diff --git a/src/main/java/strman/HtmlEntities.java b/src/main/java/strman/HtmlEntities.java index 6c698b9..9d23fc9 100644 --- a/src/main/java/strman/HtmlEntities.java +++ b/src/main/java/strman/HtmlEntities.java @@ -2240,5 +2240,1502 @@ public abstract class HtmlEntities { }; + public static final Map encodedEntities = new HashMap() {{ + put("\\u00C6", "Æ"); + put("\\u0026", "&"); + put("\\u00C1", "Á"); + put("\\u0102", "Ă"); + put("\\u00C2", "Â"); + put("\\u0410", "А"); + put("\\uD835\\uDD04", "𝔄"); + put("\\u00C0", "À"); + put("\\u0391", "Α"); + put("\\u0100", "Ā"); + put("\\u2A53", "⩓"); + put("\\u0104", "Ą"); + put("\\uD835\\uDD38", "𝔸"); + put("\\u2061", "⁡"); + put("\\u00C5", "Å"); + put("\\uD835\\uDC9C", "𝒜"); + put("\\u2254", "≔"); + put("\\u00C3", "Ã"); + put("\\u00C4", "Ä"); + put("\\u2216", "∖"); + put("\\u2AE7", "⫧"); + put("\\u2306", "⌆"); + put("\\u0411", "Б"); + put("\\u2235", "∵"); + put("\\u212C", "ℬ"); + put("\\u0392", "Β"); + put("\\uD835\\uDD05", "𝔅"); + put("\\uD835\\uDD39", "𝔹"); + put("\\u02D8", "˘"); + put("\\u224E", "≎"); + put("\\u0427", "Ч"); + put("\\u00A9", "©"); + put("\\u0106", "Ć"); + put("\\u22D2", "⋒"); + put("\\u2145", "ⅅ"); + put("\\u212D", "ℭ"); + put("\\u010C", "Č"); + put("\\u00C7", "Ç"); + put("\\u0108", "Ĉ"); + put("\\u2230", "∰"); + put("\\u010A", "Ċ"); + put("\\u00B8", "¸"); + put("\\u00B7", "·"); + put("\\u03A7", "Χ"); + put("\\u2299", "⊙"); + put("\\u2296", "⊖"); + put("\\u2295", "⊕"); + put("\\u2297", "⊗"); + put("\\u2232", "∲"); + put("\\u201D", "”"); + put("\\u2019", "’"); + put("\\u2237", "∷"); + put("\\u2A74", "⩴"); + put("\\u2261", "≡"); + put("\\u222F", "∯"); + put("\\u222E", "∮"); + put("\\u2102", "ℂ"); + put("\\u2210", "∐"); + put("\\u2233", "∳"); + put("\\u2A2F", "⨯"); + put("\\uD835\\uDC9E", "𝒞"); + put("\\u22D3", "⋓"); + put("\\u224D", "≍"); + put("\\u2911", "⤑"); + put("\\u0402", "Ђ"); + put("\\u0405", "Ѕ"); + put("\\u040F", "Џ"); + put("\\u2021", "‡"); + put("\\u21A1", "↡"); + put("\\u2AE4", "⫤"); + put("\\u010E", "Ď"); + put("\\u0414", "Д"); + put("\\u2207", "∇"); + put("\\u0394", "Δ"); + put("\\uD835\\uDD07", "𝔇"); + put("\\u00B4", "´"); + put("\\u02D9", "˙"); + put("\\u02DD", "˝"); + put("\\u0060", "`"); + put("\\u02DC", "˜"); + put("\\u22C4", "⋄"); + put("\\u2146", "ⅆ"); + put("\\uD835\\uDD3B", "𝔻"); + put("\\u00A8", "¨"); + put("\\u20DC", "⃜"); + put("\\u2250", "≐"); + put("\\u21D3", "⇓"); + put("\\u21D0", "⇐"); + put("\\u21D4", "⇔"); + put("\\u27F8", "⟸"); + put("\\u27FA", "⟺"); + put("\\u27F9", "⟹"); + put("\\u21D2", "⇒"); + put("\\u22A8", "⊨"); + put("\\u21D1", "⇑"); + put("\\u21D5", "⇕"); + put("\\u2225", "∥"); + put("\\u2193", "↓"); + put("\\u2913", "⤓"); + put("\\u21F5", "⇵"); + put("\\u0311", "̑"); + put("\\u2950", "⥐"); + put("\\u295E", "⥞"); + put("\\u21BD", "↽"); + put("\\u2956", "⥖"); + put("\\u295F", "⥟"); + put("\\u21C1", "⇁"); + put("\\u2957", "⥗"); + put("\\u22A4", "⊤"); + put("\\u21A7", "↧"); + put("\\uD835\\uDC9F", "𝒟"); + put("\\u0110", "Đ"); + put("\\u014A", "Ŋ"); + put("\\u00D0", "Ð"); + put("\\u00C9", "É"); + put("\\u011A", "Ě"); + put("\\u00CA", "Ê"); + put("\\u042D", "Э"); + put("\\u0116", "Ė"); + put("\\uD835\\uDD08", "𝔈"); + put("\\u00C8", "È"); + put("\\u2208", "∈"); + put("\\u0112", "Ē"); + put("\\u25FB", "◻"); + put("\\u25AB", "▫"); + put("\\u0118", "Ę"); + put("\\uD835\\uDD3C", "𝔼"); + put("\\u0395", "Ε"); + put("\\u2A75", "⩵"); + put("\\u2242", "≂"); + put("\\u21CC", "⇌"); + put("\\u2130", "ℰ"); + put("\\u2A73", "⩳"); + put("\\u0397", "Η"); + put("\\u00CB", "Ë"); + put("\\u2203", "∃"); + put("\\u2147", "ⅇ"); + put("\\u0424", "Ф"); + put("\\uD835\\uDD09", "𝔉"); + put("\\u25FC", "◼"); + put("\\u25AA", "▪"); + put("\\uD835\\uDD3D", "𝔽"); + put("\\u2200", "∀"); + put("\\u2131", "ℱ"); + put("\\u0403", "Ѓ"); + put("\\u003E", ">"); + put("\\u0393", "Γ"); + put("\\u03DC", "Ϝ"); + put("\\u011E", "Ğ"); + put("\\u0122", "Ģ"); + put("\\u011C", "Ĝ"); + put("\\u0413", "Г"); + put("\\u0120", "Ġ"); + put("\\uD835\\uDD0A", "𝔊"); + put("\\u22D9", "⋙"); + put("\\uD835\\uDD3E", "𝔾"); + put("\\u2265", "≥"); + put("\\u22DB", "⋛"); + put("\\u2267", "≧"); + put("\\u2AA2", "⪢"); + put("\\u2277", "≷"); + put("\\u2A7E", "⩾"); + put("\\u2273", "≳"); + put("\\uD835\\uDCA2", "𝒢"); + put("\\u226B", "≫"); + put("\\u042A", "Ъ"); + put("\\u02C7", "ˇ"); + put("\\u005E", "^"); + put("\\u0124", "Ĥ"); + put("\\u210C", "ℌ"); + put("\\u210B", "ℋ"); + put("\\u210D", "ℍ"); + put("\\u2500", "─"); + put("\\u0126", "Ħ"); + put("\\u224F", "≏"); + put("\\u0415", "Е"); + put("\\u0132", "IJ"); + put("\\u0401", "Ё"); + put("\\u00CD", "Í"); + put("\\u00CE", "Î"); + put("\\u0418", "И"); + put("\\u0130", "İ"); + put("\\u2111", "ℑ"); + put("\\u00CC", "Ì"); + put("\\u012A", "Ī"); + put("\\u2148