org.apache.commons.lang.Entities Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of aem-sdk-api Show documentation
Show all versions of aem-sdk-api Show documentation
The Adobe Experience Manager SDK
/*
* 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.apache.commons.lang;
import java.io.IOException;
import java.io.StringWriter;
import java.io.Writer;
import java.util.HashMap;
import java.util.Map;
import java.util.TreeMap;
/**
*
* Provides HTML and XML entity utilities.
*
*
* @see ISO Entities
* @see HTML 3.2 Character Entities for ISO Latin-1
* @see HTML 4.0 Character entity references
* @see HTML 4.01 Character References
* @see HTML 4.01 Code positions
*
* @author Alexander Day Chaffee
* @author Gary Gregory
* @since 2.0
* @version $Id: Entities.java 1057037 2011-01-09 21:35:32Z niallp $
*
* @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
*/
@Deprecated(since = "2021-04-30")
class Entities {
private static final String[][] BASIC_ARRAY = { // " - double-quote
{ "quot", "34" }, // & - ampersand
{ "amp", "38" }, // < - less-than
{ "lt", "60" }, // > - greater-than
{ "gt", "62" } };
private static final String[][] APOS_ARRAY = { // XML apostrophe
{ "apos", "39" } };
// package scoped for testing
static final String[][] ISO8859_1_ARRAY = { // non-breaking space
{ "nbsp", "160" }, // inverted exclamation mark
{ "iexcl", "161" }, // cent sign
{ "cent", "162" }, // pound sign
{ "pound", "163" }, // currency sign
{ "curren", "164" }, // yen sign = yuan sign
{ "yen", "165" }, // broken bar = broken vertical bar
{ "brvbar", "166" }, // section sign
{ "sect", "167" }, // diaeresis = spacing diaeresis
{ "uml", "168" }, // © - copyright sign
{ "copy", "169" }, // feminine ordinal indicator
{ "ordf", "170" }, // left-pointing double angle quotation mark = left pointing guillemet
{ "laquo", "171" }, // not sign
{ "not", "172" }, // soft hyphen = discretionary hyphen
{ "shy", "173" }, // ® - registered trademark sign
{ "reg", "174" }, // macron = spacing macron = overline = APL overbar
{ "macr", "175" }, // degree sign
{ "deg", "176" }, // plus-minus sign = plus-or-minus sign
{ "plusmn", "177" }, // superscript two = superscript digit two = squared
{ "sup2", "178" }, // superscript three = superscript digit three = cubed
{ "sup3", "179" }, // acute accent = spacing acute
{ "acute", "180" }, // micro sign
{ "micro", "181" }, // pilcrow sign = paragraph sign
{ "para", "182" }, // middle dot = Georgian comma = Greek middle dot
{ "middot", "183" }, // cedilla = spacing cedilla
{ "cedil", "184" }, // superscript one = superscript digit one
{ "sup1", "185" }, // masculine ordinal indicator
{ "ordm", "186" }, // right-pointing double angle quotation mark = right pointing guillemet
{ "raquo", "187" }, // vulgar fraction one quarter = fraction one quarter
{ "frac14", "188" }, // vulgar fraction one half = fraction one half
{ "frac12", "189" }, // vulgar fraction three quarters = fraction three quarters
{ "frac34", "190" }, // inverted question mark = turned question mark
{ "iquest", "191" }, // À - uppercase A, grave accent
{ "Agrave", "192" }, // Á - uppercase A, acute accent
{ "Aacute", "193" }, // Â - uppercase A, circumflex accent
{ "Acirc", "194" }, // Ã - uppercase A, tilde
{ "Atilde", "195" }, // Ä - uppercase A, umlaut
{ "Auml", "196" }, // Å - uppercase A, ring
{ "Aring", "197" }, // Æ - uppercase AE
{ "AElig", "198" }, // Ç - uppercase C, cedilla
