|
|
|
|
@ -1,393 +0,0 @@
|
|
|
|
|
/*
|
|
|
|
|
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
|
* contributor license agreements. See the NOTICE file distributed with
|
|
|
|
|
* this work for additional information regarding copyright ownership.
|
|
|
|
|
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
|
* (the "License"); you may not use this file except in compliance with
|
|
|
|
|
* the License. You may obtain a copy of the License at
|
|
|
|
|
*
|
|
|
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
|
*
|
|
|
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
|
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
|
* See the License for the specific language governing permissions and
|
|
|
|
|
* limitations under the License.
|
|
|
|
|
*/
|
|
|
|
|
package org.mariotaku.twidere.util
|
|
|
|
|
|
|
|
|
|
import java.util.*
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Class holding various entity data for HTML and XML - generally for use with
|
|
|
|
|
* the LookupTranslator.
|
|
|
|
|
* All Maps are generated using `java.util.Collections.unmodifiableMap()`.
|
|
|
|
|
*
|
|
|
|
|
* @since 1.0
|
|
|
|
|
*/
|
|
|
|
|
object EntityArrays {
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* A Map<CharSequence, CharSequence> to to escape
|
|
|
|
|
* [ISO-8859-1](https://secure.wikimedia.org/wikipedia/en/wiki/ISO/IEC_8859-1)
|
|
|
|
|
* characters to their named HTML 3.x equivalents.
|
|
|
|
|
*/
|
|
|
|
|
val ISO8859_1_ESCAPE: Map<CharSequence, CharSequence> = mapOf(
|
|
|
|
|
"\u00A0" to " ", // non-breaking space
|
|
|
|
|
"\u00A1" to "¡", // inverted exclamation mark
|
|
|
|
|
"\u00A2" to "¢", // cent sign
|
|
|
|
|
"\u00A3" to "£", // pound sign
|
|
|
|
|
"\u00A4" to "¤", // currency sign
|
|
|
|
|
"\u00A5" to "¥", // yen sign = yuan sign
|
|
|
|
|
"\u00A6" to "¦", // broken bar = broken vertical bar
|
|
|
|
|
"\u00A7" to "§", // section sign
|
|
|
|
|
"\u00A8" to "¨", // diaeresis = spacing diaeresis
|
|
|
|
|
"\u00A9" to "©", // © - copyright sign
|
|
|
|
|
"\u00AA" to "ª", // feminine ordinal indicator
|
|
|
|
|
"\u00AB" to "«", // left-pointing double angle quotation mark = left pointing guillemet
|
|
|
|
|
"\u00AC" to "¬", // not sign
|
|
|
|
|
"\u00AD" to "­", // soft hyphen = discretionary hyphen
|
|
|
|
|
"\u00AE" to "®", // ® - registered trademark sign
|
|
|
|
|
"\u00AF" to "¯", // macron = spacing macron = overline = APL overbar
|
|
|
|
|
"\u00B0" to "°", // degree sign
|
|
|
|
|
"\u00B1" to "±", // plus-minus sign = plus-or-minus sign
|
|
|
|
|
"\u00B2" to "²", // superscript two = superscript digit two = squared
|
|
|
|
|
"\u00B3" to "³", // superscript three = superscript digit three = cubed
|
|
|
|
|
"\u00B4" to "´", // acute accent = spacing acute
