|
@@ -51,9 +51,201 @@ public final class CommonUtils {
|
|
|
{"\"", """},
|
|
|
{"&", "&"},
|
|
|
{"\"", "”"},
|
|
|
+ {"\u0192", "ƒ"},
|
|
|
+
|
|
|
+ {"\u0391", "Α"},
|
|
|
+ {"\u0392", "Β"},
|
|
|
+ {"\u0393", "Γ"},
|
|
|
+ {"\u0394", "Δ"},
|
|
|
+ {"\u0395", "Ε"},
|
|
|
+ {"\u0396", "Ζ"},
|
|
|
+ {"\u0397", "Η"},
|
|
|
+ {"\u0398", "Θ"},
|
|
|
+ {"\u0399", "Ι"},
|
|
|
+ {"\u039A", "Κ"},
|
|
|
+ {"\u039B", "Λ"},
|
|
|
+ {"\u039C", "Μ"},
|
|
|
+ {"\u039D", "Ν"},
|
|
|
+ {"\u039E", "Ξ"},
|
|
|
+ {"\u039F", "Ο"},
|
|
|
+ {"\u03A0", "Π"},
|
|
|
+ {"\u03A1", "Ρ"},
|
|
|
+
|
|
|
+ {"\u03A3", "Σ"},
|
|
|
+ {"\u03A4", "Τ"},
|
|
|
+ {"\u03A5", "Υ"},
|
|
|
+ {"\u03A6", "Φ"},
|
|
|
+ {"\u03A7", "Χ"},
|
|
|
+ {"\u03A8", "Ψ"},
|
|
|
+ {"\u03A9", "Ω"},
|
|
|
+ {"\u03B1", "α"},
|
|
|
+ {"\u03B2", "β"},
|
|
|
+ {"\u03B3", "γ"},
|
|
|
+ {"\u03B4", "δ"},
|
|
|
+ {"\u03B5", "ε"},
|
|
|
+ {"\u03B6", "ζ"},
|
|
|
+ {"\u03B7", "η"},
|
|
|
+ {"\u03B8", "θ"},
|
|
|
+ {"\u03B9", "ι"},
|
|
|
+ {"\u03BA", "κ"},
|
|
|
+ {"\u03BB", "λ"},
|
|
|
+ {"\u03BC", "μ"},
|
|
|
+ {"\u03BD", "ν"},
|
|
|
+ {"\u03BE", "ξ"},
|
|
|
+ {"\u03BF", "ο"},
|
|
|
+ {"\u03C0", "π"},
|
|
|
+ {"\u03C1", "ρ"},
|
|
|
+ {"\u03C2", "ς"},
|
|
|
+ {"\u03C3", "σ"},
|
|
|
+ {"\u03C4", "τ"},
|
|
|
+ {"\u03C5", "υ"},
|
|
|
+ {"\u03C6", "φ"},
|
|
|
+ {"\u03C7", "χ"},
|
|
|
+ {"\u03C8", "ψ"},
|
|
|
+ {"\u03C9", "ω"},
|
|
|
+ {"\u03D1", "ϑ"},
|
|
|
+ {"\u03D2", "ϒ"},
|
|
|
+ {"\u03D6", "ϖ"},
|
|
|
+
|
|
|
+ {"\u2022", "•"},
|
|
|
+
|
|
|
+ {"\u2026", "…"},
|
|
|
+ {"\u2032", "′"},
|
|
|
+ {"\u2033", "″"},
|
|
|
+ {"\u203E", "‾"},
|
|
|
+ {"\u2044", "⁄"},
|
|
|
+
|
|
|
+ {"\u2118", "℘"},
|
|
|
+ {"\u2111", "ℑ"},
|
|
|
+ {"\u211C", "ℜ"},
|
|
|
+ {"\u2122", "™"},
|
|
|
+ {"\u2135", "ℵ"},
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2190", "←"},
|
|
|
+ {"\u2191", "↑"},
|
|
|
+ {"\u2192", "→"},
|
|
|
+ {"\u2193", "↓"},
|
|
|
+ {"\u2194", "↔"},
|
|
|
+ {"\u21B5", "↵"},
|
|
|
+ {"\u21D0", "⇐"},
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ {"\u21D1", "⇑"},
|
|
|
+ {"\u21D2", "⇒"},
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ {"\u21D3", "⇓"},
|
|
|
+ {"\u21D4", "⇔"},
|
|
|
+
|
|
|
+ {"\u2200", "∀"},
|
|
|
+ {"\u2202", "∂"},
|
|
|
+ {"\u2203", "∃"},
|
|
|
+ {"\u2205", "∅"},
|
|
|
+ {"\u2207", "∇"},
|
|
|
+ {"\u2208", "∈"},
|
|
|
+ {"\u2209", "∉"},
|
|
|
+ {"\u220B", "∋"},
|
|
|
+
|
|
|
+ {"\u220F", "∏"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2211", "∑"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2212", "−"},
|
|
|
+ {"\u2217", "∗"},
|
|
|
+ {"\u221A", "√"},
|