", "ⅈ"); + put("\\u222C", "∬"); + put("\\u222B", "∫"); + put("\\u22C2", "⋂"); + put("\\u2063", "⁣"); + put("\\u2062", "⁢"); + put("\\u012E", "Į"); + put("\\uD835\\uDD40", "𝕀"); + put("\\u0399", "Ι"); + put("\\u2110", "ℐ"); + put("\\u0128", "Ĩ"); + put("\\u0406", "І"); + put("\\u00CF", "Ï"); + put("\\u0134", "Ĵ"); + put("\\u0419", "Й"); + put("\\uD835\\uDD0D", "𝔍"); + put("\\uD835\\uDD41", "𝕁"); + put("\\uD835\\uDCA5", "𝒥"); + put("\\u0408", "Ј"); + put("\\u0404", "Є"); + put("\\u0425", "Х"); + put("\\u040C", "Ќ"); + put("\\u039A", "Κ"); + put("\\u0136", "Ķ"); + put("\\u041A", "К"); + put("\\uD835\\uDD0E", "𝔎"); + put("\\uD835\\uDD42", "𝕂"); + put("\\uD835\\uDCA6", "𝒦"); + put("\\u0409", "Љ"); + put("\\u003C", "<"); + put("\\u0139", "Ĺ"); + put("\\u039B", "Λ"); + put("\\u27EA", "⟪"); + put("\\u2112", "ℒ"); + put("\\u219E", "↞"); + put("\\u013D", "Ľ"); + put("\\u013B", "Ļ"); + put("\\u041B", "Л"); + put("\\u27E8", "⟨"); + put("\\u2190", "←"); + put("\\u21E4", "⇤"); + put("\\u21C6", "⇆"); + put("\\u2308", "⌈"); + put("\\u27E6", "⟦"); + put("\\u2961", "⥡"); + put("\\u21C3", "⇃"); + put("\\u2959", "⥙"); + put("\\u230A", "⌊"); + put("\\u2194", "↔"); + put("\\u294E", "⥎"); + put("\\u22A3", "⊣"); + put("\\u21A4", "↤"); + put("\\u295A", "⥚"); + put("\\u22B2", "⊲"); + put("\\u29CF", "⧏"); + put("\\u22B4", "⊴"); + put("\\u2951", "⥑"); + put("\\u2960", "⥠"); + put("\\u21BF", "↿"); + put("\\u2958", "⥘"); + put("\\u21BC", "↼"); + put("\\u2952", "⥒"); + put("\\u22DA", "⋚"); + put("\\u2266", "≦"); + put("\\u2276", "≶"); + put("\\u2AA1", "⪡"); + put("\\u2A7D", "⩽"); + put("\\u2272", "≲"); + put("\\uD835\\uDD0F", "𝔏"); + put("\\u22D8", "⋘"); + put("\\u21DA", "⇚"); + put("\\u013F", "Ŀ"); + put("\\u27F5", "⟵"); + put("\\u27F7", "⟷"); + put("\\u27F6", "⟶"); + put("\\uD835\\uDD43", "𝕃"); + put("\\u2199", "↙"); + put("\\u2198", "↘"); + put("\\u21B0", "↰"); + put("\\u0141", "Ł"); + put("\\u226A", "≪"); + put("\\u2905", "⤅"); + put("\\u041C", "М"); + put("\\u205F", " "); + put("\\u2133", "ℳ"); + put("\\uD835\\uDD10", "𝔐"); + put("\\u2213", "∓"); + put("\\uD835\\uDD44", "𝕄"); + put("\\u039C", "Μ"); + put("\\u040A", "Њ"); + put("\\u0143", "Ń"); + put("\\u0147", "Ň"); + put("\\u0145", "Ņ"); + put("\\u041D", "Н"); + put("\\u200B", "​"); + put("\\u000A", " "); + put("\\uD835\\uDD11", "𝔑"); + put("\\u2060", "⁠"); + put("\\u00A0", " "); + put("\\u2115", "ℕ"); + put("\\u2AEC", "⫬"); + put("\\u2262", "≢"); + put("\\u226D", "≭"); + put("\\u2226", "∦"); + put("\\u2209", "∉"); + put("\\u2260", "≠"); + put("\\u2242\\u0338", "≂̸"); + put("\\u2204", "∄"); + put("\\u226F", "≯"); + put("\\u2271", "≱"); + put("\\u2267\\u0338", "≧̸"); + put("\\u226B\\u0338", "≫̸"); + put("\\u2279", "≹"); + put("\\u2A7E\\u0338", "⩾̸"); + put("\\u2275", "≵"); + put("\\u224E\\u0338", "≎̸"); + put("\\u224F\\u0338", "≏̸"); + put("\\u22EA", "⋪"); + put("\\u29CF\\u0338", "⧏̸"); + put("\\u22EC", "⋬"); + put("\\u226E", "≮"); + put("\\u2270", "≰"); + put("\\u2278", "≸"); + put("\\u226A\\u0338", "≪̸"); + put("\\u2A7D\\u0338", "⩽̸"); + put("\\u2274", "≴"); + put("\\u2AA2\\u0338", "⪢̸"); + put("\\u2AA1\\u0338", "⪡̸"); + put("\\u2280", "⊀"); + put("\\u2AAF\\u0338", "⪯̸"); + put("\\u22E0", "⋠"); + put("\\u220C", "∌"); + put("\\u22EB", "⋫"); + put("\\u29D0\\u0338", "⧐̸"); + put("\\u22ED", "⋭"); + put("\\u228F\\u0338", "⊏̸"); + put("\\u22E2", "⋢"); + put("\\u2290\\u0338", "⊐̸"); + put("\\u22E3", "⋣"); + put("\\u2282\\u20D2", "⊂⃒"); + put("\\u2288", "⊈"); + put("\\u2281", "⊁"); + put("\\u2AB0\\u0338", "⪰̸"); + put("\\u22E1", "⋡"); + put("\\u227F\\u0338", "≿̸"); + put("\\u2283\\u20D2", "⊃⃒"); + put("\\u2289", "⊉"); + put("\\u2241", "≁"); + put("\\u2244", "≄"); + put("\\u2247", "≇"); + put("\\u2249", "≉"); + put("\\u2224", "∤"); + put("\\uD835\\uDCA9", "𝒩"); + put("\\u00D1", "Ñ"); + put("\\u039D", "Ν"); + put("\\u0152", "Œ"); + put("\\u00D3", "Ó"); + put("\\u00D4", "Ô"); + put("\\u041E", "О"); + put("\\u0150", "Ő"); + put("\\uD835\\uDD12", "𝔒"); + put("\\u00D2", "Ò"); + put("\\u014C", "Ō"); + put("\\u03A9", "Ω"); + put("\\u039F", "Ο"); + put("\\uD835\\uDD46", "𝕆"); + put("\\u201C", "“"); + put("\\u2018", "‘"); + put("\\u2A54", "⩔"); + put("\\uD835\\uDCAA", "𝒪"); + put("\\u00D8", "Ø"); + put("\\u00D5", "Õ"); + put("\\u2A37", "⨷"); + put("\\u00D6", "Ö"); + put("\\u203E", "‾"); + put("\\u23DE", "⏞"); + put("\\u23B4", "⎴"); + put("\\u23DC", "⏜"); + put("\\u2202", "∂"); + put("\\u041F", "П"); + put("\\uD835\\uDD13", "𝔓"); + put("\\u03A6", "Φ"); + put("\\u03A0", "Π"); + put("\\u00B1", "±"); + put("\\u2119", "ℙ"); + put("\\u2ABB", "⪻"); + put("\\u227A", "≺"); + put("\\u2AAF", "⪯"); + put("\\u227C", "≼"); + put("\\u227E", "≾"); + put("\\u2033", "″"); + put("\\u220F", "∏"); + put("\\u221D", "∝"); + put("\\uD835\\uDCAB", "𝒫"); + put("\\u03A8", "Ψ"); + put("\\u0022", """); + put("\\uD835\\uDD14", "𝔔"); + put("\\u211A", "ℚ"); + put("\\uD835\\uDCAC", "𝒬"); + put("\\u2910", "⤐"); + put("\\u00AE", "®"); + put("\\u0154", "Ŕ"); + put("\\u27EB", "⟫"); + put("\\u21A0", "↠"); + put("\\u2916", "⤖"); + put("\\u0158", "Ř"); + put("\\u0156", "Ŗ"); + put("\\u0420", "Р"); + put("\\u211C", "ℜ"); + put("\\u220B", "∋"); + put("\\u21CB", "⇋"); + put("\\u296F", "⥯"); + put("\\u03A1", "Ρ"); + put("\\u27E9", "⟩"); + put("\\u2192", "→"); + put("\\u21E5", "⇥"); + put("\\u21C4", "⇄"); + put("\\u2309", "⌉"); + put("\\u27E7", "⟧"); + put("\\u295D", "⥝"); + put("\\u21C2", "⇂"); + put("\\u2955", "⥕"); + put("\\u230B", "⌋"); + put("\\u22A2", "⊢"); + put("\\u21A6", "↦"); + put("\\u295B", "⥛"); + put("\\u22B3", "⊳"); + put("\\u29D0", "⧐"); + put("\\u22B5", "⊵"); + put("\\u294F", "⥏"); + put("\\u295C", "⥜"); + put("\\u21BE", "↾"); + put("\\u2954", "⥔"); + put("\\u21C0", "⇀"); + put("\\u2953", "⥓"); + put("\\u211D", "ℝ"); + put("\\u2970", "⥰"); + put("\\u21DB", "⇛"); + put("\\u211B", "ℛ"); + put("\\u21B1", "↱"); + put("\\u29F4", "⧴"); + put("\\u0429", "Щ"); + put("\\u0428", "Ш"); + put("\\u042C", "Ь"); + put("\\u015A", "Ś"); + put("\\u2ABC", "⪼"); + put("\\u0160", "Š"); + put("\\u015E", "Ş"); + put("\\u015C", "Ŝ"); + put("\\u0421", "С"); + put("\\uD835\\uDD16", "𝔖"); + put("\\u2191", "↑"); + put("\\u03A3", "Σ"); + put("\\u2218", "∘"); + put("\\uD835\\uDD4A", "𝕊"); + put("\\u221A", "√"); + put("\\u25A1", "□"); + put("\\u2293", "⊓"); + put("\\u228F", "⊏"); + put("\\u2291", "⊑"); + put("\\u2290", "⊐"); + put("\\u2292", "⊒"); + put("\\u2294", "⊔"); + put("\\uD835\\uDCAE", "𝒮"); + put("\\u22C6", "⋆"); + put("\\u22D0", "⋐"); + put("\\u2286", "⊆"); + put("\\u227B", "≻"); + put("\\u2AB0", "⪰"); + put("\\u227D", "≽"); + put("\\u227F", "≿"); + put("\\u2211", "∑"); + put("\\u22D1", "⋑"); + put("\\u2283", "⊃"); + put("\\u2287", "⊇"); + put("\\u00DE", "Þ"); + put("\\u2122", "™"); + put("\\u040B", "Ћ"); + put("\\u0426", "Ц"); + put("\\u0009", " "); + put("\\u03A4", "Τ"); + put("\\u0164", "Ť"); + put("\\u0162", "Ţ"); + put("\\u0422", "Т"); + put("\\uD835\\uDD17", "𝔗"); + put("\\u2234", "∴"); + put("\\u0398", "Θ"); + put("\\u205F\\u200A", "  "); + put("\\u2009", " "); + put("\\u223C", "∼"); + put("\\u2243", "≃"); + put("\\u2245", "≅"); + put("\\u2248", "≈"); + put("\\uD835\\uDD4B", "𝕋"); + put("\\u20DB", "⃛"); + put("\\uD835\\uDCAF", "𝒯"); + put("\\u0166", "Ŧ"); + put("\\u00DA", "Ú"); + put("\\u219F", "↟"); + put("\\u2949", "⥉"); + put("\\u040E", "Ў"); + put("\\u016C", "Ŭ"); + put("\\u00DB", "Û"); + put("\\u0423", "У"); + put("\\u0170", "Ű"); + put("\\uD835\\uDD18", "𝔘"); + put("\\u00D9", "Ù"); + put("\\u016A", "Ū"); + put("\\u005F", "_"); + put("\\u23DF", "⏟"); + put("\\u23B5", "⎵"); + put("\\u23DD", "⏝"); + put("\\u22C3", "⋃"); + put("\\u228E", "⊎"); + put("\\u0172", "Ų"); + put("\\uD835\\uDD4C", "𝕌"); + put("\\u2912", "⤒"); + put("\\u21C5", "⇅"); + put("\\u2195", "↕"); + put("\\u296E", "⥮"); + put("\\u22A5", "⊥"); + put("\\u21A5", "↥"); + put("\\u2196", "↖"); + put("\\u2197", "↗"); + put("\\u03D2", "ϒ"); + put("\\u03A5", "Υ"); + put("\\u016E", "Ů"); + put("\\uD835\\uDCB0", "𝒰"); + put("\\u0168", "Ũ"); + put("\\u00DC", "Ü"); + put("\\u22AB", "⊫"); + put("\\u2AEB", "⫫"); + put("\\u0412", "В"); + put("\\u22A9", "⊩"); + put("\\u2AE6", "⫦"); + put("\\u22C1", "⋁"); + put("\\u2016", "‖"); + put("\\u2223", "∣"); + put("\\u007C", "|"); + put("\\u2758", "❘"); + put("\\u2240", "≀"); + put("\\u200A", " "); + put("\\uD835\\uDD19", "𝔙"); + put("\\uD835\\uDD4D", "𝕍"); + put("\\uD835\\uDCB1", "𝒱"); + put("\\u22AA", "⊪"); + put("\\u0174", "Ŵ"); + put("\\u22C0", "⋀"); + put("\\uD835\\uDD1A", "𝔚"); + put("\\uD835\\uDD4E", "𝕎"); + put("\\uD835\\uDCB2", "𝒲"); + put("\\uD835\\uDD1B", "𝔛"); + put("\\u039E", "Ξ"); + put("\\uD835\\uDD4F", "𝕏"); + put("\\uD835\\uDCB3", "𝒳"); + put("\\u042F", "Я"); + put("\\u0407", "Ї"); + put("\\u042E", "Ю"); + put("\\u00DD", "Ý"); + put("\\u0176", "Ŷ"); + put("\\u042B", "Ы"); + put("\\uD835\\uDD1C", "𝔜"); + put("\\uD835\\uDD50", "𝕐"); + put("\\uD835\\uDCB4", "𝒴"); + put("\\u0178", "Ÿ"); + put("\\u0416", "Ж"); + put("\\u0179", "Ź"); + put("\\u017D", "Ž"); + put("\\u0417", "З"); + put("\\u017B", "Ż"); + put("\\u0396", "Ζ"); + put("\\u2128", "ℨ"); + put("\\u2124", "ℤ"); + put("\\uD835\\uDCB5", "𝒵"); + put("\\u00E1", "á"); + put("\\u0103", "ă"); + put("\\u223E", "∾"); + put("\\u223E\\u0333", "∾̳"); + put("\\u223F", "∿"); + put("\\u00E2", "â"); + put("\\u0430", "а"); + put("\\u00E6", "æ"); + put("\\uD835\\uDD1E", "𝔞"); + put("\\u00E0", "à"); + put("\\u2135", "ℵ"); + put("\\u03B1", "α"); + put("\\u0101", "ā"); + put("\\u2A3F", "⨿"); + put("\\u2227", "∧"); + put("\\u2A55", "⩕"); + put("\\u2A5C