1. /*

  2.  * @(#)CharacterBreakData.java	1.13 01/11/29

  3.  *

  4.  * Copyright 2002 Sun Microsystems, Inc. All rights reserved.

  5.  * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.

  6.  */

  7. 

  8. /*

  9.  * @(#)CharacterBreakData.java	1.13 01/11/29

  10.  *

  11.  * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved

  12.  * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved

  13.  *

  14.  * Portions copyright (c) 1996-1998 Sun Microsystems, Inc.

  15.  * All Rights Reserved.

  16.  *

  17.  * The original version of this source code and documentation

  18.  * is copyrighted and owned by Taligent, Inc., a wholly-owned

  19.  * subsidiary of IBM. These materials are provided under terms

  20.  * of a License Agreement between Taligent and Sun. This technology

  21.  * is protected by multiple US and International patents.

  22.  *

  23.  * This notice and attribution to Taligent may not be removed.

  24.  * Taligent is a registered trademark of Taligent, Inc.

  25.  *

  26.  * Permission to use, copy, modify, and distribute this software

  27.  * and its documentation for NON-COMMERCIAL purposes and without

  28.  * fee is hereby granted provided that this copyright notice

  29.  * appears in all copies. Please refer to the file "copyright.html"

  30.  * for further important copyright and licensing information.

  31.  *

  32.  * SUN MAKES NO REPRESENTATIONS OR WARRANTIES ABOUT THE SUITABILITY OF

  33.  * THE SOFTWARE, EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED

  34.  * TO THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A

  35.  * PARTICULAR PURPOSE, OR NON-INFRINGEMENT. SUN SHALL NOT BE LIABLE FOR

  36.  * ANY DAMAGES SUFFERED BY LICENSEE AS A RESULT OF USING, MODIFYING OR

  37.  * DISTRIBUTING THIS SOFTWARE OR ITS DERIVATIVES.

  38.  *

  39.  */

  40. 

  41. package java.text;

  42. 

  43. /**

  44.  * The CharacterBreakData contains data used by SimpleTextBoundary

  45.  * to determine character breaks.

  46.  * @see #BreakIterator

  47.  */

  48. final class CharacterBreakData extends TextBoundaryData

  49. {

  50.     private static final byte accent_diacritic = 0;

  51.     private static final byte baseForm = 1;

  52.     private static final byte baseCR = 2;

  53.     private static final byte baseLF = 3;

  54.     private static final byte choseong = 4;   // Korean initial consonant

  55.     private static final byte jungseong = 5;  // Korean vowel

  56.     private static final byte jongseong = 6;  // Korean final consonant

  57.     private static final byte EOS = 7;

  58.     private static final int COL_COUNT = 8;

  59. 

  60.     private static final byte SI = (byte)0x80;

  61.     private static final byte STOP = (byte) 0;

  62.     private static final byte SI_STOP = (byte)SI + STOP;

  63. 

  64.     public CharacterBreakData() {

  65.         super(kCharacterForwardTable, kCharacterBackwardTable, kCharacterMap);

  66.     }

  67. 

  68.     private static final byte kCharacterForwardData[] =

  69.     {

  70.         // acct        base             cr              lf

  71.         // cho         jung             jong            EOS

  72.         STOP,          STOP,            STOP,           STOP,

  73.         STOP,          STOP,            STOP,           STOP,

  74. 

  75.         // 1

  76.         (byte)(SI+2),  (byte)(SI+2),    (byte)(SI+3),   (byte)(SI+7),

  77.         (byte)(SI+4),  (byte)(SI+5),    (byte)(SI+6),   SI_STOP,

  78. 

  79.         // 2

  80.         (byte)(SI+2),  SI_STOP,         SI_STOP,        SI_STOP,

  81.         SI_STOP,       SI_STOP,         SI_STOP,        SI_STOP,

  82. 

  83.         // 3

  84.         SI_STOP,       SI_STOP,         SI_STOP,        (byte)(SI+7),

  85.         SI_STOP,       SI_STOP,         SI_STOP,        SI_STOP,

  86. 

  87.         // 4

  88.         (byte)(SI+2),  SI_STOP,         SI_STOP,        SI_STOP,

  89.         (byte)(SI+4),  (byte)(SI+5),    (byte)(SI+6),   SI_STOP,

  90. 

  91.         // 5

  92.         (byte)(SI+2),  SI_STOP,         SI_STOP,        SI_STOP,

  93.         SI_STOP,      (byte)(SI+5),    (byte)(SI+6),    SI_STOP,

  94. 

