HTMLEntities.java

Go to the documentation of this file.

/*
 * Turró i Cutiller Foundation. License notice.
 * Copyright (C) 2017 Lluis Turró Cutiller <http://www.turro.org/>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as published by
 * the Free Software Foundation, either version 3 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 Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 
package org.turro.html;
 
import org.apache.commons.text.StringEscapeUtils;
import org.turro.elephant.context.ElephantContext;
 
public class HTMLEntities {
 
  private static final String Entities_ISO88591[] = {
    "&euro;",
    "&sbquo;",
    "&fnof;",
    "&bdquo;",
    "&hellip;",
    "&dagger;",
    "&Dagger;",
    "&circ;",
    "&permil;",
    "&Scaron;",
    "&lsaquo;",
    "&OElig;",
    "&Zcaron;",
    "&lsquo;",
    "&rsquo;",
    "&ldquo;",
    "&rdquo;",
    "&bull;",
    "&ndash;",
    "&mdash;",
    "&tilde;",
    "&trade;",
    "&scaron;",
    "&rsaquo;",
    "&oelig;",
    "&zcaron;",
    "&Yuml;",
    "&iexcl;",
    "&cent;",
    "&pound;",
    "&curren;",
    "&yen;",
    "&brvbar;",
    "&sect;",
    "&uml;",
    "&copy;",
    "&ordf;",
    "&laquo;",
    "&not;",
    "&shy;",
    "&reg;",
    "&macr;",
    "&deg;",
    "&plusmn;",
    "&sup2;",
    "&sup3;",
    "&acute;",
    "&micro;",
    "&para;",
    "&middot;",
    "&cedil;",
    "&sup1;",
    "&ordm;",
    "&raquo;",
    "&frac14;",
    "&frac12;",
    "&frac34;",
    "&iquest;"
  };
  
  private static final String SINGLE_QUOTE[] = {
    "&sbquo;",
    "&lsquo;",
    "&rsquo;"
  };
    
  private static final String DOUBLE_QUOTE[] = {
    "&bdquo;",
    "&ldquo;",
    "&rdquo;"
  };
    
  private static final String HELLIP[] = {
    "&hellip;"
  };
    
  private static final String BULLET[] = {
    "&bull;"
  };
    
  private static final String DASH[] = {
    "&ndash;",
    "&mdash;"
  };
  
  public static String escape(String html) {
    if(html != null && "ISO-8859-1".equals(ElephantContext.getEncoding())) {
      for(String entity : Entities_ISO88591) {
        html = html.replaceAll("\\" + StringEscapeUtils.unescapeHtml4(entity), "\\" + entity);
      }
    }
    return html;
  }
  
  public static String unescape(String html) {
    if(html != null && "ISO-8859-1".equals(ElephantContext.getEncoding())) {
      for(String entity : Entities_ISO88591) {
        html = html.replaceAll("\\" + entity, "\\" + StringEscapeUtils.unescapeHtml4(entity));
      }
    }
    return html;
  }
  
  public static String plainWhenPossible(String html) {
    if(html != null && "ISO-8859-1".equals(ElephantContext.getEncoding())) {
      html = html.replaceAll("[\\‘\\’\\’  ]", "'")
                 .replaceAll("[\\“\\”\\“\\”]", "\"")
                 .replaceAll("[\\…]", "\\.\\.\\.")
                 .replaceAll("[\\•]", "\\·")
                 .replaceAll("[\\—]", "\\-");
    }
    return html;
  }
  
}