webpack 5.107.0 → 5.107.2

package/lib/html/walkHtmlTokens.js

@@ -5,7 +5,25 @@
 
 "use strict";
 
-// cspell:ignore apos
+// 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<Record<string, string>>} */ (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;
@@ -129,6 +147,13 @@ 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
@@ -165,6 +190,19 @@ const isAsciiHexDigit = (cc) =>
 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
@@ -173,6 +211,7 @@ const isSpace = (cc) =>
  * @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
  */
 
 /**
@@ -196,8 +235,32 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 	let attrQuoteType = QUOTE_NONE;
 	let commentStart = pos;
 	let lastOpenTagName = "";
-	let tempBuffer = "";
+	// Counter used by SCRIPT_DATA_DOUBLE_ESCAPE_{START,END} to detect whether
+	// the ASCII-alpha run after `<` / `</` spells exactly `"script"`. Values
+	// 0..6 = number of chars matched so far; 7 = no longer matches (sentinel).
+	// Avoids growing a buffer for pathological inputs with long alpha runs.
+	let scriptMatch = 0;
 	let namedEntityConsumed = 0;
+	// Tracks whether the current tag has parsed any attributes — used to
+	// fire the `end-tag-with-attributes` parse error when an end tag emits.
+	let tagHasAttributes = false;
+
+	/**
+	 * Reports a tokenizer parse error to the consumer. The offset range and
+	 * severity follow the WHATWG spec naming. Severity is `"error"` for
+	 * cases where the emitted token is incomplete (EOF inside a tag or
+	 * comment); everything else is a `"warning"`. Offsets are JS string
+	 * indices (UTF-16 code-unit offsets into `input`).
+	 * @param {string} code WHATWG parse-error code (kebab-case)
+	 * @param {number} start string offset where the error starts
+	 * @param {number} end string offset where the error ends
+	 * @param {ParseErrorSeverity} severity error severity
+	 */
+	const reportError = (code, start, end, severity) => {
+		if (callbacks.parseError !== undefined) {
+			callbacks.parseError(input, code, start, end, severity);
+		}
+	};
 
 	/**
 	 * @param {number} cc character code
@@ -239,8 +302,16 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 	 * @param {number} endPos end position
 	 */
 	const flushText = (endPos) => {
-		if (textStart < endPos && callbacks.text !== undefined) {
-			callbacks.text(input, textStart, 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;
 		}
 	};
 
@@ -249,7 +320,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 	 * @returns {number} next position
 	 */
 	const emitAttribute = (endPos) => {
-		let nextPos = 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,
@@ -260,6 +336,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				attrQuoteType
 			);
 		}
+		if (attrNameStart !== -1) tagHasAttributes = true;
 		attrNameStart = -1;
 		attrValueStart = -1;
 		attrQuoteType = QUOTE_NONE;
@@ -286,6 +363,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 		if (!selfClosing) {
 			lastOpenTagName = input.slice(tagNameStart, tagNameEnd).toLowerCase();
 		}
+		tagHasAttributes = false;
 		textStart = nextPos;
 		return nextPos;
 	};
@@ -295,6 +373,10 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 	 * @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(
@@ -305,6 +387,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				tagNameEnd
 			);
 		}
+		tagHasAttributes = false;
 		textStart = nextPos;
 		return nextPos;
 	};
@@ -348,6 +431,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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)) {
@@ -363,14 +447,27 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
-					pos++;
+					// 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.
-				} else {
+					reportError(
+						"invalid-first-character-of-tag-name",
+						pos,
+						pos + 1,
+						"warning"
+					);
 					state = STATE_DATA;
 					// Reconsume
 				}
@@ -390,6 +487,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				} 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 {
@@ -397,10 +495,16 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
-					pos++;
+					// Reconsume — let bogus-comment consume this char itself.
 				}
 				break;
 
@@ -461,6 +565,15 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					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++;
@@ -570,7 +683,13 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					pos++;
 				} else if (cc === CC_GREATER_THAN) {
 					// U+003E GREATER-THAN SIGN (>)
-					// Switch to the data state. Emit the current tag token.
+					// 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;
@@ -699,6 +818,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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
 				}
@@ -722,6 +847,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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
 				}
@@ -774,6 +900,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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
@@ -792,6 +919,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -803,7 +936,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// Anything else
 					// Reconsume in the comment state.
 					state = STATE_COMMENT;
-					pos++;
+					// Reconsume
 				}
 				break;
 