|
|
|
|
|
"\u00B5" to "µ", // micro sign
|
|
|
|
|
"\u00B6" to "¶", // pilcrow sign = paragraph sign
|
|
|
|
|
"\u00B7" to "·", // middle dot = Georgian comma = Greek middle dot
|
|
|
|
|
"\u00B8" to "¸", // cedilla = spacing cedilla
|
|
|
|
|
"\u00B9" to "¹", // superscript one = superscript digit one
|
|
|
|
|
"\u00BA" to "º", // masculine ordinal indicator
|
|
|
|
|
"\u00BB" to "»", // right-pointing double angle quotation mark = right pointing guillemet
|
|
|
|
|
"\u00BC" to "¼", // vulgar fraction one quarter = fraction one quarter
|
|
|
|
|
"\u00BD" to "½", // vulgar fraction one half = fraction one half
|
|
|
|
|
"\u00BE" to "¾", // vulgar fraction three quarters = fraction three quarters
|
|
|
|
|
"\u00BF" to "¿", // inverted question mark = turned question mark
|
|
|
|
|
"\u00C0" to "À", // À - uppercase A, grave accent
|
|
|
|
|
"\u00C1" to "Á", // Á - uppercase A, acute accent
|
|
|
|
|
"\u00C2" to "Â", // Â - uppercase A, circumflex accent
|
|
|
|
|
"\u00C3" to "Ã", // Ã - uppercase A, tilde
|
|
|
|
|
"\u00C4" to "Ä", // Ä - uppercase A, umlaut
|
|
|
|
|
"\u00C5" to "Å", // Å - uppercase A, ring
|
|
|
|
|
"\u00C6" to "Æ", // Æ - uppercase AE
|
|
|
|
|
"\u00C7" to "Ç", // Ç - uppercase C, cedilla
|
|
|
|
|
"\u00C8" to "È", // È - uppercase E, grave accent
|
|
|
|
|
"\u00C9" to "É", // É - uppercase E, acute accent
|
|
|
|
|
"\u00CA" to "Ê", // Ê - uppercase E, circumflex accent
|
|
|
|
|
"\u00CB" to "Ë", // Ë - uppercase E, umlaut
|
|
|
|
|
"\u00CC" to "Ì", // Ì - uppercase I, grave accent
|
|
|
|
|
"\u00CD" to "Í", // Í - uppercase I, acute accent
|
|
|
|
|
"\u00CE" to "Î", // Î - uppercase I, circumflex accent
|
|
|
|
|
"\u00CF" to "Ï", // Ï - uppercase I, umlaut
|
|
|
|
|
"\u00D0" to "Ð", // Ð - uppercase Eth, Icelandic
|
|
|
|
|
"\u00D1" to "Ñ", // Ñ - uppercase N, tilde
|
|
|
|
|
"\u00D2" to "Ò", // Ò - uppercase O, grave accent
|
|
|
|
|
"\u00D3" to "Ó", // Ó - uppercase O, acute accent
|
|
|
|
|
"\u00D4" to "Ô", // Ô - uppercase O, circumflex accent
|
|
|
|
|
"\u00D5" to "Õ", // Õ - uppercase O, tilde
|
|
|
|
|
"\u00D6" to "Ö", // Ö - uppercase O, umlaut
|
|
|
|
|
"\u00D7" to "×", // multiplication sign
|
|
|
|
|
"\u00D8" to "Ø", // Ø - uppercase O, slash
|
|
|
|
|
"\u00D9" to "Ù", // Ù - uppercase U, grave accent
|
|
|
|
|
"\u00DA" to "Ú", // Ú - uppercase U, acute accent
|
|
|
|
|
"\u00DB" to "Û", // Û - uppercase U, circumflex accent
|
|
|
|
|
"\u00DC" to "Ü", // Ü - uppercase U, umlaut
|
|
|
|
|
"\u00DD" to "Ý", // Ý - uppercase Y, acute accent
|
|
|
|
|
"\u00DE" to "Þ", // Þ - uppercase THORN, Icelandic
|
|
|
|
|
"\u00DF" to "ß", // ß - lowercase sharps, German
|
|
|
|
|
"\u00E0" to "à", // à - lowercase a, grave accent
|
|
|
|
|
"\u00E1" to "á", // á - lowercase a, acute accent
