How to use

decode

method

in

org.htmlparser.util.Translate

/**
 * Decode a string containing references.
 * Change all numeric character reference and character entity references
 * to unicode characters.
 * @param string The string to translate.
 */
public static String decode (String string)
{
  return decode(string, null);
}

/**
 * Decodes entities in a string if it isn't null.<p>
 *
 * @param value the string for which to decode entities
 *
 * @return the string with the decoded entities
 */
protected static String decodeEntities(String value) {
  if (value != null) {
    value = Translate.decode(value);
  }
  return value;
}

/**
 * Decode the characters in a string buffer containing references.
 * Change all numeric character reference and character entity references
 * to unicode characters.
 * @param buffer The StringBuffer containing references.
 * @return The decoded string.
 */
public static String decode (StringBuffer buffer)
{
  return decode (buffer.toString());
}

/**
 * Decode the characters in a string buffer containing references.
 * Change all numeric character reference and character entity references
 * to unicode characters.
 * @param buffer The StringBuilder containing references.
 * @return The decoded string.
 */
public static String decode (StringBuilder buffer)
{
  return decode (buffer.toString());
}

/**
 * Convert a reference to a unicode character.
 * Convert a single numeric character reference or character entity reference
 * to a unicode character.
 * @param string The string to convert. Of the form &xxxx; or &#xxxx; with
 * or without the leading ampersand or trailing semi-colon.
 * @return The converted character or '' (zero) if the string is an
 * invalid reference.
 * @deprecated Use {@link #decode(String) decode}.
 */
public static char convertToChar (String string)
{
  return (decode (string).charAt (0));
}

/**
 * Convert a reference to a unicode character.
 * Convert a single numeric character reference or character entity reference
 * to a unicode character.
 * @param string The string to convert. Of the form &xxxx; or &#xxxx; with
 * or without the leading ampersand or trailing semi-colon.
 * @param start The starting pooint in the string to look for a character reference.
 * @param end The ending point in the string to stop looking for a character reference.
 * @return The converted character or '' (zero) if the string is an
 * invalid reference.
 * @deprecated Use {@link #decode(String) decode}.
 */
public static char convertToChar (String string, int start, int end)
{
  return (decode (string.substring (start, end)).charAt (0));
}

  public String toPlainTextString() {
    return Translate.decode(delegate.toPlainTextString());
  }
}

private static String cleanText(String text) {
 return replaceNonBreakingSpaceWithOrdinarySpace(Translate.decode(text));
}
 

  /**
   * Numeric character reference and character entity reference to unicode codec.
   * Translate the <code>System.in</code> input into an encoded or decoded
   * stream and send the results to <code>System.out</code>.
   * @param args If arg[0] is <code>-encode</code> perform an encoding on
   * <code>System.in</code>, otherwise perform a decoding.
   */
  public static void main (String[] args)
  {
    boolean encode;

    if (0 < args.length && args[0].equalsIgnoreCase ("-encode"))
      encode = true;
    else
      encode = false;
    if (encode)
      encode (System.in, System.out);
    else
      decode (System.in, System.out);
  }
}

  /**
   * Numeric character reference and character entity reference to unicode codec.
   * Translate the <code>System.in</code> input into an encoded or decoded
   * stream and send the results to <code>System.out</code>.
   * @param args If arg[0] is <code>-encode</code> perform an encoding on
   * <code>System.in</code>, otherwise perform a decoding.
   */
  public static void main (String[] args)
  {
    boolean encode;

    if (0 < args.length && args[0].equalsIgnoreCase ("-encode"))
      encode = true;
    else
      encode = false;
    if (encode)
      encode (System.in, System.out);
    else
      decode (System.in, System.out);
  }
}

public void visitStringNode(Text stringNode) {
  String text = stringNode.getText();
  if (!preTagBeingProcessed) {
    text = Translate.decode(text);
    text = replaceNonBreakingSpaceWithOrdinarySpace(text);
  }
  textAccumulator.append(text);
}

/**
 * test of {@link Translate#decode(String)}
 * Note: we no longer use this method for decoding entities.
 */
public void testTranslate() {
  String orig = "http://foo.com/main?arg1=1&lang=2";
  String xlated = Translate.decode(orig);
  System.out.format("Orig(%s) xlated(%s)\n",orig,xlated);
  String orig2 = "                gaz.cgi?foo=bar&lang=2";
  String xlated2 = Translate.decode(orig2);
  System.out.format("Orig2(%s) xlated2(%s)\n",orig2,xlated2);
}

public void visitStringNode(Text stringNode) {
  String text = stringNode.getText();
  if (!preTagBeingProcessed) {
    text = Translate.decode(text);
    text = replaceNonBreakingSpaceWithOrdinarySpace(text);
  }
  textAccumulator.append(text);
}

private void compareDecodes(String orig) {
  String htmlparserDecoded = Translate.decode(orig);
  String apacheDecoded = StringEscapeUtils.unescapeHtml(orig);
  System.out.format("ORIGINAL:(%s)\n", orig);
  System.out.format("htmlparser:(%s)\n", htmlparserDecoded);
  System.out.format("apache:(%s)\n", apacheDecoded);
}

/**
 * Appends the text to the output.
 * @param string The text node.
 */
public void visitStringNode (Text string)
{
  if (!mIsScript && !mIsStyle)
  {
    String text = string.getText ();
    if (!mIsPre)
    {
      text = Translate.decode (text);
      if (getReplaceNonBreakingSpaces ())
        text = text.replace ('\u00a0', ' ');
      if (getCollapse ())
        collapse (mBuffer, text);
      else
        mBuffer.append (text);
    }
    else
      mBuffer.append (text);
  }
}

/**
 * Appends the text to the output.
 * @param string The text node.
 */
public void visitStringNode (Text string)
{
  if (!mIsScript && !mIsStyle)
  {
    String text = string.getText ();
    if (!mIsPre)
    {
      text = Translate.decode (text);
      if (getReplaceNonBreakingSpaces ())
        text = text.replace ('\u00a0', ' ');
      if (getCollapse ())
        collapse (mBuffer, text);
      else
        mBuffer.append (text);
    }
    else
      mBuffer.append (text);
  }
}

private void appendText(String text) {
    text = Translate.decode(text);
    text = collapse(text);

text = Translate.decode(text);
text = collapse(text);

private void appendText(String text) {
    text = Translate.decode(text);
    text = collapse(text);

return (Translate.decode (ret));