{ "Ccedil", "199" }, // È - uppercase E, grave accent
{ "Egrave", "200" }, // É - uppercase E, acute accent
{ "Eacute", "201" }, // Ê - uppercase E, circumflex accent
{ "Ecirc", "202" }, // Ë - uppercase E, umlaut
{ "Euml", "203" }, // Ì - uppercase I, grave accent
{ "Igrave", "204" }, // Í - uppercase I, acute accent
{ "Iacute", "205" }, // Î - uppercase I, circumflex accent
{ "Icirc", "206" }, // Ï - uppercase I, umlaut
{ "Iuml", "207" }, // Ð - uppercase Eth, Icelandic
{ "ETH", "208" }, // Ñ - uppercase N, tilde
{ "Ntilde", "209" }, // Ò - uppercase O, grave accent
{ "Ograve", "210" }, // Ó - uppercase O, acute accent
{ "Oacute", "211" }, // Ô - uppercase O, circumflex accent
{ "Ocirc", "212" }, // Õ - uppercase O, tilde
{ "Otilde", "213" }, // Ö - uppercase O, umlaut
{ "Ouml", "214" }, // multiplication sign
{ "times", "215" }, // Ø - uppercase O, slash
{ "Oslash", "216" }, // Ù - uppercase U, grave accent
{ "Ugrave", "217" }, // Ú - uppercase U, acute accent
{ "Uacute", "218" }, // Û - uppercase U, circumflex accent
{ "Ucirc", "219" }, // Ü - uppercase U, umlaut
{ "Uuml", "220" }, // Ý - uppercase Y, acute accent
{ "Yacute", "221" }, // Þ - uppercase THORN, Icelandic
{ "THORN", "222" }, // ß - lowercase sharps, German
{ "szlig", "223" }, // à - lowercase a, grave accent
{ "agrave", "224" }, // á - lowercase a, acute accent
{ "aacute", "225" }, // â - lowercase a, circumflex accent
{ "acirc", "226" }, // ã - lowercase a, tilde
{ "atilde", "227" }, // ä - lowercase a, umlaut
{ "auml", "228" }, // å - lowercase a, ring
{ "aring", "229" }, // æ - lowercase ae
{ "aelig", "230" }, // ç - lowercase c, cedilla
{ "ccedil", "231" }, // è - lowercase e, grave accent
{ "egrave", "232" }, // é - lowercase e, acute accent
{ "eacute", "233" }, // ê - lowercase e, circumflex accent
{ "ecirc", "234" }, // ë - lowercase e, umlaut
{ "euml", "235" }, // ì - lowercase i, grave accent
{ "igrave", "236" }, // í - lowercase i, acute accent
{ "iacute", "237" }, // î - lowercase i, circumflex accent
{ "icirc", "238" }, // ï - lowercase i, umlaut
{ "iuml", "239" }, // ð - lowercase eth, Icelandic
{ "eth", "240" }, // ñ - lowercase n, tilde
{ "ntilde", "241" }, // ò - lowercase o, grave accent
{ "ograve", "242" }, // ó - lowercase o, acute accent
{ "oacute", "243" }, // ô - lowercase o, circumflex accent
{ "ocirc", "244" }, // õ - lowercase o, tilde
{ "otilde", "245" }, // ö - lowercase o, umlaut
{ "ouml", "246" }, // division sign
{ "divide", "247" }, // ø - lowercase o, slash
{ "oslash", "248" }, // ù - lowercase u, grave accent
{ "ugrave", "249" }, // ú - lowercase u, acute accent
{ "uacute", "250" }, // û - lowercase u, circumflex accent
{ "ucirc", "251" }, // ü - lowercase u, umlaut
{ "uuml", "252" }, // ý - lowercase y, acute accent
{ "yacute", "253" }, // þ - lowercase thorn, Icelandic
{ "thorn", "254" }, // ÿ - lowercase y, umlaut
{ "yuml", "255" } };
// http://www.w3.org/TR/REC-html40/sgml/entities.html
// package scoped for testing
static final String[][] HTML40_ARRAY = { //
// latin small f with hook = function= florin, U+0192 ISOtech -->
{ "fnof", "402" }, //
// greek capital letter alpha, U+0391 -->
{ "Alpha", "913" }, // greek capital letter beta, U+0392 -->
{ "Beta", "914" }, // greek capital letter gamma,U+0393 ISOgrk3 -->
{ "Gamma", "915" }, // greek capital letter delta,U+0394 ISOgrk3 -->
{ "Delta", "916" }, // greek capital letter epsilon, U+0395 -->