|
|
|
|
|
"\u00E2" to "â", // â - lowercase a, circumflex accent
|
|
|
|
|
"\u00E3" to "ã", // ã - lowercase a, tilde
|
|
|
|
|
"\u00E4" to "ä", // ä - lowercase a, umlaut
|
|
|
|
|
"\u00E5" to "å", // å - lowercase a, ring
|
|
|
|
|
"\u00E6" to "æ", // æ - lowercase ae
|
|
|
|
|
"\u00E7" to "ç", // ç - lowercase c, cedilla
|
|
|
|
|
"\u00E8" to "è", // è - lowercase e, grave accent
|
|
|
|
|
"\u00E9" to "é", // é - lowercase e, acute accent
|
|
|
|
|
"\u00EA" to "ê", // ê - lowercase e, circumflex accent
|
|
|
|
|
"\u00EB" to "ë", // ë - lowercase e, umlaut
|
|
|
|
|
"\u00EC" to "ì", // ì - lowercase i, grave accent
|
|
|
|
|
"\u00ED" to "í", // í - lowercase i, acute accent
|
|
|
|
|
"\u00EE" to "î", // î - lowercase i, circumflex accent
|
|
|
|
|
"\u00EF" to "ï", // ï - lowercase i, umlaut
|
|
|
|
|
"\u00F0" to "ð", // ð - lowercase eth, Icelandic
|
|
|
|
|
"\u00F1" to "ñ", // ñ - lowercase n, tilde
|
|
|
|
|
"\u00F2" to "ò", // ò - lowercase o, grave accent
|
|
|
|
|
"\u00F3" to "ó", // ó - lowercase o, acute accent
|
|
|
|
|
"\u00F4" to "ô", // ô - lowercase o, circumflex accent
|
|
|
|
|
"\u00F5" to "õ", // õ - lowercase o, tilde
|
|
|
|
|
"\u00F6" to "ö", // ö - lowercase o, umlaut
|
|
|
|
|
"\u00F7" to "÷", // division sign
|
|
|
|
|
"\u00F8" to "ø", // ø - lowercase o, slash
|
|
|
|
|
"\u00F9" to "ù", // ù - lowercase u, grave accent
|
|
|
|
|
"\u00FA" to "ú", // ú - lowercase u, acute accent
|
|
|
|
|
"\u00FB" to "û", // û - lowercase u, circumflex accent
|
|
|
|
|
"\u00FC" to "ü", // ü - lowercase u, umlaut
|
|
|
|
|
"\u00FD" to "ý", // ý - lowercase y, acute accent
|
|
|
|
|
"\u00FE" to "þ", // þ - lowercase thorn, Icelandic
|
|
|
|
|
"\u00FF" to "ÿ" // ÿ - lowercase y, umlaut
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Reverse of [.ISO8859_1_ESCAPE] for unescaping purposes.
|
|
|
|
|
*/
|
|
|
|
|
val ISO8859_1_UNESCAPE: Map<CharSequence, CharSequence> = ISO8859_1_ESCAPE.invert()
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* A Map<CharSequence, CharSequence> to escape additional
|
|
|
|
|
* [character entity references](http://www.w3.org/TR/REC-html40/sgml/entities.html).
|
|
|
|
|
* Note that this must be used with [.ISO8859_1_ESCAPE] to get the full list of
|
|
|
|
|
* HTML 4.0 character entities.
|
|
|
|
|
*/
|
|
|
|
|
val HTML40_EXTENDED_ESCAPE: Map<CharSequence, CharSequence> = mapOf(
|
|
|
|
|
// <!-- Latin Extended-B -->
|
|
|
|
|
"\u0192" to "ƒ", // latin small f with hook = function= florin, U+0192 ISOtech -->
|
|
|
|
|
// <!-- Greek -->
|
|
|
|
|
"\u0391" to "Α", // greek capital letter alpha, U+0391 -->
|
|
|
|
|
"\u0392" to "Β", // greek capital letter beta, U+0392 -->
|
|
|
|
|
"\u0393" to "Γ", // greek capital letter gamma,U+0393 ISOgrk3 -->
|
|
|
|
|
