/* MIT License http://www.opensource.org/licenses/mit-license.php Author Raj Aryan (based on SWC parser by Alexander Akait) */ "use strict"; // cspell:ignore apos notpre noncharacters DFFF // #region html entities // The contents of this region are auto-generated by // `tooling/generate-html-entities.js` from `tooling/html-entities.json`. // Do not edit by hand — re-run the generator (via `yarn fix:special`) to refresh. // // WHATWG named character references. Keys are entity names WITHOUT the // leading `&` (some end with `;`, others omit it for legacy entities that // match without a closing semicolon). Values are the decoded character // strings (1–2 UTF-16 code units). // Built on a null prototype so bracket lookups (`HTML_ENTITIES[name]`) // can't be poisoned by inherited `Object.prototype` keys like `toString`, // `constructor`, or `__proto__` — without this, `&toString;` would falsely // look like a matched named character reference. // prettier-ignore // cspell:disable-next-line const HTML_ENTITIES = /** @type {Readonly>} */ (Object.freeze(Object.assign(Object.create(null), {"AElig":"Æ","AElig;":"Æ","AMP":"&","AMP;":"&","Aacute":"Á","Aacute;":"Á","Abreve;":"Ă","Acirc":"Â","Acirc;":"Â","Acy;":"А","Afr;":"𝔄","Agrave":"À","Agrave;":"À","Alpha;":"Α","Amacr;":"Ā","And;":"⩓","Aogon;":"Ą","Aopf;":"𝔸","ApplyFunction;":"⁡","Aring":"Å","Aring;":"Å","Ascr;":"𝒜","Assign;":"≔","Atilde":"Ã","Atilde;":"Ã","Auml":"Ä","Auml;":"Ä","Backslash;":"∖","Barv;":"⫧","Barwed;":"⌆","Bcy;":"Б","Because;":"∵","Bernoullis;":"ℬ","Beta;":"Β","Bfr;":"𝔅","Bopf;":"𝔹","Breve;":"˘","Bscr;":"ℬ","Bumpeq;":"≎","CHcy;":"Ч","COPY":"©","COPY;":"©","Cacute;":"Ć","Cap;":"⋒","CapitalDifferentialD;":"ⅅ","Cayleys;":"ℭ","Ccaron;":"Č","Ccedil":"Ç","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;":"𝒞","Cup;":"⋓","CupCap;":"≍","DD;":"ⅅ","DDotrahd;":"⤑","DJcy;":"Ђ","DScy;":"Ѕ","DZcy;":"Џ","Dagger;":"‡","Darr;":"↡","Dashv;":"⫤","Dcaron;":"Ď","Dcy;":"Д","Del;":"∇","Delta;":"Δ","Dfr;":"𝔇","DiacriticalAcute;":"´","DiacriticalDot;":"˙","DiacriticalDoubleAcute;":"˝","DiacriticalGrave;":"`","DiacriticalTilde;":"˜","Diamond;":"⋄","DifferentialD;":"ⅆ","Dopf;":"𝔻","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;":"𝒟","Dstrok;":"Đ","ENG;":"Ŋ","ETH":"Ð","ETH;":"Ð","Eacute":"É","Eacute;":"É","Ecaron;":"Ě","Ecirc":"Ê","Ecirc;":"Ê","Ecy;":"Э","Edot;":"Ė","Efr;":"𝔈","Egrave":"È","Egrave;":"È","Element;":"∈","Emacr;":"Ē","EmptySmallSquare;":"◻","EmptyVerySmallSquare;":"▫","Eogon;":"Ę","Eopf;":"𝔼","Epsilon;":"Ε","Equal;":"⩵","EqualTilde;":"≂","Equilibrium;":"⇌","Escr;":"ℰ","Esim;":"⩳","Eta;":"Η","Euml":"Ë","Euml;":"Ë","Exists;":"∃","ExponentialE;":"ⅇ","Fcy;":"Ф","Ffr;":"𝔉","FilledSmallSquare;":"◼","FilledVerySmallSquare;":"▪","Fopf;":"𝔽","ForAll;":"∀","Fouriertrf;":"ℱ","Fscr;":"ℱ","GJcy;":"Ѓ","GT":">","GT;":">","Gamma;":"Γ","Gammad;":"Ϝ","Gbreve;":"Ğ","Gcedil;":"Ģ","Gcirc;":"Ĝ","Gcy;":"Г","Gdot;":"Ġ","Gfr;":"𝔊","Gg;":"⋙","Gopf;":"𝔾","GreaterEqual;":"≥","GreaterEqualLess;":"⋛","GreaterFullEqual;":"≧","GreaterGreater;":"⪢","GreaterLess;":"≷","GreaterSlantEqual;":"⩾","GreaterTilde;":"≳","Gscr;":"𝒢","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","Iacute;":"Í","Icirc":"Î","Icirc;":"Î","Icy;":"И","Idot;":"İ","Ifr;":"ℑ","Igrave":"Ì","Igrave;":"Ì","Im;":"ℑ","Imacr;":"Ī","ImaginaryI;":"ⅈ","Implies;":"⇒","Int;":"∬","Integral;":"∫","Intersection;":"⋂","InvisibleComma;":"⁣","InvisibleTimes;":"⁢","Iogon;":"Į","Iopf;":"𝕀","Iota;":"Ι","Iscr;":"ℐ","Itilde;":"Ĩ","Iukcy;":"І","Iuml":"Ï","Iuml;":"Ï","Jcirc;":"Ĵ","Jcy;":"Й","Jfr;":"𝔍","Jopf;":"𝕁","Jscr;":"𝒥","Jsercy;":"Ј","Jukcy;":"Є","KHcy;":"Х","KJcy;":"Ќ","Kappa;":"Κ","Kcedil;":"Ķ","Kcy;":"К","Kfr;":"𝔎","Kopf;":"𝕂","Kscr;":"𝒦","LJcy;":"Љ","LT":"<","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;":"𝔏","Ll;":"⋘","Lleftarrow;":"⇚","Lmidot;":"Ŀ","LongLeftArrow;":"⟵","LongLeftRightArrow;":"⟷","LongRightArrow;":"⟶","Longleftarrow;":"⟸","Longleftrightarrow;":"⟺","Longrightarrow;":"⟹","Lopf;":"𝕃","LowerLeftArrow;":"↙","LowerRightArrow;":"↘","Lscr;":"ℒ","Lsh;":"↰","Lstrok;":"Ł","Lt;":"≪","Map;":"⤅","Mcy;":"М","MediumSpace;":" ","Mellintrf;":"ℳ","Mfr;":"𝔐","MinusPlus;":"∓","Mopf;":"𝕄","Mscr;":"ℳ","Mu;":"Μ","NJcy;":"Њ","Nacute;":"Ń","Ncaron;":"Ň","Ncedil;":"Ņ","Ncy;":"Н","NegativeMediumSpace;":"​","NegativeThickSpace;":"​","NegativeThinSpace;":"​","NegativeVeryThinSpace;":"​","NestedGreaterGreater;":"≫","NestedLessLess;":"≪","NewLine;":"\n","Nfr;":"𝔑","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;":"𝒩","Ntilde":"Ñ","Ntilde;":"Ñ","Nu;":"Ν","OElig;":"Œ","Oacute":"Ó","Oacute;":"Ó","Ocirc":"Ô","Ocirc;":"Ô","Ocy;":"О","Odblac;":"Ő","Ofr;":"𝔒","Ograve":"Ò","Ograve;":"Ò","Omacr;":"Ō","Omega;":"Ω","Omicron;":"Ο","Oopf;":"𝕆","OpenCurlyDoubleQuote;":"“","OpenCurlyQuote;":"‘","Or;":"⩔","Oscr;":"𝒪","Oslash":"Ø","Oslash;":"Ø","Otilde":"Õ","Otilde;":"Õ","Otimes;":"⨷","Ouml":"Ö","Ouml;":"Ö","OverBar;":"‾","OverBrace;":"⏞","OverBracket;":"⎴","OverParenthesis;":"⏜","PartialD;":"∂","Pcy;":"П","Pfr;":"𝔓","Phi;":"Φ","Pi;":"Π","PlusMinus;":"±","Poincareplane;":"ℌ","Popf;":"ℙ","Pr;":"⪻","Precedes;":"≺","PrecedesEqual;":"⪯","PrecedesSlantEqual;":"≼","PrecedesTilde;":"≾","Prime;":"″","Product;":"∏","Proportion;":"∷","Proportional;":"∝","Pscr;":"𝒫","Psi;":"Ψ","QUOT":"\"","QUOT;":"\"","Qfr;":"𝔔","Qopf;":"ℚ","Qscr;":"𝒬","RBarr;":"⤐","REG":"®","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;":"𝔖","ShortDownArrow;":"↓","ShortLeftArrow;":"←","ShortRightArrow;":"→","ShortUpArrow;":"↑","Sigma;":"Σ","SmallCircle;":"∘","Sopf;":"𝕊","Sqrt;":"√","Square;":"□","SquareIntersection;":"⊓","SquareSubset;":"⊏","SquareSubsetEqual;":"⊑","SquareSuperset;":"⊐","SquareSupersetEqual;":"⊒","SquareUnion;":"⊔","Sscr;":"𝒮","Star;":"⋆","Sub;":"⋐","Subset;":"⋐","SubsetEqual;":"⊆","Succeeds;":"≻","SucceedsEqual;":"⪰","SucceedsSlantEqual;":"≽","SucceedsTilde;":"≿","SuchThat;":"∋","Sum;":"∑","Sup;":"⋑","Superset;":"⊃","SupersetEqual;":"⊇","Supset;":"⋑","THORN":"Þ","THORN;":"Þ","TRADE;":"™","TSHcy;":"Ћ","TScy;":"Ц","Tab;":"\t","Tau;":"Τ","Tcaron;":"Ť","Tcedil;":"Ţ","Tcy;":"Т","Tfr;":"𝔗","Therefore;":"∴","Theta;":"Θ","ThickSpace;":"  ","ThinSpace;":" ","Tilde;":"∼","TildeEqual;":"≃","TildeFullEqual;":"≅","TildeTilde;":"≈","Topf;":"𝕋","TripleDot;":"⃛","Tscr;":"𝒯","Tstrok;":"Ŧ","Uacute":"Ú","Uacute;":"Ú","Uarr;":"↟","Uarrocir;":"⥉","Ubrcy;":"Ў","Ubreve;":"Ŭ","Ucirc":"Û","Ucirc;":"Û","Ucy;":"У","Udblac;":"Ű","Ufr;":"𝔘","Ugrave":"Ù","Ugrave;":"Ù","Umacr;":"Ū","UnderBar;":"_","UnderBrace;":"⏟","UnderBracket;":"⎵","UnderParenthesis;":"⏝","Union;":"⋃","UnionPlus;":"⊎","Uogon;":"Ų","Uopf;":"𝕌","UpArrow;":"↑","UpArrowBar;":"⤒","UpArrowDownArrow;":"⇅","UpDownArrow;":"↕","UpEquilibrium;":"⥮","UpTee;":"⊥","UpTeeArrow;":"↥","Uparrow;":"⇑","Updownarrow;":"⇕","UpperLeftArrow;":"↖","UpperRightArrow;":"↗","Upsi;":"ϒ","Upsilon;":"Υ","Uring;":"Ů","Uscr;":"𝒰","Utilde;":"Ũ","Uuml":"Ü","Uuml;":"Ü","VDash;":"⊫","Vbar;":"⫫","Vcy;":"В","Vdash;":"⊩","Vdashl;":"⫦","Vee;":"⋁","Verbar;":"‖","Vert;":"‖","VerticalBar;":"∣","VerticalLine;":"|","VerticalSeparator;":"❘","VerticalTilde;":"≀","VeryThinSpace;":" ","Vfr;":"𝔙","Vopf;":"𝕍","Vscr;":"𝒱","Vvdash;":"⊪","Wcirc;":"Ŵ","Wedge;":"⋀","Wfr;":"𝔚","Wopf;":"𝕎","Wscr;":"𝒲","Xfr;":"𝔛","Xi;":"Ξ","Xopf;":"𝕏","Xscr;":"𝒳","YAcy;":"Я","YIcy;":"Ї","YUcy;":"Ю","Yacute":"Ý","Yacute;":"Ý","Ycirc;":"Ŷ","Ycy;":"Ы","Yfr;":"𝔜","Yopf;":"𝕐","Yscr;":"𝒴","Yuml;":"Ÿ","ZHcy;":"Ж","Zacute;":"Ź","Zcaron;":"Ž","Zcy;":"З","Zdot;":"Ż","ZeroWidthSpace;":"​","Zeta;":"Ζ","Zfr;":"ℨ","Zopf;":"ℤ","Zscr;":"𝒵","aacute":"á","aacute;":"á","abreve;":"ă","ac;":"∾","acE;":"∾̳","acd;":"∿","acirc":"â","acirc;":"â","acute":"´","acute;":"´","acy;":"а","aelig":"æ","aelig;":"æ","af;":"⁡","afr;":"𝔞","agrave":"à","agrave;":"à","alefsym;":"ℵ","aleph;":"ℵ","alpha;":"α","amacr;":"ā","amalg;":"⨿","amp":"&","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;":"𝕒","ap;":"≈","apE;":"⩰","apacir;":"⩯","ape;":"≊","apid;":"≋","apos;":"'","approx;":"≈","approxeq;":"≊","aring":"å","aring;":"å","ascr;":"𝒶","ast;":"*","asymp;":"≈","asympeq;":"≍","atilde":"ã","atilde;":"ã","auml":"ä","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;":"𝔟","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;":"𝕓","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":"¦","brvbar;":"¦","bscr;":"𝒷","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","ccedil;":"ç","ccirc;":"ĉ","ccups;":"⩌","ccupssm;":"⩐","cdot;":"ċ","cedil":"¸","cedil;":"¸","cemptyv;":"⦲","cent":"¢","cent;":"¢","centerdot;":"·","cfr;":"𝔠","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;":"𝕔","coprod;":"∐","copy":"©","copy;":"©","copysr;":"℗","crarr;":"↵","cross;":"✗","cscr;":"𝒸","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":"¤","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":"°","deg;":"°","delta;":"δ","demptyv;":"⦱","dfisht;":"⥿","dfr;":"𝔡","dharl;":"⇃","dharr;":"⇂","diam;":"⋄","diamond;":"⋄","diamondsuit;":"♦","diams;":"♦","die;":"¨","digamma;":"ϝ","disin;":"⋲","div;":"÷","divide":"÷","divide;":"÷","divideontimes;":"⋇","divonx;":"⋇","djcy;":"ђ","dlcorn;":"⌞","dlcrop;":"⌍","dollar;":"$","dopf;":"𝕕","dot;":"˙","doteq;":"≐","doteqdot;":"≑","dotminus;":"∸","dotplus;":"∔","dotsquare;":"⊡","doublebarwedge;":"⌆","downarrow;":"↓","downdownarrows;":"⇊","downharpoonleft;":"⇃","downharpoonright;":"⇂","drbkarow;":"⤐","drcorn;":"⌟","drcrop;":"⌌","dscr;":"𝒹","dscy;":"ѕ","dsol;":"⧶","dstrok;":"đ","dtdot;":"⋱","dtri;":"▿","dtrif;":"▾","duarr;":"⇵","duhar;":"⥯","dwangle;":"⦦","dzcy;":"џ","dzigrarr;":"⟿","eDDot;":"⩷","eDot;":"≑","eacute":"é","eacute;":"é","easter;":"⩮","ecaron;":"ě","ecir;":"≖","ecirc":"ê","ecirc;":"ê","ecolon;":"≕","ecy;":"э","edot;":"ė","ee;":"ⅇ","efDot;":"≒","efr;":"𝔢","eg;":"⪚","egrave":"è","egrave;":"è","egs;":"⪖","egsdot;":"⪘","el;":"⪙","elinters;":"⏧","ell;":"ℓ","els;":"⪕","elsdot;":"⪗","emacr;":"ē","empty;":"∅","emptyset;":"∅","emptyv;":"∅","emsp13;":" ","emsp14;":" ","emsp;":" ","eng;":"ŋ","ensp;":" ","eogon;":"ę","eopf;":"𝕖","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","eth;":"ð","euml":"ë","euml;":"ë","euro;":"€","excl;":"!","exist;":"∃","expectation;":"ℰ","exponentiale;":"ⅇ","fallingdotseq;":"≒","fcy;":"ф","female;":"♀","ffilig;":"ffi","fflig;":"ff","ffllig;":"ffl","ffr;":"𝔣","filig;":"fi","fjlig;":"fj","flat;":"♭","fllig;":"fl","fltns;":"▱","fnof;":"ƒ","fopf;":"𝕗","forall;":"∀","fork;":"⋔","forkv;":"⫙","fpartint;":"⨍","frac12":"½","frac12;":"½","frac13;":"⅓","frac14":"¼","frac14;":"¼","frac15;":"⅕","frac16;":"⅙","frac18;":"⅛","frac23;":"⅔","frac25;":"⅖","frac34":"¾","frac34;":"¾","frac35;":"⅗","frac38;":"⅜","frac45;":"⅘","frac56;":"⅚","frac58;":"⅝","frac78;":"⅞","frasl;":"⁄","frown;":"⌢","fscr;":"𝒻","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;":"𝔤","gg;":"≫","ggg;":"⋙","gimel;":"ℷ","gjcy;":"ѓ","gl;":"≷","glE;":"⪒","gla;":"⪥","glj;":"⪤","gnE;":"≩","gnap;":"⪊","gnapprox;":"⪊","gne;":"⪈","gneq;":"⪈","gneqq;":"≩","gnsim;":"⋧","gopf;":"𝕘","grave;":"`","gscr;":"ℊ","gsim;":"≳","gsime;":"⪎","gsiml;":"⪐","gt":">","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;":"𝔥","hksearow;":"⤥","hkswarow;":"⤦","hoarr;":"⇿","homtht;":"∻","hookleftarrow;":"↩","hookrightarrow;":"↪","hopf;":"𝕙","horbar;":"―","hscr;":"𝒽","hslash;":"ℏ","hstrok;":"ħ","hybull;":"⁃","hyphen;":"‐","iacute":"í","iacute;":"í","ic;":"⁣","icirc":"î","icirc;":"î","icy;":"и","iecy;":"е","iexcl":"¡","iexcl;":"¡","iff;":"⇔","ifr;":"𝔦","igrave":"ì","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;":"𝕚","iota;":"ι","iprod;":"⨼","iquest":"¿","iquest;":"¿","iscr;":"𝒾","isin;":"∈","isinE;":"⋹","isindot;":"⋵","isins;":"⋴","isinsv;":"⋳","isinv;":"∈","it;":"⁢","itilde;":"ĩ","iukcy;":"і","iuml":"ï","iuml;":"ï","jcirc;":"ĵ","jcy;":"й","jfr;":"𝔧","jmath;":"ȷ","jopf;":"𝕛","jscr;":"𝒿","jsercy;":"ј","jukcy;":"є","kappa;":"κ","kappav;":"ϰ","kcedil;":"ķ","kcy;":"к","kfr;":"𝔨","kgreen;":"ĸ","khcy;":"х","kjcy;":"ќ","kopf;":"𝕜","kscr;":"𝓀","lAarr;":"⇚","lArr;":"⇐","lAtail;":"⤛","lBarr;":"⤎","lE;":"≦","lEg;":"⪋","lHar;":"⥢","lacute;":"ĺ","laemptyv;":"⦴","lagran;":"ℒ","lambda;":"λ","lang;":"⟨","langd;":"⦑","langle;":"⟨","lap;":"⪅","laquo":"«","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;":"𝔩","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;":"𝕝","loplus;":"⨭","lotimes;":"⨴","lowast;":"∗","lowbar;":"_","loz;":"◊","lozenge;":"◊","lozf;":"⧫","lpar;":"(","lparlt;":"⦓","lrarr;":"⇆","lrcorner;":"⌟","lrhar;":"⇋","lrhard;":"⥭","lrm;":"‎","lrtri;":"⊿","lsaquo;":"‹","lscr;":"𝓁","lsh;":"↰","lsim;":"≲","lsime;":"⪍","lsimg;":"⪏","lsqb;":"[","lsquo;":"‘","lsquor;":"‚","lstrok;":"ł","lt":"<","lt;":"<","ltcc;":"⪦","ltcir;":"⩹","ltdot;":"⋖","lthree;":"⋋","ltimes;":"⋉","ltlarr;":"⥶","ltquest;":"⩻","ltrPar;":"⦖","ltri;":"◃","ltrie;":"⊴","ltrif;":"◂","lurdshar;":"⥊","luruhar;":"⥦","lvertneqq;":"≨︀","lvnE;":"≨︀","mDDot;":"∺","macr":"¯","macr;":"¯","male;":"♂","malt;":"✠","maltese;":"✠","map;":"↦","mapsto;":"↦","mapstodown;":"↧","mapstoleft;":"↤","mapstoup;":"↥","marker;":"▮","mcomma;":"⨩","mcy;":"м","mdash;":"—","measuredangle;":"∡","mfr;":"𝔪","mho;":"℧","micro":"µ","micro;":"µ","mid;":"∣","midast;":"*","midcir;":"⫰","middot":"·","middot;":"·","minus;":"−","minusb;":"⊟","minusd;":"∸","minusdu;":"⨪","mlcp;":"⫛","mldr;":"…","mnplus;":"∓","models;":"⊧","mopf;":"𝕞","mp;":"∓","mscr;":"𝓂","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":" ","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;":"𝔫","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;":"𝕟","not":"¬","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;":"𝓃","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","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","oacute;":"ó","oast;":"⊛","ocir;":"⊚","ocirc":"ô","ocirc;":"ô","ocy;":"о","odash;":"⊝","odblac;":"ő","odiv;":"⨸","odot;":"⊙","odsold;":"⦼","oelig;":"œ","ofcir;":"⦿","ofr;":"𝔬","ogon;":"˛","ograve":"ò","ograve;":"ò","ogt;":"⧁","ohbar;":"⦵","ohm;":"Ω","oint;":"∮","olarr;":"↺","olcir;":"⦾","olcross;":"⦻","oline;":"‾","olt;":"⧀","omacr;":"ō","omega;":"ω","omicron;":"ο","omid;":"⦶","ominus;":"⊖","oopf;":"𝕠","opar;":"⦷","operp;":"⦹","oplus;":"⊕","or;":"∨","orarr;":"↻","ord;":"⩝","order;":"ℴ","orderof;":"ℴ","ordf":"ª","ordf;":"ª","ordm":"º","ordm;":"º","origof;":"⊶","oror;":"⩖","orslope;":"⩗","orv;":"⩛","oscr;":"ℴ","oslash":"ø","oslash;":"ø","osol;":"⊘","otilde":"õ","otilde;":"õ","otimes;":"⊗","otimesas;":"⨶","ouml":"ö","ouml;":"ö","ovbar;":"⌽","par;":"∥","para":"¶","para;":"¶","parallel;":"∥","parsim;":"⫳","parsl;":"⫽","part;":"∂","pcy;":"п","percnt;":"%","period;":".","permil;":"‰","perp;":"⊥","pertenk;":"‱","pfr;":"𝔭","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":"±","plusmn;":"±","plussim;":"⨦","plustwo;":"⨧","pm;":"±","pointint;":"⨕","popf;":"𝕡","pound":"£","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;":"𝓅","psi;":"ψ","puncsp;":" ","qfr;":"𝔮","qint;":"⨌","qopf;":"𝕢","qprime;":"⁗","qscr;":"𝓆","quaternions;":"ℍ","quatint;":"⨖","quest;":"?","questeq;":"≟","quot":"\"","quot;":"\"","rAarr;":"⇛","rArr;":"⇒","rAtail;":"⤜","rBarr;":"⤏","rHar;":"⥤","race;":"∽̱","racute;":"ŕ","radic;":"√","raemptyv;":"⦳","rang;":"⟩","rangd;":"⦒","range;":"⦥","rangle;":"⟩","raquo":"»","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":"®","reg;":"®","rfisht;":"⥽","rfloor;":"⌋","rfr;":"𝔯","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;":"𝕣","roplus;":"⨮","rotimes;":"⨵","rpar;":")","rpargt;":"⦔","rppolint;":"⨒","rrarr;":"⇉","rsaquo;":"›","rscr;":"𝓇","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":"§","sect;":"§","semi;":";","seswar;":"⤩","setminus;":"∖","setmn;":"∖","sext;":"✶","sfr;":"𝔰","sfrown;":"⌢","sharp;":"♯","shchcy;":"щ","shcy;":"ш","shortmid;":"∣","shortparallel;":"∥","shy":"­","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;":"𝕤","spades;":"♠","spadesuit;":"♠","spar;":"∥","sqcap;":"⊓","sqcaps;":"⊓︀","sqcup;":"⊔","sqcups;":"⊔︀","sqsub;":"⊏","sqsube;":"⊑","sqsubset;":"⊏","sqsubseteq;":"⊑","sqsup;":"⊐","sqsupe;":"⊒","sqsupset;":"⊐","sqsupseteq;":"⊒","squ;":"□","square;":"□","squarf;":"▪","squf;":"▪","srarr;":"→","sscr;":"𝓈","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;":"♪","sup1":"¹","sup1;":"¹","sup2":"²","sup2;":"²","sup3":"³","sup3;":"³","sup;":"⊃","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","szlig;":"ß","target;":"⌖","tau;":"τ","tbrk;":"⎴","tcaron;":"ť","tcedil;":"ţ","tcy;":"т","tdot;":"⃛","telrec;":"⌕","tfr;":"𝔱","there4;":"∴","therefore;":"∴","theta;":"θ","thetasym;":"ϑ","thetav;":"ϑ","thickapprox;":"≈","thicksim;":"∼","thinsp;":" ","thkap;":"≈","thksim;":"∼","thorn":"þ","thorn;":"þ","tilde;":"˜","times":"×","times;":"×","timesb;":"⊠","timesbar;":"⨱","timesd;":"⨰","tint;":"∭","toea;":"⤨","top;":"⊤","topbot;":"⌶","topcir;":"⫱","topf;":"𝕥","topfork;":"⫚","tosa;":"⤩","tprime;":"‴","trade;":"™","triangle;":"▵","triangledown;":"▿","triangleleft;":"◃","trianglelefteq;":"⊴","triangleq;":"≜","triangleright;":"▹","trianglerighteq;":"⊵","tridot;":"◬","trie;":"≜","triminus;":"⨺","triplus;":"⨹","trisb;":"⧍","tritime;":"⨻","trpezium;":"⏢","tscr;":"𝓉","tscy;":"ц","tshcy;":"ћ","tstrok;":"ŧ","twixt;":"≬","twoheadleftarrow;":"↞","twoheadrightarrow;":"↠","uArr;":"⇑","uHar;":"⥣","uacute":"ú","uacute;":"ú","uarr;":"↑","ubrcy;":"ў","ubreve;":"ŭ","ucirc":"û","ucirc;":"û","ucy;":"у","udarr;":"⇅","udblac;":"ű","udhar;":"⥮","ufisht;":"⥾","ufr;":"𝔲","ugrave":"ù","ugrave;":"ù","uharl;":"↿","uharr;":"↾","uhblk;":"▀","ulcorn;":"⌜","ulcorner;":"⌜","ulcrop;":"⌏","ultri;":"◸","umacr;":"ū","uml":"¨","uml;":"¨","uogon;":"ų","uopf;":"𝕦","uparrow;":"↑","updownarrow;":"↕","upharpoonleft;":"↿","upharpoonright;":"↾","uplus;":"⊎","upsi;":"υ","upsih;":"ϒ","upsilon;":"υ","upuparrows;":"⇈","urcorn;":"⌝","urcorner;":"⌝","urcrop;":"⌎","uring;":"ů","urtri;":"◹","uscr;":"𝓊","utdot;":"⋰","utilde;":"ũ","utri;":"▵","utrif;":"▴","uuarr;":"⇈","uuml":"ü","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;":"𝔳","vltri;":"⊲","vnsub;":"⊂⃒","vnsup;":"⊃⃒","vopf;":"𝕧","vprop;":"∝","vrtri;":"⊳","vscr;":"𝓋","vsubnE;":"⫋︀","vsubne;":"⊊︀","vsupnE;":"⫌︀","vsupne;":"⊋︀","vzigzag;":"⦚","wcirc;":"ŵ","wedbar;":"⩟","wedge;":"∧","wedgeq;":"≙","weierp;":"℘","wfr;":"𝔴","wopf;":"𝕨","wp;":"℘","wr;":"≀","wreath;":"≀","wscr;":"𝓌","xcap;":"⋂","xcirc;":"◯","xcup;":"⋃","xdtri;":"▽","xfr;":"𝔵","xhArr;":"⟺","xharr;":"⟷","xi;":"ξ","xlArr;":"⟸","xlarr;":"⟵","xmap;":"⟼","xnis;":"⋻","xodot;":"⨀","xopf;":"𝕩","xoplus;":"⨁","xotime;":"⨂","xrArr;":"⟹","xrarr;":"⟶","xscr;":"𝓍","xsqcup;":"⨆","xuplus;":"⨄","xutri;":"△","xvee;":"⋁","xwedge;":"⋀","yacute":"ý","yacute;":"ý","yacy;":"я","ycirc;":"ŷ","ycy;":"ы","yen":"¥","yen;":"¥","yfr;":"𝔶","yicy;":"ї","yopf;":"𝕪","yscr;":"𝓎","yucy;":"ю","yuml":"ÿ","yuml;":"ÿ","zacute;":"ź","zcaron;":"ž","zcy;":"з","zdot;":"ż","zeetrf;":"ℨ","zeta;":"ζ","zfr;":"𝔷","zhcy;":"ж","zigrarr;":"⇝","zopf;":"𝕫","zscr;":"𝓏","zwj;":"‍","zwnj;":"‌"}))); // #endregion const STATE_DATA = 0; const STATE_TAG_OPEN = 1; const STATE_END_TAG_OPEN = 2; const STATE_TAG_NAME = 3; const STATE_BEFORE_ATTRIBUTE_NAME = 4; const STATE_ATTRIBUTE_NAME = 5; const STATE_AFTER_ATTRIBUTE_NAME = 6; const STATE_BEFORE_ATTRIBUTE_VALUE = 7; const STATE_ATTRIBUTE_VALUE_DOUBLE_QUOTED = 8; const STATE_ATTRIBUTE_VALUE_SINGLE_QUOTED = 9; const STATE_ATTRIBUTE_VALUE_UNQUOTED = 10; const STATE_AFTER_ATTRIBUTE_VALUE_QUOTED = 11; const STATE_SELF_CLOSING_START_TAG = 12; const STATE_MARKUP_DECLARATION_OPEN = 13; const STATE_COMMENT_START = 14; const STATE_COMMENT_START_DASH = 15; const STATE_COMMENT = 16; const STATE_COMMENT_END_DASH = 17; const STATE_COMMENT_END = 18; const STATE_COMMENT_END_BANG = 19; const STATE_BOGUS_COMMENT = 20; const STATE_COMMENT_LESS_THAN_SIGN = 21; const STATE_COMMENT_LESS_THAN_SIGN_BANG = 22; const STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH = 23; const STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH = 24; const STATE_DOCTYPE = 25; const STATE_BEFORE_DOCTYPE_NAME = 26; const STATE_DOCTYPE_NAME = 27; const STATE_AFTER_DOCTYPE_NAME = 28; const STATE_AFTER_DOCTYPE_PUBLIC_KEYWORD = 29; const STATE_BEFORE_DOCTYPE_PUBLIC_IDENTIFIER = 30; const STATE_DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED = 31; const STATE_DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED = 32; const STATE_AFTER_DOCTYPE_PUBLIC_IDENTIFIER = 33; const STATE_BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS = 34; const STATE_AFTER_DOCTYPE_SYSTEM_KEYWORD = 35; const STATE_BEFORE_DOCTYPE_SYSTEM_IDENTIFIER = 36; const STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED = 37; const STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED = 38; const STATE_AFTER_DOCTYPE_SYSTEM_IDENTIFIER = 39; const STATE_BOGUS_DOCTYPE = 40; const STATE_CDATA_SECTION = 41; const STATE_CDATA_SECTION_BRACKET = 42; const STATE_CDATA_SECTION_END = 43; const STATE_RCDATA = 44; const STATE_RCDATA_LESS_THAN_SIGN = 45; const STATE_RCDATA_END_TAG_OPEN = 46; const STATE_RCDATA_END_TAG_NAME = 47; const STATE_RAWTEXT = 48; const STATE_RAWTEXT_LESS_THAN_SIGN = 49; const STATE_RAWTEXT_END_TAG_OPEN = 50; const STATE_RAWTEXT_END_TAG_NAME = 51; const STATE_SCRIPT_DATA = 52; const STATE_SCRIPT_DATA_LESS_THAN_SIGN = 53; const STATE_SCRIPT_DATA_END_TAG_OPEN = 54; const STATE_SCRIPT_DATA_END_TAG_NAME = 55; const STATE_SCRIPT_DATA_ESCAPE_START = 56; const STATE_SCRIPT_DATA_ESCAPE_START_DASH = 57; const STATE_SCRIPT_DATA_ESCAPED = 58; const STATE_SCRIPT_DATA_ESCAPED_DASH = 59; const STATE_SCRIPT_DATA_ESCAPED_DASH_DASH = 60; const STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN = 61; const STATE_SCRIPT_DATA_ESCAPED_END_TAG_OPEN = 62; const STATE_SCRIPT_DATA_ESCAPED_END_TAG_NAME = 63; const STATE_SCRIPT_DATA_DOUBLE_ESCAPE_START = 64; const STATE_SCRIPT_DATA_DOUBLE_ESCAPED = 65; const STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH = 66; const STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH = 67; const STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN = 68; const STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END = 69; const STATE_PLAINTEXT = 70; // https://html.spec.whatwg.org/multipage/parsing.html#character-reference-state const STATE_CHARACTER_REFERENCE = 71; // https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state const STATE_NAMED_CHARACTER_REFERENCE = 72; // https://html.spec.whatwg.org/multipage/parsing.html#ambiguous-ampersand-state const STATE_AMBIGUOUS_AMPERSAND = 73; // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-state const STATE_NUMERIC_CHARACTER_REFERENCE = 74; // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-start-state const STATE_HEXADECIMAL_CHARACTER_REFERENCE_START = 75; // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-start-state const STATE_DECIMAL_CHARACTER_REFERENCE_START = 76; // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-state const STATE_HEXADECIMAL_CHARACTER_REFERENCE = 77; // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-state const STATE_DECIMAL_CHARACTER_REFERENCE = 78; // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-end-state const STATE_NUMERIC_CHARACTER_REFERENCE_END = 79; const CC_TAB = 0x09; const CC_LF = 0x0a; const CC_FF = 0x0c; const CC_SPACE = 0x20; const CC_EXCLAMATION_MARK = 0x21; const CC_QUOTATION_MARK = 0x22; const CC_NUMBER_SIGN = 0x23; const CC_AMPERSAND = 0x26; const CC_APOSTROPHE = 0x27; const CC_HYPHEN_MINUS = 0x2d; const CC_SOLIDUS = 0x2f; const CC_SEMICOLON = 0x3b; const CC_LESS_THAN = 0x3c; const CC_EQUALS = 0x3d; const CC_GREATER_THAN = 0x3e; const CC_QUESTION_MARK = 0x3f; const CC_LEFT_SQUARE_BRACKET = 0x5b; const CC_RIGHT_SQUARE_BRACKET = 0x5d; const QUOTE_DOUBLE = 1; const QUOTE_SINGLE = 2; const QUOTE_NONE = 0; // Longest