fscharactertable.java

利用opensource的开源jar实现生成flash文件

/*
 *  FSCharacterTable.java
 *  Transform Utilities
 *
 * Copyright (c) 2001-2006 Flagstone Software Ltd. All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modification, 
 * are permitted provided that the following conditions are met:
 *
 *  * Redistributions of source code must retain the above copyright notice, this
 *    list of conditions and the following disclaimer.
 *  * Redistributions in binary form must reproduce the above copyright notice, 
 *    this list of conditions and the following disclaimer in the documentation 
 *    and/or other materials provided with the distribution.
 *  * Neither the name of Flagstone Software Ltd. nor the names of its contributors 
 *    may be used to endorse or promote products derived from this software 
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED 
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. 
 * IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, 
 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 
 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE 
 * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED 
 * OF THE POSSIBILITY OF SUCH DAMAGE.
 */
package com.flagstone.transform.util;

import java.util.Locale;

/**
 * The FSCharacterTable class provides predefined arrays of characters that can
 * be used with the FSTextConstructor's willDisplay() method to predefine the 
 * characters that will be displayed using a given font.
 * 
 * Character sets are simply list of characters to use. The names used to 
 * identify collections of characters use official character set names, such
 * as iso_8859_1. However they do NOT indicate how the characters are encoded
 * as such (all strings are encoded using UTF-8) they are simply a way of 
 * naming a group of characters in a recognized (and standard) way.
 * 
 * Other sets that use characters appropriate for a specific country and 
 * language also use ISO designations for a specific locale such as en_US
 * or pt_BR.
 *
 */
public class FSCharacterTable 
{
    /*
     * List of character sets supported. 
     */
    
    /**
     * Code identifying a set containing the single character for the euro
     * currency symbol. It is included as a separate set as manly formal 
     * coded character sets do not include it. A separate set makes it easier
     * to match different sets of characters together.
     * 
     * The (Unicode) character code for this symbol is 0x20AC so it will
     * typically be the last character set passed to the FSTextConstructor's
     * willDisplay() method.
     */
    public static final int euro = 0;
    /**
     * Code identifying formal the characters defined in ISO 646.
     * 
     * Alias: ASCII
     */
    public static final int iso_646 = 1;
    /**
     * Code identifying formal the characters defined in ISO-8859-1.
     * 
     * Alias: Latin-1
     */
    public static final int iso_8859_1 = 2;
    
    /*
     * The ISO 646 character set is used as a base for other characters sets.
     * Other character sets are created by including these characters in the 
     * array returned by the characterSetWithCode() method. This saves space
     * and more importantly makes it easier to correct errors.
     */
    private final static char[] iso_646_chars = {
        '\u0020', // space
        '\u0021', // exclamation mark
        '\u0022', // quotation mark
        '\u0023', // number sign
        '\u0024', // dollar sign
        '\u0025', // percent sign
        '\u0026', // ampersand
        '\'',     // apostrophe
        '\u0028', // left parenthesis
        '\u0029', // right parenthesis
        '\u002A', // asterisk
        '\u002B', // plus sign
        '\u002C', // comma
        '\u002D', // hyphen or minus
        '\u002E', // full stop
        '\u002F', // forward slash
        '\u0030', // digit zero
        '\u0031', // digit one
        '\u0032', // digit two
        '\u0033', // digit three
        '\u0034', // digit four
        '\u0035', // digit five
        '\u0036', // digit six
        '\u0037', // digit seven
        '\u0038', // digit eight
        '\u0039', // digit nine
        '\u003A', // colon
        '\u003B', // semicolon
        '\u003C', // less than sign
        '\u003D', // equals sign
        '\u003E', // greater than sign
        '\u003F', // question mark
        '\u0040', // commercial at
        '\u0041', // upper case A
        '\u0042', // upper case B
        '\u0043', // upper case C
        '\u0044', // upper case D
        '\u0045', // upper case E
        '\u0046', // upper case F
        '\u0047', // upper case G
        '\u0048', // upper case H
        '\u0049', // upper case I
        '\u004A', // upper case J
        '\u004B', // upper case K
        '\u004C', // upper case L
        '\u004D', // upper case M
        '\u004E', // upper case N
        '\u004F', // upper case O
        '\u0050', // upper case P
        '\u0051', // upper case Q
        '\u0052', // upper case R
        '\u0053', // upper case S
        '\u0054', // upper case T
        '\u0055', // upper case U
        '\u0056', // upper case V
        '\u0057', // upper case W
        '\u0058', // upper case X
        '\u0059', // upper case Y
        '\u005A', // upper case Z
        '\u005B', // left square bracket
        '\\',     // backslash
        '\u005D', // right square bracket
        '\u005E', // circumflex
        '\u005F', // underscore
        '\u0060', // grave
        '\u0061', // lower case A
        '\u0062', // lower case B
        '\u0063', // lower case C
        '\u0064', // lower case D
        '\u0065', // lower case E
        '\u0066', // lower case F
        '\u0067', // lower case G
        '\u0068', // lower case H
        '\u0069', // lower case I
        '\u006A', // lower case J
        '\u006B', // lower case K
        '\u006C', // lower case L
        '\u006D', // lower case M
        '\u006E', // lower case N
        '\u006F', // lower case O
        '\u0070', // lower case P
        '\u0071', // lower case Q
        '\u0072', // lower case R
        '\u0073', // lower case S
        '\u0074', // lower case T
        '\u0075', // lower case U
        '\u0076', // lower case V
        '\u0077', // lower case W
        '\u0078', // lower case X
        '\u0079', // lower case Y
        '\u007A', // lower case Z
        '\u007B', // left curly bracket
        '\u007C', // vertical line
        '\u007D', // right curly bracket
        '\u007E', // tilde
    };
    