"\u0394" to "Δ", // greek capital letter delta,U+0394 ISOgrk3 -->
|
|
|
|
|
"\u0395" to "Ε", // greek capital letter epsilon, U+0395 -->
|
|
|
|
|
"\u0396" to "Ζ", // greek capital letter zeta, U+0396 -->
|
|
|
|
|
"\u0397" to "Η", // greek capital letter eta, U+0397 -->
|
|
|
|
|
"\u0398" to "Θ", // greek capital letter theta,U+0398 ISOgrk3 -->
|
|
|
|
|
"\u0399" to "Ι", // greek capital letter iota, U+0399 -->
|
|
|
|
|
"\u039A" to "Κ", // greek capital letter kappa, U+039A -->
|
|
|
|
|
"\u039B" to "Λ", // greek capital letter lambda,U+039B ISOgrk3 -->
|
|
|
|
|
"\u039C" to "Μ", // greek capital letter mu, U+039C -->
|
|
|
|
|
"\u039D" to "Ν", // greek capital letter nu, U+039D -->
|
|
|
|
|
"\u039E" to "Ξ", // greek capital letter xi, U+039E ISOgrk3 -->
|
|
|
|
|
"\u039F" to "Ο", // greek capital letter omicron, U+039F -->
|
|
|
|
|
"\u03A0" to "Π", // greek capital letter pi, U+03A0 ISOgrk3 -->
|
|
|
|
|
"\u03A1" to "Ρ", // greek capital letter rho, U+03A1 -->
|
|
|
|
|
// <!-- there is no Sigmaf, and no U+03A2 character either -->
|
|
|
|
|
"\u03A3" to "Σ", // greek capital letter sigma,U+03A3 ISOgrk3 -->
|
|
|
|
|
"\u03A4" to "Τ", // greek capital letter tau, U+03A4 -->
|
|
|
|
|
"\u03A5" to "Υ", // greek capital letter upsilon,U+03A5 ISOgrk3 -->
|
|
|
|
|
"\u03A6" to "Φ", // greek capital letter phi,U+03A6 ISOgrk3 -->
|
|
|
|
|
"\u03A7" to "Χ", // greek capital letter chi, U+03A7 -->
|
|
|
|
|
"\u03A8" to "Ψ", // greek capital letter psi,U+03A8 ISOgrk3 -->
|
|
|
|
|
"\u03A9" to "Ω", // greek capital letter omega,U+03A9 ISOgrk3 -->
|
|
|
|
|
"\u03B1" to "α", // greek small letter alpha,U+03B1 ISOgrk3 -->
|
|
|
|
|
"\u03B2" to "β", // greek small letter beta, U+03B2 ISOgrk3 -->
|
|
|
|
|
"\u03B3" to "γ", // greek small letter gamma,U+03B3 ISOgrk3 -->
|
|
|
|
|
"\u03B4" to "δ", // greek small letter delta,U+03B4 ISOgrk3 -->
|
|
|
|
|
"\u03B5" to "ε", // greek small letter epsilon,U+03B5 ISOgrk3 -->
|
|
|
|
|
"\u03B6" to "ζ", // greek small letter zeta, U+03B6 ISOgrk3 -->
|
|
|
|
|
"\u03B7" to "η", // greek small letter eta, U+03B7 ISOgrk3 -->
|
|
|
|
|
"\u03B8" to "θ", // greek small letter theta,U+03B8 ISOgrk3 -->
|
|
|
|
|
"\u03B9" to "ι", // greek small letter iota, U+03B9 ISOgrk3 -->
|
|
|
|
|
"\u03BA" to "κ", // greek small letter kappa,U+03BA ISOgrk3 -->
|
|
|
|
|
"\u03BB" to "λ", // greek small letter lambda,U+03BB ISOgrk3 -->
|
|
|
|
|
"\u03BC" to "μ", // greek small letter mu, U+03BC ISOgrk3 -->
|
|
|
|
|
"\u03BD" to "ν", // greek small letter nu, U+03BD ISOgrk3 -->
|
|
|
|
|
"\u03BE" to "ξ", // greek small letter xi, U+03BE ISOgrk3 -->
|
|
|
|
|
"\u03BF" to "ο", // greek small letter omicron, U+03BF NEW -->
|
|
|
|
|
"\u03C0" to "π", // greek small letter pi, U+03C0 ISOgrk3 -->
|
|
|
|