", "⩜"); + put("\\u2A58", "⩘"); + put("\\u2A5A", "⩚"); + put("\\u2220", "∠"); + put("\\u29A4", "⦤"); + put("\\u2221", "∡"); + put("\\u29A8", "⦨"); + put("\\u29A9", "⦩"); + put("\\u29AA", "⦪"); + put("\\u29AB", "⦫"); + put("\\u29AC", "⦬"); + put("\\u29AD", "⦭"); + put("\\u29AE", "⦮"); + put("\\u29AF", "⦯"); + put("\\u221F", "∟"); + put("\\u22BE", "⊾"); + put("\\u299D", "⦝"); + put("\\u2222", "∢"); + put("\\u237C", "⍼"); + put("\\u0105", "ą"); + put("\\uD835\\uDD52", "𝕒"); + put("\\u2A70", "⩰"); + put("\\u2A6F", "⩯"); + put("\\u224A", "≊"); + put("\\u224B", "≋"); + put("\\u0027", "'"); + put("\\u00E5", "å"); + put("\\uD835\\uDCB6", "𝒶"); + put("\\u002A", "*"); + put("\\u00E3", "ã"); + put("\\u00E4", "ä"); + put("\\u2A11", "⨑"); + put("\\u2AED", "⫭"); + put("\\u224C", "≌"); + put("\\u03F6", "϶"); + put("\\u2035", "‵"); + put("\\u223D", "∽"); + put("\\u22CD", "⋍"); + put("\\u22BD", "⊽"); + put("\\u2305", "⌅"); + put("\\u23B6", "⎶"); + put("\\u0431", "б"); + put("\\u201E", "„"); + put("\\u29B0", "⦰"); + put("\\u03B2", "β"); + put("\\u2136", "ℶ"); + put("\\u226C", "≬"); + put("\\uD835\\uDD1F", "𝔟"); + put("\\u25EF", "◯"); + put("\\u2A00", "⨀"); + put("\\u2A01", "⨁"); + put("\\u2A02", "⨂"); + put("\\u2A06", "⨆"); + put("\\u2605", "★"); + put("\\u25BD", "▽"); + put("\\u25B3", "△"); + put("\\u2A04", "⨄"); + put("\\u290D", "⤍"); + put("\\u29EB", "⧫"); + put("\\u25B4", "▴"); + put("\\u25BE", "▾"); + put("\\u25C2", "◂"); + put("\\u25B8", "▸"); + put("\\u2423", "␣"); + put("\\u2592", "▒"); + put("\\u2591", "░"); + put("\\u2593", "▓"); + put("\\u2588", "█"); + put("\\u003D\\u20E5", "=⃥"); + put("\\u2261\\u20E5", "≡⃥"); + put("\\u2310", "⌐"); + put("\\uD835\\uDD53", "𝕓"); + put("\\u22C8", "⋈"); + put("\\u2557", "╗"); + put("\\u2554", "╔"); + put("\\u2556", "╖"); + put("\\u2553", "╓"); + put("\\u2550", "═"); + put("\\u2566", "╦"); + put("\\u2569", "╩"); + put("\\u2564", "╤"); + put("\\u2567", "╧"); + put("\\u255D", "╝"); + put("\\u255A", "╚"); + put("\\u255C", "╜"); + put("\\u2559", "╙"); + put("\\u2551", "║"); + put("\\u256C", "╬"); + put("\\u2563", "╣"); + put("\\u2560", "╠"); + put("\\u256B", "╫"); + put("\\u2562", "╢"); + put("\\u255F", "╟"); + put("\\u29C9", "⧉"); + put("\\u2555", "╕"); + put("\\u2552", "╒"); + put("\\u2510", "┐"); + put("\\u250C", "┌"); + put("\\u2565", "╥"); + put("\\u2568", "╨"); + put("\\u252C", "┬"); + put("\\u2534", "┴"); + put("\\u229F", "⊟"); + put("\\u229E", "⊞"); + put("\\u22A0", "⊠"); + put("\\u255B", "╛"); + put("\\u2558", "╘"); + put("\\u2518", "┘"); + put("\\u2514", "└"); + put("\\u2502", "│"); + put("\\u256A", "╪"); + put("\\u2561", "╡"); + put("\\u255E", "╞"); + put("\\u253C", "┼"); + put("\\u2524", "┤"); + put("\\u251C", "├"); + put("\\u00A6", "¦"); + put("\\uD835\\uDCB7", "𝒷"); + put("\\u204F", "⁏"); + put("\\u005C", "\"); + put("\\u29C5", "⧅"); + put("\\u27C8", "⟈"); + put("\\u2022", "•"); + put("\\u2AAE", "⪮"); + put("\\u0107", "ć"); + put("\\u2229", "∩"); + put("\\u2A44", "⩄"); + put("\\u2A49", "⩉"); + put("\\u2A4B", "⩋"); + put("\\u2A47", "⩇"); + put("\\u2A40", "⩀"); + put("\\u2229\\uFE00", "∩︀"); + put("\\u2041", "⁁"); + put("\\u2A4D", "⩍"); + put("\\u010D", "č"); + put("\\u00E7", "ç"); + put("\\u0109", "ĉ"); + put("\\u2A4C", "⩌"); + put("\\u2A50", "⩐"); + put("\\u010B", "ċ"); + put("\\u29B2", "⦲"); + put("\\u00A2", "¢"); + put("\\uD835\\uDD20", "𝔠"); + put("\\u0447", "ч"); + put("\\u2713", "✓"); + put("\\u03C7", "χ"); + put("\\u25CB", "○"); + put("\\u29C3", "⧃"); + put("\\u02C6", "ˆ"); + put("\\u2257", "≗"); + put("\\u21BA", "↺"); + put("\\u21BB", "↻"); + put("\\u24C8", "Ⓢ"); + put("\\u229B", "⊛"); + put("\\u229A", "⊚"); + put("\\u229D", "⊝"); + put("\\u2A10", "⨐"); + put("\\u2AEF", "⫯"); + put("\\u29C2", "⧂"); + put("\\u2663", "♣"); + put("\\u003A", ":"); + put("\\u002C", ","); + put("\\u0040", "@"); + put("\\u2201", "∁"); + put("\\u2A6D", "⩭"); + put("\\uD835\\uDD54", "𝕔"); + put("\\u2117", "℗"); + put("\\u21B5", "↵"); + put("\\u2717", "✗"); + put("\\uD835\\uDCB8", "𝒸"); + put("\\u2ACF", "⫏"); + put("\\u2AD1", "⫑"); + put("\\u2AD0", "⫐"); + put("\\u2AD2", "⫒"); + put("\\u22EF", "⋯"); + put("\\u2938", "⤸"); + put("\\u2935", "⤵"); + put("\\u22DE", "⋞"); + put("\\u22DF", "⋟"); + put("\\u21B6", "↶"); + put("\\u293D", "⤽"); + put("\\u222A", "∪"); + put("\\u2A48", "⩈"); + put("\\u2A46", "⩆"); + put("\\u2A4A", "⩊"); + put("\\u228D", "⊍"); + put("\\u2A45", "⩅"); + put("\\u222A\\uFE00", "∪︀"); + put("\\u21B7", "↷"); + put("\\u293C", "⤼"); + put("\\u22CE", "⋎"); + put("\\u22CF", "⋏"); + put("\\u00A4", "¤"); + put("\\u2231", "∱"); + put("\\u232D", "⌭"); + put("\\u2965", "⥥"); + put("\\u2020", "†"); + put("\\u2138", "ℸ"); + put("\\u2010", "‐"); + put("\\u290F", "⤏"); + put("\\u010F", "ď"); + put("\\u0434", "д"); + put("\\u21CA", "⇊"); + put("\\u2A77", "⩷"); + put("\\u00B0", "°"); + put("\\u03B4", "δ"); + put("\\u29B1", "⦱"); + put("\\u297F", "⥿"); + put("\\uD835\\uDD21", "𝔡"); + put("\\u2666", "♦"); + put("\\u03DD", "ϝ"); + put("\\u22F2", "⋲"); + put("\\u00F7", "÷"); + put("\\u22C7", "⋇"); + put("\\u0452", "ђ"); + put("\\u231E", "⌞"); + put("\\u230D", "⌍"); + put("\\u0024", "$"); + put("\\uD835\\uDD55", "𝕕"); + put("\\u2251", "≑"); + put("\\u2238", "∸"); + put("\\u2214", "∔"); + put("\\u22A1", "⊡"); + put("\\u231F", "⌟"); + put("\\u230C", "⌌"); + put("\\uD835\\uDCB9", "𝒹"); + put("\\u0455", "ѕ"); + put("\\u29F6", "⧶"); + put("\\u0111", "đ"); + put("\\u22F1", "⋱"); + put("\\u29A6", "⦦"); + put("\\u045F", "џ"); + put("\\u2A6E", "⩮"); + put("\\u011B", "ě"); + put("\\u2256", "≖"); + put("\\u2255", "≕"); + put("\\u044D", "э"); + put("\\u2252", "≒"); + put("\\uD835\\uDD22", "𝔢"); + put("\\u2A9A", "⪚"); + put("\\u2A96", "⪖"); + put("\\u2A98", "⪘"); + put("\\u2A99", "⪙"); + put("\\u23E7", "⏧"); + put("\\u2113", "ℓ"); + put("\\u2A95", "⪕"); + put("\\u2A97", "⪗"); + put("\\u0113", "ē"); + put("\\u2004", " "); + put("\\u2005", " "); + put("\\u2003", " "); + put("\\u014B", "ŋ"); + put("\\u2002", " "); + put("\\u0119", "ę"); + put("\\uD835\\uDD56", "𝕖"); + put("\\u22D5", "⋕"); + put("\\u29E3", "⧣"); + put("\\u2A71", "⩱"); + put("\\u03B5", "ε"); + put("\\u03F5", "ϵ"); + put("\\u003D", "="); + put("\\u225F", "≟"); + put("\\u2A78", "⩸"); + put("\\u29E5", "⧥"); + put("\\u2253", "≓"); + put("\\u2971", "⥱"); + put("\\u212F", "ℯ"); + put("\\u03B7", "η"); + put("\\u00F0", "ð"); + put("\\u00EB", "ë"); + put("\\u20AC", "€"); + put("\\u0021", "!"); + put("\\u0444", "ф"); + put("\\u2640", "♀"); + put("\\uFB03", "ffi"); + put("\\uFB00", "ff"); + put("\\uFB04", "ffl"); + put("\\uD835\\uDD23", "𝔣"); + put("\\uFB01", "fi"); + put("\\u0066\\u006A", "fj"); + put("\\u266D", "♭"); + put("\\uFB02", "fl"); + put("\\u25B1", "▱"); + put("\\u0192", "ƒ"); + put("\\uD835\\uDD57", "𝕗"); + put("\\u22D4", "⋔"); + put("\\u2AD9", "⫙"); + put("\\u2A0D", "⨍"); + put("\\u00BD", "½"); + put("\\u2153", "⅓"); + put("\\u00BC", "¼"); + put("\\u2155", "⅕"); + put("\\u2159", "⅙"); + put("\\u215B", "⅛"); + put("\\u2154", "⅔"); + put("\\u2156", "⅖"); + put("\\u00BE", "¾"); + put("\\u2157", "⅗"); + put("\\u215C", "⅜"); + put("\\u2158", "⅘"); + put("\\u215A", "⅚"); + put("\\u215D", "⅝"); + put("\\u215E", "⅞"); + put("\\u2044", "⁄"); + put("\\u2322", "⌢"); + put("\\uD835\\uDCBB", "𝒻"); + put("\\u00E9", "é"); + put("\\u2A8C", "⪌"); + put("\\u01F5", "ǵ"); + put("\\u03B3", "γ"); + put("\\u2A86", "⪆"); + put("\\u011F", "ğ"); + put("\\u011D", "ĝ"); + put("\\u0433", "г"); + put("\\u0121", "ġ"); + put("\\u2AA9", "⪩"); + put("\\u2A80", "⪀"); + put("\\u2A82", "⪂"); + put("\\u2A84", "⪄"); + put("\\u22DB\\uFE00", "⋛︀"); + put("\\u2A94", "⪔"); + put("\\uD835\\uDD24", "𝔤"); + put("\\u2137", "ℷ"); + put("\\u0453", "ѓ"); + put("\\u2A92", "⪒"); + put("\\u2AA5", "⪥"); + put("\\u2AA4", "⪤"); + put("\\u2269", "≩"); + put("\\u2A8A", "⪊"); + put("\\u2A88", "⪈"); + put("\\u22E7", "⋧"); + put("\\uD835\\uDD58", "𝕘"); + put("\\u210A", "ℊ"); + put("\\u2A8E", "⪎"); + put("\\u2A90", "⪐"); + put("\\u2AA7", "⪧"); + put("\\u2A7A", "⩺"); + put("\\u22D7", "⋗"); + put("\\u2995", "⦕"); + put("\\u2A7C", "⩼"); + put("\\u2978", "⥸"); + put("\\u2269\\uFE00", "≩︀"); + put("\\u044A", "ъ"); + put("\\u2948", "⥈"); + put("\\u21AD", "↭"); + put("\\u210F", "ℏ"); + put("\\u0125", "ĥ"); + put("\\u2665", "♥"); + put("\\u2026", "…"); + put("\\u22B9", "⊹"); + put("\\uD835\\uDD25", "𝔥"); + put("\\u2925", "⤥"); + put("\\u2926", "⤦"); + put("\\u21FF", "⇿"); + put("\\u223B", "∻"); + put("\\u21A9", "↩"); + put("\\u21AA", "↪"); + put("\\uD835\\uDD59", "𝕙"); + put("\\u2015", "―"); + put("\\uD835\\uDCBD", "𝒽"); + put("\\u0127", "ħ"); + put("\\u2043", "⁃"); + put("\\u00ED", "í"); + put("\\u00EE", "î"); + put("\\u0438", "и"); + put("\\u0435", "е"); + put("\\u00A1", "¡"); + put("\\uD835\\uDD26", "𝔦"); + put("\\u00EC", "ì"); + put("\\u2A0C", "⨌"); + put("\\u222D", "∭"); + put("\\u29DC", "⧜"); + put("\\u2129", "℩"); + put("\\u0133", "ij"); + put("\\u012B", "ī"); + put("\\u0131", "ı"); + put("\\u22B7", "⊷"); + put("\\u01B5", "Ƶ"); + put("\\u2105", "℅"); + put("\\u221E", "∞"); + put("\\u29DD", "⧝"); + put("\\u22BA", "⊺"); + put("\\u2A17", "⨗"); + put("\\u2A3C", "⨼"); + put("\\u0451", "ё"); + put("\\u012F", "į"); + put("\\uD835\\uDD5A", "𝕚"); + put("\\u03B9", "ι"); + put("\\u00BF", "¿"); + put("\\uD835\\uDCBE", "𝒾"); + put("\\u22F9", "⋹"); + put("\\u22F5", "⋵"); + put("\\u22F4", "⋴"); + put("\\u22F3", "⋳"); + put("\\u0129", "ĩ"); + put("\\u0456", "і"); + put("\\u00EF", "ï"); + put("\\u0135", "ĵ"); + put("\\u0439", "й"); + put("\\uD835\\uDD27", "𝔧"); + put("\\u0237", "ȷ"); + put("\\uD835\\uDD5B", "𝕛"); + put("\\uD835\\uDCBF", "𝒿"); + put("\\u0458", "ј"); + put("\\u0454", "є"); + put("\\u03BA", "κ"); + put("\\u03F0", "ϰ"); + put("\\u0137", "ķ"); + put("\\u043A", "к"); + put("\\uD835\\uDD28", "𝔨"); + put("\\u0138", "ĸ"); + put("\\u0445", "х"); + put("\\u045C", "ќ"); + put("\\uD835\\uDD5C", "𝕜"); + put("\\uD835\\uDCC0", "𝓀"); + put("\\u291B", "⤛"); + put("\\u290E", "⤎"); + put("\\u2A8B", "⪋"); + put("\\u2962", "⥢"); + put("\\u013A", "ĺ"); + put("\\u29B4", "⦴"); + put("\\u03BB", "λ"); + put("\\u2991", "⦑"); + put("\\u2A85", "⪅"); + put("\\u00AB", "«"); + put("\\u291F", "⤟"); + put("\\u291D", "⤝"); + put("\\u21AB", "↫"); + put("\\u2939", "⤹"); + put("\\u2973", "⥳"); + put("\\u21A2", "↢"); + put("\\u2AAB", "⪫"); + put("\\u2919", "⤙"); + put("\\u2AAD", "⪭"); + put("\\u2AAD\\uFE00", "⪭︀"); + put("\\u290C", "⤌"); + put("\\u2772", "❲"); + put("\\u007B", "{"); + put("\\u005B", "["); + put("\\u298B", "⦋"); + put("\\u298F", "⦏"); + put("\\u298D", "⦍"); + put("\\u013E", "ľ"); + put("\\u013C", "ļ"); + put("\\u043B", "л"); + put("\\u2936", "⤶"); + put("\\u2967", "⥧"); + put("\\u294B", "⥋"); + put("\\u21B2", "↲"); + put("\\u2264", "≤"); + put("\\u21C7", "⇇"); + put("\\u22CB", "⋋"); + put("\\u2AA8", "⪨"); + put("\\u2A7F", "⩿"); + put("\\u2A81", "⪁"); + put("\\u2A83", "⪃"); + put("\\u22DA\\uFE00", "⋚︀"); + put("\\u2A93", "⪓"); + put("\\u22D6", "⋖"); + put("\\u297C", "⥼"); + put("\\uD835\\uDD29", "𝔩"); + put("\\u2A91", "⪑"); + put("\\u296A", "⥪"); + put("\\u2584", "▄"); + put("\\u0459", "љ"); + put("\\u296B", "⥫"); + put("\\u25FA", "◺"); + put("\\u0140", "ŀ"); + put("\\u23B0", "⎰"); + put("\\u2268", "≨"); + put("\\u2A89", "⪉"); + put("\\u2A87", "⪇"); + put("\\u22E6", "⋦"); + put("\\u27EC", "⟬"); + put("\\u21FD", "⇽"); + put("\\u21AC", "↬"); + put("\\u2985", "⦅"); + put("\\uD835\\uDD5D", "𝕝"); + put("\\u2A2D", "⨭"); + put("\\u2A34", "⨴"); + put("\\u2217", "∗"); + put("\\u25CA", "◊"); + put("\\u0028", "("); + put("\\u2993", "⦓"); + put("\\u296D", "⥭"); + put("\\u200E", "‎"); + put("\\u22BF", "⊿"); + put("\\u2039", "‹"); + put("\\uD835\\uDCC1", "𝓁"); + put("\\u2A8D", "⪍"); + put("\\u2A8F", "⪏"); + put("\\u201A", "‚"); + put("\\u0142", "ł"); + put("\\u2AA6", "⪦"); + put("\\u2A79", "⩹"); + put("\\u22C9", "⋉"); + put("\\u2976", "⥶"); + put("\\u2A7B", "⩻"); + put("\\u2996", "⦖"); + put("\\u25C3", "◃"); + put("\\u294A", "⥊"); + put("\\u2966", "⥦"); + put("\\u2268\\uFE00", "≨︀"); + put("\\u223A", "∺"); + put("\\u00AF", "¯"); + put("\\u2642", "♂"); + put("\\u2720", "✠"); + put("\\u25AE", "▮"); + put("\\u2A29", "⨩"); + put("\\u043C", "м"); + put("\\u2014", "—"); + put("\\uD835\\uDD2A", "𝔪"); + put("\\u2127", "℧"); + put("\\u00B5", "µ"); + put("\\u2AF0", "⫰"); + put("\\u2212", "−"); + put("\\u2A2A", "⨪"); + put("\\u2ADB", "⫛"); + put("\\u22A7", "⊧"); + put("\\uD835\\uDD5E", "𝕞"); + put("\\uD835\\uDCC2", "𝓂"); + put("\\u03BC", "μ"); + put("\\u22B8", "⊸"); + put("\\u22D9\\u0338", "⋙̸"); + put("\\u226B\\u20D2", "≫⃒"); + put("\\u21CD", "⇍"); + put("\\u21CE", "⇎"); + put("\\u22D8\\u0338", "⋘̸"); + put("\\u226A\\u20D2", "≪⃒"); + put("\\u21CF", "⇏"); + put("\\u22AF", "⊯"); + put("\\u22AE", "⊮"); + put("\\u0144", "ń"); + put("\\u2220\\u20D2", "∠⃒"); + put("\\u2A70\\u0338", "⩰̸"); + put("\\u224B\\u0338", "≋̸"); + put("\\u0149", "ʼn"); + put("\\u266E", "♮"); + put("\\u2A43", "⩃"); + put("\\u0148", "ň"); + put("\\u0146", "ņ"); + put("\\u2A6D\\u0338", "⩭̸"); + put("\\u2A42", "⩂"); + put("\\u043D", "н"); + put("\\u2013", "–"); + put("\\u21D7", "⇗"); + put("\\u2924", "⤤"); + put("\\u2250\\u0338", "≐̸"); + put("\\u2928", "⤨"); + put("\\uD835\\uDD2B", "𝔫"); + put("\\u21AE", "↮"); + put("\\u2AF2", "⫲"); + put("\\u22FC", "⋼"); + put("\\u22FA", "⋺"); + put("\\u045A", "њ"); + put("\\u2266\\u0338", "≦̸"); + put("\\u219A", "↚"); + put("\\u2025", "‥"); + put("\\uD835\\uDD5F", "𝕟"); + put("\\u00AC", "¬"); + put("\\u22F9\\u0338", "⋹̸"); + put("\\u22F5\\u0338", "⋵̸"); + put("\\u22F7", "⋷"); + put("\\u22F6", "⋶"); + put("\\u22FE", "⋾"); + put("\\u22FD", "⋽"); + put("\\u2AFD\\u20E5", "⫽⃥"); + put("\\u2202\\u0338", "∂̸"); + put("\\u2A14", "⨔"); + put("\\u219B", "↛"); + put("\\u2933\\u0338", "⤳̸"); + put("\\u219D\\u0338", "↝̸"); + put("\\uD835\\uDCC3", "𝓃"); + put("\\u2284", "⊄"); + put("\\u2AC5\\u0338", "⫅̸"); + put("\\u2285", "⊅"); + put("\\u2AC6\\u0338", "⫆̸"); + put("\\u03BD", "ν"); + put("\\u0023", "#"); + put("\\u2116", "№"); + put("\\u2007", " "); + put("\\u22AD", "⊭"); + put("\\u2904", "⤄"); + put("\\u224D\\u20D2", "≍⃒"); + put("\\u22AC", "⊬"); + put("\\u2265\\u20D2", "≥⃒"); + put("\\u003E\\u20D2", ">⃒"); + put("\\u29DE", "⧞"); + put("\\u2902", "⤂"); + put("\\u2264\\u20D2", "≤⃒"); + put("\\u003C\\u20D2", "<⃒"); + put("\\u22B4\\u20D2", "⊴⃒"); + put