How to use

Translate

in

org.htmlparser.util

/**
 * 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);
}

  /**
   * 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);
  }
}

    key.setStart (index);
    key.setEnd (semi);
    item = lookup (key);
    if (null != item)
      string = decode (buffer.toString ());
      out.print (string);
      buffer.setLength (0);
else
  string = decode (buffer.toString ());
  out.print (string);
candidate = lookup (c);
if (null != candidate)

/**
 * Look up a reference by character.
 * Use a combination of direct table lookup and binary search to find
 * the reference corresponding to the character.
 * @param character The character to be looked up.
 * @return The entity reference for that character or <code>null</code>.
 */
public static CharacterReference lookup (char character)
{
  int index;
  CharacterReference ret;
  if (character < BREAKPOINT)
    ret = mCharacterList[character];
  else
  {
    index = lookup (mCharacterList, character, BREAKPOINT, mCharacterList.length - 1);
    if (index < mCharacterList.length)
    {
      ret = mCharacterList[index];
      if (character != ret.getCharacter ())
        ret = null;
    }
    else
      ret = null;
  }
  
  return (ret);
}

/**
 * Convert a character to a numeric character reference.
 * Convert a unicode character to a numeric character reference of
 * the form &#xxxx;.
 * @param character The character to convert.
 * @return The converted character.
 * @deprecated Use {@link #encode(int) encode}.
 */
public static String convertToString (int character)
{
  return (encode (character));
}

    key.setStart (index);
    key.setEnd (semi);
    item = lookup (key);
    if (null != item)
      string = decode (buffer.toString ());
      out.print (string);
      buffer.setLength (0);
else
  string = decode (buffer.toString ());
  out.print (string);
candidate = lookup (c);
if (null != candidate)

/**
 * Look up a reference by character.
 * Use a combination of direct table lookup and binary search to find
 * the reference corresponding to the character.
 * @param character The character to be looked up.
 * @return The entity reference for that character or <code>null</code>.
 */
public static CharacterReference lookup (char character)
{
  int index;
  CharacterReference ret;
  if (character < BREAKPOINT)
    ret = mCharacterList[character];
  else
  {
    index = lookup (mCharacterList, character, BREAKPOINT, mCharacterList.length - 1);
    if (index < mCharacterList.length)
    {
      ret = mCharacterList[index];
      if (character != ret.getCharacter ())
        ret = null;
    }
    else
      ret = null;
  }
  
  return (ret);
}

s = Translate.encode (ret.toString ());
children = null != tag.getChildren ();
ret = new StringBuilder (s.length () + 13 + (children ? 16 : 0));

/**
 * 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;
}

  /**
   * 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);
  }
}

candidate = lookup (c);
if (null != candidate)

/**
 * 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());
}

candidate = lookup (c);
if (null != candidate)

/**
 * 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());
}

/**
 * Look up a reference by kernel.
 * Use a binary search on the ordered list of known references.
 * <em>This is not very efficient, use {@link org.htmlparser.util.Translate#lookup(org.htmlparser.util.CharacterReference) lookup(CharacterReference)}
 * instead.</em>
 * @param kernel The string to lookup, i.e. "amp".
 * @param start The starting point in the string of the kernel.
 * @param end The ending point in the string of the kernel.
 * This should be the index of the semicolon if it exists, or failing that,
 * at least an index past the last character of the kernel.
 * @return The reference that matches the given string, or <code>null</code>
 * if it wasn't found.
 */
public static CharacterReference lookup (String kernel, int start, int end)
{
  CharacterReferenceEx probe;
  
  probe = new CharacterReferenceEx ();
  probe.setKernel (kernel);
  probe.setStart (start);
  probe.setEnd (end);
  return (lookup (probe));
}

/**
 * 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));
}

/**
 * Look up a reference by kernel.
 * Use a binary search on the ordered list of known references.
 * <em>This is not very efficient, use {@link org.htmlparser.util.Translate#lookup(org.htmlparser.util.CharacterReference) lookup(CharacterReference)}
 * instead.</em>
 * @param kernel The string to lookup, i.e. "amp".
 * @param start The starting point in the string of the kernel.
 * @param end The ending point in the string of the kernel.
 * This should be the index of the semicolon if it exists, or failing that,
 * at least an index past the last character of the kernel.
 * @return The reference that matches the given string, or <code>null</code>
 * if it wasn't found.
 */
public static CharacterReference lookup (String kernel, int start, int end)
{
  CharacterReferenceEx probe;
  
  probe = new CharacterReferenceEx ();
  probe.setKernel (kernel);
  probe.setStart (start);
  probe.setEnd (end);
  return (lookup (probe));
}

/**
 * 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));
}