|
"\u03C1" to "ρ", // greek small letter rho, U+03C1 ISOgrk3 -->
|
|
|
|
|
"\u03C2" to "ς", // greek small letter final sigma,U+03C2 ISOgrk3 -->
|
|
|
|
|
"\u03C3" to "σ", // greek small letter sigma,U+03C3 ISOgrk3 -->
|
|
|
|
|
"\u03C4" to "τ", // greek small letter tau, U+03C4 ISOgrk3 -->
|
|
|
|
|
"\u03C5" to "υ", // greek small letter upsilon,U+03C5 ISOgrk3 -->
|
|
|
|
|
"\u03C6" to "φ", // greek small letter phi, U+03C6 ISOgrk3 -->
|
|
|
|
|
"\u03C7" to "χ", // greek small letter chi, U+03C7 ISOgrk3 -->
|
|
|
|
|
"\u03C8" to "ψ", // greek small letter psi, U+03C8 ISOgrk3 -->
|
|
|
|
|
"\u03C9" to "ω", // greek small letter omega,U+03C9 ISOgrk3 -->
|
|
|
|
|
"\u03D1" to "ϑ", // greek small letter theta symbol,U+03D1 NEW -->
|
|
|
|
|
"\u03D2" to "ϒ", // greek upsilon with hook symbol,U+03D2 NEW -->
|
|
|
|
|
"\u03D6" to "ϖ", // greek pi symbol, U+03D6 ISOgrk3 -->
|
|
|
|
|
// <!-- General Punctuation -->
|
|
|
|
|
"\u2022" to "•", // bullet = black small circle,U+2022 ISOpub -->
|
|
|
|
|
// <!-- bullet is NOT the same as bullet operator, U+2219 -->
|
|
|
|
|
"\u2026" to "…", // horizontal ellipsis = three dot leader,U+2026 ISOpub -->
|
|
|
|
|
"\u2032" to "′", // prime = minutes = feet, U+2032 ISOtech -->
|
|
|
|
|
"\u2033" to "″", // double prime = seconds = inches,U+2033 ISOtech -->
|
|
|
|
|
"\u203E" to "‾", // overline = spacing overscore,U+203E NEW -->
|
|
|
|
|
"\u2044" to "⁄", // fraction slash, U+2044 NEW -->
|
|
|
|
|
// <!-- Letterlike Symbols -->
|
|
|
|
|
"\u2118" to "℘", // script capital P = power set= Weierstrass p, U+2118 ISOamso -->
|
|
|
|
|
"\u2111" to "ℑ", // blackletter capital I = imaginary part,U+2111 ISOamso -->
|
|
|
|
|
"\u211C" to "ℜ", // blackletter capital R = real part symbol,U+211C ISOamso -->
|
|
|
|
|
"\u2122" to "™", // trade mark sign, U+2122 ISOnum -->
|
|
|
|
|
"\u2135" to "ℵ", // alef symbol = first transfinite cardinal,U+2135 NEW -->
|
|
|
|
|
// <!-- alef symbol is NOT the same as hebrew letter alef,U+05D0 although the
|
|
|
|
|
// same glyph could be used to depict both characters -->
|
|
|
|
|
// <!-- Arrows -->
|
|
|
|
|
"\u2190" to "←", // leftwards arrow, U+2190 ISOnum -->
|
|
|
|
|
"\u2191" to "↑", // upwards arrow, U+2191 ISOnum-->
|
|
|
|
|
"\u2192" to "→", // rightwards arrow, U+2192 ISOnum -->
|
|
|
|
|
"\u2193" to "↓", // downwards arrow, U+2193 ISOnum -->
|
|
|
|
|
"\u2194" to "↔", // left right arrow, U+2194 ISOamsa -->
|
|
|
|
|
"\u21B5" to "↵", // downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
|
|
|
|
|
"\u21D0" to "⇐", // leftwards double arrow, U+21D0 ISOtech -->
|
|
|
|
|
// <!-- ISO 10646 does not say that lArr is the same as the 'is implied by'
|
|
|
|
|
// arrow but also does not have any other character for that function.
