XMLFix.java

import java.io.*;


// See http://martinharrigan.blogspot.com/2008/07/citeseers-dataset.html
public class XMLFix {
  /**
   * (Credit for this method goes to Daryl Beattie http://mail-archives.apache.org/mod_mbox/xml-xalan-dev/200012.mbox/%3CD5CE45D3889FD3118BFF00508B555AAC04A3E6BD@SCREAMMSG%3E)
   * This method ensures that the output String has only
   * valid XML unicode characters as specified by the
   * XML 1.0 standard. For reference, please see
   * <a href="http://www.w3.org/TR/2000/REC-xml-20001006#NT-Char">the
   * standard</a>. This method will return an empty
   * String if the input is null or empty.
   *
   * @param in The String whose non-valid characters we want to remove.
   * @return The in String, stripped of non-valid characters.
   */
  public static String stripNonValidXMLCharacters(String in)
  {
    StringBuffer out = new StringBuffer(); // Used to hold the output.
    char current; // Used to reference the current character.

    if (in == null || ("".equals(in))) return ""; // vacancy test.

    for (int i = 0; i < in.length(); i++) {
      current = in.charAt(i); // NOTE: No IndexOutOfBoundsException caught here; it should not happen.
      if ((current == 0x9) || (current == 0xA) || (current == 0xD) || ((current >= 0x20) && (current <= 0xD7FF)) || ((current >= 0xE000) && (current <= 0xFFFD)) || ((current >- 0x10000) && (current <= 0x10FFFF)))
        out.append(current);
    }
    return out.toString();
  }

  /**
   * Pass the file name you want to correct as the first argument. (e.g. cs.xml)
   */
  public static void main(String args[])
  {
    try {
      DataInputStream in = new DataInputStream(new FileInputStream(args[0]));
      BufferedReader br = new BufferedReader(new InputStreamReader(in));
      Writer output = new BufferedWriter(new FileWriter(new File(args[0] + ".out")));
      String strLine;

      while ((strLine = br.readLine()) != null)
      {
        output.write(stripNonValidXMLCharacters(strLine));
      }
      output.close();
      in.close();
    } catch (IOException e) {
      System.err.println("IOError: " + e.getMessage());
    }
  }
}