE','\u228A':'subne','\u2ABF':'subplus','\u2979':'subrarr','\u2AC7':'subsim','\u2AD5':'subsub','\u2AD3':'subsup','\u2211':'sum','\u266A':'sung','\xB9':'sup1','\xB2':'sup2','\xB3':'sup3','\u2283':'sup','\u22D1':'Sup','\u2ABE':'supdot','\u2AD8':'supdsub','\u2AC6':'supE','\u2287':'supe','\u2AC4':'supedot','\u27C9':'suphsol','\u2AD7':'suphsub','\u297B':'suplarr','\u2AC2':'supmult','\u2ACC':'supnE','\u228B':'supne','\u2AC0':'supplus','\u2AC8':'supsim','\u2AD4':'supsub','\u2AD6':'supsup','\u21D9':'swArr','\u292A':'swnwar','\xDF':'szlig','\t':'Tab','\u2316':'target','\u03A4':'Tau','\u03C4':'tau','\u0164':'Tcaron','\u0165':'tcaron','\u0162':'Tcedil','\u0163':'tcedil','\u0422':'Tcy','\u0442':'tcy','\u20DB':'tdot','\u2315':'telrec','\uD835\uDD17':'Tfr','\uD835\uDD31':'tfr','\u2234':'there4','\u0398':'Theta','\u03B8':'theta','\u03D1':'thetav','\u205F\u200A':'ThickSpace','\u2009':'thinsp','\xDE':'THORN','\xFE':'thorn','\u2A31':'timesbar','\xD7':'times','\u2A30':'timesd','\u2336':'topbot','\u2AF1':'topcir','\uD835\uDD4B':'Topf','\uD835\uDD65':'topf','\u2ADA':'topfork','\u2034':'tprime','\u2122':'trade','\u25B5':'utri','\u225C':'trie','\u25EC':'tridot','\u2A3A':'triminus','\u2A39':'triplus','\u29CD':'trisb','\u2A3B':'tritime','\u23E2':'trpezium','\uD835\uDCAF':'Tscr','\uD835\uDCC9':'tscr','\u0426':'TScy','\u0446':'tscy','\u040B':'TSHcy','\u045B':'tshcy','\u0166':'Tstrok','\u0167':'tstrok','\xDA':'Uacute','\xFA':'uacute','\u219F':'Uarr','\u2949':'Uarrocir','\u040E':'Ubrcy','\u045E':'ubrcy','\u016C':'Ubreve','\u016D':'ubreve','\xDB':'Ucirc','\xFB':'ucirc','\u0423':'Ucy','\u0443':'ucy','\u21C5':'udarr','\u0170':'Udblac','\u0171':'udblac','\u296E':'udhar','\u297E':'ufisht','\uD835\uDD18':'Ufr','\uD835\uDD32':'ufr','\xD9':'Ugrave','\xF9':'ugrave','\u2963':'uHar','\u2580':'uhblk','\u231C':'ulcorn','\u230F':'ulcrop','\u25F8':'ultri','\u016A':'Umacr','\u016B':'umacr','\u23DF':'UnderBrace','\u23DD':'UnderParenthesis','\u228E':'uplus','\u0172':'Uogon','\u0173':'uogon','\uD835\uDD4C':'Uopf','\uD835\uDD66':'uopf','\u2912':'UpArrowBar','\u2195':'varr','\u03C5':'upsi','\u03D2':'Upsi','\u03A5':'Upsilon','\u21C8':'uuarr','\u231D':'urcorn','\u230E':'urcrop','\u016E':'Uring','\u016F':'uring','\u25F9':'urtri','\uD835\uDCB0':'Uscr','\uD835\uDCCA':'uscr','\u22F0':'utdot','\u0168':'Utilde','\u0169':'utilde','\xDC':'Uuml','\xFC':'uuml','\u29A7':'uwangle','\u299C':'vangrt','\u228A\uFE00':'vsubne','\u2ACB\uFE00':'vsubnE','\u228B\uFE00':'vsupne','\u2ACC\uFE00':'vsupnE','\u2AE8':'vBar','\u2AEB':'Vbar','\u2AE9':'vBarv','\u0412':'Vcy','\u0432':'vcy','\u22A9':'Vdash','\u22AB':'VDash','\u2AE6':'Vdashl','\u22BB':'veebar','\u225A':'veeeq','\u22EE':'vellip','\u2016':'Vert','\u2758':'VerticalSeparator','\u2240':'wr','\uD835\uDD19':'Vfr','\uD835\uDD33':'vfr','\uD835\uDD4D':'Vopf','\uD835\uDD67':'vopf','\uD835\uDCB1':'Vscr','\uD835\uDCCB':'vscr','\u22AA':'Vvdash','\u299A':'vzigzag','\u0174':'Wcirc','\u0175':'wcirc','\u2A5F':'wedbar','\u2259':'wedgeq','\u2118':'wp','\uD835\uDD1A':'Wfr','\uD835\uDD34':'wfr','\uD835\uDD4E':'Wopf','\uD835\uDD68':'wopf','\uD835\uDCB2':'Wscr','\uD835\uDCCC':'wscr','\uD835\uDD1B':'Xfr','\uD835\uDD35':'xfr','\u039E':'Xi','\u03BE':'xi','\u22FB':'xnis','\uD835\uDD4F':'Xopf','\uD835\uDD69':'xopf','\uD835\uDCB3':'Xscr','\uD835\uDCCD':'xscr','\xDD':'Yacute','\xFD':'yacute','\u042F':'YAcy','\u044F':'yacy','\u0176':'Ycirc','\u0177':'ycirc','\u042B':'Ycy','\u044B':'ycy','\xA5':'yen','\uD835\uDD1C':'Yfr','\uD835\uDD36':'yfr','\u0407':'YIcy','\u0457':'yicy','\uD835\uDD50':'Yopf','\uD835\uDD6A':'yopf','\uD835\uDCB4':'Yscr','\uD835\uDCCE':'yscr','\u042E':'YUcy','\u044E':'yucy','\xFF':'yuml','\u0178':'Yuml','\u0179':'Zacute','\u017A':'zacute','\u017D':'Zcaron','\u017E':'zcaron','\u0417':'Zcy','\u0437':'zcy','\u017B':'Zdot','\u017C':'zdot','\u2128':'Zfr','\u0396':'Zeta','\u03B6':'zeta','\uD835\uDD37':'zfr','\u0416':'ZHcy','\u0436':'zhcy','\u21DD':'zigrarr','\uD835\uDD6B':'zopf','\uD835\uDCB5':'Zscr','\uD835\uDCCF':'zscr','\u200D':'zwj','\u200C':'zwnj'}; var regexEscape = /[&<>"']/g; @@ -147,7 +148,7 @@ var decode = function(html, options) { options = merge(options, decode.options); var strict = options.strict; - if (strict && /&#[xX]?[^a-fA-F0-9]/.test(html)) { + if (strict && regexInvalidEntity.test(html)) { parseError(); } return html @@ -23,6 +23,7 @@ var regexHexadecimalEscape = /&#[xX]([a-fA-F0-9]+)(;?)/g; var regexNamedReference = /&([0-9a-zA-Z]+);/g; var regexLegacyReference = /&(<%= legacyReferences %>)([=a-zA-Z0-9])?/g; + var regexInvalidEntity = /&#(?:[xX][^a-fA-F0-9]|[^0-9xX])/; var regexEncode = /<%= encodeMultipleSymbols %>|<%= encodeSingleSymbols %>/g; var encodeMap = <%= encodeMap %>; var regexEscape = /[&<>"']/g; @@ -147,7 +148,7 @@ var decode = function(html, options) { options = merge(options, decode.options); var strict = options.strict; - if (strict && /&#[xX]?[^a-fA-F0-9]/.test(html)) { + if (strict && regexInvalidEntity.test(html)) { parseError(); } return html diff --git a/tests/tests.js b/tests/tests.js index 3b41c87..65752f5 100644 --- a/tests/tests.js +++ b/tests/tests.js @@ -8384,6 +8384,16 @@ 'foo&=', 'Attribute value context' ); + raises( + function() { + he.decode('foo&=', { + 'strict': true + // 'isAttributeValue': true is set globally + }); + }, + Error, + 'Parse error: `foo&=` in attribute value context in strict mode' + ); he.decode.options.isAttributeValue = false; equal( he.decode('foo&', { @@ -8478,6 +8488,22 @@ Error, 'Parse error: decoding `` in strict mode' ); + equal( + he.decode('𯿽', { + 'strict': true + }), + '\uD87F\uDFFD', + 'Decoding `𯿽` (valid code point) in strict mode' + ); + raises( + function() { + he.decode('', { + 'strict': true + }); + }, + Error, + 'Parse error: decoding `` in strict mode' + ); // “If no characters match the range, then don't consume any characters // (and unconsume the U+0023 NUMBER SIGN character and, if appropriate, diff --git a/tests/tests.src.js b/tests/tests.src.js index 8a81d88..014b86a 100644 --- a/tests/tests.src.js +++ b/tests/tests.src.js @@ -6152,6 +6152,16 @@ 'foo&=', 'Attribute value context' ); + raises( + function() { + he.decode('foo&=', { + 'strict': true + // 'isAttributeValue': true is set globally + }); + }, + Error, + 'Parse error: `foo&=` in attribute value context in strict mode' + ); he.decode.options.isAttributeValue = false; equal( he.decode('foo&', { @@ -6246,6 +6256,22 @@ Error, 'Parse error: decoding `` in strict mode' ); + equal( + he.decode('𯿽', { + 'strict': true + }), + '\uD87F\uDFFD', + 'Decoding `𯿽` (valid code point) in strict mode' + ); + raises( + function() { + he.decode('', { + 'strict': true + }); + }, + Error, + 'Parse error: decoding `` in strict mode' + ); // “If no characters match the range, then don't consume any characters // (and unconsume the U+0023 NUMBER SIGN character and, if appropriate, |