WHATWG named entity name *including* the trailing `;` is 32 chars // (`CounterClockwiseContourIntegral;`); without the trailing `;` it's 31. // Used to cap both the tokenizer's named-character-reference run length and // the decoder's longest-prefix backtrack so pathological inputs (e.g. `&` // followed by thousands of alphanumerics) stay linear-time. const MAX_ENTITY_NAME_LEN = 32; /** * @param {number} cc character code * @returns {boolean} is ascii alpha */ const isAsciiAlpha = (cc) => (cc >= 0x41 && cc <= 0x5a) || (cc >= 0x61 && cc <= 0x7a); /** * @param {number} cc character code * @returns {boolean} is ascii alphanumeric */ const isAsciiAlphanumeric = (cc) => isAsciiAlpha(cc) || (cc >= 0x30 && cc <= 0x39); /** * @param {number} cc character code * @returns {boolean} is ascii digit */ const isAsciiDigit = (cc) => cc >= 0x30 && cc <= 0x39; /** * @param {number} cc character code * @returns {boolean} is ascii hex digit */ const isAsciiHexDigit = (cc) => (cc >= 0x30 && cc <= 0x39) || (cc >= 0x41 && cc <= 0x46) || (cc >= 0x61 && cc <= 0x66); /** * @param {number} cc character code * @returns {boolean} is space */ const isSpace = (cc) => cc === CC_TAB || cc === CC_LF || cc === CC_FF || cc === CC_SPACE; /** * Severity of a tokenizer-detected parse error. `"warning"` is recoverable * (the tokenizer continued and the emitted token is still well-formed, e.g. * missing-attribute-value); `"error"` means the emitted token's offset * range is incomplete or does not match what the spec would produce, e.g. * eof-in-tag. * * Token offsets are JS string indices (UTF-16 code-unit offsets into * `input`), not byte offsets — relevant for inputs containing non-BMP * code points where one code point spans two indices. * @typedef {"warning" | "error"} ParseErrorSeverity */ /** * @typedef {object} HtmlTokenCallbacks * @property {(input: string, start: number, end: number, nameStart: number, nameEnd: number, selfClosing: boolean) => number=} openTag * @property {(input: string, start: number, end: number, nameStart: number, nameEnd: number) => number=} closeTag * @property {(input: string, start: number, end: number) => number=} text * @property {(input: string, nameStart: number, nameEnd: number, valueStart: number, valueEnd: number, quoteType: number) => number=} attribute * @property {(input: string, start: number, end: number) => number=} comment * @property {(input: string, start: number, end: number) => number=} doctype * @property {(input: string, code: string, start: number, end: number, severity: ParseErrorSeverity) => void=} parseError */ /** * @param {string} input input string * @param {number} pos current position * @param {HtmlTokenCallbacks} callbacks callbacks * @returns {number} final position */ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => { const len = input.length; let state = STATE_DATA; let returnState = STATE_DATA; let textStart = pos; let tagStart = pos; let tagNameStart = -1; let tagNameEnd = -1; let attrNameStart = -1; let attrNameEnd = -1; let attrValueStart = -1; let attrQuoteType = QUOTE_NONE; let commentStart = pos; let lastOpenTagName = ""; // Counter used by SCRIPT_DATA_DOUBLE_ESCAPE_{START,END} to detect whether // the ASCII-alpha run after `<` / ` { if (callbacks.parseError !== undefined) { callbacks.parseError(input, code, start, end, severity); } }; /** * @param {number} cc character code * @returns {boolean} is ascii lower alpha */ const isAsciiLowerAlpha = (cc) => cc >= 0x61 && cc <= 0x7a; /** * @param {number} cc character code * @returns {boolean} is ascii upper alpha */ const isAsciiUpperAlpha = (cc) => cc >= 0x41 && cc <= 0x5a; /** * @param {string} name tag name (lowercase) * @returns {number} content mode state for this tag, or STATE_DATA */ const getContentModeForTag = (name) => { switch (name) { case "textarea": case "title": return STATE_RCDATA; case "style": case "xmp": case "iframe": case "noembed": case "noframes": return STATE_RAWTEXT; case "script": return STATE_SCRIPT_DATA; case "plaintext": return STATE_PLAINTEXT; default: return STATE_DATA; } }; /** * @param {number} endPos end position */ const flushText = (endPos) => { if (textStart < endPos) { if (callbacks.text !== undefined) { callbacks.text(input, textStart, endPos); } // Advance `textStart` so a second `flushText` for the same span // (e.g. from the EOF handler after a tag-open transition already // flushed the pending text) is a no-op rather than a duplicate // emit. emitOpenTag / emitCloseTag overwrite `textStart` with // their own `nextPos` anyway, so this doesn't shift their start. textStart = endPos; } }; /** * @param {number} endPos end position * @returns {number} next position */ const emitAttribute = (endPos) => { // Default `nextPos` advances past the closing quote (if any) so the // state machine can continue when no `attribute` callback is provided. // When a callback IS provided, its return value overrides the default — // the callback is expected to do the same advance based on the // reported `quoteType`. let nextPos = attrQuoteType === QUOTE_NONE ? endPos : endPos + 1; if (callbacks.attribute !== undefined && attrNameStart !== -1) { nextPos = callbacks.attribute( input, attrNameStart, attrNameEnd, attrValueStart, attrValueStart === -1 ? -1 : endPos, attrQuoteType ); } if (attrNameStart !== -1) tagHasAttributes = true; attrNameStart = -1; attrValueStart = -1; attrQuoteType = QUOTE_NONE; return nextPos; }; /** * @param {number} endPos end position * @param {boolean} selfClosing is self closing * @returns {number} next position */ const emitOpenTag = (endPos, selfClosing) => { let nextPos = endPos; if (callbacks.openTag !== undefined) { nextPos = callbacks.openTag( input, tagStart, endPos, tagNameStart, tagNameEnd, selfClosing ); } if (!selfClosing) { lastOpenTagName = input.slice(tagNameStart, tagNameEnd).toLowerCase(); } tagHasAttributes = false; textStart = nextPos; return nextPos; }; /** * @param {number} endPos end position * @returns {number} next position */ const emitCloseTag = (endPos) => { // Per WHATWG: an end tag emitted with attributes is a parse error. if (tagHasAttributes) { reportError("end-tag-with-attributes", tagStart, endPos, "warning"); } let nextPos = endPos; if (callbacks.closeTag !== undefined) { nextPos = callbacks.closeTag( input, tagStart, endPos, tagNameStart, tagNameEnd ); } tagHasAttributes = false; textStart = nextPos; return nextPos; }; while (pos < len) { const cc = input.charCodeAt(pos); // TODO: We don't handle all states here yet. In the future we will need to handle // all of them, and when we move all the tokenizer we will remove it. switch (state) { // https://html.spec.whatwg.org/multipage/parsing.html#data-state case STATE_DATA: // Consume the next input character: // U+003C LESS-THAN SIGN (<) // Set the return state to the data state. Switch to the tag open state. if (cc === CC_LESS_THAN) { tagStart = pos; state = STATE_TAG_OPEN; pos++; } else if (cc === CC_AMPERSAND) { // U+0026 AMPERSAND (&) // Set the return state to the data state. Switch to the // character reference state. returnState = STATE_DATA; state = STATE_CHARACTER_REFERENCE; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state case STATE_TAG_OPEN: // Consume the next input character: // U+002F SOLIDUS (/) // Switch to the end tag open state. if (cc === CC_SOLIDUS) { state = STATE_END_TAG_OPEN; pos++; } else if (cc === CC_EXCLAMATION_MARK) { // U+0021 EXCLAMATION MARK (!) // Switch to the markup declaration open state. flushText(tagStart); commentStart = tagStart; state = STATE_MARKUP_DECLARATION_OPEN; pos++; } else if (isAsciiAlpha(cc)) { // ASCII alpha // Create a new start tag token, set its tag name to the empty string. // Reconsume in the tag name state. flushText(tagStart); tagNameStart = pos; state = STATE_TAG_NAME; // Reconsume } else if (cc === CC_QUESTION_MARK) { // U+003F QUESTION MARK (?) // This is an unexpected-question-mark-instead-of-tag-name parse error. // Create a comment token whose data is the empty string. Reconsume in the // bogus comment state. reportError( "unexpected-question-mark-instead-of-tag-name", pos, pos + 1, "warning" ); flushText(tagStart); commentStart = tagStart; state = STATE_BOGUS_COMMENT; // Reconsume — let the bogus-comment state consume the `?` // itself, matching the spec. } else { // Anything else // This is an invalid-first-character-of-tag-name parse error. Emit a U+003C // LESS-THAN SIGN character token. Reconsume in the data state. reportError( "invalid-first-character-of-tag-name", pos, pos + 1, "warning" ); state = STATE_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#end-tag-open-state case STATE_END_TAG_OPEN: // Consume the next input character: // ASCII alpha // Create a new end tag token, set its tag name to the empty string. // Reconsume in the tag name state. if (isAsciiAlpha(cc)) { flushText(tagStart); tagNameStart = pos; state = STATE_TAG_NAME; // Reconsume } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-end-tag-name parse error. Switch to the data state. reportError("missing-end-tag-name", pos, pos + 1, "warning"); state = STATE_DATA; pos++; } else { // Anything else // This is an invalid-first-character-of-tag-name parse error. Create a // comment token whose data is the empty string. Reconsume in the bogus // comment state. reportError( "invalid-first-character-of-tag-name", pos, pos + 1, "warning" ); flushText(tagStart); commentStart = tagStart; state = STATE_BOGUS_COMMENT; // Reconsume — let bogus-comment consume this char itself. } break; // https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state case STATE_TAG_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the before attribute name state. if (isSpace(cc)) { tagNameEnd = pos; state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // Switch to the self-closing start tag state. tagNameEnd = pos; state = STATE_SELF_CLOSING_START_TAG; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current tag token. tagNameEnd = pos; if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { const nextPos = emitOpenTag(pos + 1, false); state = nextPos > pos + 1 ? STATE_DATA : getContentModeForTag(lastOpenTagName); pos = nextPos; } } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state case STATE_BEFORE_ATTRIBUTE_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. // Reconsume so space is handled in BEFORE_ATTRIBUTE_NAME if (isSpace(cc)) { pos++; } else if (cc === CC_SOLIDUS || cc === CC_GREATER_THAN) { // U+002F SOLIDUS (/) // U+003E GREATER-THAN SIGN (>) // EOF // Reconsume in the after attribute name state. state = STATE_AFTER_ATTRIBUTE_NAME; // Reconsume } else if (cc === CC_EQUALS) { // U+003D EQUALS SIGN (=) // This is an unexpected-equals-sign-before-attribute-name parse // error. Start a new attribute. Switch to the attribute name state. reportError( "unexpected-equals-sign-before-attribute-name", pos, pos + 1, "warning" ); attrNameStart = pos; state = STATE_ATTRIBUTE_NAME; pos++; } else { // Anything else // Start a new attribute in the current tag token. Set that attribute name // and value to the empty string. Reconsume in the attribute name state. attrNameStart = pos; state = STATE_ATTRIBUTE_NAME; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state case STATE_ATTRIBUTE_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // U+002F SOLIDUS (/) // U+003E GREATER-THAN SIGN (>) // EOF // Reconsume in the after attribute name state. if (isSpace(cc) || cc === CC_SOLIDUS || cc === CC_GREATER_THAN) { attrNameEnd = pos; state = STATE_AFTER_ATTRIBUTE_NAME; // Reconsume } else if (cc === CC_EQUALS) { attrNameEnd = pos; state = STATE_BEFORE_ATTRIBUTE_VALUE; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-attribute-name-state case