remove XML Invalid Chars - Java XML

Java examples for XML:XML Encoding

  1. HOME
  2. Java
  3. XML
  4. XML Encoding

Description

remove XML Invalid Chars

Demo Code

/* *************************************************************************
 *
 *  TMPotter - Bi-text Aligner/TMX Editor
 *
 *  Copyright (C) 2015 Hiroshi Miura//from   w ww  .  ja v a  2  s. c o  m
 *
 *  Part of this come from OmegaT.
 *
 *  Copyright (C) 2000-2006 Keith Godfrey and Maxym Mykhalchuk
 *
 *  This file is part of TMPotter.
 *
 *  TMPotter 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 3 of the License, or
 *  (at your option) any later version.
 *
 *  TMPotter 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 TMPotter.  If not, see http://www.gnu.org/licenses/.
 *
 * *************************************************************************/
//package com.java2s;

public class Main {
    public static void main(String[] argv) throws Exception {
        String str = "java2s.com";
        System.out.println(removeXMLInvalidChars(str));
    }

    public static String removeXMLInvalidChars(String str) {
        StringBuilder sb = new StringBuilder(str.length());
        for (int c, i = 0; i < str.length(); i += Character.charCount(c)) {
            c = str.codePointAt(i);
            if (!isValidXMLChar(c)) {
                c = ' ';
            }
            sb.appendCodePoint(c);
        }
        return sb.toString();
    }

    public static boolean isValidXMLChar(int codePoint) {
        if (codePoint < 0x20) {
            if (codePoint != 0x09 && codePoint != 0x0A && codePoint != 0x0D) {
                return false;
            }
        } else if (codePoint >= 0x20 && codePoint <= 0xD7FF) {
        } else if (codePoint >= 0xE000 && codePoint <= 0xFFFD) {
        } else if (codePoint >= 0x10000 && codePoint <= 0x10FFFF) {
        } else {
            return false;
        }
        return true;
    }
}

Related Tutorials