Class: Moxml::EntityRegistry

Inherits:
Object
  • Object
show all
Defined in:
lib/moxml/entity_registry.rb,
lib/moxml/entity_registry_opal_data.rb

Overview

EntityRegistry maintains a knowledge base of XML entity definitions.

Data source: W3C XML Core WG Character Entities (bundled) www.w3.org/2003/entities/2007/htmlmathml

The W3C entity data is bundled in data/w3c_entities.json and loaded from the gem’s data directory. For development, MOXML_ENTITY_DEFINITIONS_PATH can be set to an external copy.

Per W3C XML Core WG guidance:

  • Character entities are XML internal general entities providing a name for a single Unicode character

  • Standard XML entities (amp, lt, gt, quot, apos) are implicitly declared per XML specification

  • External entity sets (like HTML, MathML) can be referenced via DTD parameter entities

Examples:

Basic usage

registry = EntityRegistry.new
registry.declared?("amp")  # => true
registry.codepoint_for_name("amp")  # => 38

Defined Under Namespace

Classes: EntityDataError

Constant Summary collapse

ENTITY_DATA_FILE =

W3C entity data file name

"w3c_entities.json"
STANDARD_CODEPOINTS =

Standard XML predefined entities (XML spec §4.6)

Set[0x26, 0x3C, 0x3E, 0x22, 0x27].freeze
OPAL_ENTITY_DATA = 
{
  "AElig" => 198,
  "AMP" => 38,
  "Aacute" => 193,
  "Abreve" => 258,
  "Acirc" => 194,
  "Acy" => 1040,
  "Afr" => 120068,
  "Agrave" => 192,
  "Alpha" => 913,
  "Amacr" => 256,
  "And" => 10835,
  "Aogon" => 260,
  "Aopf" => 120120,
  "ApplyFunction" => 8289,
  "Aring" => 197,
  "Ascr" => 119964,
  "Assign" => 8788,
  "Atilde" => 195,
  "Auml" => 196,
  "Backslash" => 8726,
  "Barv" => 10983,
  "Barwed" => 8966,
  "Bcy" => 1041,
  "Because" => 8757,
  "Bernoullis" => 8492,
  "Beta" => 914,
  "Bfr" => 120069,
  "Bopf" => 120121,
  "Breve" => 728,
  "Bscr" => 8492,
  "Bumpeq" => 8782,
  "CHcy" => 1063,
  "COPY" => 169,
  "Cacute" => 262,
  "Cap" => 8914,
  "CapitalDifferentialD" => 8517,
  "Cayleys" => 8493,
  "Ccaron" => 268,
  "Ccedil" => 199,
  "Ccirc" => 264,
  "Cconint" => 8752,
  "Cdot" => 266,
  "Cedilla" => 184,
  "CenterDot" => 183,
  "Cfr" => 8493,
  "Chi" => 935,
  "CircleDot" => 8857,
  "CircleMinus" => 8854,
  "CirclePlus" => 8853,
  "CircleTimes" => 8855,
  "ClockwiseContourIntegral" => 8754,
  "CloseCurlyDoubleQuote" => 8221,
  "CloseCurlyQuote" => 8217,
  "Colon" => 8759,
  "Colone" => 10868,
  "Congruent" => 8801,
  "Conint" => 8751,
  "ContourIntegral" => 8750,
  "Copf" => 8450,
  "Coproduct" => 8720,
  "CounterClockwiseContourIntegral" => 8755,
  "Cross" => 10799,
  "Cscr" => 119966,
  "Cup" => 8915,
  "CupCap" => 8781,
  "DD" => 8517,
  "DDotrahd" => 10513,
  "DJcy" => 1026,
  "DScy" => 1029,
  "DZcy" => 1039,
  "Dagger" => 8225,
  "Darr" => 8609,
  "Dashv" => 10980,
  "Dcaron" => 270,
  "Dcy" => 1044,
  "Del" => 8711,
  "Delta" => 916,
  "Dfr" => 120071,
  "DiacriticalAcute" => 180,
  "DiacriticalDot" => 729,
  "DiacriticalDoubleAcute" => 733,
  "DiacriticalGrave" => 96,
  "DiacriticalTilde" => 732,
  "Diamond" => 8900,
  "DifferentialD" => 8518,
  "Dopf" => 120123,
  "Dot" => 168,
  "DotDot" => 32,
  "DotEqual" => 8784,
  "DoubleContourIntegral" => 8751,
  "DoubleDot" => 168,
  "DoubleDownArrow" => 8659,
  "DoubleLeftArrow" => 8656,
  "DoubleLeftRightArrow" => 8660,
  "DoubleLeftTee" => 10980,
  "DoubleLongLeftArrow" => 10232,
  "DoubleLongLeftRightArrow" => 10234,
  "DoubleLongRightArrow" => 10233,
  "DoubleRightArrow" => 8658,
  "DoubleRightTee" => 8872,
  "DoubleUpArrow" => 8657,
  "DoubleUpDownArrow" => 8661,
  "DoubleVerticalBar" => 8741,
  "DownArrow" => 8595,
  "DownArrowBar" => 10515,
  "DownArrowUpArrow" => 8693,
  "DownBreve" => 32,
  "DownLeftRightVector" => 10576,
  "DownLeftTeeVector" => 10590,
  "DownLeftVector" => 8637,
  "DownLeftVectorBar" => 10582,
  "DownRightTeeVector" => 10591,
  "DownRightVector" => 8641,
  "DownRightVectorBar" => 10583,
  "DownTee" => 8868,
  "DownTeeArrow" => 8615,
  "Downarrow" => 8659,
  "Dscr" => 119967,
  "Dstrok" => 272,
  "ENG" => 330,
  "ETH" => 208,
  "Eacute" => 201,
  "Ecaron" => 282,
  "Ecirc" => 202,
  "Ecy" => 1069,
  "Edot" => 278,
  "Efr" => 120072,
  "Egrave" => 200,
  "Element" => 8712,
  "Emacr" => 274,
  "EmptySmallSquare" => 9723,
  "EmptyVerySmallSquare" => 9643,
  "Eogon" => 280,
  "Eopf" => 120124,
  "Epsilon" => 917,
  "Equal" => 10869,
  "EqualTilde" => 8770,
  "Equilibrium" => 8652,
  "Escr" => 8496,
  "Esim" => 10867,
  "Eta" => 919,
  "Euml" => 203,
  "Exists" => 8707,
  "ExponentialE" => 8519,
  "Fcy" => 1060,
  "Ffr" => 120073,
  "FilledSmallSquare" => 9724,
  "FilledVerySmallSquare" => 9642,
  "Fopf" => 120125,
  "ForAll" => 8704,
  "Fouriertrf" => 8497,
  "Fscr" => 8497,
  "GJcy" => 1027,
  "GT" => 62,
  "Gamma" => 915,
  "Gammad" => 988,
  "Gbreve" => 286,
  "Gcedil" => 290,
  "Gcirc" => 284,
  "Gcy" => 1043,
  "Gdot" => 288,
  "Gfr" => 120074,
  "Gg" => 8921,
  "Gopf" => 120126,
  "GreaterEqual" => 8805,
  "GreaterEqualLess" => 8923,
  "GreaterFullEqual" => 8807,
  "GreaterGreater" => 10914,
  "GreaterLess" => 8823,
  "GreaterSlantEqual" => 10878,
  "GreaterTilde" => 8819,
  "Gscr" => 119970,
  "Gt" => 8811,
  "HARDcy" => 1066,
  "Hacek" => 711,
  "Hat" => 94,
  "Hcirc" => 292,
  "Hfr" => 8460,
  "HilbertSpace" => 8459,
  "Hopf" => 8461,
  "HorizontalLine" => 9472,
  "Hscr" => 8459,
  "Hstrok" => 294,
  "HumpDownHump" => 8782,
  "HumpEqual" => 8783,
  "IEcy" => 1045,
  "IJlig" => 306,
  "IOcy" => 1025,
  "Iacute" => 205,
  "Icirc" => 206,
  "Icy" => 1048,
  "Idot" => 304,
  "Ifr" => 8465,
  "Igrave" => 204,
  "Im" => 8465,
  "Imacr" => 298,
  "ImaginaryI" => 8520,
  "Implies" => 8658,
  "Int" => 8748,
  "Integral" => 8747,
  "Intersection" => 8898,
  "InvisibleComma" => 8291,
  "InvisibleTimes" => 8290,
  "Iogon" => 302,
  "Iopf" => 120128,
  "Iota" => 921,
  "Iscr" => 8464,
  "Itilde" => 296,
  "Iukcy" => 1030,
  "Iuml" => 207,
  "Jcirc" => 308,
  "Jcy" => 1049,
  "Jfr" => 120077,
  "Jopf" => 120129,
  "Jscr" => 119973,
  "Jsercy" => 1032,
  "Jukcy" => 1028,
  "KHcy" => 1061,
  "KJcy" => 1036,
  "Kappa" => 922,
  "Kcedil" => 310,
  "Kcy" => 1050,
  "Kfr" => 120078,
  "Kopf" => 120130,
  "Kscr" => 119974,
  "LJcy" => 1033,
  "LT" => 60,
  "Lacute" => 313,
  "Lambda" => 923,
  "Lang" => 10218,
  "Laplacetrf" => 8466,
  "Larr" => 8606,
  "Lcaron" => 317,
  "Lcedil" => 315,
  "Lcy" => 1051,
  "LeftAngleBracket" => 10216,
  "LeftArrow" => 8592,
  "LeftArrowBar" => 8676,
  "LeftArrowRightArrow" => 8646,
  "LeftCeiling" => 8968,
