Apache
/
commons-lang
mirror of https://github.com/apache/commons-lang.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Extracted Entities class (instead of inner class) 

Added support for full HTML 4.0 entity set
Separated XML, ISO8859-1 (HTML 3.2), and HTML 4.0 entities inside Entities object
Added escapeXml and unescapeXml public API methods
Escape now uses entities for values 0x80 or greater (previously 0x100)


git-svn-id: https://svn.apache.org/repos/asf/jakarta/commons/proper/lang/trunk@137292 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Alex Chaffee 2003-04-09 20:55:33 +00:00
parent 6af3b80369
commit 69cc0e40e6
3 changed files with 513 additions and 164 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

417
src/java/org/apache/commons/lang/Entities.java Normal file
View File

@ -0,0 +1,417 @@
/* ====================================================================
* The Apache Software License, Version 1.1
*
* Copyright (c) 2002-2003 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution, if
* any, must include the following acknowlegement:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowlegement may appear in the software itself,
* if and wherever such third-party acknowlegements normally appear.
*
* 4. The names "The Jakarta Project", "Commons", and "Apache Software
* Foundation" must not be used to endorse or promote products derived
* from this software without prior written permission. For written
* permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache"
* nor may "Apache" appear in their names without prior written
* permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*/
package org.apache.commons.lang;
import java.util.Map;
import java.util.HashMap;
import java.io.IOException;
import java.io.Writer;
import org.apache.commons.lang.exception.NestableRuntimeException;
//todo: unit test and make public
/**
* <p>HTML and XML entity utility class</p>
*
* <p>See
* <a href="http://hotwired.lycos.com/webmonkey/reference/special_characters/">WebMonkey</a>
* <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2</a>
* <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html</a>HTML 4.0</a>
* </p>
*
* @author <a href="mailto:alex@purpletech.com">Alexander Day Chaffee</a>
* @since 2.0
* @version $Id: Entities.java,v 1.1 2003/04/09 20:55:32 alex Exp $
*/
class Entities {
static private Object[][] basic = {
{"quot", "34"}, // " - double-quote
{"amp", "38"}, // & - ampersand
{"lt", "60"}, // < - less-than
{"gt", "62"}, // > - greater-than
};
static private Object[][] iso8859_1 = {
{"nbsp", "160"}, // non-breaking space
{"iexcl", "161"}, //inverted exclamation mark
{"cent", "162"}, //cent sign
{"pound", "163"}, //pound sign
{"curren", "164"}, //currency sign
{"yen", "165"}, //yen sign = yuan sign
{"brvbar", "166"}, //broken bar = broken vertical bar
{"sect", "167"}, //section sign
{"uml", "168"}, //diaeresis = spacing diaeresis
{"copy", "169"}, // © - copyright sign
{"ordf", "170"}, //feminine ordinal indicator
{"laquo", "171"}, //left-pointing double angle quotation mark = left pointing guillemet
{"not", "172"}, //not sign
{"shy", "173"}, //soft hyphen = discretionary hyphen
{"reg", "174"}, // ® - registered trademark sign
{"macr", "175"}, //macron = spacing macron = overline = APL overbar
{"deg", "176"}, //degree sign
{"plusmn", "177"}, //plus-minus sign = plus-or-minus sign
{"sup2", "178"}, //superscript two = superscript digit two = squared
{"sup3", "179"}, //superscript three = superscript digit three = cubed
{"acute", "180"}, //acute accent = spacing acute
{"micro", "181"}, //micro sign
{"para", "182"}, //pilcrow sign = paragraph sign
{"middot", "183"}, //middle dot = Georgian comma = Greek middle dot
{"cedil", "184"}, //cedilla = spacing cedilla
{"sup1", "185"}, //superscript one = superscript digit one
{"ordm", "186"}, //masculine ordinal indicator
{"raquo", "187"}, //right-pointing double angle quotation mark = right pointing guillemet
{"frac14", "188"}, //vulgar fraction one quarter = fraction one quarter
{"frac12", "189"}, //vulgar fraction one half = fraction one half
{"frac34", "190"}, //vulgar fraction three quarters = fraction three quarters
