HTML Entity Encoder/Decoder — Swift source
Encode text to HTML entities and decode entities back to text (named + numeric). UTF-8 safe, runs entirely in your browser, with a shareable link to your exact input.
This is the Swift implementation — the same logic the interactive tool runs, in a shareable, citable form.
// =============================================================================
// HtmlEntityEncoder.swift — CosmoDev polyglot showcase port of the
// `html-entity-encoder` tool
// -----------------------------------------------------------------------------
// Language : Swift (5.9, standard library only)
// Source: ported from src/lib/htmlEntities.ts (the canonical, live
// TypeScript lib); mirrors
// src/tool-sources/html-entity-encoder/{python.py,rust.rs}
// License : display source — part of CosmoDev's polyglot tool pages
// (dev.cosmolabs.org). Shown verbatim alongside the JS/TS/Go/Rust/
// Python ports and the other language ports.
// -----------------------------------------------------------------------------
// HTML entity encode / decode — pure string transforms that never trap.
// Encode escapes the five HTML-significant characters (& < > ' ") and can
// optionally flatten every non-ASCII code point to a decimal numeric
// reference. Decode resolves named (&, ©, …), decimal (©), and
// hex (©) references; unknown or malformed references pass through
// whole.
//
// Behavior matches the TypeScript lib exactly: same inputs yield identical
// outputs, including the lone-surrogate and out-of-range guards (decode
// never traps on bad input — unresolvable references are returned verbatim).
//
// Encode iterates String.unicodeScalars (full scalar values), so an astral
// character such as an emoji encodes as a single &#N; reference rather than
// two surrogate halves. Unicode.Scalar.init?(UInt32) is the single guard
// for both failure modes the TypeScript source handles separately: it
// returns nil for lone surrogates (U+D800..U+DFFF) AND for values above
// U+10FFFF, mirroring char::from_u32 in the Rust port. The reference
// scanner is hand-rolled (NSRegularExpression would drag in Foundation; a
// scalar scanner mirrors the Rust port and keeps the snippet dependency-
// free).
//
// The named-entity table is the full WHATWG HTML named-character-reference
// set (2125 entries), generated from src/lib/htmlEntityTable.ts so the data
// stays byte-identical to the canonical TypeScript lib.
// =============================================================================
/// Encode options.
public struct EncodeOptions {
/// When true, every non-ASCII code point is also emitted as a decimal
/// numeric reference (e.g. © → ©), producing ASCII-safe output.
/// When false (the default), only the five HTML-significant characters
/// are escaped.
public var ascii: Bool
public init(ascii: Bool = false) {
self.ascii = ascii
}
}
public enum HtmlEntityEncoder {
/// Escape the five HTML-significant characters.
///
/// A single-pass loop over scalar values: `&` is emitted as `&` and
/// so on. (The Python port runs five sequential replaces and must replace
/// `&` first so its own output is never re-escaped — matching on one code
/// point at a time makes that ordering concern moot.)
///
/// With `ascii` set, every non-ASCII code point is additionally rewritten
/// to a decimal numeric reference. unicodeScalars yields full scalar
/// values, so an astral character such as an emoji encodes as a single
/// reference rather than two surrogate halves.
public static func encodeHtml(_ text: String, options: EncodeOptions? = nil) -> String {
let ascii = options?.ascii ?? false
var out = ""
out.reserveCapacity(text.utf8.count + 16)
for scalar in text.unicodeScalars {
switch scalar {
case "&": out += "&"
case "<": out += "<"
case ">": out += ">"
case "'": out += "'"
case "\"": out += """
default:
if ascii && scalar.value > 0x7F {
out += "&#\(scalar.value);"
} else {
out.unicodeScalars.append(scalar)
}
}
}
return out
}
/// Decode every recognized reference in `text`. Unknown references and
/// stray ampersands are left exactly as they appear in the input. Decode
/// is total: it never traps on malformed or out-of-range input — such
/// references are returned verbatim.
public static func decodeHtml(_ text: String) -> String {
let scalars = text.unicodeScalars
var out = ""
out.reserveCapacity(text.utf8.count)
var i = scalars.startIndex
while i < scalars.endIndex {
if scalars[i] == "&", let (end, resolved) = parseReference(scalars, at: i) {
out += resolved
i = end
} else {
// No reference starts here: copy one scalar value and advance.
out.unicodeScalars.append(scalars[i])
i = scalars.index(after: i)
}
}
return out
}
/// The full WHATWG HTML named-character-reference table, name →
/// character. Generated from src/lib/htmlEntityTable.ts (2125 entries).