  "LeftDoubleBracket" => 10214,
  "LeftDownTeeVector" => 10593,
  "LeftDownVector" => 8643,
  "LeftDownVectorBar" => 10585,
  "LeftFloor" => 8970,
  "LeftRightArrow" => 8596,
  "LeftRightVector" => 10574,
  "LeftTee" => 8867,
  "LeftTeeArrow" => 8612,
  "LeftTeeVector" => 10586,
  "LeftTriangle" => 8882,
  "LeftTriangleBar" => 10703,
  "LeftTriangleEqual" => 8884,
  "LeftUpDownVector" => 10577,
  "LeftUpTeeVector" => 10592,
  "LeftUpVector" => 8639,
  "LeftUpVectorBar" => 10584,
  "LeftVector" => 8636,
  "LeftVectorBar" => 10578,
  "Leftarrow" => 8656,
  "Leftrightarrow" => 8660,
  "LessEqualGreater" => 8922,
  "LessFullEqual" => 8806,
  "LessGreater" => 8822,
  "LessLess" => 10913,
  "LessSlantEqual" => 10877,
  "LessTilde" => 8818,
  "Lfr" => 120079,
  "Ll" => 8920,
  "Lleftarrow" => 8666,
  "Lmidot" => 319,
  "LongLeftArrow" => 10229,
  "LongLeftRightArrow" => 10231,
  "LongRightArrow" => 10230,
  "Longleftarrow" => 10232,
  "Longleftrightarrow" => 10234,
  "Longrightarrow" => 10233,
  "Lopf" => 120131,
  "LowerLeftArrow" => 8601,
  "LowerRightArrow" => 8600,
  "Lscr" => 8466,
  "Lsh" => 8624,
  "Lstrok" => 321,
  "Lt" => 8810,
  "Map" => 10501,
  "Mcy" => 1052,
  "MediumSpace" => 8287,
  "Mellintrf" => 8499,
  "Mfr" => 120080,
  "MinusPlus" => 8723,
  "Mopf" => 120132,
  "Mscr" => 8499,
  "Mu" => 924,
  "NJcy" => 1034,
  "Nacute" => 323,
  "Ncaron" => 327,
  "Ncedil" => 325,
  "Ncy" => 1053,
  "NegativeMediumSpace" => 8203,
  "NegativeThickSpace" => 8203,
  "NegativeThinSpace" => 8203,
  "NegativeVeryThinSpace" => 8203,
  "NestedGreaterGreater" => 8811,
  "NestedLessLess" => 8810,
  "NewLine" => 10,
  "Nfr" => 120081,
  "NoBreak" => 8288,
  "NonBreakingSpace" => 160,
  "Nopf" => 8469,
  "Not" => 10988,
  "NotCongruent" => 8802,
  "NotCupCap" => 8813,
  "NotDoubleVerticalBar" => 8742,
  "NotElement" => 8713,
  "NotEqual" => 8800,
  "NotEqualTilde" => 8770,
  "NotExists" => 8708,
  "NotGreater" => 8815,
  "NotGreaterEqual" => 8817,
  "NotGreaterFullEqual" => 8807,
  "NotGreaterGreater" => 8811,
  "NotGreaterLess" => 8825,
  "NotGreaterSlantEqual" => 10878,
  "NotGreaterTilde" => 8821,
  "NotHumpDownHump" => 8782,
  "NotHumpEqual" => 8783,
  "NotLeftTriangle" => 8938,
  "NotLeftTriangleBar" => 10703,
  "NotLeftTriangleEqual" => 8940,
  "NotLess" => 8814,
  "NotLessEqual" => 8816,
  "NotLessGreater" => 8824,
  "NotLessLess" => 8810,
  "NotLessSlantEqual" => 10877,
  "NotLessTilde" => 8820,
  "NotNestedGreaterGreater" => 10914,
  "NotNestedLessLess" => 10913,
  "NotPrecedes" => 8832,
  "NotPrecedesEqual" => 10927,
  "NotPrecedesSlantEqual" => 8928,
  "NotReverseElement" => 8716,
  "NotRightTriangle" => 8939,
  "NotRightTriangleBar" => 10704,
  "NotRightTriangleEqual" => 8941,
  "NotSquareSubset" => 8847,
  "NotSquareSubsetEqual" => 8930,
  "NotSquareSuperset" => 8848,
  "NotSquareSupersetEqual" => 8931,
  "NotSubset" => 8834,
  "NotSubsetEqual" => 8840,
  "NotSucceeds" => 8833,
  "NotSucceedsEqual" => 10928,
  "NotSucceedsSlantEqual" => 8929,
  "NotSucceedsTilde" => 8831,
  "NotSuperset" => 8835,
  "NotSupersetEqual" => 8841,
  "NotTilde" => 8769,
  "NotTildeEqual" => 8772,
  "NotTildeFullEqual" => 8775,
  "NotTildeTilde" => 8777,
  "NotVerticalBar" => 8740,
  "Nscr" => 119977,
  "Ntilde" => 209,
  "Nu" => 925,
  "OElig" => 338,
  "Oacute" => 211,
  "Ocirc" => 212,
  "Ocy" => 1054,
  "Odblac" => 336,
  "Ofr" => 120082,
  "Ograve" => 210,
  "Omacr" => 332,
  "Omega" => 937,
  "Omicron" => 927,
  "Oopf" => 120134,
  "OpenCurlyDoubleQuote" => 8220,
  "OpenCurlyQuote" => 8216,
  "Or" => 10836,
  "Oscr" => 119978,
  "Oslash" => 216,
  "Otilde" => 213,
  "Otimes" => 10807,
  "Ouml" => 214,
  "OverBar" => 8254,
  "OverBrace" => 9182,
  "OverBracket" => 9140,
  "OverParenthesis" => 9180,
  "PartialD" => 8706,
  "Pcy" => 1055,
  "Pfr" => 120083,
  "Phi" => 934,
  "Pi" => 928,
  "PlusMinus" => 177,
  "Poincareplane" => 8460,
  "Popf" => 8473,
  "Pr" => 10939,
  "Precedes" => 8826,
  "PrecedesEqual" => 10927,
  "PrecedesSlantEqual" => 8828,
  "PrecedesTilde" => 8830,
  "Prime" => 8243,
  "Product" => 8719,
  "Proportion" => 8759,
  "Proportional" => 8733,
  "Pscr" => 119979,
  "Psi" => 936,
  "QUOT" => 34,
  "Qfr" => 120084,
  "Qopf" => 8474,
  "Qscr" => 119980,
  "RBarr" => 10512,
  "REG" => 174,
  "Racute" => 340,
  "Rang" => 10219,
  "Rarr" => 8608,
  "Rarrtl" => 10518,
  "Rcaron" => 344,
  "Rcedil" => 342,
  "Rcy" => 1056,
  "Re" => 8476,
  "ReverseElement" => 8715,
  "ReverseEquilibrium" => 8651,
  "ReverseUpEquilibrium" => 10607,
  "Rfr" => 8476,
  "Rho" => 929,
  "RightAngleBracket" => 10217,
  "RightArrow" => 8594,
  "RightArrowBar" => 8677,
  "RightArrowLeftArrow" => 8644,
  "RightCeiling" => 8969,
  "RightDoubleBracket" => 10215,
  "RightDownTeeVector" => 10589,
  "RightDownVector" => 8642,
  "RightDownVectorBar" => 10581,
  "RightFloor" => 8971,
  "RightTee" => 8866,
  "RightTeeArrow" => 8614,
  "RightTeeVector" => 10587,
  "RightTriangle" => 8883,
  "RightTriangleBar" => 10704,
  "RightTriangleEqual" => 8885,
  "RightUpDownVector" => 10575,
  "RightUpTeeVector" => 10588,
  "RightUpVector" => 8638,
  "RightUpVectorBar" => 10580,
  "RightVector" => 8640,
  "RightVectorBar" => 10579,
  "Rightarrow" => 8658,
  "Ropf" => 8477,
  "RoundImplies" => 10608,
  "Rrightarrow" => 8667,
  "Rscr" => 8475,
  "Rsh" => 8625,
  "RuleDelayed" => 10740,
  "SHCHcy" => 1065,
  "SHcy" => 1064,
  "SOFTcy" => 1068,
  "Sacute" => 346,
  "Sc" => 10940,
  "Scaron" => 352,
  "Scedil" => 350,
  "Scirc" => 348,
  "Scy" => 1057,
  "Sfr" => 120086,
  "ShortDownArrow" => 8595,
  "ShortLeftArrow" => 8592,
  "ShortRightArrow" => 8594,
  "ShortUpArrow" => 8593,
  "Sigma" => 931,
  "SmallCircle" => 8728,
  "Sopf" => 120138,
  "Sqrt" => 8730,
  "Square" => 9633,
  "SquareIntersection" => 8851,
  "SquareSubset" => 8847,
  "SquareSubsetEqual" => 8849,
  "SquareSuperset" => 8848,
  "SquareSupersetEqual" => 8850,
  "SquareUnion" => 8852,
  "Sscr" => 119982,
  "Star" => 8902,
  "Sub" => 8912,
  "Subset" => 8912,
  "SubsetEqual" => 8838,
  "Succeeds" => 8827,
  "SucceedsEqual" => 10928,
  "SucceedsSlantEqual" => 8829,
  "SucceedsTilde" => 8831,
  "SuchThat" => 8715,
  "Sum" => 8721,
  "Sup" => 8913,
  "Superset" => 8835,
  "SupersetEqual" => 8839,
  "Supset" => 8913,
  "THORN" => 222,
  "TRADE" => 8482,
  "TSHcy" => 1035,
  "TScy" => 1062,
  "Tab" => 9,
  "Tau" => 932,
  "Tcaron" => 356,
  "Tcedil" => 354,
  "Tcy" => 1058,
  "Tfr" => 120087,
  "Therefore" => 8756,
  "Theta" => 920,
  "ThickSpace" => 8287,
