/**
 * Convert HTML character enitities(Unicode) to part of a Java String
 * hiwa 8 Mar. 2004
 * comment rewritten 30 May 2006
 */
import java.util.regex.*;

public class UTF8CeToJavaString{ //this class name is misleading
                                 //it should have been UnicodeCeToJavaString
  static final String mbs = "&#(\\d+);"; //like "ロ"

  public static String EncodeCesToChars(String paramStr){
    String mbChar;
    
    StringBuffer sb = new StringBuffer();
    Pattern pat = Pattern.compile(mbs);
    Matcher mat = pat.matcher(paramStr);

    while (mat.find()){
      mbChar = getMbCharStr(mat.group(1)); //pass the digit part
      mat.appendReplacement(sb, mbChar);
    }
    mat.appendTail(sb);
    return new String(sb);
  }

  /* worker method */
  static String getMbCharStr(String digits){ //handle "12525" part which is a
    char[] cha = new char[1];                //Unicode value stringnized

    try{
      int val = Integer.parseInt(digits);
      char ch = (char)val;
      cha[0] = ch;
    }
    catch(Exception e){
      System.err.println("Error from getMbCharStr:");
      e.printStackTrace(System.err);
    }
    return new String(cha); //easy!, because Java uses Unicode
  }
}