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

1. Java Tutorial
2. Development
3. Unicode

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 CHAR_ONE_BYTE_MASK = 0xFFFFFF80;

  private static final int CHAR_TWO_BYTES_MASK = 0xFFFFF800;

  private static final int CHAR_THREE_BYTES_MASK = 0xFFFF0000;

  private static final int CHAR_FOUR_BYTES_MASK = 0xFFE00000;

  private static final int CHAR_FIVE_BYTES_MASK = 0xFC000000;

  private static final int CHAR_SIX_BYTES_MASK = 0x80000000;
  
  /**
   * Return the Unicode char which is coded in the bytes at the given
   * position.
   * 
   * @param car The character to be transformed to an array of bytes
   * 
   * @return The byte array representing the char 
   * 
   * TODO : Should stop after the third byte, as a char is only 2 bytes long.
   */
  public static final byte[] charToBytes( char car )
  {
      byte[] bytes = new byte[countNbBytesPerChar( car )];

      if ( ( car | 0x7F ) == 0x7F )
      {
          // Single byte char
          bytes[0] = ( byte ) car;
          return bytes;
      }
      else if ( ( car | 0x7F) == 0x7FF )
      {
          // two bytes char
          bytes[0] = ( byte ) ( 0x00C0 + ( ( car & 0x07C0 ) >> 6 ) );
          bytes[1] = ( byte ) ( 0x0080 + ( car & 0x3F ) );
      }
      else
      {
          // Three bytes char
          bytes[0] = ( byte ) ( 0x00E0 + ( ( car & 0xF000 ) >> 12 ) );
          bytes[1] = ( byte ) ( 0x0080 + ( ( car & 0x0FC0 ) >> 6 ) );
          bytes[2] = ( byte ) ( 0x0080 + ( car & 0x3F ) );
      }

      return bytes;
  }
  
  
  /**
   * Return the number of bytes that hold an Unicode char.
   * 
   * @param car
   *            The character to be decoded
   * @return The number of bytes to hold the char. TODO : Should stop after
   *         the third byte, as a char is only 2 bytes long.
   */
  public static final int countNbBytesPerChar( char car )
  {
      if ( ( car & CHAR_ONE_BYTE_MASK ) == 0 )
      {
          return 1;
      }
      else if ( ( car & CHAR_TWO_BYTES_MASK ) == 0 )
      {
          return 2;
      }
      else if ( ( car & CHAR_THREE_BYTES_MASK ) == 0 )
      {
          return 3;
      }
      else if ( ( car & CHAR_FOUR_BYTES_MASK ) == 0 )
      {
          return 4;
      }
      else if ( ( car & CHAR_FIVE_BYTES_MASK ) == 0 )
      {
          return 5;
      }
      else if ( ( car & CHAR_SIX_BYTES_MASK ) == 0 )
      {
          return 6;
      }
      else
      {
          return -1;
      }
  }
}