  "ThinSpace" => 8201,
  "Tilde" => 8764,
  "TildeEqual" => 8771,
  "TildeFullEqual" => 8773,
  "TildeTilde" => 8776,
  "Topf" => 120139,
  "TripleDot" => 32,
  "Tscr" => 119983,
  "Tstrok" => 358,
  "Uacute" => 218,
  "Uarr" => 8607,
  "Uarrocir" => 10569,
  "Ubrcy" => 1038,
  "Ubreve" => 364,
  "Ucirc" => 219,
  "Ucy" => 1059,
  "Udblac" => 368,
  "Ufr" => 120088,
  "Ugrave" => 217,
  "Umacr" => 362,
  "UnderBar" => 95,
  "UnderBrace" => 9183,
  "UnderBracket" => 9141,
  "UnderParenthesis" => 9181,
  "Union" => 8899,
  "UnionPlus" => 8846,
  "Uogon" => 370,
  "Uopf" => 120140,
  "UpArrow" => 8593,
  "UpArrowBar" => 10514,
  "UpArrowDownArrow" => 8645,
  "UpDownArrow" => 8597,
  "UpEquilibrium" => 10606,
  "UpTee" => 8869,
  "UpTeeArrow" => 8613,
  "Uparrow" => 8657,
  "Updownarrow" => 8661,
  "UpperLeftArrow" => 8598,
  "UpperRightArrow" => 8599,
  "Upsi" => 978,
  "Upsilon" => 933,
  "Uring" => 366,
  "Uscr" => 119984,
  "Utilde" => 360,
  "Uuml" => 220,
  "VDash" => 8875,
  "Vbar" => 10987,
  "Vcy" => 1042,
  "Vdash" => 8873,
  "Vdashl" => 10982,
  "Vee" => 8897,
  "Verbar" => 8214,
  "Vert" => 8214,
  "VerticalBar" => 8739,
  "VerticalLine" => 124,
  "VerticalSeparator" => 10072,
  "VerticalTilde" => 8768,
  "VeryThinSpace" => 8202,
  "Vfr" => 120089,
  "Vopf" => 120141,
  "Vscr" => 119985,
  "Vvdash" => 8874,
  "Wcirc" => 372,
  "Wedge" => 8896,
  "Wfr" => 120090,
  "Wopf" => 120142,
  "Wscr" => 119986,
  "Xfr" => 120091,
  "Xi" => 926,
  "Xopf" => 120143,
  "Xscr" => 119987,
  "YAcy" => 1071,
  "YIcy" => 1031,
  "YUcy" => 1070,
  "Yacute" => 221,
  "Ycirc" => 374,
  "Ycy" => 1067,
  "Yfr" => 120092,
  "Yopf" => 120144,
  "Yscr" => 119988,
  "Yuml" => 376,
  "ZHcy" => 1046,
  "Zacute" => 377,
  "Zcaron" => 381,
  "Zcy" => 1047,
  "Zdot" => 379,
  "ZeroWidthSpace" => 8203,
  "Zeta" => 918,
  "Zfr" => 8488,
  "Zopf" => 8484,
  "Zscr" => 119989,
  "aacute" => 225,
  "abreve" => 259,
  "ac" => 8766,
  "acE" => 8766,
  "acd" => 8767,
  "acirc" => 226,
  "acute" => 180,
  "acy" => 1072,
  "aelig" => 230,
  "af" => 8289,
  "afr" => 120094,
  "agrave" => 224,
  "alefsym" => 8501,
  "aleph" => 8501,
  "alpha" => 945,
  "amacr" => 257,
  "amalg" => 10815,
  "amp" => 38,
  "and" => 8743,
  "andand" => 10837,
  "andd" => 10844,
  "andslope" => 10840,
  "andv" => 10842,
  "ang" => 8736,
  "ange" => 10660,
  "angle" => 8736,
  "angmsd" => 8737,
  "angmsdaa" => 10664,
  "angmsdab" => 10665,
  "angmsdac" => 10666,
  "angmsdad" => 10667,
  "angmsdae" => 10668,
  "angmsdaf" => 10669,
  "angmsdag" => 10670,
  "angmsdah" => 10671,
  "angrt" => 8735,
  "angrtvb" => 8894,
  "angrtvbd" => 10653,
  "angsph" => 8738,
  "angst" => 197,
  "angzarr" => 9084,
  "aogon" => 261,
  "aopf" => 120146,
  "ap" => 8776,
  "apE" => 10864,
  "apacir" => 10863,
  "ape" => 8778,
  "apid" => 8779,
  "apos" => 39,
  "approx" => 8776,
  "approxeq" => 8778,
  "aring" => 229,
  "ascr" => 119990,
  "ast" => 42,
  "asymp" => 8776,
  "asympeq" => 8781,
  "atilde" => 227,
  "auml" => 228,
  "awconint" => 8755,
  "awint" => 10769,
  "bNot" => 10989,
  "backcong" => 8780,
  "backepsilon" => 1014,
  "backprime" => 8245,
  "backsim" => 8765,
  "backsimeq" => 8909,
  "barvee" => 8893,
  "barwed" => 8965,
  "barwedge" => 8965,
  "bbrk" => 9141,
  "bbrktbrk" => 9142,
  "bcong" => 8780,
  "bcy" => 1073,
  "bdquo" => 8222,
  "becaus" => 8757,
  "because" => 8757,
  "bemptyv" => 10672,
  "bepsi" => 1014,
  "bernou" => 8492,
  "beta" => 946,
  "beth" => 8502,
  "between" => 8812,
  "bfr" => 120095,
  "bigcap" => 8898,
  "bigcirc" => 9711,
  "bigcup" => 8899,
  "bigodot" => 10752,
  "bigoplus" => 10753,
  "bigotimes" => 10754,
  "bigsqcup" => 10758,
  "bigstar" => 9733,
  "bigtriangledown" => 9661,
  "bigtriangleup" => 9651,
  "biguplus" => 10756,
  "bigvee" => 8897,
  "bigwedge" => 8896,
  "bkarow" => 10509,
  "blacklozenge" => 10731,
  "blacksquare" => 9642,
  "blacktriangle" => 9652,
  "blacktriangledown" => 9662,
  "blacktriangleleft" => 9666,
  "blacktriangleright" => 9656,
  "blank" => 9251,
  "blk12" => 9618,
  "blk14" => 9617,
  "blk34" => 9619,
  "block" => 9608,
  "bne" => 61,
  "bnequiv" => 8801,
  "bnot" => 8976,
  "bopf" => 120147,
  "bot" => 8869,
  "bottom" => 8869,
  "bowtie" => 8904,
  "boxDL" => 9559,
  "boxDR" => 9556,
  "boxDl" => 9558,
  "boxDr" => 9555,
  "boxH" => 9552,
  "boxHD" => 9574,
  "boxHU" => 9577,
  "boxHd" => 9572,
  "boxHu" => 9575,
  "boxUL" => 9565,
  "boxUR" => 9562,
  "boxUl" => 9564,
  "boxUr" => 9561,
  "boxV" => 9553,
  "boxVH" => 9580,
  "boxVL" => 9571,
  "boxVR" => 9568,
  "boxVh" => 9579,
  "boxVl" => 9570,
  "boxVr" => 9567,
  "boxbox" => 10697,
  "boxdL" => 9557,
  "boxdR" => 9554,
  "boxdl" => 9488,
  "boxdr" => 9484,
  "boxh" => 9472,
  "boxhD" => 9573,
  "boxhU" => 9576,
  "boxhd" => 9516,
  "boxhu" => 9524,
  "boxminus" => 8863,
  "boxplus" => 8862,
  "boxtimes" => 8864,
  "boxuL" => 9563,
  "boxuR" => 9560,
  "boxul" => 9496,
  "boxur" => 9492,
  "boxv" => 9474,
  "boxvH" => 9578,
  "boxvL" => 9569,
  "boxvR" => 9566,
  "boxvh" => 9532,
  "boxvl" => 9508,
  "boxvr" => 9500,
  "bprime" => 8245,
  "breve" => 728,
  "brvbar" => 166,
  "bscr" => 119991,
  "bsemi" => 8271,
  "bsim" => 8765,
  "bsime" => 8909,
  "bsol" => 92,
  "bsolb" => 10693,
  "bsolhsub" => 10184,
  "bull" => 8226,
  "bullet" => 8226,
  "bump" => 8782,
  "bumpE" => 10926,
  "bumpe" => 8783,
  "bumpeq" => 8783,
  "cacute" => 263,
  "cap" => 8745,
  "capand" => 10820,
  "capbrcup" => 10825,
  "capcap" => 10827,
  "capcup" => 10823,
  "capdot" => 10816,
  "caps" => 8745,
  "caret" => 8257,
  "caron" => 711,
  "ccaps" => 10829,
  "ccaron" => 269,
  "ccedil" => 231,
  "ccirc" => 265,
  "ccups" => 10828,
  "ccupssm" => 10832,
  "cdot" => 267,
  "cedil" => 184,
  "cemptyv" => 10674,
  "cent" => 162,
  "centerdot" => 183,
  "cfr" => 120096,
  "chcy" => 1095,
  "check" => 10003,
  "checkmark" => 10003,
  "chi" => 967,
  "cir" => 9675,
  "cirE" => 10691,
  "circ" => 710,
  "circeq" => 8791,
  "circlearrowleft" => 8634,
  "circlearrowright" => 8635,
  "circledR" => 174,
  "circledS" => 9416,
  "circledast" => 8859,
  "circledcirc" => 8858,
  "circleddash" => 8861,
  "cire" => 8791,
  "cirfnint" => 10768,
  "cirmid" => 10991,
  "cirscir" => 10690,
  "clubs" => 9827,
  "clubsuit" => 9827,
  "colon" => 58,
  "colone" => 8788,
  "coloneq" => 8788,
  "comma" => 44,
  "commat" => 64,
  "comp" => 8705,
  "compfn" => 8728,
  "complement" => 8705,
  "complexes" => 8450,
  "cong" => 8773,
  "congdot" => 10861,
