All Downloads are FREE. Search and download functionalities are using the official Maven repository.

uk.co.anyware.html.HTMLEscaper Maven / Gradle / Ivy

There is a newer version: 1.5.24
Show newest version
/*

HTML Escaping code
Copyright (C) 2000 Marc Palmer / AnyWare Ltd.

This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.

This library 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
Lesser General Public License for more details.

You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

Thanks to Jason Hunter for his great book "JAVA Servlet Programming" used as
the source for the entity mappings. Thanks to CARDIACS for making the
most joyful music (www.cardiacs.com/button.html)

http://www.anyware.co.uk/java for updates and other stuff

*/

package uk.co.anyware.html;

/**
 * This class will escape characters that have an HTML entity
 * representation. It will not escape standard ASCII characters unless
 * it is necessary (i.e. will not escape ASCI #32 but will escape "&").
 * Any characters with no corresponding entity are passed through unchanged.
 * It uses a quick string -> array mapping to avoid creating thousands of
 * temporary objects.
 */
public class HTMLEscaper {

  /**
   * A little bit of unit testing
   */
  public static void main(String[] args) {

    String text =
      "This is a test of the html escaper & let's hope it really, "+
      "really works! Is there an � with an umlaut in the house?"+
      "This code is �copyleft. I like to be paid in ���s";

    System.out.println( "NOTE: Due to differences in ASCII fonts, the text "+
      "sent to the escaper may not display properly. Hopefully you will be "+
      "able to tell what it should have looked like from the escaped output.");
    System.out.println( "in: "+text );

    System.out.println( "out: "+escape( text) );
  }

  /**
   * This method will take the input and escape characters that have
   * an HTML entity representation.
   * It uses a quick string -> array mapping to avoid creating thousands of
   * temporary objects.
   * @param nonHTMLsrc String containing the text to make HTML-safe
   * @return String containing new copy of string with entities escaped
   */
  public static final String escape( String nonHTMLsrc)
  {
    StringBuffer res = new StringBuffer();
    int l = nonHTMLsrc.length();
    int idx;
    char c;
    for (int i = 0; i < l; i++)
    {
      c = nonHTMLsrc.charAt(i);
      idx = entityMap.indexOf( c);
      if (idx == -1)
        res.append( c);
      else
        res.append( quickEntities[idx]);
    }
    return res.toString();
  }

  /**
   * These are probably HTML 3.2 level... as it looks like some HTML 4 entities
   * are not present.
   */
  private static final String[][] entities = {
    /* We probably don't want to filter regular ASCII chars so we leave them out */
    { "&", "amp" },
    { "<", "lt" },
    { ">", "gt" },

    { "\u0083", "#131" },
    { "\u0084", "#132" },
    { "\u0085", "#133" },
    { "\u0086", "#134" },
    { "\u0087", "#135" },
    { "\u0089", "#137" },
    { "\u008A", "#138" },
    { "\u008B", "#139" },
    { "\u008C", "#140" },
    { "\u0091", "#145" },
    { "\u0092", "#146" },
    { "\u0093", "#147" },
    { "\u0094", "#148" },
    { "\u0095", "#149" },
    { "\u0096", "#150" },
    { "\u0097", "#151" },
    { "\u0099", "#153" },
    { "\u009A", "#154" },
    { "\u009B", "#155" },
    { "\u009C", "#156" },
    { "\u009F", "#159" },

    { "\u00A0", "nbsp" },
    { "\u00A1", "iexcl" },
    { "\u00A2", "cent" },
    { "\u00A3", "pound" },
    { "\u00A4", "curren" },
    { "\u00A5", "yen" },
    { "\u00A6", "brvbar" },
    { "\u00A7", "sect" },
    { "\u00A8", "uml" },
    { "\u00A9", "copy" },
    { "\u00AA", "ordf" },
    { "\u00AB", "laquo" },
    { "\u00AC", "not" },
    { "\u00AD", "shy" },
    { "\u00AE", "reg" },
    { "\u00AF", "macr"},
    { "\u00B0", "deg"},
    { "\u00B1", "plusmn"},
    { "\u00B2", "sup2"},
    { "\u00B3", "sup3"},