    private static final char[] iso_8859_1_chars = new char[] {
        '\u00A0', // non-breaking space
        '\u00A1', // inverted exclamation mark
        '\u00A2', // cent sign
        '\u00A3', // pound sign
        '\u00A4', // currency sign
        '\u00A5', // yen sign
        '\u00A6', // broken BAR
        '\u00A7', // section sign
        '\u00A8', // diaresis
        '\u00A9', // copyright sign
        '\u00AA', // feminine ordinal indicator
        '\u00AB', // left pointing double angle quotation mark
        '\u00AC', // not sign
        '\u00AD', // soft hyphen
        '\u00AE', // registered trademark sign
        '\u00AF', // macron
        '\u00B0', // degree sign
        '\u00B1', // plus-minus sign
        '\u00B2', // superscript two
        '\u00B3', // superscript three
        '\u00B4', // acute accent
        '\u00B5', // micro sign
        '\u00B6', // pilcrow sign
        '\u00B7', // middle dot
        '\u00B8', // cedilla
        '\u00B9', // superscript ONE
        '\u00BA', // masculine ordinal indicator
        '\u00BB', // right pointing double angle quotation mark
        '\u00BC', // vulgar fraction one quarter
        '\u00BD', // vulgar fraction one half
        '\u00BE', // vulgar fraction three quarters
        '\u00BF', // inverted question mark
        '\u00C0', // upper case letter A with grave
        '\u00C1', // upper case letter A with acute
        '\u00C2', // upper case letter A with circumflex
        '\u00C3', // upper case letter A with tilde
        '\u00C4', // upper case letter A with diaresis
        '\u00C5', // upper case letter A with ring above
        '\u00C6', // upper case letter AE
        '\u00C7', // upper case letter C with cedilla
        '\u00C8', // upper case letter E with grave
        '\u00C9', // upper case letter E with acute
        '\u00CA', // upper case letter E with circumflex
        '\u00CB', // upper case letter E with diaresis
        '\u00CC', // upper case letter I with grave
        '\u00CD', // upper case letter I with acute
        '\u00CE', // upper case letter I with circumflex
        '\u00CF', // upper case letter I with diaresis
        '\u00D0', // upper case letter Eth (Icelandic)
        '\u00D1', // upper case letter N with tilde
        '\u00D2', // upper case letter O with grave
        '\u00D3', // upper case letter O with acute
        '\u00D4', // upper case letter O with circumflex
        '\u00D5', // upper case letter O with tilde
        '\u00D6', // upper case letter O with diaresis
        '\u00D7', // multiplication sign
        '\u00D8', // upper case letter O with stroke
        '\u00D9', // upper case letter U with grave
        '\u00DA', // upper case letter U with acute
        '\u00DB', // upper case letter U with circumflex
        '\u00DC', // upper case letter U with diaresis
        '\u00DD', // upper case letter Y with acute
        '\u00DE', // upper case letter Thorn (Icelandic)
        '\u00DF', // lower case letter Sharp S (German)
        '\u00E0', // lower case letter A with grave
        '\u00E1', // lower case letter A with acute
        '\u00E2', // lower case letter A with circumflex
        '\u00E3', // lower case letter A with tilde
        '\u00E4', // lower case letter A with diaresis
        '\u00E5', // lower case letter A with ring above
        '\u00E6', // lower case letter AE
        '\u00E7', // lower case letter C with cedilla
        '\u00E8', // lower case letter E with grave
        '\u00E9', // lower case letter E with acute
        '\u00EA', // lower case letter E with circumflex
        '\u00EB', // lower case letter E with diaresis
        '\u00EC', // lower case letter I with grave
        '\u00ED', // lower case letter I with acute
        '\u00EE', // lower case letter I with circumflex
        '\u00EF', // lower case letter I with diaresis
        '\u00F0', // lower case letter Eth (Icelandic)
        '\u00F1', // lower case letter N with tilde
        '\u00F2', // lower case letter O with grave
        '\u00F3', // lower case letter O with acute
        '\u00F4', // lower case letter O with circumflex
        '\u00F5', // lower case letter O with tilde
        '\u00F6', // lower case letter O with diaresis
        '\u00F7', // division sign
        '\u00F8', // lower case letter O with stroke
        '\u00F9', // lower case letter U with grave
        '\u00FA', // lower case letter U with acute
        '\u00FB', // lower case letter U with circumflex
        '\u00FC', // lower case letter U with diaresis
        '\u00FD', // lower case letter Y with acute
        '\u00FE', // lower case letter Thorn (Icelandic)
        '\u00FF', // lower case letter Y with diaresis
    };