|
|
+ {"\u221D", "∝"},
|
|
|
+ {"\u221E", "∞"},
|
|
|
+ {"\u2220", "∠"},
|
|
|
+ {"\u2227", "∧"},
|
|
|
+ {"\u2228", "∨"},
|
|
|
+ {"\u2229", "∩"},
|
|
|
+ {"\u222A", "∪"},
|
|
|
+ {"\u222B", "∫"},
|
|
|
+ {"\u2234", "∴"},
|
|
|
+ {"\u223C", "∼"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2245", "≅"},
|
|
|
+ {"\u2248", "≈"},
|
|
|
+ {"\u2260", "≠"},
|
|
|
+ {"\u2261", "≡"},
|
|
|
+ {"\u2264", "≤"},
|
|
|
+ {"\u2265", "≥"},
|
|
|
+ {"\u2282", "⊂"},
|
|
|
+ {"\u2283", "⊃"},
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2284", "⊄"},
|
|
|
+ {"\u2286", "⊆"},
|
|
|
+ {"\u2287", "⊇"},
|
|
|
+ {"\u2295", "⊕"},
|
|
|
+ {"\u2297", "⊗"},
|
|
|
+ {"\u22A5", "⊥"},
|
|
|
+ {"\u22C5", "⋅"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u2308", "⌈"},
|
|
|
+ {"\u2309", "⌉"},
|
|
|
+ {"\u230A", "⌊"},
|
|
|
+ {"\u230B", "⌋"},
|
|
|
+ {"\u2329", "⟨"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u232A", "⟩"},
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+ {"\u25CA", "◊"},
|
|
|
+
|
|
|
+ {"\u2660", "♠"},
|
|
|
+
|
|
|
+ {"\u2663", "♣"},
|
|
|
+ {"\u2665", "♥"},
|
|
|
+ {"\u2666", "♦"},
|
|
|
+
|
|
|
+
|
|
|
+ {"\u0152", "Œ"},
|
|
|
+ {"\u0153", "œ"},
|
|
|
+
|
|
|
+ {"\u0160", "Š"},
|
|
|
+ {"\u0161", "š"},
|
|
|
+ {"\u0178", "Ÿ"},
|
|
|
+
|
|
|
+ {"\u02C6", "ˆ"},
|
|
|
+ {"\u02DC", "˜"},
|
|
|
+
|
|
|
+ {"\u2002", " "},
|
|
|
+ {"\u2003", " "},
|
|
|
+ {"\u2009", " "},
|
|
|
+ {"\u200C", "‌"},
|
|
|
+ {"\u200D", "‍"},
|
|
|
+ {"\u200E", "‎"},
|
|
|
+ {"\u200F", "‏"},
|
|
|
+ {"\u2013", "–"},
|
|
|
+ {"\u2014", "—"},
|
|
|
+ {"\u2018", "‘"},
|
|
|
+ {"\u2019", "’"},
|
|
|
+ {"\u201A", "‚"},
|
|
|
+ {"\u201C", "“"},
|
|
|
+
|
|
|
+ {"\u201E", "„"},
|
|
|
+ {"\u2020", "†"},
|
|
|
+ {"\u2021", "‡"},
|
|
|
+ {"\u2030", "‰"},
|
|
|
+ {"\u2039", "‹"},
|
|
|
+
|
|
|
+ {"\u203A", "›"},
|
|
|
+
|
|
|
+ {"\u20AC", "€"},
|
|
|
};
|
|
|
|
|
|
- public static String[][] BASIC_UNESCAPE() { return BASIC_UNESCAPE.clone(); }
|
|
|
private static final String[][] BASIC_UNESCAPE = invert(BASIC_ESCAPE);
|
|
|
|
|
|
private static final Logger log = LoggerFactory.getLogger(CommonUtils.class);
|
|
@@ -480,9 +672,8 @@ public final class CommonUtils {
|
|
|
*/
|
|
|
public static final CharSequenceTranslator UNESCAPE_HTML4 =
|
|
|
new AggregateTranslator(
|
|
|
- new LookupTranslator(CommonUtils.BASIC_UNESCAPE()),
|
|
|
+ new LookupTranslator(BASIC_UNESCAPE),
|
|
|
new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
|
|
|
- new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE()),
|
|
|
new NumericEntityUnescaper()
|
|
|
);
|
|
|
|