{ "Epsilon", "917" }, // greek capital letter zeta, U+0396 -->
{ "Zeta", "918" }, // greek capital letter eta, U+0397 -->
{ "Eta", "919" }, // greek capital letter theta,U+0398 ISOgrk3 -->
{ "Theta", "920" }, // greek capital letter iota, U+0399 -->
{ "Iota", "921" }, // greek capital letter kappa, U+039A -->
{ "Kappa", "922" }, // greek capital letter lambda,U+039B ISOgrk3 -->
{ "Lambda", "923" }, // greek capital letter mu, U+039C -->
{ "Mu", "924" }, // greek capital letter nu, U+039D -->
{ "Nu", "925" }, // greek capital letter xi, U+039E ISOgrk3 -->
{ "Xi", "926" }, // greek capital letter omicron, U+039F -->
{ "Omicron", "927" }, // greek capital letter pi, U+03A0 ISOgrk3 -->
{ "Pi", "928" }, // greek capital letter rho, U+03A1 -->
{ "Rho", "929" }, //
// greek capital letter sigma,U+03A3 ISOgrk3 -->
{ "Sigma", "931" }, // greek capital letter tau, U+03A4 -->
{ "Tau", "932" }, // greek capital letter upsilon,U+03A5 ISOgrk3 -->
{ "Upsilon", "933" }, // greek capital letter phi,U+03A6 ISOgrk3 -->
{ "Phi", "934" }, // greek capital letter chi, U+03A7 -->
{ "Chi", "935" }, // greek capital letter psi,U+03A8 ISOgrk3 -->
{ "Psi", "936" }, // greek capital letter omega,U+03A9 ISOgrk3 -->
{ "Omega", "937" }, // greek small letter alpha,U+03B1 ISOgrk3 -->
{ "alpha", "945" }, // greek small letter beta, U+03B2 ISOgrk3 -->
{ "beta", "946" }, // greek small letter gamma,U+03B3 ISOgrk3 -->
{ "gamma", "947" }, // greek small letter delta,U+03B4 ISOgrk3 -->
{ "delta", "948" }, // greek small letter epsilon,U+03B5 ISOgrk3 -->
{ "epsilon", "949" }, // greek small letter zeta, U+03B6 ISOgrk3 -->
{ "zeta", "950" }, // greek small letter eta, U+03B7 ISOgrk3 -->
{ "eta", "951" }, // greek small letter theta,U+03B8 ISOgrk3 -->
{ "theta", "952" }, // greek small letter iota, U+03B9 ISOgrk3 -->
{ "iota", "953" }, // greek small letter kappa,U+03BA ISOgrk3 -->
{ "kappa", "954" }, // greek small letter lambda,U+03BB ISOgrk3 -->
{ "lambda", "955" }, // greek small letter mu, U+03BC ISOgrk3 -->
{ "mu", "956" }, // greek small letter nu, U+03BD ISOgrk3 -->
{ "nu", "957" }, // greek small letter xi, U+03BE ISOgrk3 -->
{ "xi", "958" }, // greek small letter omicron, U+03BF NEW -->
{ "omicron", "959" }, // greek small letter pi, U+03C0 ISOgrk3 -->
{ "pi", "960" }, // greek small letter rho, U+03C1 ISOgrk3 -->
{ "rho", "961" }, // greek small letter final sigma,U+03C2 ISOgrk3 -->
{ "sigmaf", "962" }, // greek small letter sigma,U+03C3 ISOgrk3 -->
{ "sigma", "963" }, // greek small letter tau, U+03C4 ISOgrk3 -->
{ "tau", "964" }, // greek small letter upsilon,U+03C5 ISOgrk3 -->
{ "upsilon", "965" }, // greek small letter phi, U+03C6 ISOgrk3 -->
{ "phi", "966" }, // greek small letter chi, U+03C7 ISOgrk3 -->
{ "chi", "967" }, // greek small letter psi, U+03C8 ISOgrk3 -->
{ "psi", "968" }, // greek small letter omega,U+03C9 ISOgrk3 -->
{ "omega", "969" }, // greek small letter theta symbol,U+03D1 NEW -->
{ "thetasym", "977" }, // greek upsilon with hook symbol,U+03D2 NEW -->
{ "upsih", "978" }, // greek pi symbol, U+03D6 ISOgrk3 -->
{ "piv", "982" }, //
// bullet = black small circle,U+2022 ISOpub -->
{ "bull", "8226" }, //
// horizontal ellipsis = three dot leader,U+2026 ISOpub -->
{ "hellip", "8230" }, // prime = minutes = feet, U+2032 ISOtech -->
{ "prime", "8242" }, // double prime = seconds = inches,U+2033 ISOtech -->
{ "Prime", "8243" }, // overline = spacing overscore,U+203E NEW -->