/// Do not edit by hand — regenerate from the canonical source.
private static let entityTable: [String: String] = [
"AElig": "Æ",
"AMP": "&",
"Aacute": "Á",
"Abreve": "Ă",
"Acirc": "Â",
"Acy": "А",
"Afr": "𝔄",
"Agrave": "À",
"Alpha": "Α",
"Amacr": "Ā",
"And": "⩓",
"Aogon": "Ą",
"Aopf": "𝔸",
"ApplyFunction": "",
"Aring": "Å",
"Ascr": "𝒜",
"Assign": "≔",
"Atilde": "Ã",
"Auml": "Ä",
"Backslash": "∖",
"Barv": "⫧",
"Barwed": "⌆",
"Bcy": "Б",
"Because": "∵",
"Bernoullis": "ℬ",
"Beta": "Β",
"Bfr": "𝔅",
"Bopf": "𝔹",
"Breve": "˘",
"Bscr": "ℬ",
"Bumpeq": "≎",
"CHcy": "Ч",
"COPY": "©",
"Cacute": "Ć",
"Cap": "⋒",
"CapitalDifferentialD": "ⅅ",
"Cayleys": "ℭ",
"Ccaron": "Č",
"Ccedil": "Ç",
"Ccirc": "Ĉ",
"Cconint": "∰",
"Cdot": "Ċ",
"Cedilla": "¸",
"CenterDot": "·",
"Cfr": "ℭ",
"Chi": "Χ",
"CircleDot": "⊙",
"CircleMinus": "⊖",
"CirclePlus": "⊕",
"CircleTimes": "⊗",
"ClockwiseContourIntegral": "∲",
"CloseCurlyDoubleQuote": "”",
"CloseCurlyQuote": "’",
"Colon": "∷",
"Colone": "⩴",
"Congruent": "≡",
"Conint": "∯",
"ContourIntegral": "∮",
"Copf": "ℂ",
"Coproduct": "∐",
"CounterClockwiseContourIntegral": "∳",
"Cross": "⨯",
"Cscr": "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",
"Eacute": "É",
"Ecaron": "Ě",
"Ecirc": "Ê",
"Ecy": "Э",
"Edot": "Ė",
"Efr": "𝔈",
"Egrave": "È",
"Element": "∈",
"Emacr": "Ē",
"EmptySmallSquare": "◻",
"EmptyVerySmallSquare": "▫",
"Eogon": "Ę",
"Eopf": "𝔼",
"Epsilon": "Ε",
"Equal": "⩵",
"EqualTilde": "≂",
"Equilibrium": "⇌",
"Escr": "ℰ",
"Esim": "⩳",
"Eta": "Η",
"Euml": "Ë",
"Exists": "∃",
"ExponentialE": "ⅇ",
"Fcy": "Ф",
"Ffr": "𝔉",
"FilledSmallSquare": "◼",
"FilledVerySmallSquare": "▪",
"Fopf": "𝔽",
"ForAll": "∀",
"Fouriertrf": "ℱ",
"Fscr": "ℱ",
"GJcy": "Ѓ",
"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",
"Icirc": "Î",
"Icy": "И",
"Idot": "İ",
"Ifr": "ℑ",
"Igrave": "Ì",
"Im": "ℑ",
"Imacr": "Ī",
"ImaginaryI": "ⅈ",
"Implies": "⇒",
"Int": "∬",
"Integral": "∫",
"Intersection": "⋂",
"InvisibleComma": "",
"InvisibleTimes": "",
"Iogon": "Į",
"Iopf": "𝕀",
"Iota": "Ι",
"Iscr": "ℐ",
"Itilde": "Ĩ",
"Iukcy": "І",
"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": "<",
"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",
"Nu": "Ν",
"OElig": "Œ",
"Oacute": "Ó",
"Ocirc": "Ô",
"Ocy": "О",
"Odblac": "Ő",
"Ofr": "𝔒",
"Ograve": "Ò",
"Omacr": "Ō",
"Omega": "Ω",
"Omicron": "Ο",
"Oopf": "𝕆",
"OpenCurlyDoubleQuote": "“",
"OpenCurlyQuote": "‘",
"Or": "⩔",
"Oscr": "𝒪",
"Oslash": "Ø",
"Otilde": "Õ",
"Otimes": "⨷",
"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": "\"",
"Qfr": "𝔔",
"Qopf": "ℚ",
"Qscr": "𝒬",
"RBarr": "⤐",
"REG": "®",
"Racute": "Ŕ",
"Rang": "⟫",
"Rarr": "↠",
"Rarrtl": "⤖",
"Rcaron": "Ř",
"Rcedil": "Ŗ",
"Rcy": "Р",
"Re": "ℜ",
"ReverseElement": "∋",
"ReverseEquilibrium": "⇋",
"ReverseUpEquilibrium": "⥯",
"Rfr": "ℜ",
"Rho": "Ρ",
"RightAngleBracket": "⟩",
"RightArrow": "→",
"RightArrowBar": "⇥",