("\\u2903", "⤃"); + put("\\u22B5\\u20D2", "⊵⃒"); + put("\\u223C\\u20D2", "∼⃒"); + put("\\u21D6", "⇖"); + put("\\u2923", "⤣"); + put("\\u2927", "⤧"); + put("\\u00F3", "ó"); + put("\\u00F4", "ô"); + put("\\u043E", "о"); + put("\\u0151", "ő"); + put("\\u2A38", "⨸"); + put("\\u29BC", "⦼"); + put("\\u0153", "œ"); + put("\\u29BF", "⦿"); + put("\\uD835\\uDD2C", "𝔬"); + put("\\u02DB", "˛"); + put("\\u00F2", "ò"); + put("\\u29C1", "⧁"); + put("\\u29B5", "⦵"); + put("\\u29BE", "⦾"); + put("\\u29BB", "⦻"); + put("\\u29C0", "⧀"); + put("\\u014D", "ō"); + put("\\u03C9", "ω"); + put("\\u03BF", "ο"); + put("\\u29B6", "⦶"); + put("\\uD835\\uDD60", "𝕠"); + put("\\u29B7", "⦷"); + put("\\u29B9", "⦹"); + put("\\u2228", "∨"); + put("\\u2A5D", "⩝"); + put("\\u2134", "ℴ"); + put("\\u00AA", "ª"); + put("\\u00BA", "º"); + put("\\u22B6", "⊶"); + put("\\u2A56", "⩖"); + put("\\u2A57", "⩗"); + put("\\u2298", "⊘"); + put("\\u2A36", "⨶"); + put("\\u2AF3", "⫳"); + put("\\u043F", "п"); + put("\\u0025", "%"); + put("\\u002E", "."); + put("\\u2031", "‱"); + put("\\uD835\\uDD2D", "𝔭"); + put("\\u03C6", "φ"); + put("\\u260E", "☎"); + put("\\u002B", "+"); + put("\\u2A25", "⨥"); + put("\\u2A72", "⩲"); + put("\\u2A26", "⨦"); + put("\\u2A27", "⨧"); + put("\\u2A15", "⨕"); + put("\\uD835\\uDD61", "𝕡"); + put("\\u00A3", "£"); + put("\\u2AB3", "⪳"); + put("\\u2AB7", "⪷"); + put("\\u2AB9", "⪹"); + put("\\u2AB5", "⪵"); + put("\\u22E8", "⋨"); + put("\\u2032", "′"); + put("\\u232E", "⌮"); + put("\\u2312", "⌒"); + put("\\u2313", "⌓"); + put("\\u22B0", "⊰"); + put("\\uD835\\uDCC5", "𝓅"); + put("\\u03C8", "ψ"); + put("\\u2008", " "); + put("\\uD835\\uDD2E", "𝔮"); + put("\\uD835\\uDD62", "𝕢"); + put("\\u2057", "⁗"); + put("\\uD835\\uDCC6", "𝓆"); + put("\\u2A16", "⨖"); + put("\\u003F", "?"); + put("\\u291C", "⤜"); + put("\\u2964", "⥤"); + put("\\u223D\\u0331", "∽̱"); + put("\\u0155", "ŕ"); + put("\\u29B3", "⦳"); + put("\\u2992", "⦒"); + put("\\u29A5", "⦥"); + put("\\u00BB", "»"); + put("\\u2975", "⥵"); + put("\\u2920", "⤠"); + put("\\u2933", "⤳"); + put("\\u291E", "⤞"); + put("\\u2945", "⥅"); + put("\\u2974", "⥴"); + put("\\u21A3", "↣"); + put("\\u219D", "↝"); + put("\\u291A", "⤚"); + put("\\u2236", "∶"); + put("\\u2773", "❳"); + put("\\u007D", "}"); + put("\\u005D", "]"); + put("\\u298C", "⦌"); + put("\\u298E", "⦎"); + put("\\u2990", "⦐"); + put("\\u0159", "ř"); + put("\\u0157", "ŗ"); + put("\\u0440", "р"); + put("\\u2937", "⤷"); + put("\\u2969", "⥩"); + put("\\u21B3", "↳"); + put("\\u25AD", "▭"); + put("\\u297D", "⥽"); + put("\\uD835\\uDD2F", "𝔯"); + put("\\u296C", "⥬"); + put("\\u03C1", "ρ"); + put("\\u03F1", "ϱ"); + put("\\u21C9", "⇉"); + put("\\u22CC", "⋌"); + put("\\u02DA", "˚"); + put("\\u200F", "‏"); + put("\\u23B1", "⎱"); + put("\\u2AEE", "⫮"); + put("\\u27ED", "⟭"); + put("\\u21FE", "⇾"); + put("\\u2986", "⦆"); + put("\\uD835\\uDD63", "𝕣"); + put("\\u2A2E", "⨮"); + put("\\u27FC", "⟼"); + put("\\u2A35", "⨵"); + put("\\u0029", ")"); + put("\\u2994", "⦔"); + put("\\u2A12", "⨒"); + put("\\u203A", "›"); + put("\\uD835\\uDCC7", "𝓇"); + put("\\u22CA", "⋊"); + put("\\u25B9", "▹"); + put("\\u29CE", "⧎"); + put("\\u2968", "⥨"); + put("\\u211E", "℞"); + put("\\u015B", "ś"); + put("\\u2AB4", "⪴"); + put("\\u2AB8", "⪸"); + put("\\u0161", "š"); + put("\\u015F", "ş"); + put("\\u015D", "ŝ"); + put("\\u2AB6", "⪶"); + put("\\u2ABA", "⪺"); + put("\\u22E9", "⋩"); + put("\\u2A13", "⨓"); + put("\\u0441", "с"); + put("\\u22C5", "⋅"); + put("\\u2A66", "⩦"); + put("\\u21D8", "⇘"); + put("\\u00A7", "§"); + put("\\u003B", ";"); + put("\\u2929", "⤩"); + put("\\u2736", "✶"); + put("\\uD835\\uDD30", "𝔰"); + put("\\u266F", "♯"); + put("\\u0449", "щ"); + put("\\u0448", "ш"); + put("\\u00AD", "­"); + put("\\u03C3", "σ"); + put("\\u03C2", "ς"); + put("\\u2A6A", "⩪"); + put("\\u2A9E", "⪞"); + put("\\u2AA0", "⪠"); + put("\\u2A9D", "⪝"); + put("\\u2A9F", "⪟"); + put("\\u2246", "≆"); + put("\\u2A24", "⨤"); + put("\\u2972", "⥲"); + put("\\u2A33", "⨳"); + put("\\u29E4", "⧤"); + put("\\u2323", "⌣"); + put("\\u2AAA", "⪪"); + put("\\u2AAC", "⪬"); + put("\\u2AAC\\uFE00", "⪬︀"); + put("\\u044C", "ь"); + put("\\u002F", "/"); + put("\\u29C4", "⧄"); + put("\\u233F", "⌿"); + put("\\uD835\\uDD64", "𝕤"); + put("\\u2660", "♠"); + put("\\u2293\\uFE00", "⊓︀"); + put("\\u2294\\uFE00", "⊔︀"); + put("\\uD835\\uDCC8", "𝓈"); + put("\\u2606", "☆"); + put("\\u03D5", "ϕ"); + put("\\u2282", "⊂"); + put("\\u2AC5", "⫅"); + put("\\u2ABD", "⪽"); + put("\\u2AC3", "⫃"); + put("\\u2AC1", "⫁"); + put("\\u2ACB", "⫋"); + put("\\u228A", "⊊"); + put("\\u2ABF", "⪿"); + put("\\u2979", "⥹"); + put("\\u2AC7", "⫇"); + put("\\u2AD5", "⫕"); + put("\\u2AD3", "⫓"); + put("\\u266A", "♪"); + put("\\u00B9", "¹"); + put("\\u00B2", "²"); + put("\\u00B3", "³"); + put("\\u2AC6", "⫆"); + put("\\u2ABE", "⪾"); + put("\\u2AD8", "⫘"); + put("\\u2AC4", "⫄"); + put("\\u27C9", "⟉"); + put("\\u2AD7", "⫗"); + put("\\u297B", "⥻"); + put("\\u2AC2", "⫂"); + put("\\u2ACC", "⫌"); + put("\\u228B", "⊋"); + put("\\u2AC0", "⫀"); + put("\\u2AC8", "⫈"); + put("\\u2AD4", "⫔"); + put("\\u2AD6", "⫖"); + put("\\u21D9", "⇙"); + put("\\u292A", "⤪"); + put("\\u00DF", "ß"); + put("\\u2316", "⌖"); + put("\\u03C4", "τ"); + put("\\u0165", "ť"); + put("\\u0163", "ţ"); + put("\\u0442", "т"); + put("\\u2315", "⌕"); + put("\\uD835\\uDD31", "𝔱"); + put("\\u03B8", "θ"); + put("\\u03D1", "ϑ"); + put("\\u00FE", "þ"); + put("\\u00D7", "×"); + put("\\u2A31", "⨱"); + put("\\u2A30", "⨰"); + put("\\u2336", "⌶"); + put("\\u2AF1", "⫱"); + put("\\uD835\\uDD65", "𝕥"); + put("\\u2ADA", "⫚"); + put("\\u2034", "‴"); + put("\\u25B5", "▵"); + put("\\u25BF", "▿"); + put("\\u225C", "≜"); + put("\\u25EC", "◬"); + put("\\u2A3A", "⨺"); + put("\\u2A39", "⨹"); + put("\\u29CD", "⧍"); + put("\\u2A3B", "⨻"); + put("\\u23E2", "⏢"); + put("\\uD835\\uDCC9", "𝓉"); + put("\\u0446", "ц"); + put("\\u045B", "ћ"); + put("\\u0167", "ŧ"); + put("\\u2963", "⥣"); + put("\\u00FA", "ú"); + put("\\u045E", "ў"); + put("\\u016D", "ŭ"); + put("\\u00FB", "û"); + put("\\u0443", "у"); + put("\\u0171", "ű"); + put("\\u297E", "⥾"); + put("\\uD835\\uDD32", "𝔲"); + put("\\u00F9", "ù"); + put("\\u2580", "▀"); + put("\\u231C", "⌜"); + put("\\u230F", "⌏"); + put("\\u25F8", "◸"); + put("\\u016B", "ū"); + put("\\u0173", "ų"); + put("\\uD835\\uDD66", "𝕦"); + put("\\u03C5", "υ"); + put("\\u21C8", "⇈"); + put("\\u231D", "⌝"); + put("\\u230E", "⌎"); + put("\\u016F", "ů"); + put("\\u25F9", "◹"); + put("\\uD835\\uDCCA", "𝓊"); + put("\\u22F0", "⋰"); + put("\\u0169", "ũ"); + put("\\u00FC", "ü"); + put("\\u29A7", "⦧"); + put("\\u2AE8", "⫨"); + put("\\u2AE9", "⫩"); + put("\\u299C", "⦜"); + put("\\u2205", "∅"); + put("\\u228A\\uFE00", "⊊︀"); + put("\\u2ACB\\uFE00", "⫋︀"); + put("\\u228B\\uFE00", "⊋︀"); + put("\\u2ACC\\uFE00", "⫌︀"); + put("\\u0432", "в"); + put("\\u22BB", "⊻"); + put("\\u225A", "≚"); + put("\\u22EE", "⋮"); + put("\\uD835\\uDD33", "𝔳"); + put("\\uD835\\uDD67", "𝕧"); + put("\\uD835\\uDCCB", "𝓋"); + put("\\u299A", "⦚"); + put("\\u0175", "ŵ"); + put("\\u2A5F", "⩟"); + put("\\u2259", "≙"); + put("\\u2118", "℘"); + put("\\uD835\\uDD34", "𝔴"); + put("\\uD835\\uDD68", "𝕨"); + put("\\uD835\\uDCCC", "𝓌"); + put("\\uD835\\uDD35", "𝔵"); + put("\\u03BE", "ξ"); + put("\\u22FB", "⋻"); + put("\\uD835\\uDD69", "𝕩"); + put("\\uD835\\uDCCD", "𝓍"); + put("\\u00FD", "ý"); + put("\\u044F", "я"); + put("\\u0177", "ŷ"); + put("\\u044B", "ы"); + put("\\u00A5", "¥"); + put("\\uD835\\uDD36", "𝔶"); + put("\\u0457", "ї"); + put("\\uD835\\uDD6A", "𝕪"); + put("\\uD835\\uDCCE", "𝓎"); + put("\\u044E", "ю"); + put("\\u00FF", "ÿ"); + put("\\u017A", "ź"); + put("\\u017E", "ž"); + put("\\u0437", "з"); + put("\\u017C", "ż"); + put("\\u03B6", "ζ"); + put("\\uD835\\uDD37", "𝔷"); + put("\\u0436", "ж"); + put("\\u21DD", "⇝"); + put("\\uD835\\uDD6B", "𝕫"); + put("\\uD835\\uDCCF", "𝓏"); + put("\\u200D", "‍"); + put("\\u200C", "‌"); + + }}; + } diff --git a/src/main/java/strman/Strman.java b/src/main/java/strman/Strman.java index 04da8b2..517e486 100644 --- a/src/main/java/strman/Strman.java +++ b/src/main/java/strman/Strman.java @@ -897,6 +897,17 @@ public abstract class Strman { return Arrays.stream(entities).map(e -> HtmlEntities.decodedEntities.get(e)).collect(joining()); } + /** + * Convert all applicable characters to HTML entities. + * + * @param html The HTML to encode + * @return The encoded data + */ + public static String htmlEncode(final String html) { + validate(html, NULL_STRING_PREDICATE, NULL_STRING_MSG_SUPPLIER); + return html.chars().mapToObj(c -> "\\u" + String.format("%04x", c).toUpperCase()).map(e -> HtmlEntities.encodedEntities.get(e)).collect(joining()); + } + public static String decode(final String value, final int digits, final int radix) { validate(value, NULL_STRING_PREDICATE, NULL_STRING_MSG_SUPPLIER); return Arrays diff --git a/src/test/java/strman/StrmanTest.java b/src/test/java/strman/StrmanTest.java index dd317d6..8404968 100644 --- a/src/test/java/strman/StrmanTest.java +++ b/src/test/java/strman/StrmanTest.java @@ -654,4 +654,13 @@ public class StrmanTest { assertThat(htmlDecode("Ж"), equalTo("Ж")); assertThat(htmlDecode("┐"), equalTo("┐")); } + + @Test + public void htmlEncode_shouldBeEncodedToHtmlEntities() throws Exception { + assertThat(htmlEncode("á"), equalTo("á")); + assertThat(htmlEncode("áéíóú"), equalTo("áéíóú")); + assertThat(htmlEncode("Ш"), equalTo("Ш")); + assertThat(htmlEncode("Ж"), equalTo("Ж")); + assertThat(htmlEncode("┐"), equalTo("┐")); + } } \ No newline at end of file