Return the Unicode char which is coded in the bytes at position 0. : Unicode « Development « Java Tutorial






import java.io.File;
import java.io.FileFilter;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;

/*
 *  Licensed to the Apache Software Foundation (ASF) under one
 *  or more contributor license agreements.  See the NOTICE file
 *  distributed with this work for additional information
 *  regarding copyright ownership.  The ASF licenses this file
 *  to you under the Apache License, Version 2.0 (the
 *  "License"); you may not use this file except in compliance
 *  with the License.  You may obtain a copy of the License at
 *  
 *    http://www.apache.org/licenses/LICENSE-2.0
 *  
 *  Unless required by applicable law or agreed to in writing,
 *  software distributed under the License is distributed on an
 *  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 *  KIND, either express or implied.  See the License for the
 *  specific language governing permissions and limitations
 *  under the License. 
 *  
 */



/**
 * Various string manipulation methods that are more efficient then chaining
 * string operations: all is done in the same buffer without creating a bunch of
 * string objects.
 * 
 * @author <a href="mailto:dev@labs.apache.org">Dungeon Project</a>
 */
public class Main {
  private static final int UTF8_MULTI_BYTES_MASK = 0x0080;

  private static final int UTF8_TWO_BYTES_MASK = 0x00E0;

  private static final int UTF8_TWO_BYTES = 0x00C0;

  private static final int UTF8_THREE_BYTES_MASK = 0x00F0;

  private static final int UTF8_THREE_BYTES = 0x00E0;

  private static final int UTF8_FOUR_BYTES_MASK = 0x00F8;

  private static final int UTF8_FOUR_BYTES = 0x00F0;

  private static final int UTF8_FIVE_BYTES_MASK = 0x00FC;

  private static final int UTF8_FIVE_BYTES = 0x00F8;

  private static final int UTF8_SIX_BYTES_MASK = 0x00FE;

  private static final int UTF8_SIX_BYTES = 0x00FC;
  /**
   * Return the Unicode char which is coded in the bytes at position 0.
   * 
   * @param bytes
   *            The byte[] represntation of an Unicode string.
   * @return The first char found.
   */
  public static final char bytesToChar( byte[] bytes )
  {
      return bytesToChar( bytes, 0 );
  }

  /**
   * Return the Unicode char which is coded in the bytes at the given
   * position.
   * 
   * @param bytes
   *            The byte[] represntation of an Unicode string.
   * @param pos
   *            The current position to start decoding the char
   * @return The decoded char, or -1 if no char can be decoded TODO : Should
   *         stop after the third byte, as a char is only 2 bytes long.
   */
  public static final char bytesToChar( byte[] bytes, int pos )
  {
      if ( bytes == null )
      {
          return ( char ) -1;
      }