STATE_AFTER_ATTRIBUTE_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. if (isSpace(cc)) { pos++; } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // Switch to the self-closing start tag state. emitAttribute(pos); state = STATE_SELF_CLOSING_START_TAG; pos++; } else if (cc === CC_EQUALS) { // U+003D EQUALS SIGN (=) // Switch to the before attribute value state. state = STATE_BEFORE_ATTRIBUTE_VALUE; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current tag token. emitAttribute(pos); if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { const nextPos = emitOpenTag(pos + 1, false); state = nextPos > pos + 1 ? STATE_DATA : getContentModeForTag(lastOpenTagName); pos = nextPos; } } else { // Anything else // Start a new attribute in the current tag token. emitAttribute(pos); attrNameStart = pos; state = STATE_ATTRIBUTE_NAME; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-value-state case STATE_BEFORE_ATTRIBUTE_VALUE: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. if (isSpace(cc)) { pos++; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Switch to the attribute value (double-quoted) state. attrValueStart = pos + 1; attrQuoteType = QUOTE_DOUBLE; state = STATE_ATTRIBUTE_VALUE_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Switch to the attribute value (single-quoted) state. attrValueStart = pos + 1; attrQuoteType = QUOTE_SINGLE; state = STATE_ATTRIBUTE_VALUE_SINGLE_QUOTED; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-attribute-value parse error. Switch to the data // state. Emit the current tag token. The attribute is reported with // an empty value range pointing at the `>` so the open-tag offset range // still includes the `>`. reportError("missing-attribute-value", pos, pos + 1, "warning"); attrValueStart = pos; attrQuoteType = QUOTE_NONE; pos = emitAttribute(pos); if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { const nextPos = emitOpenTag(pos + 1, false); state = nextPos > pos + 1 ? STATE_DATA : getContentModeForTag(lastOpenTagName); pos = nextPos; } } else { // Anything else // Reconsume in the attribute value (unquoted) state. attrValueStart = pos; attrQuoteType = QUOTE_NONE; state = STATE_ATTRIBUTE_VALUE_UNQUOTED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(double-quoted)-state case STATE_ATTRIBUTE_VALUE_DOUBLE_QUOTED: // Consume the next input character: // U+0022 QUOTATION MARK (") // Switch to the after attribute value (quoted) state. if (cc === CC_QUOTATION_MARK) { pos = emitAttribute(pos); state = STATE_AFTER_ATTRIBUTE_VALUE_QUOTED; } else if (cc === CC_AMPERSAND) { // U+0026 AMPERSAND (&) // Set the return state to the attribute value (double-quoted) // state. Switch to the character reference state. returnState = STATE_ATTRIBUTE_VALUE_DOUBLE_QUOTED; state = STATE_CHARACTER_REFERENCE; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(single-quoted)-state case STATE_ATTRIBUTE_VALUE_SINGLE_QUOTED: // Consume the next input character: // U+0027 APOSTROPHE (') // Switch to the after attribute value (quoted) state. if (cc === CC_APOSTROPHE) { pos = emitAttribute(pos); state = STATE_AFTER_ATTRIBUTE_VALUE_QUOTED; } else if (cc === CC_AMPERSAND) { // U+0026 AMPERSAND (&) // Set the return state to the attribute value (single-quoted) // state. Switch to the character reference state. returnState = STATE_ATTRIBUTE_VALUE_SINGLE_QUOTED; state = STATE_CHARACTER_REFERENCE; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state case STATE_ATTRIBUTE_VALUE_UNQUOTED: if (isSpace(cc)) { pos = emitAttribute(pos); state = STATE_BEFORE_ATTRIBUTE_NAME; // Reconsume so space is handled in BEFORE_ATTRIBUTE_NAME } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-attribute-value parse error. Switch to the data state. // Emit the current tag token. pos = emitAttribute(pos); if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { const nextPos = emitOpenTag(pos + 1, false); state = nextPos > pos + 1 ? STATE_DATA : getContentModeForTag(lastOpenTagName); pos = nextPos; } } else if (cc === CC_AMPERSAND) { // U+0026 AMPERSAND (&) // Set the return state to the attribute value (unquoted) // state. Switch to the character reference state. returnState = STATE_ATTRIBUTE_VALUE_UNQUOTED; state = STATE_CHARACTER_REFERENCE; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-attribute-value-(quoted)-state case STATE_AFTER_ATTRIBUTE_VALUE_QUOTED: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the before attribute name state. if (isSpace(cc)) { state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // Switch to the self-closing start tag state. state = STATE_SELF_CLOSING_START_TAG; pos++; } else if (cc === CC_GREATER_THAN) { if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { const nextPos = emitOpenTag(pos + 1, false); state = nextPos > pos + 1 ? STATE_DATA : getContentModeForTag(lastOpenTagName); pos = nextPos; } } else { // Anything else // This is a missing-whitespace-between-attributes parse error. Reconsume in // the before attribute name state. reportError( "missing-whitespace-between-attributes", pos, pos + 1, "warning" ); state = STATE_BEFORE_ATTRIBUTE_NAME; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#self-closing-start-tag-state case STATE_SELF_CLOSING_START_TAG: // Consume the next input character: // U+003E GREATER-THAN SIGN (>) // Set the self-closing flag of the current tag token. Switch to the data // state. Emit the current tag token. if (cc === CC_GREATER_THAN) { if (input.charCodeAt(tagStart + 1) === CC_SOLIDUS) { state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { pos = emitOpenTag(pos + 1, true); state = STATE_DATA; } } else { // Anything else // This is an unexpected-solidus-in-tag parse error. Reconsume in the before // attribute name state. reportError("unexpected-solidus-in-tag", pos, pos + 1, "warning"); state = STATE_BEFORE_ATTRIBUTE_NAME; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state case STATE_MARKUP_DECLARATION_OPEN: // If the next few characters are: // Two U+002D HYPHEN-MINUS characters (-) // Consume those two characters, create a comment token whose data // is the empty string, and switch to the comment start state. if ( cc === CC_HYPHEN_MINUS && input.charCodeAt(pos + 1) === CC_HYPHEN_MINUS ) { pos += 2; commentStart = tagStart; state = STATE_COMMENT_START; } else if ( // ASCII case-insensitive match for the word "DOCTYPE" // Consume those characters and switch to the DOCTYPE state. (cc === 0x44 || cc === 0x64) /* D or d */ && (input.charCodeAt(pos + 1) | 0x20) === 0x6f /* o */ && (input.charCodeAt(pos + 2) | 0x20) === 0x63 /* c */ && (input.charCodeAt(pos + 3) | 0x20) === 0x74 /* t */ && (input.charCodeAt(pos + 4) | 0x20) === 0x79 /* y */ && (input.charCodeAt(pos + 5) | 0x20) === 0x70 /* p */ && (input.charCodeAt(pos + 6) | 0x20) === 0x65 /* e */ ) { pos += 7; commentStart = tagStart; state = STATE_DOCTYPE; } else if ( // The string "[CDATA[" (the five uppercase letters "CDATA" with a // U+005B LEFT SQUARE BRACKET character before and after) // Consume those characters and switch to the CDATA section state. cc === CC_LEFT_SQUARE_BRACKET && input.charCodeAt(pos + 1) === 0x43 /* C */ && input.charCodeAt(pos + 2) === 0x44 /* D */ && input.charCodeAt(pos + 3) === 0x41 /* A */ && input.charCodeAt(pos + 4) === 0x54 /* T */ && input.charCodeAt(pos + 5) === 0x41 /* A */ && input.charCodeAt(pos + 6) === CC_LEFT_SQUARE_BRACKET ) { pos += 7; commentStart = tagStart; state = STATE_CDATA_SECTION; } else { // Anything else // This is an incorrectly-opened-comment parse error. Create a comment token // whose data is the empty string. Switch to the bogus comment state (don't // consume anything in the current state). reportError("incorrectly-opened-comment", tagStart, pos, "warning"); commentStart = tagStart; state = STATE_BOGUS_COMMENT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-start-state case STATE_COMMENT_START: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment start dash state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_START_DASH; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-closing-of-empty-comment parse error. Switch to the // data state. Emit the current comment token. reportError( "abrupt-closing-of-empty-comment", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Reconsume in the comment state. state = STATE_COMMENT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-start-dash-state case STATE_COMMENT_START_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment end state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_END; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-closing-of-empty-comment parse error. Switch to the // data state. Emit the current comment token. reportError( "abrupt-closing-of-empty-comment", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append a U+002D HYPHEN-MINUS character (-) to the comment token's data. // Reconsume in the comment state. state = STATE_COMMENT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-state case STATE_COMMENT: // Consume the next input character: // U+003C LESS-THAN SIGN (<) // Append a U+003C LESS-THAN SIGN character to the comment token's data. Switch to the comment less-than sign state. if (cc === CC_LESS_THAN) { state = STATE_COMMENT_LESS_THAN_SIGN; pos++; } else if (cc === CC_HYPHEN_MINUS) { // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment end dash state. state = STATE_COMMENT_END_DASH; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-dash-state case STATE_COMMENT_END_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment end state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_END; pos++; } else { // Anything else // Append a U+002D HYPHEN-MINUS character (-) to the comment token's data. // Reconsume in the comment state. state = STATE_COMMENT; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-state case STATE_COMMENT_END: // Consume the next input character: // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current comment token. if (cc === CC_GREATER_THAN) { let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if (cc === CC_EXCLAMATION_MARK) { // U+0021 EXCLAMATION MARK (!) // Switch to the comment end bang state. state = STATE_COMMENT_END_BANG; pos++; } else if (cc === CC_HYPHEN_MINUS) { pos++; } else { // Anything else // Append two U+002D HYPHEN-MINUS characters (-) to the comment token's // data. Reconsume in the comment state. state = STATE_COMMENT; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-end-bang-state case STATE_COMMENT_END_BANG: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Append two U+002D HYPHEN-MINUS characters (-) and a U+0021 EXCLAMATION // MARK character (!) to the comment token's data. Switch to the comment end // dash state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_END_DASH; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an incorrectly-closed-comment parse error. Switch to the data // state. Emit the current comment token. reportError("incorrectly-closed-comment", pos, pos + 1, "warning"); let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append two U+002D HYPHEN-MINUS characters (-) and a U+0021 EXCLAMATION // MARK character (!) to the comment token's data. Reconsume in the comment // state. state = STATE_COMMENT; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#bogus-comment-state case STATE_BOGUS_COMMENT: // Consume the next input character: // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current comment token. if (cc === CC_GREATER_THAN) { let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-state case STATE_COMMENT_LESS_THAN_SIGN: // Consume the next input character: // U+0021 EXCLAMATION MARK (!) // Append the current input character to the comment token's data. Switch to // the comment less-than sign bang state. if (cc === CC_EXCLAMATION_MARK) { state = STATE_COMMENT_LESS_THAN_SIGN_BANG; pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Append the current input character to the comment token's data. pos++; } else { // Anything else // Reconsume in the comment state. state = STATE_COMMENT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-state case STATE_COMMENT_LESS_THAN_SIGN_BANG: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment less-than sign bang dash state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH; pos++; } else { // Anything else // Reconsume in the comment state. state = STATE_COMMENT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-dash-state case STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the comment less-than sign bang dash dash state. if (cc === CC_HYPHEN_MINUS) { state = STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH; pos++; } else { // Anything else // Reconsume in the comment end dash state. state = STATE_COMMENT_END_DASH; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#comment-less-than-sign-bang-dash-dash-state case STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH: // Consume the next input character: // U+003E GREATER-THAN SIGN (>) // EOF // Reconsume in the comment end state. // Anything else // This is a nested-comment parse error. Reconsume in the comment end state. if (cc !