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

Java
1. 2D Graphics GUI
2. 3D
3. Advanced Graphics
4. Ant
5. Apache Common
6. Chart
7. Class
8. Collections Data Structure
9. Data Type
10. Database SQL JDBC
11. Design Pattern
12. Development Class
13. EJB3
14. Email
15. Event
16. File Input Output
17. Game
18. Generics
19. GWT
20. Hibernate
21. I18N
22. J2EE
23. J2ME
24. JDK 6
25. JNDI LDAP
26. JPA
27. JSP
28. JSTL
29. Language Basics
30. Network Protocol
31. PDF RTF
32. Reflection
33. Regular Expressions
34. Scripting
35. Security
36. Servlets
37. Spring
38. Swing Components
39. Swing JFC
40. SWT JFace Eclipse
41. Threads
42. Tiny Application
43. Velocity
44. Web Services SOA
45. XML
Java Tutorial
Java Source Code / Java Documentation
Java Open Source
Jar File Download
Java Articles
Java Products
Java by API
Photoshop Tutorials
Maya Tutorials
Flash Tutorials
3ds-Max Tutorials
Illustrator Tutorials
GIMP Tutorials
C# / C Sharp
C# / CSharp Tutorial
C# / CSharp Open Source
ASP.Net
ASP.NET Tutorial
JavaScript DHTML
JavaScript Tutorial
JavaScript Reference
HTML / CSS
HTML CSS Reference
C / ANSI-C
C Tutorial
C++
C++ Tutorial
Ruby
PHP
Python
Python Tutorial
Python Open Source
SQL Server / T-SQL
SQL Server / T-SQL Tutorial
Oracle PL / SQL
Oracle PL/SQL Tutorial
PostgreSQL
SQL / MySQL
MySQL Tutorial
VB.Net
VB.Net Tutorial
Flash / Flex / ActionScript
VBA / Excel / Access / Word
XML
XML Tutorial
Microsoft Office PowerPoint 2007 Tutorial
Microsoft Office Excel 2007 Tutorial
Microsoft Office Word 2007 Tutorial
Java » Development Class » Code UnicodeScreenshots 
Return the Unicode char which is coded in the bytes at position 0.
    
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 bytesToCharbyte[] bytes )
  {
      return bytesToCharbytes, );
  }

  /**
   * 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 bytesToCharbyte[] bytes, int pos )
  {
      if bytes == null )
      {
          return char -1;
      }

