From 7e43b7d25b191e2ad1700408bf60ed917e500b55 Mon Sep 17 00:00:00 2001 From: SatriaBagusNurhadianto Date: Fri, 6 Nov 2026 12:22:35 +0700 Subject: [PATCH] fix(meta-fetcher): decode all HTML4 named entities (issue #396) --- src/lib/html-entities.ts | 2127 ++++++++++++++++++++++++++++++++++++++ src/lib/meta-fetcher.ts | 17 +- 2 files changed, 2130 insertions(+), 14 deletions(-) create mode 100644 src/lib/html-entities.ts diff --git a/src/lib/html-entities.ts b/src/lib/html-entities.ts new file mode 100644 index 0000000..785c445 --- /dev/null +++ b/src/lib/html-entities.ts @@ -0,0 +1,2127 @@ +export const NAMED_ENTITIES: Record = { + AElig: 'Æ', + AMP: '&', + Aacute: 'Á', + Abreve: 'Ă', + Acirc: 'Â', + Acy: 'А', + Afr: '\ud835\udd04', + Agrave: 'À', + Alpha: 'Α', + Amacr: 'Ā', + And: '⩓', + Aogon: 'Ą', + Aopf: '\ud835\udd38', + ApplyFunction: '⁡', + Aring: 'Å', + Ascr: '\ud835\udc9c', + Assign: '≔', + Atilde: 'Ã', + Auml: 'Ä', + Backslash: '∖', + Barv: '⫧', + Barwed: '⌆', + Bcy: 'Б', + Because: '∵', + Bernoullis: 'ℬ', + Beta: 'Β', + Bfr: '\ud835\udd05', + Bopf: '\ud835\udd39', + Breve: '˘', + Bscr: 'ℬ', + Bumpeq: '≎', + CHcy: 'Ч', + COPY: '©', + Cacute: 'Ć', + Cap: '⋒', + CapitalDifferentialD: 'ⅅ', + Cayleys: 'ℭ', + Ccaron: 'Č', + Ccedil: 'Ç', + Ccirc: 'Ĉ', + Cconint: '∰', + Cdot: 'Ċ', + Cedilla: '¸', + CenterDot: '·', + Cfr: 'ℭ', + Chi: 'Χ', + CircleDot: '⊙', + CircleMinus: '⊖', + CirclePlus: '⊕', + CircleTimes: '⊗', + ClockwiseContourIntegral: '∲', + CloseCurlyDoubleQuote: '”', + CloseCurlyQuote: '’', + Colon: '∷', + Colone: '⩴', + Congruent: '≡', + Conint: '∯', + ContourIntegral: '∮', + Copf: 'ℂ', + Coproduct: '∐', + CounterClockwiseContourIntegral: '∳', + Cross: '⨯', + Cscr: '\ud835\udc9e', + Cup: '⋓', + CupCap: '≍', + DD: 'ⅅ', + DDotrahd: '⤑', + DJcy: 'Ђ', + DScy: 'Ѕ', + DZcy: 'Џ', + Dagger: '‡', + Darr: '↡', + Dashv: '⫤', + Dcaron: 'Ď', + Dcy: 'Д', + Del: '∇', + Delta: 'Δ', + Dfr: '\ud835\udd07', + DiacriticalAcute: '´', + DiacriticalDot: '˙', + DiacriticalDoubleAcute: '˝', + DiacriticalGrave: '`', + DiacriticalTilde: '˜', + Diamond: '⋄', + DifferentialD: 'ⅆ', + Dopf: '\ud835\udd3b', + Dot: '¨', + DotDot: '⃜', + DotEqual: '≐', + DoubleContourIntegral: '∯', + DoubleDot: '¨', + DoubleDownArrow: '⇓', + DoubleLeftArrow: '⇐', + DoubleLeftRightArrow: '⇔', + DoubleLeftTee: '⫤', + DoubleLongLeftArrow: '⟸', + DoubleLongLeftRightArrow: '⟺', + DoubleLongRightArrow: '⟹', + DoubleRightArrow: '⇒', + DoubleRightTee: '⊨', + DoubleUpArrow: '⇑', + DoubleUpDownArrow: '⇕', + DoubleVerticalBar: '∥', + DownArrow: '↓', + DownArrowBar: '⤓', + DownArrowUpArrow: '⇵', + DownBreve: '̑', + DownLeftRightVector: '⥐', + DownLeftTeeVector: '⥞', + DownLeftVector: '↽', + DownLeftVectorBar: '⥖', + DownRightTeeVector: '⥟', + DownRightVector: '⇁', + DownRightVectorBar: '⥗', + DownTee: '⊤', + DownTeeArrow: '↧', + Downarrow: '⇓', + Dscr: '\ud835\udc9f', + Dstrok: 'Đ', + ENG: 'Ŋ', + ETH: 'Ð', + Eacute: 'É', + Ecaron: 'Ě', + Ecirc: 'Ê', + Ecy: 'Э', + Edot: 'Ė', + Efr: '\ud835\udd08', + Egrave: 'È', + Element: '∈', + Emacr: 'Ē', + EmptySmallSquare: '◻', + EmptyVerySmallSquare: '▫', + Eogon: 'Ę', + Eopf: '\ud835\udd3c', + Epsilon: 'Ε', + Equal: '⩵', + EqualTilde: '≂', + Equilibrium: '⇌', + Escr: 'ℰ', + Esim: '⩳', + Eta: 'Η', + Euml: 'Ë', + Exists: '∃', + ExponentialE: 'ⅇ', + Fcy: 'Ф', + Ffr: '\ud835\udd09', + FilledSmallSquare: '◼', + FilledVerySmallSquare: '▪', + Fopf: '\ud835\udd3d', + ForAll: '∀', + Fouriertrf: 'ℱ', + Fscr: 'ℱ', + GJcy: 'Ѓ', + GT: '>', + Gamma: 'Γ', + Gammad: 'Ϝ', + Gbreve: 'Ğ', + Gcedil: 'Ģ', + Gcirc: 'Ĝ', + Gcy: 'Г', + Gdot: 'Ġ', + Gfr: '\ud835\udd0a', + Gg: '⋙', + Gopf: '\ud835\udd3e', + GreaterEqual: '≥', + GreaterEqualLess: '⋛', + GreaterFullEqual: '≧', + GreaterGreater: '⪢', + GreaterLess: '≷', + GreaterSlantEqual: '⩾', + GreaterTilde: '≳', + Gscr: '\ud835\udca2', + Gt: '≫', + HARDcy: 'Ъ', + Hacek: 'ˇ', + Hat: '^', + Hcirc: 'Ĥ', + Hfr: 'ℌ', + HilbertSpace: 'ℋ', + Hopf: 'ℍ', + HorizontalLine: '─', + Hscr: 'ℋ', + Hstrok: 'Ħ', + HumpDownHump: '≎', + HumpEqual: '≏', + IEcy: 'Е', + IJlig: 'IJ', + IOcy: 'Ё', + Iacute: 'Í', + Icirc: 'Î', + Icy: 'И', + Idot: 'İ', + Ifr: 'ℑ', + Igrave: 'Ì', + Im: 'ℑ', + Imacr: 'Ī', + ImaginaryI: 'ⅈ', + Implies: '⇒', + Int: '∬', + Integral: '∫', + Intersection: '⋂', + InvisibleComma: '⁣', + InvisibleTimes: '⁢', + Iogon: 'Į', + Iopf: '\ud835\udd40', + Iota: 'Ι', + Iscr: 'ℐ', + Itilde: 'Ĩ', + Iukcy: 'І', + Iuml: 'Ï', + Jcirc: 'Ĵ', + Jcy: 'Й', + Jfr: '\ud835\udd0d', + Jopf: '\ud835\udd41', + Jscr: '\ud835\udca5', + Jsercy: 'Ј', + Jukcy: 'Є', + KHcy: 