== CC_GREATER_THAN) { reportError("nested-comment", pos, pos + 1, "warning"); } state = STATE_COMMENT_END; // Reconsume break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-state case STATE_DOCTYPE: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the before DOCTYPE name state. if (isSpace(cc)) { state = STATE_BEFORE_DOCTYPE_NAME; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Reconsume in the before DOCTYPE name state. state = STATE_BEFORE_DOCTYPE_NAME; } else { // Anything else // This is a missing-whitespace-before-doctype-name parse error. Reconsume // in the before DOCTYPE name state. reportError( "missing-whitespace-before-doctype-name", pos, pos + 1, "warning" ); state = STATE_BEFORE_DOCTYPE_NAME; } break; // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-name-state case STATE_BEFORE_DOCTYPE_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. if (isSpace(cc)) { pos++; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Create a new DOCTYPE // token. Set the token's name to a U+FFFD REPLACEMENT CHARACTER character. // Switch to the DOCTYPE name state. state = STATE_DOCTYPE_NAME; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-doctype-name parse error. Create a new DOCTYPE token. // Set its force-quirks flag to on. Switch to the data state. Emit the // current token. reportError("missing-doctype-name", pos, pos + 1, "warning"); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // ASCII upper alpha // Create a new DOCTYPE token. Set the token's name to the lowercase version // of the current input character (add 0x0020 to the character's code // point). Switch to the DOCTYPE name state. // Anything else // Create a new DOCTYPE token. Set the token's name to the current input // character. Switch to the DOCTYPE name state. state = STATE_DOCTYPE_NAME; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-name-state case STATE_DOCTYPE_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the after DOCTYPE name state. if (isSpace(cc)) { state = STATE_AFTER_DOCTYPE_NAME; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Append a U+FFFD // REPLACEMENT CHARACTER character to the current DOCTYPE token's name. pos++; } else { // ASCII upper alpha // Append the lowercase version of the current input character (add 0x0020 // to the character's code point) to the current DOCTYPE token's name. // Anything else // Append the current input character to the current DOCTYPE token's name. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-name-state case STATE_AFTER_DOCTYPE_NAME: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if ( pos + 5 < len && (cc === 0x50 || cc === 0x70) /* P or p */ && (input.charCodeAt(pos + 1) | 0x20) === 0x75 /* u */ && (input.charCodeAt(pos + 2) | 0x20) === 0x62 /* b */ && (input.charCodeAt(pos + 3) | 0x20) === 0x6c /* l */ && (input.charCodeAt(pos + 4) | 0x20) === 0x69 /* i */ && (input.charCodeAt(pos + 5) | 0x20) === 0x63 /* c */ ) { // ASCII case-insensitive match for the word "PUBLIC" pos += 6; state = STATE_AFTER_DOCTYPE_PUBLIC_KEYWORD; } else if ( pos + 5 < len && (cc === 0x53 || cc === 0x73) /* S or s */ && (input.charCodeAt(pos + 1) | 0x20) === 0x79 /* y */ && (input.charCodeAt(pos + 2) | 0x20) === 0x73 /* s */ && (input.charCodeAt(pos + 3) | 0x20) === 0x74 /* t */ && (input.charCodeAt(pos + 4) | 0x20) === 0x65 /* e */ && (input.charCodeAt(pos + 5) | 0x20) === 0x6d /* m */ ) { // ASCII case-insensitive match for the word "SYSTEM" pos += 6; state = STATE_AFTER_DOCTYPE_SYSTEM_KEYWORD; } else { // Anything else // This is an invalid-character-sequence-after-doctype-name parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "invalid-character-sequence-after-doctype-name", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-keyword-state case STATE_AFTER_DOCTYPE_PUBLIC_KEYWORD: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the before DOCTYPE public identifier state. state = STATE_BEFORE_DOCTYPE_PUBLIC_IDENTIFIER; pos++; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // This is a missing-whitespace-after-doctype-public-keyword parse error. // Set the current DOCTYPE token's public identifier to the empty string // (not missing), then switch to the DOCTYPE public identifier // (double-quoted) state. reportError( "missing-whitespace-after-doctype-public-keyword", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // This is a missing-whitespace-after-doctype-public-keyword parse error. // Set the current DOCTYPE token's public identifier to the empty string // (not missing), then switch to the DOCTYPE public identifier // (single-quoted) state. reportError( "missing-whitespace-after-doctype-public-keyword", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-doctype-public-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "missing-doctype-public-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // This is a missing-quote-before-doctype-public-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-public-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-public-identifier-state case STATE_BEFORE_DOCTYPE_PUBLIC_IDENTIFIER: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. pos++; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Set the current DOCTYPE token's public identifier to the empty string // (not missing), then switch to the DOCTYPE public identifier // (double-quoted) state. state = STATE_DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Set the current DOCTYPE token's public identifier to the empty string // (not missing), then switch to the DOCTYPE public identifier // (single-quoted) state. state = STATE_DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-doctype-public-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "missing-doctype-public-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // This is a missing-quote-before-doctype-public-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-public-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(double-quoted)-state case STATE_DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED: // Consume the next input character: if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Switch to the after DOCTYPE public identifier state. state = STATE_AFTER_DOCTYPE_PUBLIC_IDENTIFIER; pos++; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Append a U+FFFD // REPLACEMENT CHARACTER character to the current DOCTYPE token's public // identifier. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-doctype-public-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "abrupt-doctype-public-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append the current input character to the current DOCTYPE token's public // identifier. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-public-identifier-(single-quoted)-state case STATE_DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED: // Consume the next input character: if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Switch to the after DOCTYPE public identifier state. state = STATE_AFTER_DOCTYPE_PUBLIC_IDENTIFIER; pos++; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Append a U+FFFD // REPLACEMENT CHARACTER character to the current DOCTYPE token's public // identifier. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-doctype-public-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "abrupt-doctype-public-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append the current input character to the current DOCTYPE token's public // identifier. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-public-identifier-state case STATE_AFTER_DOCTYPE_PUBLIC_IDENTIFIER: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the between DOCTYPE public and system identifiers state. state = STATE_BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // This is a missing-whitespace-between-doctype-public-and-system-identifiers // parse error. Set the current DOCTYPE token's system // identifier to the empty string (not missing), then switch // to the DOCTYPE system identifier (double-quoted) state. reportError( "missing-whitespace-between-doctype-public-and-system-identifiers", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // This is a missing-whitespace-between-doctype-public-and-system-identifiers // parse error. Set the current DOCTYPE token's system // identifier to the empty string (not missing), then switch // to the DOCTYPE system identifier (single-quoted) state. reportError( "missing-whitespace-between-doctype-public-and-system-identifiers", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED; pos++; } else { // Anything else // This is a missing-quote-before-doctype-system-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-system-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#between-doctype-public-and-system-identifiers-state case STATE_BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (double-quoted) state. state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (single-quoted) state. state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED; pos++; } else { // Anything else // This is a missing-quote-before-doctype-system-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-system-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-keyword-state case STATE_AFTER_DOCTYPE_SYSTEM_KEYWORD: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Switch to the before DOCTYPE system identifier state. state = STATE_BEFORE_DOCTYPE_SYSTEM_IDENTIFIER; pos++; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // This is a missing-whitespace-after-doctype-system-keyword parse error. // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (double-quoted) state. reportError( "missing-whitespace-after-doctype-system-keyword", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // This is a missing-whitespace-after-doctype-system-keyword parse error. // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (single-quoted) state. reportError( "missing-whitespace-after-doctype-system-keyword", pos, pos + 1, "warning" ); state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-doctype-system-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "missing-doctype-system-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // This is a missing-quote-before-doctype-system-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-system-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#before-doctype-system-identifier-state case STATE_BEFORE_DOCTYPE_SYSTEM_IDENTIFIER: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. pos++; } else if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (double-quoted) state. state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED; pos++; } else if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Set the current DOCTYPE token's system identifier to the empty string // (not missing), then switch to the DOCTYPE system identifier // (single-quoted) state. state = STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is a missing-doctype-system-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "missing-doctype-system-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // This is a missing-quote-before-doctype-system-identifier parse error. Set // the current DOCTYPE token's force-quirks flag to on. Reconsume in the // bogus DOCTYPE state. reportError( "missing-quote-before-doctype-system-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(double-quoted)-state case STATE_DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED: // Consume the next input character: if (cc === CC_QUOTATION_MARK) { // U+0022 QUOTATION MARK (") // Switch to the after DOCTYPE system identifier state. state = STATE_AFTER_DOCTYPE_SYSTEM_IDENTIFIER; pos++; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Append a U+FFFD // REPLACEMENT CHARACTER character to the current DOCTYPE token's system // identifier. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-doctype-system-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "abrupt-doctype-system-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append the current input character to the current DOCTYPE token's system // identifier. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#doctype-system-identifier-(single-quoted)-state case STATE_DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED: // Consume the next input character: if (cc === CC_APOSTROPHE) { // U+0027 APOSTROPHE (') // Switch to the after DOCTYPE system identifier state. state = STATE_AFTER_DOCTYPE_SYSTEM_IDENTIFIER; pos++; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Append a U+FFFD // REPLACEMENT CHARACTER character to the current DOCTYPE token's system // identifier. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // This is an abrupt-doctype-system-identifier parse error. Set the current // DOCTYPE token's force-quirks flag to on. Switch to the data state. Emit // the current DOCTYPE token. reportError( "abrupt-doctype-system-identifier", pos, pos + 1, "warning" ); let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Append the current input character to the current DOCTYPE token's system // identifier. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#after-doctype-system-identifier-state case STATE_AFTER_DOCTYPE_SYSTEM_IDENTIFIER: // Consume the next input character: if (isSpace(cc)) { // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // Ignore the character. pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the current DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // This is an unexpected-character-after-doctype-system-identifier parse // error. Reconsume in the bogus DOCTYPE state. (This does not set the // current DOCTYPE token's force-quirks flag to on.) reportError( "unexpected-character-after-doctype-system-identifier", pos, pos + 1, "warning" ); state = STATE_BOGUS_DOCTYPE; } break; // https://html.spec.whatwg.org/multipage/parsing.html#bogus-doctype-state case STATE_BOGUS_DOCTYPE: // Consume the next input character: if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. Emit the DOCTYPE token. let nextPos = pos + 1; if (callbacks.doctype !== undefined) { nextPos = callbacks.doctype(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else if (cc === 0x00) { // U+0000 NULL // This is an unexpected-null-character parse error. Ignore the character. pos++; } else { // Anything else // Ignore the character. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-state case STATE_CDATA_SECTION: // Consume the next input character: // U+005D RIGHT SQUARE BRACKET (]) // Switch to the CDATA section bracket state. if (cc === CC_RIGHT_SQUARE_BRACKET) { state = STATE_CDATA_SECTION_BRACKET; pos++; } else { // Anything else // Emit the current input character as a character token. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-bracket-state case STATE_CDATA_SECTION_BRACKET: // Consume the next input character: // U+005D RIGHT SQUARE BRACKET (]) // Switch to the CDATA section end state. if (cc === CC_RIGHT_SQUARE_BRACKET) { state = STATE_CDATA_SECTION_END; pos++; } else { // Anything else // Emit a U+005D RIGHT SQUARE BRACKET character token. Reconsume in the // CDATA section state. state = STATE_CDATA_SECTION; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#cdata-section-end-state case STATE_CDATA_SECTION_END: // Consume the next input character: // U+005D RIGHT SQUARE BRACKET (]) // Emit a U+005D RIGHT SQUARE BRACKET character token. if (cc === CC_RIGHT_SQUARE_BRACKET) { pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the data state. let nextPos = pos + 1; if (callbacks.comment !== undefined) { nextPos = callbacks.comment(input, commentStart, pos + 1); } state = STATE_DATA; textStart = nextPos; pos = nextPos; } else { // Anything else // Emit two U+005D RIGHT SQUARE BRACKET character tokens. Reconsume in the // CDATA section state. state = STATE_CDATA_SECTION; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-state case STATE_RCDATA: // Consume the next input character: // U+003C LESS-THAN SIGN (<) // Switch to the RCDATA less-than sign state. if (cc === CC_LESS_THAN) { tagStart = pos; state = STATE_RCDATA_LESS_THAN_SIGN; pos++; } else { // Anything else // Emit the current input character as a character token. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-less-than-sign-state case STATE_RCDATA_LESS_THAN_SIGN: // Consume the next input character: // U+002F SOLIDUS (/) // Switch to the RCDATA end tag open state. (Spec sets a // temporary buffer here; we track the would-be content via // offset ranges instead.) if (cc === CC_SOLIDUS) { state = STATE_RCDATA_END_TAG_OPEN; pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token. Reconsume in the RCDATA // state. state = STATE_RCDATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-end-tag-open-state case STATE_RCDATA_END_TAG_OPEN: // Consume the next input character: // ASCII alpha // Create a new end tag token, set its tag name to the empty string. // Reconsume in the RCDATA end tag name state. if (isAsciiAlpha(cc)) { tagNameStart = pos; state = STATE_RCDATA_END_TAG_NAME; // Reconsume } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token and a U+002F SOLIDUS // character token. Reconsume in the RCDATA state. state = STATE_RCDATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rcdata-end-tag-name-state case STATE_RCDATA_END_TAG_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // If the current end tag token is an appropriate end tag token, then switch // to the before attribute name state. Otherwise, treat it as per the // "anything else" entry below. if (isSpace(cc)) { tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else { state = STATE_RCDATA; // Reconsume } } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // If the current end tag token is an appropriate end tag token, then switch // to the self-closing start tag state. Otherwise, treat it as per the // "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_SELF_CLOSING_START_TAG; pos++; } else { state = STATE_RCDATA; // Reconsume } } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // If the current end tag token is an appropriate end tag token, then switch // to the data state and emit the current tag token. Otherwise, treat it as // per the "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { state = STATE_RCDATA; // Reconsume } } else if (isAsciiAlpha(cc)) { // ASCII upper alpha / ASCII lower alpha // Append the lowercase version of the current input character to the // current tag token's tag name. Append the current input character to // the temporary buffer. pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token, a U+002F SOLIDUS character // token, and a character token for each of the characters in the temporary // buffer (in the order they were added to the buffer). Reconsume in the // RCDATA state. state = STATE_RCDATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-state case STATE_RAWTEXT: // Consume the next input character: // U+003C LESS-THAN SIGN (<) // Switch to the RAWTEXT less-than sign state. if (cc === CC_LESS_THAN) { tagStart = pos; state = STATE_RAWTEXT_LESS_THAN_SIGN; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-less-than-sign-state case STATE_RAWTEXT_LESS_THAN_SIGN: // Consume the next input character: // U+002F SOLIDUS (/) // Switch to the RAWTEXT end tag open state. (Spec sets a // temporary buffer here; we track via offset ranges instead.) if (cc === CC_SOLIDUS) { state = STATE_RAWTEXT_END_TAG_OPEN; pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token. Reconsume in the RAWTEXT // state. state = STATE_RAWTEXT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-end-tag-open-state case STATE_RAWTEXT_END_TAG_OPEN: // Consume the next input character: // ASCII alpha // Create a new end tag token, set its tag name to the empty string. // Reconsume in the RAWTEXT end tag name state. if (isAsciiAlpha(cc)) { tagNameStart = pos; state = STATE_RAWTEXT_END_TAG_NAME; // Reconsume } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token and a U+002F SOLIDUS // character token. Reconsume in the RAWTEXT state. state = STATE_RAWTEXT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#rawtext-end-tag-name-state case STATE_RAWTEXT_END_TAG_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // If the current end tag token is an appropriate end tag token, then switch // to the before attribute name state. Otherwise, treat it as per the // "anything else" entry below. if (isSpace(cc)) { tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else { state = STATE_RAWTEXT; } } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // If the current end tag token is an appropriate end tag token, then switch // to the self-closing start tag state. Otherwise, treat it as per the // "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_SELF_CLOSING_START_TAG; pos++; } else { state = STATE_RAWTEXT; } } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // If the current end tag token is an appropriate end tag token, then switch // to the data state and emit the current tag token. Otherwise, treat it as // per the "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { state = STATE_RAWTEXT; } } else if (isAsciiAlpha(cc)) { // ASCII upper alpha / ASCII lower alpha // Append the lowercase version of the current input character to the // current tag token's tag name. Append the current input character to // the temporary buffer. pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token, a U+002F SOLIDUS character // token, and a character token for each of the characters in the temporary // buffer (in the order they were added to the buffer). Reconsume in the // RAWTEXT state. state = STATE_RAWTEXT; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-state case STATE_SCRIPT_DATA: // Consume the next input character: // U+003C LESS-THAN SIGN (<) // Switch to the script data less-than sign state. if (cc === CC_LESS_THAN) { tagStart = pos; state = STATE_SCRIPT_DATA_LESS_THAN_SIGN; pos++; } else { pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-less-than-sign-state