{ "oline", "8254" }, // fraction slash, U+2044 NEW -->
{ "frasl", "8260" }, //
// script capital P = power set= Weierstrass p, U+2118 ISOamso -->
{ "weierp", "8472" }, // blackletter capital I = imaginary part,U+2111 ISOamso -->
{ "image", "8465" }, // blackletter capital R = real part symbol,U+211C ISOamso -->
{ "real", "8476" }, // trade mark sign, U+2122 ISOnum -->
{ "trade", "8482" }, // alef symbol = first transfinite cardinal,U+2135 NEW -->
{ "alefsym", "8501" }, //
//
// leftwards arrow, U+2190 ISOnum -->
{ "larr", "8592" }, // upwards arrow, U+2191 ISOnum-->
{ "uarr", "8593" }, // rightwards arrow, U+2192 ISOnum -->
{ "rarr", "8594" }, // downwards arrow, U+2193 ISOnum -->
{ "darr", "8595" }, // left right arrow, U+2194 ISOamsa -->
{ "harr", "8596" }, // downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
{ "crarr", "8629" }, // leftwards double arrow, U+21D0 ISOtech -->
{ "lArr", "8656" }, //
// upwards double arrow, U+21D1 ISOamsa -->
{ "uArr", "8657" }, // rightwards double arrow,U+21D2 ISOtech -->
{ "rArr", "8658" }, //
// downwards double arrow, U+21D3 ISOamsa -->
{ "dArr", "8659" }, // left right double arrow,U+21D4 ISOamsa -->
{ "hArr", "8660" }, //
// for all, U+2200 ISOtech -->
{ "forall", "8704" }, // partial differential, U+2202 ISOtech -->
{ "part", "8706" }, // there exists, U+2203 ISOtech -->
{ "exist", "8707" }, // empty set = null set = diameter,U+2205 ISOamso -->
{ "empty", "8709" }, // nabla = backward difference,U+2207 ISOtech -->
{ "nabla", "8711" }, // element of, U+2208 ISOtech -->
{ "isin", "8712" }, // not an element of, U+2209 ISOtech -->
{ "notin", "8713" }, // contains as member, U+220B ISOtech -->
{ "ni", "8715" }, //
// n-ary product = product sign,U+220F ISOamsb -->
{ "prod", "8719" }, //
// n-ary summation, U+2211 ISOamsb -->
{ "sum", "8721" }, //
// minus sign, U+2212 ISOtech -->
{ "minus", "8722" }, // asterisk operator, U+2217 ISOtech -->
{ "lowast", "8727" }, // square root = radical sign,U+221A ISOtech -->
{ "radic", "8730" }, // proportional to, U+221D ISOtech -->
{ "prop", "8733" }, // infinity, U+221E ISOtech -->
{ "infin", "8734" }, // angle, U+2220 ISOamso -->
{ "ang", "8736" }, // logical and = wedge, U+2227 ISOtech -->
{ "and", "8743" }, // logical or = vee, U+2228 ISOtech -->
{ "or", "8744" }, // intersection = cap, U+2229 ISOtech -->
{ "cap", "8745" }, // union = cup, U+222A ISOtech -->
{ "cup", "8746" }, // integral, U+222B ISOtech -->
{ "int", "8747" }, // therefore, U+2234 ISOtech -->
{ "there4", "8756" }, // tilde operator = varies with = similar to,U+223C ISOtech -->
{ "sim", "8764" }, //
// approximately equal to, U+2245 ISOtech -->
{ "cong", "8773" }, // almost equal to = asymptotic to,U+2248 ISOamsr -->
{ "asymp", "8776" }, // not equal to, U+2260 ISOtech -->
{ "ne", "8800" }, // identical to, U+2261 ISOtech -->
{ "equiv", "8801" }, // less-than or equal to, U+2264 ISOtech -->
{ "le", "8804" }, // greater-than or equal to,U+2265 ISOtech -->
{ "ge", "8805" }, // subset of, U+2282 ISOtech -->
{ "sub", "8834" }, // superset of, U+2283 ISOtech -->
{ "sup", "8835" }, //
// subset of or equal to, U+2286 ISOtech -->
{ "sube", "8838" }, // superset of or equal to,U+2287 ISOtech -->
{ "supe", "8839" }, // circled plus = direct sum,U+2295 ISOamsb -->
{ "oplus", "8853" }, // circled times = vector product,U+2297 ISOamsb -->
{ "otimes", "8855" }, // up tack = orthogonal to = perpendicular,U+22A5 ISOtech -->