@@ -819,6 +952,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -831,7 +970,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// Append a U+002D HYPHEN-MINUS character (-) to the comment token's data.
 					// Reconsume in the comment state.
 					state = STATE_COMMENT;
-					pos++;
+					// Reconsume
 				}
 				break;
 
@@ -886,7 +1025,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					pos = nextPos;
 				} else if (cc === CC_EXCLAMATION_MARK) {
 					// U+0021 EXCLAMATION MARK (!)
-					// Switch to the markup declaration open state.
+					// Switch to the comment end bang state.
 					state = STATE_COMMENT_END_BANG;
 					pos++;
 				} else if (cc === CC_HYPHEN_MINUS) {
@@ -914,6 +1053,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1010,6 +1150,9 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// 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;
@@ -1033,6 +1176,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1059,6 +1208,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1164,6 +1314,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1185,6 +1341,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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) {
@@ -1193,6 +1355,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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) {
@@ -1200,6 +1368,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1212,6 +1386,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1245,6 +1425,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1257,6 +1443,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1280,6 +1472,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1314,6 +1512,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1356,6 +1560,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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) {
@@ -1364,6 +1574,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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 {
@@ -1371,6 +1587,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1414,6 +1636,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1435,6 +1663,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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) {
@@ -1443,6 +1677,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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) {
@@ -1450,6 +1690,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1462,6 +1708,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1495,6 +1747,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1507,6 +1765,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1530,6 +1794,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1564,6 +1834,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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);
@@ -1604,6 +1880,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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;
@@ -1710,10 +1992,10 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 			case STATE_RCDATA_LESS_THAN_SIGN:
 				// Consume the next input character:
 				// U+002F SOLIDUS (/)
-				// Set the temporary buffer to the empty string. Switch to the RCDATA end
-				// tag open state.
+				// 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) {
-					tempBuffer = "";
 					state = STATE_RCDATA_END_TAG_OPEN;
 					pos++;
 				} else {
@@ -1760,6 +2042,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_BEFORE_ATTRIBUTE_NAME;
 						pos++;
 					} else {
@@ -1776,6 +2059,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_SELF_CLOSING_START_TAG;
 						pos++;
 					} else {
@@ -1834,10 +2118,9 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 			case STATE_RAWTEXT_LESS_THAN_SIGN:
 				// Consume the next input character:
 				// U+002F SOLIDUS (/)
-				// Set the temporary buffer to the empty string. Switch to the RAWTEXT end
-				// tag open state.
+				// Switch to the RAWTEXT end tag open state. (Spec sets a
+				// temporary buffer here; we track via offset ranges instead.)
 				if (cc === CC_SOLIDUS) {
-					tempBuffer = "";
 					state = STATE_RAWTEXT_END_TAG_OPEN;
 					pos++;
 				} else {
@@ -1884,6 +2167,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_BEFORE_ATTRIBUTE_NAME;
 						pos++;
 					} else {
@@ -1899,6 +2183,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_SELF_CLOSING_START_TAG;
 						pos++;
 					} else {
@@ -1955,10 +2240,9 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 			case STATE_SCRIPT_DATA_LESS_THAN_SIGN:
 				// Consume the next input character:
 				// U+002F SOLIDUS (/)
-				// Set the temporary buffer to the empty string. Switch to the script data
-				// end tag open state.
+				// 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) {
-					tempBuffer = "";
 					state = STATE_SCRIPT_DATA_END_TAG_OPEN;
 					pos++;
 				} else if (cc === CC_EXCLAMATION_MARK) {
@@ -2011,6 +2295,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_BEFORE_ATTRIBUTE_NAME;
 						pos++;
 					} else {
@@ -2026,6 +2311,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_SELF_CLOSING_START_TAG;
 						pos++;
 					} else {
@@ -2107,6 +2393,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				} 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 {
@@ -2128,6 +2415,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				} 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 {