case STATE_SCRIPT_DATA_LESS_THAN_SIGN: // Consume the next input character: // U+002F SOLIDUS (/) // Switch to the script data end tag open state. (Spec sets a // temporary buffer here; we track via offset ranges instead.) if (cc === CC_SOLIDUS) { state = STATE_SCRIPT_DATA_END_TAG_OPEN; pos++; } else if (cc === CC_EXCLAMATION_MARK) { // U+0021 EXCLAMATION MARK (!) // Switch to the script data escape start state. Emit a U+003C LESS-THAN // SIGN character token and a U+0021 EXCLAMATION MARK character token. state = STATE_SCRIPT_DATA_ESCAPE_START; pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token. Reconsume in the script // data state. state = STATE_SCRIPT_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-end-tag-open-state case STATE_SCRIPT_DATA_END_TAG_OPEN: // Consume the next input character: // ASCII alpha // Create a new end tag token, set its tag name to the empty string. // Reconsume in the script data end tag name state. if (isAsciiAlpha(cc)) { tagNameStart = pos; state = STATE_SCRIPT_DATA_END_TAG_NAME; // Reconsume } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token and a U+002F SOLIDUS // character token. Reconsume in the script data state. state = STATE_SCRIPT_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-end-tag-name-state case STATE_SCRIPT_DATA_END_TAG_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // If the current end tag token is an appropriate end tag token, then switch // to the before attribute name state. Otherwise, treat it as per the // "anything else" entry below. if (isSpace(cc)) { tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else { state = STATE_SCRIPT_DATA; } } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // If the current end tag token is an appropriate end tag token, then switch // to the self-closing start tag state. Otherwise, treat it as per the // "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_SELF_CLOSING_START_TAG; pos++; } else { state = STATE_SCRIPT_DATA; } } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // If the current end tag token is an appropriate end tag token, then switch // to the data state and emit the current tag token. Otherwise, treat it as // per the "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { state = STATE_SCRIPT_DATA; } } else if (isAsciiAlpha(cc)) { // ASCII upper alpha / ASCII lower alpha pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token, a U+002F SOLIDUS character // token, and a character token for each of the characters in the temporary // buffer (in the order they were added to the buffer). Reconsume in the // script data state. state = STATE_SCRIPT_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escape-start-state case STATE_SCRIPT_DATA_ESCAPE_START: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data escape start dash state. Emit a U+002D // HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_ESCAPE_START_DASH; pos++; } else { // Anything else // Reconsume in the script data state. state = STATE_SCRIPT_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escape-start-dash-state case STATE_SCRIPT_DATA_ESCAPE_START_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data escaped dash dash state. Emit a U+002D // HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_ESCAPED_DASH_DASH; pos++; } else { // Anything else // Reconsume in the script data state. state = STATE_SCRIPT_DATA; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-state case STATE_SCRIPT_DATA_ESCAPED: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data escaped dash state. Emit a U+002D HYPHEN-MINUS // character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_ESCAPED_DASH; pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data escaped less-than sign state. tagStart = pos; state = STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; pos++; } else { // Anything else // Emit the current input character as a character token. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-dash-state case STATE_SCRIPT_DATA_ESCAPED_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data escaped dash dash state. Emit a U+002D // HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_ESCAPED_DASH_DASH; pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data escaped less-than sign state. tagStart = pos; state = STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; pos++; } else { // Anything else // Switch to the script data escaped state. Emit the current input character // as a character token. state = STATE_SCRIPT_DATA_ESCAPED; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-dash-dash-state case STATE_SCRIPT_DATA_ESCAPED_DASH_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Emit a U+002D HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data escaped less-than sign state. tagStart = pos; state = STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the script data state. Emit a U+003E GREATER-THAN SIGN // character token. state = STATE_SCRIPT_DATA; pos++; } else { // Anything else // Switch to the script data escaped state. Emit the current input character // as a character token. state = STATE_SCRIPT_DATA_ESCAPED; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-less-than-sign-state case STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN: // Consume the next input character: // U+002F SOLIDUS (/) // Switch to the script data escaped end tag open state. // (Spec sets a temporary buffer; we track via offset ranges.) if (cc === CC_SOLIDUS) { state = STATE_SCRIPT_DATA_ESCAPED_END_TAG_OPEN; pos++; } else if (isAsciiAlpha(cc)) { // ASCII alpha // Set the temporary buffer to the empty string. Emit a U+003C LESS-THAN // SIGN character token. Reconsume in the script data double escape start // state. scriptMatch = 0; state = STATE_SCRIPT_DATA_DOUBLE_ESCAPE_START; // Reconsume } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token. Reconsume in the script // data escaped state. state = STATE_SCRIPT_DATA_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-end-tag-open-state case STATE_SCRIPT_DATA_ESCAPED_END_TAG_OPEN: // Consume the next input character: // ASCII alpha // Create a new end tag token, set its tag name to the empty string. // Reconsume in the script data escaped end tag name state. if (isAsciiAlpha(cc)) { tagNameStart = pos; state = STATE_SCRIPT_DATA_ESCAPED_END_TAG_NAME; // Reconsume } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token and a U+002F SOLIDUS // character token. Reconsume in the script data escaped state. state = STATE_SCRIPT_DATA_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-escaped-end-tag-name-state case STATE_SCRIPT_DATA_ESCAPED_END_TAG_NAME: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // If the current end tag token is an appropriate end tag token, then switch // to the before attribute name state. Otherwise, treat it as per the // "anything else" entry below. if (isSpace(cc)) { tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_BEFORE_ATTRIBUTE_NAME; pos++; } else { state = STATE_SCRIPT_DATA_ESCAPED; } } else if (cc === CC_SOLIDUS) { // U+002F SOLIDUS (/) // If the current end tag token is an appropriate end tag token, then switch // to the self-closing start tag state. Otherwise, treat it as per the // "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_SELF_CLOSING_START_TAG; pos++; } else { state = STATE_SCRIPT_DATA_ESCAPED; } } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // If the current end tag token is an appropriate end tag token, then switch // to the data state and emit the current tag token. Otherwise, treat it as // per the "anything else" entry below. tagNameEnd = pos; if ( input.slice(tagNameStart, tagNameEnd).toLowerCase() === lastOpenTagName ) { flushText(tagStart); state = STATE_DATA; pos = emitCloseTag(pos + 1); } else { state = STATE_SCRIPT_DATA_ESCAPED; } } else if (isAsciiAlpha(cc)) { // ASCII upper alpha / ASCII lower alpha pos++; } else { // Anything else // Emit a U+003C LESS-THAN SIGN character token, a U+002F SOLIDUS character // token, and a character token for each of the characters in the temporary // buffer (in the order they were added to the buffer). Reconsume in the // script data escaped state. state = STATE_SCRIPT_DATA_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escape-start-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPE_START: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // U+002F SOLIDUS (/) // U+003E GREATER-THAN SIGN (>) // If the temporary buffer is the string "script", then switch to the script // data double escaped state. Otherwise, switch to the script data escaped // state. Emit the current input character as a character token. if (isSpace(cc) || cc === CC_SOLIDUS || cc === CC_GREATER_THAN) { state = scriptMatch === 6 ? STATE_SCRIPT_DATA_DOUBLE_ESCAPED : STATE_SCRIPT_DATA_ESCAPED; pos++; } else if (isAsciiUpperAlpha(cc) || isAsciiLowerAlpha(cc)) { // ASCII alpha — advance the `"script"` match counter if the // lowercase form matches the next expected char, otherwise // snap to the sentinel so further chars can't revive a // match. No buffer allocation. const lower = isAsciiUpperAlpha(cc) ? cc + 0x20 : cc; if (scriptMatch < 6 && lower === "script".charCodeAt(scriptMatch)) { scriptMatch++; } else { scriptMatch = 7; } pos++; } else { // Anything else // Reconsume in the script data escaped state. state = STATE_SCRIPT_DATA_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPED: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data double escaped dash state. Emit a U+002D // HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH; pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data double escaped less-than sign state. Emit a // U+003C LESS-THAN SIGN character token. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; pos++; } else { // Anything else // Emit the current input character as a character token. pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-dash-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Switch to the script data double escaped dash dash state. Emit a U+002D // HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH; pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data double escaped less-than sign state. Emit a // U+003C LESS-THAN SIGN character token. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; pos++; } else { // Anything else // Switch to the script data double escaped state. Emit the current input // character as a character token. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-dash-dash-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH: // Consume the next input character: // U+002D HYPHEN-MINUS (-) // Emit a U+002D HYPHEN-MINUS character token. if (cc === CC_HYPHEN_MINUS) { pos++; } else if (cc === CC_LESS_THAN) { // U+003C LESS-THAN SIGN (<) // Switch to the script data double escaped less-than sign state. Emit a // U+003C LESS-THAN SIGN character token. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN; pos++; } else if (cc === CC_GREATER_THAN) { // U+003E GREATER-THAN SIGN (>) // Switch to the script data state. Emit a U+003E GREATER-THAN SIGN // character token. state = STATE_SCRIPT_DATA; pos++; } else { // Anything else // Switch to the script data double escaped state. Emit the current input // character as a character token. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED; pos++; } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escaped-less-than-sign-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN: // Consume the next input character: // U+002F SOLIDUS (/) // Set the temporary buffer to the empty string. Switch to the script data // double escape end state. Emit a U+002F SOLIDUS character token. if (cc === CC_SOLIDUS) { scriptMatch = 0; state = STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END; pos++; } else { // Anything else // Reconsume in the script data double escaped state. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#script-data-double-escape-end-state case STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END: // Consume the next input character: // U+0009 CHARACTER TABULATION (tab) // U+000A LINE FEED (LF) // U+000C FORM FEED (FF) // U+0020 SPACE // U+002F SOLIDUS (/) // U+003E GREATER-THAN SIGN (>) // If the temporary buffer is the string "script", then switch to the script // data escaped state. Otherwise, switch to the script data double escaped // state. Emit the current input character as a character token. if (isSpace(cc) || cc === CC_SOLIDUS || cc === CC_GREATER_THAN) { state = scriptMatch === 6 ? STATE_SCRIPT_DATA_ESCAPED : STATE_SCRIPT_DATA_DOUBLE_ESCAPED; pos++; } else if (isAsciiUpperAlpha(cc) || isAsciiLowerAlpha(cc)) { // ASCII alpha — advance the `"script"` match counter if the // lowercase form matches the next expected char, otherwise // snap to the sentinel so further chars can't revive a // match. No buffer allocation. const lower = isAsciiUpperAlpha(cc) ? cc + 0x20 : cc; if (scriptMatch < 6 && lower === "script".charCodeAt(scriptMatch)) { scriptMatch++; } else { scriptMatch = 7; } pos++; } else { // Anything else // Reconsume in the script data double escaped state. state = STATE_SCRIPT_DATA_DOUBLE_ESCAPED; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#plaintext-state case STATE_PLAINTEXT: // Consume the next input character: // Anything else // Emit the current input character as a character token. pos++; break; // https://html.spec.whatwg.org/multipage/parsing.html#character-reference-state case STATE_CHARACTER_REFERENCE: // Set the temporary buffer to the empty string. Append a U+0026 // AMPERSAND (&) character to the temporary buffer. // Consume the next input character: if (isAsciiAlphanumeric(cc)) { // ASCII alphanumeric // Reconsume in the named character reference state. state = STATE_NAMED_CHARACTER_REFERENCE; // Reconsume } else if (cc === CC_NUMBER_SIGN) { // U+0023 NUMBER SIGN (#) // Append the current input character to the temporary buffer. // Switch to the numeric character reference state. state = STATE_NUMERIC_CHARACTER_REFERENCE; pos++; } else { // Anything else // Flush code points consumed as a character reference. // Reconsume in the return state. state = returnState; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state case STATE_NAMED_CHARACTER_REFERENCE: { // Consume the maximum number of characters possible where the // consumed characters are one of the identifiers in the first // column of the named character references table. // // We measure the longest run of ASCII alphanumeric characters // (capped at MAX_ENTITY_NAME_LEN - 1 since the optional `;` is // handled separately), then walk that run from longest to // shortest looking for the first prefix that exists in the // entity table (with a trailing `;` if present, otherwise the // legacy bare form). let runLen = 0; while ( pos + runLen < len && isAsciiAlphanumeric(input.charCodeAt(pos + runLen)) && runLen < MAX_ENTITY_NAME_LEN - 1 ) { runLen++; } const hasSemicolon = pos + runLen < len && input.charCodeAt(pos + runLen) === CC_SEMICOLON; namedEntityConsumed = 0; for (let n = runLen; n > 0; n--) { // Try with trailing `;` first if one is present after the run. if (n === runLen && hasSemicolon) { const withSemi = `${input.slice(pos, pos + n)};`; if (HTML_ENTITIES[withSemi] !== undefined) { namedEntityConsumed = n + 1; break; } } const bare = input.slice(pos, pos + n); if (HTML_ENTITIES[bare] !== undefined) { namedEntityConsumed = n; break; } } if (namedEntityConsumed > 0) { pos += namedEntityConsumed; state = returnState; } else { // No match — flush code points consumed as a character // reference. Switch to the ambiguous ampersand state. state = STATE_AMBIGUOUS_AMPERSAND; } break; } // https://html.spec.whatwg.org/multipage/parsing.html#ambiguous-ampersand-state case STATE_AMBIGUOUS_AMPERSAND: // Consume the next input character: if (isAsciiAlphanumeric(cc)) { // ASCII alphanumeric // If the character reference was consumed as part of an // attribute, then append the current input character to the // current attribute's value. Otherwise, emit the current // input character as a character token. pos++; } else if (cc === CC_SEMICOLON) { // U+003B SEMICOLON (;) // This is an unknown-named-character-reference parse error. // Reconsume in the return state. reportError( "unknown-named-character-reference", pos, pos + 1, "warning" ); state = returnState; // Reconsume } else { // Anything else // Reconsume in the return state. state = returnState; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-state case STATE_NUMERIC_CHARACTER_REFERENCE: // Set the character reference code to zero (0). // Consume the next input character: if (cc === 0x78 || cc === 0x58) { // U+0078 LATIN SMALL LETTER X // U+0058 LATIN CAPITAL LETTER X // Append the current input character to the temporary // buffer. Switch to the hexadecimal character reference // start state. state = STATE_HEXADECIMAL_CHARACTER_REFERENCE_START; pos++; } else { // Anything else // Reconsume in the decimal character reference start state. state = STATE_DECIMAL_CHARACTER_REFERENCE_START; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-start-state case STATE_HEXADECIMAL_CHARACTER_REFERENCE_START: // Consume the next input character: // ASCII hex digit: reconsume in the hexadecimal character reference state. // Anything else: absence-of-digits-in-numeric-character-reference parse // error. Flush code points consumed as a character reference. Reconsume // in the return state. if (isAsciiHexDigit(cc)) { state = STATE_HEXADECIMAL_CHARACTER_REFERENCE; } else { reportError( "absence-of-digits-in-numeric-character-reference", pos, pos + 1, "warning" ); state = returnState; } // Reconsume break; // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-start-state case STATE_DECIMAL_CHARACTER_REFERENCE_START: // Consume the next input character: // ASCII digit: reconsume in the decimal character reference state. // Anything else: absence-of-digits-in-numeric-character-reference parse // error. Flush code points consumed as a character reference. Reconsume // in the return state. if (isAsciiDigit(cc)) { state = STATE_DECIMAL_CHARACTER_REFERENCE; } else { reportError( "absence-of-digits-in-numeric-character-reference", pos, pos + 1, "warning" ); state = returnState; } // Reconsume break; // https://html.spec.whatwg.org/multipage/parsing.html#hexadecimal-character-reference-state case STATE_HEXADECIMAL_CHARACTER_REFERENCE: // Consume the next input character: if (isAsciiHexDigit(cc)) { // ASCII digit / upper hex / lower hex // Multiply the character reference code by 16. Add a numeric // version of the current input character to the character // reference code. pos++; } else if (cc === CC_SEMICOLON) { // U+003B SEMICOLON // Switch to the numeric character reference end state. state = STATE_NUMERIC_CHARACTER_REFERENCE_END; pos++; } else { // Anything else // This is a missing-semicolon-after-character-reference // parse error. Reconsume in the numeric character reference // end state. reportError( "missing-semicolon-after-character-reference", pos, pos + 1, "warning" ); state = STATE_NUMERIC_CHARACTER_REFERENCE_END; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#decimal-character-reference-state case STATE_DECIMAL_CHARACTER_REFERENCE: // Consume the next input character: if (isAsciiDigit(cc)) { // ASCII digit // Multiply the character reference code by 10. Add a numeric // version of the current input character (subtract 0x0030 // from the character's code point) to the character reference // code. pos++; } else if (cc === CC_SEMICOLON) { // U+003B SEMICOLON // Switch to the numeric character reference end state. state = STATE_NUMERIC_CHARACTER_REFERENCE_END; pos++; } else { // Anything else // This is a missing-semicolon-after-character-reference // parse error. Reconsume in the numeric character reference // end state. reportError( "missing-semicolon-after-character-reference", pos, pos + 1, "warning" ); state = STATE_NUMERIC_CHARACTER_REFERENCE_END; // Reconsume } break; // https://html.spec.whatwg.org/multipage/parsing.html#numeric-character-reference-end-state case STATE_NUMERIC_CHARACTER_REFERENCE_END: // Check the character reference code (validation omitted for // the scanner — we don't decode, just skip past the entity). // Flush code points consumed as a character reference. // Switch to the return state. state = returnState; // Reconsume break; /* istanbul ignore next -- @preserve: defensive fallback, all states are explicit above */ default: pos++; } } // Handle EOF in non-data states per the WHATWG spec. // // Each in-progress comment / doctype / cdata / tag emits its partial // token range plus a corresponding `eof-in-X` parse error. Severity is // `"error"` because the emitted token offset range is incomplete (missing // trailing `-->`, `>`, `]]>`, etc.). For data / `<` / `= STATE_CHARACTER_REFERENCE && state <= STATE_NUMERIC_CHARACTER_REFERENCE_END ) { state = returnState; } if ( (state >= STATE_TAG_NAME && state <= STATE_SELF_CLOSING_START_TAG) || state === STATE_RCDATA_END_TAG_NAME || state === STATE_RAWTEXT_END_TAG_NAME || state === STATE_SCRIPT_DATA_END_TAG_NAME || state === STATE_SCRIPT_DATA_ESCAPED_END_TAG_NAME ) { // EOF mid-tag — emit the partial open/close tag at EOF so the // consumer still sees the tag. This is a deliberate deviation // from the spec's per-character emission model: rather than // dropping the in-progress tag, we emit its offset range up to EOF. reportError("eof-in-tag", len, len, "error"); // If we hit EOF mid-attribute-name, the name runs to EOF. Set // attrNameEnd here so the emitted attribute range is valid. if (state === STATE_ATTRIBUTE_NAME && attrNameStart !== -1) { attrNameEnd = len; } if (attrNameStart !== -1) emitAttribute(len); // If we hit EOF before the tag-name end was recorded, the name runs // to EOF. `tagNameEnd` may carry over from a previously emitted tag, // so reset it whenever it's missing or stale (less than `tagNameStart`) // — covers `x= STATE_COMMENT_START && state <= STATE_BOGUS_COMMENT) || (state >= STATE_COMMENT_LESS_THAN_SIGN && state <= STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH) || state === STATE_MARKUP_DECLARATION_OPEN ) { // Bogus comments at EOF are normal per spec (no parse error). if (state !== STATE_BOGUS_COMMENT) { reportError("eof-in-comment", len, len, "error"); } if (callbacks.comment !== undefined) { pos = callbacks.comment(input, commentStart, len); } } else if (state >= STATE_CDATA_SECTION && state <= STATE_CDATA_SECTION_END) { reportError("eof-in-cdata", len, len, "error"); if (callbacks.comment !== undefined) { pos = callbacks.comment(input, commentStart, len); } } else if (state >= STATE_DOCTYPE && state <= STATE_BOGUS_DOCTYPE) { reportError("eof-in-doctype", len, len, "error"); if (callbacks.doctype !== undefined) { pos = callbacks.doctype(input, commentStart, len); } } else { if ( state === STATE_SCRIPT_DATA_ESCAPED || state === STATE_SCRIPT_DATA_ESCAPED_DASH || state === STATE_SCRIPT_DATA_ESCAPED_DASH_DASH || state === STATE_SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN || state === STATE_SCRIPT_DATA_DOUBLE_ESCAPED || state === STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH || state === STATE_SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH || state === STATE_SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN || state === STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END ) { // Inside `