{ "perp", "8869" }, // dot operator, U+22C5 ISOamsb -->
{ "sdot", "8901" }, //
//
// left ceiling = apl upstile,U+2308 ISOamsc -->
{ "lceil", "8968" }, // right ceiling, U+2309 ISOamsc -->
{ "rceil", "8969" }, // left floor = apl downstile,U+230A ISOamsc -->
{ "lfloor", "8970" }, // right floor, U+230B ISOamsc -->
{ "rfloor", "8971" }, // left-pointing angle bracket = bra,U+2329 ISOtech -->
{ "lang", "9001" }, //
// right-pointing angle bracket = ket,U+232A ISOtech -->
{ "rang", "9002" }, //
//
// lozenge, U+25CA ISOpub -->
{ "loz", "9674" }, //
// black spade suit, U+2660 ISOpub -->
{ "spades", "9824" }, //
// black club suit = shamrock,U+2663 ISOpub -->
{ "clubs", "9827" }, // black heart suit = valentine,U+2665 ISOpub -->
{ "hearts", "9829" }, // black diamond suit, U+2666 ISOpub -->
{ "diams", "9830" }, //
// -- latin capital ligature OE,U+0152 ISOlat2 -->
{ "OElig", "338" }, // -- latin small ligature oe, U+0153 ISOlat2 -->
{ "oelig", "339" }, //
// -- latin capital letter S with caron,U+0160 ISOlat2 -->
{ "Scaron", "352" }, // -- latin small letter s with caron,U+0161 ISOlat2 -->
{ "scaron", "353" }, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 -->
{ "Yuml", "376" }, //
// -- modifier letter circumflex accent,U+02C6 ISOpub -->
{ "circ", "710" }, // small tilde, U+02DC ISOdia -->
{ "tilde", "732" }, //
// en space, U+2002 ISOpub -->
{ "ensp", "8194" }, // em space, U+2003 ISOpub -->
{ "emsp", "8195" }, // thin space, U+2009 ISOpub -->
{ "thinsp", "8201" }, // zero width non-joiner,U+200C NEW RFC 2070 -->
{ "zwnj", "8204" }, // zero width joiner, U+200D NEW RFC 2070 -->
{ "zwj", "8205" }, // left-to-right mark, U+200E NEW RFC 2070 -->
{ "lrm", "8206" }, // right-to-left mark, U+200F NEW RFC 2070 -->
{ "rlm", "8207" }, // en dash, U+2013 ISOpub -->
{ "ndash", "8211" }, // em dash, U+2014 ISOpub -->
{ "mdash", "8212" }, // left single quotation mark,U+2018 ISOnum -->
{ "lsquo", "8216" }, // right single quotation mark,U+2019 ISOnum -->
{ "rsquo", "8217" }, // single low-9 quotation mark, U+201A NEW -->
{ "sbquo", "8218" }, // left double quotation mark,U+201C ISOnum -->
{ "ldquo", "8220" }, // right double quotation mark,U+201D ISOnum -->
{ "rdquo", "8221" }, // double low-9 quotation mark, U+201E NEW -->
{ "bdquo", "8222" }, // dagger, U+2020 ISOpub -->
{ "dagger", "8224" }, // double dagger, U+2021 ISOpub -->
{ "Dagger", "8225" }, // per mille sign, U+2030 ISOtech -->
{ "permil", "8240" }, // single left-pointing angle quotation mark,U+2039 ISO proposed -->
{ "lsaquo", "8249" }, //
// single right-pointing angle quotation mark,U+203A ISO proposed -->
{ "rsaquo", "8250" }, //
// -- euro sign, U+20AC NEW -->
{ "euro", "8364" } };
/**
*
* The set of entities supported by standard XML.
*
*/
public static final Entities XML;
/**
*
* The set of entities supported by HTML 3.2.
*
*/
public static final Entities HTML32;
/**
*
* The set of entities supported by HTML 4.0.
*
*/
public static final Entities HTML40;
static {
Entities xml = new Entities();
xml.addEntities(BASIC_ARRAY);
xml.addEntities(APOS_ARRAY);
XML = xml;
}
static {
Entities html32 = new Entities();
html32.addEntities(BASIC_ARRAY);
html32.addEntities(ISO8859_1_ARRAY);
HTML32 = html32;
}
static {
Entities html40 = new Entities();
fillWithHtml40Entities(html40);
HTML40 = html40;
}
/**
*
* Fills the specified entities instance with HTML 40 entities.
*
*
* @param entities
* the instance to be filled.