      if ( ( bytes[pos] & UTF8_MULTI_BYTES_MASK ) == 0 )
      {
          return ( char ) bytes[pos];
      }
      else
      {
          if ( ( bytes[pos] & UTF8_TWO_BYTES_MASK ) == UTF8_TWO_BYTES )
          {
              // Two bytes char
              return ( char ) ( ( ( bytes[pos] & 0x1C ) << 6 ) + // 110x-xxyy
                                                                  // 10zz-zzzz
                                                                  // ->
                                                                  // 0000-0xxx
                                                                  // 0000-0000
                  ( ( bytes[pos] & 0x03 ) << 6 ) + // 110x-xxyy 10zz-zzzz
                                                      // -> 0000-0000
                                                      // yy00-0000
              ( bytes[pos + 1] & 0x3F ) // 110x-xxyy 10zz-zzzz -> 0000-0000
                                          // 00zz-zzzz
              ); // -> 0000-0xxx yyzz-zzzz (07FF)
          }
          else if ( ( bytes[pos] & UTF8_THREE_BYTES_MASK ) == UTF8_THREE_BYTES )
          {
              // Three bytes char
              return ( char ) (
              // 1110-tttt 10xx-xxyy 10zz-zzzz -> tttt-0000-0000-0000
              ( ( bytes[pos] & 0x0F ) << 12 ) +
              // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-xxxx-0000-0000
                  ( ( bytes[pos + 1] & 0x3C ) << 6 ) +
                  // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-0000-yy00-0000
                  ( ( bytes[pos + 1] & 0x03 ) << 6 ) +
              // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-0000-00zz-zzzz
              ( bytes[pos + 2] & 0x3F )
              // -> tttt-xxxx yyzz-zzzz (FF FF)
              );
          }
          else if ( ( bytes[pos] & UTF8_FOUR_BYTES_MASK ) == UTF8_FOUR_BYTES )
          {
              // Four bytes char
              return ( char ) (
              // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 000t-tt00
              // 0000-0000 0000-0000
              ( ( bytes[pos] & 0x07 ) << 18 ) +
              // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-00uu
              // 0000-0000 0000-0000
                  ( ( bytes[pos + 1] & 0x30 ) << 16 ) +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // vvvv-0000 0000-0000
                  ( ( bytes[pos + 1] & 0x0F ) << 12 ) +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // 0000-xxxx 0000-0000
                  ( ( bytes[pos + 2] & 0x3C ) << 6 ) +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // 0000-0000 yy00-0000
                  ( ( bytes[pos + 2] & 0x03 ) << 6 ) +
              // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
              // 0000-0000 00zz-zzzz
              ( bytes[pos + 3] & 0x3F )
              // -> 000t-ttuu vvvv-xxxx yyzz-zzzz (1FFFFF)
              );
          }
          else if ( ( bytes[pos] & UTF8_FIVE_BYTES_MASK ) == UTF8_FIVE_BYTES )
          {
              // Five bytes char
              return ( char ) (
              // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
              // 0000-00tt 0000-0000 0000-0000 0000-0000
              ( ( bytes[pos] & 0x03 ) << 24 ) +
              // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
              // 0000-0000 uuuu-uu00 0000-0000 0000-0000
                  ( ( bytes[pos + 1] & 0x3F ) << 18 ) +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-00vv 0000-0000 0000-0000
                  ( ( bytes[pos + 2] & 0x30 ) << 12 ) +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 wwww-0000 0000-0000
                  ( ( bytes[pos + 2] & 0x0F ) << 12 ) +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-xxxx 0000-0000
                  ( ( bytes[pos + 3] & 0x3C ) << 6 ) +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-0000 yy00-0000
                  ( ( bytes[pos + 3] & 0x03 ) << 6 ) +
              // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
              // 0000-0000 0000-0000 0000-0000 00zz-zzzz
              ( bytes[pos + 4] & 0x3F )
              // -> 0000-00tt uuuu-uuvv wwww-xxxx yyzz-zzzz (03 FF FF FF)
              );
          }
          else if ( ( bytes[pos] & UTF8_FIVE_BYTES_MASK ) == UTF8_FIVE_BYTES )
          {
              // Six bytes char
              return ( char ) (
              // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz
              // ->
              // 0s00-0000 0000-0000 0000-0000 0000-0000
              ( ( bytes[pos] & 0x01 ) << 30 ) +
              // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz
              // ->
                  // 00tt-tttt 0000-0000 0000-0000 0000-0000
                  ( ( bytes[pos + 1] & 0x3F ) << 24 ) +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 uuuu-uu00 0000-0000 0000-0000
                  ( ( bytes[pos + 2] & 0x3F ) << 18 ) +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-00vv 0000-0000 0000-0000
                  ( ( bytes[pos + 3] & 0x30 ) << 12 ) +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 wwww-0000 0000-0000
                  ( ( bytes[pos + 3] & 0x0F ) << 12 ) +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-xxxx 0000-0000
                  ( ( bytes[pos + 4] & 0x3C ) << 6 ) +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-0000 yy00-0000
                  ( ( bytes[pos + 4] & 0x03 ) << 6 ) +
              // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz
              // ->
              // 0000-0000 0000-0000 0000-0000 00zz-zzzz
              ( bytes[pos + 5] & 0x3F )
              // -> 0stt-tttt uuuu-uuvv wwww-xxxx yyzz-zzzz (7F FF FF FF)
              );
          }
          else
          {
              return ( char ) -1;
          }
      }
  }
}








6.16.Unicode
6.16.1.Using Unicode in String
6.16.2.Display special character using Unicode
6.16.3.Convert from Unicode to UTF-8
6.16.4.Convert from UTF-8 to Unicode
6.16.5.Convert string to UTF8 bytes
6.16.6.Converts Unicode into something that can be embedded in a java properties file
6.16.7.Converts the string to the unicode format
6.16.8.Return an UTF-8 encoded String
6.16.9.Return an UTF-8 encoded String by length
6.16.10.Return UTF-8 encoded byte[] representation of a String
6.16.11.Get UTF String Size
6.16.12.Return the number of bytes that hold an Unicode char.
6.16.13.Return the Unicode char which is coded in the bytes at position 0.
6.16.14.Return the Unicode char which is coded in the bytes at the given position.
6.16.15.Checks if the String contains only unicode digits or space
6.16.16.Checks if the String contains only unicode digits. A decimal point is not a unicode digit and returns false.
6.16.17.Checks if the String contains only unicode letters and space (' ').
6.16.18.Checks if the String contains only unicode letters or digits.
6.16.19.Checks if the String contains only unicode letters, digits or space (' ').
6.16.20.Checks if the String contains only unicode letters.
6.16.21.Count the number of bytes included in the given char[].
6.16.22.Count the number of bytes needed to return an Unicode char. This can be from 1 to 6.
6.16.23.Count the number of chars included in the given byte[].
6.16.24.Decodes values of attributes in the DN encoded in hex into a UTF-8 String.
6.16.25.Safe UTF: 64K serialized size