    private final static char[] euroChar = { 
        '\u20AC', // Euro currency symbol
    };
    
    private final static char[] de_DE = {
        '\u00A2', // cent sign
        '\u00C1', // upper case letter A with acute
        '\u00D6', // upper case letter O with diaresis
        '\u00DC', // upper case letter U with diaresis
        '\u00DF', // lower case letter Sharp S (German)
        '\u00E1', // lower case letter A with acute
        '\u00F6', // lower case letter O with diaresis
        '\u00FC', // lower case letter U with diaresis
        '\u20AC', // Euro currency symbol
    };

    private final static char[] dk_DK = {
        '\u00C5', // upper case letter A with ring above
        '\u00C6', // upper case letter AE
        '\u00D8', // upper case letter O with stroke
        '\u00E5', // lower case letter A with ring above
        '\u00E6', // lower case letter AE
        '\u00F8', // lower case letter O with stroke
    };

    private final static char[] en_GB = {
        '\u00A2', // cent sign
        '\u00A3', // pound sign
        '\u20AC', // Euro currency symbol
    };

    private final static char[] en_US = {
    };
    
    private final static char[] es_ES = {
        '\u00A2', // cent sign
        '\u00C1', // upper case letter A with acute
        '\u00C9', // upper case letter E with acute
        '\u00CD', // upper case letter I with acute
        '\u00D1', // upper case letter N with tilde
        '\u00D3', // upper case letter O with acute
        '\u00DA', // upper case letter U with acute
        '\u00DC', // upper case letter U with diaresis
        '\u00E1', // lower case letter A with acute
        '\u00E9', // lower case letter E with acute
        '\u00ED', // lower case letter I with acute
        '\u00F1', // lower case letter N with tilde
        '\u00F3', // lower case letter O with acute
        '\u00FA', // lower case letter U with acute
        '\u00FC', // lower case letter U with diaresis
        '\u20AC', // Euro currency symbol