    { "\u00B4", "acute" },
    { "\u00B5", "micro" },
    { "\u00B6", "para" },
    { "\u00B7", "middot" },
    { "\u00B8", "cedil" },
    { "\u00B9", "sup1" },
    { "\u00BA", "ordm" },
    { "\u00BB", "raquo" },
    { "\u00BC", "frac14" },
    { "\u00BD", "frac12" },
    { "\u00BE", "frac34" },
    { "\u00BF", "iquest" },

    { "\u00C0", "Agrave" },
    { "\u00C1", "Aacute" },
    { "\u00C2", "Acirc" },
    { "\u00C3", "Atilde" },
    { "\u00C4", "Auml" },
    { "\u00C5", "Aring" },
    { "\u00C6", "AElig" },
    { "\u00C7", "CCedil" },
    { "\u00C8", "Egrave" },
    { "\u00C9", "Eacute" },
    { "\u00CA", "Ecirc" },
    { "\u00CB", "Euml" },
    { "\u00CC", "Igrave" },
    { "\u00CD", "Iacute" },
    { "\u00CE", "Icirc" },
    { "\u00CF", "Iuml" },

    { "\u00D0", "ETH" },
    { "\u00D1", "Ntilde" },
    { "\u00D2", "Ograve" },
    { "\u00D3", "Oacute" },
    { "\u00D4", "Ocirc" },
    { "\u00D5", "Otilde" },
    { "\u00D6", "Ouml" },
    { "\u00D7", "times" },
    { "\u00D8", "Oslash" },
    { "\u00D9", "Ugrave" },
    { "\u00DA", "Uacute" },
    { "\u00DB", "Ucirc" },
    { "\u00DC", "Uuml" },
    { "\u00DD", "Yacute" },
    { "\u00DE", "THORN" },
    { "\u00DF", "szlig" },

    { "\u00E0", "agrave" },
    { "\u00E1", "aacute" },
    { "\u00E2", "acirc" },
    { "\u00E3", "atilde" },
    { "\u00E4", "auml" },
    { "\u00E5", "aring" },
    { "\u00E6", "aelig" },
    { "\u00E7", "ccedil" },
    { "\u00E8", "egrave" },
    { "\u00E9", "eacute" },
    { "\u00EA", "ecirc" },
    { "\u00EB", "euml" },
    { "\u00EC", "igrave" },
    { "\u00ED", "iacute" },
    { "\u00EE", "icirc" },
    { "\u00EF", "iuml" },

    { "\u00F0", "eth" },
    { "\u00F1", "ntilde" },
    { "\u00F2", "ograve" },
    { "\u00F3", "oacute" },
    { "\u00F4", "ocirc" },
    { "\u00F5", "otilde" },
    { "\u00F6", "ouml" },
    { "\u00F7", "divid" },
    { "\u00F8", "oslash" },
    { "\u00F9", "ugrave" },
    { "\u00FA", "uacute" },
    { "\u00FB", "ucirc" },
    { "\u00FC", "uuml" },
    { "\u00FD", "yacute" },
    { "\u00FE", "thorn" },
    { "\u00FF", "yuml" }
  };

  private static String entityMap;
  private static String[] quickEntities;

  static {
    // Initialize some local mappings to speed it all up
    int l = entities.length;
    StringBuffer temp = new StringBuffer();

    quickEntities = new String[l];
    for (int i = 0; i < l; i++)
    {
      temp.append( entities[i][0]);
      quickEntities[i] = "&"+entities[i][1]+";";
    }
    entityMap = temp.toString();
  }
}





© 2015 - 2024 Weber Informatics LLC | Privacy Policy