  95.         // 6

  96.         (byte)(SI+2),  SI_STOP,         SI_STOP,        SI_STOP,

  97.         SI_STOP,       SI_STOP,         (byte)(SI+6),   SI_STOP,

  98. 

  99.         // 7

  100.         SI_STOP,       SI_STOP,         SI_STOP,        SI_STOP,

  101.         SI_STOP,       SI_STOP,         SI_STOP,        SI_STOP

  102.     };

  103.     private static final WordBreakTable kCharacterForwardTable =

  104.     new WordBreakTable(COL_COUNT, kCharacterForwardData);

  105.     private static final byte kCharacterBackwardData[] =

  106.     {

  107.         // acct         base            cr              lf

  108.         // cho          jung            jong            EOS

  109.         STOP,           STOP,           STOP,           STOP,

  110.         STOP,           STOP,           STOP,           STOP,

  111. 

  112.         // 1

  113.         (byte)(SI+1),   SI_STOP,        SI_STOP,        (byte)(SI+1),

  114.         SI_STOP,        (byte)(SI+1),   (byte)(SI+1),   SI_STOP

  115.     };

  116. 

  117.     private static final WordBreakTable kCharacterBackwardTable =

  118.     new WordBreakTable(COL_COUNT, kCharacterBackwardData);

  119.     private static final int kRawMapping[] =

  120.     {

  121.         baseForm, //UNASSIGNED      = 0,

  122.         baseForm, //UPPERCASE_LETTER    = 1,

  123.         baseForm, //LOWERCASE_LETTER    = 2,

  124.         baseForm, //TITLECASE_LETTER    = 3,

  125.         baseForm, //MODIFIER_LETTER     = 4,

  126.         baseForm, //OTHER_LETTER        = 5,

  127.         accent_diacritic, //NON_SPACING_MARK    = 6,

  128.         accent_diacritic, //ENCLOSING_MARK      = 7,

  129.         baseForm, //COMBINING_SPACING_MARK  = 8,

  130.         baseForm, //DECIMAL_DIGIT_NUMBER    = 9,

  131.         baseForm, //LETTER_NUMBER       = 10,

  132.         baseForm, //OTHER_NUMBER        = 11,

  133.         baseForm, //SPACE_SEPARATOR     = 12,

  134.         baseForm, //LINE_SEPARATOR      = 13,

  135.         baseForm, //PARAGRAPH_SEPARATOR = 14,

  136.         baseForm, //CONTROL         = 15,

  137.         baseForm, //FORMAT      = 16,

  138.         baseForm, //????            = 17,

  139.         baseForm, //PRIVATE_USE     = 18,

  140.         baseForm, //SURROGATE        = 19,

  141.         baseForm, //DASH_PUNCTUATION    = 20,

  142.         baseForm, //START_PUNCTUATION    = 21,

  143.         baseForm, //END_PUNCTUATION     = 22,

  144.         baseForm, //CONNECTOR_PUNCTUATION   = 23,

  145.         baseForm, //OTHER_PUNCTUATION   = 24,

  146.         baseForm, //MATH_SYMBOL     = 25,

  147.         baseForm, //CURRENCY_SYMBOL     = 26,

  148.         baseForm, //MODIFIER_SYMBOL     = 27,

  149.         baseForm, //OTHER_SYMBOL        = 28;

  150.     };

  151. 

  152.     private static final SpecialMapping kExceptionChar[] = //{};

  153.     {

  154.         new SpecialMapping(ASCII_LINEFEED, baseLF),

  155.         new SpecialMapping(ASCII_CARRIAGE_RETURN, baseCR),

  156.         new SpecialMapping(HANGUL_CHOSEONG_LOW, HANGUL_CHOSEONG_HIGH, choseong),

  157.         new SpecialMapping(HANGUL_JUNGSEONG_LOW, HANGUL_JUNGSEONG_HIGH, jungseong),

  158.         new SpecialMapping(HANGUL_JONGSEONG_LOW, HANGUL_JONGSEONG_HIGH, jongseong),

  159.         new SpecialMapping(PUNCTUATION_LINE_SEPARATOR, PUNCTUATION_PARAGRAPH_SEPARATOR, baseLF),

  160.         new SpecialMapping(END_OF_STRING, EOS)

  161.     };

  162. 