"RightArrowLeftArrow": "⇄",
"RightCeiling": "⌉",
"RightDoubleBracket": "⟧",
"RightDownTeeVector": "⥝",
"RightDownVector": "⇂",
"RightDownVectorBar": "⥕",
"RightFloor": "⌋",
"RightTee": "⊢",
"RightTeeArrow": "↦",
"RightTeeVector": "⥛",
"RightTriangle": "⊳",
"RightTriangleBar": "⧐",
"RightTriangleEqual": "⊵",
"RightUpDownVector": "⥏",
"RightUpTeeVector": "⥜",
"RightUpVector": "↾",
"RightUpVectorBar": "⥔",
"RightVector": "⇀",
"RightVectorBar": "⥓",
"Rightarrow": "⇒",
"Ropf": "ℝ",
"RoundImplies": "⥰",
"Rrightarrow": "⇛",
"Rscr": "ℛ",
"Rsh": "↱",
"RuleDelayed": "⧴",
"SHCHcy": "Щ",
"SHcy": "Ш",
"SOFTcy": "Ь",
"Sacute": "Ś",
"Sc": "⪼",
"Scaron": "Š",
"Scedil": "Ş",
"Scirc": "Ŝ",
"Scy": "С",
"Sfr": "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",
"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",
"Uarr": "↟",
"Uarrocir": "⥉",
"Ubrcy": "Ў",
"Ubreve": "Ŭ",
"Ucirc": "Û",
"Ucy": "У",
"Udblac": "Ű",
"Ufr": "𝔘",
"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",
"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",
"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",
"abreve": "ă",
"ac": "∾",
"acE": "∾̳",
"acd": "∿",
"acirc": "â",
"acute": "´",
"acy": "а",
"aelig": "æ",
"af": "",
"afr": "𝔞",
"agrave": "à",
"alefsym": "ℵ",
"aleph": "ℵ",
"alpha": "α",
"amacr": "ā",
"amalg": "⨿",
"amp": "&",
"and": "∧",
"andand": "⩕",
"andd": "⩜",
"andslope": "⩘",
"andv": "⩚",
"ang": "∠",
"ange": "⦤",
"angle": "∠",
"angmsd": "∡",
"angmsdaa": "⦨",
"angmsdab": "⦩",
"angmsdac": "⦪",
"angmsdad": "⦫",
"angmsdae": "⦬",
"angmsdaf": "⦭",
"angmsdag": "⦮",
"angmsdah": "⦯",
"angrt": "∟",
"angrtvb": "⊾",
"angrtvbd": "⦝",
"angsph": "∢",
"angst": "Å",
"angzarr": "⍼",
"aogon": "ą",
"aopf": "𝕒",
"ap": "≈",
"apE": "⩰",
"apacir": "⩯",
"ape": "≊",
"apid": "≋",
"apos": "'",
"approx": "≈",
"approxeq": "≊",
"aring": "å",
"ascr": "𝒶",
"ast": "*",
"asymp": "≈",
"asympeq": "≍",
"atilde": "ã",
"auml": "ä",
"awconint": "∳",
"awint": "⨑",
"bNot": "⫭",
"backcong": "≌",
"backepsilon": "϶",
"backprime": "‵",
"backsim": "∽",
"backsimeq": "⋍",
"barvee": "⊽",
"barwed": "⌅",
"barwedge": "⌅",
"bbrk": "⎵",
"bbrktbrk": "⎶",
"bcong": "≌",
"bcy": "б",
"bdquo": "„",
"becaus": "∵",
"because": "∵",
"bemptyv": "⦰",
"bepsi": "϶",
"bernou": "ℬ",
"beta": "β",
"beth": "ℶ",
"between": "≬",
"bfr": "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": "¦",
"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",
"ccirc": "ĉ",
"ccups": "⩌",
"ccupssm": "⩐",
"cdot": "ċ",
"cedil": "¸",
"cemptyv": "⦲",
"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": "©",
"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": "¤",
"curvearrowleft": "↶",
"curvearrowright": "↷",
"cuvee": "⋎",
"cuwed": "⋏",
"cwconint": "∲",
"cwint": "∱",
"cylcty": "⌭",
"dArr": "⇓",
"dHar": "⥥",
"dagger": "†",
"daleth": "ℸ",
"darr": "↓",
"dash": "‐",
"dashv": "⊣",
"dbkarow": "⤏",
"dblac": "˝",
"dcaron": "ď",
"dcy": "д",
"dd": "ⅆ",
"ddagger": "‡",
"ddarr": "⇊",
"ddotseq": "⩷",
"deg": "°",
"delta": "δ",
"demptyv": "⦱",
"dfisht": "⥿",
"dfr": "𝔡",
"dharl": "⇃",
"dharr": "⇂",
"diam": "⋄",
"diamond": "⋄",
"diamondsuit": "♦",
"diams": "♦",
"die": "¨",
"digamma": "ϝ",
"disin": "⋲",
"div": "÷",
"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",
"easter": "⩮",
"ecaron": "ě",
"ecir": "≖",
"ecirc": "ê",
"ecolon": "≕",
"ecy": "э",
"edot": "ė",
"ee": "ⅇ",
"efDot": "≒",
"efr": "𝔢",
"eg": "⪚",
"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",
"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",
"frac13": "⅓",
"frac14": "¼",
"frac15": "⅕",
"frac16": "⅙",
"frac18": "⅛",
"frac23": "⅔",
"frac25": "⅖",
"frac34": "¾",
"frac35": "⅗",
"frac38": "⅜",
"frac45": "⅘",
"frac56": "⅚",
"frac58": "⅝",
"frac78": "⅞",
"frasl": "⁄",
"frown": "⌢",
"fscr": "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": ">",
"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",
"ic": "",
"icirc": "î",
"icy": "и",
"iecy": "е",
"iexcl": "¡",
"iff": "⇔",
"ifr": "𝔦",
"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": "¿",
"iscr": "𝒾",
"isin": "∈",
"isinE": "⋹",
"isindot": "⋵",
"isins": "⋴",
"isinsv": "⋳",
"isinv": "∈",
"it": "",
"itilde": "ĩ",
"iukcy": "і",
"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": "«",
"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": "<",
"ltcc": "⪦",
"ltcir": "⩹",
"ltdot": "⋖",
"lthree": "⋋",
"ltimes": "⋉",
"ltlarr": "⥶",
"ltquest": "⩻",
"ltrPar": "⦖",
"ltri": "◃",
"ltrie": "⊴",
"ltrif": "◂",
"lurdshar": "⥊",
"luruhar": "⥦",
"lvertneqq": "≨︀",
"lvnE": "≨︀",
"mDDot": "∺",
"macr": "¯",
"male": "♂",
"malt": "✠",
"maltese": "✠",
"map": "↦",
"mapsto": "↦",
"mapstodown": "↧",
"mapstoleft": "↤",
"mapstoup": "↥",
"marker": "▮",
"mcomma": "⨩",
"mcy": "м",
"mdash": "—",
"measuredangle": "∡",
"mfr": "𝔪",
"mho": "℧",
"micro": "µ",
"mid": "∣",
"midast": "*",
"midcir": "⫰",
"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": " ",
"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": "¬",
"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",
"ntlg": "≸",
"ntriangleleft": "⋪",
"ntrianglelefteq": "⋬",
"ntriangleright": "⋫",
"ntrianglerighteq": "⋭",
"nu": "ν",
"num": "#",
"numero": "№",
"numsp": " ",
"nvDash": "⊭",
"nvHarr": "⤄",
"nvap": "≍⃒",
"nvdash": "⊬",
"nvge": "≥⃒",
"nvgt": ">⃒",
"nvinfin": "⧞",
"nvlArr": "⤂",
"nvle": "≤⃒",
"nvlt": "<⃒",
"nvltrie": "⊴⃒",
"nvrArr": "⤃",
"nvrtrie": "⊵⃒",
"nvsim": "∼⃒",
"nwArr": "⇖",
"nwarhk": "⤣",
"nwarr": "↖",
"nwarrow": "↖",
"nwnear": "⤧",
"oS": "Ⓢ",
"oacute": "ó",
"oast": "⊛",
"ocir": "⊚",
"ocirc": "ô",
"ocy": "о",
"odash": "⊝",
"odblac": "ő",
"odiv": "⨸",
"odot": "⊙",
"odsold": "⦼",
"oelig": "œ",
"ofcir": "⦿",
"ofr": "𝔬",
"ogon": "˛",
"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",
"ordm": "º",
"origof": "⊶",
"oror": "⩖",
"orslope": "⩗",