'Х', + KJcy: 'Ќ', + Kappa: 'Κ', + Kcedil: 'Ķ', + Kcy: 'К', + Kfr: '\ud835\udd0e', + Kopf: '\ud835\udd42', + Kscr: '\ud835\udca6', + LJcy: 'Љ', + LT: '<', + Lacute: 'Ĺ', + Lambda: 'Λ', + Lang: '⟪', + Laplacetrf: 'ℒ', + Larr: '↞', + Lcaron: 'Ľ', + Lcedil: 'Ļ', + Lcy: 'Л', + LeftAngleBracket: '⟨', + LeftArrow: '←', + LeftArrowBar: '⇤', + LeftArrowRightArrow: '⇆', + LeftCeiling: '⌈', + LeftDoubleBracket: '⟦', + LeftDownTeeVector: '⥡', + LeftDownVector: '⇃', + LeftDownVectorBar: '⥙', + LeftFloor: '⌊', + LeftRightArrow: '↔', + LeftRightVector: '⥎', + LeftTee: '⊣', + LeftTeeArrow: '↤', + LeftTeeVector: '⥚', + LeftTriangle: '⊲', + LeftTriangleBar: '⧏', + LeftTriangleEqual: '⊴', + LeftUpDownVector: '⥑', + LeftUpTeeVector: '⥠', + LeftUpVector: '↿', + LeftUpVectorBar: '⥘', + LeftVector: '↼', + LeftVectorBar: '⥒', + Leftarrow: '⇐', + Leftrightarrow: '⇔', + LessEqualGreater: '⋚', + LessFullEqual: '≦', + LessGreater: '≶', + LessLess: '⪡', + LessSlantEqual: '⩽', + LessTilde: '≲', + Lfr: '\ud835\udd0f', + Ll: '⋘', + Lleftarrow: '⇚', + Lmidot: 'Ŀ', + LongLeftArrow: '⟵', + LongLeftRightArrow: '⟷', + LongRightArrow: '⟶', + Longleftarrow: '⟸', + Longleftrightarrow: '⟺', + Longrightarrow: '⟹', + Lopf: '\ud835\udd43', + LowerLeftArrow: '↙', + LowerRightArrow: '↘', + Lscr: 'ℒ', + Lsh: '↰', + Lstrok: 'Ł', + Lt: '≪', + Map: '⤅', + Mcy: 'М', + MediumSpace: ' ', + Mellintrf: 'ℳ', + Mfr: '\ud835\udd10', + MinusPlus: '∓', + Mopf: '\ud835\udd44', + Mscr: 'ℳ', + Mu: 'Μ', + NJcy: 'Њ', + Nacute: 'Ń', + Ncaron: 'Ň', + Ncedil: 'Ņ', + Ncy: 'Н', + NegativeMediumSpace: '​', + NegativeThickSpace: '​', + NegativeThinSpace: '​', + NegativeVeryThinSpace: '​', + NestedGreaterGreater: '≫', + NestedLessLess: '≪', + NewLine: '\u000a', + Nfr: '\ud835\udd11', + NoBreak: '⁠', + NonBreakingSpace: ' ', + Nopf: 'ℕ', + Not: '⫬', + NotCongruent: '≢', + NotCupCap: '≭', + NotDoubleVerticalBar: '∦', + NotElement: '∉', + NotEqual: '≠', + NotEqualTilde: '≂̸', + NotExists: '∄', + NotGreater: '≯', + NotGreaterEqual: '≱', + NotGreaterFullEqual: '≧̸', + NotGreaterGreater: '≫̸', + NotGreaterLess: '≹', + NotGreaterSlantEqual: '⩾̸', + NotGreaterTilde: '≵', + NotHumpDownHump: '≎̸', + NotHumpEqual: '≏̸', + NotLeftTriangle: '⋪', + NotLeftTriangleBar: '⧏̸', + NotLeftTriangleEqual: '⋬', + NotLess: '≮', + NotLessEqual: '≰', + NotLessGreater: '≸', + NotLessLess: '≪̸', + NotLessSlantEqual: '⩽̸', + NotLessTilde: '≴', + NotNestedGreaterGreater: '⪢̸', + NotNestedLessLess: '⪡̸', + NotPrecedes: '⊀', + NotPrecedesEqual: '⪯̸', + NotPrecedesSlantEqual: '⋠', + NotReverseElement: '∌', + NotRightTriangle: '⋫', + NotRightTriangleBar: '⧐̸', + NotRightTriangleEqual: '⋭', + NotSquareSubset: '⊏̸', + NotSquareSubsetEqual: '⋢', + NotSquareSuperset: '⊐̸', + NotSquareSupersetEqual: '⋣', + NotSubset: '⊂⃒', + NotSubsetEqual: '⊈', + NotSucceeds: '⊁', + NotSucceedsEqual: '⪰̸', + NotSucceedsSlantEqual: '⋡', + NotSucceedsTilde: '≿̸', + NotSuperset: '⊃⃒', + NotSupersetEqual: '⊉', + NotTilde: '≁', + NotTildeEqual: '≄', + NotTildeFullEqual: '≇', + NotTildeTilde: '≉', + NotVerticalBar: '∤', + Nscr: '\ud835\udca9', + Ntilde: 'Ñ', + Nu: 'Ν', + OElig: 'Œ', + Oacute: 'Ó', + Ocirc: 'Ô', + Ocy: 'О', + Odblac: 'Ő', + Ofr: '\ud835\udd12', + Ograve: 'Ò', + Omacr: 'Ō', + Omega: 'Ω', + Omicron: 'Ο', + Oopf: '\ud835\udd46', + OpenCurlyDoubleQuote: '“', + OpenCurlyQuote: '‘', + Or: '⩔', + Oscr: '\ud835\udcaa', + Oslash: 'Ø', + Otilde: 'Õ', + Otimes: '⨷', + Ouml: 'Ö', + OverBar: '‾', + OverBrace: '⏞', + OverBracket: '⎴', + OverParenthesis: '⏜', + PartialD: '∂', + Pcy: 'П', + Pfr: '\ud835\udd13', + Phi: 'Φ', + Pi: 'Π', + PlusMinus: '±', + Poincareplane: 'ℌ', + Popf: 'ℙ', + Pr: '⪻', + Precedes: '≺', + PrecedesEqual: '⪯', + PrecedesSlantEqual: '≼', + PrecedesTilde: '≾', + Prime: '″', + Product: '∏', + Proportion: '∷', + Proportional: '∝', + Pscr: '\ud835\udcab', + Psi: 'Ψ', + QUOT: '"', + Qfr: '\ud835\udd14', + Qopf: 'ℚ', + Qscr: '\ud835\udcac', + RBarr: '⤐', + REG: '®', + Racute: 'Ŕ', + Rang: '⟫', + Rarr: '↠', + Rarrtl: '⤖', + Rcaron: 'Ř', + Rcedil: 'Ŗ', + Rcy: 'Р', + Re: 'ℜ', + ReverseElement: '∋', + ReverseEquilibrium: '⇋', + ReverseUpEquilibrium: '⥯', + Rfr: 'ℜ', + Rho: 'Ρ', + RightAngleBracket: '⟩', + RightArrow: '→', + RightArrowBar: '⇥', + RightArrowLeftArrow: '⇄', + RightCeiling: '⌉', + RightDoubleBracket: '⟧', + RightDownTeeVector: '⥝', + RightDownVector: '⇂', + RightDownVectorBar: '⥕', + RightFloor: '⌋', + RightTee: '⊢', + RightTeeArrow: '↦', + RightTeeVector: '⥛', + RightTriangle: '⊳', + RightTriangleBar: '⧐', + RightTriangleEqual: '⊵', + RightUpDownVector: '⥏', + RightUpTeeVector: '⥜', + RightUpVector: '↾', + RightUpVectorBar: '⥔', + RightVector: '⇀', + RightVectorBar: '⥓', + Rightarrow: '⇒', + Ropf: 'ℝ', + RoundImplies: '⥰', + Rrightarrow: '⇛', + Rscr: 'ℛ', + Rsh: '↱', + RuleDelayed: '⧴', + SHCHcy: 'Щ', + SHcy: 'Ш', + SOFTcy: 'Ь', + Sacute: 'Ś', + Sc: '⪼', + Scaron: 'Š', + Scedil: 'Ş', + Scirc: 'Ŝ', + Scy: 'С', + Sfr: '\ud835\udd16', + ShortDownArrow: '↓', + ShortLeftArrow: '←', + ShortRightArrow: '→', + ShortUpArrow: '↑', + Sigma: 'Σ', + SmallCircle: '∘', + Sopf: '\ud835\udd4a', + Sqrt: '√', + Square: '□', + SquareIntersection: '⊓', + SquareSubset: '⊏', + SquareSubsetEqual: '⊑', + SquareSuperset: '⊐', + SquareSupersetEqual: '⊒', + SquareUnion: '⊔', + Sscr: '\ud835\udcae', + Star: '⋆', + Sub: '⋐', + Subset: '⋐', + SubsetEqual: '⊆', + Succeeds: '≻', + SucceedsEqual: '⪰', + SucceedsSlantEqual: '≽', + SucceedsTilde: '≿', + SuchThat: '∋', + Sum: '∑', + Sup: '⋑', + Superset: '⊃', + SupersetEqual: '⊇', + Supset: '⋑', + THORN: 'Þ', + TRADE: '™', + TSHcy: 'Ћ', + TScy: 'Ц', + Tab: '\u0009', + Tau: 'Τ', + Tcaron: 'Ť', + Tcedil: 'Ţ', + Tcy: 'Т', + Tfr: '\ud835\udd17', + Therefore: '∴', + Theta: 'Θ', + ThickSpace: '  ', + ThinSpace: ' ', + Tilde: '∼', + TildeEqual: '≃', + TildeFullEqual: '≅', + TildeTilde: '≈', + Topf: '\ud835\udd4b', + TripleDot: '⃛', + Tscr: '\ud835\udcaf', + Tstrok: 'Ŧ', + Uacute: 'Ú', + Uarr: '↟', + Uarrocir: '⥉', + Ubrcy: 'Ў', + Ubreve: 'Ŭ', + Ucirc: 'Û', + Ucy: 'У', + Udblac: 'Ű', + Ufr: '\ud835\udd18', + Ugrave: 'Ù', + Umacr: 'Ū', + UnderBar: '_', + UnderBrace: '⏟', + UnderBracket: '⎵', + UnderParenthesis: '⏝', + Union: '⋃', + UnionPlus: '⊎', + Uogon: 'Ų', + Uopf: '\ud835\udd4c', + UpArrow: '↑', + UpArrowBar: '⤒', + UpArrowDownArrow: '⇅', + UpDownArrow: '↕', + UpEquilibrium: '⥮', + UpTee: '⊥', + UpTeeArrow: '↥', + Uparrow: '⇑', + Updownarrow: '⇕', + UpperLeftArrow: '↖', + UpperRightArrow: '↗', + Upsi: 'ϒ', + Upsilon: 'Υ', + Uring: 'Ů', + Uscr: '\ud835\udcb0', + Utilde: 'Ũ', + Uuml: 'Ü', + VDash: '⊫', + Vbar: '⫫', + Vcy: 'В', + Vdash: '⊩', + Vdashl: '⫦', + Vee: '⋁', + Verbar: '‖', + Vert: '‖', + VerticalBar: '∣', + VerticalLine: '|', + VerticalSeparator: '❘', + VerticalTilde: '≀', + VeryThinSpace: ' ', + Vfr: '\ud835\udd19', + Vopf: '\ud835\udd4d', + Vscr: '\ud835\udcb1', + Vvdash: '⊪', + Wcirc: 'Ŵ', + Wedge: '⋀', + Wfr: '\ud835\udd1a', + Wopf: '\ud835\udd4e', + Wscr: '\ud835\udcb2', + Xfr: '\ud835\udd1b', + Xi: 'Ξ', + Xopf: '\ud835\udd4f', + Xscr: '\ud835\udcb3', + YAcy: 'Я', + YIcy: 'Ї', + YUcy: 'Ю', + Yacute: 'Ý', + Ycirc: 'Ŷ', + Ycy: 'Ы', + Yfr: '\ud835\udd1c', + Yopf: '\ud835\udd50', + Yscr: '\ud835\udcb4', + Yuml: 'Ÿ', + ZHcy: 'Ж', + Zacute: 'Ź', + Zcaron: 'Ž', + Zcy: 'З', + Zdot: 'Ż', + ZeroWidthSpace: '​', + Zeta: 'Ζ', + Zfr: 'ℨ', + Zopf: 'ℤ', + Zscr: '\ud835\udcb5', + aacute: 'á', + abreve: 'ă', + ac: '∾', + acE: '∾̳', + acd: '∿', + acirc: 'â', + acute: '´', + acy: 'а', + aelig: 'æ', + af: '⁡', + afr: '\ud835\udd1e', + agrave: 'à', + alefsym: 'ℵ', + aleph: 'ℵ', + alpha: 'α', + amacr: 'ā', + amalg: '⨿', + amp: '&', + and: '∧', + andand: '⩕', + andd: '⩜', + andslope: '⩘', + andv: '⩚', + ang: '∠', + ange: '⦤', + angle: '∠', + angmsd: '∡', + angmsdaa: '⦨', + angmsdab: '⦩', + angmsdac: '⦪', + angmsdad: '⦫', + angmsdae: '⦬', + angmsdaf: '⦭', + angmsdag: '⦮', + angmsdah: '⦯', + angrt: '∟', + angrtvb: '⊾', + angrtvbd: '⦝', + angsph: '∢', + angst: 'Å', + angzarr: '⍼', + aogon: 'ą', + aopf: '\ud835\udd52', + ap: '≈', + apE: '⩰', + apacir: '⩯', + ape: '≊', + apid: '≋', + apos: '\'', + approx: '≈', + approxeq: '≊', + aring: 'å', + ascr: '\ud835\udcb6', + ast: '*', + asymp: '≈', + asympeq: '≍', + atilde: 'ã', + auml: 'ä', + awconint: '∳', + awint: '⨑', + bNot: '⫭', + backcong: '≌', + backepsilon: '϶', + backprime: '‵', + backsim: '∽', + backsimeq: '⋍', + barvee: '⊽', + barwed: '⌅', + barwedge: '⌅', + bbrk: '⎵', + bbrktbrk: '⎶', + bcong: '≌', + bcy: 'б', + bdquo: '„', + becaus: '∵', + because: '∵', + bemptyv: '⦰', + bepsi: '϶', + bernou: 'ℬ', + beta: 'β', + beth: 'ℶ', + between: '≬', + bfr: '\ud835\udd1f', + bigcap: '⋂', + bigcirc: '◯', + bigcup: '⋃', + bigodot: '⨀', + bigoplus: '⨁', + bigotimes: '⨂', + bigsqcup: '⨆', + bigstar: '★', + bigtriangledown: '▽', + bigtriangleup: '△', + biguplus: '⨄', + bigvee: '⋁', + bigwedge: '⋀', + bkarow: '⤍', + blacklozenge: '⧫', + blacksquare: '▪', + blacktriangle: '▴', + blacktriangledown: '▾', + blacktriangleleft: '◂', + blacktriangleright: '▸', + blank: '␣', + blk12: '▒', + blk14: '░', + blk34: '▓', + block: '█', + bne: '=⃥', + bnequiv: '≡⃥', + bnot: '⌐', + bopf: '\ud835\udd53', + bot: '⊥', + bottom: '⊥', + bowtie: '⋈', + boxDL: '╗', + boxDR: '╔', + boxDl: '╖', + boxDr: '╓', + boxH: '═', + boxHD: '╦', + boxHU: '╩', + boxHd: '╤', + boxHu: '╧', + boxUL: '╝', + boxUR: '╚', + boxUl: '╜', + boxUr: '╙', + boxV: '║', + boxVH: '╬', + boxVL: '╣', + boxVR: '╠', + boxVh: '╫', + boxVl: '╢', + boxVr: '╟', + boxbox: '⧉', + boxdL: '╕', + boxdR: '╒', + boxdl: '┐', + boxdr: '┌', + boxh: '─', + boxhD: '╥', + boxhU: '╨', + boxhd: '┬', + boxhu: '┴', + boxminus: '⊟', + boxplus: '⊞', + boxtimes: '⊠', + boxuL: '╛', + boxuR: '╘', + boxul: '┘', + boxur: '└', + boxv: '│', + boxvH: '╪', + boxvL: '╡', + boxvR: '╞', + boxvh: '┼', + boxvl: '┤', + boxvr: '├', + bprime: '‵', + breve: '˘', + brvbar: '¦', + bscr: '\ud835\udcb7', + bsemi: '⁏', + bsim: '∽', + bsime: '⋍', + bsol: '\\', + bsolb: '⧅', + bsolhsub: '⟈', + bull: '•', + bullet: '•', + bump: '≎', + bumpE: '⪮', + bumpe: '≏', + bumpeq: '≏', + cacute: 'ć', + cap: '∩', + capand: '⩄', + capbrcup: '⩉', + capcap: '⩋', + capcup: '⩇', + capdot: '⩀', + caps: '∩︀', + caret: '⁁', + caron: 'ˇ', + ccaps: '⩍', + ccaron: 'č', + ccedil: 'ç', + ccirc: 'ĉ', + ccups: '⩌', + ccupssm: '⩐', + cdot: 'ċ', + cedil: '¸', + cemptyv: '⦲', + cent: '¢', + centerdot: '·', + cfr: '\ud835\udd20', + chcy: 'ч', + check: '✓', + checkmark: '✓', + chi: 'χ', + cir: '○', + cirE: '⧃', + circ: 'ˆ', + circeq: '≗', + circlearrowleft: '↺', + circlearrowright: '↻', + circledR: '®', + circledS: 'Ⓢ', + circledast: '⊛', + circledcirc: '⊚', + circleddash: '⊝', + cire: '≗', + cirfnint: '⨐', + cirmid: '⫯', + cirscir: '⧂', + clubs: '♣', + clubsuit: '♣', + colon: ':', + colone: '≔', + coloneq: '≔', + comma: ',', + commat: '@', + comp: '∁', + compfn: '∘', + complement: '∁', + complexes: 'ℂ', + cong: '≅', + congdot: '⩭', + conint: '∮', + copf: '\ud835\udd54', + coprod: '∐', + copy: '©', + copysr: '℗', + crarr: '↵', + cross: '✗', + cscr: '\ud835\udcb8', + csub: '⫏', + csube: '⫑', + csup: '⫐', + csupe: '⫒', + ctdot: '⋯', + cudarrl: '⤸', + cudarrr: '⤵', + cuepr: '⋞', + cuesc: '⋟', + cularr: '↶', + cularrp: '⤽', + cup: '∪', + cupbrcap: '⩈', + cupcap: '⩆', + cupcup: '⩊', + cupdot: '⊍', + cupor: '⩅', + cups: '∪︀', + curarr: '↷', + curarrm: '⤼', + curlyeqprec: '⋞', + curlyeqsucc: '⋟', + curlyvee: '⋎', + curlywedge: '⋏', + curren: '¤', + curvearrowleft: '↶', + curvearrowright: '↷', + cuvee: '⋎', + cuwed: '⋏', + cwconint: '∲', + cwint: '∱', + cylcty: '⌭', + dArr: '⇓', + dHar: '⥥', + dagger: '†', + daleth: 'ℸ', + darr: '↓', + dash: '‐', + dashv: '⊣', + dbkarow: '⤏', + dblac: '˝', + dcaron: 'ď', + dcy: 'д', + dd: 'ⅆ', + ddagger: '‡', + ddarr: '⇊', + ddotseq: '⩷', + deg: '°', + delta: 'δ', + demptyv: '⦱', + dfisht: '⥿', + dfr: '\ud835\udd21', + dharl: '⇃', + dharr: '⇂', + diam: '⋄', + diamond: '⋄', + diamondsuit: '♦', + diams: '♦', + die: '¨', + digamma: 'ϝ', + disin: '⋲', + div: '÷', + divide: '÷', + divideontimes: '⋇', + divonx: '⋇', + djcy: 'ђ', + dlcorn: '⌞', + dlcrop: '⌍', + dollar: '$', + dopf: '\ud835\udd55', + dot: '˙', + doteq: '≐', + doteqdot: '≑', + dotminus: '∸', + dotplus: '∔', + dotsquare: '⊡', + doublebarwedge: '⌆', + downarrow: '↓', + downdownarrows: '⇊', + downharpoonleft: '⇃', + downharpoonright: '⇂', + drbkarow: '⤐', + drcorn: '⌟', + drcrop: '⌌', + dscr: '\ud835\udcb9', + dscy: 'ѕ', + dsol: '⧶', + dstrok: 'đ', + dtdot: '⋱', + dtri: '▿', + dtrif: '▾', + duarr: '⇵', + duhar: '⥯', + dwangle: '⦦', + dzcy: 'џ', + dzigrarr: '⟿', + eDDot: '⩷', + eDot: '≑', + eacute: 'é', + easter: '⩮', + ecaron: 'ě', + ecir: '≖', + ecirc: 'ê', + ecolon: '≕', + ecy: 'э', + edot: 'ė', + ee: 'ⅇ', + efDot: '≒', + efr: '\ud835\udd22', + eg: '⪚', + egrave: 'è', + egs: '⪖', + egsdot: '⪘', + el: '⪙', + elinters: '⏧', + ell: 'ℓ', + els: '⪕', + elsdot: '⪗', + emacr: 'ē', + empty: '∅', + emptyset: '∅', + emptyv: '∅', + emsp: ' ', + emsp13: ' ', + emsp14: ' ', + eng: 'ŋ', + ensp: ' ', + eogon: 'ę', + eopf: '\ud835\udd56', + epar: '⋕', + eparsl: '⧣', + eplus: '⩱', + epsi: 'ε', + epsilon: 'ε', + epsiv: 'ϵ', + eqcirc: '≖', + eqcolon: '≕', + eqsim: '≂', + eqslantgtr: '⪖', + eqslantless: '⪕', + equals: '=', + equest: '≟', + equiv: '≡', + equivDD: '⩸', + eqvparsl: '⧥', + erDot: '≓', + erarr: '⥱', + escr: 'ℯ', + esdot: '≐', + esim: '≂', + eta: 'η', + eth: 'ð', + euml: 'ë', + euro: '€', + excl: '!', + exist: '∃', + expectation: 'ℰ', + exponentiale: 'ⅇ', + fallingdotseq: '≒', + fcy: 'ф', + female: '♀', + ffilig: 'ffi', + fflig: 'ff', + ffllig: 'ffl', + ffr: '\ud835\udd23', + filig: 'fi', + fjlig: 'fj', + flat: '♭', + fllig: 'fl', + fltns: '▱', + fnof: 'ƒ', + fopf: '\ud835\udd57', + forall: '∀', + fork: '⋔', + forkv: '⫙', + fpartint: '⨍', + frac12: '½', + frac13: '⅓', + frac14: '¼', + frac15: '⅕', + frac16: '⅙', + frac18: '⅛', + frac23: '⅔', + frac25: '⅖', + frac34: '¾', + frac35: '⅗', + frac38: '⅜', + frac45: '⅘', + frac56: '⅚', + frac58: '⅝', + frac78: '⅞', + frasl: '⁄', + frown: '⌢', + fscr: '\ud835\udcbb', + gE: '≧', + gEl: '⪌', + gacute: 'ǵ', + gamma: 'γ', + gammad: 'ϝ', + gap: '⪆', + gbreve: 'ğ', + gcirc: 'ĝ', + gcy: 'г', + gdot: 'ġ', + ge: '≥', + gel: '⋛', + geq: '≥', + geqq: '≧', + geqslant: '⩾', + ges: '⩾', + gescc: '⪩', + gesdot: '⪀', + gesdoto: '⪂', + gesdotol: '⪄', + gesl: '⋛︀', + gesles: '⪔', + gfr: '\ud835\udd24', + gg: '≫', + ggg: '⋙', + gimel: 'ℷ', + gjcy: 'ѓ', + gl: '≷', + glE: '⪒', + gla: '⪥', + glj: '⪤', + gnE: '≩', + gnap: '⪊', + gnapprox: '⪊', + gne: '⪈', + gneq: '⪈', + gneqq: '≩', + gnsim: '⋧', + gopf: '\ud835\udd58', + grave: '`', + gscr: 'ℊ', + gsim: '≳', + gsime: '⪎', + gsiml: '⪐', + gt: '>', + gtcc: '⪧', + gtcir: '⩺', + gtdot: '⋗', + gtlPar: '⦕', + gtquest: '⩼', + gtrapprox: '⪆', + gtrarr: '⥸', + gtrdot: '⋗', + gtreqless: '⋛', + gtreqqless: '⪌', + gtrless: '≷', + gtrsim: '≳', + gvertneqq: '≩︀', + gvnE: '≩︀', + hArr: '⇔', + hairsp: ' ', + half: '½', + hamilt: 'ℋ', + hardcy: 'ъ', + harr: '↔', + harrcir: '⥈', + harrw: '↭', + hbar: 'ℏ', + hcirc: 'ĥ', + hearts: '♥', + heartsuit: '♥', + hellip: '…', + hercon: '⊹', + hfr: '\ud835\udd25', + hksearow: '⤥', + hkswarow: '⤦', + hoarr: '⇿', + homtht: '∻', + hookleftarrow: '↩', + hookrightarrow: '↪', + hopf: '\ud835\udd59', + horbar: '―', + hscr: '\ud835\udcbd', + hslash: 'ℏ', + hstrok: 'ħ', + hybull: '⁃', + hyphen: '‐', + iacute: 'í', + ic: '⁣', + icirc: 'î', + icy: 'и', + iecy: 'е', + iexcl: '¡', + iff: '⇔', + ifr: '\ud835\udd26', + igrave: 'ì', + ii: 'ⅈ', + iiiint: '⨌', + iiint: '∭', + iinfin: '⧜', + iiota: '℩', + ijlig: 'ij', + imacr: 'ī', + image: 'ℑ', + imagline: 'ℐ', + imagpart: 'ℑ', + imath: 'ı', + imof: '⊷', + imped: 'Ƶ', + in: '∈', + incare: '℅', + infin: '∞', + infintie: '⧝', + inodot: 'ı', + int: '∫', + intcal: '⊺', + integers: 'ℤ', + intercal: '⊺', + intlarhk: '⨗', + intprod: '⨼', + iocy: 'ё', + iogon: 'į', + iopf: '\ud835\udd5a', + iota: 'ι', + iprod: '⨼', + iquest: '¿', + iscr: '\ud835\udcbe', + isin: '∈', + isinE: '⋹', + isindot: '⋵', + isins: '⋴', + isinsv: '⋳', + isinv: '∈', + it: '⁢', + itilde: 'ĩ', + iukcy: 'і', + iuml: 'ï', + jcirc: 'ĵ', + jcy: 'й', + jfr: '\ud835\udd27', + jmath: 'ȷ', + jopf: '\ud835\udd5b', + jscr: '\ud835\udcbf', + jsercy: 'ј', + jukcy: 'є', + kappa: 'κ', + kappav: 'ϰ', + kcedil: 'ķ', + kcy: 'к', + kfr: '\ud835\udd28', + kgreen: 'ĸ', + khcy: 'х', + kjcy: 'ќ', + kopf: '\ud835\udd5c', + kscr: '\ud835\udcc0', + lAarr: '⇚', + lArr: '⇐', + lAtail: '⤛', + lBarr: '⤎', + lE: '≦', + lEg: '⪋', + lHar: '⥢', + lacute: 'ĺ', + laemptyv: '⦴', + lagran: 'ℒ', + lambda: 'λ', + lang: '⟨', + langd: '⦑', + langle: '⟨', + lap: '⪅', + laquo: '«', + larr: '←', + larrb: '⇤', + larrbfs: '⤟', + larrfs: '⤝', + larrhk: '↩', + larrlp: '↫', + larrpl: '⤹', + larrsim: '⥳', + larrtl: '↢', + lat: '⪫', + latail: '⤙', + late: '⪭', + lates: '⪭︀', + lbarr: '⤌', + lbbrk: '❲', + lbrace: '{', + lbrack: '[', + lbrke: '⦋', + lbrksld: '⦏', + lbrkslu: '⦍', + lcaron: 'ľ', + lcedil: 'ļ', + lceil: '⌈', + lcub: '{', + lcy: 'л', + ldca: '⤶', + ldquo: '“', + ldquor: '„', + ldrdhar: '⥧', + ldrushar: '⥋', + ldsh: '↲', + le: '≤', + leftarrow: '←', + leftarrowtail: '↢', + leftharpoondown: '↽', + leftharpoonup: '↼', + leftleftarrows: '⇇', + leftrightarrow: '↔', + leftrightarrows: '⇆', + leftrightharpoons: '⇋', + leftrightsquigarrow: '↭', + leftthreetimes: '⋋', + leg: '⋚', + leq: '≤', + leqq: '≦', + leqslant: '⩽', + les: '⩽', + lescc: '⪨', + lesdot: '⩿', + lesdoto: '⪁', + lesdotor: '⪃', + lesg: '⋚︀', + lesges: '⪓', + lessapprox: '⪅', + lessdot: '⋖', + lesseqgtr: '⋚', + lesseqqgtr: '⪋', + lessgtr: '≶', + lesssim: '≲', + lfisht: '⥼', + lfloor: '⌊', + lfr: '\ud835\udd29', + lg: '≶', + lgE: '⪑', + lhard: '↽', + lharu: '↼', + lharul: '⥪', + lhblk: '▄', + ljcy: 'љ', + ll: '≪', + llarr: '⇇', + llcorner: '⌞', + llhard: '⥫', + lltri: '◺', + lmidot: 'ŀ', + lmoust: '⎰', + lmoustache: '⎰', + lnE: '≨', + lnap: '⪉', + lnapprox: '⪉', + lne: '⪇', + lneq: '⪇', + lneqq: '≨', + lnsim: '⋦', + loang: '⟬', + loarr: '⇽', + lobrk: '⟦', + longleftarrow: '⟵', + longleftrightarrow: '⟷', + longmapsto: '⟼', + longrightarrow: '⟶', + looparrowleft: '↫', + looparrowright: '↬', + lopar: '⦅', + lopf: '\ud835\udd5d', + loplus: '⨭', + lotimes: '⨴', + lowast: '∗', + lowbar: '_', + loz: '◊', + lozenge: '◊', + lozf: '⧫', + lpar: '(', + lparlt: '⦓', + lrarr: '⇆', + lrcorner: '⌟', + lrhar: '⇋', + lrhard: '⥭', + lrm: '‎', + lrtri: '⊿', + lsaquo: '‹', + lscr: '\ud835\udcc1', + lsh: '↰', + lsim: '≲', + lsime: '⪍', + lsimg: '⪏', + lsqb: '[', + lsquo: '‘', + lsquor: '‚', + lstrok: 'ł', + lt: '<', + ltcc: '⪦', + ltcir: '⩹', + ltdot: '⋖', + lthree: '⋋', + ltimes: '⋉', + ltlarr: '⥶', + ltquest: '⩻', + ltrPar: '⦖', + ltri: '◃', + ltrie: '⊴', + ltrif: '◂', + lurdshar: '⥊', + luruhar: '⥦', + lvertneqq: '≨︀', + lvnE: '≨︀', + mDDot: '∺', + macr: '¯', + male: '♂', + malt: '✠', + maltese: '✠', + map: '↦', + mapsto: '↦', + mapstodown: '↧', + mapstoleft: '↤', + mapstoup: '↥', + marker: '▮', + mcomma: '⨩', + mcy: 'м', + mdash: '—', + measuredangle: '∡', + mfr: '\ud835\udd2a', + mho: '℧', + micro: 'µ', + mid: '∣', + midast: '*', + midcir: '⫰', + middot: '·', + minus: '−', + minusb: '⊟', + minusd: '∸', + minusdu: '⨪', + mlcp: '⫛', + mldr: '…', + mnplus: '∓', + models: '⊧', + mopf: '\ud835\udd5e', + mp: '∓', + mscr: '\ud835\udcc2', + mstpos: '∾', + mu: 'μ', + multimap: '⊸', + mumap: '⊸', + nGg: '⋙̸', + nGt: '≫⃒', + nGtv: '≫̸', + nLeftarrow: '⇍', + nLeftrightarrow: '⇎', + nLl: '⋘̸', + nLt: '≪⃒', + nLtv: '≪̸', + nRightarrow: '⇏', + nVDash: '⊯', + nVdash: '⊮', + nabla: '∇', + nacute: 'ń', + nang: '∠⃒', + nap: '≉', + napE: '⩰̸', + napid: '≋̸', + napos: 'ʼn', + napprox: '≉', + natur: '♮', + natural: '♮', + naturals: 'ℕ', + nbsp: ' ', + nbump: '≎̸', + nbumpe: '≏̸', + ncap: '⩃', + ncaron: 'ň', + ncedil: 'ņ', + ncong: '≇', + ncongdot: '⩭̸', + ncup: '⩂', + ncy: 'н', + ndash: '–', + ne: '≠', + neArr: '⇗', + nearhk: '⤤', + nearr: '↗', + nearrow: '↗', + nedot: '≐̸', + nequiv: '≢', + nesear: '⤨', + nesim: '≂̸', + nexist: '∄', + nexists: '∄', + nfr: '\ud835\udd2b', + ngE: '≧̸', + nge: '≱', + ngeq: '≱', + ngeqq: '≧̸', + ngeqslant: '⩾̸', + nges: '⩾̸', + ngsim: '≵', + ngt: '≯', + ngtr: '≯', + nhArr: '⇎', + nharr: '↮', + nhpar: '⫲', + ni: '∋', + nis: '⋼', + nisd: '⋺', + niv: '∋', + njcy: 'њ', + nlArr: '⇍', + nlE: '≦̸', + nlarr: '↚', + nldr: '‥', + nle: '≰', + nleftarrow: '↚', + nleftrightarrow: '↮', + nleq: '≰', + nleqq: '≦̸', + nleqslant: '⩽̸', + nles: '⩽̸', + nless: '≮', + nlsim: '≴', + nlt: '≮', + nltri: '⋪', + nltrie: '⋬', + nmid: '∤', + nopf: '\ud835\udd5f', + not: '¬', + notin: '∉', + notinE: '⋹̸', + notindot: '⋵̸', + notinva: '∉', + notinvb: '⋷', + notinvc: '⋶', + notni: '∌', + notniva: '∌', + notnivb: '⋾', + notnivc: '⋽', + npar: '∦', + nparallel: '∦', + nparsl: '⫽⃥', + npart: '∂̸', + npolint: '⨔', + npr: '⊀', + nprcue: '⋠', + npre: '⪯̸', + nprec: '⊀', + npreceq: '⪯̸', + nrArr: '⇏', + nrarr: '↛', + nrarrc: '⤳̸', + nrarrw: '↝̸', + nrightarrow: '↛', + nrtri: '⋫', + nrtrie: '⋭', + nsc: '⊁', + nsccue: '⋡', + nsce: '⪰̸', + nscr: '\ud835\udcc3', + nshortmid: '∤', + nshortparallel: '∦', + nsim: '≁', + nsime: '≄', + nsimeq: '≄', + nsmid: '∤', + nspar: '∦', + nsqsube: '⋢', + nsqsupe: '⋣', + nsub: '⊄', + nsubE: '⫅̸', + nsube: '⊈', + nsubset: '⊂⃒', + nsubseteq: '⊈', + nsubseteqq: '⫅̸', + nsucc: '⊁', + nsucceq: '⪰̸', + nsup: '⊅', + nsupE: '⫆̸', + nsupe: '⊉', + nsupset: '⊃⃒', + nsupseteq: '⊉', + nsupseteqq: '⫆̸', + ntgl: '≹', + ntilde: 'ñ', + ntlg: '≸', + ntriangleleft: '⋪', + ntrianglelefteq: '⋬', + ntriangleright: '⋫', + ntrianglerighteq: '⋭', + nu: 'ν', + num: '#', + numero: '№', + numsp: ' ', + nvDash: '⊭', + nvHarr: '⤄', + nvap: '≍⃒', + nvdash: '⊬', + nvge: '≥⃒', + nvgt: '>⃒', + nvinfin: '⧞', + nvlArr: '⤂', + nvle: '≤⃒', + nvlt: '<⃒', + nvltrie: '⊴⃒', + nvrArr: '⤃', + nvrtrie: '⊵⃒', + nvsim: '∼⃒', + nwArr: '⇖', + nwarhk: '⤣', + nwarr: '↖', + nwarrow: '↖', + nwnear: '⤧', + oS: 'Ⓢ', + oacute: 'ó', + oast: '⊛', + ocir: '⊚', + ocirc: 'ô', + ocy: 'о', + odash: '⊝', + odblac: 'ő', + odiv: '⨸', + odot: '⊙', + odsold: '⦼', + oelig: 'œ', + ofcir: '⦿', + ofr: '\ud835\udd2c', + ogon: '˛', + ograve: 'ò', + ogt: '⧁', + ohbar: '⦵', + ohm: 'Ω', + oint: '∮', + olarr: '↺', + olcir: '⦾', + olcross: '⦻', + oline: '‾', + olt: '⧀', + omacr: 'ō', + omega: 'ω', + omicron: 'ο', + omid: '⦶', + ominus: '⊖', + oopf: '\ud835\udd60', + opar: '⦷', + operp: '⦹', + oplus: '⊕', + or: '∨', + orarr: '↻', + ord: '⩝', + order: 'ℴ', + orderof: 'ℴ', + ordf: 'ª', + ordm: 'º', + origof: '⊶', + oror: '⩖', + orslope: '⩗', + orv: '⩛', + oscr: 'ℴ', + oslash: 'ø', + osol: '⊘', + otilde: 'õ', + otimes: '⊗', + otimesas: '⨶', + ouml: 'ö', + ovbar: '⌽', + par: '∥', + para: '¶', + parallel: '∥', + parsim: '⫳', + parsl: '⫽', + part: '∂', + pcy: 'п', + percnt: '%', + period: '.', + permil: '‰', + perp: '⊥', + pertenk: '‱', + pfr: '\ud835\udd2d', + phi: 'φ', + phiv: 'ϕ', + phmmat: 'ℳ', + phone: '☎', + pi: 'π', + pitchfork: '⋔', + piv: 'ϖ', + planck: 'ℏ', + planckh: 'ℎ', + plankv: 'ℏ', + plus: '+', + plusacir: '⨣', + plusb: '⊞', + pluscir: '⨢', + plusdo: '∔', + plusdu: '⨥', + pluse: '⩲', + plusmn: '±', + plussim: '⨦', + plustwo: '⨧', + pm: '±', + pointint: '⨕', + popf: '\ud835\udd61', + pound: '£', + pr: '≺', + prE: '⪳', + prap: '⪷', + prcue: '≼', + pre: '⪯', + prec: '≺', + precapprox: '⪷', + preccurlyeq: '≼', + preceq: '⪯', + precnapprox: '⪹', + precneqq: '⪵', + precnsim: '⋨', + precsim: '≾', + prime: '′', + primes: 'ℙ', + prnE: '⪵', + prnap: '⪹', + prnsim: '⋨', + prod: '∏', + profalar: '⌮', + profline: '⌒', + profsurf: '⌓', + prop: '∝', + propto: '∝', + prsim: '≾', + prurel: '⊰', + pscr: '\ud835\udcc5', + psi: 'ψ', + puncsp: ' ', + qfr: '\ud835\udd2e', + qint: '⨌', + qopf: '\ud835\udd62', + qprime: '⁗', + qscr: '\ud835\udcc6', + quaternions: 'ℍ', + quatint: '⨖', + quest: '?', + questeq: '≟', + quot: '"', + rAarr: '⇛', + rArr: '⇒', + rAtail: '⤜', + rBarr: '⤏', + rHar: '⥤', + race: '∽̱', + racute: 'ŕ', + radic: '√', + raemptyv: '⦳', + rang: '⟩', + rangd: '⦒', + range: '⦥', + rangle: '⟩', + raquo: '»', + rarr: '→', + rarrap: '⥵', + rarrb: '⇥', + rarrbfs: '⤠', + rarrc: '⤳', + rarrfs: '⤞', + rarrhk: '↪', + rarrlp: '↬', + rarrpl: '⥅', + rarrsim: '⥴', + rarrtl: '↣', + rarrw: '↝', + ratail: '⤚', + ratio: '∶', + rationals: 'ℚ', + rbarr: '⤍', + rbbrk: '❳', + rbrace: '}', + rbrack: ']', + rbrke: '⦌', + rbrksld: '⦎', + rbrkslu: '⦐', + rcaron: 'ř', + rcedil: 'ŗ', + rceil: '⌉', + rcub: '}', + rcy: 'р', + rdca: '⤷', + rdldhar: '⥩', + rdquo: '”', + rdquor: '”', + rdsh: '↳', + real: 'ℜ', + realine: 'ℛ', + realpart: 'ℜ', + reals: 'ℝ', + rect: '▭', + reg: '®', + rfisht: '⥽', + rfloor: '⌋', + rfr: '\ud835\udd2f', + rhard: '⇁', + rharu: '⇀', + rharul: '⥬', + rho: 'ρ', + rhov: 'ϱ', + rightarrow: '→', + rightarrowtail: '↣', + rightharpoondown: '⇁', + rightharpoonup: '⇀', + rightleftarrows: '⇄', + rightleftharpoons: '⇌', + rightrightarrows: '⇉', + rightsquigarrow: '↝', + rightthreetimes: '⋌', + ring: '˚', + risingdotseq: '≓', + rlarr: '⇄', + rlhar: '⇌', + rlm: '‏', + rmoust: '⎱', + rmoustache: '⎱', + rnmid: '⫮', + roang: '⟭', + roarr: '⇾', + robrk: '⟧', + ropar: '⦆', + ropf: '\ud835\udd63', + roplus: '⨮', + rotimes: '⨵', + rpar: ')', + rpargt: '⦔', + rppolint: '⨒', + rrarr: '⇉', + rsaquo: '›', + rscr: '\ud835\udcc7', + rsh: '↱', + rsqb: ']', + rsquo: '’', + rsquor: '’', + rthree: '⋌', + rtimes: '⋊', + rtri: '▹', + rtrie: '⊵', + rtrif: '▸', + rtriltri: '⧎', + ruluhar: '⥨', + rx: '℞', + sacute: 'ś', + sbquo: '‚', + sc: '≻', + scE: '⪴', + scap: '⪸', + scaron: 'š', + sccue: '≽', + sce: '⪰', + scedil: 'ş', + scirc: 'ŝ', + scnE: '⪶', + scnap: '⪺', + scnsim: '⋩', + scpolint: '⨓', + scsim: '≿', + scy: 'с', + sdot: '⋅', + sdotb: '⊡', + sdote: '⩦', + seArr: '⇘', + searhk: '⤥', + searr: '↘', + searrow: '↘', + sect: '§', + semi: ';', + seswar: '⤩', + setminus: '∖', + setmn: '∖', + sext: '✶', + sfr: '\ud835\udd30', + sfrown: '⌢', + sharp: '♯', + shchcy: 'щ', + shcy: 'ш', + shortmid: '∣', + shortparallel: '∥', + shy: '­', + sigma: 'σ', + sigmaf: 'ς', + sigmav: 'ς', + sim: '∼', + simdot: '⩪', + sime: '≃', + simeq: '≃', + simg: '⪞', + simgE: '⪠', + siml: '⪝', + simlE: '⪟', + simne: '≆', + simplus: '⨤', + simrarr: '⥲', + slarr: '←', + smallsetminus: '∖', + smashp: '⨳', + smeparsl: '⧤', + smid: '∣', + smile: '⌣', + smt: '⪪', + smte: '⪬', + smtes: '⪬︀', + softcy: 'ь', + sol: '/', + solb: '⧄', + solbar: '⌿', + sopf: '\ud835\udd64', + spades: '♠', + spadesuit: '♠', + spar: '∥', + sqcap: '⊓', + sqcaps: '⊓︀', + sqcup: '⊔', + sqcups: '⊔︀', + sqsub: '⊏', + sqsube: '⊑', + sqsubset: '⊏', + sqsubseteq: '⊑', + sqsup: '⊐', + sqsupe: '⊒', + sqsupset: '⊐', + sqsupseteq: '⊒', + squ: '□', + square: '□', + squarf: '▪', + squf: '▪', + srarr: '→', + sscr: '\ud835\udcc8', + ssetmn: '∖', + ssmile: '⌣', + sstarf: '⋆', + star: '☆', + starf: '★', + straightepsilon: 'ϵ', + straightphi: 'ϕ', + strns: '¯', + sub: '⊂', + subE: '⫅', + subdot: '⪽', + sube: '⊆', + subedot: '⫃', + submult: '⫁', + subnE: '⫋', + subne: '⊊', + subplus: '⪿', + subrarr: '⥹', + subset: '⊂', + subseteq: '⊆', + subseteqq: '⫅', + subsetneq: '⊊', + subsetneqq: '⫋', + subsim: '⫇', + subsub: '⫕', + subsup: '⫓', + succ: '≻', + succapprox: '⪸', + succcurlyeq: '≽', + succeq: '⪰', + succnapprox: '⪺', + succneqq: '⪶', + succnsim: '⋩', + succsim: '≿', + sum: '∑', + sung: '♪', + sup: '⊃', + sup1: '¹', + sup2: '²', + sup3: '³', + supE: '⫆', + supdot: '⪾', + supdsub: '⫘', + supe: '⊇', + supedot: '⫄', + suphsol: '⟉', + suphsub: '⫗', + suplarr: '⥻', + supmult: '⫂', + supnE: '⫌', + supne: '⊋', + supplus: '⫀', + supset: '⊃', + supseteq: '⊇', + supseteqq: '⫆', + supsetneq: '⊋', + supsetneqq: '⫌', + supsim: '⫈', + supsub: '⫔', + supsup: '⫖', + swArr: '⇙', + swarhk: '⤦', + swarr: '↙', + swarrow: '↙', + swnwar: '⤪', + szlig: 'ß', + target: '⌖', + tau: 'τ', + tbrk: '⎴', + tcaron: 'ť', + tcedil: 'ţ', + tcy: 'т', + tdot: '⃛', + telrec: '⌕', + tfr: '\ud835\udd31', + there4: '∴', + therefore: '∴', + theta: 'θ', + thetasym: 'ϑ', + thetav: 'ϑ', + thickapprox: '≈', + thicksim: '∼', + thinsp: ' ', + thkap: '≈', + thksim: '∼', + thorn: 'þ', + tilde: '˜', + times: '×', + timesb: '⊠', + timesbar: '⨱', + timesd: '⨰', + tint: '∭', + toea: '⤨', + top: '⊤', + topbot: '⌶', + topcir: '⫱', + topf: '\ud835\udd65', + topfork: '⫚', + tosa: '⤩', + tprime: '‴', + trade: '™', + triangle: '▵', + triangledown: '▿', + triangleleft: '◃', + trianglelefteq: '⊴', + triangleq: '≜', + triangleright: '▹', + trianglerighteq: '⊵', + tridot: '◬', + trie: '≜', + triminus: '⨺', + triplus: '⨹', + trisb: '⧍', + tritime: '⨻', + trpezium: '⏢', + tscr: '\ud835\udcc9', + tscy: 'ц', + tshcy: 'ћ', + tstrok: 'ŧ', + twixt: '≬', + twoheadleftarrow: '↞', + twoheadrightarrow: '↠', + uArr: '⇑', + uHar: '⥣', + uacute: 'ú', + uarr: '↑', + ubrcy: 'ў', + ubreve: 'ŭ', + ucirc: 'û', + ucy: 'у', + udarr: '⇅', + udblac: 'ű', + udhar: '⥮', + ufisht: '⥾', + ufr: '\ud835\udd32', + ugrave: 'ù', + uharl: '↿', + uharr: '↾', + uhblk: '▀', + ulcorn: '⌜', + ulcorner: '⌜', + ulcrop: '⌏', + ultri: '◸', + umacr: 'ū', + uml: '¨', + uogon: 'ų', + uopf: '\ud835\udd66', + uparrow: '↑', + updownarrow: '↕', + upharpoonleft: '↿', + upharpoonright: '↾', + uplus: '⊎', + upsi: 'υ', + upsih: 'ϒ', + upsilon: 'υ', + upuparrows: '⇈', + urcorn: '⌝', + urcorner: '⌝', + urcrop: '⌎', + uring: 'ů', + urtri: '◹', + uscr: '\ud835\udcca', + utdot: '⋰', + utilde: 'ũ', + utri: '▵', + utrif: '▴', + uuarr: '⇈', + uuml: 'ü', + uwangle: '⦧', + vArr: '⇕', + vBar: '⫨', + vBarv: '⫩', + vDash: '⊨', + vangrt: '⦜', + varepsilon: 'ϵ', + varkappa: 'ϰ', + varnothing: '∅', + varphi: 'ϕ', + varpi: 'ϖ', + varpropto: '∝', + varr: '↕', + varrho: 'ϱ', + varsigma: 'ς', + varsubsetneq: '⊊︀', + varsubsetneqq: '⫋︀', + varsupsetneq: '⊋︀', + varsupsetneqq: '⫌︀', + vartheta: 'ϑ', + vartriangleleft: '⊲', + vartriangleright: '⊳', + vcy: 'в', + vdash: '⊢', + vee: '∨', + veebar: '⊻', + veeeq: '≚', + vellip: '⋮', + verbar: '|', + vert: '|', + vfr: '\ud835\udd33', + vltri: '⊲', + vnsub: '⊂⃒', + vnsup: '⊃⃒', + vopf: '\ud835\udd67', + vprop: '∝', + vrtri: '⊳', + vscr: '\ud835\udccb', + vsubnE: '⫋︀', + vsubne: '⊊︀', + vsupnE: '⫌︀', + vsupne: '⊋︀', + vzigzag: '⦚', + wcirc: 'ŵ', + wedbar: '⩟', + wedge: '∧', + wedgeq: '≙', + weierp: '℘', + wfr: '\ud835\udd34', + wopf: '\ud835\udd68', + wp: '℘', + wr: '≀', + wreath: '≀', + wscr: '\ud835\udccc', + xcap: '⋂', + xcirc: '◯', + xcup: '⋃', + xdtri: '▽', + xfr: '\ud835\udd35', + xhArr: '⟺', + xharr: '⟷', + xi: 'ξ', + xlArr: '⟸', + xlarr: '⟵', + xmap: '⟼', + xnis: '⋻', + xodot: '⨀', + xopf: '\ud835\udd69', + xoplus: '⨁', + xotime: '⨂', + xrArr: '⟹', + xrarr: '⟶', + xscr: '\ud835\udccd', + xsqcup: '⨆', + xuplus: '⨄', + xutri: '△', + xvee: '⋁', + xwedge: '⋀', + yacute: 'ý', + yacy: 'я', + ycirc: 'ŷ', + ycy: 'ы', + yen: '¥', + yfr: '\ud835\udd36', + yicy: 'ї', + yopf: '\ud835\udd6a', + yscr: '\ud835\udcce', + yucy: 'ю', + yuml: 'ÿ', + zacute: 'ź', + zcaron: 'ž', + zcy: 'з', + zdot: 'ż', + zeetrf: 'ℨ', + zeta: 'ζ', + zfr: '\ud835\udd37', + zhcy: 'ж', + zigrarr: '⇝', + zopf: '\ud835\udd6b', + zscr: '\ud835\udccf', + zwj: '‍', + zwnj: '‌', +}; diff --git a/src/lib/meta-fetcher.ts b/src/lib/meta-fetcher.ts index 59d7775..4654f79 100644 --- a/src/lib/meta-fetcher.ts +++ b/src/lib/meta-fetcher.ts @@ -1,3 +1,5 @@ +import { NAMED_ENTITIES } from './html-entities'; + export interface MetaTags { title?: string; description?: string; @@ -187,21 +189,8 @@ function findTags(html: string, tagName: 'meta' | 'link'): string[] { return tags; } -const NAMED_ENTITIES: Record = { - amp: '&', - lt: '<', - gt: '>', - quot: '"', - apos: "'", - nbsp: '\u00a0', - AMP: '&', - LT: '<', - GT: '>', - QUOT: '"', -}; - function decodeEntities(str: string): string { - return str.replace(/&(#\d+|#x[0-9a-f]+|[a-z]+);/gi, (entity, body: string) => { + return str.replace(/&(#\d+|#x[0-9a-f]+|[a-z][a-z0-9]*);/gi, (entity, body: string) => { if (body[0] !== '#') return Object.hasOwn(NAMED_ENTITIES, body) ? NAMED_ENTITIES[body] : entity; const hex = body[1] === 'x' || body[1] === 'X'; const code = parseInt(body.slice(hex ? 2 : 1), hex ? 16 : 10);