HTMLEscape.java

/*
Copyright 2008-2010 Gephi
Authors : Eduardo Ramos <eduramiba@gmail.com>
Website : http://www.gephi.org

This file is part of Gephi.

Gephi 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.

Gephi 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 Gephi.  If not, see <http://www.gnu.org/licenses/>.
 */
package org.gephi.utils;

/**
 * Class for escaping html of a String to show it in a hrml report without problems
 * @author Eduardo Ramos <eduramiba@gmail.com>
 */
public class HTMLEscape {

    /**Code previously used in web applications, adapted from a google search**/

    /**
     * Escape html from a string to make it safe to show.
     * @param string String to escape html
     * @return Result string
     */
    public static String stringToHTMLString(String string) {
        StringBuilder sb = new StringBuilder(string.length());
        // true if last char was blank
        boolean lastWasBlankChar = false;
        int len = string.length();
        char c;

        for (int i = 0; i < len; i++) {
            c = string.charAt(i);
            if (c == ' ') {
                // blank gets extra work,
                // this solves the problem you get if you replace all
                // blanks with  , if you do that you loss
                // word breaking
                if (lastWasBlankChar) {
                    lastWasBlankChar = false;
                    sb.append(" ");
                } else {
                    lastWasBlankChar = true;
                    sb.append(' ');
                }
            } else {
                lastWasBlankChar = false;
                //
                // HTML Special Chars
                if (c == '"') {
                    sb.append(""");
                } else if (c == '&') {
                    sb.append("&");
                } else if (c == '<') {
                    sb.append("<");
                } else if (c == '>') {
                    sb.append(">");

                } else if (c == '\n') {
                    sb.append("<br>\n");
                } else if (c == '\r') {
                } else {
                    int ci = 0xffff & c;
                    if (ci < 160) {
                        // nothing special only 7 Bit
                        sb.append(c);
                    } else {
                        // Not 7 Bit use the unicode system
                        sb.append("&#");
                        sb.append(new Integer(ci).toString());
                        sb.append(';');
                    }
                }
            }
        }
        return sb.toString();
    }
}