"orv": "⩛",
"oscr": "ℴ",
"oslash": "ø",
"osol": "⊘",
"otilde": "õ",
"otimes": "⊗",
"otimesas": "⨶",
"ouml": "ö",
"ovbar": "⌽",
"par": "∥",
"para": "¶",
"parallel": "∥",
"parsim": "⫳",
"parsl": "⫽",
"part": "∂",
"pcy": "п",
"percnt": "%",
"period": ".",
"permil": "‰",
"perp": "⊥",
"pertenk": "‱",
"pfr": "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": "±",
"plussim": "⨦",
"plustwo": "⨧",
"pm": "±",
"pointint": "⨕",
"popf": "𝕡",
"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": "\"",
"rAarr": "⇛",
"rArr": "⇒",
"rAtail": "⤜",
"rBarr": "⤏",
"rHar": "⥤",
"race": "∽̱",
"racute": "ŕ",
"radic": "√",
"raemptyv": "⦳",
"rang": "⟩",
"rangd": "⦒",
"range": "⦥",
"rangle": "⟩",
"raquo": "»",
"rarr": "→",
"rarrap": "⥵",
"rarrb": "⇥",
"rarrbfs": "⤠",
"rarrc": "⤳",
"rarrfs": "⤞",
"rarrhk": "↪",
"rarrlp": "↬",
"rarrpl": "⥅",
"rarrsim": "⥴",
"rarrtl": "↣",
"rarrw": "↝",
"ratail": "⤚",
"ratio": "∶",
"rationals": "ℚ",
"rbarr": "⤍",
"rbbrk": "❳",
"rbrace": "}",
"rbrack": "]",
"rbrke": "⦌",
"rbrksld": "⦎",
"rbrkslu": "⦐",
"rcaron": "ř",
"rcedil": "ŗ",
"rceil": "⌉",
"rcub": "}",
"rcy": "р",
"rdca": "⤷",
"rdldhar": "⥩",
"rdquo": "”",
"rdquor": "”",
"rdsh": "↳",
"real": "ℜ",
"realine": "ℛ",
"realpart": "ℜ",
"reals": "ℝ",
"rect": "▭",
"reg": "®",
"rfisht": "⥽",
"rfloor": "⌋",
"rfr": "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": "§",
"semi": ";",
"seswar": "⤩",
"setminus": "∖",
"setmn": "∖",
"sext": "✶",
"sfr": "𝔰",
"sfrown": "⌢",
"sharp": "♯",
"shchcy": "щ",
"shcy": "ш",
"shortmid": "∣",
"shortparallel": "∥",
"shy": "",
"sigma": "σ",
"sigmaf": "ς",
"sigmav": "ς",
"sim": "∼",
"simdot": "⩪",
"sime": "≃",
"simeq": "≃",
"simg": "⪞",
"simgE": "⪠",
"siml": "⪝",
"simlE": "⪟",
"simne": "≆",
"simplus": "⨤",
"simrarr": "⥲",
"slarr": "←",
"smallsetminus": "∖",
"smashp": "⨳",
"smeparsl": "⧤",
"smid": "∣",
"smile": "⌣",
"smt": "⪪",
"smte": "⪬",
"smtes": "⪬︀",
"softcy": "ь",
"sol": "/",
"solb": "⧄",
"solbar": "⌿",
"sopf": "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",
"sup2": "²",
"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",
"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",
"tilde": "˜",
"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",
"uarr": "↑",
"ubrcy": "ў",
"ubreve": "ŭ",
"ucirc": "û",
"ucy": "у",
"udarr": "⇅",
"udblac": "ű",
"udhar": "⥮",
"ufisht": "⥾",
"ufr": "𝔲",
"ugrave": "ù",
"uharl": "↿",
"uharr": "↾",
"uhblk": "▀",
"ulcorn": "⌜",
"ulcorner": "⌜",
"ulcrop": "⌏",
"ultri": "◸",
"umacr": "ū",
"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",
"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",
"yacy": "я",
"ycirc": "ŷ",
"ycy": "ы",
"yen": "¥",
"yfr": "𝔶",
"yicy": "ї",
"yopf": "𝕪",
"yscr": "𝓎",
"yucy": "ю",
"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": "",
]
/// Hand-rolled matcher for the grammar
/// `&(#[xX][0-9a-fA-F]+|#[0-9]+|[A-Za-z][A-Za-z0-9]*);`.