      if ( ( bytes[pos& UTF8_MULTI_BYTES_MASK == )
      {
          return char bytes[pos];
      }
      else
      {
          if ( ( bytes[pos& UTF8_TWO_BYTES_MASK == UTF8_TWO_BYTES )
          {
              // Two bytes char
              return char ) ( ( ( bytes[pos0x1C << // 110x-xxyy
                                                                  // 10zz-zzzz
                                                                  // ->
                                                                  // 0000-0xxx
                                                                  // 0000-0000
                  ( ( bytes[pos0x03 << // 110x-xxyy 10zz-zzzz
                                                      // -> 0000-0000
                                                      // yy00-0000
              bytes[pos + 10x3F // 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[pos0x0F << 12 +
              // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-xxxx-0000-0000
                  ( ( bytes[pos + 10x3C << +
                  // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-0000-yy00-0000
                  ( ( bytes[pos + 10x03 << +
              // 1110-tttt 10xx-xxyy 10zz-zzzz -> 0000-0000-00zz-zzzz
              bytes[pos + 20x3F )
              // -> 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[pos0x07 << 18 +
              // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-00uu
              // 0000-0000 0000-0000
                  ( ( bytes[pos + 10x30 << 16 +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // vvvv-0000 0000-0000
                  ( ( bytes[pos + 10x0F << 12 +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // 0000-xxxx 0000-0000
                  ( ( bytes[pos + 20x3C << +
                  // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
                  // 0000-0000 yy00-0000
                  ( ( bytes[pos + 20x03 << +
              // 1111-0ttt 10uu-vvvv 10xx-xxyy 10zz-zzzz -> 0000-0000
              // 0000-0000 00zz-zzzz
              bytes[pos + 30x3F )
              // -> 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[pos0x03 << 24 +
              // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
              // 0000-0000 uuuu-uu00 0000-0000 0000-0000
                  ( ( bytes[pos + 10x3F << 18 +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-00vv 0000-0000 0000-0000
                  ( ( bytes[pos + 20x30 << 12 +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 wwww-0000 0000-0000
                  ( ( bytes[pos + 20x0F << 12 +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-xxxx 0000-0000
                  ( ( bytes[pos + 30x3C << +
                  // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-0000 yy00-0000
                  ( ( bytes[pos + 30x03 << +
              // 1111-10tt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz ->
              // 0000-0000 0000-0000 0000-0000 00zz-zzzz
              bytes[pos + 40x3F )
              // -> 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[pos0x01 << 30 +
              // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz
              // ->
                  // 00tt-tttt 0000-0000 0000-0000 0000-0000
                  ( ( bytes[pos + 10x3F << 24 +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 uuuu-uu00 0000-0000 0000-0000
                  ( ( bytes[pos + 20x3F << 18 +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-00vv 0000-0000 0000-0000
                  ( ( bytes[pos + 30x30 << 12 +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 wwww-0000 0000-0000
                  ( ( bytes[pos + 30x0F << 12 +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-xxxx 0000-0000
                  ( ( bytes[pos + 40x3C << +
                  // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy
                  // 10zz-zzzz ->
                  // 0000-0000 0000-0000 0000-0000 yy00-0000
                  ( ( bytes[pos + 40x03 << +
              // 1111-110s 10tt-tttt 10uu-uuuu 10vv-wwww 10xx-xxyy 10zz-zzzz
              // ->
              // 0000-0000 0000-0000 0000-0000 00zz-zzzz
              bytes[pos + 50x3F )
              // -> 0stt-tttt uuuu-uuvv wwww-xxxx yyzz-zzzz (7F FF FF FF)
              );
          }
          else
          {
              return char -1;
          }
      }
  }
}

   
    
    
    
  
Related examples in the same category
1. Unicode sortingUnicode sorting
2. Unicode: Fonts and Text RenderingUnicode: Fonts and Text Rendering
3. Unicode: TrueType Font TestUnicode: TrueType Font Test
4. Unicode: test layoutUnicode: test layout
5. Conversion between Unicode characters and StringsConversion between Unicode characters and Strings
6. Convert among Unicode, ASCII and byte/intConvert among Unicode, ASCII and byte/int
7. Unicode - show a page of Unicode characters
8. Return the Unicode char which is coded in the bytes at the given position.
9. Vis - make special characters visible
10. Demonstrate creating readers and writers with a specific encoding
11. TextArea with UnicodeTextArea with Unicode
12. Unicode displayUnicode display
13. Check if the current character is an 7 bits ASCII CHAR (between 0 and 127). <char> ::= <alpha> | <digit> | '-'
14. Internationalized Graphical User Interfaces: unicode cut and pasteInternationalized Graphical User Interfaces: unicode cut and paste
15. Unicode to ascii
16. Count the number of bytes needed to return an Unicode char. This can be from 1 to 6.
17. Return the number of bytes that hold an Unicode char.
18. An optimized reader for reading byte streams that only contain 7-bit ASCII characters.
19. Stream Converter UnicodeStream Converter Unicode
20. String Converter UnicodeString Converter Unicode
21. Checks if the String contains only unicode digits or space
22. Checks if the String contains only unicode digits. A decimal point is not a unicode digit and returns false.
23. Checks if the String contains only unicode letters and space (' ').
24. Checks if the String contains only unicode letters or digits.
25. Checks if the String contains only unicode letters, digits or space (' ').
26. Checks if the String contains only unicode letters.
27. Unicode Util
28. Unicode reader
29. Get UTF String Size
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.