{"iquest", "191"}, //inverted question mark = turned question mark
{"Agrave", "192"}, // À - uppercase A, grave accent
{"Aacute", "193"}, // Á - uppercase A, acute accent
{"Acirc", "194"}, // Â - uppercase A, circumflex accent
{"Atilde", "195"}, // Ã - uppercase A, tilde
{"Auml", "196"}, // Ä - uppercase A, umlaut
{"Aring", "197"}, // Å - uppercase A, ring
{"AElig", "198"}, // Æ - uppercase AE
{"Ccedil", "199"}, // Ç - uppercase C, cedilla
{"Egrave", "200"}, // È - uppercase E, grave accent
{"Eacute", "201"}, // É - uppercase E, acute accent
{"Ecirc", "202"}, // Ê - uppercase E, circumflex accent
{"Euml", "203"}, // Ë - uppercase E, umlaut
{"Igrave", "204"}, // Ì - uppercase I, grave accent
{"Iacute", "205"}, // Í - uppercase I, acute accent
{"Icirc", "206"}, // Î - uppercase I, circumflex accent
{"Iuml", "207"}, // Ï - uppercase I, umlaut
{"ETH", "208"}, // Ð - uppercase Eth, Icelandic
{"Ntilde", "209"}, // Ñ - uppercase N, tilde
{"Ograve", "210"}, // Ò - uppercase O, grave accent
{"Oacute", "211"}, // Ó - uppercase O, acute accent
{"Ocirc", "212"}, // Ô - uppercase O, circumflex accent
{"Otilde", "213"}, // Õ - uppercase O, tilde
{"Ouml", "214"}, // Ö - uppercase O, umlaut
{"times", "215"}, //multiplication sign
{"Oslash", "216"}, // Ø - uppercase O, slash
{"Ugrave", "217"}, // Ù - uppercase U, grave accent
{"Uacute", "218"}, // Ú - uppercase U, acute accent
{"Ucirc", "219"}, // Û - uppercase U, circumflex accent
{"Uuml", "220"}, // Ü - uppercase U, umlaut
{"Yacute", "221"}, // Ý - uppercase Y, acute accent
{"THORN", "222"}, // Þ - uppercase THORN, Icelandic
{"szlig", "223"}, // ß - lowercase sharps, German
{"agrave", "224"}, // à - lowercase a, grave accent
{"aacute", "225"}, // á - lowercase a, acute accent
{"acirc", "226"}, // â - lowercase a, circumflex accent
{"atilde", "227"}, // ã - lowercase a, tilde
{"auml", "228"}, // ä - lowercase a, umlaut
{"aring", "229"}, // å - lowercase a, ring
{"aelig", "230"}, // æ - lowercase ae
{"ccedil", "231"}, // ç - lowercase c, cedilla
{"egrave", "232"}, // è - lowercase e, grave accent
{"eacute", "233"}, // é - lowercase e, acute accent
{"ecirc", "234"}, // ê - lowercase e, circumflex accent
{"euml", "235"}, // ë - lowercase e, umlaut
{"igrave", "236"}, // ì - lowercase i, grave accent
{"iacute", "237"}, // í - lowercase i, acute accent
{"icirc", "238"}, // î - lowercase i, circumflex accent
{"iuml", "239"}, // ï - lowercase i, umlaut
{"eth", "240"}, // ð - lowercase eth, Icelandic
{"ntilde", "241"}, // ñ - lowercase n, tilde
{"ograve", "242"}, // ò - lowercase o, grave accent
{"oacute", "243"}, // ó - lowercase o, acute accent
{"ocirc", "244"}, // ô - lowercase o, circumflex accent
{"otilde", "245"}, // õ - lowercase o, tilde
{"ouml", "246"}, // ö - lowercase o, umlaut
{"divide", "247"}, // division sign
{"oslash", "248"}, // ø - lowercase o, slash
{"ugrave", "249"}, // ù - lowercase u, grave accent
{"uacute", "250"}, // ú - lowercase u, acute accent
{"ucirc", "251"}, // û - lowercase u, circumflex accent
{"uuml", "252"}, // ü - lowercase u, umlaut
{"yacute", "253"}, // ý - lowercase y, acute accent
{"thorn", "254"}, // þ - lowercase thorn, Icelandic
{"yuml", "255"}, // ÿ - lowercase y, umlaut
};
// http://www.w3.org/TR/REC-html40/sgml/entities.html
static Object[][] html40 = {
// <!-- Latin Extended-B -->
{"fnof", "402"}, //latin small f with hook = function= florin, U+0192 ISOtech -->
// <!-- Greek -->
{"Alpha", "913"}, //greek capital letter alpha, U+0391 -->
{"Beta", "914"}, //greek capital letter beta, U+0392 -->
{"Gamma", "915"}, //greek capital letter gamma,U+0393 ISOgrk3 -->
{"Delta", "916"}, //greek capital letter delta,U+0394 ISOgrk3 -->
{"Epsilon", "917"}, //greek capital letter epsilon, U+0395 -->
{"Zeta", "918"}, //greek capital letter zeta, U+0396 -->
{"Eta", "919"}, //greek capital letter eta, U+0397 -->
{"Theta", "920"}, //greek capital letter theta,U+0398 ISOgrk3 -->
{"Iota", "921"}, //greek capital letter iota, U+0399 -->
{"Kappa", "922"}, //greek capital letter kappa, U+039A -->
{"Lambda", "923"}, //greek capital letter lambda,U+039B ISOgrk3 -->