///
/// Given that `s[start]` begins with `&`, attempt to parse a well-formed
/// reference. On success, return the index just past the closing `;` and
/// the decoded string (which may equal the original `&…;` text when the
/// reference is unknown / invalid — it never traps). Returns nil when no
/// reference grammar matches at all.
private static func parseReference(
_ s: String.UnicodeScalarView, at start: String.UnicodeScalarView.Index
) -> (end: String.UnicodeScalarView.Index, resolved: String)? {
var j = s.index(after: start) // just past '&'
guard j < s.endIndex else { return nil }
let bodyStart = j
if s[j] == "#" {
j = s.index(after: j)
guard j < s.endIndex else { return nil }
let hex = s[j] == "x" || s[j] == "X"
if hex {
j = s.index(after: j)
}
let digitsStart = j
while j < s.endIndex, isDigit(s[j], hex: hex) {
j = s.index(after: j)
}
if j == digitsStart {
return nil // '#' / '#x' with no digits is not a reference
}
} else if isAsciiLetter(s[j]) {
j = s.index(after: j)
while j < s.endIndex, isAsciiAlphanumeric(s[j]) {
j = s.index(after: j)
}
} else {
return nil // '&' not followed by '#' or a letter
}
// The body must be terminated by ';'.
guard j < s.endIndex, s[j] == ";" else { return nil }
let end = s.index(after: j)
let full = String(s[start..<end])
let body = String(s[bodyStart..<j])
return (end, resolveBody(body, full: full))
}
/// Resolve one reference body (name, or "#digits") to its character, or
/// return the original match unchanged when the reference is
/// unrecognized / unsafe.
///
/// UInt32.init(_:radix:) returns nil on overflow (absurd digit runs) and
/// Unicode.Scalar.init?(UInt32) returns nil for lone surrogates AND
/// values above U+10FFFF — together they reproduce both the explicit
/// surrogate guard and the fromCodePoint try/catch of the TypeScript
/// source, exactly like char::from_u32 in the Rust port.
private static func resolveBody(_ body: String, full: String) -> String {
let bytes = Array(body.utf8) // the grammar guarantees ASCII-only bodies
if bytes[0] == UInt8(ascii: "#") {
let hex = bytes.count >= 2
&& (bytes[1] == UInt8(ascii: "x") || bytes[1] == UInt8(ascii: "X"))
let digits = bytes[(hex ? 2 : 1)...]
if let num = UInt32(String(decoding: digits, as: UTF8.self),
radix: hex ? 16 : 10),
let scalar = Unicode.Scalar(num) {
return String(Character(scalar))
}
return full // overflow, > U+10FFFF, or a lone surrogate
}
// Named reference: one hash lookup over the full WHATWG table.
return entityTable[body] ?? full // unknown name — keep the original whole
}
/// true when c is a valid digit for the radix (10 or 16).
private static func isDigit(_ c: Unicode.Scalar, hex: Bool) -> Bool {
(c >= "0" && c <= "9")
|| (hex && ((c >= "a" && c <= "f") || (c >= "A" && c <= "F")))
}
private static func isAsciiLetter(_ c: Unicode.Scalar) -> Bool {
(c >= "A" && c <= "Z") || (c >= "a" && c <= "z")
}
private static func isAsciiAlphanumeric(_ c: Unicode.Scalar) -> Bool {
isAsciiLetter(c) || (c >= "0" && c <= "9")
}
}
Also available in 13 other languages
Every CosmoDev tool ships its pure logic in TypeScript (web) and Go (CLI), with authored implementations in a dozen-plus languages — the same contract, ported. Compare all languages side by side →