|
|
|
|
|
// So ? lArr canbe used for 'is implied by' as ISOtech suggests -->
|
|
|
|
|
"\u21D1" to "⇑", // upwards double arrow, U+21D1 ISOamsa -->
|
|
|
|
|
"\u21D2" to "⇒", // rightwards double arrow,U+21D2 ISOtech -->
|
|
|
|
|
// <!-- ISO 10646 does not say this is the 'implies' character but does not
|
|
|
|
|
// have another character with this function so ?rArr can be used for
|
|
|
|
|
// 'implies' as ISOtech suggests -->
|
|
|
|
|
"\u21D3" to "⇓", // downwards double arrow, U+21D3 ISOamsa -->
|
|
|
|
|
"\u21D4" to "⇔", // left right double arrow,U+21D4 ISOamsa -->
|
|
|
|
|
// <!-- Mathematical Operators -->
|
|
|
|
|
"\u2200" to "∀", // for all, U+2200 ISOtech -->
|
|
|
|
|
"\u2202" to "∂", // partial differential, U+2202 ISOtech -->
|
|
|
|
|
"\u2203" to "∃", // there exists, U+2203 ISOtech -->
|
|
|
|
|
"\u2205" to "∅", // empty set = null set = diameter,U+2205 ISOamso -->
|
|
|
|
|
"\u2207" to "∇", // nabla = backward difference,U+2207 ISOtech -->
|
|
|
|
|
"\u2208" to "∈", // element of, U+2208 ISOtech -->
|
|
|
|
|
"\u2209" to "∉", // not an element of, U+2209 ISOtech -->
|
|
|
|
|
"\u220B" to "∋", // contains as member, U+220B ISOtech -->
|
|
|
|
|
// <!-- should there be a more memorable name than 'ni'? -->
|
|
|
|
|
"\u220F" to "∏", // n-ary product = product sign,U+220F ISOamsb -->
|
|
|
|
|
// <!-- prod is NOT the same character as U+03A0 'greek capital letter pi'
|
|
|
|
|
// though the same glyph might be used for both -->
|
|
|
|
|
"\u2211" to "∑", // n-ary summation, U+2211 ISOamsb -->
|
|
|
|
|
// <!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
|
|
|
|
|
// though the same glyph might be used for both -->
|
|
|
|
|
"\u2212" to "−", // minus sign, U+2212 ISOtech -->
|
|
|
|
|
"\u2217" to "∗", // asterisk operator, U+2217 ISOtech -->
|
|
|
|
|
"\u221A" to "√", // square root = radical sign,U+221A ISOtech -->
|
|
|
|
|
"\u221D" to "∝", // proportional to, U+221D ISOtech -->
|
|
|
|
|
"\u221E" to "∞", // infinity, U+221E ISOtech -->
|
|
|
|
|
"\u2220" to "∠", // angle, U+2220 ISOamso -->
|
|
|
|
|
"\u2227" to "∧", // logical and = wedge, U+2227 ISOtech -->
|
|
|
|
|
"\u2228" to "∨", // logical or = vee, U+2228 ISOtech -->
|
|
|
|
|
"\u2229" to "∩", // intersection = cap, U+2229 ISOtech -->
|
|
|
|
|
"\u222A" to "∪", // union = cup, U+222A ISOtech -->
|
|
|
|
|
"\u222B" to "∫", // integral, U+222B ISOtech -->
|
|
|
|
|
"\u2234" to "∴", // therefore, U+2234 ISOtech -->
|
|
|
|
|
"\u223C" to "∼", // tilde operator = varies with = similar to,U+223C ISOtech -->
|
|
|
|
|
// <!-- tilde operator is NOT the same character as the tilde, U+007E,although
|
|
|
|
|
// the same glyph might be used to represent both -->
|
|
|
|
|
"\u2245" to "≅", // approximately equal to, U+2245 ISOtech -->
|
|
|
|
|
"\u2248" to "≈", // almost equal to = asymptotic to,U+2248 ISOamsr -->
|
|
|
|
|
"\u2260" to "≠", // not equal to, U+2260 ISOtech -->
|
|
|
|
|
"\u2261" to "≡", // identical to, U+2261 ISOtech -->
|
|
|
|
|
"\u2264" to "≤", // less-than or equal to, U+2264 ISOtech -->
|
|
|
|
|
"\u2265" to "≥", // greater-than or equal to,U+2265 ISOtech -->
|
|
|
|
|
"\u2282" to "⊂", // subset of, U+2282 ISOtech -->
|
|
|
|
|
"\u2283" to "⊃", // superset of, U+2283 ISOtech -->
|
|
|
|
|
// <!-- note that nsup, 'not a superset of, U+2283' is not covered by the
|
|
|
|
|
// Symbol font encoding and is not included. Should it be, for symmetry?
