Java

StringBuilder Encode Charset

Demonstrates the importance of the charset argument when encoding/decoding. Java

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    String s = "é é é";

    CkStringBuilder sb = new CkStringBuilder();

    sb.Append(s);
    sb.EntityDecode();

    //  The string now contains: "é é é"
    System.out.println(sb.getAsString());

    //  If encoded to hex using the iso-8859-1 charset, 
    //  each é char is represented in 1 byte.
    //  Output: E920E920E9
    System.out.println(sb.getEncoded("hex","iso-8859-1"));

    //  If encoded to hex using the utf-8 charset, 
    //  each é char is represented in 2 bytes.
    //  Output: C3A920C3A920C3A9
    System.out.println(sb.getEncoded("hex","utf-8"));

    //  Here's utf-16
    //  Output: E9002000E9002000E900
    System.out.println(sb.getEncoded("hex","utf-16"));

    //  utf-32
    //  Output: E900000020000000E900000020000000E9000000
    System.out.println(sb.getEncoded("hex","utf-32"));
  }
}