  "conint" => 8750,
  "copf" => 120148,
  "coprod" => 8720,
  "copy" => 169,
  "copysr" => 8471,
  "crarr" => 8629,
  "cross" => 10007,
  "cscr" => 119992,
  "csub" => 10959,
  "csube" => 10961,
  "csup" => 10960,
  "csupe" => 10962,
  "ctdot" => 8943,
  "cudarrl" => 10552,
  "cudarrr" => 10549,
  "cuepr" => 8926,
  "cuesc" => 8927,
  "cularr" => 8630,
  "cularrp" => 10557,
  "cup" => 8746,
  "cupbrcap" => 10824,
  "cupcap" => 10822,
  "cupcup" => 10826,
  "cupdot" => 8845,
  "cupor" => 10821,
  "cups" => 8746,
  "curarr" => 8631,
  "curarrm" => 10556,
  "curlyeqprec" => 8926,
  "curlyeqsucc" => 8927,
  "curlyvee" => 8910,
  "curlywedge" => 8911,
  "curren" => 164,
  "curvearrowleft" => 8630,
  "curvearrowright" => 8631,
  "cuvee" => 8910,
  "cuwed" => 8911,
  "cwconint" => 8754,
  "cwint" => 8753,
  "cylcty" => 9005,
  "dArr" => 8659,
  "dHar" => 10597,
  "dagger" => 8224,
  "daleth" => 8504,
  "darr" => 8595,
  "dash" => 8208,
  "dashv" => 8867,
  "dbkarow" => 10511,
  "dblac" => 733,
  "dcaron" => 271,
  "dcy" => 1076,
  "dd" => 8518,
  "ddagger" => 8225,
  "ddarr" => 8650,
  "ddotseq" => 10871,
  "deg" => 176,
  "delta" => 948,
  "demptyv" => 10673,
  "dfisht" => 10623,
  "dfr" => 120097,
  "dharl" => 8643,
  "dharr" => 8642,
  "diam" => 8900,
  "diamond" => 8900,
  "diamondsuit" => 9830,
  "diams" => 9830,
  "die" => 168,
  "digamma" => 989,
  "disin" => 8946,
  "div" => 247,
  "divide" => 247,
  "divideontimes" => 8903,
  "divonx" => 8903,
  "djcy" => 1106,
  "dlcorn" => 8990,
  "dlcrop" => 8973,
  "dollar" => 36,
  "dopf" => 120149,
  "dot" => 729,
  "doteq" => 8784,
  "doteqdot" => 8785,
  "dotminus" => 8760,
  "dotplus" => 8724,
  "dotsquare" => 8865,
  "doublebarwedge" => 8966,
  "downarrow" => 8595,
  "downdownarrows" => 8650,
  "downharpoonleft" => 8643,
  "downharpoonright" => 8642,
  "drbkarow" => 10512,
  "drcorn" => 8991,
  "drcrop" => 8972,
  "dscr" => 119993,
  "dscy" => 1109,
  "dsol" => 10742,
  "dstrok" => 273,
  "dtdot" => 8945,
  "dtri" => 9663,
  "dtrif" => 9662,
  "duarr" => 8693,
  "duhar" => 10607,
  "dwangle" => 10662,
  "dzcy" => 1119,
  "dzigrarr" => 10239,
  "eDDot" => 10871,
  "eDot" => 8785,
  "eacute" => 233,
  "easter" => 10862,
  "ecaron" => 283,
  "ecir" => 8790,
  "ecirc" => 234,
  "ecolon" => 8789,
  "ecy" => 1101,
  "edot" => 279,
  "ee" => 8519,
  "efDot" => 8786,
  "efr" => 120098,
  "eg" => 10906,
  "egrave" => 232,
  "egs" => 10902,
  "egsdot" => 10904,
  "el" => 10905,
  "elinters" => 9191,
  "ell" => 8467,
  "els" => 10901,
  "elsdot" => 10903,
  "emacr" => 275,
  "empty" => 8709,
  "emptyset" => 8709,
  "emptyv" => 8709,
  "emsp" => 8195,
  "emsp13" => 8196,
  "emsp14" => 8197,
  "eng" => 331,
  "ensp" => 8194,
  "eogon" => 281,
  "eopf" => 120150,
  "epar" => 8917,
  "eparsl" => 10723,
  "eplus" => 10865,
  "epsi" => 949,
  "epsilon" => 949,
  "epsiv" => 1013,
  "eqcirc" => 8790,
  "eqcolon" => 8789,
  "eqsim" => 8770,
  "eqslantgtr" => 10902,
  "eqslantless" => 10901,
  "equals" => 61,
  "equest" => 8799,
  "equiv" => 8801,
  "equivDD" => 10872,
  "eqvparsl" => 10725,
  "erDot" => 8787,
  "erarr" => 10609,
  "escr" => 8495,
  "esdot" => 8784,
  "esim" => 8770,
  "eta" => 951,
  "eth" => 240,
  "euml" => 235,
  "euro" => 8364,
  "excl" => 33,
  "exist" => 8707,
  "expectation" => 8496,
  "exponentiale" => 8519,
  "fallingdotseq" => 8786,
  "fcy" => 1092,
  "female" => 9792,
  "ffilig" => 64259,
  "fflig" => 64256,
  "ffllig" => 64260,
  "ffr" => 120099,
  "filig" => 64257,
  "fjlig" => 102,
  "flat" => 9837,
  "fllig" => 64258,
  "fltns" => 9649,
  "fnof" => 402,
  "fopf" => 120151,
  "forall" => 8704,
  "fork" => 8916,
  "forkv" => 10969,
  "fpartint" => 10765,
  "frac12" => 189,
  "frac13" => 8531,
  "frac14" => 188,
  "frac15" => 8533,
  "frac16" => 8537,
  "frac18" => 8539,
  "frac23" => 8532,
  "frac25" => 8534,
  "frac34" => 190,
  "frac35" => 8535,
  "frac38" => 8540,
  "frac45" => 8536,
  "frac56" => 8538,
  "frac58" => 8541,
  "frac78" => 8542,
  "frasl" => 8260,
  "frown" => 8994,
  "fscr" => 119995,
  "gE" => 8807,
  "gEl" => 10892,
  "gacute" => 501,
  "gamma" => 947,
  "gammad" => 989,
  "gap" => 10886,
  "gbreve" => 287,
  "gcirc" => 285,
  "gcy" => 1075,
  "gdot" => 289,
  "ge" => 8805,
  "gel" => 8923,
  "geq" => 8805,
  "geqq" => 8807,
  "geqslant" => 10878,
  "ges" => 10878,
  "gescc" => 10921,
  "gesdot" => 10880,
  "gesdoto" => 10882,
  "gesdotol" => 10884,
  "gesl" => 8923,
  "gesles" => 10900,
  "gfr" => 120100,
  "gg" => 8811,
  "ggg" => 8921,
  "gimel" => 8503,
  "gjcy" => 1107,
  "gl" => 8823,
  "glE" => 10898,
  "gla" => 10917,
  "glj" => 10916,
  "gnE" => 8809,
  "gnap" => 10890,
  "gnapprox" => 10890,
  "gne" => 10888,
  "gneq" => 10888,
  "gneqq" => 8809,
  "gnsim" => 8935,
  "gopf" => 120152,
  "grave" => 96,
  "gscr" => 8458,
  "gsim" => 8819,
  "gsime" => 10894,
  "gsiml" => 10896,
  "gt" => 62,
  "gtcc" => 10919,
  "gtcir" => 10874,
  "gtdot" => 8919,
  "gtlPar" => 10645,
  "gtquest" => 10876,
  "gtrapprox" => 10886,
  "gtrarr" => 10616,
  "gtrdot" => 8919,
  "gtreqless" => 8923,
  "gtreqqless" => 10892,
  "gtrless" => 8823,
  "gtrsim" => 8819,
  "gvertneqq" => 8809,
  "gvnE" => 8809,
  "hArr" => 8660,
  "hairsp" => 8202,
  "half" => 189,
  "hamilt" => 8459,
  "hardcy" => 1098,
  "harr" => 8596,
  "harrcir" => 10568,
  "harrw" => 8621,
  "hbar" => 8463,
  "hcirc" => 293,
  "hearts" => 9829,
  "heartsuit" => 9829,
  "hellip" => 8230,
  "hercon" => 8889,
  "hfr" => 120101,
  "hksearow" => 10533,
  "hkswarow" => 10534,
  "hoarr" => 8703,
  "homtht" => 8763,
  "hookleftarrow" => 8617,
  "hookrightarrow" => 8618,
  "hopf" => 120153,
  "horbar" => 8213,
  "hscr" => 119997,
  "hslash" => 8463,
  "hstrok" => 295,
  "hybull" => 8259,
  "hyphen" => 8208,
  "iacute" => 237,
  "ic" => 8291,
  "icirc" => 238,
  "icy" => 1080,
  "iecy" => 1077,
  "iexcl" => 161,
  "iff" => 8660,
  "ifr" => 120102,
  "igrave" => 236,
  "ii" => 8520,
  "iiiint" => 10764,
  "iiint" => 8749,
  "iinfin" => 10716,
  "iiota" => 8489,
  "ijlig" => 307,
  "imacr" => 299,
  "image" => 8465,
  "imagline" => 8464,
  "imagpart" => 8465,
  "imath" => 305,
  "imof" => 8887,
  "imped" => 437,
  "in" => 8712,
  "incare" => 8453,
  "infin" => 8734,
  "infintie" => 10717,
  "inodot" => 305,
  "int" => 8747,
  "intcal" => 8890,
  "integers" => 8484,
  "intercal" => 8890,
  "intlarhk" => 10775,
  "intprod" => 10812,
  "iocy" => 1105,
  "iogon" => 303,
  "iopf" => 120154,
  "iota" => 953,
  "iprod" => 10812,
  "iquest" => 191,
