libjava/gnu/java/text/CharacterBreakIterator.java

   1 /* CharacterBreakIterator.java - Default character BreakIterator.
   2    Copyright (C) 1999, 2001 Free Software Foundation, Inc.
   3
   4 This file is part of GNU Classpath.
   5
   6 GNU Classpath is free software; you can redistribute it and/or modify
   7 it under the terms of the GNU General Public License as published by
   8 the Free Software Foundation; either version 2, or (at your option)
   9 any later version.
  10
  11 GNU Classpath is distributed in the hope that it will be useful, but
  12 WITHOUT ANY WARRANTY; without even the implied warranty of
  13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14 General Public License for more details.
  15
  16 You should have received a copy of the GNU General Public License
  17 along with GNU Classpath; see the file COPYING.  If not, write to the
  18 Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
  19 02111-1307 USA.
  20
  21 Linking this library statically or dynamically with other modules is
  22 making a combined work based on this library.  Thus, the terms and
  23 conditions of the GNU General Public License cover the whole
  24 combination.
  25
  26 As a special exception, the copyright holders of this library give you
  27 permission to link this library with independent modules to produce an
  28 executable, regardless of the license terms of these independent
  29 modules, and to copy and distribute the resulting executable under
  30 terms of your choice, provided that you also meet, for each linked
  31 independent module, the terms and conditions of the license of that
  32 module.  An independent module is a module which is not derived from
  33 or based on this library.  If you modify this library, you may extend
  34 this exception to your version of the library, but you are not
  35 obligated to do so.  If you do not wish to do so, delete this
  36 exception statement from your version. */
  37
  38
  39 package gnu.java.text;
  40
  41 import java.text.BreakIterator;
  42 import java.text.CharacterIterator;
  43
  44 /**
  45  * @author Tom Tromey <tromey@cygnus.com>
  46  * @date March 19, 1999
  47  * Written using The Unicode Standard, Version 2.0.
  48  */
  49
  50 public class CharacterBreakIterator extends BaseBreakIterator
  51 {
  52   // Hangul Jamo constants from Unicode book.
  53   private static final int LBase = 0x1100;
  54   private static final int VBase = 0x1161;
  55   private static final int TBase = 0x11a7;
  56   private static final int LCount = 19;
  57   private static final int VCount = 21;
  58   private static final int TCount = 28;
  59
  60   // Information about surrogates.
  61   private static final int highSurrogateStart = 0xD800;
  62   private static final int highSurrogateEnd = 0xDBFF;
  63   private static final int lowSurrogateStart = 0xDC00;
  64   private static final int lowSurrogateEnd = 0xDFFF;
  65
  66   public Object clone ()
  67   {
  68     return new CharacterBreakIterator (this);
  69   }
  70
  71   public CharacterBreakIterator ()
  72   {
  73     iter = null;                // FIXME?
  74   }
  75
  76   private CharacterBreakIterator (CharacterBreakIterator other)
  77   {
  78     iter = (CharacterIterator) other.iter.clone();
  79   }
  80
  81   // Some methods to tell us different properties of characters.
  82   private final boolean isL (char c)
  83   {
  84     return c >= LBase && c <= LBase + LCount;
  85   }
  86   private final boolean isV (char c)
  87   {
  88     return c >= VBase && c <= VBase + VCount;
  89   }
  90   private final boolean isT (char c)
  91   {
  92     return c >= TBase && c <= TBase + TCount;
  93   }
  94   private final boolean isLVT (char c)
  95   {
  96     return isL (c) || isV (c) || isT (c);
  97   }
  98   private final boolean isHighSurrogate (char c)
  99   {
 100     return c >= highSurrogateStart && c <= highSurrogateEnd;
 101   }
 102   private final boolean isLowSurrogate (char c)
 103   {
 104     return c >= lowSurrogateStart && c <= lowSurrogateEnd;
 105   }
 106
 107   public int next ()
 108   {
 109     int end = iter.getEndIndex();
 110     if (iter.getIndex() == end)
 111       return DONE;
 112
 113     char c;
 114     for (char prev = CharacterIterator.DONE; iter.getIndex() < end; prev = c)
 115       {
 116         c = iter.next();
 117         if (c == CharacterIterator.DONE)
 118           break;
 119         int type = Character.getType(c);
 120
 121         // Break after paragraph separators.
 122         if (type == Character.PARAGRAPH_SEPARATOR)
 123           break;
 124
 125         // Now we need some lookahead.
 126         char ahead = iter.next();
 127         iter.previous();
 128         if (ahead == CharacterIterator.DONE)
 129           break;
 130         int aheadType = Character.getType(ahead);
 131
 132         if (aheadType != Character.NON_SPACING_MARK
 133             && ! isLowSurrogate (ahead)
 134             && ! isLVT (ahead))
 135           break;
 136         if (! isLVT (c) && isLVT (ahead))
 137           break;
 138         if (isL (c) && ! isLVT (ahead)
 139             && aheadType != Character.NON_SPACING_MARK)
 140           break;
 141         if (isV (c) && ! isV (ahead) && !isT (ahead)
 142             && aheadType != Character.NON_SPACING_MARK)
 143           break;
 144         if (isT (c) && ! isT (ahead)
 145             && aheadType != Character.NON_SPACING_MARK)
 146           break;
 147
 148         if (! isHighSurrogate (c) && isLowSurrogate (ahead))
 149           break;
 150         if (isHighSurrogate (c) && ! isLowSurrogate (ahead))
 151           break;
 152         if (! isHighSurrogate (prev) && isLowSurrogate (c))
 153           break;
 154       }
 155
 156     return iter.getIndex();
 157   }
 158
 159   public int previous ()
 160   {
 161     if (iter.getIndex() == iter.getBeginIndex())
 162       return DONE;
 163
 164     int start = iter.getBeginIndex();
 165     while (iter.getIndex() >= iter.getBeginIndex())
 166       {
 167         char c = iter.previous();
 168         if (c == CharacterIterator.DONE)
 169           break;
 170         int type = Character.getType(c);
 171
 172         if (type != Character.NON_SPACING_MARK
 173             && ! isLowSurrogate (c)
 174             && ! isLVT (c))
 175           break;
 176
 177         // Now we need some lookahead.
 178         char ahead = iter.previous();
 179         if (ahead == CharacterIterator.DONE)
 180           {
 181             iter.next();
 182             break;
 183           }
 184         char ahead2 = iter.previous();
 185         iter.next();
 186         iter.next();
 187         if (ahead2 == CharacterIterator.DONE)
 188           break;
 189         int aheadType = Character.getType(ahead);
 190
 191         if (aheadType == Character.PARAGRAPH_SEPARATOR)
 192           break;
 193
 194         if (isLVT (c) && ! isLVT (ahead))
 195           break;
 196         if (! isLVT (c) && type != Character.NON_SPACING_MARK
 197             && isL (ahead))
 198           break;
 199         if (! isV (c) && ! isT (c) && type != Character.NON_SPACING_MARK
 200             && isV (ahead))
 201           break;
 202         if (! isT (c) && type != Character.NON_SPACING_MARK
 203             && isT (ahead))
 204           break;
 205
 206         if (isLowSurrogate (c) && ! isHighSurrogate (ahead))
 207           break;
 208         if (! isLowSurrogate (c) && isHighSurrogate (ahead))
 209           break;
 210         if (isLowSurrogate (ahead) && ! isHighSurrogate (ahead2))
 211           break;
 212       }
 213
 214     return iter.getIndex();
 215   }
 216 }