|
|
|
|
|
// It is in ISOamsn -->,
|
|
|
|
|
"\u2284" to "⊄", // not a subset of, U+2284 ISOamsn -->
|
|
|
|
|
"\u2286" to "⊆", // subset of or equal to, U+2286 ISOtech -->
|
|
|
|
|
"\u2287" to "⊇", // superset of or equal to,U+2287 ISOtech -->
|
|
|
|
|
"\u2295" to "⊕", // circled plus = direct sum,U+2295 ISOamsb -->
|
|
|
|
|
"\u2297" to "⊗", // circled times = vector product,U+2297 ISOamsb -->
|
|
|
|
|
"\u22A5" to "⊥", // up tack = orthogonal to = perpendicular,U+22A5 ISOtech -->
|
|
|
|
|
"\u22C5" to "⋅", // dot operator, U+22C5 ISOamsb -->
|
|
|
|
|
// <!-- dot operator is NOT the same character as U+00B7 middle dot -->
|
|
|
|
|
// <!-- Miscellaneous Technical -->
|
|
|
|
|
"\u2308" to "⌈", // left ceiling = apl upstile,U+2308 ISOamsc -->
|
|
|
|
|
"\u2309" to "⌉", // right ceiling, U+2309 ISOamsc -->
|
|
|
|
|
"\u230A" to "⌊", // left floor = apl downstile,U+230A ISOamsc -->
|
|
|
|
|
"\u230B" to "⌋", // right floor, U+230B ISOamsc -->
|
|
|
|
|
"\u2329" to "⟨", // left-pointing angle bracket = bra,U+2329 ISOtech -->
|
|
|
|
|
// <!-- lang is NOT the same character as U+003C 'less than' or U+2039 'single left-pointing angle quotation
|
|
|
|
|
// mark' -->
|
|
|
|
|
"\u232A" to "⟩", // right-pointing angle bracket = ket,U+232A ISOtech -->
|
|
|
|
|
// <!-- rang is NOT the same character as U+003E 'greater than' or U+203A
|
|
|
|
|
// 'single right-pointing angle quotation mark' -->
|
|
|
|
|
// <!-- Geometric Shapes -->
|
|
|
|
|
"\u25CA" to "◊", // lozenge, U+25CA ISOpub -->
|
|
|
|
|
// <!-- Miscellaneous Symbols -->
|
|
|
|
|
"\u2660" to "♠", // black spade suit, U+2660 ISOpub -->
|
|
|
|
|
// <!-- black here seems to mean filled as opposed to hollow -->
|
|
|
|
|
"\u2663" to "♣", // black club suit = shamrock,U+2663 ISOpub -->
|
|
|
|
|
"\u2665" to "♥", // black heart suit = valentine,U+2665 ISOpub -->
|
|
|
|
|
"\u2666" to "♦", // black diamond suit, U+2666 ISOpub -->
|
|
|
|
|
|
|
|
|
|
// <!-- Latin Extended-A -->
|
|
|
|
|
"\u0152" to "Œ", // -- latin capital ligature OE,U+0152 ISOlat2 -->
|
|
|
|
|
"\u0153" to "œ", // -- latin small ligature oe, U+0153 ISOlat2 -->
|
|
|
|
|
// <!-- ligature is a misnomer, this is a separate character in some languages -->
|
|
|
|
|
"\u0160" to "Š", // -- latin capital letter S with caron,U+0160 ISOlat2 -->
|
|
|
|
|
"\u0161" to "š", // -- latin small letter s with caron,U+0161 ISOlat2 -->
|
|
|
|
|
"\u0178" to "Ÿ", // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 -->
|
|
|
|
|
// <!-- Spacing Modifier Letters -->
|
|
|
|
|
"\u02C6" to "ˆ", // -- modifier letter circumflex accent,U+02C6 ISOpub -->
|
|
|
|
|
"\u02DC" to "˜", // small tilde, U+02DC ISOdia -->
|
|
|
|
|
// <!-- General Punctuation -->
|
|
|
|
|
"\u2002" to " ", // en space, U+2002 ISOpub -->
|
|
|
|
|
"\u2003" to " ", // em space, U+2003 ISOpub -->
|
|
|
|
|
"\u2009" to " ", // thin space, U+2009 ISOpub -->
|
|
|
|
|
"\u200C" to "‌", // zero width non-joiner,U+200C NEW RFC 2070 -->
|
|
|
|
|
"\u200D" to "‍", // zero width joiner, U+200D NEW RFC 2070 -->
|
|
|
|
|
"\u200E" to "‎", // left-to-right mark, U+200E NEW RFC 2070 -->
|
|
|
|
|