  "iscr" => 119998,
  "isin" => 8712,
  "isinE" => 8953,
  "isindot" => 8949,
  "isins" => 8948,
  "isinsv" => 8947,
  "isinv" => 8712,
  "it" => 8290,
  "itilde" => 297,
  "iukcy" => 1110,
  "iuml" => 239,
  "jcirc" => 309,
  "jcy" => 1081,
  "jfr" => 120103,
  "jmath" => 567,
  "jopf" => 120155,
  "jscr" => 119999,
  "jsercy" => 1112,
  "jukcy" => 1108,
  "kappa" => 954,
  "kappav" => 1008,
  "kcedil" => 311,
  "kcy" => 1082,
  "kfr" => 120104,
  "kgreen" => 312,
  "khcy" => 1093,
  "kjcy" => 1116,
  "kopf" => 120156,
  "kscr" => 120000,
  "lAarr" => 8666,
  "lArr" => 8656,
  "lAtail" => 10523,
  "lBarr" => 10510,
  "lE" => 8806,
  "lEg" => 10891,
  "lHar" => 10594,
  "lacute" => 314,
  "laemptyv" => 10676,
  "lagran" => 8466,
  "lambda" => 955,
  "lang" => 10216,
  "langd" => 10641,
  "langle" => 10216,
  "lap" => 10885,
  "laquo" => 171,
  "larr" => 8592,
  "larrb" => 8676,
  "larrbfs" => 10527,
  "larrfs" => 10525,
  "larrhk" => 8617,
  "larrlp" => 8619,
  "larrpl" => 10553,
  "larrsim" => 10611,
  "larrtl" => 8610,
  "lat" => 10923,
  "latail" => 10521,
  "late" => 10925,
  "lates" => 10925,
  "lbarr" => 10508,
  "lbbrk" => 10098,
  "lbrace" => 123,
  "lbrack" => 91,
  "lbrke" => 10635,
  "lbrksld" => 10639,
  "lbrkslu" => 10637,
  "lcaron" => 318,
  "lcedil" => 316,
  "lceil" => 8968,
  "lcub" => 123,
  "lcy" => 1083,
  "ldca" => 10550,
  "ldquo" => 8220,
  "ldquor" => 8222,
  "ldrdhar" => 10599,
  "ldrushar" => 10571,
  "ldsh" => 8626,
  "le" => 8804,
  "leftarrow" => 8592,
  "leftarrowtail" => 8610,
  "leftharpoondown" => 8637,
  "leftharpoonup" => 8636,
  "leftleftarrows" => 8647,
  "leftrightarrow" => 8596,
  "leftrightarrows" => 8646,
  "leftrightharpoons" => 8651,
  "leftrightsquigarrow" => 8621,
  "leftthreetimes" => 8907,
  "leg" => 8922,
  "leq" => 8804,
  "leqq" => 8806,
  "leqslant" => 10877,
  "les" => 10877,
  "lescc" => 10920,
  "lesdot" => 10879,
  "lesdoto" => 10881,
  "lesdotor" => 10883,
  "lesg" => 8922,
  "lesges" => 10899,
  "lessapprox" => 10885,
  "lessdot" => 8918,
  "lesseqgtr" => 8922,
  "lesseqqgtr" => 10891,
  "lessgtr" => 8822,
  "lesssim" => 8818,
  "lfisht" => 10620,
  "lfloor" => 8970,
  "lfr" => 120105,
  "lg" => 8822,
  "lgE" => 10897,
  "lhard" => 8637,
  "lharu" => 8636,
  "lharul" => 10602,
  "lhblk" => 9604,
  "ljcy" => 1113,
  "ll" => 8810,
  "llarr" => 8647,
  "llcorner" => 8990,
  "llhard" => 10603,
  "lltri" => 9722,
  "lmidot" => 320,
  "lmoust" => 9136,
  "lmoustache" => 9136,
  "lnE" => 8808,
  "lnap" => 10889,
  "lnapprox" => 10889,
  "lne" => 10887,
  "lneq" => 10887,
  "lneqq" => 8808,
  "lnsim" => 8934,
  "loang" => 10220,
  "loarr" => 8701,
  "lobrk" => 10214,
  "longleftarrow" => 10229,
  "longleftrightarrow" => 10231,
  "longmapsto" => 10236,
  "longrightarrow" => 10230,
  "looparrowleft" => 8619,
  "looparrowright" => 8620,
  "lopar" => 10629,
  "lopf" => 120157,
  "loplus" => 10797,
  "lotimes" => 10804,
  "lowast" => 8727,
  "lowbar" => 95,
  "loz" => 9674,
  "lozenge" => 9674,
  "lozf" => 10731,
  "lpar" => 40,
  "lparlt" => 10643,
  "lrarr" => 8646,
  "lrcorner" => 8991,
  "lrhar" => 8651,
  "lrhard" => 10605,
  "lrm" => 8206,
  "lrtri" => 8895,
  "lsaquo" => 8249,
  "lscr" => 120001,
  "lsh" => 8624,
  "lsim" => 8818,
  "lsime" => 10893,
  "lsimg" => 10895,
  "lsqb" => 91,
  "lsquo" => 8216,
  "lsquor" => 8218,
  "lstrok" => 322,
  "lt" => 60,
  "ltcc" => 10918,
  "ltcir" => 10873,
  "ltdot" => 8918,
  "lthree" => 8907,
  "ltimes" => 8905,
  "ltlarr" => 10614,
  "ltquest" => 10875,
  "ltrPar" => 10646,
  "ltri" => 9667,
  "ltrie" => 8884,
  "ltrif" => 9666,
  "lurdshar" => 10570,
  "luruhar" => 10598,
  "lvertneqq" => 8808,
  "lvnE" => 8808,
  "mDDot" => 8762,
  "macr" => 175,
  "male" => 9794,
  "malt" => 10016,
  "maltese" => 10016,
  "map" => 8614,
  "mapsto" => 8614,
  "mapstodown" => 8615,
  "mapstoleft" => 8612,
  "mapstoup" => 8613,
  "marker" => 9646,
  "mcomma" => 10793,
  "mcy" => 1084,
  "mdash" => 8212,
  "measuredangle" => 8737,
  "mfr" => 120106,
  "mho" => 8487,
  "micro" => 181,
  "mid" => 8739,
  "midast" => 42,
  "midcir" => 10992,
  "middot" => 183,
  "minus" => 8722,
  "minusb" => 8863,
  "minusd" => 8760,
  "minusdu" => 10794,
  "mlcp" => 10971,
  "mldr" => 8230,
  "mnplus" => 8723,
  "models" => 8871,
  "mopf" => 120158,
  "mp" => 8723,
  "mscr" => 120002,
  "mstpos" => 8766,
  "mu" => 956,
  "multimap" => 8888,
  "mumap" => 8888,
  "nGg" => 8921,
  "nGt" => 8811,
  "nGtv" => 8811,
  "nLeftarrow" => 8653,
  "nLeftrightarrow" => 8654,
  "nLl" => 8920,
  "nLt" => 8810,
  "nLtv" => 8810,
  "nRightarrow" => 8655,
  "nVDash" => 8879,
  "nVdash" => 8878,
  "nabla" => 8711,
  "nacute" => 324,
  "nang" => 8736,
  "nap" => 8777,
  "napE" => 10864,
  "napid" => 8779,
  "napos" => 329,
  "napprox" => 8777,
  "natur" => 9838,
  "natural" => 9838,
  "naturals" => 8469,
  "nbsp" => 160,
  "nbump" => 8782,
  "nbumpe" => 8783,
  "ncap" => 10819,
  "ncaron" => 328,
  "ncedil" => 326,
  "ncong" => 8775,
  "ncongdot" => 10861,
  "ncup" => 10818,
  "ncy" => 1085,
  "ndash" => 8211,
  "ne" => 8800,
  "neArr" => 8663,
  "nearhk" => 10532,
  "nearr" => 8599,
  "nearrow" => 8599,
  "nedot" => 8784,
  "nequiv" => 8802,
  "nesear" => 10536,
  "nesim" => 8770,
  "nexist" => 8708,
  "nexists" => 8708,
  "nfr" => 120107,
  "ngE" => 8807,
  "nge" => 8817,
  "ngeq" => 8817,
  "ngeqq" => 8807,
  "ngeqslant" => 10878,
  "nges" => 10878,
  "ngsim" => 8821,
  "ngt" => 8815,
  "ngtr" => 8815,
  "nhArr" => 8654,
  "nharr" => 8622,
  "nhpar" => 10994,
  "ni" => 8715,
  "nis" => 8956,
  "nisd" => 8954,
  "niv" => 8715,
  "njcy" => 1114,
  "nlArr" => 8653,
  "nlE" => 8806,
  "nlarr" => 8602,
  "nldr" => 8229,
  "nle" => 8816,
  "nleftarrow" => 8602,
  "nleftrightarrow" => 8622,
  "nleq" => 8816,
  "nleqq" => 8806,
  "nleqslant" => 10877,
  "nles" => 10877,
  "nless" => 8814,
  "nlsim" => 8820,
  "nlt" => 8814,
  "nltri" => 8938,
  "nltrie" => 8940,
  "nmid" => 8740,
  "nopf" => 120159,
  "not" => 172,
  "notin" => 8713,
  "notinE" => 8953,
  "notindot" => 8949,
  "notinva" => 8713,
  "notinvb" => 8951,
  "notinvc" => 8950,
  "notni" => 8716,
  "notniva" => 8716,
  "notnivb" => 8958,
  "notnivc" => 8957,
  "npar" => 8742,
  "nparallel" => 8742,
  "nparsl" => 11005,
  "npart" => 8706,
  "npolint" => 10772,
  "npr" => 8832,
  "nprcue" => 8928,
  "npre" => 10927,
  "nprec" => 8832,
  "npreceq" => 10927,
  "nrArr" => 8655,
  "nrarr" => 8603,
  "nrarrc" => 10547,
  "nrarrw" => 8605,
  "nrightarrow" => 8603,