{"Mu", "924"}, //greek capital letter mu, U+039C -->
{"Nu", "925"}, //greek capital letter nu, U+039D -->
{"Xi", "926"}, //greek capital letter xi, U+039E ISOgrk3 -->
{"Omicron", "927"}, //greek capital letter omicron, U+039F -->
{"Pi", "928"}, //greek capital letter pi, U+03A0 ISOgrk3 -->
{"Rho", "929"}, //greek capital letter rho, U+03A1 -->
// <!-- there is no Sigmaf, and no U+03A2 character either -->
{"Sigma", "931"}, //greek capital letter sigma,U+03A3 ISOgrk3 -->
{"Tau", "932"}, //greek capital letter tau, U+03A4 -->
{"Upsilon", "933"}, //greek capital letter upsilon,U+03A5 ISOgrk3 -->
{"Phi", "934"}, //greek capital letter phi,U+03A6 ISOgrk3 -->
{"Chi", "935"}, //greek capital letter chi, U+03A7 -->
{"Psi", "936"}, //greek capital letter psi,U+03A8 ISOgrk3 -->
{"Omega", "937"}, //greek capital letter omega,U+03A9 ISOgrk3 -->
{"alpha", "945"}, //greek small letter alpha,U+03B1 ISOgrk3 -->
{"beta", "946"}, //greek small letter beta, U+03B2 ISOgrk3 -->
{"gamma", "947"}, //greek small letter gamma,U+03B3 ISOgrk3 -->
{"delta", "948"}, //greek small letter delta,U+03B4 ISOgrk3 -->
{"epsilon", "949"}, //greek small letter epsilon,U+03B5 ISOgrk3 -->
{"zeta", "950"}, //greek small letter zeta, U+03B6 ISOgrk3 -->
{"eta", "951"}, //greek small letter eta, U+03B7 ISOgrk3 -->
{"theta", "952"}, //greek small letter theta,U+03B8 ISOgrk3 -->
{"iota", "953"}, //greek small letter iota, U+03B9 ISOgrk3 -->
{"kappa", "954"}, //greek small letter kappa,U+03BA ISOgrk3 -->
{"lambda", "955"}, //greek small letter lambda,U+03BB ISOgrk3 -->
{"mu", "956"}, //greek small letter mu, U+03BC ISOgrk3 -->
{"nu", "957"}, //greek small letter nu, U+03BD ISOgrk3 -->
{"xi", "958"}, //greek small letter xi, U+03BE ISOgrk3 -->
{"omicron", "959"}, //greek small letter omicron, U+03BF NEW -->
{"pi", "960"}, //greek small letter pi, U+03C0 ISOgrk3 -->
{"rho", "961"}, //greek small letter rho, U+03C1 ISOgrk3 -->
{"sigmaf", "962"}, //greek small letter final sigma,U+03C2 ISOgrk3 -->
{"sigma", "963"}, //greek small letter sigma,U+03C3 ISOgrk3 -->
{"tau", "964"}, //greek small letter tau, U+03C4 ISOgrk3 -->
{"upsilon", "965"}, //greek small letter upsilon,U+03C5 ISOgrk3 -->
{"phi", "966"}, //greek small letter phi, U+03C6 ISOgrk3 -->
{"chi", "967"}, //greek small letter chi, U+03C7 ISOgrk3 -->
{"psi", "968"}, //greek small letter psi, U+03C8 ISOgrk3 -->
{"omega", "969"}, //greek small letter omega,U+03C9 ISOgrk3 -->
{"thetasym", "977"}, //greek small letter theta symbol,U+03D1 NEW -->
{"upsih", "978"}, //greek upsilon with hook symbol,U+03D2 NEW -->
{"piv", "982"}, //greek pi symbol, U+03D6 ISOgrk3 -->
// <!-- General Punctuation -->
{"bull", "8226"}, //bullet = black small circle,U+2022 ISOpub -->
// <!-- bullet is NOT the same as bullet operator, U+2219 -->
{"hellip", "8230"}, //horizontal ellipsis = three dot leader,U+2026 ISOpub -->
{"prime", "8242"}, //prime = minutes = feet, U+2032 ISOtech -->
{"Prime", "8243"}, //double prime = seconds = inches,U+2033 ISOtech -->
{"oline", "8254"}, //overline = spacing overscore,U+203E NEW -->
{"frasl", "8260"}, //fraction slash, U+2044 NEW -->
// <!-- Letterlike Symbols -->
{"weierp", "8472"}, //script capital P = power set= Weierstrass p, U+2118 ISOamso -->
{"image", "8465"}, //blackletter capital I = imaginary part,U+2111 ISOamso -->
{"real", "8476"}, //blackletter capital R = real part symbol,U+211C ISOamso -->
{"trade", "8482"}, //trade mark sign, U+2122 ISOnum -->
{"alefsym", "8501"}, //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 -->
{"larr", "8592"}, //leftwards arrow, U+2190 ISOnum -->
{"uarr", "8593"}, //upwards arrow, U+2191 ISOnum-->
{"rarr", "8594"}, //rightwards arrow, U+2192 ISOnum -->
{"darr", "8595"}, //downwards arrow, U+2193 ISOnum -->
{"harr", "8596"}, //left right arrow, U+2194 ISOamsa -->
{"crarr", "8629"}, //downwards arrow with corner leftwards= carriage return, U+21B5 NEW -->
{"lArr", "8656"}, //leftwards double arrow, U+21D0 ISOtech -->
// <!-- ISO 10646 does not say that lArr is the same as the 'is implied by' arrowbut also does not have any other character for that function. So ? lArr canbe used for 'is implied by' as ISOtech suggests -->
{"uArr", "8657"}, //upwards double arrow, U+21D1 ISOamsa -->
{"rArr", "8658"}, //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 -->
{"dArr", "8659"}, //downwards double arrow, U+21D3 ISOamsa -->
{"hArr", "8660"}, //left right double arrow,U+21D4 ISOamsa -->
// <!-- Mathematical Operators -->
{"forall", "8704"}, //for all, U+2200 ISOtech -->
{"part", "8706"}, //partial differential, U+2202 ISOtech -->
{"exist", "8707"}, //there exists, U+2203 ISOtech -->
{"empty", "8709"}, //empty set = null set = diameter,U+2205 ISOamso -->
{"nabla", "8711"}, //nabla = backward difference,U+2207 ISOtech -->
{"isin", "8712"}, //element of, U+2208 ISOtech -->
{"notin", "8713"}, //not an element of, U+2209 ISOtech -->
{"ni", "8715"}, //contains as member, U+220B ISOtech -->
// <!-- should there be a more memorable name than 'ni'? -->
{"prod", "8719"}, //n-ary product = product sign,U+220F ISOamsb -->
// <!-- prod is NOT the same character as U+03A0 'greek capital letter pi' thoughthe same glyph might be used for both -->
{"sum", "8721"}, //n-ary sumation, 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 -->
{"minus", "8722"}, //minus sign, U+2212 ISOtech -->
{"lowast", "8727"}, //asterisk operator, U+2217 ISOtech -->
{"radic", "8730"}, //square root = radical sign,U+221A ISOtech -->
{"prop", "8733"}, //proportional to, U+221D ISOtech -->
{"infin", "8734"}, //infinity, U+221E ISOtech -->
{"ang", "8736"}, //angle, U+2220 ISOamso -->
{"and", "8743"}, //logical and = wedge, U+2227 ISOtech -->
{"or", "8744"}, //logical or = vee, U+2228 ISOtech -->
{"cap", "8745"}, //intersection = cap, U+2229 ISOtech -->
{"cup", "8746"}, //union = cup, U+222A ISOtech -->
{"int", "8747"}, //integral, U+222B ISOtech -->
{"there4", "8756"}, //therefore, U+2234 ISOtech -->
{"sim", "8764"}, //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 -->
{"cong", "8773"}, //approximately equal to, U+2245 ISOtech -->
{"asymp", "8776"}, //almost equal to = asymptotic to,U+2248 ISOamsr -->
{"ne", "8800"}, //not equal to, U+2260 ISOtech -->
{"equiv", "8801"}, //identical to, U+2261 ISOtech -->
{"le", "8804"}, //less-than or equal to, U+2264 ISOtech -->
{"ge", "8805"}, //greater-than or equal to,U+2265 ISOtech -->
{"sub", "8834"}, //subset of, U+2282 ISOtech -->
{"sup", "8835"}, //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 --> <!ENTITY nsub", "8836"}, //not a subset of, U+2284 ISOamsn -->
{"sube", "8838"}, //subset of or equal to, U+2286 ISOtech -->
{"supe", "8839"}, //superset of or equal to,U+2287 ISOtech -->
{"oplus", "8853"}, //circled plus = direct sum,U+2295 ISOamsb -->
{"otimes", "8855"}, //circled times = vector product,U+2297 ISOamsb -->
{"perp", "8869"}, //up tack = orthogonal to = perpendicular,U+22A5 ISOtech -->
{"sdot", "8901"}, //dot operator, U+22C5 ISOamsb -->
// <!-- dot operator is NOT the same character as U+00B7 middle dot -->
// <!-- Miscellaneous Technical -->
{"lceil", "8968"}, //left ceiling = apl upstile,U+2308 ISOamsc -->
{"rceil", "8969"}, //right ceiling, U+2309 ISOamsc -->
{"lfloor", "8970"}, //left floor = apl downstile,U+230A ISOamsc -->
{"rfloor", "8971"}, //right floor, U+230B ISOamsc -->
{"lang", "9001"}, //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' -->
{"rang", "9002"}, //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 -->
{"loz", "9674"}, //lozenge, U+25CA ISOpub -->
// <!-- Miscellaneous Symbols -->
{"spades", "9824"}, //black spade suit, U+2660 ISOpub -->
// <!-- black here seems to mean filled as opposed to hollow -->
{"clubs", "9827"}, //black club suit = shamrock,U+2663 ISOpub -->
{"hearts", "9829"}, //black heart suit = valentine,U+2665 ISOpub -->
{"diams", "9830"}, //black diamond suit, U+2666 ISOpub -->
// <!-- Latin Extended-A -->
{"OElig", "338"}, // -- latin capital ligature OE,U+0152 ISOlat2 -->
{"oelig", "339"}, // -- latin small ligature oe, U+0153 ISOlat2 -->
// <!-- ligature is a misnomer, this is a separate character in some languages -->
{"Scaron", "352"}, // -- latin capital letter S with caron,U+0160 ISOlat2 -->
{"scaron", "353"}, // -- latin small letter s with caron,U+0161 ISOlat2 -->
{"Yuml", "376"}, // -- latin capital letter Y with diaeresis,U+0178 ISOlat2 -->
// <!-- Spacing Modifier Letters -->
{"circ", "710"}, // -- modifier letter circumflex accent,U+02C6 ISOpub -->
{"tilde", "732"}, //small tilde, U+02DC ISOdia -->
// <!-- General Punctuation -->
{"ensp", "8194"}, //en space, U+2002 ISOpub -->
{"emsp", "8195"}, //em space, U+2003 ISOpub -->
{"thinsp", "8201"}, //thin space, U+2009 ISOpub -->
{"zwnj", "8204"}, //zero width non-joiner,U+200C NEW RFC 2070 -->
{"zwj", "8205"}, //zero width joiner, U+200D NEW RFC 2070 -->
{"lrm", "8206"}, //left-to-right mark, U+200E NEW RFC 2070 -->
{"rlm", "8207"}, //right-to-left mark, U+200F NEW RFC 2070 -->
{"ndash", "8211"}, //en dash, U+2013 ISOpub -->
{"mdash", "8212"}, //em dash, U+2014 ISOpub -->
{"lsquo", "8216"}, //left single quotation mark,U+2018 ISOnum -->
{"rsquo", "8217"}, //right single quotation mark,U+2019 ISOnum -->
{"sbquo", "8218"}, //single low-9 quotation mark, U+201A NEW -->
{"ldquo", "8220"}, //left double quotation mark,U+201C ISOnum -->
{"rdquo", "8221"}, //right double quotation mark,U+201D ISOnum -->
{"bdquo", "8222"}, //double low-9 quotation mark, U+201E NEW -->
{"dagger", "8224"}, //dagger, U+2020 ISOpub -->
{"Dagger", "8225"}, //double dagger, U+2021 ISOpub -->
{"permil", "8240"}, //per mille sign, U+2030 ISOtech -->
{"lsaquo", "8249"}, //single left-pointing angle quotation mark,U+2039 ISO proposed -->
// <!-- lsaquo is proposed but not yet ISO standardized -->
{"rsaquo", "8250"}, //single right-pointing angle quotation mark,U+203A ISO proposed -->
// <!-- rsaquo is proposed but not yet ISO standardized -->
{"euro", "8364"}, // -- euro sign, U+20AC NEW -->
};
public static Entities XML;
public static Entities HTML32;
public static Entities HTML40;
static {
XML = new Entities();
XML.addEntities(basic);
}
static {
HTML32 = new Entities();
HTML32.addEntities(basic);
HTML32.addEntities(iso8859_1);
}
static {
HTML40 = new Entities();
HTML40.addEntities(basic);
HTML40.addEntities(iso8859_1);
HTML40.addEntities(html40);
}
//todo: refactor into a bi-di map object (or look for one and use it)
private Map mapNameToValue;
private Map mapValueToName;
private Entities() {
mapNameToValue = new HashMap();
mapValueToName = new HashMap();
}
private void addEntities(Object[][] entityArray) {
//todo: analyze whether it's more efficient to use strings or integers as the value
for (int i = 0; i < entityArray.length; ++i) {
mapNameToValue.put(entityArray[i][0], new Integer((String) entityArray[i][1]));
mapValueToName.put(new Integer((String) entityArray[i][1]), entityArray[i][0]);
}
}
public String entityName(int value) {
return (String) mapValueToName.get(new Integer(value));
}
public Integer entityValue(String name) {
return (Integer) mapNameToValue.get(name);
}
}

223
src/java/org/apache/commons/lang/StringEscapeUtils.java
View File

@ -75,10 +75,15 @@ import org.apache.commons.lang.exception.NestableRuntimeException;
* @author Helge Tesgaard
* @author <a href="sean@boohai.com">Sean Brown</a>
* @since 2.0
* @version $Id: StringEscapeUtils.java,v 1.5 2003/04/09 18:45:28 alex Exp $
* @version $Id: StringEscapeUtils.java,v 1.6 2003/04/09 20:55:32 alex Exp $
*/
public class StringEscapeUtils {
/**
* The entity set to use when escaping and unescaping HTML
*/
protected static Entities DEFAULT_ENTITIES = Entities.HTML40;
/**
* <p><code>StringEscapeUtils</code> instances should NOT be constructed in
* standard programming. Instead, the class should be used as
@ -351,167 +356,72 @@ public class StringEscapeUtils {
// HTML and XML
//--------------------------------------------------------------------------
private static class Entities {
// see http://hotwired.lycos.com/webmonkey/reference/special_characters/
// see http://www.w3.org/TR/REC-html40/sgml/entities.html
static Object[][] entities = {
// {"#39", new Integer(39)}, // ' - apostrophe
{"quot", new Integer(34)}, // " - double-quote
{"amp", new Integer(38)}, // & - ampersand
{"lt", new Integer(60)}, // < - less-than
{"gt", new Integer(62)}, // > - greater-than
{"nbsp", new Integer(160)}, // non-breaking space
{"iexcl", new Integer(161)}, //inverted exclamation mark
{"cent", new Integer(162)}, //cent sign
{"pound", new Integer(163)}, //pound sign
{"curren", new Integer(164)}, //currency sign
{"yen", new Integer(165)}, //yen sign = yuan sign
{"brvbar", new Integer(166)}, //broken bar = broken vertical bar
{"sect", new Integer(167)}, //section sign
{"uml", new Integer(168)}, //diaeresis = spacing diaeresis
{"copy", new Integer(169)}, // © - copyright sign
{"ordf", new Integer(170)}, //feminine ordinal indicator
{"laquo", new Integer(171)}, //left-pointing double angle quotation mark = left pointing guillemet
{"not", new Integer(172)}, //not sign
{"shy", new Integer(173)}, //soft hyphen = discretionary hyphen
{"reg", new Integer(174)}, // ® - registered trademark sign
{"macr", new Integer(175)}, //macron = spacing macron = overline = APL overbar
{"deg", new Integer(176)}, //degree sign
{"plusmn", new Integer(177)}, //plus-minus sign = plus-or-minus sign
{"sup2", new Integer(178)}, //superscript two = superscript digit two = squared
{"sup3", new Integer(179)}, //superscript three = superscript digit three = cubed
{"acute", new Integer(180)}, //acute accent = spacing acute
{"micro", new Integer(181)}, //micro sign
{"para", new Integer(182)}, //pilcrow sign = paragraph sign
{"middot", new Integer(183)}, //middle dot = Georgian comma = Greek middle dot
{"cedil", new Integer(184)}, //cedilla = spacing cedilla
{"sup1", new Integer(185)}, //superscript one = superscript digit one
{"ordm", new Integer(186)}, //masculine ordinal indicator
{"raquo", new Integer(187)}, //right-pointing double angle quotation mark = right pointing guillemet
{"frac14", new Integer(188)}, //vulgar fraction one quarter = fraction one quarter
{"frac12", new Integer(189)}, //vulgar fraction one half = fraction one half
{"frac34", new Integer(190)}, //vulgar fraction three quarters = fraction three quarters
{"iquest", new Integer(191)}, //inverted question mark = turned question mark
{"Agrave", new Integer(192)}, // À - uppercase A, grave accent
{"Aacute", new Integer(193)}, // Á - uppercase A, acute accent
{"Acirc", new Integer(194)}, // Â - uppercase A, circumflex accent
{"Atilde", new Integer(195)}, // Ã - uppercase A, tilde
{"Auml", new Integer(196)}, // Ä - uppercase A, umlaut
{"Aring", new Integer(197)}, // Å - uppercase A, ring
{"AElig", new Integer(198)}, // Æ - uppercase AE
{"Ccedil", new Integer(199)}, // Ç - uppercase C, cedilla
{"Egrave", new Integer(200)}, // È - uppercase E, grave accent
{"Eacute", new Integer(201)}, // É - uppercase E, acute accent
{"Ecirc", new Integer(202)}, // Ê - uppercase E, circumflex accent
{"Euml", new Integer(203)}, // Ë - uppercase E, umlaut
{"Igrave", new Integer(204)}, // Ì - uppercase I, grave accent
{"Iacute", new Integer(205)}, // Í - uppercase I, acute accent
{"Icirc", new Integer(206)}, // Î - uppercase I, circumflex accent
{"Iuml", new Integer(207)}, // Ï - uppercase I, umlaut
{"ETH", new Integer(208)}, // Ð - uppercase Eth, Icelandic
{"Ntilde", new Integer(209)}, // Ñ - uppercase N, tilde
{"Ograve", new Integer(210)}, // Ò - uppercase O, grave accent
{"Oacute", new Integer(211)}, // Ó - uppercase O, acute accent
{"Ocirc", new Integer(212)}, // Ô - uppercase O, circumflex accent
{"Otilde", new Integer(213)}, // Õ - uppercase O, tilde
{"Ouml", new Integer(214)}, // Ö - uppercase O, umlaut
{"times", new Integer(215)}, //multiplication sign
{"Oslash", new Integer(216)}, // Ø - uppercase O, slash
{"Ugrave", new Integer(217)}, // Ù - uppercase U, grave accent
{"Uacute", new Integer(218)}, // Ú - uppercase U, acute accent
{"Ucirc", new Integer(219)}, // Û - uppercase U, circumflex accent
{"Uuml", new Integer(220)}, // Ü - uppercase U, umlaut
{"Yacute", new Integer(221)}, // Ý - uppercase Y, acute accent
{"THORN", new Integer(222)}, // Þ - uppercase THORN, Icelandic
{"szlig", new Integer(223)}, // ß - lowercase sharps, German
{"agrave", new Integer(224)}, // à - lowercase a, grave accent
{"aacute", new Integer(225)}, // á - lowercase a, acute accent
{"acirc", new Integer(226)}, // â - lowercase a, circumflex accent
{"atilde", new Integer(227)}, // ã - lowercase a, tilde
{"auml", new Integer(228)}, // ä - lowercase a, umlaut
{"aring", new Integer(229)}, // å - lowercase a, ring
{"aelig", new Integer(230)}, // æ - lowercase ae
{"ccedil", new Integer(231)}, // ç - lowercase c, cedilla
{"egrave", new Integer(232)}, // è - lowercase e, grave accent
{"eacute", new Integer(233)}, // é - lowercase e, acute accent
{"ecirc", new Integer(234)}, // ê - lowercase e, circumflex accent
{"euml", new Integer(235)}, // ë - lowercase e, umlaut
{"igrave", new Integer(236)}, // ì - lowercase i, grave accent
{"iacute", new Integer(237)}, // í - lowercase i, acute accent
{"icirc", new Integer(238)}, // î - lowercase i, circumflex accent
{"iuml", new Integer(239)}, // ï - lowercase i, umlaut
{"eth", new Integer(240)}, // ð - lowercase eth, Icelandic
{"ntilde", new Integer(241)}, // ñ - lowercase n, tilde
{"ograve", new Integer(242)}, // ò - lowercase o, grave accent
{"oacute", new Integer(243)}, // ó - lowercase o, acute accent
{"ocirc", new Integer(244)}, // ô - lowercase o, circumflex accent
{"otilde", new Integer(245)}, // õ - lowercase o, tilde
{"ouml", new Integer(246)}, // ö - lowercase o, umlaut
{"divide", new Integer(247)}, // division sign
{"oslash", new Integer(248)}, // ø - lowercase o, slash
{"ugrave", new Integer(249)}, // ù - lowercase u, grave accent
{"uacute", new Integer(250)}, // ú - lowercase u, acute accent
{"ucirc", new Integer(251)}, // û - lowercase u, circumflex accent
{"uuml", new Integer(252)}, // ü - lowercase u, umlaut
{"yacute", new Integer(253)}, // ý - lowercase y, acute accent
{"thorn", new Integer(254)}, // þ - lowercase thorn, Icelandic
{"yuml", new Integer(255)}, // ÿ - lowercase y, umlaut
{"euro", new Integer(8364)}, // Euro symbol
};
private Map mapNameToValue;
private Map mapValueToName;
public Entities() {
mapNameToValue = new HashMap();
mapValueToName = new HashMap();
for (int i = 0; i < entities.length; ++i) {
mapNameToValue.put(entities[i][0], entities[i][1]);
mapValueToName.put(entities[i][1], entities[i][0]);
}
}
public String entityName(int value) {
return (String) mapValueToName.get(new Integer(value));
}
public Integer entityValue(String name) {
return (Integer) mapNameToValue.get(name);
}
}
private static Entities entities;
private static void initEntities() {
if (entities == null)
entities = new Entities();
}
private static String entityName(char ch) {
initEntities();
return entities.entityName(ch);
}
private static Integer entityValue(String entity) {
initEntities();
return entities.entityValue(entity);
}
/**
* <p>Turns funky characters into HTML entity equivalents.</p>
* <p>
* For example: <tt>"bread" & "butter"</tt> => <tt>&amp;quot;bread&amp;quot; &amp;amp; &amp;quot;butter&amp;quot;</tt>.
* Supports all known HTML entities, including funky accents. See the source code for more detail.
* see http://hotwired.lycos.com/webmonkey/reference/special_characters/
* </p>
* <p>Supports all known HTML 4.0 entities, including funky accents.
* See the source code for more detail.
* </p>
* @see http://hotwired.lycos.com/webmonkey/reference/special_characters/
* @see Entities
* @see #unescapeHtml(String)
**/
public static String escapeHtml(String str) {
return escapeEntities(str, Entities.HTML40);
}
/**
* Given a string containing entity escapes, returns a string
* containing the actual Unicode characters corresponding to the
* escapes.
*
* @see #escapeHtml(String)
**/
public static String unescapeHtml(String str) {
return unescapeEntities(str, Entities.HTML40);
}
/**
* <p>Turns funky characters into XML entity equivalents.</p>
* <p>
* For example: <tt>"bread" & "butter"</tt> => <tt>&amp;quot;bread&amp;quot; &amp;amp; &amp;quot;butter&amp;quot;</tt>.
* </p>
* <p>
* Supports only the four basic XML entities (gt, lt, quot, amp).
* Does not support DTDs or external entities.
* </p>
* @see #unescapeXml(java.lang.String)
**/
public static String escapeXml(String str) {
return escapeEntities(str, Entities.XML);
}
/**
* <p>Given a string containing XML entity escapes, returns a string
* containing the actual Unicode characters corresponding to the
* escapes.
* </p>
* <p>
* Supports only the four basic XML entities (gt, lt, quot, amp).
* Does not support DTDs or external entities.
* </p>
*
* @see #escapeXml(String)
**/
public static String unescapeXml(String str) {
return unescapeEntities(str, Entities.XML);
}
private static String escapeEntities(String str, Entities entities) {
StringBuffer buf = new StringBuffer(str.length() * 2);
int i;
for (i = 0; i < str.length(); ++i) {
char ch = str.charAt(i);
String entity = entityName(ch);
String entity = entities.entityName(ch);
if (entity == null) {
if (((int) ch) > 128) { // should this be 127 or 128?
if (((int) ch) > 0x7F) {
int intValue = ((int) ch);
buf.append("&#" + intValue + ";");
} else {
@ -524,14 +434,7 @@ public class StringEscapeUtils {
return buf.toString();
}
/**
* Given a string containing entity escapes, returns a string
* containing the actual Unicode characters corresponding to the
* escapes.
*
* @see #escapeHtml(String)
**/
public static String unescapeHtml(String str) {
private static String unescapeEntities(String str, Entities entities) {
StringBuffer buf = new StringBuffer(str.length());
int i;
for (i = 0; i < str.length(); ++i) {
@ -547,7 +450,7 @@ public class StringEscapeUtils {
if (entity.charAt(0) == '#') {
iso = new Integer(entity.substring(1));
} else {
iso = entityValue(entity);
iso = entities.entityValue(entity);
}
if (iso == null) {
buf.append("&" + entity + ";");

37
src/test/org/apache/commons/lang/StringEscapeUtilsTest.java
View File

@ -66,7 +66,7 @@ import junit.textui.TestRunner;
*
* @author of original StringUtilsTest.testEscape = ?
* @author <a href="mailto:alex@purpletech.com">Alexander Day Chaffee</a>
* @version $Id: StringEscapeUtilsTest.java,v 1.3 2003/04/09 18:45:29 alex Exp $
* @version $Id: StringEscapeUtilsTest.java,v 1.4 2003/04/09 20:55:33 alex Exp $
*/
public class StringEscapeUtilsTest extends TestCase {
private final static String FOO = "foo";
@ -143,8 +143,8 @@ public class StringEscapeUtilsTest extends TestCase {
assertEquals("unescape(String) failed" +
(message == null ? "" : (": " + message)) +
// we escape this so we can see it in the error message
": expected '" + StringUtils.escape(expected) +
// we escape this so we can see it in the error message
"' actual '" + StringUtils.escape(actual) + "'",
expected, actual);
@ -159,8 +159,16 @@ public class StringEscapeUtilsTest extends TestCase {
}
// HTML
// HTML and XML
//--------------------------------------------------------------
public void testEntitiesObject() throws Exception
{
assertEquals("gt", Entities.XML.entityName('>'));
assertEquals(new Integer('>'), Entities.XML.entityValue("gt"));
assertEquals(null, Entities.XML.entityValue("xyzzy"));
}
String[][] htmlEscapes = {
{"no escaping", "plain text", "plain text"},
{"no escaping", "plain text", "plain text"},
@ -171,6 +179,8 @@ public class StringEscapeUtilsTest extends TestCase {
{"first character only", "&lt; less than", "< less than"},
{"apostrophe", "Huntington's chorea", "Huntington's chorea"},
{"languages", "English,Fran&ccedil;ais,&#26085;&#26412;&#35486; (nihongo)", "English,Fran\u00E7ais,\u65E5\u672C\u8A9E (nihongo)"},
{"8-bit ascii doesn't number-escape", "~\u007F", "\u007E\u007F"},
{"8-bit ascii does number-escape", "&#128;&#159;", "\u0080\u009F"},
};
public void testEscapeHtml() {
@ -180,7 +190,7 @@ public class StringEscapeUtilsTest extends TestCase {
}
}
public void testHtmlunescape() {
public void testUnescapeHtml() {
for (int i = 0; i < htmlEscapes.length; ++i) {
assertEquals(htmlEscapes[i][0], htmlEscapes[i][2], StringEscapeUtils.unescapeHtml(htmlEscapes[i][1]));
// todo: add test for (and implement) Writer-based version
@ -191,6 +201,25 @@ public class StringEscapeUtilsTest extends TestCase {
assertEquals("funny chars pass through OK", "Fran\u00E7ais", StringEscapeUtils.unescapeHtml("Fran\u00E7ais"));
}
public void testEscapeHtmlVersions() throws Exception
{
assertEquals("&Beta;", StringEscapeUtils.escapeHtml("\u0392"));
assertEquals("\u0392", StringEscapeUtils.unescapeHtml("&Beta;"));
//todo: refine API for escaping/unescaping specific HTML versions
}
public void testEscapeXml() throws Exception {
assertEquals("&lt;abc&gt;", StringEscapeUtils.escapeXml("<abc>"));
assertEquals("<abc>", StringEscapeUtils.unescapeXml("&lt;abc&gt;"));
assertEquals("XML should use numbers, not names for HTML entities",
"&#161;", StringEscapeUtils.escapeXml("\u00A1"));
assertEquals("XML should use numbers, not names for HTML entities",
"\u00A0", StringEscapeUtils.unescapeXml("&#160;"));
}
// SQL
// see http://www.jguru.com/faq/view.jsp?EID=8881
//--------------------