@@ -2149,6 +2437,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				} 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) {
@@ -2170,10 +2459,9 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 			case STATE_SCRIPT_DATA_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
-				// escaped end tag open state.
+				// Switch to the script data escaped end tag open state.
+				// (Spec sets a temporary buffer; we track via offset ranges.)
 				if (cc === CC_SOLIDUS) {
-					tempBuffer = "";
 					state = STATE_SCRIPT_DATA_ESCAPED_END_TAG_OPEN;
 					pos++;
 				} else if (isAsciiAlpha(cc)) {
@@ -2181,7 +2469,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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.
-					tempBuffer = "";
+					scriptMatch = 0;
 					state = STATE_SCRIPT_DATA_DOUBLE_ESCAPE_START;
 					// Reconsume
 				} else {
@@ -2228,6 +2516,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_BEFORE_ATTRIBUTE_NAME;
 						pos++;
 					} else {
@@ -2243,6 +2532,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 						input.slice(tagNameStart, tagNameEnd).toLowerCase() ===
 						lastOpenTagName
 					) {
+						flushText(tagStart);
 						state = STATE_SELF_CLOSING_START_TAG;
 						pos++;
 					} else {
@@ -2292,22 +2582,21 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// state. Emit the current input character as a character token.
 				if (isSpace(cc) || cc === CC_SOLIDUS || cc === CC_GREATER_THAN) {
 					state =
-						tempBuffer === "script"
+						scriptMatch === 6
 							? STATE_SCRIPT_DATA_DOUBLE_ESCAPED
 							: STATE_SCRIPT_DATA_ESCAPED;
 					pos++;
-				} else if (isAsciiUpperAlpha(cc)) {
-					// ASCII upper alpha
-					// Append the lowercase version of the current input character (add 0x0020
-					// to the character's code point) to the temporary buffer. Emit the current
-					// input character as a character token.
-					tempBuffer += String.fromCharCode(cc + 0x20);
-					pos++;
-				} else if (isAsciiLowerAlpha(cc)) {
-					// ASCII lower alpha
-					// Append the current input character to the temporary buffer. Emit the
-					// current input character as a character token.
-					tempBuffer += String.fromCharCode(cc);
+				} 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
@@ -2398,7 +2687,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// 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) {
-					tempBuffer = "";
+					scriptMatch = 0;
 					state = STATE_SCRIPT_DATA_DOUBLE_ESCAPE_END;
 					pos++;
 				} else {
@@ -2423,25 +2712,20 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// state. Emit the current input character as a character token.
 				if (isSpace(cc) || cc === CC_SOLIDUS || cc === CC_GREATER_THAN) {
 					state =
-						tempBuffer === "script"
+						scriptMatch === 6
 							? STATE_SCRIPT_DATA_ESCAPED
 							: STATE_SCRIPT_DATA_DOUBLE_ESCAPED;
 					pos++;
-				} else if (isAsciiUpperAlpha(cc)) {
-					// ASCII upper alpha
-					// Append the lowercase version of the current input character (add 0x0020
-					// to the character's code point) to the temporary buffer. Emit the current
-					// input character as a character token.
-					if (tempBuffer.length < 6) {
-						tempBuffer += String.fromCharCode(cc + 0x20);
-					}
-					pos++;
-				} else if (isAsciiLowerAlpha(cc)) {
-					// ASCII lower alpha
-					// Append the current input character to the temporary buffer. Emit the
-					// current input character as a character token.
-					if (tempBuffer.length < 6) {
-						tempBuffer += String.fromCharCode(cc);
+				} 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 {
@@ -2486,36 +2770,42 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				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
+			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. Append each
-				// character to the temporary buffer when it's consumed.
+				// column of the named character references table.
 				//
-				// TODO(named-entities): The WHATWG spec requires matching against
-				// the full named character references table (~2,000 entries).
-				// For now, we scan past the entity name without table lookup to keep
-				// the core tokenizer lightweight. A follow-up PR will provide a build-time
-				// script to generate a compact Trie/Map or dynamic import for the full
-				// table, along with the `is_consumed_as_part_of_an_attribute` check.
-				// The semantic fallback for consumers (like HtmlParser) is to use the
-				// minimal `decodeHtmlEntities` utility exported below, which guarantees
-				// correctness for URLs (`&amp;`) and common characters without bundle bloat.
-				namedEntityConsumed = 0;
+				// 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 + namedEntityConsumed < len &&
-					isAsciiAlphanumeric(input.charCodeAt(pos + namedEntityConsumed))
+					pos + runLen < len &&
+					isAsciiAlphanumeric(input.charCodeAt(pos + runLen)) &&
+					runLen < MAX_ENTITY_NAME_LEN - 1
 				) {
-					namedEntityConsumed++;
-					// Safety cap — the longest entity is ~33 chars
-					if (namedEntityConsumed > 33) break;
+					runLen++;
 				}
-				// Check for trailing semicolon
-				if (
-					pos + namedEntityConsumed < len &&
-					input.charCodeAt(pos + namedEntityConsumed) === CC_SEMICOLON
-				) {
-					namedEntityConsumed++;
+				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;
@@ -2526,6 +2816,7 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					state = STATE_AMBIGUOUS_AMPERSAND;
 				}
 				break;
+			}
 