*/
static void fillWithHtml40Entities(Entities entities) {
entities.addEntities(BASIC_ARRAY);
entities.addEntities(ISO8859_1_ARRAY);
entities.addEntities(HTML40_ARRAY);
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static interface EntityMap {
/**
*
* Add an entry to this entity map.
*
*
* @param name
* the entity name
* @param value
* the entity value
*/
void add(String name, int value);
/**
*
* Returns the name of the entity identified by the specified value.
*
*
* @param value
* the value to locate
* @return entity name associated with the specified value
*/
String name(int value);
/**
*
* Returns the value of the entity identified by the specified name.
*
*
* @param name
* the name to locate
* @return entity value associated with the specified name
*/
int value(String name);
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class PrimitiveEntityMap implements EntityMap {
private final Map mapNameToValue = new HashMap();
private final IntHashMap mapValueToName = new IntHashMap();
/**
* {@inheritDoc}
*/
// TODO not thread-safe as there is a window between changing the two maps
public void add(String name, int value) {
mapNameToValue.put(name, new Integer(value));
mapValueToName.put(value, name);
}
/**
* {@inheritDoc}
*/
public String name(int value) {
return (String) mapValueToName.get(value);
}
/**
* {@inheritDoc}
*/
public int value(String name) {
Object value = mapNameToValue.get(name);
if (value == null) {
return -1;
}
return ((Integer) value).intValue();
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static abstract class MapIntMap implements Entities.EntityMap {
protected final Map mapNameToValue;
protected final Map mapValueToName;
/**
* Construct a new instance with specified maps.
*
* @param nameToValue name to value map
* @param valueToName value to namee map
*/
MapIntMap(Map nameToValue, Map valueToName) {
mapNameToValue = nameToValue;
mapValueToName = valueToName;
}
/**
* {@inheritDoc}
*/
public void add(String name, int value) {
mapNameToValue.put(name, new Integer(value));
mapValueToName.put(new Integer(value), name);
}
/**
* {@inheritDoc}
*/
public String name(int value) {
return (String) mapValueToName.get(new Integer(value));
}
/**
* {@inheritDoc}
*/
public int value(String name) {
Object value = mapNameToValue.get(name);
if (value == null) {
return -1;
}
return ((Integer) value).intValue();
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class HashEntityMap extends MapIntMap {
/**
* Constructs a new instance of HashEntityMap.
*/
public HashEntityMap() {
super(new HashMap(), new HashMap());
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class TreeEntityMap extends MapIntMap {
/**
* Constructs a new instance of TreeEntityMap.
*/
public TreeEntityMap() {
super(new TreeMap(), new TreeMap());
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class LookupEntityMap extends PrimitiveEntityMap {
// TODO this class is not thread-safe
private String[] lookupTable;
private static final int LOOKUP_TABLE_SIZE = 256;
/**
* {@inheritDoc}
*/
public String name(int value) {
if (value < LOOKUP_TABLE_SIZE) {
return lookupTable()[value];
}
return super.name(value);
}
/**
*
* Returns the lookup table for this entity map. The lookup table is created if it has not been previously.
*
*
* @return the lookup table
*/
private String[] lookupTable() {
if (lookupTable == null) {
createLookupTable();
}
return lookupTable;
}
/**
*
* Creates an entity lookup table of LOOKUP_TABLE_SIZE elements, initialized with entity names.
*
*/
private void createLookupTable() {
lookupTable = new String[LOOKUP_TABLE_SIZE];
for (int i = 0; i < LOOKUP_TABLE_SIZE; ++i) {
lookupTable[i] = super.name(i);
}
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class ArrayEntityMap implements EntityMap {
// TODO this class is not thread-safe
protected final int growBy;
protected int size = 0;
protected String[] names;
protected int[] values;
/**
* Constructs a new instance of ArrayEntityMap.
*/
public ArrayEntityMap() {
this.growBy = 100;
names = new String[growBy];
values = new int[growBy];
}
/**
* Constructs a new instance of ArrayEntityMap specifying the size by which the array should
* grow.
*
* @param growBy
* array will be initialized to and will grow by this amount
*/
public ArrayEntityMap(int growBy) {
this.growBy = growBy;
names = new String[growBy];
values = new int[growBy];
}
/**
* {@inheritDoc}
*/
public void add(String name, int value) {
ensureCapacity(size + 1);
names[size] = name;
values[size] = value;
size++;
}
/**
* Verifies the capacity of the entity array, adjusting the size if necessary.