  "nrtri" => 8939,
  "nrtrie" => 8941,
  "nsc" => 8833,
  "nsccue" => 8929,
  "nsce" => 10928,
  "nscr" => 120003,
  "nshortmid" => 8740,
  "nshortparallel" => 8742,
  "nsim" => 8769,
  "nsime" => 8772,
  "nsimeq" => 8772,
  "nsmid" => 8740,
  "nspar" => 8742,
  "nsqsube" => 8930,
  "nsqsupe" => 8931,
  "nsub" => 8836,
  "nsubE" => 10949,
  "nsube" => 8840,
  "nsubset" => 8834,
  "nsubseteq" => 8840,
  "nsubseteqq" => 10949,
  "nsucc" => 8833,
  "nsucceq" => 10928,
  "nsup" => 8837,
  "nsupE" => 10950,
  "nsupe" => 8841,
  "nsupset" => 8835,
  "nsupseteq" => 8841,
  "nsupseteqq" => 10950,
  "ntgl" => 8825,
  "ntilde" => 241,
  "ntlg" => 8824,
  "ntriangleleft" => 8938,
  "ntrianglelefteq" => 8940,
  "ntriangleright" => 8939,
  "ntrianglerighteq" => 8941,
  "nu" => 957,
  "num" => 35,
  "numero" => 8470,
  "numsp" => 8199,
  "nvDash" => 8877,
  "nvHarr" => 10500,
  "nvap" => 8781,
  "nvdash" => 8876,
  "nvge" => 8805,
  "nvgt" => 62,
  "nvinfin" => 10718,
  "nvlArr" => 10498,
  "nvle" => 8804,
  "nvlt" => 60,
  "nvltrie" => 8884,
  "nvrArr" => 10499,
  "nvrtrie" => 8885,
  "nvsim" => 8764,
  "nwArr" => 8662,
  "nwarhk" => 10531,
  "nwarr" => 8598,
  "nwarrow" => 8598,
  "nwnear" => 10535,
  "oS" => 9416,
  "oacute" => 243,
  "oast" => 8859,
  "ocir" => 8858,
  "ocirc" => 244,
  "ocy" => 1086,
  "odash" => 8861,
  "odblac" => 337,
  "odiv" => 10808,
  "odot" => 8857,
  "odsold" => 10684,
  "oelig" => 339,
  "ofcir" => 10687,
  "ofr" => 120108,
  "ogon" => 731,
  "ograve" => 242,
  "ogt" => 10689,
  "ohbar" => 10677,
  "ohm" => 937,
  "oint" => 8750,
  "olarr" => 8634,
  "olcir" => 10686,
  "olcross" => 10683,
  "oline" => 8254,
  "olt" => 10688,
  "omacr" => 333,
  "omega" => 969,
  "omicron" => 959,
  "omid" => 10678,
  "ominus" => 8854,
  "oopf" => 120160,
  "opar" => 10679,
  "operp" => 10681,
  "oplus" => 8853,
  "or" => 8744,
  "orarr" => 8635,
  "ord" => 10845,
  "order" => 8500,
  "orderof" => 8500,
  "ordf" => 170,
  "ordm" => 186,
  "origof" => 8886,
  "oror" => 10838,
  "orslope" => 10839,
  "orv" => 10843,
  "oscr" => 8500,
  "oslash" => 248,
  "osol" => 8856,
  "otilde" => 245,
  "otimes" => 8855,
  "otimesas" => 10806,
  "ouml" => 246,
  "ovbar" => 9021,
  "par" => 8741,
  "para" => 182,
  "parallel" => 8741,
  "parsim" => 10995,
  "parsl" => 11005,
  "part" => 8706,
  "pcy" => 1087,
  "percnt" => 37,
  "period" => 46,
  "permil" => 8240,
  "perp" => 8869,
  "pertenk" => 8241,
  "pfr" => 120109,
  "phi" => 966,
  "phiv" => 981,
  "phmmat" => 8499,
  "phone" => 9742,
  "pi" => 960,
  "pitchfork" => 8916,
  "piv" => 982,
  "planck" => 8463,
  "planckh" => 8462,
  "plankv" => 8463,
  "plus" => 43,
  "plusacir" => 10787,
  "plusb" => 8862,
  "pluscir" => 10786,
  "plusdo" => 8724,
  "plusdu" => 10789,
  "pluse" => 10866,
  "plusmn" => 177,
  "plussim" => 10790,
  "plustwo" => 10791,
  "pm" => 177,
  "pointint" => 10773,
  "popf" => 120161,
  "pound" => 163,
  "pr" => 8826,
  "prE" => 10931,
  "prap" => 10935,
  "prcue" => 8828,
  "pre" => 10927,
  "prec" => 8826,
  "precapprox" => 10935,
  "preccurlyeq" => 8828,
  "preceq" => 10927,
  "precnapprox" => 10937,
  "precneqq" => 10933,
  "precnsim" => 8936,
  "precsim" => 8830,
  "prime" => 8242,
  "primes" => 8473,
  "prnE" => 10933,
  "prnap" => 10937,
  "prnsim" => 8936,
  "prod" => 8719,
  "profalar" => 9006,
  "profline" => 8978,
  "profsurf" => 8979,
  "prop" => 8733,
  "propto" => 8733,
  "prsim" => 8830,
  "prurel" => 8880,
  "pscr" => 120005,
  "psi" => 968,
  "puncsp" => 8200,
  "qfr" => 120110,
  "qint" => 10764,
  "qopf" => 120162,
  "qprime" => 8279,
  "qscr" => 120006,
  "quaternions" => 8461,
  "quatint" => 10774,
  "quest" => 63,
  "questeq" => 8799,
  "quot" => 34,
  "rAarr" => 8667,
  "rArr" => 8658,
  "rAtail" => 10524,
  "rBarr" => 10511,
  "rHar" => 10596,
  "race" => 8765,
  "racute" => 341,
  "radic" => 8730,
  "raemptyv" => 10675,
  "rang" => 10217,
  "rangd" => 10642,
  "range" => 10661,
  "rangle" => 10217,
  "raquo" => 187,
  "rarr" => 8594,
  "rarrap" => 10613,
  "rarrb" => 8677,
  "rarrbfs" => 10528,
  "rarrc" => 10547,
  "rarrfs" => 10526,
  "rarrhk" => 8618,
  "rarrlp" => 8620,
  "rarrpl" => 10565,
  "rarrsim" => 10612,
  "rarrtl" => 8611,
  "rarrw" => 8605,
  "ratail" => 10522,
  "ratio" => 8758,
  "rationals" => 8474,
  "rbarr" => 10509,
  "rbbrk" => 10099,
  "rbrace" => 125,
  "rbrack" => 93,
  "rbrke" => 10636,
  "rbrksld" => 10638,
  "rbrkslu" => 10640,
  "rcaron" => 345,
  "rcedil" => 343,
  "rceil" => 8969,
  "rcub" => 125,
  "rcy" => 1088,
  "rdca" => 10551,
  "rdldhar" => 10601,
  "rdquo" => 8221,
  "rdquor" => 8221,
  "rdsh" => 8627,
  "real" => 8476,
  "realine" => 8475,
  "realpart" => 8476,
  "reals" => 8477,
  "rect" => 9645,
  "reg" => 174,
  "rfisht" => 10621,
  "rfloor" => 8971,
  "rfr" => 120111,
  "rhard" => 8641,
  "rharu" => 8640,
  "rharul" => 10604,
  "rho" => 961,
  "rhov" => 1009,
  "rightarrow" => 8594,
  "rightarrowtail" => 8611,
  "rightharpoondown" => 8641,
  "rightharpoonup" => 8640,
  "rightleftarrows" => 8644,
  "rightleftharpoons" => 8652,
  "rightrightarrows" => 8649,
  "rightsquigarrow" => 8605,
  "rightthreetimes" => 8908,
  "ring" => 730,
  "risingdotseq" => 8787,
  "rlarr" => 8644,
  "rlhar" => 8652,
  "rlm" => 8207,
  "rmoust" => 9137,
  "rmoustache" => 9137,
  "rnmid" => 10990,
  "roang" => 10221,
  "roarr" => 8702,
  "robrk" => 10215,
  "ropar" => 10630,
  "ropf" => 120163,
  "roplus" => 10798,
  "rotimes" => 10805,
  "rpar" => 41,
  "rpargt" => 10644,
  "rppolint" => 10770,
  "rrarr" => 8649,
  "rsaquo" => 8250,
  "rscr" => 120007,
  "rsh" => 8625,
  "rsqb" => 93,
  "rsquo" => 8217,
  "rsquor" => 8217,
  "rthree" => 8908,
  "rtimes" => 8906,
  "rtri" => 9657,
  "rtrie" => 8885,
  "rtrif" => 9656,
  "rtriltri" => 10702,
  "ruluhar" => 10600,
  "rx" => 8478,
  "sacute" => 347,
  "sbquo" => 8218,
  "sc" => 8827,
  "scE" => 10932,
  "scap" => 10936,
  "scaron" => 353,
  "sccue" => 8829,
  "sce" => 10928,
  "scedil" => 351,
  "scirc" => 349,
  "scnE" => 10934,
  "scnap" => 10938,
  "scnsim" => 8937,
  "scpolint" => 10771,
  "scsim" => 8831,
  "scy" => 1089,
  "sdot" => 8901,
  "sdotb" => 8865,
  "sdote" => 10854,
  "seArr" => 8664,
  "searhk" => 10533,
  "searr" => 8600,
  "searrow" => 8600,
  "sect" => 167,
  "semi" => 59,
  "seswar" => 10537,
  "setminus" => 8726,
  "setmn" => 8726,
  "sext" => 10038,
  "sfr" => 120112,
  "sfrown" => 8994,
  "sharp" => 9839,
  "shchcy" => 1097,
  "shcy" => 1096,
  "shortmid" => 8739,
  "shortparallel" => 8741,