 			// https://html.spec.whatwg.org/multipage/parsing.html#ambiguous-ampersand-state
 			case STATE_AMBIGUOUS_AMPERSAND:
@@ -2533,14 +2824,20 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				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.
+					// 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 {
@@ -2578,9 +2875,17 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// Anything else: absence-of-digits-in-numeric-character-reference parse
 				// error. Flush code points consumed as a character reference. Reconsume
 				// in the return state.
-				state = isAsciiHexDigit(cc)
-					? STATE_HEXADECIMAL_CHARACTER_REFERENCE
-					: returnState;
+				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;
 
@@ -2591,9 +2896,17 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// Anything else: absence-of-digits-in-numeric-character-reference parse
 				// error. Flush code points consumed as a character reference. Reconsume
 				// in the return state.
-				state = isAsciiDigit(cc)
-					? STATE_DECIMAL_CHARACTER_REFERENCE
-					: returnState;
+				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;
 
@@ -2616,6 +2929,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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
 				}
@@ -2641,6 +2960,12 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 					// 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
 				}
@@ -2656,26 +2981,111 @@ const walkHtmlTokens = (input, pos = 0, callbacks = {}) => {
 				// 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 / `<` / `</` / `<!`-only
+	// inputs we emit `eof-before-tag-name` and fall through to flush the
+	// pending text span (which still contains the lone `<`).
+	// If EOF caught us inside a character-reference state, flush whatever the
+	// scanner had consumed and resume in the return state so any in-progress
+	// tag/comment is handled correctly by the branches below.
+	if (
+		state >= STATE_CHARACTER_REFERENCE &&
+		state <= STATE_NUMERIC_CHARACTER_REFERENCE_END
+	) {
+		state = returnState;
+	}
+
 	if (
-		(state >= STATE_MARKUP_DECLARATION_OPEN && state <= STATE_BOGUS_COMMENT) ||
+		(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 `<div` open-tag EOFs as well as `<title>x</tit` and other
+		// content-mode end-tag-name EOFs.
+		if (tagNameStart !== -1 && tagNameEnd < tagNameStart) {
+			tagNameEnd = len;
+		}
+		flushText(tagStart);
+		pos =
+			input.charCodeAt(tagStart + 1) === CC_SOLIDUS
+				? emitCloseTag(len)
+				: emitOpenTag(len, false);
+	} else if (
+		(state >= STATE_COMMENT_START && state <= STATE_BOGUS_COMMENT) ||
 		(state >= STATE_COMMENT_LESS_THAN_SIGN &&
 			state <= STATE_COMMENT_LESS_THAN_SIGN_BANG_DASH_DASH) ||
-		(state >= STATE_CDATA_SECTION && state <= STATE_CDATA_SECTION_END)
+		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 (textStart < len && callbacks.text !== undefined) {
-		callbacks.text(input, textStart, 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 `<script><!-- … ` at EOF — spec calls this an
+			// eof-in-script-html-comment-like-text parse error. The
+			// less-than-sign and double-escape-end states reconsume back
+			// into the (double-)escaped state on EOF per spec, which then
+			// hits this same error.
+			reportError("eof-in-script-html-comment-like-text", len, len, "error");
+		} else if (state === STATE_TAG_OPEN || state === STATE_END_TAG_OPEN) {
+			// `<` or `</` with nothing after; spec calls this
+			// eof-before-tag-name. The lone `<` / `</` is preserved in the
+			// pending text span which is flushed below.
+			reportError("eof-before-tag-name", len, len, "warning");
+		}
+		if (textStart < len && callbacks.text !== undefined) {
+			callbacks.text(input, textStart, len);
+		}
 	}
 
 	return pos;
@@ -2685,49 +3095,155 @@ walkHtmlTokens.QUOTE_NONE = QUOTE_NONE;
 walkHtmlTokens.QUOTE_SINGLE = QUOTE_SINGLE;
 walkHtmlTokens.QUOTE_DOUBLE = QUOTE_DOUBLE;
 
