blob: 553cdefdfc1749e6bdb8072bcf7fed30a2788815 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
// Default word BreakIterator.
/* Copyright (C) 1999 Free Software Foundation
This file is part of libgcj.
This software is copyrighted work licensed under the terms of the
Libgcj License. Please consult the file "LIBGCJ_LICENSE" for
details. */
package gnu.gcj.text;
import java.text.BreakIterator;
import java.text.CharacterIterator;
/**
* @author Tom Tromey <tromey@cygnus.com>
* @date March 22, 1999
* Written using The Unicode Standard, Version 2.0.
*/
public class WordBreakIterator extends BaseBreakIterator
{
public Object clone ()
{
return new WordBreakIterator (this);
}
public WordBreakIterator ()
{
iter = null;
}
private WordBreakIterator (WordBreakIterator other)
{
iter = (CharacterIterator) other.iter.clone();
}
// Some methods to tell us different properties of characters.
private final boolean isHira (char c)
{
return c >= 0x3040 && c <= 0x309f;
}
private final boolean isKata (char c)
{
return c >= 0x30a0 && c <= 0x30ff;
}
private final boolean isHan (char c)
{
return c >= 0x4e00 && c <= 0x9fff;
}
public int next ()
{
int end = iter.getEndIndex();
if (iter.getIndex() == end)
return DONE;
while (iter.getIndex() < end)
{
char c = iter.current();
if (c == CharacterIterator.DONE)
break;
int type = Character.getType(c);
char n = iter.next();
if (n == CharacterIterator.DONE)
break;
// Break after paragraph separators.
if (type == Character.PARAGRAPH_SEPARATOR
|| type == Character.LINE_SEPARATOR)
break;
// Break between letters and non-letters.
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
boolean is_letter = Character.isLetter(c);
if (c != '\'' && ! is_letter && type != Character.NON_SPACING_MARK
&& Character.isLetter(n))
break;
// Always break after certain symbols, such as punctuation.
// This heuristic is derived from hints in the JCL book and is
// not part of Unicode. It seems to be right, however.
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
if (c != '\''
&& (type == Character.DASH_PUNCTUATION
|| type == Character.START_PUNCTUATION
|| type == Character.END_PUNCTUATION
|| type == Character.CONNECTOR_PUNCTUATION
|| type == Character.OTHER_PUNCTUATION
|| type == Character.MATH_SYMBOL
|| type == Character.CURRENCY_SYMBOL
|| type == Character.MODIFIER_SYMBOL
|| type == Character.OTHER_SYMBOL
|| type == Character.FORMAT
|| type == Character.CONTROL))
break;
boolean is_hira = isHira (c);
boolean is_kata = isKata (c);
boolean is_han = isHan (c);
// Special case Japanese.
if (! is_hira && ! is_kata && ! is_han
&& type != Character.NON_SPACING_MARK
&& (isHira (n) || isKata (n) || isHan (n)))
break;
if (is_hira || is_kata || is_han || is_letter)
{
// Now we need to do some lookahead. We might need to do
// quite a bit of lookahead, so we save our position and
// restore it later.
int save = iter.getIndex();
// Skip string of non spacing marks.
while (n != CharacterIterator.DONE
&& Character.getType(n) == Character.NON_SPACING_MARK)
n = iter.next();
if (n == CharacterIterator.DONE)
break;
if ((is_hira && ! isHira (n))
|| (is_kata && ! isHira (n) && ! isKata (n))
|| (is_han && ! isHira (n) && ! isHan (n))
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
|| (is_letter && ! Character.isLetter(n) && n != '\''))
break;
iter.setIndex(save);
}
}
return iter.getIndex();
}
public int previous ()
{
int start = iter.getBeginIndex();
if (iter.getIndex() == start)
return DONE;
while (iter.getIndex() >= start)
{
char c = iter.previous();
if (c == CharacterIterator.DONE)
break;
boolean is_hira = isHira (c);
boolean is_kata = isKata (c);
boolean is_han = isHan (c);
boolean is_letter = Character.isLetter(c);
char n = iter.previous();
if (n == CharacterIterator.DONE)
break;
iter.next();
int type = Character.getType(n);
// Break after paragraph separators.
if (type == Character.PARAGRAPH_SEPARATOR
|| type == Character.LINE_SEPARATOR)
break;
// Break between letters and non-letters.
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
if (n != '\'' && ! Character.isLetter(n)
&& type != Character.NON_SPACING_MARK
&& is_letter)
break;
// Always break after certain symbols, such as punctuation.
// This heuristic is derived from hints in the JCL book and is
// not part of Unicode. It seems to be right, however.
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
if (n != '\''
&& (type == Character.DASH_PUNCTUATION
|| type == Character.START_PUNCTUATION
|| type == Character.END_PUNCTUATION
|| type == Character.CONNECTOR_PUNCTUATION
|| type == Character.OTHER_PUNCTUATION
|| type == Character.MATH_SYMBOL
|| type == Character.CURRENCY_SYMBOL
|| type == Character.MODIFIER_SYMBOL
|| type == Character.OTHER_SYMBOL
|| type == Character.FORMAT
|| type == Character.CONTROL))
break;
// Special case Japanese.
if ((is_hira || is_kata || is_han)
&& ! isHira (n) && ! isKata (n) && ! isHan (n)
&& type != Character.NON_SPACING_MARK)
break;
// We might have to skip over non spacing marks to see what's
// on the other side.
if (! is_hira || (! is_letter && c != '\''))
{
int save = iter.getIndex();
while (n != CharacterIterator.DONE
&& Character.getType(n) == Character.NON_SPACING_MARK)
n = iter.previous();
iter.setIndex(save);
// This is a strange case: a bunch of non-spacing marks at
// the beginning. We treat the current location as a word
// break.
if (n == CharacterIterator.DONE)
break;
if ((isHira (n) && ! is_hira)
|| (isKata (n) && ! is_hira && ! is_kata)
|| (isHan (n) && ! is_hira && ! is_han)
// FIXME: we treat apostrophe as part of a word. This
// is an English-ism.
|| (! is_letter && c != '\'' && Character.isLetter(n)))
break;
}
}
return iter.getIndex();
}
}
|
