1 |
769 |
jeremybenn |
/* WordBreakIterator.java - Default word BreakIterator.
|
2 |
|
|
Copyright (C) 1999, 2001, 2004 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., 51 Franklin Street, Fifth Floor, Boston, MA
|
19 |
|
|
02110-1301 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.CharacterIterator;
|
42 |
|
|
|
43 |
|
|
/**
|
44 |
|
|
* @author Tom Tromey <tromey@cygnus.com>
|
45 |
|
|
* @date March 22, 1999
|
46 |
|
|
* Written using The Unicode Standard, Version 2.0.
|
47 |
|
|
*/
|
48 |
|
|
|
49 |
|
|
public class WordBreakIterator extends BaseBreakIterator
|
50 |
|
|
{
|
51 |
|
|
public Object clone ()
|
52 |
|
|
{
|
53 |
|
|
return new WordBreakIterator (this);
|
54 |
|
|
}
|
55 |
|
|
|
56 |
|
|
public WordBreakIterator ()
|
57 |
|
|
{
|
58 |
|
|
}
|
59 |
|
|
|
60 |
|
|
private WordBreakIterator (WordBreakIterator other)
|
61 |
|
|
{
|
62 |
|
|
iter = (CharacterIterator) other.iter.clone();
|
63 |
|
|
}
|
64 |
|
|
|
65 |
|
|
// Some methods to tell us different properties of characters.
|
66 |
|
|
private final boolean isHira (char c)
|
67 |
|
|
{
|
68 |
|
|
return c >= 0x3040 && c <= 0x309f;
|
69 |
|
|
}
|
70 |
|
|
private final boolean isKata (char c)
|
71 |
|
|
{
|
72 |
|
|
return c >= 0x30a0 && c <= 0x30ff;
|
73 |
|
|
}
|
74 |
|
|
private final boolean isHan (char c)
|
75 |
|
|
{
|
76 |
|
|
return c >= 0x4e00 && c <= 0x9fff;
|
77 |
|
|
}
|
78 |
|
|
|
79 |
|
|
public int next ()
|
80 |
|
|
{
|
81 |
|
|
int end = iter.getEndIndex();
|
82 |
|
|
if (iter.getIndex() == end)
|
83 |
|
|
return DONE;
|
84 |
|
|
|
85 |
|
|
while (iter.getIndex() < end)
|
86 |
|
|
{
|
87 |
|
|
char c = iter.current();
|
88 |
|
|
if (c == CharacterIterator.DONE)
|
89 |
|
|
break;
|
90 |
|
|
int type = Character.getType(c);
|
91 |
|
|
|
92 |
|
|
char n = iter.next();
|
93 |
|
|
if (n == CharacterIterator.DONE)
|
94 |
|
|
break;
|
95 |
|
|
|
96 |
|
|
// Break after paragraph separators.
|
97 |
|
|
if (type == Character.PARAGRAPH_SEPARATOR
|
98 |
|
|
|| type == Character.LINE_SEPARATOR)
|
99 |
|
|
break;
|
100 |
|
|
|
101 |
|
|
// Break between letters and non-letters.
|
102 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
103 |
|
|
// is an English-ism.
|
104 |
|
|
boolean is_letter = Character.isLetter(c);
|
105 |
|
|
if (c != '\'' && ! is_letter && type != Character.NON_SPACING_MARK
|
106 |
|
|
&& Character.isLetter(n))
|
107 |
|
|
break;
|
108 |
|
|
|
109 |
|
|
// Always break after certain symbols, such as punctuation.
|
110 |
|
|
// This heuristic is derived from hints in the JCL book and is
|
111 |
|
|
// not part of Unicode. It seems to be right, however.
|
112 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
113 |
|
|
// is an English-ism.
|
114 |
|
|
if (c != '\''
|
115 |
|
|
&& (type == Character.DASH_PUNCTUATION
|
116 |
|
|
|| type == Character.START_PUNCTUATION
|
117 |
|
|
|| type == Character.END_PUNCTUATION
|
118 |
|
|
|| type == Character.CONNECTOR_PUNCTUATION
|
119 |
|
|
|| type == Character.OTHER_PUNCTUATION
|
120 |
|
|
|| type == Character.MATH_SYMBOL
|
121 |
|
|
|| type == Character.CURRENCY_SYMBOL
|
122 |
|
|
|| type == Character.MODIFIER_SYMBOL
|
123 |
|
|
|| type == Character.OTHER_SYMBOL
|
124 |
|
|
|| type == Character.FORMAT
|
125 |
|
|
|| type == Character.CONTROL))
|
126 |
|
|
break;
|
127 |
|
|
|
128 |
|
|
boolean is_hira = isHira (c);
|
129 |
|
|
boolean is_kata = isKata (c);
|
130 |
|
|
boolean is_han = isHan (c);
|
131 |
|
|
|
132 |
|
|
// Special case Japanese.
|
133 |
|
|
if (! is_hira && ! is_kata && ! is_han
|
134 |
|
|
&& type != Character.NON_SPACING_MARK
|
135 |
|
|
&& (isHira (n) || isKata (n) || isHan (n)))
|
136 |
|
|
break;
|
137 |
|
|
|
138 |
|
|
if (is_hira || is_kata || is_han || is_letter)
|
139 |
|
|
{
|
140 |
|
|
// Now we need to do some lookahead. We might need to do
|
141 |
|
|
// quite a bit of lookahead, so we save our position and
|
142 |
|
|
// restore it later.
|
143 |
|
|
int save = iter.getIndex();
|
144 |
|
|
// Skip string of non spacing marks.