*
* @param capacity
* size the array should be
*/
protected void ensureCapacity(int capacity) {
if (capacity > names.length) {
int newSize = Math.max(capacity, size + growBy);
String[] newNames = new String[newSize];
System.arraycopy(names, 0, newNames, 0, size);
names = newNames;
int[] newValues = new int[newSize];
System.arraycopy(values, 0, newValues, 0, size);
values = newValues;
}
}
/**
* {@inheritDoc}
*/
public String name(int value) {
for (int i = 0; i < size; ++i) {
if (values[i] == value) {
return names[i];
}
}
return null;
}
/**
* {@inheritDoc}
*/
public int value(String name) {
for (int i = 0; i < size; ++i) {
if (names[i].equals(name)) {
return values[i];
}
}
return -1;
}
}
// @deprecated Commons Lang 2 is in maintenance mode. Commons Lang 3 should be used instead.
@Deprecated(since = "2021-04-30")
static class BinaryEntityMap extends ArrayEntityMap {
// TODO - not thread-safe, because parent is not. Also references size.
/**
* Constructs a new instance of BinaryEntityMap.
*/
public BinaryEntityMap() {
super();
}
/**
* Constructs a new instance of ArrayEntityMap specifying the size by which the underlying array
* should grow.
*
* @param growBy
* array will be initialized to and will grow by this amount
*/
public BinaryEntityMap(int growBy) {
super(growBy);
}
/**
* Performs a binary search of the entity array for the specified key. This method is based on code in
* {@link java.util.Arrays}.
*
* @param key
* the key to be found
* @return the index of the entity array matching the specified key
*/
private int binarySearch(int key) {
int low = 0;
int high = size - 1;
while (low <= high) {
int mid = (low + high) >>> 1;
int midVal = values[mid];
if (midVal < key) {
low = mid + 1;
} else if (midVal > key) {
high = mid - 1;
} else {
// key found
return mid;
}
}
// key not found.
return -(low + 1);
}
/**
* {@inheritDoc}
*/
public void add(String name, int value) {
ensureCapacity(size + 1);
int insertAt = binarySearch(value);
if (insertAt > 0) {
// note: this means you can't insert the same value twice
return;
}
// binarySearch returns it negative and off-by-one
insertAt = -(insertAt + 1);
System.arraycopy(values, insertAt, values, insertAt + 1, size - insertAt);
values[insertAt] = value;
System.arraycopy(names, insertAt, names, insertAt + 1, size - insertAt);
names[insertAt] = name;
size++;
}
/**
* {@inheritDoc}
*/
public String name(int value) {
int index = binarySearch(value);
if (index < 0) {
return null;
}
return names[index];
}
}
private final EntityMap map;
/**
* Default constructor.
*/
public Entities() {
map = new Entities.LookupEntityMap();
}
/**
* package scoped constructor for testing.
*
* @param emap entity map.
*/
Entities(EntityMap emap) {
map = emap;
}
/**
*
* Adds entities to this entity.
*
*
* @param entityArray
* array of entities to be added
*/
public void addEntities(String[][] entityArray) {
for (int i = 0; i < entityArray.length; ++i) {
addEntity(entityArray[i][0], Integer.parseInt(entityArray[i][1]));
}
}
/**
*
* Add an entity to this entity.
*
*
* @param name
* name of the entity
* @param value
* vale of the entity
*/
public void addEntity(String name, int value) {
map.add(name, value);
}
/**
*
* Returns the name of the entity identified by the specified value.
*
*
* @param value
* the value to locate
* @return entity name associated with the specified value
*/
public String entityName(int value) {
return map.name(value);
}
/**
*
* Returns the value of the entity identified by the specified name.
*
*
* @param name
* the name to locate
* @return entity value associated with the specified name
*/
public int entityValue(String name) {
return map.value(name);
}
/**
*
* Escapes the characters in a String.
*
*
*
* For example, if you have called addEntity("foo", 0xA1), escape("\u00A1") will return
* "&foo;"
*
*
* @param str
* The String to escape.
* @return A new escaped String.
*/
public String escape(String str) {
StringWriter stringWriter = createStringWriter(str);
try {
this.escape(stringWriter, str);
} catch (IOException e) {
// This should never happen because ALL the StringWriter methods called by #escape(Writer, String) do not
// throw IOExceptions.
throw new UnhandledException(e);
}
return stringWriter.toString();
}
/**
*
* Escapes the characters in the String passed and writes the result to the Writer
* passed.