-const MINIMAL_ENTITIES = {
-	amp: "&",
-	lt: "<",
-	gt: ">",
-	quot: '"',
-	apos: "'",
-	nbsp: "\u00A0"
+// WHATWG numeric-character-reference-end Windows-1252 remap table for the
+// 0x80-0x9F range. Per spec these C1 control code points decode to the
+// corresponding Windows-1252 glyph (with a parse error) rather than to the
+// raw C1 control character.
+const NUMERIC_C1_REMAP = {
+	0x80: "€",
+	0x82: "‚",
+	0x83: "ƒ",
+	0x84: "„",
+	0x85: "…",
+	0x86: "†",
+	0x87: "‡",
+	0x88: "ˆ",
+	0x89: "‰",
+	0x8a: "Š",
+	0x8b: "‹",
+	0x8c: "Œ",
+	0x8e: "Ž",
+	0x91: "‘",
+	0x92: "’",
+	0x93: "“",
+	0x94: "”",
+	0x95: "•",
+	0x96: "–",
+	0x97: "—",
+	0x98: "˜",
+	0x99: "™",
+	0x9a: "š",
+	0x9b: "›",
+	0x9c: "œ",
+	0x9e: "ž",
+	0x9f: "Ÿ"
 };
 
 /**
- * Minimal entity decoder for safe string resolution without bundle bloat.
- * Decodes the core URL-safe named entities and all numeric references.
- * Leaves unknown entities as literal strings to prevent silent character drops.
+ * @param {number} code numeric character reference code point
+ * @returns {string} decoded character per WHATWG remap rules
+ */
+const decodeNumericReference = (code) => {
+	// Per WHATWG numeric-character-reference-end-state:
+	//   - 0x00, > 0x10FFFF, or surrogate (0xD800-0xDFFF) -> U+FFFD.
+	//   - 0x80-0x9F -> Windows-1252 remap (above).
+	//   - Anything else (including noncharacters and C0 controls) -> the
+	//     code point itself; we don't surface the spec's parse-error
+	//     classes here since decoding is happening after the scanner ran.
+	if (code === 0 || code > 0x10ffff || (code >= 0xd800 && code <= 0xdfff)) {
+		return "�";
+	}
+	if (code >= 0x80 && code <= 0x9f) {
+		const remapped = /** @type {Record<number, string>} */ (NUMERIC_C1_REMAP)[
+			code
+		];
+		if (remapped !== undefined) return remapped;
+	}
+	return String.fromCodePoint(code);
+};
+
+/**
+ * Decode HTML character references in a string. Handles all numeric
+ * references (with WHATWG remap of 0x00, surrogates, out-of-range, and the
+ * C1 Windows-1252 table) and the full WHATWG named character references
+ * table. Unknown or malformed references are left as literal text.
+ *
+ * When `isAttribute` is `true`, applies the WHATWG
+ * "consumed-as-part-of-an-attribute" rule: a named reference without a
+ * trailing `;` whose next character is `=` or ASCII alphanumeric is left
+ * undecoded, so e.g. `&amp=foo` stays literal in an attribute value but
+ * decodes to `&=foo` in text.
  * @param {string} str the raw string from the token slice
+ * @param {boolean=} isAttribute true if `str` came from an attribute value
  * @returns {string} decoded string
  */
-walkHtmlTokens.decodeHtmlEntities = (str) => {
+walkHtmlTokens.decodeHtmlEntities = (str, isAttribute) => {
 	if (!str.includes("&")) return str;
 