  163.     private static final boolean CharacterExceptionFlags[] = {

  164.         false,          // kNonCharacter            = 0,

  165.         false,          // kUppercaseLetter         = 1,

  166.         false,          // kLowercaseLetter         = 2,

  167.         false,          // kTitlecaseLetter         = 3,

  168.         false,          // kModifierLetter          = 4,

  169.         true,           // kOtherLetter             = 5,

  170.         false,          // kNonSpacingMark          = 6,

  171.         false,          // kEnclosingMark           = 7,

  172.         false,          // kCombiningSpacingMark    = 8,

  173.         false,          // kDecimalNumber           = 9,

  174.         false,          // kLetterNumber            = 10,

  175.         false,          // kOtherNumber             = 11,

  176.         false,          // kSpaceSeparator          = 12,

  177.         true,           // kLineSeparator           = 13,

  178.         true,           // kParagraphSeparator      = 14,

  179.         true,           // kControlCharacter        = 15,

  180.         false,          // kFormatCharacter         = 16,

  181.         false,          // UNDEFINED                = 17,

  182.         false,          // kPrivateUseCharacter     = 18,

  183.         false,          // kSurrogate               = 19,

  184.         false,          // kDashPunctuation         = 20,

  185.         false,          // kOpenPunctuation         = 21,

  186.         false,          // kClosePunctuation        = 22,

  187.         false,          // kConnectorPunctuation    = 23,

  188.         false,          // kOtherPunctuation        = 24,

  189.         false,          // kMathSymbol              = 25,

  190.         false,          // kCurrencySymbol          = 26,

  191.         false,          // kModifierSymbol          = 27,

  192.         false           // kOtherSymbol             = 28

  193.     };

  194. 

  195.     private static final int kCharacterAsciiValues[] = {

  196.         //  null      soh       stx       etx       eot       enq       ask       bell

  197.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  198.         //  bs        ht        lf      vt        ff        cr      so        si

  199.             baseForm, baseForm, baseLF, baseForm, baseForm, baseCR, baseForm, baseForm,

  200.         //  dle       dc1       dc2       dc3       dc4       nak       syn       etb

  201.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  202.         //  can       em        sub       esc       fs        gs        rs        us

  203.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  204.         //  sp        !         "         #         $         %         &         '

  205.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  206.         //  (         )         *         +         ,         -         .         /

  207.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  208.         //  0         1         2         3         4         5         6         7

  209.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  210.         //  8         9         :         ;         <         =         >         ?

  211.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  212.         //  @         A         B         C         D         E         F         G

  213.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  214.         //  H         I         J         K         L         M         N         O

  215.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  216.         //  P         Q         R         S         T         U         V         W

  217.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  218.         //  X         Y         Z         [         \         ]         ^         _

  219.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  220.         //  `         a         b         c         d         e         f         g

  221.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  222.         //  h         i         j         k         l         m         n         o

  223.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  224.         //  p         q         r         s         t         u         v         w

  225.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  226.         //  x         y         z         {         |         }         ~         del

  227.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  228.         //  ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl

  229.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  230.         //  ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl

  231.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  232.         //  ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl

  233.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  234.         //  ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl      ctrl

  235.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  236.         //  nbsp      inv-!     cents     pounds    currency  yen       broken-bar  section

  237.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  238.         //  umlaut    copyright super-a   gui-left  not       soft-hyph registered  macron

  239.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  240.         //  degree    +/-       super-2   super-3   acute     micro     paragraph  bullet

  241.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  242.         //  cedilla   super-1   super-o   gui-right 1/4       1/2       3/4      inv-?

  243.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  244.         //  A-grave   A-acute   A-hat     A-tilde   A-umlaut A-ring    AE        C-cedilla

  245.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  246.         //  E-grave   E-acute   E-hat     E-umlaut  I-grave   I-acute   I-hat    I-umlaut

  247.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  248.         //  Edh       N-tilde   O-grave   O-acute   O-hat     O-tilde   O-umlaut times

  249.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  250.         //  O-slash   U-grave   U-acute   U-hat     U-umlaut  Y-acute   Thorn    ess-zed

  251.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  252.         //  a-grave   a-acute   a-hat     a-tilde   a-umlaut  a-ring    ae       c-cedilla

  253.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  254.         //  e-grave   e-acute   e-hat     e-umlaut  i-grave   i-acute   i-hat    i-umlaut

  255.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  256.         //  edh       n-tilde   o-grave   o-acute   o-hat     o-tilde   o-umlaut  over

  257.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm,

  258.         //  o-slash   u-grave   u-acute   u-hat     u-umlaut  y-acute   thorn    y-umlaut

  259.             baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm, baseForm

  260.     };

  261. 

  262.     private static final UnicodeClassMapping kCharacterMap

  263.         = new UnicodeClassMapping(kRawMapping, kExceptionChar, CharacterExceptionFlags,

  264.         kCharacterAsciiValues);

  265. }

  266.