  "shy" => 173,
  "sigma" => 963,
  "sigmaf" => 962,
  "sigmav" => 962,
  "sim" => 8764,
  "simdot" => 10858,
  "sime" => 8771,
  "simeq" => 8771,
  "simg" => 10910,
  "simgE" => 10912,
  "siml" => 10909,
  "simlE" => 10911,
  "simne" => 8774,
  "simplus" => 10788,
  "simrarr" => 10610,
  "slarr" => 8592,
  "smallsetminus" => 8726,
  "smashp" => 10803,
  "smeparsl" => 10724,
  "smid" => 8739,
  "smile" => 8995,
  "smt" => 10922,
  "smte" => 10924,
  "smtes" => 10924,
  "softcy" => 1100,
  "sol" => 47,
  "solb" => 10692,
  "solbar" => 9023,
  "sopf" => 120164,
  "spades" => 9824,
  "spadesuit" => 9824,
  "spar" => 8741,
  "sqcap" => 8851,
  "sqcaps" => 8851,
  "sqcup" => 8852,
  "sqcups" => 8852,
  "sqsub" => 8847,
  "sqsube" => 8849,
  "sqsubset" => 8847,
  "sqsubseteq" => 8849,
  "sqsup" => 8848,
  "sqsupe" => 8850,
  "sqsupset" => 8848,
  "sqsupseteq" => 8850,
  "squ" => 9633,
  "square" => 9633,
  "squarf" => 9642,
  "squf" => 9642,
  "srarr" => 8594,
  "sscr" => 120008,
  "ssetmn" => 8726,
  "ssmile" => 8995,
  "sstarf" => 8902,
  "star" => 9734,
  "starf" => 9733,
  "straightepsilon" => 1013,
  "straightphi" => 981,
  "strns" => 175,
  "sub" => 8834,
  "subE" => 10949,
  "subdot" => 10941,
  "sube" => 8838,
  "subedot" => 10947,
  "submult" => 10945,
  "subnE" => 10955,
  "subne" => 8842,
  "subplus" => 10943,
  "subrarr" => 10617,
  "subset" => 8834,
  "subseteq" => 8838,
  "subseteqq" => 10949,
  "subsetneq" => 8842,
  "subsetneqq" => 10955,
  "subsim" => 10951,
  "subsub" => 10965,
  "subsup" => 10963,
  "succ" => 8827,
  "succapprox" => 10936,
  "succcurlyeq" => 8829,
  "succeq" => 10928,
  "succnapprox" => 10938,
  "succneqq" => 10934,
  "succnsim" => 8937,
  "succsim" => 8831,
  "sum" => 8721,
  "sung" => 9834,
  "sup" => 8835,
  "sup1" => 185,
  "sup2" => 178,
  "sup3" => 179,
  "supE" => 10950,
  "supdot" => 10942,
  "supdsub" => 10968,
  "supe" => 8839,
  "supedot" => 10948,
  "suphsol" => 10185,
  "suphsub" => 10967,
  "suplarr" => 10619,
  "supmult" => 10946,
  "supnE" => 10956,
  "supne" => 8843,
  "supplus" => 10944,
  "supset" => 8835,
  "supseteq" => 8839,
  "supseteqq" => 10950,
  "supsetneq" => 8843,
  "supsetneqq" => 10956,
  "supsim" => 10952,
  "supsub" => 10964,
  "supsup" => 10966,
  "swArr" => 8665,
  "swarhk" => 10534,
  "swarr" => 8601,
  "swarrow" => 8601,
  "swnwar" => 10538,
  "szlig" => 223,
  "target" => 8982,
  "tau" => 964,
  "tbrk" => 9140,
  "tcaron" => 357,
  "tcedil" => 355,
  "tcy" => 1090,
  "tdot" => 32,
  "telrec" => 8981,
  "tfr" => 120113,
  "there4" => 8756,
  "therefore" => 8756,
  "theta" => 952,
  "thetasym" => 977,
  "thetav" => 977,
  "thickapprox" => 8776,
  "thicksim" => 8764,
  "thinsp" => 8201,
  "thkap" => 8776,
  "thksim" => 8764,
  "thorn" => 254,
  "tilde" => 732,
  "times" => 215,
  "timesb" => 8864,
  "timesbar" => 10801,
  "timesd" => 10800,
  "tint" => 8749,
  "toea" => 10536,
  "top" => 8868,
  "topbot" => 9014,
  "topcir" => 10993,
  "topf" => 120165,
  "topfork" => 10970,
  "tosa" => 10537,
  "tprime" => 8244,
  "trade" => 8482,
  "triangle" => 9653,
  "triangledown" => 9663,
  "triangleleft" => 9667,
  "trianglelefteq" => 8884,
  "triangleq" => 8796,
  "triangleright" => 9657,
  "trianglerighteq" => 8885,
  "tridot" => 9708,
  "trie" => 8796,
  "triminus" => 10810,
  "triplus" => 10809,
  "trisb" => 10701,
  "tritime" => 10811,
  "trpezium" => 9186,
  "tscr" => 120009,
  "tscy" => 1094,
  "tshcy" => 1115,
  "tstrok" => 359,
  "twixt" => 8812,
  "twoheadleftarrow" => 8606,
  "twoheadrightarrow" => 8608,
  "uArr" => 8657,
  "uHar" => 10595,
  "uacute" => 250,
  "uarr" => 8593,
  "ubrcy" => 1118,
  "ubreve" => 365,
  "ucirc" => 251,
  "ucy" => 1091,
  "udarr" => 8645,
  "udblac" => 369,
  "udhar" => 10606,
  "ufisht" => 10622,
  "ufr" => 120114,
  "ugrave" => 249,
  "uharl" => 8639,
  "uharr" => 8638,
  "uhblk" => 9600,
  "ulcorn" => 8988,
  "ulcorner" => 8988,
  "ulcrop" => 8975,
  "ultri" => 9720,
  "umacr" => 363,
  "uml" => 168,
  "uogon" => 371,
  "uopf" => 120166,
  "uparrow" => 8593,
  "updownarrow" => 8597,
  "upharpoonleft" => 8639,
  "upharpoonright" => 8638,
  "uplus" => 8846,
  "upsi" => 965,
  "upsih" => 978,
  "upsilon" => 965,
  "upuparrows" => 8648,
  "urcorn" => 8989,
  "urcorner" => 8989,
  "urcrop" => 8974,
  "uring" => 367,
  "urtri" => 9721,
  "uscr" => 120010,
  "utdot" => 8944,
  "utilde" => 361,
  "utri" => 9653,
  "utrif" => 9652,
  "uuarr" => 8648,
  "uuml" => 252,
  "uwangle" => 10663,
  "vArr" => 8661,
  "vBar" => 10984,
  "vBarv" => 10985,
  "vDash" => 8872,
  "vangrt" => 10652,
  "varepsilon" => 1013,
  "varkappa" => 1008,
  "varnothing" => 8709,
  "varphi" => 981,
  "varpi" => 982,
  "varpropto" => 8733,
  "varr" => 8597,
  "varrho" => 1009,
  "varsigma" => 962,
  "varsubsetneq" => 8842,
  "varsubsetneqq" => 10955,
  "varsupsetneq" => 8843,
  "varsupsetneqq" => 10956,
  "vartheta" => 977,
  "vartriangleleft" => 8882,
  "vartriangleright" => 8883,
  "vcy" => 1074,
  "vdash" => 8866,
  "vee" => 8744,
  "veebar" => 8891,
  "veeeq" => 8794,
  "vellip" => 8942,
  "verbar" => 124,
  "vert" => 124,
  "vfr" => 120115,
  "vltri" => 8882,
  "vnsub" => 8834,
  "vnsup" => 8835,
  "vopf" => 120167,
  "vprop" => 8733,
  "vrtri" => 8883,
  "vscr" => 120011,
  "vsubnE" => 10955,
  "vsubne" => 8842,
  "vsupnE" => 10956,
  "vsupne" => 8843,
  "vzigzag" => 10650,
  "wcirc" => 373,
  "wedbar" => 10847,
  "wedge" => 8743,
  "wedgeq" => 8793,
  "weierp" => 8472,
  "wfr" => 120116,
  "wopf" => 120168,
  "wp" => 8472,
  "wr" => 8768,
  "wreath" => 8768,
  "wscr" => 120012,
  "xcap" => 8898,
  "xcirc" => 9711,
  "xcup" => 8899,
  "xdtri" => 9661,
  "xfr" => 120117,
  "xhArr" => 10234,
  "xharr" => 10231,
  "xi" => 958,
  "xlArr" => 10232,
  "xlarr" => 10229,
  "xmap" => 10236,
  "xnis" => 8955,
  "xodot" => 10752,
  "xopf" => 120169,
  "xoplus" => 10753,
  "xotime" => 10754,
  "xrArr" => 10233,
  "xrarr" => 10230,
  "xscr" => 120013,
  "xsqcup" => 10758,
  "xuplus" => 10756,
  "xutri" => 9651,
  "xvee" => 8897,
  "xwedge" => 8896,
  "yacute" => 253,
  "yacy" => 1103,
  "ycirc" => 375,
  "ycy" => 1099,
  "yen" => 165,
  "yfr" => 120118,
  "yicy" => 1111,
  "yopf" => 120170,
  "yscr" => 120014,
  "yucy" => 1102,
  "yuml" => 255,
  "zacute" => 378,
  "zcaron" => 382,
  "zcy" => 1079,
  "zdot" => 380,
  "zeetrf" => 8488,
  "zeta" => 950,
  "zfr" => 120119,
  "zhcy" => 1078,
  "zigrarr" => 8669,
  "zopf" => 120171,
  "zscr" => 120015,
  "zwj" => 8205,
  "zwnj" => 8204,
}.freeze