-	return str.replace(/&(#?[0-9a-zA-Z]+);?/g, (match, entity) => {
-		// Decimal numeric reference: &#65;
-		if (entity.charCodeAt(0) === 0x23 /* # */) {
-			const isHex =
-				entity.charCodeAt(1) === 0x78 || entity.charCodeAt(1) === 0x58; // x or X
-			const code = isHex
-				? Number.parseInt(entity.slice(2), 16)
-				: Number.parseInt(entity.slice(1), 10);
-			if (!Number.isNaN(code)) {
-				// Handle basic out-of-bounds (minimal approximation of WHATWG replacement char)
-				return code > 0x10ffff ? "\uFFFD" : String.fromCodePoint(code);
+	// Match one of three forms (each with an optional trailing `;`):
+	//   `&#x<hex>` - hex numeric reference (requires the `x`/`X`).
+	//   `&#<dec>`  - decimal numeric reference (digits only).
+	//   `&<name>`  - named reference (letter followed by alphanumerics).
+	// The three alternatives are kept separate so a decimal reference like
+	// `&#65b` doesn't greedily eat the trailing `b` as if it were hex.
+	return str.replace(
+		/&(?:#[xX][0-9a-fA-F]+|#[0-9]+|[a-zA-Z][a-zA-Z0-9]*);?/g,
+		(match, offset, source) => {
+			// Numeric reference: &#65; or &#x41;
+			if (match.charCodeAt(1) === 0x23 /* # */) {
+				const lastChar = match.charAt(match.length - 1);
+				const isHex =
+					match.charCodeAt(2) === 0x78 || match.charCodeAt(2) === 0x58;
+				const body = isHex
+					? lastChar === ";"
+						? match.slice(3, -1)
+						: match.slice(3)
+					: lastChar === ";"
+						? match.slice(2, -1)
+						: match.slice(2);
+				// The regex above guarantees at least one digit in `body`,
+				// so `parseInt` always returns a finite number here.
+				return decodeNumericReference(Number.parseInt(body, isHex ? 16 : 10));
 			}
-			return match; // Invalid numeric (e.g. &#;)
-		}
 
-		// Known minimal named reference: &amp;
-		const key = entity.toLowerCase();
-		if (Object.prototype.hasOwnProperty.call(MINIMAL_ENTITIES, key)) {
-			return /** @type {Record<string, string>} */ (MINIMAL_ENTITIES)[key];
-		}
+			// Named reference. Try the full captured name first, then
+			// progressively shorter prefixes - this handles direct matches
+			// like `&amp;` as well as WHATWG longest-prefix semantics where
+			// e.g. `&notpre;` decodes as `&not` (a legacy bare entity)
+			// followed by `pre;` as literal text.
+			const name = match.slice(1);
+			const matchEndsWithSemi = name.charCodeAt(name.length - 1) === 0x3b;
+
+			// Attribute-context guard: if the entity match didn't end with `;`
+			// and the next character in the source is `=` or ASCII
+			// alphanumeric, the WHATWG spec says to flush the literal text
+			// rather than decode. The greedy regex already absorbed any
+			// trailing alphanumerics, so the only candidate "next char" here
+			// is `=` (or any non-alphanumeric).
+			if (isAttribute && !matchEndsWithSemi) {
+				const after = source.charCodeAt(offset + match.length);
+				if (after === 0x3d /* = */) return match;
+			}
 
-		// Unknown named entity: preserve as literal to avoid data loss
-		return match;
-	});
+			// Cap the longest-prefix search at MAX_ENTITY_NAME_LEN so pathological
+			// inputs like `&` + thousands of alphanumerics stay linear-time.
+			// Anything past that cap can't possibly match and is appended
+			// verbatim as part of `name.slice(i)`.
+			const searchLen =
+				name.length > MAX_ENTITY_NAME_LEN ? MAX_ENTITY_NAME_LEN : name.length;
+			for (let i = searchLen; i > 0; i--) {
+				const prefix = name.slice(0, i);
+				if (HTML_ENTITIES[prefix] !== undefined) {
+					// Attribute-context longest-prefix guard: if the matched
+					// prefix doesn't end with `;` and the leftover starts with
+					// an alphanumeric character, leave literal per WHATWG.
+					// (The regex greedy-consumes alphanumerics, so any leftover
+					// within `name` is itself alphanumeric — we only need to
+					// check non-empty leftover here; the `=` case is handled
+					// above against the source character after the match.)
+					if (
+						isAttribute &&
+						i < name.length &&
+						prefix.charCodeAt(prefix.length - 1) !== 0x3b
+					) {
+						return match;
+					}
+					return HTML_ENTITIES[prefix] + name.slice(i);
+				}
+			}
+			return match;
+		}
+	);
 };
 
 module.exports = walkHtmlTokens;