|
145 |
|
|
while (n != CharacterIterator.DONE
|
146 |
|
|
&& Character.getType(n) == Character.NON_SPACING_MARK)
|
147 |
|
|
n = iter.next();
|
148 |
|
|
if (n == CharacterIterator.DONE)
|
149 |
|
|
break;
|
150 |
|
|
if ((is_hira && ! isHira (n))
|
151 |
|
|
|| (is_kata && ! isHira (n) && ! isKata (n))
|
152 |
|
|
|| (is_han && ! isHira (n) && ! isHan (n))
|
153 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
154 |
|
|
// is an English-ism.
|
155 |
|
|
|| (is_letter && ! Character.isLetter(n) && n != '\''))
|
156 |
|
|
break;
|
157 |
|
|
iter.setIndex(save);
|
158 |
|
|
}
|
159 |
|
|
}
|
160 |
|
|
|
161 |
|
|
return iter.getIndex();
|
162 |
|
|
}
|
163 |
|
|
|
164 |
|
|
public int previous ()
|
165 |
|
|
{
|
166 |
|
|
int start = iter.getBeginIndex();
|
167 |
|
|
if (iter.getIndex() == start)
|
168 |
|
|
return DONE;
|
169 |
|
|
|
170 |
|
|
while (iter.getIndex() >= start)
|
171 |
|
|
{
|
172 |
|
|
char c = iter.previous();
|
173 |
|
|
if (c == CharacterIterator.DONE)
|
174 |
|
|
break;
|
175 |
|
|
|
176 |
|
|
boolean is_hira = isHira (c);
|
177 |
|
|
boolean is_kata = isKata (c);
|
178 |
|
|
boolean is_han = isHan (c);
|
179 |
|
|
boolean is_letter = Character.isLetter(c);
|
180 |
|
|
|
181 |
|
|
char n = iter.previous();
|
182 |
|
|
if (n == CharacterIterator.DONE)
|
183 |
|
|
break;
|
184 |
|
|
iter.next();
|
185 |
|
|
int type = Character.getType(n);
|
186 |
|
|
// Break after paragraph separators.
|
187 |
|
|
if (type == Character.PARAGRAPH_SEPARATOR
|
188 |
|
|
|| type == Character.LINE_SEPARATOR)
|
189 |
|
|
break;
|
190 |
|
|
|
191 |
|
|
// Break between letters and non-letters.
|
192 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
193 |
|
|
// is an English-ism.
|
194 |
|
|
if (n != '\'' && ! Character.isLetter(n)
|
195 |
|
|
&& type != Character.NON_SPACING_MARK
|
196 |
|
|
&& is_letter)
|
197 |
|
|
break;
|
198 |
|
|
|
199 |
|
|
// Always break after certain symbols, such as punctuation.
|
200 |
|
|
// This heuristic is derived from hints in the JCL book and is
|
201 |
|
|
// not part of Unicode. It seems to be right, however.
|
202 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
203 |
|
|
// is an English-ism.
|
204 |
|
|
if (n != '\''
|
205 |
|
|
&& (type == Character.DASH_PUNCTUATION
|
206 |
|
|
|| type == Character.START_PUNCTUATION
|
207 |
|
|
|| type == Character.END_PUNCTUATION
|
208 |
|
|
|| type == Character.CONNECTOR_PUNCTUATION
|
209 |
|
|
|| type == Character.OTHER_PUNCTUATION
|
210 |
|
|
|| type == Character.MATH_SYMBOL
|
211 |
|
|
|| type == Character.CURRENCY_SYMBOL
|
212 |
|
|
|| type == Character.MODIFIER_SYMBOL
|
213 |
|
|
|| type == Character.OTHER_SYMBOL
|
214 |
|
|
|| type == Character.FORMAT
|
215 |
|
|
|| type == Character.CONTROL))
|
216 |
|
|
break;
|
217 |
|
|
|
218 |
|
|
// Special case Japanese.
|
219 |
|
|
if ((is_hira || is_kata || is_han)
|
220 |
|
|
&& ! isHira (n) && ! isKata (n) && ! isHan (n)
|
221 |
|
|
&& type != Character.NON_SPACING_MARK)
|
222 |
|
|
break;
|
223 |
|
|
|
224 |
|
|
// We might have to skip over non spacing marks to see what's
|
225 |
|
|
// on the other side.
|
226 |
|
|
if (! is_hira || (! is_letter && c != '\''))
|
227 |
|
|
{
|
228 |
|
|
int save = iter.getIndex();
|
229 |
|
|
while (n != CharacterIterator.DONE
|
230 |
|
|
&& Character.getType(n) == Character.NON_SPACING_MARK)
|
231 |
|
|
n = iter.previous();
|
232 |
|
|
iter.setIndex(save);
|
233 |
|
|
// This is a strange case: a bunch of non-spacing marks at
|
234 |
|
|
// the beginning. We treat the current location as a word
|
235 |
|
|
// break.
|
236 |
|
|
if (n == CharacterIterator.DONE)
|
237 |
|
|
break;
|
238 |
|
|
if ((isHira (n) && ! is_hira)
|
239 |
|
|
|| (isKata (n) && ! is_hira && ! is_kata)
|
240 |
|
|
|| (isHan (n) && ! is_hira && ! is_han)
|
241 |
|
|
// FIXME: we treat apostrophe as part of a word. This
|
242 |
|
|
// is an English-ism.
|
243 |
|
|
|| (! is_letter && c != '\'' && Character.isLetter(n)))
|
244 |
|
|
break;
|
245 |
|
|
}
|
246 |
|
|
}
|
247 |
|
|
|
248 |
|
|
return iter.getIndex();
|
249 |
|
|
}
|
250 |
|
|
}
|