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(mode: :required, entity_provider: nil) ⇒ EntityRegistry

Returns a new instance of EntityRegistry.

Parameters:

  • mode (Symbol) (defaults to: :required) —

    Loading mode: :required, :optional, :disabled, :custom

  • entity_provider (Proc, nil) (defaults to: nil) —

    Custom entity provider proc/lambda



119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
 
# File 'lib/moxml/entity_registry.rb', line 119

def initialize(mode: :required, entity_provider: nil)
  @by_name = {}
  @by_codepoint = Hash.new { |h, k| h[k] = [] }
  @mode = mode
  @entity_provider = entity_provider

  case mode
  when :required
    load_from_entity_data
  when :optional
    load_from_entity_data_optional
  when :custom
    load_custom_entities
  when :disabled
    # Don't load anything - empty registry
  end
end

Instance Attribute Details

#by_codepoint ⇒ Hash{Integer => Array<String>} (readonly)

Returns codepoint to entity names mapping.

Returns:

  • (Hash{Integer => Array<String>}) —

    codepoint to entity names mapping



115
116
117
 
# File 'lib/moxml/entity_registry.rb', line 115

def by_codepoint
  @by_codepoint
end

#by_name ⇒ Hash{String => Integer} (readonly)

Returns entity name to codepoint mapping.

Returns:

  • (Hash{String => Integer}) —

    entity name to codepoint mapping



112
113
114
 
# File 'lib/moxml/entity_registry.rb', line 112

def by_name
  @by_name
end

Class Method Details

.default ⇒ EntityRegistry

Get the default registry instance (lazy loaded)

Returns:



43
44
45
 
# File 'lib/moxml/entity_registry.rb', line 43

def default
  @default ||= new
end

.entity_data ⇒ Hash{String => String}

Get the raw entity data from the bundled JSON source

Returns:

  • (Hash{String => String}) —

    entity name to character mapping



37
38
39
 
# File 'lib/moxml/entity_registry.rb', line 37

def entity_data
  @entity_data ||= load_entity_data
end

.reset ⇒ void

This method returns an undefined value.

Reset the default registry (mainly for testing)



49
50
51
52
 
# File 'lib/moxml/entity_registry.rb', line 49

def reset
  @default = nil
  @entity_data = nil
end

Instance Method Details

#clear! ⇒ self

Clear all entities (reset to empty)

Returns:

  • (self) 


263
264
265
266
267
 
# File 'lib/moxml/entity_registry.rb', line 263

def clear!
  @by_name = {}
  @by_codepoint = Hash.new { |h, k| h[k] = [] }
  self
end

#codepoint_for_name(name) ⇒ Integer?

Get the Unicode codepoint for an entity name

Parameters:

  • name (String) —

    entity name

Returns:

  • (Integer, nil) —

    codepoint or nil if not found



147
148
149
 
# File 'lib/moxml/entity_registry.rb', line 147

def codepoint_for_name(name)
  @by_name[name]
end

#declared?(name) ⇒ Boolean

Check if an entity name is declared

Parameters:

  • name (String) —

    entity name (e.g., “amp”, “nbsp”)

Returns:

  • (Boolean) 


140
141
142
 
# File 'lib/moxml/entity_registry.rb', line 140

def declared?(name)
  @by_name.key?(name)
end

#load_all ⇒ self

Load all standard entity sets. All entities are loaded during initialize; this method is a no-op kept for backward compatibility.

Returns:

  • (self) 


256
257
258
259
 
# File 'lib/moxml/entity_registry.rb', line 256

def load_all
  warn "EntityRegistry#load_all is a no-op (all entities load during initialize)", uplevel: 1
  self
end

#load_html5 ⇒ self

Load all entities from the W3C HTMLMathML entity set. All entities are loaded during initialize; this method is a no-op kept for backward compatibility.

Returns:

  • (self) 


228
229
230
231
 
# File 'lib/moxml/entity_registry.rb', line 228

def load_html5
  warn "EntityRegistry#load_html5 is a no-op (all entities load during initialize)", uplevel: 1
  self
end

#load_iso(_set_name = :iso8879) ⇒ self

Load ISO entity sets (included in HTMLMathML). All entities are loaded during initialize; this method is a no-op kept for backward compatibility.

Parameters:

  • _set_name (Symbol) (defaults to: :iso8879) —

    (ignored, all loaded together)

Returns:

  • (self) 


247
248
249
250
 
# File 'lib/moxml/entity_registry.rb', line 247

def load_iso(_set_name = :iso8879)
  warn "EntityRegistry#load_iso is a no-op (all entities load during initialize)", uplevel: 1
  self
end

#load_mathml ⇒ self

Load MathML entity set (included in HTMLMathML). All entities are loaded during initialize; this method is a no-op kept for backward compatibility.

Returns:

  • (self) 


237
238
239
240
 
# File 'lib/moxml/entity_registry.rb', line 237

def load_mathml
  warn "EntityRegistry#load_mathml is a no-op (all entities load during initialize)", uplevel: 1
  self
end

#names_for_codepoint(codepoint) ⇒ Array<String>

Get all entity names for a codepoint

Parameters:

  • codepoint (Integer) —

    Unicode codepoint

Returns:

  • (Array<String>) —

    entity names mapping to this codepoint



154
155
156
 
# File 'lib/moxml/entity_registry.rb', line 154

def names_for_codepoint(codepoint)
  @by_codepoint[codepoint]
end

#primary_name_for_codepoint(codepoint) ⇒ String?

Get the primary (preferred) entity name for a codepoint

Parameters:

  • codepoint (Integer) —

    Unicode codepoint

Returns:

  • (String, nil) —

    primary entity name or nil



161
162
163
164
165
166
167
 
# File 'lib/moxml/entity_registry.rb', line 161

def primary_name_for_codepoint(codepoint)
  names = @by_codepoint[codepoint]
  return nil unless names&.any?

  # Prefer lowercase names (e.g., "amp" over "AMP") for XML compatibility
  names.find { |n| n == n.downcase } || names.first
end

#register(entities) ⇒ self

Register additional entities

Parameters:

  • entities (Hash{String => Integer}) —

    name => codepoint mapping

Returns:

  • (self) 


215
216
217
218
219
220
221
222
 
# File 'lib/moxml/entity_registry.rb', line 215

def register(entities)
  entities.each do |name, codepoint|
    @by_name[name] = codepoint
    @by_codepoint[codepoint] ||= []
    @by_codepoint[codepoint] << name unless @by_codepoint[codepoint].include?(name)
  end
  self
end

#restorable_codepoints ⇒ Set<Integer>

Returns the set of codepoints that could potentially be restored as entities. Used by DocumentBuilder for O(1) fast-path checks.

Returns:

  • (Set<Integer>) 


204
205
206
207
208
209
210
 
# File 'lib/moxml/entity_registry.rb', line 204

def restorable_codepoints
  @restorable_codepoints ||= if @by_name.empty?
                               STANDARD_CODEPOINTS
                             else
                               Set.new(@by_name.values).freeze
                             end
end

#should_restore?(codepoint, config:) ⇒ Boolean

Determine if an entity reference should be restored for a codepoint. Standard XML entities are always restored (required by XML spec). Non-standard entities are only restored when restore_entities is enabled.

Parameters:

  • codepoint (Integer) —

    Unicode codepoint

  • config (Moxml::Config) —

    configuration object

Returns:

  • (Boolean) 


182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
 
# File 'lib/moxml/entity_registry.rb', line 182

def should_restore?(codepoint, config:)
  name = primary_name_for_codepoint(codepoint)
  return false unless name
  return true if standard_entity?(codepoint)

  return false unless config.restore_entities

  case config.entity_restoration_mode
  when :lenient
    # Any known entity from the registry
    true
  when :strict
    # Only DTD-declared entities (falls back to lenient until DTD parsing is implemented)
    true
  else
    false
  end
end

#standard_entity?(codepoint) ⇒ Boolean

Check if a codepoint is one of the 5 standard XML predefined entities

Parameters:

  • codepoint (Integer) —

    Unicode codepoint

Returns:

  • (Boolean) 


172
173
174
 
# File 'lib/moxml/entity_registry.rb', line 172

def standard_entity?(codepoint)
  STANDARD_CODEPOINTS.include?(codepoint)
end