"\u200F" to "‏", // right-to-left mark, U+200F NEW RFC 2070 -->
|
|
|
|
|
"\u2013" to "–", // en dash, U+2013 ISOpub -->
|
|
|
|
|
"\u2014" to "—", // em dash, U+2014 ISOpub -->
|
|
|
|
|
"\u2018" to "‘", // left single quotation mark,U+2018 ISOnum -->
|
|
|
|
|
"\u2019" to "’", // right single quotation mark,U+2019 ISOnum -->
|
|
|
|
|
"\u201A" to "‚", // single low-9 quotation mark, U+201A NEW -->
|
|
|
|
|
"\u201C" to "“", // left double quotation mark,U+201C ISOnum -->
|
|
|
|
|
"\u201D" to "”", // right double quotation mark,U+201D ISOnum -->
|
|
|
|
|
"\u201E" to "„", // double low-9 quotation mark, U+201E NEW -->
|
|
|
|
|
"\u2020" to "†", // dagger, U+2020 ISOpub -->
|
|
|
|
|
"\u2021" to "‡", // double dagger, U+2021 ISOpub -->
|
|
|
|
|
"\u2030" to "‰", // per mille sign, U+2030 ISOtech -->
|
|
|
|
|
"\u2039" to "‹", // single left-pointing angle quotation mark,U+2039 ISO proposed -->
|
|
|
|
|
// <!-- lsaquo is proposed but not yet ISO standardized -->
|
|
|
|
|
"\u203A" to "›", // single right-pointing angle quotation mark,U+203A ISO proposed -->
|
|
|
|
|
// <!-- rsaquo is proposed but not yet ISO standardized -->
|
|
|
|
|
"\u20AC" to "€" // -- euro sign, U+20AC NEW -->
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Reverse of [.HTML40_EXTENDED_ESCAPE] for unescaping purposes.
|
|
|
|
|
*/
|
|
|
|
|
val HTML40_EXTENDED_UNESCAPE: Map<CharSequence, CharSequence> = HTML40_EXTENDED_ESCAPE.invert()
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* A Map<CharSequence, CharSequence> to escape the basic XML and HTML
|
|
|
|
|
* character entities.
|
|
|
|
|
*
|
|
|
|
|
* Namely: `" & < >`
|
|
|
|
|
*/
|
|
|
|
|
val BASIC_ESCAPE: Map<CharSequence, CharSequence> = mapOf(
|
|
|
|
|
"\"" to """, // " - double-quote
|
|
|
|
|
"&" to "&", // & - ampersand
|
|
|
|
|
"<" to "<", // < - less-than
|
|
|
|
|
">" to ">" // > - greater-than
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Reverse of [.BASIC_ESCAPE] for unescaping purposes.
|
|
|
|
|
*/
|
|
|
|
|
val BASIC_UNESCAPE: Map<CharSequence, CharSequence> = BASIC_ESCAPE.invert()
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* A Map<CharSequence, CharSequence> to escape the apostrophe character to
|
|
|
|
|
* its XML character entity.
|
|
|
|
|
*/
|
|
|
|
|
val APOS_ESCAPE: Map<CharSequence, CharSequence> = mapOf(
|
|
|
|
|
"'" to "'" // XML apostrophe
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Reverse of [.APOS_ESCAPE] for unescaping purposes.
|
|
|
|
|
*/
|
|
|
|
|
val APOS_UNESCAPE: Map<CharSequence, CharSequence> = APOS_ESCAPE.invert()
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Used to invert an escape Map into an unescape Map.
|
|
|
|
|
* @param this@invert Map<String, String> to be inverted
|
|
|
|
|
* @return Map<String, String> inverted array
|
|
|
|
|
*/
|
|
|
|
|
private fun <K, V> Map<K, V>.invert(): Map<V, K> {
|
|
|
|
|
val newMap = HashMap<V, K>()
|
|
|
|
|
val it = entries.iterator()
|
|
|
|
|
while (it.hasNext()) {
|
|
|
|
|
val pair = it.next()
|
|
|
|
|
newMap[pair.value] = pair.key
|
|
|
|
|
}
|
|
|
|
|
return newMap
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
}
|
TacoTheDank