*
*
* @param writer
* The Writer to write the results of the escaping to. Assumed to be a non-null value.
* @param str
* The String to escape. Assumed to be a non-null value.
* @throws IOException
* when Writer passed throws the exception from calls to the {@link Writer#write(int)}
* methods.
*
* @see #escape(String)
* @see Writer
*/
public void escape(Writer writer, String str) throws IOException {
int len = str.length();
for (int i = 0; i < len; i++) {
char c = str.charAt(i);
String entityName = this.entityName(c);
if (entityName == null) {
if (c > 0x7F) {
writer.write("&#");
writer.write(Integer.toString(c, 10));
writer.write(';');
} else {
writer.write(c);
}
} else {
writer.write('&');
writer.write(entityName);
writer.write(';');
}
}
}
/**
*
* Unescapes the entities in a String.
*
*
*
* For example, if you have called addEntity("foo", 0xA1), unescape("&foo;") will return
* "\u00A1"
*
*
* @param str
* The String to escape.
* @return A new escaped String.
*/
public String unescape(String str) {
int firstAmp = str.indexOf('&');
if (firstAmp < 0) {
return str;
} else {
StringWriter stringWriter = createStringWriter(str);
try {
this.doUnescape(stringWriter, str, firstAmp);
} catch (IOException e) {
// This should never happen because ALL the StringWriter methods called by #escape(Writer, String)
// do not throw IOExceptions.
throw new UnhandledException(e);
}
return stringWriter.toString();
}
}
/**
* Make the StringWriter 10% larger than the source String to avoid growing the writer
*
* @param str The source string
* @return A newly created StringWriter
*/
private StringWriter createStringWriter(String str) {
return new StringWriter((int) (str.length() + (str.length() * 0.1)));
}
/**
*
* Unescapes the escaped entities in the String passed and writes the result to the
* Writer passed.
*
*
* @param writer
* The Writer to write the results to; assumed to be non-null.
* @param str
* The source String to unescape; assumed to be non-null.
* @throws IOException
* when Writer passed throws the exception from calls to the {@link Writer#write(int)}
* methods.
*
* @see #escape(String)
* @see Writer
*/
public void unescape(Writer writer, String str) throws IOException {
int firstAmp = str.indexOf('&');
if (firstAmp < 0) {
writer.write(str);
return;
} else {
doUnescape(writer, str, firstAmp);
}
}
/**
* Underlying unescape method that allows the optimisation of not starting from the 0 index again.
*
* @param writer
* The Writer to write the results to; assumed to be non-null.
* @param str
* The source String to unescape; assumed to be non-null.
* @param firstAmp
* The int index of the first ampersand in the source String.
* @throws IOException
* when Writer passed throws the exception from calls to the {@link Writer#write(int)}
* methods.
*/
private void doUnescape(Writer writer, String str, int firstAmp) throws IOException {
writer.write(str, 0, firstAmp);
int len = str.length();
for (int i = firstAmp; i < len; i++) {
char c = str.charAt(i);
if (c == '&') {
int nextIdx = i + 1;
int semiColonIdx = str.indexOf(';', nextIdx);
if (semiColonIdx == -1) {
writer.write(c);
continue;
}
int amphersandIdx = str.indexOf('&', i + 1);
if (amphersandIdx != -1 && amphersandIdx < semiColonIdx) {
// Then the text looks like &...&...;
writer.write(c);
continue;
}
String entityContent = str.substring(nextIdx, semiColonIdx);
int entityValue = -1;
int entityContentLen = entityContent.length();
if (entityContentLen > 0) {
if (entityContent.charAt(0) == '#') {
// escaped value content is an integer (decimal or
// hexidecimal)
if (entityContentLen > 1) {
char isHexChar = entityContent.charAt(1);
try {
switch(isHexChar) {
case 'X':
case 'x':
{
entityValue = Integer.parseInt(entityContent.substring(2), 16);
break;
}
default:
{
entityValue = Integer.parseInt(entityContent.substring(1), 10);
}
}
if (entityValue > 0xFFFF) {
entityValue = -1;
}
} catch (NumberFormatException e) {
entityValue = -1;
}
}
} else {
// escaped value content is an entity name
entityValue = this.entityValue(entityContent);
}
}
if (entityValue == -1) {
writer.write('&');
writer.write(entityContent);
writer.write(';');
} else {
writer.write(entityValue);
}
// move index up to the semi-colon
i = semiColonIdx;
} else {
writer.write(c);
}
}
}
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy