Java Unicode Unescape unescapeHTMLUnicodeEntity(final String text)

Description

unescape HTML Unicode Entity

License

Open Source License

Declaration

public static String unescapeHTMLUnicodeEntity(final String text) 

Method Source Code

//package com.java2s;
/*/*  w  w w .  j  a  v a  2s . c  o  m*/
 *  Freeplane - mind map editor
 *  Copyright (C) 2008 Joerg Mueller, Daniel Polansky, Christian Foltin, Dimitry Polivaev
 *
 *  This file is modified by Dimitry Polivaev in 2008.
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation, either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

public class Main {
    public static String unescapeHTMLUnicodeEntity(final String text) {
        final StringBuilder resultBuilder = new StringBuilder(text.length());
        final StringBuilder entity = new StringBuilder();
        boolean readingEntity = false;
        char myChar;
        for (int i = 0; i < text.length(); ++i) {
            myChar = text.charAt(i);
            if (readingEntity) {
                if (myChar == ';') {
                    if (entity.charAt(0) == '#') {
                        try {
                            final char c;
                            if (entity.charAt(1) == 'x') {
                                c = (char) Integer.parseInt(entity.substring(2), 16);
                            } else {
                                c = (char) Integer.parseInt(entity.substring(1), 10);
                            }
                            if (c >= ' ' || c == '\t' || c == '\r' || c == '\n') {
                                resultBuilder.append(c);
                            } else {
                                resultBuilder.append(' ');
                            }
                        } catch (final NumberFormatException e) {
                            resultBuilder.append('&').append(entity).append(';');
                        }
                    } else {
                        resultBuilder.append('&').append(entity).append(';');
                    }
                    entity.setLength(0);
                    readingEntity = false;
                } else {
                    entity.append(myChar);
                }
            } else {
                if (myChar == '&') {
                    readingEntity = true;
                } else {
                    resultBuilder.append(myChar);
                }
            }
        }
        if (entity.length() > 0) {
            resultBuilder.append('&').append(entity);
        }
        final String result = resultBuilder.toString();
        return result;
    }
}

Related

1. unescapeUnicode(String encoded)
2. unescapeUnicode(String s)
3. unescapeUnicode(String s)
4. unescapeUnicodeChars(String string)